Merge branches 'work.path' and 'work.mount' into work.f_path

2026-03-22 07:27:12 +08:00 · 2025-09-27 20:18:21 -04:00
parent cdc59a62bc 1b25dea386 a797652486
commit ae8425014d
36 changed files with 663 additions and 712 deletions
--- a/fs/bpf_fs_kfuncs.c
+++ b/fs/bpf_fs_kfuncs.c
@@ -79,7 +79,7 @@ __bpf_kfunc void bpf_put_file(struct file *file)
 * pathname in *buf*, including the NUL termination character. On error, a
 * negative integer is returned.
 */
-__bpf_kfunc int bpf_path_d_path(struct path *path, char *buf, size_t buf__sz)
+__bpf_kfunc int bpf_path_d_path(const struct path *path, char *buf, size_t buf__sz)
 {
 	int len;
 	char *ret;
--- a/fs/configfs/symlink.c
+++ b/fs/configfs/symlink.c
@@ -114,26 +114,21 @@ static int create_link(struct config_item *parent_item,
 }


-static int get_target(const char *symname, struct path *path,
-		      struct config_item **target, struct super_block *sb)
+static int get_target(const char *symname, struct config_item **target,
+		      struct super_block *sb)
 {
+	struct path path __free(path_put) = {};
 	int ret;

-	ret = kern_path(symname, LOOKUP_FOLLOW|LOOKUP_DIRECTORY, path);
-	if (!ret) {
-		if (path->dentry->d_sb == sb) {
-			*target = configfs_get_config_item(path->dentry);
-			if (!*target) {
-				ret = -ENOENT;
-				path_put(path);
-			}
-		} else {
-			ret = -EPERM;
-			path_put(path);
-		}
-	}
-
-	return ret;
+	ret = kern_path(symname, LOOKUP_FOLLOW|LOOKUP_DIRECTORY, &path);
+	if (ret)
+		return ret;
+	if (path.dentry->d_sb != sb)
+		return -EPERM;
+	*target = configfs_get_config_item(path.dentry);
+	if (!*target)
+		return -ENOENT;
+	return 0;
 }


@@ -141,7 +136,6 @@ int configfs_symlink(struct mnt_idmap *idmap, struct inode *dir,
 		     struct dentry *dentry, const char *symname)
 {
 	int ret;
-	struct path path;
 	struct configfs_dirent *sd;
 	struct config_item *parent_item;
 	struct config_item *target_item = NULL;
@@ -188,7 +182,7 @@ int configfs_symlink(struct mnt_idmap *idmap, struct inode *dir,
 	 *  AV, a thoroughly annoyed bastard.
 	 */
 	inode_unlock(dir);
-	ret = get_target(symname, &path, &target_item, dentry->d_sb);
+	ret = get_target(symname, &target_item, dentry->d_sb);
 	inode_lock(dir);
 	if (ret)
 		goto out_put;
@@ -210,7 +204,6 @@ int configfs_symlink(struct mnt_idmap *idmap, struct inode *dir,
 	}

 	config_item_put(target_item);
-	path_put(&path);

 out_put:
 	config_item_put(parent_item);
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -1390,6 +1390,7 @@ struct check_mount {
 	unsigned int mounted;
 };

+/* locks: mount_locked_reader && dentry->d_lock */
 static enum d_walk_ret path_check_mount(void *data, struct dentry *dentry)
 {
 	struct check_mount *info = data;
@@ -1416,9 +1417,8 @@ int path_has_submounts(const struct path *parent)
 {
 	struct check_mount data = { .mnt = parent->mnt, .mounted = 0 };

-	read_seqlock_excl(&mount_lock);
+	guard(mount_locked_reader)();
 	d_walk(parent->dentry, &data, path_check_mount);
-	read_sequnlock_excl(&mount_lock);

 	return data.mounted;
 }
--- a/fs/ecryptfs/dentry.c
+++ b/fs/ecryptfs/dentry.c
@@ -59,14 +59,6 @@ static int ecryptfs_d_revalidate(struct inode *dir, const struct qstr *name,
 	return rc;
 }

-struct kmem_cache *ecryptfs_dentry_info_cache;
-
-static void ecryptfs_dentry_free_rcu(struct rcu_head *head)
-{
-	kmem_cache_free(ecryptfs_dentry_info_cache,
-		container_of(head, struct ecryptfs_dentry_info, rcu));
-}
-
 /**
 * ecryptfs_d_release
 * @dentry: The ecryptfs dentry
@@ -75,11 +67,7 @@ static void ecryptfs_dentry_free_rcu(struct rcu_head *head)
 */
 static void ecryptfs_d_release(struct dentry *dentry)
 {
-	struct ecryptfs_dentry_info *p = dentry->d_fsdata;
-	if (p) {
-		path_put(&p->lower_path);
-		call_rcu(&p->rcu, ecryptfs_dentry_free_rcu);
-	}
+	dput(dentry->d_fsdata);
 }

 const struct dentry_operations ecryptfs_dops = {
--- a/fs/ecryptfs/ecryptfs_kernel.h
+++ b/fs/ecryptfs/ecryptfs_kernel.h
@@ -258,13 +258,6 @@ struct ecryptfs_inode_info {
 	struct ecryptfs_crypt_stat crypt_stat;
 };

-/* dentry private data. Each dentry must keep track of a lower
- * vfsmount too. */
-struct ecryptfs_dentry_info {
-	struct path lower_path;
-	struct rcu_head rcu;
-};
-
 /**
 * ecryptfs_global_auth_tok - A key used to encrypt all new files under the mountpoint
 * @flags: Status flags
@@ -348,6 +341,7 @@ struct ecryptfs_mount_crypt_stat {
 /* superblock private data. */
 struct ecryptfs_sb_info {
 	struct super_block *wsi_sb;
+	struct vfsmount *lower_mnt;
 	struct ecryptfs_mount_crypt_stat mount_crypt_stat;
 };

@@ -494,22 +488,25 @@ ecryptfs_set_superblock_lower(struct super_block *sb,
 }

 static inline void
-ecryptfs_set_dentry_private(struct dentry *dentry,
-			    struct ecryptfs_dentry_info *dentry_info)
+ecryptfs_set_dentry_lower(struct dentry *dentry,
+			  struct dentry *lower_dentry)
 {
-	dentry->d_fsdata = dentry_info;
+	dentry->d_fsdata = lower_dentry;
 }

 static inline struct dentry *
 ecryptfs_dentry_to_lower(struct dentry *dentry)
 {
-	return ((struct ecryptfs_dentry_info *)dentry->d_fsdata)->lower_path.dentry;
+	return dentry->d_fsdata;
 }

-static inline const struct path *
-ecryptfs_dentry_to_lower_path(struct dentry *dentry)
+static inline struct path
+ecryptfs_lower_path(struct dentry *dentry)
 {
-	return &((struct ecryptfs_dentry_info *)dentry->d_fsdata)->lower_path;
+	return (struct path){
+		.mnt = ecryptfs_superblock_to_private(dentry->d_sb)->lower_mnt,
+		.dentry = ecryptfs_dentry_to_lower(dentry)
+	};
 }

 #define ecryptfs_printk(type, fmt, arg...) \
@@ -532,7 +529,6 @@ extern unsigned int ecryptfs_number_of_users;

 extern struct kmem_cache *ecryptfs_auth_tok_list_item_cache;
 extern struct kmem_cache *ecryptfs_file_info_cache;
-extern struct kmem_cache *ecryptfs_dentry_info_cache;
 extern struct kmem_cache *ecryptfs_inode_info_cache;
 extern struct kmem_cache *ecryptfs_sb_info_cache;
 extern struct kmem_cache *ecryptfs_header_cache;
@@ -557,7 +553,6 @@ int ecryptfs_encrypt_and_encode_filename(
 	size_t *encoded_name_size,
 	struct ecryptfs_mount_crypt_stat *mount_crypt_stat,
 	const char *name, size_t name_size);
-struct dentry *ecryptfs_lower_dentry(struct dentry *this_dentry);
 void ecryptfs_dump_hex(char *data, int bytes);
 int virt_to_scatterlist(const void *addr, int size, struct scatterlist *sg,
 			int sg_size);
--- a/fs/ecryptfs/file.c
+++ b/fs/ecryptfs/file.c
@@ -33,13 +33,12 @@ static ssize_t ecryptfs_read_update_atime(struct kiocb *iocb,
 				struct iov_iter *to)
 {
 	ssize_t rc;
-	const struct path *path;
 	struct file *file = iocb->ki_filp;

 	rc = generic_file_read_iter(iocb, to);
 	if (rc >= 0) {
-		path = ecryptfs_dentry_to_lower_path(file->f_path.dentry);
-		touch_atime(path);
+		struct path path = ecryptfs_lower_path(file->f_path.dentry);
+		touch_atime(&path);
 	}
 	return rc;
 }
@@ -59,12 +58,11 @@ static ssize_t ecryptfs_splice_read_update_atime(struct file *in, loff_t *ppos,
 						 size_t len, unsigned int flags)
 {
 	ssize_t rc;
-	const struct path *path;

 	rc = filemap_splice_read(in, ppos, pipe, len, flags);
 	if (rc >= 0) {
-		path = ecryptfs_dentry_to_lower_path(in->f_path.dentry);
-		touch_atime(path);
+		struct path path = ecryptfs_lower_path(in->f_path.dentry);
+		touch_atime(&path);
 	}
 	return rc;
 }
@@ -283,6 +281,7 @@ static int ecryptfs_dir_open(struct inode *inode, struct file *file)
 	 * ecryptfs_lookup() */
 	struct ecryptfs_file_info *file_info;
 	struct file *lower_file;
+	struct path path;

 	/* Released in ecryptfs_release or end of function if failure */
 	file_info = kmem_cache_zalloc(ecryptfs_file_info_cache, GFP_KERNEL);
@@ -292,8 +291,8 @@ static int ecryptfs_dir_open(struct inode *inode, struct file *file)
 				"Error attempting to allocate memory\n");
 		return -ENOMEM;
 	}
-	lower_file = dentry_open(ecryptfs_dentry_to_lower_path(ecryptfs_dentry),
-				 file->f_flags, current_cred());
+	path = ecryptfs_lower_path(ecryptfs_dentry);
+	lower_file = dentry_open(&path, file->f_flags, current_cred());
 	if (IS_ERR(lower_file)) {
 		printk(KERN_ERR "%s: Error attempting to initialize "
 			"the lower file for the dentry with name "
--- a/fs/ecryptfs/inode.c
+++ b/fs/ecryptfs/inode.c
@@ -327,24 +327,15 @@ static int ecryptfs_i_size_read(struct dentry *dentry, struct inode *inode)
 static struct dentry *ecryptfs_lookup_interpose(struct dentry *dentry,
 				     struct dentry *lower_dentry)
 {
-	const struct path *path = ecryptfs_dentry_to_lower_path(dentry->d_parent);
+	struct dentry *lower_parent = ecryptfs_dentry_to_lower(dentry->d_parent);
 	struct inode *inode, *lower_inode;
-	struct ecryptfs_dentry_info *dentry_info;
 	int rc = 0;

-	dentry_info = kmem_cache_alloc(ecryptfs_dentry_info_cache, GFP_KERNEL);
-	if (!dentry_info) {
-		dput(lower_dentry);
-		return ERR_PTR(-ENOMEM);
-	}
-
 	fsstack_copy_attr_atime(d_inode(dentry->d_parent),
-				d_inode(path->dentry));
+				d_inode(lower_parent));
 	BUG_ON(!d_count(lower_dentry));

-	ecryptfs_set_dentry_private(dentry, dentry_info);
-	dentry_info->lower_path.mnt = mntget(path->mnt);
-	dentry_info->lower_path.dentry = lower_dentry;
+	ecryptfs_set_dentry_lower(dentry, lower_dentry);

 	/*
 	 * negative dentry can go positive under us here - its parent is not
@@ -1022,10 +1013,10 @@ static int ecryptfs_getattr(struct mnt_idmap *idmap,
 {
 	struct dentry *dentry = path->dentry;
 	struct kstat lower_stat;
+	struct path lower_path = ecryptfs_lower_path(dentry);
 	int rc;

-	rc = vfs_getattr_nosec(ecryptfs_dentry_to_lower_path(dentry),
-			       &lower_stat, request_mask, flags);
+	rc = vfs_getattr_nosec(&lower_path, &lower_stat, request_mask, flags);
 	if (!rc) {
 		fsstack_copy_attr_all(d_inode(dentry),
 				      ecryptfs_inode_to_lower(d_inode(dentry)));
--- a/fs/ecryptfs/main.c
+++ b/fs/ecryptfs/main.c
@@ -106,15 +106,14 @@ static int ecryptfs_init_lower_file(struct dentry *dentry,
 				    struct file **lower_file)
 {
 	const struct cred *cred = current_cred();
-	const struct path *path = ecryptfs_dentry_to_lower_path(dentry);
+	struct path path = ecryptfs_lower_path(dentry);
 	int rc;

-	rc = ecryptfs_privileged_open(lower_file, path->dentry, path->mnt,
-				      cred);
+	rc = ecryptfs_privileged_open(lower_file, path.dentry, path.mnt, cred);
 	if (rc) {
 		printk(KERN_ERR "Error opening lower file "
 		       "for lower_dentry [0x%p] and lower_mnt [0x%p]; "
-		       "rc = [%d]\n", path->dentry, path->mnt, rc);
+		       "rc = [%d]\n", path.dentry, path.mnt, rc);
 		(*lower_file) = NULL;
 	}
 	return rc;
@@ -437,7 +436,6 @@ static int ecryptfs_get_tree(struct fs_context *fc)
 	struct ecryptfs_fs_context *ctx = fc->fs_private;
 	struct ecryptfs_sb_info *sbi = fc->s_fs_info;
 	struct ecryptfs_mount_crypt_stat *mount_crypt_stat;
-	struct ecryptfs_dentry_info *root_info;
 	const char *err = "Getting sb failed";
 	struct inode *inode;
 	struct path path;
@@ -543,14 +541,8 @@ static int ecryptfs_get_tree(struct fs_context *fc)
 		goto out_free;
 	}

-	rc = -ENOMEM;
-	root_info = kmem_cache_zalloc(ecryptfs_dentry_info_cache, GFP_KERNEL);
-	if (!root_info)
-		goto out_free;
-
-	/* ->kill_sb() will take care of root_info */
-	ecryptfs_set_dentry_private(s->s_root, root_info);
-	root_info->lower_path = path;
+	ecryptfs_set_dentry_lower(s->s_root, path.dentry);
+	ecryptfs_superblock_to_private(s)->lower_mnt = path.mnt;

 	s->s_flags |= SB_ACTIVE;
 	fc->root = dget(s->s_root);
@@ -580,6 +572,7 @@ static void ecryptfs_kill_block_super(struct super_block *sb)
 	kill_anon_super(sb);
 	if (!sb_info)
 		return;
+	mntput(sb_info->lower_mnt);
 	ecryptfs_destroy_mount_crypt_stat(&sb_info->mount_crypt_stat);
 	kmem_cache_free(ecryptfs_sb_info_cache, sb_info);
 }
@@ -667,11 +660,6 @@ static struct ecryptfs_cache_info {
 		.name = "ecryptfs_file_cache",
 		.size = sizeof(struct ecryptfs_file_info),
 	},
-	{
-		.cache = &ecryptfs_dentry_info_cache,
-		.name = "ecryptfs_dentry_info_cache",
-		.size = sizeof(struct ecryptfs_dentry_info),
-	},
 	{
 		.cache = &ecryptfs_inode_info_cache,
 		.name = "ecryptfs_inode_cache",
--- a/fs/file_table.c
+++ b/fs/file_table.c
@@ -54,7 +54,7 @@ struct backing_file {

 #define backing_file(f) container_of(f, struct backing_file, file)

-struct path *backing_file_user_path(const struct file *f)
+const struct path *backing_file_user_path(const struct file *f)
 {
 	return &backing_file(f)->user_path;
 }
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -53,7 +53,7 @@ extern int finish_clean_context(struct fs_context *fc);
 * namei.c
 */
 extern int filename_lookup(int dfd, struct filename *name, unsigned flags,
-			   struct path *path, struct path *root);
+			   struct path *path, const struct path *root);
 int do_rmdir(int dfd, struct filename *name);
 int do_unlinkat(int dfd, struct filename *name);
 int may_linkat(struct mnt_idmap *idmap, const struct path *link);
@@ -84,9 +84,9 @@ void mnt_put_write_access_file(struct file *file);
 extern void dissolve_on_fput(struct vfsmount *);
 extern bool may_mount(void);

-int path_mount(const char *dev_name, struct path *path,
+int path_mount(const char *dev_name, const struct path *path,
 		const char *type_page, unsigned long flags, void *data_page);
-int path_umount(struct path *path, int flags);
+int path_umount(const struct path *path, int flags);

 int show_path(struct seq_file *m, struct dentry *root);

--- a/fs/mount.h
+++ b/fs/mount.h
@@ -64,7 +64,10 @@ struct mount {
 #endif
 	struct list_head mnt_mounts;	/* list of children, anchored here */
 	struct list_head mnt_child;	/* and going through their mnt_child */
-	struct list_head mnt_instance;	/* mount instance on sb->s_mounts */
+	struct mount *mnt_next_for_sb;	/* the next two fields are hlist_node, */
+	struct mount * __aligned(1) *mnt_pprev_for_sb;
+					/* except that LSB of pprev is stolen */
+#define WRITE_HOLD 1			/* ... for use by mnt_hold_writers() */
 	const char *mnt_devname;	/* Name of device e.g. /dev/dsk/hda1 */
 	struct list_head mnt_list;
 	struct list_head mnt_expire;	/* link in fs-specific expiry list */
@@ -154,6 +157,11 @@ static inline void get_mnt_ns(struct mnt_namespace *ns)

 extern seqlock_t mount_lock;

+DEFINE_LOCK_GUARD_0(mount_writer, write_seqlock(&mount_lock),
+		    write_sequnlock(&mount_lock))
+DEFINE_LOCK_GUARD_0(mount_locked_reader, read_seqlock_excl(&mount_lock),
+		    read_sequnlock_excl(&mount_lock))
+
 struct proc_mounts {
 	struct mnt_namespace *ns;
 	struct path root;
@@ -230,4 +238,33 @@ static inline void mnt_notify_add(struct mount *m)
 }
 #endif

+static inline struct mount *topmost_overmount(struct mount *m)
+{
+	while (m->overmount)
+		m = m->overmount;
+	return m;
+}
+
+static inline bool __test_write_hold(struct mount * __aligned(1) *val)
+{
+	return (unsigned long)val & WRITE_HOLD;
+}
+
+static inline bool test_write_hold(const struct mount *m)
+{
+	return __test_write_hold(m->mnt_pprev_for_sb);
+}
+
+static inline void set_write_hold(struct mount *m)
+{
+	m->mnt_pprev_for_sb = (void *)((unsigned long)m->mnt_pprev_for_sb
+				       | WRITE_HOLD);
+}
+
+static inline void clear_write_hold(struct mount *m)
+{
+	m->mnt_pprev_for_sb = (void *)((unsigned long)m->mnt_pprev_for_sb
+				       & ~WRITE_HOLD);
+}
+
 struct mnt_namespace *mnt_ns_from_dentry(struct dentry *dentry);
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -2673,7 +2673,7 @@ static int path_lookupat(struct nameidata *nd, unsigned flags, struct path *path
 }

 int filename_lookup(int dfd, struct filename *name, unsigned flags,
-		    struct path *path, struct path *root)
+		    struct path *path, const struct path *root)
 {
 	int retval;
 	struct nameidata nd;
@@ -4170,7 +4170,7 @@ struct dentry *kern_path_create(int dfd, const char *pathname,
 }
 EXPORT_SYMBOL(kern_path_create);

-void done_path_create(struct path *path, struct dentry *dentry)
+void done_path_create(const struct path *path, struct dentry *dentry)
 {
 	if (!IS_ERR(dentry))
 		dput(dentry);
--- a/fs/namespace.c
+++ b/fs/namespace.c
--- a/fs/nfs/localio.c
+++ b/fs/nfs/localio.c
@@ -529,7 +529,7 @@ nfs_set_local_verifier(struct inode *inode,
 }

 /* Factored out from fs/nfsd/vfs.h:fh_getattr() */
-static int __vfs_getattr(struct path *p, struct kstat *stat, int version)
+static int __vfs_getattr(const struct path *p, struct kstat *stat, int version)
 {
 	u32 request_mask = STATX_BASIC_STATS;

--- a/fs/nfsd/export.c
+++ b/fs/nfsd/export.c
@@ -402,7 +402,7 @@ static struct svc_export *svc_export_update(struct svc_export *new,
 					    struct svc_export *old);
 static struct svc_export *svc_export_lookup(struct svc_export *);

-static int check_export(struct path *path, int *flags, unsigned char *uuid)
+static int check_export(const struct path *path, int *flags, unsigned char *uuid)
 {
 	struct inode *inode = d_inode(path->dentry);

@@ -1181,7 +1181,7 @@ denied:
 * use exp_get_by_name() or exp_find().
 */
 struct svc_export *
-rqst_exp_get_by_name(struct svc_rqst *rqstp, struct path *path)
+rqst_exp_get_by_name(struct svc_rqst *rqstp, const struct path *path)
 {
 	struct svc_export *gssexp, *exp = ERR_PTR(-ENOENT);
 	struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id);
--- a/fs/nfsd/export.h
+++ b/fs/nfsd/export.h
@@ -111,7 +111,7 @@ int			nfsd_export_init(struct net *);
 void			nfsd_export_shutdown(struct net *);
 void			nfsd_export_flush(struct net *);
 struct svc_export *	rqst_exp_get_by_name(struct svc_rqst *,
-					     struct path *);
+					     const struct path *);
 struct svc_export *	rqst_exp_parent(struct svc_rqst *,
 					struct path *);
 struct svc_export *	rqst_find_fsidzero_export(struct svc_rqst *);
--- a/fs/overlayfs/copy_up.c
+++ b/fs/overlayfs/copy_up.c
@@ -242,7 +242,7 @@ static int ovl_verify_area(loff_t pos, loff_t pos2, loff_t len, loff_t totlen)
 	return 0;
 }

-static int ovl_sync_file(struct path *path)
+static int ovl_sync_file(const struct path *path)
 {
 	struct file *new_file;
 	int err;
--- a/fs/overlayfs/file.c
+++ b/fs/overlayfs/file.c
@@ -120,7 +120,7 @@ static bool ovl_is_real_file(const struct file *realfile,
 }

 static struct file *ovl_real_file_path(const struct file *file,
-				       struct path *realpath)
+				       const struct path *realpath)
 {
 	struct ovl_file *of = file->private_data;
 	struct file *realfile = of->realfile;
--- a/fs/overlayfs/overlayfs.h
+++ b/fs/overlayfs/overlayfs.h
@@ -563,11 +563,11 @@ int ovl_set_metacopy_xattr(struct ovl_fs *ofs, struct dentry *d,
 			   struct ovl_metacopy *metacopy);
 bool ovl_is_metacopy_dentry(struct dentry *dentry);
 char *ovl_get_redirect_xattr(struct ovl_fs *ofs, const struct path *path, int padding);
-int ovl_ensure_verity_loaded(struct path *path);
+int ovl_ensure_verity_loaded(const struct path *path);
 int ovl_validate_verity(struct ovl_fs *ofs,
-			struct path *metapath,
-			struct path *datapath);
-int ovl_get_verity_digest(struct ovl_fs *ofs, struct path *src,
+			const struct path *metapath,
+			const struct path *datapath);
+int ovl_get_verity_digest(struct ovl_fs *ofs, const struct path *src,
 			  struct ovl_metacopy *metacopy);
 int ovl_sync_status(struct ovl_fs *ofs);

--- a/fs/overlayfs/super.c
+++ b/fs/overlayfs/super.c
@@ -394,7 +394,7 @@ static int ovl_check_namelen(const struct path *path, struct ovl_fs *ofs,
 	return err;
 }

-static int ovl_lower_dir(const char *name, struct path *path,
+static int ovl_lower_dir(const char *name, const struct path *path,
 			 struct ovl_fs *ofs, int *stack_depth)
 {
 	int fh_type;
--- a/fs/overlayfs/util.c
+++ b/fs/overlayfs/util.c
@@ -1381,7 +1381,7 @@ err_free:
 }

 /* Call with mounter creds as it may open the file */
-int ovl_ensure_verity_loaded(struct path *datapath)
+int ovl_ensure_verity_loaded(const struct path *datapath)
 {
 	struct inode *inode = d_inode(datapath->dentry);
 	struct file *filp;
@@ -1401,8 +1401,8 @@ int ovl_ensure_verity_loaded(struct path *datapath)
 }

 int ovl_validate_verity(struct ovl_fs *ofs,
-			struct path *metapath,
-			struct path *datapath)
+			const struct path *metapath,
+			const struct path *datapath)
 {
 	struct ovl_metacopy metacopy_data;
 	u8 actual_digest[FS_VERITY_MAX_DIGEST_SIZE];
@@ -1455,7 +1455,7 @@ int ovl_validate_verity(struct ovl_fs *ofs,
 	return 0;
 }

-int ovl_get_verity_digest(struct ovl_fs *ofs, struct path *src,
+int ovl_get_verity_digest(struct ovl_fs *ofs, const struct path *src,
 			  struct ovl_metacopy *metacopy)
 {
 	int err, digest_size;
--- a/fs/pidfs.c
+++ b/fs/pidfs.c
@@ -847,7 +847,7 @@ static int pidfs_export_permission(struct handle_to_path_ctx *ctx,
 	return 0;
 }

-static struct file *pidfs_export_open(struct path *path, unsigned int oflags)
+static struct file *pidfs_export_open(const struct path *path, unsigned int oflags)
 {
 	/*
 	 * Clear O_LARGEFILE as open_by_handle_at() forces it and raise
--- a/fs/pnode.c
+++ b/fs/pnode.c
@@ -29,6 +29,7 @@ static inline struct mount *next_slave(struct mount *p)
 	return hlist_entry(p->mnt_slave.next, struct mount, mnt_slave);
 }

+/* locks: namespace_shared && is_mounted(mnt) */
 static struct mount *get_peer_under_root(struct mount *mnt,
 					 struct mnt_namespace *ns,
 					 const struct path *root)
@@ -50,7 +51,7 @@ static struct mount *get_peer_under_root(struct mount *mnt,
 * Get ID of closest dominating peer group having a representative
 * under the given root.
 *
- * Caller must hold namespace_sem
+ * locks: namespace_shared
 */
 int get_dominating_id(struct mount *mnt, const struct path *root)
 {
@@ -70,19 +71,6 @@ static inline bool will_be_unmounted(struct mount *m)
 	return m->mnt.mnt_flags & MNT_UMOUNT;
 }

-static struct mount *propagation_source(struct mount *mnt)
-{
-	do {
-		struct mount *m;
-		for (m = next_peer(mnt); m != mnt; m = next_peer(m)) {
-			if (!will_be_unmounted(m))
-				return m;
-		}
-		mnt = mnt->mnt_master;
-	} while (mnt && will_be_unmounted(mnt));
-	return mnt;
-}
-
 static void transfer_propagation(struct mount *mnt, struct mount *to)
 {
 	struct hlist_node *p = NULL, *n;
@@ -111,11 +99,10 @@ void change_mnt_propagation(struct mount *mnt, int type)
 		return;
 	}
 	if (IS_MNT_SHARED(mnt)) {
-		if (type == MS_SLAVE || !hlist_empty(&mnt->mnt_slave_list))
-			m = propagation_source(mnt);
 		if (list_empty(&mnt->mnt_share)) {
 			mnt_release_group_id(mnt);
 		} else {
+			m = next_peer(mnt);
 			list_del_init(&mnt->mnt_share);
 			mnt->mnt_group_id = 0;
 		}
@@ -136,6 +123,57 @@ void change_mnt_propagation(struct mount *mnt, int type)
 	}
 }

+static struct mount *trace_transfers(struct mount *m)
+{
+	while (1) {
+		struct mount *next = next_peer(m);
+
+		if (next != m) {
+			list_del_init(&m->mnt_share);
+			m->mnt_group_id = 0;
+			m->mnt_master = next;
+		} else {
+			if (IS_MNT_SHARED(m))
+				mnt_release_group_id(m);
+			next = m->mnt_master;
+		}
+		hlist_del_init(&m->mnt_slave);
+		CLEAR_MNT_SHARED(m);
+		SET_MNT_MARK(m);
+
+		if (!next || !will_be_unmounted(next))
+			return next;
+		if (IS_MNT_MARKED(next))
+			return next->mnt_master;
+		m = next;
+	}
+}
+
+static void set_destinations(struct mount *m, struct mount *master)
+{
+	struct mount *next;
+
+	while ((next = m->mnt_master) != master) {
+		m->mnt_master = master;
+		m = next;
+	}
+}
+
+void bulk_make_private(struct list_head *set)
+{
+	struct mount *m;
+
+	list_for_each_entry(m, set, mnt_list)
+		if (!IS_MNT_MARKED(m))
+			set_destinations(m, trace_transfers(m));
+
+	list_for_each_entry(m, set, mnt_list) {
+		transfer_propagation(m, m->mnt_master);
+		m->mnt_master = NULL;
+		CLEAR_MNT_MARK(m);
+	}
+}
+
 static struct mount *__propagation_next(struct mount *m,
 					 struct mount *origin)
 {
@@ -304,9 +342,8 @@ int propagate_mnt(struct mount *dest_mnt, struct mountpoint *dest_mp,
 				err = PTR_ERR(this);
 				break;
 			}
-			read_seqlock_excl(&mount_lock);
-			mnt_set_mountpoint(n, dest_mp, this);
-			read_sequnlock_excl(&mount_lock);
+			scoped_guard(mount_locked_reader)
+				mnt_set_mountpoint(n, dest_mp, this);
 			if (n->mnt_master)
 				SET_MNT_MARK(n->mnt_master);
 			copy = this;
--- a/fs/pnode.h
+++ b/fs/pnode.h
@@ -42,6 +42,7 @@ static inline bool peers(const struct mount *m1, const struct mount *m2)
 }

 void change_mnt_propagation(struct mount *, int);
+void bulk_make_private(struct list_head *);
 int propagate_mnt(struct mount *, struct mountpoint *, struct mount *,
 		struct hlist_head *);
 void propagate_umount(struct list_head *);
--- a/fs/smb/server/vfs.c
+++ b/fs/smb/server/vfs.c
@@ -72,7 +72,7 @@ static int ksmbd_vfs_path_lookup(struct ksmbd_share_config *share_conf,
 {
 	struct qstr last;
 	struct filename *filename __free(putname) = NULL;
-	struct path *root_share_path = &share_conf->vfs_path;
+	const struct path *root_share_path = &share_conf->vfs_path;
 	int err, type;
 	struct dentry *d;

@@ -1306,7 +1306,7 @@ int ksmbd_vfs_kern_path_locked(struct ksmbd_work *work, char *filepath,
 				     caseless, true);
 }

-void ksmbd_vfs_kern_path_unlock(struct path *path)
+void ksmbd_vfs_kern_path_unlock(const struct path *path)
 {
 	/* While lock is still held, ->d_parent is safe */
 	inode_unlock(d_inode(path->dentry->d_parent));
@@ -1856,7 +1856,7 @@ void ksmbd_vfs_posix_lock_unblock(struct file_lock *flock)
 }

 int ksmbd_vfs_set_init_posix_acl(struct mnt_idmap *idmap,
-				 struct path *path)
+				 const struct path *path)
 {
 	struct posix_acl_state acl_state;
 	struct posix_acl *acls;
@@ -1909,7 +1909,7 @@ int ksmbd_vfs_set_init_posix_acl(struct mnt_idmap *idmap,
 }

 int ksmbd_vfs_inherit_posix_acl(struct mnt_idmap *idmap,
-				struct path *path, struct inode *parent_inode)
+				const struct path *path, struct inode *parent_inode)
 {
 	struct posix_acl *acls;
 	struct posix_acl_entry *pace;
--- a/fs/smb/server/vfs.h
+++ b/fs/smb/server/vfs.h
@@ -123,7 +123,7 @@ int ksmbd_vfs_kern_path(struct ksmbd_work *work, char *name,
 int ksmbd_vfs_kern_path_locked(struct ksmbd_work *work, char *name,
 			       unsigned int flags,
 			       struct path *path, bool caseless);
-void ksmbd_vfs_kern_path_unlock(struct path *path);
+void ksmbd_vfs_kern_path_unlock(const struct path *path);
 struct dentry *ksmbd_vfs_kern_path_create(struct ksmbd_work *work,
 					  const char *name,
 					  unsigned int flags,
@@ -164,8 +164,8 @@ int ksmbd_vfs_get_dos_attrib_xattr(struct mnt_idmap *idmap,
 				   struct dentry *dentry,
 				   struct xattr_dos_attrib *da);
 int ksmbd_vfs_set_init_posix_acl(struct mnt_idmap *idmap,
-				 struct path *path);
+				 const struct path *path);
 int ksmbd_vfs_inherit_posix_acl(struct mnt_idmap *idmap,
-				struct path *path,
+				const struct path *path,
 				struct inode *parent_inode);
 #endif /* __KSMBD_VFS_H__ */
--- a/fs/stat.c
+++ b/fs/stat.c
@@ -293,7 +293,7 @@ static int statx_lookup_flags(int flags)
 	return lookup_flags;
 }

-static int vfs_statx_path(struct path *path, int flags, struct kstat *stat,
+static int vfs_statx_path(const struct path *path, int flags, struct kstat *stat,
 			  u32 request_mask)
 {
 	int error = vfs_getattr(path, stat, request_mask, flags);
--- a/fs/super.c
+++ b/fs/super.c
@@ -323,7 +323,6 @@ static struct super_block *alloc_super(struct file_system_type *type, int flags,
 	if (!s)
 		return NULL;

-	INIT_LIST_HEAD(&s->s_mounts);
 	s->s_user_ns = get_user_ns(user_ns);
 	init_rwsem(&s->s_umount);
 	lockdep_set_class(&s->s_umount, &type->s_umount_key);
@@ -408,7 +407,7 @@ static void __put_super(struct super_block *s)
 		list_del_init(&s->s_list);
 		WARN_ON(s->s_dentry_lru.node);
 		WARN_ON(s->s_inode_lru.node);
-		WARN_ON(!list_empty(&s->s_mounts));
+		WARN_ON(s->s_mounts);
 		call_rcu(&s->rcu, destroy_super_rcu);
 	}
 }
--- a/include/linux/exportfs.h
+++ b/include/linux/exportfs.h
@@ -270,7 +270,7 @@ struct export_operations {
 	int (*commit_blocks)(struct inode *inode, struct iomap *iomaps,
 			     int nr_iomaps, struct iattr *iattr);
 	int (*permission)(struct handle_to_path_ctx *ctx, unsigned int oflags);
-	struct file * (*open)(struct path *path, unsigned int oflags);
+	struct file * (*open)(const struct path *path, unsigned int oflags);
 #define	EXPORT_OP_NOWCC			(0x1) /* don't collect v3 wcc data */
 #define	EXPORT_OP_NOSUBTREECHK		(0x2) /* no subtree checking */
 #define	EXPORT_OP_CLOSE_BEFORE_UNLINK	(0x4) /* close files before unlink */
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1324,6 +1324,8 @@ struct sb_writers {
 	struct percpu_rw_semaphore	rw_sem[SB_FREEZE_LEVELS];
 };

+struct mount;
+
 struct super_block {
 	struct list_head	s_list;		/* Keep this first */
 	dev_t			s_dev;		/* search index; _not_ kdev_t */
@@ -1358,7 +1360,7 @@ struct super_block {
 	__u16 s_encoding_flags;
 #endif
 	struct hlist_bl_head	s_roots;	/* alternate root dentries for NFS */
-	struct list_head	s_mounts;	/* list of mounts; _not_ for fs use */
+	struct mount		*s_mounts;	/* list of mounts; _not_ for fs use */
 	struct block_device	*s_bdev;	/* can go away once we use an accessor for @s_bdev_file */
 	struct file		*s_bdev_file;
 	struct backing_dev_info *s_bdi;
@@ -2879,7 +2881,7 @@ struct file *dentry_open_nonotify(const struct path *path, int flags,
 				  const struct cred *cred);
 struct file *dentry_create(const struct path *path, int flags, umode_t mode,
 			   const struct cred *cred);
-struct path *backing_file_user_path(const struct file *f);
+const struct path *backing_file_user_path(const struct file *f);

 /*
 * When mmapping a file on a stackable filesystem (e.g., overlayfs), the file
--- a/include/linux/mount.h
+++ b/include/linux/mount.h
@@ -33,7 +33,6 @@ enum mount_flags {
 	MNT_NOSYMFOLLOW	= 0x80,

 	MNT_SHRINKABLE	= 0x100,
-	MNT_WRITE_HOLD	= 0x200,

 	MNT_INTERNAL	= 0x4000,

@@ -52,7 +51,7 @@ enum mount_flags {
 				  | MNT_READONLY | MNT_NOSYMFOLLOW,
 	MNT_ATIME_MASK = MNT_NOATIME | MNT_NODIRATIME | MNT_RELATIME,

-	MNT_INTERNAL_FLAGS = MNT_WRITE_HOLD | MNT_INTERNAL | MNT_DOOMED |
+	MNT_INTERNAL_FLAGS = MNT_INTERNAL | MNT_DOOMED |
 			     MNT_SYNC_UMOUNT | MNT_LOCKED
 };

@@ -77,7 +76,7 @@ extern void mntput(struct vfsmount *mnt);
 extern struct vfsmount *mntget(struct vfsmount *mnt);
 extern void mnt_make_shortterm(struct vfsmount *mnt);
 extern struct vfsmount *mnt_clone_internal(const struct path *path);
-extern bool __mnt_is_readonly(struct vfsmount *mnt);
+extern bool __mnt_is_readonly(const struct vfsmount *mnt);
 extern bool mnt_may_suid(struct vfsmount *mnt);

 extern struct vfsmount *clone_private_mount(const struct path *path);
@@ -104,8 +103,8 @@ extern int may_umount_tree(struct vfsmount *);
 extern int may_umount(struct vfsmount *);
 int do_mount(const char *, const char __user *,
 		     const char *, unsigned long, void *);
-extern struct path *collect_paths(const struct path *, struct path *, unsigned);
-extern void drop_collected_paths(struct path *, struct path *);
+extern const struct path *collect_paths(const struct path *, struct path *, unsigned);
+extern void drop_collected_paths(const struct path *, const struct path *);
 extern void kern_unmount_array(struct vfsmount *mnt[], unsigned int num);

 extern int cifs_root_data(char **dev, char **opts);
--- a/include/linux/namei.h
+++ b/include/linux/namei.h
@@ -60,7 +60,7 @@ extern int kern_path(const char *, unsigned, struct path *);

 extern struct dentry *kern_path_create(int, const char *, struct path *, unsigned int);
 extern struct dentry *user_path_create(int, const char __user *, struct path *, unsigned int);
-extern void done_path_create(struct path *, struct dentry *);
+extern void done_path_create(const struct path *, struct dentry *);
 extern struct dentry *kern_path_locked(const char *, struct path *);
 extern struct dentry *kern_path_locked_negative(const char *, struct path *);
 extern struct dentry *user_path_locked_at(int , const char __user *, struct path *);
--- a/kernel/audit_tree.c
+++ b/kernel/audit_tree.c
@@ -678,7 +678,7 @@ void audit_trim_trees(void)
 		struct audit_tree *tree;
 		struct path path;
 		struct audit_node *node;
-		struct path *paths;
+		const struct path *paths;
 		struct path array[16];
 		int err;

@@ -701,7 +701,7 @@ void audit_trim_trees(void)
 			struct audit_chunk *chunk = find_chunk(node);
 			/* this could be NULL if the watch is dying else where... */
 			node->index |= 1U<<31;
-			for (struct path *p = paths; p->dentry; p++) {
+			for (const struct path *p = paths; p->dentry; p++) {
 				struct inode *inode = p->dentry->d_inode;
 				if (inode_to_key(inode) == chunk->key) {
 					node->index &= ~(1U<<31);
@@ -740,9 +740,9 @@ void audit_put_tree(struct audit_tree *tree)
 	put_tree(tree);
 }

-static int tag_mounts(struct path *paths, struct audit_tree *tree)
+static int tag_mounts(const struct path *paths, struct audit_tree *tree)
 {
-	for (struct path *p = paths; p->dentry; p++) {
+	for (const struct path *p = paths; p->dentry; p++) {
 		int err = tag_chunk(p->dentry->d_inode, tree);
 		if (err)
 			return err;
@@ -805,7 +805,7 @@ int audit_add_tree_rule(struct audit_krule *rule)
 	struct audit_tree *seed = rule->tree, *tree;
 	struct path path;
 	struct path array[16];
-	struct path *paths;
+	const struct path *paths;
 	int err;

 	rule->tree = NULL;
@@ -877,7 +877,7 @@ int audit_tag_tree(char *old, char *new)
 	int failed = 0;
 	struct path path1, path2;
 	struct path array[16];
-	struct path *paths;
+	const struct path *paths;
 	int err;

 	err = kern_path(new, 0, &path2);
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -900,7 +900,7 @@ const struct bpf_func_proto bpf_send_signal_thread_proto = {
 	.arg1_type	= ARG_ANYTHING,
 };

-BPF_CALL_3(bpf_d_path, struct path *, path, char *, buf, u32, sz)
+BPF_CALL_3(bpf_d_path, const struct path *, path, char *, buf, u32, sz)
 {
 	struct path copy;
 	long len;
--- a/security/apparmor/af_unix.c
+++ b/security/apparmor/af_unix.c
@@ -31,7 +31,7 @@ static inline struct sock *aa_unix_sk(struct unix_sock *u)
 }

 static int unix_fs_perm(const char *op, u32 mask, const struct cred *subj_cred,
-			struct aa_label *label, struct path *path)
+			struct aa_label *label, const struct path *path)
 {
 	AA_BUG(!label);
 	AA_BUG(!path);
@@ -224,7 +224,7 @@ static int profile_create_perm(struct aa_profile *profile, int family,

 static int profile_sk_perm(struct aa_profile *profile,
 			   struct apparmor_audit_data *ad,
-			   u32 request, struct sock *sk, struct path *path)
+			   u32 request, struct sock *sk, const struct path *path)
 {
 	struct aa_ruleset *rules = profile->label.rules[0];
 	struct aa_perms *p = NULL;
@@ -386,9 +386,9 @@ static int profile_opt_perm(struct aa_profile *profile, u32 request,

 /* null peer_label is allowed, in which case the peer_sk label is used */
 static int profile_peer_perm(struct aa_profile *profile, u32 request,
-			     struct sock *sk, struct path *path,
+			     struct sock *sk, const struct path *path,
 			     struct sockaddr_un *peer_addr,
-			     int peer_addrlen, struct path *peer_path,
+			     int peer_addrlen, const struct path *peer_path,
 			     struct aa_label *peer_label,
 			     struct apparmor_audit_data *ad)
 {
@@ -445,7 +445,7 @@ int aa_unix_create_perm(struct aa_label *label, int family, int type,
 static int aa_unix_label_sk_perm(const struct cred *subj_cred,
 				 struct aa_label *label,
 				 const char *op, u32 request, struct sock *sk,
-				 struct path *path)
+				 const struct path *path)
 {
 	if (!unconfined(label)) {
 		struct aa_profile *profile;
@@ -599,9 +599,9 @@ int aa_unix_opt_perm(const char *op, u32 request, struct socket *sock,

 static int unix_peer_perm(const struct cred *subj_cred,
 			  struct aa_label *label, const char *op, u32 request,
-			  struct sock *sk, struct path *path,
+			  struct sock *sk, const struct path *path,
 			  struct sockaddr_un *peer_addr, int peer_addrlen,
-			  struct path *peer_path, struct aa_label *peer_label)
+			  const struct path *peer_path, struct aa_label *peer_label)
 {
 	struct aa_profile *profile;
 	DEFINE_AUDIT_SK(ad, op, subj_cred, sk);
--- a/tools/testing/selftests/bpf/bpf_experimental.h
+++ b/tools/testing/selftests/bpf/bpf_experimental.h
@@ -219,7 +219,7 @@ extern void bpf_put_file(struct file *file) __ksym;
 *	including the NULL termination character, stored in the supplied
 *	buffer. On error, a negative integer is returned.
 */
-extern int bpf_path_d_path(struct path *path, char *buf, size_t buf__sz) __ksym;
+extern int bpf_path_d_path(const struct path *path, char *buf, size_t buf__sz) __ksym;

 /* This macro must be used to mark the exception callback corresponding to the
 * main program. For example: