Merge tag 'vfs-6.15-rc1.misc' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs

Pull misc vfs updates from Christian Brauner:
 "Features:

   - Add CONFIG_DEBUG_VFS infrastucture:
      - Catch invalid modes in open
      - Use the new debug macros in inode_set_cached_link()
      - Use debug-only asserts around fd allocation and install

   - Place f_ref to 3rd cache line in struct file to resolve false
     sharing

Cleanups:

   - Start using anon_inode_getfile_fmode() helper in various places

   - Don't take f_lock during SEEK_CUR if exclusion is guaranteed by
     f_pos_lock

   - Add unlikely() to kcmp()

   - Remove legacy ->remount_fs method from ecryptfs after port to the
     new mount api

   - Remove invalidate_inodes() in favour of evict_inodes()

   - Simplify ep_busy_loopER by removing unused argument

   - Avoid mmap sem relocks when coredumping with many missing pages

   - Inline getname()

   - Inline new_inode_pseudo() and de-staticize alloc_inode()

   - Dodge an atomic in putname if ref == 1

   - Consistently deref the files table with rcu_dereference_raw()

   - Dedup handling of struct filename init and refcounts bumps

   - Use wq_has_sleeper() in end_dir_add()

   - Drop the lock trip around I_NEW wake up in evict()

   - Load the ->i_sb pointer once in inode_sb_list_{add,del}

   - Predict not reaching the limit in alloc_empty_file()

   - Tidy up do_sys_openat2() with likely/unlikely

   - Call inode_sb_list_add() outside of inode hash lock

   - Sort out fd allocation vs dup2 race commentary

   - Turn page_offset() into a wrapper around folio_pos()

   - Remove locking in exportfs around ->get_parent() call

   - try_lookup_one_len() does not need any locks in autofs

   - Fix return type of several functions from long to int in open

   - Fix return type of several functions from long to int in ioctls

  Fixes:

   - Fix watch queue accounting mismatch"

* tag 'vfs-6.15-rc1.misc' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs: (30 commits)
  fs: sort out fd allocation vs dup2 race commentary, take 2
  fs: call inode_sb_list_add() outside of inode hash lock
  fs: tidy up do_sys_openat2() with likely/unlikely
  fs: predict not reaching the limit in alloc_empty_file()
  fs: load the ->i_sb pointer once in inode_sb_list_{add,del}
  fs: drop the lock trip around I_NEW wake up in evict()
  fs: use wq_has_sleeper() in end_dir_add()
  VFS/autofs: try_lookup_one_len() does not need any locks
  fs: dedup handling of struct filename init and refcounts bumps
  fs: consistently deref the files table with rcu_dereference_raw()
  exportfs: remove locking around ->get_parent() call.
  fs: use debug-only asserts around fd allocation and install
  fs: dodge an atomic in putname if ref == 1
  vfs: Remove invalidate_inodes()
  ecryptfs: remove NULL remount_fs from super_operations
  watch_queue: fix pipe accounting mismatch
  fs: place f_ref to 3rd cache line in struct file to resolve false sharing
  epoll: simplify ep_busy_loop by removing always 0 argument
  fs: Turn page_offset() into a wrapper around folio_pos()
  kcmp: improve performance adding an unlikely hint to task comparisons
  ...

1 files changed, 22 insertions, 20 deletions

diff --git a/fs/namei.c b/fs/namei.c
index ecb7b95c2ca3..2a12238e696a 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -125,6 +125,13 @@
 
 #define EMBEDDED_NAME_MAX	(PATH_MAX - offsetof(struct filename, iname))
 
+static inline void initname(struct filename *name)
+{
+	name->uptr = NULL;
+	name->aname = NULL;
+	atomic_set(&name->refcnt, 1);
+}
+
 struct filename *
 getname_flags(const char __user *filename, int flags)
 {
@@ -203,10 +210,7 @@ getname_flags(const char __user *filename, int flags)
 			return ERR_PTR(-ENAMETOOLONG);
 		}
 	}
-
-	atomic_set(&result->refcnt, 1);
-	result->uptr = filename;
-	result->aname = NULL;
+	initname(result);
 	audit_getname(result);
 	return result;
 }
@@ -218,11 +222,6 @@ struct filename *getname_uflags(const char __user *filename, int uflags)
 	return getname_flags(filename, flags);
 }
 
-struct filename *getname(const char __user * filename)
-{
-	return getname_flags(filename, 0);
-}
-
 struct filename *__getname_maybe_null(const char __user *pathname)
 {
 	struct filename *name;
@@ -269,25 +268,27 @@ struct filename *getname_kernel(const char * filename)
 		return ERR_PTR(-ENAMETOOLONG);
 	}
 	memcpy((char *)result->name, filename, len);
-	result->uptr = NULL;
-	result->aname = NULL;
-	atomic_set(&result->refcnt, 1);
+	initname(result);
 	audit_getname(result);
-
 	return result;
 }
 EXPORT_SYMBOL(getname_kernel);
 
 void putname(struct filename *name)
 {
+	int refcnt;
+
 	if (IS_ERR_OR_NULL(name))
 		return;
 
-	if (WARN_ON_ONCE(!atomic_read(&name->refcnt)))
-		return;
+	refcnt = atomic_read(&name->refcnt);
+	if (refcnt != 1) {
+		if (WARN_ON_ONCE(!refcnt))
+			return;
 
-	if (!atomic_dec_and_test(&name->refcnt))
-		return;
+		if (!atomic_dec_and_test(&name->refcnt))
+			return;
+	}
 
 	if (name->name != name->iname) {
 		__putname(name->name);
@@ -2863,15 +2864,14 @@ static int lookup_one_common(struct mnt_idmap *idmap,
  * Note that this routine is purely a helper for filesystem usage and should
  * not be called by generic code.
  *
- * The caller must hold base->i_mutex.
+ * No locks need be held - only a counted reference to @base is needed.
+ *
  */
 struct dentry *try_lookup_one_len(const char *name, struct dentry *base, int len)
 {
 	struct qstr this;
 	int err;
 
-	WARN_ON_ONCE(!inode_is_locked(base->d_inode));
-
 	err = lookup_one_common(&nop_mnt_idmap, name, base, len, &this);
 	if (err)
 		return ERR_PTR(err);
@@ -3415,6 +3415,8 @@ static int may_open(struct mnt_idmap *idmap, const struct path *path,
 		if ((acc_mode & MAY_EXEC) && path_noexec(path))
 			return -EACCES;
 		break;
+	default:
+		VFS_BUG_ON_INODE(1, inode);
 	}
 
 	error = inode_permission(idmap, inode, MAY_OPEN | acc_mode);