Merge tag 'pull-dcache' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs

Pull dentry d_flags updates from Al Viro:
 "The current exclusion rules for dentry->d_flags stores are rather
  unpleasant. The basic rules are simple:

   - stores to dentry->d_flags are OK under dentry->d_lock

   - stores to dentry->d_flags are OK in the dentry constructor, before
     becomes potentially visible to other threads

  Unfortunately, there's a couple of exceptions to that, and that's
  where the headache comes from.

  The main PITA comes from d_set_d_op(); that primitive sets ->d_op of
  dentry and adjusts the flags that correspond to presence of individual
  methods. It's very easy to misuse; existing uses _are_ safe, but proof
  of correctness is brittle.

  Use in __d_alloc() is safe (we are within a constructor), but we might
  as well precalculate the initial value of 'd_flags' when we set the
  default ->d_op for given superblock and set 'd_flags' directly instead
  of messing with that helper.

  The reasons why other uses are safe are bloody convoluted; I'm not
  going to reproduce it here. See [1] for gory details, if you care. The
  critical part is using d_set_d_op() only just prior to
  d_splice_alias(), which makes a combination of d_splice_alias() with
  setting ->d_op, etc a natural replacement primitive.

  Better yet, if we go that way, it's easy to take setting ->d_op and
  modifying 'd_flags' under ->d_lock, which eliminates the headache as
  far as 'd_flags' exclusion rules are concerned. Other exceptions are
  minor and easy to deal with.

  What this series does:

   - d_set_d_op() is no longer available; instead a new primitive
     (d_splice_alias_ops()) is provided, equivalent to combination of
     d_set_d_op() and d_splice_alias().

   - new field of struct super_block - 's_d_flags'. This sets the
     default value of 'd_flags' to be used when allocating dentries on
     this filesystem.

   - new primitive for setting 's_d_op': set_default_d_op(). This
     replaces stores to 's_d_op' at mount time.

     All in-tree filesystems converted; out-of-tree ones will get caught
     by the compiler ('s_d_op' is renamed, so stores to it will be
     caught). 's_d_flags' is set by the same primitive to match the
     's_d_op'.

   - a lot of filesystems had sb->s_d_op->d_delete equal to
     always_delete_dentry; that is equivalent to setting
     DCACHE_DONTCACHE in 'd_flags', so such filesystems can bloody well
     set that bit in 's_d_flags' and drop 'd_delete()' from
     dentry_operations.

     In quite a few cases that results in empty dentry_operations, which
     means that we can get rid of those.

   - kill simple_dentry_operations - not needed anymore

   - massage d_alloc_parallel() to get rid of the other exception wrt
     'd_flags' stores - we can set DCACHE_PAR_LOOKUP as soon as we
     allocate the new dentry; no need to delay that until we commit to
     using the sucker.

  As the result, 'd_flags' stores are all either under ->d_lock or done
  before the dentry becomes visible in any shared data structures"

Link: https://lore.kernel.org/all/20250224010624.GT1977892@ZenIV/ [1]

* tag 'pull-dcache' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs: (21 commits)
  configfs: use DCACHE_DONTCACHE
  debugfs: use DCACHE_DONTCACHE
  efivarfs: use DCACHE_DONTCACHE instead of always_delete_dentry()
  9p: don't bother with always_delete_dentry
  ramfs, hugetlbfs, mqueue: set DCACHE_DONTCACHE
  kill simple_dentry_operations
  devpts, sunrpc, hostfs: don't bother with ->d_op
  shmem: no dentry retention past the refcount reaching zero
  d_alloc_parallel(): set DCACHE_PAR_LOOKUP earlier
  make d_set_d_op() static
  simple_lookup(): just set DCACHE_DONTCACHE
  tracefs: Add d_delete to remove negative dentries
  set_default_d_op(): calculate the matching value for ->d_flags
  correct the set of flags forbidden at d_set_d_op() time
  split d_flags calculation out of d_set_d_op()
  new helper: set_default_d_op()
  fuse: no need for special dentry_operations for root dentry
  switch procfs from d_set_d_op() to d_splice_alias_ops()
  new helper: d_splice_alias_ops()
  procfs: kill ->proc_dops
  ...

3 files changed, 9 insertions, 3 deletions

diff --git a/include/linux/dcache.h b/include/linux/dcache.h
index e29823c701ac..cc3e1c1a3454 100644
--- a/include/linux/dcache.h
+++ b/include/linux/dcache.h
@@ -237,7 +237,6 @@ extern void d_instantiate_new(struct dentry *, struct inode *);
 extern void __d_drop(struct dentry *dentry);
 extern void d_drop(struct dentry *dentry);
 extern void d_delete(struct dentry *);
-extern void d_set_d_op(struct dentry *dentry, const struct dentry_operations *op);
 
 /* allocate/de-allocate */
 extern struct dentry * d_alloc(struct dentry *, const struct qstr *);
@@ -245,6 +244,9 @@ extern struct dentry * d_alloc_anon(struct super_block *);
 extern struct dentry * d_alloc_parallel(struct dentry *, const struct qstr *,
 					wait_queue_head_t *);
 extern struct dentry * d_splice_alias(struct inode *, struct dentry *);
+/* weird procfs mess; *NOT* exported */
+extern struct dentry * d_splice_alias_ops(struct inode *, struct dentry *,
+					  const struct dentry_operations *);
 extern struct dentry * d_add_ci(struct dentry *, struct inode *, struct qstr *);
 extern bool d_same_name(const struct dentry *dentry, const struct dentry *parent,
 			const struct qstr *name);
@@ -604,4 +606,6 @@ static inline struct dentry *d_next_sibling(const struct dentry *dentry)
 	return hlist_entry_safe(dentry->d_sib.next, struct dentry, d_sib);
 }
 
+void set_default_d_op(struct super_block *, const struct dentry_operations *);
+
 #endif	/* __LINUX_DCACHE_H */
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 040c0036320f..169150976274 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1402,6 +1402,7 @@ struct super_block {
 	char			s_sysfs_name[UUID_STRING_LEN + 1];
 
 	unsigned int		s_max_links;
+	unsigned int		s_d_flags;	/* default d_flags for dentries */
 
 	/*
 	 * The next field is for VFS *only*. No filesystems have any business
@@ -1415,7 +1416,7 @@ struct super_block {
 	 */
 	const char *s_subtype;
 
-	const struct dentry_operations *s_d_op; /* default d_op for dentries */
+	const struct dentry_operations *__s_d_op; /* default d_op for dentries */
 
 	struct shrinker *s_shrink;	/* per-sb shrinker handle */
 
@@ -3611,7 +3612,6 @@ extern struct inode *alloc_anon_inode(struct super_block *);
 struct inode *anon_inode_make_secure_inode(struct super_block *sb, const char *name,
 					   const struct inode *context_inode);
 extern int simple_nosetlease(struct file *, int, struct file_lease **, void **);
-extern const struct dentry_operations simple_dentry_operations;
 
 extern struct dentry *simple_lookup(struct inode *, struct dentry *, unsigned int flags);
 extern ssize_t generic_read_dir(struct file *, char __user *, size_t, loff_t *);
diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h
index ea62201c74c4..de1d24f19f76 100644
--- a/include/linux/proc_fs.h
+++ b/include/linux/proc_fs.h
@@ -27,6 +27,8 @@ enum {
 
 	PROC_ENTRY_proc_read_iter	= 1U << 1,
 	PROC_ENTRY_proc_compat_ioctl	= 1U << 2,
+
+	PROC_ENTRY_FORCE_LOOKUP		= 1U << 7,
 };
 
 struct proc_ops {