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
  ...

Author: torvalds

Documentation/filesystems/porting.rst

@@ -1258,3 +1258,21 @@ iterator needed.  Instead of a cloned mount tree, the new interface returns
 an array of struct path, one for each mount collect_mounts() would've
 created.  These struct path point to locations in the caller's namespace
 that would be roots of the cloned mounts.
+
+---
+
+**mandatory**
+
+If your filesystem sets the default dentry_operations, use set_default_d_op()
+rather than manually setting sb->s_d_op.
+
+---
+
+**mandatory**
+
+d_set_d_op() is no longer exported (or public, for that matter); _if_
+your filesystem really needed that, make use of d_splice_alias_ops()
+to have them set.  Better yet, think hard whether you need different
+->d_op for different dentries - if not, just use set_default_d_op()
+at mount time and be done with that.  Currently procfs is the only
+thing that really needs ->d_op varying between dentries.

fs/9p/vfs_dentry.c

@@ -127,7 +127,6 @@ const struct dentry_operations v9fs_cached_dentry_operations = {
 };
 
 const struct dentry_operations v9fs_dentry_operations = {
-	.d_delete = always_delete_dentry,
 	.d_release = v9fs_dentry_release,
 	.d_unalias_trylock = v9fs_dentry_unalias_trylock,
 	.d_unalias_unlock = v9fs_dentry_unalias_unlock,

fs/9p/vfs_super.c

@@ -134,10 +134,12 @@ static struct dentry *v9fs_mount(struct file_system_type *fs_type, int flags,
 	if (retval)
 		goto release_sb;
 
-	if (v9ses->cache & (CACHE_META|CACHE_LOOSE))
-		sb->s_d_op = &v9fs_cached_dentry_operations;
-	else
-		sb->s_d_op = &v9fs_dentry_operations;
+	if (v9ses->cache & (CACHE_META|CACHE_LOOSE)) {
+		set_default_d_op(sb, &v9fs_cached_dentry_operations);
+	} else {
+		set_default_d_op(sb, &v9fs_dentry_operations);
+		sb->s_d_flags |= DCACHE_DONTCACHE;
+	}
 
 	inode = v9fs_get_new_inode_from_fid(v9ses, fid, sb);
 	if (IS_ERR(inode)) {

fs/adfs/super.c

@@ -397,7 +397,7 @@ static int adfs_fill_super(struct super_block *sb, struct fs_context *fc)
 	if (asb->s_ftsuffix)
 		asb->s_namelen += 4;
 
-	sb->s_d_op = &adfs_dentry_operations;
+	set_default_d_op(sb, &adfs_dentry_operations);
 	root = adfs_iget(sb, &root_obj);
 	sb->s_root = d_make_root(root);
 	if (!sb->s_root) {

fs/affs/super.c

@@ -500,9 +500,9 @@ static int affs_fill_super(struct super_block *sb, struct fs_context *fc)
 		return PTR_ERR(root_inode);
 
 	if (affs_test_opt(AFFS_SB(sb)->s_flags, SF_INTL))
-		sb->s_d_op = &affs_intl_dentry_operations;
+		set_default_d_op(sb, &affs_intl_dentry_operations);
 	else
-		sb->s_d_op = &affs_dentry_operations;
+		set_default_d_op(sb, &affs_dentry_operations);
 
 	sb->s_root = d_make_root(root_inode);
 	if (!sb->s_root) {

fs/afs/super.c

@@ -483,9 +483,9 @@ static int afs_fill_super(struct super_block *sb, struct afs_fs_context *ctx)
 		goto error;
 
 	if (as->dyn_root) {
-		sb->s_d_op = &afs_dynroot_dentry_operations;
+		set_default_d_op(sb, &afs_dynroot_dentry_operations);
 	} else {
-		sb->s_d_op = &afs_fs_dentry_operations;
+		set_default_d_op(sb, &afs_fs_dentry_operations);
 		rcu_assign_pointer(as->volume->sb, sb);
 	}
 

fs/autofs/inode.c

@@ -311,7 +311,7 @@ static int autofs_fill_super(struct super_block *s, struct fs_context *fc)
 	s->s_blocksize_bits = 10;
 	s->s_magic = AUTOFS_SUPER_MAGIC;
 	s->s_op = &autofs_sops;
-	s->s_d_op = &autofs_dentry_operations;
+	set_default_d_op(s, &autofs_dentry_operations);
 	s->s_time_gran = 1;
 
 	/*

fs/btrfs/super.c

@@ -959,7 +959,7 @@ static int btrfs_fill_super(struct super_block *sb,
 	sb->s_maxbytes = MAX_LFS_FILESIZE;
 	sb->s_magic = BTRFS_SUPER_MAGIC;
 	sb->s_op = &btrfs_super_ops;
-	sb->s_d_op = &btrfs_dentry_operations;
+	set_default_d_op(sb, &btrfs_dentry_operations);
 	sb->s_export_op = &btrfs_export_ops;
 #ifdef CONFIG_FS_VERITY
 	sb->s_vop = &btrfs_verityops;

fs/ceph/super.c

@@ -1219,7 +1219,7 @@ static int ceph_set_super(struct super_block *s, struct fs_context *fc)
 	fsc->max_file_size = 1ULL << 40; /* temp value until we get mdsmap */
 
 	s->s_op = &ceph_super_ops;
-	s->s_d_op = &ceph_dentry_ops;
+	set_default_d_op(s, &ceph_dentry_ops);
 	s->s_export_op = &ceph_export_ops;
 
 	s->s_time_gran = 1;

fs/coda/inode.c

@@ -230,7 +230,7 @@ static int coda_fill_super(struct super_block *sb, struct fs_context *fc)
 	sb->s_blocksize_bits = 12;
 	sb->s_magic = CODA_SUPER_MAGIC;
 	sb->s_op = &coda_super_operations;
-	sb->s_d_op = &coda_dentry_operations;
+	set_default_d_op(sb, &coda_dentry_operations);
 	sb->s_time_gran = 1;
 	sb->s_time_min = S64_MIN;
 	sb->s_time_max = S64_MAX;