Pull misc vfs cleanups from Al Viro:
 "Two unrelated patches - one is a removal of long-obsolete include in
  overlayfs (it used to need fs/internal.h, but the extern it wanted has
  been moved back to include/linux/namei.h) and another introduces
  convenience helper constructing struct qstr by a NUL-terminated
  string"

* tag 'pull-misc' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs:
  add a string-to-qstr constructor
  fs/overlayfs/namei.c: get rid of include ../internal.h

Quite a few places want to build a struct qstr by given string;
it would be convenient to have a primitive doing that, rather
than open-coding it via QSTR_INIT().

The closest approximation was in bcachefs, but that expands to
initializer list - {.len = strlen(string), .name = string}.
It would be more useful to have it as compound literal -
(struct qstr){.len = strlen(string), .name = string}.

Unlike initializer list it's a valid expression.  What's more,
it's a valid lvalue - it's an equivalent of anonymous local
variable with such initializer, so the things like
	path->dentry = d_alloc_pseudo(mnt->mnt_sb, &QSTR(name));
are valid.  It can also be used as initializer, with identical
effect -
	struct qstr x = (struct qstr){.name = s, .len = strlen(s)};
is equivalent to
	struct qstr anon_variable = {.name = s, .len = strlen(s)};
	struct qstr x = anon_variable;
	// anon_variable is never used after that point
and any even remotely sane compiler will manage to collapse that
into
	struct qstr x = {.name = s, .len = strlen(s)};

What compound literals can't be used for is initialization of
global variables, but those are covered by QSTR_INIT().

This commit lifts definition(s) of QSTR() into linux/dcache.h,
converts it to compound literal (all bcachefs users are fine
with that) and converts assorted open-coded instances to using
that.

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>

9p wants to be able to build a path from given dentry to fs root and keep
it valid over a blocking operation.

->s_vfs_rename_mutex would be a natural candidate, but there are places
where we need that and where we have no way to tell if ->s_vfs_rename_mutex
is already held deeper in callchain.  Moreover, it's only held for
cross-directory renames; name changes within the same directory happen
without it.

Solution:
	* have d_move() done in ->rename() rather than in its caller
	* maintain a 9p-private rwsem (per-filesystem)
	* hold it exclusive over the relevant part of ->rename()
	* hold it shared over the places where we want the path.

That almost works.  FS_RENAME_DOES_D_MOVE is enough to put all d_move()
and d_exchange() calls under filesystem's control.  However, there's
also __d_unalias(), which isn't covered by any of that.

If ->lookup() hits a directory inode with preexisting dentry elsewhere
(due to e.g. rename done on server behind our back), d_splice_alias()
called by ->lookup() will move/rename that alias.

Add a couple of optional methods, so that __d_unalias() would do
	if alias->d_op->d_unalias_trylock != NULL
		if (!alias->d_op->d_unalias_trylock(alias))
			fail (resulting in -ESTALE from lookup)
	__d_move(...)
	if alias->d_op->d_unalias_unlock != NULL
		alias->d_unalias_unlock(alias)
where it currently does __d_move().  9p instances do down_write_trylock()
and up_write() of ->rename_mutex.

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>

->d_revalidate() often needs to access dentry parent and name; that has
to be done carefully, since the locking environment varies from caller
to caller.  We are not guaranteed that dentry in question will not be
moved right under us - not unless the filesystem is such that nothing
on it ever gets renamed.

It can be dealt with, but that results in boilerplate code that isn't
even needed - the callers normally have just found the dentry via dcache
lookup and want to verify that it's in the right place; they already
have the values of ->d_parent and ->d_name stable.  There is a couple
of exceptions (overlayfs and, to less extent, ecryptfs), but for the
majority of calls that song and dance is not needed at all.

It's easier to make ecryptfs and overlayfs find and pass those values if
there's a ->d_revalidate() instance to be called, rather than doing that
in the instances.

This commit only changes the calling conventions; making use of supplied
values is left to followups.

NOTE: some instances need more than just the parent - things like CIFS
may need to build an entire path from filesystem root, so they need
more precautions than the usual boilerplate.  This series doesn't
do anything to that need - these filesystems have to keep their locking
mechanisms (rename_lock loops, use of dentry_path_raw(), private rwsem
a-la v9fs).

One thing to keep in mind when using name is that name->name will normally
point into the pathname being resolved; the filename in question occupies
name->len bytes starting at name->name, and there is NUL somewhere after it,
but it the next byte might very well be '/' rather than '\0'.  Do not
ignore name->len.

Reviewed-by: Jeff Layton <jlayton@kernel.org>
Reviewed-by: Gabriel Krisman Bertazi <gabriel@krisman.be>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>

... so that they can be copied with struct assignment (which generates
better code) and accessed word-by-word.

The type is union shortname_storage; it's a union of arrays of
unsigned char and unsigned long.

struct name_snapshot.inline_name turned into union shortname_storage;
users (all in fs/dcache.c) adjusted.

struct dentry.d_iname has some users outside of fs/dcache.c; to
reduce the amount of noise in commit, it is replaced with
union shortname_storage d_shortname and d_iname is turned into a macro
that expands to d_shortname.string (similar to d_lock handling).
That compat macro is temporary - most of the remaining instances will
be taken out by debugfs series, and once that is merged and few others
are taken care of this will go away.

Reviewed-by: Jeff Layton <jlayton@kernel.org>
Reviewed-by: Jan Kara <jack@suse.cz>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>

... calling the number of words DNAME_INLINE_WORDS.

The next step will be to have a structure to hold inline name arrays
(both in dentry and in name_snapshot) and use that to alias the
existing arrays of unsigned char there.  That will allow both
full-structure copies and convenient word-by-word accesses.

Reviewed-by: Jeff Layton <jlayton@kernel.org>
Reviewed-by: Jan Kara <jack@suse.cz>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>

Pull vfs inode / dentry updates from Christian Brauner:
 "This contains smaller performance improvements to inodes and dentries:

  inode:

   - Add rcu based inode lookup variants.

     They avoid one inode hash lock acquire in the common case thereby
     significantly reducing contention. We already support RCU-based
     operations but didn't take advantage of them during inode
     insertion.

     Callers of iget_locked() get the improvement without any code
     changes. Callers that need a custom callback can switch to
     iget5_locked_rcu() as e.g., did btrfs.

     With 20 threads each walking a dedicated 1000 dirs * 1000 files
     directory tree to stat(2) on a 32 core + 24GB ram vm:

        before: 3.54s user 892.30s system 1966% cpu 45.549 total
        after:  3.28s user 738.66s system 1955% cpu 37.932 total (-16.7%)

     Long-term we should pick up the effort to introduce more
     fine-grained locking and possibly improve on the currently used
     hash implementation.

   - Start zeroing i_state in inode_init_always() instead of doing it in
     individual filesystems.

     This allows us to remove an unneeded lock acquire in new_inode()
     and not burden individual filesystems with this.

  dcache:

   - Move d_lockref out of the area used by RCU lookup to avoid
     cacheline ping poing because the embedded name is sharing a
     cacheline with d_lockref.

   - Fix dentry size on 32bit with CONFIG_SMP=y so it does actually end
     up with 128 bytes in total"

* tag 'vfs-6.11.inode' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs:
  fs: fix dentry size
  vfs: move d_lockref out of the area used by RCU lookup
  bcachefs: remove now spurious i_state initialization
  xfs: remove now spurious i_state initialization in xfs_inode_alloc
  vfs: partially sanitize i_state zeroing on inode creation
  xfs: preserve i_state around inode_init_always in xfs_reinit_inode
  btrfs: use iget5_locked_rcu
  vfs: add rcu-based find_inode variants for iget ops

On CONFIG_SMP=y and on 32bit we need to decrease DNAME_INLINE_LEN to 36
btyes to end up with 128 bytes in total.

Reported-by: Linus Torvalds <torvalds@linux-foundation.org>
Links: https://lore.kernel.org/r/CAHk-=whtoqTSCcAvV-X-KPqoDWxS4vxmWpuKLB+Vv8=FtUd5vA@mail.gmail.com
Signed-off-by: Christian Brauner <brauner@kernel.org>

Stock kernel scales worse than FreeBSD when doing a 20-way stat(2) on
the same tmpfs-backed file.

According to perf top:
  38.09%  lockref_put_return
  26.08%  lockref_get_not_dead
  25.60%  __d_lookup_rcu
   0.89%  clear_bhb_loop

__d_lookup_rcu is participating in cacheline ping pong due to the
embedded name sharing a cacheline with lockref.

Moving it out resolves the problem:
  41.50%  lockref_put_return
  41.03%  lockref_get_not_dead
   1.54%  clear_bhb_loop

benchmark (will-it-scale, Sapphire Rapids, tmpfs, ops/s):
FreeBSD:7219334
before:	5038006
after:	7842883 (+55%)

One minor remark: the 'after' result is unstable, fluctuating in the
range ~7.8 mln to ~9 mln during different runs.

Signed-off-by: Mateusz Guzik <mjguzik@gmail.com>
Link: https://lore.kernel.org/r/20240613001215.648829-3-mjguzik@gmail.com
Signed-off-by: Christian Brauner <brauner@kernel.org>

The routine is used by procfs through dir_emit_dots.

The combined RCU and lock fallback implementation is too big for an
inline. Given that the routine takes a dentry argument fs/dcache.c seems
like the place to put it in.

Signed-off-by: Mateusz Guzik <mjguzik@gmail.com>
Link: https://lore.kernel.org/r/20240627161152.802567-1-mjguzik@gmail.com
Signed-off-by: Christian Brauner <brauner@kernel.org>