public inbox for linux-efi@vger.kernel.org
 help / color / mirror / Atom feed
From: NeilBrown <neilb@ownmail.net>
To: Linus Torvalds <torvalds@linux-foundation.org>,
	Alexander Viro <viro@zeniv.linux.org.uk>,
	Christian Brauner <brauner@kernel.org>, Jan Kara <jack@suse.cz>,
	Jeff Layton <jlayton@kernel.org>,
	Trond Myklebust <trondmy@kernel.org>,
	Anna Schumaker <anna@kernel.org>,
	Miklos Szeredi <miklos@szeredi.hu>,
	Amir Goldstein <amir73il@gmail.com>, Jeremy Kerr <jk@ozlabs.org>,
	Ard Biesheuvel <ardb@kernel.org>,
	Christoph Hellwig <hch@infradead.org>
Cc: linux-efi@vger.kernel.org, linux-fsdevel@vger.kernel.org,
	linux-nfs@vger.kernel.org, linux-unionfs@vger.kernel.org,
	linux-kernel@vger.kernel
Subject: [PATCH v2 08/19] VFS/xfs/ntfs: drop parent lock across d_alloc_parallel() in d_add_ci()
Date: Mon, 27 Apr 2026 13:29:41 +1000	[thread overview]
Message-ID: <20260427033527.773006-9-neilb@ownmail.net> (raw)
In-Reply-To: <20260427033527.773006-1-neilb@ownmail.net>

From: NeilBrown <neil@brown.name>

A proposed change will invert the lock ordering between
d_alloc_parallel() and inode_lock() on the parent.
When that happens it will not be safe to call d_alloc_parallel() while
holding the parent lock - even shared.

We don't need to keep the parent lock held when d_add_ci() is run - the
VFS doesn't need it as dentry is exclusively held due to
DCACHE_PAR_LOOKUP and the filesystem has finished its work.

So drop and reclaim the lock (shared or exclusive as determined by
LOOKUP_SHARED) to avoid future deadlock.

Signed-off-by: NeilBrown <neil@brown.name>
---
 fs/dcache.c            | 18 +++++++++++++++++-
 fs/ntfs/namei.c        |  4 +++-
 fs/xfs/xfs_iops.c      |  3 ++-
 include/linux/dcache.h |  3 ++-
 4 files changed, 24 insertions(+), 4 deletions(-)

diff --git a/fs/dcache.c b/fs/dcache.c
index 569a8ddf4c0d..a2ddfe811df3 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -2294,6 +2294,7 @@ EXPORT_SYMBOL(d_obtain_root);
  * @dentry: the negative dentry that was passed to the parent's lookup func
  * @inode:  the inode case-insensitive lookup has found
  * @name:   the case-exact name to be associated with the returned dentry
+ * @bool:   %true if lookup was performed with LOOKUP_SHARED
  *
  * This is to avoid filling the dcache with case-insensitive names to the
  * same inode, only the actual correct case is stored in the dcache for
@@ -2306,7 +2307,7 @@ EXPORT_SYMBOL(d_obtain_root);
  * the exact case, and return the spliced entry.
  */
 struct dentry *d_add_ci(struct dentry *dentry, struct inode *inode,
-			struct qstr *name)
+			struct qstr *name, bool shared)
 {
 	struct dentry *found, *res;
 
@@ -2319,6 +2320,17 @@ struct dentry *d_add_ci(struct dentry *dentry, struct inode *inode,
 		iput(inode);
 		return found;
 	}
+	/*
+	 * We are holding parent lock and so don't want to wait for a
+	 * d_in_lookup() dentry.  We can safely drop the parent lock and
+	 * reclaim it as we have exclusive access to dentry as it is
+	 * d_in_lookup() (so ->d_parent is stable) and we are near the
+	 * end ->lookup() and will shortly drop the lock anyway.
+	 */
+	if (shared)
+		inode_unlock_shared(d_inode(dentry->d_parent));
+	else
+		inode_unlock(d_inode(dentry->d_parent));
 	if (d_in_lookup(dentry)) {
 		found = d_alloc_parallel(dentry->d_parent, name);
 		if (IS_ERR(found) || !d_in_lookup(found)) {
@@ -2332,6 +2344,10 @@ struct dentry *d_add_ci(struct dentry *dentry, struct inode *inode,
 			return ERR_PTR(-ENOMEM);
 		}
 	}
+	if (shared)
+		inode_lock_shared(d_inode(dentry->d_parent));
+	else
+		inode_lock_nested(d_inode(dentry->d_parent), I_MUTEX_PARENT);
 	res = d_splice_alias(inode, found);
 	if (res) {
 		d_lookup_done(found);
diff --git a/fs/ntfs/namei.c b/fs/ntfs/namei.c
index 10894de519c3..30dddef43300 100644
--- a/fs/ntfs/namei.c
+++ b/fs/ntfs/namei.c
@@ -8,6 +8,7 @@
 
 #include <linux/exportfs.h>
 #include <linux/iversion.h>
+#include <linux/namei.h> // for LOOKUP_SHARED
 
 #include "ntfs.h"
 #include "time.h"
@@ -310,7 +311,8 @@ static struct dentry *ntfs_lookup(struct inode *dir_ino, struct dentry *dent,
 		}
 		nls_name.hash = full_name_hash(dent, nls_name.name, nls_name.len);
 
-		dent = d_add_ci(dent, dent_inode, &nls_name);
+		dent = d_add_ci(dent, dent_inode, &nls_name,
+				!!(flags & LOOKUP_SHARED));
 		kfree(nls_name.name);
 		return dent;
 
diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c
index 325c2200c501..f03d832f1468 100644
--- a/fs/xfs/xfs_iops.c
+++ b/fs/xfs/xfs_iops.c
@@ -35,6 +35,7 @@
 #include <linux/security.h>
 #include <linux/iversion.h>
 #include <linux/fiemap.h>
+#include <linux/namei.h> // for LOOKUP_SHARED
 
 /*
  * Directories have different lock order w.r.t. mmap_lock compared to regular
@@ -369,7 +370,7 @@ xfs_vn_ci_lookup(
 	/* else case-insensitive match... */
 	dname.name = ci_name.name;
 	dname.len = ci_name.len;
-	dentry = d_add_ci(dentry, VFS_I(ip), &dname);
+	dentry = d_add_ci(dentry, VFS_I(ip), &dname, !!(flags & LOOKUP_SHARED));
 	kfree(ci_name.name);
 	return dentry;
 }
diff --git a/include/linux/dcache.h b/include/linux/dcache.h
index 3991f9988599..662b98185337 100644
--- a/include/linux/dcache.h
+++ b/include/linux/dcache.h
@@ -263,7 +263,8 @@ struct dentry *d_duplicate(struct dentry *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 struct dentry * d_add_ci(struct dentry *, struct inode *, struct qstr *,
+				bool);
 extern bool d_same_name(const struct dentry *dentry, const struct dentry *parent,
 			const struct qstr *name);
 extern struct dentry *d_find_any_alias(struct inode *inode);
-- 
2.50.0.107.gf914562f5916.dirty


  parent reply	other threads:[~2026-04-27  3:37 UTC|newest]

Thread overview: 22+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-04-27  3:29 [PATCH v2 00/19] Prepare to lift lookup out of exclusive lock for directory ops NeilBrown
2026-04-27  3:29 ` [PATCH v2 01/19] VFS: fix various typos in documentation for start_creating start_removing etc NeilBrown
2026-04-27  3:29 ` [PATCH v2 02/19] VFS: enhance d_splice_alias() to handle in-lookup dentries NeilBrown
2026-04-27  3:29 ` [PATCH v2 03/19] VFS: allow d_alloc_name() to be used with ->d_hash NeilBrown
2026-04-27  3:29 ` [PATCH v2 04/19] VFS: use wait_var_event for waiting in d_alloc_parallel() NeilBrown
2026-04-27  3:29 ` [PATCH v2 05/19] VFS: introduce d_alloc_noblock() NeilBrown
2026-04-27  3:29 ` [PATCH v2 06/19] VFS: add d_duplicate() NeilBrown
2026-04-27  3:29 ` [PATCH v2 07/19] VFS: Add LOOKUP_SHARED flag NeilBrown
2026-04-27  3:29 ` NeilBrown [this message]
2026-04-27  3:29 ` [PATCH v2 09/19] ovl: stop using lookup_one() in iterate_shared() handling NeilBrown
2026-04-27  3:29 ` [PATCH v2 10/19] VFS/ovl: add d_alloc_noblock_return() NeilBrown
2026-04-27  3:29 ` [PATCH v2 11/19] efivarfs: use d_alloc_name() NeilBrown
2026-04-27  3:29 ` [PATCH v2 12/19] shmem: use d_duplicate() NeilBrown
2026-04-27  3:29 ` [PATCH v2 13/19] nfs: remove d_drop()/d_alloc_parallel() from nfs_atomic_open() NeilBrown
2026-04-27  3:29 ` [PATCH v2 14/19] nfs: use d_splice_alias() in nfs_link() NeilBrown
2026-04-27  3:29 ` [PATCH v2 15/19] nfs: don't d_drop() before d_splice_alias() NeilBrown
2026-04-27  3:29 ` [PATCH v2 16/19] nfs: don't d_drop() before d_splice_alias() in atomic_create NeilBrown
2026-04-27  3:29 ` [PATCH v2 17/19] nfs: Use d_alloc_noblock() in nfs_prime_dcache() NeilBrown
2026-04-27  3:29 ` [PATCH v2 18/19] nfs: use d_alloc_noblock() in silly-rename NeilBrown
2026-04-27  3:29 ` [PATCH v2 19/19] nfs: use d_duplicate() NeilBrown
2026-04-27  3:47 ` [PATCH v2 00/19] Prepare to lift lookup out of exclusive lock for directory ops Al Viro
2026-04-27  8:41 ` [syzbot ci] " syzbot ci

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20260427033527.773006-9-neilb@ownmail.net \
    --to=neilb@ownmail.net \
    --cc=amir73il@gmail.com \
    --cc=anna@kernel.org \
    --cc=ardb@kernel.org \
    --cc=brauner@kernel.org \
    --cc=hch@infradead.org \
    --cc=jack@suse.cz \
    --cc=jk@ozlabs.org \
    --cc=jlayton@kernel.org \
    --cc=linux-efi@vger.kernel.org \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=linux-kernel@vger.kernel \
    --cc=linux-nfs@vger.kernel.org \
    --cc=linux-unionfs@vger.kernel.org \
    --cc=miklos@szeredi.hu \
    --cc=neil@brown.name \
    --cc=torvalds@linux-foundation.org \
    --cc=trondmy@kernel.org \
    --cc=viro@zeniv.linux.org.uk \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox