mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: NeilBrown <neilb@ownmail.net>
To: Alexander Viro <viro@zeniv.linux.org.uk>,
	Christian Brauner <brauner@kernel.org>
Cc: Jan Harkes <jaharkes@cs.cmu.edu>,
	coda@cs.cmu.edu, Jan Kara <jack@suse.cz>,
	Richard Weinberger <richard@nod.at>,
	Anton Ivanov <anton.ivanov@cambridgegreys.com>,
	Johannes Berg <johannes@sipsolutions.net>,
	Namjae Jeon <linkinjeon@kernel.org>,
	Hyunchul Lee <hyc.lee@gmail.com>,
	Carlos Maiolino <cem@kernel.org>,
	Jeff Layton <jlayton@kernel.org>,
	Amir Goldstein <amir73il@gmail.com>,
	linux-kernel@vger.kernel.org, codalist@coda.cs.cmu.edu,
	linux-fsdevel@vger.kernel.org, linux-um@lists.infradead.org,
	ntfs@lists.linux.dev, linux-xfs@vger.kernel.org
Subject: [PATCH v2 1/4] VFS/xfs/ntfs: drop parent lock across d_alloc_parallel() in d_add_ci()
Date: Tue, 17 Nov 2026 10:54:58 +1100	[thread overview]
Message-ID: <20261117000115.1433875-2-neilb@ownmail.net> (raw)
In-Reply-To: <20261117000115.1433875-1-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>
---
 Documentation/filesystems/porting.rst |  7 ++++++
 fs/dcache.c                           | 32 +++++++++++++++++++++++----
 fs/ntfs/namei.c                       |  2 +-
 fs/xfs/xfs_iops.c                     |  2 +-
 include/linux/dcache.h                |  3 ++-
 5 files changed, 39 insertions(+), 7 deletions(-)

diff --git a/Documentation/filesystems/porting.rst b/Documentation/filesystems/porting.rst
index c38f5df755bb..4cab51e1bd6c 100644
--- a/Documentation/filesystems/porting.rst
+++ b/Documentation/filesystems/porting.rst
@@ -1422,3 +1422,10 @@ helpers take a const struct mnt_idmap *. mnt_idmap() and file_mnt_idmap()
 return one. The idmapping is immutable so nothing should have modified it
 anyway. References are taken and dropped via mnt_idmap_get() and
 mnt_idmap_put() as before, both accept a const pointer.
+
+---
+
+**mandatory**
+
+d_add_ci() must now be passed the flags arguemnt that was given to ->lookup
+
diff --git a/fs/dcache.c b/fs/dcache.c
index 720b32cb2e03..255ebdad303d 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -2419,6 +2419,7 @@ 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
+ * @lookup_flags: flags passed to ->lookup
  *
  * 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
@@ -2431,9 +2432,10 @@ 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, unsigned int lookup_flags)
 {
 	struct dentry *found, *res;
+	bool must_relock = false;
 
 	/*
 	 * First check if a dentry matching the name already exists,
@@ -2445,24 +2447,46 @@ struct dentry *d_add_ci(struct dentry *dentry, struct inode *inode,
 		return found;
 	}
 	if (d_in_lookup(dentry)) {
+		/*
+		 * 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.
+		 * We cannot retake the lock while the new dentry is in-lookup
+		 */
+		if (lookup_flags & LOOKUP_SHARED)
+			inode_unlock_shared(d_inode(dentry->d_parent));
+		else
+			inode_unlock(d_inode(dentry->d_parent));
+		must_relock = true;
 		found = d_alloc_parallel(dentry->d_parent, name);
 		if (IS_ERR(found) || !d_in_lookup(found)) {
 			iput(inode);
-			return found;
+			goto out_relock;
 		}
 	} else {
 		found = d_alloc(dentry->d_parent, name);
 		if (!found) {
 			iput(inode);
 			return ERR_PTR(-ENOMEM);
-		} 
+		}
 	}
 	res = d_splice_alias(inode, found);
 	if (res) {
 		d_lookup_done(found);
 		dput(found);
-		return res;
+		found = res;
 	}
+	if (!must_relock)
+		return found;
+out_relock:
+	d_lookup_done(dentry);
+	if (lookup_flags & LOOKUP_SHARED)
+		inode_lock_shared(d_inode(dentry->d_parent));
+	else
+		inode_lock_nested(d_inode(dentry->d_parent), I_MUTEX_PARENT);
 	return found;
 }
 EXPORT_SYMBOL(d_add_ci);
diff --git a/fs/ntfs/namei.c b/fs/ntfs/namei.c
index b46fe44b63b5..16ed6027fa13 100644
--- a/fs/ntfs/namei.c
+++ b/fs/ntfs/namei.c
@@ -332,7 +332,7 @@ 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);
 		kfree(nls_name.name);
 		return dent;
 
diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c
index d307ec97fac8..ec08c882c6f7 100644
--- a/fs/xfs/xfs_iops.c
+++ b/fs/xfs/xfs_iops.c
@@ -368,7 +368,7 @@ 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);
 	kfree(ci_name.name);
 	return dentry;
 }
diff --git a/include/linux/dcache.h b/include/linux/dcache.h
index aaa4ba7a1299..9dd91ba2fe33 100644
--- a/include/linux/dcache.h
+++ b/include/linux/dcache.h
@@ -267,7 +267,8 @@ 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 *,
+				unsigned int);
 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);

base-commit: 7475ea8b58616b33c04afb976cf0fbaad9dd63fb
-- 
2.50.0.107.gf914562f5916.dirty


  reply	other threads:[~2026-11-17  0:01 UTC|newest]

Thread overview: 9+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-11-16 23:54 [PATCH v2 0/4] multiple-filesystems: prepare for changes to VFS locking NeilBrown
2026-11-16 23:54 ` NeilBrown [this message]
2026-11-20 13:35   ` [PATCH v2 1/4] VFS/xfs/ntfs: drop parent lock across d_alloc_parallel() in d_add_ci() Christian Brauner
2026-11-20 16:47   ` Christoph Hellwig
2026-11-16 23:54 ` [PATCH v2 2/4] coda: don't d_drop() early NeilBrown
2026-11-20 17:30   ` Jan Harkes
2026-11-16 23:55 ` [PATCH v2 3/4] hostfs: don't d_drop() before d_splice_alias() in hostfs_mkdir() NeilBrown
2026-11-16 23:55 ` [PATCH v2 4/4] procfs: drop parent lock for d_alloc_parallel() in iterate_shared() NeilBrown
2026-11-20 13:38   ` Christian Brauner

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=20261117000115.1433875-2-neilb@ownmail.net \
    --to=neilb@ownmail.net \
    --cc=amir73il@gmail.com \
    --cc=anton.ivanov@cambridgegreys.com \
    --cc=brauner@kernel.org \
    --cc=cem@kernel.org \
    --cc=coda@cs.cmu.edu \
    --cc=codalist@coda.cs.cmu.edu \
    --cc=hyc.lee@gmail.com \
    --cc=jack@suse.cz \
    --cc=jaharkes@cs.cmu.edu \
    --cc=jlayton@kernel.org \
    --cc=johannes@sipsolutions.net \
    --cc=linkinjeon@kernel.org \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-um@lists.infradead.org \
    --cc=linux-xfs@vger.kernel.org \
    --cc=neil@brown.name \
    --cc=ntfs@lists.linux.dev \
    --cc=richard@nod.at \
    --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

all inboxes | Powered by JetHome®