All of lore.kernel.org
 help / color / mirror / Atom feed
From: Justin Suess <utilityemal77@gmail.com>
To: "Christian Brauner" <brauner@kernel.org>,
	"Alexander Viro" <viro@zeniv.linux.org.uk>,
	"Jan Kara" <jack@suse.cz>, NeilBrown <neil@brown.name>,
	"Mickaël Salaün" <mic@digikod.net>,
	"Alexei Starovoitov" <ast@kernel.org>,
	"Daniel Borkmann" <daniel@iogearbox.net>,
	"Andrii Nakryiko" <andrii@kernel.org>,
	"Song Liu" <song@kernel.org>
Cc: linux-fsdevel@vger.kernel.org, bpf@vger.kernel.org,
	linux-security-module@vger.kernel.org,
	linux-kernel@vger.kernel.org, "Günther Noack" <gnoack@google.com>,
	"Paul Moore" <paul@paul-moore.com>,
	"James Morris" <jmorris@namei.org>,
	"Serge E . Hallyn" <serge@hallyn.com>,
	"Martin KaFai Lau" <martin.lau@linux.dev>,
	"Eduard Zingerman" <eddyz87@gmail.com>,
	"Yonghong Song" <yonghong.song@linux.dev>,
	"John Fastabend" <john.fastabend@gmail.com>,
	"Kumar Kartikeya Dwivedi" <memxor@gmail.com>,
	"Jiri Olsa" <jolsa@kernel.org>,
	"Jeff Layton" <jlayton@kernel.org>,
	"Amir Goldstein" <amir73il@gmail.com>,
	"Mateusz Guzik" <mjguzik@gmail.com>,
	"Shuah Khan" <shuah@kernel.org>, "Tingmao Wang" <m@maowtm.org>,
	"Justin Suess" <utilityemal77@gmail.com>
Subject: [RFC PATCH bpf-next 05/12] namei: make vfs_walk_ancestors() stepwise
Date: Mon,  5 Oct 2026 20:20:12 -0400	[thread overview]
Message-ID: <20261006002020.2890858-6-utilityemal77@gmail.com> (raw)
In-Reply-To: <20261006002020.2890858-1-utilityemal77@gmail.com>

Restructure the walk into a stepwise engine - vfs_walk_start(),
vfs_walk_next(), vfs_walk_end() - private to fs/, so an iterating
consumer (BPF) can drive it with every step and invariant staying in
namei.c.  vfs_walk_ancestors() becomes a loop over it, preserving the
callback contract.

The position's flags move into the walk state, where the next step
needs them anyway: stepping off a disconnected position resumes at the
root of its mount.

Signed-off-by: Justin Suess <utilityemal77@gmail.com>
---
 fs/internal.h |  15 ++++++
 fs/namei.c    | 141 ++++++++++++++++++++++++++++++++++++--------------
 2 files changed, 117 insertions(+), 39 deletions(-)

diff --git a/fs/internal.h b/fs/internal.h
index c658c8a5ebd5..3ce2220ff57f 100644
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -71,6 +71,21 @@ struct dentry *start_dirop(struct dentry *parent, struct qstr *name,
 			   unsigned int lookup_flags);
 int lookup_noperm_common(struct qstr *qname, struct dentry *base);
 
+/*
+ * The stepwise engine under vfs_walk_ancestors(); fs-internal so iterating
+ * consumers (BPF) can drive it, with the walk invariants staying in namei.c.
+ */
+struct vfs_ancestor_walk {
+	struct path pos;
+	unsigned int pos_flags;	/* VFS_WALK_POS_* describing pos */
+	unsigned int flags;	/* VFS_WALK_* */
+};
+
+void vfs_walk_start(struct vfs_ancestor_walk *aw, const struct path *path,
+		    unsigned int flags);
+int vfs_walk_next(struct vfs_ancestor_walk *aw);
+void vfs_walk_end(struct vfs_ancestor_walk *aw);
+
 void __init filename_init(void);
 
 /*
diff --git a/fs/namei.c b/fs/namei.c
index 2e6ea19714b2..73f25152d917 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -2229,6 +2229,97 @@ static struct dentry *__path_walk_parent(struct path *path, const struct path *r
 	return dget(path->dentry);
 }
 
+static unsigned int vfs_walk_pos_flags(const struct vfsmount *mnt,
+				       const struct dentry *dentry)
+{
+	if (unlikely(IS_ROOT(dentry) && dentry != mnt->mnt_root))
+		return VFS_WALK_POS_DISCONNECTED;
+	return 0;
+}
+
+/* No boundary: ancestor walks go up to the real root. */
+static const struct path vfs_walk_no_root;
+
+/* Internal walk flag: the starting position has been yielded. */
+#define VFS_WALK_STARTED	BIT(31)
+
+/**
+ * vfs_walk_start - begin a stepwise ancestor walk
+ * @aw: walk state, valid until vfs_walk_end()
+ * @path: position to walk up from; never modified
+ * @flags: %VFS_WALK_* flags; none defined yet, pass 0
+ */
+void vfs_walk_start(struct vfs_ancestor_walk *aw, const struct path *path,
+		    unsigned int flags)
+{
+	aw->pos = *path;
+	aw->flags = flags;
+	aw->pos_flags = 0;
+	path_get(&aw->pos);
+}
+
+static int vfs_walk_step_ref(struct vfs_ancestor_walk *aw)
+{
+	struct dentry *parent;
+
+	if (unlikely(aw->pos_flags & VFS_WALK_POS_DISCONNECTED)) {
+		/* Resume at the root of the disconnected position's mount. */
+		dput(aw->pos.dentry);
+		aw->pos.dentry = dget(aw->pos.mnt->mnt_root);
+		aw->pos_flags = 0;
+		return 0;
+	}
+	parent = __path_walk_parent(&aw->pos, &vfs_walk_no_root,
+				    LOOKUP_BENEATH);
+	if (IS_ERR(parent))
+		/* The real root. */
+		return 1;
+	/*
+	 * A mount crossing can step onto a disconnected root, whose parent
+	 * is itself: only then is the mountpoint itself yielded, flagged.
+	 */
+	aw->pos_flags = parent == aw->pos.dentry ?
+		VFS_WALK_POS_DISCONNECTED | VFS_WALK_POS_MOUNTPOINT :
+		vfs_walk_pos_flags(aw->pos.mnt, parent);
+	dput(aw->pos.dentry);
+	aw->pos.dentry = parent;
+	return 0;
+}
+
+/**
+ * vfs_walk_next - yield the walk's next position in @aw->pos
+ * @aw: the walk
+ *
+ * The first call yields the starting position itself.  @aw->pos_flags
+ * carries the position's %VFS_WALK_POS_* flags, with the semantics
+ * described at vfs_walk_ancestors().
+ *
+ * Returns: 0 with @aw->pos valid, 1 once the walk has passed the real
+ * root.
+ */
+int vfs_walk_next(struct vfs_ancestor_walk *aw)
+{
+	if (aw->flags & VFS_WALK_STARTED) {
+		int err = vfs_walk_step_ref(aw);
+
+		if (err)
+			return err;
+	} else {
+		aw->flags |= VFS_WALK_STARTED;
+		aw->pos_flags = vfs_walk_pos_flags(aw->pos.mnt, aw->pos.dentry);
+	}
+	return 0;
+}
+
+/**
+ * vfs_walk_end - finish a stepwise ancestor walk
+ * @aw: the walk; its positions, including @aw->pos, become invalid
+ */
+void vfs_walk_end(struct vfs_ancestor_walk *aw)
+{
+	path_put(&aw->pos);
+}
+
 /**
  * vfs_walk_ancestors - invoke a callback on a path and each of its ancestors
  * @path: path to walk up from; the caller's path is never modified
@@ -2253,55 +2344,27 @@ int vfs_walk_ancestors(const struct path *path,
 				 unsigned int pos_flags, void *data),
 		       void *data, unsigned int flags)
 {
-	const struct path root = {};
-	struct path walk = *path;
-	unsigned int pos_flags = 0;
+	struct vfs_ancestor_walk aw;
 	int ret;
 
-	path_get(&walk);
-	if (unlikely(IS_ROOT(walk.dentry) &&
-		     walk.dentry != walk.mnt->mnt_root))
-		pos_flags = VFS_WALK_POS_DISCONNECTED;
+	vfs_walk_start(&aw, path, flags);
 	for (;;) {
-		struct dentry *parent;
-
-		ret = cb(&walk, pos_flags, data);
+		ret = vfs_walk_next(&aw);
+		if (ret) {
+			if (ret == 1)
+				/* The real root was reached. */
+				ret = 0;
+			break;
+		}
+		ret = cb(&aw.pos, aw.pos_flags, data);
 		if (ret < 0)
 			break;
 		if (ret == VFS_WALK_STOP) {
 			ret = 1;
 			break;
 		}
-
-		if (unlikely(pos_flags & VFS_WALK_POS_DISCONNECTED)) {
-			dput(walk.dentry);
-			walk.dentry = dget(walk.mnt->mnt_root);
-			pos_flags = 0;
-			continue;
-		}
-		parent = __path_walk_parent(&walk, &root, LOOKUP_BENEATH);
-		if (IS_ERR(parent)) {
-			/* The real root. */
-			ret = 0;
-			break;
-		}
-		/*
-		 * A mount crossing can step onto a disconnected root, whose
-		 * parent is itself: only then is the mountpoint itself
-		 * visited, flagged, next iteration.
-		 */
-		if (unlikely(parent == walk.dentry))
-			pos_flags = VFS_WALK_POS_DISCONNECTED |
-				    VFS_WALK_POS_MOUNTPOINT;
-		else if (unlikely(IS_ROOT(parent) &&
-				  parent != walk.mnt->mnt_root))
-			pos_flags = VFS_WALK_POS_DISCONNECTED;
-		else
-			pos_flags = 0;
-		dput(walk.dentry);
-		walk.dentry = parent;
 	}
-	path_put(&walk);
+	vfs_walk_end(&aw);
 	return ret;
 }
 
-- 
2.55.0


  parent reply	other threads:[~2026-10-06  0:20 UTC|newest]

Thread overview: 34+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-10-06  0:20 [RFC PATCH bpf-next 00/12] fs: unified VFS ancestor walk for Landlock and BPF Justin Suess
2026-10-06  0:20 ` [RFC PATCH bpf-next 01/12] namei: introduce __path_walk_parent() Justin Suess
2026-10-06  0:27   ` sashiko-bot
2026-10-06  0:20 ` [RFC PATCH bpf-next 02/12] namei: add vfs_walk_ancestors() Justin Suess
2026-10-06  0:30   ` sashiko-bot
2026-10-06  0:20 ` [RFC PATCH bpf-next 03/12] landlock: convert ancestor walk to vfs_walk_ancestors() Justin Suess
2026-10-06  0:27   ` sashiko-bot
2026-10-06  1:10   ` bot+bpf-ci
2026-10-06  0:20 ` [RFC PATCH bpf-next 04/12] bpf: mark struct path trusted Justin Suess
2026-10-06  0:34   ` sashiko-bot
2026-10-06  1:10   ` bot+bpf-ci
2026-10-06  0:20 ` Justin Suess [this message]
2026-10-06  0:30   ` [RFC PATCH bpf-next 05/12] namei: make vfs_walk_ancestors() stepwise sashiko-bot
2026-10-06  0:20 ` [RFC PATCH bpf-next 06/12] bpf: add a path ancestor iterator Justin Suess
2026-10-06  0:30   ` sashiko-bot
2026-10-06  1:11   ` bot+bpf-ci
2026-10-06  0:20 ` [RFC PATCH bpf-next 07/12] selftests/bpf: exercise the " Justin Suess
2026-10-06  0:28   ` sashiko-bot
2026-10-06  1:10   ` bot+bpf-ci
2026-10-06  0:20 ` [RFC PATCH bpf-next 08/12] fs: add mnt_undo_legitimize() Justin Suess
2026-10-06  0:28   ` sashiko-bot
2026-10-06  0:20 ` [RFC PATCH bpf-next 09/12] namei: add an rcu-walk mode to the ancestor walk Justin Suess
2026-10-06  0:33   ` sashiko-bot
2026-10-06  1:10   ` bot+bpf-ci
2026-10-06  0:20 ` [RFC PATCH bpf-next 10/12] bpf: support "__uninit" iterator arguments in generic kfuncs Justin Suess
2026-10-06  0:37   ` sashiko-bot
2026-10-06 14:58     ` Justin Suess
2026-10-06  0:20 ` [RFC PATCH bpf-next 11/12] bpf: add a lockless path ancestor iterator Justin Suess
2026-10-06  0:31   ` sashiko-bot
2026-10-06  1:10   ` bot+bpf-ci
2026-10-06 14:44     ` Justin Suess
2026-10-06  0:20 ` [RFC PATCH bpf-next 12/12] selftests/bpf: exercise the " Justin Suess
2026-10-06  0:25   ` sashiko-bot
2026-10-06  1:10   ` bot+bpf-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=20261006002020.2890858-6-utilityemal77@gmail.com \
    --to=utilityemal77@gmail.com \
    --cc=amir73il@gmail.com \
    --cc=andrii@kernel.org \
    --cc=ast@kernel.org \
    --cc=bpf@vger.kernel.org \
    --cc=brauner@kernel.org \
    --cc=daniel@iogearbox.net \
    --cc=eddyz87@gmail.com \
    --cc=gnoack@google.com \
    --cc=jack@suse.cz \
    --cc=jlayton@kernel.org \
    --cc=jmorris@namei.org \
    --cc=john.fastabend@gmail.com \
    --cc=jolsa@kernel.org \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-security-module@vger.kernel.org \
    --cc=m@maowtm.org \
    --cc=martin.lau@linux.dev \
    --cc=memxor@gmail.com \
    --cc=mic@digikod.net \
    --cc=mjguzik@gmail.com \
    --cc=neil@brown.name \
    --cc=paul@paul-moore.com \
    --cc=serge@hallyn.com \
    --cc=shuah@kernel.org \
    --cc=song@kernel.org \
    --cc=viro@zeniv.linux.org.uk \
    --cc=yonghong.song@linux.dev \
    /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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.