Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.31 as permitted sender) client-ip=23.128.96.31;
From:   Miklos Szeredi <mszeredi@redhat.com>
To:     linux-fsdevel@vger.kernel.org
Cc:     linux-kernel@vger.kernel.org, linux-api@vger.kernel.org,
        linux-man@vger.kernel.org, linux-security-module@vger.kernel.org,
        Karel Zak <kzak@redhat.com>, Ian Kent <raven@themaw.net>,
        David Howells <dhowells@redhat.com>,
        Linus Torvalds <torvalds@linux-foundation.org>,
        Al Viro <viro@zeniv.linux.org.uk>,
        Christian Brauner <christian@brauner.io>,
        Amir Goldstein <amir73il@gmail.com>
Subject: [RFC PATCH 1/3] add unique mount ID
Date:   Wed, 13 Sep 2023 17:22:34 +0200
Message-ID: <20230913152238.905247-2-mszeredi@redhat.com>
In-Reply-To: <20230913152238.905247-1-mszeredi@redhat.com>
References: <20230913152238.905247-1-mszeredi@redhat.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

If a mount is released then it's mnt_id can immediately be reused.  This is
bad news for user interfaces that want to uniquely identify a mount.

Implementing a unique mount ID is trivial (use a 64bit counter).
Unfortunately userspace assumes 32bit size and would overflow after the
counter reaches 2^32.

Introduce a new 64bit ID alongside the old one.  Allow new interfaces to
work on both the old and new IDs by starting the counter from 2^32.

Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
---
 fs/mount.h                | 3 ++-
 fs/namespace.c            | 4 ++++
 fs/stat.c                 | 9 +++++++--
 include/uapi/linux/stat.h | 1 +
 4 files changed, 14 insertions(+), 3 deletions(-)

diff --git a/fs/mount.h b/fs/mount.h
index 130c07c2f8d2..a14f762b3f29 100644
--- a/fs/mount.h
+++ b/fs/mount.h
@@ -72,7 +72,8 @@ struct mount {
 	struct fsnotify_mark_connector __rcu *mnt_fsnotify_marks;
 	__u32 mnt_fsnotify_mask;
 #endif
-	int mnt_id;			/* mount identifier */
+	int mnt_id;			/* mount identifier, reused */
+	u64 mnt_id_unique;		/* mount ID unique until reboot */
 	int mnt_group_id;		/* peer group identifier */
 	int mnt_expiry_mark;		/* true if marked for expiry */
 	struct hlist_head mnt_pins;
diff --git a/fs/namespace.c b/fs/namespace.c
index e157efc54023..de47c5f66e17 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -68,6 +68,9 @@ static u64 event;
 static DEFINE_IDA(mnt_id_ida);
 static DEFINE_IDA(mnt_group_ida);
 
+/* Don't allow confusion with mount ID allocated wit IDA */
+static atomic64_t mnt_id_ctr = ATOMIC64_INIT(1ULL << 32);
+
 static struct hlist_head *mount_hashtable __read_mostly;
 static struct hlist_head *mountpoint_hashtable __read_mostly;
 static struct kmem_cache *mnt_cache __read_mostly;
@@ -131,6 +134,7 @@ static int mnt_alloc_id(struct mount *mnt)
 	if (res < 0)
 		return res;
 	mnt->mnt_id = res;
+	mnt->mnt_id_unique = atomic64_inc_return(&mnt_id_ctr);
 	return 0;
 }
 
diff --git a/fs/stat.c b/fs/stat.c
index 6822ac77aec2..46d901b6b2de 100644
--- a/fs/stat.c
+++ b/fs/stat.c
@@ -280,8 +280,13 @@ static int vfs_statx(int dfd, struct filename *filename, int flags,
 
 	error = vfs_getattr(&path, stat, request_mask, flags);
 
-	stat->mnt_id = real_mount(path.mnt)->mnt_id;
-	stat->result_mask |= STATX_MNT_ID;
+	if (request_mask & STATX_MNT_ID_UNIQUE) {
+		stat->mnt_id = real_mount(path.mnt)->mnt_id_unique;
+		stat->result_mask |= STATX_MNT_ID_UNIQUE;
+	} else {
+		stat->mnt_id = real_mount(path.mnt)->mnt_id;
+		stat->result_mask |= STATX_MNT_ID;
+	}
 
 	if (path.mnt->mnt_root == path.dentry)
 		stat->attributes |= STATX_ATTR_MOUNT_ROOT;
diff --git a/include/uapi/linux/stat.h b/include/uapi/linux/stat.h
index 7cab2c65d3d7..2f2ee82d5517 100644
--- a/include/uapi/linux/stat.h
+++ b/include/uapi/linux/stat.h
@@ -154,6 +154,7 @@ struct statx {
 #define STATX_BTIME		0x00000800U	/* Want/got stx_btime */
 #define STATX_MNT_ID		0x00001000U	/* Got stx_mnt_id */
 #define STATX_DIOALIGN		0x00002000U	/* Want/got direct I/O alignment info */
+#define STATX_MNT_ID_UNIQUE	0x00004000U	/* Want/got extended stx_mount_id */
 
 #define STATX__RESERVED		0x80000000U	/* Reserved for future struct statx expansion */
 
-- 
2.41.0