Skip to contentSkip to conversation

af_unix: Remove spin_lock_nested() and convert to lock_cmp_fn.

PATCH Superseded Kuniyuki Iwashima 2 participants 13 messages Jun 14, 2024 – Jun 18, 2024

Subsystems (3)

v3 of 4 Superseded Latest is v4 →

lore
Share & tools
lore
#0 lore raw

v3 cover af_unix: Remove spin_lock_nested() and convert to lock_cmp_fn.

This series removes spin_lock_nested() in AF_UNIX and instead defines the locking orders as functions tied to each lock by lockdep_set_lock_cmp_fn().

When the defined function returns a negative value, lockdep considers it will not cause deadlock. (See ->cmp_fn() in check_deadlock() and check_prev_add().)

When we cannot define the total ordering, we return -1 for the allowed ordering and otherwise 0 as undefined. [0]

[0]: https://lore.kernel.org/netdev/thzkgbuwuo3knevpipu4rzsh5qgmwhklihypdgziiruabvh46f@uwdkpcfxgloo/

Changes:
v3:
* Patch 3
* Cache sk->sk_state
* s/unix_state_lock()/unix_state_unlock()/
* Patch 8
* Add embryo -> listener locking order

v2: https://lore.kernel.org/netdev/[email protected]/
* Patch 1 & 2
* Use (((l) > (r)) - ((l) < (r))) for comparison

v1: https://lore.kernel.org/netdev/[email protected]/

Kuniyuki Iwashima (11):
af_unix: Define locking order for unix_table_double_lock().
af_unix: Define locking order for U_LOCK_SECOND in
unix_state_double_lock().
af_unix: Don't retry after unix_state_lock_nested() in
unix_stream_connect().
af_unix: Define locking order for U_LOCK_SECOND in
unix_stream_connect().
af_unix: Don't acquire unix_state_lock() for sock_i_ino().
af_unix: Remove U_LOCK_DIAG.
af_unix: Remove U_LOCK_GC_LISTENER.
af_unix: Define locking order for U_RECVQ_LOCK_EMBRYO in

    unix_collect_skb().

af_unix: Set sk_peer_pid/sk_peer_cred locklessly for new socket.
af_unix: Remove put_pid()/put_cred() in copy_peercred().
af_unix: Don't use spin_lock_nested() in copy_peercred().

 include/net/af_unix.h |  14 -----
 net/unix/af_unix.c    | 139 +++++++++++++++++++++++++++---------------
 net/unix/diag.c       |  47 ++++----------
 net/unix/garbage.c    |   8 +--
 4 files changed, 105 insertions(+), 103 deletions(-)
Signature · 1 line
2.30.2
#1 lore raw

PATCH v3 1/11 af_unix: Define locking order for unix_table_double_lock().

When created, AF_UNIX socket is put into net->unx.table.buckets[], and the hash is stored in sk->sk_hash.

* unbound socket : 0 <= sk_hash <= UNIX_HASH_MOD

When bind() is called, the socket could be moved to another bucket.

* pathname socket : 0 <= sk_hash <= UNIX_HASH_MOD
* abstract socket : UNIX_HASH_MOD + 1 <= sk_hash <= UNIX_HASH_MOD * 2 + 1

Then, we call unix_table_double_lock() which locks a single bucket or two.

Let's define the order as unix_table_lock_cmp_fn() instead of using spin_lock_nested().

The locking is always done in ascending order of sk->sk_hash, which is the index of buckets/locks array allocated by kvmalloc_array().

sk_hash_A < sk_hash_B
<=> &locks[sk_hash_A].dep_map < &locks[sk_hash_B].dep_map

So, the relation of two sk->sk_hash can be derived from the addresses of dep_map in the array of locks.

---
 net/unix/af_unix.c | 12 +++++++++++-
 1 file changed, 11 insertions(+), 1 deletion(-)
net/unix/af_unix.c +11 -1
index e9c941e6a464..7889d4723959 100644
@@ -126,6 +126,15 @@ static spinlock_t bsd_socket_locks[UNIX_HASH_SIZE / 2];
  *    hash table is protected with spinlock.
  *    each socket state is protected by separate spinlock.
  */
+#ifdef CONFIG_PROVE_LOCKING
+#define cmp_ptr(l, r)	(((l) > (r)) - ((l) < (r)))
+
+static int unix_table_lock_cmp_fn(const struct lockdep_map *a,
+				  const struct lockdep_map *b)
+{
+	return cmp_ptr(a, b);
+}
+#endif
 
 static unsigned int unix_unbound_hash(struct sock *sk)
 {
@@ -168,7 +177,7 @@ static void unix_table_double_lock(struct net *net,
 		swap(hash1, hash2);
 
 	spin_lock(&net->unx.table.locks[hash1]);
-	spin_lock_nested(&net->unx.table.locks[hash2], SINGLE_DEPTH_NESTING);
+	spin_lock(&net->unx.table.locks[hash2]);
 }
 
 static void unix_table_double_unlock(struct net *net,
@@ -3578,6 +3587,7 @@ static int __net_init unix_net_init(struct net *net)
 
 	for (i = 0; i < UNIX_HASH_SIZE; i++) {
 		spin_lock_init(&net->unx.table.locks[i]);
+		lock_set_cmp_fn(&net->unx.table.locks[i], unix_table_lock_cmp_fn, NULL);
 		INIT_HLIST_HEAD(&net->unx.table.buckets[i]);
 	}
 
Signature · 1 line
2.30.2
#2 lore raw

PATCH v3 2/11 af_unix: Define locking order for U_LOCK_SECOND in unix_state_double_lock().

In reply to Kuniyuki Iwashima

unix_dgram_connect() and unix_dgram_{send,recv}msg() lock the socket and peer in ascending order of the socket address.

Let's define the order as unix_state_lock_cmp_fn() instead of using unix_state_lock_nested().

---
 net/unix/af_unix.c | 16 +++++++++++++++-
 1 file changed, 15 insertions(+), 1 deletion(-)
net/unix/af_unix.c +15 -1
index 7889d4723959..0657f599bbef 100644
@@ -134,6 +134,18 @@ static int unix_table_lock_cmp_fn(const struct lockdep_map *a,
 {
 	return cmp_ptr(a, b);
 }
+
+static int unix_state_lock_cmp_fn(const struct lockdep_map *_a,
+				  const struct lockdep_map *_b)
+{
+	const struct unix_sock *a, *b;
+
+	a = container_of(_a, struct unix_sock, lock.dep_map);
+	b = container_of(_b, struct unix_sock, lock.dep_map);
+
+	/* unix_state_double_lock(): ascending address order. */
+	return cmp_ptr(a, b);
+}
 #endif
 
 static unsigned int unix_unbound_hash(struct sock *sk)
@@ -987,6 +999,7 @@ static struct sock *unix_create1(struct net *net, struct socket *sock, int kern,
 	u->path.dentry = NULL;
 	u->path.mnt = NULL;
 	spin_lock_init(&u->lock);
+	lock_set_cmp_fn(&u->lock, unix_state_lock_cmp_fn, NULL);
 	mutex_init(&u->iolock); /* single task reading lock */
 	mutex_init(&u->bindlock); /* single task binding lock */
 	init_waitqueue_head(&u->peer_wait);
@@ -1335,11 +1348,12 @@ static void unix_state_double_lock(struct sock *sk1, struct sock *sk2)
 		unix_state_lock(sk1);
 		return;
 	}
+
 	if (sk1 > sk2)
 		swap(sk1, sk2);
 
 	unix_state_lock(sk1);
-	unix_state_lock_nested(sk2, U_LOCK_SECOND);
+	unix_state_lock(sk2);
 }
 
 static void unix_state_double_unlock(struct sock *sk1, struct sock *sk2)
Signature · 1 line
2.30.2
#3 lore raw

PATCH v3 3/11 af_unix: Don't retry after unix_state_lock_nested() in unix_stream_connect().

In reply to Kuniyuki Iwashima

When a SOCK_(STREAM|SEQPACKET) socket connect()s to another one, we need to lock the two sockets to check their states in unix_stream_connect().

We use unix_state_lock() for the server and unix_state_lock_nested() for client with tricky sk->sk_state check to avoid deadlock.

The possible deadlock scenario are the following:

1) Self connect()
2) Simultaneous connect()

The former is simple, attempt to grab the same lock, and the latter is AB-BA deadlock.

After the server's unix_state_lock(), we check the server socket's state, and if it's not TCP_LISTEN, connect() fails with -EINVAL.

Then, we avoid the former deadlock by checking the client's state before unix_state_lock_nested(). If its state is not TCP_LISTEN, we can make sure that the client and the server are not identical based on the state.

Also, the latter deadlock can be avoided in the same way. Due to the server sk->sk_state requirement, AB-BA deadlock could happen only with TCP_LISTEN sockets. So, if the client's state is TCP_LISTEN, we can give up the second lock to avoid the deadlock.

  CPU 1                 CPU 2                  CPU 3
  connect(A -> B)       connect(B -> A)        listen(A)
  ---                   ---                    ---
  unix_state_lock(B)
  B->sk_state == TCP_LISTEN
  READ_ONCE(A->sk_state) == TCP_CLOSE
                            ^^^^^^^^^
                            ok, will lock A    unix_state_lock(A)
             .--------------'                  WRITE_ONCE(A->sk_state, TCP_LISTEN)
             |                                 unix_state_unlock(A)
             |
             |          unix_state_lock(A)
             |          A->sk_sk_state == TCP_LISTEN
             |          READ_ONCE(B->sk_state) == TCP_LISTEN
             v                                    ^^^^^^^^^^

unix_state_lock_nested(A) Don't lock B !!

Currently, while checking the client's state, we also check if it's TCP_ESTABLISHED, but this is unlikely and can be checked after we know the state is not TCP_CLOSE.

Moreover, if it happens after the second lock, we now jump to the restart label, but it's unlikely that the server is not found during the retry, so the jump is mostly to revist the client state check.

Let's remove the retry logic and check the state against TCP_CLOSE first.

---
 net/unix/af_unix.c | 34 +++++++++-------------------------
 1 file changed, 9 insertions(+), 25 deletions(-)
net/unix/af_unix.c +9 -25
index 0657f599bbef..88f2c5d039c4 100644
@@ -1496,6 +1496,7 @@ static int unix_stream_connect(struct socket *sock, struct sockaddr *uaddr,
 	struct unix_sock *u = unix_sk(sk), *newu, *otheru;
 	struct net *net = sock_net(sk);
 	struct sk_buff *skb = NULL;
+	unsigned char state;
 	long timeo;
 	int err;
 
@@ -1546,7 +1547,6 @@ static int unix_stream_connect(struct socket *sock, struct sockaddr *uaddr,
 		goto out;
 	}
 
-	/* Latch state of peer */
 	unix_state_lock(other);
 
 	/* Apparently VFS overslept socket death. Retry. */
@@ -1576,37 +1576,21 @@ static int unix_stream_connect(struct socket *sock, struct sockaddr *uaddr,
 		goto restart;
 	}
 
-	/* Latch our state.
-
-	   It is tricky place. We need to grab our state lock and cannot
-	   drop lock on peer. It is dangerous because deadlock is
-	   possible. Connect to self case and simultaneous
-	   attempt to connect are eliminated by checking socket
-	   state. other is TCP_LISTEN, if sk is TCP_LISTEN we
-	   check this before attempt to grab lock.
-
-	   Well, and we have to recheck the state after socket locked.
+	/* self connect and simultaneous connect are eliminated
+	 * by rejecting TCP_LISTEN socket to avoid deadlock.
 	 */
-	switch (READ_ONCE(sk->sk_state)) {
-	case TCP_CLOSE:
-		/* This is ok... continue with connect */
-		break;
-	case TCP_ESTABLISHED:
-		/* Socket is already connected */
-		err = -EISCONN;
-		goto out_unlock;
-	default:
-		err = -EINVAL;
+	state = READ_ONCE(sk->sk_state);
+	if (unlikely(state != TCP_CLOSE)) {
+		err = state == TCP_ESTABLISHED ? -EISCONN : -EINVAL;
 		goto out_unlock;
 	}
 
 	unix_state_lock_nested(sk, U_LOCK_SECOND);
 
-	if (sk->sk_state != TCP_CLOSE) {
+	if (unlikely(sk->sk_state != TCP_CLOSE)) {
+		err = sk->sk_state == TCP_ESTABLISHED ? -EISCONN : -EINVAL;
 		unix_state_unlock(sk);
-		unix_state_unlock(other);
-		sock_put(other);
-		goto restart;
+		goto out_unlock;
 	}
 
 	err = security_unix_stream_connect(sk, other, newsk);
Signature · 1 line
2.30.2
#4 lore raw

PATCH v3 4/11 af_unix: Define locking order for U_LOCK_SECOND in unix_stream_connect().

In reply to Kuniyuki Iwashima

While a SOCK_(STREAM|SEQPACKET) socket connect()s to another, we hold two locks of them by unix_state_lock() and unix_state_lock_nested() in unix_stream_connect().

Before unix_state_lock_nested(), the following is guaranteed by checking sk->sk_state:

1. The first socket is TCP_LISTEN
2. The second socket is not the first one
3. Simultaneous connect() must fail

So, the client state can be TCP_CLOSE or TCP_LISTEN or TCP_ESTABLISHED.

Let's define the expected states as unix_state_lock_cmp_fn() instead of using unix_state_lock_nested().

Note that 2. is detected by debug_spin_lock_before() and 3. cannot be expressed as lock_cmp_fn.

---
 include/net/af_unix.h |  1 -
 net/unix/af_unix.c    | 26 +++++++++++++++++++++++++-
 2 files changed, 25 insertions(+), 2 deletions(-)
include/net/af_unix.h +0 -1
index b6eedf7650da..fd813ad73ab8 100644
@@ -98,7 +98,6 @@ struct unix_sock {
 #define unix_state_unlock(s)	spin_unlock(&unix_sk(s)->lock)
 enum unix_socket_lock_class {
 	U_LOCK_NORMAL,
-	U_LOCK_SECOND,	/* for double locking, see unix_state_double_lock(). */
 	U_LOCK_DIAG, /* used while dumping icons, see sk_diag_dump_icons(). */
 	U_LOCK_GC_LISTENER, /* used for listening socket while determining gc
 			     * candidates to close a small race window.
net/unix/af_unix.c +25 -1
index 88f2c5d039c4..5d2728e33f3f 100644
@@ -143,6 +143,30 @@ static int unix_state_lock_cmp_fn(const struct lockdep_map *_a,
 	a = container_of(_a, struct unix_sock, lock.dep_map);
 	b = container_of(_b, struct unix_sock, lock.dep_map);
 
+	if (a->sk.sk_state == TCP_LISTEN) {
+		/* unix_stream_connect(): Before the 2nd unix_state_lock(),
+		 *
+		 *   1. a is TCP_LISTEN.
+		 *   2. b is not a.
+		 *   3. concurrent connect(b -> a) must fail.
+		 *
+		 * Except for 2. & 3., the b's state can be any possible
+		 * value due to concurrent connect() or listen().
+		 *
+		 * 2. is detected in debug_spin_lock_before(), and 3. cannot
+		 * be expressed as lock_cmp_fn.
+		 */
+		switch (b->sk.sk_state) {
+		case TCP_CLOSE:
+		case TCP_ESTABLISHED:
+		case TCP_LISTEN:
+			return -1;
+		default:
+			/* Invalid case. */
+			return 0;
+		}
+	}
+
 	/* unix_state_double_lock(): ascending address order. */
 	return cmp_ptr(a, b);
 }
@@ -1585,7 +1609,7 @@ static int unix_stream_connect(struct socket *sock, struct sockaddr *uaddr,
 		goto out_unlock;
 	}
 
-	unix_state_lock_nested(sk, U_LOCK_SECOND);
+	unix_state_lock(sk);
 
 	if (unlikely(sk->sk_state != TCP_CLOSE)) {
 		err = sk->sk_state == TCP_ESTABLISHED ? -EISCONN : -EINVAL;
Signature · 1 line
2.30.2
maintainer
#5 lore raw

Re: [PATCH v3 net-next 04/11] af_unix: Define locking order for U_LOCK_SECOND in unix_stream_connect().

Quoted 57 lines · Kuniyuki Iwashima

While a SOCK_(STREAM|SEQPACKET) socket connect()s to another, we hold two locks of them by unix_state_lock() and unix_state_lock_nested() in unix_stream_connect().

Before unix_state_lock_nested(), the following is guaranteed by checking sk->sk_state:

1. The first socket is TCP_LISTEN
2. The second socket is not the first one
3. Simultaneous connect() must fail

So, the client state can be TCP_CLOSE or TCP_LISTEN or TCP_ESTABLISHED.

Let's define the expected states as unix_state_lock_cmp_fn() instead of using unix_state_lock_nested().

Note that 2. is detected by debug_spin_lock_before() and 3. cannot be expressed as lock_cmp_fn.

---
 include/net/af_unix.h |  1 -
 net/unix/af_unix.c    | 26 +++++++++++++++++++++++++-
 2 files changed, 25 insertions(+), 2 deletions(-)
include/net/af_unix.h +0 -1
index b6eedf7650da..fd813ad73ab8 100644
@@ -98,7 +98,6 @@ struct unix_sock {
 #define unix_state_unlock(s)	spin_unlock(&unix_sk(s)->lock)
 enum unix_socket_lock_class {
 	U_LOCK_NORMAL,
-	U_LOCK_SECOND,	/* for double locking, see unix_state_double_lock(). */
 	U_LOCK_DIAG, /* used while dumping icons, see sk_diag_dump_icons(). */
 	U_LOCK_GC_LISTENER, /* used for listening socket while determining gc
 			     * candidates to close a small race window.
net/unix/af_unix.c +12 -0
index 88f2c5d039c4..5d2728e33f3f 100644
@@ -143,6 +143,30 @@ static int unix_state_lock_cmp_fn(const struct lockdep_map *_a,
 	a = container_of(_a, struct unix_sock, lock.dep_map);
 	b = container_of(_b, struct unix_sock, lock.dep_map);
 
+	if (a->sk.sk_state == TCP_LISTEN) {
+		/* unix_stream_connect(): Before the 2nd unix_state_lock(),
+		 *
+		 *   1. a is TCP_LISTEN.
+		 *   2. b is not a.
+		 *   3. concurrent connect(b -> a) must fail.
+		 *
+		 * Except for 2. & 3., the b's state can be any possible
+		 * value due to concurrent connect() or listen().
+		 *
+		 * 2. is detected in debug_spin_lock_before(), and 3. cannot
+		 * be expressed as lock_cmp_fn.

net/unix/af_unix.c static int unix_state_lock_cmp_fn(const struct lockdep_map *_a, · line 167

Quoted 10 lines
net/unix/af_unix.c +10 -0
+		 */
+		switch (b->sk.sk_state) {
+		case TCP_CLOSE:
+		case TCP_ESTABLISHED:
+		case TCP_LISTEN:
+			return -1;
+		default:
+			/* Invalid case. */
+			return 0;
+		}

I'm sorry for missing this before, but I'm wondering if we need to enforce even this case to be symmetric? that is, explicitly check for b state == TCP_LISTEN, ...

Kent, WDYT?

Thanks!

Paolo

#6 lore raw

PATCH v3 5/11 af_unix: Don't acquire unix_state_lock() for sock_i_ino().

In reply to Kuniyuki Iwashima

sk_diag_dump_peer() and sk_diag_dump() call unix_state_lock() for sock_i_ino() which reads SOCK_INODE(sk->sk_socket)->i_ino, but it's protected by sk->sk_callback_lock.

Let's remove unnecessary unix_state_lock().

---
 net/unix/diag.c | 30 ++++++++++--------------------
 1 file changed, 10 insertions(+), 20 deletions(-)
net/unix/diag.c +10 -20
index 937edf4afed4..d2d66727b0da 100644
@@ -47,9 +47,7 @@ static int sk_diag_dump_peer(struct sock *sk, struct sk_buff *nlskb)
 
 	peer = unix_peer_get(sk);
 	if (peer) {
-		unix_state_lock(peer);
 		ino = sock_i_ino(peer);
-		unix_state_unlock(peer);
 		sock_put(peer);
 
 		return nla_put_u32(nlskb, UNIX_DIAG_PEER, ino);
@@ -180,22 +178,6 @@ static int sk_diag_fill(struct sock *sk, struct sk_buff *skb, struct unix_diag_r
 	return -EMSGSIZE;
 }
 
-static int sk_diag_dump(struct sock *sk, struct sk_buff *skb, struct unix_diag_req *req,
-			struct user_namespace *user_ns,
-			u32 portid, u32 seq, u32 flags)
-{
-	int sk_ino;
-
-	unix_state_lock(sk);
-	sk_ino = sock_i_ino(sk);
-	unix_state_unlock(sk);
-
-	if (!sk_ino)
-		return 0;
-
-	return sk_diag_fill(sk, skb, req, user_ns, portid, seq, flags, sk_ino);
-}
-
 static int unix_diag_dump(struct sk_buff *skb, struct netlink_callback *cb)
 {
 	struct net *net = sock_net(skb->sk);
@@ -213,14 +195,22 @@ static int unix_diag_dump(struct sk_buff *skb, struct netlink_callback *cb)
 		num = 0;
 		spin_lock(&net->unx.table.locks[slot]);
 		sk_for_each(sk, &net->unx.table.buckets[slot]) {
+			int sk_ino;
+
 			if (num < s_num)
 				goto next;
+
 			if (!(req->udiag_states & (1 << READ_ONCE(sk->sk_state))))
 				goto next;
-			if (sk_diag_dump(sk, skb, req, sk_user_ns(skb->sk),
+
+			sk_ino = sock_i_ino(sk);
+			if (!sk_ino)
+				goto next;
+
+			if (sk_diag_fill(sk, skb, req, sk_user_ns(skb->sk),
 					 NETLINK_CB(cb->skb).portid,
 					 cb->nlh->nlmsg_seq,
-					 NLM_F_MULTI) < 0) {
+					 NLM_F_MULTI, sk_ino) < 0) {
 				spin_unlock(&net->unx.table.locks[slot]);
 				goto done;
 			}
Signature · 1 line
2.30.2
#7 lore raw

PATCH v3 6/11 af_unix: Remove U_LOCK_DIAG.

In reply to Kuniyuki Iwashima

sk_diag_dump_icons() acquires embryo's lock by unix_state_lock_nested() to fetch its peer.

The embryo's ->peer is set to NULL only when its parent listener is close()d. Then, unix_release_sock() is called for each embryo after unlinking skb by skb_dequeue().

In sk_diag_dump_icons(), we hold the parent's recvq lock, so we need not acquire unix_state_lock_nested(), and peer is always non-NULL.

Let's remove unnecessary unix_state_lock_nested() and non-NULL test for peer.

---
 include/net/af_unix.h |  1 -
 net/unix/diag.c       | 17 +++--------------
 2 files changed, 3 insertions(+), 15 deletions(-)
include/net/af_unix.h +0 -1
index fd813ad73ab8..c42645199cee 100644
@@ -98,7 +98,6 @@ struct unix_sock {
 #define unix_state_unlock(s)	spin_unlock(&unix_sk(s)->lock)
 enum unix_socket_lock_class {
 	U_LOCK_NORMAL,
-	U_LOCK_DIAG, /* used while dumping icons, see sk_diag_dump_icons(). */
 	U_LOCK_GC_LISTENER, /* used for listening socket while determining gc
 			     * candidates to close a small race window.
 			     */
net/unix/diag.c +3 -14
index d2d66727b0da..9138af8b465e 100644
@@ -73,20 +73,9 @@ static int sk_diag_dump_icons(struct sock *sk, struct sk_buff *nlskb)
 
 		buf = nla_data(attr);
 		i = 0;
-		skb_queue_walk(&sk->sk_receive_queue, skb) {
-			struct sock *req, *peer;
-
-			req = skb->sk;
-			/*
-			 * The state lock is outer for the same sk's
-			 * queue lock. With the other's queue locked it's
-			 * OK to lock the state.
-			 */
-			unix_state_lock_nested(req, U_LOCK_DIAG);
-			peer = unix_sk(req)->peer;
-			buf[i++] = (peer ? sock_i_ino(peer) : 0);
-			unix_state_unlock(req);
-		}
+		skb_queue_walk(&sk->sk_receive_queue, skb)
+			buf[i++] = sock_i_ino(unix_peer(skb->sk));
+
 		spin_unlock(&sk->sk_receive_queue.lock);
 	}
 
Signature · 1 line
2.30.2
#8 lore raw

PATCH v3 7/11 af_unix: Remove U_LOCK_GC_LISTENER.

In reply to Kuniyuki Iwashima

Commit 1971d13ffa84 ("af_unix: Suppress false-positive lockdep splat for spin_lock() in __unix_gc().") added U_LOCK_GC_LISTENER for the old GC, but it's no longer needed for the new GC.

Let's remove U_LOCK_GC_LISTENER and unix_state_lock_nested() as there's no user.

---
 include/net/af_unix.h | 12 ------------
 1 file changed, 12 deletions(-)
include/net/af_unix.h +0 -12
index c42645199cee..63129c79b8cb 100644
@@ -96,18 +96,6 @@ struct unix_sock {
 
 #define unix_state_lock(s)	spin_lock(&unix_sk(s)->lock)
 #define unix_state_unlock(s)	spin_unlock(&unix_sk(s)->lock)
-enum unix_socket_lock_class {
-	U_LOCK_NORMAL,
-	U_LOCK_GC_LISTENER, /* used for listening socket while determining gc
-			     * candidates to close a small race window.
-			     */
-};
-
-static inline void unix_state_lock_nested(struct sock *sk,
-				   enum unix_socket_lock_class subclass)
-{
-	spin_lock_nested(&unix_sk(sk)->lock, subclass);
-}
 
 #define peer_wait peer_wq.wait
 
Signature · 1 line
2.30.2
#9 lore raw

PATCH v3 8/11 af_unix: Define locking order for U_RECVQ_LOCK_EMBRYO in unix_collect_skb().

In reply to Kuniyuki Iwashima

While GC is cleaning up cyclic references by SCM_RIGHTS, unix_collect_skb() collects skb in the socket's recvq.

If the socket is TCP_LISTEN, we need to collect skb in the embryo's queue. Then, both the listener's recvq lock and the embroy's one are held.

The locking is always done in the listener -> embryo order.

Let's define it as unix_recvq_lock_cmp_fn() instead of using spin_lock_nested().

Note that the reverse order is defined for consistency.

---
 net/unix/af_unix.c | 20 ++++++++++++++++++++
 net/unix/garbage.c |  8 +-------
 2 files changed, 21 insertions(+), 7 deletions(-)
net/unix/af_unix.c +20 -0
index 5d2728e33f3f..9bbd112926ad 100644
@@ -170,6 +170,24 @@ static int unix_state_lock_cmp_fn(const struct lockdep_map *_a,
 	/* unix_state_double_lock(): ascending address order. */
 	return cmp_ptr(a, b);
 }
+
+static int unix_recvq_lock_cmp_fn(const struct lockdep_map *_a,
+				  const struct lockdep_map *_b)
+{
+	const struct sock *a, *b;
+
+	a = container_of(_a, struct sock, sk_receive_queue.lock.dep_map);
+	b = container_of(_b, struct sock, sk_receive_queue.lock.dep_map);
+
+	/* unix_collect_skb(): listener -> embryo order. */
+	if (a->sk_state == TCP_LISTEN && unix_sk(b)->listener == a)
+		return -1;
+
+	if (b->sk_state == TCP_LISTEN && unix_sk(a)->listener == b)
+		return 1;
+
+	return 0;
+}
 #endif
 
 static unsigned int unix_unbound_hash(struct sock *sk)
@@ -1017,6 +1035,8 @@ static struct sock *unix_create1(struct net *net, struct socket *sock, int kern,
 	sk->sk_write_space	= unix_write_space;
 	sk->sk_max_ack_backlog	= READ_ONCE(net->unx.sysctl_max_dgram_qlen);
 	sk->sk_destruct		= unix_sock_destructor;
+	lock_set_cmp_fn(&sk->sk_receive_queue.lock, unix_recvq_lock_cmp_fn, NULL);
+
 	u = unix_sk(sk);
 	u->listener = NULL;
 	u->vertex = NULL;
net/unix/garbage.c +1 -7
index dfe94a90ece4..eb8aa5171a68 100644
@@ -337,11 +337,6 @@ static bool unix_vertex_dead(struct unix_vertex *vertex)
 	return true;
 }
 
-enum unix_recv_queue_lock_class {
-	U_RECVQ_LOCK_NORMAL,
-	U_RECVQ_LOCK_EMBRYO,
-};
-
 static void unix_collect_queue(struct unix_sock *u, struct sk_buff_head *hitlist)
 {
 	skb_queue_splice_init(&u->sk.sk_receive_queue, hitlist);
@@ -375,8 +370,7 @@ static void unix_collect_skb(struct list_head *scc, struct sk_buff_head *hitlist
 			skb_queue_walk(queue, skb) {
 				struct sk_buff_head *embryo_queue = &skb->sk->sk_receive_queue;
 
-				/* listener -> embryo order, the inversion never happens. */
-				spin_lock_nested(&embryo_queue->lock, U_RECVQ_LOCK_EMBRYO);
+				spin_lock(&embryo_queue->lock);
 				unix_collect_queue(unix_sk(skb->sk), hitlist);
 				spin_unlock(&embryo_queue->lock);
 			}
Signature · 1 line
2.30.2
#10 lore raw

PATCH v3 9/11 af_unix: Set sk_peer_pid/sk_peer_cred locklessly for new socket.

In reply to Kuniyuki Iwashima

init_peercred() is called in 3 places:

1. socketpair() : both sockets
2. connect() : child socket
3. listen() : listening socket

The first two need not hold sk_peer_lock because no one can touch the socket.

Let's set cred/pid without holding lock for the two cases and rename the old init_peercred() to update_peercred() to properly reflect the use case.

---
 net/unix/af_unix.c | 11 ++++++++---
 1 file changed, 8 insertions(+), 3 deletions(-)
net/unix/af_unix.c +8 -3
index 9bbd112926ad..3c62fb4f3df5 100644
@@ -738,6 +738,12 @@ static void unix_release_sock(struct sock *sk, int embrion)
 }
 
 static void init_peercred(struct sock *sk)
+{
+	sk->sk_peer_pid = get_pid(task_tgid(current));
+	sk->sk_peer_cred = get_current_cred();
+}
+
+static void update_peercred(struct sock *sk)
 {
 	const struct cred *old_cred;
 	struct pid *old_pid;
@@ -745,8 +751,7 @@ static void init_peercred(struct sock *sk)
 	spin_lock(&sk->sk_peer_lock);
 	old_pid = sk->sk_peer_pid;
 	old_cred = sk->sk_peer_cred;
-	sk->sk_peer_pid  = get_pid(task_tgid(current));
-	sk->sk_peer_cred = get_current_cred();
+	init_peercred(sk);
 	spin_unlock(&sk->sk_peer_lock);
 
 	put_pid(old_pid);
@@ -798,7 +803,7 @@ static int unix_listen(struct socket *sock, int backlog)
 	WRITE_ONCE(sk->sk_state, TCP_LISTEN);
 
 	/* set credentials so connect can copy them */
-	init_peercred(sk);
+	update_peercred(sk);
 	err = 0;
 
 out_unlock:
Signature · 1 line
2.30.2
#11 lore raw

PATCH v3 10/11 af_unix: Remove put_pid()/put_cred() in copy_peercred().

In reply to Kuniyuki Iwashima

When (AF_UNIX, SOCK_STREAM) socket connect()s to a listening socket, the listener's sk_peer_pid/sk_peer_cred are copied to the client in copy_peercred().

Then, the client's sk_peer_pid and sk_peer_cred are always NULL, so we need not call put_pid() and put_cred() there.

---
 net/unix/af_unix.c | 9 +--------
 1 file changed, 1 insertion(+), 8 deletions(-)
net/unix/af_unix.c +1 -8
index 3c62fb4f3df5..c828022128ec 100644
@@ -760,9 +760,6 @@ static void update_peercred(struct sock *sk)
 
 static void copy_peercred(struct sock *sk, struct sock *peersk)
 {
-	const struct cred *old_cred;
-	struct pid *old_pid;
-
 	if (sk < peersk) {
 		spin_lock(&sk->sk_peer_lock);
 		spin_lock_nested(&peersk->sk_peer_lock, SINGLE_DEPTH_NESTING);
@@ -770,16 +767,12 @@ static void copy_peercred(struct sock *sk, struct sock *peersk)
 		spin_lock(&peersk->sk_peer_lock);
 		spin_lock_nested(&sk->sk_peer_lock, SINGLE_DEPTH_NESTING);
 	}
-	old_pid = sk->sk_peer_pid;
-	old_cred = sk->sk_peer_cred;
+
 	sk->sk_peer_pid  = get_pid(peersk->sk_peer_pid);
 	sk->sk_peer_cred = get_cred(peersk->sk_peer_cred);
 
 	spin_unlock(&sk->sk_peer_lock);
 	spin_unlock(&peersk->sk_peer_lock);
-
-	put_pid(old_pid);
-	put_cred(old_cred);
 }
 
 static int unix_listen(struct socket *sock, int backlog)
Signature · 1 line
2.30.2
#12 lore raw

PATCH v3 11/11 af_unix: Don't use spin_lock_nested() in copy_peercred().

In reply to Kuniyuki Iwashima

When (AF_UNIX, SOCK_STREAM) socket connect()s to a listening socket, the listener's sk_peer_pid/sk_peer_cred are copied to the client in copy_peercred().

Then, two sk_peer_locks are held there; one is client's and another is listener's.

However, the latter is not needed because we hold the listner's unix_state_lock() there and unix_listen() cannot update the cred concurrently.

Let's drop the unnecessary spin_lock() and use the bare spin_lock() for the client to protect concurrent read by getsockopt(SO_PEERCRED).

---
 net/unix/af_unix.c | 13 +++----------
 1 file changed, 3 insertions(+), 10 deletions(-)
net/unix/af_unix.c +3 -10
index c828022128ec..4dffff23a0fd 100644
@@ -760,19 +760,12 @@ static void update_peercred(struct sock *sk)
 
 static void copy_peercred(struct sock *sk, struct sock *peersk)
 {
-	if (sk < peersk) {
-		spin_lock(&sk->sk_peer_lock);
-		spin_lock_nested(&peersk->sk_peer_lock, SINGLE_DEPTH_NESTING);
-	} else {
-		spin_lock(&peersk->sk_peer_lock);
-		spin_lock_nested(&sk->sk_peer_lock, SINGLE_DEPTH_NESTING);
-	}
+	lockdep_assert_held(&unix_sk(peersk)->lock);
 
-	sk->sk_peer_pid  = get_pid(peersk->sk_peer_pid);
+	spin_lock(&sk->sk_peer_lock);
+	sk->sk_peer_pid = get_pid(peersk->sk_peer_pid);
 	sk->sk_peer_cred = get_cred(peersk->sk_peer_cred);
-
 	spin_unlock(&sk->sk_peer_lock);
-	spin_unlock(&peersk->sk_peer_lock);
 }
 
 static int unix_listen(struct socket *sock, int backlog)
Signature · 1 line
2.30.2