Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

include/linux/bpf.h
  1f6e04a1c7b8 ("bpf: Fix offset calculation error in __copy_map_value and zero_map_value")
  aa3496accc41 ("bpf: Refactor kptr_off_tab into btf_record")
  f71b2f64177a ("bpf: Refactor map->off_arr handling")
https://lore.kernel.org/all/20221114095000.67a73239@canb.auug.org.au/

Signed-off-by: Jakub Kicinski <kuba@kernel.org>

13 files changed, 81 insertions, 74 deletions

diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c
index 13d578ce2a09..fcb3e6c5e03c 100644
--- a/net/bpf/test_run.c
+++ b/net/bpf/test_run.c
@@ -774,6 +774,7 @@ static void *bpf_test_init(const union bpf_attr *kattr, u32 user_size,
 	if (user_size > size)
 		return ERR_PTR(-EMSGSIZE);
 
+	size = SKB_DATA_ALIGN(size);
 	data = kzalloc(size + headroom + tailroom, GFP_USER);
 	if (!data)
 		return ERR_PTR(-ENOMEM);
diff --git a/net/bridge/br_vlan.c b/net/bridge/br_vlan.c
index f2fc284abab3..bc75fa1e4666 100644
--- a/net/bridge/br_vlan.c
+++ b/net/bridge/br_vlan.c
@@ -959,6 +959,8 @@ int __br_vlan_set_proto(struct net_bridge *br, __be16 proto,
 	list_for_each_entry(p, &br->port_list, list) {
 		vg = nbp_vlan_group(p);
 		list_for_each_entry(vlan, &vg->vlan_list, vlist) {
+			if (vlan->priv_flags & BR_VLFLAG_ADDED_BY_SWITCHDEV)
+				continue;
 			err = vlan_vid_add(p->dev, proto, vlan->vid);
 			if (err)
 				goto err_filt;
@@ -973,8 +975,11 @@ int __br_vlan_set_proto(struct net_bridge *br, __be16 proto,
 	/* Delete VLANs for the old proto from the device filter. */
 	list_for_each_entry(p, &br->port_list, list) {
 		vg = nbp_vlan_group(p);
-		list_for_each_entry(vlan, &vg->vlan_list, vlist)
+		list_for_each_entry(vlan, &vg->vlan_list, vlist) {
+			if (vlan->priv_flags & BR_VLFLAG_ADDED_BY_SWITCHDEV)
+				continue;
 			vlan_vid_del(p->dev, oldproto, vlan->vid);
+		}
 	}
 
 	return 0;
@@ -983,13 +988,19 @@ err_filt:
 	attr.u.vlan_protocol = ntohs(oldproto);
 	switchdev_port_attr_set(br->dev, &attr, NULL);
 
-	list_for_each_entry_continue_reverse(vlan, &vg->vlan_list, vlist)
+	list_for_each_entry_continue_reverse(vlan, &vg->vlan_list, vlist) {
+		if (vlan->priv_flags & BR_VLFLAG_ADDED_BY_SWITCHDEV)
+			continue;
 		vlan_vid_del(p->dev, proto, vlan->vid);
+	}
 
 	list_for_each_entry_continue_reverse(p, &br->port_list, list) {
 		vg = nbp_vlan_group(p);
-		list_for_each_entry(vlan, &vg->vlan_list, vlist)
+		list_for_each_entry(vlan, &vg->vlan_list, vlist) {
+			if (vlan->priv_flags & BR_VLFLAG_ADDED_BY_SWITCHDEV)
+				continue;
 			vlan_vid_del(p->dev, proto, vlan->vid);
+		}
 	}
 
 	return err;
diff --git a/net/caif/chnl_net.c b/net/caif/chnl_net.c
index 4d63ef13a1fd..f35fc87c453a 100644
--- a/net/caif/chnl_net.c
+++ b/net/caif/chnl_net.c
@@ -310,9 +310,6 @@ static int chnl_net_open(struct net_device *dev)
 
 	if (result == 0) {
 		pr_debug("connect timeout\n");
-		caif_disconnect_client(dev_net(dev), &priv->chnl);
-		priv->state = CAIF_DISCONNECTED;
-		pr_debug("state disconnected\n");
 		result = -ETIMEDOUT;
 		goto error;
 	}
diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c
index b80dbd02e154..12145c852902 100644
--- a/net/dsa/dsa2.c
+++ b/net/dsa/dsa2.c
@@ -855,6 +855,14 @@ disconnect:
 	return err;
 }
 
+static void dsa_switch_teardown_tag_protocol(struct dsa_switch *ds)
+{
+	const struct dsa_device_ops *tag_ops = ds->dst->tag_ops;
+
+	if (tag_ops->disconnect)
+		tag_ops->disconnect(ds);
+}
+
 static int dsa_switch_setup(struct dsa_switch *ds)
 {
 	struct dsa_devlink_priv *dl_priv;
@@ -944,6 +952,8 @@ static void dsa_switch_teardown(struct dsa_switch *ds)
 		ds->slave_mii_bus = NULL;
 	}
 
+	dsa_switch_teardown_tag_protocol(ds);
+
 	if (ds->ops->teardown)
 		ds->ops->teardown(ds);
 
diff --git a/net/dsa/dsa_priv.h b/net/dsa/dsa_priv.h
index 6e65c7ffd6f3..71e9707d11d4 100644
--- a/net/dsa/dsa_priv.h
+++ b/net/dsa/dsa_priv.h
@@ -210,6 +210,7 @@ static inline struct net_device *dsa_master_find_slave(struct net_device *dev,
 extern struct rtnl_link_ops dsa_link_ops __read_mostly;
 
 /* port.c */
+bool dsa_port_supports_hwtstamp(struct dsa_port *dp, struct ifreq *ifr);
 void dsa_port_set_tag_protocol(struct dsa_port *cpu_dp,
 			       const struct dsa_device_ops *tag_ops);
 int dsa_port_set_state(struct dsa_port *dp, u8 state, bool do_fast_age);
diff --git a/net/dsa/master.c b/net/dsa/master.c
index 40367ab41cf8..421de166515f 100644
--- a/net/dsa/master.c
+++ b/net/dsa/master.c
@@ -204,8 +204,7 @@ static int dsa_master_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 		 * switch in the tree that is PTP capable.
 		 */
 		list_for_each_entry(dp, &dst->ports, list)
-			if (dp->ds->ops->port_hwtstamp_get ||
-			    dp->ds->ops->port_hwtstamp_set)
+			if (dsa_port_supports_hwtstamp(dp, ifr))
 				return -EBUSY;
 		break;
 	}
diff --git a/net/dsa/port.c b/net/dsa/port.c
index 48c9eaa74aee..707bd854cea2 100644
--- a/net/dsa/port.c
+++ b/net/dsa/port.c
@@ -110,6 +110,22 @@ static bool dsa_port_can_configure_learning(struct dsa_port *dp)
 	return !err;
 }
 
+bool dsa_port_supports_hwtstamp(struct dsa_port *dp, struct ifreq *ifr)
+{
+	struct dsa_switch *ds = dp->ds;
+	int err;
+
+	if (!ds->ops->port_hwtstamp_get || !ds->ops->port_hwtstamp_set)
+		return false;
+
+	/* "See through" shim implementations of the "get" method.
+	 * This will clobber the ifreq structure, but we will either return an
+	 * error, or the master will overwrite it with proper values.
+	 */
+	err = ds->ops->port_hwtstamp_get(ds, dp->index, ifr);
+	return err != -EOPNOTSUPP;
+}
+
 int dsa_port_set_state(struct dsa_port *dp, u8 state, bool do_fast_age)
 {
 	struct dsa_switch *ds = dp->ds;
diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig
index e983bb0c5012..2dfb12230f08 100644
--- a/net/ipv4/Kconfig
+++ b/net/ipv4/Kconfig
@@ -402,6 +402,16 @@ config INET_IPCOMP
 
 	  If unsure, say Y.
 
+config INET_TABLE_PERTURB_ORDER
+	int "INET: Source port perturbation table size (as power of 2)" if EXPERT
+	default 16
+	help
+	  Source port perturbation table size (as power of 2) for
+	  RFC 6056 3.3.4.  Algorithm 4: Double-Hash Port Selection Algorithm.
+
+	  The default is almost always what you want.
+	  Only change this if you know what you are doing.
+
 config INET_XFRM_TUNNEL
 	tristate
 	select INET_TUNNEL
diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index d3dc28156622..033bf3c2538f 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -906,13 +906,13 @@ EXPORT_SYMBOL_GPL(inet_bhash2_update_saddr);
  * Note that we use 32bit integers (vs RFC 'short integers')
  * because 2^16 is not a multiple of num_ephemeral and this
  * property might be used by clever attacker.
+ *
  * RFC claims using TABLE_LENGTH=10 buckets gives an improvement, though
- * attacks were since demonstrated, thus we use 65536 instead to really
- * give more isolation and privacy, at the expense of 256kB of kernel
- * memory.
+ * attacks were since demonstrated, thus we use 65536 by default instead
+ * to really give more isolation and privacy, at the expense of 256kB
+ * of kernel memory.
  */
-#define INET_TABLE_PERTURB_SHIFT 16
-#define INET_TABLE_PERTURB_SIZE (1 << INET_TABLE_PERTURB_SHIFT)
+#define INET_TABLE_PERTURB_SIZE (1 << CONFIG_INET_TABLE_PERTURB_ORDER)
 static u32 *table_perturb;
 
 int __inet_hash_connect(struct inet_timewait_death_row *death_row,
diff --git a/net/kcm/kcmsock.c b/net/kcm/kcmsock.c
index a5004228111d..890a2423f559 100644
--- a/net/kcm/kcmsock.c
+++ b/net/kcm/kcmsock.c
@@ -222,7 +222,7 @@ static void requeue_rx_msgs(struct kcm_mux *mux, struct sk_buff_head *head)
 	struct sk_buff *skb;
 	struct kcm_sock *kcm;
 
-	while ((skb = __skb_dequeue(head))) {
+	while ((skb = skb_dequeue(head))) {
 		/* Reset destructor to avoid calling kcm_rcv_ready */
 		skb->destructor = sock_rfree;
 		skb_orphan(skb);
@@ -1085,53 +1085,17 @@ out_error:
 	return err;
 }
 
-static struct sk_buff *kcm_wait_data(struct sock *sk, int flags,
-				     long timeo, int *err)
-{
-	struct sk_buff *skb;
-
-	while (!(skb = skb_peek(&sk->sk_receive_queue))) {
-		if (sk->sk_err) {
-			*err = sock_error(sk);
-			return NULL;
-		}
-
-		if (sock_flag(sk, SOCK_DONE))
-			return NULL;
-
-		if ((flags & MSG_DONTWAIT) || !timeo) {
-			*err = -EAGAIN;
-			return NULL;
-		}
-
-		sk_wait_data(sk, &timeo, NULL);
-
-		/* Handle signals */
-		if (signal_pending(current)) {
-			*err = sock_intr_errno(timeo);
-			return NULL;
-		}
-	}
-
-	return skb;
-}
-
 static int kcm_recvmsg(struct socket *sock, struct msghdr *msg,
 		       size_t len, int flags)
 {
 	struct sock *sk = sock->sk;
 	struct kcm_sock *kcm = kcm_sk(sk);
 	int err = 0;
-	long timeo;
 	struct strp_msg *stm;
 	int copied = 0;
 	struct sk_buff *skb;
 
-	timeo = sock_rcvtimeo(sk, flags & MSG_DONTWAIT);
-
-	lock_sock(sk);
-
-	skb = kcm_wait_data(sk, flags, timeo, &err);
+	skb = skb_recv_datagram(sk, flags, &err);
 	if (!skb)
 		goto out;
 
@@ -1162,14 +1126,11 @@ msg_finished:
 			/* Finished with message */
 			msg->msg_flags |= MSG_EOR;
 			KCM_STATS_INCR(kcm->stats.rx_msgs);
-			skb_unlink(skb, &sk->sk_receive_queue);
-			kfree_skb(skb);
 		}
 	}
 
 out:
-	release_sock(sk);
-
+	skb_free_datagram(sk, skb);
 	return copied ? : err;
 }
 
@@ -1179,7 +1140,6 @@ static ssize_t kcm_splice_read(struct socket *sock, loff_t *ppos,
 {
 	struct sock *sk = sock->sk;
 	struct kcm_sock *kcm = kcm_sk(sk);
-	long timeo;
 	struct strp_msg *stm;
 	int err = 0;
 	ssize_t copied;
@@ -1187,11 +1147,7 @@ static ssize_t kcm_splice_read(struct socket *sock, loff_t *ppos,
 
 	/* Only support splice for SOCKSEQPACKET */
 
-	timeo = sock_rcvtimeo(sk, flags & MSG_DONTWAIT);
-
-	lock_sock(sk);
-
-	skb = kcm_wait_data(sk, flags, timeo, &err);
+	skb = skb_recv_datagram(sk, flags, &err);
 	if (!skb)
 		goto err_out;
 
@@ -1219,13 +1175,11 @@ static ssize_t kcm_splice_read(struct socket *sock, loff_t *ppos,
 	 * finish reading the message.
 	 */
 
-	release_sock(sk);
-
+	skb_free_datagram(sk, skb);
 	return copied;
 
 err_out:
-	release_sock(sk);
-
+	skb_free_datagram(sk, skb);
 	return err;
 }
 
diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index 7499c51b1850..754fdda8a5f5 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -1150,8 +1150,10 @@ static void l2tp_tunnel_destruct(struct sock *sk)
 	}
 
 	/* Remove hooks into tunnel socket */
+	write_lock_bh(&sk->sk_callback_lock);
 	sk->sk_destruct = tunnel->old_sk_destruct;
 	sk->sk_user_data = NULL;
+	write_unlock_bh(&sk->sk_callback_lock);
 
 	/* Call the original destructor */
 	if (sk->sk_destruct)
@@ -1469,16 +1471,18 @@ int l2tp_tunnel_register(struct l2tp_tunnel *tunnel, struct net *net,
 		sock = sockfd_lookup(tunnel->fd, &ret);
 		if (!sock)
 			goto err;
-
-		ret = l2tp_validate_socket(sock->sk, net, tunnel->encap);
-		if (ret < 0)
-			goto err_sock;
 	}
 
+	sk = sock->sk;
+	write_lock(&sk->sk_callback_lock);
+
+	ret = l2tp_validate_socket(sk, net, tunnel->encap);
+	if (ret < 0)
+		goto err_sock;
+
 	tunnel->l2tp_net = net;
 	pn = l2tp_pernet(net);
 
-	sk = sock->sk;
 	sock_hold(sk);
 	tunnel->sock = sk;
 
@@ -1504,7 +1508,7 @@ int l2tp_tunnel_register(struct l2tp_tunnel *tunnel, struct net *net,
 
 		setup_udp_tunnel_sock(net, sock, &udp_cfg);
 	} else {
-		sk->sk_user_data = tunnel;
+		rcu_assign_sk_user_data(sk, tunnel);
 	}
 
 	tunnel->old_sk_destruct = sk->sk_destruct;
@@ -1518,6 +1522,7 @@ int l2tp_tunnel_register(struct l2tp_tunnel *tunnel, struct net *net,
 	if (tunnel->fd >= 0)
 		sockfd_put(sock);
 
+	write_unlock(&sk->sk_callback_lock);
 	return 0;
 
 err_sock:
@@ -1525,6 +1530,8 @@ err_sock:
 		sock_release(sock);
 	else
 		sockfd_put(sock);
+
+	write_unlock(&sk->sk_callback_lock);
 err:
 	return ret;
 }
diff --git a/net/tls/tls_device_fallback.c b/net/tls/tls_device_fallback.c
index cdb391a8754b..7fbb1d0b69b3 100644
--- a/net/tls/tls_device_fallback.c
+++ b/net/tls/tls_device_fallback.c
@@ -346,7 +346,7 @@ static struct sk_buff *tls_enc_skb(struct tls_context *tls_ctx,
 		salt = tls_ctx->crypto_send.aes_gcm_256.salt;
 		break;
 	default:
-		return NULL;
+		goto free_req;
 	}
 	cipher_sz = &tls_cipher_size_desc[tls_ctx->crypto_send.info.cipher_type];
 	buf_len = cipher_sz->salt + cipher_sz->iv + TLS_AAD_SPACE_SIZE +
@@ -492,7 +492,8 @@ int tls_sw_fallback_init(struct sock *sk,
 		key = ((struct tls12_crypto_info_aes_gcm_256 *)crypto_info)->key;
 		break;
 	default:
-		return -EINVAL;
+		rc = -EINVAL;
+		goto free_aead;
 	}
 	cipher_sz = &tls_cipher_size_desc[crypto_info->cipher_type];
 
diff --git a/net/x25/x25_dev.c b/net/x25/x25_dev.c
index 5259ef8f5242..748d8630ab58 100644
--- a/net/x25/x25_dev.c
+++ b/net/x25/x25_dev.c
@@ -117,7 +117,7 @@ int x25_lapb_receive_frame(struct sk_buff *skb, struct net_device *dev,
 
 	if (!pskb_may_pull(skb, 1)) {
 		x25_neigh_put(nb);
-		return 0;
+		goto drop;
 	}
 
 	switch (skb->data[0]) {