Merge tag 'net-6.15-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Pull networking fixes from Paolo Abeni:
 "Including fixes from netfilter.

  Current release - regressions:

    - core: hold instance lock during NETDEV_CHANGE

    - rtnetlink: fix bad unlock balance in do_setlink()

    - ipv6:
       - fix null-ptr-deref in addrconf_add_ifaddr()
       - align behavior across nexthops during path selection

  Previous releases - regressions:

    - sctp: prevent transport UaF in sendmsg

    - mptcp: only inc MPJoinAckHMacFailure for HMAC failures

  Previous releases - always broken:

    - sched:
       - make ->qlen_notify() idempotent
       - ensure sufficient space when sending filter netlink notifications
       - sch_sfq: really don't allow 1 packet limit

    - netfilter: fix incorrect avx2 match of 5th field octet

    - tls: explicitly disallow disconnect

    - eth: octeontx2-pf: fix VF root node parent queue priority"

* tag 'net-6.15-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (38 commits)
  ethtool: cmis_cdb: Fix incorrect read / write length extension
  selftests: netfilter: add test case for recent mismatch bug
  nft_set_pipapo: fix incorrect avx2 match of 5th field octet
  net: ppp: Add bound checking for skb data on ppp_sync_txmung
  net: Fix null-ptr-deref by sock_lock_init_class_and_name() and rmmod.
  ipv6: Align behavior across nexthops during path selection
  net: phy: allow MDIO bus PM ops to start/stop state machine for phylink-controlled PHY
  net: phy: move phy_link_change() prior to mdio_bus_phy_may_suspend()
  selftests/tc-testing: sfq: check that a derived limit of 1 is rejected
  net_sched: sch_sfq: move the limit validation
  net_sched: sch_sfq: use a temporary work area for validating configuration
  net: libwx: handle page_pool_dev_alloc_pages error
  selftests: mptcp: validate MPJoin HMacFailure counters
  mptcp: only inc MPJoinAckHMacFailure for HMAC failures
  rtnetlink: Fix bad unlock balance in do_setlink().
  net: ethtool: Don't call .cleanup_data when prepare_data fails
  tc: Ensure we have enough buffer space when sending filter netlink notifications
  net: libwx: Fix the wrong Rx descriptor field
  octeontx2-pf: qos: fix VF root node parent queue index
  selftests: tls: check that disconnect does nothing
  ...

29 files changed, 228 insertions, 121 deletions

diff --git a/net/core/dev.c b/net/core/dev.c
index 0608605cfc24..75e104322ad5 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1518,15 +1518,7 @@ void netdev_features_change(struct net_device *dev)
 }
 EXPORT_SYMBOL(netdev_features_change);
 
-/**
- *	netdev_state_change - device changes state
- *	@dev: device to cause notification
- *
- *	Called to indicate a device has changed state. This function calls
- *	the notifier chains for netdev_chain and sends a NEWLINK message
- *	to the routing socket.
- */
-void netdev_state_change(struct net_device *dev)
+void netif_state_change(struct net_device *dev)
 {
 	if (dev->flags & IFF_UP) {
 		struct netdev_notifier_change_info change_info = {
@@ -1538,7 +1530,6 @@ void netdev_state_change(struct net_device *dev)
 		rtmsg_ifinfo(RTM_NEWLINK, dev, 0, GFP_KERNEL, 0, NULL);
 	}
 }
-EXPORT_SYMBOL(netdev_state_change);
 
 /**
  * __netdev_notify_peers - notify network peers about existence of @dev,
diff --git a/net/core/dev_api.c b/net/core/dev_api.c
index 90bafb0b1b8c..90898cd540ce 100644
--- a/net/core/dev_api.c
+++ b/net/core/dev_api.c
@@ -327,3 +327,19 @@ int dev_xdp_propagate(struct net_device *dev, struct netdev_bpf *bpf)
 	return ret;
 }
 EXPORT_SYMBOL_GPL(dev_xdp_propagate);
+
+/**
+ * netdev_state_change() - device changes state
+ * @dev: device to cause notification
+ *
+ * Called to indicate a device has changed state. This function calls
+ * the notifier chains for netdev_chain and sends a NEWLINK message
+ * to the routing socket.
+ */
+void netdev_state_change(struct net_device *dev)
+{
+	netdev_lock_ops(dev);
+	netif_state_change(dev);
+	netdev_unlock_ops(dev);
+}
+EXPORT_SYMBOL(netdev_state_change);
diff --git a/net/core/link_watch.c b/net/core/link_watch.c
index cb04ef2b9807..864f3bbc3a4c 100644
--- a/net/core/link_watch.c
+++ b/net/core/link_watch.c
@@ -183,7 +183,7 @@ static void linkwatch_do_dev(struct net_device *dev)
 		else
 			dev_deactivate(dev);
 
-		netdev_state_change(dev);
+		netif_state_change(dev);
 	}
 	/* Note: our callers are responsible for calling netdev_tracker_free().
 	 * This is the reason we use __dev_put() instead of dev_put().
@@ -240,7 +240,9 @@ static void __linkwatch_run_queue(int urgent_only)
 		 */
 		netdev_tracker_free(dev, &dev->linkwatch_dev_tracker);
 		spin_unlock_irq(&lweventlist_lock);
+		netdev_lock_ops(dev);
 		linkwatch_do_dev(dev);
+		netdev_unlock_ops(dev);
 		do_dev--;
 		spin_lock_irq(&lweventlist_lock);
 	}
@@ -253,25 +255,41 @@ static void __linkwatch_run_queue(int urgent_only)
 	spin_unlock_irq(&lweventlist_lock);
 }
 
-void linkwatch_sync_dev(struct net_device *dev)
+static bool linkwatch_clean_dev(struct net_device *dev)
 {
 	unsigned long flags;
-	int clean = 0;
+	bool clean = false;
 
 	spin_lock_irqsave(&lweventlist_lock, flags);
 	if (!list_empty(&dev->link_watch_list)) {
 		list_del_init(&dev->link_watch_list);
-		clean = 1;
+		clean = true;
 		/* We must release netdev tracker under
 		 * the spinlock protection.
 		 */
 		netdev_tracker_free(dev, &dev->linkwatch_dev_tracker);
 	}
 	spin_unlock_irqrestore(&lweventlist_lock, flags);
-	if (clean)
+
+	return clean;
+}
+
+void __linkwatch_sync_dev(struct net_device *dev)
+{
+	netdev_ops_assert_locked(dev);
+
+	if (linkwatch_clean_dev(dev))
 		linkwatch_do_dev(dev);
 }
 
+void linkwatch_sync_dev(struct net_device *dev)
+{
+	if (linkwatch_clean_dev(dev)) {
+		netdev_lock_ops(dev);
+		linkwatch_do_dev(dev);
+		netdev_unlock_ops(dev);
+	}
+}
 
 /* Must be called with the rtnl semaphore held */
 void linkwatch_run_queue(void)
diff --git a/net/core/lock_debug.c b/net/core/lock_debug.c
index b7f22dc92a6f..941e26c1343d 100644
--- a/net/core/lock_debug.c
+++ b/net/core/lock_debug.c
@@ -20,11 +20,11 @@ int netdev_debug_event(struct notifier_block *nb, unsigned long event,
 	switch (cmd) {
 	case NETDEV_REGISTER:
 	case NETDEV_UP:
+	case NETDEV_CHANGE:
 		netdev_ops_assert_locked(dev);
 		fallthrough;
 	case NETDEV_DOWN:
 	case NETDEV_REBOOT:
-	case NETDEV_CHANGE:
 	case NETDEV_UNREGISTER:
 	case NETDEV_CHANGEMTU:
 	case NETDEV_CHANGEADDR:
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index c23852835050..39a5b72e861f 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -1043,7 +1043,7 @@ int rtnl_put_cacheinfo(struct sk_buff *skb, struct dst_entry *dst, u32 id,
 }
 EXPORT_SYMBOL_GPL(rtnl_put_cacheinfo);
 
-void netdev_set_operstate(struct net_device *dev, int newstate)
+void netif_set_operstate(struct net_device *dev, int newstate)
 {
 	unsigned int old = READ_ONCE(dev->operstate);
 
@@ -1052,9 +1052,9 @@ void netdev_set_operstate(struct net_device *dev, int newstate)
 			return;
 	} while (!try_cmpxchg(&dev->operstate, &old, newstate));
 
-	netdev_state_change(dev);
+	netif_state_change(dev);
 }
-EXPORT_SYMBOL(netdev_set_operstate);
+EXPORT_SYMBOL(netif_set_operstate);
 
 static void set_operstate(struct net_device *dev, unsigned char transition)
 {
@@ -1080,7 +1080,7 @@ static void set_operstate(struct net_device *dev, unsigned char transition)
 		break;
 	}
 
-	netdev_set_operstate(dev, operstate);
+	netif_set_operstate(dev, operstate);
 }
 
 static unsigned int rtnl_dev_get_flags(const struct net_device *dev)
@@ -3027,7 +3027,7 @@ static int do_setlink(const struct sk_buff *skb, struct net_device *dev,
 
 	err = validate_linkmsg(dev, tb, extack);
 	if (err < 0)
-		goto errout;
+		return err;
 
 	if (tb[IFLA_IFNAME])
 		nla_strscpy(ifname, tb[IFLA_IFNAME], IFNAMSIZ);
@@ -3396,7 +3396,7 @@ static int do_setlink(const struct sk_buff *skb, struct net_device *dev,
 errout:
 	if (status & DO_SETLINK_MODIFIED) {
 		if ((status & DO_SETLINK_NOTIFY) == DO_SETLINK_NOTIFY)
-			netdev_state_change(dev);
+			netif_state_change(dev);
 
 		if (err < 0)
 			net_warn_ratelimited("A link change request failed with some changes committed already. Interface %s may have been left with an inconsistent configuration, please check.\n",
@@ -3676,8 +3676,11 @@ struct net_device *rtnl_create_link(struct net *net, const char *ifname,
 				nla_len(tb[IFLA_BROADCAST]));
 	if (tb[IFLA_TXQLEN])
 		dev->tx_queue_len = nla_get_u32(tb[IFLA_TXQLEN]);
-	if (tb[IFLA_OPERSTATE])
+	if (tb[IFLA_OPERSTATE]) {
+		netdev_lock_ops(dev);
 		set_operstate(dev, nla_get_u8(tb[IFLA_OPERSTATE]));
+		netdev_unlock_ops(dev);
+	}
 	if (tb[IFLA_LINKMODE])
 		dev->link_mode = nla_get_u8(tb[IFLA_LINKMODE]);
 	if (tb[IFLA_GROUP])
diff --git a/net/core/sock.c b/net/core/sock.c
index f67a3c5b0988..e54449c9ab0b 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -2130,6 +2130,8 @@ lenout:
  */
 static inline void sock_lock_init(struct sock *sk)
 {
+	sk_owner_clear(sk);
+
 	if (sk->sk_kern_sock)
 		sock_lock_init_class_and_name(
 			sk,
@@ -2226,6 +2228,9 @@ static void sk_prot_free(struct proto *prot, struct sock *sk)
 	cgroup_sk_free(&sk->sk_cgrp_data);
 	mem_cgroup_sk_free(sk);
 	security_sk_free(sk);
+
+	sk_owner_put(sk);
+
 	if (slab != NULL)
 		kmem_cache_free(slab, sk);
 	else
diff --git a/net/ethtool/cmis.h b/net/ethtool/cmis.h
index 1e790413db0e..4a9a946cabf0 100644
--- a/net/ethtool/cmis.h
+++ b/net/ethtool/cmis.h
@@ -101,7 +101,6 @@ struct ethtool_cmis_cdb_rpl {
 };
 
 u32 ethtool_cmis_get_max_lpl_size(u8 num_of_byte_octs);
-u32 ethtool_cmis_get_max_epl_size(u8 num_of_byte_octs);
 
 void ethtool_cmis_cdb_compose_args(struct ethtool_cmis_cdb_cmd_args *args,
 				   enum ethtool_cmis_cdb_cmd_id cmd, u8 *lpl,
diff --git a/net/ethtool/cmis_cdb.c b/net/ethtool/cmis_cdb.c
index d159dc121bde..0e2691ccb0df 100644
--- a/net/ethtool/cmis_cdb.c
+++ b/net/ethtool/cmis_cdb.c
@@ -16,15 +16,6 @@ u32 ethtool_cmis_get_max_lpl_size(u8 num_of_byte_octs)
 	return 8 * (1 + min_t(u8, num_of_byte_octs, 15));
 }
 
-/* For accessing the EPL field on page 9Fh, the allowable length extension is
- * min(i, 255) byte octets where i specifies the allowable additional number of
- * byte octets in a READ or a WRITE.
- */
-u32 ethtool_cmis_get_max_epl_size(u8 num_of_byte_octs)
-{
-	return 8 * (1 + min_t(u8, num_of_byte_octs, 255));
-}
-
 void ethtool_cmis_cdb_compose_args(struct ethtool_cmis_cdb_cmd_args *args,
 				   enum ethtool_cmis_cdb_cmd_id cmd, u8 *lpl,
 				   u8 lpl_len, u8 *epl, u16 epl_len,
@@ -33,19 +24,16 @@ void ethtool_cmis_cdb_compose_args(struct ethtool_cmis_cdb_cmd_args *args,
 {
 	args->req.id = cpu_to_be16(cmd);
 	args->req.lpl_len = lpl_len;
-	if (lpl) {
+	if (lpl)
 		memcpy(args->req.payload, lpl, args->req.lpl_len);
-		args->read_write_len_ext =
-			ethtool_cmis_get_max_lpl_size(read_write_len_ext);
-	}
 	if (epl) {
 		args->req.epl_len = cpu_to_be16(epl_len);
 		args->req.epl = epl;
-		args->read_write_len_ext =
-			ethtool_cmis_get_max_epl_size(read_write_len_ext);
 	}
 
 	args->max_duration = max_duration;
+	args->read_write_len_ext =
+		ethtool_cmis_get_max_lpl_size(read_write_len_ext);
 	args->msleep_pre_rpl = msleep_pre_rpl;
 	args->rpl_exp_len = rpl_exp_len;
 	args->flags = flags;
diff --git a/net/ethtool/common.c b/net/ethtool/common.c
index 0cb6da1f692a..49bea6b45bd5 100644
--- a/net/ethtool/common.c
+++ b/net/ethtool/common.c
@@ -830,6 +830,7 @@ void ethtool_ringparam_get_cfg(struct net_device *dev,
 
 	/* Driver gives us current state, we want to return current config */
 	kparam->tcp_data_split = dev->cfg->hds_config;
+	kparam->hds_thresh = dev->cfg->hds_thresh;
 }
 
 static void ethtool_init_tsinfo(struct kernel_ethtool_ts_info *info)
diff --git a/net/ethtool/ioctl.c b/net/ethtool/ioctl.c
index 221639407c72..8262cc10f98d 100644
--- a/net/ethtool/ioctl.c
+++ b/net/ethtool/ioctl.c
@@ -60,7 +60,7 @@ static struct devlink *netdev_to_devlink_get(struct net_device *dev)
 u32 ethtool_op_get_link(struct net_device *dev)
 {
 	/* Synchronize carrier state with link watch, see also rtnl_getlink() */
-	linkwatch_sync_dev(dev);
+	__linkwatch_sync_dev(dev);
 
 	return netif_carrier_ok(dev) ? 1 : 0;
 }
diff --git a/net/ethtool/netlink.c b/net/ethtool/netlink.c
index a163d40c6431..977beeaaa2f9 100644
--- a/net/ethtool/netlink.c
+++ b/net/ethtool/netlink.c
@@ -500,7 +500,7 @@ static int ethnl_default_doit(struct sk_buff *skb, struct genl_info *info)
 		netdev_unlock_ops(req_info->dev);
 	rtnl_unlock();
 	if (ret < 0)
-		goto err_cleanup;
+		goto err_dev;
 	ret = ops->reply_size(req_info, reply_data);
 	if (ret < 0)
 		goto err_cleanup;
@@ -560,7 +560,7 @@ static int ethnl_default_dump_one(struct sk_buff *skb, struct net_device *dev,
 	netdev_unlock_ops(dev);
 	rtnl_unlock();
 	if (ret < 0)
-		goto out;
+		goto out_cancel;
 	ret = ethnl_fill_reply_header(skb, dev, ctx->ops->hdr_attr);
 	if (ret < 0)
 		goto out;
@@ -569,6 +569,7 @@ static int ethnl_default_dump_one(struct sk_buff *skb, struct net_device *dev,
 out:
 	if (ctx->ops->cleanup_data)
 		ctx->ops->cleanup_data(ctx->reply_data);
+out_cancel:
 	ctx->reply_data->dev = NULL;
 	if (ret < 0)
 		genlmsg_cancel(skb, ehdr);
@@ -793,7 +794,7 @@ static void ethnl_default_notify(struct net_device *dev, unsigned int cmd,
 	ethnl_init_reply_data(reply_data, ops, dev);
 	ret = ops->prepare_data(req_info, reply_data, &info);
 	if (ret < 0)
-		goto err_cleanup;
+		goto err_rep;
 	ret = ops->reply_size(req_info, reply_data);
 	if (ret < 0)
 		goto err_cleanup;
@@ -828,6 +829,7 @@ err_skb:
 err_cleanup:
 	if (ops->cleanup_data)
 		ops->cleanup_data(reply_data);
+err_rep:
 	kfree(reply_data);
 	kfree(req_info);
 	return;
diff --git a/net/hsr/hsr_device.c b/net/hsr/hsr_device.c
index 439cfb7ad5d1..1b1b700ec05e 100644
--- a/net/hsr/hsr_device.c
+++ b/net/hsr/hsr_device.c
@@ -33,14 +33,14 @@ static void hsr_set_operstate(struct hsr_port *master, bool has_carrier)
 	struct net_device *dev = master->dev;
 
 	if (!is_admin_up(dev)) {
-		netdev_set_operstate(dev, IF_OPER_DOWN);
+		netif_set_operstate(dev, IF_OPER_DOWN);
 		return;
 	}
 
 	if (has_carrier)
-		netdev_set_operstate(dev, IF_OPER_UP);
+		netif_set_operstate(dev, IF_OPER_UP);
 	else
-		netdev_set_operstate(dev, IF_OPER_LOWERLAYERDOWN);
+		netif_set_operstate(dev, IF_OPER_LOWERLAYERDOWN);
 }
 
 static bool hsr_check_carrier(struct hsr_port *master)
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 2cffb8f4a2bc..9ba83f0c9928 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -3154,12 +3154,13 @@ int addrconf_add_ifaddr(struct net *net, void __user *arg)
 
 	rtnl_net_lock(net);
 	dev = __dev_get_by_index(net, ireq.ifr6_ifindex);
-	netdev_lock_ops(dev);
-	if (dev)
+	if (dev) {
+		netdev_lock_ops(dev);
 		err = inet6_addr_add(net, dev, &cfg, 0, 0, NULL);
-	else
+		netdev_unlock_ops(dev);
+	} else {
 		err = -ENODEV;
-	netdev_unlock_ops(dev);
+	}
 	rtnl_net_unlock(net);
 	return err;
 }
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index ab12b816ab94..210b84cecc24 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -470,10 +470,10 @@ void fib6_select_path(const struct net *net, struct fib6_result *res,
 		goto out;
 
 	hash = fl6->mp_hash;
-	if (hash <= atomic_read(&first->fib6_nh->fib_nh_upper_bound) &&
-	    rt6_score_route(first->fib6_nh, first->fib6_flags, oif,
-			    strict) >= 0) {
-		match = first;
+	if (hash <= atomic_read(&first->fib6_nh->fib_nh_upper_bound)) {
+		if (rt6_score_route(first->fib6_nh, first->fib6_flags, oif,
+				    strict) >= 0)
+			match = first;
 		goto out;
 	}
 
diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index 409bd415ef1d..24c2de1891bd 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -899,13 +899,17 @@ create_child:
 				goto dispose_child;
 			}
 
-			if (!subflow_hmac_valid(req, &mp_opt) ||
-			    !mptcp_can_accept_new_subflow(subflow_req->msk)) {
+			if (!subflow_hmac_valid(req, &mp_opt)) {
 				SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINACKMAC);
 				subflow_add_reset_reason(skb, MPTCP_RST_EPROHIBIT);
 				goto dispose_child;
 			}
 
+			if (!mptcp_can_accept_new_subflow(owner)) {
+				subflow_add_reset_reason(skb, MPTCP_RST_EPROHIBIT);
+				goto dispose_child;
+			}
+
 			/* move the msk reference ownership to the subflow */
 			subflow_req->msk = NULL;
 			ctx->conn = (struct sock *)owner;
diff --git a/net/netfilter/nft_set_pipapo_avx2.c b/net/netfilter/nft_set_pipapo_avx2.c
index b8d3c3213efe..c15db28c5ebc 100644
--- a/net/netfilter/nft_set_pipapo_avx2.c
+++ b/net/netfilter/nft_set_pipapo_avx2.c
@@ -994,8 +994,9 @@ static int nft_pipapo_avx2_lookup_8b_16(unsigned long *map, unsigned long *fill,
 		NFT_PIPAPO_AVX2_BUCKET_LOAD8(5, lt,  8,  pkt[8], bsize);
 
 		NFT_PIPAPO_AVX2_AND(6, 2, 3);
+		NFT_PIPAPO_AVX2_AND(3, 4, 7);
 		NFT_PIPAPO_AVX2_BUCKET_LOAD8(7, lt,  9,  pkt[9], bsize);
-		NFT_PIPAPO_AVX2_AND(0, 4, 5);
+		NFT_PIPAPO_AVX2_AND(0, 3, 5);
 		NFT_PIPAPO_AVX2_BUCKET_LOAD8(1, lt, 10, pkt[10], bsize);
 		NFT_PIPAPO_AVX2_AND(2, 6, 7);
 		NFT_PIPAPO_AVX2_BUCKET_LOAD8(3, lt, 11, pkt[11], bsize);
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index 4f648af8cfaa..ecec0a1e1c1a 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -2057,6 +2057,7 @@ static int tcf_fill_node(struct net *net, struct sk_buff *skb,
 	struct tcmsg *tcm;
 	struct nlmsghdr  *nlh;
 	unsigned char *b = skb_tail_pointer(skb);
+	int ret = -EMSGSIZE;
 
 	nlh = nlmsg_put(skb, portid, seq, event, sizeof(*tcm), flags);
 	if (!nlh)
@@ -2101,11 +2102,45 @@ static int tcf_fill_node(struct net *net, struct sk_buff *skb,
 
 	return skb->len;
 
+cls_op_not_supp:
+	ret = -EOPNOTSUPP;
 out_nlmsg_trim:
 nla_put_failure:
-cls_op_not_supp:
 	nlmsg_trim(skb, b);
-	return -1;
+	return ret;
+}
+
+static struct sk_buff *tfilter_notify_prep(struct net *net,
+					   struct sk_buff *oskb,
+					   struct nlmsghdr *n,
+					   struct tcf_proto *tp,
+					   struct tcf_block *block,
+					   struct Qdisc *q, u32 parent,
+					   void *fh, int event,
+					   u32 portid, bool rtnl_held,
+					   struct netlink_ext_ack *extack)
+{
+	unsigned int size = oskb ? max(NLMSG_GOODSIZE, oskb->len) : NLMSG_GOODSIZE;
+	struct sk_buff *skb;
+	int ret;
+
+retry:
+	skb = alloc_skb(size, GFP_KERNEL);
+	if (!skb)
+		return ERR_PTR(-ENOBUFS);
+
+	ret = tcf_fill_node(net, skb, tp, block, q, parent, fh, portid,
+			    n->nlmsg_seq, n->nlmsg_flags, event, false,
+			    rtnl_held, extack);
+	if (ret <= 0) {
+		kfree_skb(skb);
+		if (ret == -EMSGSIZE) {
+			size += NLMSG_GOODSIZE;
+			goto retry;
+		}
+		return ERR_PTR(-EINVAL);
+	}
+	return skb;
 }
 
 static int tfilter_notify(struct net *net, struct sk_buff *oskb,
@@ -2121,16 +2156,10 @@ static int tfilter_notify(struct net *net, struct sk_buff *oskb,
 	if (!unicast && !rtnl_notify_needed(net, n->nlmsg_flags, RTNLGRP_TC))
 		return 0;
 
-	skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL);
-	if (!skb)
-		return -ENOBUFS;
-
-	if (tcf_fill_node(net, skb, tp, block, q, parent, fh, portid,
-			  n->nlmsg_seq, n->nlmsg_flags, event,
-			  false, rtnl_held, extack) <= 0) {
-		kfree_skb(skb);
-		return -EINVAL;
-	}
+	skb = tfilter_notify_prep(net, oskb, n, tp, block, q, parent, fh, event,
+				  portid, rtnl_held, extack);
+	if (IS_ERR(skb))
+		return PTR_ERR(skb);
 
 	if (unicast)
 		err = rtnl_unicast(skb, net, portid);
@@ -2153,16 +2182,11 @@ static int tfilter_del_notify(struct net *net, struct sk_buff *oskb,
 	if (!rtnl_notify_needed(net, n->nlmsg_flags, RTNLGRP_TC))
 		return tp->ops->delete(tp, fh, last, rtnl_held, extack);
 
-	skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL);
-	if (!skb)
-		return -ENOBUFS;
-
-	if (tcf_fill_node(net, skb, tp, block, q, parent, fh, portid,
-			  n->nlmsg_seq, n->nlmsg_flags, RTM_DELTFILTER,
-			  false, rtnl_held, extack) <= 0) {
+	skb = tfilter_notify_prep(net, oskb, n, tp, block, q, parent, fh,
+				  RTM_DELTFILTER, portid, rtnl_held, extack);
+	if (IS_ERR(skb)) {
 		NL_SET_ERR_MSG(extack, "Failed to build del event notification");
-		kfree_skb(skb);
-		return -EINVAL;
+		return PTR_ERR(skb);
 	}
 
 	err = tp->ops->delete(tp, fh, last, rtnl_held, extack);
diff --git a/net/sched/sch_codel.c b/net/sched/sch_codel.c
index 81189d02fee7..12dd71139da3 100644
--- a/net/sched/sch_codel.c
+++ b/net/sched/sch_codel.c
@@ -65,10 +65,7 @@ static struct sk_buff *codel_qdisc_dequeue(struct Qdisc *sch)
 			    &q->stats, qdisc_pkt_len, codel_get_enqueue_time,
 			    drop_func, dequeue_func);
 
-	/* We cant call qdisc_tree_reduce_backlog() if our qlen is 0,
-	 * or HTB crashes. Defer it for next round.
-	 */
-	if (q->stats.drop_count && sch->q.qlen) {
+	if (q->stats.drop_count) {
 		qdisc_tree_reduce_backlog(sch, q->stats.drop_count, q->stats.drop_len);
 		q->stats.drop_count = 0;
 		q->stats.drop_len = 0;
diff --git a/net/sched/sch_drr.c b/net/sched/sch_drr.c
index c69b999fae17..e0a81d313aa7 100644
--- a/net/sched/sch_drr.c
+++ b/net/sched/sch_drr.c
@@ -105,6 +105,7 @@ static int drr_change_class(struct Qdisc *sch, u32 classid, u32 parentid,
 		return -ENOBUFS;
 
 	gnet_stats_basic_sync_init(&cl->bstats);
+	INIT_LIST_HEAD(&cl->alist);
 	cl->common.classid = classid;
 	cl->quantum	   = quantum;
 	cl->qdisc	   = qdisc_create_dflt(sch->dev_queue,
@@ -229,7 +230,7 @@ static void drr_qlen_notify(struct Qdisc *csh, unsigned long arg)
 {
 	struct drr_class *cl = (struct drr_class *)arg;
 
-	list_del(&cl->alist);
+	list_del_init(&cl->alist);
 }
 
 static int drr_dump_class(struct Qdisc *sch, unsigned long arg,
@@ -390,7 +391,7 @@ static struct sk_buff *drr_dequeue(struct Qdisc *sch)
 			if (unlikely(skb == NULL))
 				goto out;
 			if (cl->qdisc->q.qlen == 0)
-				list_del(&cl->alist);
+				list_del_init(&cl->alist);
 
 			bstats_update(&cl->bstats, skb);
 			qdisc_bstats_update(sch, skb);
@@ -431,7 +432,7 @@ static void drr_reset_qdisc(struct Qdisc *sch)
 	for (i = 0; i < q->clhash.hashsize; i++) {
 		hlist_for_each_entry(cl, &q->clhash.hash[i], common.hnode) {
 			if (cl->qdisc->q.qlen)
-				list_del(&cl->alist);
+				list_del_init(&cl->alist);
 			qdisc_reset(cl->qdisc);
 		}
 	}
diff --git a/net/sched/sch_ets.c b/net/sched/sch_ets.c
index 516038a44163..c3bdeb14185b 100644
--- a/net/sched/sch_ets.c
+++ b/net/sched/sch_ets.c
@@ -293,7 +293,7 @@ static void ets_class_qlen_notify(struct Qdisc *sch, unsigned long arg)
 	 * to remove them.
 	 */
 	if (!ets_class_is_strict(q, cl) && sch->q.qlen)
-		list_del(&cl->alist);
+		list_del_init(&cl->alist);
 }
 
 static int ets_class_dump(struct Qdisc *sch, unsigned long arg,
@@ -488,7 +488,7 @@ static struct sk_buff *ets_qdisc_dequeue(struct Qdisc *sch)
 			if (unlikely(!skb))
 				goto out;
 			if (cl->qdisc->q.qlen == 0)
-				list_del(&cl->alist);
+				list_del_init(&cl->alist);
 			return ets_qdisc_dequeue_skb(sch, skb);
 		}
 
@@ -657,7 +657,7 @@ static int ets_qdisc_change(struct Qdisc *sch, struct nlattr *opt,
 	}
 	for (i = q->nbands; i < oldbands; i++) {
 		if (i >= q->nstrict && q->classes[i].qdisc->q.qlen)
-			list_del(&q->classes[i].alist);
+			list_del_init(&q->classes[i].alist);
 		qdisc_tree_flush_backlog(q->classes[i].qdisc);
 	}
 	WRITE_ONCE(q->nstrict, nstrict);
@@ -713,7 +713,7 @@ static void ets_qdisc_reset(struct Qdisc *sch)
 
 	for (band = q->nstrict; band < q->nbands; band++) {
 		if (q->classes[band].qdisc->q.qlen)
-			list_del(&q->classes[band].alist);
+			list_del_init(&q->classes[band].alist);
 	}
 	for (band = 0; band < q->nbands; band++)
 		qdisc_reset(q->classes[band].qdisc);
diff --git a/net/sched/sch_fq_codel.c b/net/sched/sch_fq_codel.c
index 799f5397ad4c..6c9029f71e88 100644
--- a/net/sched/sch_fq_codel.c
+++ b/net/sched/sch_fq_codel.c
@@ -315,10 +315,8 @@ begin:
 	}
 	qdisc_bstats_update(sch, skb);
 	flow->deficit -= qdisc_pkt_len(skb);
-	/* We cant call qdisc_tree_reduce_backlog() if our qlen is 0,
-	 * or HTB crashes. Defer it for next round.
-	 */
-	if (q->cstats.drop_count && sch->q.qlen) {
+
+	if (q->cstats.drop_count) {
 		qdisc_tree_reduce_backlog(sch, q->cstats.drop_count,
 					  q->cstats.drop_len);
 		q->cstats.drop_count = 0;
diff --git a/net/sched/sch_hfsc.c b/net/sched/sch_hfsc.c
index c287bf8423b4..ce5045eea065 100644
--- a/net/sched/sch_hfsc.c
+++ b/net/sched/sch_hfsc.c
@@ -203,7 +203,10 @@ eltree_insert(struct hfsc_class *cl)
 static inline void
 eltree_remove(struct hfsc_class *cl)
 {
-	rb_erase(&cl->el_node, &cl->sched->eligible);
+	if (!RB_EMPTY_NODE(&cl->el_node)) {
+		rb_erase(&cl->el_node, &cl->sched->eligible);
+		RB_CLEAR_NODE(&cl->el_node);
+	}
 }
 
 static inline void
@@ -1220,7 +1223,8 @@ hfsc_qlen_notify(struct Qdisc *sch, unsigned long arg)
 	/* vttree is now handled in update_vf() so that update_vf(cl, 0, 0)
 	 * needs to be called explicitly to remove a class from vttree.
 	 */
-	update_vf(cl, 0, 0);
+	if (cl->cl_nactive)
+		update_vf(cl, 0, 0);
 	if (cl->cl_flags & HFSC_RSC)
 		eltree_remove(cl);
 }
diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c
index c31bc5489bdd..4b9a639b642e 100644
--- a/net/sched/sch_htb.c
+++ b/net/sched/sch_htb.c
@@ -1485,6 +1485,8 @@ static void htb_qlen_notify(struct Qdisc *sch, unsigned long arg)
 {
 	struct htb_class *cl = (struct htb_class *)arg;
 
+	if (!cl->prio_activity)
+		return;
 	htb_deactivate(qdisc_priv(sch), cl);
 }
 
diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c
index 2cfbc977fe6d..687a932eb9b2 100644
--- a/net/sched/sch_qfq.c
+++ b/net/sched/sch_qfq.c
@@ -347,7 +347,7 @@ static void qfq_deactivate_class(struct qfq_sched *q, struct qfq_class *cl)
 	struct qfq_aggregate *agg = cl->agg;
 
 
-	list_del(&cl->alist); /* remove from RR queue of the aggregate */
+	list_del_init(&cl->alist); /* remove from RR queue of the aggregate */
 	if (list_empty(&agg->active)) /* agg is now inactive */
 		qfq_deactivate_agg(q, agg);
 }
@@ -474,6 +474,7 @@ static int qfq_change_class(struct Qdisc *sch, u32 classid, u32 parentid,
 	gnet_stats_basic_sync_init(&cl->bstats);
 	cl->common.classid = classid;
 	cl->deficit = lmax;
+	INIT_LIST_HEAD(&cl->alist);
 
 	cl->qdisc = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops,
 				      classid, NULL);
@@ -982,7 +983,7 @@ static struct sk_buff *agg_dequeue(struct qfq_aggregate *agg,
 	cl->deficit -= (int) len;
 
 	if (cl->qdisc->q.qlen == 0) /* no more packets, remove from list */
-		list_del(&cl->alist);
+		list_del_init(&cl->alist);
 	else if (cl->deficit < qdisc_pkt_len(cl->qdisc->ops->peek(cl->qdisc))) {
 		cl->deficit += agg->lmax;
 		list_move_tail(&cl->alist, &agg->active);
@@ -1415,6 +1416,8 @@ static void qfq_qlen_notify(struct Qdisc *sch, unsigned long arg)
 	struct qfq_sched *q = qdisc_priv(sch);
 	struct qfq_class *cl = (struct qfq_class *)arg;
 
+	if (list_empty(&cl->alist))
+		return;
 	qfq_deactivate_class(q, cl);
 }
 
diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c
index 9ed197e96396..b912ad99aa15 100644
--- a/net/sched/sch_sfq.c
+++ b/net/sched/sch_sfq.c
@@ -631,6 +631,15 @@ static int sfq_change(struct Qdisc *sch, struct nlattr *opt,
 	struct red_parms *p = NULL;
 	struct sk_buff *to_free = NULL;
 	struct sk_buff *tail = NULL;
+	unsigned int maxflows;
+	unsigned int quantum;
+	unsigned int divisor;
+	int perturb_period;
+	u8 headdrop;
+	u8 maxdepth;
+	int limit;
+	u8 flags;
+
 
 	if (opt->nla_len < nla_attr_size(sizeof(*ctl)))
 		return -EINVAL;
@@ -652,39 +661,64 @@ static int sfq_change(struct Qdisc *sch, struct nlattr *opt,
 		if (!p)
 			return -ENOMEM;
 	}
-	if (ctl->limit == 1) {
-		NL_SET_ERR_MSG_MOD(extack, "invalid limit");
-		return -EINVAL;
-	}
+
 	sch_tree_lock(sch);
+
+	limit = q->limit;
+	divisor = q->divisor;
+	headdrop = q->headdrop;
+	maxdepth = q->maxdepth;
+	maxflows = q->maxflows;
+	perturb_period = q->perturb_period;
+	quantum = q->quantum;
+	flags = q->flags;
+
+	/* update and validate configuration */
 	if (ctl->quantum)
-		q->quantum = ctl->quantum;
-	WRITE_ONCE(q->perturb_period, ctl->perturb_period * HZ);
+		quantum = ctl->quantum;
+	perturb_period = ctl->perturb_period * HZ;
 	if (ctl->flows)
-		q->maxflows = min_t(u32, ctl->flows, SFQ_MAX_FLOWS);
+		maxflows = min_t(u32, ctl->flows, SFQ_MAX_FLOWS);
 	if (ctl->divisor) {
-		q->divisor = ctl->divisor;
-		q->maxflows = min_t(u32, q->maxflows, q->divisor);
+		divisor = ctl->divisor;
+		maxflows = min_t(u32, maxflows, divisor);
 	}
 	if (ctl_v1) {
 		if (ctl_v1->depth)
-			q->maxdepth = min_t(u32, ctl_v1->depth, SFQ_MAX_DEPTH);
+			maxdepth = min_t(u32, ctl_v1->depth, SFQ_MAX_DEPTH);
 		if (p) {
-			swap(q->red_parms, p);
-			red_set_parms(q->red_parms,
+			red_set_parms(p,
 				      ctl_v1->qth_min, ctl_v1->qth_max,
 				      ctl_v1->Wlog,
 				      ctl_v1->Plog, ctl_v1->Scell_log,
 				      NULL,
 				      ctl_v1->max_P);
 		}
-		q->flags = ctl_v1->flags;
-		q->headdrop = ctl_v1->headdrop;
+		flags = ctl_v1->flags;
+		headdrop = ctl_v1->headdrop;
 	}
 	if (ctl->limit) {
-		q->limit = min_t(u32, ctl->limit, q->maxdepth * q->maxflows);
-		q->maxflows = min_t(u32, q->maxflows, q->limit);
+		limit = min_t(u32, ctl->limit, maxdepth * maxflows);
+		maxflows = min_t(u32, maxflows, limit);
 	}
+	if (limit == 1) {
+		sch_tree_unlock(sch);
+		kfree(p);
+		NL_SET_ERR_MSG_MOD(extack, "invalid limit");
+		return -EINVAL;
+	}
+
+	/* commit configuration */
+	q->limit = limit;
+	q->divisor = divisor;
+	q->headdrop = headdrop;
+	q->maxdepth = maxdepth;
+	q->maxflows = maxflows;
+	WRITE_ONCE(q->perturb_period, perturb_period);
+	q->quantum = quantum;
+	q->flags = flags;
+	if (p)
+		swap(q->red_parms, p);
 
 	qlen = sch->q.qlen;
 	while (sch->q.qlen > q->limit) {
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 36ee34f483d7..53725ee7ba06 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -72,8 +72,9 @@
 /* Forward declarations for internal helper functions. */
 static bool sctp_writeable(const struct sock *sk);
 static void sctp_wfree(struct sk_buff *skb);
-static int sctp_wait_for_sndbuf(struct sctp_association *asoc, long *timeo_p,
-				size_t msg_len);
+static int sctp_wait_for_sndbuf(struct sctp_association *asoc,
+				struct sctp_transport *transport,
+				long *timeo_p, size_t msg_len);
 static int sctp_wait_for_packet(struct sock *sk, int *err, long *timeo_p);
 static int sctp_wait_for_connect(struct sctp_association *, long *timeo_p);
 static int sctp_wait_for_accept(struct sock *sk, long timeo);
@@ -1828,7 +1829,7 @@ static int sctp_sendmsg_to_asoc(struct sctp_association *asoc,
 
 	if (sctp_wspace(asoc) <= 0 || !sk_wmem_schedule(sk, msg_len)) {
 		timeo = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT);
-		err = sctp_wait_for_sndbuf(asoc, &timeo, msg_len);
+		err = sctp_wait_for_sndbuf(asoc, transport, &timeo, msg_len);
 		if (err)
 			goto err;
 		if (unlikely(sinfo->sinfo_stream >= asoc->stream.outcnt)) {
@@ -9214,8 +9215,9 @@ void sctp_sock_rfree(struct sk_buff *skb)
 
 
 /* Helper function to wait for space in the sndbuf.  */
-static int sctp_wait_for_sndbuf(struct sctp_association *asoc, long *timeo_p,
-				size_t msg_len)
+static int sctp_wait_for_sndbuf(struct sctp_association *asoc,
+				struct sctp_transport *transport,
+				long *timeo_p, size_t msg_len)
 {
 	struct sock *sk = asoc->base.sk;
 	long current_timeo = *timeo_p;
@@ -9225,7 +9227,9 @@ static int sctp_wait_for_sndbuf(struct sctp_association *asoc, long *timeo_p,
 	pr_debug("%s: asoc:%p, timeo:%ld, msg_len:%zu\n", __func__, asoc,
 		 *timeo_p, msg_len);
 
-	/* Increment the association's refcnt.  */
+	/* Increment the transport and association's refcnt. */
+	if (transport)
+		sctp_transport_hold(transport);
 	sctp_association_hold(asoc);
 
 	/* Wait on the association specific sndbuf space. */
@@ -9234,7 +9238,7 @@ static int sctp_wait_for_sndbuf(struct sctp_association *asoc, long *timeo_p,
 					  TASK_INTERRUPTIBLE);
 		if (asoc->base.dead)
 			goto do_dead;
-		if (!*timeo_p)
+		if ((!*timeo_p) || (transport && transport->dead))
 			goto do_nonblock;
 		if (sk->sk_err || asoc->state >= SCTP_STATE_SHUTDOWN_PENDING)
 			goto do_error;
@@ -9259,7 +9263,9 @@ static int sctp_wait_for_sndbuf(struct sctp_association *asoc, long *timeo_p,
 out:
 	finish_wait(&asoc->wait, &wait);
 
-	/* Release the association's refcnt.  */
+	/* Release the transport and association's refcnt. */
+	if (transport)
+		sctp_transport_put(transport);
 	sctp_association_put(asoc);
 
 	return err;
diff --git a/net/sctp/transport.c b/net/sctp/transport.c
index 59675f6d9e7d..6946c1462793 100644
--- a/net/sctp/transport.c
+++ b/net/sctp/transport.c
@@ -117,6 +117,8 @@ fail:
  */
 void sctp_transport_free(struct sctp_transport *transport)
 {
+	transport->dead = 1;
+
 	/* Try to delete the heartbeat timer.  */
 	if (timer_delete(&transport->hb_timer))
 		sctp_transport_put(transport);
diff --git a/net/tipc/link.c b/net/tipc/link.c
index 50c2e0846ea4..18be6ff4c3db 100644
--- a/net/tipc/link.c
+++ b/net/tipc/link.c
@@ -1046,6 +1046,7 @@ int tipc_link_xmit(struct tipc_link *l, struct sk_buff_head *list,
 	if (unlikely(l->backlog[imp].len >= l->backlog[imp].limit)) {
 		if (imp == TIPC_SYSTEM_IMPORTANCE) {
 			pr_warn("%s<%s>, link overflow", link_rst_msg, l->name);
+			__skb_queue_purge(list);
 			return -ENOBUFS;
 		}
 		rc = link_schedule_user(l, hdr);
diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c
index cb86b0bf9a53..a3ccb3135e51 100644
--- a/net/tls/tls_main.c
+++ b/net/tls/tls_main.c
@@ -852,6 +852,11 @@ static int tls_setsockopt(struct sock *sk, int level, int optname,
 	return do_tls_setsockopt(sk, optname, optval, optlen);
 }
 
+static int tls_disconnect(struct sock *sk, int flags)
+{
+	return -EOPNOTSUPP;
+}
+
 struct tls_context *tls_ctx_create(struct sock *sk)
 {
 	struct inet_connection_sock *icsk = inet_csk(sk);
@@ -947,6 +952,7 @@ static void build_protos(struct proto prot[TLS_NUM_CONFIG][TLS_NUM_CONFIG],
 	prot[TLS_BASE][TLS_BASE] = *base;
 	prot[TLS_BASE][TLS_BASE].setsockopt	= tls_setsockopt;
 	prot[TLS_BASE][TLS_BASE].getsockopt	= tls_getsockopt;
+	prot[TLS_BASE][TLS_BASE].disconnect	= tls_disconnect;
 	prot[TLS_BASE][TLS_BASE].close		= tls_sk_proto_close;
 
 	prot[TLS_SW][TLS_BASE] = prot[TLS_BASE][TLS_BASE];