Merge tag 'net-5.15-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Pull networking fixes from Jakub Kicinski:
 "Including fixes from bpf.

  Current release - regressions:

   - vhost_net: fix OoB on sendmsg() failure

   - mlx5: bridge, fix uninitialized variable usage

   - bnxt_en: fix error recovery regression

  Current release - new code bugs:

   - bpf, mm: fix lockdep warning triggered by stack_map_get_build_id_offset()

  Previous releases - regressions:

   - r6040: restore MDIO clock frequency after MAC reset

   - tcp: fix tp->undo_retrans accounting in tcp_sacktag_one()

   - dsa: flush switchdev workqueue before tearing down CPU/DSA ports

  Previous releases - always broken:

   - ptp: dp83640: don't define PAGE0, avoid compiler warning

   - igc: fix tunnel segmentation offloads

   - phylink: update SFP selected interface on advertising changes

   - stmmac: fix system hang caused by eee_ctrl_timer during suspend/resume

   - mlx5e: fix mutual exclusion between CQE compression and HW TS

  Misc:

   - bpf, cgroups: fix cgroup v2 fallback on v1/v2 mixed mode

   - sfc: fallback for lack of xdp tx queues

   - hns3: add option to turn off page pool feature"

* tag 'net-5.15-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (67 commits)
  mlxbf_gige: clear valid_polarity upon open
  igc: fix tunnel offloading
  net/{mlx5|nfp|bnxt}: Remove unnecessary RTNL lock assert
  net: wan: wanxl: define CROSS_COMPILE_M68K
  selftests: nci: replace unsigned int with int
  net: dsa: flush switchdev workqueue before tearing down CPU/DSA ports
  Revert "net: phy: Uniform PHY driver access"
  net: dsa: destroy the phylink instance on any error in dsa_slave_phy_setup
  ptp: dp83640: don't define PAGE0
  bnx2x: Fix enabling network interfaces without VFs
  Revert "Revert "ipv4: fix memory leaks in ip_cmsg_send() callers""
  tcp: fix tp->undo_retrans accounting in tcp_sacktag_one()
  net-caif: avoid user-triggerable WARN_ON(1)
  bpf, selftests: Add test case for mixed cgroup v1/v2
  bpf, selftests: Add cgroup v1 net_cls classid helpers
  bpf, cgroups: Fix cgroup v2 fallback on v1/v2 mixed mode
  bpf: Add oversize check before call kvcalloc()
  net: hns3: fix the timing issue of VF clearing interrupt sources
  net: hns3: fix the exception when query imp info
  net: hns3: disable mac in flr process
  ...

16 files changed, 62 insertions, 59 deletions

diff --git a/net/caif/chnl_net.c b/net/caif/chnl_net.c
index 37b67194c0df..414dc5671c45 100644
--- a/net/caif/chnl_net.c
+++ b/net/caif/chnl_net.c
@@ -53,20 +53,6 @@ struct chnl_net {
 	enum caif_states state;
 };
 
-static void robust_list_del(struct list_head *delete_node)
-{
-	struct list_head *list_node;
-	struct list_head *n;
-	ASSERT_RTNL();
-	list_for_each_safe(list_node, n, &chnl_net_list) {
-		if (list_node == delete_node) {
-			list_del(list_node);
-			return;
-		}
-	}
-	WARN_ON(1);
-}
-
 static int chnl_recv_cb(struct cflayer *layr, struct cfpkt *pkt)
 {
 	struct sk_buff *skb;
@@ -364,6 +350,7 @@ static int chnl_net_init(struct net_device *dev)
 	ASSERT_RTNL();
 	priv = netdev_priv(dev);
 	strncpy(priv->name, dev->name, sizeof(priv->name));
+	INIT_LIST_HEAD(&priv->list_field);
 	return 0;
 }
 
@@ -372,7 +359,7 @@ static void chnl_net_uninit(struct net_device *dev)
 	struct chnl_net *priv;
 	ASSERT_RTNL();
 	priv = netdev_priv(dev);
-	robust_list_del(&priv->list_field);
+	list_del_init(&priv->list_field);
 }
 
 static const struct net_device_ops netdev_ops = {
@@ -537,7 +524,7 @@ static void __exit chnl_exit_module(void)
 	rtnl_lock();
 	list_for_each_safe(list_node, _tmp, &chnl_net_list) {
 		dev = list_entry(list_node, struct chnl_net, list_field);
-		list_del(list_node);
+		list_del_init(list_node);
 		delete_device(dev);
 	}
 	rtnl_unlock();
diff --git a/net/core/netclassid_cgroup.c b/net/core/netclassid_cgroup.c
index b49c57d35a88..1a6a86693b74 100644
--- a/net/core/netclassid_cgroup.c
+++ b/net/core/netclassid_cgroup.c
@@ -71,11 +71,8 @@ static int update_classid_sock(const void *v, struct file *file, unsigned n)
 	struct update_classid_context *ctx = (void *)v;
 	struct socket *sock = sock_from_file(file);
 
-	if (sock) {
-		spin_lock(&cgroup_sk_update_lock);
+	if (sock)
 		sock_cgroup_set_classid(&sock->sk->sk_cgrp_data, ctx->classid);
-		spin_unlock(&cgroup_sk_update_lock);
-	}
 	if (--ctx->batch == 0) {
 		ctx->batch = UPDATE_CLASSID_BATCH;
 		return n + 1;
@@ -121,8 +118,6 @@ static int write_classid(struct cgroup_subsys_state *css, struct cftype *cft,
 	struct css_task_iter it;
 	struct task_struct *p;
 
-	cgroup_sk_alloc_disable();
-
 	cs->classid = (u32)value;
 
 	css_task_iter_start(css, 0, &it);
diff --git a/net/core/netprio_cgroup.c b/net/core/netprio_cgroup.c
index 99a431c56f23..8456dfbe2eb4 100644
--- a/net/core/netprio_cgroup.c
+++ b/net/core/netprio_cgroup.c
@@ -207,8 +207,6 @@ static ssize_t write_priomap(struct kernfs_open_file *of,
 	if (!dev)
 		return -ENODEV;
 
-	cgroup_sk_alloc_disable();
-
 	rtnl_lock();
 
 	ret = netprio_set_prio(of_css(of), dev, prio);
@@ -221,12 +219,10 @@ static ssize_t write_priomap(struct kernfs_open_file *of,
 static int update_netprio(const void *v, struct file *file, unsigned n)
 {
 	struct socket *sock = sock_from_file(file);
-	if (sock) {
-		spin_lock(&cgroup_sk_update_lock);
+
+	if (sock)
 		sock_cgroup_set_prioidx(&sock->sk->sk_cgrp_data,
 					(unsigned long)v);
-		spin_unlock(&cgroup_sk_update_lock);
-	}
 	return 0;
 }
 
@@ -235,8 +231,6 @@ static void net_prio_attach(struct cgroup_taskset *tset)
 	struct task_struct *p;
 	struct cgroup_subsys_state *css;
 
-	cgroup_sk_alloc_disable();
-
 	cgroup_taskset_for_each(p, css, tset) {
 		void *v = (void *)(unsigned long)css->id;
 
diff --git a/net/dccp/minisocks.c b/net/dccp/minisocks.c
index c5c74a34d139..91e7a2202697 100644
--- a/net/dccp/minisocks.c
+++ b/net/dccp/minisocks.c
@@ -94,6 +94,8 @@ struct sock *dccp_create_openreq_child(const struct sock *sk,
 		newdp->dccps_role	    = DCCP_ROLE_SERVER;
 		newdp->dccps_hc_rx_ackvec   = NULL;
 		newdp->dccps_service_list   = NULL;
+		newdp->dccps_hc_rx_ccid     = NULL;
+		newdp->dccps_hc_tx_ccid     = NULL;
 		newdp->dccps_service	    = dreq->dreq_service;
 		newdp->dccps_timestamp_echo = dreq->dreq_timestamp_echo;
 		newdp->dccps_timestamp_time = dreq->dreq_timestamp_time;
diff --git a/net/dsa/dsa.c b/net/dsa/dsa.c
index 1dc45e40f961..41f36ad8b0ec 100644
--- a/net/dsa/dsa.c
+++ b/net/dsa/dsa.c
@@ -345,6 +345,11 @@ bool dsa_schedule_work(struct work_struct *work)
 	return queue_work(dsa_owq, work);
 }
 
+void dsa_flush_workqueue(void)
+{
+	flush_workqueue(dsa_owq);
+}
+
 int dsa_devlink_param_get(struct devlink *dl, u32 id,
 			  struct devlink_param_gset_ctx *ctx)
 {
diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c
index 1b2b25d7bd02..eef13cd20f19 100644
--- a/net/dsa/dsa2.c
+++ b/net/dsa/dsa2.c
@@ -897,6 +897,33 @@ static void dsa_switch_teardown(struct dsa_switch *ds)
 	ds->setup = false;
 }
 
+/* First tear down the non-shared, then the shared ports. This ensures that
+ * all work items scheduled by our switchdev handlers for user ports have
+ * completed before we destroy the refcounting kept on the shared ports.
+ */
+static void dsa_tree_teardown_ports(struct dsa_switch_tree *dst)
+{
+	struct dsa_port *dp;
+
+	list_for_each_entry(dp, &dst->ports, list)
+		if (dsa_port_is_user(dp) || dsa_port_is_unused(dp))
+			dsa_port_teardown(dp);
+
+	dsa_flush_workqueue();
+
+	list_for_each_entry(dp, &dst->ports, list)
+		if (dsa_port_is_dsa(dp) || dsa_port_is_cpu(dp))
+			dsa_port_teardown(dp);
+}
+
+static void dsa_tree_teardown_switches(struct dsa_switch_tree *dst)
+{
+	struct dsa_port *dp;
+
+	list_for_each_entry(dp, &dst->ports, list)
+		dsa_switch_teardown(dp->ds);
+}
+
 static int dsa_tree_setup_switches(struct dsa_switch_tree *dst)
 {
 	struct dsa_port *dp;
@@ -923,26 +950,13 @@ static int dsa_tree_setup_switches(struct dsa_switch_tree *dst)
 	return 0;
 
 teardown:
-	list_for_each_entry(dp, &dst->ports, list)
-		dsa_port_teardown(dp);
+	dsa_tree_teardown_ports(dst);
 
-	list_for_each_entry(dp, &dst->ports, list)
-		dsa_switch_teardown(dp->ds);
+	dsa_tree_teardown_switches(dst);
 
 	return err;
 }
 
-static void dsa_tree_teardown_switches(struct dsa_switch_tree *dst)
-{
-	struct dsa_port *dp;
-
-	list_for_each_entry(dp, &dst->ports, list)
-		dsa_port_teardown(dp);
-
-	list_for_each_entry(dp, &dst->ports, list)
-		dsa_switch_teardown(dp->ds);
-}
-
 static int dsa_tree_setup_master(struct dsa_switch_tree *dst)
 {
 	struct dsa_port *dp;
@@ -1052,6 +1066,8 @@ static void dsa_tree_teardown(struct dsa_switch_tree *dst)
 
 	dsa_tree_teardown_master(dst);
 
+	dsa_tree_teardown_ports(dst);
+
 	dsa_tree_teardown_switches(dst);
 
 	dsa_tree_teardown_cpu_ports(dst);
diff --git a/net/dsa/dsa_priv.h b/net/dsa/dsa_priv.h
index 33ab7d7af9eb..a5c9bc7b66c6 100644
--- a/net/dsa/dsa_priv.h
+++ b/net/dsa/dsa_priv.h
@@ -170,6 +170,7 @@ void dsa_tag_driver_put(const struct dsa_device_ops *ops);
 const struct dsa_device_ops *dsa_find_tagger_by_name(const char *buf);
 
 bool dsa_schedule_work(struct work_struct *work);
+void dsa_flush_workqueue(void);
 const char *dsa_tag_protocol_to_str(const struct dsa_device_ops *ops);
 
 static inline int dsa_tag_protocol_overhead(const struct dsa_device_ops *ops)
diff --git a/net/dsa/slave.c b/net/dsa/slave.c
index 662ff531d4e2..a2bf2d8ac65b 100644
--- a/net/dsa/slave.c
+++ b/net/dsa/slave.c
@@ -1854,13 +1854,11 @@ static int dsa_slave_phy_setup(struct net_device *slave_dev)
 		 * use the switch internal MDIO bus instead
 		 */
 		ret = dsa_slave_phy_connect(slave_dev, dp->index, phy_flags);
-		if (ret) {
-			netdev_err(slave_dev,
-				   "failed to connect to port %d: %d\n",
-				   dp->index, ret);
-			phylink_destroy(dp->pl);
-			return ret;
-		}
+	}
+	if (ret) {
+		netdev_err(slave_dev, "failed to connect to PHY: %pe\n",
+			   ERR_PTR(ret));
+		phylink_destroy(dp->pl);
 	}
 
 	return ret;
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 3f7bd7ae7d7a..141e85e6422b 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -1346,7 +1346,7 @@ static u8 tcp_sacktag_one(struct sock *sk,
 	if (dup_sack && (sacked & TCPCB_RETRANS)) {
 		if (tp->undo_marker && tp->undo_retrans > 0 &&
 		    after(end_seq, tp->undo_marker))
-			tp->undo_retrans--;
+			tp->undo_retrans = max_t(int, 0, tp->undo_retrans - pcount);
 		if ((sacked & TCPCB_SACKED_ACKED) &&
 		    before(start_seq, state->reord))
 				state->reord = start_seq;
diff --git a/net/ipv4/udp_tunnel_nic.c b/net/ipv4/udp_tunnel_nic.c
index 0d122edc368d..b91003538d87 100644
--- a/net/ipv4/udp_tunnel_nic.c
+++ b/net/ipv4/udp_tunnel_nic.c
@@ -935,7 +935,7 @@ static int __init udp_tunnel_nic_init_module(void)
 {
 	int err;
 
-	udp_tunnel_nic_workqueue = alloc_workqueue("udp_tunnel_nic", 0, 0);
+	udp_tunnel_nic_workqueue = alloc_ordered_workqueue("udp_tunnel_nic", 0);
 	if (!udp_tunnel_nic_workqueue)
 		return -ENOMEM;
 
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index 1bec5b22f80d..0371d2c14145 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -1378,7 +1378,6 @@ int fib6_add(struct fib6_node *root, struct fib6_info *rt,
 	int err = -ENOMEM;
 	int allow_create = 1;
 	int replace_required = 0;
-	int sernum = fib6_new_sernum(info->nl_net);
 
 	if (info->nlh) {
 		if (!(info->nlh->nlmsg_flags & NLM_F_CREATE))
@@ -1478,7 +1477,7 @@ int fib6_add(struct fib6_node *root, struct fib6_info *rt,
 	if (!err) {
 		if (rt->nh)
 			list_add(&rt->nh_list, &rt->nh->f6i_list);
-		__fib6_update_sernum_upto_root(rt, sernum);
+		__fib6_update_sernum_upto_root(rt, fib6_new_sernum(info->nl_net));
 		fib6_start_gc(info->nl_net, rt);
 	}
 
diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index 53486b162f01..93271a2632b8 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -869,8 +869,10 @@ static int l2tp_udp_recv_core(struct l2tp_tunnel *tunnel, struct sk_buff *skb)
 	}
 
 	if (tunnel->version == L2TP_HDR_VER_3 &&
-	    l2tp_v3_ensure_opt_in_linear(session, skb, &ptr, &optr))
+	    l2tp_v3_ensure_opt_in_linear(session, skb, &ptr, &optr)) {
+		l2tp_session_dec_refcount(session);
 		goto invalid;
+	}
 
 	l2tp_recv_common(session, skb, ptr, optr, hdrflags, length);
 	l2tp_session_dec_refcount(session);
diff --git a/net/mctp/route.c b/net/mctp/route.c
index 5265525011ad..5ca186d53cb0 100644
--- a/net/mctp/route.c
+++ b/net/mctp/route.c
@@ -1083,8 +1083,10 @@ static void __net_exit mctp_routes_net_exit(struct net *net)
 {
 	struct mctp_route *rt;
 
+	rcu_read_lock();
 	list_for_each_entry_rcu(rt, &net->mctp.routes, list)
 		mctp_route_release(rt);
+	rcu_read_unlock();
 }
 
 static struct pernet_operations mctp_net_ops = {
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 543365f58e97..2a2bc64f75cf 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -46,6 +46,8 @@
  *					Copyright (C) 2011, <lokec@ccs.neu.edu>
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/ethtool.h>
 #include <linux/types.h>
 #include <linux/mm.h>
diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index a0a27d87f631..ad570c2450be 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -2423,7 +2423,7 @@ static int tipc_sk_backlog_rcv(struct sock *sk, struct sk_buff *skb)
 static void tipc_sk_enqueue(struct sk_buff_head *inputq, struct sock *sk,
 			    u32 dport, struct sk_buff_head *xmitq)
 {
-	unsigned long time_limit = jiffies + 2;
+	unsigned long time_limit = jiffies + usecs_to_jiffies(20000);
 	struct sk_buff *skb;
 	unsigned int lim;
 	atomic_t *dcnt;
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index eb47b9de2380..92345c9bb60c 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -3073,7 +3073,7 @@ static __poll_t unix_dgram_poll(struct file *file, struct socket *sock,
 
 		other = unix_peer(sk);
 		if (other && unix_peer(other) != sk &&
-		    unix_recvq_full(other) &&
+		    unix_recvq_full_lockless(other) &&
 		    unix_dgram_peer_wake_me(sk, other))
 			writable = 0;