Merge tag 'net-6.0-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

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

  Current release - regressions:

   - tcp: fix cleanup and leaks in tcp_read_skb() (the new way BPF
     socket maps get data out of the TCP stack)

   - tls: rx: react to strparser initialization errors

   - netfilter: nf_tables: fix scheduling-while-atomic splat

   - net: fix suspicious RCU usage in bpf_sk_reuseport_detach()

  Current release - new code bugs:

   - mlxsw: ptp: fix a couple of races, static checker warnings and
     error handling

  Previous releases - regressions:

   - netfilter:
      - nf_tables: fix possible module reference underflow in error path
      - make conntrack helpers deal with BIG TCP (skbs > 64kB)
      - nfnetlink: re-enable conntrack expectation events

   - net: fix potential refcount leak in ndisc_router_discovery()

  Previous releases - always broken:

   - sched: cls_route: disallow handle of 0

   - neigh: fix possible local DoS due to net iface start/stop loop

   - rtnetlink: fix module refcount leak in rtnetlink_rcv_msg

   - sched: fix adding qlen to qcpu->backlog in gnet_stats_add_queue_cpu

   - virtio_net: fix endian-ness for RSS

   - dsa: mv88e6060: prevent crash on an unused port

   - fec: fix timer capture timing in `fec_ptp_enable_pps()`

   - ocelot: stats: fix races, integer wrapping and reading incorrect
     registers (the change of register definitions here accounts for
     bulk of the changed LoC in this PR)"

* tag 'net-6.0-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (77 commits)
  net: moxa: MAC address reading, generating, validity checking
  tcp: handle pure FIN case correctly
  tcp: refactor tcp_read_skb() a bit
  tcp: fix tcp_cleanup_rbuf() for tcp_read_skb()
  tcp: fix sock skb accounting in tcp_read_skb()
  igb: Add lock to avoid data race
  dt-bindings: Fix incorrect "the the" corrections
  net: genl: fix error path memory leak in policy dumping
  stmmac: intel: Add a missing clk_disable_unprepare() call in intel_eth_pci_remove()
  net: ethernet: mtk_eth_soc: fix possible NULL pointer dereference in mtk_xdp_run
  net/mlx5e: Allocate flow steering storage during uplink initialization
  net: mscc: ocelot: report ndo_get_stats64 from the wraparound-resistant ocelot->stats
  net: mscc: ocelot: keep ocelot_stat_layout by reg address, not offset
  net: mscc: ocelot: make struct ocelot_stat_layout array indexable
  net: mscc: ocelot: fix race between ndo_get_stats64 and ocelot_check_stats_work
  net: mscc: ocelot: turn stats_lock into a spinlock
  net: mscc: ocelot: fix address of SYS_COUNT_TX_AGING counter
  net: mscc: ocelot: fix incorrect ndo_get_stats64 packet counters
  net: dsa: felix: fix ethtool 256-511 and 512-1023 TX packet counters
  net: dsa: don't warn in dsa_port_set_state_now() when driver doesn't support it
  ...

4 files changed, 42 insertions, 12 deletions

diff --git a/net/core/gen_stats.c b/net/core/gen_stats.c
index a10335b4ba2d..c8d137ef5980 100644
--- a/net/core/gen_stats.c
+++ b/net/core/gen_stats.c
@@ -345,7 +345,7 @@ static void gnet_stats_add_queue_cpu(struct gnet_stats_queue *qstats,
 	for_each_possible_cpu(i) {
 		const struct gnet_stats_queue *qcpu = per_cpu_ptr(q, i);
 
-		qstats->qlen += qcpu->backlog;
+		qstats->qlen += qcpu->qlen;
 		qstats->backlog += qcpu->backlog;
 		qstats->drops += qcpu->drops;
 		qstats->requeues += qcpu->requeues;
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index 6a8c2596ebab..5b669eb80270 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -307,14 +307,32 @@ static int neigh_del_timer(struct neighbour *n)
 	return 0;
 }
 
-static void pneigh_queue_purge(struct sk_buff_head *list)
+static void pneigh_queue_purge(struct sk_buff_head *list, struct net *net)
 {
+	unsigned long flags;
 	struct sk_buff *skb;
 
-	while ((skb = skb_dequeue(list)) != NULL) {
-		dev_put(skb->dev);
-		kfree_skb(skb);
+	spin_lock_irqsave(&list->lock, flags);
+	skb = skb_peek(list);
+	while (skb != NULL) {
+		struct sk_buff *skb_next = skb_peek_next(skb, list);
+		struct net_device *dev = skb->dev;
+		if (net == NULL || net_eq(dev_net(dev), net)) {
+			struct in_device *in_dev;
+
+			rcu_read_lock();
+			in_dev = __in_dev_get_rcu(dev);
+			if (in_dev)
+				in_dev->arp_parms->qlen--;
+			rcu_read_unlock();
+			__skb_unlink(skb, list);
+
+			dev_put(dev);
+			kfree_skb(skb);
+		}
+		skb = skb_next;
 	}
+	spin_unlock_irqrestore(&list->lock, flags);
 }
 
 static void neigh_flush_dev(struct neigh_table *tbl, struct net_device *dev,
@@ -385,9 +403,9 @@ static int __neigh_ifdown(struct neigh_table *tbl, struct net_device *dev,
 	write_lock_bh(&tbl->lock);
 	neigh_flush_dev(tbl, dev, skip_perm);
 	pneigh_ifdown_and_unlock(tbl, dev);
-
-	del_timer_sync(&tbl->proxy_timer);
-	pneigh_queue_purge(&tbl->proxy_queue);
+	pneigh_queue_purge(&tbl->proxy_queue, dev_net(dev));
+	if (skb_queue_empty_lockless(&tbl->proxy_queue))
+		del_timer_sync(&tbl->proxy_timer);
 	return 0;
 }
 
@@ -1597,8 +1615,15 @@ static void neigh_proxy_process(struct timer_list *t)
 
 		if (tdif <= 0) {
 			struct net_device *dev = skb->dev;
+			struct in_device *in_dev;
 
+			rcu_read_lock();
+			in_dev = __in_dev_get_rcu(dev);
+			if (in_dev)
+				in_dev->arp_parms->qlen--;
+			rcu_read_unlock();
 			__skb_unlink(skb, &tbl->proxy_queue);
+
 			if (tbl->proxy_redo && netif_running(dev)) {
 				rcu_read_lock();
 				tbl->proxy_redo(skb);
@@ -1623,7 +1648,7 @@ void pneigh_enqueue(struct neigh_table *tbl, struct neigh_parms *p,
 	unsigned long sched_next = jiffies +
 			prandom_u32_max(NEIGH_VAR(p, PROXY_DELAY));
 
-	if (tbl->proxy_queue.qlen > NEIGH_VAR(p, PROXY_QLEN)) {
+	if (p->qlen > NEIGH_VAR(p, PROXY_QLEN)) {
 		kfree_skb(skb);
 		return;
 	}
@@ -1639,6 +1664,7 @@ void pneigh_enqueue(struct neigh_table *tbl, struct neigh_parms *p,
 	skb_dst_drop(skb);
 	dev_hold(skb->dev);
 	__skb_queue_tail(&tbl->proxy_queue, skb);
+	p->qlen++;
 	mod_timer(&tbl->proxy_timer, sched_next);
 	spin_unlock(&tbl->proxy_queue.lock);
 }
@@ -1671,6 +1697,7 @@ struct neigh_parms *neigh_parms_alloc(struct net_device *dev,
 		refcount_set(&p->refcnt, 1);
 		p->reachable_time =
 				neigh_rand_reach_time(NEIGH_VAR(p, BASE_REACHABLE_TIME));
+		p->qlen = 0;
 		netdev_hold(dev, &p->dev_tracker, GFP_KERNEL);
 		p->dev = dev;
 		write_pnet(&p->net, net);
@@ -1736,6 +1763,7 @@ void neigh_table_init(int index, struct neigh_table *tbl)
 	refcount_set(&tbl->parms.refcnt, 1);
 	tbl->parms.reachable_time =
 			  neigh_rand_reach_time(NEIGH_VAR(&tbl->parms, BASE_REACHABLE_TIME));
+	tbl->parms.qlen = 0;
 
 	tbl->stats = alloc_percpu(struct neigh_statistics);
 	if (!tbl->stats)
@@ -1787,7 +1815,7 @@ int neigh_table_clear(int index, struct neigh_table *tbl)
 	cancel_delayed_work_sync(&tbl->managed_work);
 	cancel_delayed_work_sync(&tbl->gc_work);
 	del_timer_sync(&tbl->proxy_timer);
-	pneigh_queue_purge(&tbl->proxy_queue);
+	pneigh_queue_purge(&tbl->proxy_queue, NULL);
 	neigh_ifdown(tbl, NULL);
 	if (atomic_read(&tbl->entries))
 		pr_crit("neighbour leakage\n");
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index ac45328607f7..4b5b15c684ed 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -6070,6 +6070,7 @@ static int rtnetlink_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh,
 	if (kind == RTNL_KIND_DEL && (nlh->nlmsg_flags & NLM_F_BULK) &&
 	    !(flags & RTNL_FLAG_BULK_DEL_SUPPORTED)) {
 		NL_SET_ERR_MSG(extack, "Bulk delete is not supported");
+		module_put(owner);
 		goto err_unlock;
 	}
 
diff --git a/net/core/skmsg.c b/net/core/skmsg.c
index f47338d89d5d..59e75ffcc1f4 100644
--- a/net/core/skmsg.c
+++ b/net/core/skmsg.c
@@ -1194,8 +1194,9 @@ static int sk_psock_verdict_recv(struct sock *sk, struct sk_buff *skb)
 		ret = bpf_prog_run_pin_on_cpu(prog, skb);
 		ret = sk_psock_map_verd(ret, skb_bpf_redirect_fetch(skb));
 	}
-	if (sk_psock_verdict_apply(psock, skb, ret) < 0)
-		len = 0;
+	ret = sk_psock_verdict_apply(psock, skb, ret);
+	if (ret < 0)
+		len = ret;
 out:
 	rcu_read_unlock();
 	return len;