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

Pull networking fixes from David Miller:
 "Various fixes, all over:

   1) Fix overflow in ptp_qoriq_adjfine(), from Yangbo Lu.

   2) Always store the rx queue mapping in veth, from Maciej
      Fijalkowski.

   3) Don't allow vmlinux btf in map_create, from Alexei Starovoitov.

   4) Fix memory leak in octeontx2-af from Colin Ian King.

   5) Use kvalloc in bpf x86 JIT for storing jit'd addresses, from
      Yonghong Song.

   6) Fix tx ptp stats in mlx5, from Aya Levin.

   7) Check correct ip version in tun decap, fropm Roi Dayan.

   8) Fix rate calculation in mlx5 E-Switch code, from arav Pandit.

   9) Work item memork leak in mlx5, from Shay Drory.

  10) Fix ip6ip6 tunnel crash with bpf, from Daniel Borkmann.

  11) Lack of preemptrion awareness in macvlan, from Eric Dumazet.

  12) Fix data race in pxa168_eth, from Pavel Andrianov.

  13) Range validate stab in red_check_params(), from Eric Dumazet.

  14) Inherit vlan filtering setting properly in b53 driver, from
      Florian Fainelli.

  15) Fix rtnl locking in igc driver, from Sasha Neftin.

  16) Pause handling fixes in igc driver, from Muhammad Husaini
      Zulkifli.

  17) Missing rtnl locking in e1000_reset_task, from Vitaly Lifshits.

  18) Use after free in qlcnic, from Lv Yunlong.

  19) fix crash in fritzpci mISDN, from Tong Zhang.

  20) Premature rx buffer reuse in igb, from Li RongQing.

  21) Missing termination of ip[a driver message handler arrays, from
      Alex Elder.

  22) Fix race between "x25_close" and "x25_xmit"/"x25_rx" in hdlc_x25
      driver, from Xie He.

  23) Use after free in c_can_pci_remove(), from Tong Zhang.

  24) Uninitialized variable use in nl80211, from Jarod Wilson.

  25) Off by one size calc in bpf verifier, from Piotr Krysiuk.

  26) Use delayed work instead of deferrable for flowtable GC, from
      Yinjun Zhang.

  27) Fix infinite loop in NPC unmap of octeontx2 driver, from
      Hariprasad Kelam.

  28) Fix being unable to change MTU of dwmac-sun8i devices due to lack
      of fifo sizes, from Corentin Labbe.

  29) DMA use after free in r8169 with WoL, fom Heiner Kallweit.

  30) Mismatched prototypes in isdn-capi, from Arnd Bergmann.

  31) Fix psample UAPI breakage, from Ido Schimmel"

* git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (171 commits)
  psample: Fix user API breakage
  math: Export mul_u64_u64_div_u64
  ch_ktls: fix enum-conversion warning
  octeontx2-af: Fix memory leak of object buf
  ptp_qoriq: fix overflow in ptp_qoriq_adjfine() u64 calcalation
  net: bridge: don't notify switchdev for local FDB addresses
  net/sched: act_ct: clear post_ct if doing ct_clear
  net: dsa: don't assign an error value to tag_ops
  isdn: capi: fix mismatched prototypes
  net/mlx5: SF, do not use ecpu bit for vhca state processing
  net/mlx5e: Fix division by 0 in mlx5e_select_queue
  net/mlx5e: Fix error path for ethtool set-priv-flag
  net/mlx5e: Offload tuple rewrite for non-CT flows
  net/mlx5e: Allow to match on MPLS parameters only for MPLS over UDP
  net/mlx5: Add back multicast stats for uplink representor
  net: ipconfig: ic_dev can be NULL in ic_close_devs
  MAINTAINERS: Combine "QLOGIC QLGE 10Gb ETHERNET DRIVER" sections into one
  docs: networking: Fix a typo
  r8169: fix DMA being used after buffer free if WoL is enabled
  net: ipa: fix init header command validation
  ...

6 files changed, 135 insertions, 38 deletions

diff --git a/net/core/dev.c b/net/core/dev.c
index 6c5967e80132..0f72ff5d34ba 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1184,6 +1184,18 @@ static int __dev_alloc_name(struct net *net, const char *name, char *buf)
 			return -ENOMEM;
 
 		for_each_netdev(net, d) {
+			struct netdev_name_node *name_node;
+			list_for_each_entry(name_node, &d->name_node->list, list) {
+				if (!sscanf(name_node->name, name, &i))
+					continue;
+				if (i < 0 || i >= max_netdevices)
+					continue;
+
+				/*  avoid cases where sscanf is not exact inverse of printf */
+				snprintf(buf, IFNAMSIZ, name, i);
+				if (!strncmp(buf, name_node->name, IFNAMSIZ))
+					set_bit(i, inuse);
+			}
 			if (!sscanf(d->name, name, &i))
 				continue;
 			if (i < 0 || i >= max_netdevices)
@@ -4294,6 +4306,13 @@ static inline void ____napi_schedule(struct softnet_data *sd,
 		 */
 		thread = READ_ONCE(napi->thread);
 		if (thread) {
+			/* Avoid doing set_bit() if the thread is in
+			 * INTERRUPTIBLE state, cause napi_thread_wait()
+			 * makes sure to proceed with napi polling
+			 * if the thread is explicitly woken from here.
+			 */
+			if (READ_ONCE(thread->state) != TASK_INTERRUPTIBLE)
+				set_bit(NAPI_STATE_SCHED_THREADED, &napi->state);
 			wake_up_process(thread);
 			return;
 		}
@@ -6486,6 +6505,7 @@ bool napi_complete_done(struct napi_struct *n, int work_done)
 		WARN_ON_ONCE(!(val & NAPIF_STATE_SCHED));
 
 		new = val & ~(NAPIF_STATE_MISSED | NAPIF_STATE_SCHED |
+			      NAPIF_STATE_SCHED_THREADED |
 			      NAPIF_STATE_PREFER_BUSY_POLL);
 
 		/* If STATE_MISSED was set, leave STATE_SCHED set,
@@ -6968,16 +6988,25 @@ static int napi_poll(struct napi_struct *n, struct list_head *repoll)
 
 static int napi_thread_wait(struct napi_struct *napi)
 {
+	bool woken = false;
+
 	set_current_state(TASK_INTERRUPTIBLE);
 
 	while (!kthread_should_stop() && !napi_disable_pending(napi)) {
-		if (test_bit(NAPI_STATE_SCHED, &napi->state)) {
+		/* Testing SCHED_THREADED bit here to make sure the current
+		 * kthread owns this napi and could poll on this napi.
+		 * Testing SCHED bit is not enough because SCHED bit might be
+		 * set by some other busy poll thread or by napi_disable().
+		 */
+		if (test_bit(NAPI_STATE_SCHED_THREADED, &napi->state) || woken) {
 			WARN_ON(!list_empty(&napi->poll_list));
 			__set_current_state(TASK_RUNNING);
 			return 0;
 		}
 
 		schedule();
+		/* woken being true indicates this thread owns this napi. */
+		woken = true;
 		set_current_state(TASK_INTERRUPTIBLE);
 	}
 	__set_current_state(TASK_RUNNING);
@@ -11346,7 +11375,7 @@ static void __net_exit default_device_exit(struct net *net)
 			continue;
 
 		/* Leave virtual devices for the generic cleanup */
-		if (dev->rtnl_link_ops)
+		if (dev->rtnl_link_ops && !dev->rtnl_link_ops->netns_refund)
 			continue;
 
 		/* Push remaining network devices to init_net */
diff --git a/net/core/drop_monitor.c b/net/core/drop_monitor.c
index 571f191c06d9..db65ce62b625 100644
--- a/net/core/drop_monitor.c
+++ b/net/core/drop_monitor.c
@@ -1053,6 +1053,20 @@ static int net_dm_hw_monitor_start(struct netlink_ext_ack *extack)
 	return 0;
 
 err_module_put:
+	for_each_possible_cpu(cpu) {
+		struct per_cpu_dm_data *hw_data = &per_cpu(dm_hw_cpu_data, cpu);
+		struct sk_buff *skb;
+
+		del_timer_sync(&hw_data->send_timer);
+		cancel_work_sync(&hw_data->dm_alert_work);
+		while ((skb = __skb_dequeue(&hw_data->drop_queue))) {
+			struct devlink_trap_metadata *hw_metadata;
+
+			hw_metadata = NET_DM_SKB_CB(skb)->hw_metadata;
+			net_dm_hw_metadata_free(hw_metadata);
+			consume_skb(skb);
+		}
+	}
 	module_put(THIS_MODULE);
 	return rc;
 }
@@ -1134,6 +1148,15 @@ static int net_dm_trace_on_set(struct netlink_ext_ack *extack)
 err_unregister_trace:
 	unregister_trace_kfree_skb(ops->kfree_skb_probe, NULL);
 err_module_put:
+	for_each_possible_cpu(cpu) {
+		struct per_cpu_dm_data *data = &per_cpu(dm_cpu_data, cpu);
+		struct sk_buff *skb;
+
+		del_timer_sync(&data->send_timer);
+		cancel_work_sync(&data->dm_alert_work);
+		while ((skb = __skb_dequeue(&data->drop_queue)))
+			consume_skb(skb);
+	}
 	module_put(THIS_MODULE);
 	return rc;
 }
diff --git a/net/core/dst.c b/net/core/dst.c
index 0c01bd8d9d81..fb3bcba87744 100644
--- a/net/core/dst.c
+++ b/net/core/dst.c
@@ -237,37 +237,62 @@ void __dst_destroy_metrics_generic(struct dst_entry *dst, unsigned long old)
 }
 EXPORT_SYMBOL(__dst_destroy_metrics_generic);
 
-static struct dst_ops md_dst_ops = {
-	.family =		AF_UNSPEC,
-};
+struct dst_entry *dst_blackhole_check(struct dst_entry *dst, u32 cookie)
+{
+	return NULL;
+}
 
-static int dst_md_discard_out(struct net *net, struct sock *sk, struct sk_buff *skb)
+u32 *dst_blackhole_cow_metrics(struct dst_entry *dst, unsigned long old)
 {
-	WARN_ONCE(1, "Attempting to call output on metadata dst\n");
-	kfree_skb(skb);
-	return 0;
+	return NULL;
 }
 
-static int dst_md_discard(struct sk_buff *skb)
+struct neighbour *dst_blackhole_neigh_lookup(const struct dst_entry *dst,
+					     struct sk_buff *skb,
+					     const void *daddr)
 {
-	WARN_ONCE(1, "Attempting to call input on metadata dst\n");
-	kfree_skb(skb);
-	return 0;
+	return NULL;
+}
+
+void dst_blackhole_update_pmtu(struct dst_entry *dst, struct sock *sk,
+			       struct sk_buff *skb, u32 mtu,
+			       bool confirm_neigh)
+{
+}
+EXPORT_SYMBOL_GPL(dst_blackhole_update_pmtu);
+
+void dst_blackhole_redirect(struct dst_entry *dst, struct sock *sk,
+			    struct sk_buff *skb)
+{
+}
+EXPORT_SYMBOL_GPL(dst_blackhole_redirect);
+
+unsigned int dst_blackhole_mtu(const struct dst_entry *dst)
+{
+	unsigned int mtu = dst_metric_raw(dst, RTAX_MTU);
+
+	return mtu ? : dst->dev->mtu;
 }
+EXPORT_SYMBOL_GPL(dst_blackhole_mtu);
+
+static struct dst_ops dst_blackhole_ops = {
+	.family		= AF_UNSPEC,
+	.neigh_lookup	= dst_blackhole_neigh_lookup,
+	.check		= dst_blackhole_check,
+	.cow_metrics	= dst_blackhole_cow_metrics,
+	.update_pmtu	= dst_blackhole_update_pmtu,
+	.redirect	= dst_blackhole_redirect,
+	.mtu		= dst_blackhole_mtu,
+};
 
 static void __metadata_dst_init(struct metadata_dst *md_dst,
 				enum metadata_type type, u8 optslen)
-
 {
 	struct dst_entry *dst;
 
 	dst = &md_dst->dst;
-	dst_init(dst, &md_dst_ops, NULL, 1, DST_OBSOLETE_NONE,
+	dst_init(dst, &dst_blackhole_ops, NULL, 1, DST_OBSOLETE_NONE,
 		 DST_METADATA | DST_NOCOUNT);
-
-	dst->input = dst_md_discard;
-	dst->output = dst_md_discard_out;
-
 	memset(dst + 1, 0, sizeof(*md_dst) + optslen - sizeof(*dst));
 	md_dst->type = type;
 }
diff --git a/net/core/filter.c b/net/core/filter.c
index adfdad234674..9323d34d34cc 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -5658,7 +5658,7 @@ BPF_CALL_5(bpf_skb_check_mtu, struct sk_buff *, skb,
 	if (unlikely(flags & ~(BPF_MTU_CHK_SEGS)))
 		return -EINVAL;
 
-	if (unlikely(flags & BPF_MTU_CHK_SEGS && len_diff))
+	if (unlikely(flags & BPF_MTU_CHK_SEGS && (len_diff || *mtu_len)))
 		return -EINVAL;
 
 	dev = __dev_via_ifindex(dev, ifindex);
@@ -5668,7 +5668,11 @@ BPF_CALL_5(bpf_skb_check_mtu, struct sk_buff *, skb,
 	mtu = READ_ONCE(dev->mtu);
 
 	dev_len = mtu + dev->hard_header_len;
-	skb_len = skb->len + len_diff; /* minus result pass check */
+
+	/* If set use *mtu_len as input, L3 as iph->tot_len (like fib_lookup) */
+	skb_len = *mtu_len ? *mtu_len + dev->hard_header_len : skb->len;
+
+	skb_len += len_diff; /* minus result pass check */
 	if (skb_len <= dev_len) {
 		ret = BPF_MTU_CHK_RET_SUCCESS;
 		goto out;
@@ -5713,6 +5717,10 @@ BPF_CALL_5(bpf_xdp_check_mtu, struct xdp_buff *, xdp,
 	/* Add L2-header as dev MTU is L3 size */
 	dev_len = mtu + dev->hard_header_len;
 
+	/* Use *mtu_len as input, L3 as iph->tot_len (like fib_lookup) */
+	if (*mtu_len)
+		xdp_len = *mtu_len + dev->hard_header_len;
+
 	xdp_len += len_diff; /* minus result pass check */
 	if (xdp_len > dev_len)
 		ret = BPF_MTU_CHK_RET_FRAG_NEEDED;
diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index 2ef2224b3bff..a96a4f5de0ce 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -176,7 +176,7 @@ void skb_flow_get_icmp_tci(const struct sk_buff *skb,
 	 * avoid confusion with packets without such field
 	 */
 	if (icmp_has_id(ih->type))
-		key_icmp->id = ih->un.echo.id ? : 1;
+		key_icmp->id = ih->un.echo.id ? ntohs(ih->un.echo.id) : 1;
 	else
 		key_icmp->id = 0;
 }
diff --git a/net/core/sock.c b/net/core/sock.c
index 0ed98f20448a..cc31b601ae10 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -3440,6 +3440,32 @@ static void tw_prot_cleanup(struct timewait_sock_ops *twsk_prot)
 	twsk_prot->twsk_slab = NULL;
 }
 
+static int tw_prot_init(const struct proto *prot)
+{
+	struct timewait_sock_ops *twsk_prot = prot->twsk_prot;
+
+	if (!twsk_prot)
+		return 0;
+
+	twsk_prot->twsk_slab_name = kasprintf(GFP_KERNEL, "tw_sock_%s",
+					      prot->name);
+	if (!twsk_prot->twsk_slab_name)
+		return -ENOMEM;
+
+	twsk_prot->twsk_slab =
+		kmem_cache_create(twsk_prot->twsk_slab_name,
+				  twsk_prot->twsk_obj_size, 0,
+				  SLAB_ACCOUNT | prot->slab_flags,
+				  NULL);
+	if (!twsk_prot->twsk_slab) {
+		pr_crit("%s: Can't create timewait sock SLAB cache!\n",
+			prot->name);
+		return -ENOMEM;
+	}
+
+	return 0;
+}
+
 static void req_prot_cleanup(struct request_sock_ops *rsk_prot)
 {
 	if (!rsk_prot)
@@ -3496,22 +3522,8 @@ int proto_register(struct proto *prot, int alloc_slab)
 		if (req_prot_init(prot))
 			goto out_free_request_sock_slab;
 
-		if (prot->twsk_prot != NULL) {
-			prot->twsk_prot->twsk_slab_name = kasprintf(GFP_KERNEL, "tw_sock_%s", prot->name);
-
-			if (prot->twsk_prot->twsk_slab_name == NULL)
-				goto out_free_request_sock_slab;
-
-			prot->twsk_prot->twsk_slab =
-				kmem_cache_create(prot->twsk_prot->twsk_slab_name,
-						  prot->twsk_prot->twsk_obj_size,
-						  0,
-						  SLAB_ACCOUNT |
-						  prot->slab_flags,
-						  NULL);
-			if (prot->twsk_prot->twsk_slab == NULL)
-				goto out_free_timewait_sock_slab;
-		}
+		if (tw_prot_init(prot))
+			goto out_free_timewait_sock_slab;
 	}
 
 	mutex_lock(&proto_list_mutex);