Merge tag 'net-5.17-rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Pull networking fixes from Jakub Kicinski:
 "Including fixes from bpf, netfilter, and ieee802154.

  Current release - regressions:

   - Partially revert "net/smc: Add netlink net namespace support", fix
     uABI breakage

   - netfilter:
      - nft_ct: fix use after free when attaching zone template
      - nft_byteorder: track register operations

  Previous releases - regressions:

   - ipheth: fix EOVERFLOW in ipheth_rcvbulk_callback

   - phy: qca8081: fix speeds lower than 2.5Gb/s

   - sched: fix use-after-free in tc_new_tfilter()

  Previous releases - always broken:

   - tcp: fix mem under-charging with zerocopy sendmsg()

   - tcp: add missing tcp_skb_can_collapse() test in
     tcp_shift_skb_data()

   - neigh: do not trigger immediate probes on NUD_FAILED from
     neigh_managed_work, avoid a deadlock

   - bpf: use VM_MAP instead of VM_ALLOC for ringbuf, avoid KASAN
     false-positives

   - netfilter: nft_reject_bridge: fix for missing reply from prerouting

   - smc: forward wakeup to smc socket waitqueue after fallback

   - ieee802154:
      - return meaningful error codes from the netlink helpers
      - mcr20a: fix lifs/sifs periods
      - at86rf230, ca8210: stop leaking skbs on error paths

   - macsec: add missing un-offload call for NETDEV_UNREGISTER of parent

   - ax25: add refcount in ax25_dev to avoid UAF bugs

   - eth: mlx5e:
      - fix SFP module EEPROM query
      - fix broken SKB allocation in HW-GRO
      - IPsec offload: fix tunnel mode crypto for non-TCP/UDP flows

   - eth: amd-xgbe:
      - fix skb data length underflow
      - ensure reset of the tx_timer_active flag, avoid Tx timeouts

   - eth: stmmac: fix runtime pm use in stmmac_dvr_remove()

   - eth: e1000e: handshake with CSME starts from Alder Lake platforms"

* tag 'net-5.17-rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (69 commits)
  ax25: fix reference count leaks of ax25_dev
  net: stmmac: ensure PTP time register reads are consistent
  net: ipa: request IPA register values be retained
  dt-bindings: net: qcom,ipa: add optional qcom,qmp property
  tools/resolve_btfids: Do not print any commands when building silently
  bpf: Use VM_MAP instead of VM_ALLOC for ringbuf
  net, neigh: Do not trigger immediate probes on NUD_FAILED from neigh_managed_work
  tcp: add missing tcp_skb_can_collapse() test in tcp_shift_skb_data()
  net: sparx5: do not refer to skb after passing it on
  Partially revert "net/smc: Add netlink net namespace support"
  net/mlx5e: Avoid field-overflowing memcpy()
  net/mlx5e: Use struct_group() for memcpy() region
  net/mlx5e: Avoid implicit modify hdr for decap drop rule
  net/mlx5e: IPsec: Fix tunnel mode crypto offload for non TCP/UDP traffic
  net/mlx5e: IPsec: Fix crypto offload for non TCP/UDP encapsulated traffic
  net/mlx5e: Don't treat small ceil values as unlimited in HTB offload
  net/mlx5: E-Switch, Fix uninitialized variable modact
  net/mlx5e: Fix handling of wrong devices during bond netevent
  net/mlx5e: Fix broken SKB allocation in HW-GRO
  net/mlx5e: Fix wrong calculation of header index in HW_GRO
  ...

21 files changed, 247 insertions, 69 deletions

diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c
index 02f43f3e2c5640..3e49d28824ed9b 100644
--- a/net/ax25/af_ax25.c
+++ b/net/ax25/af_ax25.c
@@ -77,6 +77,7 @@ static void ax25_kill_by_device(struct net_device *dev)
 {
 	ax25_dev *ax25_dev;
 	ax25_cb *s;
+	struct sock *sk;
 
 	if ((ax25_dev = ax25_dev_ax25dev(dev)) == NULL)
 		return;
@@ -85,13 +86,16 @@ static void ax25_kill_by_device(struct net_device *dev)
 again:
 	ax25_for_each(s, &ax25_list) {
 		if (s->ax25_dev == ax25_dev) {
+			sk = s->sk;
+			sock_hold(sk);
 			spin_unlock_bh(&ax25_list_lock);
-			lock_sock(s->sk);
+			lock_sock(sk);
 			s->ax25_dev = NULL;
-			release_sock(s->sk);
+			ax25_dev_put(ax25_dev);
+			release_sock(sk);
 			ax25_disconnect(s, ENETUNREACH);
 			spin_lock_bh(&ax25_list_lock);
-
+			sock_put(sk);
 			/* The entry could have been deleted from the
 			 * list meanwhile and thus the next pointer is
 			 * no longer valid.  Play it safe and restart
@@ -355,21 +359,25 @@ static int ax25_ctl_ioctl(const unsigned int cmd, void __user *arg)
 	if (copy_from_user(&ax25_ctl, arg, sizeof(ax25_ctl)))
 		return -EFAULT;
 
-	if ((ax25_dev = ax25_addr_ax25dev(&ax25_ctl.port_addr)) == NULL)
-		return -ENODEV;
-
 	if (ax25_ctl.digi_count > AX25_MAX_DIGIS)
 		return -EINVAL;
 
 	if (ax25_ctl.arg > ULONG_MAX / HZ && ax25_ctl.cmd != AX25_KILL)
 		return -EINVAL;
 
+	ax25_dev = ax25_addr_ax25dev(&ax25_ctl.port_addr);
+	if (!ax25_dev)
+		return -ENODEV;
+
 	digi.ndigi = ax25_ctl.digi_count;
 	for (k = 0; k < digi.ndigi; k++)
 		digi.calls[k] = ax25_ctl.digi_addr[k];
 
-	if ((ax25 = ax25_find_cb(&ax25_ctl.source_addr, &ax25_ctl.dest_addr, &digi, ax25_dev->dev)) == NULL)
+	ax25 = ax25_find_cb(&ax25_ctl.source_addr, &ax25_ctl.dest_addr, &digi, ax25_dev->dev);
+	if (!ax25) {
+		ax25_dev_put(ax25_dev);
 		return -ENOTCONN;
+	}
 
 	switch (ax25_ctl.cmd) {
 	case AX25_KILL:
@@ -436,6 +444,7 @@ static int ax25_ctl_ioctl(const unsigned int cmd, void __user *arg)
 	  }
 
 out_put:
+	ax25_dev_put(ax25_dev);
 	ax25_cb_put(ax25);
 	return ret;
 
diff --git a/net/ax25/ax25_dev.c b/net/ax25/ax25_dev.c
index 256fadb94df312..d2a244e1c260f3 100644
--- a/net/ax25/ax25_dev.c
+++ b/net/ax25/ax25_dev.c
@@ -37,6 +37,7 @@ ax25_dev *ax25_addr_ax25dev(ax25_address *addr)
 	for (ax25_dev = ax25_dev_list; ax25_dev != NULL; ax25_dev = ax25_dev->next)
 		if (ax25cmp(addr, (const ax25_address *)ax25_dev->dev->dev_addr) == 0) {
 			res = ax25_dev;
+			ax25_dev_hold(ax25_dev);
 		}
 	spin_unlock_bh(&ax25_dev_lock);
 
@@ -56,6 +57,7 @@ void ax25_dev_device_up(struct net_device *dev)
 		return;
 	}
 
+	refcount_set(&ax25_dev->refcount, 1);
 	dev->ax25_ptr     = ax25_dev;
 	ax25_dev->dev     = dev;
 	dev_hold_track(dev, &ax25_dev->dev_tracker, GFP_ATOMIC);
@@ -84,6 +86,7 @@ void ax25_dev_device_up(struct net_device *dev)
 	ax25_dev->next = ax25_dev_list;
 	ax25_dev_list  = ax25_dev;
 	spin_unlock_bh(&ax25_dev_lock);
+	ax25_dev_hold(ax25_dev);
 
 	ax25_register_dev_sysctl(ax25_dev);
 }
@@ -113,9 +116,10 @@ void ax25_dev_device_down(struct net_device *dev)
 	if ((s = ax25_dev_list) == ax25_dev) {
 		ax25_dev_list = s->next;
 		spin_unlock_bh(&ax25_dev_lock);
+		ax25_dev_put(ax25_dev);
 		dev->ax25_ptr = NULL;
 		dev_put_track(dev, &ax25_dev->dev_tracker);
-		kfree(ax25_dev);
+		ax25_dev_put(ax25_dev);
 		return;
 	}
 
@@ -123,9 +127,10 @@ void ax25_dev_device_down(struct net_device *dev)
 		if (s->next == ax25_dev) {
 			s->next = ax25_dev->next;
 			spin_unlock_bh(&ax25_dev_lock);
+			ax25_dev_put(ax25_dev);
 			dev->ax25_ptr = NULL;
 			dev_put_track(dev, &ax25_dev->dev_tracker);
-			kfree(ax25_dev);
+			ax25_dev_put(ax25_dev);
 			return;
 		}
 
@@ -133,6 +138,7 @@ void ax25_dev_device_down(struct net_device *dev)
 	}
 	spin_unlock_bh(&ax25_dev_lock);
 	dev->ax25_ptr = NULL;
+	ax25_dev_put(ax25_dev);
 }
 
 int ax25_fwd_ioctl(unsigned int cmd, struct ax25_fwd_struct *fwd)
@@ -144,20 +150,32 @@ int ax25_fwd_ioctl(unsigned int cmd, struct ax25_fwd_struct *fwd)
 
 	switch (cmd) {
 	case SIOCAX25ADDFWD:
-		if ((fwd_dev = ax25_addr_ax25dev(&fwd->port_to)) == NULL)
+		fwd_dev = ax25_addr_ax25dev(&fwd->port_to);
+		if (!fwd_dev) {
+			ax25_dev_put(ax25_dev);
 			return -EINVAL;
-		if (ax25_dev->forward != NULL)
+		}
+		if (ax25_dev->forward) {
+			ax25_dev_put(fwd_dev);
+			ax25_dev_put(ax25_dev);
 			return -EINVAL;
+		}
 		ax25_dev->forward = fwd_dev->dev;
+		ax25_dev_put(fwd_dev);
+		ax25_dev_put(ax25_dev);
 		break;
 
 	case SIOCAX25DELFWD:
-		if (ax25_dev->forward == NULL)
+		if (!ax25_dev->forward) {
+			ax25_dev_put(ax25_dev);
 			return -EINVAL;
+		}
 		ax25_dev->forward = NULL;
+		ax25_dev_put(ax25_dev);
 		break;
 
 	default:
+		ax25_dev_put(ax25_dev);
 		return -EINVAL;
 	}
 
diff --git a/net/ax25/ax25_route.c b/net/ax25/ax25_route.c
index d0b2e094bd552f..9751207f775727 100644
--- a/net/ax25/ax25_route.c
+++ b/net/ax25/ax25_route.c
@@ -75,11 +75,13 @@ static int __must_check ax25_rt_add(struct ax25_routes_struct *route)
 	ax25_dev *ax25_dev;
 	int i;
 
-	if ((ax25_dev = ax25_addr_ax25dev(&route->port_addr)) == NULL)
-		return -EINVAL;
 	if (route->digi_count > AX25_MAX_DIGIS)
 		return -EINVAL;
 
+	ax25_dev = ax25_addr_ax25dev(&route->port_addr);
+	if (!ax25_dev)
+		return -EINVAL;
+
 	write_lock_bh(&ax25_route_lock);
 
 	ax25_rt = ax25_route_list;
@@ -91,6 +93,7 @@ static int __must_check ax25_rt_add(struct ax25_routes_struct *route)
 			if (route->digi_count != 0) {
 				if ((ax25_rt->digipeat = kmalloc(sizeof(ax25_digi), GFP_ATOMIC)) == NULL) {
 					write_unlock_bh(&ax25_route_lock);
+					ax25_dev_put(ax25_dev);
 					return -ENOMEM;
 				}
 				ax25_rt->digipeat->lastrepeat = -1;
@@ -101,6 +104,7 @@ static int __must_check ax25_rt_add(struct ax25_routes_struct *route)
 				}
 			}
 			write_unlock_bh(&ax25_route_lock);
+			ax25_dev_put(ax25_dev);
 			return 0;
 		}
 		ax25_rt = ax25_rt->next;
@@ -108,6 +112,7 @@ static int __must_check ax25_rt_add(struct ax25_routes_struct *route)
 
 	if ((ax25_rt = kmalloc(sizeof(ax25_route), GFP_ATOMIC)) == NULL) {
 		write_unlock_bh(&ax25_route_lock);
+		ax25_dev_put(ax25_dev);
 		return -ENOMEM;
 	}
 
@@ -120,6 +125,7 @@ static int __must_check ax25_rt_add(struct ax25_routes_struct *route)
 		if ((ax25_rt->digipeat = kmalloc(sizeof(ax25_digi), GFP_ATOMIC)) == NULL) {
 			write_unlock_bh(&ax25_route_lock);
 			kfree(ax25_rt);
+			ax25_dev_put(ax25_dev);
 			return -ENOMEM;
 		}
 		ax25_rt->digipeat->lastrepeat = -1;
@@ -132,6 +138,7 @@ static int __must_check ax25_rt_add(struct ax25_routes_struct *route)
 	ax25_rt->next   = ax25_route_list;
 	ax25_route_list = ax25_rt;
 	write_unlock_bh(&ax25_route_lock);
+	ax25_dev_put(ax25_dev);
 
 	return 0;
 }
@@ -173,6 +180,7 @@ static int ax25_rt_del(struct ax25_routes_struct *route)
 		}
 	}
 	write_unlock_bh(&ax25_route_lock);
+	ax25_dev_put(ax25_dev);
 
 	return 0;
 }
@@ -215,6 +223,7 @@ static int ax25_rt_opt(struct ax25_route_opt_struct *rt_option)
 
 out:
 	write_unlock_bh(&ax25_route_lock);
+	ax25_dev_put(ax25_dev);
 	return err;
 }
 
diff --git a/net/bridge/netfilter/nft_reject_bridge.c b/net/bridge/netfilter/nft_reject_bridge.c
index eba0efe64d05a7..fbf858ddec3521 100644
--- a/net/bridge/netfilter/nft_reject_bridge.c
+++ b/net/bridge/netfilter/nft_reject_bridge.c
@@ -49,7 +49,7 @@ static void nft_reject_br_send_v4_tcp_reset(struct net *net,
 {
 	struct sk_buff *nskb;
 
-	nskb = nf_reject_skb_v4_tcp_reset(net, oldskb, dev, hook);
+	nskb = nf_reject_skb_v4_tcp_reset(net, oldskb, NULL, hook);
 	if (!nskb)
 		return;
 
@@ -65,7 +65,7 @@ static void nft_reject_br_send_v4_unreach(struct net *net,
 {
 	struct sk_buff *nskb;
 
-	nskb = nf_reject_skb_v4_unreach(net, oldskb, dev, hook, code);
+	nskb = nf_reject_skb_v4_unreach(net, oldskb, NULL, hook, code);
 	if (!nskb)
 		return;
 
@@ -81,7 +81,7 @@ static void nft_reject_br_send_v6_tcp_reset(struct net *net,
 {
 	struct sk_buff *nskb;
 
-	nskb = nf_reject_skb_v6_tcp_reset(net, oldskb, dev, hook);
+	nskb = nf_reject_skb_v6_tcp_reset(net, oldskb, NULL, hook);
 	if (!nskb)
 		return;
 
@@ -98,7 +98,7 @@ static void nft_reject_br_send_v6_unreach(struct net *net,
 {
 	struct sk_buff *nskb;
 
-	nskb = nf_reject_skb_v6_unreach(net, oldskb, dev, hook, code);
+	nskb = nf_reject_skb_v6_unreach(net, oldskb, NULL, hook, code);
 	if (!nskb)
 		return;
 
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index 6c2016f7f3d19e..ec0bf737b076ac 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -1133,7 +1133,8 @@ out:
 	neigh_release(neigh);
 }
 
-int __neigh_event_send(struct neighbour *neigh, struct sk_buff *skb)
+int __neigh_event_send(struct neighbour *neigh, struct sk_buff *skb,
+		       const bool immediate_ok)
 {
 	int rc;
 	bool immediate_probe = false;
@@ -1154,12 +1155,17 @@ int __neigh_event_send(struct neighbour *neigh, struct sk_buff *skb)
 			atomic_set(&neigh->probes,
 				   NEIGH_VAR(neigh->parms, UCAST_PROBES));
 			neigh_del_timer(neigh);
-			neigh->nud_state     = NUD_INCOMPLETE;
+			neigh->nud_state = NUD_INCOMPLETE;
 			neigh->updated = now;
-			next = now + max(NEIGH_VAR(neigh->parms, RETRANS_TIME),
-					 HZ/100);
+			if (!immediate_ok) {
+				next = now + 1;
+			} else {
+				immediate_probe = true;
+				next = now + max(NEIGH_VAR(neigh->parms,
+							   RETRANS_TIME),
+						 HZ / 100);
+			}
 			neigh_add_timer(neigh, next);
-			immediate_probe = true;
 		} else {
 			neigh->nud_state = NUD_FAILED;
 			neigh->updated = jiffies;
@@ -1571,7 +1577,7 @@ static void neigh_managed_work(struct work_struct *work)
 
 	write_lock_bh(&tbl->lock);
 	list_for_each_entry(neigh, &tbl->managed_list, managed_list)
-		neigh_event_send(neigh, NULL);
+		neigh_event_send_probe(neigh, NULL, false);
 	queue_delayed_work(system_power_efficient_wq, &tbl->managed_work,
 			   NEIGH_VAR(&tbl->parms, DELAY_PROBE_TIME));
 	write_unlock_bh(&tbl->lock);
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index e476403231f000..710da8a36729d6 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -3275,8 +3275,8 @@ static int __rtnl_newlink(struct sk_buff *skb, struct nlmsghdr *nlh,
 	struct nlattr *slave_attr[RTNL_SLAVE_MAX_TYPE + 1];
 	unsigned char name_assign_type = NET_NAME_USER;
 	struct nlattr *linkinfo[IFLA_INFO_MAX + 1];
-	const struct rtnl_link_ops *m_ops = NULL;
-	struct net_device *master_dev = NULL;
+	const struct rtnl_link_ops *m_ops;
+	struct net_device *master_dev;
 	struct net *net = sock_net(skb->sk);
 	const struct rtnl_link_ops *ops;
 	struct nlattr *tb[IFLA_MAX + 1];
@@ -3314,6 +3314,8 @@ replay:
 	else
 		dev = NULL;
 
+	master_dev = NULL;
+	m_ops = NULL;
 	if (dev) {
 		master_dev = netdev_master_upper_dev_get(dev);
 		if (master_dev)
diff --git a/net/ieee802154/nl802154.c b/net/ieee802154/nl802154.c
index 277124f206e063..e0b072aecf0f30 100644
--- a/net/ieee802154/nl802154.c
+++ b/net/ieee802154/nl802154.c
@@ -1441,7 +1441,7 @@ static int nl802154_send_key(struct sk_buff *msg, u32 cmd, u32 portid,
 
 	hdr = nl802154hdr_put(msg, portid, seq, flags, cmd);
 	if (!hdr)
-		return -1;
+		return -ENOBUFS;
 
 	if (nla_put_u32(msg, NL802154_ATTR_IFINDEX, dev->ifindex))
 		goto nla_put_failure;
@@ -1634,7 +1634,7 @@ static int nl802154_send_device(struct sk_buff *msg, u32 cmd, u32 portid,
 
 	hdr = nl802154hdr_put(msg, portid, seq, flags, cmd);
 	if (!hdr)
-		return -1;
+		return -ENOBUFS;
 
 	if (nla_put_u32(msg, NL802154_ATTR_IFINDEX, dev->ifindex))
 		goto nla_put_failure;
@@ -1812,7 +1812,7 @@ static int nl802154_send_devkey(struct sk_buff *msg, u32 cmd, u32 portid,
 
 	hdr = nl802154hdr_put(msg, portid, seq, flags, cmd);
 	if (!hdr)
-		return -1;
+		return -ENOBUFS;
 
 	if (nla_put_u32(msg, NL802154_ATTR_IFINDEX, dev->ifindex))
 		goto nla_put_failure;
@@ -1988,7 +1988,7 @@ static int nl802154_send_seclevel(struct sk_buff *msg, u32 cmd, u32 portid,
 
 	hdr = nl802154hdr_put(msg, portid, seq, flags, cmd);
 	if (!hdr)
-		return -1;
+		return -ENOBUFS;
 
 	if (nla_put_u32(msg, NL802154_ATTR_IFINDEX, dev->ifindex))
 		goto nla_put_failure;
diff --git a/net/ipv4/netfilter/Kconfig b/net/ipv4/netfilter/Kconfig
index 67087f95579fde..aab384126f61ff 100644
--- a/net/ipv4/netfilter/Kconfig
+++ b/net/ipv4/netfilter/Kconfig
@@ -58,10 +58,6 @@ config NF_TABLES_ARP
 
 endif # NF_TABLES
 
-config NF_FLOW_TABLE_IPV4
-	tristate
-	select NF_FLOW_TABLE_INET
-
 config NF_DUP_IPV4
 	tristate "Netfilter IPv4 packet duplication to alternate destination"
 	depends on !NF_CONNTRACK || NF_CONNTRACK
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 78e81465f5f363..bdf108f544a45a 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -1322,10 +1322,13 @@ new_segment:
 
 			/* skb changing from pure zc to mixed, must charge zc */
 			if (unlikely(skb_zcopy_pure(skb))) {
-				if (!sk_wmem_schedule(sk, skb->data_len))
+				u32 extra = skb->truesize -
+					    SKB_TRUESIZE(skb_end_offset(skb));
+
+				if (!sk_wmem_schedule(sk, extra))
 					goto wait_for_space;
 
-				sk_mem_charge(sk, skb->data_len);
+				sk_mem_charge(sk, extra);
 				skb_shinfo(skb)->flags &= ~SKBFL_PURE_ZEROCOPY;
 			}
 
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index dc49a3d551eb91..bfe4112e000c09 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -1660,6 +1660,8 @@ static struct sk_buff *tcp_shift_skb_data(struct sock *sk, struct sk_buff *skb,
 	    (mss != tcp_skb_seglen(skb)))
 		goto out;
 
+	if (!tcp_skb_can_collapse(prev, skb))
+		goto out;
 	len = skb->len;
 	pcount = tcp_skb_pcount(skb);
 	if (tcp_skb_shift(prev, skb, pcount, len))
diff --git a/net/ipv6/netfilter/Kconfig b/net/ipv6/netfilter/Kconfig
index 97d3d1b36dbceb..0ba62f4868f976 100644
--- a/net/ipv6/netfilter/Kconfig
+++ b/net/ipv6/netfilter/Kconfig
@@ -47,10 +47,6 @@ config NFT_FIB_IPV6
 endif # NF_TABLES_IPV6
 endif # NF_TABLES
 
-config NF_FLOW_TABLE_IPV6
-	tristate
-	select NF_FLOW_TABLE_INET
-
 config NF_DUP_IPV6
 	tristate "Netfilter IPv6 packet duplication to alternate destination"
 	depends on !NF_CONNTRACK || NF_CONNTRACK
diff --git a/net/ipv6/netfilter/Makefile b/net/ipv6/netfilter/Makefile
index b85383606df71b..b8d6dc9aeeb6f4 100644
--- a/net/ipv6/netfilter/Makefile
+++ b/net/ipv6/netfilter/Makefile
@@ -28,9 +28,6 @@ obj-$(CONFIG_NFT_REJECT_IPV6) += nft_reject_ipv6.o
 obj-$(CONFIG_NFT_DUP_IPV6) += nft_dup_ipv6.o
 obj-$(CONFIG_NFT_FIB_IPV6) += nft_fib_ipv6.o
 
-# flow table support
-obj-$(CONFIG_NF_FLOW_TABLE_IPV6) += nf_flow_table_ipv6.o
-
 # matches
 obj-$(CONFIG_IP6_NF_MATCH_AH) += ip6t_ah.o
 obj-$(CONFIG_IP6_NF_MATCH_EUI64) += ip6t_eui64.o
diff --git a/net/ipv6/netfilter/nf_flow_table_ipv6.c b/net/ipv6/netfilter/nf_flow_table_ipv6.c
deleted file mode 100644
index e69de29bb2d1d6..00000000000000
--- a/net/ipv6/netfilter/nf_flow_table_ipv6.c
+++ /dev/null
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index cf454f8ca2b09a..5fa16990da9517 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -2011,7 +2011,6 @@ static void nft_last_rule(struct nft_rule_blob *blob, const void *ptr)
 
 	prule = (struct nft_rule_dp *)ptr;
 	prule->is_last = 1;
-	ptr += offsetof(struct nft_rule_dp, data);
 	/* blob size does not include the trailer rule */
 }
 
diff --git a/net/netfilter/nft_byteorder.c b/net/netfilter/nft_byteorder.c
index 9d5947ab8d4ef3..e646e9ee4a9875 100644
--- a/net/netfilter/nft_byteorder.c
+++ b/net/netfilter/nft_byteorder.c
@@ -167,12 +167,24 @@ nla_put_failure:
 	return -1;
 }
 
+static bool nft_byteorder_reduce(struct nft_regs_track *track,
+				 const struct nft_expr *expr)
+{
+	struct nft_byteorder *priv = nft_expr_priv(expr);
+
+	track->regs[priv->dreg].selector = NULL;
+	track->regs[priv->dreg].bitwise = NULL;
+
+	return false;
+}
+
 static const struct nft_expr_ops nft_byteorder_ops = {
 	.type		= &nft_byteorder_type,
 	.size		= NFT_EXPR_SIZE(sizeof(struct nft_byteorder)),
 	.eval		= nft_byteorder_eval,
 	.init		= nft_byteorder_init,
 	.dump		= nft_byteorder_dump,
+	.reduce		= nft_byteorder_reduce,
 };
 
 struct nft_expr_type nft_byteorder_type __read_mostly = {
diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c
index 518d96c8c24714..5adf8bb628a80e 100644
--- a/net/netfilter/nft_ct.c
+++ b/net/netfilter/nft_ct.c
@@ -260,9 +260,12 @@ static void nft_ct_set_zone_eval(const struct nft_expr *expr,
 	ct = this_cpu_read(nft_ct_pcpu_template);
 
 	if (likely(refcount_read(&ct->ct_general.use) == 1)) {
+		refcount_inc(&ct->ct_general.use);
 		nf_ct_zone_add(ct, &zone);
 	} else {
-		/* previous skb got queued to userspace */
+		/* previous skb got queued to userspace, allocate temporary
+		 * one until percpu template can be reused.
+		 */
 		ct = nf_ct_tmpl_alloc(nft_net(pkt), &zone, GFP_ATOMIC);
 		if (!ct) {
 			regs->verdict.code = NF_DROP;
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 85ea7ddb48db6a..ab87f22cc7ecde 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -1789,7 +1789,10 @@ static int fanout_add(struct sock *sk, struct fanout_args *args)
 		err = -ENOSPC;
 		if (refcount_read(&match->sk_ref) < match->max_num_members) {
 			__dev_remove_pack(&po->prot_hook);
-			po->fanout = match;
+
+			/* Paired with packet_setsockopt(PACKET_FANOUT_DATA) */
+			WRITE_ONCE(po->fanout, match);
+
 			po->rollover = rollover;
 			rollover = NULL;
 			refcount_set(&match->sk_ref, refcount_read(&match->sk_ref) + 1);
@@ -3934,7 +3937,8 @@ packet_setsockopt(struct socket *sock, int level, int optname, sockptr_t optval,
 	}
 	case PACKET_FANOUT_DATA:
 	{
-		if (!po->fanout)
+		/* Paired with the WRITE_ONCE() in fanout_add() */
+		if (!READ_ONCE(po->fanout))
 			return -EINVAL;
 
 		return fanout_set_data(po, optval, optlen);
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index d4e27c679123f0..5f0f346b576fc0 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -1945,9 +1945,9 @@ static int tc_new_tfilter(struct sk_buff *skb, struct nlmsghdr *n,
 	bool prio_allocate;
 	u32 parent;
 	u32 chain_index;
-	struct Qdisc *q = NULL;
+	struct Qdisc *q;
 	struct tcf_chain_info chain_info;
-	struct tcf_chain *chain = NULL;
+	struct tcf_chain *chain;
 	struct tcf_block *block;
 	struct tcf_proto *tp;
 	unsigned long cl;
@@ -1976,6 +1976,8 @@ replay:
 	tp = NULL;
 	cl = 0;
 	block = NULL;
+	q = NULL;
+	chain = NULL;
 	flags = 0;
 
 	if (prio == 0) {
@@ -2798,8 +2800,8 @@ static int tc_ctl_chain(struct sk_buff *skb, struct nlmsghdr *n,
 	struct tcmsg *t;
 	u32 parent;
 	u32 chain_index;
-	struct Qdisc *q = NULL;
-	struct tcf_chain *chain = NULL;
+	struct Qdisc *q;
+	struct tcf_chain *chain;
 	struct tcf_block *block;
 	unsigned long cl;
 	int err;
@@ -2809,6 +2811,7 @@ static int tc_ctl_chain(struct sk_buff *skb, struct nlmsghdr *n,
 		return -EPERM;
 
 replay:
+	q = NULL;
 	err = nlmsg_parse_deprecated(n, sizeof(*t), tca, TCA_MAX,
 				     rtm_tca_policy, extack);
 	if (err < 0)
diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index d5ea62b82bb897..8c89d0b0ca1857 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -566,17 +566,115 @@ static void smc_stat_fallback(struct smc_sock *smc)
 	mutex_unlock(&net->smc.mutex_fback_rsn);
 }
 
+/* must be called under rcu read lock */
+static void smc_fback_wakeup_waitqueue(struct smc_sock *smc, void *key)
+{
+	struct socket_wq *wq;
+	__poll_t flags;
+
+	wq = rcu_dereference(smc->sk.sk_wq);
+	if (!skwq_has_sleeper(wq))
+		return;
+
+	/* wake up smc sk->sk_wq */
+	if (!key) {
+		/* sk_state_change */
+		wake_up_interruptible_all(&wq->wait);
+	} else {
+		flags = key_to_poll(key);
+		if (flags & (EPOLLIN | EPOLLOUT))
+			/* sk_data_ready or sk_write_space */
+			wake_up_interruptible_sync_poll(&wq->wait, flags);
+		else if (flags & EPOLLERR)
+			/* sk_error_report */
+			wake_up_interruptible_poll(&wq->wait, flags);
+	}
+}
+
+static int smc_fback_mark_woken(wait_queue_entry_t *wait,
+				unsigned int mode, int sync, void *key)
+{
+	struct smc_mark_woken *mark =
+		container_of(wait, struct smc_mark_woken, wait_entry);
+
+	mark->woken = true;
+	mark->key = key;
+	return 0;
+}
+
+static void smc_fback_forward_wakeup(struct smc_sock *smc, struct sock *clcsk,
+				     void (*clcsock_callback)(struct sock *sk))
+{
+	struct smc_mark_woken mark = { .woken = false };
+	struct socket_wq *wq;
+
+	init_waitqueue_func_entry(&mark.wait_entry,
+				  smc_fback_mark_woken);
+	rcu_read_lock();
+	wq = rcu_dereference(clcsk->sk_wq);
+	if (!wq)
+		goto out;
+	add_wait_queue(sk_sleep(clcsk), &mark.wait_entry);
+	clcsock_callback(clcsk);
+	remove_wait_queue(sk_sleep(clcsk), &mark.wait_entry);
+
+	if (mark.woken)
+		smc_fback_wakeup_waitqueue(smc, mark.key);
+out:
+	rcu_read_unlock();
+}
+
+static void smc_fback_state_change(struct sock *clcsk)
+{
+	struct smc_sock *smc =
+		smc_clcsock_user_data(clcsk);
+
+	if (!smc)
+		return;
+	smc_fback_forward_wakeup(smc, clcsk, smc->clcsk_state_change);
+}
+
+static void smc_fback_data_ready(struct sock *clcsk)
+{
+	struct smc_sock *smc =
+		smc_clcsock_user_data(clcsk);
+
+	if (!smc)
+		return;
+	smc_fback_forward_wakeup(smc, clcsk, smc->clcsk_data_ready);
+}
+
+static void smc_fback_write_space(struct sock *clcsk)
+{
+	struct smc_sock *smc =
+		smc_clcsock_user_data(clcsk);
+
+	if (!smc)
+		return;
+	smc_fback_forward_wakeup(smc, clcsk, smc->clcsk_write_space);
+}
+
+static void smc_fback_error_report(struct sock *clcsk)
+{
+	struct smc_sock *smc =
+		smc_clcsock_user_data(clcsk);
+
+	if (!smc)
+		return;
+	smc_fback_forward_wakeup(smc, clcsk, smc->clcsk_error_report);
+}
+
 static int smc_switch_to_fallback(struct smc_sock *smc, int reason_code)
 {
-	wait_queue_head_t *smc_wait = sk_sleep(&smc->sk);
-	wait_queue_head_t *clc_wait;
-	unsigned long flags;
+	struct sock *clcsk;
 
 	mutex_lock(&smc->clcsock_release_lock);
 	if (!smc->clcsock) {
 		mutex_unlock(&smc->clcsock_release_lock);
 		return -EBADF;
 	}
+	clcsk = smc->clcsock->sk;
+
 	smc->use_fallback = true;
 	smc->fallback_rsn = reason_code;
 	smc_stat_fallback(smc);
@@ -587,16 +685,22 @@ static int smc_switch_to_fallback(struct smc_sock *smc, int reason_code)
 		smc->clcsock->wq.fasync_list =
 			smc->sk.sk_socket->wq.fasync_list;
 
-		/* There may be some entries remaining in
-		 * smc socket->wq, which should be removed
-		 * to clcsocket->wq during the fallback.
+		/* There might be some wait entries remaining
+		 * in smc sk->sk_wq and they should be woken up
+		 * as clcsock's wait queue is woken up.
 		 */
-		clc_wait = sk_sleep(smc->clcsock->sk);
-		spin_lock_irqsave(&smc_wait->lock, flags);
-		spin_lock_nested(&clc_wait->lock, SINGLE_DEPTH_NESTING);
-		list_splice_init(&smc_wait->head, &clc_wait->head);
-		spin_unlock(&clc_wait->lock);
-		spin_unlock_irqrestore(&smc_wait->lock, flags);
+		smc->clcsk_state_change = clcsk->sk_state_change;
+		smc->clcsk_data_ready = clcsk->sk_data_ready;
+		smc->clcsk_write_space = clcsk->sk_write_space;
+		smc->clcsk_error_report = clcsk->sk_error_report;
+
+		clcsk->sk_state_change = smc_fback_state_change;
+		clcsk->sk_data_ready = smc_fback_data_ready;
+		clcsk->sk_write_space = smc_fback_write_space;
+		clcsk->sk_error_report = smc_fback_error_report;
+
+		smc->clcsock->sk->sk_user_data =
+			(void *)((uintptr_t)smc | SK_USER_DATA_NOCOPY);
 	}
 	mutex_unlock(&smc->clcsock_release_lock);
 	return 0;
@@ -2115,10 +2219,9 @@ out:
 
 static void smc_clcsock_data_ready(struct sock *listen_clcsock)
 {
-	struct smc_sock *lsmc;
+	struct smc_sock *lsmc =
+		smc_clcsock_user_data(listen_clcsock);
 
-	lsmc = (struct smc_sock *)
-	       ((uintptr_t)listen_clcsock->sk_user_data & ~SK_USER_DATA_NOCOPY);
 	if (!lsmc)
 		return;
 	lsmc->clcsk_data_ready(listen_clcsock);
diff --git a/net/smc/smc.h b/net/smc/smc.h
index 3d0b8e300deb32..37b2001a02557e 100644
--- a/net/smc/smc.h
+++ b/net/smc/smc.h
@@ -139,6 +139,12 @@ enum smc_urg_state {
 	SMC_URG_READ	= 3,			/* data was already read */
 };
 
+struct smc_mark_woken {
+	bool woken;
+	void *key;
+	wait_queue_entry_t wait_entry;
+};
+
 struct smc_connection {
 	struct rb_node		alert_node;
 	struct smc_link_group	*lgr;		/* link group of connection */
@@ -228,8 +234,14 @@ struct smc_connection {
 struct smc_sock {				/* smc sock container */
 	struct sock		sk;
 	struct socket		*clcsock;	/* internal tcp socket */
+	void			(*clcsk_state_change)(struct sock *sk);
+						/* original stat_change fct. */
 	void			(*clcsk_data_ready)(struct sock *sk);
-						/* original data_ready fct. **/
+						/* original data_ready fct. */
+	void			(*clcsk_write_space)(struct sock *sk);
+						/* original write_space fct. */
+	void			(*clcsk_error_report)(struct sock *sk);
+						/* original error_report fct. */
 	struct smc_connection	conn;		/* smc connection */
 	struct smc_sock		*listen_smc;	/* listen parent */
 	struct work_struct	connect_work;	/* handle non-blocking connect*/
@@ -264,6 +276,12 @@ static inline struct smc_sock *smc_sk(const struct sock *sk)
 	return (struct smc_sock *)sk;
 }
 
+static inline struct smc_sock *smc_clcsock_user_data(struct sock *clcsk)
+{
+	return (struct smc_sock *)
+	       ((uintptr_t)clcsk->sk_user_data & ~SK_USER_DATA_NOCOPY);
+}
+
 extern struct workqueue_struct	*smc_hs_wq;	/* wq for handshake work */
 extern struct workqueue_struct	*smc_close_wq;	/* wq for close work */
 
diff --git a/net/smc/smc_diag.c b/net/smc/smc_diag.c
index b8898c787d233c..1fca2f90a9c791 100644
--- a/net/smc/smc_diag.c
+++ b/net/smc/smc_diag.c
@@ -146,13 +146,11 @@ static int __smc_diag_dump(struct sock *sk, struct sk_buff *skb,
 	    (req->diag_ext & (1 << (SMC_DIAG_LGRINFO - 1))) &&
 	    !list_empty(&smc->conn.lgr->list)) {
 		struct smc_link *link = smc->conn.lnk;
-		struct net *net = read_pnet(&link->smcibdev->ibdev->coredev.rdma_net);
 
 		struct smc_diag_lgrinfo linfo = {
 			.role = smc->conn.lgr->role,
 			.lnk[0].ibport = link->ibport,
 			.lnk[0].link_id = link->link_id,
-			.lnk[0].net_cookie = net->net_cookie,
 		};
 
 		memcpy(linfo.lnk[0].ibname,