Merge tag 'net-next-6.16' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next

Pull networking updates from Paolo Abeni:
 "Core:

   - Implement the Device Memory TCP transmit path, allowing zero-copy
     data transmission on top of TCP from e.g. GPU memory to the wire.

   - Move all the IPv6 routing tables management outside the RTNL scope,
     under its own lock and RCU. The route control path is now 3x times
     faster.

   - Convert queue related netlink ops to instance lock, reducing again
     the scope of the RTNL lock. This improves the control plane
     scalability.

   - Refactor the software crc32c implementation, removing unneeded
     abstraction layers and improving significantly the related
     micro-benchmarks.

   - Optimize the GRO engine for UDP-tunneled traffic, for a 10%
     performance improvement in related stream tests.

   - Cover more per-CPU storage with local nested BH locking; this is a
     prep work to remove the current per-CPU lock in local_bh_disable()
     on PREMPT_RT.

   - Introduce and use nlmsg_payload helper, combining buffer bounds
     verification with accessing payload carried by netlink messages.

  Netfilter:

   - Rewrite the procfs conntrack table implementation, improving
     considerably the dump performance. A lot of user-space tools still
     use this interface.

   - Implement support for wildcard netdevice in netdev basechain and
     flowtables.

   - Integrate conntrack information into nft trace infrastructure.

   - Export set count and backend name to userspace, for better
     introspection.

  BPF:

   - BPF qdisc support: BPF-qdisc can be implemented with BPF struct_ops
     programs and can be controlled in similar way to traditional qdiscs
     using the "tc qdisc" command.

   - Refactor the UDP socket iterator, addressing long standing issues
     WRT duplicate hits or missed sockets.

  Protocols:

   - Improve TCP receive buffer auto-tuning and increase the default
     upper bound for the receive buffer; overall this improves the
     single flow maximum thoughput on 200Gbs link by over 60%.

   - Add AFS GSSAPI security class to AF_RXRPC; it provides transport
     security for connections to the AFS fileserver and VL server.

   - Improve TCP multipath routing, so that the sources address always
     matches the nexthop device.

   - Introduce SO_PASSRIGHTS for AF_UNIX, to allow disabling SCM_RIGHTS,
     and thus preventing DoS caused by passing around problematic FDs.

   - Retire DCCP socket. DCCP only receives updates for bugs, and major
     distros disable it by default. Its removal allows for better
     organisation of TCP fields to reduce the number of cache lines hit
     in the fast path.

   - Extend TCP drop-reason support to cover PAWS checks.

  Driver API:

   - Reorganize PTP ioctl flag support to require an explicit opt-in for
     the drivers, avoiding the problem of drivers not rejecting new
     unsupported flags.

   - Converted several device drivers to timestamping APIs.

   - Introduce per-PHY ethtool dump helpers, improving the support for
     dump operations targeting PHYs.

  Tests and tooling:

   - Add support for classic netlink in user space C codegen, so that
     ynl-c can now read, create and modify links, routes addresses and
     qdisc layer configuration.

   - Add ynl sub-types for binary attributes, allowing ynl-c to output
     known struct instead of raw binary data, clarifying the classic
     netlink output.

   - Extend MPTCP selftests to improve the code-coverage.

   - Add tests for XDP tail adjustment in AF_XDP.

  New hardware / drivers:

   - OpenVPN virtual driver: offload OpenVPN data channels processing to
     the kernel-space, increasing the data transfer throughput WRT the
     user-space implementation.

   - Renesas glue driver for the gigabit ethernet RZ/V2H(P) SoC.

   - Broadcom asp-v3.0 ethernet driver.

   - AMD Renoir ethernet device.

   - ReakTek MT9888 2.5G ethernet PHY driver.

   - Aeonsemi 10G C45 PHYs driver.

  Drivers:

   - Ethernet high-speed NICs:
       - nVidia/Mellanox (mlx5):
           - refactor the steering table handling to significantly
             reduce the amount of memory used
           - add support for complex matches in H/W flow steering
           - improve flow streeing error handling
           - convert to netdev instance locking
       - Intel (100G, ice, igb, ixgbe, idpf):
           - ice: add switchdev support for LLDP traffic over VF
           - ixgbe: add firmware manipulation and regions devlink support
           - igb: introduce support for frame transmission premption
           - igb: adds persistent NAPI configuration
           - idpf: introduce RDMA support
           - idpf: add initial PTP support
       - Meta (fbnic):
           - extend hardware stats coverage
           - add devlink dev flash support
       - Broadcom (bnxt):
           - add support for RX-side device memory TCP
       - Wangxun (txgbe):
           - implement support for udp tunnel offload
           - complete PTP and SRIOV support for AML 25G/10G devices

   - Ethernet NICs embedded and virtual:
       - Google (gve):
           - add device memory TCP TX support
       - Amazon (ena):
           - support persistent per-NAPI config
       - Airoha:
           - add H/W support for L2 traffic offload
           - add per flow stats for flow offloading
       - RealTek (rtl8211): add support for WoL magic packet
       - Synopsys (stmmac):
           - dwmac-socfpga 1000BaseX support
           - add Loongson-2K3000 support
           - introduce support for hardware-accelerated VLAN stripping
       - Broadcom (bcmgenet):
           - expose more H/W stats
       - Freescale (enetc, dpaa2-eth):
           - enetc: add MAC filter, VLAN filter RSS and loopback support
           - dpaa2-eth: convert to H/W timestamping APIs
       - vxlan: convert FDB table to rhashtable, for better scalabilty
       - veth: apply qdisc backpressure on full ring to reduce TX drops

   - Ethernet switches:
       - Microchip (kzZ88x3): add ETS scheduler support

   - Ethernet PHYs:
       - RealTek (rtl8211):
           - add support for WoL magic packet
           - add support for PHY LEDs

   - CAN:
       - Adds RZ/G3E CANFD support to the rcar_canfd driver.
       - Preparatory work for CAN-XL support.
       - Add self-tests framework with support for CAN physical interfaces.

   - WiFi:
       - mac80211:
           - scan improvements with multi-link operation (MLO)
       - Qualcomm (ath12k):
           - enable AHB support for IPQ5332
           - add monitor interface support to QCN9274
           - add multi-link operation support to WCN7850
           - add 802.11d scan offload support to WCN7850
           - monitor mode for WCN7850, better 6 GHz regulatory
       - Qualcomm (ath11k):
           - restore hibernation support
       - MediaTek (mt76):
           - WiFi-7 improvements
           - implement support for mt7990
       - Intel (iwlwifi):
           - enhanced multi-link single-radio (EMLSR) support on 5 GHz links
           - rework device configuration
       - RealTek (rtw88):
           - improve throughput for RTL8814AU
       - RealTek (rtw89):
           - add multi-link operation support
           - STA/P2P concurrency improvements
           - support different SAR configs by antenna

   - Bluetooth:
       - introduce HCI Driver protocol
       - btintel_pcie: do not generate coredump for diagnostic events
       - btusb: add HCI Drv commands for configuring altsetting
       - btusb: add RTL8851BE device 0x0bda:0xb850
       - btusb: add new VID/PID 13d3/3584 for MT7922
       - btusb: add new VID/PID 13d3/3630 and 13d3/3613 for MT7925
       - btnxpuart: implement host-wakeup feature"

* tag 'net-next-6.16' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1611 commits)
  selftests/bpf: Fix bpf selftest build warning
  selftests: netfilter: Fix skip of wildcard interface test
  net: phy: mscc: Stop clearing the the UDPv4 checksum for L2 frames
  net: openvswitch: Fix the dead loop of MPLS parse
  calipso: Don't call calipso functions for AF_INET sk.
  selftests/tc-testing: Add a test for HFSC eltree double add with reentrant enqueue behaviour on netem
  net_sched: hfsc: Address reentrant enqueue adding class to eltree twice
  octeontx2-pf: QOS: Refactor TC_HTB_LEAF_DEL_LAST callback
  octeontx2-pf: QOS: Perform cache sync on send queue teardown
  net: mana: Add support for Multi Vports on Bare metal
  net: devmem: ncdevmem: remove unused variable
  net: devmem: ksft: upgrade rx test to send 1K data
  net: devmem: ksft: add 5 tuple FS support
  net: devmem: ksft: add exit_wait to make rx test pass
  net: devmem: ksft: add ipv4 support
  net: devmem: preserve sockc_err
  page_pool: fix ugly page_pool formatting
  net: devmem: move list_add to net_devmem_bind_dmabuf.
  selftests: netfilter: nft_queue.sh: include file transfer duration in log message
  net: phy: mscc: Fix memory leak when using one step timestamping
  ...

20 files changed, 474 insertions, 328 deletions

diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index c6b22170dc49..43b19adfbf88 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -5349,12 +5349,12 @@ static int inet6_valid_dump_ifaddr_req(const struct nlmsghdr *nlh,
 	struct ifaddrmsg *ifm;
 	int err, i;
 
-	if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*ifm))) {
+	ifm = nlmsg_payload(nlh, sizeof(*ifm));
+	if (!ifm) {
 		NL_SET_ERR_MSG_MOD(extack, "Invalid header for address dump request");
 		return -EINVAL;
 	}
 
-	ifm = nlmsg_data(nlh);
 	if (ifm->ifa_prefixlen || ifm->ifa_flags || ifm->ifa_scope) {
 		NL_SET_ERR_MSG_MOD(extack, "Invalid values in header for address dump request");
 		return -EINVAL;
@@ -5487,7 +5487,8 @@ static int inet6_rtm_valid_getaddr_req(struct sk_buff *skb,
 	struct ifaddrmsg *ifm;
 	int i, err;
 
-	if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*ifm))) {
+	ifm = nlmsg_payload(nlh, sizeof(*ifm));
+	if (!ifm) {
 		NL_SET_ERR_MSG_MOD(extack, "Invalid header for get address request");
 		return -EINVAL;
 	}
@@ -5496,7 +5497,6 @@ static int inet6_rtm_valid_getaddr_req(struct sk_buff *skb,
 		return nlmsg_parse_deprecated(nlh, sizeof(*ifm), tb, IFA_MAX,
 					      ifa_ipv6_policy, extack);
 
-	ifm = nlmsg_data(nlh);
 	if (ifm->ifa_prefixlen || ifm->ifa_flags || ifm->ifa_scope) {
 		NL_SET_ERR_MSG_MOD(extack, "Invalid values in header for get address request");
 		return -EINVAL;
@@ -6115,7 +6115,8 @@ static int inet6_valid_dump_ifinfo(const struct nlmsghdr *nlh,
 {
 	struct ifinfomsg *ifm;
 
-	if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*ifm))) {
+	ifm = nlmsg_payload(nlh, sizeof(*ifm));
+	if (!ifm) {
 		NL_SET_ERR_MSG_MOD(extack, "Invalid header for link dump request");
 		return -EINVAL;
 	}
@@ -6125,7 +6126,6 @@ static int inet6_valid_dump_ifinfo(const struct nlmsghdr *nlh,
 		return -EINVAL;
 	}
 
-	ifm = nlmsg_data(nlh);
 	if (ifm->__ifi_pad || ifm->ifi_type || ifm->ifi_flags ||
 	    ifm->ifi_change || ifm->ifi_index) {
 		NL_SET_ERR_MSG_MOD(extack, "Invalid values in header for dump request");
diff --git a/net/ipv6/addrlabel.c b/net/ipv6/addrlabel.c
index ab054f329e12..fb63ffbcfc64 100644
--- a/net/ipv6/addrlabel.c
+++ b/net/ipv6/addrlabel.c
@@ -473,12 +473,12 @@ static int ip6addrlbl_valid_dump_req(const struct nlmsghdr *nlh,
 {
 	struct ifaddrlblmsg *ifal;
 
-	if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*ifal))) {
+	ifal = nlmsg_payload(nlh, sizeof(*ifal));
+	if (!ifal) {
 		NL_SET_ERR_MSG_MOD(extack, "Invalid header for address label dump request");
 		return -EINVAL;
 	}
 
-	ifal = nlmsg_data(nlh);
 	if (ifal->__ifal_reserved || ifal->ifal_prefixlen ||
 	    ifal->ifal_flags || ifal->ifal_index || ifal->ifal_seq) {
 		NL_SET_ERR_MSG_MOD(extack, "Invalid values in header for address label dump request");
@@ -543,7 +543,8 @@ static int ip6addrlbl_valid_get_req(struct sk_buff *skb,
 	struct ifaddrlblmsg *ifal;
 	int i, err;
 
-	if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*ifal))) {
+	ifal = nlmsg_payload(nlh, sizeof(*ifal));
+	if (!ifal) {
 		NL_SET_ERR_MSG_MOD(extack, "Invalid header for addrlabel get request");
 		return -EINVAL;
 	}
@@ -552,7 +553,6 @@ static int ip6addrlbl_valid_get_req(struct sk_buff *skb,
 		return nlmsg_parse_deprecated(nlh, sizeof(*ifal), tb,
 					      IFAL_MAX, ifal_policy, extack);
 
-	ifal = nlmsg_data(nlh);
 	if (ifal->__ifal_reserved || ifal->ifal_flags || ifal->ifal_seq) {
 		NL_SET_ERR_MSG_MOD(extack, "Invalid values in header for addrlabel get request");
 		return -EINVAL;
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index f60ec8b0f8ea..acaff1296783 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -715,6 +715,7 @@ const struct proto_ops inet6_stream_ops = {
 #endif
 	.set_rcvlowat	   = tcp_set_rcvlowat,
 };
+EXPORT_SYMBOL_GPL(inet6_stream_ops);
 
 const struct proto_ops inet6_dgram_ops = {
 	.family		   = PF_INET6,
@@ -881,7 +882,6 @@ bool ipv6_opt_accepted(const struct sock *sk, const struct sk_buff *skb,
 	}
 	return false;
 }
-EXPORT_SYMBOL_GPL(ipv6_opt_accepted);
 
 static struct packet_type ipv6_packet_type __read_mostly = {
 	.type = cpu_to_be16(ETH_P_IPV6),
diff --git a/net/ipv6/inet6_connection_sock.c b/net/ipv6/inet6_connection_sock.c
index dbcf556a35bb..8f500eaf33cf 100644
--- a/net/ipv6/inet6_connection_sock.c
+++ b/net/ipv6/inet6_connection_sock.c
@@ -54,7 +54,6 @@ struct dst_entry *inet6_csk_route_req(const struct sock *sk,
 
 	return dst;
 }
-EXPORT_SYMBOL(inet6_csk_route_req);
 
 static inline
 struct dst_entry *__inet6_csk_dst_check(struct sock *sk, u32 cookie)
@@ -137,4 +136,3 @@ struct dst_entry *inet6_csk_update_pmtu(struct sock *sk, u32 mtu)
 	dst = inet6_csk_route_socket(sk, &fl6);
 	return IS_ERR(dst) ? NULL : dst;
 }
-EXPORT_SYMBOL_GPL(inet6_csk_update_pmtu);
diff --git a/net/ipv6/ioam6_iptunnel.c b/net/ipv6/ioam6_iptunnel.c
index 09065187378e..40df8bdfaacd 100644
--- a/net/ipv6/ioam6_iptunnel.c
+++ b/net/ipv6/ioam6_iptunnel.c
@@ -38,6 +38,7 @@ struct ioam6_lwt_freq {
 };
 
 struct ioam6_lwt {
+	struct dst_entry null_dst;
 	struct dst_cache cache;
 	struct ioam6_lwt_freq freq;
 	atomic_t pkt_cnt;
@@ -177,6 +178,14 @@ static int ioam6_build_state(struct net *net, struct nlattr *nla,
 	if (err)
 		goto free_lwt;
 
+	/* This "fake" dst_entry will be stored in a dst_cache, which will call
+	 * dst_hold() and dst_release() on it. We must ensure that dst_destroy()
+	 * will never be called. For that, its initial refcount is 1 and +1 when
+	 * it is stored in the cache. Then, +1/-1 each time we read the cache
+	 * and release it. Long story short, we're fine.
+	 */
+	dst_init(&ilwt->null_dst, NULL, NULL, DST_OBSOLETE_NONE, DST_NOCOUNT);
+
 	atomic_set(&ilwt->pkt_cnt, 0);
 	ilwt->freq.k = freq_k;
 	ilwt->freq.n = freq_n;
@@ -336,7 +345,8 @@ static int ioam6_do_encap(struct net *net, struct sk_buff *skb,
 
 static int ioam6_output(struct net *net, struct sock *sk, struct sk_buff *skb)
 {
-	struct dst_entry *dst = skb_dst(skb), *cache_dst = NULL;
+	struct dst_entry *orig_dst = skb_dst(skb);
+	struct dst_entry *dst = NULL;
 	struct ioam6_lwt *ilwt;
 	int err = -EINVAL;
 	u32 pkt_cnt;
@@ -344,7 +354,7 @@ static int ioam6_output(struct net *net, struct sock *sk, struct sk_buff *skb)
 	if (skb->protocol != htons(ETH_P_IPV6))
 		goto drop;
 
-	ilwt = ioam6_lwt_state(dst->lwtstate);
+	ilwt = ioam6_lwt_state(orig_dst->lwtstate);
 
 	/* Check for insertion frequency (i.e., "k over n" insertions) */
 	pkt_cnt = atomic_fetch_inc(&ilwt->pkt_cnt);
@@ -352,9 +362,20 @@ static int ioam6_output(struct net *net, struct sock *sk, struct sk_buff *skb)
 		goto out;
 
 	local_bh_disable();
-	cache_dst = dst_cache_get(&ilwt->cache);
+	dst = dst_cache_get(&ilwt->cache);
 	local_bh_enable();
 
+	/* This is how we notify that the destination does not change after
+	 * transformation and that we need to use orig_dst instead of the cache
+	 */
+	if (dst == &ilwt->null_dst) {
+		dst_release(dst);
+
+		dst = orig_dst;
+		/* keep refcount balance: dst_release() is called at the end */
+		dst_hold(dst);
+	}
+
 	switch (ilwt->mode) {
 	case IOAM6_IPTUNNEL_MODE_INLINE:
 do_inline:
@@ -362,7 +383,7 @@ do_inline:
 		if (ipv6_hdr(skb)->nexthdr == NEXTHDR_HOP)
 			goto out;
 
-		err = ioam6_do_inline(net, skb, &ilwt->tuninfo, cache_dst);
+		err = ioam6_do_inline(net, skb, &ilwt->tuninfo, dst);
 		if (unlikely(err))
 			goto drop;
 
@@ -372,7 +393,7 @@ do_encap:
 		/* Encapsulation (ip6ip6) */
 		err = ioam6_do_encap(net, skb, &ilwt->tuninfo,
 				     ilwt->has_tunsrc, &ilwt->tunsrc,
-				     &ilwt->tundst, cache_dst);
+				     &ilwt->tundst, dst);
 		if (unlikely(err))
 			goto drop;
 
@@ -390,7 +411,7 @@ do_encap:
 		goto drop;
 	}
 
-	if (unlikely(!cache_dst)) {
+	if (unlikely(!dst)) {
 		struct ipv6hdr *hdr = ipv6_hdr(skb);
 		struct flowi6 fl6;
 
@@ -401,20 +422,27 @@ do_encap:
 		fl6.flowi6_mark = skb->mark;
 		fl6.flowi6_proto = hdr->nexthdr;
 
-		cache_dst = ip6_route_output(net, NULL, &fl6);
-		if (cache_dst->error) {
-			err = cache_dst->error;
+		dst = ip6_route_output(net, NULL, &fl6);
+		if (dst->error) {
+			err = dst->error;
 			goto drop;
 		}
 
-		/* cache only if we don't create a dst reference loop */
-		if (dst->lwtstate != cache_dst->lwtstate) {
-			local_bh_disable();
-			dst_cache_set_ip6(&ilwt->cache, cache_dst, &fl6.saddr);
-			local_bh_enable();
-		}
-
-		err = skb_cow_head(skb, LL_RESERVED_SPACE(cache_dst->dev));
+		/* If the destination is the same after transformation (which is
+		 * a valid use case for IOAM), then we don't want to add it to
+		 * the cache in order to avoid a reference loop. Instead, we add
+		 * our fake dst_entry to the cache as a way to detect this case.
+		 * Otherwise, we add the resolved destination to the cache.
+		 */
+		local_bh_disable();
+		if (orig_dst->lwtstate == dst->lwtstate)
+			dst_cache_set_ip6(&ilwt->cache,
+					  &ilwt->null_dst, &fl6.saddr);
+		else
+			dst_cache_set_ip6(&ilwt->cache, dst, &fl6.saddr);
+		local_bh_enable();
+
+		err = skb_cow_head(skb, LL_RESERVED_SPACE(dst->dev));
 		if (unlikely(err))
 			goto drop;
 	}
@@ -422,22 +450,26 @@ do_encap:
 	/* avoid lwtunnel_output() reentry loop when destination is the same
 	 * after transformation (e.g., with the inline mode)
 	 */
-	if (dst->lwtstate != cache_dst->lwtstate) {
+	if (orig_dst->lwtstate != dst->lwtstate) {
 		skb_dst_drop(skb);
-		skb_dst_set(skb, cache_dst);
+		skb_dst_set(skb, dst);
 		return dst_output(net, sk, skb);
 	}
 out:
-	dst_release(cache_dst);
-	return dst->lwtstate->orig_output(net, sk, skb);
+	dst_release(dst);
+	return orig_dst->lwtstate->orig_output(net, sk, skb);
 drop:
-	dst_release(cache_dst);
+	dst_release(dst);
 	kfree_skb(skb);
 	return err;
 }
 
 static void ioam6_destroy_state(struct lwtunnel_state *lwt)
 {
+	/* Since the refcount of per-cpu dst_entry caches will never be 0 (see
+	 * why above) when our "fake" dst_entry is used, it is not necessary to
+	 * remove them before calling dst_cache_destroy()
+	 */
 	dst_cache_destroy(&ioam6_lwt_state(lwt)->cache);
 }
 
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index bf727149fdec..7094d7708686 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -249,40 +249,52 @@ static struct fib6_table *fib6_alloc_table(struct net *net, u32 id)
 
 struct fib6_table *fib6_new_table(struct net *net, u32 id)
 {
-	struct fib6_table *tb;
+	struct fib6_table *tb, *new_tb;
 
 	if (id == 0)
 		id = RT6_TABLE_MAIN;
+
 	tb = fib6_get_table(net, id);
 	if (tb)
 		return tb;
 
-	tb = fib6_alloc_table(net, id);
-	if (tb)
-		fib6_link_table(net, tb);
+	new_tb = fib6_alloc_table(net, id);
+	if (!new_tb)
+		return NULL;
+
+	spin_lock_bh(&net->ipv6.fib_table_hash_lock);
+
+	tb = fib6_get_table(net, id);
+	if (unlikely(tb)) {
+		spin_unlock_bh(&net->ipv6.fib_table_hash_lock);
+		kfree(new_tb);
+		return tb;
+	}
+
+	fib6_link_table(net, new_tb);
+
+	spin_unlock_bh(&net->ipv6.fib_table_hash_lock);
 
-	return tb;
+	return new_tb;
 }
 EXPORT_SYMBOL_GPL(fib6_new_table);
 
 struct fib6_table *fib6_get_table(struct net *net, u32 id)
 {
-	struct fib6_table *tb;
 	struct hlist_head *head;
-	unsigned int h;
+	struct fib6_table *tb;
 
-	if (id == 0)
+	if (!id)
 		id = RT6_TABLE_MAIN;
-	h = id & (FIB6_TABLE_HASHSZ - 1);
-	rcu_read_lock();
-	head = &net->ipv6.fib_table_hash[h];
-	hlist_for_each_entry_rcu(tb, head, tb6_hlist) {
-		if (tb->tb6_id == id) {
-			rcu_read_unlock();
+
+	head = &net->ipv6.fib_table_hash[id & (FIB6_TABLE_HASHSZ - 1)];
+
+	/* See comment in fib6_link_table().  RCU is not required,
+	 * but rcu_dereference_raw() is used to avoid data-race.
+	 */
+	hlist_for_each_entry_rcu(tb, head, tb6_hlist, true)
+		if (tb->tb6_id == id)
 			return tb;
-		}
-	}
-	rcu_read_unlock();
 
 	return NULL;
 }
@@ -1015,8 +1027,9 @@ static void fib6_drop_pcpu_from(struct fib6_info *f6i,
 			.table = table
 		};
 
-		nexthop_for_each_fib6_nh(f6i->nh, fib6_nh_drop_pcpu_from,
-					 &arg);
+		rcu_read_lock();
+		nexthop_for_each_fib6_nh(f6i->nh, fib6_nh_drop_pcpu_from, &arg);
+		rcu_read_unlock();
 	} else {
 		struct fib6_nh *fib6_nh;
 
@@ -1034,8 +1047,14 @@ static void fib6_purge_rt(struct fib6_info *rt, struct fib6_node *fn,
 	rt6_flush_exceptions(rt);
 	fib6_drop_pcpu_from(rt, table);
 
-	if (rt->nh && !list_empty(&rt->nh_list))
-		list_del_init(&rt->nh_list);
+	if (rt->nh) {
+		spin_lock(&rt->nh->lock);
+
+		if (!list_empty(&rt->nh_list))
+			list_del_init(&rt->nh_list);
+
+		spin_unlock(&rt->nh->lock);
+	}
 
 	if (refcount_read(&rt->fib6_ref) != 1) {
 		/* This route is used as dummy address holder in some split
@@ -1069,8 +1088,8 @@ static void fib6_purge_rt(struct fib6_info *rt, struct fib6_node *fn,
  */
 
 static int fib6_add_rt2node(struct fib6_node *fn, struct fib6_info *rt,
-			    struct nl_info *info,
-			    struct netlink_ext_ack *extack)
+			    struct nl_info *info, struct netlink_ext_ack *extack,
+			    struct list_head *purge_list)
 {
 	struct fib6_info *leaf = rcu_dereference_protected(fn->leaf,
 				    lockdep_is_held(&rt->fib6_table->tb6_lock));
@@ -1203,7 +1222,9 @@ next_iter:
 			fib6_nsiblings++;
 		}
 		BUG_ON(fib6_nsiblings != rt->fib6_nsiblings);
+		rcu_read_lock();
 		rt6_multipath_rebalance(temp_sibling);
+		rcu_read_unlock();
 	}
 
 	/*
@@ -1246,7 +1267,9 @@ add:
 					sibling->fib6_nsiblings--;
 				rt->fib6_nsiblings = 0;
 				list_del_rcu(&rt->fib6_siblings);
+				rcu_read_lock();
 				rt6_multipath_rebalance(next_sibling);
+				rcu_read_unlock();
 				return err;
 			}
 		}
@@ -1294,10 +1317,9 @@ add:
 		}
 		nsiblings = iter->fib6_nsiblings;
 		iter->fib6_node = NULL;
-		fib6_purge_rt(iter, fn, info->nl_net);
+		list_add(&iter->purge_link, purge_list);
 		if (rcu_access_pointer(fn->rr_ptr) == iter)
 			fn->rr_ptr = NULL;
-		fib6_info_release(iter);
 
 		if (nsiblings) {
 			/* Replacing an ECMP route, remove all siblings */
@@ -1310,10 +1332,9 @@ add:
 				if (rt6_qualify_for_ecmp(iter)) {
 					*ins = iter->fib6_next;
 					iter->fib6_node = NULL;
-					fib6_purge_rt(iter, fn, info->nl_net);
+					list_add(&iter->purge_link, purge_list);
 					if (rcu_access_pointer(fn->rr_ptr) == iter)
 						fn->rr_ptr = NULL;
-					fib6_info_release(iter);
 					nsiblings--;
 					info->nl_net->ipv6.rt6_stats->fib_rt_entries--;
 				} else {
@@ -1329,6 +1350,28 @@ add:
 	return 0;
 }
 
+static int fib6_add_rt2node_nh(struct fib6_node *fn, struct fib6_info *rt,
+			       struct nl_info *info, struct netlink_ext_ack *extack,
+			       struct list_head *purge_list)
+{
+	int err;
+
+	spin_lock(&rt->nh->lock);
+
+	if (rt->nh->dead) {
+		NL_SET_ERR_MSG(extack, "Nexthop has been deleted");
+		err = -EINVAL;
+	} else {
+		err = fib6_add_rt2node(fn, rt, info, extack, purge_list);
+		if (!err)
+			list_add(&rt->nh_list, &rt->nh->f6i_list);
+	}
+
+	spin_unlock(&rt->nh->lock);
+
+	return err;
+}
+
 static void fib6_start_gc(struct net *net, struct fib6_info *rt)
 {
 	if (!timer_pending(&net->ipv6.ip6_fib_timer) &&
@@ -1383,6 +1426,7 @@ int fib6_add(struct fib6_node *root, struct fib6_info *rt,
 	     struct nl_info *info, struct netlink_ext_ack *extack)
 {
 	struct fib6_table *table = rt->fib6_table;
+	LIST_HEAD(purge_list);
 	struct fib6_node *fn;
 #ifdef CONFIG_IPV6_SUBTREES
 	struct fib6_node *pn = NULL;
@@ -1485,10 +1529,19 @@ int fib6_add(struct fib6_node *root, struct fib6_info *rt,
 	}
 #endif
 
-	err = fib6_add_rt2node(fn, rt, info, extack);
+	if (rt->nh)
+		err = fib6_add_rt2node_nh(fn, rt, info, extack, &purge_list);
+	else
+		err = fib6_add_rt2node(fn, rt, info, extack, &purge_list);
 	if (!err) {
-		if (rt->nh)
-			list_add(&rt->nh_list, &rt->nh->f6i_list);
+		struct fib6_info *iter, *next;
+
+		list_for_each_entry_safe(iter, next, &purge_list, purge_link) {
+			list_del(&iter->purge_link);
+			fib6_purge_rt(iter, fn, info->nl_net);
+			fib6_info_release(iter);
+		}
+
 		__fib6_update_sernum_upto_root(rt, fib6_new_sernum(info->nl_net));
 
 		if (rt->fib6_flags & RTF_EXPIRES)
@@ -2423,6 +2476,8 @@ static int __net_init fib6_net_init(struct net *net)
 	if (!net->ipv6.fib_table_hash)
 		goto out_rt6_stats;
 
+	spin_lock_init(&net->ipv6.fib_table_hash_lock);
+
 	net->ipv6.fib6_main_tbl = kzalloc(sizeof(*net->ipv6.fib6_main_tbl),
 					  GFP_KERNEL);
 	if (!net->ipv6.fib6_main_tbl)
diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index 957ca98fa70f..2dc9dcffe2ca 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -1570,7 +1570,7 @@ static struct inet6_protocol ip6gre_protocol __read_mostly = {
 	.flags       = INET6_PROTO_FINAL,
 };
 
-static void ip6gre_destroy_tunnels(struct net *net, struct list_head *head)
+static void __net_exit ip6gre_exit_rtnl_net(struct net *net, struct list_head *head)
 {
 	struct ip6gre_net *ign = net_generic(net, ip6gre_net_id);
 	struct net_device *dev, *aux;
@@ -1587,16 +1587,16 @@ static void ip6gre_destroy_tunnels(struct net *net, struct list_head *head)
 		for (h = 0; h < IP6_GRE_HASH_SIZE; h++) {
 			struct ip6_tnl *t;
 
-			t = rtnl_dereference(ign->tunnels[prio][h]);
+			t = rtnl_net_dereference(net, ign->tunnels[prio][h]);
 
 			while (t) {
 				/* If dev is in the same netns, it has already
 				 * been added to the list by the previous loop.
 				 */
 				if (!net_eq(dev_net(t->dev), net))
-					unregister_netdevice_queue(t->dev,
-								   head);
-				t = rtnl_dereference(t->next);
+					unregister_netdevice_queue(t->dev, head);
+
+				t = rtnl_net_dereference(net, t->next);
 			}
 		}
 	}
@@ -1640,19 +1640,9 @@ err_alloc_dev:
 	return err;
 }
 
-static void __net_exit ip6gre_exit_batch_rtnl(struct list_head *net_list,
-					      struct list_head *dev_to_kill)
-{
-	struct net *net;
-
-	ASSERT_RTNL();
-	list_for_each_entry(net, net_list, exit_list)
-		ip6gre_destroy_tunnels(net, dev_to_kill);
-}
-
 static struct pernet_operations ip6gre_net_ops = {
 	.init = ip6gre_init_net,
-	.exit_batch_rtnl = ip6gre_exit_batch_rtnl,
+	.exit_rtnl = ip6gre_exit_rtnl_net,
 	.id   = &ip6gre_net_id,
 	.size = sizeof(struct ip6gre_net),
 };
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 581bc6289081..7bd29a9ff0db 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -259,7 +259,7 @@ bool ip6_autoflowlabel(struct net *net, const struct sock *sk)
 }
 
 /*
- * xmit an sk_buff (used by TCP, SCTP and DCCP)
+ * xmit an sk_buff (used by TCP and SCTP)
  * Note : socket lock is not held for SYNACK packets, but might be modified
  * by calls to skb_set_owner_w() and ipv6_local_error(),
  * which are using proper atomic operations or spinlocks.
@@ -1524,7 +1524,8 @@ emsgsize:
 				uarg = msg->msg_ubuf;
 			}
 		} else if (sock_flag(sk, SOCK_ZEROCOPY)) {
-			uarg = msg_zerocopy_realloc(sk, length, skb_zcopy(skb));
+			uarg = msg_zerocopy_realloc(sk, length, skb_zcopy(skb),
+						    false);
 			if (!uarg)
 				return -ENOBUFS;
 			extra_uref = !skb_zcopy(skb);	/* only ref on new uarg */
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index a04dd1bb4b19..894d3158a6f0 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -2210,7 +2210,7 @@ static struct xfrm6_tunnel mplsip6_handler __read_mostly = {
 	.priority	=	1,
 };
 
-static void __net_exit ip6_tnl_destroy_tunnels(struct net *net, struct list_head *list)
+static void __net_exit ip6_tnl_exit_rtnl_net(struct net *net, struct list_head *list)
 {
 	struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id);
 	struct net_device *dev, *aux;
@@ -2222,25 +2222,27 @@ static void __net_exit ip6_tnl_destroy_tunnels(struct net *net, struct list_head
 			unregister_netdevice_queue(dev, list);
 
 	for (h = 0; h < IP6_TUNNEL_HASH_SIZE; h++) {
-		t = rtnl_dereference(ip6n->tnls_r_l[h]);
+		t = rtnl_net_dereference(net, ip6n->tnls_r_l[h]);
 		while (t) {
 			/* If dev is in the same netns, it has already
 			 * been added to the list by the previous loop.
 			 */
 			if (!net_eq(dev_net(t->dev), net))
 				unregister_netdevice_queue(t->dev, list);
-			t = rtnl_dereference(t->next);
+
+			t = rtnl_net_dereference(net, t->next);
 		}
 	}
 
-	t = rtnl_dereference(ip6n->tnls_wc[0]);
+	t = rtnl_net_dereference(net, ip6n->tnls_wc[0]);
 	while (t) {
 		/* If dev is in the same netns, it has already
 		 * been added to the list by the previous loop.
 		 */
 		if (!net_eq(dev_net(t->dev), net))
 			unregister_netdevice_queue(t->dev, list);
-		t = rtnl_dereference(t->next);
+
+		t = rtnl_net_dereference(net, t->next);
 	}
 }
 
@@ -2287,19 +2289,9 @@ err_alloc_dev:
 	return err;
 }
 
-static void __net_exit ip6_tnl_exit_batch_rtnl(struct list_head *net_list,
-					       struct list_head *dev_to_kill)
-{
-	struct net *net;
-
-	ASSERT_RTNL();
-	list_for_each_entry(net, net_list, exit_list)
-		ip6_tnl_destroy_tunnels(net, dev_to_kill);
-}
-
 static struct pernet_operations ip6_tnl_net_ops = {
 	.init = ip6_tnl_init_net,
-	.exit_batch_rtnl = ip6_tnl_exit_batch_rtnl,
+	.exit_rtnl = ip6_tnl_exit_rtnl_net,
 	.id   = &ip6_tnl_net_id,
 	.size = sizeof(struct ip6_tnl_net),
 };
diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c
index 09ec4b0ad7dc..40464a88bca6 100644
--- a/net/ipv6/ip6_vti.c
+++ b/net/ipv6/ip6_vti.c
@@ -1112,21 +1112,21 @@ static struct rtnl_link_ops vti6_link_ops __read_mostly = {
 	.get_link_net	= ip6_tnl_get_link_net,
 };
 
-static void __net_exit vti6_destroy_tunnels(struct vti6_net *ip6n,
-					    struct list_head *list)
+static void __net_exit vti6_exit_rtnl_net(struct net *net, struct list_head *list)
 {
-	int h;
+	struct vti6_net *ip6n = net_generic(net, vti6_net_id);
 	struct ip6_tnl *t;
+	int h;
 
 	for (h = 0; h < IP6_VTI_HASH_SIZE; h++) {
-		t = rtnl_dereference(ip6n->tnls_r_l[h]);
+		t = rtnl_net_dereference(net, ip6n->tnls_r_l[h]);
 		while (t) {
 			unregister_netdevice_queue(t->dev, list);
-			t = rtnl_dereference(t->next);
+			t = rtnl_net_dereference(net, t->next);
 		}
 	}
 
-	t = rtnl_dereference(ip6n->tnls_wc[0]);
+	t = rtnl_net_dereference(net, ip6n->tnls_wc[0]);
 	if (t)
 		unregister_netdevice_queue(t->dev, list);
 }
@@ -1170,22 +1170,9 @@ err_alloc_dev:
 	return err;
 }
 
-static void __net_exit vti6_exit_batch_rtnl(struct list_head *net_list,
-					    struct list_head *dev_to_kill)
-{
-	struct vti6_net *ip6n;
-	struct net *net;
-
-	ASSERT_RTNL();
-	list_for_each_entry(net, net_list, exit_list) {
-		ip6n = net_generic(net, vti6_net_id);
-		vti6_destroy_tunnels(ip6n, dev_to_kill);
-	}
-}
-
 static struct pernet_operations vti6_net_ops = {
 	.init = vti6_init_net,
-	.exit_batch_rtnl = vti6_exit_batch_rtnl,
+	.exit_rtnl = vti6_exit_rtnl_net,
 	.id   = &vti6_net_id,
 	.size = sizeof(struct vti6_net),
 };
diff --git a/net/ipv6/netfilter.c b/net/ipv6/netfilter.c
index 581ce055bf52..4541836ee3da 100644
--- a/net/ipv6/netfilter.c
+++ b/net/ipv6/netfilter.c
@@ -164,20 +164,20 @@ int br_ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
 		struct ip6_fraglist_iter iter;
 		struct sk_buff *frag2;
 
-		if (first_len - hlen > mtu ||
-		    skb_headroom(skb) < (hroom + sizeof(struct frag_hdr)))
+		if (first_len - hlen > mtu)
 			goto blackhole;
 
-		if (skb_cloned(skb))
+		if (skb_cloned(skb) ||
+		    skb_headroom(skb) < (hroom + sizeof(struct frag_hdr)))
 			goto slow_path;
 
 		skb_walk_frags(skb, frag2) {
-			if (frag2->len > mtu ||
-			    skb_headroom(frag2) < (hlen + hroom + sizeof(struct frag_hdr)))
+			if (frag2->len > mtu)
 				goto blackhole;
 
 			/* Partially cloned skb? */
-			if (skb_shared(frag2))
+			if (skb_shared(frag2) ||
+			    skb_headroom(frag2) < (hlen + hroom + sizeof(struct frag_hdr)))
 				goto slow_path;
 		}
 
diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c
index 7d5602950ae7..d585ac3c1113 100644
--- a/net/ipv6/netfilter/ip6_tables.c
+++ b/net/ipv6/netfilter/ip6_tables.c
@@ -292,7 +292,7 @@ ip6t_do_table(void *priv, struct sk_buff *skb,
 	 * but it is no problem since absolute verdict is issued by these.
 	 */
 	if (static_key_false(&xt_tee_enabled))
-		jumpstack += private->stacksize * __this_cpu_read(nf_skb_duplicated);
+		jumpstack += private->stacksize * current->in_nf_duplicate;
 
 	e = get_entry(table_base, private->hook_entry[hook]);
 
diff --git a/net/ipv6/netfilter/nf_dup_ipv6.c b/net/ipv6/netfilter/nf_dup_ipv6.c
index 0c39c77fe8a8..b903c62c00c9 100644
--- a/net/ipv6/netfilter/nf_dup_ipv6.c
+++ b/net/ipv6/netfilter/nf_dup_ipv6.c
@@ -48,7 +48,7 @@ void nf_dup_ipv6(struct net *net, struct sk_buff *skb, unsigned int hooknum,
 		 const struct in6_addr *gw, int oif)
 {
 	local_bh_disable();
-	if (this_cpu_read(nf_skb_duplicated))
+	if (current->in_nf_duplicate)
 		goto out;
 	skb = pskb_copy(skb, GFP_ATOMIC);
 	if (skb == NULL)
@@ -64,9 +64,9 @@ void nf_dup_ipv6(struct net *net, struct sk_buff *skb, unsigned int hooknum,
 		--iph->hop_limit;
 	}
 	if (nf_dup_ipv6_route(net, skb, gw, oif)) {
-		__this_cpu_write(nf_skb_duplicated, true);
+		current->in_nf_duplicate = true;
 		ip6_local_out(net, skb->sk, skb);
-		__this_cpu_write(nf_skb_duplicated, false);
+		current->in_nf_duplicate = false;
 	} else {
 		kfree_skb(skb);
 	}
diff --git a/net/ipv6/netfilter/nft_fib_ipv6.c b/net/ipv6/netfilter/nft_fib_ipv6.c
index 7fd9d7b21cd4..421036a3605b 100644
--- a/net/ipv6/netfilter/nft_fib_ipv6.c
+++ b/net/ipv6/netfilter/nft_fib_ipv6.c
@@ -50,6 +50,7 @@ static int nft_fib6_flowi_init(struct flowi6 *fl6, const struct nft_fib *priv,
 		fl6->flowi6_mark = pkt->skb->mark;
 
 	fl6->flowlabel = (*(__be32 *)iph) & IPV6_FLOWINFO_MASK;
+	fl6->flowi6_l3mdev = nft_fib_l3mdev_master_ifindex_rcu(pkt, dev);
 
 	return lookup_flags;
 }
@@ -73,8 +74,6 @@ static u32 __nft_fib6_eval_type(const struct nft_fib *priv,
 	else if (priv->flags & NFTA_FIB_F_OIF)
 		dev = nft_out(pkt);
 
-	fl6.flowi6_l3mdev = l3mdev_master_ifindex_rcu(dev);
-
 	nft_fib6_flowi_init(&fl6, priv, pkt, dev, iph);
 
 	if (dev && nf_ipv6_chk_addr(nft_net(pkt), &fl6.daddr, dev, true))
@@ -158,6 +157,7 @@ void nft_fib6_eval(const struct nft_expr *expr, struct nft_regs *regs,
 {
 	const struct nft_fib *priv = nft_expr_priv(expr);
 	int noff = skb_network_offset(pkt->skb);
+	const struct net_device *found = NULL;
 	const struct net_device *oif = NULL;
 	u32 *dest = &regs->data[priv->dreg];
 	struct ipv6hdr *iph, _iph;
@@ -165,7 +165,6 @@ void nft_fib6_eval(const struct nft_expr *expr, struct nft_regs *regs,
 		.flowi6_iif = LOOPBACK_IFINDEX,
 		.flowi6_proto = pkt->tprot,
 		.flowi6_uid = sock_net_uid(nft_net(pkt), NULL),
-		.flowi6_l3mdev = l3mdev_master_ifindex_rcu(nft_in(pkt)),
 	};
 	struct rt6_info *rt;
 	int lookup_flags;
@@ -203,11 +202,15 @@ void nft_fib6_eval(const struct nft_expr *expr, struct nft_regs *regs,
 	if (rt->rt6i_flags & (RTF_REJECT | RTF_ANYCAST | RTF_LOCAL))
 		goto put_rt_err;
 
-	if (oif && oif != rt->rt6i_idev->dev &&
-	    l3mdev_master_ifindex_rcu(rt->rt6i_idev->dev) != oif->ifindex)
-		goto put_rt_err;
+	if (!oif) {
+		found = rt->rt6i_idev->dev;
+	} else {
+		if (oif == rt->rt6i_idev->dev ||
+		    l3mdev_master_ifindex_rcu(rt->rt6i_idev->dev) == oif->ifindex)
+			found = oif;
+	}
 
-	nft_fib_store_result(dest, priv, rt->rt6i_idev->dev);
+	nft_fib_store_result(dest, priv, found);
  put_rt_err:
 	ip6_rt_put(rt);
 }
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 96f1621e2381..0143262094b0 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -1820,11 +1820,13 @@ static int rt6_nh_flush_exceptions(struct fib6_nh *nh, void *arg)
 
 void rt6_flush_exceptions(struct fib6_info *f6i)
 {
-	if (f6i->nh)
-		nexthop_for_each_fib6_nh(f6i->nh, rt6_nh_flush_exceptions,
-					 f6i);
-	else
+	if (f6i->nh) {
+		rcu_read_lock();
+		nexthop_for_each_fib6_nh(f6i->nh, rt6_nh_flush_exceptions, f6i);
+		rcu_read_unlock();
+	} else {
 		fib6_nh_flush_exceptions(f6i->fib6_nh, f6i);
+	}
 }
 
 /* Find cached rt in the hash table inside passed in rt
@@ -2492,8 +2494,12 @@ static u32 rt6_multipath_custom_hash_fl6(const struct net *net,
 		hash_keys.basic.ip_proto = fl6->flowi6_proto;
 	if (hash_fields & FIB_MULTIPATH_HASH_FIELD_FLOWLABEL)
 		hash_keys.tags.flow_label = (__force u32)flowi6_get_flowlabel(fl6);
-	if (hash_fields & FIB_MULTIPATH_HASH_FIELD_SRC_PORT)
-		hash_keys.ports.src = fl6->fl6_sport;
+	if (hash_fields & FIB_MULTIPATH_HASH_FIELD_SRC_PORT) {
+		if (fl6->flowi6_flags & FLOWI_FLAG_ANY_SPORT)
+			hash_keys.ports.src = (__force __be16)get_random_u16();
+		else
+			hash_keys.ports.src = fl6->fl6_sport;
+	}
 	if (hash_fields & FIB_MULTIPATH_HASH_FIELD_DST_PORT)
 		hash_keys.ports.dst = fl6->fl6_dport;
 
@@ -2547,7 +2553,10 @@ u32 rt6_multipath_hash(const struct net *net, const struct flowi6 *fl6,
 			hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS;
 			hash_keys.addrs.v6addrs.src = fl6->saddr;
 			hash_keys.addrs.v6addrs.dst = fl6->daddr;
-			hash_keys.ports.src = fl6->fl6_sport;
+			if (fl6->flowi6_flags & FLOWI_FLAG_ANY_SPORT)
+				hash_keys.ports.src = (__force __be16)get_random_u16();
+			else
+				hash_keys.ports.src = fl6->fl6_sport;
 			hash_keys.ports.dst = fl6->fl6_dport;
 			hash_keys.basic.ip_proto = fl6->flowi6_proto;
 		}
@@ -3729,61 +3738,14 @@ void fib6_nh_release_dsts(struct fib6_nh *fib6_nh)
 }
 
 static struct fib6_info *ip6_route_info_create(struct fib6_config *cfg,
-					      gfp_t gfp_flags,
-					      struct netlink_ext_ack *extack)
+					       gfp_t gfp_flags,
+					       struct netlink_ext_ack *extack)
 {
 	struct net *net = cfg->fc_nlinfo.nl_net;
-	struct fib6_info *rt = NULL;
-	struct nexthop *nh = NULL;
 	struct fib6_table *table;
-	struct fib6_nh *fib6_nh;
-	int err = -EINVAL;
-	int addr_type;
-
-	/* RTF_PCPU is an internal flag; can not be set by userspace */
-	if (cfg->fc_flags & RTF_PCPU) {
-		NL_SET_ERR_MSG(extack, "Userspace can not set RTF_PCPU");
-		goto out;
-	}
-
-	/* RTF_CACHE is an internal flag; can not be set by userspace */
-	if (cfg->fc_flags & RTF_CACHE) {
-		NL_SET_ERR_MSG(extack, "Userspace can not set RTF_CACHE");
-		goto out;
-	}
-
-	if (cfg->fc_type > RTN_MAX) {
-		NL_SET_ERR_MSG(extack, "Invalid route type");
-		goto out;
-	}
-
-	if (cfg->fc_dst_len > 128) {
-		NL_SET_ERR_MSG(extack, "Invalid prefix length");
-		goto out;
-	}
-	if (cfg->fc_src_len > 128) {
-		NL_SET_ERR_MSG(extack, "Invalid source address length");
-		goto out;
-	}
-#ifndef CONFIG_IPV6_SUBTREES
-	if (cfg->fc_src_len) {
-		NL_SET_ERR_MSG(extack,
-			       "Specifying source address requires IPV6_SUBTREES to be enabled");
-		goto out;
-	}
-#endif
-	if (cfg->fc_nh_id) {
-		nh = nexthop_find_by_id(net, cfg->fc_nh_id);
-		if (!nh) {
-			NL_SET_ERR_MSG(extack, "Nexthop id does not exist");
-			goto out;
-		}
-		err = fib6_check_nexthop(nh, cfg, extack);
-		if (err)
-			goto out;
-	}
+	struct fib6_info *rt;
+	int err;
 
-	err = -ENOBUFS;
 	if (cfg->fc_nlinfo.nlh &&
 	    !(cfg->fc_nlinfo.nlh->nlmsg_flags & NLM_F_CREATE)) {
 		table = fib6_get_table(net, cfg->fc_table);
@@ -3794,22 +3756,22 @@ static struct fib6_info *ip6_route_info_create(struct fib6_config *cfg,
 	} else {
 		table = fib6_new_table(net, cfg->fc_table);
 	}
+	if (!table) {
+		err = -ENOBUFS;
+		goto err;
+	}
 
-	if (!table)
-		goto out;
-
-	err = -ENOMEM;
-	rt = fib6_info_alloc(gfp_flags, !nh);
-	if (!rt)
-		goto out;
+	rt = fib6_info_alloc(gfp_flags, !cfg->fc_nh_id);
+	if (!rt) {
+		err = -ENOMEM;
+		goto err;
+	}
 
 	rt->fib6_metrics = ip_fib_metrics_init(cfg->fc_mx, cfg->fc_mx_len,
 					       extack);
 	if (IS_ERR(rt->fib6_metrics)) {
 		err = PTR_ERR(rt->fib6_metrics);
-		/* Do not leave garbage there. */
-		rt->fib6_metrics = (struct dst_metrics *)&dst_default_metrics;
-		goto out_free;
+		goto free;
 	}
 
 	if (cfg->fc_flags & RTF_ADDRCONF)
@@ -3817,12 +3779,12 @@ static struct fib6_info *ip6_route_info_create(struct fib6_config *cfg,
 
 	if (cfg->fc_flags & RTF_EXPIRES)
 		fib6_set_expires(rt, jiffies +
-				clock_t_to_jiffies(cfg->fc_expires));
+				 clock_t_to_jiffies(cfg->fc_expires));
 
 	if (cfg->fc_protocol == RTPROT_UNSPEC)
 		cfg->fc_protocol = RTPROT_BOOT;
-	rt->fib6_protocol = cfg->fc_protocol;
 
+	rt->fib6_protocol = cfg->fc_protocol;
 	rt->fib6_table = table;
 	rt->fib6_metric = cfg->fc_metric;
 	rt->fib6_type = cfg->fc_type ? : RTN_UNICAST;
@@ -3835,23 +3797,54 @@ static struct fib6_info *ip6_route_info_create(struct fib6_config *cfg,
 	ipv6_addr_prefix(&rt->fib6_src.addr, &cfg->fc_src, cfg->fc_src_len);
 	rt->fib6_src.plen = cfg->fc_src_len;
 #endif
-	if (nh) {
-		if (rt->fib6_src.plen) {
-			NL_SET_ERR_MSG(extack, "Nexthops can not be used with source routing");
+	return rt;
+free:
+	kfree(rt);
+err:
+	return ERR_PTR(err);
+}
+
+static int ip6_route_info_create_nh(struct fib6_info *rt,
+				    struct fib6_config *cfg,
+				    gfp_t gfp_flags,
+				    struct netlink_ext_ack *extack)
+{
+	struct net *net = cfg->fc_nlinfo.nl_net;
+	struct fib6_nh *fib6_nh;
+	int err;
+
+	if (cfg->fc_nh_id) {
+		struct nexthop *nh;
+
+		rcu_read_lock();
+
+		nh = nexthop_find_by_id(net, cfg->fc_nh_id);
+		if (!nh) {
 			err = -EINVAL;
+			NL_SET_ERR_MSG(extack, "Nexthop id does not exist");
 			goto out_free;
 		}
+
+		err = fib6_check_nexthop(nh, cfg, extack);
+		if (err)
+			goto out_free;
+
 		if (!nexthop_get(nh)) {
 			NL_SET_ERR_MSG(extack, "Nexthop has been deleted");
 			err = -ENOENT;
 			goto out_free;
 		}
+
 		rt->nh = nh;
 		fib6_nh = nexthop_fib6_nh(rt->nh);
+
+		rcu_read_unlock();
 	} else {
+		int addr_type;
+
 		err = fib6_nh_init(net, rt->fib6_nh, cfg, gfp_flags, extack);
 		if (err)
-			goto out;
+			goto out_release;
 
 		fib6_nh = rt->fib6_nh;
 
@@ -3870,21 +3863,21 @@ static struct fib6_info *ip6_route_info_create(struct fib6_config *cfg,
 		if (!ipv6_chk_addr(net, &cfg->fc_prefsrc, dev, 0)) {
 			NL_SET_ERR_MSG(extack, "Invalid source address");
 			err = -EINVAL;
-			goto out;
+			goto out_release;
 		}
 		rt->fib6_prefsrc.addr = cfg->fc_prefsrc;
 		rt->fib6_prefsrc.plen = 128;
-	} else
-		rt->fib6_prefsrc.plen = 0;
+	}
 
-	return rt;
-out:
+	return 0;
+out_release:
 	fib6_info_release(rt);
-	return ERR_PTR(err);
+	return err;
 out_free:
+	rcu_read_unlock();
 	ip_fib_metrics_put(rt->fib6_metrics);
 	kfree(rt);
-	return ERR_PTR(err);
+	return err;
 }
 
 int ip6_route_add(struct fib6_config *cfg, gfp_t gfp_flags,
@@ -3897,6 +3890,10 @@ int ip6_route_add(struct fib6_config *cfg, gfp_t gfp_flags,
 	if (IS_ERR(rt))
 		return PTR_ERR(rt);
 
+	err = ip6_route_info_create_nh(rt, cfg, gfp_flags, extack);
+	if (err)
+		return err;
+
 	err = __ip6_ins_rt(rt, &cfg->fc_nlinfo, extack);
 	fib6_info_release(rt);
 
@@ -4125,9 +4122,9 @@ static int ip6_route_del(struct fib6_config *cfg,
 			if (rt->nh) {
 				if (!fib6_info_hold_safe(rt))
 					continue;
-				rcu_read_unlock();
 
-				return __ip6_del_rt(rt, &cfg->fc_nlinfo);
+				err =  __ip6_del_rt(rt, &cfg->fc_nlinfo);
+				break;
 			}
 			if (cfg->fc_nh_id)
 				continue;
@@ -4142,13 +4139,13 @@ static int ip6_route_del(struct fib6_config *cfg,
 				continue;
 			if (!fib6_info_hold_safe(rt))
 				continue;
-			rcu_read_unlock();
 
 			/* if gateway was specified only delete the one hop */
 			if (cfg->fc_flags & RTF_GATEWAY)
-				return __ip6_del_rt(rt, &cfg->fc_nlinfo);
-
-			return __ip6_del_rt_siblings(rt, cfg);
+				err = __ip6_del_rt(rt, &cfg->fc_nlinfo);
+			else
+				err = __ip6_del_rt_siblings(rt, cfg);
+			break;
 		}
 	}
 	rcu_read_unlock();
@@ -4482,6 +4479,53 @@ void rt6_purge_dflt_routers(struct net *net)
 	rcu_read_unlock();
 }
 
+static int fib6_config_validate(struct fib6_config *cfg,
+				struct netlink_ext_ack *extack)
+{
+	/* RTF_PCPU is an internal flag; can not be set by userspace */
+	if (cfg->fc_flags & RTF_PCPU) {
+		NL_SET_ERR_MSG(extack, "Userspace can not set RTF_PCPU");
+		goto errout;
+	}
+
+	/* RTF_CACHE is an internal flag; can not be set by userspace */
+	if (cfg->fc_flags & RTF_CACHE) {
+		NL_SET_ERR_MSG(extack, "Userspace can not set RTF_CACHE");
+		goto errout;
+	}
+
+	if (cfg->fc_type > RTN_MAX) {
+		NL_SET_ERR_MSG(extack, "Invalid route type");
+		goto errout;
+	}
+
+	if (cfg->fc_dst_len > 128) {
+		NL_SET_ERR_MSG(extack, "Invalid prefix length");
+		goto errout;
+	}
+
+#ifdef CONFIG_IPV6_SUBTREES
+	if (cfg->fc_src_len > 128) {
+		NL_SET_ERR_MSG(extack, "Invalid source address length");
+		goto errout;
+	}
+
+	if (cfg->fc_nh_id && cfg->fc_src_len) {
+		NL_SET_ERR_MSG(extack, "Nexthops can not be used with source routing");
+		goto errout;
+	}
+#else
+	if (cfg->fc_src_len) {
+		NL_SET_ERR_MSG(extack,
+			       "Specifying source address requires IPV6_SUBTREES to be enabled");
+		goto errout;
+	}
+#endif
+	return 0;
+errout:
+	return -EINVAL;
+}
+
 static void rtmsg_to_fib6_config(struct net *net,
 				 struct in6_rtmsg *rtmsg,
 				 struct fib6_config *cfg)
@@ -4517,9 +4561,12 @@ int ipv6_route_ioctl(struct net *net, unsigned int cmd, struct in6_rtmsg *rtmsg)
 
 	rtmsg_to_fib6_config(net, rtmsg, &cfg);
 
-	rtnl_lock();
 	switch (cmd) {
 	case SIOCADDRT:
+		err = fib6_config_validate(&cfg, NULL);
+		if (err)
+			break;
+
 		/* Only do the default setting of fc_metric in route adding */
 		if (cfg.fc_metric == 0)
 			cfg.fc_metric = IP6_RT_PRIO_USER;
@@ -4529,7 +4576,7 @@ int ipv6_route_ioctl(struct net *net, unsigned int cmd, struct in6_rtmsg *rtmsg)
 		err = ip6_route_del(&cfg, NULL);
 		break;
 	}
-	rtnl_unlock();
+
 	return err;
 }
 
@@ -4619,6 +4666,7 @@ struct fib6_info *addrconf_f6i_alloc(struct net *net,
 		.fc_ignore_dev_down = true,
 	};
 	struct fib6_info *f6i;
+	int err;
 
 	if (anycast) {
 		cfg.fc_type = RTN_ANYCAST;
@@ -4629,14 +4677,19 @@ struct fib6_info *addrconf_f6i_alloc(struct net *net,
 	}
 
 	f6i = ip6_route_info_create(&cfg, gfp_flags, extack);
-	if (!IS_ERR(f6i)) {
-		f6i->dst_nocount = true;
+	if (IS_ERR(f6i))
+		return f6i;
 
-		if (!anycast &&
-		    (READ_ONCE(net->ipv6.devconf_all->disable_policy) ||
-		     READ_ONCE(idev->cnf.disable_policy)))
-			f6i->dst_nopolicy = true;
-	}
+	err = ip6_route_info_create_nh(f6i, &cfg, gfp_flags, extack);
+	if (err)
+		return ERR_PTR(err);
+
+	f6i->dst_nocount = true;
+
+	if (!anycast &&
+	    (READ_ONCE(net->ipv6.devconf_all->disable_policy) ||
+	     READ_ONCE(idev->cnf.disable_policy)))
+		f6i->dst_nopolicy = true;
 
 	return f6i;
 }
@@ -5051,12 +5104,60 @@ static const struct nla_policy rtm_ipv6_policy[RTA_MAX+1] = {
 	[RTA_FLOWLABEL]		= { .type = NLA_BE32 },
 };
 
+static int rtm_to_fib6_multipath_config(struct fib6_config *cfg,
+					struct netlink_ext_ack *extack,
+					bool newroute)
+{
+	struct rtnexthop *rtnh;
+	int remaining;
+
+	remaining = cfg->fc_mp_len;
+	rtnh = (struct rtnexthop *)cfg->fc_mp;
+
+	if (!rtnh_ok(rtnh, remaining)) {
+		NL_SET_ERR_MSG(extack, "Invalid nexthop configuration - no valid nexthops");
+		return -EINVAL;
+	}
+
+	do {
+		bool has_gateway = cfg->fc_flags & RTF_GATEWAY;
+		int attrlen = rtnh_attrlen(rtnh);
+
+		if (attrlen > 0) {
+			struct nlattr *nla, *attrs;
+
+			attrs = rtnh_attrs(rtnh);
+			nla = nla_find(attrs, attrlen, RTA_GATEWAY);
+			if (nla) {
+				if (nla_len(nla) < sizeof(cfg->fc_gateway)) {
+					NL_SET_ERR_MSG(extack,
+						       "Invalid IPv6 address in RTA_GATEWAY");
+					return -EINVAL;
+				}
+
+				has_gateway = true;
+			}
+		}
+
+		if (newroute && (cfg->fc_nh_id || !has_gateway)) {
+			NL_SET_ERR_MSG(extack,
+				       "Device only routes can not be added for IPv6 using the multipath API.");
+			return -EINVAL;
+		}
+
+		rtnh = rtnh_next(rtnh, &remaining);
+	} while (rtnh_ok(rtnh, remaining));
+
+	return lwtunnel_valid_encap_type_attr(cfg->fc_mp, cfg->fc_mp_len, extack);
+}
+
 static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh,
 			      struct fib6_config *cfg,
 			      struct netlink_ext_ack *extack)
 {
-	struct rtmsg *rtm;
+	bool newroute = nlh->nlmsg_type == RTM_NEWROUTE;
 	struct nlattr *tb[RTA_MAX+1];
+	struct rtmsg *rtm;
 	unsigned int pref;
 	int err;
 
@@ -5165,9 +5266,7 @@ static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh,
 		cfg->fc_mp = nla_data(tb[RTA_MULTIPATH]);
 		cfg->fc_mp_len = nla_len(tb[RTA_MULTIPATH]);
 
-		err = lwtunnel_valid_encap_type_attr(cfg->fc_mp,
-						     cfg->fc_mp_len,
-						     extack, true);
+		err = rtm_to_fib6_multipath_config(cfg, extack, newroute);
 		if (err < 0)
 			goto errout;
 	}
@@ -5186,8 +5285,7 @@ static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh,
 	if (tb[RTA_ENCAP_TYPE]) {
 		cfg->fc_encap_type = nla_get_u16(tb[RTA_ENCAP_TYPE]);
 
-		err = lwtunnel_valid_encap_type(cfg->fc_encap_type,
-						extack, true);
+		err = lwtunnel_valid_encap_type(cfg->fc_encap_type, extack);
 		if (err < 0)
 			goto errout;
 	}
@@ -5209,29 +5307,28 @@ errout:
 struct rt6_nh {
 	struct fib6_info *fib6_info;
 	struct fib6_config r_cfg;
-	struct list_head next;
+	struct list_head list;
 };
 
-static int ip6_route_info_append(struct net *net,
-				 struct list_head *rt6_nh_list,
+static int ip6_route_info_append(struct list_head *rt6_nh_list,
 				 struct fib6_info *rt,
 				 struct fib6_config *r_cfg)
 {
 	struct rt6_nh *nh;
-	int err = -EEXIST;
 
-	list_for_each_entry(nh, rt6_nh_list, next) {
+	list_for_each_entry(nh, rt6_nh_list, list) {
 		/* check if fib6_info already exists */
 		if (rt6_duplicate_nexthop(nh->fib6_info, rt))
-			return err;
+			return -EEXIST;
 	}
 
 	nh = kzalloc(sizeof(*nh), GFP_KERNEL);
 	if (!nh)
 		return -ENOMEM;
+
 	nh->fib6_info = rt;
 	memcpy(&nh->r_cfg, r_cfg, sizeof(*r_cfg));
-	list_add_tail(&nh->next, rt6_nh_list);
+	list_add_tail(&nh->list, rt6_nh_list);
 
 	return 0;
 }
@@ -5287,37 +5384,26 @@ out:
 	return should_notify;
 }
 
-static int fib6_gw_from_attr(struct in6_addr *gw, struct nlattr *nla,
-			     struct netlink_ext_ack *extack)
-{
-	if (nla_len(nla) < sizeof(*gw)) {
-		NL_SET_ERR_MSG(extack, "Invalid IPv6 address in RTA_GATEWAY");
-		return -EINVAL;
-	}
-
-	*gw = nla_get_in6_addr(nla);
-
-	return 0;
-}
-
 static int ip6_route_multipath_add(struct fib6_config *cfg,
 				   struct netlink_ext_ack *extack)
 {
 	struct fib6_info *rt_notif = NULL, *rt_last = NULL;
 	struct nl_info *info = &cfg->fc_nlinfo;
+	struct rt6_nh *nh, *nh_safe;
 	struct fib6_config r_cfg;
 	struct rtnexthop *rtnh;
-	struct fib6_info *rt;
+	LIST_HEAD(rt6_nh_list);
 	struct rt6_nh *err_nh;
-	struct rt6_nh *nh, *nh_safe;
+	struct fib6_info *rt;
 	__u16 nlflags;
 	int remaining;
 	int attrlen;
-	int err = 1;
+	int replace;
 	int nhn = 0;
-	int replace = (cfg->fc_nlinfo.nlh &&
-		       (cfg->fc_nlinfo.nlh->nlmsg_flags & NLM_F_REPLACE));
-	LIST_HEAD(rt6_nh_list);
+	int err;
+
+	replace = (cfg->fc_nlinfo.nlh &&
+		   (cfg->fc_nlinfo.nlh->nlmsg_flags & NLM_F_REPLACE));
 
 	nlflags = replace ? NLM_F_REPLACE : NLM_F_CREATE;
 	if (info->nlh && info->nlh->nlmsg_flags & NLM_F_APPEND)
@@ -5340,18 +5426,11 @@ static int ip6_route_multipath_add(struct fib6_config *cfg,
 
 			nla = nla_find(attrs, attrlen, RTA_GATEWAY);
 			if (nla) {
-				err = fib6_gw_from_attr(&r_cfg.fc_gateway, nla,
-							extack);
-				if (err)
-					goto cleanup;
-
+				r_cfg.fc_gateway = nla_get_in6_addr(nla);
 				r_cfg.fc_flags |= RTF_GATEWAY;
 			}
-			r_cfg.fc_encap = nla_find(attrs, attrlen, RTA_ENCAP);
 
-			/* RTA_ENCAP_TYPE length checked in
-			 * lwtunnel_valid_encap_type_attr
-			 */
+			r_cfg.fc_encap = nla_find(attrs, attrlen, RTA_ENCAP);
 			nla = nla_find(attrs, attrlen, RTA_ENCAP_TYPE);
 			if (nla)
 				r_cfg.fc_encap_type = nla_get_u16(nla);
@@ -5364,18 +5443,16 @@ static int ip6_route_multipath_add(struct fib6_config *cfg,
 			rt = NULL;
 			goto cleanup;
 		}
-		if (!rt6_qualify_for_ecmp(rt)) {
-			err = -EINVAL;
-			NL_SET_ERR_MSG(extack,
-				       "Device only routes can not be added for IPv6 using the multipath API.");
-			fib6_info_release(rt);
+
+		err = ip6_route_info_create_nh(rt, &r_cfg, GFP_KERNEL, extack);
+		if (err) {
+			rt = NULL;
 			goto cleanup;
 		}
 
 		rt->fib6_nh->fib_nh_weight = rtnh->rtnh_hops + 1;
 
-		err = ip6_route_info_append(info->nl_net, &rt6_nh_list,
-					    rt, &r_cfg);
+		err = ip6_route_info_append(&rt6_nh_list, rt, &r_cfg);
 		if (err) {
 			fib6_info_release(rt);
 			goto cleanup;
@@ -5384,12 +5461,6 @@ static int ip6_route_multipath_add(struct fib6_config *cfg,
 		rtnh = rtnh_next(rtnh, &remaining);
 	}
 
-	if (list_empty(&rt6_nh_list)) {
-		NL_SET_ERR_MSG(extack,
-			       "Invalid nexthop configuration - no valid nexthops");
-		return -EINVAL;
-	}
-
 	/* for add and replace send one notification with all nexthops.
 	 * Skip the notification in fib6_add_rt2node and send one with
 	 * the full route when done
@@ -5402,7 +5473,7 @@ static int ip6_route_multipath_add(struct fib6_config *cfg,
 	info->skip_notify_kernel = 1;
 
 	err_nh = NULL;
-	list_for_each_entry(nh, &rt6_nh_list, next) {
+	list_for_each_entry(nh, &rt6_nh_list, list) {
 		err = __ip6_ins_rt(nh->fib6_info, info, extack);
 
 		if (err) {
@@ -5470,16 +5541,16 @@ add_errout:
 		ip6_route_mpath_notify(rt_notif, rt_last, info, nlflags);
 
 	/* Delete routes that were already added */
-	list_for_each_entry(nh, &rt6_nh_list, next) {
+	list_for_each_entry(nh, &rt6_nh_list, list) {
 		if (err_nh == nh)
 			break;
 		ip6_route_del(&nh->r_cfg, extack);
 	}
 
 cleanup:
-	list_for_each_entry_safe(nh, nh_safe, &rt6_nh_list, next) {
+	list_for_each_entry_safe(nh, nh_safe, &rt6_nh_list, list) {
 		fib6_info_release(nh->fib6_info);
-		list_del(&nh->next);
+		list_del(&nh->list);
 		kfree(nh);
 	}
 
@@ -5511,21 +5582,15 @@ static int ip6_route_multipath_del(struct fib6_config *cfg,
 
 			nla = nla_find(attrs, attrlen, RTA_GATEWAY);
 			if (nla) {
-				err = fib6_gw_from_attr(&r_cfg.fc_gateway, nla,
-							extack);
-				if (err) {
-					last_err = err;
-					goto next_rtnh;
-				}
-
+				r_cfg.fc_gateway = nla_get_in6_addr(nla);
 				r_cfg.fc_flags |= RTF_GATEWAY;
 			}
 		}
+
 		err = ip6_route_del(&r_cfg, extack);
 		if (err)
 			last_err = err;
 
-next_rtnh:
 		rtnh = rtnh_next(rtnh, &remaining);
 	}
 
@@ -5542,15 +5607,20 @@ static int inet6_rtm_delroute(struct sk_buff *skb, struct nlmsghdr *nlh,
 	if (err < 0)
 		return err;
 
-	if (cfg.fc_nh_id &&
-	    !nexthop_find_by_id(sock_net(skb->sk), cfg.fc_nh_id)) {
-		NL_SET_ERR_MSG(extack, "Nexthop id does not exist");
-		return -EINVAL;
+	if (cfg.fc_nh_id) {
+		rcu_read_lock();
+		err = !nexthop_find_by_id(sock_net(skb->sk), cfg.fc_nh_id);
+		rcu_read_unlock();
+
+		if (err) {
+			NL_SET_ERR_MSG(extack, "Nexthop id does not exist");
+			return -EINVAL;
+		}
 	}
 
-	if (cfg.fc_mp)
+	if (cfg.fc_mp) {
 		return ip6_route_multipath_del(&cfg, extack);
-	else {
+	} else {
 		cfg.fc_delete_all_nh = 1;
 		return ip6_route_del(&cfg, extack);
 	}
@@ -5566,6 +5636,10 @@ static int inet6_rtm_newroute(struct sk_buff *skb, struct nlmsghdr *nlh,
 	if (err < 0)
 		return err;
 
+	err = fib6_config_validate(&cfg, extack);
+	if (err)
+		return err;
+
 	if (cfg.fc_metric == 0)
 		cfg.fc_metric = IP6_RT_PRIO_USER;
 
@@ -6030,7 +6104,8 @@ static int inet6_rtm_valid_getroute_req(struct sk_buff *skb,
 	struct rtmsg *rtm;
 	int i, err;
 
-	if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*rtm))) {
+	rtm = nlmsg_payload(nlh, sizeof(*rtm));
+	if (!rtm) {
 		NL_SET_ERR_MSG_MOD(extack,
 				   "Invalid header for get route request");
 		return -EINVAL;
@@ -6040,7 +6115,6 @@ static int inet6_rtm_valid_getroute_req(struct sk_buff *skb,
 		return nlmsg_parse_deprecated(nlh, sizeof(*rtm), tb, RTA_MAX,
 					      rtm_ipv6_policy, extack);
 
-	rtm = nlmsg_data(nlh);
 	if ((rtm->rtm_src_len && rtm->rtm_src_len != 128) ||
 	    (rtm->rtm_dst_len && rtm->rtm_dst_len != 128) ||
 	    rtm->rtm_table || rtm->rtm_protocol || rtm->rtm_scope ||
@@ -6255,6 +6329,8 @@ void inet6_rt_notify(int event, struct fib6_info *rt, struct nl_info *info,
 	err = -ENOBUFS;
 	seq = info->nlh ? info->nlh->nlmsg_seq : 0;
 
+	rcu_read_lock();
+
 	skb = nlmsg_new(rt6_nlmsg_size(rt), GFP_ATOMIC);
 	if (!skb)
 		goto errout;
@@ -6267,10 +6343,14 @@ void inet6_rt_notify(int event, struct fib6_info *rt, struct nl_info *info,
 		kfree_skb(skb);
 		goto errout;
 	}
+
+	rcu_read_unlock();
+
 	rtnl_notify(skb, net, info->portid, RTNLGRP_IPV6_ROUTE,
 		    info->nlh, GFP_ATOMIC);
 	return;
 errout:
+	rcu_read_unlock();
 	rtnl_set_sk_err(net, RTNLGRP_IPV6_ROUTE, err);
 }
 
@@ -6760,9 +6840,9 @@ static void bpf_iter_unregister(void)
 
 static const struct rtnl_msg_handler ip6_route_rtnl_msg_handlers[] __initconst_or_module = {
 	{.owner = THIS_MODULE, .protocol = PF_INET6, .msgtype = RTM_NEWROUTE,
-	 .doit = inet6_rtm_newroute},
+	 .doit = inet6_rtm_newroute, .flags = RTNL_FLAG_DOIT_UNLOCKED},
 	{.owner = THIS_MODULE, .protocol = PF_INET6, .msgtype = RTM_DELROUTE,
-	 .doit = inet6_rtm_delroute},
+	 .doit = inet6_rtm_delroute, .flags = RTNL_FLAG_DOIT_UNLOCKED},
 	{.owner = THIS_MODULE, .protocol = PF_INET6, .msgtype = RTM_GETROUTE,
 	 .doit = inet6_rtm_getroute, .flags = RTNL_FLAG_DOIT_UNLOCKED},
 };
diff --git a/net/ipv6/seg6_hmac.c b/net/ipv6/seg6_hmac.c
index bbf5b84a70fc..f78ecb6ad838 100644
--- a/net/ipv6/seg6_hmac.c
+++ b/net/ipv6/seg6_hmac.c
@@ -40,7 +40,14 @@
 #include <net/seg6_hmac.h>
 #include <linux/random.h>
 
-static DEFINE_PER_CPU(char [SEG6_HMAC_RING_SIZE], hmac_ring);
+struct hmac_storage {
+	local_lock_t bh_lock;
+	char hmac_ring[SEG6_HMAC_RING_SIZE];
+};
+
+static DEFINE_PER_CPU(struct hmac_storage, hmac_storage) = {
+	.bh_lock = INIT_LOCAL_LOCK(bh_lock),
+};
 
 static int seg6_hmac_cmpfn(struct rhashtable_compare_arg *arg, const void *obj)
 {
@@ -187,7 +194,8 @@ int seg6_hmac_compute(struct seg6_hmac_info *hinfo, struct ipv6_sr_hdr *hdr,
 	 */
 
 	local_bh_disable();
-	ring = this_cpu_ptr(hmac_ring);
+	local_lock_nested_bh(&hmac_storage.bh_lock);
+	ring = this_cpu_ptr(hmac_storage.hmac_ring);
 	off = ring;
 
 	/* source address */
@@ -212,6 +220,7 @@ int seg6_hmac_compute(struct seg6_hmac_info *hinfo, struct ipv6_sr_hdr *hdr,
 
 	dgsize = __do_hmac(hinfo, ring, plen, tmp_out,
 			   SEG6_HMAC_MAX_DIGESTSIZE);
+	local_unlock_nested_bh(&hmac_storage.bh_lock);
 	local_bh_enable();
 
 	if (dgsize < 0)
diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index 9a0f32acb750..a72dbca9e8fc 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -1804,8 +1804,7 @@ static struct xfrm_tunnel mplsip_handler __read_mostly = {
 };
 #endif
 
-static void __net_exit sit_destroy_tunnels(struct net *net,
-					   struct list_head *head)
+static void __net_exit sit_exit_rtnl_net(struct net *net, struct list_head *head)
 {
 	struct sit_net *sitn = net_generic(net, sit_net_id);
 	struct net_device *dev, *aux;
@@ -1820,15 +1819,15 @@ static void __net_exit sit_destroy_tunnels(struct net *net,
 		for (h = 0; h < (prio ? IP6_SIT_HASH_SIZE : 1); h++) {
 			struct ip_tunnel *t;
 
-			t = rtnl_dereference(sitn->tunnels[prio][h]);
+			t = rtnl_net_dereference(net, sitn->tunnels[prio][h]);
 			while (t) {
 				/* If dev is in the same netns, it has already
 				 * been added to the list by the previous loop.
 				 */
 				if (!net_eq(dev_net(t->dev), net))
-					unregister_netdevice_queue(t->dev,
-								   head);
-				t = rtnl_dereference(t->next);
+					unregister_netdevice_queue(t->dev, head);
+
+				t = rtnl_net_dereference(net, t->next);
 			}
 		}
 	}
@@ -1881,19 +1880,9 @@ err_alloc_dev:
 	return err;
 }
 
-static void __net_exit sit_exit_batch_rtnl(struct list_head *net_list,
-					   struct list_head *dev_to_kill)
-{
-	struct net *net;
-
-	ASSERT_RTNL();
-	list_for_each_entry(net, net_list, exit_list)
-		sit_destroy_tunnels(net, dev_to_kill);
-}
-
 static struct pernet_operations sit_net_ops = {
 	.init = sit_init_net,
-	.exit_batch_rtnl = sit_exit_batch_rtnl,
+	.exit_rtnl = sit_exit_rtnl_net,
 	.id   = &sit_net_id,
 	.size = sizeof(struct sit_net),
 };
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index b03c223eda4f..e8e68a142649 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -267,6 +267,8 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
 	fl6.flowi6_mark = sk->sk_mark;
 	fl6.fl6_dport = usin->sin6_port;
 	fl6.fl6_sport = inet->inet_sport;
+	if (IS_ENABLED(CONFIG_IP_ROUTE_MULTIPATH) && !fl6.fl6_sport)
+		fl6.flowi6_flags = FLOWI_FLAG_ANY_SPORT;
 	fl6.flowi6_uid = sk->sk_uid;
 
 	opt = rcu_dereference_protected(np->opt, lockdep_sock_is_held(sk));
@@ -1970,7 +1972,8 @@ do_time_wait:
 		goto csum_error;
 	}
 
-	tw_status = tcp_timewait_state_process(inet_twsk(sk), skb, th, &isn);
+	tw_status = tcp_timewait_state_process(inet_twsk(sk), skb, th, &isn,
+					       &drop_reason);
 	switch (tw_status) {
 	case TCP_TW_SYN:
 	{
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 024458ef163c..7317f8e053f1 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -46,6 +46,7 @@
 #include <net/tcp_states.h>
 #include <net/ip6_checksum.h>
 #include <net/ip6_tunnel.h>
+#include <net/udp_tunnel.h>
 #include <net/xfrm.h>
 #include <net/inet_hashtables.h>
 #include <net/inet6_hashtables.h>
@@ -1825,6 +1826,7 @@ void udpv6_destroy_sock(struct sock *sk)
 		if (udp_test_bit(ENCAP_ENABLED, sk)) {
 			static_branch_dec(&udpv6_encap_needed_key);
 			udp_encap_disable();
+			udp_tunnel_cleanup_gro(sk);
 		}
 	}
 }
diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c
index 404212dfc99a..d8445ac1b2e4 100644
--- a/net/ipv6/udp_offload.c
+++ b/net/ipv6/udp_offload.c
@@ -118,8 +118,13 @@ static struct sock *udp6_gro_lookup_skb(struct sk_buff *skb, __be16 sport,
 {
 	const struct ipv6hdr *iph = skb_gro_network_header(skb);
 	struct net *net = dev_net_rcu(skb->dev);
+	struct sock *sk;
 	int iif, sdif;
 
+	sk = udp_tunnel_sk(net, true);
+	if (sk && dport == htons(sk->sk_num))
+		return sk;
+
 	inet6_get_iif_sdif(skb, &iif, &sdif);
 
 	return __udp6_lib_lookup(net, &iph->saddr, sport,