Merge tag 'net-6.2-rc8' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Pull networking fixes from Paolo Abeni:
 "Including fixes from can and ipsec subtrees.

  Current release - regressions:

   - sched: fix off by one in htb_activate_prios()

   - eth: mana: fix accessing freed irq affinity_hint

   - eth: ice: fix out-of-bounds KASAN warning in virtchnl

  Current release - new code bugs:

   - eth: mtk_eth_soc: enable special tag when any MAC uses DSA

  Previous releases - always broken:

   - core: fix sk->sk_txrehash default

   - neigh: make sure used and confirmed times are valid

   - mptcp: be careful on subflow status propagation on errors

   - xfrm: prevent potential spectre v1 gadget in xfrm_xlate32_attr()

   - phylink: move phy_device_free() to correctly release phy device

   - eth: mlx5:
      - fix crash unsetting rx-vlan-filter in switchdev mode
      - fix hang on firmware reset
      - serialize module cleanup with reload and remove"

* tag 'net-6.2-rc8' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (57 commits)
  selftests: forwarding: lib: quote the sysctl values
  net: mscc: ocelot: fix all IPv6 getting trapped to CPU when PTP timestamping is used
  rds: rds_rm_zerocopy_callback() use list_first_entry()
  net: txgbe: Update support email address
  selftests: Fix failing VXLAN VNI filtering test
  selftests: mptcp: stop tests earlier
  selftests: mptcp: allow more slack for slow test-case
  mptcp: be careful on subflow status propagation on errors
  mptcp: fix locking for in-kernel listener creation
  mptcp: fix locking for setsockopt corner-case
  mptcp: do not wait for bare sockets' timeout
  net: ethernet: mtk_eth_soc: fix DSA TX tag hwaccel for switch port 0
  nfp: ethtool: fix the bug of setting unsupported port speed
  txhash: fix sk->sk_txrehash default
  net: ethernet: mtk_eth_soc: fix wrong parameters order in __xdp_rxq_info_reg()
  net: ethernet: mtk_eth_soc: enable special tag when any MAC uses DSA
  net: sched: sch: Fix off by one in htb_activate_prios()
  igc: Add ndo_tx_timeout support
  net: mana: Fix accessing freed irq affinity_hint
  hv_netvsc: Allocate memory in netvsc_dma_map() with GFP_ATOMIC
  ...

18 files changed, 176 insertions, 42 deletions

diff --git a/net/can/j1939/address-claim.c b/net/can/j1939/address-claim.c
index f33c47327927..ca4ad6cdd5cb 100644
--- a/net/can/j1939/address-claim.c
+++ b/net/can/j1939/address-claim.c
@@ -165,6 +165,46 @@ static void j1939_ac_process(struct j1939_priv *priv, struct sk_buff *skb)
 	 * leaving this function.
 	 */
 	ecu = j1939_ecu_get_by_name_locked(priv, name);
+
+	if (ecu && ecu->addr == skcb->addr.sa) {
+		/* The ISO 11783-5 standard, in "4.5.2 - Address claim
+		 * requirements", states:
+		 *   d) No CF shall begin, or resume, transmission on the
+		 *      network until 250 ms after it has successfully claimed
+		 *      an address except when responding to a request for
+		 *      address-claimed.
+		 *
+		 * But "Figure 6" and "Figure 7" in "4.5.4.2 - Address-claim
+		 * prioritization" show that the CF begins the transmission
+		 * after 250 ms from the first AC (address-claimed) message
+		 * even if it sends another AC message during that time window
+		 * to resolve the address contention with another CF.
+		 *
+		 * As stated in "4.4.2.3 - Address-claimed message":
+		 *   In order to successfully claim an address, the CF sending
+		 *   an address claimed message shall not receive a contending
+		 *   claim from another CF for at least 250 ms.
+		 *
+		 * As stated in "4.4.3.2 - NAME management (NM) message":
+		 *   1) A commanding CF can
+		 *      d) request that a CF with a specified NAME transmit
+		 *         the address-claimed message with its current NAME.
+		 *   2) A target CF shall
+		 *      d) send an address-claimed message in response to a
+		 *         request for a matching NAME
+		 *
+		 * Taking the above arguments into account, the 250 ms wait is
+		 * requested only during network initialization.
+		 *
+		 * Do not restart the timer on AC message if both the NAME and
+		 * the address match and so if the address has already been
+		 * claimed (timer has expired) or the AC message has been sent
+		 * to resolve the contention with another CF (timer is still
+		 * running).
+		 */
+		goto out_ecu_put;
+	}
+
 	if (!ecu && j1939_address_is_unicast(skcb->addr.sa))
 		ecu = j1939_ecu_create_locked(priv, name);
 
diff --git a/net/core/devlink.c b/net/core/devlink.c
index 032d6d0a5ce6..909a10e4b0dd 100644
--- a/net/core/devlink.c
+++ b/net/core/devlink.c
@@ -9979,7 +9979,7 @@ struct devlink *devlink_alloc_ns(const struct devlink_ops *ops,
 		goto err_xa_alloc;
 
 	devlink->netdevice_nb.notifier_call = devlink_netdevice_event;
-	ret = register_netdevice_notifier_net(net, &devlink->netdevice_nb);
+	ret = register_netdevice_notifier(&devlink->netdevice_nb);
 	if (ret)
 		goto err_register_netdevice_notifier;
 
@@ -10171,8 +10171,7 @@ void devlink_free(struct devlink *devlink)
 	xa_destroy(&devlink->snapshot_ids);
 	xa_destroy(&devlink->ports);
 
-	WARN_ON_ONCE(unregister_netdevice_notifier_net(devlink_net(devlink),
-						       &devlink->netdevice_nb));
+	WARN_ON_ONCE(unregister_netdevice_notifier(&devlink->netdevice_nb));
 
 	xa_erase(&devlinks, devlink->index);
 
@@ -10503,6 +10502,8 @@ static int devlink_netdevice_event(struct notifier_block *nb,
 		break;
 	case NETDEV_REGISTER:
 	case NETDEV_CHANGENAME:
+		if (devlink_net(devlink) != dev_net(netdev))
+			return NOTIFY_OK;
 		/* Set the netdev on top of previously set type. Note this
 		 * event happens also during net namespace change so here
 		 * we take into account netdev pointer appearing in this
@@ -10512,6 +10513,8 @@ static int devlink_netdevice_event(struct notifier_block *nb,
 					netdev);
 		break;
 	case NETDEV_UNREGISTER:
+		if (devlink_net(devlink) != dev_net(netdev))
+			return NOTIFY_OK;
 		/* Clear netdev pointer, but not the type. This event happens
 		 * also during net namespace change so we need to clear
 		 * pointer to netdev that is going to another net namespace.
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index f00a79fc301b..4edd2176e238 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -269,7 +269,7 @@ static int neigh_forced_gc(struct neigh_table *tbl)
 			    (n->nud_state == NUD_NOARP) ||
 			    (tbl->is_multicast &&
 			     tbl->is_multicast(n->primary_key)) ||
-			    time_after(tref, n->updated))
+			    !time_in_range(n->updated, tref, jiffies))
 				remove = true;
 			write_unlock(&n->lock);
 
@@ -289,7 +289,17 @@ static int neigh_forced_gc(struct neigh_table *tbl)
 
 static void neigh_add_timer(struct neighbour *n, unsigned long when)
 {
+	/* Use safe distance from the jiffies - LONG_MAX point while timer
+	 * is running in DELAY/PROBE state but still show to user space
+	 * large times in the past.
+	 */
+	unsigned long mint = jiffies - (LONG_MAX - 86400 * HZ);
+
 	neigh_hold(n);
+	if (!time_in_range(n->confirmed, mint, jiffies))
+		n->confirmed = mint;
+	if (time_before(n->used, n->confirmed))
+		n->used = n->confirmed;
 	if (unlikely(mod_timer(&n->timer, when))) {
 		printk("NEIGH: BUG, double timer add, state is %x\n",
 		       n->nud_state);
@@ -1001,12 +1011,14 @@ static void neigh_periodic_work(struct work_struct *work)
 				goto next_elt;
 			}
 
-			if (time_before(n->used, n->confirmed))
+			if (time_before(n->used, n->confirmed) &&
+			    time_is_before_eq_jiffies(n->confirmed))
 				n->used = n->confirmed;
 
 			if (refcount_read(&n->refcnt) == 1 &&
 			    (state == NUD_FAILED ||
-			     time_after(jiffies, n->used + NEIGH_VAR(n->parms, GC_STALETIME)))) {
+			     !time_in_range_open(jiffies, n->used,
+						 n->used + NEIGH_VAR(n->parms, GC_STALETIME)))) {
 				*np = n->next;
 				neigh_mark_dead(n);
 				write_unlock(&n->lock);
diff --git a/net/core/sock.c b/net/core/sock.c
index f954d5893e79..6f27c24016fe 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1531,6 +1531,8 @@ set_sndbuf:
 			ret = -EINVAL;
 			break;
 		}
+		if ((u8)val == SOCK_TXREHASH_DEFAULT)
+			val = READ_ONCE(sock_net(sk)->core.sysctl_txrehash);
 		/* Paired with READ_ONCE() in tcp_rtx_synack() */
 		WRITE_ONCE(sk->sk_txrehash, (u8)val);
 		break;
@@ -3451,7 +3453,6 @@ void sock_init_data(struct socket *sock, struct sock *sk)
 	sk->sk_pacing_rate = ~0UL;
 	WRITE_ONCE(sk->sk_pacing_shift, 10);
 	sk->sk_incoming_cpu = -1;
-	sk->sk_txrehash = SOCK_TXREHASH_DEFAULT;
 
 	sk_rx_queue_clear(sk);
 	/*
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 6c0ec2789943..cf11f10927e1 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -347,6 +347,7 @@ lookup_protocol:
 	sk->sk_destruct	   = inet_sock_destruct;
 	sk->sk_protocol	   = protocol;
 	sk->sk_backlog_rcv = sk->sk_prot->backlog_rcv;
+	sk->sk_txrehash = READ_ONCE(net->core.sysctl_txrehash);
 
 	inet->uc_ttl	= -1;
 	inet->mc_loop	= 1;
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index d1f837579398..f2c43f67187d 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -1225,9 +1225,6 @@ int inet_csk_listen_start(struct sock *sk)
 	sk->sk_ack_backlog = 0;
 	inet_csk_delack_init(sk);
 
-	if (sk->sk_txrehash == SOCK_TXREHASH_DEFAULT)
-		sk->sk_txrehash = READ_ONCE(sock_net(sk)->core.sysctl_txrehash);
-
 	/* There is race window here: we announce ourselves listening,
 	 * but this transition is still not validated by get_port().
 	 * It is OK, because this socket enters to hash table only
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index fee9163382c2..847934763868 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -222,6 +222,7 @@ lookup_protocol:
 	np->pmtudisc	= IPV6_PMTUDISC_WANT;
 	np->repflow	= net->ipv6.sysctl.flowlabel_reflect & FLOWLABEL_REFLECT_ESTABLISHED;
 	sk->sk_ipv6only	= net->ipv6.sysctl.bindv6only;
+	sk->sk_txrehash = READ_ONCE(net->core.sysctl_txrehash);
 
 	/* Init the ipv4 part of the socket since we can have sockets
 	 * using v6 API for ipv4.
diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c
index 2ea7eae43bdb..10fe9771a852 100644
--- a/net/mptcp/pm_netlink.c
+++ b/net/mptcp/pm_netlink.c
@@ -998,8 +998,8 @@ static int mptcp_pm_nl_create_listen_socket(struct sock *sk,
 {
 	int addrlen = sizeof(struct sockaddr_in);
 	struct sockaddr_storage addr;
-	struct mptcp_sock *msk;
 	struct socket *ssock;
+	struct sock *newsk;
 	int backlog = 1024;
 	int err;
 
@@ -1008,11 +1008,13 @@ static int mptcp_pm_nl_create_listen_socket(struct sock *sk,
 	if (err)
 		return err;
 
-	msk = mptcp_sk(entry->lsk->sk);
-	if (!msk)
+	newsk = entry->lsk->sk;
+	if (!newsk)
 		return -EINVAL;
 
-	ssock = __mptcp_nmpc_socket(msk);
+	lock_sock(newsk);
+	ssock = __mptcp_nmpc_socket(mptcp_sk(newsk));
+	release_sock(newsk);
 	if (!ssock)
 		return -EINVAL;
 
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 8cd6cc67c2c5..bc6c1f62a690 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -2897,6 +2897,7 @@ bool __mptcp_close(struct sock *sk, long timeout)
 	struct mptcp_subflow_context *subflow;
 	struct mptcp_sock *msk = mptcp_sk(sk);
 	bool do_cancel_work = false;
+	int subflows_alive = 0;
 
 	sk->sk_shutdown = SHUTDOWN_MASK;
 
@@ -2922,6 +2923,8 @@ cleanup:
 		struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
 		bool slow = lock_sock_fast_nested(ssk);
 
+		subflows_alive += ssk->sk_state != TCP_CLOSE;
+
 		/* since the close timeout takes precedence on the fail one,
 		 * cancel the latter
 		 */
@@ -2937,6 +2940,12 @@ cleanup:
 	}
 	sock_orphan(sk);
 
+	/* all the subflows are closed, only timeout can change the msk
+	 * state, let's not keep resources busy for no reasons
+	 */
+	if (subflows_alive == 0)
+		inet_sk_state_store(sk, TCP_CLOSE);
+
 	sock_hold(sk);
 	pr_debug("msk=%p state=%d", sk, sk->sk_state);
 	if (msk->token)
diff --git a/net/mptcp/sockopt.c b/net/mptcp/sockopt.c
index d4b1e6ec1b36..7f2c3727ab23 100644
--- a/net/mptcp/sockopt.c
+++ b/net/mptcp/sockopt.c
@@ -760,14 +760,21 @@ static int mptcp_setsockopt_v4(struct mptcp_sock *msk, int optname,
 static int mptcp_setsockopt_first_sf_only(struct mptcp_sock *msk, int level, int optname,
 					  sockptr_t optval, unsigned int optlen)
 {
+	struct sock *sk = (struct sock *)msk;
 	struct socket *sock;
+	int ret = -EINVAL;
 
 	/* Limit to first subflow, before the connection establishment */
+	lock_sock(sk);
 	sock = __mptcp_nmpc_socket(msk);
 	if (!sock)
-		return -EINVAL;
+		goto unlock;
 
-	return tcp_setsockopt(sock->sk, level, optname, optval, optlen);
+	ret = tcp_setsockopt(sock->sk, level, optname, optval, optlen);
+
+unlock:
+	release_sock(sk);
+	return ret;
 }
 
 static int mptcp_setsockopt_sol_tcp(struct mptcp_sock *msk, int optname,
diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index ec54413fb31f..32904c76c6a1 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -1399,6 +1399,7 @@ void __mptcp_error_report(struct sock *sk)
 	mptcp_for_each_subflow(msk, subflow) {
 		struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
 		int err = sock_error(ssk);
+		int ssk_state;
 
 		if (!err)
 			continue;
@@ -1409,7 +1410,14 @@ void __mptcp_error_report(struct sock *sk)
 		if (sk->sk_state != TCP_SYN_SENT && !__mptcp_check_fallback(msk))
 			continue;
 
-		inet_sk_state_store(sk, inet_sk_state_load(ssk));
+		/* We need to propagate only transition to CLOSE state.
+		 * Orphaned socket will see such state change via
+		 * subflow_sched_work_if_closed() and that path will properly
+		 * destroy the msk as needed.
+		 */
+		ssk_state = inet_sk_state_load(ssk);
+		if (ssk_state == TCP_CLOSE && !sock_flag(sk, SOCK_DEAD))
+			inet_sk_state_store(sk, ssk_state);
 		sk->sk_err = -err;
 
 		/* This barrier is coupled with smp_rmb() in mptcp_poll() */
@@ -1679,7 +1687,7 @@ int mptcp_subflow_create_socket(struct sock *sk, unsigned short family,
 	if (err)
 		return err;
 
-	lock_sock(sf->sk);
+	lock_sock_nested(sf->sk, SINGLE_DEPTH_NESTING);
 
 	/* the newly created socket has to be in the same cgroup as its parent */
 	mptcp_attach_cgroup(sk, sf->sk);
diff --git a/net/rds/message.c b/net/rds/message.c
index b47e4f0a1639..c19c93561227 100644
--- a/net/rds/message.c
+++ b/net/rds/message.c
@@ -104,9 +104,9 @@ static void rds_rm_zerocopy_callback(struct rds_sock *rs,
 	spin_lock_irqsave(&q->lock, flags);
 	head = &q->zcookie_head;
 	if (!list_empty(head)) {
-		info = list_entry(head, struct rds_msg_zcopy_info,
-				  rs_zcookie_next);
-		if (info && rds_zcookie_add(info, cookie)) {
+		info = list_first_entry(head, struct rds_msg_zcopy_info,
+					rs_zcookie_next);
+		if (rds_zcookie_add(info, cookie)) {
 			spin_unlock_irqrestore(&q->lock, flags);
 			kfree(rds_info_from_znotifier(znotif));
 			/* caller invokes rds_wake_sk_sleep() */
diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c
index cc28e41fb745..92f2975b6a82 100644
--- a/net/sched/sch_htb.c
+++ b/net/sched/sch_htb.c
@@ -433,7 +433,7 @@ static void htb_activate_prios(struct htb_sched *q, struct htb_class *cl)
 		while (m) {
 			unsigned int prio = ffz(~m);
 
-			if (WARN_ON_ONCE(prio > ARRAY_SIZE(p->inner.clprio)))
+			if (WARN_ON_ONCE(prio >= ARRAY_SIZE(p->inner.clprio)))
 				break;
 			m &= ~(1 << prio);
 
diff --git a/net/xfrm/xfrm_compat.c b/net/xfrm/xfrm_compat.c
index a0f62fa02e06..8cbf45a8bcdc 100644
--- a/net/xfrm/xfrm_compat.c
+++ b/net/xfrm/xfrm_compat.c
@@ -5,6 +5,7 @@
  * Based on code and translator idea by: Florian Westphal <fw@strlen.de>
  */
 #include <linux/compat.h>
+#include <linux/nospec.h>
 #include <linux/xfrm.h>
 #include <net/xfrm.h>
 
@@ -302,7 +303,7 @@ static int xfrm_xlate64(struct sk_buff *dst, const struct nlmsghdr *nlh_src)
 	nla_for_each_attr(nla, attrs, len, remaining) {
 		int err;
 
-		switch (type) {
+		switch (nlh_src->nlmsg_type) {
 		case XFRM_MSG_NEWSPDINFO:
 			err = xfrm_nla_cpy(dst, nla, nla_len(nla));
 			break;
@@ -437,6 +438,7 @@ static int xfrm_xlate32_attr(void *dst, const struct nlattr *nla,
 		NL_SET_ERR_MSG(extack, "Bad attribute");
 		return -EOPNOTSUPP;
 	}
+	type = array_index_nospec(type, XFRMA_MAX + 1);
 	if (nla_len(nla) < compat_policy[type].len) {
 		NL_SET_ERR_MSG(extack, "Attribute bad length");
 		return -EOPNOTSUPP;
diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c
index c06e54a10540..436d29640ac2 100644
--- a/net/xfrm/xfrm_input.c
+++ b/net/xfrm/xfrm_input.c
@@ -279,8 +279,7 @@ static int xfrm6_remove_tunnel_encap(struct xfrm_state *x, struct sk_buff *skb)
 		goto out;
 
 	if (x->props.flags & XFRM_STATE_DECAP_DSCP)
-		ipv6_copy_dscp(ipv6_get_dsfield(ipv6_hdr(skb)),
-			       ipipv6_hdr(skb));
+		ipv6_copy_dscp(XFRM_MODE_SKB_CB(skb)->tos, ipipv6_hdr(skb));
 	if (!(x->props.flags & XFRM_STATE_NOECN))
 		ipip6_ecn_decapsulate(skb);
 
diff --git a/net/xfrm/xfrm_interface_core.c b/net/xfrm/xfrm_interface_core.c
index 1f99dc469027..35279c220bd7 100644
--- a/net/xfrm/xfrm_interface_core.c
+++ b/net/xfrm/xfrm_interface_core.c
@@ -310,6 +310,52 @@ static void xfrmi_scrub_packet(struct sk_buff *skb, bool xnet)
 	skb->mark = 0;
 }
 
+static int xfrmi_input(struct sk_buff *skb, int nexthdr, __be32 spi,
+		       int encap_type, unsigned short family)
+{
+	struct sec_path *sp;
+
+	sp = skb_sec_path(skb);
+	if (sp && (sp->len || sp->olen) &&
+	    !xfrm_policy_check(NULL, XFRM_POLICY_IN, skb, family))
+		goto discard;
+
+	XFRM_SPI_SKB_CB(skb)->family = family;
+	if (family == AF_INET) {
+		XFRM_SPI_SKB_CB(skb)->daddroff = offsetof(struct iphdr, daddr);
+		XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4 = NULL;
+	} else {
+		XFRM_SPI_SKB_CB(skb)->daddroff = offsetof(struct ipv6hdr, daddr);
+		XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip6 = NULL;
+	}
+
+	return xfrm_input(skb, nexthdr, spi, encap_type);
+discard:
+	kfree_skb(skb);
+	return 0;
+}
+
+static int xfrmi4_rcv(struct sk_buff *skb)
+{
+	return xfrmi_input(skb, ip_hdr(skb)->protocol, 0, 0, AF_INET);
+}
+
+static int xfrmi6_rcv(struct sk_buff *skb)
+{
+	return xfrmi_input(skb, skb_network_header(skb)[IP6CB(skb)->nhoff],
+			   0, 0, AF_INET6);
+}
+
+static int xfrmi4_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type)
+{
+	return xfrmi_input(skb, nexthdr, spi, encap_type, AF_INET);
+}
+
+static int xfrmi6_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type)
+{
+	return xfrmi_input(skb, nexthdr, spi, encap_type, AF_INET6);
+}
+
 static int xfrmi_rcv_cb(struct sk_buff *skb, int err)
 {
 	const struct xfrm_mode *inner_mode;
@@ -945,8 +991,8 @@ static struct pernet_operations xfrmi_net_ops = {
 };
 
 static struct xfrm6_protocol xfrmi_esp6_protocol __read_mostly = {
-	.handler	=	xfrm6_rcv,
-	.input_handler	=	xfrm_input,
+	.handler	=	xfrmi6_rcv,
+	.input_handler	=	xfrmi6_input,
 	.cb_handler	=	xfrmi_rcv_cb,
 	.err_handler	=	xfrmi6_err,
 	.priority	=	10,
@@ -996,8 +1042,8 @@ static struct xfrm6_tunnel xfrmi_ip6ip_handler __read_mostly = {
 #endif
 
 static struct xfrm4_protocol xfrmi_esp4_protocol __read_mostly = {
-	.handler	=	xfrm4_rcv,
-	.input_handler	=	xfrm_input,
+	.handler	=	xfrmi4_rcv,
+	.input_handler	=	xfrmi4_input,
 	.cb_handler	=	xfrmi_rcv_cb,
 	.err_handler	=	xfrmi4_err,
 	.priority	=	10,
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index e9eb82c5457d..5c61ec04b839 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -336,7 +336,7 @@ static void xfrm_policy_timer(struct timer_list *t)
 	}
 	if (xp->lft.hard_use_expires_seconds) {
 		time64_t tmo = xp->lft.hard_use_expires_seconds +
-			(xp->curlft.use_time ? : xp->curlft.add_time) - now;
+			(READ_ONCE(xp->curlft.use_time) ? : xp->curlft.add_time) - now;
 		if (tmo <= 0)
 			goto expired;
 		if (tmo < next)
@@ -354,7 +354,7 @@ static void xfrm_policy_timer(struct timer_list *t)
 	}
 	if (xp->lft.soft_use_expires_seconds) {
 		time64_t tmo = xp->lft.soft_use_expires_seconds +
-			(xp->curlft.use_time ? : xp->curlft.add_time) - now;
+			(READ_ONCE(xp->curlft.use_time) ? : xp->curlft.add_time) - now;
 		if (tmo <= 0) {
 			warn = 1;
 			tmo = XFRM_KM_TIMEOUT;
@@ -3661,7 +3661,8 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb,
 		return 1;
 	}
 
-	pol->curlft.use_time = ktime_get_real_seconds();
+	/* This lockless write can happen from different cpus. */
+	WRITE_ONCE(pol->curlft.use_time, ktime_get_real_seconds());
 
 	pols[0] = pol;
 	npols++;
@@ -3676,7 +3677,9 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb,
 				xfrm_pol_put(pols[0]);
 				return 0;
 			}
-			pols[1]->curlft.use_time = ktime_get_real_seconds();
+			/* This write can happen from different cpus. */
+			WRITE_ONCE(pols[1]->curlft.use_time,
+				   ktime_get_real_seconds());
 			npols++;
 		}
 	}
@@ -3742,6 +3745,9 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb,
 			goto reject;
 		}
 
+		if (if_id)
+			secpath_reset(skb);
+
 		xfrm_pols_put(pols, npols);
 		return 1;
 	}
diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c
index 89c731f4f0c7..00afe831c71c 100644
--- a/net/xfrm/xfrm_state.c
+++ b/net/xfrm/xfrm_state.c
@@ -577,7 +577,7 @@ static enum hrtimer_restart xfrm_timer_handler(struct hrtimer *me)
 	if (x->km.state == XFRM_STATE_EXPIRED)
 		goto expired;
 	if (x->lft.hard_add_expires_seconds) {
-		long tmo = x->lft.hard_add_expires_seconds +
+		time64_t tmo = x->lft.hard_add_expires_seconds +
 			x->curlft.add_time - now;
 		if (tmo <= 0) {
 			if (x->xflags & XFRM_SOFT_EXPIRE) {
@@ -594,8 +594,8 @@ static enum hrtimer_restart xfrm_timer_handler(struct hrtimer *me)
 			next = tmo;
 	}
 	if (x->lft.hard_use_expires_seconds) {
-		long tmo = x->lft.hard_use_expires_seconds +
-			(x->curlft.use_time ? : now) - now;
+		time64_t tmo = x->lft.hard_use_expires_seconds +
+			(READ_ONCE(x->curlft.use_time) ? : now) - now;
 		if (tmo <= 0)
 			goto expired;
 		if (tmo < next)
@@ -604,7 +604,7 @@ static enum hrtimer_restart xfrm_timer_handler(struct hrtimer *me)
 	if (x->km.dying)
 		goto resched;
 	if (x->lft.soft_add_expires_seconds) {
-		long tmo = x->lft.soft_add_expires_seconds +
+		time64_t tmo = x->lft.soft_add_expires_seconds +
 			x->curlft.add_time - now;
 		if (tmo <= 0) {
 			warn = 1;
@@ -616,8 +616,8 @@ static enum hrtimer_restart xfrm_timer_handler(struct hrtimer *me)
 		}
 	}
 	if (x->lft.soft_use_expires_seconds) {
-		long tmo = x->lft.soft_use_expires_seconds +
-			(x->curlft.use_time ? : now) - now;
+		time64_t tmo = x->lft.soft_use_expires_seconds +
+			(READ_ONCE(x->curlft.use_time) ? : now) - now;
 		if (tmo <= 0)
 			warn = 1;
 		else if (tmo < next)
@@ -1906,7 +1906,7 @@ out:
 
 		hrtimer_start(&x1->mtimer, ktime_set(1, 0),
 			      HRTIMER_MODE_REL_SOFT);
-		if (x1->curlft.use_time)
+		if (READ_ONCE(x1->curlft.use_time))
 			xfrm_state_check_expire(x1);
 
 		if (x->props.smark.m || x->props.smark.v || x->if_id) {
@@ -1940,8 +1940,8 @@ int xfrm_state_check_expire(struct xfrm_state *x)
 {
 	xfrm_dev_state_update_curlft(x);
 
-	if (!x->curlft.use_time)
-		x->curlft.use_time = ktime_get_real_seconds();
+	if (!READ_ONCE(x->curlft.use_time))
+		WRITE_ONCE(x->curlft.use_time, ktime_get_real_seconds());
 
 	if (x->curlft.bytes >= x->lft.hard_byte_limit ||
 	    x->curlft.packets >= x->lft.hard_packet_limit) {