Merge tag 'net-6.4-rc8' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Pull networking fixes from Paolo Abeni:
 "Including fixes from ipsec, bpf, mptcp and netfilter.

  Current release - regressions:

   - netfilter: add NFT_TRANS_PREPARE_ERROR to deal with bound set/chain

   - eth: mlx5e:
      - fix scheduling of IPsec ASO query while in atomic
      - free IRQ rmap and notifier on kernel shutdown

  Current release - new code bugs:

   - phy: manual remove LEDs to ensure correct ordering

  Previous releases - regressions:

   - mptcp: fix possible divide by zero in recvmsg()

   - dsa: revert "net: phy: dp83867: perform soft reset and retain
     established link"

  Previous releases - always broken:

   - sched: netem: acquire qdisc lock in netem_change()

   - bpf:
      - fix verifier id tracking of scalars on spill
      - fix NULL dereference on exceptions
      - accept function names that contain dots

   - netfilter: disallow element updates of bound anonymous sets

   - mptcp: ensure listener is unhashed before updating the sk status

   - xfrm:
      - add missed call to delete offloaded policies
      - fix inbound ipv4/udp/esp packets to UDPv6 dualstack sockets

   - selftests: fixes for FIPS mode

   - dsa: mt7530: fix multiple CPU ports, BPDU and LLDP handling

   - eth: sfc: use budget for TX completions

  Misc:

   - wifi: iwlwifi: add support for SO-F device with PCI id 0x7AF0"

* tag 'net-6.4-rc8' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (74 commits)
  revert "net: align SO_RCVMARK required privileges with SO_MARK"
  net: wwan: iosm: Convert single instance struct member to flexible array
  sch_netem: acquire qdisc lock in netem_change()
  selftests: forwarding: Fix race condition in mirror installation
  wifi: mac80211: report all unusable beacon frames
  mptcp: ensure listener is unhashed before updating the sk status
  mptcp: drop legacy code around RX EOF
  mptcp: consolidate fallback and non fallback state machine
  mptcp: fix possible list corruption on passive MPJ
  mptcp: fix possible divide by zero in recvmsg()
  mptcp: handle correctly disconnect() failures
  bpf: Force kprobe multi expected_attach_type for kprobe_multi link
  bpf/btf: Accept function names that contain dots
  Revert "net: phy: dp83867: perform soft reset and retain established link"
  net: mdio: fix the wrong parameters
  netfilter: nf_tables: Fix for deleting base chains with payload
  netfilter: nfnetlink_osf: fix module autoload
  netfilter: nf_tables: drop module reference after updating chain
  netfilter: nf_tables: disallow timeout for anonymous sets
  netfilter: nf_tables: disallow updates of anonymous sets
  ...

3 files changed, 68 insertions, 8 deletions

diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c
index 39fb91ff23d9..815b38080401 100644
--- a/net/xfrm/xfrm_input.c
+++ b/net/xfrm/xfrm_input.c
@@ -131,6 +131,7 @@ struct sec_path *secpath_set(struct sk_buff *skb)
 	memset(sp->ovec, 0, sizeof(sp->ovec));
 	sp->olen = 0;
 	sp->len = 0;
+	sp->verified_cnt = 0;
 
 	return sp;
 }
@@ -330,11 +331,10 @@ xfrm_inner_mode_encap_remove(struct xfrm_state *x,
 {
 	switch (x->props.mode) {
 	case XFRM_MODE_BEET:
-		switch (XFRM_MODE_SKB_CB(skb)->protocol) {
-		case IPPROTO_IPIP:
-		case IPPROTO_BEETPH:
+		switch (x->sel.family) {
+		case AF_INET:
 			return xfrm4_remove_beet_encap(x, skb);
-		case IPPROTO_IPV6:
+		case AF_INET6:
 			return xfrm6_remove_beet_encap(x, skb);
 		}
 		break;
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 6d15788b5123..e7617c9959c3 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -1831,6 +1831,7 @@ again:
 
 		__xfrm_policy_unlink(pol, dir);
 		spin_unlock_bh(&net->xfrm.xfrm_policy_lock);
+		xfrm_dev_policy_delete(pol);
 		cnt++;
 		xfrm_audit_policy_delete(pol, 1, task_valid);
 		xfrm_policy_kill(pol);
@@ -1869,6 +1870,7 @@ again:
 
 		__xfrm_policy_unlink(pol, dir);
 		spin_unlock_bh(&net->xfrm.xfrm_policy_lock);
+		xfrm_dev_policy_delete(pol);
 		cnt++;
 		xfrm_audit_policy_delete(pol, 1, task_valid);
 		xfrm_policy_kill(pol);
@@ -3349,6 +3351,13 @@ xfrm_policy_ok(const struct xfrm_tmpl *tmpl, const struct sec_path *sp, int star
 		if (xfrm_state_ok(tmpl, sp->xvec[idx], family, if_id))
 			return ++idx;
 		if (sp->xvec[idx]->props.mode != XFRM_MODE_TRANSPORT) {
+			if (idx < sp->verified_cnt) {
+				/* Secpath entry previously verified, consider optional and
+				 * continue searching
+				 */
+				continue;
+			}
+
 			if (start == -1)
 				start = -2-idx;
 			break;
@@ -3723,6 +3732,9 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb,
 		 * Order is _important_. Later we will implement
 		 * some barriers, but at the moment barriers
 		 * are implied between each two transformations.
+		 * Upon success, marks secpath entries as having been
+		 * verified to allow them to be skipped in future policy
+		 * checks (e.g. nested tunnels).
 		 */
 		for (i = xfrm_nr-1, k = 0; i >= 0; i--) {
 			k = xfrm_policy_ok(tpp[i], sp, k, family, if_id);
@@ -3741,6 +3753,8 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb,
 		}
 
 		xfrm_pols_put(pols, npols);
+		sp->verified_cnt = k;
+
 		return 1;
 	}
 	XFRM_INC_STATS(net, LINUX_MIB_XFRMINPOLBLOCK);