Merge tag 'net-7.3-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/netstable

Pull networking fixes from Jakub Kicinski:
 "Including fixes from Bluetooth, IPSec and Netfilter.

  Current release - fix to a fix:

   - netfilter: ipset: remove need to allocate memory on delete operations

  Current release - regressions:

   - macb: drop CONFIG_OF #if block, fix build

  Previous releases - always broken:

   - stream of fixes for SCTP continues

   - inet: frags: strip GSO state from fragments before reassembly

   - virtio-net: ensure that TCP packets don't overflow gso_segs

   - tcp-ao: fix use-after-free of current_key on reconnect to another
     peer

   - page_pool: remove zone/policy GFP flags when allocating XArray
     entries

   - Bluetooth: L2CAP: reject accept queue add unless BT_LISTEN

   - tls: device: fix out-of-bounds write in tls_append_frag()

   - eth: bnxt:
      - ring the doorbell when SW USO exits early, avoid packets stuck
        in Tx
      - gate TPH enablement behind BNXT_SUPPORTS_QUEUE_API check, avoid
        users of older NICs seeing non-actionable warning messages

   - eth: qede: fix NULL pointer dereference in TPA fragment processing"

* tag 'net-7.3-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (216 commits)
  inet: frags: strip GSO state from fragments before reassembly
  net/sched: sch_htb: limit htb_classify inner-class filter hops
  selftests/net: packetdrill: add tcp_urg_ptr_retransmit
  tcp: fix corruption of urgent data on multi-segment retransmit
  usb: atm: usbatm: fix invalid ci_range initialization
  net: fec: only stop PTP if it was initialized
  slip: remove slip_hangup() to fix use-after-free in slip_receive_buf()
  net: bridge: mcast: fix use-after-free of a master VLAN's multicast context
  net/sched: bound qdisc_pkt_len to prevent qdisc soft lockup
  net: dsa: mxl862xx: enable assisted learning on CPU port
  net: stmmac: restore NET_IP_ALIGN in the RX DMA offset
  net: stmmac: drop gso_enabled_types and rely on netdev features
  net: stmmac: selftests: Don't test flow control for small rx fifos
  net: stmmac: selftests: Account for the UC filter list for filtering tests
  net: stmmac: dwxgmac: Account for the primary MAC address for UC filtering
  net: stmmac: dwmac4: Account for the primary MAC address for UC filtering
  net: stmmac: dwmac1000: Account for the primary MAC address for UC filtering
  net: stmmac: selftests: Check multiple MMC counters
  selftests: net: Fix slow configurations in big_tcp_tunnels.sh
  selftests: net: Lower threshold with csum offload off in big_tcp_tunnels.sh
  ...

1 files changed, 51 insertions, 4 deletions

diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c
index 065228026c58..9cea71fc1db3 100644
--- a/net/sched/act_ife.c
+++ b/net/sched/act_ife.c
@@ -28,6 +28,7 @@
 #include <uapi/linux/tc_act/tc_ife.h>
 #include <net/tc_act/tc_ife.h>
 #include <linux/etherdevice.h>
+#include <linux/if_arp.h>
 #include <net/ife.h>
 #include <net/tc_wrapper.h>
 
@@ -723,7 +724,7 @@ static int tcf_ife_decode(struct sk_buff *skb, const struct tc_action *a,
 	tcf_lastuse_update(&ife->tcf_tm);
 
 	if (skb_at_tc_ingress(skb))
-		skb_push(skb, skb->dev->hard_header_len);
+		skb_push(skb, ETH_HLEN);
 
 	tlv_data = ife_decode(skb, &metalen);
 	if (unlikely(!tlv_data)) {
@@ -795,7 +796,7 @@ static int tcf_ife_encode(struct sk_buff *skb, const struct tc_action *a,
 	   where ORIGDATA = original ethernet header ...
 	 */
 	u16 metalen = ife_get_sz(skb, p);
-	int hdrm = metalen + skb->dev->hard_header_len + IFE_METAHDRLEN;
+	int hdrm = metalen + ETH_HLEN + IFE_METAHDRLEN;
 	unsigned int skboff = 0;
 	int new_len = skb->len + hdrm;
 	bool exceed_mtu = false;
@@ -826,7 +827,7 @@ drop:
 	}
 
 	if (skb_at_tc_ingress(skb))
-		skb_push(skb, skb->dev->hard_header_len);
+		skb_push(skb, ETH_HLEN);
 
 	ife_meta = ife_encode(skb, metalen);
 	if (!ife_meta)
@@ -856,11 +857,27 @@ drop:
 	oethh->h_proto = htons(p->eth_type);
 
 	if (skb_at_tc_ingress(skb))
-		skb_pull(skb, skb->dev->hard_header_len);
+		skb_pull(skb, ETH_HLEN);
 
 	return action;
 }
 
+/* IFE encapsulates the original Ethernet header and, on decode, expects to
+ * find one, so it can only ever work on skbs that carry one. Loopback carries
+ * Ethernet header as well, so it qualifies here.
+ * At ingress, also verify that the L2 header about to be pushed back really
+ * is an Ethernet header because the skb could've been redirected with mirred
+ * from a non-Ethernet device.
+ */
+static bool tcf_ife_is_eth_skb(const struct sk_buff *skb)
+{
+	if (skb->dev->type != ARPHRD_ETHER &&
+	    skb->dev->type != ARPHRD_LOOPBACK)
+		return false;
+
+	return !skb_at_tc_ingress(skb) || skb->mac_len == ETH_HLEN;
+}
+
 TC_INDIRECT_SCOPE int tcf_ife_act(struct sk_buff *skb,
 				  const struct tc_action *a,
 				  struct tcf_result *res)
@@ -869,6 +886,13 @@ TC_INDIRECT_SCOPE int tcf_ife_act(struct sk_buff *skb,
 	struct tcf_ife_params *p;
 	int ret;
 
+	if (unlikely(!tcf_ife_is_eth_skb(skb))) {
+		bstats_update(this_cpu_ptr(ife->common.cpu_bstats), skb);
+		tcf_lastuse_update(&ife->tcf_tm);
+		qstats_cpu_drop_inc(ife->common.cpu_qstats);
+		return TC_ACT_SHOT;
+	}
+
 	p = rcu_dereference_bh(ife->params);
 	if (p->flags & IFE_ENCODE) {
 		ret = tcf_ife_encode(skb, a, res, p);
@@ -878,6 +902,28 @@ TC_INDIRECT_SCOPE int tcf_ife_act(struct sk_buff *skb,
 	return tcf_ife_decode(skb, a, res);
 }
 
+static size_t tcf_ife_get_fill_size(const struct tc_action *act)
+{
+	struct tcf_ife_info *ife = to_ife(act);
+	const struct tcf_ife_params *p;
+	struct tcf_meta_info *e;
+	size_t size = nla_total_size(sizeof(struct tc_ife)) /* TCA_IFE_PARMS */
+		+ nla_total_size(ETH_ALEN) /* TCA_IFE_DMAC */
+		+ nla_total_size(ETH_ALEN) /* TCA_IFE_SMAC */
+		+ nla_total_size(2) /* TCA_IFE_TYPE */
+		+ nla_total_size(0); /* TCA_IFE_METALST */
+
+	rcu_read_lock();
+	p = rcu_dereference(ife->params);
+	if (p) {
+		list_for_each_entry_rcu(e, &p->metalist, metalist)
+			size += nla_total_size(sizeof(u32));
+	}
+	rcu_read_unlock();
+
+	return size;
+}
+
 static struct tc_action_ops act_ife_ops = {
 	.kind = "ife",
 	.id = TCA_ID_IFE,
@@ -886,6 +932,7 @@ static struct tc_action_ops act_ife_ops = {
 	.dump = tcf_ife_dump,
 	.cleanup = tcf_ife_cleanup,
 	.init = tcf_ife_init,
+	.get_fill_size = tcf_ife_get_fill_size,
 	.size =	sizeof(struct tcf_ife_info),
 };
 MODULE_ALIAS_NET_ACT("ife");