Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net

Pull networking fixes from David Miller:
 "The iwlwifi firmware compat fix is in here as well as some other
  stuff:

  1) Fix request socket leak introduced by BPF deadlock fix, from Eric
     Dumazet.

  2) Fix VLAN handling with TXQs in mac80211, from Johannes Berg.

  3) Missing __qdisc_drop conversions in prio and qfq schedulers, from
     Gao Feng.

  4) Use after free in netlink nlk groups handling, from Xin Long.

  5) Handle MTU update properly in ipv6 gre tunnels, from Xin Long.

  6) Fix leak of ipv6 fib tables on netns teardown, from Sabrina Dubroca
     with follow-on fix from Eric Dumazet.

  7) Need RCU and preemption disabled during generic XDP data patch,
     from John Fastabend"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (54 commits)
  bpf: make error reporting in bpf_warn_invalid_xdp_action more clear
  Revert "mdio_bus: Remove unneeded gpiod NULL check"
  bpf: devmap, use cond_resched instead of cpu_relax
  bpf: add support for sockmap detach programs
  net: rcu lock and preempt disable missing around generic xdp
  bpf: don't select potentially stale ri->map from buggy xdp progs
  net: tulip: Constify tulip_tbl
  net: ethernet: ti: netcp_core: no need in netif_napi_del
  davicom: Display proper debug level up to 6
  net: phy: sfp: rename dt properties to match the binding
  dt-binding: net: sfp binding documentation
  dt-bindings: add SFF vendor prefix
  dt-bindings: net: don't confuse with generic PHY property
  ip6_tunnel: fix setting hop_limit value for ipv6 tunnel
  ip_tunnel: fix setting ttl and tos value in collect_md mode
  ipv6: fix typo in fib6_net_exit()
  tcp: fix a request socket leak
  sctp: fix missing wake ups in some situations
  netfilter: xt_hashlimit: fix build error caused by 64bit division
  netfilter: xt_hashlimit: alloc hashtable with right size
  ...

net/core/dev.c

@@ -3981,8 +3981,13 @@ static int netif_rx_internal(struct sk_buff *skb)
 	trace_netif_rx(skb);
 
 	if (static_key_false(&generic_xdp_needed)) {
-		int ret = do_xdp_generic(rcu_dereference(skb->dev->xdp_prog),
-					 skb);
+		int ret;
+
+		preempt_disable();
+		rcu_read_lock();
+		ret = do_xdp_generic(rcu_dereference(skb->dev->xdp_prog), skb);
+		rcu_read_unlock();
+		preempt_enable();
 
 		/* Consider XDP consuming the packet a success from
 		 * the netdev point of view we do not want to count
@@ -4500,18 +4505,20 @@ static int netif_receive_skb_internal(struct sk_buff *skb)
 	if (skb_defer_rx_timestamp(skb))
 		return NET_RX_SUCCESS;
 
-	rcu_read_lock();
-
 	if (static_key_false(&generic_xdp_needed)) {
-		int ret = do_xdp_generic(rcu_dereference(skb->dev->xdp_prog),
-					 skb);
+		int ret;
 
-		if (ret != XDP_PASS) {
-			rcu_read_unlock();
+		preempt_disable();
+		rcu_read_lock();
+		ret = do_xdp_generic(rcu_dereference(skb->dev->xdp_prog), skb);
+		rcu_read_unlock();
+		preempt_enable();
+
+		if (ret != XDP_PASS)
 			return NET_RX_DROP;
-		}
 	}
 
+	rcu_read_lock();
 #ifdef CONFIG_RPS
 	if (static_key_false(&rps_needed)) {
 		struct rps_dev_flow voidflow, *rflow = &voidflow;

net/core/filter.c

@@ -1794,6 +1794,7 @@ struct redirect_info {
 	u32 flags;
 	struct bpf_map *map;
 	struct bpf_map *map_to_flush;
+	const struct bpf_prog *map_owner;
 };
 
 static DEFINE_PER_CPU(struct redirect_info, redirect_info);
@@ -1807,7 +1808,6 @@ BPF_CALL_2(bpf_redirect, u32, ifindex, u64, flags)
 
 	ri->ifindex = ifindex;
 	ri->flags = flags;
-	ri->map = NULL;
 
 	return TC_ACT_REDIRECT;
 }
@@ -2504,6 +2504,7 @@ static int xdp_do_redirect_map(struct net_device *dev, struct xdp_buff *xdp,
 			       struct bpf_prog *xdp_prog)
 {
 	struct redirect_info *ri = this_cpu_ptr(&redirect_info);
+	const struct bpf_prog *map_owner = ri->map_owner;
 	struct bpf_map *map = ri->map;
 	u32 index = ri->ifindex;
 	struct net_device *fwd;
@@ -2511,6 +2512,15 @@ static int xdp_do_redirect_map(struct net_device *dev, struct xdp_buff *xdp,
 
 	ri->ifindex = 0;
 	ri->map = NULL;
+	ri->map_owner = NULL;
+
+	/* This is really only caused by a deliberately crappy
+	 * BPF program, normally we would never hit that case,
+	 * so no need to inform someone via tracepoints either,
+	 * just bail out.
+	 */
+	if (unlikely(map_owner != xdp_prog))
+		return -EINVAL;
 
 	fwd = __dev_map_lookup_elem(map, index);
 	if (!fwd) {
@@ -2607,6 +2617,8 @@ BPF_CALL_2(bpf_xdp_redirect, u32, ifindex, u64, flags)
 
 	ri->ifindex = ifindex;
 	ri->flags = flags;
+	ri->map = NULL;
+	ri->map_owner = NULL;
 
 	return XDP_REDIRECT;
 }
@@ -2619,7 +2631,8 @@ static const struct bpf_func_proto bpf_xdp_redirect_proto = {
 	.arg2_type      = ARG_ANYTHING,
 };
 
-BPF_CALL_3(bpf_xdp_redirect_map, struct bpf_map *, map, u32, ifindex, u64, flags)
+BPF_CALL_4(bpf_xdp_redirect_map, struct bpf_map *, map, u32, ifindex, u64, flags,
+	   const struct bpf_prog *, map_owner)
 {
 	struct redirect_info *ri = this_cpu_ptr(&redirect_info);
 
@@ -2629,10 +2642,14 @@ BPF_CALL_3(bpf_xdp_redirect_map, struct bpf_map *, map, u32, ifindex, u64, flags
 	ri->ifindex = ifindex;
 	ri->flags = flags;
 	ri->map = map;
+	ri->map_owner = map_owner;
 
 	return XDP_REDIRECT;
 }
 
+/* Note, arg4 is hidden from users and populated by the verifier
+ * with the right pointer.
+ */
 static const struct bpf_func_proto bpf_xdp_redirect_map_proto = {
 	.func           = bpf_xdp_redirect_map,
 	.gpl_only       = false,
@@ -3592,7 +3609,11 @@ static bool xdp_is_valid_access(int off, int size,
 
 void bpf_warn_invalid_xdp_action(u32 act)
 {
-	WARN_ONCE(1, "Illegal XDP return value %u, expect packet loss\n", act);
+	const u32 act_max = XDP_REDIRECT;
+
+	WARN_ONCE(1, "%s XDP return value %u, expect packet loss!\n",
+		  act > act_max ? "Illegal" : "Driver unsupported",
+		  act);
 }
 EXPORT_SYMBOL_GPL(bpf_warn_invalid_xdp_action);
 

net/core/skbuff.c

@@ -710,14 +710,11 @@ EXPORT_SYMBOL(consume_skb);
  *	consume_stateless_skb - free an skbuff, assuming it is stateless
  *	@skb: buffer to free
  *
- *	Works like consume_skb(), but this variant assumes that all the head
- *	states have been already dropped.
+ *	Alike consume_skb(), but this variant assumes that this is the last
+ *	skb reference and all the head states have been already dropped
  */
-void consume_stateless_skb(struct sk_buff *skb)
+void __consume_stateless_skb(struct sk_buff *skb)
 {
-	if (!skb_unref(skb))
-		return;
-
 	trace_consume_skb(skb);
 	skb_release_data(skb);
 	kfree_skbmem(skb);