Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next

Pull networking updates from David Miller:
 "Another merge window, another pull full of stuff:

   1) Support alternative names for network devices, from Jiri Pirko.

   2) Introduce per-netns netdev notifiers, also from Jiri Pirko.

   3) Support MSG_PEEK in vsock/virtio, from Matias Ezequiel Vara
      Larsen.

   4) Allow compiling out the TLS TOE code, from Jakub Kicinski.

   5) Add several new tracepoints to the kTLS code, also from Jakub.

   6) Support set channels ethtool callback in ena driver, from Sameeh
      Jubran.

   7) New SCTP events SCTP_ADDR_ADDED, SCTP_ADDR_REMOVED,
      SCTP_ADDR_MADE_PRIM, and SCTP_SEND_FAILED_EVENT. From Xin Long.

   8) Add XDP support to mvneta driver, from Lorenzo Bianconi.

   9) Lots of netfilter hw offload fixes, cleanups and enhancements,
      from Pablo Neira Ayuso.

  10) PTP support for aquantia chips, from Egor Pomozov.

  11) Add UDP segmentation offload support to igb, ixgbe, and i40e. From
      Josh Hunt.

  12) Add smart nagle to tipc, from Jon Maloy.

  13) Support L2 field rewrite by TC offloads in bnxt_en, from Venkat
      Duvvuru.

  14) Add a flow mask cache to OVS, from Tonghao Zhang.

  15) Add XDP support to ice driver, from Maciej Fijalkowski.

  16) Add AF_XDP support to ice driver, from Krzysztof Kazimierczak.

  17) Support UDP GSO offload in atlantic driver, from Igor Russkikh.

  18) Support it in stmmac driver too, from Jose Abreu.

  19) Support TIPC encryption and auth, from Tuong Lien.

  20) Introduce BPF trampolines, from Alexei Starovoitov.

  21) Make page_pool API more numa friendly, from Saeed Mahameed.

  22) Introduce route hints to ipv4 and ipv6, from Paolo Abeni.

  23) Add UDP segmentation offload to cxgb4, Rahul Lakkireddy"

* git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1857 commits)
  libbpf: Fix usage of u32 in userspace code
  mm: Implement no-MMU variant of vmalloc_user_node_flags
  slip: Fix use-after-free Read in slip_open
  net: dsa: sja1105: fix sja1105_parse_rgmii_delays()
  macvlan: schedule bc_work even if error
  enetc: add support Credit Based Shaper(CBS) for hardware offload
  net: phy: add helpers phy_(un)lock_mdio_bus
  mdio_bus: don't use managed reset-controller
  ax88179_178a: add ethtool_op_get_ts_info()
  mlxsw: spectrum_router: Fix use of uninitialized adjacency index
  mlxsw: spectrum_router: After underlay moves, demote conflicting tunnels
  bpf: Simplify __bpf_arch_text_poke poke type handling
  bpf: Introduce BPF_TRACE_x helper for the tracing tests
  bpf: Add bpf_jit_blinding_enabled for !CONFIG_BPF_JIT
  bpf, testing: Add various tail call test cases
  bpf, x86: Emit patchable direct jump as tail call
  bpf: Constant map key tracking for prog array pokes
  bpf: Add poke dependency tracking for prog array maps
  bpf: Add initial poke descriptor table for jit images
  bpf: Move owner type, jited info into array auxiliary data
  ...

1 files changed, 117 insertions, 38 deletions

diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index 68eda10d0680..ca871657a4c4 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -114,19 +114,50 @@ int skb_flow_dissector_bpf_prog_attach(const union bpf_attr *attr,
 {
 	struct bpf_prog *attached;
 	struct net *net;
+	int ret = 0;
 
 	net = current->nsproxy->net_ns;
 	mutex_lock(&flow_dissector_mutex);
+
+	if (net == &init_net) {
+		/* BPF flow dissector in the root namespace overrides
+		 * any per-net-namespace one. When attaching to root,
+		 * make sure we don't have any BPF program attached
+		 * to the non-root namespaces.
+		 */
+		struct net *ns;
+
+		for_each_net(ns) {
+			if (ns == &init_net)
+				continue;
+			if (rcu_access_pointer(ns->flow_dissector_prog)) {
+				ret = -EEXIST;
+				goto out;
+			}
+		}
+	} else {
+		/* Make sure root flow dissector is not attached
+		 * when attaching to the non-root namespace.
+		 */
+		if (rcu_access_pointer(init_net.flow_dissector_prog)) {
+			ret = -EEXIST;
+			goto out;
+		}
+	}
+
 	attached = rcu_dereference_protected(net->flow_dissector_prog,
 					     lockdep_is_held(&flow_dissector_mutex));
-	if (attached) {
-		/* Only one BPF program can be attached at a time */
-		mutex_unlock(&flow_dissector_mutex);
-		return -EEXIST;
+	if (attached == prog) {
+		/* The same program cannot be attached twice */
+		ret = -EINVAL;
+		goto out;
 	}
 	rcu_assign_pointer(net->flow_dissector_prog, prog);
+	if (attached)
+		bpf_prog_put(attached);
+out:
 	mutex_unlock(&flow_dissector_mutex);
-	return 0;
+	return ret;
 }
 
 int skb_flow_dissector_bpf_prog_detach(const union bpf_attr *attr)
@@ -147,27 +178,6 @@ int skb_flow_dissector_bpf_prog_detach(const union bpf_attr *attr)
 	mutex_unlock(&flow_dissector_mutex);
 	return 0;
 }
-/**
- * skb_flow_get_be16 - extract be16 entity
- * @skb: sk_buff to extract from
- * @poff: offset to extract at
- * @data: raw buffer pointer to the packet
- * @hlen: packet header length
- *
- * The function will try to retrieve a be32 entity at
- * offset poff
- */
-static __be16 skb_flow_get_be16(const struct sk_buff *skb, int poff,
-				void *data, int hlen)
-{
-	__be16 *u, _u;
-
-	u = __skb_header_pointer(skb, poff, sizeof(_u), data, hlen, &_u);
-	if (u)
-		return *u;
-
-	return 0;
-}
 
 /**
  * __skb_flow_get_ports - extract the upper layer ports and return them
@@ -203,6 +213,72 @@ __be32 __skb_flow_get_ports(const struct sk_buff *skb, int thoff, u8 ip_proto,
 }
 EXPORT_SYMBOL(__skb_flow_get_ports);
 
+static bool icmp_has_id(u8 type)
+{
+	switch (type) {
+	case ICMP_ECHO:
+	case ICMP_ECHOREPLY:
+	case ICMP_TIMESTAMP:
+	case ICMP_TIMESTAMPREPLY:
+	case ICMPV6_ECHO_REQUEST:
+	case ICMPV6_ECHO_REPLY:
+		return true;
+	}
+
+	return false;
+}
+
+/**
+ * skb_flow_get_icmp_tci - extract ICMP(6) Type, Code and Identifier fields
+ * @skb: sk_buff to extract from
+ * @key_icmp: struct flow_dissector_key_icmp to fill
+ * @data: raw buffer pointer to the packet
+ * @toff: offset to extract at
+ * @hlen: packet header length
+ */
+void skb_flow_get_icmp_tci(const struct sk_buff *skb,
+			   struct flow_dissector_key_icmp *key_icmp,
+			   void *data, int thoff, int hlen)
+{
+	struct icmphdr *ih, _ih;
+
+	ih = __skb_header_pointer(skb, thoff, sizeof(_ih), data, hlen, &_ih);
+	if (!ih)
+		return;
+
+	key_icmp->type = ih->type;
+	key_icmp->code = ih->code;
+
+	/* As we use 0 to signal that the Id field is not present,
+	 * avoid confusion with packets without such field
+	 */
+	if (icmp_has_id(ih->type))
+		key_icmp->id = ih->un.echo.id ? : 1;
+	else
+		key_icmp->id = 0;
+}
+EXPORT_SYMBOL(skb_flow_get_icmp_tci);
+
+/* If FLOW_DISSECTOR_KEY_ICMP is set, dissect an ICMP packet
+ * using skb_flow_get_icmp_tci().
+ */
+static void __skb_flow_dissect_icmp(const struct sk_buff *skb,
+				    struct flow_dissector *flow_dissector,
+				    void *target_container,
+				    void *data, int thoff, int hlen)
+{
+	struct flow_dissector_key_icmp *key_icmp;
+
+	if (!dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_ICMP))
+		return;
+
+	key_icmp = skb_flow_dissector_target(flow_dissector,
+					     FLOW_DISSECTOR_KEY_ICMP,
+					     target_container);
+
+	skb_flow_get_icmp_tci(skb, key_icmp, data, thoff, hlen);
+}
+
 void skb_flow_dissect_meta(const struct sk_buff *skb,
 			   struct flow_dissector *flow_dissector,
 			   void *target_container)
@@ -853,7 +929,6 @@ bool __skb_flow_dissect(const struct net *net,
 	struct flow_dissector_key_basic *key_basic;
 	struct flow_dissector_key_addrs *key_addrs;
 	struct flow_dissector_key_ports *key_ports;
-	struct flow_dissector_key_icmp *key_icmp;
 	struct flow_dissector_key_tags *key_tags;
 	struct flow_dissector_key_vlan *key_vlan;
 	struct bpf_prog *attached = NULL;
@@ -910,7 +985,10 @@ bool __skb_flow_dissect(const struct net *net,
 	WARN_ON_ONCE(!net);
 	if (net) {
 		rcu_read_lock();
-		attached = rcu_dereference(net->flow_dissector_prog);
+		attached = rcu_dereference(init_net.flow_dissector_prog);
+
+		if (!attached)
+			attached = rcu_dereference(net->flow_dissector_prog);
 
 		if (attached) {
 			struct bpf_flow_keys flow_keys;
@@ -1295,6 +1373,12 @@ ip_proto_again:
 				       data, nhoff, hlen);
 		break;
 
+	case IPPROTO_ICMP:
+	case IPPROTO_ICMPV6:
+		__skb_flow_dissect_icmp(skb, flow_dissector, target_container,
+					data, nhoff, hlen);
+		break;
+
 	default:
 		break;
 	}
@@ -1308,14 +1392,6 @@ ip_proto_again:
 							data, hlen);
 	}
 
-	if (dissector_uses_key(flow_dissector,
-			       FLOW_DISSECTOR_KEY_ICMP)) {
-		key_icmp = skb_flow_dissector_target(flow_dissector,
-						     FLOW_DISSECTOR_KEY_ICMP,
-						     target_container);
-		key_icmp->icmp = skb_flow_get_be16(skb, nhoff, data, hlen);
-	}
-
 	/* Process result of IP proto processing */
 	switch (fdret) {
 	case FLOW_DISSECT_RET_PROTO_AGAIN:
@@ -1365,8 +1441,8 @@ static const void *flow_keys_hash_start(const struct flow_keys *flow)
 static inline size_t flow_keys_hash_length(const struct flow_keys *flow)
 {
 	size_t diff = FLOW_KEYS_HASH_OFFSET + sizeof(flow->addrs);
-	BUILD_BUG_ON(offsetof(typeof(*flow), addrs) !=
-		     sizeof(*flow) - sizeof(flow->addrs));
+
+	BUILD_BUG_ON((sizeof(*flow) - FLOW_KEYS_HASH_OFFSET) % sizeof(u32));
 
 	switch (flow->control.addr_type) {
 	case FLOW_DISSECTOR_KEY_IPV4_ADDRS:
@@ -1412,6 +1488,9 @@ __be32 flow_get_u32_dst(const struct flow_keys *flow)
 }
 EXPORT_SYMBOL(flow_get_u32_dst);
 
+/* Sort the source and destination IP (and the ports if the IP are the same),
+ * to have consistent hash within the two directions
+ */
 static inline void __flow_hash_consistentify(struct flow_keys *keys)
 {
 	int addr_diff, i;