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

Pull networking updates from David Miller:
 "Highlights:

   1) Fix the iwlwifi regression, from Johannes Berg.

   2) Support BSS coloring and 802.11 encapsulation offloading in
      hardware, from John Crispin.

   3) Fix some potential Spectre issues in qtnfmac, from Sergey
      Matyukevich.

   4) Add TTL decrement action to openvswitch, from Matteo Croce.

   5) Allow paralleization through flow_action setup by not taking the
      RTNL mutex, from Vlad Buslov.

   6) A lot of zero-length array to flexible-array conversions, from
      Gustavo A. R. Silva.

   7) Align XDP statistics names across several drivers for consistency,
      from Lorenzo Bianconi.

   8) Add various pieces of infrastructure for offloading conntrack, and
      make use of it in mlx5 driver, from Paul Blakey.

   9) Allow using listening sockets in BPF sockmap, from Jakub Sitnicki.

  10) Lots of parallelization improvements during configuration changes
      in mlxsw driver, from Ido Schimmel.

  11) Add support to devlink for generic packet traps, which report
      packets dropped during ACL processing. And use them in mlxsw
      driver. From Jiri Pirko.

  12) Support bcmgenet on ACPI, from Jeremy Linton.

  13) Make BPF compatible with RT, from Thomas Gleixnet, Alexei
      Starovoitov, and your's truly.

  14) Support XDP meta-data in virtio_net, from Yuya Kusakabe.

  15) Fix sysfs permissions when network devices change namespaces, from
      Christian Brauner.

  16) Add a flags element to ethtool_ops so that drivers can more simply
      indicate which coalescing parameters they actually support, and
      therefore the generic layer can validate the user's ethtool
      request. Use this in all drivers, from Jakub Kicinski.

  17) Offload FIFO qdisc in mlxsw, from Petr Machata.

  18) Support UDP sockets in sockmap, from Lorenz Bauer.

  19) Fix stretch ACK bugs in several TCP congestion control modules,
      from Pengcheng Yang.

  20) Support virtual functiosn in octeontx2 driver, from Tomasz
      Duszynski.

  21) Add region operations for devlink and use it in ice driver to dump
      NVM contents, from Jacob Keller.

  22) Add support for hw offload of MACSEC, from Antoine Tenart.

  23) Add support for BPF programs that can be attached to LSM hooks,
      from KP Singh.

  24) Support for multiple paths, path managers, and counters in MPTCP.
      From Peter Krystad, Paolo Abeni, Florian Westphal, Davide Caratti,
      and others.

  25) More progress on adding the netlink interface to ethtool, from
      Michal Kubecek"

* git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (2121 commits)
  net: ipv6: rpl_iptunnel: Fix potential memory leak in rpl_do_srh_inline
  cxgb4/chcr: nic-tls stats in ethtool
  net: dsa: fix oops while probing Marvell DSA switches
  net/bpfilter: remove superfluous testing message
  net: macb: Fix handling of fixed-link node
  net: dsa: ksz: Select KSZ protocol tag
  netdevsim: dev: Fix memory leak in nsim_dev_take_snapshot_write
  net: stmmac: add EHL 2.5Gbps PCI info and PCI ID
  net: stmmac: add EHL PSE0 & PSE1 1Gbps PCI info and PCI ID
  net: stmmac: create dwmac-intel.c to contain all Intel platform
  net: dsa: bcm_sf2: Support specifying VLAN tag egress rule
  net: dsa: bcm_sf2: Add support for matching VLAN TCI
  net: dsa: bcm_sf2: Move writing of CFP_DATA(5) into slicing functions
  net: dsa: bcm_sf2: Check earlier for FLOW_EXT and FLOW_MAC_EXT
  net: dsa: bcm_sf2: Disable learning for ASP port
  net: dsa: b53: Deny enslaving port 7 for 7278 into a bridge
  net: dsa: b53: Prevent tagged VLAN on port 7 for 7278
  net: dsa: b53: Restore VLAN entries upon (re)configuration
  net: dsa: bcm_sf2: Fix overflow checks
  hv_netvsc: Remove unnecessary round_up for recv_completion_cnt
  ...

1 files changed, 136 insertions, 32 deletions

diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index c2cdd0fc2e70..f6a3b969ead0 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -22,6 +22,7 @@
 #include <linux/idr.h>
 #include <linux/rhashtable.h>
 #include <linux/jhash.h>
+#include <linux/rculist.h>
 #include <net/net_namespace.h>
 #include <net/sock.h>
 #include <net/netlink.h>
@@ -354,7 +355,7 @@ static struct tcf_chain *tcf_chain_create(struct tcf_block *block,
 	chain = kzalloc(sizeof(*chain), GFP_KERNEL);
 	if (!chain)
 		return NULL;
-	list_add_tail(&chain->list, &block->chain_list);
+	list_add_tail_rcu(&chain->list, &block->chain_list);
 	mutex_init(&chain->filter_chain_lock);
 	chain->block = block;
 	chain->index = chain_index;
@@ -394,7 +395,7 @@ static bool tcf_chain_detach(struct tcf_chain *chain)
 
 	ASSERT_BLOCK_LOCKED(block);
 
-	list_del(&chain->list);
+	list_del_rcu(&chain->list);
 	if (!chain->index)
 		block->chain0.chain = NULL;
 
@@ -453,6 +454,20 @@ static struct tcf_chain *tcf_chain_lookup(struct tcf_block *block,
 	return NULL;
 }
 
+#if IS_ENABLED(CONFIG_NET_TC_SKB_EXT)
+static struct tcf_chain *tcf_chain_lookup_rcu(const struct tcf_block *block,
+					      u32 chain_index)
+{
+	struct tcf_chain *chain;
+
+	list_for_each_entry_rcu(chain, &block->chain_list, list) {
+		if (chain->index == chain_index)
+			return chain;
+	}
+	return NULL;
+}
+#endif
+
 static int tc_chain_notify(struct tcf_chain *chain, struct sk_buff *oskb,
 			   u32 seq, u16 flags, int event, bool unicast);
 
@@ -693,7 +708,7 @@ static void tc_indr_block_call(struct tcf_block *block,
 	};
 	INIT_LIST_HEAD(&bo.cb_list);
 
-	flow_indr_block_call(dev, &bo, command);
+	flow_indr_block_call(dev, &bo, command, TC_SETUP_BLOCK);
 	tcf_block_setup(block, &bo);
 }
 
@@ -1559,12 +1574,15 @@ static int tcf_block_setup(struct tcf_block *block,
  * to this qdisc, (optionally) tests for protocol and asks
  * specific classifiers.
  */
-int tcf_classify(struct sk_buff *skb, const struct tcf_proto *tp,
-		 struct tcf_result *res, bool compat_mode)
+static inline int __tcf_classify(struct sk_buff *skb,
+				 const struct tcf_proto *tp,
+				 const struct tcf_proto *orig_tp,
+				 struct tcf_result *res,
+				 bool compat_mode,
+				 u32 *last_executed_chain)
 {
 #ifdef CONFIG_NET_CLS_ACT
 	const int max_reclassify_loop = 4;
-	const struct tcf_proto *orig_tp = tp;
 	const struct tcf_proto *first_tp;
 	int limit = 0;
 
@@ -1582,21 +1600,11 @@ reclassify:
 #ifdef CONFIG_NET_CLS_ACT
 		if (unlikely(err == TC_ACT_RECLASSIFY && !compat_mode)) {
 			first_tp = orig_tp;
+			*last_executed_chain = first_tp->chain->index;
 			goto reset;
 		} else if (unlikely(TC_ACT_EXT_CMP(err, TC_ACT_GOTO_CHAIN))) {
 			first_tp = res->goto_tp;
-
-#if IS_ENABLED(CONFIG_NET_TC_SKB_EXT)
-			{
-				struct tc_skb_ext *ext;
-
-				ext = skb_ext_add(skb, TC_SKB_EXT);
-				if (WARN_ON_ONCE(!ext))
-					return TC_ACT_SHOT;
-
-				ext->chain = err & TC_ACT_EXT_VAL_MASK;
-			}
-#endif
+			*last_executed_chain = err & TC_ACT_EXT_VAL_MASK;
 			goto reset;
 		}
 #endif
@@ -1619,8 +1627,64 @@ reset:
 	goto reclassify;
 #endif
 }
+
+int tcf_classify(struct sk_buff *skb, const struct tcf_proto *tp,
+		 struct tcf_result *res, bool compat_mode)
+{
+	u32 last_executed_chain = 0;
+
+	return __tcf_classify(skb, tp, tp, res, compat_mode,
+			      &last_executed_chain);
+}
 EXPORT_SYMBOL(tcf_classify);
 
+int tcf_classify_ingress(struct sk_buff *skb,
+			 const struct tcf_block *ingress_block,
+			 const struct tcf_proto *tp,
+			 struct tcf_result *res, bool compat_mode)
+{
+#if !IS_ENABLED(CONFIG_NET_TC_SKB_EXT)
+	u32 last_executed_chain = 0;
+
+	return __tcf_classify(skb, tp, tp, res, compat_mode,
+			      &last_executed_chain);
+#else
+	u32 last_executed_chain = tp ? tp->chain->index : 0;
+	const struct tcf_proto *orig_tp = tp;
+	struct tc_skb_ext *ext;
+	int ret;
+
+	ext = skb_ext_find(skb, TC_SKB_EXT);
+
+	if (ext && ext->chain) {
+		struct tcf_chain *fchain;
+
+		fchain = tcf_chain_lookup_rcu(ingress_block, ext->chain);
+		if (!fchain)
+			return TC_ACT_SHOT;
+
+		/* Consume, so cloned/redirect skbs won't inherit ext */
+		skb_ext_del(skb, TC_SKB_EXT);
+
+		tp = rcu_dereference_bh(fchain->filter_chain);
+	}
+
+	ret = __tcf_classify(skb, tp, orig_tp, res, compat_mode,
+			     &last_executed_chain);
+
+	/* If we missed on some chain */
+	if (ret == TC_ACT_UNSPEC && last_executed_chain) {
+		ext = skb_ext_add(skb, TC_SKB_EXT);
+		if (WARN_ON_ONCE(!ext))
+			return TC_ACT_SHOT;
+		ext->chain = last_executed_chain;
+	}
+
+	return ret;
+#endif
+}
+EXPORT_SYMBOL(tcf_classify_ingress);
+
 struct tcf_chain_info {
 	struct tcf_proto __rcu **pprev;
 	struct tcf_proto __rcu *next;
@@ -3382,14 +3446,40 @@ int tc_setup_cb_reoffload(struct tcf_block *block, struct tcf_proto *tp,
 }
 EXPORT_SYMBOL(tc_setup_cb_reoffload);
 
+static int tcf_act_get_cookie(struct flow_action_entry *entry,
+			      const struct tc_action *act)
+{
+	struct tc_cookie *cookie;
+	int err = 0;
+
+	rcu_read_lock();
+	cookie = rcu_dereference(act->act_cookie);
+	if (cookie) {
+		entry->cookie = flow_action_cookie_create(cookie->data,
+							  cookie->len,
+							  GFP_ATOMIC);
+		if (!entry->cookie)
+			err = -ENOMEM;
+	}
+	rcu_read_unlock();
+	return err;
+}
+
+static void tcf_act_put_cookie(struct flow_action_entry *entry)
+{
+	flow_action_cookie_destroy(entry->cookie);
+}
+
 void tc_cleanup_flow_action(struct flow_action *flow_action)
 {
 	struct flow_action_entry *entry;
 	int i;
 
-	flow_action_for_each(i, entry, flow_action)
+	flow_action_for_each(i, entry, flow_action) {
+		tcf_act_put_cookie(entry);
 		if (entry->destructor)
 			entry->destructor(entry->destructor_priv);
+	}
 }
 EXPORT_SYMBOL(tc_cleanup_flow_action);
 
@@ -3433,22 +3523,30 @@ static void tcf_sample_get_group(struct flow_action_entry *entry,
 }
 
 int tc_setup_flow_action(struct flow_action *flow_action,
-			 const struct tcf_exts *exts, bool rtnl_held)
+			 const struct tcf_exts *exts)
 {
-	const struct tc_action *act;
+	struct tc_action *act;
 	int i, j, k, err = 0;
 
+	BUILD_BUG_ON(TCA_ACT_HW_STATS_ANY != FLOW_ACTION_HW_STATS_ANY);
+	BUILD_BUG_ON(TCA_ACT_HW_STATS_IMMEDIATE != FLOW_ACTION_HW_STATS_IMMEDIATE);
+	BUILD_BUG_ON(TCA_ACT_HW_STATS_DELAYED != FLOW_ACTION_HW_STATS_DELAYED);
+
 	if (!exts)
 		return 0;
 
-	if (!rtnl_held)
-		rtnl_lock();
-
 	j = 0;
 	tcf_exts_for_each_action(i, act, exts) {
 		struct flow_action_entry *entry;
 
 		entry = &flow_action->entries[j];
+		spin_lock_bh(&act->tcfa_lock);
+		err = tcf_act_get_cookie(entry, act);
+		if (err)
+			goto err_out_locked;
+
+		entry->hw_stats = act->hw_stats;
+
 		if (is_tcf_gact_ok(act)) {
 			entry->id = FLOW_ACTION_ACCEPT;
 		} else if (is_tcf_gact_shot(act)) {
@@ -3489,13 +3587,13 @@ int tc_setup_flow_action(struct flow_action *flow_action,
 				break;
 			default:
 				err = -EOPNOTSUPP;
-				goto err_out;
+				goto err_out_locked;
 			}
 		} else if (is_tcf_tunnel_set(act)) {
 			entry->id = FLOW_ACTION_TUNNEL_ENCAP;
 			err = tcf_tunnel_encap_get_tunnel(entry, act);
 			if (err)
-				goto err_out;
+				goto err_out_locked;
 		} else if (is_tcf_tunnel_release(act)) {
 			entry->id = FLOW_ACTION_TUNNEL_DECAP;
 		} else if (is_tcf_pedit(act)) {
@@ -3509,12 +3607,13 @@ int tc_setup_flow_action(struct flow_action *flow_action,
 					break;
 				default:
 					err = -EOPNOTSUPP;
-					goto err_out;
+					goto err_out_locked;
 				}
 				entry->mangle.htype = tcf_pedit_htype(act, k);
 				entry->mangle.mask = tcf_pedit_mask(act, k);
 				entry->mangle.val = tcf_pedit_val(act, k);
 				entry->mangle.offset = tcf_pedit_offset(act, k);
+				entry->hw_stats = act->hw_stats;
 				entry = &flow_action->entries[++j];
 			}
 		} else if (is_tcf_csum(act)) {
@@ -3538,6 +3637,7 @@ int tc_setup_flow_action(struct flow_action *flow_action,
 			entry->id = FLOW_ACTION_CT;
 			entry->ct.action = tcf_ct_action(act);
 			entry->ct.zone = tcf_ct_zone(act);
+			entry->ct.flow_table = tcf_ct_ft(act);
 		} else if (is_tcf_mpls(act)) {
 			switch (tcf_mpls_action(act)) {
 			case TCA_MPLS_ACT_PUSH:
@@ -3560,28 +3660,32 @@ int tc_setup_flow_action(struct flow_action *flow_action,
 				entry->mpls_mangle.ttl = tcf_mpls_ttl(act);
 				break;
 			default:
-				goto err_out;
+				goto err_out_locked;
 			}
 		} else if (is_tcf_skbedit_ptype(act)) {
 			entry->id = FLOW_ACTION_PTYPE;
 			entry->ptype = tcf_skbedit_ptype(act);
+		} else if (is_tcf_skbedit_priority(act)) {
+			entry->id = FLOW_ACTION_PRIORITY;
+			entry->priority = tcf_skbedit_priority(act);
 		} else {
 			err = -EOPNOTSUPP;
-			goto err_out;
+			goto err_out_locked;
 		}
+		spin_unlock_bh(&act->tcfa_lock);
 
 		if (!is_tcf_pedit(act))
 			j++;
 	}
 
 err_out:
-	if (!rtnl_held)
-		rtnl_unlock();
-
 	if (err)
 		tc_cleanup_flow_action(flow_action);
 
 	return err;
+err_out_locked:
+	spin_unlock_bh(&act->tcfa_lock);
+	goto err_out;
 }
 EXPORT_SYMBOL(tc_setup_flow_action);