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

Pull networking updates from David Miller:

 1) Allow setting bluetooth L2CAP modes via socket option, from Luiz
    Augusto von Dentz.

 2) Add GSO partial support to igc, from Sasha Neftin.

 3) Several cleanups and improvements to r8169 from Heiner Kallweit.

 4) Add IF_OPER_TESTING link state and use it when ethtool triggers a
    device self-test. From Andrew Lunn.

 5) Start moving away from custom driver versions, use the globally
    defined kernel version instead, from Leon Romanovsky.

 6) Support GRO vis gro_cells in DSA layer, from Alexander Lobakin.

 7) Allow hard IRQ deferral during NAPI, from Eric Dumazet.

 8) Add sriov and vf support to hinic, from Luo bin.

 9) Support Media Redundancy Protocol (MRP) in the bridging code, from
    Horatiu Vultur.

10) Support netmap in the nft_nat code, from Pablo Neira Ayuso.

11) Allow UDPv6 encapsulation of ESP in the ipsec code, from Sabrina
    Dubroca. Also add ipv6 support for espintcp.

12) Lots of ReST conversions of the networking documentation, from Mauro
    Carvalho Chehab.

13) Support configuration of ethtool rxnfc flows in bcmgenet driver,
    from Doug Berger.

14) Allow to dump cgroup id and filter by it in inet_diag code, from
    Dmitry Yakunin.

15) Add infrastructure to export netlink attribute policies to
    userspace, from Johannes Berg.

16) Several optimizations to sch_fq scheduler, from Eric Dumazet.

17) Fallback to the default qdisc if qdisc init fails because otherwise
    a packet scheduler init failure will make a device inoperative. From
    Jesper Dangaard Brouer.

18) Several RISCV bpf jit optimizations, from Luke Nelson.

19) Correct the return type of the ->ndo_start_xmit() method in several
    drivers, it's netdev_tx_t but many drivers were using
    'int'. From Yunjian Wang.

20) Add an ethtool interface for PHY master/slave config, from Oleksij
    Rempel.

21) Add BPF iterators, from Yonghang Song.

22) Add cable test infrastructure, including ethool interfaces, from
    Andrew Lunn. Marvell PHY driver is the first to support this
    facility.

23) Remove zero-length arrays all over, from Gustavo A. R. Silva.

24) Calculate and maintain an explicit frame size in XDP, from Jesper
    Dangaard Brouer.

25) Add CAP_BPF, from Alexei Starovoitov.

26) Support terse dumps in the packet scheduler, from Vlad Buslov.

27) Support XDP_TX bulking in dpaa2 driver, from Ioana Ciornei.

28) Add devm_register_netdev(), from Bartosz Golaszewski.

29) Minimize qdisc resets, from Cong Wang.

30) Get rid of kernel_getsockopt and kernel_setsockopt in order to
    eliminate set_fs/get_fs calls. From Christoph Hellwig.

* git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (2517 commits)
  selftests: net: ip_defrag: ignore EPERM
  net_failover: fixed rollback in net_failover_open()
  Revert "tipc: Fix potential tipc_aead refcnt leak in tipc_crypto_rcv"
  Revert "tipc: Fix potential tipc_node refcnt leak in tipc_rcv"
  vmxnet3: allow rx flow hash ops only when rss is enabled
  hinic: add set_channels ethtool_ops support
  selftests/bpf: Add a default $(CXX) value
  tools/bpf: Don't use $(COMPILE.c)
  bpf, selftests: Use bpf_probe_read_kernel
  s390/bpf: Use bcr 0,%0 as tail call nop filler
  s390/bpf: Maintain 8-byte stack alignment
  selftests/bpf: Fix verifier test
  selftests/bpf: Fix sample_cnt shared between two threads
  bpf, selftests: Adapt cls_redirect to call csum_level helper
  bpf: Add csum_level helper for fixing up csum levels
  bpf: Fix up bpf_skb_adjust_room helper's skb csum setting
  sfc: add missing annotation for efx_ef10_try_update_nic_stats_vf()
  crypto/chtls: IPv6 support for inline TLS
  Crypto/chcr: Fixes a coccinile check error
  Crypto/chcr: Fixes compilations warnings
  ...

1 files changed, 139 insertions, 121 deletions

diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index 0a7ecc292bd3..a00a203b2ef5 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -39,6 +39,7 @@
 #include <net/tc_act/tc_skbedit.h>
 #include <net/tc_act/tc_ct.h>
 #include <net/tc_act/tc_mpls.h>
+#include <net/tc_act/tc_gate.h>
 #include <net/flow_offload.h>
 
 extern const struct nla_policy rtm_tca_policy[TCA_MAX + 1];
@@ -620,96 +621,42 @@ static void tcf_chain_flush(struct tcf_chain *chain, bool rtnl_held)
 static int tcf_block_setup(struct tcf_block *block,
 			   struct flow_block_offload *bo);
 
-static void tc_indr_block_cmd(struct net_device *dev, struct tcf_block *block,
-			      flow_indr_block_bind_cb_t *cb, void *cb_priv,
-			      enum flow_block_command command, bool ingress)
-{
-	struct flow_block_offload bo = {
-		.command	= command,
-		.binder_type	= ingress ?
-				  FLOW_BLOCK_BINDER_TYPE_CLSACT_INGRESS :
-				  FLOW_BLOCK_BINDER_TYPE_CLSACT_EGRESS,
-		.net		= dev_net(dev),
-		.block_shared	= tcf_block_non_null_shared(block),
-	};
-	INIT_LIST_HEAD(&bo.cb_list);
-
-	if (!block)
-		return;
-
-	bo.block = &block->flow_block;
-
-	down_write(&block->cb_lock);
-	cb(dev, cb_priv, TC_SETUP_BLOCK, &bo);
-
-	tcf_block_setup(block, &bo);
-	up_write(&block->cb_lock);
-}
-
-static struct tcf_block *tc_dev_block(struct net_device *dev, bool ingress)
+static void tcf_block_offload_init(struct flow_block_offload *bo,
+				   struct net_device *dev,
+				   enum flow_block_command command,
+				   enum flow_block_binder_type binder_type,
+				   struct flow_block *flow_block,
+				   bool shared, struct netlink_ext_ack *extack)
 {
-	const struct Qdisc_class_ops *cops;
-	const struct Qdisc_ops *ops;
-	struct Qdisc *qdisc;
-
-	if (!dev_ingress_queue(dev))
-		return NULL;
-
-	qdisc = dev_ingress_queue(dev)->qdisc_sleeping;
-	if (!qdisc)
-		return NULL;
-
-	ops = qdisc->ops;
-	if (!ops)
-		return NULL;
-
-	if (!ingress && !strcmp("ingress", ops->id))
-		return NULL;
-
-	cops = ops->cl_ops;
-	if (!cops)
-		return NULL;
-
-	if (!cops->tcf_block)
-		return NULL;
-
-	return cops->tcf_block(qdisc,
-			       ingress ? TC_H_MIN_INGRESS : TC_H_MIN_EGRESS,
-			       NULL);
+	bo->net = dev_net(dev);
+	bo->command = command;
+	bo->binder_type = binder_type;
+	bo->block = flow_block;
+	bo->block_shared = shared;
+	bo->extack = extack;
+	INIT_LIST_HEAD(&bo->cb_list);
 }
 
-static void tc_indr_block_get_and_cmd(struct net_device *dev,
-				      flow_indr_block_bind_cb_t *cb,
-				      void *cb_priv,
-				      enum flow_block_command command)
-{
-	struct tcf_block *block;
-
-	block = tc_dev_block(dev, true);
-	tc_indr_block_cmd(dev, block, cb, cb_priv, command, true);
-
-	block = tc_dev_block(dev, false);
-	tc_indr_block_cmd(dev, block, cb, cb_priv, command, false);
-}
+static void tcf_block_unbind(struct tcf_block *block,
+			     struct flow_block_offload *bo);
 
-static void tc_indr_block_call(struct tcf_block *block,
-			       struct net_device *dev,
-			       struct tcf_block_ext_info *ei,
-			       enum flow_block_command command,
-			       struct netlink_ext_ack *extack)
+static void tc_block_indr_cleanup(struct flow_block_cb *block_cb)
 {
-	struct flow_block_offload bo = {
-		.command	= command,
-		.binder_type	= ei->binder_type,
-		.net		= dev_net(dev),
-		.block		= &block->flow_block,
-		.block_shared	= tcf_block_shared(block),
-		.extack		= extack,
-	};
-	INIT_LIST_HEAD(&bo.cb_list);
+	struct tcf_block *block = block_cb->indr.data;
+	struct net_device *dev = block_cb->indr.dev;
+	struct netlink_ext_ack extack = {};
+	struct flow_block_offload bo;
 
-	flow_indr_block_call(dev, &bo, command, TC_SETUP_BLOCK);
-	tcf_block_setup(block, &bo);
+	tcf_block_offload_init(&bo, dev, FLOW_BLOCK_UNBIND,
+			       block_cb->indr.binder_type,
+			       &block->flow_block, tcf_block_shared(block),
+			       &extack);
+	down_write(&block->cb_lock);
+	list_move(&block_cb->list, &bo.cb_list);
+	up_write(&block->cb_lock);
+	rtnl_lock();
+	tcf_block_unbind(block, &bo);
+	rtnl_unlock();
 }
 
 static bool tcf_block_offload_in_use(struct tcf_block *block)
@@ -726,17 +673,21 @@ static int tcf_block_offload_cmd(struct tcf_block *block,
 	struct flow_block_offload bo = {};
 	int err;
 
-	bo.net = dev_net(dev);
-	bo.command = command;
-	bo.binder_type = ei->binder_type;
-	bo.block = &block->flow_block;
-	bo.block_shared = tcf_block_shared(block);
-	bo.extack = extack;
-	INIT_LIST_HEAD(&bo.cb_list);
+	tcf_block_offload_init(&bo, dev, command, ei->binder_type,
+			       &block->flow_block, tcf_block_shared(block),
+			       extack);
 
-	err = dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_BLOCK, &bo);
-	if (err < 0)
+	if (dev->netdev_ops->ndo_setup_tc)
+		err = dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_BLOCK, &bo);
+	else
+		err = flow_indr_dev_setup_offload(dev, TC_SETUP_BLOCK, block,
+						  &bo, tc_block_indr_cleanup);
+
+	if (err < 0) {
+		if (err != -EOPNOTSUPP)
+			NL_SET_ERR_MSG(extack, "Driver ndo_setup_tc failed");
 		return err;
+	}
 
 	return tcf_block_setup(block, &bo);
 }
@@ -749,13 +700,13 @@ static int tcf_block_offload_bind(struct tcf_block *block, struct Qdisc *q,
 	int err;
 
 	down_write(&block->cb_lock);
-	if (!dev->netdev_ops->ndo_setup_tc)
-		goto no_offload_dev_inc;
 
 	/* If tc offload feature is disabled and the block we try to bind
 	 * to already has some offloaded filters, forbid to bind.
 	 */
-	if (!tc_can_offload(dev) && tcf_block_offload_in_use(block)) {
+	if (dev->netdev_ops->ndo_setup_tc &&
+	    !tc_can_offload(dev) &&
+	    tcf_block_offload_in_use(block)) {
 		NL_SET_ERR_MSG(extack, "Bind to offloaded block failed as dev has offload disabled");
 		err = -EOPNOTSUPP;
 		goto err_unlock;
@@ -767,18 +718,15 @@ static int tcf_block_offload_bind(struct tcf_block *block, struct Qdisc *q,
 	if (err)
 		goto err_unlock;
 
-	tc_indr_block_call(block, dev, ei, FLOW_BLOCK_BIND, extack);
 	up_write(&block->cb_lock);
 	return 0;
 
 no_offload_dev_inc:
-	if (tcf_block_offload_in_use(block)) {
-		err = -EOPNOTSUPP;
+	if (tcf_block_offload_in_use(block))
 		goto err_unlock;
-	}
+
 	err = 0;
 	block->nooffloaddevcnt++;
-	tc_indr_block_call(block, dev, ei, FLOW_BLOCK_BIND, extack);
 err_unlock:
 	up_write(&block->cb_lock);
 	return err;
@@ -791,10 +739,6 @@ static void tcf_block_offload_unbind(struct tcf_block *block, struct Qdisc *q,
 	int err;
 
 	down_write(&block->cb_lock);
-	tc_indr_block_call(block, dev, ei, FLOW_BLOCK_UNBIND, NULL);
-
-	if (!dev->netdev_ops->ndo_setup_tc)
-		goto no_offload_dev_dec;
 	err = tcf_block_offload_cmd(block, dev, ei, FLOW_BLOCK_UNBIND, NULL);
 	if (err == -EOPNOTSUPP)
 		goto no_offload_dev_dec;
@@ -1847,7 +1791,7 @@ static int tcf_fill_node(struct net *net, struct sk_buff *skb,
 			 struct tcf_proto *tp, struct tcf_block *block,
 			 struct Qdisc *q, u32 parent, void *fh,
 			 u32 portid, u32 seq, u16 flags, int event,
-			 bool rtnl_held)
+			 bool terse_dump, bool rtnl_held)
 {
 	struct tcmsg *tcm;
 	struct nlmsghdr  *nlh;
@@ -1874,6 +1818,14 @@ static int tcf_fill_node(struct net *net, struct sk_buff *skb,
 		goto nla_put_failure;
 	if (!fh) {
 		tcm->tcm_handle = 0;
+	} else if (terse_dump) {
+		if (tp->ops->terse_dump) {
+			if (tp->ops->terse_dump(net, tp, fh, skb, tcm,
+						rtnl_held) < 0)
+				goto nla_put_failure;
+		} else {
+			goto cls_op_not_supp;
+		}
 	} else {
 		if (tp->ops->dump &&
 		    tp->ops->dump(net, tp, fh, skb, tcm, rtnl_held) < 0)
@@ -1884,6 +1836,7 @@ static int tcf_fill_node(struct net *net, struct sk_buff *skb,
 
 out_nlmsg_trim:
 nla_put_failure:
+cls_op_not_supp:
 	nlmsg_trim(skb, b);
 	return -1;
 }
@@ -1904,7 +1857,7 @@ static int tfilter_notify(struct net *net, struct sk_buff *oskb,
 
 	if (tcf_fill_node(net, skb, tp, block, q, parent, fh, portid,
 			  n->nlmsg_seq, n->nlmsg_flags, event,
-			  rtnl_held) <= 0) {
+			  false, rtnl_held) <= 0) {
 		kfree_skb(skb);
 		return -EINVAL;
 	}
@@ -1936,7 +1889,7 @@ static int tfilter_del_notify(struct net *net, struct sk_buff *oskb,
 
 	if (tcf_fill_node(net, skb, tp, block, q, parent, fh, portid,
 			  n->nlmsg_seq, n->nlmsg_flags, RTM_DELTFILTER,
-			  rtnl_held) <= 0) {
+			  false, rtnl_held) <= 0) {
 		NL_SET_ERR_MSG(extack, "Failed to build del event notification");
 		kfree_skb(skb);
 		return -EINVAL;
@@ -2497,6 +2450,7 @@ struct tcf_dump_args {
 	struct tcf_block *block;
 	struct Qdisc *q;
 	u32 parent;
+	bool terse_dump;
 };
 
 static int tcf_node_dump(struct tcf_proto *tp, void *n, struct tcf_walker *arg)
@@ -2507,12 +2461,12 @@ static int tcf_node_dump(struct tcf_proto *tp, void *n, struct tcf_walker *arg)
 	return tcf_fill_node(net, a->skb, tp, a->block, a->q, a->parent,
 			     n, NETLINK_CB(a->cb->skb).portid,
 			     a->cb->nlh->nlmsg_seq, NLM_F_MULTI,
-			     RTM_NEWTFILTER, true);
+			     RTM_NEWTFILTER, a->terse_dump, true);
 }
 
 static bool tcf_chain_dump(struct tcf_chain *chain, struct Qdisc *q, u32 parent,
 			   struct sk_buff *skb, struct netlink_callback *cb,
-			   long index_start, long *p_index)
+			   long index_start, long *p_index, bool terse)
 {
 	struct net *net = sock_net(skb->sk);
 	struct tcf_block *block = chain->block;
@@ -2541,7 +2495,7 @@ static bool tcf_chain_dump(struct tcf_chain *chain, struct Qdisc *q, u32 parent,
 			if (tcf_fill_node(net, skb, tp, block, q, parent, NULL,
 					  NETLINK_CB(cb->skb).portid,
 					  cb->nlh->nlmsg_seq, NLM_F_MULTI,
-					  RTM_NEWTFILTER, true) <= 0)
+					  RTM_NEWTFILTER, false, true) <= 0)
 				goto errout;
 			cb->args[1] = 1;
 		}
@@ -2557,6 +2511,7 @@ static bool tcf_chain_dump(struct tcf_chain *chain, struct Qdisc *q, u32 parent,
 		arg.w.skip = cb->args[1] - 1;
 		arg.w.count = 0;
 		arg.w.cookie = cb->args[2];
+		arg.terse_dump = terse;
 		tp->ops->walk(tp, &arg.w, true);
 		cb->args[2] = arg.w.cookie;
 		cb->args[1] = arg.w.count + 1;
@@ -2570,6 +2525,10 @@ errout:
 	return false;
 }
 
+static const struct nla_policy tcf_tfilter_dump_policy[TCA_MAX + 1] = {
+	[TCA_DUMP_FLAGS] = NLA_POLICY_BITFIELD32(TCA_DUMP_FLAGS_TERSE),
+};
+
 /* called with RTNL */
 static int tc_dump_tfilter(struct sk_buff *skb, struct netlink_callback *cb)
 {
@@ -2579,6 +2538,7 @@ static int tc_dump_tfilter(struct sk_buff *skb, struct netlink_callback *cb)
 	struct Qdisc *q = NULL;
 	struct tcf_block *block;
 	struct tcmsg *tcm = nlmsg_data(cb->nlh);
+	bool terse_dump = false;
 	long index_start;
 	long index;
 	u32 parent;
@@ -2588,10 +2548,17 @@ static int tc_dump_tfilter(struct sk_buff *skb, struct netlink_callback *cb)
 		return skb->len;
 
 	err = nlmsg_parse_deprecated(cb->nlh, sizeof(*tcm), tca, TCA_MAX,
-				     NULL, cb->extack);
+				     tcf_tfilter_dump_policy, cb->extack);
 	if (err)
 		return err;
 
+	if (tca[TCA_DUMP_FLAGS]) {
+		struct nla_bitfield32 flags =
+			nla_get_bitfield32(tca[TCA_DUMP_FLAGS]);
+
+		terse_dump = flags.value & TCA_DUMP_FLAGS_TERSE;
+	}
+
 	if (tcm->tcm_ifindex == TCM_IFINDEX_MAGIC_BLOCK) {
 		block = tcf_block_refcnt_get(net, tcm->tcm_block_index);
 		if (!block)
@@ -2649,7 +2616,7 @@ static int tc_dump_tfilter(struct sk_buff *skb, struct netlink_callback *cb)
 		    nla_get_u32(tca[TCA_CHAIN]) != chain->index)
 			continue;
 		if (!tcf_chain_dump(chain, q, parent, skb, cb,
-				    index_start, &index)) {
+				    index_start, &index, terse_dump)) {
 			tcf_chain_put(chain);
 			err = -EMSGSIZE;
 			break;
@@ -3152,7 +3119,8 @@ int tcf_exts_dump(struct sk_buff *skb, struct tcf_exts *exts)
 			if (nest == NULL)
 				goto nla_put_failure;
 
-			if (tcf_action_dump(skb, exts->actions, 0, 0) < 0)
+			if (tcf_action_dump(skb, exts->actions, 0, 0, false)
+			    < 0)
 				goto nla_put_failure;
 			nla_nest_end(skb, nest);
 		} else if (exts->police) {
@@ -3176,6 +3144,31 @@ nla_put_failure:
 }
 EXPORT_SYMBOL(tcf_exts_dump);
 
+int tcf_exts_terse_dump(struct sk_buff *skb, struct tcf_exts *exts)
+{
+#ifdef CONFIG_NET_CLS_ACT
+	struct nlattr *nest;
+
+	if (!exts->action || !tcf_exts_has_actions(exts))
+		return 0;
+
+	nest = nla_nest_start_noflag(skb, exts->action);
+	if (!nest)
+		goto nla_put_failure;
+
+	if (tcf_action_dump(skb, exts->actions, 0, 0, true) < 0)
+		goto nla_put_failure;
+	nla_nest_end(skb, nest);
+	return 0;
+
+nla_put_failure:
+	nla_nest_cancel(skb, nest);
+	return -1;
+#else
+	return 0;
+#endif
+}
+EXPORT_SYMBOL(tcf_exts_terse_dump);
 
 int tcf_exts_dump_stats(struct sk_buff *skb, struct tcf_exts *exts)
 {
@@ -3523,6 +3516,27 @@ static void tcf_sample_get_group(struct flow_action_entry *entry,
 #endif
 }
 
+static void tcf_gate_entry_destructor(void *priv)
+{
+	struct action_gate_entry *oe = priv;
+
+	kfree(oe);
+}
+
+static int tcf_gate_get_entries(struct flow_action_entry *entry,
+				const struct tc_action *act)
+{
+	entry->gate.entries = tcf_gate_get_list(act);
+
+	if (!entry->gate.entries)
+		return -EINVAL;
+
+	entry->destructor = tcf_gate_entry_destructor;
+	entry->destructor_priv = entry->gate.entries;
+
+	return 0;
+}
+
 static enum flow_action_hw_stats tc_act_hw_stats(u8 hw_stats)
 {
 	if (WARN_ON_ONCE(hw_stats > TCA_ACT_HW_STATS_ANY))
@@ -3679,6 +3693,17 @@ int tc_setup_flow_action(struct flow_action *flow_action,
 		} else if (is_tcf_skbedit_priority(act)) {
 			entry->id = FLOW_ACTION_PRIORITY;
 			entry->priority = tcf_skbedit_priority(act);
+		} else if (is_tcf_gate(act)) {
+			entry->id = FLOW_ACTION_GATE;
+			entry->gate.index = tcf_gate_index(act);
+			entry->gate.prio = tcf_gate_prio(act);
+			entry->gate.basetime = tcf_gate_basetime(act);
+			entry->gate.cycletime = tcf_gate_cycletime(act);
+			entry->gate.cycletimeext = tcf_gate_cycletimeext(act);
+			entry->gate.num_entries = tcf_gate_num_entries(act);
+			err = tcf_gate_get_entries(entry, act);
+			if (err)
+				goto err_out;
 		} else {
 			err = -EOPNOTSUPP;
 			goto err_out_locked;
@@ -3739,11 +3764,6 @@ static struct pernet_operations tcf_net_ops = {
 	.size = sizeof(struct tcf_net),
 };
 
-static struct flow_indr_block_entry block_entry = {
-	.cb = tc_indr_block_get_and_cmd,
-	.list = LIST_HEAD_INIT(block_entry.list),
-};
-
 static int __init tc_filter_init(void)
 {
 	int err;
@@ -3756,8 +3776,6 @@ static int __init tc_filter_init(void)
 	if (err)
 		goto err_register_pernet_subsys;
 
-	flow_indr_add_block_cb(&block_entry);
-
 	rtnl_register(PF_UNSPEC, RTM_NEWTFILTER, tc_new_tfilter, NULL,
 		      RTNL_FLAG_DOIT_UNLOCKED);
 	rtnl_register(PF_UNSPEC, RTM_DELTFILTER, tc_del_tfilter, NULL,