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

Pull networking updates from David Miller:
 "Highlights:

   - Gustavo A. R. Silva keeps working on the implicit switch fallthru
     changes.

   - Support 802.11ax High-Efficiency wireless in cfg80211 et al, From
     Luca Coelho.

   - Re-enable ASPM in r8169, from Kai-Heng Feng.

   - Add virtual XFRM interfaces, which avoids all of the limitations of
     existing IPSEC tunnels. From Steffen Klassert.

   - Convert GRO over to use a hash table, so that when we have many
     flows active we don't traverse a long list during accumluation.

   - Many new self tests for routing, TC, tunnels, etc. Too many
     contributors to mention them all, but I'm really happy to keep
     seeing this stuff.

   - Hardware timestamping support for dpaa_eth/fsl-fman from Yangbo Lu.

   - Lots of cleanups and fixes in L2TP code from Guillaume Nault.

   - Add IPSEC offload support to netdevsim, from Shannon Nelson.

   - Add support for slotting with non-uniform distribution to netem
     packet scheduler, from Yousuk Seung.

   - Add UDP GSO support to mlx5e, from Boris Pismenny.

   - Support offloading of Team LAG in NFP, from John Hurley.

   - Allow to configure TX queue selection based upon RX queue, from
     Amritha Nambiar.

   - Support ethtool ring size configuration in aquantia, from Anton
     Mikaev.

   - Support DSCP and flowlabel per-transport in SCTP, from Xin Long.

   - Support list based batching and stack traversal of SKBs, this is
     very exciting work. From Edward Cree.

   - Busyloop optimizations in vhost_net, from Toshiaki Makita.

   - Introduce the ETF qdisc, which allows time based transmissions. IGB
     can offload this in hardware. From Vinicius Costa Gomes.

   - Add parameter support to devlink, from Moshe Shemesh.

   - Several multiplication and division optimizations for BPF JIT in
     nfp driver, from Jiong Wang.

   - Lots of prepatory work to make more of the packet scheduler layer
     lockless, when possible, from Vlad Buslov.

   - Add ACK filter and NAT awareness to sch_cake packet scheduler, from
     Toke Høiland-Jørgensen.

   - Support regions and region snapshots in devlink, from Alex Vesker.

   - Allow to attach XDP programs to both HW and SW at the same time on
     a given device, with initial support in nfp. From Jakub Kicinski.

   - Add TLS RX offload and support in mlx5, from Ilya Lesokhin.

   - Use PHYLIB in r8169 driver, from Heiner Kallweit.

   - All sorts of changes to support Spectrum 2 in mlxsw driver, from
     Ido Schimmel.

   - PTP support in mv88e6xxx DSA driver, from Andrew Lunn.

   - Make TCP_USER_TIMEOUT socket option more accurate, from Jon
     Maxwell.

   - Support for templates in packet scheduler classifier, from Jiri
     Pirko.

   - IPV6 support in RDS, from Ka-Cheong Poon.

   - Native tproxy support in nf_tables, from Máté Eckl.

   - Maintain IP fragment queue in an rbtree, but optimize properly for
     in-order frags. From Peter Oskolkov.

   - Improvde handling of ACKs on hole repairs, from Yuchung Cheng"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1996 commits)
  bpf: test: fix spelling mistake "REUSEEPORT" -> "REUSEPORT"
  hv/netvsc: Fix NULL dereference at single queue mode fallback
  net: filter: mark expected switch fall-through
  xen-netfront: fix warn message as irq device name has '/'
  cxgb4: Add new T5 PCI device ids 0x50af and 0x50b0
  net: dsa: mv88e6xxx: missing unlock on error path
  rds: fix building with IPV6=m
  inet/connection_sock: prefer _THIS_IP_ to current_text_addr
  net: dsa: mv88e6xxx: bitwise vs logical bug
  net: sock_diag: Fix spectre v1 gadget in __sock_diag_cmd()
  ieee802154: hwsim: using right kind of iteration
  net: hns3: Add vlan filter setting by ethtool command -K
  net: hns3: Set tx ring' tc info when netdev is up
  net: hns3: Remove tx ring BD len register in hns3_enet
  net: hns3: Fix desc num set to default when setting channel
  net: hns3: Fix for phy link issue when using marvell phy driver
  net: hns3: Fix for information of phydev lost problem when down/up
  net: hns3: Fix for command format parsing error in hclge_is_all_function_id_zero
  net: hns3: Add support for serdes loopback selftest
  bnxt_en: take coredump_record structure off stack
  ...

1 files changed, 34 insertions, 16 deletions

diff --git a/net/sched/act_sample.c b/net/sched/act_sample.c
index 5db358497c9e..81071afe1b43 100644
--- a/net/sched/act_sample.c
+++ b/net/sched/act_sample.c
@@ -37,7 +37,8 @@ static const struct nla_policy sample_policy[TCA_SAMPLE_MAX + 1] = {
 
 static int tcf_sample_init(struct net *net, struct nlattr *nla,
 			   struct nlattr *est, struct tc_action **a, int ovr,
-			   int bind, struct netlink_ext_ack *extack)
+			   int bind, bool rtnl_held,
+			   struct netlink_ext_ack *extack)
 {
 	struct tc_action_net *tn = net_generic(net, sample_net_id);
 	struct nlattr *tb[TCA_SAMPLE_MAX + 1];
@@ -45,7 +46,7 @@ static int tcf_sample_init(struct net *net, struct nlattr *nla,
 	struct tc_sample *parm;
 	struct tcf_sample *s;
 	bool exists = false;
-	int ret;
+	int ret, err;
 
 	if (!nla)
 		return -EINVAL;
@@ -58,30 +59,35 @@ static int tcf_sample_init(struct net *net, struct nlattr *nla,
 
 	parm = nla_data(tb[TCA_SAMPLE_PARMS]);
 
-	exists = tcf_idr_check(tn, parm->index, a, bind);
+	err = tcf_idr_check_alloc(tn, &parm->index, a, bind);
+	if (err < 0)
+		return err;
+	exists = err;
 	if (exists && bind)
 		return 0;
 
 	if (!exists) {
 		ret = tcf_idr_create(tn, parm->index, est, a,
 				     &act_sample_ops, bind, false);
-		if (ret)
+		if (ret) {
+			tcf_idr_cleanup(tn, parm->index);
 			return ret;
+		}
 		ret = ACT_P_CREATED;
-	} else {
+	} else if (!ovr) {
 		tcf_idr_release(*a, bind);
-		if (!ovr)
-			return -EEXIST;
+		return -EEXIST;
 	}
 	s = to_sample(*a);
 
+	spin_lock(&s->tcf_lock);
 	s->tcf_action = parm->action;
 	s->rate = nla_get_u32(tb[TCA_SAMPLE_RATE]);
 	s->psample_group_num = nla_get_u32(tb[TCA_SAMPLE_PSAMPLE_GROUP]);
 	psample_group = psample_group_get(net, s->psample_group_num);
 	if (!psample_group) {
-		if (ret == ACT_P_CREATED)
-			tcf_idr_release(*a, bind);
+		spin_unlock(&s->tcf_lock);
+		tcf_idr_release(*a, bind);
 		return -ENOMEM;
 	}
 	RCU_INIT_POINTER(s->psample_group, psample_group);
@@ -90,6 +96,7 @@ static int tcf_sample_init(struct net *net, struct nlattr *nla,
 		s->truncate = true;
 		s->trunc_size = nla_get_u32(tb[TCA_SAMPLE_TRUNC_SIZE]);
 	}
+	spin_unlock(&s->tcf_lock);
 
 	if (ret == ACT_P_CREATED)
 		tcf_idr_insert(tn, *a);
@@ -101,7 +108,8 @@ static void tcf_sample_cleanup(struct tc_action *a)
 	struct tcf_sample *s = to_sample(a);
 	struct psample_group *psample_group;
 
-	psample_group = rtnl_dereference(s->psample_group);
+	/* last reference to action, no need to lock */
+	psample_group = rcu_dereference_protected(s->psample_group, 1);
 	RCU_INIT_POINTER(s->psample_group, NULL);
 	if (psample_group)
 		psample_group_put(psample_group);
@@ -136,8 +144,7 @@ static int tcf_sample_act(struct sk_buff *skb, const struct tc_action *a,
 	bstats_cpu_update(this_cpu_ptr(s->common.cpu_bstats), skb);
 	retval = READ_ONCE(s->tcf_action);
 
-	rcu_read_lock();
-	psample_group = rcu_dereference(s->psample_group);
+	psample_group = rcu_dereference_bh(s->psample_group);
 
 	/* randomly sample packets according to rate */
 	if (psample_group && (prandom_u32() % s->rate == 0)) {
@@ -161,7 +168,6 @@ static int tcf_sample_act(struct sk_buff *skb, const struct tc_action *a,
 			skb_pull(skb, skb->mac_len);
 	}
 
-	rcu_read_unlock();
 	return retval;
 }
 
@@ -172,12 +178,13 @@ static int tcf_sample_dump(struct sk_buff *skb, struct tc_action *a,
 	struct tcf_sample *s = to_sample(a);
 	struct tc_sample opt = {
 		.index      = s->tcf_index,
-		.action     = s->tcf_action,
-		.refcnt     = s->tcf_refcnt - ref,
-		.bindcnt    = s->tcf_bindcnt - bind,
+		.refcnt     = refcount_read(&s->tcf_refcnt) - ref,
+		.bindcnt    = atomic_read(&s->tcf_bindcnt) - bind,
 	};
 	struct tcf_t t;
 
+	spin_lock(&s->tcf_lock);
+	opt.action = s->tcf_action;
 	if (nla_put(skb, TCA_SAMPLE_PARMS, sizeof(opt), &opt))
 		goto nla_put_failure;
 
@@ -194,9 +201,12 @@ static int tcf_sample_dump(struct sk_buff *skb, struct tc_action *a,
 
 	if (nla_put_u32(skb, TCA_SAMPLE_PSAMPLE_GROUP, s->psample_group_num))
 		goto nla_put_failure;
+	spin_unlock(&s->tcf_lock);
+
 	return skb->len;
 
 nla_put_failure:
+	spin_unlock(&s->tcf_lock);
 	nlmsg_trim(skb, b);
 	return -1;
 }
@@ -219,6 +229,13 @@ static int tcf_sample_search(struct net *net, struct tc_action **a, u32 index,
 	return tcf_idr_search(tn, a, index);
 }
 
+static int tcf_sample_delete(struct net *net, u32 index)
+{
+	struct tc_action_net *tn = net_generic(net, sample_net_id);
+
+	return tcf_idr_delete_index(tn, index);
+}
+
 static struct tc_action_ops act_sample_ops = {
 	.kind	  = "sample",
 	.type	  = TCA_ACT_SAMPLE,
@@ -229,6 +246,7 @@ static struct tc_action_ops act_sample_ops = {
 	.cleanup  = tcf_sample_cleanup,
 	.walk	  = tcf_sample_walker,
 	.lookup	  = tcf_sample_search,
+	.delete	  = tcf_sample_delete,
 	.size	  = sizeof(struct tcf_sample),
 };