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, 35 insertions, 19 deletions

diff --git a/net/sched/act_bpf.c b/net/sched/act_bpf.c
index 18089c02e557..9b30e62805c7 100644
--- a/net/sched/act_bpf.c
+++ b/net/sched/act_bpf.c
@@ -34,8 +34,8 @@ struct tcf_bpf_cfg {
 static unsigned int bpf_net_id;
 static struct tc_action_ops act_bpf_ops;
 
-static int tcf_bpf(struct sk_buff *skb, const struct tc_action *act,
-		   struct tcf_result *res)
+static int tcf_bpf_act(struct sk_buff *skb, const struct tc_action *act,
+		       struct tcf_result *res)
 {
 	bool at_ingress = skb_at_tc_ingress(skb);
 	struct tcf_bpf *prog = to_bpf(act);
@@ -141,13 +141,14 @@ static int tcf_bpf_dump(struct sk_buff *skb, struct tc_action *act,
 	struct tcf_bpf *prog = to_bpf(act);
 	struct tc_act_bpf opt = {
 		.index   = prog->tcf_index,
-		.refcnt  = prog->tcf_refcnt - ref,
-		.bindcnt = prog->tcf_bindcnt - bind,
-		.action  = prog->tcf_action,
+		.refcnt  = refcount_read(&prog->tcf_refcnt) - ref,
+		.bindcnt = atomic_read(&prog->tcf_bindcnt) - bind,
 	};
 	struct tcf_t tm;
 	int ret;
 
+	spin_lock(&prog->tcf_lock);
+	opt.action = prog->tcf_action;
 	if (nla_put(skb, TCA_ACT_BPF_PARMS, sizeof(opt), &opt))
 		goto nla_put_failure;
 
@@ -163,9 +164,11 @@ static int tcf_bpf_dump(struct sk_buff *skb, struct tc_action *act,
 			  TCA_ACT_BPF_PAD))
 		goto nla_put_failure;
 
+	spin_unlock(&prog->tcf_lock);
 	return skb->len;
 
 nla_put_failure:
+	spin_unlock(&prog->tcf_lock);
 	nlmsg_trim(skb, tp);
 	return -1;
 }
@@ -196,12 +199,10 @@ static int tcf_bpf_init_from_ops(struct nlattr **tb, struct tcf_bpf_cfg *cfg)
 	if (bpf_size != nla_len(tb[TCA_ACT_BPF_OPS]))
 		return -EINVAL;
 
-	bpf_ops = kzalloc(bpf_size, GFP_KERNEL);
+	bpf_ops = kmemdup(nla_data(tb[TCA_ACT_BPF_OPS]), bpf_size, GFP_KERNEL);
 	if (bpf_ops == NULL)
 		return -ENOMEM;
 
-	memcpy(bpf_ops, nla_data(tb[TCA_ACT_BPF_OPS]), bpf_size);
-
 	fprog_tmp.len = bpf_num_ops;
 	fprog_tmp.filter = bpf_ops;
 
@@ -266,7 +267,7 @@ static void tcf_bpf_prog_fill_cfg(const struct tcf_bpf *prog,
 {
 	cfg->is_ebpf = tcf_bpf_is_ebpf(prog);
 	/* updates to prog->filter are prevented, since it's called either
-	 * with rtnl lock or during final cleanup in rcu callback
+	 * with tcf lock or during final cleanup in rcu callback
 	 */
 	cfg->filter = rcu_dereference_protected(prog->filter, 1);
 
@@ -276,7 +277,8 @@ static void tcf_bpf_prog_fill_cfg(const struct tcf_bpf *prog,
 
 static int tcf_bpf_init(struct net *net, struct nlattr *nla,
 			struct nlattr *est, struct tc_action **act,
-			int replace, int bind, struct netlink_ext_ack *extack)
+			int replace, int bind, bool rtnl_held,
+			struct netlink_ext_ack *extack)
 {
 	struct tc_action_net *tn = net_generic(net, bpf_net_id);
 	struct nlattr *tb[TCA_ACT_BPF_MAX + 1];
@@ -298,21 +300,27 @@ static int tcf_bpf_init(struct net *net, struct nlattr *nla,
 
 	parm = nla_data(tb[TCA_ACT_BPF_PARMS]);
 
-	if (!tcf_idr_check(tn, parm->index, act, bind)) {
+	ret = tcf_idr_check_alloc(tn, &parm->index, act, bind);
+	if (!ret) {
 		ret = tcf_idr_create(tn, parm->index, est, act,
 				     &act_bpf_ops, bind, true);
-		if (ret < 0)
+		if (ret < 0) {
+			tcf_idr_cleanup(tn, parm->index);
 			return ret;
+		}
 
 		res = ACT_P_CREATED;
-	} else {
+	} else if (ret > 0) {
 		/* Don't override defaults. */
 		if (bind)
 			return 0;
 
-		tcf_idr_release(*act, bind);
-		if (!replace)
+		if (!replace) {
+			tcf_idr_release(*act, bind);
 			return -EEXIST;
+		}
+	} else {
+		return ret;
 	}
 
 	is_bpf = tb[TCA_ACT_BPF_OPS_LEN] && tb[TCA_ACT_BPF_OPS];
@@ -331,8 +339,8 @@ static int tcf_bpf_init(struct net *net, struct nlattr *nla,
 		goto out;
 
 	prog = to_bpf(*act);
-	ASSERT_RTNL();
 
+	spin_lock(&prog->tcf_lock);
 	if (res != ACT_P_CREATED)
 		tcf_bpf_prog_fill_cfg(prog, &old);
 
@@ -344,6 +352,7 @@ static int tcf_bpf_init(struct net *net, struct nlattr *nla,
 
 	prog->tcf_action = parm->action;
 	rcu_assign_pointer(prog->filter, cfg.filter);
+	spin_unlock(&prog->tcf_lock);
 
 	if (res == ACT_P_CREATED) {
 		tcf_idr_insert(tn, *act);
@@ -355,8 +364,7 @@ static int tcf_bpf_init(struct net *net, struct nlattr *nla,
 
 	return res;
 out:
-	if (res == ACT_P_CREATED)
-		tcf_idr_release(*act, bind);
+	tcf_idr_release(*act, bind);
 
 	return ret;
 }
@@ -387,16 +395,24 @@ static int tcf_bpf_search(struct net *net, struct tc_action **a, u32 index,
 	return tcf_idr_search(tn, a, index);
 }
 
+static int tcf_bpf_delete(struct net *net, u32 index)
+{
+	struct tc_action_net *tn = net_generic(net, bpf_net_id);
+
+	return tcf_idr_delete_index(tn, index);
+}
+
 static struct tc_action_ops act_bpf_ops __read_mostly = {
 	.kind		=	"bpf",
 	.type		=	TCA_ACT_BPF,
 	.owner		=	THIS_MODULE,
-	.act		=	tcf_bpf,
+	.act		=	tcf_bpf_act,
 	.dump		=	tcf_bpf_dump,
 	.cleanup	=	tcf_bpf_cleanup,
 	.init		=	tcf_bpf_init,
 	.walk		=	tcf_bpf_walker,
 	.lookup		=	tcf_bpf_search,
+	.delete		=	tcf_bpf_delete,
 	.size		=	sizeof(struct tcf_bpf),
 };