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

Pull networking updates from David Miller:
 "Highlights:

   1) Maintain the TCP retransmit queue using an rbtree, with 1GB
      windows at 100Gb this really has become necessary. From Eric
      Dumazet.

   2) Multi-program support for cgroup+bpf, from Alexei Starovoitov.

   3) Perform broadcast flooding in hardware in mv88e6xxx, from Andrew
      Lunn.

   4) Add meter action support to openvswitch, from Andy Zhou.

   5) Add a data meta pointer for BPF accessible packets, from Daniel
      Borkmann.

   6) Namespace-ify almost all TCP sysctl knobs, from Eric Dumazet.

   7) Turn on Broadcom Tags in b53 driver, from Florian Fainelli.

   8) More work to move the RTNL mutex down, from Florian Westphal.

   9) Add 'bpftool' utility, to help with bpf program introspection.
      From Jakub Kicinski.

  10) Add new 'cpumap' type for XDP_REDIRECT action, from Jesper
      Dangaard Brouer.

  11) Support 'blocks' of transformations in the packet scheduler which
      can span multiple network devices, from Jiri Pirko.

  12) TC flower offload support in cxgb4, from Kumar Sanghvi.

  13) Priority based stream scheduler for SCTP, from Marcelo Ricardo
      Leitner.

  14) Thunderbolt networking driver, from Amir Levy and Mika Westerberg.

  15) Add RED qdisc offloadability, and use it in mlxsw driver. From
      Nogah Frankel.

  16) eBPF based device controller for cgroup v2, from Roman Gushchin.

  17) Add some fundamental tracepoints for TCP, from Song Liu.

  18) Remove garbage collection from ipv6 route layer, this is a
      significant accomplishment. From Wei Wang.

  19) Add multicast route offload support to mlxsw, from Yotam Gigi"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (2177 commits)
  tcp: highest_sack fix
  geneve: fix fill_info when link down
  bpf: fix lockdep splat
  net: cdc_ncm: GetNtbFormat endian fix
  openvswitch: meter: fix NULL pointer dereference in ovs_meter_cmd_reply_start
  netem: remove unnecessary 64 bit modulus
  netem: use 64 bit divide by rate
  tcp: Namespace-ify sysctl_tcp_default_congestion_control
  net: Protect iterations over net::fib_notifier_ops in fib_seq_sum()
  ipv6: set all.accept_dad to 0 by default
  uapi: fix linux/tls.h userspace compilation error
  usbnet: ipheth: prevent TX queue timeouts when device not ready
  vhost_net: conditionally enable tx polling
  uapi: fix linux/rxrpc.h userspace compilation errors
  net: stmmac: fix LPI transitioning for dwmac4
  atm: horizon: Fix irq release error
  net-sysfs: trigger netlink notification on ifalias change via sysfs
  openvswitch: Using kfree_rcu() to simplify the code
  openvswitch: Make local function ovs_nsh_key_attr_size() static
  openvswitch: Fix return value check in ovs_meter_cmd_features()
  ...

1 files changed, 46 insertions, 44 deletions

diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c
index c3aec62..0dab33f 100644
--- a/net/openvswitch/datapath.c
+++ b/net/openvswitch/datapath.c
@@ -55,6 +55,7 @@
 #include "flow.h"
 #include "flow_table.h"
 #include "flow_netlink.h"
+#include "meter.h"
 #include "vport-internal_dev.h"
 #include "vport-netdev.h"
 
@@ -142,35 +143,6 @@ static int queue_userspace_packet(struct datapath *dp, struct sk_buff *,
 				  const struct dp_upcall_info *,
 				  uint32_t cutlen);
 
-/* Must be called with rcu_read_lock. */
-static struct datapath *get_dp_rcu(struct net *net, int dp_ifindex)
-{
-	struct net_device *dev = dev_get_by_index_rcu(net, dp_ifindex);
-
-	if (dev) {
-		struct vport *vport = ovs_internal_dev_get_vport(dev);
-		if (vport)
-			return vport->dp;
-	}
-
-	return NULL;
-}
-
-/* The caller must hold either ovs_mutex or rcu_read_lock to keep the
- * returned dp pointer valid.
- */
-static inline struct datapath *get_dp(struct net *net, int dp_ifindex)
-{
-	struct datapath *dp;
-
-	WARN_ON_ONCE(!rcu_read_lock_held() && !lockdep_ovsl_is_held());
-	rcu_read_lock();
-	dp = get_dp_rcu(net, dp_ifindex);
-	rcu_read_unlock();
-
-	return dp;
-}
-
 /* Must be called with rcu_read_lock or ovs_mutex. */
 const char *ovs_dp_name(const struct datapath *dp)
 {
@@ -203,6 +175,7 @@ static void destroy_dp_rcu(struct rcu_head *rcu)
 	ovs_flow_tbl_destroy(&dp->table);
 	free_percpu(dp->stats_percpu);
 	kfree(dp->ports);
+	ovs_meters_exit(dp);
 	kfree(dp);
 }
 
@@ -1601,6 +1574,10 @@ static int ovs_dp_cmd_new(struct sk_buff *skb, struct genl_info *info)
 	for (i = 0; i < DP_VPORT_HASH_BUCKETS; i++)
 		INIT_HLIST_HEAD(&dp->ports[i]);
 
+	err = ovs_meters_init(dp);
+	if (err)
+		goto err_destroy_ports_array;
+
 	/* Set up our datapath device. */
 	parms.name = nla_data(a[OVS_DP_ATTR_NAME]);
 	parms.type = OVS_VPORT_TYPE_INTERNAL;
@@ -1629,7 +1606,7 @@ static int ovs_dp_cmd_new(struct sk_buff *skb, struct genl_info *info)
 				ovs_dp_reset_user_features(skb, info);
 		}
 
-		goto err_destroy_ports_array;
+		goto err_destroy_meters;
 	}
 
 	err = ovs_dp_cmd_fill_info(dp, reply, info->snd_portid,
@@ -1644,8 +1621,10 @@ static int ovs_dp_cmd_new(struct sk_buff *skb, struct genl_info *info)
 	ovs_notify(&dp_datapath_genl_family, reply, info);
 	return 0;
 
-err_destroy_ports_array:
+err_destroy_meters:
 	ovs_unlock();
+	ovs_meters_exit(dp);
+err_destroy_ports_array:
 	kfree(dp->ports);
 err_destroy_percpu:
 	free_percpu(dp->stats_percpu);
@@ -1848,7 +1827,8 @@ static struct genl_family dp_datapath_genl_family __ro_after_init = {
 
 /* Called with ovs_mutex or RCU read lock. */
 static int ovs_vport_cmd_fill_info(struct vport *vport, struct sk_buff *skb,
-				   u32 portid, u32 seq, u32 flags, u8 cmd)
+				   struct net *net, u32 portid, u32 seq,
+				   u32 flags, u8 cmd)
 {
 	struct ovs_header *ovs_header;
 	struct ovs_vport_stats vport_stats;
@@ -1864,9 +1844,17 @@ static int ovs_vport_cmd_fill_info(struct vport *vport, struct sk_buff *skb,
 	if (nla_put_u32(skb, OVS_VPORT_ATTR_PORT_NO, vport->port_no) ||
 	    nla_put_u32(skb, OVS_VPORT_ATTR_TYPE, vport->ops->type) ||
 	    nla_put_string(skb, OVS_VPORT_ATTR_NAME,
-			   ovs_vport_name(vport)))
+			   ovs_vport_name(vport)) ||
+	    nla_put_u32(skb, OVS_VPORT_ATTR_IFINDEX, vport->dev->ifindex))
 		goto nla_put_failure;
 
+	if (!net_eq(net, dev_net(vport->dev))) {
+		int id = peernet2id_alloc(net, dev_net(vport->dev));
+
+		if (nla_put_s32(skb, OVS_VPORT_ATTR_NETNSID, id))
+			goto nla_put_failure;
+	}
+
 	ovs_vport_get_stats(vport, &vport_stats);
 	if (nla_put_64bit(skb, OVS_VPORT_ATTR_STATS,
 			  sizeof(struct ovs_vport_stats), &vport_stats,
@@ -1896,8 +1884,8 @@ static struct sk_buff *ovs_vport_cmd_alloc_info(void)
 }
 
 /* Called with ovs_mutex, only via ovs_dp_notify_wq(). */
-struct sk_buff *ovs_vport_cmd_build_info(struct vport *vport, u32 portid,
-					 u32 seq, u8 cmd)
+struct sk_buff *ovs_vport_cmd_build_info(struct vport *vport, struct net *net,
+					 u32 portid, u32 seq, u8 cmd)
 {
 	struct sk_buff *skb;
 	int retval;
@@ -1906,7 +1894,7 @@ struct sk_buff *ovs_vport_cmd_build_info(struct vport *vport, u32 portid,
 	if (!skb)
 		return ERR_PTR(-ENOMEM);
 
-	retval = ovs_vport_cmd_fill_info(vport, skb, portid, seq, 0, cmd);
+	retval = ovs_vport_cmd_fill_info(vport, skb, net, portid, seq, 0, cmd);
 	BUG_ON(retval < 0);
 
 	return skb;
@@ -1920,6 +1908,8 @@ static struct vport *lookup_vport(struct net *net,
 	struct datapath *dp;
 	struct vport *vport;
 
+	if (a[OVS_VPORT_ATTR_IFINDEX])
+		return ERR_PTR(-EOPNOTSUPP);
 	if (a[OVS_VPORT_ATTR_NAME]) {
 		vport = ovs_vport_locate(net, nla_data(a[OVS_VPORT_ATTR_NAME]));
 		if (!vport)
@@ -1944,6 +1934,7 @@ static struct vport *lookup_vport(struct net *net,
 		return vport;
 	} else
 		return ERR_PTR(-EINVAL);
+
 }
 
 /* Called with ovs_mutex */
@@ -1983,6 +1974,8 @@ static int ovs_vport_cmd_new(struct sk_buff *skb, struct genl_info *info)
 	if (!a[OVS_VPORT_ATTR_NAME] || !a[OVS_VPORT_ATTR_TYPE] ||
 	    !a[OVS_VPORT_ATTR_UPCALL_PID])
 		return -EINVAL;
+	if (a[OVS_VPORT_ATTR_IFINDEX])
+		return -EOPNOTSUPP;
 
 	port_no = a[OVS_VPORT_ATTR_PORT_NO]
 		? nla_get_u32(a[OVS_VPORT_ATTR_PORT_NO]) : 0;
@@ -2032,8 +2025,9 @@ restart:
 		goto exit_unlock_free;
 	}
 
-	err = ovs_vport_cmd_fill_info(vport, reply, info->snd_portid,
-				      info->snd_seq, 0, OVS_VPORT_CMD_NEW);
+	err = ovs_vport_cmd_fill_info(vport, reply, genl_info_net(info),
+				      info->snd_portid, info->snd_seq, 0,
+				      OVS_VPORT_CMD_NEW);
 
 	if (netdev_get_fwd_headroom(vport->dev) > dp->max_headroom)
 		update_headroom(dp);
@@ -2090,8 +2084,9 @@ static int ovs_vport_cmd_set(struct sk_buff *skb, struct genl_info *info)
 			goto exit_unlock_free;
 	}
 
-	err = ovs_vport_cmd_fill_info(vport, reply, info->snd_portid,
-				      info->snd_seq, 0, OVS_VPORT_CMD_NEW);
+	err = ovs_vport_cmd_fill_info(vport, reply, genl_info_net(info),
+				      info->snd_portid, info->snd_seq, 0,
+				      OVS_VPORT_CMD_NEW);
 	BUG_ON(err < 0);
 
 	ovs_unlock();
@@ -2128,8 +2123,9 @@ static int ovs_vport_cmd_del(struct sk_buff *skb, struct genl_info *info)
 		goto exit_unlock_free;
 	}
 
-	err = ovs_vport_cmd_fill_info(vport, reply, info->snd_portid,
-				      info->snd_seq, 0, OVS_VPORT_CMD_DEL);
+	err = ovs_vport_cmd_fill_info(vport, reply, genl_info_net(info),
+				      info->snd_portid, info->snd_seq, 0,
+				      OVS_VPORT_CMD_DEL);
 	BUG_ON(err < 0);
 
 	/* the vport deletion may trigger dp headroom update */
@@ -2169,8 +2165,9 @@ static int ovs_vport_cmd_get(struct sk_buff *skb, struct genl_info *info)
 	err = PTR_ERR(vport);
 	if (IS_ERR(vport))
 		goto exit_unlock_free;
-	err = ovs_vport_cmd_fill_info(vport, reply, info->snd_portid,
-				      info->snd_seq, 0, OVS_VPORT_CMD_NEW);
+	err = ovs_vport_cmd_fill_info(vport, reply, genl_info_net(info),
+				      info->snd_portid, info->snd_seq, 0,
+				      OVS_VPORT_CMD_NEW);
 	BUG_ON(err < 0);
 	rcu_read_unlock();
 
@@ -2202,6 +2199,7 @@ static int ovs_vport_cmd_dump(struct sk_buff *skb, struct netlink_callback *cb)
 		hlist_for_each_entry_rcu(vport, &dp->ports[i], dp_hash_node) {
 			if (j >= skip &&
 			    ovs_vport_cmd_fill_info(vport, skb,
+						    sock_net(skb->sk),
 						    NETLINK_CB(cb->skb).portid,
 						    cb->nlh->nlmsg_seq,
 						    NLM_F_MULTI,
@@ -2228,6 +2226,8 @@ static const struct nla_policy vport_policy[OVS_VPORT_ATTR_MAX + 1] = {
 	[OVS_VPORT_ATTR_TYPE] = { .type = NLA_U32 },
 	[OVS_VPORT_ATTR_UPCALL_PID] = { .type = NLA_U32 },
 	[OVS_VPORT_ATTR_OPTIONS] = { .type = NLA_NESTED },
+	[OVS_VPORT_ATTR_IFINDEX] = { .type = NLA_U32 },
+	[OVS_VPORT_ATTR_NETNSID] = { .type = NLA_S32 },
 };
 
 static const struct genl_ops dp_vport_genl_ops[] = {
@@ -2273,6 +2273,7 @@ static struct genl_family * const dp_genl_families[] = {
 	&dp_vport_genl_family,
 	&dp_flow_genl_family,
 	&dp_packet_genl_family,
+	&dp_meter_genl_family,
 };
 
 static void dp_unregister_genl(int n_families)
@@ -2453,3 +2454,4 @@ MODULE_ALIAS_GENL_FAMILY(OVS_DATAPATH_FAMILY);
 MODULE_ALIAS_GENL_FAMILY(OVS_VPORT_FAMILY);
 MODULE_ALIAS_GENL_FAMILY(OVS_FLOW_FAMILY);
 MODULE_ALIAS_GENL_FAMILY(OVS_PACKET_FAMILY);
+MODULE_ALIAS_GENL_FAMILY(OVS_METER_FAMILY);