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

Pull networking updates from David Miller:

 1) Support offloading wireless authentication to userspace via
    NL80211_CMD_EXTERNAL_AUTH, from Srinivas Dasari.

 2) A lot of work on network namespace setup/teardown from Kirill Tkhai.
    Setup and cleanup of namespaces now all run asynchronously and thus
    performance is significantly increased.

 3) Add rx/tx timestamping support to mv88e6xxx driver, from Brandon
    Streiff.

 4) Support zerocopy on RDS sockets, from Sowmini Varadhan.

 5) Use denser instruction encoding in x86 eBPF JIT, from Daniel
    Borkmann.

 6) Support hw offload of vlan filtering in mvpp2 dreiver, from Maxime
    Chevallier.

 7) Support grafting of child qdiscs in mlxsw driver, from Nogah
    Frankel.

 8) Add packet forwarding tests to selftests, from Ido Schimmel.

 9) Deal with sub-optimal GSO packets better in BBR congestion control,
    from Eric Dumazet.

10) Support 5-tuple hashing in ipv6 multipath routing, from David Ahern.

11) Add path MTU tests to selftests, from Stefano Brivio.

12) Various bits of IPSEC offloading support for mlx5, from Aviad
    Yehezkel, Yossi Kuperman, and Saeed Mahameed.

13) Support RSS spreading on ntuple filters in SFC driver, from Edward
    Cree.

14) Lots of sockmap work from John Fastabend. Applications can use eBPF
    to filter sendmsg and sendpage operations.

15) In-kernel receive TLS support, from Dave Watson.

16) Add XDP support to ixgbevf, this is significant because it should
    allow optimized XDP usage in various cloud environments. From Tony
    Nguyen.

17) Add new Intel E800 series "ice" ethernet driver, from Anirudh
    Venkataramanan et al.

18) IP fragmentation match offload support in nfp driver, from Pieter
    Jansen van Vuuren.

19) Support XDP redirect in i40e driver, from Björn Töpel.

20) Add BPF_RAW_TRACEPOINT program type for accessing the arguments of
    tracepoints in their raw form, from Alexei Starovoitov.

21) Lots of striding RQ improvements to mlx5 driver with many
    performance improvements, from Tariq Toukan.

22) Use rhashtable for inet frag reassembly, from Eric Dumazet.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1678 commits)
  net: mvneta: improve suspend/resume
  net: mvneta: split rxq/txq init and txq deinit into SW and HW parts
  ipv6: frags: fix /proc/sys/net/ipv6/ip6frag_low_thresh
  net: bgmac: Fix endian access in bgmac_dma_tx_ring_free()
  net: bgmac: Correctly annotate register space
  route: check sysctl_fib_multipath_use_neigh earlier than hash
  fix typo in command value in drivers/net/phy/mdio-bitbang.
  sky2: Increase D3 delay to sky2 stops working after suspend
  net/mlx5e: Set EQE based as default TX interrupt moderation mode
  ibmvnic: Disable irqs before exiting reset from closed state
  net: sched: do not emit messages while holding spinlock
  vlan: also check phy_driver ts_info for vlan's real device
  Bluetooth: Mark expected switch fall-throughs
  Bluetooth: Set HCI_QUIRK_SIMULTANEOUS_DISCOVERY for BTUSB_QCA_ROME
  Bluetooth: btrsi: remove unused including <linux/version.h>
  Bluetooth: hci_bcm: Remove DMI quirk for the MINIX Z83-4
  sh_eth: kill useless check in __sh_eth_get_regs()
  sh_eth: add sh_eth_cpu_data::no_xdfar flag
  ipv6: factorize sk_wmem_alloc updates done by __ip6_append_data()
  ipv4: factorize sk_wmem_alloc updates done by __ip_append_data()
  ...

1 files changed, 136 insertions, 51 deletions

diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index 7dfa9fc99ec3..3e5eba30865e 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -289,10 +289,9 @@ static bool tipc_sk_type_connectionless(struct sock *sk)
 static bool tsk_peer_msg(struct tipc_sock *tsk, struct tipc_msg *msg)
 {
 	struct sock *sk = &tsk->sk;
-	struct tipc_net *tn = net_generic(sock_net(sk), tipc_net_id);
+	u32 self = tipc_own_addr(sock_net(sk));
 	u32 peer_port = tsk_peer_port(tsk);
-	u32 orig_node;
-	u32 peer_node;
+	u32 orig_node, peer_node;
 
 	if (unlikely(!tipc_sk_connected(sk)))
 		return false;
@@ -306,10 +305,10 @@ static bool tsk_peer_msg(struct tipc_sock *tsk, struct tipc_msg *msg)
 	if (likely(orig_node == peer_node))
 		return true;
 
-	if (!orig_node && (peer_node == tn->own_addr))
+	if (!orig_node && peer_node == self)
 		return true;
 
-	if (!peer_node && (orig_node == tn->own_addr))
+	if (!peer_node && orig_node == self)
 		return true;
 
 	return false;
@@ -461,8 +460,8 @@ static int tipc_sk_create(struct net *net, struct socket *sock,
 	/* Ensure tsk is visible before we read own_addr. */
 	smp_mb();
 
-	tipc_msg_init(tn->own_addr, msg, TIPC_LOW_IMPORTANCE, TIPC_NAMED_MSG,
-		      NAMED_H_SIZE, 0);
+	tipc_msg_init(tipc_own_addr(net), msg, TIPC_LOW_IMPORTANCE,
+		      TIPC_NAMED_MSG, NAMED_H_SIZE, 0);
 
 	msg_set_origport(msg, tsk->portid);
 	timer_setup(&sk->sk_timer, tipc_sk_timeout, 0);
@@ -644,7 +643,7 @@ static int tipc_bind(struct socket *sock, struct sockaddr *uaddr,
 		goto exit;
 	}
 
-	res = (addr->scope > 0) ?
+	res = (addr->scope >= 0) ?
 		tipc_sk_publish(tsk, addr->scope, &addr->addr.nameseq) :
 		tipc_sk_withdraw(tsk, -addr->scope, &addr->addr.nameseq);
 exit:
@@ -666,12 +665,11 @@ exit:
  *       a completely predictable manner).
  */
 static int tipc_getname(struct socket *sock, struct sockaddr *uaddr,
-			int *uaddr_len, int peer)
+			int peer)
 {
 	struct sockaddr_tipc *addr = (struct sockaddr_tipc *)uaddr;
 	struct sock *sk = sock->sk;
 	struct tipc_sock *tsk = tipc_sk(sk);
-	struct tipc_net *tn = net_generic(sock_net(sock->sk), tipc_net_id);
 
 	memset(addr, 0, sizeof(*addr));
 	if (peer) {
@@ -682,16 +680,15 @@ static int tipc_getname(struct socket *sock, struct sockaddr *uaddr,
 		addr->addr.id.node = tsk_peer_node(tsk);
 	} else {
 		addr->addr.id.ref = tsk->portid;
-		addr->addr.id.node = tn->own_addr;
+		addr->addr.id.node = tipc_own_addr(sock_net(sk));
 	}
 
-	*uaddr_len = sizeof(*addr);
 	addr->addrtype = TIPC_ADDR_ID;
 	addr->family = AF_TIPC;
 	addr->scope = 0;
 	addr->addr.name.domain = 0;
 
-	return 0;
+	return sizeof(*addr);
 }
 
 /**
@@ -1281,8 +1278,8 @@ static int __tipc_sendmsg(struct socket *sock, struct msghdr *m, size_t dlen)
 	struct tipc_msg *hdr = &tsk->phdr;
 	struct tipc_name_seq *seq;
 	struct sk_buff_head pkts;
-	u32 type, inst, domain;
 	u32 dnode, dport;
+	u32 type, inst;
 	int mtu, rc;
 
 	if (unlikely(dlen > TIPC_MAX_USER_MSG_SIZE))
@@ -1333,13 +1330,12 @@ static int __tipc_sendmsg(struct socket *sock, struct msghdr *m, size_t dlen)
 	if (dest->addrtype == TIPC_ADDR_NAME) {
 		type = dest->addr.name.name.type;
 		inst = dest->addr.name.name.instance;
-		domain = dest->addr.name.domain;
-		dnode = domain;
+		dnode = dest->addr.name.domain;
 		msg_set_type(hdr, TIPC_NAMED_MSG);
 		msg_set_hdr_sz(hdr, NAMED_H_SIZE);
 		msg_set_nametype(hdr, type);
 		msg_set_nameinst(hdr, inst);
-		msg_set_lookup_scope(hdr, tipc_addr_scope(domain));
+		msg_set_lookup_scope(hdr, tipc_node2scope(dnode));
 		dport = tipc_nametbl_translate(net, type, inst, &dnode);
 		msg_set_destnode(hdr, dnode);
 		msg_set_destport(hdr, dport);
@@ -2124,8 +2120,10 @@ static void tipc_sk_filter_rcv(struct sock *sk, struct sk_buff *skb,
 		    (!sk_conn && msg_connected(hdr)) ||
 		    (!grp && msg_in_group(hdr)))
 			err = TIPC_ERR_NO_PORT;
-		else if (sk_rmem_alloc_get(sk) + skb->truesize >= limit)
+		else if (sk_rmem_alloc_get(sk) + skb->truesize >= limit) {
+			atomic_inc(&sk->sk_drops);
 			err = TIPC_ERR_OVERLOAD;
+		}
 
 		if (unlikely(err)) {
 			tipc_skb_reject(net, err, skb, xmitq);
@@ -2204,6 +2202,7 @@ static void tipc_sk_enqueue(struct sk_buff_head *inputq, struct sock *sk,
 
 		/* Overload => reject message back to sender */
 		onode = tipc_own_addr(sock_net(sk));
+		atomic_inc(&sk->sk_drops);
 		if (tipc_msg_reverse(onode, &skb, TIPC_ERR_OVERLOAD))
 			__skb_queue_tail(xmitq, skb);
 		break;
@@ -2593,6 +2592,9 @@ static int tipc_sk_publish(struct tipc_sock *tsk, uint scope,
 	struct publication *publ;
 	u32 key;
 
+	if (scope != TIPC_NODE_SCOPE)
+		scope = TIPC_CLUSTER_SCOPE;
+
 	if (tipc_sk_connected(sk))
 		return -EINVAL;
 	key = tsk->portid + tsk->pub_count + 1;
@@ -2604,7 +2606,7 @@ static int tipc_sk_publish(struct tipc_sock *tsk, uint scope,
 	if (unlikely(!publ))
 		return -EINVAL;
 
-	list_add(&publ->pport_list, &tsk->publications);
+	list_add(&publ->binding_sock, &tsk->publications);
 	tsk->pub_count++;
 	tsk->published = 1;
 	return 0;
@@ -2618,7 +2620,10 @@ static int tipc_sk_withdraw(struct tipc_sock *tsk, uint scope,
 	struct publication *safe;
 	int rc = -EINVAL;
 
-	list_for_each_entry_safe(publ, safe, &tsk->publications, pport_list) {
+	if (scope != TIPC_NODE_SCOPE)
+		scope = TIPC_CLUSTER_SCOPE;
+
+	list_for_each_entry_safe(publ, safe, &tsk->publications, binding_sock) {
 		if (seq) {
 			if (publ->scope != scope)
 				continue;
@@ -2629,12 +2634,12 @@ static int tipc_sk_withdraw(struct tipc_sock *tsk, uint scope,
 			if (publ->upper != seq->upper)
 				break;
 			tipc_nametbl_withdraw(net, publ->type, publ->lower,
-					      publ->ref, publ->key);
+					      publ->upper, publ->key);
 			rc = 0;
 			break;
 		}
 		tipc_nametbl_withdraw(net, publ->type, publ->lower,
-				      publ->ref, publ->key);
+				      publ->upper, publ->key);
 		rc = 0;
 	}
 	if (list_empty(&tsk->publications))
@@ -2660,8 +2665,8 @@ void tipc_sk_reinit(struct net *net)
 		while ((tsk = rhashtable_walk_next(&iter)) && !IS_ERR(tsk)) {
 			spin_lock_bh(&tsk->sk.sk_lock.slock);
 			msg = &tsk->phdr;
-			msg_set_prevnode(msg, tn->own_addr);
-			msg_set_orignode(msg, tn->own_addr);
+			msg_set_prevnode(msg, tipc_own_addr(net));
+			msg_set_orignode(msg, tipc_own_addr(net));
 			spin_unlock_bh(&tsk->sk.sk_lock.slock);
 		}
 
@@ -3156,16 +3161,32 @@ msg_full:
 	return -EMSGSIZE;
 }
 
+static int __tipc_nl_add_sk_info(struct sk_buff *skb, struct tipc_sock
+			  *tsk)
+{
+	struct net *net = sock_net(skb->sk);
+	struct sock *sk = &tsk->sk;
+
+	if (nla_put_u32(skb, TIPC_NLA_SOCK_REF, tsk->portid) ||
+	    nla_put_u32(skb, TIPC_NLA_SOCK_ADDR, tipc_own_addr(net)))
+		return -EMSGSIZE;
+
+	if (tipc_sk_connected(sk)) {
+		if (__tipc_nl_add_sk_con(skb, tsk))
+			return -EMSGSIZE;
+	} else if (!list_empty(&tsk->publications)) {
+		if (nla_put_flag(skb, TIPC_NLA_SOCK_HAS_PUBL))
+			return -EMSGSIZE;
+	}
+	return 0;
+}
+
 /* Caller should hold socket lock for the passed tipc socket. */
 static int __tipc_nl_add_sk(struct sk_buff *skb, struct netlink_callback *cb,
 			    struct tipc_sock *tsk)
 {
-	int err;
-	void *hdr;
 	struct nlattr *attrs;
-	struct net *net = sock_net(skb->sk);
-	struct tipc_net *tn = net_generic(net, tipc_net_id);
-	struct sock *sk = &tsk->sk;
+	void *hdr;
 
 	hdr = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq,
 			  &tipc_genl_family, NLM_F_MULTI, TIPC_NL_SOCK_GET);
@@ -3175,19 +3196,10 @@ static int __tipc_nl_add_sk(struct sk_buff *skb, struct netlink_callback *cb,
 	attrs = nla_nest_start(skb, TIPC_NLA_SOCK);
 	if (!attrs)
 		goto genlmsg_cancel;
-	if (nla_put_u32(skb, TIPC_NLA_SOCK_REF, tsk->portid))
-		goto attr_msg_cancel;
-	if (nla_put_u32(skb, TIPC_NLA_SOCK_ADDR, tn->own_addr))
+
+	if (__tipc_nl_add_sk_info(skb, tsk))
 		goto attr_msg_cancel;
 
-	if (tipc_sk_connected(sk)) {
-		err = __tipc_nl_add_sk_con(skb, tsk);
-		if (err)
-			goto attr_msg_cancel;
-	} else if (!list_empty(&tsk->publications)) {
-		if (nla_put_flag(skb, TIPC_NLA_SOCK_HAS_PUBL))
-			goto attr_msg_cancel;
-	}
 	nla_nest_end(skb, attrs);
 	genlmsg_end(skb, hdr);
 
@@ -3201,16 +3213,19 @@ msg_cancel:
 	return -EMSGSIZE;
 }
 
-int tipc_nl_sk_dump(struct sk_buff *skb, struct netlink_callback *cb)
+int tipc_nl_sk_walk(struct sk_buff *skb, struct netlink_callback *cb,
+		    int (*skb_handler)(struct sk_buff *skb,
+				       struct netlink_callback *cb,
+				       struct tipc_sock *tsk))
 {
-	int err;
-	struct tipc_sock *tsk;
-	const struct bucket_table *tbl;
-	struct rhash_head *pos;
 	struct net *net = sock_net(skb->sk);
-	struct tipc_net *tn = net_generic(net, tipc_net_id);
-	u32 tbl_id = cb->args[0];
+	struct tipc_net *tn = tipc_net(net);
+	const struct bucket_table *tbl;
 	u32 prev_portid = cb->args[1];
+	u32 tbl_id = cb->args[0];
+	struct rhash_head *pos;
+	struct tipc_sock *tsk;
+	int err;
 
 	rcu_read_lock();
 	tbl = rht_dereference_rcu((&tn->sk_rht)->tbl, &tn->sk_rht);
@@ -3222,12 +3237,13 @@ int tipc_nl_sk_dump(struct sk_buff *skb, struct netlink_callback *cb)
 				continue;
 			}
 
-			err = __tipc_nl_add_sk(skb, cb, tsk);
+			err = skb_handler(skb, cb, tsk);
 			if (err) {
 				prev_portid = tsk->portid;
 				spin_unlock_bh(&tsk->sk.sk_lock.slock);
 				goto out;
 			}
+
 			prev_portid = 0;
 			spin_unlock_bh(&tsk->sk.sk_lock.slock);
 		}
@@ -3239,6 +3255,75 @@ out:
 
 	return skb->len;
 }
+EXPORT_SYMBOL(tipc_nl_sk_walk);
+
+int tipc_sk_fill_sock_diag(struct sk_buff *skb, struct tipc_sock *tsk,
+			   u32 sk_filter_state,
+			   u64 (*tipc_diag_gen_cookie)(struct sock *sk))
+{
+	struct sock *sk = &tsk->sk;
+	struct nlattr *attrs;
+	struct nlattr *stat;
+
+	/*filter response w.r.t sk_state*/
+	if (!(sk_filter_state & (1 << sk->sk_state)))
+		return 0;
+
+	attrs = nla_nest_start(skb, TIPC_NLA_SOCK);
+	if (!attrs)
+		goto msg_cancel;
+
+	if (__tipc_nl_add_sk_info(skb, tsk))
+		goto attr_msg_cancel;
+
+	if (nla_put_u32(skb, TIPC_NLA_SOCK_TYPE, (u32)sk->sk_type) ||
+	    nla_put_u32(skb, TIPC_NLA_SOCK_TIPC_STATE, (u32)sk->sk_state) ||
+	    nla_put_u32(skb, TIPC_NLA_SOCK_INO, sock_i_ino(sk)) ||
+	    nla_put_u32(skb, TIPC_NLA_SOCK_UID,
+			from_kuid_munged(sk_user_ns(sk), sock_i_uid(sk))) ||
+	    nla_put_u64_64bit(skb, TIPC_NLA_SOCK_COOKIE,
+			      tipc_diag_gen_cookie(sk),
+			      TIPC_NLA_SOCK_PAD))
+		goto attr_msg_cancel;
+
+	stat = nla_nest_start(skb, TIPC_NLA_SOCK_STAT);
+	if (!stat)
+		goto attr_msg_cancel;
+
+	if (nla_put_u32(skb, TIPC_NLA_SOCK_STAT_RCVQ,
+			skb_queue_len(&sk->sk_receive_queue)) ||
+	    nla_put_u32(skb, TIPC_NLA_SOCK_STAT_SENDQ,
+			skb_queue_len(&sk->sk_write_queue)) ||
+	    nla_put_u32(skb, TIPC_NLA_SOCK_STAT_DROP,
+			atomic_read(&sk->sk_drops)))
+		goto stat_msg_cancel;
+
+	if (tsk->cong_link_cnt &&
+	    nla_put_flag(skb, TIPC_NLA_SOCK_STAT_LINK_CONG))
+		goto stat_msg_cancel;
+
+	if (tsk_conn_cong(tsk) &&
+	    nla_put_flag(skb, TIPC_NLA_SOCK_STAT_CONN_CONG))
+		goto stat_msg_cancel;
+
+	nla_nest_end(skb, stat);
+	nla_nest_end(skb, attrs);
+
+	return 0;
+
+stat_msg_cancel:
+	nla_nest_cancel(skb, stat);
+attr_msg_cancel:
+	nla_nest_cancel(skb, attrs);
+msg_cancel:
+	return -EMSGSIZE;
+}
+EXPORT_SYMBOL(tipc_sk_fill_sock_diag);
+
+int tipc_nl_sk_dump(struct sk_buff *skb, struct netlink_callback *cb)
+{
+	return tipc_nl_sk_walk(skb, cb, __tipc_nl_add_sk);
+}
 
 /* Caller should hold socket lock for the passed tipc socket. */
 static int __tipc_nl_add_sk_publ(struct sk_buff *skb,
@@ -3288,7 +3373,7 @@ static int __tipc_nl_list_sk_publ(struct sk_buff *skb,
 	struct publication *p;
 
 	if (*last_publ) {
-		list_for_each_entry(p, &tsk->publications, pport_list) {
+		list_for_each_entry(p, &tsk->publications, binding_sock) {
 			if (p->key == *last_publ)
 				break;
 		}
@@ -3305,10 +3390,10 @@ static int __tipc_nl_list_sk_publ(struct sk_buff *skb,
 		}
 	} else {
 		p = list_first_entry(&tsk->publications, struct publication,
-				     pport_list);
+				     binding_sock);
 	}
 
-	list_for_each_entry_from(p, &tsk->publications, pport_list) {
+	list_for_each_entry_from(p, &tsk->publications, binding_sock) {
 		err = __tipc_nl_add_sk_publ(skb, cb, p);
 		if (err) {
 			*last_publ = p->key;