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

Pull networking updates from David Miller:

Changes of note:

 1) Allow to schedule ICMP packets in IPVS, from Alex Gartrell.

 2) Provide FIB table ID in ipv4 route dumps just as ipv6 does, from
    David Ahern.

 3) Allow the user to ask for the statistics to be filtered out of
    ipv4/ipv6 address netlink dumps.  From Sowmini Varadhan.

 4) More work to pass the network namespace context around deep into
    various packet path APIs, starting with the netfilter hooks.  From
    Eric W Biederman.

 5) Add layer 2 TX/RX checksum offloading to qeth driver, from Thomas
    Richter.

 6) Use usec resolution for SYN/ACK RTTs in TCP, from Yuchung Cheng.

 7) Support Very High Throughput in wireless MESH code, from Bob
    Copeland.

 8) Allow setting the ageing_time in switchdev/rocker.  From Scott
    Feldman.

 9) Properly autoload L2TP type modules, from Stephen Hemminger.

10) Fix and enable offload features by default in 8139cp driver, from
    David Woodhouse.

11) Support both ipv4 and ipv6 sockets in a single vxlan device, from
    Jiri Benc.

12) Fix CWND limiting of thin streams in TCP, from Bendik Rønning
    Opstad.

13) Fix IPSEC flowcache overflows on large systems, from Steffen
    Klassert.

14) Convert bridging to track VLANs using rhashtable entries rather than
    a bitmap.  From Nikolay Aleksandrov.

15) Make TCP listener handling completely lockless, this is a major
    accomplishment.  Incoming request sockets now live in the
    established hash table just like any other socket too.

    From Eric Dumazet.

15) Provide more bridging attributes to netlink, from Nikolay
    Aleksandrov.

16) Use hash based algorithm for ipv4 multipath routing, this was very
    long overdue.  From Peter Nørlund.

17) Several y2038 cures, mostly avoiding timespec.  From Arnd Bergmann.

18) Allow non-root execution of EBPF programs, from Alexei Starovoitov.

19) Support SO_INCOMING_CPU as setsockopt, from Eric Dumazet.  This
    influences the port binding selection logic used by SO_REUSEPORT.

20) Add ipv6 support to VRF, from David Ahern.

21) Add support for Mellanox Spectrum switch ASIC, from Jiri Pirko.

22) Add rtl8xxxu Realtek wireless driver, from Jes Sorensen.

23) Implement RACK loss recovery in TCP, from Yuchung Cheng.

24) Support multipath routes in MPLS, from Roopa Prabhu.

25) Fix POLLOUT notification for listening sockets in AF_UNIX, from Eric
    Dumazet.

26) Add new QED Qlogic river, from Yuval Mintz, Manish Chopra, and
    Sudarsana Kalluru.

27) Don't fetch timestamps on AF_UNIX sockets, from Hannes Frederic
    Sowa.

28) Support ipv6 geneve tunnels, from John W Linville.

29) Add flood control support to switchdev layer, from Ido Schimmel.

30) Fix CHECKSUM_PARTIAL handling of potentially fragmented frames, from
    Hannes Frederic Sowa.

31) Support persistent maps and progs in bpf, from Daniel Borkmann.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1790 commits)
  sh_eth: use DMA barriers
  switchdev: respect SKIP_EOPNOTSUPP flag in case there is no recursion
  net: sched: kill dead code in sch_choke.c
  irda: Delete an unnecessary check before the function call "irlmp_unregister_service"
  net: dsa: mv88e6xxx: include DSA ports in VLANs
  net: dsa: mv88e6xxx: disable SA learning for DSA and CPU ports
  net/core: fix for_each_netdev_feature
  vlan: Invoke driver vlan hooks only if device is present
  arcnet/com20020: add LEDS_CLASS dependency
  bpf, verifier: annotate verbose printer with __printf
  dp83640: Only wait for timestamps for packets with timestamping enabled.
  ptp: Change ptp_class to a proper bitmask
  dp83640: Prune rx timestamp list before reading from it
  dp83640: Delay scheduled work.
  dp83640: Include hash in timestamp/packet matching
  ipv6: fix tunnel error handling
  net/mlx5e: Fix LSO vlan insertion
  net/mlx5e: Re-eanble client vlan TX acceleration
  net/mlx5e: Return error in case mlx5e_set_features() fails
  net/mlx5e: Don't allow more than max supported channels
  ...

1 files changed, 124 insertions, 147 deletions

diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 61b45a17fc73..1feb15f23de8 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -330,14 +330,12 @@ struct sock *inet_csk_accept(struct sock *sk, int flags, int *err)
 		if (error)
 			goto out_err;
 	}
-	req = reqsk_queue_remove(queue);
+	req = reqsk_queue_remove(queue, sk);
 	newsk = req->sk;
 
-	sk_acceptq_removed(sk);
 	if (sk->sk_protocol == IPPROTO_TCP &&
-	    tcp_rsk(req)->tfo_listener &&
-	    queue->fastopenq) {
-		spin_lock_bh(&queue->fastopenq->lock);
+	    tcp_rsk(req)->tfo_listener) {
+		spin_lock_bh(&queue->fastopenq.lock);
 		if (tcp_rsk(req)->tfo_listener) {
 			/* We are still waiting for the final ACK from 3WHS
 			 * so can't free req now. Instead, we set req->sk to
@@ -348,7 +346,7 @@ struct sock *inet_csk_accept(struct sock *sk, int flags, int *err)
 			req->sk = NULL;
 			req = NULL;
 		}
-		spin_unlock_bh(&queue->fastopenq->lock);
+		spin_unlock_bh(&queue->fastopenq.lock);
 	}
 out:
 	release_sock(sk);
@@ -408,7 +406,7 @@ void inet_csk_reset_keepalive_timer(struct sock *sk, unsigned long len)
 }
 EXPORT_SYMBOL(inet_csk_reset_keepalive_timer);
 
-struct dst_entry *inet_csk_route_req(struct sock *sk,
+struct dst_entry *inet_csk_route_req(const struct sock *sk,
 				     struct flowi4 *fl4,
 				     const struct request_sock *req)
 {
@@ -439,7 +437,7 @@ no_route:
 }
 EXPORT_SYMBOL_GPL(inet_csk_route_req);
 
-struct dst_entry *inet_csk_route_child_sock(struct sock *sk,
+struct dst_entry *inet_csk_route_child_sock(const struct sock *sk,
 					    struct sock *newsk,
 					    const struct request_sock *req)
 {
@@ -478,65 +476,12 @@ no_route:
 }
 EXPORT_SYMBOL_GPL(inet_csk_route_child_sock);
 
-static inline u32 inet_synq_hash(const __be32 raddr, const __be16 rport,
-				 const u32 rnd, const u32 synq_hsize)
-{
-	return jhash_2words((__force u32)raddr, (__force u32)rport, rnd) & (synq_hsize - 1);
-}
-
 #if IS_ENABLED(CONFIG_IPV6)
 #define AF_INET_FAMILY(fam) ((fam) == AF_INET)
 #else
 #define AF_INET_FAMILY(fam) true
 #endif
 
-/* Note: this is temporary :
- * req sock will no longer be in listener hash table
-*/
-struct request_sock *inet_csk_search_req(struct sock *sk,
-					 const __be16 rport,
-					 const __be32 raddr,
-					 const __be32 laddr)
-{
-	struct inet_connection_sock *icsk = inet_csk(sk);
-	struct listen_sock *lopt = icsk->icsk_accept_queue.listen_opt;
-	struct request_sock *req;
-	u32 hash = inet_synq_hash(raddr, rport, lopt->hash_rnd,
-				  lopt->nr_table_entries);
-
-	spin_lock(&icsk->icsk_accept_queue.syn_wait_lock);
-	for (req = lopt->syn_table[hash]; req != NULL; req = req->dl_next) {
-		const struct inet_request_sock *ireq = inet_rsk(req);
-
-		if (ireq->ir_rmt_port == rport &&
-		    ireq->ir_rmt_addr == raddr &&
-		    ireq->ir_loc_addr == laddr &&
-		    AF_INET_FAMILY(req->rsk_ops->family)) {
-			atomic_inc(&req->rsk_refcnt);
-			WARN_ON(req->sk);
-			break;
-		}
-	}
-	spin_unlock(&icsk->icsk_accept_queue.syn_wait_lock);
-
-	return req;
-}
-EXPORT_SYMBOL_GPL(inet_csk_search_req);
-
-void inet_csk_reqsk_queue_hash_add(struct sock *sk, struct request_sock *req,
-				   unsigned long timeout)
-{
-	struct inet_connection_sock *icsk = inet_csk(sk);
-	struct listen_sock *lopt = icsk->icsk_accept_queue.listen_opt;
-	const u32 h = inet_synq_hash(inet_rsk(req)->ir_rmt_addr,
-				     inet_rsk(req)->ir_rmt_port,
-				     lopt->hash_rnd, lopt->nr_table_entries);
-
-	reqsk_queue_hash_req(&icsk->icsk_accept_queue, h, req, timeout);
-	inet_csk_reqsk_queue_added(sk, timeout);
-}
-EXPORT_SYMBOL_GPL(inet_csk_reqsk_queue_hash_add);
-
 /* Only thing we need from tcp.h */
 extern int sysctl_tcp_synack_retries;
 
@@ -563,7 +508,7 @@ static inline void syn_ack_recalc(struct request_sock *req, const int thresh,
 		  req->num_timeout >= rskq_defer_accept - 1;
 }
 
-int inet_rtx_syn_ack(struct sock *parent, struct request_sock *req)
+int inet_rtx_syn_ack(const struct sock *parent, struct request_sock *req)
 {
 	int err = req->rsk_ops->rtx_syn_ack(parent, req);
 
@@ -573,27 +518,20 @@ int inet_rtx_syn_ack(struct sock *parent, struct request_sock *req)
 }
 EXPORT_SYMBOL(inet_rtx_syn_ack);
 
-/* return true if req was found in the syn_table[] */
+/* return true if req was found in the ehash table */
 static bool reqsk_queue_unlink(struct request_sock_queue *queue,
 			       struct request_sock *req)
 {
-	struct request_sock **prev;
-	struct listen_sock *lopt;
+	struct inet_hashinfo *hashinfo = req_to_sk(req)->sk_prot->h.hashinfo;
 	bool found = false;
 
-	spin_lock(&queue->syn_wait_lock);
-	lopt = queue->listen_opt;
-	if (lopt) {
-		for (prev = &lopt->syn_table[req->rsk_hash]; *prev != NULL;
-		     prev = &(*prev)->dl_next) {
-			if (*prev == req) {
-				*prev = req->dl_next;
-				found = true;
-				break;
-			}
-		}
+	if (sk_hashed(req_to_sk(req))) {
+		spinlock_t *lock = inet_ehash_lockp(hashinfo, req->rsk_hash);
+
+		spin_lock(lock);
+		found = __sk_nulls_del_node_init_rcu(req_to_sk(req));
+		spin_unlock(lock);
 	}
-	spin_unlock(&queue->syn_wait_lock);
 	if (timer_pending(&req->rsk_timer) && del_timer_sync(&req->rsk_timer))
 		reqsk_put(req);
 	return found;
@@ -608,21 +546,25 @@ void inet_csk_reqsk_queue_drop(struct sock *sk, struct request_sock *req)
 }
 EXPORT_SYMBOL(inet_csk_reqsk_queue_drop);
 
+void inet_csk_reqsk_queue_drop_and_put(struct sock *sk, struct request_sock *req)
+{
+	inet_csk_reqsk_queue_drop(sk, req);
+	reqsk_put(req);
+}
+EXPORT_SYMBOL(inet_csk_reqsk_queue_drop_and_put);
+
 static void reqsk_timer_handler(unsigned long data)
 {
 	struct request_sock *req = (struct request_sock *)data;
 	struct sock *sk_listener = req->rsk_listener;
 	struct inet_connection_sock *icsk = inet_csk(sk_listener);
 	struct request_sock_queue *queue = &icsk->icsk_accept_queue;
-	struct listen_sock *lopt = queue->listen_opt;
 	int qlen, expire = 0, resend = 0;
 	int max_retries, thresh;
 	u8 defer_accept;
 
-	if (sk_listener->sk_state != TCP_LISTEN || !lopt) {
-		reqsk_put(req);
-		return;
-	}
+	if (sk_listener->sk_state != TCP_LISTEN)
+		goto drop;
 
 	max_retries = icsk->icsk_syn_retries ? : sysctl_tcp_synack_retries;
 	thresh = max_retries;
@@ -643,9 +585,9 @@ static void reqsk_timer_handler(unsigned long data)
 	 * embrions; and abort old ones without pity, if old
 	 * ones are about to clog our table.
 	 */
-	qlen = listen_sock_qlen(lopt);
-	if (qlen >> (lopt->max_qlen_log - 1)) {
-		int young = listen_sock_young(lopt) << 1;
+	qlen = reqsk_queue_len(queue);
+	if ((qlen << 1) > max(8U, sk_listener->sk_max_ack_backlog)) {
+		int young = reqsk_queue_len_young(queue) << 1;
 
 		while (thresh > 2) {
 			if (qlen < young)
@@ -667,41 +609,40 @@ static void reqsk_timer_handler(unsigned long data)
 		unsigned long timeo;
 
 		if (req->num_timeout++ == 0)
-			atomic_inc(&lopt->young_dec);
+			atomic_dec(&queue->young);
 		timeo = min(TCP_TIMEOUT_INIT << req->num_timeout, TCP_RTO_MAX);
 		mod_timer_pinned(&req->rsk_timer, jiffies + timeo);
 		return;
 	}
-	inet_csk_reqsk_queue_drop(sk_listener, req);
-	reqsk_put(req);
+drop:
+	inet_csk_reqsk_queue_drop_and_put(sk_listener, req);
 }
 
-void reqsk_queue_hash_req(struct request_sock_queue *queue,
-			  u32 hash, struct request_sock *req,
-			  unsigned long timeout)
+static void reqsk_queue_hash_req(struct request_sock *req,
+				 unsigned long timeout)
 {
-	struct listen_sock *lopt = queue->listen_opt;
-
 	req->num_retrans = 0;
 	req->num_timeout = 0;
 	req->sk = NULL;
 
 	setup_timer(&req->rsk_timer, reqsk_timer_handler, (unsigned long)req);
 	mod_timer_pinned(&req->rsk_timer, jiffies + timeout);
-	req->rsk_hash = hash;
 
+	inet_ehash_insert(req_to_sk(req), NULL);
 	/* before letting lookups find us, make sure all req fields
 	 * are committed to memory and refcnt initialized.
 	 */
 	smp_wmb();
-	atomic_set(&req->rsk_refcnt, 2);
+	atomic_set(&req->rsk_refcnt, 2 + 1);
+}
 
-	spin_lock(&queue->syn_wait_lock);
-	req->dl_next = lopt->syn_table[hash];
-	lopt->syn_table[hash] = req;
-	spin_unlock(&queue->syn_wait_lock);
+void inet_csk_reqsk_queue_hash_add(struct sock *sk, struct request_sock *req,
+				   unsigned long timeout)
+{
+	reqsk_queue_hash_req(req, timeout);
+	inet_csk_reqsk_queue_added(sk);
 }
-EXPORT_SYMBOL(reqsk_queue_hash_req);
+EXPORT_SYMBOL_GPL(inet_csk_reqsk_queue_hash_add);
 
 /**
  *	inet_csk_clone_lock - clone an inet socket, and lock its clone
@@ -792,16 +733,14 @@ void inet_csk_prepare_forced_close(struct sock *sk)
 }
 EXPORT_SYMBOL(inet_csk_prepare_forced_close);
 
-int inet_csk_listen_start(struct sock *sk, const int nr_table_entries)
+int inet_csk_listen_start(struct sock *sk, int backlog)
 {
-	struct inet_sock *inet = inet_sk(sk);
 	struct inet_connection_sock *icsk = inet_csk(sk);
-	int rc = reqsk_queue_alloc(&icsk->icsk_accept_queue, nr_table_entries);
+	struct inet_sock *inet = inet_sk(sk);
 
-	if (rc != 0)
-		return rc;
+	reqsk_queue_alloc(&icsk->icsk_accept_queue);
 
-	sk->sk_max_ack_backlog = 0;
+	sk->sk_max_ack_backlog = backlog;
 	sk->sk_ack_backlog = 0;
 	inet_csk_delack_init(sk);
 
@@ -821,11 +760,76 @@ int inet_csk_listen_start(struct sock *sk, const int nr_table_entries)
 	}
 
 	sk->sk_state = TCP_CLOSE;
-	__reqsk_queue_destroy(&icsk->icsk_accept_queue);
 	return -EADDRINUSE;
 }
 EXPORT_SYMBOL_GPL(inet_csk_listen_start);
 
+static void inet_child_forget(struct sock *sk, struct request_sock *req,
+			      struct sock *child)
+{
+	sk->sk_prot->disconnect(child, O_NONBLOCK);
+
+	sock_orphan(child);
+
+	percpu_counter_inc(sk->sk_prot->orphan_count);
+
+	if (sk->sk_protocol == IPPROTO_TCP && tcp_rsk(req)->tfo_listener) {
+		BUG_ON(tcp_sk(child)->fastopen_rsk != req);
+		BUG_ON(sk != req->rsk_listener);
+
+		/* Paranoid, to prevent race condition if
+		 * an inbound pkt destined for child is
+		 * blocked by sock lock in tcp_v4_rcv().
+		 * Also to satisfy an assertion in
+		 * tcp_v4_destroy_sock().
+		 */
+		tcp_sk(child)->fastopen_rsk = NULL;
+	}
+	inet_csk_destroy_sock(child);
+	reqsk_put(req);
+}
+
+void inet_csk_reqsk_queue_add(struct sock *sk, struct request_sock *req,
+			      struct sock *child)
+{
+	struct request_sock_queue *queue = &inet_csk(sk)->icsk_accept_queue;
+
+	spin_lock(&queue->rskq_lock);
+	if (unlikely(sk->sk_state != TCP_LISTEN)) {
+		inet_child_forget(sk, req, child);
+	} else {
+		req->sk = child;
+		req->dl_next = NULL;
+		if (queue->rskq_accept_head == NULL)
+			queue->rskq_accept_head = req;
+		else
+			queue->rskq_accept_tail->dl_next = req;
+		queue->rskq_accept_tail = req;
+		sk_acceptq_added(sk);
+	}
+	spin_unlock(&queue->rskq_lock);
+}
+EXPORT_SYMBOL(inet_csk_reqsk_queue_add);
+
+struct sock *inet_csk_complete_hashdance(struct sock *sk, struct sock *child,
+					 struct request_sock *req, bool own_req)
+{
+	if (own_req) {
+		inet_csk_reqsk_queue_drop(sk, req);
+		reqsk_queue_removed(&inet_csk(sk)->icsk_accept_queue, req);
+		inet_csk_reqsk_queue_add(sk, req, child);
+		/* Warning: caller must not call reqsk_put(req);
+		 * child stole last reference on it.
+		 */
+		return child;
+	}
+	/* Too bad, another child took ownership of the request, undo. */
+	bh_unlock_sock(child);
+	sock_put(child);
+	return NULL;
+}
+EXPORT_SYMBOL(inet_csk_complete_hashdance);
+
 /*
  *	This routine closes sockets which have been at least partially
  *	opened, but not yet accepted.
@@ -834,11 +838,7 @@ void inet_csk_listen_stop(struct sock *sk)
 {
 	struct inet_connection_sock *icsk = inet_csk(sk);
 	struct request_sock_queue *queue = &icsk->icsk_accept_queue;
-	struct request_sock *acc_req;
-	struct request_sock *req;
-
-	/* make all the listen_opt local to us */
-	acc_req = reqsk_queue_yank_acceptq(queue);
+	struct request_sock *next, *req;
 
 	/* Following specs, it would be better either to send FIN
 	 * (and enter FIN-WAIT-1, it is normal close)
@@ -848,57 +848,34 @@ void inet_csk_listen_stop(struct sock *sk)
 	 * To be honest, we are not able to make either
 	 * of the variants now.			--ANK
 	 */
-	reqsk_queue_destroy(queue);
-
-	while ((req = acc_req) != NULL) {
+	while ((req = reqsk_queue_remove(queue, sk)) != NULL) {
 		struct sock *child = req->sk;
 
-		acc_req = req->dl_next;
-
 		local_bh_disable();
 		bh_lock_sock(child);
 		WARN_ON(sock_owned_by_user(child));
 		sock_hold(child);
 
-		sk->sk_prot->disconnect(child, O_NONBLOCK);
-
-		sock_orphan(child);
-
-		percpu_counter_inc(sk->sk_prot->orphan_count);
-
-		if (sk->sk_protocol == IPPROTO_TCP && tcp_rsk(req)->tfo_listener) {
-			BUG_ON(tcp_sk(child)->fastopen_rsk != req);
-			BUG_ON(sk != req->rsk_listener);
-
-			/* Paranoid, to prevent race condition if
-			 * an inbound pkt destined for child is
-			 * blocked by sock lock in tcp_v4_rcv().
-			 * Also to satisfy an assertion in
-			 * tcp_v4_destroy_sock().
-			 */
-			tcp_sk(child)->fastopen_rsk = NULL;
-		}
-		inet_csk_destroy_sock(child);
-
+		inet_child_forget(sk, req, child);
 		bh_unlock_sock(child);
 		local_bh_enable();
 		sock_put(child);
 
-		sk_acceptq_removed(sk);
-		reqsk_put(req);
+		cond_resched();
 	}
-	if (queue->fastopenq) {
+	if (queue->fastopenq.rskq_rst_head) {
 		/* Free all the reqs queued in rskq_rst_head. */
-		spin_lock_bh(&queue->fastopenq->lock);
-		acc_req = queue->fastopenq->rskq_rst_head;
-		queue->fastopenq->rskq_rst_head = NULL;
-		spin_unlock_bh(&queue->fastopenq->lock);
-		while ((req = acc_req) != NULL) {
-			acc_req = req->dl_next;
+		spin_lock_bh(&queue->fastopenq.lock);
+		req = queue->fastopenq.rskq_rst_head;
+		queue->fastopenq.rskq_rst_head = NULL;
+		spin_unlock_bh(&queue->fastopenq.lock);
+		while (req != NULL) {
+			next = req->dl_next;
 			reqsk_put(req);
+			req = next;
 		}
 	}
-	WARN_ON(sk->sk_ack_backlog);
+	WARN_ON_ONCE(sk->sk_ack_backlog);
 }
 EXPORT_SYMBOL_GPL(inet_csk_listen_stop);