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, 60 insertions, 126 deletions

diff --git a/include/net/request_sock.h b/include/net/request_sock.h
index 87935cad2f7b..a0dde04eb178 100644
--- a/include/net/request_sock.h
+++ b/include/net/request_sock.h
@@ -32,17 +32,17 @@ struct request_sock_ops {
 	int		obj_size;
 	struct kmem_cache	*slab;
 	char		*slab_name;
-	int		(*rtx_syn_ack)(struct sock *sk,
+	int		(*rtx_syn_ack)(const struct sock *sk,
 				       struct request_sock *req);
-	void		(*send_ack)(struct sock *sk, struct sk_buff *skb,
+	void		(*send_ack)(const struct sock *sk, struct sk_buff *skb,
 				    struct request_sock *req);
-	void		(*send_reset)(struct sock *sk,
+	void		(*send_reset)(const struct sock *sk,
 				      struct sk_buff *skb);
 	void		(*destructor)(struct request_sock *req);
 	void		(*syn_ack_timeout)(const struct request_sock *req);
 };
 
-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);
 
 /* struct request_sock - mini sock to represent a connection request
  */
@@ -50,16 +50,15 @@ struct request_sock {
 	struct sock_common		__req_common;
 #define rsk_refcnt			__req_common.skc_refcnt
 #define rsk_hash			__req_common.skc_hash
+#define rsk_listener			__req_common.skc_listener
+#define rsk_window_clamp		__req_common.skc_window_clamp
+#define rsk_rcv_wnd			__req_common.skc_rcv_wnd
 
 	struct request_sock		*dl_next;
-	struct sock			*rsk_listener;
 	u16				mss;
 	u8				num_retrans; /* number of retransmits */
 	u8				cookie_ts:1; /* syncookie: encode tcpopts in timestamp */
 	u8				num_timeout:7; /* number of timeouts */
-	/* The following two fields can be easily recomputed I think -AK */
-	u32				window_clamp; /* window clamp at creation time */
-	u32				rcv_wnd;	  /* rcv_wnd offered first time */
 	u32				ts_recent;
 	struct timer_list		rsk_timer;
 	const struct request_sock_ops	*rsk_ops;
@@ -69,15 +68,35 @@ struct request_sock {
 	u32				peer_secid;
 };
 
+static inline struct request_sock *inet_reqsk(struct sock *sk)
+{
+	return (struct request_sock *)sk;
+}
+
+static inline struct sock *req_to_sk(struct request_sock *req)
+{
+	return (struct sock *)req;
+}
+
 static inline struct request_sock *
-reqsk_alloc(const struct request_sock_ops *ops, struct sock *sk_listener)
+reqsk_alloc(const struct request_sock_ops *ops, struct sock *sk_listener,
+	    bool attach_listener)
 {
-	struct request_sock *req = kmem_cache_alloc(ops->slab, GFP_ATOMIC);
+	struct request_sock *req;
+
+	req = kmem_cache_alloc(ops->slab, GFP_ATOMIC | __GFP_NOWARN);
 
 	if (req) {
 		req->rsk_ops = ops;
-		sock_hold(sk_listener);
-		req->rsk_listener = sk_listener;
+		if (attach_listener) {
+			sock_hold(sk_listener);
+			req->rsk_listener = sk_listener;
+		} else {
+			req->rsk_listener = NULL;
+		}
+		req_to_sk(req)->sk_prot = sk_listener->sk_prot;
+		sk_node_init(&req_to_sk(req)->sk_node);
+		sk_tx_queue_clear(req_to_sk(req));
 		req->saved_syn = NULL;
 		/* Following is temporary. It is coupled with debugging
 		 * helpers in reqsk_put() & reqsk_free()
@@ -87,16 +106,6 @@ reqsk_alloc(const struct request_sock_ops *ops, struct sock *sk_listener)
 	return req;
 }
 
-static inline struct request_sock *inet_reqsk(struct sock *sk)
-{
-	return (struct request_sock *)sk;
-}
-
-static inline struct sock *req_to_sk(struct request_sock *req)
-{
-	return (struct sock *)req;
-}
-
 static inline void reqsk_free(struct request_sock *req)
 {
 	/* temporary debugging */
@@ -117,26 +126,6 @@ static inline void reqsk_put(struct request_sock *req)
 
 extern int sysctl_max_syn_backlog;
 
-/** struct listen_sock - listen state
- *
- * @max_qlen_log - log_2 of maximal queued SYNs/REQUESTs
- */
-struct listen_sock {
-	int			qlen_inc; /* protected by listener lock */
-	int			young_inc;/* protected by listener lock */
-
-	/* following fields can be updated by timer */
-	atomic_t		qlen_dec; /* qlen = qlen_inc - qlen_dec */
-	atomic_t		young_dec;
-
-	u8			max_qlen_log ____cacheline_aligned_in_smp;
-	u8			synflood_warned;
-	/* 2 bytes hole, try to use */
-	u32			hash_rnd;
-	u32			nr_table_entries;
-	struct request_sock	*syn_table[0];
-};
-
 /*
  * For a TCP Fast Open listener -
  *	lock - protects the access to all the reqsk, which is co-owned by
@@ -170,127 +159,72 @@ struct fastopen_queue {
  * @rskq_accept_head - FIFO head of established children
  * @rskq_accept_tail - FIFO tail of established children
  * @rskq_defer_accept - User waits for some data after accept()
- * @syn_wait_lock - serializer
- *
- * %syn_wait_lock is necessary only to avoid proc interface having to grab the main
- * lock sock while browsing the listening hash (otherwise it's deadlock prone).
  *
  */
 struct request_sock_queue {
+	spinlock_t		rskq_lock;
+	u8			rskq_defer_accept;
+
+	u32			synflood_warned;
+	atomic_t		qlen;
+	atomic_t		young;
+
 	struct request_sock	*rskq_accept_head;
 	struct request_sock	*rskq_accept_tail;
-	u8			rskq_defer_accept;
-	struct listen_sock	*listen_opt;
-	struct fastopen_queue	*fastopenq; /* This is non-NULL iff TFO has been
-					     * enabled on this listener. Check
-					     * max_qlen != 0 in fastopen_queue
-					     * to determine if TFO is enabled
-					     * right at this moment.
+	struct fastopen_queue	fastopenq;  /* Check max_qlen != 0 to determine
+					     * if TFO is enabled.
 					     */
-
-	/* temporary alignment, our goal is to get rid of this lock */
-	spinlock_t		syn_wait_lock ____cacheline_aligned_in_smp;
 };
 
-int reqsk_queue_alloc(struct request_sock_queue *queue,
-		      unsigned int nr_table_entries);
+void reqsk_queue_alloc(struct request_sock_queue *queue);
 
-void __reqsk_queue_destroy(struct request_sock_queue *queue);
-void reqsk_queue_destroy(struct request_sock_queue *queue);
 void reqsk_fastopen_remove(struct sock *sk, struct request_sock *req,
 			   bool reset);
 
-static inline struct request_sock *
-	reqsk_queue_yank_acceptq(struct request_sock_queue *queue)
-{
-	struct request_sock *req = queue->rskq_accept_head;
-
-	queue->rskq_accept_head = NULL;
-	return req;
-}
-
-static inline int reqsk_queue_empty(struct request_sock_queue *queue)
+static inline bool reqsk_queue_empty(const struct request_sock_queue *queue)
 {
 	return queue->rskq_accept_head == NULL;
 }
 
-static inline void reqsk_queue_add(struct request_sock_queue *queue,
-				   struct request_sock *req,
-				   struct sock *parent,
-				   struct sock *child)
+static inline struct request_sock *reqsk_queue_remove(struct request_sock_queue *queue,
+						      struct sock *parent)
 {
-	req->sk = child;
-	sk_acceptq_added(parent);
-
-	if (queue->rskq_accept_head == NULL)
-		queue->rskq_accept_head = req;
-	else
-		queue->rskq_accept_tail->dl_next = req;
-
-	queue->rskq_accept_tail = req;
-	req->dl_next = NULL;
-}
-
-static inline struct request_sock *reqsk_queue_remove(struct request_sock_queue *queue)
-{
-	struct request_sock *req = queue->rskq_accept_head;
-
-	WARN_ON(req == NULL);
-
-	queue->rskq_accept_head = req->dl_next;
-	if (queue->rskq_accept_head == NULL)
-		queue->rskq_accept_tail = NULL;
+	struct request_sock *req;
 
+	spin_lock_bh(&queue->rskq_lock);
+	req = queue->rskq_accept_head;
+	if (req) {
+		sk_acceptq_removed(parent);
+		queue->rskq_accept_head = req->dl_next;
+		if (queue->rskq_accept_head == NULL)
+			queue->rskq_accept_tail = NULL;
+	}
+	spin_unlock_bh(&queue->rskq_lock);
 	return req;
 }
 
 static inline void reqsk_queue_removed(struct request_sock_queue *queue,
 				       const struct request_sock *req)
 {
-	struct listen_sock *lopt = queue->listen_opt;
-
 	if (req->num_timeout == 0)
-		atomic_inc(&lopt->young_dec);
-	atomic_inc(&lopt->qlen_dec);
+		atomic_dec(&queue->young);
+	atomic_dec(&queue->qlen);
 }
 
 static inline void reqsk_queue_added(struct request_sock_queue *queue)
 {
-	struct listen_sock *lopt = queue->listen_opt;
-
-	lopt->young_inc++;
-	lopt->qlen_inc++;
-}
-
-static inline int listen_sock_qlen(const struct listen_sock *lopt)
-{
-	return lopt->qlen_inc - atomic_read(&lopt->qlen_dec);
-}
-
-static inline int listen_sock_young(const struct listen_sock *lopt)
-{
-	return lopt->young_inc - atomic_read(&lopt->young_dec);
+	atomic_inc(&queue->young);
+	atomic_inc(&queue->qlen);
 }
 
 static inline int reqsk_queue_len(const struct request_sock_queue *queue)
 {
-	const struct listen_sock *lopt = queue->listen_opt;
-
-	return lopt ? listen_sock_qlen(lopt) : 0;
+	return atomic_read(&queue->qlen);
 }
 
 static inline int reqsk_queue_len_young(const struct request_sock_queue *queue)
 {
-	return listen_sock_young(queue->listen_opt);
+	return atomic_read(&queue->young);
 }
 
-static inline int reqsk_queue_is_full(const struct request_sock_queue *queue)
-{
-	return reqsk_queue_len(queue) >> queue->listen_opt->max_qlen_log;
-}
-
-void reqsk_queue_hash_req(struct request_sock_queue *queue,
-			  u32 hash, struct request_sock *req,
-			  unsigned long timeout);
-
 #endif /* _REQUEST_SOCK_H */