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

Pull networking updates from David Miller:
 "Highlights:

   1) Steady transitioning of the BPF instructure to a generic spot so
      all kernel subsystems can make use of it, from Alexei Starovoitov.

   2) SFC driver supports busy polling, from Alexandre Rames.

   3) Take advantage of hash table in UDP multicast delivery, from David
      Held.

   4) Lighten locking, in particular by getting rid of the LRU lists, in
      inet frag handling.  From Florian Westphal.

   5) Add support for various RFC6458 control messages in SCTP, from
      Geir Ola Vaagland.

   6) Allow to filter bridge forwarding database dumps by device, from
      Jamal Hadi Salim.

   7) virtio-net also now supports busy polling, from Jason Wang.

   8) Some low level optimization tweaks in pktgen from Jesper Dangaard
      Brouer.

   9) Add support for ipv6 address generation modes, so that userland
      can have some input into the process.  From Jiri Pirko.

  10) Consolidate common TCP connection request code in ipv4 and ipv6,
      from Octavian Purdila.

  11) New ARP packet logger in netfilter, from Pablo Neira Ayuso.

  12) Generic resizable RCU hash table, with intial users in netlink and
      nftables.  From Thomas Graf.

  13) Maintain a name assignment type so that userspace can see where a
      network device name came from (enumerated by kernel, assigned
      explicitly by userspace, etc.) From Tom Gundersen.

  14) Automatic flow label generation on transmit in ipv6, from Tom
      Herbert.

  15) New packet timestamping facilities from Willem de Bruijn, meant to
      assist in measuring latencies going into/out-of the packet
      scheduler, latency from TCP data transmission to ACK, etc"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1536 commits)
  cxgb4 : Disable recursive mailbox commands when enabling vi
  net: reduce USB network driver config options.
  tg3: Modify tg3_tso_bug() to handle multiple TX rings
  amd-xgbe: Perform phy connect/disconnect at dev open/stop
  amd-xgbe: Use dma_set_mask_and_coherent to set DMA mask
  net: sun4i-emac: fix memory leak on bad packet
  sctp: fix possible seqlock seadlock in sctp_packet_transmit()
  Revert "net: phy: Set the driver when registering an MDIO bus device"
  cxgb4vf: Turn off SGE RX/TX Callback Timers and interrupts in PCI shutdown routine
  team: Simplify return path of team_newlink
  bridge: Update outdated comment on promiscuous mode
  net-timestamp: ACK timestamp for bytestreams
  net-timestamp: TCP timestamping
  net-timestamp: SCHED timestamp on entering packet scheduler
  net-timestamp: add key to disambiguate concurrent datagrams
  net-timestamp: move timestamp flags out of sk_flags
  net-timestamp: extend SCM_TIMESTAMPING ancillary data struct
  cxgb4i : Move stray CPL definitions to cxgb4 driver
  tcp: reduce spurious retransmits due to transient SACK reneging
  qlcnic: Initialize dcbnl_ops before register_netdev
  ...

1 files changed, 45 insertions, 27 deletions

diff --git a/include/net/sock.h b/include/net/sock.h
index 156350745700..52fe0bc5598a 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -67,6 +67,7 @@
 #include <linux/atomic.h>
 #include <net/dst.h>
 #include <net/checksum.h>
+#include <linux/net_tstamp.h>
 
 struct cgroup;
 struct cgroup_subsys;
@@ -181,7 +182,8 @@ struct sock_common {
 	unsigned short		skc_family;
 	volatile unsigned char	skc_state;
 	unsigned char		skc_reuse:4;
-	unsigned char		skc_reuseport:4;
+	unsigned char		skc_reuseport:1;
+	unsigned char		skc_ipv6only:1;
 	int			skc_bound_dev_if;
 	union {
 		struct hlist_node	skc_bind_node;
@@ -272,10 +274,13 @@ struct cg_proto;
   *	@sk_rcvtimeo: %SO_RCVTIMEO setting
   *	@sk_sndtimeo: %SO_SNDTIMEO setting
   *	@sk_rxhash: flow hash received from netif layer
+  *	@sk_txhash: computed flow hash for use on transmit
   *	@sk_filter: socket filtering instructions
   *	@sk_protinfo: private area, net family specific, when not using slab
   *	@sk_timer: sock cleanup timer
   *	@sk_stamp: time stamp of last packet received
+  *	@sk_tsflags: SO_TIMESTAMPING socket options
+  *	@sk_tskey: counter to disambiguate concurrent tstamp requests
   *	@sk_socket: Identd and reporting IO signals
   *	@sk_user_data: RPC layer private data
   *	@sk_frag: cached page frag
@@ -317,6 +322,7 @@ struct sock {
 #define sk_state		__sk_common.skc_state
 #define sk_reuse		__sk_common.skc_reuse
 #define sk_reuseport		__sk_common.skc_reuseport
+#define sk_ipv6only		__sk_common.skc_ipv6only
 #define sk_bound_dev_if		__sk_common.skc_bound_dev_if
 #define sk_bind_node		__sk_common.skc_bind_node
 #define sk_prot			__sk_common.skc_prot
@@ -345,6 +351,7 @@ struct sock {
 #ifdef CONFIG_RPS
 	__u32			sk_rxhash;
 #endif
+	__u32			sk_txhash;
 #ifdef CONFIG_NET_RX_BUSY_POLL
 	unsigned int		sk_napi_id;
 	unsigned int		sk_ll_usec;
@@ -407,6 +414,8 @@ struct sock {
 	void			*sk_protinfo;
 	struct timer_list	sk_timer;
 	ktime_t			sk_stamp;
+	u16			sk_tsflags;
+	u32			sk_tskey;
 	struct socket		*sk_socket;
 	void			*sk_user_data;
 	struct page_frag	sk_frag;
@@ -656,6 +665,20 @@ static inline void sk_add_bind_node(struct sock *sk,
 #define sk_for_each_bound(__sk, list) \
 	hlist_for_each_entry(__sk, list, sk_bind_node)
 
+/**
+ * sk_nulls_for_each_entry_offset - iterate over a list at a given struct offset
+ * @tpos:	the type * to use as a loop cursor.
+ * @pos:	the &struct hlist_node to use as a loop cursor.
+ * @head:	the head for your list.
+ * @offset:	offset of hlist_node within the struct.
+ *
+ */
+#define sk_nulls_for_each_entry_offset(tpos, pos, head, offset)		       \
+	for (pos = (head)->first;					       \
+	     (!is_a_nulls(pos)) &&					       \
+		({ tpos = (typeof(*tpos) *)((void *)pos - offset); 1;});       \
+	     pos = pos->next)
+
 static inline struct user_namespace *sk_user_ns(struct sock *sk)
 {
 	/* Careful only use this in a context where these parameters
@@ -683,13 +706,7 @@ enum sock_flags {
 	SOCK_LOCALROUTE, /* route locally only, %SO_DONTROUTE setting */
 	SOCK_QUEUE_SHRUNK, /* write queue has been shrunk recently */
 	SOCK_MEMALLOC, /* VM depends on this socket for swapping */
-	SOCK_TIMESTAMPING_TX_HARDWARE,  /* %SOF_TIMESTAMPING_TX_HARDWARE */
-	SOCK_TIMESTAMPING_TX_SOFTWARE,  /* %SOF_TIMESTAMPING_TX_SOFTWARE */
-	SOCK_TIMESTAMPING_RX_HARDWARE,  /* %SOF_TIMESTAMPING_RX_HARDWARE */
 	SOCK_TIMESTAMPING_RX_SOFTWARE,  /* %SOF_TIMESTAMPING_RX_SOFTWARE */
-	SOCK_TIMESTAMPING_SOFTWARE,     /* %SOF_TIMESTAMPING_SOFTWARE */
-	SOCK_TIMESTAMPING_RAW_HARDWARE, /* %SOF_TIMESTAMPING_RAW_HARDWARE */
-	SOCK_TIMESTAMPING_SYS_HARDWARE, /* %SOF_TIMESTAMPING_SYS_HARDWARE */
 	SOCK_FASYNC, /* fasync() active */
 	SOCK_RXQ_OVFL,
 	SOCK_ZEROCOPY, /* buffers from userspace */
@@ -792,8 +809,7 @@ static inline void __sk_add_backlog(struct sock *sk, struct sk_buff *skb)
  * Do not take into account this skb truesize,
  * to allow even a single big packet to come.
  */
-static inline bool sk_rcvqueues_full(const struct sock *sk, const struct sk_buff *skb,
-				     unsigned int limit)
+static inline bool sk_rcvqueues_full(const struct sock *sk, unsigned int limit)
 {
 	unsigned int qsize = sk->sk_backlog.len + atomic_read(&sk->sk_rmem_alloc);
 
@@ -804,7 +820,7 @@ static inline bool sk_rcvqueues_full(const struct sock *sk, const struct sk_buff
 static inline __must_check int sk_add_backlog(struct sock *sk, struct sk_buff *skb,
 					      unsigned int limit)
 {
-	if (sk_rcvqueues_full(sk, skb, limit))
+	if (sk_rcvqueues_full(sk, limit))
 		return -ENOBUFS;
 
 	__sk_add_backlog(sk, skb);
@@ -1978,6 +1994,14 @@ static inline void sock_poll_wait(struct file *filp,
 	}
 }
 
+static inline void skb_set_hash_from_sk(struct sk_buff *skb, struct sock *sk)
+{
+	if (sk->sk_txhash) {
+		skb->l4_hash = 1;
+		skb->hash = sk->sk_txhash;
+	}
+}
+
 /*
  *	Queue a received datagram if it will fit. Stream and sequenced
  *	protocols can't normally use this as they need to fit buffers in
@@ -1992,6 +2016,7 @@ static inline void skb_set_owner_w(struct sk_buff *skb, struct sock *sk)
 	skb_orphan(skb);
 	skb->sk = sk;
 	skb->destructor = sock_wfree;
+	skb_set_hash_from_sk(skb, sk);
 	/*
 	 * We used to take a refcount on sk, but following operation
 	 * is enough to guarantee sk_free() wont free this sock until
@@ -2135,21 +2160,17 @@ sock_recv_timestamp(struct msghdr *msg, struct sock *sk, struct sk_buff *skb)
 
 	/*
 	 * generate control messages if
-	 * - receive time stamping in software requested (SOCK_RCVTSTAMP
-	 *   or SOCK_TIMESTAMPING_RX_SOFTWARE)
+	 * - receive time stamping in software requested
 	 * - software time stamp available and wanted
-	 *   (SOCK_TIMESTAMPING_SOFTWARE)
 	 * - hardware time stamps available and wanted
-	 *   (SOCK_TIMESTAMPING_SYS_HARDWARE or
-	 *   SOCK_TIMESTAMPING_RAW_HARDWARE)
 	 */
 	if (sock_flag(sk, SOCK_RCVTSTAMP) ||
-	    sock_flag(sk, SOCK_TIMESTAMPING_RX_SOFTWARE) ||
-	    (kt.tv64 && sock_flag(sk, SOCK_TIMESTAMPING_SOFTWARE)) ||
+	    (sk->sk_tsflags & SOF_TIMESTAMPING_RX_SOFTWARE) ||
+	    (kt.tv64 &&
+	     (sk->sk_tsflags & SOF_TIMESTAMPING_SOFTWARE ||
+	      skb_shinfo(skb)->tx_flags & SKBTX_ANY_SW_TSTAMP)) ||
 	    (hwtstamps->hwtstamp.tv64 &&
-	     sock_flag(sk, SOCK_TIMESTAMPING_RAW_HARDWARE)) ||
-	    (hwtstamps->syststamp.tv64 &&
-	     sock_flag(sk, SOCK_TIMESTAMPING_SYS_HARDWARE)))
+	     (sk->sk_tsflags & SOF_TIMESTAMPING_RAW_HARDWARE)))
 		__sock_recv_timestamp(msg, sk, skb);
 	else
 		sk->sk_stamp = kt;
@@ -2165,12 +2186,11 @@ static inline void sock_recv_ts_and_drops(struct msghdr *msg, struct sock *sk,
 					  struct sk_buff *skb)
 {
 #define FLAGS_TS_OR_DROPS ((1UL << SOCK_RXQ_OVFL)			| \
-			   (1UL << SOCK_RCVTSTAMP)			| \
-			   (1UL << SOCK_TIMESTAMPING_SOFTWARE)		| \
-			   (1UL << SOCK_TIMESTAMPING_RAW_HARDWARE)	| \
-			   (1UL << SOCK_TIMESTAMPING_SYS_HARDWARE))
+			   (1UL << SOCK_RCVTSTAMP))
+#define TSFLAGS_ANY	  (SOF_TIMESTAMPING_SOFTWARE			| \
+			   SOF_TIMESTAMPING_RAW_HARDWARE)
 
-	if (sk->sk_flags & FLAGS_TS_OR_DROPS)
+	if (sk->sk_flags & FLAGS_TS_OR_DROPS || sk->sk_tsflags & TSFLAGS_ANY)
 		__sock_recv_ts_and_drops(msg, sk, skb);
 	else
 		sk->sk_stamp = skb->tstamp;
@@ -2180,8 +2200,6 @@ static inline void sock_recv_ts_and_drops(struct msghdr *msg, struct sock *sk,
  * sock_tx_timestamp - checks whether the outgoing packet is to be time stamped
  * @sk:		socket sending this packet
  * @tx_flags:	filled with instructions for time stamping
- *
- * Currently only depends on SOCK_TIMESTAMPING* flags.
  */
 void sock_tx_timestamp(struct sock *sk, __u8 *tx_flags);