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

Pull networking changes from David Miller:

 1) Get rid of the error prone NLA_PUT*() macros that used an embedded
    goto.

 2) Kill off the token-ring and MCA networking drivers, from Paul
    Gortmaker.

 3) Reduce high-order allocations made by datagram AF_UNIX sockets, from
    Eric Dumazet.

 4) Add PTP hardware clock support to IGB and IXGBE, from Richard
    Cochran and Jacob Keller.

 5) Allow users to query timestamping capabilities of a card via
    ethtool, from Richard Cochran.

 6) Add loadbalance mode to the teaming driver, from Jiri Pirko.  Part
    of this is that we can now have BPF filters not attached to sockets,
    and the loadbalancing function is calculated using one.

 7) Francois Romieu went through the network drivers removing gratuitous
    uses of netdev->base_addr, perhaps some day we can remove it
    completely but it's used for ISA probing still.

 8) Add a BPF JIT for sparc.  I know, who cares, right? :-)

 9) Move networking sysctl registry away from using the compatability
    mode interfaces in the sysctl code.  From Eric W Biederman.

10) Pavel Emelyanov added a way to save and restore TCP socket state via
    TCP_REPAIR, TCP_REPAIR_QUEUE, and TCP_QUEUE_SEQ socket options as
    well as a way to forcefully bind a socket to a port via the
    sk->sk_reuse value SK_FORCE_REUSE.  There is also a
    TCP_REPAIR_OPTIONS which allows to reinstante the TCP options
    enabled on the connection.

11) Several enhancements from Eric Dumazet that, in particular, can
    enhance splice performance on TCP sockets significantly.

     a) Reset the offset of the per-socket sendmsg page when we know
        we're the only use of the page in linear_to_page().

     b) Add facilities such that skb->data can be backed a page rather
        than SLAB kmalloc'd memory.  In particular devices which were
        receiving into linear RX buffers can now end up providing paged
        data.

    The big result is that code like splice and GRO do not have to copy
    any more.

12) Allow a pure sender to more gracefully handle ACK backlogs in TCP.
    What can happen at high rates is that the sender hasn't grown his
    receive buffer limits at all (he's not receiving data so really
    doesn't need to), but the non-data ACKs consume receive buffer
    space.

    sk_add_backlog() is too aggressive in dropping frames in this case,
    so relax it's requirements by using the receive buffer plus the send
    buffer limit as the backlog limit instead of just the former.

    Also from Eric Dumazet.

13) Add ipv6 support to L2TP, from Benjamin LaHaise, James Chapman, and
    Chris Elston.

14) Implement TCP early retransmit (RFC 5827), from Yuchung Cheng.
    Basically, we can start fast retransmit before hiting the dupack
    threshold under certain conditions.

15) New CODEL active queue management packet scheduler, from Eric
    Dumazet based upon initial work by Dave Taht.

    Basically, the big feature is that packets are dropped (or ECN bits
    are set) based upon how long packets live in the queue, rather than
    the queue length (which is what RED uses).

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1341 commits)
  drivers/net/stmmac: seq_file fix memory leak
  ipv6/exthdrs: strict Pad1 and PadN check
  USB: qmi_wwan: Add ZTE (Vodafone) K3520-Z
  USB: qmi_wwan: Add ZTE (Vodafone) K3765-Z
  USB: qmi_wwan: Make forced int 4 whitelist generic
  net/ipv4: replace simple_strtoul with kstrtoul
  net/ipv4/ipconfig: neaten __setup placement
  net: qmi_wwan: Add Vodafone/Huawei K5005 support
  net: cdc_ether: Add ZTE WWAN matches before generic Ethernet
  ipv6: use skb coalescing in reassembly
  ipv4: use skb coalescing in defragmentation
  net: introduce skb_try_coalesce()
  net:ipv6:fixed space issues relating to operators.
  net:ipv6:fixed a trailing white space issue.
  ipv6: disable GSO on sockets hitting dst_allfrag
  tg3: use netdev_alloc_frag() API
  net: napi_frags_skb() is static
  ppp: avoid false drop_monitor false positives
  ipv6: bool/const conversions phase2
  ipx: Remove spurious NULL checking in ipx_ioctl().
  ...

1 files changed, 87 insertions, 18 deletions

diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index 72522f08737..d6146b4811c 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -10,7 +10,6 @@
 
 #include <asm/types.h>                  /* for __uXX types */
 
-#include <linux/sysctl.h>               /* for ctl_path */
 #include <linux/list.h>                 /* for struct list_head */
 #include <linux/spinlock.h>             /* for struct rwlock_t */
 #include <linux/atomic.h>                 /* for struct atomic_t */
@@ -505,6 +504,7 @@ struct ip_vs_conn {
 						 * state transition triggerd
 						 * synchronization
 						 */
+	unsigned long		sync_endtime;	/* jiffies + sent_retries */
 
 	/* Control members */
 	struct ip_vs_conn       *control;       /* Master control connection */
@@ -580,8 +580,8 @@ struct ip_vs_service_user_kern {
 	/* virtual service options */
 	char			*sched_name;
 	char			*pe_name;
-	unsigned		flags;		/* virtual service flags */
-	unsigned		timeout;	/* persistent timeout in sec */
+	unsigned int		flags;		/* virtual service flags */
+	unsigned int		timeout;	/* persistent timeout in sec */
 	u32			netmask;	/* persistent netmask */
 };
 
@@ -592,7 +592,7 @@ struct ip_vs_dest_user_kern {
 	u16			port;
 
 	/* real server options */
-	unsigned		conn_flags;	/* connection flags */
+	unsigned int		conn_flags;	/* connection flags */
 	int			weight;		/* destination weight */
 
 	/* thresholds for active connections */
@@ -616,8 +616,8 @@ struct ip_vs_service {
 	union nf_inet_addr	addr;	  /* IP address for virtual service */
 	__be16			port;	  /* port number for the service */
 	__u32                   fwmark;   /* firewall mark of the service */
-	unsigned		flags;	  /* service status flags */
-	unsigned		timeout;  /* persistent timeout in ticks */
+	unsigned int		flags;	  /* service status flags */
+	unsigned int		timeout;  /* persistent timeout in ticks */
 	__be32			netmask;  /* grouping granularity */
 	struct net		*net;
 
@@ -647,7 +647,7 @@ struct ip_vs_dest {
 	u16			af;		/* address family */
 	__be16			port;		/* port number of the server */
 	union nf_inet_addr	addr;		/* IP address of the server */
-	volatile unsigned	flags;		/* dest status flags */
+	volatile unsigned int	flags;		/* dest status flags */
 	atomic_t		conn_flags;	/* flags to copy to conn */
 	atomic_t		weight;		/* server weight */
 
@@ -784,6 +784,16 @@ struct ip_vs_app {
 	void (*timeout_change)(struct ip_vs_app *app, int flags);
 };
 
+struct ipvs_master_sync_state {
+	struct list_head	sync_queue;
+	struct ip_vs_sync_buff	*sync_buff;
+	int			sync_queue_len;
+	unsigned int		sync_queue_delay;
+	struct task_struct	*master_thread;
+	struct delayed_work	master_wakeup_work;
+	struct netns_ipvs	*ipvs;
+};
+
 /* IPVS in network namespace */
 struct netns_ipvs {
 	int			gen;		/* Generation */
@@ -870,10 +880,15 @@ struct netns_ipvs {
 #endif
 	int			sysctl_snat_reroute;
 	int			sysctl_sync_ver;
+	int			sysctl_sync_ports;
+	int			sysctl_sync_qlen_max;
+	int			sysctl_sync_sock_size;
 	int			sysctl_cache_bypass;
 	int			sysctl_expire_nodest_conn;
 	int			sysctl_expire_quiescent_template;
 	int			sysctl_sync_threshold[2];
+	unsigned int		sysctl_sync_refresh_period;
+	int			sysctl_sync_retries;
 	int			sysctl_nat_icmp_send;
 
 	/* ip_vs_lblc */
@@ -889,13 +904,11 @@ struct netns_ipvs {
 	spinlock_t		est_lock;
 	struct timer_list	est_timer;	/* Estimation timer */
 	/* ip_vs_sync */
-	struct list_head	sync_queue;
 	spinlock_t		sync_lock;
-	struct ip_vs_sync_buff  *sync_buff;
+	struct ipvs_master_sync_state *ms;
 	spinlock_t		sync_buff_lock;
-	struct sockaddr_in	sync_mcast_addr;
-	struct task_struct	*master_thread;
-	struct task_struct	*backup_thread;
+	struct task_struct	**backup_threads;
+	int			threads_mask;
 	int			send_mesg_maxlen;
 	int			recv_mesg_maxlen;
 	volatile int		sync_state;
@@ -912,6 +925,14 @@ struct netns_ipvs {
 #define DEFAULT_SYNC_THRESHOLD	3
 #define DEFAULT_SYNC_PERIOD	50
 #define DEFAULT_SYNC_VER	1
+#define DEFAULT_SYNC_REFRESH_PERIOD	(0U * HZ)
+#define DEFAULT_SYNC_RETRIES		0
+#define IPVS_SYNC_WAKEUP_RATE	8
+#define IPVS_SYNC_QLEN_MAX	(IPVS_SYNC_WAKEUP_RATE * 4)
+#define IPVS_SYNC_SEND_DELAY	(HZ / 50)
+#define IPVS_SYNC_CHECK_PERIOD	HZ
+#define IPVS_SYNC_FLUSH_TIME	(HZ * 2)
+#define IPVS_SYNC_PORTS_MAX	(1 << 6)
 
 #ifdef CONFIG_SYSCTL
 
@@ -922,7 +943,17 @@ static inline int sysctl_sync_threshold(struct netns_ipvs *ipvs)
 
 static inline int sysctl_sync_period(struct netns_ipvs *ipvs)
 {
-	return ipvs->sysctl_sync_threshold[1];
+	return ACCESS_ONCE(ipvs->sysctl_sync_threshold[1]);
+}
+
+static inline unsigned int sysctl_sync_refresh_period(struct netns_ipvs *ipvs)
+{
+	return ACCESS_ONCE(ipvs->sysctl_sync_refresh_period);
+}
+
+static inline int sysctl_sync_retries(struct netns_ipvs *ipvs)
+{
+	return ipvs->sysctl_sync_retries;
 }
 
 static inline int sysctl_sync_ver(struct netns_ipvs *ipvs)
@@ -930,6 +961,21 @@ static inline int sysctl_sync_ver(struct netns_ipvs *ipvs)
 	return ipvs->sysctl_sync_ver;
 }
 
+static inline int sysctl_sync_ports(struct netns_ipvs *ipvs)
+{
+	return ACCESS_ONCE(ipvs->sysctl_sync_ports);
+}
+
+static inline int sysctl_sync_qlen_max(struct netns_ipvs *ipvs)
+{
+	return ipvs->sysctl_sync_qlen_max;
+}
+
+static inline int sysctl_sync_sock_size(struct netns_ipvs *ipvs)
+{
+	return ipvs->sysctl_sync_sock_size;
+}
+
 #else
 
 static inline int sysctl_sync_threshold(struct netns_ipvs *ipvs)
@@ -942,18 +988,43 @@ static inline int sysctl_sync_period(struct netns_ipvs *ipvs)
 	return DEFAULT_SYNC_PERIOD;
 }
 
+static inline unsigned int sysctl_sync_refresh_period(struct netns_ipvs *ipvs)
+{
+	return DEFAULT_SYNC_REFRESH_PERIOD;
+}
+
+static inline int sysctl_sync_retries(struct netns_ipvs *ipvs)
+{
+	return DEFAULT_SYNC_RETRIES & 3;
+}
+
 static inline int sysctl_sync_ver(struct netns_ipvs *ipvs)
 {
 	return DEFAULT_SYNC_VER;
 }
 
+static inline int sysctl_sync_ports(struct netns_ipvs *ipvs)
+{
+	return 1;
+}
+
+static inline int sysctl_sync_qlen_max(struct netns_ipvs *ipvs)
+{
+	return IPVS_SYNC_QLEN_MAX;
+}
+
+static inline int sysctl_sync_sock_size(struct netns_ipvs *ipvs)
+{
+	return 0;
+}
+
 #endif
 
 /*
  *      IPVS core functions
  *      (from ip_vs_core.c)
  */
-extern const char *ip_vs_proto_name(unsigned proto);
+extern const char *ip_vs_proto_name(unsigned int proto);
 extern void ip_vs_init_hash_table(struct list_head *table, int rows);
 #define IP_VS_INIT_HASH_TABLE(t) ip_vs_init_hash_table((t), ARRAY_SIZE((t)))
 
@@ -1014,7 +1085,7 @@ extern void ip_vs_conn_fill_cport(struct ip_vs_conn *cp, __be16 cport);
 
 struct ip_vs_conn *ip_vs_conn_new(const struct ip_vs_conn_param *p,
 				  const union nf_inet_addr *daddr,
-				  __be16 dport, unsigned flags,
+				  __be16 dport, unsigned int flags,
 				  struct ip_vs_dest *dest, __u32 fwmark);
 extern void ip_vs_conn_expire_now(struct ip_vs_conn *cp);
 
@@ -1184,10 +1255,8 @@ extern void ip_vs_scheduler_err(struct ip_vs_service *svc, const char *msg);
  *      IPVS control data and functions (from ip_vs_ctl.c)
  */
 extern struct ip_vs_stats ip_vs_stats;
-extern const struct ctl_path net_vs_ctl_path[];
 extern int sysctl_ip_vs_sync_ver;
 
-extern void ip_vs_sync_switch_mode(struct net *net, int mode);
 extern struct ip_vs_service *
 ip_vs_service_get(struct net *net, int af, __u32 fwmark, __u16 protocol,
 		  const union nf_inet_addr *vaddr, __be16 vport);
@@ -1221,7 +1290,7 @@ extern struct ip_vs_dest *ip_vs_try_bind_dest(struct ip_vs_conn *cp);
 extern int start_sync_thread(struct net *net, int state, char *mcast_ifn,
 			     __u8 syncid);
 extern int stop_sync_thread(struct net *net, int state);
-extern void ip_vs_sync_conn(struct net *net, struct ip_vs_conn *cp);
+extern void ip_vs_sync_conn(struct net *net, struct ip_vs_conn *cp, int pkts);
 
 
 /*