Merge branch 'master' of git://1984.lsi.us.es/net-next

9 files changed, 96 insertions, 92 deletions

diff --git a/include/linux/ip_vs.h b/include/linux/ip_vs.h
index be0ef3df4acb..8a2d438dc499 100644
--- a/include/linux/ip_vs.h
+++ b/include/linux/ip_vs.h
@@ -89,6 +89,7 @@
 #define IP_VS_CONN_F_TEMPLATE	0x1000		/* template, not connection */
 #define IP_VS_CONN_F_ONE_PACKET	0x2000		/* forward only one packet */
 
+/* Initial bits allowed in backup server */
 #define IP_VS_CONN_F_BACKUP_MASK (IP_VS_CONN_F_FWD_MASK | \
 				  IP_VS_CONN_F_NOOUTPUT | \
 				  IP_VS_CONN_F_INACTIVE | \
@@ -97,6 +98,10 @@
 				  IP_VS_CONN_F_TEMPLATE \
 				 )
 
+/* Bits allowed to update in backup server */
+#define IP_VS_CONN_F_BACKUP_UPD_MASK (IP_VS_CONN_F_INACTIVE | \
+				      IP_VS_CONN_F_SEQ_MASK)
+
 /* Flags that are not sent to backup server start from bit 16 */
 #define IP_VS_CONN_F_NFCT	(1 << 16)	/* use netfilter conntrack */
 
diff --git a/include/linux/netfilter/nf_conntrack_common.h b/include/linux/netfilter/nf_conntrack_common.h
index 0d3dd66322ec..d146872a0b91 100644
--- a/include/linux/netfilter/nf_conntrack_common.h
+++ b/include/linux/netfilter/nf_conntrack_common.h
@@ -83,6 +83,10 @@ enum ip_conntrack_status {
 	/* Conntrack is a fake untracked entry */
 	IPS_UNTRACKED_BIT = 12,
 	IPS_UNTRACKED = (1 << IPS_UNTRACKED_BIT),
+
+	/* Conntrack got a helper explicitly attached via CT target. */
+	IPS_HELPER_BIT = 13,
+	IPS_HELPER = (1 << IPS_HELPER_BIT),
 };
 
 /* Connection tracking event types */
diff --git a/include/linux/netfilter_ipv4/Kbuild b/include/linux/netfilter_ipv4/Kbuild
index 31f8bec95650..c61b8fb1a9ef 100644
--- a/include/linux/netfilter_ipv4/Kbuild
+++ b/include/linux/netfilter_ipv4/Kbuild
@@ -1,4 +1,3 @@
-header-y += ip_queue.h
 header-y += ip_tables.h
 header-y += ipt_CLUSTERIP.h
 header-y += ipt_ECN.h
diff --git a/include/linux/netfilter_ipv4/ip_queue.h b/include/linux/netfilter_ipv4/ip_queue.h
deleted file mode 100644
index a03507f465f8..000000000000
--- a/include/linux/netfilter_ipv4/ip_queue.h
+++ /dev/null
@@ -1,72 +0,0 @@
-/*
- * This is a module which is used for queueing IPv4 packets and
- * communicating with userspace via netlink.
- *
- * (C) 2000 James Morris, this code is GPL.
- */
-#ifndef _IP_QUEUE_H
-#define _IP_QUEUE_H
-
-#ifdef __KERNEL__
-#ifdef DEBUG_IPQ
-#define QDEBUG(x...) printk(KERN_DEBUG ## x)
-#else
-#define QDEBUG(x...)
-#endif  /* DEBUG_IPQ */
-#else
-#include <net/if.h>
-#endif	/* ! __KERNEL__ */
-
-/* Messages sent from kernel */
-typedef struct ipq_packet_msg {
-	unsigned long packet_id;	/* ID of queued packet */
-	unsigned long mark;		/* Netfilter mark value */
-	long timestamp_sec;		/* Packet arrival time (seconds) */
-	long timestamp_usec;		/* Packet arrvial time (+useconds) */
-	unsigned int hook;		/* Netfilter hook we rode in on */
-	char indev_name[IFNAMSIZ];	/* Name of incoming interface */
-	char outdev_name[IFNAMSIZ];	/* Name of outgoing interface */
-	__be16 hw_protocol;		/* Hardware protocol (network order) */
-	unsigned short hw_type;		/* Hardware type */
-	unsigned char hw_addrlen;	/* Hardware address length */
-	unsigned char hw_addr[8];	/* Hardware address */
-	size_t data_len;		/* Length of packet data */
-	unsigned char payload[0];	/* Optional packet data */
-} ipq_packet_msg_t;
-
-/* Messages sent from userspace */
-typedef struct ipq_mode_msg {
-	unsigned char value;		/* Requested mode */
-	size_t range;			/* Optional range of packet requested */
-} ipq_mode_msg_t;
-
-typedef struct ipq_verdict_msg {
-	unsigned int value;		/* Verdict to hand to netfilter */
-	unsigned long id;		/* Packet ID for this verdict */
-	size_t data_len;		/* Length of replacement data */
-	unsigned char payload[0];	/* Optional replacement packet */
-} ipq_verdict_msg_t;
-
-typedef struct ipq_peer_msg {
-	union {
-		ipq_verdict_msg_t verdict;
-		ipq_mode_msg_t mode;
-	} msg;
-} ipq_peer_msg_t;
-
-/* Packet delivery modes */
-enum {
-	IPQ_COPY_NONE,		/* Initial mode, packets are dropped */
-	IPQ_COPY_META,		/* Copy metadata */
-	IPQ_COPY_PACKET		/* Copy metadata + packet (range) */
-};
-#define IPQ_COPY_MAX IPQ_COPY_PACKET
-
-/* Types of messages */
-#define IPQM_BASE	0x10	/* standard netlink messages below this */
-#define IPQM_MODE	(IPQM_BASE + 1)		/* Mode request from peer */
-#define IPQM_VERDICT	(IPQM_BASE + 2)		/* Verdict from peer */ 
-#define IPQM_PACKET	(IPQM_BASE + 3)		/* Packet from kernel */
-#define IPQM_MAX	(IPQM_BASE + 4)
-
-#endif /*_IP_QUEUE_H*/
diff --git a/include/linux/netlink.h b/include/linux/netlink.h
index a2092f582a78..0f628ffa420c 100644
--- a/include/linux/netlink.h
+++ b/include/linux/netlink.h
@@ -7,7 +7,7 @@
 #define NETLINK_ROUTE		0	/* Routing/device hook				*/
 #define NETLINK_UNUSED		1	/* Unused number				*/
 #define NETLINK_USERSOCK	2	/* Reserved for user mode socket protocols 	*/
-#define NETLINK_FIREWALL	3	/* Firewalling hook				*/
+#define NETLINK_FIREWALL	3	/* Unused number, formerly ip_queue		*/
 #define NETLINK_SOCK_DIAG	4	/* socket monitoring				*/
 #define NETLINK_NFLOG		5	/* netfilter/iptables ULOG */
 #define NETLINK_XFRM		6	/* ipsec */
diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index 93b81aa73429..d6146b4811c2 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -504,6 +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 */
@@ -783,6 +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 */
@@ -869,10 +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 */
@@ -888,13 +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;
@@ -911,6 +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
 
@@ -921,7 +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)
@@ -929,6 +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)
@@ -941,11 +988,36 @@ 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
 
 /*
@@ -1185,7 +1257,6 @@ extern void ip_vs_scheduler_err(struct ip_vs_service *svc, const char *msg);
 extern struct ip_vs_stats ip_vs_stats;
 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);
@@ -1219,7 +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);
 
 
 /*
diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h
index ab86036bbf0c..cce7f6a798bf 100644
--- a/include/net/netfilter/nf_conntrack.h
+++ b/include/net/netfilter/nf_conntrack.h
@@ -321,14 +321,8 @@ extern unsigned int nf_conntrack_max;
 extern unsigned int nf_conntrack_hash_rnd;
 void init_nf_conntrack_hash_rnd(void);
 
-#define NF_CT_STAT_INC(net, count)	\
-	__this_cpu_inc((net)->ct.stat->count)
-#define NF_CT_STAT_INC_ATOMIC(net, count)		\
-do {							\
-	local_bh_disable();				\
-	__this_cpu_inc((net)->ct.stat->count);		\
-	local_bh_enable();				\
-} while (0)
+#define NF_CT_STAT_INC(net, count)	  __this_cpu_inc((net)->ct.stat->count)
+#define NF_CT_STAT_INC_ATOMIC(net, count) this_cpu_inc((net)->ct.stat->count)
 
 #define MODULE_ALIAS_NFCT_HELPER(helper) \
         MODULE_ALIAS("nfct-helper-" helper)
diff --git a/include/net/netfilter/nf_conntrack_helper.h b/include/net/netfilter/nf_conntrack_helper.h
index 5767dc242dee..1d1889409b9e 100644
--- a/include/net/netfilter/nf_conntrack_helper.h
+++ b/include/net/netfilter/nf_conntrack_helper.h
@@ -60,8 +60,8 @@ static inline struct nf_conn_help *nfct_help(const struct nf_conn *ct)
 	return nf_ct_ext_find(ct, NF_CT_EXT_HELPER);
 }
 
-extern int nf_conntrack_helper_init(void);
-extern void nf_conntrack_helper_fini(void);
+extern int nf_conntrack_helper_init(struct net *net);
+extern void nf_conntrack_helper_fini(struct net *net);
 
 extern int nf_conntrack_broadcast_help(struct sk_buff *skb,
 				       unsigned int protoff,
diff --git a/include/net/netns/conntrack.h b/include/net/netns/conntrack.h
index 7a911eca0f18..a053a19870cf 100644
--- a/include/net/netns/conntrack.h
+++ b/include/net/netns/conntrack.h
@@ -26,11 +26,14 @@ struct netns_ct {
 	int			sysctl_tstamp;
 	int			sysctl_checksum;
 	unsigned int		sysctl_log_invalid; /* Log invalid packets */
+	int			sysctl_auto_assign_helper;
+	bool			auto_assign_helper_warned;
 #ifdef CONFIG_SYSCTL
 	struct ctl_table_header	*sysctl_header;
 	struct ctl_table_header	*acct_sysctl_header;
 	struct ctl_table_header	*tstamp_sysctl_header;
 	struct ctl_table_header	*event_sysctl_header;
+	struct ctl_table_header	*helper_sysctl_header;
 #endif
 	char			*slabname;
 };