Merge branch 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/kaber/nf-next-2.6

include/linux/audit.h

@@ -103,6 +103,8 @@
 #define AUDIT_BPRM_FCAPS	1321	/* Information about fcaps increasing perms */
 #define AUDIT_CAPSET		1322	/* Record showing argument to sys_capset */
 #define AUDIT_MMAP		1323	/* Record showing descriptor and flags in mmap */
+#define AUDIT_NETFILTER_PKT	1324	/* Packets traversing netfilter chains */
+#define AUDIT_NETFILTER_CFG	1325	/* Netfilter chain modifications */
 
 #define AUDIT_AVC		1400	/* SE Linux avc denial or grant */
 #define AUDIT_SELINUX_ERR	1401	/* Internal SE Linux Errors */

include/linux/ip_vs.h

@@ -89,6 +89,14 @@
 #define IP_VS_CONN_F_TEMPLATE	0x1000		/* template, not connection */
 #define IP_VS_CONN_F_ONE_PACKET	0x2000		/* forward only one packet */
 
+#define IP_VS_CONN_F_BACKUP_MASK (IP_VS_CONN_F_FWD_MASK | \
+				  IP_VS_CONN_F_NOOUTPUT | \
+				  IP_VS_CONN_F_INACTIVE | \
+				  IP_VS_CONN_F_SEQ_MASK | \
+				  IP_VS_CONN_F_NO_CPORT | \
+				  IP_VS_CONN_F_TEMPLATE \
+				 )
+
 /* Flags that are not sent to backup server start from bit 16 */
 #define IP_VS_CONN_F_NFCT	(1 << 16)	/* use netfilter conntrack */
 

include/linux/netfilter.h

@@ -24,16 +24,20 @@
 #define NF_MAX_VERDICT NF_STOP
 
 /* we overload the higher bits for encoding auxiliary data such as the queue
- * number. Not nice, but better than additional function arguments. */
-#define NF_VERDICT_MASK 0x0000ffff
-#define NF_VERDICT_BITS 16
+ * number or errno values. Not nice, but better than additional function
+ * arguments. */
+#define NF_VERDICT_MASK 0x000000ff
+
+/* extra verdict flags have mask 0x0000ff00 */
+#define NF_VERDICT_FLAG_QUEUE_BYPASS	0x00008000
 
+/* queue number (NF_QUEUE) or errno (NF_DROP) */
 #define NF_VERDICT_QMASK 0xffff0000
 #define NF_VERDICT_QBITS 16
 
-#define NF_QUEUE_NR(x) ((((x) << NF_VERDICT_BITS) & NF_VERDICT_QMASK) | NF_QUEUE)
+#define NF_QUEUE_NR(x) ((((x) << 16) & NF_VERDICT_QMASK) | NF_QUEUE)
 
-#define NF_DROP_ERR(x) (((-x) << NF_VERDICT_BITS) | NF_DROP)
+#define NF_DROP_ERR(x) (((-x) << 16) | NF_DROP)
 
 /* only for userspace compatibility */
 #ifndef __KERNEL__
@@ -41,6 +45,9 @@
    <= 0x2000 is used for protocol-flags. */
 #define NFC_UNKNOWN 0x4000
 #define NFC_ALTERED 0x8000
+
+/* NF_VERDICT_BITS should be 8 now, but userspace might break if this changes */
+#define NF_VERDICT_BITS 16
 #endif
 
 enum nf_inet_hooks {
@@ -72,6 +79,10 @@ union nf_inet_addr {
 
 #ifdef __KERNEL__
 #ifdef CONFIG_NETFILTER
+static inline int NF_DROP_GETERR(int verdict)
+{
+	return -(verdict >> NF_VERDICT_QBITS);
+}
 
 static inline int nf_inet_addr_cmp(const union nf_inet_addr *a1,
 				   const union nf_inet_addr *a2)
@@ -267,7 +278,7 @@ struct nf_afinfo {
 	int		route_key_size;
 };
 
-extern const struct nf_afinfo *nf_afinfo[NFPROTO_NUMPROTO];
+extern const struct nf_afinfo __rcu *nf_afinfo[NFPROTO_NUMPROTO];
 static inline const struct nf_afinfo *nf_get_afinfo(unsigned short family)
 {
 	return rcu_dereference(nf_afinfo[family]);
@@ -357,9 +368,9 @@ nf_nat_decode_session(struct sk_buff *skb, struct flowi *fl, u_int8_t family)
 #endif /*CONFIG_NETFILTER*/
 
 #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
-extern void (*ip_ct_attach)(struct sk_buff *, struct sk_buff *);
+extern void (*ip_ct_attach)(struct sk_buff *, struct sk_buff *) __rcu;
 extern void nf_ct_attach(struct sk_buff *, struct sk_buff *);
-extern void (*nf_ct_destroy)(struct nf_conntrack *);
+extern void (*nf_ct_destroy)(struct nf_conntrack *) __rcu;
 #else
 static inline void nf_ct_attach(struct sk_buff *new, struct sk_buff *skb) {}
 #endif

include/linux/netfilter/Kbuild

@@ -9,6 +9,7 @@ header-y += nfnetlink_conntrack.h
 header-y += nfnetlink_log.h
 header-y += nfnetlink_queue.h
 header-y += x_tables.h
+header-y += xt_AUDIT.h
 header-y += xt_CHECKSUM.h
 header-y += xt_CLASSIFY.h
 header-y += xt_CONNMARK.h
@@ -55,6 +56,7 @@ header-y += xt_rateest.h
 header-y += xt_realm.h
 header-y += xt_recent.h
 header-y += xt_sctp.h
+header-y += xt_socket.h
 header-y += xt_state.h
 header-y += xt_statistic.h
 header-y += xt_string.h

include/linux/netfilter/nf_conntrack_snmp.h

@@ -0,0 +1,9 @@
+#ifndef _NF_CONNTRACK_SNMP_H
+#define _NF_CONNTRACK_SNMP_H
+
+extern int (*nf_nat_snmp_hook)(struct sk_buff *skb,
+				unsigned int protoff,
+				struct nf_conn *ct,
+				enum ip_conntrack_info ctinfo);
+
+#endif /* _NF_CONNTRACK_SNMP_H */

include/linux/netfilter/nfnetlink_conntrack.h

@@ -42,6 +42,7 @@ enum ctattr_type {
 	CTA_SECMARK,		/* obsolete */
 	CTA_ZONE,
 	CTA_SECCTX,
+	CTA_TIMESTAMP,
 	__CTA_MAX
 };
 #define CTA_MAX (__CTA_MAX - 1)
@@ -127,6 +128,14 @@ enum ctattr_counters {
 };
 #define CTA_COUNTERS_MAX (__CTA_COUNTERS_MAX - 1)
 
+enum ctattr_tstamp {
+	CTA_TIMESTAMP_UNSPEC,
+	CTA_TIMESTAMP_START,
+	CTA_TIMESTAMP_STOP,
+	__CTA_TIMESTAMP_MAX
+};
+#define CTA_TIMESTAMP_MAX (__CTA_TIMESTAMP_MAX - 1)
+
 enum ctattr_nat {
 	CTA_NAT_UNSPEC,
 	CTA_NAT_MINIP,

include/linux/netfilter/x_tables.h

@@ -611,8 +611,9 @@ struct _compat_xt_align {
 extern void xt_compat_lock(u_int8_t af);
 extern void xt_compat_unlock(u_int8_t af);
 
-extern int xt_compat_add_offset(u_int8_t af, unsigned int offset, short delta);
+extern int xt_compat_add_offset(u_int8_t af, unsigned int offset, int delta);
 extern void xt_compat_flush_offsets(u_int8_t af);
+extern void xt_compat_init_offsets(u_int8_t af, unsigned int number);
 extern int xt_compat_calc_jump(u_int8_t af, unsigned int offset);
 
 extern int xt_compat_match_offset(const struct xt_match *match);

include/linux/netfilter/xt_AUDIT.h

@@ -0,0 +1,30 @@
+/*
+ * Header file for iptables xt_AUDIT target
+ *
+ * (C) 2010-2011 Thomas Graf <tgraf@redhat.com>
+ * (C) 2010-2011 Red Hat, Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef _XT_AUDIT_TARGET_H
+#define _XT_AUDIT_TARGET_H
+
+#include <linux/types.h>
+
+enum {
+	XT_AUDIT_TYPE_ACCEPT = 0,
+	XT_AUDIT_TYPE_DROP,
+	XT_AUDIT_TYPE_REJECT,
+	__XT_AUDIT_TYPE_MAX,
+};
+
+#define XT_AUDIT_TYPE_MAX (__XT_AUDIT_TYPE_MAX - 1)
+
+struct xt_audit_info {
+	__u8 type; /* XT_AUDIT_TYPE_* */
+};
+
+#endif /* _XT_AUDIT_TARGET_H */

include/linux/netfilter/xt_CT.h

@@ -4,11 +4,11 @@
 #define XT_CT_NOTRACK	0x1
 
 struct xt_ct_target_info {
-	u_int16_t	flags;
-	u_int16_t	zone;
-	u_int32_t	ct_events;
-	u_int32_t	exp_events;
-	char		helper[16];
+	__u16 flags;
+	__u16 zone;
+	__u32 ct_events;
+	__u32 exp_events;
+	char helper[16];
 
 	/* Used internally by the kernel */
 	struct nf_conn	*ct __attribute__((aligned(8)));

include/linux/netfilter/xt_NFQUEUE.h

@@ -20,4 +20,10 @@ struct xt_NFQ_info_v1 {
 	__u16 queues_total;
 };
 
+struct xt_NFQ_info_v2 {
+	__u16 queuenum;
+	__u16 queues_total;
+	__u16 bypass;
+};
+
 #endif /* _XT_NFQ_TARGET_H */

include/linux/netfilter/xt_TCPOPTSTRIP.h

@@ -7,7 +7,7 @@
 	(((1U << (idx & 31)) & bmap[(idx) >> 5]) != 0)
 
 struct xt_tcpoptstrip_target_info {
-	u_int32_t strip_bmap[8];
+	__u32 strip_bmap[8];
 };
 
 #endif /* _XT_TCPOPTSTRIP_H */

include/linux/netfilter/xt_TPROXY.h

@@ -5,15 +5,15 @@
  * redirection. We can get rid of that whenever we get support for
  * mutliple targets in the same rule. */
 struct xt_tproxy_target_info {
-	u_int32_t mark_mask;
-	u_int32_t mark_value;
+	__u32 mark_mask;
+	__u32 mark_value;
 	__be32 laddr;
 	__be16 lport;
 };
 
 struct xt_tproxy_target_info_v1 {
-	u_int32_t mark_mask;
-	u_int32_t mark_value;
+	__u32 mark_mask;
+	__u32 mark_value;
 	union nf_inet_addr laddr;
 	__be16 lport;
 };

include/linux/netfilter/xt_cluster.h

@@ -6,10 +6,10 @@ enum xt_cluster_flags {
 };
 
 struct xt_cluster_match_info {
-	u_int32_t		total_nodes;
-	u_int32_t		node_mask;
-	u_int32_t		hash_seed;
-	u_int32_t		flags;
+	__u32 total_nodes;
+	__u32 node_mask;
+	__u32 hash_seed;
+	__u32 flags;
 };
 
 #define XT_CLUSTER_NODES_MAX	32

include/linux/netfilter/xt_comment.h

@@ -4,7 +4,7 @@
 #define XT_MAX_COMMENT_LEN 256
 
 struct xt_comment_info {
-	unsigned char comment[XT_MAX_COMMENT_LEN];
+	char comment[XT_MAX_COMMENT_LEN];
 };
 
 #endif /* XT_COMMENT_H */

include/linux/netfilter/xt_conntrack.h

@@ -58,4 +58,19 @@ struct xt_conntrack_mtinfo2 {
 	__u16 state_mask, status_mask;
 };
 
+struct xt_conntrack_mtinfo3 {
+	union nf_inet_addr origsrc_addr, origsrc_mask;
+	union nf_inet_addr origdst_addr, origdst_mask;
+	union nf_inet_addr replsrc_addr, replsrc_mask;
+	union nf_inet_addr repldst_addr, repldst_mask;
+	__u32 expires_min, expires_max;
+	__u16 l4proto;
+	__u16 origsrc_port, origdst_port;
+	__u16 replsrc_port, repldst_port;
+	__u16 match_flags, invert_flags;
+	__u16 state_mask, status_mask;
+	__u16 origsrc_port_high, origdst_port_high;
+	__u16 replsrc_port_high, repldst_port_high;
+};
+
 #endif /*_XT_CONNTRACK_H*/

include/linux/netfilter/xt_quota.h

@@ -9,9 +9,9 @@ enum xt_quota_flags {
 struct xt_quota_priv;
 
 struct xt_quota_info {
-	u_int32_t		flags;
-	u_int32_t		pad;
-	aligned_u64		quota;
+	__u32 flags;
+	__u32 pad;
+	aligned_u64 quota;
 
 	/* Used internally by the kernel */
 	struct xt_quota_priv	*master;

include/linux/netfilter/xt_time.h

@@ -2,13 +2,13 @@
 #define _XT_TIME_H 1
 
 struct xt_time_info {
-	u_int32_t date_start;
-	u_int32_t date_stop;
-	u_int32_t daytime_start;
-	u_int32_t daytime_stop;
-	u_int32_t monthdays_match;
-	u_int8_t weekdays_match;
-	u_int8_t flags;
+	__u32 date_start;
+	__u32 date_stop;
+	__u32 daytime_start;
+	__u32 daytime_stop;
+	__u32 monthdays_match;
+	__u8 weekdays_match;
+	__u8 flags;
 };
 
 enum {

include/linux/netfilter/xt_u32.h

@@ -9,13 +9,13 @@ enum xt_u32_ops {
 };
 
 struct xt_u32_location_element {
-	u_int32_t number;
-	u_int8_t nextop;
+	__u32 number;
+	__u8 nextop;
 };
 
 struct xt_u32_value_element {
-	u_int32_t min;
-	u_int32_t max;
+	__u32 min;
+	__u32 max;
 };
 
 /*
@@ -27,14 +27,14 @@ struct xt_u32_value_element {
 struct xt_u32_test {
 	struct xt_u32_location_element location[XT_U32_MAXSIZE+1];
 	struct xt_u32_value_element value[XT_U32_MAXSIZE+1];
-	u_int8_t nnums;
-	u_int8_t nvalues;
+	__u8 nnums;
+	__u8 nvalues;
 };
 
 struct xt_u32 {
 	struct xt_u32_test tests[XT_U32_MAXSIZE+1];
-	u_int8_t ntests;
-	u_int8_t invert;
+	__u8 ntests;
+	__u8 invert;
 };
 
 #endif /* _XT_U32_H */

include/linux/netfilter_bridge/ebt_802_3.h

@@ -24,24 +24,24 @@
 
 /* ui has one byte ctrl, ni has two */
 struct hdr_ui {
-	uint8_t dsap;
-	uint8_t ssap;
-	uint8_t ctrl;
-	uint8_t orig[3];
+	__u8 dsap;
+	__u8 ssap;
+	__u8 ctrl;
+	__u8 orig[3];
 	__be16 type;
 };
 
 struct hdr_ni {
-	uint8_t dsap;
-	uint8_t ssap;
+	__u8 dsap;
+	__u8 ssap;
 	__be16 ctrl;
-	uint8_t  orig[3];
+	__u8  orig[3];
 	__be16 type;
 };
 
 struct ebt_802_3_hdr {
-	uint8_t  daddr[6];
-	uint8_t  saddr[6];
+	__u8  daddr[6];
+	__u8  saddr[6];
 	__be16 len;
 	union {
 		struct hdr_ui ui;
@@ -59,10 +59,10 @@ static inline struct ebt_802_3_hdr *ebt_802_3_hdr(const struct sk_buff *skb)
 #endif
 
 struct ebt_802_3_info {
-	uint8_t  sap;
+	__u8  sap;
 	__be16 type;
-	uint8_t  bitmask;
-	uint8_t  invflags;
+	__u8  bitmask;
+	__u8  invflags;
 };
 
 #endif

include/linux/netfilter_bridge/ebt_among.h

@@ -30,7 +30,7 @@
  */
 
 struct ebt_mac_wormhash_tuple {
-	uint32_t cmp[2];
+	__u32 cmp[2];
 	__be32 ip;
 };
 

include/linux/netfilter_bridge/ebt_arp.h

@@ -27,8 +27,8 @@ struct ebt_arp_info
 	unsigned char smmsk[ETH_ALEN];
 	unsigned char dmaddr[ETH_ALEN];
 	unsigned char dmmsk[ETH_ALEN];
-	uint8_t  bitmask;
-	uint8_t  invflags;
+	__u8  bitmask;
+	__u8  invflags;
 };
 
 #endif

include/linux/netfilter_bridge/ebt_ip.h

@@ -31,12 +31,12 @@ struct ebt_ip_info {
 	__be32 daddr;
 	__be32 smsk;
 	__be32 dmsk;
-	uint8_t  tos;
-	uint8_t  protocol;
-	uint8_t  bitmask;
-	uint8_t  invflags;
-	uint16_t sport[2];
-	uint16_t dport[2];
+	__u8  tos;
+	__u8  protocol;
+	__u8  bitmask;
+	__u8  invflags;
+	__u16 sport[2];
+	__u16 dport[2];
 };
 
 #endif

include/linux/netfilter_bridge/ebt_ip6.h

@@ -18,8 +18,11 @@
 #define EBT_IP6_PROTO 0x08
 #define EBT_IP6_SPORT 0x10
 #define EBT_IP6_DPORT 0x20
+#define EBT_IP6_ICMP6 0x40
+
 #define EBT_IP6_MASK (EBT_IP6_SOURCE | EBT_IP6_DEST | EBT_IP6_TCLASS |\
-		      EBT_IP6_PROTO | EBT_IP6_SPORT | EBT_IP6_DPORT)
+		      EBT_IP6_PROTO | EBT_IP6_SPORT | EBT_IP6_DPORT | \
+		      EBT_IP6_ICMP6)
 #define EBT_IP6_MATCH "ip6"
 
 /* the same values are used for the invflags */
@@ -28,12 +31,18 @@ struct ebt_ip6_info {
 	struct in6_addr daddr;
 	struct in6_addr smsk;
 	struct in6_addr dmsk;
-	uint8_t  tclass;
-	uint8_t  protocol;
-	uint8_t  bitmask;
-	uint8_t  invflags;
-	uint16_t sport[2];
-	uint16_t dport[2];
+	__u8  tclass;
+	__u8  protocol;
+	__u8  bitmask;
+	__u8  invflags;
+	union {
+		__u16 sport[2];
+		__u8 icmpv6_type[2];
+	};
+	union {
+		__u16 dport[2];
+		__u8 icmpv6_code[2];
+	};
 };
 
 #endif

include/linux/netfilter_bridge/ebt_limit.h

@@ -10,13 +10,13 @@
    seconds, or one every 59 hours. */
 
 struct ebt_limit_info {
-	u_int32_t avg;    /* Average secs between packets * scale */
-	u_int32_t burst;  /* Period multiplier for upper limit. */
+	__u32 avg;    /* Average secs between packets * scale */
+	__u32 burst;  /* Period multiplier for upper limit. */
 
 	/* Used internally by the kernel */
 	unsigned long prev;
-	u_int32_t credit;
-	u_int32_t credit_cap, cost;
+	__u32 credit;
+	__u32 credit_cap, cost;
 };
 
 #endif

include/linux/netfilter_bridge/ebt_log.h

@@ -10,9 +10,9 @@
 #define EBT_LOG_WATCHER "log"
 
 struct ebt_log_info {
-	uint8_t loglevel;
-	uint8_t prefix[EBT_LOG_PREFIX_SIZE];
-	uint32_t bitmask;
+	__u8 loglevel;
+	__u8 prefix[EBT_LOG_PREFIX_SIZE];
+	__u32 bitmask;
 };
 
 #endif

include/linux/netfilter_bridge/ebt_mark_m.h

@@ -6,8 +6,8 @@
 #define EBT_MARK_MASK (EBT_MARK_AND | EBT_MARK_OR)
 struct ebt_mark_m_info {
 	unsigned long mark, mask;
-	uint8_t invert;
-	uint8_t bitmask;
+	__u8 invert;
+	__u8 bitmask;
 };
 #define EBT_MARK_MATCH "mark_m"
 

include/linux/netfilter_bridge/ebt_nflog.h

@@ -10,11 +10,11 @@
 #define EBT_NFLOG_DEFAULT_THRESHOLD	1
 
 struct ebt_nflog_info {
-	u_int32_t len;
-	u_int16_t group;
-	u_int16_t threshold;
-	u_int16_t flags;
-	u_int16_t pad;
+	__u32 len;
+	__u16 group;
+	__u16 threshold;
+	__u16 flags;
+	__u16 pad;
 	char prefix[EBT_NFLOG_PREFIX_SIZE];
 };
 

include/linux/netfilter_bridge/ebt_pkttype.h

@@ -2,8 +2,8 @@
 #define __LINUX_BRIDGE_EBT_PKTTYPE_H
 
 struct ebt_pkttype_info {
-	uint8_t pkt_type;
-	uint8_t invert;
+	__u8 pkt_type;
+	__u8 invert;
 };
 #define EBT_PKTTYPE_MATCH "pkttype"
 

include/linux/netfilter_bridge/ebt_stp.h

@@ -21,24 +21,24 @@
 #define EBT_STP_MATCH "stp"
 
 struct ebt_stp_config_info {
-	uint8_t flags;
-	uint16_t root_priol, root_priou;
+	__u8 flags;
+	__u16 root_priol, root_priou;
 	char root_addr[6], root_addrmsk[6];
-	uint32_t root_costl, root_costu;
-	uint16_t sender_priol, sender_priou;
+	__u32 root_costl, root_costu;
+	__u16 sender_priol, sender_priou;
 	char sender_addr[6], sender_addrmsk[6];
-	uint16_t portl, portu;
-	uint16_t msg_agel, msg_ageu;
-	uint16_t max_agel, max_ageu;
-	uint16_t hello_timel, hello_timeu;
-	uint16_t forward_delayl, forward_delayu;
+	__u16 portl, portu;
+	__u16 msg_agel, msg_ageu;
+	__u16 max_agel, max_ageu;
+	__u16 hello_timel, hello_timeu;
+	__u16 forward_delayl, forward_delayu;
 };
 
 struct ebt_stp_info {
-	uint8_t type;
+	__u8 type;
 	struct ebt_stp_config_info config;
-	uint16_t bitmask;
-	uint16_t invflags;
+	__u16 bitmask;
+	__u16 invflags;
 };
 
 #endif

include/linux/netfilter_bridge/ebt_ulog.h

@@ -10,7 +10,7 @@
 #define EBT_ULOG_VERSION 1
 
 struct ebt_ulog_info {
-	uint32_t nlgroup;
+	__u32 nlgroup;
 	unsigned int cprange;
 	unsigned int qthreshold;
 	char prefix[EBT_ULOG_PREFIX_LEN];

include/linux/netfilter_bridge/ebt_vlan.h

@@ -8,12 +8,12 @@
 #define EBT_VLAN_MATCH "vlan"
 
 struct ebt_vlan_info {
-	uint16_t id;		/* VLAN ID {1-4095} */
-	uint8_t prio;		/* VLAN User Priority {0-7} */
+	__u16 id;		/* VLAN ID {1-4095} */
+	__u8 prio;		/* VLAN User Priority {0-7} */
 	__be16 encap;		/* VLAN Encapsulated frame code {0-65535} */
-	uint8_t bitmask;		/* Args bitmask bit 1=1 - ID arg,
+	__u8 bitmask;		/* Args bitmask bit 1=1 - ID arg,
 				   bit 2=1 User-Priority arg, bit 3=1 encap*/
-	uint8_t invflags;		/* Inverse bitmask  bit 1=1 - inversed ID arg, 
+	__u8 invflags;		/* Inverse bitmask  bit 1=1 - inversed ID arg, 
 				   bit 2=1 - inversed Pirority arg */
 };
 

include/linux/netfilter_ipv4/ipt_CLUSTERIP.h

@@ -17,15 +17,15 @@ struct clusterip_config;
 
 struct ipt_clusterip_tgt_info {
 
-	u_int32_t flags;
+	__u32 flags;
 
 	/* only relevant for new ones */
-	u_int8_t clustermac[6];
-	u_int16_t num_total_nodes;
-	u_int16_t num_local_nodes;
-	u_int16_t local_nodes[CLUSTERIP_MAX_NODES];
-	u_int32_t hash_mode;
-	u_int32_t hash_initval;
+	__u8 clustermac[6];
+	__u16 num_total_nodes;
+	__u16 num_local_nodes;
+	__u16 local_nodes[CLUSTERIP_MAX_NODES];
+	__u32 hash_mode;
+	__u32 hash_initval;
 
 	/* Used internally by the kernel */
 	struct clusterip_config *config;

include/linux/netfilter_ipv4/ipt_ECN.h

@@ -19,11 +19,11 @@
 #define IPT_ECN_OP_MASK		0xce
 
 struct ipt_ECN_info {
-	u_int8_t operation;	/* bitset of operations */
-	u_int8_t ip_ect;	/* ECT codepoint of IPv4 header, pre-shifted */
+	__u8 operation;	/* bitset of operations */
+	__u8 ip_ect;	/* ECT codepoint of IPv4 header, pre-shifted */
 	union {
 		struct {
-			u_int8_t ece:1, cwr:1; /* TCP ECT bits */
+			__u8 ece:1, cwr:1; /* TCP ECT bits */
 		} tcp;
 	} proto;
 };

include/linux/netfilter_ipv4/ipt_SAME.h

@@ -7,9 +7,9 @@
 
 struct ipt_same_info {
 	unsigned char info;
-	u_int32_t rangesize;
-	u_int32_t ipnum;
-	u_int32_t *iparray;
+	__u32 rangesize;
+	__u32 ipnum;
+	__u32 *iparray;
 
 	/* hangs off end. */
 	struct nf_nat_range range[IPT_SAME_MAX_RANGE];

include/linux/netfilter_ipv4/ipt_TTL.h

@@ -13,8 +13,8 @@ enum {
 #define IPT_TTL_MAXMODE	IPT_TTL_DEC
 
 struct ipt_TTL_info {
-	u_int8_t	mode;
-	u_int8_t	ttl;
+	__u8	mode;
+	__u8	ttl;
 };
 
 

include/linux/netfilter_ipv4/ipt_addrtype.h

@@ -9,17 +9,17 @@ enum {
 };
 
 struct ipt_addrtype_info_v1 {
-	u_int16_t	source;		/* source-type mask */
-	u_int16_t	dest;		/* dest-type mask */
-	u_int32_t	flags;
+	__u16	source;		/* source-type mask */
+	__u16	dest;		/* dest-type mask */
+	__u32	flags;
 };
 
 /* revision 0 */
 struct ipt_addrtype_info {
-	u_int16_t	source;		/* source-type mask */
-	u_int16_t	dest;		/* dest-type mask */
-	u_int32_t	invert_source;
-	u_int32_t	invert_dest;
+	__u16	source;		/* source-type mask */
+	__u16	dest;		/* dest-type mask */
+	__u32	invert_source;
+	__u32	invert_dest;
 };
 
 #endif

include/linux/netfilter_ipv4/ipt_ah.h

@@ -2,8 +2,8 @@
 #define _IPT_AH_H
 
 struct ipt_ah {
-	u_int32_t spis[2];			/* Security Parameter Index */
-	u_int8_t  invflags;			/* Inverse flags */
+	__u32 spis[2];			/* Security Parameter Index */
+	__u8  invflags;			/* Inverse flags */
 };
 
 

include/linux/netfilter_ipv4/ipt_ecn.h

@@ -20,12 +20,12 @@
 
 /* match info */
 struct ipt_ecn_info {
-	u_int8_t operation;
-	u_int8_t invert;
-	u_int8_t ip_ect;
+	__u8 operation;
+	__u8 invert;
+	__u8 ip_ect;
 	union {
 		struct {
-			u_int8_t ect;
+			__u8 ect;
 		} tcp;
 	} proto;
 };

include/linux/netfilter_ipv4/ipt_ttl.h

@@ -13,8 +13,8 @@ enum {
 
 
 struct ipt_ttl_info {
-	u_int8_t	mode;
-	u_int8_t	ttl;
+	__u8	mode;
+	__u8	ttl;
 };
 
 

include/linux/netfilter_ipv6/ip6t_HL.h

@@ -14,8 +14,8 @@ enum {
 #define IP6T_HL_MAXMODE	IP6T_HL_DEC
 
 struct ip6t_HL_info {
-	u_int8_t	mode;
-	u_int8_t	hop_limit;
+	__u8	mode;
+	__u8	hop_limit;
 };
 
 

include/linux/netfilter_ipv6/ip6t_REJECT.h

@@ -12,7 +12,7 @@ enum ip6t_reject_with {
 };
 
 struct ip6t_reject_info {
-	u_int32_t	with;	/* reject type */
+	__u32	with;	/* reject type */
 };
 
 #endif /*_IP6T_REJECT_H*/

include/linux/netfilter_ipv6/ip6t_ah.h

@@ -2,10 +2,10 @@
 #define _IP6T_AH_H
 
 struct ip6t_ah {
-	u_int32_t spis[2];			/* Security Parameter Index */
-	u_int32_t hdrlen;			/* Header Length */
-	u_int8_t  hdrres;			/* Test of the Reserved Filed */
-	u_int8_t  invflags;			/* Inverse flags */
+	__u32 spis[2];			/* Security Parameter Index */
+	__u32 hdrlen;			/* Header Length */
+	__u8  hdrres;			/* Test of the Reserved Filed */
+	__u8  invflags;			/* Inverse flags */
 };
 
 #define IP6T_AH_SPI 0x01

include/linux/netfilter_ipv6/ip6t_frag.h

@@ -2,10 +2,10 @@
 #define _IP6T_FRAG_H
 
 struct ip6t_frag {
-	u_int32_t ids[2];			/* Security Parameter Index */
-	u_int32_t hdrlen;			/* Header Length */
-	u_int8_t  flags;			/*  */
-	u_int8_t  invflags;			/* Inverse flags */
+	__u32 ids[2];			/* Security Parameter Index */
+	__u32 hdrlen;			/* Header Length */
+	__u8  flags;			/*  */
+	__u8  invflags;			/* Inverse flags */
 };
 
 #define IP6T_FRAG_IDS 		0x01

include/linux/netfilter_ipv6/ip6t_hl.h

@@ -14,8 +14,8 @@ enum {
 
 
 struct ip6t_hl_info {
-	u_int8_t	mode;
-	u_int8_t	hop_limit;
+	__u8	mode;
+	__u8	hop_limit;
 };
 
 

include/linux/netfilter_ipv6/ip6t_ipv6header.h

@@ -9,9 +9,9 @@ on whether they contain certain headers */
 #define __IPV6HEADER_H
 
 struct ip6t_ipv6header_info {
-	u_int8_t matchflags;
-	u_int8_t invflags;
-	u_int8_t modeflag;
+	__u8 matchflags;
+	__u8 invflags;
+	__u8 modeflag;
 };
 
 #define MASK_HOPOPTS    128

include/linux/netfilter_ipv6/ip6t_mh.h

@@ -3,8 +3,8 @@
 
 /* MH matching stuff */
 struct ip6t_mh {
-	u_int8_t types[2];	/* MH type range */
-	u_int8_t invflags;	/* Inverse flags */
+	__u8 types[2];	/* MH type range */
+	__u8 invflags;	/* Inverse flags */
 };
 
 /* Values for "invflags" field in struct ip6t_mh. */

include/linux/netfilter_ipv6/ip6t_opts.h

@@ -4,11 +4,11 @@
 #define IP6T_OPTS_OPTSNR 16
 
 struct ip6t_opts {
-	u_int32_t hdrlen;			/* Header Length */
-	u_int8_t flags;				/*  */
-	u_int8_t invflags;			/* Inverse flags */
-	u_int16_t opts[IP6T_OPTS_OPTSNR];	/* opts */
-	u_int8_t optsnr;			/* Nr of OPts */
+	__u32 hdrlen;			/* Header Length */
+	__u8 flags;				/*  */
+	__u8 invflags;			/* Inverse flags */
+	__u16 opts[IP6T_OPTS_OPTSNR];	/* opts */
+	__u8 optsnr;			/* Nr of OPts */
 };
 
 #define IP6T_OPTS_LEN 		0x01

include/linux/netfilter_ipv6/ip6t_rt.h

@@ -6,13 +6,13 @@
 #define IP6T_RT_HOPS 16
 
 struct ip6t_rt {
-	u_int32_t rt_type;			/* Routing Type */
-	u_int32_t segsleft[2];			/* Segments Left */
-	u_int32_t hdrlen;			/* Header Length */
-	u_int8_t  flags;			/*  */
-	u_int8_t  invflags;			/* Inverse flags */
+	__u32 rt_type;			/* Routing Type */
+	__u32 segsleft[2];			/* Segments Left */
+	__u32 hdrlen;			/* Header Length */
+	__u8  flags;			/*  */
+	__u8  invflags;			/* Inverse flags */
 	struct in6_addr addrs[IP6T_RT_HOPS];	/* Hops */
-	u_int8_t addrnr;			/* Nr of Addresses */
+	__u8 addrnr;			/* Nr of Addresses */
 };
 
 #define IP6T_RT_TYP 		0x01

include/net/dst.h

@@ -72,7 +72,7 @@ struct dst_entry {
 
 	u32			_metrics[RTAX_MAX];
 
-#ifdef CONFIG_NET_CLS_ROUTE
+#ifdef CONFIG_IP_ROUTE_CLASSID
 	__u32			tclassid;
 #else
 	__u32			__pad2;

include/net/ip_fib.h

@@ -55,7 +55,7 @@ struct fib_nh {
 	int			nh_weight;
 	int			nh_power;
 #endif
-#ifdef CONFIG_NET_CLS_ROUTE
+#ifdef CONFIG_IP_ROUTE_CLASSID
 	__u32			nh_tclassid;
 #endif
 	int			nh_oif;
@@ -201,7 +201,7 @@ static inline int fib_lookup(struct net *net, const struct flowi *flp,
 extern int __net_init fib4_rules_init(struct net *net);
 extern void __net_exit fib4_rules_exit(struct net *net);
 
-#ifdef CONFIG_NET_CLS_ROUTE
+#ifdef CONFIG_IP_ROUTE_CLASSID
 extern u32 fib_rules_tclass(struct fib_result *res);
 #endif
 
@@ -235,7 +235,7 @@ extern struct fib_table *fib_hash_table(u32 id);
 
 static inline void fib_combine_itag(u32 *itag, struct fib_result *res)
 {
-#ifdef CONFIG_NET_CLS_ROUTE
+#ifdef CONFIG_IP_ROUTE_CLASSID
 #ifdef CONFIG_IP_MULTIPLE_TABLES
 	u32 rtag;
 #endif

include/net/ip_vs.h

@@ -28,6 +28,80 @@
 #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
 #include <net/netfilter/nf_conntrack.h>
 #endif
+#include <net/net_namespace.h>		/* Netw namespace */
+
+/*
+ * Generic access of ipvs struct
+ */
+static inline struct netns_ipvs *net_ipvs(struct net* net)
+{
+	return net->ipvs;
+}
+/*
+ * Get net ptr from skb in traffic cases
+ * use skb_sknet when call is from userland (ioctl or netlink)
+ */
+static inline struct net *skb_net(const struct sk_buff *skb)
+{
+#ifdef CONFIG_NET_NS
+#ifdef CONFIG_IP_VS_DEBUG
+	/*
+	 * This is used for debug only.
+	 * Start with the most likely hit
+	 * End with BUG
+	 */
+	if (likely(skb->dev && skb->dev->nd_net))
+		return dev_net(skb->dev);
+	if (skb_dst(skb)->dev)
+		return dev_net(skb_dst(skb)->dev);
+	WARN(skb->sk, "Maybe skb_sknet should be used in %s() at line:%d\n",
+		      __func__, __LINE__);
+	if (likely(skb->sk && skb->sk->sk_net))
+		return sock_net(skb->sk);
+	pr_err("There is no net ptr to find in the skb in %s() line:%d\n",
+		__func__, __LINE__);
+	BUG();
+#else
+	return dev_net(skb->dev ? : skb_dst(skb)->dev);
+#endif
+#else
+	return &init_net;
+#endif
+}
+
+static inline struct net *skb_sknet(const struct sk_buff *skb)
+{
+#ifdef CONFIG_NET_NS
+#ifdef CONFIG_IP_VS_DEBUG
+	/* Start with the most likely hit */
+	if (likely(skb->sk && skb->sk->sk_net))
+		return sock_net(skb->sk);
+	WARN(skb->dev, "Maybe skb_net should be used instead in %s() line:%d\n",
+		       __func__, __LINE__);
+	if (likely(skb->dev && skb->dev->nd_net))
+		return dev_net(skb->dev);
+	pr_err("There is no net ptr to find in the skb in %s() line:%d\n",
+		__func__, __LINE__);
+	BUG();
+#else
+	return sock_net(skb->sk);
+#endif
+#else
+	return &init_net;
+#endif
+}
+/*
+ * This one needed for single_open_net since net is stored directly in
+ * private not as a struct i.e. seq_file_net cant be used.
+ */
+static inline struct net *seq_file_single_net(struct seq_file *seq)
+{
+#ifdef CONFIG_NET_NS
+	return (struct net *)seq->private;
+#else
+	return &init_net;
+#endif
+}
 
 /* Connections' size value needed by ip_vs_ctl.c */
 extern int ip_vs_conn_tab_size;
@@ -258,6 +332,23 @@ struct ip_vs_seq {
 						   before last resized pkt */
 };
 
+/*
+ * counters per cpu
+ */
+struct ip_vs_counters {
+	__u32		conns;		/* connections scheduled */
+	__u32		inpkts;		/* incoming packets */
+	__u32		outpkts;	/* outgoing packets */
+	__u64		inbytes;	/* incoming bytes */
+	__u64		outbytes;	/* outgoing bytes */
+};
+/*
+ * Stats per cpu
+ */
+struct ip_vs_cpu_stats {
+	struct ip_vs_counters   ustats;
+	struct u64_stats_sync   syncp;
+};
 
 /*
  *	IPVS statistics objects
@@ -279,17 +370,34 @@ struct ip_vs_estimator {
 };
 
 struct ip_vs_stats {
-	struct ip_vs_stats_user	ustats;         /* statistics */
+	struct ip_vs_stats_user	ustats;		/* statistics */
 	struct ip_vs_estimator	est;		/* estimator */
-
-	spinlock_t              lock;           /* spin lock */
+	struct ip_vs_cpu_stats	*cpustats;	/* per cpu counters */
+	spinlock_t		lock;		/* spin lock */
 };
 
+/*
+ * Helper Macros for per cpu
+ * ipvs->tot_stats->ustats.count
+ */
+#define IPVS_STAT_INC(ipvs, count)	\
+	__this_cpu_inc((ipvs)->ustats->count)
+
+#define IPVS_STAT_ADD(ipvs, count, value) \
+	do {\
+		write_seqcount_begin(per_cpu_ptr((ipvs)->ustats_seq, \
+				     raw_smp_processor_id())); \
+		__this_cpu_add((ipvs)->ustats->count, value); \
+		write_seqcount_end(per_cpu_ptr((ipvs)->ustats_seq, \
+				   raw_smp_processor_id())); \
+	} while (0)
+
 struct dst_entry;
 struct iphdr;
 struct ip_vs_conn;
 struct ip_vs_app;
 struct sk_buff;
+struct ip_vs_proto_data;
 
 struct ip_vs_protocol {
 	struct ip_vs_protocol	*next;
@@ -297,21 +405,22 @@ struct ip_vs_protocol {
 	u16			protocol;
 	u16			num_states;
 	int			dont_defrag;
-	atomic_t		appcnt;		/* counter of proto app incs */
-	int			*timeout_table;	/* protocol timeout table */
 
 	void (*init)(struct ip_vs_protocol *pp);
 
 	void (*exit)(struct ip_vs_protocol *pp);
 
+	void (*init_netns)(struct net *net, struct ip_vs_proto_data *pd);
+
+	void (*exit_netns)(struct net *net, struct ip_vs_proto_data *pd);
+
 	int (*conn_schedule)(int af, struct sk_buff *skb,
-			     struct ip_vs_protocol *pp,
+			     struct ip_vs_proto_data *pd,
 			     int *verdict, struct ip_vs_conn **cpp);
 
 	struct ip_vs_conn *
 	(*conn_in_get)(int af,
 		       const struct sk_buff *skb,
-		       struct ip_vs_protocol *pp,
 		       const struct ip_vs_iphdr *iph,
 		       unsigned int proto_off,
 		       int inverse);
@@ -319,7 +428,6 @@ struct ip_vs_protocol {
 	struct ip_vs_conn *
 	(*conn_out_get)(int af,
 			const struct sk_buff *skb,
-			struct ip_vs_protocol *pp,
 			const struct ip_vs_iphdr *iph,
 			unsigned int proto_off,
 			int inverse);
@@ -337,11 +445,11 @@ struct ip_vs_protocol {
 
 	int (*state_transition)(struct ip_vs_conn *cp, int direction,
 				const struct sk_buff *skb,
-				struct ip_vs_protocol *pp);
+				struct ip_vs_proto_data *pd);
 
-	int (*register_app)(struct ip_vs_app *inc);
+	int (*register_app)(struct net *net, struct ip_vs_app *inc);
 
-	void (*unregister_app)(struct ip_vs_app *inc);
+	void (*unregister_app)(struct net *net, struct ip_vs_app *inc);
 
 	int (*app_conn_bind)(struct ip_vs_conn *cp);
 
@@ -350,14 +458,26 @@ struct ip_vs_protocol {
 			     int offset,
 			     const char *msg);
 
-	void (*timeout_change)(struct ip_vs_protocol *pp, int flags);
+	void (*timeout_change)(struct ip_vs_proto_data *pd, int flags);
+};
 
-	int (*set_state_timeout)(struct ip_vs_protocol *pp, char *sname, int to);
+/*
+ * protocol data per netns
+ */
+struct ip_vs_proto_data {
+	struct ip_vs_proto_data	*next;
+	struct ip_vs_protocol	*pp;
+	int			*timeout_table;	/* protocol timeout table */
+	atomic_t		appcnt;		/* counter of proto app incs. */
+	struct tcp_states_t	*tcp_state_table;
 };
 
-extern struct ip_vs_protocol * ip_vs_proto_get(unsigned short proto);
+extern struct ip_vs_protocol   *ip_vs_proto_get(unsigned short proto);
+extern struct ip_vs_proto_data *ip_vs_proto_data_get(struct net *net,
+						     unsigned short proto);
 
 struct ip_vs_conn_param {
+	struct net			*net;
 	const union nf_inet_addr	*caddr;
 	const union nf_inet_addr	*vaddr;
 	__be16				cport;
@@ -375,16 +495,19 @@ struct ip_vs_conn_param {
  */
 struct ip_vs_conn {
 	struct list_head        c_list;         /* hashed list heads */
-
+#ifdef CONFIG_NET_NS
+	struct net              *net;           /* Name space */
+#endif
 	/* Protocol, addresses and port numbers */
-	u16                      af;		/* address family */
-	union nf_inet_addr       caddr;          /* client address */
-	union nf_inet_addr       vaddr;          /* virtual address */
-	union nf_inet_addr       daddr;          /* destination address */
-	volatile __u32           flags;          /* status flags */
-	__be16                   cport;
-	__be16                   vport;
-	__be16                   dport;
+	u16                     af;             /* address family */
+	__be16                  cport;
+	__be16                  vport;
+	__be16                  dport;
+	__u32                   fwmark;         /* Fire wall mark from skb */
+	union nf_inet_addr      caddr;          /* client address */
+	union nf_inet_addr      vaddr;          /* virtual address */
+	union nf_inet_addr      daddr;          /* destination address */
+	volatile __u32          flags;          /* status flags */
 	__u16                   protocol;       /* Which protocol (TCP/UDP) */
 
 	/* counter and timer */
@@ -422,10 +545,38 @@ struct ip_vs_conn {
 	struct ip_vs_seq        in_seq;         /* incoming seq. struct */
 	struct ip_vs_seq        out_seq;        /* outgoing seq. struct */
 
+	const struct ip_vs_pe	*pe;
 	char			*pe_data;
 	__u8			pe_data_len;
 };
 
+/*
+ *  To save some memory in conn table when name space is disabled.
+ */
+static inline struct net *ip_vs_conn_net(const struct ip_vs_conn *cp)
+{
+#ifdef CONFIG_NET_NS
+	return cp->net;
+#else
+	return &init_net;
+#endif
+}
+static inline void ip_vs_conn_net_set(struct ip_vs_conn *cp, struct net *net)
+{
+#ifdef CONFIG_NET_NS
+	cp->net = net;
+#endif
+}
+
+static inline int ip_vs_conn_net_eq(const struct ip_vs_conn *cp,
+				    struct net *net)
+{
+#ifdef CONFIG_NET_NS
+	return cp->net == net;
+#else
+	return 1;
+#endif
+}
 
 /*
  *	Extended internal versions of struct ip_vs_service_user and
@@ -485,6 +636,7 @@ struct ip_vs_service {
 	unsigned		flags;	  /* service status flags */
 	unsigned		timeout;  /* persistent timeout in ticks */
 	__be32			netmask;  /* grouping granularity */
+	struct net		*net;
 
 	struct list_head	destinations;  /* real server d-linked list */
 	__u32			num_dests;     /* number of servers */
@@ -510,8 +662,8 @@ struct ip_vs_dest {
 	struct list_head	d_list;   /* for table with all the dests */
 
 	u16			af;		/* address family */
-	union nf_inet_addr	addr;		/* IP address of the server */
 	__be16			port;		/* port number of the server */
+	union nf_inet_addr	addr;		/* IP address of the server */
 	volatile unsigned	flags;		/* dest status flags */
 	atomic_t		conn_flags;	/* flags to copy to conn */
 	atomic_t		weight;		/* server weight */
@@ -538,8 +690,8 @@ struct ip_vs_dest {
 	/* for virtual service */
 	struct ip_vs_service	*svc;		/* service it belongs to */
 	__u16			protocol;	/* which protocol (TCP/UDP) */
-	union nf_inet_addr	vaddr;		/* virtual IP address */
 	__be16			vport;		/* virtual port number */
+	union nf_inet_addr	vaddr;		/* virtual IP address */
 	__u32			vfwmark;	/* firewall mark of service */
 };
 
@@ -674,13 +826,14 @@ enum {
 	IP_VS_DIR_LAST,
 };
 
-static inline void ip_vs_conn_fill_param(int af, int protocol,
+static inline void ip_vs_conn_fill_param(struct net *net, int af, int protocol,
 					 const union nf_inet_addr *caddr,
 					 __be16 cport,
 					 const union nf_inet_addr *vaddr,
 					 __be16 vport,
 					 struct ip_vs_conn_param *p)
 {
+	p->net = net;
 	p->af = af;
 	p->protocol = protocol;
 	p->caddr = caddr;
@@ -695,7 +848,6 @@ struct ip_vs_conn *ip_vs_conn_in_get(const struct ip_vs_conn_param *p);
 struct ip_vs_conn *ip_vs_ct_in_get(const struct ip_vs_conn_param *p);
 
 struct ip_vs_conn * ip_vs_conn_in_get_proto(int af, const struct sk_buff *skb,
-					    struct ip_vs_protocol *pp,
 					    const struct ip_vs_iphdr *iph,
 					    unsigned int proto_off,
 					    int inverse);
@@ -703,7 +855,6 @@ struct ip_vs_conn * ip_vs_conn_in_get_proto(int af, const struct sk_buff *skb,
 struct ip_vs_conn *ip_vs_conn_out_get(const struct ip_vs_conn_param *p);
 
 struct ip_vs_conn * ip_vs_conn_out_get_proto(int af, const struct sk_buff *skb,
-					     struct ip_vs_protocol *pp,
 					     const struct ip_vs_iphdr *iph,
 					     unsigned int proto_off,
 					     int inverse);
@@ -719,14 +870,14 @@ 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,
-				  struct ip_vs_dest *dest);
+				  struct ip_vs_dest *dest, __u32 fwmark);
 extern void ip_vs_conn_expire_now(struct ip_vs_conn *cp);
 
 extern const char * ip_vs_state_name(__u16 proto, int state);
 
-extern void ip_vs_tcp_conn_listen(struct ip_vs_conn *cp);
+extern void ip_vs_tcp_conn_listen(struct net *net, struct ip_vs_conn *cp);
 extern int ip_vs_check_template(struct ip_vs_conn *ct);
-extern void ip_vs_random_dropentry(void);
+extern void ip_vs_random_dropentry(struct net *net);
 extern int ip_vs_conn_init(void);
 extern void ip_vs_conn_cleanup(void);
 
@@ -796,12 +947,12 @@ ip_vs_control_add(struct ip_vs_conn *cp, struct ip_vs_conn *ctl_cp)
  *      (from ip_vs_app.c)
  */
 #define IP_VS_APP_MAX_PORTS  8
-extern int register_ip_vs_app(struct ip_vs_app *app);
-extern void unregister_ip_vs_app(struct ip_vs_app *app);
+extern int register_ip_vs_app(struct net *net, struct ip_vs_app *app);
+extern void unregister_ip_vs_app(struct net *net, struct ip_vs_app *app);
 extern int ip_vs_bind_app(struct ip_vs_conn *cp, struct ip_vs_protocol *pp);
 extern void ip_vs_unbind_app(struct ip_vs_conn *cp);
-extern int
-register_ip_vs_app_inc(struct ip_vs_app *app, __u16 proto, __u16 port);
+extern int register_ip_vs_app_inc(struct net *net, struct ip_vs_app *app,
+				  __u16 proto, __u16 port);
 extern int ip_vs_app_inc_get(struct ip_vs_app *inc);
 extern void ip_vs_app_inc_put(struct ip_vs_app *inc);
 
@@ -814,15 +965,27 @@ void ip_vs_bind_pe(struct ip_vs_service *svc, struct ip_vs_pe *pe);
 void ip_vs_unbind_pe(struct ip_vs_service *svc);
 int register_ip_vs_pe(struct ip_vs_pe *pe);
 int unregister_ip_vs_pe(struct ip_vs_pe *pe);
-extern struct ip_vs_pe *ip_vs_pe_get(const char *name);
-extern void ip_vs_pe_put(struct ip_vs_pe *pe);
+struct ip_vs_pe *ip_vs_pe_getbyname(const char *name);
+struct ip_vs_pe *__ip_vs_pe_getbyname(const char *pe_name);
+
+static inline void ip_vs_pe_get(const struct ip_vs_pe *pe)
+{
+	if (pe && pe->module)
+		__module_get(pe->module);
+}
+
+static inline void ip_vs_pe_put(const struct ip_vs_pe *pe)
+{
+	if (pe && pe->module)
+		module_put(pe->module);
+}
 
 /*
  *	IPVS protocol functions (from ip_vs_proto.c)
  */
 extern int ip_vs_protocol_init(void);
 extern void ip_vs_protocol_cleanup(void);
-extern void ip_vs_protocol_timeout_change(int flags);
+extern void ip_vs_protocol_timeout_change(struct netns_ipvs *ipvs, int flags);
 extern int *ip_vs_create_timeout_table(int *table, int size);
 extern int
 ip_vs_set_state_timeout(int *table, int num, const char *const *names,
@@ -852,26 +1015,21 @@ extern struct ip_vs_scheduler *ip_vs_scheduler_get(const char *sched_name);
 extern void ip_vs_scheduler_put(struct ip_vs_scheduler *scheduler);
 extern struct ip_vs_conn *
 ip_vs_schedule(struct ip_vs_service *svc, struct sk_buff *skb,
-	       struct ip_vs_protocol *pp, int *ignored);
+	       struct ip_vs_proto_data *pd, int *ignored);
 extern int ip_vs_leave(struct ip_vs_service *svc, struct sk_buff *skb,
-			struct ip_vs_protocol *pp);
+			struct ip_vs_proto_data *pd);
 
 
 /*
  *      IPVS control data and functions (from ip_vs_ctl.c)
  */
-extern int sysctl_ip_vs_cache_bypass;
-extern int sysctl_ip_vs_expire_nodest_conn;
-extern int sysctl_ip_vs_expire_quiescent_template;
-extern int sysctl_ip_vs_sync_threshold[2];
-extern int sysctl_ip_vs_nat_icmp_send;
-extern int sysctl_ip_vs_conntrack;
-extern int sysctl_ip_vs_snat_reroute;
 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(int af, __u32 fwmark, __u16 protocol,
+ip_vs_service_get(struct net *net, int af, __u32 fwmark, __u16 protocol,
 		  const union nf_inet_addr *vaddr, __be16 vport);
 
 static inline void ip_vs_service_put(struct ip_vs_service *svc)
@@ -880,7 +1038,7 @@ static inline void ip_vs_service_put(struct ip_vs_service *svc)
 }
 
 extern struct ip_vs_dest *
-ip_vs_lookup_real_service(int af, __u16 protocol,
+ip_vs_lookup_real_service(struct net *net, int af, __u16 protocol,
 			  const union nf_inet_addr *daddr, __be16 dport);
 
 extern int ip_vs_use_count_inc(void);
@@ -888,8 +1046,9 @@ extern void ip_vs_use_count_dec(void);
 extern int ip_vs_control_init(void);
 extern void ip_vs_control_cleanup(void);
 extern struct ip_vs_dest *
-ip_vs_find_dest(int af, const union nf_inet_addr *daddr, __be16 dport,
-		const union nf_inet_addr *vaddr, __be16 vport, __u16 protocol);
+ip_vs_find_dest(struct net *net, int af, const union nf_inet_addr *daddr,
+		__be16 dport, const union nf_inet_addr *vaddr, __be16 vport,
+		__u16 protocol, __u32 fwmark);
 extern struct ip_vs_dest *ip_vs_try_bind_dest(struct ip_vs_conn *cp);
 
 
@@ -897,14 +1056,12 @@ extern struct ip_vs_dest *ip_vs_try_bind_dest(struct ip_vs_conn *cp);
  *      IPVS sync daemon data and function prototypes
  *      (from ip_vs_sync.c)
  */
-extern volatile int ip_vs_sync_state;
-extern volatile int ip_vs_master_syncid;
-extern volatile int ip_vs_backup_syncid;
-extern char ip_vs_master_mcast_ifn[IP_VS_IFNAME_MAXLEN];
-extern char ip_vs_backup_mcast_ifn[IP_VS_IFNAME_MAXLEN];
-extern int start_sync_thread(int state, char *mcast_ifn, __u8 syncid);
-extern int stop_sync_thread(int state);
-extern void ip_vs_sync_conn(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 int ip_vs_sync_init(void);
+extern void ip_vs_sync_cleanup(void);
 
 
 /*
@@ -912,8 +1069,8 @@ extern void ip_vs_sync_conn(struct ip_vs_conn *cp);
  */
 extern int ip_vs_estimator_init(void);
 extern void ip_vs_estimator_cleanup(void);
-extern void ip_vs_new_estimator(struct ip_vs_stats *stats);
-extern void ip_vs_kill_estimator(struct ip_vs_stats *stats);
+extern void ip_vs_new_estimator(struct net *net, struct ip_vs_stats *stats);
+extern void ip_vs_kill_estimator(struct net *net, struct ip_vs_stats *stats);
 extern void ip_vs_zero_estimator(struct ip_vs_stats *stats);
 
 /*
@@ -955,11 +1112,13 @@ extern int ip_vs_icmp_xmit_v6
 extern int ip_vs_drop_rate;
 extern int ip_vs_drop_counter;
 
-static __inline__ int ip_vs_todrop(void)
+static inline int ip_vs_todrop(struct netns_ipvs *ipvs)
 {
-	if (!ip_vs_drop_rate) return 0;
-	if (--ip_vs_drop_counter > 0) return 0;
-	ip_vs_drop_counter = ip_vs_drop_rate;
+	if (!ipvs->drop_rate)
+		return 0;
+	if (--ipvs->drop_counter > 0)
+		return 0;
+	ipvs->drop_counter = ipvs->drop_rate;
 	return 1;
 }
 
@@ -1047,9 +1206,9 @@ static inline void ip_vs_notrack(struct sk_buff *skb)
  *      Netfilter connection tracking
  *      (from ip_vs_nfct.c)
  */
-static inline int ip_vs_conntrack_enabled(void)
+static inline int ip_vs_conntrack_enabled(struct netns_ipvs *ipvs)
 {
-	return sysctl_ip_vs_conntrack;
+	return ipvs->sysctl_conntrack;
 }
 
 extern void ip_vs_update_conntrack(struct sk_buff *skb, struct ip_vs_conn *cp,
@@ -1062,7 +1221,7 @@ extern void ip_vs_conn_drop_conntrack(struct ip_vs_conn *cp);
 
 #else
 
-static inline int ip_vs_conntrack_enabled(void)
+static inline int ip_vs_conntrack_enabled(struct netns_ipvs *ipvs)
 {
 	return 0;
 }

include/net/net_namespace.h

@@ -20,6 +20,7 @@
 #include <net/netns/conntrack.h>
 #endif
 #include <net/netns/xfrm.h>
+#include <net/netns/ip_vs.h>
 
 struct proc_dir_entry;
 struct net_device;
@@ -94,6 +95,7 @@ struct net {
 #ifdef CONFIG_XFRM
 	struct netns_xfrm	xfrm;
 #endif
+	struct netns_ipvs	*ipvs;
 };
 
 

include/net/netfilter/nf_conntrack.h

@@ -50,11 +50,24 @@ union nf_conntrack_expect_proto {
 /* per conntrack: application helper private data */
 union nf_conntrack_help {
 	/* insert conntrack helper private data (master) here */
+#if defined(CONFIG_NF_CONNTRACK_FTP) || defined(CONFIG_NF_CONNTRACK_FTP_MODULE)
 	struct nf_ct_ftp_master ct_ftp_info;
+#endif
+#if defined(CONFIG_NF_CONNTRACK_PPTP) || \
+    defined(CONFIG_NF_CONNTRACK_PPTP_MODULE)
 	struct nf_ct_pptp_master ct_pptp_info;
+#endif
+#if defined(CONFIG_NF_CONNTRACK_H323) || \
+    defined(CONFIG_NF_CONNTRACK_H323_MODULE)
 	struct nf_ct_h323_master ct_h323_info;
+#endif
+#if defined(CONFIG_NF_CONNTRACK_SANE) || \
+    defined(CONFIG_NF_CONNTRACK_SANE_MODULE)
 	struct nf_ct_sane_master ct_sane_info;
+#endif
+#if defined(CONFIG_NF_CONNTRACK_SIP) || defined(CONFIG_NF_CONNTRACK_SIP_MODULE)
 	struct nf_ct_sip_master ct_sip_info;
+#endif
 };
 
 #include <linux/types.h>
@@ -116,14 +129,14 @@ struct nf_conn {
 	u_int32_t secmark;
 #endif
 
-	/* Storage reserved for other modules: */
-	union nf_conntrack_proto proto;
-
 	/* Extensions */
 	struct nf_ct_ext *ext;
 #ifdef CONFIG_NET_NS
 	struct net *ct_net;
 #endif
+
+	/* Storage reserved for other modules, must be the last member */
+	union nf_conntrack_proto proto;
 };
 
 static inline struct nf_conn *
@@ -189,9 +202,9 @@ extern void nf_ct_l3proto_module_put(unsigned short l3proto);
  * Allocate a hashtable of hlist_head (if nulls == 0),
  * or hlist_nulls_head (if nulls == 1)
  */
-extern void *nf_ct_alloc_hashtable(unsigned int *sizep, int *vmalloced, int nulls);
+extern void *nf_ct_alloc_hashtable(unsigned int *sizep, int nulls);
 
-extern void nf_ct_free_hashtable(void *hash, int vmalloced, unsigned int size);
+extern void nf_ct_free_hashtable(void *hash, unsigned int size);
 
 extern struct nf_conntrack_tuple_hash *
 __nf_conntrack_find(struct net *net, u16 zone,

include/net/netfilter/nf_conntrack_ecache.h

@@ -23,12 +23,17 @@ struct nf_conntrack_ecache {
 static inline struct nf_conntrack_ecache *
 nf_ct_ecache_find(const struct nf_conn *ct)
 {
+#ifdef CONFIG_NF_CONNTRACK_EVENTS
 	return nf_ct_ext_find(ct, NF_CT_EXT_ECACHE);
+#else
+	return NULL;
+#endif
 }
 
 static inline struct nf_conntrack_ecache *
 nf_ct_ecache_ext_add(struct nf_conn *ct, u16 ctmask, u16 expmask, gfp_t gfp)
 {
+#ifdef CONFIG_NF_CONNTRACK_EVENTS
 	struct net *net = nf_ct_net(ct);
 	struct nf_conntrack_ecache *e;
 
@@ -45,6 +50,9 @@ nf_ct_ecache_ext_add(struct nf_conn *ct, u16 ctmask, u16 expmask, gfp_t gfp)
 		e->expmask = expmask;
 	}
 	return e;
+#else
+	return NULL;
+#endif
 };
 
 #ifdef CONFIG_NF_CONNTRACK_EVENTS
@@ -59,7 +67,7 @@ struct nf_ct_event_notifier {
 	int (*fcn)(unsigned int events, struct nf_ct_event *item);
 };
 
-extern struct nf_ct_event_notifier *nf_conntrack_event_cb;
+extern struct nf_ct_event_notifier __rcu *nf_conntrack_event_cb;
 extern int nf_conntrack_register_notifier(struct nf_ct_event_notifier *nb);
 extern void nf_conntrack_unregister_notifier(struct nf_ct_event_notifier *nb);
 
@@ -159,7 +167,7 @@ struct nf_exp_event_notifier {
 	int (*fcn)(unsigned int events, struct nf_exp_event *item);
 };
 
-extern struct nf_exp_event_notifier *nf_expect_event_cb;
+extern struct nf_exp_event_notifier __rcu *nf_expect_event_cb;
 extern int nf_ct_expect_register_notifier(struct nf_exp_event_notifier *nb);
 extern void nf_ct_expect_unregister_notifier(struct nf_exp_event_notifier *nb);
 

include/net/netfilter/nf_conntrack_extend.h

@@ -7,10 +7,19 @@
 
 enum nf_ct_ext_id {
 	NF_CT_EXT_HELPER,
+#if defined(CONFIG_NF_NAT) || defined(CONFIG_NF_NAT_MODULE)
 	NF_CT_EXT_NAT,
+#endif
 	NF_CT_EXT_ACCT,
+#ifdef CONFIG_NF_CONNTRACK_EVENTS
 	NF_CT_EXT_ECACHE,
+#endif
+#ifdef CONFIG_NF_CONNTRACK_ZONES
 	NF_CT_EXT_ZONE,
+#endif
+#ifdef CONFIG_NF_CONNTRACK_TIMESTAMP
+	NF_CT_EXT_TSTAMP,
+#endif
 	NF_CT_EXT_NUM,
 };
 
@@ -19,6 +28,7 @@ enum nf_ct_ext_id {
 #define NF_CT_EXT_ACCT_TYPE struct nf_conn_counter
 #define NF_CT_EXT_ECACHE_TYPE struct nf_conntrack_ecache
 #define NF_CT_EXT_ZONE_TYPE struct nf_conntrack_zone
+#define NF_CT_EXT_TSTAMP_TYPE struct nf_conn_tstamp
 
 /* Extensions: optional stuff which isn't permanently in struct. */
 struct nf_ct_ext {

include/net/netfilter/nf_conntrack_helper.h

@@ -63,4 +63,10 @@ static inline struct nf_conn_help *nfct_help(const struct nf_conn *ct)
 extern int nf_conntrack_helper_init(void);
 extern void nf_conntrack_helper_fini(void);
 
+extern int nf_conntrack_broadcast_help(struct sk_buff *skb,
+				       unsigned int protoff,
+				       struct nf_conn *ct,
+				       enum ip_conntrack_info ctinfo,
+				       unsigned int timeout);
+
 #endif /*_NF_CONNTRACK_HELPER_H*/

include/net/netfilter/nf_conntrack_l3proto.h

@@ -73,7 +73,7 @@ struct nf_conntrack_l3proto {
 	struct module *me;
 };
 
-extern struct nf_conntrack_l3proto *nf_ct_l3protos[AF_MAX];
+extern struct nf_conntrack_l3proto __rcu *nf_ct_l3protos[AF_MAX];
 
 /* Protocol registration. */
 extern int nf_conntrack_l3proto_register(struct nf_conntrack_l3proto *proto);

include/net/netfilter/nf_conntrack_timestamp.h

@@ -0,0 +1,53 @@
+#ifndef _NF_CONNTRACK_TSTAMP_H
+#define _NF_CONNTRACK_TSTAMP_H
+
+#include <net/net_namespace.h>
+#include <linux/netfilter/nf_conntrack_common.h>
+#include <linux/netfilter/nf_conntrack_tuple_common.h>
+#include <net/netfilter/nf_conntrack.h>
+#include <net/netfilter/nf_conntrack_extend.h>
+
+struct nf_conn_tstamp {
+	u_int64_t start;
+	u_int64_t stop;
+};
+
+static inline
+struct nf_conn_tstamp *nf_conn_tstamp_find(const struct nf_conn *ct)
+{
+#ifdef CONFIG_NF_CONNTRACK_TIMESTAMP
+	return nf_ct_ext_find(ct, NF_CT_EXT_TSTAMP);
+#else
+	return NULL;
+#endif
+}
+
+static inline
+struct nf_conn_tstamp *nf_ct_tstamp_ext_add(struct nf_conn *ct, gfp_t gfp)
+{
+#ifdef CONFIG_NF_CONNTRACK_TIMESTAMP
+	struct net *net = nf_ct_net(ct);
+
+	if (!net->ct.sysctl_tstamp)
+		return NULL;
+
+	return nf_ct_ext_add(ct, NF_CT_EXT_TSTAMP, gfp);
+#else
+	return NULL;
+#endif
+};
+
+static inline bool nf_ct_tstamp_enabled(struct net *net)
+{
+	return net->ct.sysctl_tstamp != 0;
+}
+
+static inline void nf_ct_set_tstamp(struct net *net, bool enable)
+{
+	net->ct.sysctl_tstamp = enable;
+}
+
+extern int nf_conntrack_tstamp_init(struct net *net);
+extern void nf_conntrack_tstamp_fini(struct net *net);
+
+#endif /* _NF_CONNTRACK_TSTAMP_H */

include/net/netfilter/nf_nat.h

@@ -56,7 +56,9 @@ struct nf_nat_multi_range_compat {
 /* per conntrack: nat application helper private data */
 union nf_conntrack_nat_help {
 	/* insert nat helper private data here */
+#if defined(CONFIG_NF_NAT_PPTP) || defined(CONFIG_NF_NAT_PPTP_MODULE)
 	struct nf_nat_pptp nat_pptp_info;
+#endif
 };
 
 struct nf_conn;
@@ -84,7 +86,11 @@ extern int nf_nat_used_tuple(const struct nf_conntrack_tuple *tuple,
 
 static inline struct nf_conn_nat *nfct_nat(const struct nf_conn *ct)
 {
+#if defined(CONFIG_NF_NAT) || defined(CONFIG_NF_NAT_MODULE)
 	return nf_ct_ext_find(ct, NF_CT_EXT_NAT);
+#else
+	return NULL;
+#endif
 }
 
 #else  /* !__KERNEL__: iptables wants this to compile. */

include/net/netfilter/nf_nat_core.h

@@ -21,9 +21,9 @@ static inline int nf_nat_initialized(struct nf_conn *ct,
 				     enum nf_nat_manip_type manip)
 {
 	if (manip == IP_NAT_MANIP_SRC)
-		return test_bit(IPS_SRC_NAT_DONE_BIT, &ct->status);
+		return ct->status & IPS_SRC_NAT_DONE;
 	else
-		return test_bit(IPS_DST_NAT_DONE_BIT, &ct->status);
+		return ct->status & IPS_DST_NAT_DONE;
 }
 
 struct nlattr;

include/net/netns/conntrack.h

@@ -21,15 +21,15 @@ struct netns_ct {
 	int			sysctl_events;
 	unsigned int		sysctl_events_retry_timeout;
 	int			sysctl_acct;
+	int			sysctl_tstamp;
 	int			sysctl_checksum;
 	unsigned int		sysctl_log_invalid; /* Log invalid packets */
 #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;
 #endif
-	int			hash_vmalloc;
-	int			expect_vmalloc;
 	char			*slabname;
 };
 #endif

include/net/netns/ip_vs.h

@@ -0,0 +1,143 @@
+/*
+ *  IP Virtual Server
+ *  Data structure for network namspace
+ *
+ */
+
+#ifndef IP_VS_H_
+#define IP_VS_H_
+
+#include <linux/list.h>
+#include <linux/mutex.h>
+#include <linux/list_nulls.h>
+#include <linux/ip_vs.h>
+#include <asm/atomic.h>
+#include <linux/in.h>
+
+struct ip_vs_stats;
+struct ip_vs_sync_buff;
+struct ctl_table_header;
+
+struct netns_ipvs {
+	int			gen;		/* Generation */
+	/*
+	 *	Hash table: for real service lookups
+	 */
+	#define IP_VS_RTAB_BITS 4
+	#define IP_VS_RTAB_SIZE (1 << IP_VS_RTAB_BITS)
+	#define IP_VS_RTAB_MASK (IP_VS_RTAB_SIZE - 1)
+
+	struct list_head	rs_table[IP_VS_RTAB_SIZE];
+	/* ip_vs_app */
+	struct list_head	app_list;
+	struct mutex		app_mutex;
+	struct lock_class_key	app_key;	/* mutex debuging */
+
+	/* ip_vs_proto */
+	#define IP_VS_PROTO_TAB_SIZE	32	/* must be power of 2 */
+	struct ip_vs_proto_data *proto_data_table[IP_VS_PROTO_TAB_SIZE];
+	/* ip_vs_proto_tcp */
+#ifdef CONFIG_IP_VS_PROTO_TCP
+	#define	TCP_APP_TAB_BITS	4
+	#define	TCP_APP_TAB_SIZE	(1 << TCP_APP_TAB_BITS)
+	#define	TCP_APP_TAB_MASK	(TCP_APP_TAB_SIZE - 1)
+	struct list_head	tcp_apps[TCP_APP_TAB_SIZE];
+	spinlock_t		tcp_app_lock;
+#endif
+	/* ip_vs_proto_udp */
+#ifdef CONFIG_IP_VS_PROTO_UDP
+	#define	UDP_APP_TAB_BITS	4
+	#define	UDP_APP_TAB_SIZE	(1 << UDP_APP_TAB_BITS)
+	#define	UDP_APP_TAB_MASK	(UDP_APP_TAB_SIZE - 1)
+	struct list_head	udp_apps[UDP_APP_TAB_SIZE];
+	spinlock_t		udp_app_lock;
+#endif
+	/* ip_vs_proto_sctp */
+#ifdef CONFIG_IP_VS_PROTO_SCTP
+	#define SCTP_APP_TAB_BITS	4
+	#define SCTP_APP_TAB_SIZE	(1 << SCTP_APP_TAB_BITS)
+	#define SCTP_APP_TAB_MASK	(SCTP_APP_TAB_SIZE - 1)
+	/* Hash table for SCTP application incarnations	 */
+	struct list_head	sctp_apps[SCTP_APP_TAB_SIZE];
+	spinlock_t		sctp_app_lock;
+#endif
+	/* ip_vs_conn */
+	atomic_t		conn_count;      /*  connection counter */
+
+	/* ip_vs_ctl */
+	struct ip_vs_stats		*tot_stats;  /* Statistics & est. */
+	struct ip_vs_cpu_stats __percpu *cpustats;   /* Stats per cpu */
+	seqcount_t			*ustats_seq; /* u64 read retry */
+
+	int			num_services;    /* no of virtual services */
+	/* 1/rate drop and drop-entry variables */
+	struct delayed_work	defense_work;   /* Work handler */
+	int			drop_rate;
+	int			drop_counter;
+	atomic_t		dropentry;
+	/* locks in ctl.c */
+	spinlock_t		dropentry_lock;  /* drop entry handling */
+	spinlock_t		droppacket_lock; /* drop packet handling */
+	spinlock_t		securetcp_lock;  /* state and timeout tables */
+	rwlock_t		rs_lock;         /* real services table */
+	/* semaphore for IPVS sockopts. And, [gs]etsockopt may sleep. */
+	struct lock_class_key	ctl_key;	/* ctl_mutex debuging */
+	/* Trash for destinations */
+	struct list_head	dest_trash;
+	/* Service counters */
+	atomic_t		ftpsvc_counter;
+	atomic_t		nullsvc_counter;
+
+	/* sys-ctl struct */
+	struct ctl_table_header	*sysctl_hdr;
+	struct ctl_table	*sysctl_tbl;
+	/* sysctl variables */
+	int			sysctl_amemthresh;
+	int			sysctl_am_droprate;
+	int			sysctl_drop_entry;
+	int			sysctl_drop_packet;
+	int			sysctl_secure_tcp;
+#ifdef CONFIG_IP_VS_NFCT
+	int			sysctl_conntrack;
+#endif
+	int			sysctl_snat_reroute;
+	int			sysctl_sync_ver;
+	int			sysctl_cache_bypass;
+	int			sysctl_expire_nodest_conn;
+	int			sysctl_expire_quiescent_template;
+	int			sysctl_sync_threshold[2];
+	int			sysctl_nat_icmp_send;
+
+	/* ip_vs_lblc */
+	int			sysctl_lblc_expiration;
+	struct ctl_table_header	*lblc_ctl_header;
+	struct ctl_table	*lblc_ctl_table;
+	/* ip_vs_lblcr */
+	int			sysctl_lblcr_expiration;
+	struct ctl_table_header	*lblcr_ctl_header;
+	struct ctl_table	*lblcr_ctl_table;
+	/* ip_vs_est */
+	struct list_head	est_list;	/* estimator list */
+	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;
+	spinlock_t		sync_buff_lock;
+	struct sockaddr_in	sync_mcast_addr;
+	struct task_struct	*master_thread;
+	struct task_struct	*backup_thread;
+	int			send_mesg_maxlen;
+	int			recv_mesg_maxlen;
+	volatile int		sync_state;
+	volatile int		master_syncid;
+	volatile int		backup_syncid;
+	/* multicast interface name */
+	char			master_mcast_ifn[IP_VS_IFNAME_MAXLEN];
+	char			backup_mcast_ifn[IP_VS_IFNAME_MAXLEN];
+	/* net name space ptr */
+	struct net		*net;            /* Needed by timer routines */
+};
+
+#endif /* IP_VS_H_ */

include/net/netns/ipv4.h

@@ -43,7 +43,6 @@ struct netns_ipv4 {
 	struct xt_table		*nat_table;
 	struct hlist_head	*nat_bysource;
 	unsigned int		nat_htable_size;
-	int			nat_vmalloced;
 #endif
 
 	int sysctl_icmp_echo_ignore_all;

kernel/audit.c

@@ -74,6 +74,8 @@ static int	audit_initialized;
 int		audit_enabled;
 int		audit_ever_enabled;
 
+EXPORT_SYMBOL_GPL(audit_enabled);
+
 /* Default state when kernel boots without any parameters. */
 static int	audit_default;
 

net/bridge/netfilter/ebt_ip6.c

@@ -22,9 +22,15 @@
 #include <linux/netfilter_bridge/ebtables.h>
 #include <linux/netfilter_bridge/ebt_ip6.h>
 
-struct tcpudphdr {
-	__be16 src;
-	__be16 dst;
+union pkthdr {
+	struct {
+		__be16 src;
+		__be16 dst;
+	} tcpudphdr;
+	struct {
+		u8 type;
+		u8 code;
+	} icmphdr;
 };
 
 static bool
@@ -33,8 +39,8 @@ ebt_ip6_mt(const struct sk_buff *skb, struct xt_action_param *par)
 	const struct ebt_ip6_info *info = par->matchinfo;
 	const struct ipv6hdr *ih6;
 	struct ipv6hdr _ip6h;
-	const struct tcpudphdr *pptr;
-	struct tcpudphdr _ports;
+	const union pkthdr *pptr;
+	union pkthdr _pkthdr;
 
 	ih6 = skb_header_pointer(skb, 0, sizeof(_ip6h), &_ip6h);
 	if (ih6 == NULL)
@@ -56,26 +62,34 @@ ebt_ip6_mt(const struct sk_buff *skb, struct xt_action_param *par)
 			return false;
 		if (FWINV(info->protocol != nexthdr, EBT_IP6_PROTO))
 			return false;
-		if (!(info->bitmask & EBT_IP6_DPORT) &&
-		    !(info->bitmask & EBT_IP6_SPORT))
+		if (!(info->bitmask & ( EBT_IP6_DPORT |
+					EBT_IP6_SPORT | EBT_IP6_ICMP6)))
 			return true;
-		pptr = skb_header_pointer(skb, offset_ph, sizeof(_ports),
-					  &_ports);
+
+		/* min icmpv6 headersize is 4, so sizeof(_pkthdr) is ok. */
+		pptr = skb_header_pointer(skb, offset_ph, sizeof(_pkthdr),
+					  &_pkthdr);
 		if (pptr == NULL)
 			return false;
 		if (info->bitmask & EBT_IP6_DPORT) {
-			u32 dst = ntohs(pptr->dst);
+			u16 dst = ntohs(pptr->tcpudphdr.dst);
 			if (FWINV(dst < info->dport[0] ||
 				  dst > info->dport[1], EBT_IP6_DPORT))
 				return false;
 		}
 		if (info->bitmask & EBT_IP6_SPORT) {
-			u32 src = ntohs(pptr->src);
+			u16 src = ntohs(pptr->tcpudphdr.src);
 			if (FWINV(src < info->sport[0] ||
 				  src > info->sport[1], EBT_IP6_SPORT))
 			return false;
 		}
-		return true;
+		if ((info->bitmask & EBT_IP6_ICMP6) &&
+		     FWINV(pptr->icmphdr.type < info->icmpv6_type[0] ||
+			   pptr->icmphdr.type > info->icmpv6_type[1] ||
+			   pptr->icmphdr.code < info->icmpv6_code[0] ||
+			   pptr->icmphdr.code > info->icmpv6_code[1],
+							EBT_IP6_ICMP6))
+			return false;
 	}
 	return true;
 }
@@ -103,6 +117,14 @@ static int ebt_ip6_mt_check(const struct xt_mtchk_param *par)
 		return -EINVAL;
 	if (info->bitmask & EBT_IP6_SPORT && info->sport[0] > info->sport[1])
 		return -EINVAL;
+	if (info->bitmask & EBT_IP6_ICMP6) {
+		if ((info->invflags & EBT_IP6_PROTO) ||
+		     info->protocol != IPPROTO_ICMPV6)
+			return -EINVAL;
+		if (info->icmpv6_type[0] > info->icmpv6_type[1] ||
+		    info->icmpv6_code[0] > info->icmpv6_code[1])
+			return -EINVAL;
+	}
 	return 0;
 }
 

net/bridge/netfilter/ebtables.c

@@ -1764,6 +1764,7 @@ static int compat_table_info(const struct ebt_table_info *info,
 
 	newinfo->entries_size = size;
 
+	xt_compat_init_offsets(AF_INET, info->nentries);
 	return EBT_ENTRY_ITERATE(entries, size, compat_calc_entry, info,
 							entries, newinfo);
 }

net/ipv4/Kconfig

@@ -140,6 +140,9 @@ config IP_ROUTE_VERBOSE
 	  handled by the klogd daemon which is responsible for kernel messages
 	  ("man klogd").
 
+config IP_ROUTE_CLASSID
+	bool
+
 config IP_PNP
 	bool "IP: kernel level autoconfiguration"
 	help
@@ -657,4 +660,3 @@ config TCP_MD5SIG
 	  on the Internet.
 
 	  If unsure, say N.
-

net/ipv4/fib_rules.c

@@ -41,12 +41,12 @@ struct fib4_rule {
 	__be32			srcmask;
 	__be32			dst;
 	__be32			dstmask;
-#ifdef CONFIG_NET_CLS_ROUTE
+#ifdef CONFIG_IP_ROUTE_CLASSID
 	u32			tclassid;
 #endif
 };
 
-#ifdef CONFIG_NET_CLS_ROUTE
+#ifdef CONFIG_IP_ROUTE_CLASSID
 u32 fib_rules_tclass(struct fib_result *res)
 {
 	return res->r ? ((struct fib4_rule *) res->r)->tclassid : 0;
@@ -165,7 +165,7 @@ static int fib4_rule_configure(struct fib_rule *rule, struct sk_buff *skb,
 	if (frh->dst_len)
 		rule4->dst = nla_get_be32(tb[FRA_DST]);
 
-#ifdef CONFIG_NET_CLS_ROUTE
+#ifdef CONFIG_IP_ROUTE_CLASSID
 	if (tb[FRA_FLOW])
 		rule4->tclassid = nla_get_u32(tb[FRA_FLOW]);
 #endif
@@ -195,7 +195,7 @@ static int fib4_rule_compare(struct fib_rule *rule, struct fib_rule_hdr *frh,
 	if (frh->tos && (rule4->tos != frh->tos))
 		return 0;
 
-#ifdef CONFIG_NET_CLS_ROUTE
+#ifdef CONFIG_IP_ROUTE_CLASSID
 	if (tb[FRA_FLOW] && (rule4->tclassid != nla_get_u32(tb[FRA_FLOW])))
 		return 0;
 #endif
@@ -224,7 +224,7 @@ static int fib4_rule_fill(struct fib_rule *rule, struct sk_buff *skb,
 	if (rule4->src_len)
 		NLA_PUT_BE32(skb, FRA_SRC, rule4->src);
 
-#ifdef CONFIG_NET_CLS_ROUTE
+#ifdef CONFIG_IP_ROUTE_CLASSID
 	if (rule4->tclassid)
 		NLA_PUT_U32(skb, FRA_FLOW, rule4->tclassid);
 #endif

net/ipv4/fib_semantics.c

@@ -200,7 +200,7 @@ static inline int nh_comp(const struct fib_info *fi, const struct fib_info *ofi)
 #ifdef CONFIG_IP_ROUTE_MULTIPATH
 		    nh->nh_weight != onh->nh_weight ||
 #endif
-#ifdef CONFIG_NET_CLS_ROUTE
+#ifdef CONFIG_IP_ROUTE_CLASSID
 		    nh->nh_tclassid != onh->nh_tclassid ||
 #endif
 		    ((nh->nh_flags ^ onh->nh_flags) & ~RTNH_F_DEAD))
@@ -422,7 +422,7 @@ static int fib_get_nhs(struct fib_info *fi, struct rtnexthop *rtnh,
 
 			nla = nla_find(attrs, attrlen, RTA_GATEWAY);
 			nexthop_nh->nh_gw = nla ? nla_get_be32(nla) : 0;
-#ifdef CONFIG_NET_CLS_ROUTE
+#ifdef CONFIG_IP_ROUTE_CLASSID
 			nla = nla_find(attrs, attrlen, RTA_FLOW);
 			nexthop_nh->nh_tclassid = nla ? nla_get_u32(nla) : 0;
 #endif
@@ -476,7 +476,7 @@ int fib_nh_match(struct fib_config *cfg, struct fib_info *fi)
 			nla = nla_find(attrs, attrlen, RTA_GATEWAY);
 			if (nla && nla_get_be32(nla) != nh->nh_gw)
 				return 1;
-#ifdef CONFIG_NET_CLS_ROUTE
+#ifdef CONFIG_IP_ROUTE_CLASSID
 			nla = nla_find(attrs, attrlen, RTA_FLOW);
 			if (nla && nla_get_u32(nla) != nh->nh_tclassid)
 				return 1;
@@ -779,7 +779,7 @@ struct fib_info *fib_create_info(struct fib_config *cfg)
 			goto err_inval;
 		if (cfg->fc_gw && fi->fib_nh->nh_gw != cfg->fc_gw)
 			goto err_inval;
-#ifdef CONFIG_NET_CLS_ROUTE
+#ifdef CONFIG_IP_ROUTE_CLASSID
 		if (cfg->fc_flow && fi->fib_nh->nh_tclassid != cfg->fc_flow)
 			goto err_inval;
 #endif
@@ -792,7 +792,7 @@ struct fib_info *fib_create_info(struct fib_config *cfg)
 		nh->nh_oif = cfg->fc_oif;
 		nh->nh_gw = cfg->fc_gw;
 		nh->nh_flags = cfg->fc_flags;
-#ifdef CONFIG_NET_CLS_ROUTE
+#ifdef CONFIG_IP_ROUTE_CLASSID
 		nh->nh_tclassid = cfg->fc_flow;
 #endif
 #ifdef CONFIG_IP_ROUTE_MULTIPATH
@@ -1002,7 +1002,7 @@ int fib_dump_info(struct sk_buff *skb, u32 pid, u32 seq, int event,
 
 		if (fi->fib_nh->nh_oif)
 			NLA_PUT_U32(skb, RTA_OIF, fi->fib_nh->nh_oif);
-#ifdef CONFIG_NET_CLS_ROUTE
+#ifdef CONFIG_IP_ROUTE_CLASSID
 		if (fi->fib_nh[0].nh_tclassid)
 			NLA_PUT_U32(skb, RTA_FLOW, fi->fib_nh[0].nh_tclassid);
 #endif
@@ -1027,7 +1027,7 @@ int fib_dump_info(struct sk_buff *skb, u32 pid, u32 seq, int event,
 
 			if (nh->nh_gw)
 				NLA_PUT_BE32(skb, RTA_GATEWAY, nh->nh_gw);
-#ifdef CONFIG_NET_CLS_ROUTE
+#ifdef CONFIG_IP_ROUTE_CLASSID
 			if (nh->nh_tclassid)
 				NLA_PUT_U32(skb, RTA_FLOW, nh->nh_tclassid);
 #endif

net/ipv4/ip_input.c

@@ -340,7 +340,7 @@ static int ip_rcv_finish(struct sk_buff *skb)
 		}
 	}
 
-#ifdef CONFIG_NET_CLS_ROUTE
+#ifdef CONFIG_IP_ROUTE_CLASSID
 	if (unlikely(skb_dst(skb)->tclassid)) {
 		struct ip_rt_acct *st = this_cpu_ptr(ip_rt_acct);
 		u32 idx = skb_dst(skb)->tclassid;

net/ipv4/netfilter/Kconfig

@@ -206,8 +206,9 @@ config IP_NF_TARGET_REDIRECT
 
 config NF_NAT_SNMP_BASIC
 	tristate "Basic SNMP-ALG support"
-	depends on NF_NAT
+	depends on NF_CONNTRACK_SNMP && NF_NAT
 	depends on NETFILTER_ADVANCED
+	default NF_NAT && NF_CONNTRACK_SNMP
 	---help---
 
 	  This module implements an Application Layer Gateway (ALG) for

net/ipv4/netfilter/arp_tables.c

@@ -866,6 +866,7 @@ static int compat_table_info(const struct xt_table_info *info,
 	memcpy(newinfo, info, offsetof(struct xt_table_info, entries));
 	newinfo->initial_entries = 0;
 	loc_cpu_entry = info->entries[raw_smp_processor_id()];
+	xt_compat_init_offsets(NFPROTO_ARP, info->number);
 	xt_entry_foreach(iter, loc_cpu_entry, info->size) {
 		ret = compat_calc_entry(iter, info, loc_cpu_entry, newinfo);
 		if (ret != 0)
@@ -1333,6 +1334,7 @@ static int translate_compat_table(const char *name,
 	duprintf("translate_compat_table: size %u\n", info->size);
 	j = 0;
 	xt_compat_lock(NFPROTO_ARP);
+	xt_compat_init_offsets(NFPROTO_ARP, number);
 	/* Walk through entries, checking offsets. */
 	xt_entry_foreach(iter0, entry0, total_size) {
 		ret = check_compat_entry_size_and_hooks(iter0, info, &size,

net/ipv4/netfilter/ip_tables.c

@@ -1063,6 +1063,7 @@ static int compat_table_info(const struct xt_table_info *info,
 	memcpy(newinfo, info, offsetof(struct xt_table_info, entries));
 	newinfo->initial_entries = 0;
 	loc_cpu_entry = info->entries[raw_smp_processor_id()];
+	xt_compat_init_offsets(AF_INET, info->number);
 	xt_entry_foreach(iter, loc_cpu_entry, info->size) {
 		ret = compat_calc_entry(iter, info, loc_cpu_entry, newinfo);
 		if (ret != 0)
@@ -1664,6 +1665,7 @@ translate_compat_table(struct net *net,
 	duprintf("translate_compat_table: size %u\n", info->size);
 	j = 0;
 	xt_compat_lock(AF_INET);
+	xt_compat_init_offsets(AF_INET, number);
 	/* Walk through entries, checking offsets. */
 	xt_entry_foreach(iter0, entry0, total_size) {
 		ret = check_compat_entry_size_and_hooks(iter0, info, &size,

net/ipv4/netfilter/ipt_CLUSTERIP.c

@@ -300,13 +300,8 @@ clusterip_tg(struct sk_buff *skb, const struct xt_action_param *par)
 	 * that the ->target() function isn't called after ->destroy() */
 
 	ct = nf_ct_get(skb, &ctinfo);
-	if (ct == NULL) {
-		pr_info("no conntrack!\n");
-			/* FIXME: need to drop invalid ones, since replies
-			 * to outgoing connections of other nodes will be
-			 * marked as INVALID */
+	if (ct == NULL)
 		return NF_DROP;
-	}
 
 	/* special case: ICMP error handling. conntrack distinguishes between
 	 * error messages (RELATED) and information requests (see below) */

net/ipv4/netfilter/ipt_LOG.c

@@ -442,8 +442,7 @@ ipt_log_packet(u_int8_t pf,
 	}
 #endif
 
-	/* MAC logging for input path only. */
-	if (in && !out)
+	if (in != NULL)
 		dump_mac_header(m, loginfo, skb);
 
 	dump_packet(m, loginfo, skb, 0);

net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c

@@ -20,6 +20,7 @@
 #include <net/netfilter/nf_conntrack_l4proto.h>
 #include <net/netfilter/nf_conntrack_expect.h>
 #include <net/netfilter/nf_conntrack_acct.h>
+#include <linux/rculist_nulls.h>
 
 struct ct_iter_state {
 	struct seq_net_private p;
@@ -35,7 +36,8 @@ static struct hlist_nulls_node *ct_get_first(struct seq_file *seq)
 	for (st->bucket = 0;
 	     st->bucket < net->ct.htable_size;
 	     st->bucket++) {
-		n = rcu_dereference(net->ct.hash[st->bucket].first);
+		n = rcu_dereference(
+			hlist_nulls_first_rcu(&net->ct.hash[st->bucket]));
 		if (!is_a_nulls(n))
 			return n;
 	}
@@ -48,13 +50,14 @@ static struct hlist_nulls_node *ct_get_next(struct seq_file *seq,
 	struct net *net = seq_file_net(seq);
 	struct ct_iter_state *st = seq->private;
 
-	head = rcu_dereference(head->next);
+	head = rcu_dereference(hlist_nulls_next_rcu(head));
 	while (is_a_nulls(head)) {
 		if (likely(get_nulls_value(head) == st->bucket)) {
 			if (++st->bucket >= net->ct.htable_size)
 				return NULL;
 		}
-		head = rcu_dereference(net->ct.hash[st->bucket].first);
+		head = rcu_dereference(
+			hlist_nulls_first_rcu(&net->ct.hash[st->bucket]));
 	}
 	return head;
 }
@@ -217,7 +220,8 @@ static struct hlist_node *ct_expect_get_first(struct seq_file *seq)
 	struct hlist_node *n;
 
 	for (st->bucket = 0; st->bucket < nf_ct_expect_hsize; st->bucket++) {
-		n = rcu_dereference(net->ct.expect_hash[st->bucket].first);
+		n = rcu_dereference(
+			hlist_first_rcu(&net->ct.expect_hash[st->bucket]));
 		if (n)
 			return n;
 	}
@@ -230,11 +234,12 @@ static struct hlist_node *ct_expect_get_next(struct seq_file *seq,
 	struct net *net = seq_file_net(seq);
 	struct ct_expect_iter_state *st = seq->private;
 
-	head = rcu_dereference(head->next);
+	head = rcu_dereference(hlist_next_rcu(head));
 	while (head == NULL) {
 		if (++st->bucket >= nf_ct_expect_hsize)
 			return NULL;
-		head = rcu_dereference(net->ct.expect_hash[st->bucket].first);
+		head = rcu_dereference(
+			hlist_first_rcu(&net->ct.expect_hash[st->bucket]));
 	}
 	return head;
 }

net/ipv4/netfilter/nf_nat_amanda.c

@@ -44,13 +44,13 @@ static unsigned int help(struct sk_buff *skb,
 
 	/* Try to get same port: if not, try to change it. */
 	for (port = ntohs(exp->saved_proto.tcp.port); port != 0; port++) {
-		int ret;
+		int res;
 
 		exp->tuple.dst.u.tcp.port = htons(port);
-		ret = nf_ct_expect_related(exp);
-		if (ret == 0)
+		res = nf_ct_expect_related(exp);
+		if (res == 0)
 			break;
-		else if (ret != -EBUSY) {
+		else if (res != -EBUSY) {
 			port = 0;
 			break;
 		}

net/ipv4/netfilter/nf_nat_core.c

@@ -323,9 +323,9 @@ nf_nat_setup_info(struct nf_conn *ct,
 
 	/* It's done. */
 	if (maniptype == IP_NAT_MANIP_DST)
-		set_bit(IPS_DST_NAT_DONE_BIT, &ct->status);
+		ct->status |= IPS_DST_NAT_DONE;
 	else
-		set_bit(IPS_SRC_NAT_DONE_BIT, &ct->status);
+		ct->status |= IPS_SRC_NAT_DONE;
 
 	return NF_ACCEPT;
 }
@@ -502,7 +502,10 @@ int nf_nat_protocol_register(const struct nf_nat_protocol *proto)
 	int ret = 0;
 
 	spin_lock_bh(&nf_nat_lock);
-	if (nf_nat_protos[proto->protonum] != &nf_nat_unknown_protocol) {
+	if (rcu_dereference_protected(
+			nf_nat_protos[proto->protonum],
+			lockdep_is_held(&nf_nat_lock)
+			) != &nf_nat_unknown_protocol) {
 		ret = -EBUSY;
 		goto out;
 	}
@@ -679,8 +682,7 @@ static int __net_init nf_nat_net_init(struct net *net)
 {
 	/* Leave them the same for the moment. */
 	net->ipv4.nat_htable_size = net->ct.htable_size;
-	net->ipv4.nat_bysource = nf_ct_alloc_hashtable(&net->ipv4.nat_htable_size,
-						       &net->ipv4.nat_vmalloced, 0);
+	net->ipv4.nat_bysource = nf_ct_alloc_hashtable(&net->ipv4.nat_htable_size, 0);
 	if (!net->ipv4.nat_bysource)
 		return -ENOMEM;
 	return 0;
@@ -702,8 +704,7 @@ static void __net_exit nf_nat_net_exit(struct net *net)
 {
 	nf_ct_iterate_cleanup(net, &clean_nat, NULL);
 	synchronize_rcu();
-	nf_ct_free_hashtable(net->ipv4.nat_bysource, net->ipv4.nat_vmalloced,
-			     net->ipv4.nat_htable_size);
+	nf_ct_free_hashtable(net->ipv4.nat_bysource, net->ipv4.nat_htable_size);
 }
 
 static struct pernet_operations nf_nat_net_ops = {

net/ipv4/netfilter/nf_nat_snmp_basic.c

@@ -54,6 +54,7 @@
 #include <net/netfilter/nf_conntrack_expect.h>
 #include <net/netfilter/nf_conntrack_helper.h>
 #include <net/netfilter/nf_nat_helper.h>
+#include <linux/netfilter/nf_conntrack_snmp.h>
 
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("James Morris <jmorris@intercode.com.au>");
@@ -1310,9 +1311,9 @@ static int __init nf_nat_snmp_basic_init(void)
 {
 	int ret = 0;
 
-	ret = nf_conntrack_helper_register(&snmp_helper);
-	if (ret < 0)
-		return ret;
+	BUG_ON(nf_nat_snmp_hook != NULL);
+	rcu_assign_pointer(nf_nat_snmp_hook, help);
+
 	ret = nf_conntrack_helper_register(&snmp_trap_helper);
 	if (ret < 0) {
 		nf_conntrack_helper_unregister(&snmp_helper);
@@ -1323,7 +1324,7 @@ static int __init nf_nat_snmp_basic_init(void)
 
 static void __exit nf_nat_snmp_basic_fini(void)
 {
-	nf_conntrack_helper_unregister(&snmp_helper);
+	rcu_assign_pointer(nf_nat_snmp_hook, NULL);
 	nf_conntrack_helper_unregister(&snmp_trap_helper);
 }
 

net/ipv4/route.c

@@ -514,7 +514,7 @@ static const struct file_operations rt_cpu_seq_fops = {
 	.release = seq_release,
 };
 
-#ifdef CONFIG_NET_CLS_ROUTE
+#ifdef CONFIG_IP_ROUTE_CLASSID
 static int rt_acct_proc_show(struct seq_file *m, void *v)
 {
 	struct ip_rt_acct *dst, *src;
@@ -567,14 +567,14 @@ static int __net_init ip_rt_do_proc_init(struct net *net)
 	if (!pde)
 		goto err2;
 
-#ifdef CONFIG_NET_CLS_ROUTE
+#ifdef CONFIG_IP_ROUTE_CLASSID
 	pde = proc_create("rt_acct", 0, net->proc_net, &rt_acct_proc_fops);
 	if (!pde)
 		goto err3;
 #endif
 	return 0;
 
-#ifdef CONFIG_NET_CLS_ROUTE
+#ifdef CONFIG_IP_ROUTE_CLASSID
 err3:
 	remove_proc_entry("rt_cache", net->proc_net_stat);
 #endif
@@ -588,7 +588,7 @@ static void __net_exit ip_rt_do_proc_exit(struct net *net)
 {
 	remove_proc_entry("rt_cache", net->proc_net_stat);
 	remove_proc_entry("rt_cache", net->proc_net);
-#ifdef CONFIG_NET_CLS_ROUTE
+#ifdef CONFIG_IP_ROUTE_CLASSID
 	remove_proc_entry("rt_acct", net->proc_net);
 #endif
 }
@@ -1775,7 +1775,7 @@ void ip_rt_get_source(u8 *addr, struct rtable *rt)
 	memcpy(addr, &src, 4);
 }
 
-#ifdef CONFIG_NET_CLS_ROUTE
+#ifdef CONFIG_IP_ROUTE_CLASSID
 static void set_class_tag(struct rtable *rt, u32 tag)
 {
 	if (!(rt->dst.tclassid & 0xFFFF))
@@ -1825,7 +1825,7 @@ static void rt_set_nexthop(struct rtable *rt, struct fib_result *res, u32 itag)
 		    FIB_RES_NH(*res).nh_scope == RT_SCOPE_LINK)
 			rt->rt_gateway = FIB_RES_GW(*res);
 		dst_import_metrics(dst, fi->fib_metrics);
-#ifdef CONFIG_NET_CLS_ROUTE
+#ifdef CONFIG_IP_ROUTE_CLASSID
 		dst->tclassid = FIB_RES_NH(*res).nh_tclassid;
 #endif
 	}
@@ -1835,7 +1835,7 @@ static void rt_set_nexthop(struct rtable *rt, struct fib_result *res, u32 itag)
 	if (dst_metric_raw(dst, RTAX_ADVMSS) > 65535 - 40)
 		dst_metric_set(dst, RTAX_ADVMSS, 65535 - 40);
 
-#ifdef CONFIG_NET_CLS_ROUTE
+#ifdef CONFIG_IP_ROUTE_CLASSID
 #ifdef CONFIG_IP_MULTIPLE_TABLES
 	set_class_tag(rt, fib_rules_tclass(res));
 #endif
@@ -1891,7 +1891,7 @@ static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr,
 	rth->fl.mark    = skb->mark;
 	rth->fl.fl4_src	= saddr;
 	rth->rt_src	= saddr;
-#ifdef CONFIG_NET_CLS_ROUTE
+#ifdef CONFIG_IP_ROUTE_CLASSID
 	rth->dst.tclassid = itag;
 #endif
 	rth->rt_iif	=
@@ -2208,7 +2208,7 @@ local_input:
 	rth->fl.mark    = skb->mark;
 	rth->fl.fl4_src	= saddr;
 	rth->rt_src	= saddr;
-#ifdef CONFIG_NET_CLS_ROUTE
+#ifdef CONFIG_IP_ROUTE_CLASSID
 	rth->dst.tclassid = itag;
 #endif
 	rth->rt_iif	=
@@ -2828,7 +2828,7 @@ static int rt_fill_info(struct net *net,
 	}
 	if (rt->dst.dev)
 		NLA_PUT_U32(skb, RTA_OIF, rt->dst.dev->ifindex);
-#ifdef CONFIG_NET_CLS_ROUTE
+#ifdef CONFIG_IP_ROUTE_CLASSID
 	if (rt->dst.tclassid)
 		NLA_PUT_U32(skb, RTA_FLOW, rt->dst.tclassid);
 #endif
@@ -3249,9 +3249,9 @@ static __net_initdata struct pernet_operations rt_genid_ops = {
 };
 
 
-#ifdef CONFIG_NET_CLS_ROUTE
+#ifdef CONFIG_IP_ROUTE_CLASSID
 struct ip_rt_acct __percpu *ip_rt_acct __read_mostly;
-#endif /* CONFIG_NET_CLS_ROUTE */
+#endif /* CONFIG_IP_ROUTE_CLASSID */
 
 static __initdata unsigned long rhash_entries;
 static int __init set_rhash_entries(char *str)
@@ -3267,7 +3267,7 @@ int __init ip_rt_init(void)
 {
 	int rc = 0;
 
-#ifdef CONFIG_NET_CLS_ROUTE
+#ifdef CONFIG_IP_ROUTE_CLASSID
 	ip_rt_acct = __alloc_percpu(256 * sizeof(struct ip_rt_acct), __alignof__(struct ip_rt_acct));
 	if (!ip_rt_acct)
 		panic("IP: failed to allocate ip_rt_acct\n");

net/ipv6/netfilter/ip6_tables.c

@@ -1076,6 +1076,7 @@ static int compat_table_info(const struct xt_table_info *info,
 	memcpy(newinfo, info, offsetof(struct xt_table_info, entries));
 	newinfo->initial_entries = 0;
 	loc_cpu_entry = info->entries[raw_smp_processor_id()];
+	xt_compat_init_offsets(AF_INET6, info->number);
 	xt_entry_foreach(iter, loc_cpu_entry, info->size) {
 		ret = compat_calc_entry(iter, info, loc_cpu_entry, newinfo);
 		if (ret != 0)
@@ -1679,6 +1680,7 @@ translate_compat_table(struct net *net,
 	duprintf("translate_compat_table: size %u\n", info->size);
 	j = 0;
 	xt_compat_lock(AF_INET6);
+	xt_compat_init_offsets(AF_INET6, number);
 	/* Walk through entries, checking offsets. */
 	xt_entry_foreach(iter0, entry0, total_size) {
 		ret = check_compat_entry_size_and_hooks(iter0, info, &size,

net/ipv6/netfilter/ip6t_LOG.c

@@ -452,8 +452,7 @@ ip6t_log_packet(u_int8_t pf,
 	       in ? in->name : "",
 	       out ? out->name : "");
 
-	/* MAC logging for input path only. */
-	if (in && !out)
+	if (in != NULL)
 		dump_mac_header(m, loginfo, skb);
 
 	dump_packet(m, loginfo, skb, skb_network_offset(skb), 1);

net/ipv6/netfilter/nf_conntrack_reasm.c

@@ -73,7 +73,7 @@ static struct inet_frags nf_frags;
 static struct netns_frags nf_init_frags;
 
 #ifdef CONFIG_SYSCTL
-struct ctl_table nf_ct_frag6_sysctl_table[] = {
+static struct ctl_table nf_ct_frag6_sysctl_table[] = {
 	{
 		.procname	= "nf_conntrack_frag6_timeout",
 		.data		= &nf_init_frags.timeout,

net/netfilter/Kconfig

@@ -85,6 +85,17 @@ config NF_CONNTRACK_EVENTS
 
 	  If unsure, say `N'.
 
+config NF_CONNTRACK_TIMESTAMP
+	bool  'Connection tracking timestamping'
+	depends on NETFILTER_ADVANCED
+	help
+	  This option enables support for connection tracking timestamping.
+	  This allows you to store the flow start-time and to obtain
+	  the flow-stop time (once it has been destroyed) via Connection
+	  tracking events.
+
+	  If unsure, say `N'.
+
 config NF_CT_PROTO_DCCP
 	tristate 'DCCP protocol connection tracking support (EXPERIMENTAL)'
 	depends on EXPERIMENTAL
@@ -185,9 +196,13 @@ config NF_CONNTRACK_IRC
 
 	  To compile it as a module, choose M here.  If unsure, say N.
 
+config NF_CONNTRACK_BROADCAST
+	tristate
+
 config NF_CONNTRACK_NETBIOS_NS
 	tristate "NetBIOS name service protocol support"
 	depends on NETFILTER_ADVANCED
+	select NF_CONNTRACK_BROADCAST
 	help
 	  NetBIOS name service requests are sent as broadcast messages from an
 	  unprivileged port and responded to with unicast messages to the
@@ -204,6 +219,21 @@ config NF_CONNTRACK_NETBIOS_NS
 
 	  To compile it as a module, choose M here.  If unsure, say N.
 
+config NF_CONNTRACK_SNMP
+	tristate "SNMP service protocol support"
+	depends on NETFILTER_ADVANCED
+	select NF_CONNTRACK_BROADCAST
+	help
+	  SNMP service requests are sent as broadcast messages from an
+	  unprivileged port and responded to with unicast messages to the
+	  same port. This make them hard to firewall properly because connection
+	  tracking doesn't deal with broadcasts. This helper tracks locally
+	  originating SNMP service requests and the corresponding
+	  responses. It relies on correct IP address configuration, specifically
+	  netmask and broadcast address.
+
+	  To compile it as a module, choose M here.  If unsure, say N.
+
 config NF_CONNTRACK_PPTP
 	tristate "PPtP protocol support"
 	depends on NETFILTER_ADVANCED
@@ -326,6 +356,16 @@ config NETFILTER_XT_CONNMARK
 
 comment "Xtables targets"
 
+config NETFILTER_XT_TARGET_AUDIT
+	tristate "AUDIT target support"
+	depends on AUDIT
+	depends on NETFILTER_ADVANCED
+	---help---
+	  This option adds a 'AUDIT' target, which can be used to create
+	  audit records for packets dropped/accepted.
+
+	  To compileit as a module, choose M here. If unsure, say N.
+
 config NETFILTER_XT_TARGET_CHECKSUM
 	tristate "CHECKSUM target support"
 	depends on IP_NF_MANGLE || IP6_NF_MANGLE
@@ -477,6 +517,7 @@ config NETFILTER_XT_TARGET_NFLOG
 config NETFILTER_XT_TARGET_NFQUEUE
 	tristate '"NFQUEUE" target Support'
 	depends on NETFILTER_ADVANCED
+	select NETFILTER_NETLINK_QUEUE
 	help
 	  This target replaced the old obsolete QUEUE target.
 
@@ -886,7 +927,7 @@ config NETFILTER_XT_MATCH_RATEEST
 config NETFILTER_XT_MATCH_REALM
 	tristate  '"realm" match support'
 	depends on NETFILTER_ADVANCED
-	select NET_CLS_ROUTE
+	select IP_ROUTE_CLASSID
 	help
 	  This option adds a `realm' match, which allows you to use the realm
 	  key from the routing subsystem inside iptables.

net/netfilter/Makefile

@@ -1,6 +1,7 @@
 netfilter-objs := core.o nf_log.o nf_queue.o nf_sockopt.o
 
 nf_conntrack-y	:= nf_conntrack_core.o nf_conntrack_standalone.o nf_conntrack_expect.o nf_conntrack_helper.o nf_conntrack_proto.o nf_conntrack_l3proto_generic.o nf_conntrack_proto_generic.o nf_conntrack_proto_tcp.o nf_conntrack_proto_udp.o nf_conntrack_extend.o nf_conntrack_acct.o
+nf_conntrack-$(CONFIG_NF_CONNTRACK_TIMESTAMP) += nf_conntrack_timestamp.o
 nf_conntrack-$(CONFIG_NF_CONNTRACK_EVENTS) += nf_conntrack_ecache.o
 
 obj-$(CONFIG_NETFILTER) = netfilter.o
@@ -28,7 +29,9 @@ obj-$(CONFIG_NF_CONNTRACK_AMANDA) += nf_conntrack_amanda.o
 obj-$(CONFIG_NF_CONNTRACK_FTP) += nf_conntrack_ftp.o
 obj-$(CONFIG_NF_CONNTRACK_H323) += nf_conntrack_h323.o
 obj-$(CONFIG_NF_CONNTRACK_IRC) += nf_conntrack_irc.o
+obj-$(CONFIG_NF_CONNTRACK_BROADCAST) += nf_conntrack_broadcast.o
 obj-$(CONFIG_NF_CONNTRACK_NETBIOS_NS) += nf_conntrack_netbios_ns.o
+obj-$(CONFIG_NF_CONNTRACK_SNMP) += nf_conntrack_snmp.o
 obj-$(CONFIG_NF_CONNTRACK_PPTP) += nf_conntrack_pptp.o
 obj-$(CONFIG_NF_CONNTRACK_SANE) += nf_conntrack_sane.o
 obj-$(CONFIG_NF_CONNTRACK_SIP) += nf_conntrack_sip.o
@@ -45,6 +48,7 @@ obj-$(CONFIG_NETFILTER_XT_MARK) += xt_mark.o
 obj-$(CONFIG_NETFILTER_XT_CONNMARK) += xt_connmark.o
 
 # targets
+obj-$(CONFIG_NETFILTER_XT_TARGET_AUDIT) += xt_AUDIT.o
 obj-$(CONFIG_NETFILTER_XT_TARGET_CHECKSUM) += xt_CHECKSUM.o
 obj-$(CONFIG_NETFILTER_XT_TARGET_CLASSIFY) += xt_CLASSIFY.o
 obj-$(CONFIG_NETFILTER_XT_TARGET_CONNSECMARK) += xt_CONNSECMARK.o

net/netfilter/core.c

@@ -175,13 +175,21 @@ next_hook:
 		ret = 1;
 	} else if ((verdict & NF_VERDICT_MASK) == NF_DROP) {
 		kfree_skb(skb);
-		ret = -(verdict >> NF_VERDICT_BITS);
+		ret = NF_DROP_GETERR(verdict);
 		if (ret == 0)
 			ret = -EPERM;
 	} else if ((verdict & NF_VERDICT_MASK) == NF_QUEUE) {
-		if (!nf_queue(skb, elem, pf, hook, indev, outdev, okfn,
-			      verdict >> NF_VERDICT_BITS))
-			goto next_hook;
+		ret = nf_queue(skb, elem, pf, hook, indev, outdev, okfn,
+			       verdict >> NF_VERDICT_QBITS);
+		if (ret < 0) {
+			if (ret == -ECANCELED)
+				goto next_hook;
+			if (ret == -ESRCH &&
+			   (verdict & NF_VERDICT_FLAG_QUEUE_BYPASS))
+				goto next_hook;
+			kfree_skb(skb);
+		}
+		ret = 0;
 	}
 	rcu_read_unlock();
 	return ret;
@@ -214,7 +222,7 @@ EXPORT_SYMBOL(skb_make_writable);
 /* This does not belong here, but locally generated errors need it if connection
    tracking in use: without this, connection may not be in hash table, and hence
    manufactured ICMP or RST packets will not be associated with it. */
-void (*ip_ct_attach)(struct sk_buff *, struct sk_buff *);
+void (*ip_ct_attach)(struct sk_buff *, struct sk_buff *) __rcu __read_mostly;
 EXPORT_SYMBOL(ip_ct_attach);
 
 void nf_ct_attach(struct sk_buff *new, struct sk_buff *skb)
@@ -231,7 +239,7 @@ void nf_ct_attach(struct sk_buff *new, struct sk_buff *skb)
 }
 EXPORT_SYMBOL(nf_ct_attach);
 
-void (*nf_ct_destroy)(struct nf_conntrack *);
+void (*nf_ct_destroy)(struct nf_conntrack *) __rcu __read_mostly;
 EXPORT_SYMBOL(nf_ct_destroy);
 
 void nf_conntrack_destroy(struct nf_conntrack *nfct)

net/netfilter/ipvs/ip_vs_app.c

@@ -43,11 +43,6 @@ EXPORT_SYMBOL(register_ip_vs_app);
 EXPORT_SYMBOL(unregister_ip_vs_app);
 EXPORT_SYMBOL(register_ip_vs_app_inc);
 
-/* ipvs application list head */
-static LIST_HEAD(ip_vs_app_list);
-static DEFINE_MUTEX(__ip_vs_app_mutex);
-
-
 /*
  *	Get an ip_vs_app object
  */
@@ -67,7 +62,8 @@ static inline void ip_vs_app_put(struct ip_vs_app *app)
  *	Allocate/initialize app incarnation and register it in proto apps.
  */
 static int
-ip_vs_app_inc_new(struct ip_vs_app *app, __u16 proto, __u16 port)
+ip_vs_app_inc_new(struct net *net, struct ip_vs_app *app, __u16 proto,
+		  __u16 port)
 {
 	struct ip_vs_protocol *pp;
 	struct ip_vs_app *inc;
@@ -98,7 +94,7 @@ ip_vs_app_inc_new(struct ip_vs_app *app, __u16 proto, __u16 port)
 		}
 	}
 
-	ret = pp->register_app(inc);
+	ret = pp->register_app(net, inc);
 	if (ret)
 		goto out;
 
@@ -119,7 +115,7 @@ ip_vs_app_inc_new(struct ip_vs_app *app, __u16 proto, __u16 port)
  *	Release app incarnation
  */
 static void
-ip_vs_app_inc_release(struct ip_vs_app *inc)
+ip_vs_app_inc_release(struct net *net, struct ip_vs_app *inc)
 {
 	struct ip_vs_protocol *pp;
 
@@ -127,7 +123,7 @@ ip_vs_app_inc_release(struct ip_vs_app *inc)
 		return;
 
 	if (pp->unregister_app)
-		pp->unregister_app(inc);
+		pp->unregister_app(net, inc);
 
 	IP_VS_DBG(9, "%s App %s:%u unregistered\n",
 		  pp->name, inc->name, ntohs(inc->port));
@@ -168,15 +164,17 @@ void ip_vs_app_inc_put(struct ip_vs_app *inc)
  *	Register an application incarnation in protocol applications
  */
 int
-register_ip_vs_app_inc(struct ip_vs_app *app, __u16 proto, __u16 port)
+register_ip_vs_app_inc(struct net *net, struct ip_vs_app *app, __u16 proto,
+		       __u16 port)
 {
+	struct netns_ipvs *ipvs = net_ipvs(net);
 	int result;
 
-	mutex_lock(&__ip_vs_app_mutex);
+	mutex_lock(&ipvs->app_mutex);
 
-	result = ip_vs_app_inc_new(app, proto, port);
+	result = ip_vs_app_inc_new(net, app, proto, port);
 
-	mutex_unlock(&__ip_vs_app_mutex);
+	mutex_unlock(&ipvs->app_mutex);
 
 	return result;
 }
@@ -185,16 +183,17 @@ register_ip_vs_app_inc(struct ip_vs_app *app, __u16 proto, __u16 port)
 /*
  *	ip_vs_app registration routine
  */
-int register_ip_vs_app(struct ip_vs_app *app)
+int register_ip_vs_app(struct net *net, struct ip_vs_app *app)
 {
+	struct netns_ipvs *ipvs = net_ipvs(net);
 	/* increase the module use count */
 	ip_vs_use_count_inc();
 
-	mutex_lock(&__ip_vs_app_mutex);
+	mutex_lock(&ipvs->app_mutex);
 
-	list_add(&app->a_list, &ip_vs_app_list);
+	list_add(&app->a_list, &ipvs->app_list);
 
-	mutex_unlock(&__ip_vs_app_mutex);
+	mutex_unlock(&ipvs->app_mutex);
 
 	return 0;
 }
@@ -204,19 +203,20 @@ int register_ip_vs_app(struct ip_vs_app *app)
  *	ip_vs_app unregistration routine
  *	We are sure there are no app incarnations attached to services
  */
-void unregister_ip_vs_app(struct ip_vs_app *app)
+void unregister_ip_vs_app(struct net *net, struct ip_vs_app *app)
 {
+	struct netns_ipvs *ipvs = net_ipvs(net);
 	struct ip_vs_app *inc, *nxt;
 
-	mutex_lock(&__ip_vs_app_mutex);
+	mutex_lock(&ipvs->app_mutex);
 
 	list_for_each_entry_safe(inc, nxt, &app->incs_list, a_list) {
-		ip_vs_app_inc_release(inc);
+		ip_vs_app_inc_release(net, inc);
 	}
 
 	list_del(&app->a_list);
 
-	mutex_unlock(&__ip_vs_app_mutex);
+	mutex_unlock(&ipvs->app_mutex);
 
 	/* decrease the module use count */
 	ip_vs_use_count_dec();
@@ -226,7 +226,8 @@ void unregister_ip_vs_app(struct ip_vs_app *app)
 /*
  *	Bind ip_vs_conn to its ip_vs_app (called by cp constructor)
  */
-int ip_vs_bind_app(struct ip_vs_conn *cp, struct ip_vs_protocol *pp)
+int ip_vs_bind_app(struct ip_vs_conn *cp,
+		   struct ip_vs_protocol *pp)
 {
 	return pp->app_conn_bind(cp);
 }
@@ -481,11 +482,11 @@ int ip_vs_app_pkt_in(struct ip_vs_conn *cp, struct sk_buff *skb)
  *	/proc/net/ip_vs_app entry function
  */
 
-static struct ip_vs_app *ip_vs_app_idx(loff_t pos)
+static struct ip_vs_app *ip_vs_app_idx(struct netns_ipvs *ipvs, loff_t pos)
 {
 	struct ip_vs_app *app, *inc;
 
-	list_for_each_entry(app, &ip_vs_app_list, a_list) {
+	list_for_each_entry(app, &ipvs->app_list, a_list) {
 		list_for_each_entry(inc, &app->incs_list, a_list) {
 			if (pos-- == 0)
 				return inc;
@@ -497,19 +498,24 @@ static struct ip_vs_app *ip_vs_app_idx(loff_t pos)
 
 static void *ip_vs_app_seq_start(struct seq_file *seq, loff_t *pos)
 {
-	mutex_lock(&__ip_vs_app_mutex);
+	struct net *net = seq_file_net(seq);
+	struct netns_ipvs *ipvs = net_ipvs(net);
 
-	return *pos ? ip_vs_app_idx(*pos - 1) : SEQ_START_TOKEN;
+	mutex_lock(&ipvs->app_mutex);
+
+	return *pos ? ip_vs_app_idx(ipvs, *pos - 1) : SEQ_START_TOKEN;
 }
 
 static void *ip_vs_app_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 {
 	struct ip_vs_app *inc, *app;
 	struct list_head *e;
+	struct net *net = seq_file_net(seq);
+	struct netns_ipvs *ipvs = net_ipvs(net);
 
 	++*pos;
 	if (v == SEQ_START_TOKEN)
-		return ip_vs_app_idx(0);
+		return ip_vs_app_idx(ipvs, 0);
 
 	inc = v;
 	app = inc->app;
@@ -518,7 +524,7 @@ static void *ip_vs_app_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 		return list_entry(e, struct ip_vs_app, a_list);
 
 	/* go on to next application */
-	for (e = app->a_list.next; e != &ip_vs_app_list; e = e->next) {
+	for (e = app->a_list.next; e != &ipvs->app_list; e = e->next) {
 		app = list_entry(e, struct ip_vs_app, a_list);
 		list_for_each_entry(inc, &app->incs_list, a_list) {
 			return inc;
@@ -529,7 +535,9 @@ static void *ip_vs_app_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 
 static void ip_vs_app_seq_stop(struct seq_file *seq, void *v)
 {
-	mutex_unlock(&__ip_vs_app_mutex);
+	struct netns_ipvs *ipvs = net_ipvs(seq_file_net(seq));
+
+	mutex_unlock(&ipvs->app_mutex);
 }
 
 static int ip_vs_app_seq_show(struct seq_file *seq, void *v)
@@ -557,7 +565,8 @@ static const struct seq_operations ip_vs_app_seq_ops = {
 
 static int ip_vs_app_open(struct inode *inode, struct file *file)
 {
-	return seq_open(file, &ip_vs_app_seq_ops);
+	return seq_open_net(inode, file, &ip_vs_app_seq_ops,
+			    sizeof(struct seq_net_private));
 }
 
 static const struct file_operations ip_vs_app_fops = {
@@ -569,15 +578,36 @@ static const struct file_operations ip_vs_app_fops = {
 };
 #endif
 
-int __init ip_vs_app_init(void)
+static int __net_init __ip_vs_app_init(struct net *net)
 {
-	/* we will replace it with proc_net_ipvs_create() soon */
-	proc_net_fops_create(&init_net, "ip_vs_app", 0, &ip_vs_app_fops);
+	struct netns_ipvs *ipvs = net_ipvs(net);
+
+	INIT_LIST_HEAD(&ipvs->app_list);
+	__mutex_init(&ipvs->app_mutex, "ipvs->app_mutex", &ipvs->app_key);
+	proc_net_fops_create(net, "ip_vs_app", 0, &ip_vs_app_fops);
 	return 0;
 }
 
+static void __net_exit __ip_vs_app_cleanup(struct net *net)
+{
+	proc_net_remove(net, "ip_vs_app");
+}
+
+static struct pernet_operations ip_vs_app_ops = {
+	.init = __ip_vs_app_init,
+	.exit = __ip_vs_app_cleanup,
+};
+
+int __init ip_vs_app_init(void)
+{
+	int rv;
+
+	rv = register_pernet_subsys(&ip_vs_app_ops);
+	return rv;
+}
+
 
 void ip_vs_app_cleanup(void)
 {
-	proc_net_remove(&init_net, "ip_vs_app");
+	unregister_pernet_subsys(&ip_vs_app_ops);
 }

net/netfilter/ipvs/ip_vs_conn.c

@@ -48,35 +48,32 @@
 /*
  * Connection hash size. Default is what was selected at compile time.
 */
-int ip_vs_conn_tab_bits = CONFIG_IP_VS_TAB_BITS;
+static int ip_vs_conn_tab_bits = CONFIG_IP_VS_TAB_BITS;
 module_param_named(conn_tab_bits, ip_vs_conn_tab_bits, int, 0444);
 MODULE_PARM_DESC(conn_tab_bits, "Set connections' hash size");
 
 /* size and mask values */
-int ip_vs_conn_tab_size;
-int ip_vs_conn_tab_mask;
+int ip_vs_conn_tab_size __read_mostly;
+static int ip_vs_conn_tab_mask __read_mostly;
 
 /*
  *  Connection hash table: for input and output packets lookups of IPVS
  */
-static struct list_head *ip_vs_conn_tab;
+static struct list_head *ip_vs_conn_tab __read_mostly;
 
 /*  SLAB cache for IPVS connections */
 static struct kmem_cache *ip_vs_conn_cachep __read_mostly;
 
-/*  counter for current IPVS connections */
-static atomic_t ip_vs_conn_count = ATOMIC_INIT(0);
-
 /*  counter for no client port connections */
 static atomic_t ip_vs_conn_no_cport_cnt = ATOMIC_INIT(0);
 
 /* random value for IPVS connection hash */
-static unsigned int ip_vs_conn_rnd;
+static unsigned int ip_vs_conn_rnd __read_mostly;
 
 /*
  *  Fine locking granularity for big connection hash table
  */
-#define CT_LOCKARRAY_BITS  4
+#define CT_LOCKARRAY_BITS  5
 #define CT_LOCKARRAY_SIZE  (1<<CT_LOCKARRAY_BITS)
 #define CT_LOCKARRAY_MASK  (CT_LOCKARRAY_SIZE-1)
 
@@ -133,19 +130,19 @@ static inline void ct_write_unlock_bh(unsigned key)
 /*
  *	Returns hash value for IPVS connection entry
  */
-static unsigned int ip_vs_conn_hashkey(int af, unsigned proto,
+static unsigned int ip_vs_conn_hashkey(struct net *net, int af, unsigned proto,
 				       const union nf_inet_addr *addr,
 				       __be16 port)
 {
 #ifdef CONFIG_IP_VS_IPV6
 	if (af == AF_INET6)
-		return jhash_3words(jhash(addr, 16, ip_vs_conn_rnd),
-				    (__force u32)port, proto, ip_vs_conn_rnd)
-			& ip_vs_conn_tab_mask;
+		return (jhash_3words(jhash(addr, 16, ip_vs_conn_rnd),
+				    (__force u32)port, proto, ip_vs_conn_rnd) ^
+			((size_t)net>>8)) & ip_vs_conn_tab_mask;
 #endif
-	return jhash_3words((__force u32)addr->ip, (__force u32)port, proto,
-			    ip_vs_conn_rnd)
-		& ip_vs_conn_tab_mask;
+	return (jhash_3words((__force u32)addr->ip, (__force u32)port, proto,
+			    ip_vs_conn_rnd) ^
+		((size_t)net>>8)) & ip_vs_conn_tab_mask;
 }
 
 static unsigned int ip_vs_conn_hashkey_param(const struct ip_vs_conn_param *p,
@@ -166,18 +163,18 @@ static unsigned int ip_vs_conn_hashkey_param(const struct ip_vs_conn_param *p,
 		port = p->vport;
 	}
 
-	return ip_vs_conn_hashkey(p->af, p->protocol, addr, port);
+	return ip_vs_conn_hashkey(p->net, p->af, p->protocol, addr, port);
 }
 
 static unsigned int ip_vs_conn_hashkey_conn(const struct ip_vs_conn *cp)
 {
 	struct ip_vs_conn_param p;
 
-	ip_vs_conn_fill_param(cp->af, cp->protocol, &cp->caddr, cp->cport,
-			      NULL, 0, &p);
+	ip_vs_conn_fill_param(ip_vs_conn_net(cp), cp->af, cp->protocol,
+			      &cp->caddr, cp->cport, NULL, 0, &p);
 
-	if (cp->dest && cp->dest->svc->pe) {
-		p.pe = cp->dest->svc->pe;
+	if (cp->pe) {
+		p.pe = cp->pe;
 		p.pe_data = cp->pe_data;
 		p.pe_data_len = cp->pe_data_len;
 	}
@@ -186,7 +183,7 @@ static unsigned int ip_vs_conn_hashkey_conn(const struct ip_vs_conn *cp)
 }
 
 /*
- *	Hashes ip_vs_conn in ip_vs_conn_tab by proto,addr,port.
+ *	Hashes ip_vs_conn in ip_vs_conn_tab by netns,proto,addr,port.
  *	returns bool success.
  */
 static inline int ip_vs_conn_hash(struct ip_vs_conn *cp)
@@ -269,11 +266,12 @@ __ip_vs_conn_in_get(const struct ip_vs_conn_param *p)
 
 	list_for_each_entry(cp, &ip_vs_conn_tab[hash], c_list) {
 		if (cp->af == p->af &&
+		    p->cport == cp->cport && p->vport == cp->vport &&
 		    ip_vs_addr_equal(p->af, p->caddr, &cp->caddr) &&
 		    ip_vs_addr_equal(p->af, p->vaddr, &cp->vaddr) &&
-		    p->cport == cp->cport && p->vport == cp->vport &&
 		    ((!p->cport) ^ (!(cp->flags & IP_VS_CONN_F_NO_CPORT))) &&
-		    p->protocol == cp->protocol) {
+		    p->protocol == cp->protocol &&
+		    ip_vs_conn_net_eq(cp, p->net)) {
 			/* HIT */
 			atomic_inc(&cp->refcnt);
 			ct_read_unlock(hash);
@@ -313,23 +311,23 @@ ip_vs_conn_fill_param_proto(int af, const struct sk_buff *skb,
 			    struct ip_vs_conn_param *p)
 {
 	__be16 _ports[2], *pptr;
+	struct net *net = skb_net(skb);
 
 	pptr = skb_header_pointer(skb, proto_off, sizeof(_ports), _ports);
 	if (pptr == NULL)
 		return 1;
 
 	if (likely(!inverse))
-		ip_vs_conn_fill_param(af, iph->protocol, &iph->saddr, pptr[0],
-				      &iph->daddr, pptr[1], p);
+		ip_vs_conn_fill_param(net, af, iph->protocol, &iph->saddr,
+				      pptr[0], &iph->daddr, pptr[1], p);
 	else
-		ip_vs_conn_fill_param(af, iph->protocol, &iph->daddr, pptr[1],
-				      &iph->saddr, pptr[0], p);
+		ip_vs_conn_fill_param(net, af, iph->protocol, &iph->daddr,
+				      pptr[1], &iph->saddr, pptr[0], p);
 	return 0;
 }
 
 struct ip_vs_conn *
 ip_vs_conn_in_get_proto(int af, const struct sk_buff *skb,
-			struct ip_vs_protocol *pp,
 			const struct ip_vs_iphdr *iph,
 			unsigned int proto_off, int inverse)
 {
@@ -353,8 +351,10 @@ struct ip_vs_conn *ip_vs_ct_in_get(const struct ip_vs_conn_param *p)
 	ct_read_lock(hash);
 
 	list_for_each_entry(cp, &ip_vs_conn_tab[hash], c_list) {
+		if (!ip_vs_conn_net_eq(cp, p->net))
+			continue;
 		if (p->pe_data && p->pe->ct_match) {
-			if (p->pe->ct_match(p, cp))
+			if (p->pe == cp->pe && p->pe->ct_match(p, cp))
 				goto out;
 			continue;
 		}
@@ -404,10 +404,11 @@ struct ip_vs_conn *ip_vs_conn_out_get(const struct ip_vs_conn_param *p)
 
 	list_for_each_entry(cp, &ip_vs_conn_tab[hash], c_list) {
 		if (cp->af == p->af &&
+		    p->vport == cp->cport && p->cport == cp->dport &&
 		    ip_vs_addr_equal(p->af, p->vaddr, &cp->caddr) &&
 		    ip_vs_addr_equal(p->af, p->caddr, &cp->daddr) &&
-		    p->vport == cp->cport && p->cport == cp->dport &&
-		    p->protocol == cp->protocol) {
+		    p->protocol == cp->protocol &&
+		    ip_vs_conn_net_eq(cp, p->net)) {
 			/* HIT */
 			atomic_inc(&cp->refcnt);
 			ret = cp;
@@ -428,7 +429,6 @@ struct ip_vs_conn *ip_vs_conn_out_get(const struct ip_vs_conn_param *p)
 
 struct ip_vs_conn *
 ip_vs_conn_out_get_proto(int af, const struct sk_buff *skb,
-			 struct ip_vs_protocol *pp,
 			 const struct ip_vs_iphdr *iph,
 			 unsigned int proto_off, int inverse)
 {
@@ -611,9 +611,9 @@ struct ip_vs_dest *ip_vs_try_bind_dest(struct ip_vs_conn *cp)
 	struct ip_vs_dest *dest;
 
 	if ((cp) && (!cp->dest)) {
-		dest = ip_vs_find_dest(cp->af, &cp->daddr, cp->dport,
-				       &cp->vaddr, cp->vport,
-				       cp->protocol);
+		dest = ip_vs_find_dest(ip_vs_conn_net(cp), cp->af, &cp->daddr,
+				       cp->dport, &cp->vaddr, cp->vport,
+				       cp->protocol, cp->fwmark);
 		ip_vs_bind_dest(cp, dest);
 		return dest;
 	} else
@@ -686,13 +686,14 @@ static inline void ip_vs_unbind_dest(struct ip_vs_conn *cp)
 int ip_vs_check_template(struct ip_vs_conn *ct)
 {
 	struct ip_vs_dest *dest = ct->dest;
+	struct netns_ipvs *ipvs = net_ipvs(ip_vs_conn_net(ct));
 
 	/*
 	 * Checking the dest server status.
 	 */
 	if ((dest == NULL) ||
 	    !(dest->flags & IP_VS_DEST_F_AVAILABLE) ||
-	    (sysctl_ip_vs_expire_quiescent_template &&
+	    (ipvs->sysctl_expire_quiescent_template &&
 	     (atomic_read(&dest->weight) == 0))) {
 		IP_VS_DBG_BUF(9, "check_template: dest not available for "
 			      "protocol %s s:%s:%d v:%s:%d "
@@ -730,6 +731,7 @@ int ip_vs_check_template(struct ip_vs_conn *ct)
 static void ip_vs_conn_expire(unsigned long data)
 {
 	struct ip_vs_conn *cp = (struct ip_vs_conn *)data;
+	struct netns_ipvs *ipvs = net_ipvs(ip_vs_conn_net(cp));
 
 	cp->timeout = 60*HZ;
 
@@ -765,13 +767,14 @@ static void ip_vs_conn_expire(unsigned long data)
 		if (cp->flags & IP_VS_CONN_F_NFCT)
 			ip_vs_conn_drop_conntrack(cp);
 
+		ip_vs_pe_put(cp->pe);
 		kfree(cp->pe_data);
 		if (unlikely(cp->app != NULL))
 			ip_vs_unbind_app(cp);
 		ip_vs_unbind_dest(cp);
 		if (cp->flags & IP_VS_CONN_F_NO_CPORT)
 			atomic_dec(&ip_vs_conn_no_cport_cnt);
-		atomic_dec(&ip_vs_conn_count);
+		atomic_dec(&ipvs->conn_count);
 
 		kmem_cache_free(ip_vs_conn_cachep, cp);
 		return;
@@ -802,10 +805,12 @@ void ip_vs_conn_expire_now(struct ip_vs_conn *cp)
 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,
-	       struct ip_vs_dest *dest)
+	       struct ip_vs_dest *dest, __u32 fwmark)
 {
 	struct ip_vs_conn *cp;
-	struct ip_vs_protocol *pp = ip_vs_proto_get(p->protocol);
+	struct netns_ipvs *ipvs = net_ipvs(p->net);
+	struct ip_vs_proto_data *pd = ip_vs_proto_data_get(p->net,
+							   p->protocol);
 
 	cp = kmem_cache_zalloc(ip_vs_conn_cachep, GFP_ATOMIC);
 	if (cp == NULL) {
@@ -815,6 +820,7 @@ ip_vs_conn_new(const struct ip_vs_conn_param *p,
 
 	INIT_LIST_HEAD(&cp->c_list);
 	setup_timer(&cp->timer, ip_vs_conn_expire, (unsigned long)cp);
+	ip_vs_conn_net_set(cp, p->net);
 	cp->af		   = p->af;
 	cp->protocol	   = p->protocol;
 	ip_vs_addr_copy(p->af, &cp->caddr, p->caddr);
@@ -826,7 +832,10 @@ ip_vs_conn_new(const struct ip_vs_conn_param *p,
 			&cp->daddr, daddr);
 	cp->dport          = dport;
 	cp->flags	   = flags;
-	if (flags & IP_VS_CONN_F_TEMPLATE && p->pe_data) {
+	cp->fwmark         = fwmark;
+	if (flags & IP_VS_CONN_F_TEMPLATE && p->pe) {
+		ip_vs_pe_get(p->pe);
+		cp->pe = p->pe;
 		cp->pe_data = p->pe_data;
 		cp->pe_data_len = p->pe_data_len;
 	}
@@ -842,7 +851,7 @@ ip_vs_conn_new(const struct ip_vs_conn_param *p,
 	atomic_set(&cp->n_control, 0);
 	atomic_set(&cp->in_pkts, 0);
 
-	atomic_inc(&ip_vs_conn_count);
+	atomic_inc(&ipvs->conn_count);
 	if (flags & IP_VS_CONN_F_NO_CPORT)
 		atomic_inc(&ip_vs_conn_no_cport_cnt);
 
@@ -861,8 +870,8 @@ ip_vs_conn_new(const struct ip_vs_conn_param *p,
 #endif
 		ip_vs_bind_xmit(cp);
 
-	if (unlikely(pp && atomic_read(&pp->appcnt)))
-		ip_vs_bind_app(cp, pp);
+	if (unlikely(pd && atomic_read(&pd->appcnt)))
+		ip_vs_bind_app(cp, pd->pp);
 
 	/*
 	 * Allow conntrack to be preserved. By default, conntrack
@@ -871,7 +880,7 @@ ip_vs_conn_new(const struct ip_vs_conn_param *p,
 	 * IP_VS_CONN_F_ONE_PACKET too.
 	 */
 
-	if (ip_vs_conntrack_enabled())
+	if (ip_vs_conntrack_enabled(ipvs))
 		cp->flags |= IP_VS_CONN_F_NFCT;
 
 	/* Hash it in the ip_vs_conn_tab finally */
@@ -884,17 +893,22 @@ ip_vs_conn_new(const struct ip_vs_conn_param *p,
  *	/proc/net/ip_vs_conn entries
  */
 #ifdef CONFIG_PROC_FS
+struct ip_vs_iter_state {
+	struct seq_net_private p;
+	struct list_head *l;
+};
 
 static void *ip_vs_conn_array(struct seq_file *seq, loff_t pos)
 {
 	int idx;
 	struct ip_vs_conn *cp;
+	struct ip_vs_iter_state *iter = seq->private;
 
 	for (idx = 0; idx < ip_vs_conn_tab_size; idx++) {
 		ct_read_lock_bh(idx);
 		list_for_each_entry(cp, &ip_vs_conn_tab[idx], c_list) {
 			if (pos-- == 0) {
-				seq->private = &ip_vs_conn_tab[idx];
+				iter->l = &ip_vs_conn_tab[idx];
 			return cp;
 			}
 		}
@@ -906,14 +920,17 @@ static void *ip_vs_conn_array(struct seq_file *seq, loff_t pos)
 
 static void *ip_vs_conn_seq_start(struct seq_file *seq, loff_t *pos)
 {
-	seq->private = NULL;
+	struct ip_vs_iter_state *iter = seq->private;
+
+	iter->l = NULL;
 	return *pos ? ip_vs_conn_array(seq, *pos - 1) :SEQ_START_TOKEN;
 }
 
 static void *ip_vs_conn_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 {
 	struct ip_vs_conn *cp = v;
-	struct list_head *e, *l = seq->private;
+	struct ip_vs_iter_state *iter = seq->private;
+	struct list_head *e, *l = iter->l;
 	int idx;
 
 	++*pos;
@@ -930,18 +947,19 @@ static void *ip_vs_conn_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 	while (++idx < ip_vs_conn_tab_size) {
 		ct_read_lock_bh(idx);
 		list_for_each_entry(cp, &ip_vs_conn_tab[idx], c_list) {
-			seq->private = &ip_vs_conn_tab[idx];
+			iter->l = &ip_vs_conn_tab[idx];
 			return cp;
 		}
 		ct_read_unlock_bh(idx);
 	}
-	seq->private = NULL;
+	iter->l = NULL;
 	return NULL;
 }
 
 static void ip_vs_conn_seq_stop(struct seq_file *seq, void *v)
 {
-	struct list_head *l = seq->private;
+	struct ip_vs_iter_state *iter = seq->private;
+	struct list_head *l = iter->l;
 
 	if (l)
 		ct_read_unlock_bh(l - ip_vs_conn_tab);
@@ -955,18 +973,19 @@ static int ip_vs_conn_seq_show(struct seq_file *seq, void *v)
    "Pro FromIP   FPrt ToIP     TPrt DestIP   DPrt State       Expires PEName PEData\n");
 	else {
 		const struct ip_vs_conn *cp = v;
+		struct net *net = seq_file_net(seq);
 		char pe_data[IP_VS_PENAME_MAXLEN + IP_VS_PEDATA_MAXLEN + 3];
 		size_t len = 0;
 
-		if (cp->dest && cp->pe_data &&
-		    cp->dest->svc->pe->show_pe_data) {
+		if (!ip_vs_conn_net_eq(cp, net))
+			return 0;
+		if (cp->pe_data) {
 			pe_data[0] = ' ';
-			len = strlen(cp->dest->svc->pe->name);
-			memcpy(pe_data + 1, cp->dest->svc->pe->name, len);
+			len = strlen(cp->pe->name);
+			memcpy(pe_data + 1, cp->pe->name, len);
 			pe_data[len + 1] = ' ';
 			len += 2;
-			len += cp->dest->svc->pe->show_pe_data(cp,
-							       pe_data + len);
+			len += cp->pe->show_pe_data(cp, pe_data + len);
 		}
 		pe_data[len] = '\0';
 
@@ -1004,7 +1023,8 @@ static const struct seq_operations ip_vs_conn_seq_ops = {
 
 static int ip_vs_conn_open(struct inode *inode, struct file *file)
 {
-	return seq_open(file, &ip_vs_conn_seq_ops);
+	return seq_open_net(inode, file, &ip_vs_conn_seq_ops,
+			    sizeof(struct ip_vs_iter_state));
 }
 
 static const struct file_operations ip_vs_conn_fops = {
@@ -1031,6 +1051,10 @@ static int ip_vs_conn_sync_seq_show(struct seq_file *seq, void *v)
    "Pro FromIP   FPrt ToIP     TPrt DestIP   DPrt State       Origin Expires\n");
 	else {
 		const struct ip_vs_conn *cp = v;
+		struct net *net = seq_file_net(seq);
+
+		if (!ip_vs_conn_net_eq(cp, net))
+			return 0;
 
 #ifdef CONFIG_IP_VS_IPV6
 		if (cp->af == AF_INET6)
@@ -1067,7 +1091,8 @@ static const struct seq_operations ip_vs_conn_sync_seq_ops = {
 
 static int ip_vs_conn_sync_open(struct inode *inode, struct file *file)
 {
-	return seq_open(file, &ip_vs_conn_sync_seq_ops);
+	return seq_open_net(inode, file, &ip_vs_conn_sync_seq_ops,
+			    sizeof(struct ip_vs_iter_state));
 }
 
 static const struct file_operations ip_vs_conn_sync_fops = {
@@ -1113,7 +1138,7 @@ static inline int todrop_entry(struct ip_vs_conn *cp)
 }
 
 /* Called from keventd and must protect itself from softirqs */
-void ip_vs_random_dropentry(void)
+void ip_vs_random_dropentry(struct net *net)
 {
 	int idx;
 	struct ip_vs_conn *cp;
@@ -1133,7 +1158,8 @@ void ip_vs_random_dropentry(void)
 			if (cp->flags & IP_VS_CONN_F_TEMPLATE)
 				/* connection template */
 				continue;
-
+			if (!ip_vs_conn_net_eq(cp, net))
+				continue;
 			if (cp->protocol == IPPROTO_TCP) {
 				switch(cp->state) {
 				case IP_VS_TCP_S_SYN_RECV:
@@ -1168,12 +1194,13 @@ void ip_vs_random_dropentry(void)
 /*
  *      Flush all the connection entries in the ip_vs_conn_tab
  */
-static void ip_vs_conn_flush(void)
+static void ip_vs_conn_flush(struct net *net)
 {
 	int idx;
 	struct ip_vs_conn *cp;
+	struct netns_ipvs *ipvs = net_ipvs(net);
 
-  flush_again:
+flush_again:
 	for (idx = 0; idx < ip_vs_conn_tab_size; idx++) {
 		/*
 		 *  Lock is actually needed in this loop.
@@ -1181,7 +1208,8 @@ static void ip_vs_conn_flush(void)
 		ct_write_lock_bh(idx);
 
 		list_for_each_entry(cp, &ip_vs_conn_tab[idx], c_list) {
-
+			if (!ip_vs_conn_net_eq(cp, net))
+				continue;
 			IP_VS_DBG(4, "del connection\n");
 			ip_vs_conn_expire_now(cp);
 			if (cp->control) {
@@ -1194,16 +1222,41 @@ static void ip_vs_conn_flush(void)
 
 	/* the counter may be not NULL, because maybe some conn entries
 	   are run by slow timer handler or unhashed but still referred */
-	if (atomic_read(&ip_vs_conn_count) != 0) {
+	if (atomic_read(&ipvs->conn_count) != 0) {
 		schedule();
 		goto flush_again;
 	}
 }
+/*
+ * per netns init and exit
+ */
+int __net_init __ip_vs_conn_init(struct net *net)
+{
+	struct netns_ipvs *ipvs = net_ipvs(net);
+
+	atomic_set(&ipvs->conn_count, 0);
+
+	proc_net_fops_create(net, "ip_vs_conn", 0, &ip_vs_conn_fops);
+	proc_net_fops_create(net, "ip_vs_conn_sync", 0, &ip_vs_conn_sync_fops);
+	return 0;
+}
 
+static void __net_exit __ip_vs_conn_cleanup(struct net *net)
+{
+	/* flush all the connection entries first */
+	ip_vs_conn_flush(net);
+	proc_net_remove(net, "ip_vs_conn");
+	proc_net_remove(net, "ip_vs_conn_sync");
+}
+static struct pernet_operations ipvs_conn_ops = {
+	.init = __ip_vs_conn_init,
+	.exit = __ip_vs_conn_cleanup,
+};
 
 int __init ip_vs_conn_init(void)
 {
 	int idx;
+	int retc;
 
 	/* Compute size and mask */
 	ip_vs_conn_tab_size = 1 << ip_vs_conn_tab_bits;
@@ -1241,24 +1294,18 @@ int __init ip_vs_conn_init(void)
 		rwlock_init(&__ip_vs_conntbl_lock_array[idx].l);
 	}
 
-	proc_net_fops_create(&init_net, "ip_vs_conn", 0, &ip_vs_conn_fops);
-	proc_net_fops_create(&init_net, "ip_vs_conn_sync", 0, &ip_vs_conn_sync_fops);
+	retc = register_pernet_subsys(&ipvs_conn_ops);
 
 	/* calculate the random value for connection hash */
 	get_random_bytes(&ip_vs_conn_rnd, sizeof(ip_vs_conn_rnd));
 
-	return 0;
+	return retc;
 }
 
-
 void ip_vs_conn_cleanup(void)
 {
-	/* flush all the connection entries first */
-	ip_vs_conn_flush();
-
+	unregister_pernet_subsys(&ipvs_conn_ops);
 	/* Release the empty cache */
 	kmem_cache_destroy(ip_vs_conn_cachep);
-	proc_net_remove(&init_net, "ip_vs_conn");
-	proc_net_remove(&init_net, "ip_vs_conn_sync");
 	vfree(ip_vs_conn_tab);
 }

net/netfilter/ipvs/ip_vs_core.c

@@ -41,6 +41,7 @@
 #include <net/icmp.h>                   /* for icmp_send */
 #include <net/route.h>
 #include <net/ip6_checksum.h>
+#include <net/netns/generic.h>		/* net_generic() */
 
 #include <linux/netfilter.h>
 #include <linux/netfilter_ipv4.h>
@@ -68,6 +69,12 @@ EXPORT_SYMBOL(ip_vs_conn_put);
 EXPORT_SYMBOL(ip_vs_get_debug_level);
 #endif
 
+int ip_vs_net_id __read_mostly;
+#ifdef IP_VS_GENERIC_NETNS
+EXPORT_SYMBOL(ip_vs_net_id);
+#endif
+/* netns cnt used for uniqueness */
+static atomic_t ipvs_netns_cnt = ATOMIC_INIT(0);
 
 /* ID used in ICMP lookups */
 #define icmp_id(icmph)          (((icmph)->un).echo.id)
@@ -108,21 +115,28 @@ static inline void
 ip_vs_in_stats(struct ip_vs_conn *cp, struct sk_buff *skb)
 {
 	struct ip_vs_dest *dest = cp->dest;
+	struct netns_ipvs *ipvs = net_ipvs(skb_net(skb));
+
 	if (dest && (dest->flags & IP_VS_DEST_F_AVAILABLE)) {
-		spin_lock(&dest->stats.lock);
-		dest->stats.ustats.inpkts++;
-		dest->stats.ustats.inbytes += skb->len;
-		spin_unlock(&dest->stats.lock);
-
-		spin_lock(&dest->svc->stats.lock);
-		dest->svc->stats.ustats.inpkts++;
-		dest->svc->stats.ustats.inbytes += skb->len;
-		spin_unlock(&dest->svc->stats.lock);
-
-		spin_lock(&ip_vs_stats.lock);
-		ip_vs_stats.ustats.inpkts++;
-		ip_vs_stats.ustats.inbytes += skb->len;
-		spin_unlock(&ip_vs_stats.lock);
+		struct ip_vs_cpu_stats *s;
+
+		s = this_cpu_ptr(dest->stats.cpustats);
+		s->ustats.inpkts++;
+		u64_stats_update_begin(&s->syncp);
+		s->ustats.inbytes += skb->len;
+		u64_stats_update_end(&s->syncp);
+
+		s = this_cpu_ptr(dest->svc->stats.cpustats);
+		s->ustats.inpkts++;
+		u64_stats_update_begin(&s->syncp);
+		s->ustats.inbytes += skb->len;
+		u64_stats_update_end(&s->syncp);
+
+		s = this_cpu_ptr(ipvs->cpustats);
+		s->ustats.inpkts++;
+		u64_stats_update_begin(&s->syncp);
+		s->ustats.inbytes += skb->len;
+		u64_stats_update_end(&s->syncp);
 	}
 }
 
@@ -131,21 +145,28 @@ static inline void
 ip_vs_out_stats(struct ip_vs_conn *cp, struct sk_buff *skb)
 {
 	struct ip_vs_dest *dest = cp->dest;
+	struct netns_ipvs *ipvs = net_ipvs(skb_net(skb));
+
 	if (dest && (dest->flags & IP_VS_DEST_F_AVAILABLE)) {
-		spin_lock(&dest->stats.lock);
-		dest->stats.ustats.outpkts++;
-		dest->stats.ustats.outbytes += skb->len;
-		spin_unlock(&dest->stats.lock);
-
-		spin_lock(&dest->svc->stats.lock);
-		dest->svc->stats.ustats.outpkts++;
-		dest->svc->stats.ustats.outbytes += skb->len;
-		spin_unlock(&dest->svc->stats.lock);
-
-		spin_lock(&ip_vs_stats.lock);
-		ip_vs_stats.ustats.outpkts++;
-		ip_vs_stats.ustats.outbytes += skb->len;
-		spin_unlock(&ip_vs_stats.lock);
+		struct ip_vs_cpu_stats *s;
+
+		s = this_cpu_ptr(dest->stats.cpustats);
+		s->ustats.outpkts++;
+		u64_stats_update_begin(&s->syncp);
+		s->ustats.outbytes += skb->len;
+		u64_stats_update_end(&s->syncp);
+
+		s = this_cpu_ptr(dest->svc->stats.cpustats);
+		s->ustats.outpkts++;
+		u64_stats_update_begin(&s->syncp);
+		s->ustats.outbytes += skb->len;
+		u64_stats_update_end(&s->syncp);
+
+		s = this_cpu_ptr(ipvs->cpustats);
+		s->ustats.outpkts++;
+		u64_stats_update_begin(&s->syncp);
+		s->ustats.outbytes += skb->len;
+		u64_stats_update_end(&s->syncp);
 	}
 }
 
@@ -153,41 +174,44 @@ ip_vs_out_stats(struct ip_vs_conn *cp, struct sk_buff *skb)
 static inline void
 ip_vs_conn_stats(struct ip_vs_conn *cp, struct ip_vs_service *svc)
 {
-	spin_lock(&cp->dest->stats.lock);
-	cp->dest->stats.ustats.conns++;
-	spin_unlock(&cp->dest->stats.lock);
+	struct netns_ipvs *ipvs = net_ipvs(svc->net);
+	struct ip_vs_cpu_stats *s;
+
+	s = this_cpu_ptr(cp->dest->stats.cpustats);
+	s->ustats.conns++;
 
-	spin_lock(&svc->stats.lock);
-	svc->stats.ustats.conns++;
-	spin_unlock(&svc->stats.lock);
+	s = this_cpu_ptr(svc->stats.cpustats);
+	s->ustats.conns++;
 
-	spin_lock(&ip_vs_stats.lock);
-	ip_vs_stats.ustats.conns++;
-	spin_unlock(&ip_vs_stats.lock);
+	s = this_cpu_ptr(ipvs->cpustats);
+	s->ustats.conns++;
 }
 
 
 static inline int
 ip_vs_set_state(struct ip_vs_conn *cp, int direction,
 		const struct sk_buff *skb,
-		struct ip_vs_protocol *pp)
+		struct ip_vs_proto_data *pd)
 {
-	if (unlikely(!pp->state_transition))
+	if (unlikely(!pd->pp->state_transition))
 		return 0;
-	return pp->state_transition(cp, direction, skb, pp);
+	return pd->pp->state_transition(cp, direction, skb, pd);
 }
 
-static inline void
+static inline int
 ip_vs_conn_fill_param_persist(const struct ip_vs_service *svc,
 			      struct sk_buff *skb, int protocol,
 			      const union nf_inet_addr *caddr, __be16 cport,
 			      const union nf_inet_addr *vaddr, __be16 vport,
 			      struct ip_vs_conn_param *p)
 {
-	ip_vs_conn_fill_param(svc->af, protocol, caddr, cport, vaddr, vport, p);
+	ip_vs_conn_fill_param(svc->net, svc->af, protocol, caddr, cport, vaddr,
+			      vport, p);
 	p->pe = svc->pe;
 	if (p->pe && p->pe->fill_param)
-		p->pe->fill_param(p, skb);
+		return p->pe->fill_param(p, skb);
+
+	return 0;
 }
 
 /*
@@ -200,7 +224,7 @@ ip_vs_conn_fill_param_persist(const struct ip_vs_service *svc,
 static struct ip_vs_conn *
 ip_vs_sched_persist(struct ip_vs_service *svc,
 		    struct sk_buff *skb,
-		    __be16 ports[2])
+		    __be16 src_port, __be16 dst_port, int *ignored)
 {
 	struct ip_vs_conn *cp = NULL;
 	struct ip_vs_iphdr iph;
@@ -224,8 +248,8 @@ ip_vs_sched_persist(struct ip_vs_service *svc,
 
 	IP_VS_DBG_BUF(6, "p-schedule: src %s:%u dest %s:%u "
 		      "mnet %s\n",
-		      IP_VS_DBG_ADDR(svc->af, &iph.saddr), ntohs(ports[0]),
-		      IP_VS_DBG_ADDR(svc->af, &iph.daddr), ntohs(ports[1]),
+		      IP_VS_DBG_ADDR(svc->af, &iph.saddr), ntohs(src_port),
+		      IP_VS_DBG_ADDR(svc->af, &iph.daddr), ntohs(dst_port),
 		      IP_VS_DBG_ADDR(svc->af, &snet));
 
 	/*
@@ -247,14 +271,14 @@ ip_vs_sched_persist(struct ip_vs_service *svc,
 		const union nf_inet_addr fwmark = { .ip = htonl(svc->fwmark) };
 		__be16 vport = 0;
 
-		if (ports[1] == svc->port) {
+		if (dst_port == svc->port) {
 			/* non-FTP template:
 			 * <protocol, caddr, 0, vaddr, vport, daddr, dport>
 			 * FTP template:
 			 * <protocol, caddr, 0, vaddr, 0, daddr, 0>
 			 */
 			if (svc->port != FTPPORT)
-				vport = ports[1];
+				vport = dst_port;
 		} else {
 			/* Note: persistent fwmark-based services and
 			 * persistent port zero service are handled here.
@@ -268,24 +292,31 @@ ip_vs_sched_persist(struct ip_vs_service *svc,
 				vaddr = &fwmark;
 			}
 		}
-		ip_vs_conn_fill_param_persist(svc, skb, protocol, &snet, 0,
-					      vaddr, vport, &param);
+		/* return *ignored = -1 so NF_DROP can be used */
+		if (ip_vs_conn_fill_param_persist(svc, skb, protocol, &snet, 0,
+						  vaddr, vport, &param) < 0) {
+			*ignored = -1;
+			return NULL;
+		}
 	}
 
 	/* Check if a template already exists */
 	ct = ip_vs_ct_in_get(&param);
 	if (!ct || !ip_vs_check_template(ct)) {
-		/* No template found or the dest of the connection
+		/*
+		 * No template found or the dest of the connection
 		 * template is not available.
+		 * return *ignored=0 i.e. ICMP and NF_DROP
 		 */
 		dest = svc->scheduler->schedule(svc, skb);
 		if (!dest) {
 			IP_VS_DBG(1, "p-schedule: no dest found.\n");
 			kfree(param.pe_data);
+			*ignored = 0;
 			return NULL;
 		}
 
-		if (ports[1] == svc->port && svc->port != FTPPORT)
+		if (dst_port == svc->port && svc->port != FTPPORT)
 			dport = dest->port;
 
 		/* Create a template
@@ -293,9 +324,10 @@ ip_vs_sched_persist(struct ip_vs_service *svc,
 		 * and thus param.pe_data will be destroyed
 		 * when the template expires */
 		ct = ip_vs_conn_new(&param, &dest->addr, dport,
-				    IP_VS_CONN_F_TEMPLATE, dest);
+				    IP_VS_CONN_F_TEMPLATE, dest, skb->mark);
 		if (ct == NULL) {
 			kfree(param.pe_data);
+			*ignored = -1;
 			return NULL;
 		}
 
@@ -306,7 +338,7 @@ ip_vs_sched_persist(struct ip_vs_service *svc,
 		kfree(param.pe_data);
 	}
 
-	dport = ports[1];
+	dport = dst_port;
 	if (dport == svc->port && dest->port)
 		dport = dest->port;
 
@@ -317,11 +349,13 @@ ip_vs_sched_persist(struct ip_vs_service *svc,
 	/*
 	 *    Create a new connection according to the template
 	 */
-	ip_vs_conn_fill_param(svc->af, iph.protocol, &iph.saddr, ports[0],
-			      &iph.daddr, ports[1], &param);
-	cp = ip_vs_conn_new(&param, &dest->addr, dport, flags, dest);
+	ip_vs_conn_fill_param(svc->net, svc->af, iph.protocol, &iph.saddr,
+			      src_port, &iph.daddr, dst_port, &param);
+
+	cp = ip_vs_conn_new(&param, &dest->addr, dport, flags, dest, skb->mark);
 	if (cp == NULL) {
 		ip_vs_conn_put(ct);
+		*ignored = -1;
 		return NULL;
 	}
 
@@ -341,11 +375,27 @@ ip_vs_sched_persist(struct ip_vs_service *svc,
  *  It selects a server according to the virtual service, and
  *  creates a connection entry.
  *  Protocols supported: TCP, UDP
+ *
+ *  Usage of *ignored
+ *
+ * 1 :   protocol tried to schedule (eg. on SYN), found svc but the
+ *       svc/scheduler decides that this packet should be accepted with
+ *       NF_ACCEPT because it must not be scheduled.
+ *
+ * 0 :   scheduler can not find destination, so try bypass or
+ *       return ICMP and then NF_DROP (ip_vs_leave).
+ *
+ * -1 :  scheduler tried to schedule but fatal error occurred, eg.
+ *       ip_vs_conn_new failure (ENOMEM) or ip_vs_sip_fill_param
+ *       failure such as missing Call-ID, ENOMEM on skb_linearize
+ *       or pe_data. In this case we should return NF_DROP without
+ *       any attempts to send ICMP with ip_vs_leave.
  */
 struct ip_vs_conn *
 ip_vs_schedule(struct ip_vs_service *svc, struct sk_buff *skb,
-	       struct ip_vs_protocol *pp, int *ignored)
+	       struct ip_vs_proto_data *pd, int *ignored)
 {
+	struct ip_vs_protocol *pp = pd->pp;
 	struct ip_vs_conn *cp = NULL;
 	struct ip_vs_iphdr iph;
 	struct ip_vs_dest *dest;
@@ -371,12 +421,10 @@ ip_vs_schedule(struct ip_vs_service *svc, struct sk_buff *skb,
 	}
 
 	/*
-	 * Do not schedule replies from local real server. It is risky
-	 * for fwmark services but mostly for persistent services.
+	 *    Do not schedule replies from local real server.
 	 */
 	if ((!skb->dev || skb->dev->flags & IFF_LOOPBACK) &&
-	    (svc->flags & IP_VS_SVC_F_PERSISTENT || svc->fwmark) &&
-	    (cp = pp->conn_in_get(svc->af, skb, pp, &iph, iph.len, 1))) {
+	    (cp = pp->conn_in_get(svc->af, skb, &iph, iph.len, 1))) {
 		IP_VS_DBG_PKT(12, svc->af, pp, skb, 0,
 			      "Not scheduling reply for existing connection");
 		__ip_vs_conn_put(cp);
@@ -386,10 +434,10 @@ ip_vs_schedule(struct ip_vs_service *svc, struct sk_buff *skb,
 	/*
 	 *    Persistent service
 	 */
-	if (svc->flags & IP_VS_SVC_F_PERSISTENT) {
-		*ignored = 0;
-		return ip_vs_sched_persist(svc, skb, pptr);
-	}
+	if (svc->flags & IP_VS_SVC_F_PERSISTENT)
+		return ip_vs_sched_persist(svc, skb, pptr[0], pptr[1], ignored);
+
+	*ignored = 0;
 
 	/*
 	 *    Non-persistent service
@@ -402,8 +450,6 @@ ip_vs_schedule(struct ip_vs_service *svc, struct sk_buff *skb,
 		return NULL;
 	}
 
-	*ignored = 0;
-
 	dest = svc->scheduler->schedule(svc, skb);
 	if (dest == NULL) {
 		IP_VS_DBG(1, "Schedule: no dest found.\n");
@@ -419,13 +465,17 @@ ip_vs_schedule(struct ip_vs_service *svc, struct sk_buff *skb,
 	 */
 	{
 		struct ip_vs_conn_param p;
-		ip_vs_conn_fill_param(svc->af, iph.protocol, &iph.saddr,
-				      pptr[0], &iph.daddr, pptr[1], &p);
+
+		ip_vs_conn_fill_param(svc->net, svc->af, iph.protocol,
+				      &iph.saddr, pptr[0], &iph.daddr, pptr[1],
+				      &p);
 		cp = ip_vs_conn_new(&p, &dest->addr,
 				    dest->port ? dest->port : pptr[1],
-				    flags, dest);
-		if (!cp)
+				    flags, dest, skb->mark);
+		if (!cp) {
+			*ignored = -1;
 			return NULL;
+		}
 	}
 
 	IP_VS_DBG_BUF(6, "Schedule fwd:%c c:%s:%u v:%s:%u "
@@ -447,11 +497,14 @@ ip_vs_schedule(struct ip_vs_service *svc, struct sk_buff *skb,
  *  no destination is available for a new connection.
  */
 int ip_vs_leave(struct ip_vs_service *svc, struct sk_buff *skb,
-		struct ip_vs_protocol *pp)
+		struct ip_vs_proto_data *pd)
 {
+	struct net *net;
+	struct netns_ipvs *ipvs;
 	__be16 _ports[2], *pptr;
 	struct ip_vs_iphdr iph;
 	int unicast;
+
 	ip_vs_fill_iphdr(svc->af, skb_network_header(skb), &iph);
 
 	pptr = skb_header_pointer(skb, iph.len, sizeof(_ports), _ports);
@@ -459,18 +512,20 @@ int ip_vs_leave(struct ip_vs_service *svc, struct sk_buff *skb,
 		ip_vs_service_put(svc);
 		return NF_DROP;
 	}
+	net = skb_net(skb);
 
 #ifdef CONFIG_IP_VS_IPV6
 	if (svc->af == AF_INET6)
 		unicast = ipv6_addr_type(&iph.daddr.in6) & IPV6_ADDR_UNICAST;
 	else
 #endif
-		unicast = (inet_addr_type(&init_net, iph.daddr.ip) == RTN_UNICAST);
+		unicast = (inet_addr_type(net, iph.daddr.ip) == RTN_UNICAST);
 
 	/* if it is fwmark-based service, the cache_bypass sysctl is up
 	   and the destination is a non-local unicast, then create
 	   a cache_bypass connection entry */
-	if (sysctl_ip_vs_cache_bypass && svc->fwmark && unicast) {
+	ipvs = net_ipvs(net);
+	if (ipvs->sysctl_cache_bypass && svc->fwmark && unicast) {
 		int ret, cs;
 		struct ip_vs_conn *cp;
 		unsigned int flags = (svc->flags & IP_VS_SVC_F_ONEPACKET &&
@@ -484,12 +539,12 @@ int ip_vs_leave(struct ip_vs_service *svc, struct sk_buff *skb,
 		IP_VS_DBG(6, "%s(): create a cache_bypass entry\n", __func__);
 		{
 			struct ip_vs_conn_param p;
-			ip_vs_conn_fill_param(svc->af, iph.protocol,
+			ip_vs_conn_fill_param(svc->net, svc->af, iph.protocol,
 					      &iph.saddr, pptr[0],
 					      &iph.daddr, pptr[1], &p);
 			cp = ip_vs_conn_new(&p, &daddr, 0,
 					    IP_VS_CONN_F_BYPASS | flags,
-					    NULL);
+					    NULL, skb->mark);
 			if (!cp)
 				return NF_DROP;
 		}
@@ -498,10 +553,10 @@ int ip_vs_leave(struct ip_vs_service *svc, struct sk_buff *skb,
 		ip_vs_in_stats(cp, skb);
 
 		/* set state */
-		cs = ip_vs_set_state(cp, IP_VS_DIR_INPUT, skb, pp);
+		cs = ip_vs_set_state(cp, IP_VS_DIR_INPUT, skb, pd);
 
 		/* transmit the first SYN packet */
-		ret = cp->packet_xmit(skb, cp, pp);
+		ret = cp->packet_xmit(skb, cp, pd->pp);
 		/* do not touch skb anymore */
 
 		atomic_inc(&cp->in_pkts);
@@ -682,6 +737,7 @@ static int handle_response_icmp(int af, struct sk_buff *skb,
 				struct ip_vs_protocol *pp,
 				unsigned int offset, unsigned int ihl)
 {
+	struct netns_ipvs *ipvs;
 	unsigned int verdict = NF_DROP;
 
 	if (IP_VS_FWD_METHOD(cp) != 0) {
@@ -703,6 +759,8 @@ static int handle_response_icmp(int af, struct sk_buff *skb,
 	if (!skb_make_writable(skb, offset))
 		goto out;
 
+	ipvs = net_ipvs(skb_net(skb));
+
 #ifdef CONFIG_IP_VS_IPV6
 	if (af == AF_INET6)
 		ip_vs_nat_icmp_v6(skb, pp, cp, 1);
@@ -712,11 +770,11 @@ static int handle_response_icmp(int af, struct sk_buff *skb,
 
 #ifdef CONFIG_IP_VS_IPV6
 	if (af == AF_INET6) {
-		if (sysctl_ip_vs_snat_reroute && ip6_route_me_harder(skb) != 0)
+		if (ipvs->sysctl_snat_reroute && ip6_route_me_harder(skb) != 0)
 			goto out;
 	} else
 #endif
-		if ((sysctl_ip_vs_snat_reroute ||
+		if ((ipvs->sysctl_snat_reroute ||
 		     skb_rtable(skb)->rt_flags & RTCF_LOCAL) &&
 		    ip_route_me_harder(skb, RTN_LOCAL) != 0)
 			goto out;
@@ -808,7 +866,7 @@ static int ip_vs_out_icmp(struct sk_buff *skb, int *related,
 
 	ip_vs_fill_iphdr(AF_INET, cih, &ciph);
 	/* The embedded headers contain source and dest in reverse order */
-	cp = pp->conn_out_get(AF_INET, skb, pp, &ciph, offset, 1);
+	cp = pp->conn_out_get(AF_INET, skb, &ciph, offset, 1);
 	if (!cp)
 		return NF_ACCEPT;
 
@@ -885,7 +943,7 @@ static int ip_vs_out_icmp_v6(struct sk_buff *skb, int *related,
 
 	ip_vs_fill_iphdr(AF_INET6, cih, &ciph);
 	/* The embedded headers contain source and dest in reverse order */
-	cp = pp->conn_out_get(AF_INET6, skb, pp, &ciph, offset, 1);
+	cp = pp->conn_out_get(AF_INET6, skb, &ciph, offset, 1);
 	if (!cp)
 		return NF_ACCEPT;
 
@@ -924,9 +982,12 @@ static inline int is_tcp_reset(const struct sk_buff *skb, int nh_len)
  * Used for NAT and local client.
  */
 static unsigned int
-handle_response(int af, struct sk_buff *skb, struct ip_vs_protocol *pp,
+handle_response(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd,
 		struct ip_vs_conn *cp, int ihl)
 {
+	struct ip_vs_protocol *pp = pd->pp;
+	struct netns_ipvs *ipvs;
+
 	IP_VS_DBG_PKT(11, af, pp, skb, 0, "Outgoing packet");
 
 	if (!skb_make_writable(skb, ihl))
@@ -961,13 +1022,15 @@ handle_response(int af, struct sk_buff *skb, struct ip_vs_protocol *pp,
 	 * if it came from this machine itself.  So re-compute
 	 * the routing information.
 	 */
+	ipvs = net_ipvs(skb_net(skb));
+
 #ifdef CONFIG_IP_VS_IPV6
 	if (af == AF_INET6) {
-		if (sysctl_ip_vs_snat_reroute && ip6_route_me_harder(skb) != 0)
+		if (ipvs->sysctl_snat_reroute && ip6_route_me_harder(skb) != 0)
 			goto drop;
 	} else
 #endif
-		if ((sysctl_ip_vs_snat_reroute ||
+		if ((ipvs->sysctl_snat_reroute ||
 		     skb_rtable(skb)->rt_flags & RTCF_LOCAL) &&
 		    ip_route_me_harder(skb, RTN_LOCAL) != 0)
 			goto drop;
@@ -975,7 +1038,7 @@ handle_response(int af, struct sk_buff *skb, struct ip_vs_protocol *pp,
 	IP_VS_DBG_PKT(10, af, pp, skb, 0, "After SNAT");
 
 	ip_vs_out_stats(cp, skb);
-	ip_vs_set_state(cp, IP_VS_DIR_OUTPUT, skb, pp);
+	ip_vs_set_state(cp, IP_VS_DIR_OUTPUT, skb, pd);
 	skb->ipvs_property = 1;
 	if (!(cp->flags & IP_VS_CONN_F_NFCT))
 		ip_vs_notrack(skb);
@@ -999,9 +1062,12 @@ drop:
 static unsigned int
 ip_vs_out(unsigned int hooknum, struct sk_buff *skb, int af)
 {
+	struct net *net = NULL;
 	struct ip_vs_iphdr iph;
 	struct ip_vs_protocol *pp;
+	struct ip_vs_proto_data *pd;
 	struct ip_vs_conn *cp;
+	struct netns_ipvs *ipvs;
 
 	EnterFunction(11);
 
@@ -1022,6 +1088,7 @@ ip_vs_out(unsigned int hooknum, struct sk_buff *skb, int af)
 	if (unlikely(!skb_dst(skb)))
 		return NF_ACCEPT;
 
+	net = skb_net(skb);
 	ip_vs_fill_iphdr(af, skb_network_header(skb), &iph);
 #ifdef CONFIG_IP_VS_IPV6
 	if (af == AF_INET6) {
@@ -1045,9 +1112,10 @@ ip_vs_out(unsigned int hooknum, struct sk_buff *skb, int af)
 			ip_vs_fill_iphdr(af, skb_network_header(skb), &iph);
 		}
 
-	pp = ip_vs_proto_get(iph.protocol);
-	if (unlikely(!pp))
+	pd = ip_vs_proto_data_get(net, iph.protocol);
+	if (unlikely(!pd))
 		return NF_ACCEPT;
+	pp = pd->pp;
 
 	/* reassemble IP fragments */
 #ifdef CONFIG_IP_VS_IPV6
@@ -1073,11 +1141,12 @@ ip_vs_out(unsigned int hooknum, struct sk_buff *skb, int af)
 	/*
 	 * Check if the packet belongs to an existing entry
 	 */
-	cp = pp->conn_out_get(af, skb, pp, &iph, iph.len, 0);
+	cp = pp->conn_out_get(af, skb, &iph, iph.len, 0);
+	ipvs = net_ipvs(net);
 
 	if (likely(cp))
-		return handle_response(af, skb, pp, cp, iph.len);
-	if (sysctl_ip_vs_nat_icmp_send &&
+		return handle_response(af, skb, pd, cp, iph.len);
+	if (ipvs->sysctl_nat_icmp_send &&
 	    (pp->protocol == IPPROTO_TCP ||
 	     pp->protocol == IPPROTO_UDP ||
 	     pp->protocol == IPPROTO_SCTP)) {
@@ -1087,7 +1156,7 @@ ip_vs_out(unsigned int hooknum, struct sk_buff *skb, int af)
 					  sizeof(_ports), _ports);
 		if (pptr == NULL)
 			return NF_ACCEPT;	/* Not for me */
-		if (ip_vs_lookup_real_service(af, iph.protocol,
+		if (ip_vs_lookup_real_service(net, af, iph.protocol,
 					      &iph.saddr,
 					      pptr[0])) {
 			/*
@@ -1202,12 +1271,14 @@ ip_vs_local_reply6(unsigned int hooknum, struct sk_buff *skb,
 static int
 ip_vs_in_icmp(struct sk_buff *skb, int *related, unsigned int hooknum)
 {
+	struct net *net = NULL;
 	struct iphdr *iph;
 	struct icmphdr	_icmph, *ic;
 	struct iphdr	_ciph, *cih;	/* The ip header contained within the ICMP */
 	struct ip_vs_iphdr ciph;
 	struct ip_vs_conn *cp;
 	struct ip_vs_protocol *pp;
+	struct ip_vs_proto_data *pd;
 	unsigned int offset, ihl, verdict;
 	union nf_inet_addr snet;
 
@@ -1249,9 +1320,11 @@ ip_vs_in_icmp(struct sk_buff *skb, int *related, unsigned int hooknum)
 	if (cih == NULL)
 		return NF_ACCEPT; /* The packet looks wrong, ignore */
 
-	pp = ip_vs_proto_get(cih->protocol);
-	if (!pp)
+	net = skb_net(skb);
+	pd = ip_vs_proto_data_get(net, cih->protocol);
+	if (!pd)
 		return NF_ACCEPT;
+	pp = pd->pp;
 
 	/* Is the embedded protocol header present? */
 	if (unlikely(cih->frag_off & htons(IP_OFFSET) &&
@@ -1265,10 +1338,10 @@ ip_vs_in_icmp(struct sk_buff *skb, int *related, unsigned int hooknum)
 
 	ip_vs_fill_iphdr(AF_INET, cih, &ciph);
 	/* The embedded headers contain source and dest in reverse order */
-	cp = pp->conn_in_get(AF_INET, skb, pp, &ciph, offset, 1);
+	cp = pp->conn_in_get(AF_INET, skb, &ciph, offset, 1);
 	if (!cp) {
 		/* The packet could also belong to a local client */
-		cp = pp->conn_out_get(AF_INET, skb, pp, &ciph, offset, 1);
+		cp = pp->conn_out_get(AF_INET, skb, &ciph, offset, 1);
 		if (cp) {
 			snet.ip = iph->saddr;
 			return handle_response_icmp(AF_INET, skb, &snet,
@@ -1312,6 +1385,7 @@ ip_vs_in_icmp(struct sk_buff *skb, int *related, unsigned int hooknum)
 static int
 ip_vs_in_icmp_v6(struct sk_buff *skb, int *related, unsigned int hooknum)
 {
+	struct net *net = NULL;
 	struct ipv6hdr *iph;
 	struct icmp6hdr	_icmph, *ic;
 	struct ipv6hdr	_ciph, *cih;	/* The ip header contained
@@ -1319,6 +1393,7 @@ ip_vs_in_icmp_v6(struct sk_buff *skb, int *related, unsigned int hooknum)
 	struct ip_vs_iphdr ciph;
 	struct ip_vs_conn *cp;
 	struct ip_vs_protocol *pp;
+	struct ip_vs_proto_data *pd;
 	unsigned int offset, verdict;
 	union nf_inet_addr snet;
 	struct rt6_info *rt;
@@ -1361,9 +1436,11 @@ ip_vs_in_icmp_v6(struct sk_buff *skb, int *related, unsigned int hooknum)
 	if (cih == NULL)
 		return NF_ACCEPT; /* The packet looks wrong, ignore */
 
-	pp = ip_vs_proto_get(cih->nexthdr);
-	if (!pp)
+	net = skb_net(skb);
+	pd = ip_vs_proto_data_get(net, cih->nexthdr);
+	if (!pd)
 		return NF_ACCEPT;
+	pp = pd->pp;
 
 	/* Is the embedded protocol header present? */
 	/* TODO: we don't support fragmentation at the moment anyways */
@@ -1377,10 +1454,10 @@ ip_vs_in_icmp_v6(struct sk_buff *skb, int *related, unsigned int hooknum)
 
 	ip_vs_fill_iphdr(AF_INET6, cih, &ciph);
 	/* The embedded headers contain source and dest in reverse order */
-	cp = pp->conn_in_get(AF_INET6, skb, pp, &ciph, offset, 1);
+	cp = pp->conn_in_get(AF_INET6, skb, &ciph, offset, 1);
 	if (!cp) {
 		/* The packet could also belong to a local client */
-		cp = pp->conn_out_get(AF_INET6, skb, pp, &ciph, offset, 1);
+		cp = pp->conn_out_get(AF_INET6, skb, &ciph, offset, 1);
 		if (cp) {
 			ipv6_addr_copy(&snet.in6, &iph->saddr);
 			return handle_response_icmp(AF_INET6, skb, &snet,
@@ -1423,10 +1500,13 @@ ip_vs_in_icmp_v6(struct sk_buff *skb, int *related, unsigned int hooknum)
 static unsigned int
 ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af)
 {
+	struct net *net;
 	struct ip_vs_iphdr iph;
 	struct ip_vs_protocol *pp;
+	struct ip_vs_proto_data *pd;
 	struct ip_vs_conn *cp;
 	int ret, restart, pkts;
+	struct netns_ipvs *ipvs;
 
 	/* Already marked as IPVS request or reply? */
 	if (skb->ipvs_property)
@@ -1480,20 +1560,21 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af)
 			ip_vs_fill_iphdr(af, skb_network_header(skb), &iph);
 		}
 
+	net = skb_net(skb);
 	/* Protocol supported? */
-	pp = ip_vs_proto_get(iph.protocol);
-	if (unlikely(!pp))
+	pd = ip_vs_proto_data_get(net, iph.protocol);
+	if (unlikely(!pd))
 		return NF_ACCEPT;
-
+	pp = pd->pp;
 	/*
 	 * Check if the packet belongs to an existing connection entry
 	 */
-	cp = pp->conn_in_get(af, skb, pp, &iph, iph.len, 0);
+	cp = pp->conn_in_get(af, skb, &iph, iph.len, 0);
 
 	if (unlikely(!cp)) {
 		int v;
 
-		if (!pp->conn_schedule(af, skb, pp, &v, &cp))
+		if (!pp->conn_schedule(af, skb, pd, &v, &cp))
 			return v;
 	}
 
@@ -1505,12 +1586,13 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af)
 	}
 
 	IP_VS_DBG_PKT(11, af, pp, skb, 0, "Incoming packet");
-
+	net = skb_net(skb);
+	ipvs = net_ipvs(net);
 	/* Check the server status */
 	if (cp->dest && !(cp->dest->flags & IP_VS_DEST_F_AVAILABLE)) {
 		/* the destination server is not available */
 
-		if (sysctl_ip_vs_expire_nodest_conn) {
+		if (ipvs->sysctl_expire_nodest_conn) {
 			/* try to expire the connection immediately */
 			ip_vs_conn_expire_now(cp);
 		}
@@ -1521,7 +1603,7 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af)
 	}
 
 	ip_vs_in_stats(cp, skb);
-	restart = ip_vs_set_state(cp, IP_VS_DIR_INPUT, skb, pp);
+	restart = ip_vs_set_state(cp, IP_VS_DIR_INPUT, skb, pd);
 	if (cp->packet_xmit)
 		ret = cp->packet_xmit(skb, cp, pp);
 		/* do not touch skb anymore */
@@ -1535,35 +1617,41 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af)
 	 *
 	 * Sync connection if it is about to close to
 	 * encorage the standby servers to update the connections timeout
+	 *
+	 * For ONE_PKT let ip_vs_sync_conn() do the filter work.
 	 */
-	pkts = atomic_add_return(1, &cp->in_pkts);
-	if (af == AF_INET && (ip_vs_sync_state & IP_VS_STATE_MASTER) &&
+
+	if (cp->flags & IP_VS_CONN_F_ONE_PACKET)
+		pkts = ipvs->sysctl_sync_threshold[0];
+	else
+		pkts = atomic_add_return(1, &cp->in_pkts);
+
+	if ((ipvs->sync_state & IP_VS_STATE_MASTER) &&
 	    cp->protocol == IPPROTO_SCTP) {
 		if ((cp->state == IP_VS_SCTP_S_ESTABLISHED &&
-			(pkts % sysctl_ip_vs_sync_threshold[1]
-			 == sysctl_ip_vs_sync_threshold[0])) ||
+			(pkts % ipvs->sysctl_sync_threshold[1]
+			 == ipvs->sysctl_sync_threshold[0])) ||
 				(cp->old_state != cp->state &&
 				 ((cp->state == IP_VS_SCTP_S_CLOSED) ||
 				  (cp->state == IP_VS_SCTP_S_SHUT_ACK_CLI) ||
 				  (cp->state == IP_VS_SCTP_S_SHUT_ACK_SER)))) {
-			ip_vs_sync_conn(cp);
+			ip_vs_sync_conn(net, cp);
 			goto out;
 		}
 	}
 
 	/* Keep this block last: TCP and others with pp->num_states <= 1 */
-	else if (af == AF_INET &&
-	    (ip_vs_sync_state & IP_VS_STATE_MASTER) &&
+	else if ((ipvs->sync_state & IP_VS_STATE_MASTER) &&
 	    (((cp->protocol != IPPROTO_TCP ||
 	       cp->state == IP_VS_TCP_S_ESTABLISHED) &&
-	      (pkts % sysctl_ip_vs_sync_threshold[1]
-	       == sysctl_ip_vs_sync_threshold[0])) ||
+	      (pkts % ipvs->sysctl_sync_threshold[1]
+	       == ipvs->sysctl_sync_threshold[0])) ||
 	     ((cp->protocol == IPPROTO_TCP) && (cp->old_state != cp->state) &&
 	      ((cp->state == IP_VS_TCP_S_FIN_WAIT) ||
 	       (cp->state == IP_VS_TCP_S_CLOSE) ||
 	       (cp->state == IP_VS_TCP_S_CLOSE_WAIT) ||
 	       (cp->state == IP_VS_TCP_S_TIME_WAIT)))))
-		ip_vs_sync_conn(cp);
+		ip_vs_sync_conn(net, cp);
 out:
 	cp->old_state = cp->state;
 
@@ -1782,7 +1870,41 @@ static struct nf_hook_ops ip_vs_ops[] __read_mostly = {
 	},
 #endif
 };
+/*
+ *	Initialize IP Virtual Server netns mem.
+ */
+static int __net_init __ip_vs_init(struct net *net)
+{
+	struct netns_ipvs *ipvs;
+
+	ipvs = net_generic(net, ip_vs_net_id);
+	if (ipvs == NULL) {
+		pr_err("%s(): no memory.\n", __func__);
+		return -ENOMEM;
+	}
+	ipvs->net = net;
+	/* Counters used for creating unique names */
+	ipvs->gen = atomic_read(&ipvs_netns_cnt);
+	atomic_inc(&ipvs_netns_cnt);
+	net->ipvs = ipvs;
+	printk(KERN_INFO "IPVS: Creating netns size=%lu id=%d\n",
+			 sizeof(struct netns_ipvs), ipvs->gen);
+	return 0;
+}
+
+static void __net_exit __ip_vs_cleanup(struct net *net)
+{
+	struct netns_ipvs *ipvs = net_ipvs(net);
 
+	IP_VS_DBG(10, "ipvs netns %d released\n", ipvs->gen);
+}
+
+static struct pernet_operations ipvs_core_ops = {
+	.init = __ip_vs_init,
+	.exit = __ip_vs_cleanup,
+	.id   = &ip_vs_net_id,
+	.size = sizeof(struct netns_ipvs),
+};
 
 /*
  *	Initialize IP Virtual Server
@@ -1791,8 +1913,11 @@ static int __init ip_vs_init(void)
 {
 	int ret;
 
-	ip_vs_estimator_init();
+	ret = register_pernet_subsys(&ipvs_core_ops);	/* Alloc ip_vs struct */
+	if (ret < 0)
+		return ret;
 
+	ip_vs_estimator_init();
 	ret = ip_vs_control_init();
 	if (ret < 0) {
 		pr_err("can't setup control.\n");
@@ -1813,15 +1938,23 @@ static int __init ip_vs_init(void)
 		goto cleanup_app;
 	}
 
+	ret = ip_vs_sync_init();
+	if (ret < 0) {
+		pr_err("can't setup sync data.\n");
+		goto cleanup_conn;
+	}
+
 	ret = nf_register_hooks(ip_vs_ops, ARRAY_SIZE(ip_vs_ops));
 	if (ret < 0) {
 		pr_err("can't register hooks.\n");
-		goto cleanup_conn;
+		goto cleanup_sync;
 	}
 
 	pr_info("ipvs loaded.\n");
 	return ret;
 
+cleanup_sync:
+	ip_vs_sync_cleanup();
   cleanup_conn:
 	ip_vs_conn_cleanup();
   cleanup_app:
@@ -1831,17 +1964,20 @@ static int __init ip_vs_init(void)
 	ip_vs_control_cleanup();
   cleanup_estimator:
 	ip_vs_estimator_cleanup();
+	unregister_pernet_subsys(&ipvs_core_ops);	/* free ip_vs struct */
 	return ret;
 }
 
 static void __exit ip_vs_cleanup(void)
 {
 	nf_unregister_hooks(ip_vs_ops, ARRAY_SIZE(ip_vs_ops));
+	ip_vs_sync_cleanup();
 	ip_vs_conn_cleanup();
 	ip_vs_app_cleanup();
 	ip_vs_protocol_cleanup();
 	ip_vs_control_cleanup();
 	ip_vs_estimator_cleanup();
+	unregister_pernet_subsys(&ipvs_core_ops);	/* free ip_vs struct */
 	pr_info("ipvs unloaded.\n");
 }
 

net/netfilter/ipvs/ip_vs_est.c

@@ -8,8 +8,12 @@
  *              as published by the Free Software Foundation; either version
  *              2 of the License, or (at your option) any later version.
  *
- * Changes:
- *
+ * Changes:     Hans Schillstrom <hans.schillstrom@ericsson.com>
+ *              Network name space (netns) aware.
+ *              Global data moved to netns i.e struct netns_ipvs
+ *              Affected data: est_list and est_lock.
+ *              estimation_timer() runs with timer per netns.
+ *              get_stats()) do the per cpu summing.
  */
 
 #define KMSG_COMPONENT "IPVS"
@@ -48,11 +52,42 @@
  */
 
 
-static void estimation_timer(unsigned long arg);
+/*
+ * Make a summary from each cpu
+ */
+static void ip_vs_read_cpu_stats(struct ip_vs_stats_user *sum,
+				 struct ip_vs_cpu_stats *stats)
+{
+	int i;
+
+	for_each_possible_cpu(i) {
+		struct ip_vs_cpu_stats *s = per_cpu_ptr(stats, i);
+		unsigned int start;
+		__u64 inbytes, outbytes;
+		if (i) {
+			sum->conns += s->ustats.conns;
+			sum->inpkts += s->ustats.inpkts;
+			sum->outpkts += s->ustats.outpkts;
+			do {
+				start = u64_stats_fetch_begin_bh(&s->syncp);
+				inbytes = s->ustats.inbytes;
+				outbytes = s->ustats.outbytes;
+			} while (u64_stats_fetch_retry_bh(&s->syncp, start));
+			sum->inbytes += inbytes;
+			sum->outbytes += outbytes;
+		} else {
+			sum->conns = s->ustats.conns;
+			sum->inpkts = s->ustats.inpkts;
+			sum->outpkts = s->ustats.outpkts;
+			do {
+				start = u64_stats_fetch_begin_bh(&s->syncp);
+				sum->inbytes = s->ustats.inbytes;
+				sum->outbytes = s->ustats.outbytes;
+			} while (u64_stats_fetch_retry_bh(&s->syncp, start));
+		}
+	}
+}
 
-static LIST_HEAD(est_list);
-static DEFINE_SPINLOCK(est_lock);
-static DEFINE_TIMER(est_timer, estimation_timer, 0, 0);
 
 static void estimation_timer(unsigned long arg)
 {
@@ -62,11 +97,16 @@ static void estimation_timer(unsigned long arg)
 	u32 n_inpkts, n_outpkts;
 	u64 n_inbytes, n_outbytes;
 	u32 rate;
+	struct net *net = (struct net *)arg;
+	struct netns_ipvs *ipvs;
 
-	spin_lock(&est_lock);
-	list_for_each_entry(e, &est_list, list) {
+	ipvs = net_ipvs(net);
+	ip_vs_read_cpu_stats(&ipvs->tot_stats->ustats, ipvs->cpustats);
+	spin_lock(&ipvs->est_lock);
+	list_for_each_entry(e, &ipvs->est_list, list) {
 		s = container_of(e, struct ip_vs_stats, est);
 
+		ip_vs_read_cpu_stats(&s->ustats, s->cpustats);
 		spin_lock(&s->lock);
 		n_conns = s->ustats.conns;
 		n_inpkts = s->ustats.inpkts;
@@ -75,38 +115,39 @@ static void estimation_timer(unsigned long arg)
 		n_outbytes = s->ustats.outbytes;
 
 		/* scaled by 2^10, but divided 2 seconds */
-		rate = (n_conns - e->last_conns)<<9;
+		rate = (n_conns - e->last_conns) << 9;
 		e->last_conns = n_conns;
-		e->cps += ((long)rate - (long)e->cps)>>2;
-		s->ustats.cps = (e->cps+0x1FF)>>10;
+		e->cps += ((long)rate - (long)e->cps) >> 2;
+		s->ustats.cps = (e->cps + 0x1FF) >> 10;
 
-		rate = (n_inpkts - e->last_inpkts)<<9;
+		rate = (n_inpkts - e->last_inpkts) << 9;
 		e->last_inpkts = n_inpkts;
-		e->inpps += ((long)rate - (long)e->inpps)>>2;
-		s->ustats.inpps = (e->inpps+0x1FF)>>10;
+		e->inpps += ((long)rate - (long)e->inpps) >> 2;
+		s->ustats.inpps = (e->inpps + 0x1FF) >> 10;
 
-		rate = (n_outpkts - e->last_outpkts)<<9;
+		rate = (n_outpkts - e->last_outpkts) << 9;
 		e->last_outpkts = n_outpkts;
-		e->outpps += ((long)rate - (long)e->outpps)>>2;
-		s->ustats.outpps = (e->outpps+0x1FF)>>10;
+		e->outpps += ((long)rate - (long)e->outpps) >> 2;
+		s->ustats.outpps = (e->outpps + 0x1FF) >> 10;
 
-		rate = (n_inbytes - e->last_inbytes)<<4;
+		rate = (n_inbytes - e->last_inbytes) << 4;
 		e->last_inbytes = n_inbytes;
-		e->inbps += ((long)rate - (long)e->inbps)>>2;
-		s->ustats.inbps = (e->inbps+0xF)>>5;
+		e->inbps += ((long)rate - (long)e->inbps) >> 2;
+		s->ustats.inbps = (e->inbps + 0xF) >> 5;
 
-		rate = (n_outbytes - e->last_outbytes)<<4;
+		rate = (n_outbytes - e->last_outbytes) << 4;
 		e->last_outbytes = n_outbytes;
-		e->outbps += ((long)rate - (long)e->outbps)>>2;
-		s->ustats.outbps = (e->outbps+0xF)>>5;
+		e->outbps += ((long)rate - (long)e->outbps) >> 2;
+		s->ustats.outbps = (e->outbps + 0xF) >> 5;
 		spin_unlock(&s->lock);
 	}
-	spin_unlock(&est_lock);
-	mod_timer(&est_timer, jiffies + 2*HZ);
+	spin_unlock(&ipvs->est_lock);
+	mod_timer(&ipvs->est_timer, jiffies + 2*HZ);
 }
 
-void ip_vs_new_estimator(struct ip_vs_stats *stats)
+void ip_vs_new_estimator(struct net *net, struct ip_vs_stats *stats)
 {
+	struct netns_ipvs *ipvs = net_ipvs(net);
 	struct ip_vs_estimator *est = &stats->est;
 
 	INIT_LIST_HEAD(&est->list);
@@ -126,18 +167,19 @@ void ip_vs_new_estimator(struct ip_vs_stats *stats)
 	est->last_outbytes = stats->ustats.outbytes;
 	est->outbps = stats->ustats.outbps<<5;
 
-	spin_lock_bh(&est_lock);
-	list_add(&est->list, &est_list);
-	spin_unlock_bh(&est_lock);
+	spin_lock_bh(&ipvs->est_lock);
+	list_add(&est->list, &ipvs->est_list);
+	spin_unlock_bh(&ipvs->est_lock);
 }
 
-void ip_vs_kill_estimator(struct ip_vs_stats *stats)
+void ip_vs_kill_estimator(struct net *net, struct ip_vs_stats *stats)
 {
+	struct netns_ipvs *ipvs = net_ipvs(net);
 	struct ip_vs_estimator *est = &stats->est;
 
-	spin_lock_bh(&est_lock);
+	spin_lock_bh(&ipvs->est_lock);
 	list_del(&est->list);
-	spin_unlock_bh(&est_lock);
+	spin_unlock_bh(&ipvs->est_lock);
 }
 
 void ip_vs_zero_estimator(struct ip_vs_stats *stats)
@@ -157,13 +199,35 @@ void ip_vs_zero_estimator(struct ip_vs_stats *stats)
 	est->outbps = 0;
 }
 
-int __init ip_vs_estimator_init(void)
+static int __net_init __ip_vs_estimator_init(struct net *net)
 {
-	mod_timer(&est_timer, jiffies + 2 * HZ);
+	struct netns_ipvs *ipvs = net_ipvs(net);
+
+	INIT_LIST_HEAD(&ipvs->est_list);
+	spin_lock_init(&ipvs->est_lock);
+	setup_timer(&ipvs->est_timer, estimation_timer, (unsigned long)net);
+	mod_timer(&ipvs->est_timer, jiffies + 2 * HZ);
 	return 0;
 }
 
+static void __net_exit __ip_vs_estimator_exit(struct net *net)
+{
+	del_timer_sync(&net_ipvs(net)->est_timer);
+}
+static struct pernet_operations ip_vs_app_ops = {
+	.init = __ip_vs_estimator_init,
+	.exit = __ip_vs_estimator_exit,
+};
+
+int __init ip_vs_estimator_init(void)
+{
+	int rv;
+
+	rv = register_pernet_subsys(&ip_vs_app_ops);
+	return rv;
+}
+
 void ip_vs_estimator_cleanup(void)
 {
-	del_timer_sync(&est_timer);
+	unregister_pernet_subsys(&ip_vs_app_ops);
 }

net/netfilter/ipvs/ip_vs_ftp.c

@@ -157,6 +157,7 @@ static int ip_vs_ftp_out(struct ip_vs_app *app, struct ip_vs_conn *cp,
 	int ret = 0;
 	enum ip_conntrack_info ctinfo;
 	struct nf_conn *ct;
+	struct net *net;
 
 #ifdef CONFIG_IP_VS_IPV6
 	/* This application helper doesn't work with IPv6 yet,
@@ -197,18 +198,20 @@ static int ip_vs_ftp_out(struct ip_vs_app *app, struct ip_vs_conn *cp,
 		 */
 		{
 			struct ip_vs_conn_param p;
-			ip_vs_conn_fill_param(AF_INET, iph->protocol,
-					      &from, port, &cp->caddr, 0, &p);
+			ip_vs_conn_fill_param(ip_vs_conn_net(cp), AF_INET,
+					      iph->protocol, &from, port,
+					      &cp->caddr, 0, &p);
 			n_cp = ip_vs_conn_out_get(&p);
 		}
 		if (!n_cp) {
 			struct ip_vs_conn_param p;
-			ip_vs_conn_fill_param(AF_INET, IPPROTO_TCP, &cp->caddr,
+			ip_vs_conn_fill_param(ip_vs_conn_net(cp),
+					      AF_INET, IPPROTO_TCP, &cp->caddr,
 					      0, &cp->vaddr, port, &p);
 			n_cp = ip_vs_conn_new(&p, &from, port,
 					      IP_VS_CONN_F_NO_CPORT |
 					      IP_VS_CONN_F_NFCT,
-					      cp->dest);
+					      cp->dest, skb->mark);
 			if (!n_cp)
 				return 0;
 
@@ -257,8 +260,9 @@ static int ip_vs_ftp_out(struct ip_vs_app *app, struct ip_vs_conn *cp,
 		 * would be adjusted twice.
 		 */
 
+		net = skb_net(skb);
 		cp->app_data = NULL;
-		ip_vs_tcp_conn_listen(n_cp);
+		ip_vs_tcp_conn_listen(net, n_cp);
 		ip_vs_conn_put(n_cp);
 		return ret;
 	}
@@ -287,6 +291,7 @@ static int ip_vs_ftp_in(struct ip_vs_app *app, struct ip_vs_conn *cp,
 	union nf_inet_addr to;
 	__be16 port;
 	struct ip_vs_conn *n_cp;
+	struct net *net;
 
 #ifdef CONFIG_IP_VS_IPV6
 	/* This application helper doesn't work with IPv6 yet,
@@ -358,14 +363,15 @@ static int ip_vs_ftp_in(struct ip_vs_app *app, struct ip_vs_conn *cp,
 
 	{
 		struct ip_vs_conn_param p;
-		ip_vs_conn_fill_param(AF_INET, iph->protocol, &to, port,
-				      &cp->vaddr, htons(ntohs(cp->vport)-1),
-				      &p);
+		ip_vs_conn_fill_param(ip_vs_conn_net(cp), AF_INET,
+				      iph->protocol, &to, port, &cp->vaddr,
+				      htons(ntohs(cp->vport)-1), &p);
 		n_cp = ip_vs_conn_in_get(&p);
 		if (!n_cp) {
 			n_cp = ip_vs_conn_new(&p, &cp->daddr,
 					      htons(ntohs(cp->dport)-1),
-					      IP_VS_CONN_F_NFCT, cp->dest);
+					      IP_VS_CONN_F_NFCT, cp->dest,
+					      skb->mark);
 			if (!n_cp)
 				return 0;
 
@@ -377,7 +383,8 @@ static int ip_vs_ftp_in(struct ip_vs_app *app, struct ip_vs_conn *cp,
 	/*
 	 *	Move tunnel to listen state
 	 */
-	ip_vs_tcp_conn_listen(n_cp);
+	net = skb_net(skb);
+	ip_vs_tcp_conn_listen(net, n_cp);
 	ip_vs_conn_put(n_cp);
 
 	return 1;
@@ -398,23 +405,22 @@ static struct ip_vs_app ip_vs_ftp = {
 	.pkt_in =	ip_vs_ftp_in,
 };
 
-
 /*
- *	ip_vs_ftp initialization
+ *	per netns ip_vs_ftp initialization
  */
-static int __init ip_vs_ftp_init(void)
+static int __net_init __ip_vs_ftp_init(struct net *net)
 {
 	int i, ret;
 	struct ip_vs_app *app = &ip_vs_ftp;
 
-	ret = register_ip_vs_app(app);
+	ret = register_ip_vs_app(net, app);
 	if (ret)
 		return ret;
 
 	for (i=0; i<IP_VS_APP_MAX_PORTS; i++) {
 		if (!ports[i])
 			continue;
-		ret = register_ip_vs_app_inc(app, app->protocol, ports[i]);
+		ret = register_ip_vs_app_inc(net, app, app->protocol, ports[i]);
 		if (ret)
 			break;
 		pr_info("%s: loaded support on port[%d] = %d\n",
@@ -422,18 +428,39 @@ static int __init ip_vs_ftp_init(void)
 	}
 
 	if (ret)
-		unregister_ip_vs_app(app);
+		unregister_ip_vs_app(net, app);
 
 	return ret;
 }
+/*
+ *	netns exit
+ */
+static void __ip_vs_ftp_exit(struct net *net)
+{
+	struct ip_vs_app *app = &ip_vs_ftp;
+
+	unregister_ip_vs_app(net, app);
+}
+
+static struct pernet_operations ip_vs_ftp_ops = {
+	.init = __ip_vs_ftp_init,
+	.exit = __ip_vs_ftp_exit,
+};
 
+int __init ip_vs_ftp_init(void)
+{
+	int rv;
+
+	rv = register_pernet_subsys(&ip_vs_ftp_ops);
+	return rv;
+}
 
 /*
  *	ip_vs_ftp finish.
  */
 static void __exit ip_vs_ftp_exit(void)
 {
-	unregister_ip_vs_app(&ip_vs_ftp);
+	unregister_pernet_subsys(&ip_vs_ftp_ops);
 }
 
 

net/netfilter/ipvs/ip_vs_lblc.c

@@ -70,7 +70,6 @@
  *    entries that haven't been touched for a day.
  */
 #define COUNT_FOR_FULL_EXPIRATION   30
-static int sysctl_ip_vs_lblc_expiration = 24*60*60*HZ;
 
 
 /*
@@ -117,7 +116,7 @@ struct ip_vs_lblc_table {
 static ctl_table vs_vars_table[] = {
 	{
 		.procname	= "lblc_expiration",
-		.data		= &sysctl_ip_vs_lblc_expiration,
+		.data		= NULL,
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_jiffies,
@@ -125,8 +124,6 @@ static ctl_table vs_vars_table[] = {
 	{ }
 };
 
-static struct ctl_table_header * sysctl_header;
-
 static inline void ip_vs_lblc_free(struct ip_vs_lblc_entry *en)
 {
 	list_del(&en->list);
@@ -248,6 +245,7 @@ static inline void ip_vs_lblc_full_check(struct ip_vs_service *svc)
 	struct ip_vs_lblc_entry *en, *nxt;
 	unsigned long now = jiffies;
 	int i, j;
+	struct netns_ipvs *ipvs = net_ipvs(svc->net);
 
 	for (i=0, j=tbl->rover; i<IP_VS_LBLC_TAB_SIZE; i++) {
 		j = (j + 1) & IP_VS_LBLC_TAB_MASK;
@@ -255,7 +253,8 @@ static inline void ip_vs_lblc_full_check(struct ip_vs_service *svc)
 		write_lock(&svc->sched_lock);
 		list_for_each_entry_safe(en, nxt, &tbl->bucket[j], list) {
 			if (time_before(now,
-					en->lastuse + sysctl_ip_vs_lblc_expiration))
+					en->lastuse +
+					ipvs->sysctl_lblc_expiration))
 				continue;
 
 			ip_vs_lblc_free(en);
@@ -543,23 +542,73 @@ static struct ip_vs_scheduler ip_vs_lblc_scheduler =
 	.schedule =		ip_vs_lblc_schedule,
 };
 
+/*
+ *  per netns init.
+ */
+static int __net_init __ip_vs_lblc_init(struct net *net)
+{
+	struct netns_ipvs *ipvs = net_ipvs(net);
+
+	if (!net_eq(net, &init_net)) {
+		ipvs->lblc_ctl_table = kmemdup(vs_vars_table,
+						sizeof(vs_vars_table),
+						GFP_KERNEL);
+		if (ipvs->lblc_ctl_table == NULL)
+			goto err_dup;
+	} else
+		ipvs->lblc_ctl_table = vs_vars_table;
+	ipvs->sysctl_lblc_expiration = 24*60*60*HZ;
+	ipvs->lblc_ctl_table[0].data = &ipvs->sysctl_lblc_expiration;
+
+	ipvs->lblc_ctl_header =
+		register_net_sysctl_table(net, net_vs_ctl_path,
+					  ipvs->lblc_ctl_table);
+	if (!ipvs->lblc_ctl_header)
+		goto err_reg;
+
+	return 0;
+
+err_reg:
+	if (!net_eq(net, &init_net))
+		kfree(ipvs->lblc_ctl_table);
+
+err_dup:
+	return -ENOMEM;
+}
+
+static void __net_exit __ip_vs_lblc_exit(struct net *net)
+{
+	struct netns_ipvs *ipvs = net_ipvs(net);
+
+	unregister_net_sysctl_table(ipvs->lblc_ctl_header);
+
+	if (!net_eq(net, &init_net))
+		kfree(ipvs->lblc_ctl_table);
+}
+
+static struct pernet_operations ip_vs_lblc_ops = {
+	.init = __ip_vs_lblc_init,
+	.exit = __ip_vs_lblc_exit,
+};
 
 static int __init ip_vs_lblc_init(void)
 {
 	int ret;
 
-	sysctl_header = register_sysctl_paths(net_vs_ctl_path, vs_vars_table);
+	ret = register_pernet_subsys(&ip_vs_lblc_ops);
+	if (ret)
+		return ret;
+
 	ret = register_ip_vs_scheduler(&ip_vs_lblc_scheduler);
 	if (ret)
-		unregister_sysctl_table(sysctl_header);
+		unregister_pernet_subsys(&ip_vs_lblc_ops);
 	return ret;
 }
 
-
 static void __exit ip_vs_lblc_cleanup(void)
 {
-	unregister_sysctl_table(sysctl_header);
 	unregister_ip_vs_scheduler(&ip_vs_lblc_scheduler);
+	unregister_pernet_subsys(&ip_vs_lblc_ops);
 }
 
 

net/netfilter/ipvs/ip_vs_lblcr.c

@@ -70,8 +70,6 @@
  *    entries that haven't been touched for a day.
  */
 #define COUNT_FOR_FULL_EXPIRATION   30
-static int sysctl_ip_vs_lblcr_expiration = 24*60*60*HZ;
-
 
 /*
  *     for IPVS lblcr entry hash table
@@ -296,7 +294,7 @@ struct ip_vs_lblcr_table {
 static ctl_table vs_vars_table[] = {
 	{
 		.procname	= "lblcr_expiration",
-		.data		= &sysctl_ip_vs_lblcr_expiration,
+		.data		= NULL,
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_jiffies,
@@ -304,8 +302,6 @@ static ctl_table vs_vars_table[] = {
 	{ }
 };
 
-static struct ctl_table_header * sysctl_header;
-
 static inline void ip_vs_lblcr_free(struct ip_vs_lblcr_entry *en)
 {
 	list_del(&en->list);
@@ -425,14 +421,15 @@ static inline void ip_vs_lblcr_full_check(struct ip_vs_service *svc)
 	unsigned long now = jiffies;
 	int i, j;
 	struct ip_vs_lblcr_entry *en, *nxt;
+	struct netns_ipvs *ipvs = net_ipvs(svc->net);
 
 	for (i=0, j=tbl->rover; i<IP_VS_LBLCR_TAB_SIZE; i++) {
 		j = (j + 1) & IP_VS_LBLCR_TAB_MASK;
 
 		write_lock(&svc->sched_lock);
 		list_for_each_entry_safe(en, nxt, &tbl->bucket[j], list) {
-			if (time_after(en->lastuse+sysctl_ip_vs_lblcr_expiration,
-				       now))
+			if (time_after(en->lastuse
+					+ ipvs->sysctl_lblcr_expiration, now))
 				continue;
 
 			ip_vs_lblcr_free(en);
@@ -664,6 +661,7 @@ ip_vs_lblcr_schedule(struct ip_vs_service *svc, const struct sk_buff *skb)
 	read_lock(&svc->sched_lock);
 	en = ip_vs_lblcr_get(svc->af, tbl, &iph.daddr);
 	if (en) {
+		struct netns_ipvs *ipvs = net_ipvs(svc->net);
 		/* We only hold a read lock, but this is atomic */
 		en->lastuse = jiffies;
 
@@ -675,7 +673,7 @@ ip_vs_lblcr_schedule(struct ip_vs_service *svc, const struct sk_buff *skb)
 		/* More than one destination + enough time passed by, cleanup */
 		if (atomic_read(&en->set.size) > 1 &&
 				time_after(jiffies, en->set.lastmod +
-				sysctl_ip_vs_lblcr_expiration)) {
+				ipvs->sysctl_lblcr_expiration)) {
 			struct ip_vs_dest *m;
 
 			write_lock(&en->set.lock);
@@ -744,23 +742,73 @@ static struct ip_vs_scheduler ip_vs_lblcr_scheduler =
 	.schedule =		ip_vs_lblcr_schedule,
 };
 
+/*
+ *  per netns init.
+ */
+static int __net_init __ip_vs_lblcr_init(struct net *net)
+{
+	struct netns_ipvs *ipvs = net_ipvs(net);
+
+	if (!net_eq(net, &init_net)) {
+		ipvs->lblcr_ctl_table = kmemdup(vs_vars_table,
+						sizeof(vs_vars_table),
+						GFP_KERNEL);
+		if (ipvs->lblcr_ctl_table == NULL)
+			goto err_dup;
+	} else
+		ipvs->lblcr_ctl_table = vs_vars_table;
+	ipvs->sysctl_lblcr_expiration = 24*60*60*HZ;
+	ipvs->lblcr_ctl_table[0].data = &ipvs->sysctl_lblcr_expiration;
+
+	ipvs->lblcr_ctl_header =
+		register_net_sysctl_table(net, net_vs_ctl_path,
+					  ipvs->lblcr_ctl_table);
+	if (!ipvs->lblcr_ctl_header)
+		goto err_reg;
+
+	return 0;
+
+err_reg:
+	if (!net_eq(net, &init_net))
+		kfree(ipvs->lblcr_ctl_table);
+
+err_dup:
+	return -ENOMEM;
+}
+
+static void __net_exit __ip_vs_lblcr_exit(struct net *net)
+{
+	struct netns_ipvs *ipvs = net_ipvs(net);
+
+	unregister_net_sysctl_table(ipvs->lblcr_ctl_header);
+
+	if (!net_eq(net, &init_net))
+		kfree(ipvs->lblcr_ctl_table);
+}
+
+static struct pernet_operations ip_vs_lblcr_ops = {
+	.init = __ip_vs_lblcr_init,
+	.exit = __ip_vs_lblcr_exit,
+};
 
 static int __init ip_vs_lblcr_init(void)
 {
 	int ret;
 
-	sysctl_header = register_sysctl_paths(net_vs_ctl_path, vs_vars_table);
+	ret = register_pernet_subsys(&ip_vs_lblcr_ops);
+	if (ret)
+		return ret;
+
 	ret = register_ip_vs_scheduler(&ip_vs_lblcr_scheduler);
 	if (ret)
-		unregister_sysctl_table(sysctl_header);
+		unregister_pernet_subsys(&ip_vs_lblcr_ops);
 	return ret;
 }
 
-
 static void __exit ip_vs_lblcr_cleanup(void)
 {
-	unregister_sysctl_table(sysctl_header);
 	unregister_ip_vs_scheduler(&ip_vs_lblcr_scheduler);
+	unregister_pernet_subsys(&ip_vs_lblcr_ops);
 }
 
 

net/netfilter/ipvs/ip_vs_nfct.c

@@ -141,6 +141,7 @@ static void ip_vs_nfct_expect_callback(struct nf_conn *ct,
 	struct nf_conntrack_tuple *orig, new_reply;
 	struct ip_vs_conn *cp;
 	struct ip_vs_conn_param p;
+	struct net *net = nf_ct_net(ct);
 
 	if (exp->tuple.src.l3num != PF_INET)
 		return;
@@ -155,7 +156,7 @@ static void ip_vs_nfct_expect_callback(struct nf_conn *ct,
 
 	/* RS->CLIENT */
 	orig = &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple;
-	ip_vs_conn_fill_param(exp->tuple.src.l3num, orig->dst.protonum,
+	ip_vs_conn_fill_param(net, exp->tuple.src.l3num, orig->dst.protonum,
 			      &orig->src.u3, orig->src.u.tcp.port,
 			      &orig->dst.u3, orig->dst.u.tcp.port, &p);
 	cp = ip_vs_conn_out_get(&p);
@@ -268,7 +269,8 @@ void ip_vs_conn_drop_conntrack(struct ip_vs_conn *cp)
 		" for conn " FMT_CONN "\n",
 		__func__, ARG_TUPLE(&tuple), ARG_CONN(cp));
 
-	h = nf_conntrack_find_get(&init_net, NF_CT_DEFAULT_ZONE, &tuple);
+	h = nf_conntrack_find_get(ip_vs_conn_net(cp), NF_CT_DEFAULT_ZONE,
+				  &tuple);
 	if (h) {
 		ct = nf_ct_tuplehash_to_ctrack(h);
 		/* Show what happens instead of calling nf_ct_kill() */

net/netfilter/ipvs/ip_vs_pe.c

@@ -29,12 +29,11 @@ void ip_vs_unbind_pe(struct ip_vs_service *svc)
 }
 
 /* Get pe in the pe list by name */
-static struct ip_vs_pe *
-ip_vs_pe_getbyname(const char *pe_name)
+struct ip_vs_pe *__ip_vs_pe_getbyname(const char *pe_name)
 {
 	struct ip_vs_pe *pe;
 
-	IP_VS_DBG(2, "%s(): pe_name \"%s\"\n", __func__,
+	IP_VS_DBG(10, "%s(): pe_name \"%s\"\n", __func__,
 		  pe_name);
 
 	spin_lock_bh(&ip_vs_pe_lock);
@@ -60,28 +59,22 @@ ip_vs_pe_getbyname(const char *pe_name)
 }
 
 /* Lookup pe and try to load it if it doesn't exist */
-struct ip_vs_pe *ip_vs_pe_get(const char *name)
+struct ip_vs_pe *ip_vs_pe_getbyname(const char *name)
 {
 	struct ip_vs_pe *pe;
 
 	/* Search for the pe by name */
-	pe = ip_vs_pe_getbyname(name);
+	pe = __ip_vs_pe_getbyname(name);
 
 	/* If pe not found, load the module and search again */
 	if (!pe) {
 		request_module("ip_vs_pe_%s", name);
-		pe = ip_vs_pe_getbyname(name);
+		pe = __ip_vs_pe_getbyname(name);
 	}
 
 	return pe;
 }
 
-void ip_vs_pe_put(struct ip_vs_pe *pe)
-{
-	if (pe && pe->module)
-		module_put(pe->module);
-}
-
 /* Register a pe in the pe list */
 int register_ip_vs_pe(struct ip_vs_pe *pe)
 {

net/netfilter/ipvs/ip_vs_pe_sip.c

@@ -71,6 +71,7 @@ ip_vs_sip_fill_param(struct ip_vs_conn_param *p, struct sk_buff *skb)
 	struct ip_vs_iphdr iph;
 	unsigned int dataoff, datalen, matchoff, matchlen;
 	const char *dptr;
+	int retc;
 
 	ip_vs_fill_iphdr(p->af, skb_network_header(skb), &iph);
 
@@ -83,6 +84,8 @@ ip_vs_sip_fill_param(struct ip_vs_conn_param *p, struct sk_buff *skb)
 	if (dataoff >= skb->len)
 		return -EINVAL;
 
+	if ((retc=skb_linearize(skb)) < 0)
+		return retc;
 	dptr = skb->data + dataoff;
 	datalen = skb->len - dataoff;
 

net/netfilter/ipvs/ip_vs_proto.c

@@ -60,6 +60,31 @@ static int __used __init register_ip_vs_protocol(struct ip_vs_protocol *pp)
 	return 0;
 }
 
+/*
+ *	register an ipvs protocols netns related data
+ */
+static int
+register_ip_vs_proto_netns(struct net *net, struct ip_vs_protocol *pp)
+{
+	struct netns_ipvs *ipvs = net_ipvs(net);
+	unsigned hash = IP_VS_PROTO_HASH(pp->protocol);
+	struct ip_vs_proto_data *pd =
+			kzalloc(sizeof(struct ip_vs_proto_data), GFP_ATOMIC);
+
+	if (!pd) {
+		pr_err("%s(): no memory.\n", __func__);
+		return -ENOMEM;
+	}
+	pd->pp = pp;	/* For speed issues */
+	pd->next = ipvs->proto_data_table[hash];
+	ipvs->proto_data_table[hash] = pd;
+	atomic_set(&pd->appcnt, 0);	/* Init app counter */
+
+	if (pp->init_netns != NULL)
+		pp->init_netns(net, pd);
+
+	return 0;
+}
 
 /*
  *	unregister an ipvs protocol
@@ -82,6 +107,29 @@ static int unregister_ip_vs_protocol(struct ip_vs_protocol *pp)
 	return -ESRCH;
 }
 
+/*
+ *	unregister an ipvs protocols netns data
+ */
+static int
+unregister_ip_vs_proto_netns(struct net *net, struct ip_vs_proto_data *pd)
+{
+	struct netns_ipvs *ipvs = net_ipvs(net);
+	struct ip_vs_proto_data **pd_p;
+	unsigned hash = IP_VS_PROTO_HASH(pd->pp->protocol);
+
+	pd_p = &ipvs->proto_data_table[hash];
+	for (; *pd_p; pd_p = &(*pd_p)->next) {
+		if (*pd_p == pd) {
+			*pd_p = pd->next;
+			if (pd->pp->exit_netns != NULL)
+				pd->pp->exit_netns(net, pd);
+			kfree(pd);
+			return 0;
+		}
+	}
+
+	return -ESRCH;
+}
 
 /*
  *	get ip_vs_protocol object by its proto.
@@ -100,19 +148,44 @@ struct ip_vs_protocol * ip_vs_proto_get(unsigned short proto)
 }
 EXPORT_SYMBOL(ip_vs_proto_get);
 
+/*
+ *	get ip_vs_protocol object data by netns and proto
+ */
+struct ip_vs_proto_data *
+__ipvs_proto_data_get(struct netns_ipvs *ipvs, unsigned short proto)
+{
+	struct ip_vs_proto_data *pd;
+	unsigned hash = IP_VS_PROTO_HASH(proto);
+
+	for (pd = ipvs->proto_data_table[hash]; pd; pd = pd->next) {
+		if (pd->pp->protocol == proto)
+			return pd;
+	}
+
+	return NULL;
+}
+
+struct ip_vs_proto_data *
+ip_vs_proto_data_get(struct net *net, unsigned short proto)
+{
+	struct netns_ipvs *ipvs = net_ipvs(net);
+
+	return __ipvs_proto_data_get(ipvs, proto);
+}
+EXPORT_SYMBOL(ip_vs_proto_data_get);
 
 /*
  *	Propagate event for state change to all protocols
  */
-void ip_vs_protocol_timeout_change(int flags)
+void ip_vs_protocol_timeout_change(struct netns_ipvs *ipvs, int flags)
 {
-	struct ip_vs_protocol *pp;
+	struct ip_vs_proto_data *pd;
 	int i;
 
 	for (i = 0; i < IP_VS_PROTO_TAB_SIZE; i++) {
-		for (pp = ip_vs_proto_table[i]; pp; pp = pp->next) {
-			if (pp->timeout_change)
-				pp->timeout_change(pp, flags);
+		for (pd = ipvs->proto_data_table[i]; pd; pd = pd->next) {
+			if (pd->pp->timeout_change)
+				pd->pp->timeout_change(pd, flags);
 		}
 	}
 }
@@ -236,6 +309,46 @@ ip_vs_tcpudp_debug_packet(int af, struct ip_vs_protocol *pp,
 		ip_vs_tcpudp_debug_packet_v4(pp, skb, offset, msg);
 }
 
+/*
+ * per network name-space init
+ */
+static int __net_init __ip_vs_protocol_init(struct net *net)
+{
+#ifdef CONFIG_IP_VS_PROTO_TCP
+	register_ip_vs_proto_netns(net, &ip_vs_protocol_tcp);
+#endif
+#ifdef CONFIG_IP_VS_PROTO_UDP
+	register_ip_vs_proto_netns(net, &ip_vs_protocol_udp);
+#endif
+#ifdef CONFIG_IP_VS_PROTO_SCTP
+	register_ip_vs_proto_netns(net, &ip_vs_protocol_sctp);
+#endif
+#ifdef CONFIG_IP_VS_PROTO_AH
+	register_ip_vs_proto_netns(net, &ip_vs_protocol_ah);
+#endif
+#ifdef CONFIG_IP_VS_PROTO_ESP
+	register_ip_vs_proto_netns(net, &ip_vs_protocol_esp);
+#endif
+	return 0;
+}
+
+static void __net_exit __ip_vs_protocol_cleanup(struct net *net)
+{
+	struct netns_ipvs *ipvs = net_ipvs(net);
+	struct ip_vs_proto_data *pd;
+	int i;
+
+	/* unregister all the ipvs proto data for this netns */
+	for (i = 0; i < IP_VS_PROTO_TAB_SIZE; i++) {
+		while ((pd = ipvs->proto_data_table[i]) != NULL)
+			unregister_ip_vs_proto_netns(net, pd);
+	}
+}
+
+static struct pernet_operations ipvs_proto_ops = {
+	.init = __ip_vs_protocol_init,
+	.exit = __ip_vs_protocol_cleanup,
+};
 
 int __init ip_vs_protocol_init(void)
 {
@@ -265,6 +378,7 @@ int __init ip_vs_protocol_init(void)
 	REGISTER_PROTOCOL(&ip_vs_protocol_esp);
 #endif
 	pr_info("Registered protocols (%s)\n", &protocols[2]);
+	return register_pernet_subsys(&ipvs_proto_ops);
 
 	return 0;
 }
@@ -275,6 +389,7 @@ void ip_vs_protocol_cleanup(void)
 	struct ip_vs_protocol *pp;
 	int i;
 
+	unregister_pernet_subsys(&ipvs_proto_ops);
 	/* unregister all the ipvs protocols */
 	for (i = 0; i < IP_VS_PROTO_TAB_SIZE; i++) {
 		while ((pp = ip_vs_proto_table[i]) != NULL)

net/netfilter/ipvs/ip_vs_proto_ah_esp.c

@@ -41,28 +41,30 @@ struct isakmp_hdr {
 #define PORT_ISAKMP	500
 
 static void
-ah_esp_conn_fill_param_proto(int af, const struct ip_vs_iphdr *iph,
-			     int inverse, struct ip_vs_conn_param *p)
+ah_esp_conn_fill_param_proto(struct net *net, int af,
+			     const struct ip_vs_iphdr *iph, int inverse,
+			     struct ip_vs_conn_param *p)
 {
 	if (likely(!inverse))
-		ip_vs_conn_fill_param(af, IPPROTO_UDP,
+		ip_vs_conn_fill_param(net, af, IPPROTO_UDP,
 				      &iph->saddr, htons(PORT_ISAKMP),
 				      &iph->daddr, htons(PORT_ISAKMP), p);
 	else
-		ip_vs_conn_fill_param(af, IPPROTO_UDP,
+		ip_vs_conn_fill_param(net, af, IPPROTO_UDP,
 				      &iph->daddr, htons(PORT_ISAKMP),
 				      &iph->saddr, htons(PORT_ISAKMP), p);
 }
 
 static struct ip_vs_conn *
-ah_esp_conn_in_get(int af, const struct sk_buff *skb, struct ip_vs_protocol *pp,
+ah_esp_conn_in_get(int af, const struct sk_buff *skb,
 		   const struct ip_vs_iphdr *iph, unsigned int proto_off,
 		   int inverse)
 {
 	struct ip_vs_conn *cp;
 	struct ip_vs_conn_param p;
+	struct net *net = skb_net(skb);
 
-	ah_esp_conn_fill_param_proto(af, iph, inverse, &p);
+	ah_esp_conn_fill_param_proto(net, af, iph, inverse, &p);
 	cp = ip_vs_conn_in_get(&p);
 	if (!cp) {
 		/*
@@ -72,7 +74,7 @@ ah_esp_conn_in_get(int af, const struct sk_buff *skb, struct ip_vs_protocol *pp,
 		IP_VS_DBG_BUF(12, "Unknown ISAKMP entry for outin packet "
 			      "%s%s %s->%s\n",
 			      inverse ? "ICMP+" : "",
-			      pp->name,
+			      ip_vs_proto_get(iph->protocol)->name,
 			      IP_VS_DBG_ADDR(af, &iph->saddr),
 			      IP_VS_DBG_ADDR(af, &iph->daddr));
 	}
@@ -83,21 +85,21 @@ ah_esp_conn_in_get(int af, const struct sk_buff *skb, struct ip_vs_protocol *pp,
 
 static struct ip_vs_conn *
 ah_esp_conn_out_get(int af, const struct sk_buff *skb,
-		    struct ip_vs_protocol *pp,
 		    const struct ip_vs_iphdr *iph,
 		    unsigned int proto_off,
 		    int inverse)
 {
 	struct ip_vs_conn *cp;
 	struct ip_vs_conn_param p;
+	struct net *net = skb_net(skb);
 
-	ah_esp_conn_fill_param_proto(af, iph, inverse, &p);
+	ah_esp_conn_fill_param_proto(net, af, iph, inverse, &p);
 	cp = ip_vs_conn_out_get(&p);
 	if (!cp) {
 		IP_VS_DBG_BUF(12, "Unknown ISAKMP entry for inout packet "
 			      "%s%s %s->%s\n",
 			      inverse ? "ICMP+" : "",
-			      pp->name,
+			      ip_vs_proto_get(iph->protocol)->name,
 			      IP_VS_DBG_ADDR(af, &iph->saddr),
 			      IP_VS_DBG_ADDR(af, &iph->daddr));
 	}
@@ -107,7 +109,7 @@ ah_esp_conn_out_get(int af, const struct sk_buff *skb,
 
 
 static int
-ah_esp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_protocol *pp,
+ah_esp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd,
 		     int *verdict, struct ip_vs_conn **cpp)
 {
 	/*
@@ -117,26 +119,14 @@ ah_esp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_protocol *pp,
 	return 0;
 }
 
-static void ah_esp_init(struct ip_vs_protocol *pp)
-{
-	/* nothing to do now */
-}
-
-
-static void ah_esp_exit(struct ip_vs_protocol *pp)
-{
-	/* nothing to do now */
-}
-
-
 #ifdef CONFIG_IP_VS_PROTO_AH
 struct ip_vs_protocol ip_vs_protocol_ah = {
 	.name =			"AH",
 	.protocol =		IPPROTO_AH,
 	.num_states =		1,
 	.dont_defrag =		1,
-	.init =			ah_esp_init,
-	.exit =			ah_esp_exit,
+	.init =			NULL,
+	.exit =			NULL,
 	.conn_schedule =	ah_esp_conn_schedule,
 	.conn_in_get =		ah_esp_conn_in_get,
 	.conn_out_get =		ah_esp_conn_out_get,
@@ -149,7 +139,6 @@ struct ip_vs_protocol ip_vs_protocol_ah = {
 	.app_conn_bind =	NULL,
 	.debug_packet =		ip_vs_tcpudp_debug_packet,
 	.timeout_change =	NULL,		/* ISAKMP */
-	.set_state_timeout =	NULL,
 };
 #endif
 
@@ -159,8 +148,8 @@ struct ip_vs_protocol ip_vs_protocol_esp = {
 	.protocol =		IPPROTO_ESP,
 	.num_states =		1,
 	.dont_defrag =		1,
-	.init =			ah_esp_init,
-	.exit =			ah_esp_exit,
+	.init =			NULL,
+	.exit =			NULL,
 	.conn_schedule =	ah_esp_conn_schedule,
 	.conn_in_get =		ah_esp_conn_in_get,
 	.conn_out_get =		ah_esp_conn_out_get,

net/netfilter/ipvs/ip_vs_proto_sctp.c

@@ -9,9 +9,10 @@
 #include <net/ip_vs.h>
 
 static int
-sctp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_protocol *pp,
+sctp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd,
 		   int *verdict, struct ip_vs_conn **cpp)
 {
+	struct net *net;
 	struct ip_vs_service *svc;
 	sctp_chunkhdr_t _schunkh, *sch;
 	sctp_sctphdr_t *sh, _sctph;
@@ -27,13 +28,13 @@ sctp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_protocol *pp,
 				 sizeof(_schunkh), &_schunkh);
 	if (sch == NULL)
 		return 0;
-
+	net = skb_net(skb);
 	if ((sch->type == SCTP_CID_INIT) &&
-	    (svc = ip_vs_service_get(af, skb->mark, iph.protocol,
+	    (svc = ip_vs_service_get(net, af, skb->mark, iph.protocol,
 				     &iph.daddr, sh->dest))) {
 		int ignored;
 
-		if (ip_vs_todrop()) {
+		if (ip_vs_todrop(net_ipvs(net))) {
 			/*
 			 * It seems that we are very loaded.
 			 * We have to drop this packet :(
@@ -46,14 +47,19 @@ sctp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_protocol *pp,
 		 * Let the virtual server select a real server for the
 		 * incoming connection, and create a connection entry.
 		 */
-		*cpp = ip_vs_schedule(svc, skb, pp, &ignored);
-		if (!*cpp && !ignored) {
-			*verdict = ip_vs_leave(svc, skb, pp);
+		*cpp = ip_vs_schedule(svc, skb, pd, &ignored);
+		if (!*cpp && ignored <= 0) {
+			if (!ignored)
+				*verdict = ip_vs_leave(svc, skb, pd);
+			else {
+				ip_vs_service_put(svc);
+				*verdict = NF_DROP;
+			}
 			return 0;
 		}
 		ip_vs_service_put(svc);
 	}
-
+	/* NF_ACCEPT */
 	return 1;
 }
 
@@ -856,7 +862,7 @@ static struct ipvs_sctp_nextstate
 /*
  *      Timeout table[state]
  */
-static int sctp_timeouts[IP_VS_SCTP_S_LAST + 1] = {
+static const int sctp_timeouts[IP_VS_SCTP_S_LAST + 1] = {
 	[IP_VS_SCTP_S_NONE]         =     2 * HZ,
 	[IP_VS_SCTP_S_INIT_CLI]     =     1 * 60 * HZ,
 	[IP_VS_SCTP_S_INIT_SER]     =     1 * 60 * HZ,
@@ -900,20 +906,8 @@ static const char *sctp_state_name(int state)
 	return "?";
 }
 
-static void sctp_timeout_change(struct ip_vs_protocol *pp, int flags)
-{
-}
-
-static int
-sctp_set_state_timeout(struct ip_vs_protocol *pp, char *sname, int to)
-{
-
-return ip_vs_set_state_timeout(pp->timeout_table, IP_VS_SCTP_S_LAST,
-				sctp_state_name_table, sname, to);
-}
-
 static inline int
-set_sctp_state(struct ip_vs_protocol *pp, struct ip_vs_conn *cp,
+set_sctp_state(struct ip_vs_proto_data *pd, struct ip_vs_conn *cp,
 		int direction, const struct sk_buff *skb)
 {
 	sctp_chunkhdr_t _sctpch, *sch;
@@ -971,7 +965,7 @@ set_sctp_state(struct ip_vs_protocol *pp, struct ip_vs_conn *cp,
 
 		IP_VS_DBG_BUF(8, "%s %s  %s:%d->"
 				"%s:%d state: %s->%s conn->refcnt:%d\n",
-				pp->name,
+				pd->pp->name,
 				((direction == IP_VS_DIR_OUTPUT) ?
 				 "output " : "input "),
 				IP_VS_DBG_ADDR(cp->af, &cp->daddr),
@@ -995,75 +989,73 @@ set_sctp_state(struct ip_vs_protocol *pp, struct ip_vs_conn *cp,
 			}
 		}
 	}
+	if (likely(pd))
+		cp->timeout = pd->timeout_table[cp->state = next_state];
+	else	/* What to do ? */
+		cp->timeout = sctp_timeouts[cp->state = next_state];
 
-	 cp->timeout = pp->timeout_table[cp->state = next_state];
-
-	 return 1;
+	return 1;
 }
 
 static int
 sctp_state_transition(struct ip_vs_conn *cp, int direction,
-		const struct sk_buff *skb, struct ip_vs_protocol *pp)
+		const struct sk_buff *skb, struct ip_vs_proto_data *pd)
 {
 	int ret = 0;
 
 	spin_lock(&cp->lock);
-	ret = set_sctp_state(pp, cp, direction, skb);
+	ret = set_sctp_state(pd, cp, direction, skb);
 	spin_unlock(&cp->lock);
 
 	return ret;
 }
 
-/*
- *      Hash table for SCTP application incarnations
- */
-#define SCTP_APP_TAB_BITS        4
-#define SCTP_APP_TAB_SIZE        (1 << SCTP_APP_TAB_BITS)
-#define SCTP_APP_TAB_MASK        (SCTP_APP_TAB_SIZE - 1)
-
-static struct list_head sctp_apps[SCTP_APP_TAB_SIZE];
-static DEFINE_SPINLOCK(sctp_app_lock);
-
 static inline __u16 sctp_app_hashkey(__be16 port)
 {
 	return (((__force u16)port >> SCTP_APP_TAB_BITS) ^ (__force u16)port)
 		& SCTP_APP_TAB_MASK;
 }
 
-static int sctp_register_app(struct ip_vs_app *inc)
+static int sctp_register_app(struct net *net, struct ip_vs_app *inc)
 {
 	struct ip_vs_app *i;
 	__u16 hash;
 	__be16 port = inc->port;
 	int ret = 0;
+	struct netns_ipvs *ipvs = net_ipvs(net);
+	struct ip_vs_proto_data *pd = ip_vs_proto_data_get(net, IPPROTO_SCTP);
 
 	hash = sctp_app_hashkey(port);
 
-	spin_lock_bh(&sctp_app_lock);
-	list_for_each_entry(i, &sctp_apps[hash], p_list) {
+	spin_lock_bh(&ipvs->sctp_app_lock);
+	list_for_each_entry(i, &ipvs->sctp_apps[hash], p_list) {
 		if (i->port == port) {
 			ret = -EEXIST;
 			goto out;
 		}
 	}
-	list_add(&inc->p_list, &sctp_apps[hash]);
-	atomic_inc(&ip_vs_protocol_sctp.appcnt);
+	list_add(&inc->p_list, &ipvs->sctp_apps[hash]);
+	atomic_inc(&pd->appcnt);
 out:
-	spin_unlock_bh(&sctp_app_lock);
+	spin_unlock_bh(&ipvs->sctp_app_lock);
 
 	return ret;
 }
 
-static void sctp_unregister_app(struct ip_vs_app *inc)
+static void sctp_unregister_app(struct net *net, struct ip_vs_app *inc)
 {
-	spin_lock_bh(&sctp_app_lock);
-	atomic_dec(&ip_vs_protocol_sctp.appcnt);
+	struct netns_ipvs *ipvs = net_ipvs(net);
+	struct ip_vs_proto_data *pd = ip_vs_proto_data_get(net, IPPROTO_SCTP);
+
+	spin_lock_bh(&ipvs->sctp_app_lock);
+	atomic_dec(&pd->appcnt);
 	list_del(&inc->p_list);
-	spin_unlock_bh(&sctp_app_lock);
+	spin_unlock_bh(&ipvs->sctp_app_lock);
 }
 
 static int sctp_app_conn_bind(struct ip_vs_conn *cp)
 {
+	struct netns_ipvs *ipvs = net_ipvs(ip_vs_conn_net(cp));
 	int hash;
 	struct ip_vs_app *inc;
 	int result = 0;
@@ -1074,12 +1066,12 @@ static int sctp_app_conn_bind(struct ip_vs_conn *cp)
 	/* Lookup application incarnations and bind the right one */
 	hash = sctp_app_hashkey(cp->vport);
 
-	spin_lock(&sctp_app_lock);
-	list_for_each_entry(inc, &sctp_apps[hash], p_list) {
+	spin_lock(&ipvs->sctp_app_lock);
+	list_for_each_entry(inc, &ipvs->sctp_apps[hash], p_list) {
 		if (inc->port == cp->vport) {
 			if (unlikely(!ip_vs_app_inc_get(inc)))
 				break;
-			spin_unlock(&sctp_app_lock);
+			spin_unlock(&ipvs->sctp_app_lock);
 
 			IP_VS_DBG_BUF(9, "%s: Binding conn %s:%u->"
 					"%s:%u to app %s on port %u\n",
@@ -1095,43 +1087,50 @@ static int sctp_app_conn_bind(struct ip_vs_conn *cp)
 			goto out;
 		}
 	}
-	spin_unlock(&sctp_app_lock);
+	spin_unlock(&ipvs->sctp_app_lock);
 out:
 	return result;
 }
 
-static void ip_vs_sctp_init(struct ip_vs_protocol *pp)
+/* ---------------------------------------------
+ *   timeouts is netns related now.
+ * ---------------------------------------------
+ */
+static void __ip_vs_sctp_init(struct net *net, struct ip_vs_proto_data *pd)
 {
-	IP_VS_INIT_HASH_TABLE(sctp_apps);
-	pp->timeout_table = sctp_timeouts;
-}
+	struct netns_ipvs *ipvs = net_ipvs(net);
 
+	ip_vs_init_hash_table(ipvs->sctp_apps, SCTP_APP_TAB_SIZE);
+	spin_lock_init(&ipvs->tcp_app_lock);
+	pd->timeout_table = ip_vs_create_timeout_table((int *)sctp_timeouts,
+							sizeof(sctp_timeouts));
+}
 
-static void ip_vs_sctp_exit(struct ip_vs_protocol *pp)
+static void __ip_vs_sctp_exit(struct net *net, struct ip_vs_proto_data *pd)
 {
-
+	kfree(pd->timeout_table);
 }
 
 struct ip_vs_protocol ip_vs_protocol_sctp = {
-	.name = "SCTP",
-	.protocol = IPPROTO_SCTP,
-	.num_states = IP_VS_SCTP_S_LAST,
-	.dont_defrag = 0,
-	.appcnt = ATOMIC_INIT(0),
-	.init = ip_vs_sctp_init,
-	.exit = ip_vs_sctp_exit,
-	.register_app = sctp_register_app,
+	.name		= "SCTP",
+	.protocol	= IPPROTO_SCTP,
+	.num_states	= IP_VS_SCTP_S_LAST,
+	.dont_defrag	= 0,
+	.init		= NULL,
+	.exit		= NULL,
+	.init_netns	= __ip_vs_sctp_init,
+	.exit_netns	= __ip_vs_sctp_exit,
+	.register_app	= sctp_register_app,
 	.unregister_app = sctp_unregister_app,
-	.conn_schedule = sctp_conn_schedule,
-	.conn_in_get = ip_vs_conn_in_get_proto,
-	.conn_out_get = ip_vs_conn_out_get_proto,
-	.snat_handler = sctp_snat_handler,
-	.dnat_handler = sctp_dnat_handler,
-	.csum_check = sctp_csum_check,
-	.state_name = sctp_state_name,
+	.conn_schedule	= sctp_conn_schedule,
+	.conn_in_get	= ip_vs_conn_in_get_proto,
+	.conn_out_get	= ip_vs_conn_out_get_proto,
+	.snat_handler	= sctp_snat_handler,
+	.dnat_handler	= sctp_dnat_handler,
+	.csum_check	= sctp_csum_check,
+	.state_name	= sctp_state_name,
 	.state_transition = sctp_state_transition,
-	.app_conn_bind = sctp_app_conn_bind,
-	.debug_packet = ip_vs_tcpudp_debug_packet,
-	.timeout_change = sctp_timeout_change,
-	.set_state_timeout = sctp_set_state_timeout,
+	.app_conn_bind	= sctp_app_conn_bind,
+	.debug_packet	= ip_vs_tcpudp_debug_packet,
+	.timeout_change	= NULL,
 };