ipvs: convert connection locking

[mirror_ubuntu-zesty-kernel.git] / include / net / ip_vs.h

diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index 68c69d54d39281ee033d765a1b9b66567c55d06f..5700b07b5186e7c4b7dc3bda391681c4d42793b5 100644 (file)
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -459,7 +459,7 @@ struct ip_vs_estimator {
 struct ip_vs_stats {
        struct ip_vs_stats_user ustats;         /* statistics */
        struct ip_vs_estimator  est;            /* estimator */
-       struct ip_vs_cpu_stats  *cpustats;      /* per cpu counters */
+       struct ip_vs_cpu_stats __percpu *cpustats;      /* per cpu counters */
        spinlock_t              lock;           /* spin lock */
        struct ip_vs_stats_user ustats0;        /* reset values */
 };
@@ -620,6 +620,8 @@ struct ip_vs_conn {
        const struct ip_vs_pe   *pe;
        char                    *pe_data;
        __u8                    pe_data_len;
+
+       struct rcu_head         rcu_head;
 };
 
 /*
@@ -724,6 +726,13 @@ struct ip_vs_service {
        struct ip_vs_pe         *pe;
 };
 
+/* Information for cached dst */
+struct ip_vs_dest_dst {
+       struct dst_entry        *dst_cache;     /* destination cache entry */
+       u32                     dst_cookie;
+       union nf_inet_addr      dst_saddr;
+       struct rcu_head         rcu_head;
+};
 
 /*
  *     The real server destination forwarding entry
@@ -731,7 +740,7 @@ struct ip_vs_service {
  */
 struct ip_vs_dest {
        struct list_head        n_list;   /* for the dests in the service */
-       struct list_head        d_list;   /* for table with all the dests */
+       struct hlist_node       d_list;   /* for table with all the dests */
 
        u16                     af;             /* address family */
        __be16                  port;           /* port number of the server */
@@ -752,10 +761,7 @@ struct ip_vs_dest {
 
        /* for destination cache */
        spinlock_t              dst_lock;       /* lock of dst_cache */
-       struct dst_entry        *dst_cache;     /* destination cache entry */
-       u32                     dst_rtos;       /* RT_TOS(tos) for dst */
-       u32                     dst_cookie;
-       union nf_inet_addr      dst_saddr;
+       struct ip_vs_dest_dst __rcu *dest_dst;  /* cached dst info */
 
        /* for virtual service */
        struct ip_vs_service    *svc;           /* service it belongs to */
@@ -763,6 +769,9 @@ struct ip_vs_dest {
        __be16                  vport;          /* virtual port number */
        union nf_inet_addr      vaddr;          /* virtual IP address */
        __u32                   vfwmark;        /* firewall mark of service */
+
+       struct rcu_head         rcu_head;
+       unsigned int            in_rs_table:1;  /* we are in rs_table */
 };
 
 
@@ -819,6 +828,7 @@ struct ip_vs_app {
        struct ip_vs_app        *app;           /* its real application */
        __be16                  port;           /* port number in net order */
        atomic_t                usecnt;         /* usage counter */
+       struct rcu_head         rcu_head;
 
        /*
         * output hook: Process packet in inout direction, diff set for TCP.
@@ -892,7 +902,7 @@ struct netns_ipvs {
        #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];
+       struct hlist_head       rs_table[IP_VS_RTAB_SIZE];
        /* ip_vs_app */
        struct list_head        app_list;
        /* ip_vs_proto */
@@ -904,7 +914,6 @@ struct netns_ipvs {
        #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
@@ -912,7 +921,6 @@ struct netns_ipvs {
        #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
@@ -921,7 +929,6 @@ struct netns_ipvs {
        #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 */
@@ -931,7 +938,6 @@ struct netns_ipvs {
 
        int                     num_services;    /* no of virtual services */
 
-       rwlock_t                rs_lock;         /* real services table */
        /* Trash for destinations */
        struct list_head        dest_trash;
        /* Service counters */
@@ -976,6 +982,7 @@ struct netns_ipvs {
        int                     sysctl_sync_retries;
        int                     sysctl_nat_icmp_send;
        int                     sysctl_pmtu_disc;
+       int                     sysctl_backup_only;
 
        /* ip_vs_lblc */
        int                     sysctl_lblc_expiration;
@@ -1067,6 +1074,12 @@ static inline int sysctl_pmtu_disc(struct netns_ipvs *ipvs)
        return ipvs->sysctl_pmtu_disc;
 }
 
+static inline int sysctl_backup_only(struct netns_ipvs *ipvs)
+{
+       return ipvs->sync_state & IP_VS_STATE_BACKUP &&
+              ipvs->sysctl_backup_only;
+}
+
 #else
 
 static inline int sysctl_sync_threshold(struct netns_ipvs *ipvs)
@@ -1114,6 +1127,11 @@ static inline int sysctl_pmtu_disc(struct netns_ipvs *ipvs)
        return 1;
 }
 
+static inline int sysctl_backup_only(struct netns_ipvs *ipvs)
+{
+       return 0;
+}
+
 #endif
 
 /*
@@ -1169,9 +1187,19 @@ struct ip_vs_conn * ip_vs_conn_out_get_proto(int af, const struct sk_buff *skb,
                                             const struct ip_vs_iphdr *iph,
                                             int inverse);
 
+/* Get reference to gain full access to conn.
+ * By default, RCU read-side critical sections have access only to
+ * conn fields and its PE data, see ip_vs_conn_rcu_free() for reference.
+ */
+static inline bool __ip_vs_conn_get(struct ip_vs_conn *cp)
+{
+       return atomic_inc_not_zero(&cp->refcnt);
+}
+
 /* put back the conn without restarting its timer */
 static inline void __ip_vs_conn_put(struct ip_vs_conn *cp)
 {
+       smp_mb__before_atomic_dec();
        atomic_dec(&cp->refcnt);
 }
 extern void ip_vs_conn_put(struct ip_vs_conn *cp);
@@ -1362,9 +1390,9 @@ static inline void ip_vs_service_put(struct ip_vs_service *svc)
        atomic_dec(&svc->usecnt);
 }
 
-extern struct ip_vs_dest *
-ip_vs_lookup_real_service(struct net *net, int af, __u16 protocol,
-                         const union nf_inet_addr *daddr, __be16 dport);
+extern bool
+ip_vs_has_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);
 extern void ip_vs_use_count_dec(void);
@@ -1416,7 +1444,7 @@ extern int ip_vs_dr_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
 extern int ip_vs_icmp_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
                           struct ip_vs_protocol *pp, int offset,
                           unsigned int hooknum, struct ip_vs_iphdr *iph);
-extern void ip_vs_dst_reset(struct ip_vs_dest *dest);
+extern void ip_vs_dest_dst_rcu_free(struct rcu_head *head);
 
 #ifdef CONFIG_IP_VS_IPV6
 extern int ip_vs_bypass_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,