ipvs: convert services to rcu

This is the final step in RCU conversion.

Things that are removed:

- svc->usecnt: now svc is accessed under RCU read lock
- svc->inc: and some unused code
- ip_vs_bind_pe and ip_vs_unbind_pe: no ability to replace PE
- __ip_vs_svc_lock: replaced with RCU
- IP_VS_WAIT_WHILE: now readers lookup svcs and dests under
	RCU and work in parallel with configuration

Other changes:

- before now, a RCU read-side critical section included the
calling of the schedule method, now it is extended to include
service lookup
- ip_vs_svc_table and ip_vs_svc_fwm_table are now using hlist
- svc->pe and svc->scheduler remain to the end (of grace period),
	the schedulers are prepared for such RCU readers
	even after done_service is called but they need
	to use synchronize_rcu because last ip_vs_scheduler_put
	can happen while RCU read-side critical sections
	use an outdated svc->scheduler pointer
- as planned, update_service is removed
- empty services can be freed immediately after grace period.
	If dests were present, the services are freed from
	the dest trash code
Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>

include/net/ip_vs.h

@@ -359,8 +359,6 @@ static inline const char *ip_vs_dbg_addr(int af, char *buf, size_t buf_len,
 #define LeaveFunction(level)   do {} while (0)
 #endif
 
-#define	IP_VS_WAIT_WHILE(expr)	while (expr) { cpu_relax(); }
-
 
 /*
  *      The port number of FTP service (in network order).
@@ -712,10 +710,9 @@ struct ip_vs_dest_user_kern {
  *	and the forwarding entries
  */
 struct ip_vs_service {
-	struct list_head	s_list;   /* for normal service table */
-	struct list_head	f_list;   /* for fwmark-based service table */
+	struct hlist_node	s_list;   /* for normal service table */
+	struct hlist_node	f_list;   /* for fwmark-based service table */
 	atomic_t		refcnt;   /* reference counter */
-	atomic_t		usecnt;   /* use counter */
 
 	u16			af;       /* address family */
 	__u16			protocol; /* which protocol (TCP/UDP) */
@@ -730,15 +727,16 @@ struct ip_vs_service {
 	struct list_head	destinations;  /* real server d-linked list */
 	__u32			num_dests;     /* number of servers */
 	struct ip_vs_stats      stats;         /* statistics for the service */
-	struct ip_vs_app	*inc;	  /* bind conns to this app inc */
 
 	/* for scheduling */
-	struct ip_vs_scheduler	*scheduler;    /* bound scheduler object */
+	struct ip_vs_scheduler __rcu *scheduler; /* bound scheduler object */
 	spinlock_t		sched_lock;    /* lock sched_data */
 	void			*sched_data;   /* scheduler application data */
 
 	/* alternate persistence engine */
-	struct ip_vs_pe		*pe;
+	struct ip_vs_pe __rcu	*pe;
+
+	struct rcu_head		rcu_head;
 };
 
 /* Information for cached dst */
@@ -807,8 +805,6 @@ struct ip_vs_scheduler {
 	int (*init_service)(struct ip_vs_service *svc);
 	/* scheduling service finish */
 	void (*done_service)(struct ip_vs_service *svc);
-	/* scheduler updating service */
-	int (*update_service)(struct ip_vs_service *svc);
 	/* dest is linked */
 	int (*add_dest)(struct ip_vs_service *svc, struct ip_vs_dest *dest);
 	/* dest is unlinked */
@@ -1344,8 +1340,6 @@ extern void ip_vs_app_inc_put(struct ip_vs_app *inc);
 extern int ip_vs_app_pkt_out(struct ip_vs_conn *, struct sk_buff *skb);
 extern int ip_vs_app_pkt_in(struct ip_vs_conn *, struct sk_buff *skb);
 
-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);
 struct ip_vs_pe *ip_vs_pe_getbyname(const char *name);
@@ -1392,7 +1386,8 @@ extern int register_ip_vs_scheduler(struct ip_vs_scheduler *scheduler);
 extern int unregister_ip_vs_scheduler(struct ip_vs_scheduler *scheduler);
 extern int ip_vs_bind_scheduler(struct ip_vs_service *svc,
 				struct ip_vs_scheduler *scheduler);
-extern void ip_vs_unbind_scheduler(struct ip_vs_service *svc);
+extern void ip_vs_unbind_scheduler(struct ip_vs_service *svc,
+				   struct ip_vs_scheduler *sched);
 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 *
@@ -1412,14 +1407,9 @@ extern struct ip_vs_stats ip_vs_stats;
 extern int sysctl_ip_vs_sync_ver;
 
 extern struct ip_vs_service *
-ip_vs_service_get(struct net *net, int af, __u32 fwmark, __u16 protocol,
+ip_vs_service_find(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)
-{
-	atomic_dec(&svc->usecnt);
-}
-
 extern bool
 ip_vs_has_real_service(struct net *net, int af, __u16 protocol,
 		       const union nf_inet_addr *daddr, __be16 dport);

net/netfilter/ipvs/ip_vs_core.c

@@ -203,7 +203,7 @@ ip_vs_conn_fill_param_persist(const struct ip_vs_service *svc,
 {
 	ip_vs_conn_fill_param(svc->net, svc->af, protocol, caddr, cport, vaddr,
 			      vport, p);
-	p->pe = svc->pe;
+	p->pe = rcu_dereference(svc->pe);
 	if (p->pe && p->pe->fill_param)
 		return p->pe->fill_param(p, skb);
 
@@ -296,15 +296,16 @@ ip_vs_sched_persist(struct ip_vs_service *svc,
 	/* Check if a template already exists */
 	ct = ip_vs_ct_in_get(&param);
 	if (!ct || !ip_vs_check_template(ct)) {
+		struct ip_vs_scheduler *sched;
+
 		/*
 		 * No template found or the dest of the connection
 		 * template is not available.
 		 * return *ignored=0 i.e. ICMP and NF_DROP
 		 */
-		rcu_read_lock();
-		dest = svc->scheduler->schedule(svc, skb);
+		sched = rcu_dereference(svc->scheduler);
+		dest = sched->schedule(svc, skb);
 		if (!dest) {
-			rcu_read_unlock();
 			IP_VS_DBG(1, "p-schedule: no dest found.\n");
 			kfree(param.pe_data);
 			*ignored = 0;
@@ -320,7 +321,6 @@ ip_vs_sched_persist(struct ip_vs_service *svc,
 		 * when the template expires */
 		ct = ip_vs_conn_new(&param, &dest->addr, dport,
 				    IP_VS_CONN_F_TEMPLATE, dest, skb->mark);
-		rcu_read_unlock();
 		if (ct == NULL) {
 			kfree(param.pe_data);
 			*ignored = -1;
@@ -394,6 +394,7 @@ ip_vs_schedule(struct ip_vs_service *svc, struct sk_buff *skb,
 {
 	struct ip_vs_protocol *pp = pd->pp;
 	struct ip_vs_conn *cp = NULL;
+	struct ip_vs_scheduler *sched;
 	struct ip_vs_dest *dest;
 	__be16 _ports[2], *pptr;
 	unsigned int flags;
@@ -449,10 +450,9 @@ ip_vs_schedule(struct ip_vs_service *svc, struct sk_buff *skb,
 		return NULL;
 	}
 
-	rcu_read_lock();
-	dest = svc->scheduler->schedule(svc, skb);
+	sched = rcu_dereference(svc->scheduler);
+	dest = sched->schedule(svc, skb);
 	if (dest == NULL) {
-		rcu_read_unlock();
 		IP_VS_DBG(1, "Schedule: no dest found.\n");
 		return NULL;
 	}
@@ -473,7 +473,6 @@ ip_vs_schedule(struct ip_vs_service *svc, struct sk_buff *skb,
 		cp = ip_vs_conn_new(&p, &dest->addr,
 				    dest->port ? dest->port : pptr[1],
 				    flags, dest, skb->mark);
-		rcu_read_unlock();
 		if (!cp) {
 			*ignored = -1;
 			return NULL;
@@ -510,7 +509,6 @@ int ip_vs_leave(struct ip_vs_service *svc, struct sk_buff *skb,
 
 	pptr = frag_safe_skb_hp(skb, iph->len, sizeof(_ports), _ports, iph);
 	if (pptr == NULL) {
-		ip_vs_service_put(svc);
 		return NF_DROP;
 	}
 
@@ -536,8 +534,6 @@ int ip_vs_leave(struct ip_vs_service *svc, struct sk_buff *skb,
 				      IP_VS_CONN_F_ONE_PACKET : 0;
 		union nf_inet_addr daddr =  { .all = { 0, 0, 0, 0 } };
 
-		ip_vs_service_put(svc);
-
 		/* create a new connection entry */
 		IP_VS_DBG(6, "%s(): create a cache_bypass entry\n", __func__);
 		{
@@ -574,12 +570,8 @@ int ip_vs_leave(struct ip_vs_service *svc, struct sk_buff *skb,
 	 * listed in the ipvs table), pass the packets, because it is
 	 * not ipvs job to decide to drop the packets.
 	 */
-	if ((svc->port == FTPPORT) && (pptr[1] != FTPPORT)) {
-		ip_vs_service_put(svc);
+	if ((svc->port == FTPPORT) && (pptr[1] != FTPPORT))
 		return NF_ACCEPT;
-	}
-
-	ip_vs_service_put(svc);
 
 	/*
 	 * Notify the client that the destination is unreachable, and

net/netfilter/ipvs/ip_vs_dh.c

@@ -269,6 +269,7 @@ static int __init ip_vs_dh_init(void)
 static void __exit ip_vs_dh_cleanup(void)
 {
 	unregister_ip_vs_scheduler(&ip_vs_dh_scheduler);
+	synchronize_rcu();
 }
 
 

net/netfilter/ipvs/ip_vs_lblc.c

@@ -633,6 +633,7 @@ static void __exit ip_vs_lblc_cleanup(void)
 {
 	unregister_ip_vs_scheduler(&ip_vs_lblc_scheduler);
 	unregister_pernet_subsys(&ip_vs_lblc_ops);
+	synchronize_rcu();
 }
 
 

net/netfilter/ipvs/ip_vs_lblcr.c

@@ -821,6 +821,7 @@ static void __exit ip_vs_lblcr_cleanup(void)
 {
 	unregister_ip_vs_scheduler(&ip_vs_lblcr_scheduler);
 	unregister_pernet_subsys(&ip_vs_lblcr_ops);
+	synchronize_rcu();
 }
 
 

net/netfilter/ipvs/ip_vs_lc.c

@@ -84,6 +84,7 @@ static int __init ip_vs_lc_init(void)
 static void __exit ip_vs_lc_cleanup(void)
 {
 	unregister_ip_vs_scheduler(&ip_vs_lc_scheduler);
+	synchronize_rcu();
 }
 
 module_init(ip_vs_lc_init);

net/netfilter/ipvs/ip_vs_nq.c

@@ -133,6 +133,7 @@ static int __init ip_vs_nq_init(void)
 static void __exit ip_vs_nq_cleanup(void)
 {
 	unregister_ip_vs_scheduler(&ip_vs_nq_scheduler);
+	synchronize_rcu();
 }
 
 module_init(ip_vs_nq_init);

net/netfilter/ipvs/ip_vs_pe.c

@@ -16,18 +16,6 @@ static LIST_HEAD(ip_vs_pe);
 /* semaphore for IPVS PEs. */
 static DEFINE_MUTEX(ip_vs_pe_mutex);
 
-/* Bind a service with a pe */
-void ip_vs_bind_pe(struct ip_vs_service *svc, struct ip_vs_pe *pe)
-{
-	svc->pe = pe;
-}
-
-/* Unbind a service from its pe */
-void ip_vs_unbind_pe(struct ip_vs_service *svc)
-{
-	svc->pe = NULL;
-}
-
 /* Get pe in the pe list by name */
 struct ip_vs_pe *__ip_vs_pe_getbyname(const char *pe_name)
 {

net/netfilter/ipvs/ip_vs_proto_sctp.c

@@ -27,8 +27,9 @@ sctp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd,
 	if (sch == NULL)
 		return 0;
 	net = skb_net(skb);
+	rcu_read_lock();
 	if ((sch->type == SCTP_CID_INIT) &&
-	    (svc = ip_vs_service_get(net, af, skb->mark, iph->protocol,
+	    (svc = ip_vs_service_find(net, af, skb->mark, iph->protocol,
 				      &iph->daddr, sh->dest))) {
 		int ignored;
 
@@ -37,7 +38,7 @@ sctp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd,
 			 * It seems that we are very loaded.
 			 * We have to drop this packet :(
 			 */
-			ip_vs_service_put(svc);
+			rcu_read_unlock();
 			*verdict = NF_DROP;
 			return 0;
 		}
@@ -49,14 +50,13 @@ sctp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd,
 		if (!*cpp && ignored <= 0) {
 			if (!ignored)
 				*verdict = ip_vs_leave(svc, skb, pd, iph);
-			else {
-				ip_vs_service_put(svc);
+			else
 				*verdict = NF_DROP;
-			}
+			rcu_read_unlock();
 			return 0;
 		}
-		ip_vs_service_put(svc);
 	}
+	rcu_read_unlock();
 	/* NF_ACCEPT */
 	return 1;
 }

net/netfilter/ipvs/ip_vs_proto_tcp.c

@@ -47,8 +47,9 @@ tcp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd,
 	}
 	net = skb_net(skb);
 	/* No !th->ack check to allow scheduling on SYN+ACK for Active FTP */
+	rcu_read_lock();
 	if (th->syn &&
-	    (svc = ip_vs_service_get(net, af, skb->mark, iph->protocol,
+	    (svc = ip_vs_service_find(net, af, skb->mark, iph->protocol,
 				      &iph->daddr, th->dest))) {
 		int ignored;
 
@@ -57,7 +58,7 @@ tcp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd,
 			 * It seems that we are very loaded.
 			 * We have to drop this packet :(
 			 */
-			ip_vs_service_put(svc);
+			rcu_read_unlock();
 			*verdict = NF_DROP;
 			return 0;
 		}
@@ -70,14 +71,13 @@ tcp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd,
 		if (!*cpp && ignored <= 0) {
 			if (!ignored)
 				*verdict = ip_vs_leave(svc, skb, pd, iph);
-			else {
-				ip_vs_service_put(svc);
+			else
 				*verdict = NF_DROP;
-			}
+			rcu_read_unlock();
 			return 0;
 		}
-		ip_vs_service_put(svc);
 	}
+	rcu_read_unlock();
 	/* NF_ACCEPT */
 	return 1;
 }

net/netfilter/ipvs/ip_vs_proto_udp.c

@@ -44,7 +44,8 @@ udp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd,
 		return 0;
 	}
 	net = skb_net(skb);
-	svc = ip_vs_service_get(net, af, skb->mark, iph->protocol,
+	rcu_read_lock();
+	svc = ip_vs_service_find(net, af, skb->mark, iph->protocol,
 				 &iph->daddr, uh->dest);
 	if (svc) {
 		int ignored;
@@ -54,7 +55,7 @@ udp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd,
 			 * It seems that we are very loaded.
 			 * We have to drop this packet :(
 			 */
-			ip_vs_service_put(svc);
+			rcu_read_unlock();
 			*verdict = NF_DROP;
 			return 0;
 		}
@@ -67,14 +68,13 @@ udp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd,
 		if (!*cpp && ignored <= 0) {
 			if (!ignored)
 				*verdict = ip_vs_leave(svc, skb, pd, iph);
-			else {
-				ip_vs_service_put(svc);
+			else
 				*verdict = NF_DROP;
-			}
+			rcu_read_unlock();
 			return 0;
 		}
-		ip_vs_service_put(svc);
 	}
+	rcu_read_unlock();
 	/* NF_ACCEPT */
 	return 1;
 }

net/netfilter/ipvs/ip_vs_rr.c

@@ -121,6 +121,7 @@ static int __init ip_vs_rr_init(void)
 static void __exit ip_vs_rr_cleanup(void)
 {
 	unregister_ip_vs_scheduler(&ip_vs_rr_scheduler);
+	synchronize_rcu();
 }
 
 module_init(ip_vs_rr_init);

net/netfilter/ipvs/ip_vs_sched.c

@@ -47,8 +47,6 @@ int ip_vs_bind_scheduler(struct ip_vs_service *svc,
 {
 	int ret;
 
-	svc->scheduler = scheduler;
-
 	if (scheduler->init_service) {
 		ret = scheduler->init_service(svc);
 		if (ret) {
@@ -56,7 +54,7 @@ int ip_vs_bind_scheduler(struct ip_vs_service *svc,
 			return ret;
 		}
 	}
-
+	rcu_assign_pointer(svc->scheduler, scheduler);
 	return 0;
 }
 
@@ -64,17 +62,19 @@ int ip_vs_bind_scheduler(struct ip_vs_service *svc,
 /*
  *  Unbind a service with its scheduler
  */
-void ip_vs_unbind_scheduler(struct ip_vs_service *svc)
+void ip_vs_unbind_scheduler(struct ip_vs_service *svc,
+			    struct ip_vs_scheduler *sched)
 {
-	struct ip_vs_scheduler *sched = svc->scheduler;
+	struct ip_vs_scheduler *cur_sched;
 
-	if (!sched)
+	cur_sched = rcu_dereference_protected(svc->scheduler, 1);
+	/* This check proves that old 'sched' was installed */
+	if (!cur_sched)
 		return;
 
 	if (sched->done_service)
 		sched->done_service(svc);
-
-	svc->scheduler = NULL;
+	/* svc->scheduler can not be set to NULL */
 }
 
 
@@ -148,21 +148,21 @@ void ip_vs_scheduler_put(struct ip_vs_scheduler *scheduler)
 
 void ip_vs_scheduler_err(struct ip_vs_service *svc, const char *msg)
 {
+	struct ip_vs_scheduler *sched;
+
+	sched = rcu_dereference(svc->scheduler);
 	if (svc->fwmark) {
 		IP_VS_ERR_RL("%s: FWM %u 0x%08X - %s\n",
-			     svc->scheduler->name, svc->fwmark,
-			     svc->fwmark, msg);
+			     sched->name, svc->fwmark, svc->fwmark, msg);
 #ifdef CONFIG_IP_VS_IPV6
 	} else if (svc->af == AF_INET6) {
 		IP_VS_ERR_RL("%s: %s [%pI6c]:%d - %s\n",
-			     svc->scheduler->name,
-			     ip_vs_proto_name(svc->protocol),
+			     sched->name, ip_vs_proto_name(svc->protocol),
 			     &svc->addr.in6, ntohs(svc->port), msg);
 #endif
 	} else {
 		IP_VS_ERR_RL("%s: %s %pI4:%d - %s\n",
-			     svc->scheduler->name,
-			     ip_vs_proto_name(svc->protocol),
+			     sched->name, ip_vs_proto_name(svc->protocol),
 			     &svc->addr.ip, ntohs(svc->port), msg);
 	}
 }

net/netfilter/ipvs/ip_vs_sed.c

@@ -134,6 +134,7 @@ static int __init ip_vs_sed_init(void)
 static void __exit ip_vs_sed_cleanup(void)
 {
 	unregister_ip_vs_scheduler(&ip_vs_sed_scheduler);
+	synchronize_rcu();
 }
 
 module_init(ip_vs_sed_init);

net/netfilter/ipvs/ip_vs_sh.c

@@ -283,6 +283,7 @@ static int __init ip_vs_sh_init(void)
 static void __exit ip_vs_sh_cleanup(void)
 {
 	unregister_ip_vs_scheduler(&ip_vs_sh_scheduler);
+	synchronize_rcu();
 }
 
 

net/netfilter/ipvs/ip_vs_wlc.c

@@ -106,6 +106,7 @@ static int __init ip_vs_wlc_init(void)
 static void __exit ip_vs_wlc_cleanup(void)
 {
 	unregister_ip_vs_scheduler(&ip_vs_wlc_scheduler);
+	synchronize_rcu();
 }
 
 module_init(ip_vs_wlc_init);

net/netfilter/ipvs/ip_vs_wrr.c

@@ -261,6 +261,7 @@ static int __init ip_vs_wrr_init(void)
 static void __exit ip_vs_wrr_cleanup(void)
 {
 	unregister_ip_vs_scheduler(&ip_vs_wrr_scheduler);
+	synchronize_rcu();
 }
 
 module_init(ip_vs_wrr_init);