Commit ceec4c38 authored by Julian Anastasov's avatar Julian Anastasov Committed by Pablo Neira Ayuso
Browse files

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	use an outdated svc-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: default avatarJulian Anastasov <ja@ssi.bg>
Signed-off-by: default avatarSimon Horman <horms@verge.net.au>
parent 413c2d04

include/net/ip_vs.h

+9 −19
Original line number Diff line number Diff line
@@ -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

+9 −17
Original line number Diff line number Diff line
@@ -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_ctl.c

+123 −176

File changed.

Preview size limit exceeded, changes collapsed.

net/netfilter/ipvs/ip_vs_dh.c

+1 −0

File changed.

Preview size limit exceeded, changes collapsed.

net/netfilter/ipvs/ip_vs_lblc.c

+1 −0

File changed.

Preview size limit exceeded, changes collapsed.