Donate to e Foundation | Murena handsets with /e/OS | Own a part of Murena! Learn more

Commit fcfa8f49 authored by Pablo Neira Ayuso's avatar Pablo Neira Ayuso
Browse files

Merge branch 'ipvs-next' 



Simon Horman says:

====================
This pull requests makes the following changes:

* Add simple weighted fail-over scheduler.
  - Unlike other IPVS schedulers this offers fail-over rather than load
    balancing. Connections are directed to the appropriate server based
    solely on highest weight value and server availability.
  - Thanks to Kenny Mathis

* Support IPv6 real servers in IPv4 virtual-services and vice versa
  - This feature is supported in conjunction with the tunnel (IPIP)
    forwarding mechanism. That is, IPv4 may be forwarded in IPv6 and
    vice versa.
  - The motivation for this is to allow more flexibility in the
    choice of IP version offered by both virtual-servers and
    real-servers as they no longer need to match: An IPv4 connection from an
    end-user may be forwarded to a real-server using IPv6 and vice versa.
  - Further work need to be done to support this feature in conjunction
    with connection synchronisation. For now such configurations are
    not allowed.
  - This change includes update to netlink protocol, adding a new
    destination address family attribute. And the necessary changes
    to plumb this information throughout IPVS.
  - Thanks to Alex Gartrell and Julian Anastasov
====================

Signed-off-by: default avatarPablo Neira Ayuso <pablo@netfilter.org>
parents 07034aea bc18d37f

include/net/ip_vs.h

+12 −3
Original line number Diff line number Diff line
@@ -535,6 +535,7 @@ struct ip_vs_conn { 
	union nf_inet_addr      daddr;          /* destination address */

	volatile __u32          flags;          /* status flags */

	__u16                   protocol;       /* Which protocol (TCP/UDP) */

	__u16			daf;		/* Address family of the dest */

#ifdef CONFIG_NET_NS

	struct net              *net;           /* Name space */

#endif
@@ -648,6 +649,9 @@ struct ip_vs_dest_user_kern { 
	/* thresholds for active connections */

	u32			u_threshold;	/* upper threshold */

	u32			l_threshold;	/* lower threshold */



	/* Address family of addr */

	u16			af;

};
@@ -986,6 +990,10 @@ struct netns_ipvs { 
	char			backup_mcast_ifn[IP_VS_IFNAME_MAXLEN];

	/* net name space ptr */

	struct net		*net;            /* Needed by timer routines */

	/* Number of heterogeneous destinations, needed because

	 * heterogeneous are not supported when synchronization is

	 * enabled */

	unsigned int		mixed_address_family_dests;

};



#define DEFAULT_SYNC_THRESHOLD	3
@@ -1210,7 +1218,7 @@ static inline void __ip_vs_conn_put(struct ip_vs_conn *cp) 
void ip_vs_conn_put(struct ip_vs_conn *cp);

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,

struct ip_vs_conn *ip_vs_conn_new(const struct ip_vs_conn_param *p, int dest_af,

				  const union nf_inet_addr *daddr,

				  __be16 dport, unsigned int flags,

				  struct ip_vs_dest *dest, __u32 fwmark);
@@ -1396,8 +1404,9 @@ void ip_vs_unregister_nl_ioctl(void); 
int ip_vs_control_init(void);

void ip_vs_control_cleanup(void);

struct ip_vs_dest *

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,

ip_vs_find_dest(struct net *net, int svc_af, int dest_af,

		const union nf_inet_addr *daddr, __be16 dport,

		const union nf_inet_addr *vaddr, __be16 vport,

		__u16 protocol, __u32 fwmark, __u32 flags);

void ip_vs_try_bind_dest(struct ip_vs_conn *cp);

include/uapi/linux/ip_vs.h

+3 −0
Original line number Diff line number Diff line
@@ -384,6 +384,9 @@ enum { 
	IPVS_DEST_ATTR_PERSIST_CONNS,	/* persistent connections */



	IPVS_DEST_ATTR_STATS,		/* nested attribute for dest stats */



	IPVS_DEST_ATTR_ADDR_FAMILY,	/* Address family of address */



	__IPVS_DEST_ATTR_MAX,

};

net/netfilter/ipvs/Kconfig

+10 −0
Original line number Diff line number Diff line
@@ -152,6 +152,16 @@ config IP_VS_WLC 
	  If you want to compile it in kernel, say Y. To compile it as a

	  module, choose M here. If unsure, say N.



config  IP_VS_FO

		tristate "weighted failover scheduling"

	---help---

	  The weighted failover scheduling algorithm directs network

	  connections to the server with the highest weight that is

	  currently available.



	  If you want to compile it in kernel, say Y. To compile it as a

	  module, choose M here. If unsure, say N.



config	IP_VS_LBLC

	tristate "locality-based least-connection scheduling"

	---help---

net/netfilter/ipvs/Makefile

+1 −0
Original line number Diff line number Diff line
@@ -26,6 +26,7 @@ obj-$(CONFIG_IP_VS_RR) += ip_vs_rr.o 
obj-$(CONFIG_IP_VS_WRR) += ip_vs_wrr.o

obj-$(CONFIG_IP_VS_LC) += ip_vs_lc.o

obj-$(CONFIG_IP_VS_WLC) += ip_vs_wlc.o

obj-$(CONFIG_IP_VS_FO) += ip_vs_fo.o

obj-$(CONFIG_IP_VS_LBLC) += ip_vs_lblc.o

obj-$(CONFIG_IP_VS_LBLCR) += ip_vs_lblcr.o

obj-$(CONFIG_IP_VS_DH) += ip_vs_dh.o

net/netfilter/ipvs/ip_vs_conn.c

+58 −16
Original line number Diff line number Diff line
@@ -27,6 +27,7 @@ 


#include <linux/interrupt.h>

#include <linux/in.h>

#include <linux/inet.h>

#include <linux/net.h>

#include <linux/kernel.h>

#include <linux/module.h>
@@ -77,6 +78,13 @@ static unsigned int ip_vs_conn_rnd __read_mostly; 
#define CT_LOCKARRAY_SIZE  (1<<CT_LOCKARRAY_BITS)

#define CT_LOCKARRAY_MASK  (CT_LOCKARRAY_SIZE-1)



/* We need an addrstrlen that works with or without v6 */

#ifdef CONFIG_IP_VS_IPV6

#define IP_VS_ADDRSTRLEN INET6_ADDRSTRLEN

#else

#define IP_VS_ADDRSTRLEN (8+1)

#endif



struct ip_vs_aligned_lock

{

	spinlock_t	l;
@@ -488,6 +496,11 @@ static inline void ip_vs_bind_xmit(struct ip_vs_conn *cp) 
		break;



	case IP_VS_CONN_F_TUNNEL:

#ifdef CONFIG_IP_VS_IPV6

		if (cp->daf == AF_INET6)

			cp->packet_xmit = ip_vs_tunnel_xmit_v6;

		else

#endif

			cp->packet_xmit = ip_vs_tunnel_xmit;

		break;
@@ -514,7 +527,10 @@ static inline void ip_vs_bind_xmit_v6(struct ip_vs_conn *cp) 
		break;



	case IP_VS_CONN_F_TUNNEL:

		if (cp->daf == AF_INET6)

			cp->packet_xmit = ip_vs_tunnel_xmit_v6;

		else

			cp->packet_xmit = ip_vs_tunnel_xmit;

		break;



	case IP_VS_CONN_F_DROUTE:
@@ -580,7 +596,7 @@ ip_vs_bind_dest(struct ip_vs_conn *cp, struct ip_vs_dest *dest) 
		      ip_vs_proto_name(cp->protocol),

		      IP_VS_DBG_ADDR(cp->af, &cp->caddr), ntohs(cp->cport),

		      IP_VS_DBG_ADDR(cp->af, &cp->vaddr), ntohs(cp->vport),

		      IP_VS_DBG_ADDR(cp->af, &cp->daddr), ntohs(cp->dport),

		      IP_VS_DBG_ADDR(cp->daf, &cp->daddr), ntohs(cp->dport),

		      ip_vs_fwd_tag(cp), cp->state,

		      cp->flags, atomic_read(&cp->refcnt),

		      atomic_read(&dest->refcnt));
@@ -616,7 +632,13 @@ void ip_vs_try_bind_dest(struct ip_vs_conn *cp) 
	struct ip_vs_dest *dest;



	rcu_read_lock();

	dest = ip_vs_find_dest(ip_vs_conn_net(cp), cp->af, &cp->daddr,



	/* This function is only invoked by the synchronization code. We do

	 * not currently support heterogeneous pools with synchronization,

	 * so we can make the assumption that the svc_af is the same as the

	 * dest_af

	 */

	dest = ip_vs_find_dest(ip_vs_conn_net(cp), cp->af, cp->af, &cp->daddr,

			       cp->dport, &cp->vaddr, cp->vport,

			       cp->protocol, cp->fwmark, cp->flags);

	if (dest) {
@@ -671,7 +693,7 @@ static inline void ip_vs_unbind_dest(struct ip_vs_conn *cp) 
		      ip_vs_proto_name(cp->protocol),

		      IP_VS_DBG_ADDR(cp->af, &cp->caddr), ntohs(cp->cport),

		      IP_VS_DBG_ADDR(cp->af, &cp->vaddr), ntohs(cp->vport),

		      IP_VS_DBG_ADDR(cp->af, &cp->daddr), ntohs(cp->dport),

		      IP_VS_DBG_ADDR(cp->daf, &cp->daddr), ntohs(cp->dport),

		      ip_vs_fwd_tag(cp), cp->state,

		      cp->flags, atomic_read(&cp->refcnt),

		      atomic_read(&dest->refcnt));
@@ -740,7 +762,7 @@ int ip_vs_check_template(struct ip_vs_conn *ct) 
			      ntohs(ct->cport),

			      IP_VS_DBG_ADDR(ct->af, &ct->vaddr),

			      ntohs(ct->vport),

			      IP_VS_DBG_ADDR(ct->af, &ct->daddr),

			      IP_VS_DBG_ADDR(ct->daf, &ct->daddr),

			      ntohs(ct->dport));



		/*
@@ -848,7 +870,7 @@ void ip_vs_conn_expire_now(struct ip_vs_conn *cp) 
 *	Create a new connection entry and hash it into the ip_vs_conn_tab

 */

struct ip_vs_conn *

ip_vs_conn_new(const struct ip_vs_conn_param *p,

ip_vs_conn_new(const struct ip_vs_conn_param *p, int dest_af,

	       const union nf_inet_addr *daddr, __be16 dport, unsigned int flags,

	       struct ip_vs_dest *dest, __u32 fwmark)

{
@@ -867,6 +889,7 @@ ip_vs_conn_new(const struct ip_vs_conn_param *p, 
	setup_timer(&cp->timer, ip_vs_conn_expire, (unsigned long)cp);

	ip_vs_conn_net_set(cp, p->net);

	cp->af		   = p->af;

	cp->daf		   = dest_af;

	cp->protocol	   = p->protocol;

	ip_vs_addr_set(p->af, &cp->caddr, p->caddr);

	cp->cport	   = p->cport;
@@ -874,7 +897,7 @@ ip_vs_conn_new(const struct ip_vs_conn_param *p, 
	ip_vs_addr_set(p->protocol == IPPROTO_IP ? AF_UNSPEC : p->af,

		       &cp->vaddr, p->vaddr);

	cp->vport	   = p->vport;

	ip_vs_addr_set(p->af, &cp->daddr, daddr);

	ip_vs_addr_set(cp->daf, &cp->daddr, daddr);

	cp->dport          = dport;

	cp->flags	   = flags;

	cp->fwmark         = fwmark;
@@ -1036,6 +1059,7 @@ static int ip_vs_conn_seq_show(struct seq_file *seq, void *v) 
		struct net *net = seq_file_net(seq);

		char pe_data[IP_VS_PENAME_MAXLEN + IP_VS_PEDATA_MAXLEN + 3];

		size_t len = 0;

		char dbuf[IP_VS_ADDRSTRLEN];



		if (!ip_vs_conn_net_eq(cp, net))

			return 0;
@@ -1049,25 +1073,33 @@ static int ip_vs_conn_seq_show(struct seq_file *seq, void *v) 
		}

		pe_data[len] = '\0';



#ifdef CONFIG_IP_VS_IPV6

		if (cp->daf == AF_INET6)

			snprintf(dbuf, sizeof(dbuf), "%pI6", &cp->daddr.in6);

		else

#endif

			snprintf(dbuf, sizeof(dbuf), "%08X",

				 ntohl(cp->daddr.ip));



#ifdef CONFIG_IP_VS_IPV6

		if (cp->af == AF_INET6)

			seq_printf(seq, "%-3s %pI6 %04X %pI6 %04X "

				"%pI6 %04X %-11s %7lu%s\n",

				"%s %04X %-11s %7lu%s\n",

				ip_vs_proto_name(cp->protocol),

				&cp->caddr.in6, ntohs(cp->cport),

				&cp->vaddr.in6, ntohs(cp->vport),

				&cp->daddr.in6, ntohs(cp->dport),

				dbuf, ntohs(cp->dport),

				ip_vs_state_name(cp->protocol, cp->state),

				(cp->timer.expires-jiffies)/HZ, pe_data);

		else

#endif

			seq_printf(seq,

				"%-3s %08X %04X %08X %04X"

				" %08X %04X %-11s %7lu%s\n",

				" %s %04X %-11s %7lu%s\n",

				ip_vs_proto_name(cp->protocol),

				ntohl(cp->caddr.ip), ntohs(cp->cport),

				ntohl(cp->vaddr.ip), ntohs(cp->vport),

				ntohl(cp->daddr.ip), ntohs(cp->dport),

				dbuf, ntohs(cp->dport),

				ip_vs_state_name(cp->protocol, cp->state),

				(cp->timer.expires-jiffies)/HZ, pe_data);

	}
@@ -1105,6 +1137,7 @@ static const char *ip_vs_origin_name(unsigned int flags) 


static int ip_vs_conn_sync_seq_show(struct seq_file *seq, void *v)

{

	char dbuf[IP_VS_ADDRSTRLEN];



	if (v == SEQ_START_TOKEN)

		seq_puts(seq,
@@ -1116,13 +1149,22 @@ static int ip_vs_conn_sync_seq_show(struct seq_file *seq, void *v) 
		if (!ip_vs_conn_net_eq(cp, net))

			return 0;



#ifdef CONFIG_IP_VS_IPV6

		if (cp->daf == AF_INET6)

			snprintf(dbuf, sizeof(dbuf), "%pI6", &cp->daddr.in6);

		else

#endif

			snprintf(dbuf, sizeof(dbuf), "%08X",

				 ntohl(cp->daddr.ip));



#ifdef CONFIG_IP_VS_IPV6

		if (cp->af == AF_INET6)

			seq_printf(seq, "%-3s %pI6 %04X %pI6 %04X %pI6 %04X %-11s %-6s %7lu\n",

			seq_printf(seq, "%-3s %pI6 %04X %pI6 %04X "

				"%s %04X %-11s %-6s %7lu\n",

				ip_vs_proto_name(cp->protocol),

				&cp->caddr.in6, ntohs(cp->cport),

				&cp->vaddr.in6, ntohs(cp->vport),

				&cp->daddr.in6, ntohs(cp->dport),

				dbuf, ntohs(cp->dport),

				ip_vs_state_name(cp->protocol, cp->state),

				ip_vs_origin_name(cp->flags),

				(cp->timer.expires-jiffies)/HZ);
@@ -1130,11 +1172,11 @@ static int ip_vs_conn_sync_seq_show(struct seq_file *seq, void *v) 
#endif

			seq_printf(seq,

				"%-3s %08X %04X %08X %04X "

				"%08X %04X %-11s %-6s %7lu\n",

				"%s %04X %-11s %-6s %7lu\n",

				ip_vs_proto_name(cp->protocol),

				ntohl(cp->caddr.ip), ntohs(cp->cport),

				ntohl(cp->vaddr.ip), ntohs(cp->vport),

				ntohl(cp->daddr.ip), ntohs(cp->dport),

				dbuf, ntohs(cp->dport),

				ip_vs_state_name(cp->protocol, cp->state),

				ip_vs_origin_name(cp->flags),

				(cp->timer.expires-jiffies)/HZ);