summaryrefslogtreecommitdiff
path: root/net/ipv4/ipvs
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2008-01-29 11:54:01 (GMT)
committerLinus Torvalds <torvalds@linux-foundation.org>2008-01-29 11:54:01 (GMT)
commit0ba6c33bcddc64a54b5f1c25a696c4767dc76292 (patch)
tree62e616f97a4762d8e75bf732e4827af2d15d52c5 /net/ipv4/ipvs
parent21af0297c7e56024a5ccc4d8ad2a590f9ec371ba (diff)
parent85040bcb4643cba578839e953f25e2d1965d83d0 (diff)
downloadlinux-fsl-qoriq-0ba6c33bcddc64a54b5f1c25a696c4767dc76292.tar.xz
Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-2.6.25
* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-2.6.25: (1470 commits) [IPV6] ADDRLABEL: Fix double free on label deletion. [PPP]: Sparse warning fixes. [IPV4] fib_trie: remove unneeded NULL check [IPV4] fib_trie: More whitespace cleanup. [NET_SCHED]: Use nla_policy for attribute validation in ematches [NET_SCHED]: Use nla_policy for attribute validation in actions [NET_SCHED]: Use nla_policy for attribute validation in classifiers [NET_SCHED]: Use nla_policy for attribute validation in packet schedulers [NET_SCHED]: sch_api: introduce constant for rate table size [NET_SCHED]: Use typeful attribute parsing helpers [NET_SCHED]: Use typeful attribute construction helpers [NET_SCHED]: Use NLA_PUT_STRING for string dumping [NET_SCHED]: Use nla_nest_start/nla_nest_end [NET_SCHED]: Propagate nla_parse return value [NET_SCHED]: act_api: use PTR_ERR in tcf_action_init/tcf_action_get [NET_SCHED]: act_api: use nlmsg_parse [NET_SCHED]: act_api: fix netlink API conversion bug [NET_SCHED]: sch_netem: use nla_parse_nested_compat [NET_SCHED]: sch_atm: fix format string warning [NETNS]: Add namespace for ICMP replying code. ...
Diffstat (limited to 'net/ipv4/ipvs')
-rw-r--r--net/ipv4/ipvs/ip_vs_app.c9
-rw-r--r--net/ipv4/ipvs/ip_vs_conn.c73
-rw-r--r--net/ipv4/ipvs/ip_vs_core.c116
-rw-r--r--net/ipv4/ipvs/ip_vs_ctl.c39
-rw-r--r--net/ipv4/ipvs/ip_vs_est.c4
-rw-r--r--net/ipv4/ipvs/ip_vs_lblc.c36
-rw-r--r--net/ipv4/ipvs/ip_vs_lblcr.c36
-rw-r--r--net/ipv4/ipvs/ip_vs_proto.c2
-rw-r--r--net/ipv4/ipvs/ip_vs_proto_esp.c16
-rw-r--r--net/ipv4/ipvs/ip_vs_sched.c1
-rw-r--r--net/ipv4/ipvs/ip_vs_sync.c34
-rw-r--r--net/ipv4/ipvs/ip_vs_xmit.c16
12 files changed, 177 insertions, 205 deletions
diff --git a/net/ipv4/ipvs/ip_vs_app.c b/net/ipv4/ipvs/ip_vs_app.c
index 664cb8e..535abe0 100644
--- a/net/ipv4/ipvs/ip_vs_app.c
+++ b/net/ipv4/ipvs/ip_vs_app.c
@@ -51,18 +51,13 @@ static DEFINE_MUTEX(__ip_vs_app_mutex);
*/
static inline int ip_vs_app_get(struct ip_vs_app *app)
{
- /* test and get the module atomically */
- if (app->module)
- return try_module_get(app->module);
- else
- return 1;
+ return try_module_get(app->module);
}
static inline void ip_vs_app_put(struct ip_vs_app *app)
{
- if (app->module)
- module_put(app->module);
+ module_put(app->module);
}
diff --git a/net/ipv4/ipvs/ip_vs_conn.c b/net/ipv4/ipvs/ip_vs_conn.c
index 0a9f3c3..65f1ba1 100644
--- a/net/ipv4/ipvs/ip_vs_conn.c
+++ b/net/ipv4/ipvs/ip_vs_conn.c
@@ -393,7 +393,15 @@ ip_vs_bind_dest(struct ip_vs_conn *cp, struct ip_vs_dest *dest)
atomic_inc(&dest->refcnt);
/* Bind with the destination and its corresponding transmitter */
- cp->flags |= atomic_read(&dest->conn_flags);
+ if ((cp->flags & IP_VS_CONN_F_SYNC) &&
+ (!(cp->flags & IP_VS_CONN_F_TEMPLATE)))
+ /* if the connection is not template and is created
+ * by sync, preserve the activity flag.
+ */
+ cp->flags |= atomic_read(&dest->conn_flags) &
+ (~IP_VS_CONN_F_INACTIVE);
+ else
+ cp->flags |= atomic_read(&dest->conn_flags);
cp->dest = dest;
IP_VS_DBG(7, "Bind-dest %s c:%u.%u.%u.%u:%d v:%u.%u.%u.%u:%d "
@@ -412,7 +420,11 @@ ip_vs_bind_dest(struct ip_vs_conn *cp, struct ip_vs_dest *dest)
/* It is a normal connection, so increase the inactive
connection counter because it is in TCP SYNRECV
state (inactive) or other protocol inacive state */
- atomic_inc(&dest->inactconns);
+ if ((cp->flags & IP_VS_CONN_F_SYNC) &&
+ (!(cp->flags & IP_VS_CONN_F_INACTIVE)))
+ atomic_inc(&dest->activeconns);
+ else
+ atomic_inc(&dest->inactconns);
} else {
/* It is a persistent connection/template, so increase
the peristent connection counter */
@@ -629,9 +641,7 @@ ip_vs_conn_new(int proto, __be32 caddr, __be16 cport, __be32 vaddr, __be16 vport
}
INIT_LIST_HEAD(&cp->c_list);
- init_timer(&cp->timer);
- cp->timer.data = (unsigned long)cp;
- cp->timer.function = ip_vs_conn_expire;
+ setup_timer(&cp->timer, ip_vs_conn_expire, (unsigned long)cp);
cp->protocol = proto;
cp->caddr = caddr;
cp->cport = cport;
@@ -783,6 +793,57 @@ static const struct file_operations ip_vs_conn_fops = {
.llseek = seq_lseek,
.release = seq_release,
};
+
+static const char *ip_vs_origin_name(unsigned flags)
+{
+ if (flags & IP_VS_CONN_F_SYNC)
+ return "SYNC";
+ else
+ return "LOCAL";
+}
+
+static int ip_vs_conn_sync_seq_show(struct seq_file *seq, void *v)
+{
+
+ if (v == SEQ_START_TOKEN)
+ seq_puts(seq,
+ "Pro FromIP FPrt ToIP TPrt DestIP DPrt State Origin Expires\n");
+ else {
+ const struct ip_vs_conn *cp = v;
+
+ seq_printf(seq,
+ "%-3s %08X %04X %08X %04X %08X %04X %-11s %-6s %7lu\n",
+ ip_vs_proto_name(cp->protocol),
+ ntohl(cp->caddr), ntohs(cp->cport),
+ ntohl(cp->vaddr), ntohs(cp->vport),
+ ntohl(cp->daddr), ntohs(cp->dport),
+ ip_vs_state_name(cp->protocol, cp->state),
+ ip_vs_origin_name(cp->flags),
+ (cp->timer.expires-jiffies)/HZ);
+ }
+ return 0;
+}
+
+static const struct seq_operations ip_vs_conn_sync_seq_ops = {
+ .start = ip_vs_conn_seq_start,
+ .next = ip_vs_conn_seq_next,
+ .stop = ip_vs_conn_seq_stop,
+ .show = ip_vs_conn_sync_seq_show,
+};
+
+static int ip_vs_conn_sync_open(struct inode *inode, struct file *file)
+{
+ return seq_open(file, &ip_vs_conn_sync_seq_ops);
+}
+
+static const struct file_operations ip_vs_conn_sync_fops = {
+ .owner = THIS_MODULE,
+ .open = ip_vs_conn_sync_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = seq_release,
+};
+
#endif
@@ -942,6 +1003,7 @@ int ip_vs_conn_init(void)
}
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);
/* calculate the random value for connection hash */
get_random_bytes(&ip_vs_conn_rnd, sizeof(ip_vs_conn_rnd));
@@ -958,5 +1020,6 @@ void ip_vs_conn_cleanup(void)
/* 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);
}
diff --git a/net/ipv4/ipvs/ip_vs_core.c b/net/ipv4/ipvs/ip_vs_core.c
index 8fba202..963981a 100644
--- a/net/ipv4/ipvs/ip_vs_core.c
+++ b/net/ipv4/ipvs/ip_vs_core.c
@@ -423,7 +423,7 @@ int ip_vs_leave(struct ip_vs_service *svc, struct sk_buff *skb,
and the destination is RTN_UNICAST (and not local), then create
a cache_bypass connection entry */
if (sysctl_ip_vs_cache_bypass && svc->fwmark
- && (inet_addr_type(iph->daddr) == RTN_UNICAST)) {
+ && (inet_addr_type(&init_net, iph->daddr) == RTN_UNICAST)) {
int ret, cs;
struct ip_vs_conn *cp;
@@ -481,7 +481,7 @@ int ip_vs_leave(struct ip_vs_service *svc, struct sk_buff *skb,
/*
- * It is hooked before NF_IP_PRI_NAT_SRC at the NF_IP_POST_ROUTING
+ * It is hooked before NF_IP_PRI_NAT_SRC at the NF_INET_POST_ROUTING
* chain, and is used for VS/NAT.
* It detects packets for VS/NAT connections and sends the packets
* immediately. This can avoid that iptable_nat mangles the packets
@@ -679,7 +679,7 @@ static inline int is_tcp_reset(const struct sk_buff *skb)
}
/*
- * It is hooked at the NF_IP_FORWARD chain, used only for VS/NAT.
+ * It is hooked at the NF_INET_FORWARD chain, used only for VS/NAT.
* Check if outgoing packet belongs to the established ip_vs_conn,
* rewrite addresses of the packet and send it on its way...
*/
@@ -814,7 +814,7 @@ ip_vs_in_icmp(struct sk_buff *skb, int *related, unsigned int hooknum)
/* reassemble IP fragments */
if (ip_hdr(skb)->frag_off & htons(IP_MF | IP_OFFSET)) {
- if (ip_vs_gather_frags(skb, hooknum == NF_IP_LOCAL_IN ?
+ if (ip_vs_gather_frags(skb, hooknum == NF_INET_LOCAL_IN ?
IP_DEFRAG_VS_IN : IP_DEFRAG_VS_FWD))
return NF_STOLEN;
}
@@ -1003,12 +1003,12 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb,
/*
- * It is hooked at the NF_IP_FORWARD chain, in order to catch ICMP
+ * It is hooked at the NF_INET_FORWARD chain, in order to catch ICMP
* related packets destined for 0.0.0.0/0.
* When fwmark-based virtual service is used, such as transparent
* cache cluster, TCP packets can be marked and routed to ip_vs_in,
* but ICMP destined for 0.0.0.0/0 cannot not be easily marked and
- * sent to ip_vs_in_icmp. So, catch them at the NF_IP_FORWARD chain
+ * sent to ip_vs_in_icmp. So, catch them at the NF_INET_FORWARD chain
* and send them to ip_vs_in_icmp.
*/
static unsigned int
@@ -1025,43 +1025,42 @@ ip_vs_forward_icmp(unsigned int hooknum, struct sk_buff *skb,
}
-/* After packet filtering, forward packet through VS/DR, VS/TUN,
- or VS/NAT(change destination), so that filtering rules can be
- applied to IPVS. */
-static struct nf_hook_ops ip_vs_in_ops = {
- .hook = ip_vs_in,
- .owner = THIS_MODULE,
- .pf = PF_INET,
- .hooknum = NF_IP_LOCAL_IN,
- .priority = 100,
-};
-
-/* After packet filtering, change source only for VS/NAT */
-static struct nf_hook_ops ip_vs_out_ops = {
- .hook = ip_vs_out,
- .owner = THIS_MODULE,
- .pf = PF_INET,
- .hooknum = NF_IP_FORWARD,
- .priority = 100,
-};
-
-/* After packet filtering (but before ip_vs_out_icmp), catch icmp
- destined for 0.0.0.0/0, which is for incoming IPVS connections */
-static struct nf_hook_ops ip_vs_forward_icmp_ops = {
- .hook = ip_vs_forward_icmp,
- .owner = THIS_MODULE,
- .pf = PF_INET,
- .hooknum = NF_IP_FORWARD,
- .priority = 99,
-};
-
-/* Before the netfilter connection tracking, exit from POST_ROUTING */
-static struct nf_hook_ops ip_vs_post_routing_ops = {
- .hook = ip_vs_post_routing,
- .owner = THIS_MODULE,
- .pf = PF_INET,
- .hooknum = NF_IP_POST_ROUTING,
- .priority = NF_IP_PRI_NAT_SRC-1,
+static struct nf_hook_ops ip_vs_ops[] __read_mostly = {
+ /* After packet filtering, forward packet through VS/DR, VS/TUN,
+ * or VS/NAT(change destination), so that filtering rules can be
+ * applied to IPVS. */
+ {
+ .hook = ip_vs_in,
+ .owner = THIS_MODULE,
+ .pf = PF_INET,
+ .hooknum = NF_INET_LOCAL_IN,
+ .priority = 100,
+ },
+ /* After packet filtering, change source only for VS/NAT */
+ {
+ .hook = ip_vs_out,
+ .owner = THIS_MODULE,
+ .pf = PF_INET,
+ .hooknum = NF_INET_FORWARD,
+ .priority = 100,
+ },
+ /* After packet filtering (but before ip_vs_out_icmp), catch icmp
+ * destined for 0.0.0.0/0, which is for incoming IPVS connections */
+ {
+ .hook = ip_vs_forward_icmp,
+ .owner = THIS_MODULE,
+ .pf = PF_INET,
+ .hooknum = NF_INET_FORWARD,
+ .priority = 99,
+ },
+ /* Before the netfilter connection tracking, exit from POST_ROUTING */
+ {
+ .hook = ip_vs_post_routing,
+ .owner = THIS_MODULE,
+ .pf = PF_INET,
+ .hooknum = NF_INET_POST_ROUTING,
+ .priority = NF_IP_PRI_NAT_SRC-1,
+ },
};
@@ -1092,37 +1091,15 @@ static int __init ip_vs_init(void)
goto cleanup_app;
}
- ret = nf_register_hook(&ip_vs_in_ops);
+ ret = nf_register_hooks(ip_vs_ops, ARRAY_SIZE(ip_vs_ops));
if (ret < 0) {
- IP_VS_ERR("can't register in hook.\n");
+ IP_VS_ERR("can't register hooks.\n");
goto cleanup_conn;
}
- ret = nf_register_hook(&ip_vs_out_ops);
- if (ret < 0) {
- IP_VS_ERR("can't register out hook.\n");
- goto cleanup_inops;
- }
- ret = nf_register_hook(&ip_vs_post_routing_ops);
- if (ret < 0) {
- IP_VS_ERR("can't register post_routing hook.\n");
- goto cleanup_outops;
- }
- ret = nf_register_hook(&ip_vs_forward_icmp_ops);
- if (ret < 0) {
- IP_VS_ERR("can't register forward_icmp hook.\n");
- goto cleanup_postroutingops;
- }
-
IP_VS_INFO("ipvs loaded.\n");
return ret;
- cleanup_postroutingops:
- nf_unregister_hook(&ip_vs_post_routing_ops);
- cleanup_outops:
- nf_unregister_hook(&ip_vs_out_ops);
- cleanup_inops:
- nf_unregister_hook(&ip_vs_in_ops);
cleanup_conn:
ip_vs_conn_cleanup();
cleanup_app:
@@ -1136,10 +1113,7 @@ static int __init ip_vs_init(void)
static void __exit ip_vs_cleanup(void)
{
- nf_unregister_hook(&ip_vs_forward_icmp_ops);
- nf_unregister_hook(&ip_vs_post_routing_ops);
- nf_unregister_hook(&ip_vs_out_ops);
- nf_unregister_hook(&ip_vs_in_ops);
+ nf_unregister_hooks(ip_vs_ops, ARRAY_SIZE(ip_vs_ops));
ip_vs_conn_cleanup();
ip_vs_app_cleanup();
ip_vs_protocol_cleanup();
diff --git a/net/ipv4/ipvs/ip_vs_ctl.c b/net/ipv4/ipvs/ip_vs_ctl.c
index 693d924..94c5767 100644
--- a/net/ipv4/ipvs/ip_vs_ctl.c
+++ b/net/ipv4/ipvs/ip_vs_ctl.c
@@ -704,7 +704,7 @@ __ip_vs_update_dest(struct ip_vs_service *svc,
conn_flags = udest->conn_flags | IP_VS_CONN_F_INACTIVE;
/* check if local node and update the flags */
- if (inet_addr_type(udest->addr) == RTN_LOCAL) {
+ if (inet_addr_type(&init_net, udest->addr) == RTN_LOCAL) {
conn_flags = (conn_flags & ~IP_VS_CONN_F_FWD_MASK)
| IP_VS_CONN_F_LOCALNODE;
}
@@ -756,7 +756,7 @@ ip_vs_new_dest(struct ip_vs_service *svc, struct ip_vs_dest_user *udest,
EnterFunction(2);
- atype = inet_addr_type(udest->addr);
+ atype = inet_addr_type(&init_net, udest->addr);
if (atype != RTN_LOCAL && atype != RTN_UNICAST)
return -EINVAL;
@@ -1591,34 +1591,13 @@ static struct ctl_table vs_vars[] = {
{ .ctl_name = 0 }
};
-static ctl_table vs_table[] = {
- {
- .procname = "vs",
- .mode = 0555,
- .child = vs_vars
- },
- { .ctl_name = 0 }
-};
-
-static ctl_table ipvs_ipv4_table[] = {
- {
- .ctl_name = NET_IPV4,
- .procname = "ipv4",
- .mode = 0555,
- .child = vs_table,
- },
- { .ctl_name = 0 }
-};
-
-static ctl_table vs_root_table[] = {
- {
- .ctl_name = CTL_NET,
- .procname = "net",
- .mode = 0555,
- .child = ipvs_ipv4_table,
- },
- { .ctl_name = 0 }
+struct ctl_path net_vs_ctl_path[] = {
+ { .procname = "net", .ctl_name = CTL_NET, },
+ { .procname = "ipv4", .ctl_name = NET_IPV4, },
+ { .procname = "vs", },
+ { }
};
+EXPORT_SYMBOL_GPL(net_vs_ctl_path);
static struct ctl_table_header * sysctl_header;
@@ -2345,7 +2324,7 @@ int ip_vs_control_init(void)
proc_net_fops_create(&init_net, "ip_vs", 0, &ip_vs_info_fops);
proc_net_fops_create(&init_net, "ip_vs_stats",0, &ip_vs_stats_fops);
- sysctl_header = register_sysctl_table(vs_root_table);
+ sysctl_header = register_sysctl_paths(net_vs_ctl_path, vs_vars);
/* Initialize ip_vs_svc_table, ip_vs_svc_fwm_table, ip_vs_rtable */
for(idx = 0; idx < IP_VS_SVC_TAB_SIZE; idx++) {
diff --git a/net/ipv4/ipvs/ip_vs_est.c b/net/ipv4/ipvs/ip_vs_est.c
index 7d68b80..dfa0d71 100644
--- a/net/ipv4/ipvs/ip_vs_est.c
+++ b/net/ipv4/ipvs/ip_vs_est.c
@@ -18,6 +18,7 @@
#include <linux/slab.h>
#include <linux/types.h>
#include <linux/interrupt.h>
+#include <linux/sysctl.h>
#include <net/ip_vs.h>
@@ -146,9 +147,8 @@ int ip_vs_new_estimator(struct ip_vs_stats *stats)
write_lock_bh(&est_lock);
est->next = est_list;
if (est->next == NULL) {
- init_timer(&est_timer);
+ setup_timer(&est_timer, estimation_timer, 0);
est_timer.expires = jiffies + 2*HZ;
- est_timer.function = estimation_timer;
add_timer(&est_timer);
}
est_list = est;
diff --git a/net/ipv4/ipvs/ip_vs_lblc.c b/net/ipv4/ipvs/ip_vs_lblc.c
index ad89644..3888642 100644
--- a/net/ipv4/ipvs/ip_vs_lblc.c
+++ b/net/ipv4/ipvs/ip_vs_lblc.c
@@ -123,35 +123,6 @@ static ctl_table vs_vars_table[] = {
{ .ctl_name = 0 }
};
-static ctl_table vs_table[] = {
- {
- .procname = "vs",
- .mode = 0555,
- .child = vs_vars_table
- },
- { .ctl_name = 0 }
-};
-
-static ctl_table ipvs_ipv4_table[] = {
- {
- .ctl_name = NET_IPV4,
- .procname = "ipv4",
- .mode = 0555,
- .child = vs_table
- },
- { .ctl_name = 0 }
-};
-
-static ctl_table lblc_root_table[] = {
- {
- .ctl_name = CTL_NET,
- .procname = "net",
- .mode = 0555,
- .child = ipvs_ipv4_table
- },
- { .ctl_name = 0 }
-};
-
static struct ctl_table_header * sysctl_header;
/*
@@ -391,9 +362,8 @@ static int ip_vs_lblc_init_svc(struct ip_vs_service *svc)
/*
* Hook periodic timer for garbage collection
*/
- init_timer(&tbl->periodic_timer);
- tbl->periodic_timer.data = (unsigned long)tbl;
- tbl->periodic_timer.function = ip_vs_lblc_check_expire;
+ setup_timer(&tbl->periodic_timer, ip_vs_lblc_check_expire,
+ (unsigned long)tbl);
tbl->periodic_timer.expires = jiffies+CHECK_EXPIRE_INTERVAL;
add_timer(&tbl->periodic_timer);
@@ -583,7 +553,7 @@ static int __init ip_vs_lblc_init(void)
int ret;
INIT_LIST_HEAD(&ip_vs_lblc_scheduler.n_list);
- sysctl_header = register_sysctl_table(lblc_root_table);
+ sysctl_header = register_sysctl_paths(net_vs_ctl_path, vs_vars_table);
ret = register_ip_vs_scheduler(&ip_vs_lblc_scheduler);
if (ret)
unregister_sysctl_table(sysctl_header);
diff --git a/net/ipv4/ipvs/ip_vs_lblcr.c b/net/ipv4/ipvs/ip_vs_lblcr.c
index 2a5ed85..daa260e 100644
--- a/net/ipv4/ipvs/ip_vs_lblcr.c
+++ b/net/ipv4/ipvs/ip_vs_lblcr.c
@@ -311,35 +311,6 @@ static ctl_table vs_vars_table[] = {
{ .ctl_name = 0 }
};
-static ctl_table vs_table[] = {
- {
- .procname = "vs",
- .mode = 0555,
- .child = vs_vars_table
- },
- { .ctl_name = 0 }
-};
-
-static ctl_table ipvs_ipv4_table[] = {
- {
- .ctl_name = NET_IPV4,
- .procname = "ipv4",
- .mode = 0555,
- .child = vs_table
- },
- { .ctl_name = 0 }
-};
-
-static ctl_table lblcr_root_table[] = {
- {
- .ctl_name = CTL_NET,
- .procname = "net",
- .mode = 0555,
- .child = ipvs_ipv4_table
- },
- { .ctl_name = 0 }
-};
-
static struct ctl_table_header * sysctl_header;
/*
@@ -575,9 +546,8 @@ static int ip_vs_lblcr_init_svc(struct ip_vs_service *svc)
/*
* Hook periodic timer for garbage collection
*/
- init_timer(&tbl->periodic_timer);
- tbl->periodic_timer.data = (unsigned long)tbl;
- tbl->periodic_timer.function = ip_vs_lblcr_check_expire;
+ setup_timer(&tbl->periodic_timer, ip_vs_lblcr_check_expire,
+ (unsigned long)tbl);
tbl->periodic_timer.expires = jiffies+CHECK_EXPIRE_INTERVAL;
add_timer(&tbl->periodic_timer);
@@ -772,7 +742,7 @@ static int __init ip_vs_lblcr_init(void)
int ret;
INIT_LIST_HEAD(&ip_vs_lblcr_scheduler.n_list);
- sysctl_header = register_sysctl_table(lblcr_root_table);
+ sysctl_header = register_sysctl_paths(net_vs_ctl_path, vs_vars_table);
ret = register_ip_vs_scheduler(&ip_vs_lblcr_scheduler);
if (ret)
unregister_sysctl_table(sysctl_header);
diff --git a/net/ipv4/ipvs/ip_vs_proto.c b/net/ipv4/ipvs/ip_vs_proto.c
index c0e11ec8..dde28a2 100644
--- a/net/ipv4/ipvs/ip_vs_proto.c
+++ b/net/ipv4/ipvs/ip_vs_proto.c
@@ -165,7 +165,7 @@ ip_vs_tcpudp_debug_packet(struct ip_vs_protocol *pp,
ih = skb_header_pointer(skb, offset, sizeof(_iph), &_iph);
if (ih == NULL)
sprintf(buf, "%s TRUNCATED", pp->name);
- else if (ih->frag_off & __constant_htons(IP_OFFSET))
+ else if (ih->frag_off & htons(IP_OFFSET))
sprintf(buf, "%s %u.%u.%u.%u->%u.%u.%u.%u frag",
pp->name, NIPQUAD(ih->saddr),
NIPQUAD(ih->daddr));
diff --git a/net/ipv4/ipvs/ip_vs_proto_esp.c b/net/ipv4/ipvs/ip_vs_proto_esp.c
index c36ccf0..aef0d3e 100644
--- a/net/ipv4/ipvs/ip_vs_proto_esp.c
+++ b/net/ipv4/ipvs/ip_vs_proto_esp.c
@@ -52,15 +52,15 @@ esp_conn_in_get(const struct sk_buff *skb,
if (likely(!inverse)) {
cp = ip_vs_conn_in_get(IPPROTO_UDP,
iph->saddr,
- __constant_htons(PORT_ISAKMP),
+ htons(PORT_ISAKMP),
iph->daddr,
- __constant_htons(PORT_ISAKMP));
+ htons(PORT_ISAKMP));
} else {
cp = ip_vs_conn_in_get(IPPROTO_UDP,
iph->daddr,
- __constant_htons(PORT_ISAKMP),
+ htons(PORT_ISAKMP),
iph->saddr,
- __constant_htons(PORT_ISAKMP));
+ htons(PORT_ISAKMP));
}
if (!cp) {
@@ -89,15 +89,15 @@ esp_conn_out_get(const struct sk_buff *skb, struct ip_vs_protocol *pp,
if (likely(!inverse)) {
cp = ip_vs_conn_out_get(IPPROTO_UDP,
iph->saddr,
- __constant_htons(PORT_ISAKMP),
+ htons(PORT_ISAKMP),
iph->daddr,
- __constant_htons(PORT_ISAKMP));
+ htons(PORT_ISAKMP));
} else {
cp = ip_vs_conn_out_get(IPPROTO_UDP,
iph->daddr,
- __constant_htons(PORT_ISAKMP),
+ htons(PORT_ISAKMP),
iph->saddr,
- __constant_htons(PORT_ISAKMP));
+ htons(PORT_ISAKMP));
}
if (!cp) {
diff --git a/net/ipv4/ipvs/ip_vs_sched.c b/net/ipv4/ipvs/ip_vs_sched.c
index 4322358..121a32b 100644
--- a/net/ipv4/ipvs/ip_vs_sched.c
+++ b/net/ipv4/ipvs/ip_vs_sched.c
@@ -24,6 +24,7 @@
#include <linux/interrupt.h>
#include <asm/string.h>
#include <linux/kmod.h>
+#include <linux/sysctl.h>
#include <net/ip_vs.h>
diff --git a/net/ipv4/ipvs/ip_vs_sync.c b/net/ipv4/ipvs/ip_vs_sync.c
index bd930ef..948378d 100644
--- a/net/ipv4/ipvs/ip_vs_sync.c
+++ b/net/ipv4/ipvs/ip_vs_sync.c
@@ -305,10 +305,11 @@ static void ip_vs_process_message(const char *buffer, const size_t buflen)
p = (char *)buffer + sizeof(struct ip_vs_sync_mesg);
for (i=0; i<m->nr_conns; i++) {
- unsigned flags;
+ unsigned flags, state;
s = (struct ip_vs_sync_conn *)p;
- flags = ntohs(s->flags);
+ flags = ntohs(s->flags) | IP_VS_CONN_F_SYNC;
+ state = ntohs(s->state);
if (!(flags & IP_VS_CONN_F_TEMPLATE))
cp = ip_vs_conn_in_get(s->protocol,
s->caddr, s->cport,
@@ -326,6 +327,13 @@ static void ip_vs_process_message(const char *buffer, const size_t buflen)
dest = ip_vs_find_dest(s->daddr, s->dport,
s->vaddr, s->vport,
s->protocol);
+ /* Set the approprite ativity flag */
+ if (s->protocol == IPPROTO_TCP) {
+ if (state != IP_VS_TCP_S_ESTABLISHED)
+ flags |= IP_VS_CONN_F_INACTIVE;
+ else
+ flags &= ~IP_VS_CONN_F_INACTIVE;
+ }
cp = ip_vs_conn_new(s->protocol,
s->caddr, s->cport,
s->vaddr, s->vport,
@@ -337,7 +345,7 @@ static void ip_vs_process_message(const char *buffer, const size_t buflen)
IP_VS_ERR("ip_vs_conn_new failed\n");
return;
}
- cp->state = ntohs(s->state);
+ cp->state = state;
} else if (!cp->dest) {
dest = ip_vs_try_bind_dest(cp);
if (!dest) {
@@ -346,8 +354,22 @@ static void ip_vs_process_message(const char *buffer, const size_t buflen)
cp->flags = flags | IP_VS_CONN_F_HASHED;
} else
atomic_dec(&dest->refcnt);
- } /* Note that we don't touch its state and flags
- if it is a normal entry. */
+ } else if ((cp->dest) && (cp->protocol == IPPROTO_TCP) &&
+ (cp->state != state)) {
+ /* update active/inactive flag for the connection */
+ dest = cp->dest;
+ if (!(cp->flags & IP_VS_CONN_F_INACTIVE) &&
+ (state != IP_VS_TCP_S_ESTABLISHED)) {
+ atomic_dec(&dest->activeconns);
+ atomic_inc(&dest->inactconns);
+ cp->flags |= IP_VS_CONN_F_INACTIVE;
+ } else if ((cp->flags & IP_VS_CONN_F_INACTIVE) &&
+ (state == IP_VS_TCP_S_ESTABLISHED)) {
+ atomic_inc(&dest->activeconns);
+ atomic_dec(&dest->inactconns);
+ cp->flags &= ~IP_VS_CONN_F_INACTIVE;
+ }
+ }
if (flags & IP_VS_CONN_F_SEQ_MASK) {
opt = (struct ip_vs_sync_conn_options *)&s[1];
@@ -357,7 +379,7 @@ static void ip_vs_process_message(const char *buffer, const size_t buflen)
p += SIMPLE_CONN_SIZE;
atomic_set(&cp->in_pkts, sysctl_ip_vs_sync_threshold[0]);
- cp->state = ntohs(s->state);
+ cp->state = state;
pp = ip_vs_proto_get(s->protocol);
cp->timeout = pp->timeout_table[cp->state];
ip_vs_conn_put(cp);
diff --git a/net/ipv4/ipvs/ip_vs_xmit.c b/net/ipv4/ipvs/ip_vs_xmit.c
index 7c074e3..f63006c 100644
--- a/net/ipv4/ipvs/ip_vs_xmit.c
+++ b/net/ipv4/ipvs/ip_vs_xmit.c
@@ -16,8 +16,8 @@
*/
#include <linux/kernel.h>
-#include <linux/ip.h>
#include <linux/tcp.h> /* for tcphdr */
+#include <net/ip.h>
#include <net/tcp.h> /* for csum_tcpudp_magic */
#include <net/udp.h>
#include <net/icmp.h> /* for icmp_send */
@@ -59,7 +59,7 @@ __ip_vs_dst_check(struct ip_vs_dest *dest, u32 rtos, u32 cookie)
return dst;
}
-static inline struct rtable *
+static struct rtable *
__ip_vs_get_out_rt(struct ip_vs_conn *cp, u32 rtos)
{
struct rtable *rt; /* Route to the other host */
@@ -78,7 +78,7 @@ __ip_vs_get_out_rt(struct ip_vs_conn *cp, u32 rtos)
.tos = rtos, } },
};
- if (ip_route_output_key(&rt, &fl)) {
+ if (ip_route_output_key(&init_net, &rt, &fl)) {
spin_unlock(&dest->dst_lock);
IP_VS_DBG_RL("ip_route_output error, "
"dest: %u.%u.%u.%u\n",
@@ -101,7 +101,7 @@ __ip_vs_get_out_rt(struct ip_vs_conn *cp, u32 rtos)
.tos = rtos, } },
};
- if (ip_route_output_key(&rt, &fl)) {
+ if (ip_route_output_key(&init_net, &rt, &fl)) {
IP_VS_DBG_RL("ip_route_output error, dest: "
"%u.%u.%u.%u\n", NIPQUAD(cp->daddr));
return NULL;
@@ -129,7 +129,7 @@ ip_vs_dst_reset(struct ip_vs_dest *dest)
do { \
(skb)->ipvs_property = 1; \
skb_forward_csum(skb); \
- NF_HOOK(PF_INET, NF_IP_LOCAL_OUT, (skb), NULL, \
+ NF_HOOK(PF_INET, NF_INET_LOCAL_OUT, (skb), NULL, \
(rt)->u.dst.dev, dst_output); \
} while (0)
@@ -170,7 +170,7 @@ ip_vs_bypass_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
EnterFunction(10);
- if (ip_route_output_key(&rt, &fl)) {
+ if (ip_route_output_key(&init_net, &rt, &fl)) {
IP_VS_DBG_RL("ip_vs_bypass_xmit(): ip_route_output error, "
"dest: %u.%u.%u.%u\n", NIPQUAD(iph->daddr));
goto tx_error_icmp;
@@ -406,14 +406,12 @@ ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
iph->daddr = rt->rt_dst;
iph->saddr = rt->rt_src;
iph->ttl = old_iph->ttl;
- iph->tot_len = htons(skb->len);
ip_select_ident(iph, &rt->u.dst, NULL);
- ip_send_check(iph);
/* Another hack: avoid icmp_send in ip_fragment */
skb->local_df = 1;
- IP_VS_XMIT(skb, rt);
+ ip_local_out(skb);
LeaveFunction(10);