LVS
lvs-devel
Google
 
Web LinuxVirtualServer.org

[*v2 PATCH 16/22] IPVS: netns, connection hash got net as param.

To: <horms@xxxxxxxxxxxx>, <ja@xxxxxx>, <daniel.lezcano@xxxxxxx>, <wensong@xxxxxxxxxxxx>, <lvs-devel@xxxxxxxxxxxxxxx>, <netdev@xxxxxxxxxxxxxxx>, <netfilter-devel@xxxxxxxxxxxxxxx>
Subject: [*v2 PATCH 16/22] IPVS: netns, connection hash got net as param.
Cc: <hans@xxxxxxxxxxxxxxx>, Hans Schillstrom <hans.schillstrom@xxxxxxxxxxxx>
From: Hans Schillstrom <hans.schillstrom@xxxxxxxxxxxx>
Date: Mon, 13 Dec 2010 14:38:24 +0100
Connection hash table is now name space aware.
i.e. net ptr >> 8 is xor:ed to the hash,
and this is the first param to be compared.
The net struct is 0xa40 in size ( a little bit smaller for 32 bit arch:s)
and cache-line aligned, so a ptr >> 5 might be a more clever solution ?

All lookups where net is compared uses net_eq() which returns 1 when netns
is disabled, and the compiler seems to do something clever in that case.

ip_vs_conn_fill_param() have *net as first param now.

Three new inlines added to keep conn struct smaller
when names space is disabled.
- ip_vs_conn_net()
- ip_vs_conn_net_set()
- ip_vs_conn_net_eq()

Signed-off-by: Hans Schillstrom <hans.schillstrom@xxxxxxxxxxxx>
---
 include/net/ip_vs.h                     |   54 ++++++++---
 include/net/netns/ip_vs.h               |    2 +
 net/netfilter/ipvs/ip_vs_conn.c         |  165 ++++++++++++++++++-------------
 net/netfilter/ipvs/ip_vs_core.c         |   15 ++-
 net/netfilter/ipvs/ip_vs_ftp.c          |   14 ++-
 net/netfilter/ipvs/ip_vs_nfct.c         |    6 +-
 net/netfilter/ipvs/ip_vs_proto_ah_esp.c |   15 ++-
 net/netfilter/ipvs/ip_vs_proto_sctp.c   |    2 +-
 net/netfilter/ipvs/ip_vs_proto_tcp.c    |    2 +-
 net/netfilter/ipvs/ip_vs_proto_udp.c    |    2 +-
 net/netfilter/ipvs/ip_vs_sync.c         |   13 +--
 11 files changed, 177 insertions(+), 113 deletions(-)

diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index 848fcda..446e417 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -105,7 +105,6 @@ static inline struct net *seq_file_single_net(struct 
seq_file *seq)
 #endif
 }
 
-
 /* Connections' size value needed by ip_vs_ctl.c */
 extern int ip_vs_conn_tab_size;
 
@@ -460,6 +459,7 @@ extern struct ip_vs_proto_data * 
ip_vs_proto_data_get(struct net *net,
                                                      unsigned short proto);
 
 struct ip_vs_conn_param {
+       struct net *                    net;
        const union nf_inet_addr        *caddr;
        const union nf_inet_addr        *vaddr;
        __be16                          cport;
@@ -477,17 +477,19 @@ struct ip_vs_conn_param {
  */
 struct ip_vs_conn {
        struct list_head        c_list;         /* hashed list heads */
-
+#ifdef CONFIG_NET_NS
+       struct net              *net;           /* Name space */
+#endif
        /* Protocol, addresses and port numbers */
-       u16                      af;            /* address family */
-       union nf_inet_addr       caddr;          /* client address */
-       union nf_inet_addr       vaddr;          /* virtual address */
-       union nf_inet_addr       daddr;          /* destination address */
-       volatile __u32           flags;          /* status flags */
-       __u32                    fwmark;         /* Fire wall mark from skb */
-       __be16                   cport;
-       __be16                   vport;
-       __be16                   dport;
+       u16                     af;             /* address family */
+       __be16                  cport;
+       __be16                  vport;
+       __be16                  dport;
+       __u32                   fwmark;         /* Fire wall mark from skb */
+       union nf_inet_addr      caddr;          /* client address */
+       union nf_inet_addr      vaddr;          /* virtual address */
+       union nf_inet_addr      daddr;          /* destination address */
+       volatile __u32          flags;          /* status flags */
        __u16                   protocol;       /* Which protocol (TCP/UDP) */
 
        /* counter and timer */
@@ -530,6 +532,33 @@ struct ip_vs_conn {
        __u8                    pe_data_len;
 };
 
+/*
+ *  To save some memory in conn table when name space is disabled.
+ */
+static inline struct net *ip_vs_conn_net(const struct ip_vs_conn *cp)
+{
+#ifdef CONFIG_NET_NS
+       return cp->net;
+#else
+       return &init_net;
+#endif
+}
+static inline void ip_vs_conn_net_set(struct ip_vs_conn *cp, struct net *net)
+{
+#ifdef CONFIG_NET_NS
+       cp->net = net;
+#endif
+}
+
+static inline int ip_vs_conn_net_eq(const struct ip_vs_conn *cp,
+                                   struct net *net)
+{
+#ifdef CONFIG_NET_NS
+       return cp->net == net;
+#else
+       return 1;
+#endif
+}
 
 /*
  *     Extended internal versions of struct ip_vs_service_user and
@@ -779,13 +808,14 @@ enum {
        IP_VS_DIR_LAST,
 };
 
-static inline void ip_vs_conn_fill_param(int af, int protocol,
+static inline void ip_vs_conn_fill_param(struct net *net, int af, int protocol,
                                         const union nf_inet_addr *caddr,
                                         __be16 cport,
                                         const union nf_inet_addr *vaddr,
                                         __be16 vport,
                                         struct ip_vs_conn_param *p)
 {
+       p->net = net;
        p->af = af;
        p->protocol = protocol;
        p->caddr = caddr;
diff --git a/include/net/netns/ip_vs.h b/include/net/netns/ip_vs.h
index b6642f0..f2d5bcd 100644
--- a/include/net/netns/ip_vs.h
+++ b/include/net/netns/ip_vs.h
@@ -66,6 +66,8 @@ struct netns_ipvs {
        struct ip_vs_stats              *ctl_stats; /* Statistics & estimator */
        struct ip_vs_stats_user __percpu *ustats;   /* Statistics */
 
+       /* ip_vs_conn */
+       atomic_t                conn_count;         /*  connection counter */
        /* ip_vs_lblc */
        int                     sysctl_lblc_expiration;
        struct ctl_table_header *lblc_ctl_header;
diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c
index ef35e5d..41f93cc 100644
--- a/net/netfilter/ipvs/ip_vs_conn.c
+++ b/net/netfilter/ipvs/ip_vs_conn.c
@@ -64,9 +64,6 @@ static struct list_head *ip_vs_conn_tab __read_mostly;
 /*  SLAB cache for IPVS connections */
 static struct kmem_cache *ip_vs_conn_cachep __read_mostly;
 
-/*  counter for current IPVS connections */
-static atomic_t ip_vs_conn_count = ATOMIC_INIT(0);
-
 /*  counter for no client port connections */
 static atomic_t ip_vs_conn_no_cport_cnt = ATOMIC_INIT(0);
 
@@ -76,7 +73,7 @@ static unsigned int ip_vs_conn_rnd __read_mostly;
 /*
  *  Fine locking granularity for big connection hash table
  */
-#define CT_LOCKARRAY_BITS  4
+#define CT_LOCKARRAY_BITS  5
 #define CT_LOCKARRAY_SIZE  (1<<CT_LOCKARRAY_BITS)
 #define CT_LOCKARRAY_MASK  (CT_LOCKARRAY_SIZE-1)
 
@@ -133,19 +130,19 @@ static inline void ct_write_unlock_bh(unsigned key)
 /*
  *     Returns hash value for IPVS connection entry
  */
-static unsigned int ip_vs_conn_hashkey(int af, unsigned proto,
+static unsigned int ip_vs_conn_hashkey(struct net *net, int af, unsigned proto,
                                       const union nf_inet_addr *addr,
                                       __be16 port)
 {
 #ifdef CONFIG_IP_VS_IPV6
        if (af == AF_INET6)
-               return jhash_3words(jhash(addr, 16, ip_vs_conn_rnd),
-                                   (__force u32)port, proto, ip_vs_conn_rnd)
-                       & ip_vs_conn_tab_mask;
+               return (jhash_3words(jhash(addr, 16, ip_vs_conn_rnd),
+                                   (__force u32)port, proto, ip_vs_conn_rnd) ^
+                       ((size_t)net>>8)) & ip_vs_conn_tab_mask;
 #endif
-       return jhash_3words((__force u32)addr->ip, (__force u32)port, proto,
-                           ip_vs_conn_rnd)
-               & ip_vs_conn_tab_mask;
+       return (jhash_3words((__force u32)addr->ip, (__force u32)port, proto,
+                           ip_vs_conn_rnd) ^
+               ((size_t)net>>8)) & ip_vs_conn_tab_mask;
 }
 
 static unsigned int ip_vs_conn_hashkey_param(const struct ip_vs_conn_param *p,
@@ -166,15 +163,15 @@ static unsigned int ip_vs_conn_hashkey_param(const struct 
ip_vs_conn_param *p,
                port = p->vport;
        }
 
-       return ip_vs_conn_hashkey(p->af, p->protocol, addr, port);
+       return ip_vs_conn_hashkey(p->net, p->af, p->protocol, addr, port);
 }
 
 static unsigned int ip_vs_conn_hashkey_conn(const struct ip_vs_conn *cp)
 {
        struct ip_vs_conn_param p;
 
-       ip_vs_conn_fill_param(cp->af, cp->protocol, &cp->caddr, cp->cport,
-                             NULL, 0, &p);
+       ip_vs_conn_fill_param(ip_vs_conn_net(cp), cp->af, cp->protocol,
+                             &cp->caddr, cp->cport, NULL, 0, &p);
 
        if (cp->pe) {
                p.pe = cp->pe;
@@ -186,7 +183,7 @@ static unsigned int ip_vs_conn_hashkey_conn(const struct 
ip_vs_conn *cp)
 }
 
 /*
- *     Hashes ip_vs_conn in ip_vs_conn_tab by proto,addr,port.
+ *     Hashes ip_vs_conn in ip_vs_conn_tab by netns,proto,addr,port.
  *     returns bool success.
  */
 static inline int ip_vs_conn_hash(struct ip_vs_conn *cp)
@@ -268,10 +265,10 @@ __ip_vs_conn_in_get(const struct ip_vs_conn_param *p)
        ct_read_lock(hash);
 
        list_for_each_entry(cp, &ip_vs_conn_tab[hash], c_list) {
-               if (cp->af == p->af &&
+               if (ip_vs_conn_net_eq(cp, p->net) && cp->af == p->af &&
+                   p->cport == cp->cport && p->vport == cp->vport &&
                    ip_vs_addr_equal(p->af, p->caddr, &cp->caddr) &&
                    ip_vs_addr_equal(p->af, p->vaddr, &cp->vaddr) &&
-                   p->cport == cp->cport && p->vport == cp->vport &&
                    ((!p->cport) ^ (!(cp->flags & IP_VS_CONN_F_NO_CPORT))) &&
                    p->protocol == cp->protocol) {
                        /* HIT */
@@ -313,17 +310,18 @@ ip_vs_conn_fill_param_proto(int af, const struct sk_buff 
*skb,
                            struct ip_vs_conn_param *p)
 {
        __be16 _ports[2], *pptr;
+       struct net *net = skb_net(skb);
 
        pptr = skb_header_pointer(skb, proto_off, sizeof(_ports), _ports);
        if (pptr == NULL)
                return 1;
 
        if (likely(!inverse))
-               ip_vs_conn_fill_param(af, iph->protocol, &iph->saddr, pptr[0],
-                                     &iph->daddr, pptr[1], p);
+               ip_vs_conn_fill_param(net, af, iph->protocol, &iph->saddr,
+                                     pptr[0], &iph->daddr, pptr[1], p);
        else
-               ip_vs_conn_fill_param(af, iph->protocol, &iph->daddr, pptr[1],
-                                     &iph->saddr, pptr[0], p);
+               ip_vs_conn_fill_param(net, af, iph->protocol, &iph->daddr,
+                                     pptr[1], &iph->saddr, pptr[0], p);
        return 0;
 }
 
@@ -353,6 +351,8 @@ struct ip_vs_conn *ip_vs_ct_in_get(const struct 
ip_vs_conn_param *p)
        ct_read_lock(hash);
 
        list_for_each_entry(cp, &ip_vs_conn_tab[hash], c_list) {
+               if (!ip_vs_conn_net_eq(cp, p->net))
+                       continue;
                if (p->pe_data && p->pe->ct_match) {
                        if (p->pe == cp->pe && p->pe->ct_match(p, cp))
                                goto out;
@@ -403,10 +403,10 @@ struct ip_vs_conn *ip_vs_conn_out_get(const struct 
ip_vs_conn_param *p)
        ct_read_lock(hash);
 
        list_for_each_entry(cp, &ip_vs_conn_tab[hash], c_list) {
-               if (cp->af == p->af &&
+               if (ip_vs_conn_net_eq(cp, p->net) && cp->af == p->af &&
+                   p->vport == cp->cport && p->cport == cp->dport &&
                    ip_vs_addr_equal(p->af, p->vaddr, &cp->caddr) &&
                    ip_vs_addr_equal(p->af, p->caddr, &cp->daddr) &&
-                   p->vport == cp->cport && p->cport == cp->dport &&
                    p->protocol == cp->protocol) {
                        /* HIT */
                        atomic_inc(&cp->refcnt);
@@ -611,8 +611,8 @@ struct ip_vs_dest *ip_vs_try_bind_dest(struct ip_vs_conn 
*cp)
        struct ip_vs_dest *dest;
 
        if ((cp) && (!cp->dest)) {
-               dest = ip_vs_find_dest(&init_net, cp->af, &cp->daddr, cp->dport,
-                                      &cp->vaddr, cp->vport,
+               dest = ip_vs_find_dest(ip_vs_conn_net(cp), cp->af, &cp->daddr,
+                                      cp->dport, &cp->vaddr, cp->vport,
                                       cp->protocol, cp->fwmark);
                ip_vs_bind_dest(cp, dest);
                return dest;
@@ -730,6 +730,7 @@ int ip_vs_check_template(struct ip_vs_conn *ct)
 static void ip_vs_conn_expire(unsigned long data)
 {
        struct ip_vs_conn *cp = (struct ip_vs_conn *)data;
+       struct netns_ipvs *ipvs = net_ipvs(ip_vs_conn_net(cp));
 
        cp->timeout = 60*HZ;
 
@@ -772,7 +773,7 @@ static void ip_vs_conn_expire(unsigned long data)
                ip_vs_unbind_dest(cp);
                if (cp->flags & IP_VS_CONN_F_NO_CPORT)
                        atomic_dec(&ip_vs_conn_no_cport_cnt);
-               atomic_dec(&ip_vs_conn_count);
+               atomic_dec(&ipvs->conn_count);
 
                kmem_cache_free(ip_vs_conn_cachep, cp);
                return;
@@ -806,7 +807,9 @@ ip_vs_conn_new(const struct ip_vs_conn_param *p,
               struct ip_vs_dest *dest, __u32 fwmark)
 {
        struct ip_vs_conn *cp;
-       struct ip_vs_proto_data *pd = ip_vs_proto_data_get(&init_net, 
p->protocol);
+       struct netns_ipvs *ipvs = net_ipvs(p->net);
+       struct ip_vs_proto_data *pd = ip_vs_proto_data_get(p->net,
+                                                          p->protocol);
 
        cp = kmem_cache_zalloc(ip_vs_conn_cachep, GFP_ATOMIC);
        if (cp == NULL) {
@@ -816,6 +819,7 @@ ip_vs_conn_new(const struct ip_vs_conn_param *p,
 
        INIT_LIST_HEAD(&cp->c_list);
        setup_timer(&cp->timer, ip_vs_conn_expire, (unsigned long)cp);
+       ip_vs_conn_net_set(cp, p->net);
        cp->af             = p->af;
        cp->protocol       = p->protocol;
        ip_vs_addr_copy(p->af, &cp->caddr, p->caddr);
@@ -846,7 +850,7 @@ ip_vs_conn_new(const struct ip_vs_conn_param *p,
        atomic_set(&cp->n_control, 0);
        atomic_set(&cp->in_pkts, 0);
 
-       atomic_inc(&ip_vs_conn_count);
+       atomic_inc(&ipvs->conn_count);
        if (flags & IP_VS_CONN_F_NO_CPORT)
                atomic_inc(&ip_vs_conn_no_cport_cnt);
 
@@ -888,17 +892,22 @@ ip_vs_conn_new(const struct ip_vs_conn_param *p,
  *     /proc/net/ip_vs_conn entries
  */
 #ifdef CONFIG_PROC_FS
+struct ip_vs_iter_state {
+       struct seq_net_private p;
+       struct list_head *l;
+};
 
 static void *ip_vs_conn_array(struct seq_file *seq, loff_t pos)
 {
        int idx;
        struct ip_vs_conn *cp;
+       struct ip_vs_iter_state *iter = seq->private;
 
        for (idx = 0; idx < ip_vs_conn_tab_size; idx++) {
                ct_read_lock_bh(idx);
                list_for_each_entry(cp, &ip_vs_conn_tab[idx], c_list) {
                        if (pos-- == 0) {
-                               seq->private = &ip_vs_conn_tab[idx];
+                               iter->l = &ip_vs_conn_tab[idx];
                        return cp;
                        }
                }
@@ -910,14 +919,17 @@ static void *ip_vs_conn_array(struct seq_file *seq, 
loff_t pos)
 
 static void *ip_vs_conn_seq_start(struct seq_file *seq, loff_t *pos)
 {
-       seq->private = NULL;
+       struct ip_vs_iter_state *iter = seq->private;
+
+       iter->l = NULL;
        return *pos ? ip_vs_conn_array(seq, *pos - 1) :SEQ_START_TOKEN;
 }
 
 static void *ip_vs_conn_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 {
        struct ip_vs_conn *cp = v;
-       struct list_head *e, *l = seq->private;
+       struct ip_vs_iter_state *iter = seq->private;
+       struct list_head *e, *l = iter->l;
        int idx;
 
        ++*pos;
@@ -934,18 +946,19 @@ static void *ip_vs_conn_seq_next(struct seq_file *seq, 
void *v, loff_t *pos)
        while (++idx < ip_vs_conn_tab_size) {
                ct_read_lock_bh(idx);
                list_for_each_entry(cp, &ip_vs_conn_tab[idx], c_list) {
-                       seq->private = &ip_vs_conn_tab[idx];
+                       iter->l = &ip_vs_conn_tab[idx];
                        return cp;
                }
                ct_read_unlock_bh(idx);
        }
-       seq->private = NULL;
+       iter->l = NULL;
        return NULL;
 }
 
 static void ip_vs_conn_seq_stop(struct seq_file *seq, void *v)
 {
-       struct list_head *l = seq->private;
+       struct ip_vs_iter_state *iter = seq->private;
+       struct list_head *l = iter->l;
 
        if (l)
                ct_read_unlock_bh(l - ip_vs_conn_tab);
@@ -959,9 +972,12 @@ static int ip_vs_conn_seq_show(struct seq_file *seq, void 
*v)
    "Pro FromIP   FPrt ToIP     TPrt DestIP   DPrt State       Expires PEName 
PEData\n");
        else {
                const struct ip_vs_conn *cp = v;
+               struct net *net = seq_file_net(seq);
                char pe_data[IP_VS_PENAME_MAXLEN + IP_VS_PEDATA_MAXLEN + 3];
                size_t len = 0;
 
+               if (!ip_vs_conn_net_eq(cp, net))
+                       return 0;
                if (cp->pe_data) {
                        pe_data[0] = ' ';
                        len = strlen(cp->pe->name);
@@ -1006,7 +1022,8 @@ static const struct seq_operations ip_vs_conn_seq_ops = {
 
 static int ip_vs_conn_open(struct inode *inode, struct file *file)
 {
-       return seq_open(file, &ip_vs_conn_seq_ops);
+       return seq_open_net(inode, file, &ip_vs_conn_seq_ops,
+                           sizeof(struct ip_vs_iter_state));
 }
 
 static const struct file_operations ip_vs_conn_fops = {
@@ -1033,6 +1050,10 @@ static int ip_vs_conn_sync_seq_show(struct seq_file 
*seq, void *v)
    "Pro FromIP   FPrt ToIP     TPrt DestIP   DPrt State       Origin 
Expires\n");
        else {
                const struct ip_vs_conn *cp = v;
+               struct net *net = seq_file_net(seq);
+
+               if (!ip_vs_conn_net_eq(cp, net))
+                       return 0;
 
 #ifdef CONFIG_IP_VS_IPV6
                if (cp->af == AF_INET6)
@@ -1069,7 +1090,8 @@ static const struct seq_operations 
ip_vs_conn_sync_seq_ops = {
 
 static int ip_vs_conn_sync_open(struct inode *inode, struct file *file)
 {
-       return seq_open(file, &ip_vs_conn_sync_seq_ops);
+       return seq_open_net(inode, file, &ip_vs_conn_sync_seq_ops,
+                           sizeof(struct ip_vs_iter_state));
 }
 
 static const struct file_operations ip_vs_conn_sync_fops = {
@@ -1170,10 +1192,11 @@ void ip_vs_random_dropentry(void)
 /*
  *      Flush all the connection entries in the ip_vs_conn_tab
  */
-static void ip_vs_conn_flush(void)
+static void ip_vs_conn_flush(struct net *net)
 {
        int idx;
        struct ip_vs_conn *cp;
+       struct netns_ipvs *ipvs = net_ipvs(net);
 
   flush_again:
        for (idx = 0; idx < ip_vs_conn_tab_size; idx++) {
@@ -1183,7 +1206,8 @@ static void ip_vs_conn_flush(void)
                ct_write_lock_bh(idx);
 
                list_for_each_entry(cp, &ip_vs_conn_tab[idx], c_list) {
-
+                       if (!ip_vs_conn_net_eq(cp, net))
+                               continue;
                        IP_VS_DBG(4, "del connection\n");
                        ip_vs_conn_expire_now(cp);
                        if (cp->control) {
@@ -1196,7 +1220,7 @@ static void ip_vs_conn_flush(void)
 
        /* the counter may be not NULL, because maybe some conn entries
           are run by slow timer handler or unhashed but still referred */
-       if (atomic_read(&ip_vs_conn_count) != 0) {
+       if (atomic_read(&ipvs->conn_count) != 0) {
                schedule();
                goto flush_again;
        }
@@ -1204,14 +1228,37 @@ static void ip_vs_conn_flush(void)
 
 int __net_init __ip_vs_conn_init(struct net *net)
 {
-       int idx;
+       struct netns_ipvs *ipvs = net_ipvs(net);
 
        if (!net_eq(net, &init_net))    /* netns not enabled yet */
                return -EPERM;
+       atomic_set(&ipvs->conn_count, 0);
 
-       /* Compute size and mask */
-       ip_vs_conn_tab_size = 1 << ip_vs_conn_tab_bits;
-       ip_vs_conn_tab_mask = ip_vs_conn_tab_size - 1;
+       proc_net_fops_create(net, "ip_vs_conn", 0, &ip_vs_conn_fops);
+       proc_net_fops_create(net, "ip_vs_conn_sync", 0, &ip_vs_conn_sync_fops);
+
+       return 0;
+}
+/* Cleanup and release all netns related ... */
+static void __net_exit __ip_vs_conn_cleanup(struct net *net)
+{
+       if (!net_eq(net, &init_net))    /* netns not enabled yet */
+               return;
+
+       /* flush all the connection entries first */
+       ip_vs_conn_flush(net);
+       proc_net_remove(net, "ip_vs_conn");
+       proc_net_remove(net, "ip_vs_conn_sync");
+}
+static struct pernet_operations ipvs_conn_ops = {
+       .init = __ip_vs_conn_init,
+       .exit = __ip_vs_conn_cleanup,
+};
+
+int __init ip_vs_conn_init(void)
+{
+       int rv;
+       int idx;
 
        /* Compute size and mask */
        ip_vs_conn_tab_size = 1 << ip_vs_conn_tab_bits;
@@ -1249,34 +1296,6 @@ int __net_init __ip_vs_conn_init(struct net *net)
                rwlock_init(&__ip_vs_conntbl_lock_array[idx].l);
        }
 
-       proc_net_fops_create(net, "ip_vs_conn", 0, &ip_vs_conn_fops);
-       proc_net_fops_create(net, "ip_vs_conn_sync", 0, &ip_vs_conn_sync_fops);
-
-       return 0;
-}
-/* Cleanup and release all netns related ... */
-static void __net_exit __ip_vs_conn_cleanup(struct net *net)
-{
-       if (!net_eq(net, &init_net))    /* netns not enabled yet */
-               return;
-
-       /* flush all the connection entries first */
-       ip_vs_conn_flush();
-       /* Release the empty cache */
-       kmem_cache_destroy(ip_vs_conn_cachep);
-       proc_net_remove(net, "ip_vs_conn");
-       proc_net_remove(net, "ip_vs_conn_sync");
-       vfree(ip_vs_conn_tab);
-}
-static struct pernet_operations ipvs_conn_ops = {
-       .init = __ip_vs_conn_init,
-       .exit = __ip_vs_conn_cleanup,
-};
-
-int __init ip_vs_conn_init(void)
-{
-       int rv;
-
        rv = register_pernet_subsys(&ipvs_conn_ops);
 
        /* calculate the random value for connection hash */
@@ -1287,4 +1306,8 @@ int __init ip_vs_conn_init(void)
 void ip_vs_conn_cleanup(void)
 {
        unregister_pernet_subsys(&ipvs_conn_ops);
+       /* Release the empty cache */
+       kmem_cache_destroy(ip_vs_conn_cachep);
+       vfree(ip_vs_conn_tab);
+
 }
diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
index 679eb16..69ba8cc 100644
--- a/net/netfilter/ipvs/ip_vs_core.c
+++ b/net/netfilter/ipvs/ip_vs_core.c
@@ -193,7 +193,8 @@ ip_vs_conn_fill_param_persist(const struct ip_vs_service 
*svc,
                              const union nf_inet_addr *vaddr, __be16 vport,
                              struct ip_vs_conn_param *p)
 {
-       ip_vs_conn_fill_param(svc->af, protocol, caddr, cport, vaddr, vport, p);
+       ip_vs_conn_fill_param(svc->net, svc->af, protocol, caddr, cport, vaddr,
+                             vport, p);
        p->pe = svc->pe;
        if (p->pe && p->pe->fill_param)
                return p->pe->fill_param(p, skb);
@@ -336,8 +337,8 @@ ip_vs_sched_persist(struct ip_vs_service *svc,
        /*
         *    Create a new connection according to the template
         */
-       ip_vs_conn_fill_param(svc->af, iph.protocol, &iph.saddr, src_port,
-                             &iph.daddr, dst_port, &param);
+       ip_vs_conn_fill_param(svc->net, svc->af, iph.protocol, &iph.saddr,
+                             src_port, &iph.daddr, dst_port, &param);
 
        cp = ip_vs_conn_new(&param, &dest->addr, dport, flags, dest, skb->mark);
        if (cp == NULL) {
@@ -451,8 +452,10 @@ ip_vs_schedule(struct ip_vs_service *svc, struct sk_buff 
*skb,
         */
        {
                struct ip_vs_conn_param p;
-               ip_vs_conn_fill_param(svc->af, iph.protocol, &iph.saddr,
-                                     pptr[0], &iph.daddr, pptr[1], &p);
+
+               ip_vs_conn_fill_param(svc->net, svc->af, iph.protocol,
+                                     &iph.saddr, pptr[0], &iph.daddr, pptr[1],
+                                     &p);
                cp = ip_vs_conn_new(&p, &dest->addr,
                                    dest->port ? dest->port : pptr[1],
                                    flags, dest, skb->mark);
@@ -518,7 +521,7 @@ int ip_vs_leave(struct ip_vs_service *svc, struct sk_buff 
*skb,
                IP_VS_DBG(6, "%s(): create a cache_bypass entry\n", __func__);
                {
                        struct ip_vs_conn_param p;
-                       ip_vs_conn_fill_param(svc->af, iph.protocol,
+                       ip_vs_conn_fill_param(svc->net, svc->af, iph.protocol,
                                              &iph.saddr, pptr[0],
                                              &iph.daddr, pptr[1], &p);
                        cp = ip_vs_conn_new(&p, &daddr, 0,
diff --git a/net/netfilter/ipvs/ip_vs_ftp.c b/net/netfilter/ipvs/ip_vs_ftp.c
index b39befd..78d5980 100644
--- a/net/netfilter/ipvs/ip_vs_ftp.c
+++ b/net/netfilter/ipvs/ip_vs_ftp.c
@@ -198,13 +198,15 @@ static int ip_vs_ftp_out(struct ip_vs_app *app, struct 
ip_vs_conn *cp,
                 */
                {
                        struct ip_vs_conn_param p;
-                       ip_vs_conn_fill_param(AF_INET, iph->protocol,
-                                             &from, port, &cp->caddr, 0, &p);
+                       ip_vs_conn_fill_param(ip_vs_conn_net(cp), AF_INET,
+                                             iph->protocol, &from, port,
+                                             &cp->caddr, 0, &p);
                        n_cp = ip_vs_conn_out_get(&p);
                }
                if (!n_cp) {
                        struct ip_vs_conn_param p;
-                       ip_vs_conn_fill_param(AF_INET, IPPROTO_TCP, &cp->caddr,
+                       ip_vs_conn_fill_param(ip_vs_conn_net(cp),
+                                             AF_INET, IPPROTO_TCP, &cp->caddr,
                                              0, &cp->vaddr, port, &p);
                        n_cp = ip_vs_conn_new(&p, &from, port,
                                              IP_VS_CONN_F_NO_CPORT |
@@ -360,9 +362,9 @@ static int ip_vs_ftp_in(struct ip_vs_app *app, struct 
ip_vs_conn *cp,
 
        {
                struct ip_vs_conn_param p;
-               ip_vs_conn_fill_param(AF_INET, iph->protocol, &to, port,
-                                     &cp->vaddr, htons(ntohs(cp->vport)-1),
-                                     &p);
+               ip_vs_conn_fill_param(ip_vs_conn_net(cp), AF_INET,
+                                     iph->protocol, &to, port, &cp->vaddr,
+                                     htons(ntohs(cp->vport)-1), &p);
                n_cp = ip_vs_conn_in_get(&p);
                if (!n_cp) {
                        n_cp = ip_vs_conn_new(&p, &cp->daddr,
diff --git a/net/netfilter/ipvs/ip_vs_nfct.c b/net/netfilter/ipvs/ip_vs_nfct.c
index 4680647..f454c80 100644
--- a/net/netfilter/ipvs/ip_vs_nfct.c
+++ b/net/netfilter/ipvs/ip_vs_nfct.c
@@ -141,6 +141,7 @@ static void ip_vs_nfct_expect_callback(struct nf_conn *ct,
        struct nf_conntrack_tuple *orig, new_reply;
        struct ip_vs_conn *cp;
        struct ip_vs_conn_param p;
+       struct net *net = nf_ct_net(ct);
 
        if (exp->tuple.src.l3num != PF_INET)
                return;
@@ -155,7 +156,7 @@ static void ip_vs_nfct_expect_callback(struct nf_conn *ct,
 
        /* RS->CLIENT */
        orig = &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple;
-       ip_vs_conn_fill_param(exp->tuple.src.l3num, orig->dst.protonum,
+       ip_vs_conn_fill_param(net, exp->tuple.src.l3num, orig->dst.protonum,
                              &orig->src.u3, orig->src.u.tcp.port,
                              &orig->dst.u3, orig->dst.u.tcp.port, &p);
        cp = ip_vs_conn_out_get(&p);
@@ -268,7 +269,8 @@ void ip_vs_conn_drop_conntrack(struct ip_vs_conn *cp)
                " for conn " FMT_CONN "\n",
                __func__, ARG_TUPLE(&tuple), ARG_CONN(cp));
 
-       h = nf_conntrack_find_get(&init_net, NF_CT_DEFAULT_ZONE, &tuple);
+       h = nf_conntrack_find_get(ip_vs_conn_net(cp), NF_CT_DEFAULT_ZONE,
+                                 &tuple);
        if (h) {
                ct = nf_ct_tuplehash_to_ctrack(h);
                /* Show what happens instead of calling nf_ct_kill() */
diff --git a/net/netfilter/ipvs/ip_vs_proto_ah_esp.c 
b/net/netfilter/ipvs/ip_vs_proto_ah_esp.c
index b8b37fa..ded1adb 100644
--- a/net/netfilter/ipvs/ip_vs_proto_ah_esp.c
+++ b/net/netfilter/ipvs/ip_vs_proto_ah_esp.c
@@ -41,15 +41,16 @@ struct isakmp_hdr {
 #define PORT_ISAKMP    500
 
 static void
-ah_esp_conn_fill_param_proto(int af, const struct ip_vs_iphdr *iph,
-                            int inverse, struct ip_vs_conn_param *p)
+ah_esp_conn_fill_param_proto(struct net *net, int af,
+                            const struct ip_vs_iphdr *iph, int inverse,
+                            struct ip_vs_conn_param *p)
 {
        if (likely(!inverse))
-               ip_vs_conn_fill_param(af, IPPROTO_UDP,
+               ip_vs_conn_fill_param(net, af, IPPROTO_UDP,
                                      &iph->saddr, htons(PORT_ISAKMP),
                                      &iph->daddr, htons(PORT_ISAKMP), p);
        else
-               ip_vs_conn_fill_param(af, IPPROTO_UDP,
+               ip_vs_conn_fill_param(net, af, IPPROTO_UDP,
                                      &iph->daddr, htons(PORT_ISAKMP),
                                      &iph->saddr, htons(PORT_ISAKMP), p);
 }
@@ -61,8 +62,9 @@ ah_esp_conn_in_get(int af, const struct sk_buff *skb, struct 
ip_vs_protocol *pp,
 {
        struct ip_vs_conn *cp;
        struct ip_vs_conn_param p;
+       struct net *net = skb_net(skb);
 
-       ah_esp_conn_fill_param_proto(af, iph, inverse, &p);
+       ah_esp_conn_fill_param_proto(net, af, iph, inverse, &p);
        cp = ip_vs_conn_in_get(&p);
        if (!cp) {
                /*
@@ -90,8 +92,9 @@ ah_esp_conn_out_get(int af, const struct sk_buff *skb,
 {
        struct ip_vs_conn *cp;
        struct ip_vs_conn_param p;
+       struct net *net = skb_net(skb);
 
-       ah_esp_conn_fill_param_proto(af, iph, inverse, &p);
+       ah_esp_conn_fill_param_proto(net, af, iph, inverse, &p);
        cp = ip_vs_conn_out_get(&p);
        if (!cp) {
                IP_VS_DBG_BUF(12, "Unknown ISAKMP entry for inout packet "
diff --git a/net/netfilter/ipvs/ip_vs_proto_sctp.c 
b/net/netfilter/ipvs/ip_vs_proto_sctp.c
index 3c6d06d..c011830 100644
--- a/net/netfilter/ipvs/ip_vs_proto_sctp.c
+++ b/net/netfilter/ipvs/ip_vs_proto_sctp.c
@@ -1064,7 +1064,7 @@ static void sctp_unregister_app(struct net *net, struct 
ip_vs_app *inc)
 
 static int sctp_app_conn_bind(struct ip_vs_conn *cp)
 {
-       struct netns_ipvs *ipvs = net_ipvs(&init_net);
+       struct netns_ipvs *ipvs = net_ipvs(ip_vs_conn_net(cp));
        int hash;
        struct ip_vs_app *inc;
        int result = 0;
diff --git a/net/netfilter/ipvs/ip_vs_proto_tcp.c 
b/net/netfilter/ipvs/ip_vs_proto_tcp.c
index 326768d..2e270b6 100644
--- a/net/netfilter/ipvs/ip_vs_proto_tcp.c
+++ b/net/netfilter/ipvs/ip_vs_proto_tcp.c
@@ -626,7 +626,7 @@ tcp_unregister_app(struct net *net, struct ip_vs_app *inc)
 static int
 tcp_app_conn_bind(struct ip_vs_conn *cp)
 {
-       struct netns_ipvs *ipvs = net_ipvs(&init_net);
+       struct netns_ipvs *ipvs = net_ipvs(ip_vs_conn_net(cp));
        int hash;
        struct ip_vs_app *inc;
        int result = 0;
diff --git a/net/netfilter/ipvs/ip_vs_proto_udp.c 
b/net/netfilter/ipvs/ip_vs_proto_udp.c
index 7e894d5..882a547 100644
--- a/net/netfilter/ipvs/ip_vs_proto_udp.c
+++ b/net/netfilter/ipvs/ip_vs_proto_udp.c
@@ -396,7 +396,7 @@ udp_unregister_app(struct net *net, struct ip_vs_app *inc)
 
 static int udp_app_conn_bind(struct ip_vs_conn *cp)
 {
-       struct netns_ipvs *ipvs = net_ipvs(&init_net);
+       struct netns_ipvs *ipvs = net_ipvs(ip_vs_conn_net(cp));
        int hash;
        struct ip_vs_app *inc;
        int result = 0;
diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c
index 29c6bbb..2887c34 100644
--- a/net/netfilter/ipvs/ip_vs_sync.c
+++ b/net/netfilter/ipvs/ip_vs_sync.c
@@ -657,21 +657,21 @@ control:
  *  fill_param used by version 1
  */
 static inline int
-ip_vs_conn_fill_param_sync(int af, union ip_vs_sync_conn *sc,
+ip_vs_conn_fill_param_sync(struct net *net, int af, union ip_vs_sync_conn *sc,
                           struct ip_vs_conn_param *p,
                           __u8 *pe_data, unsigned int pe_data_len,
                           __u8 *pe_name, unsigned int pe_name_len)
 {
 #ifdef CONFIG_IP_VS_IPV6
        if (af == AF_INET6)
-               ip_vs_conn_fill_param(af, sc->v6.protocol,
+               ip_vs_conn_fill_param(net, af, sc->v6.protocol,
                                      (const union nf_inet_addr *)&sc->v6.caddr,
                                      sc->v6.cport,
                                      (const union nf_inet_addr *)&sc->v6.vaddr,
                                      sc->v6.vport, p);
        else
 #endif
-               ip_vs_conn_fill_param(af, sc->v4.protocol,
+               ip_vs_conn_fill_param(net, af, sc->v4.protocol,
                                      (const union nf_inet_addr *)&sc->v4.caddr,
                                      sc->v4.cport,
                                      (const union nf_inet_addr *)&sc->v4.vaddr,
@@ -878,7 +878,7 @@ static void ip_vs_process_message_v0(struct net *net, const 
char *buffer,
                        }
                }
 
-               ip_vs_conn_fill_param(AF_INET, s->protocol,
+               ip_vs_conn_fill_param(net, AF_INET, s->protocol,
                                      (const union nf_inet_addr *)&s->caddr,
                                      s->cport,
                                      (const union nf_inet_addr *)&s->vaddr,
@@ -1040,9 +1040,8 @@ static inline int ip_vs_proc_sync_conn(struct net *net, 
__u8 *p, __u8 *msg_end)
                        state = 0;
                }
        }
-       if (ip_vs_conn_fill_param_sync(af, s, &param,
-                                       pe_data, pe_data_len,
-                                       pe_name, pe_name_len)) {
+       if (ip_vs_conn_fill_param_sync(net, af, s, &param, pe_data,
+                                      pe_data_len, pe_name, pe_name_len)) {
                retc = 50;
                goto out;
        }
-- 
1.7.2.3

--
To unsubscribe from this list: send the line "unsubscribe lvs-devel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html

<Prev in Thread] Current Thread [Next in Thread>