| Message ID | 201010081316.57914.hans.schillstrom@ericsson.com |
|---|---|
| State | Not Applicable, archived |
| Delegated to: | David Miller |
| Headers | show |
On Fri, Oct 08, 2010 at 01:16:57PM +0200, Hans Schillstrom wrote: > > This patch just contains ip_vs_conn.c > and does the normal > - moving to vars to struct ipvs > - adding per netns init and exit > > proc_fs required some extra work with adding/chaning private data to get the net ptr. I am currently working on rebasing this patch against the current nf-next-2.6 tree with includes persistence engines and I noticed a few things. > Signed-off-by:Hans Schillstrom <hans.schillstrom@ericsson.com> > > diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c > index b71c69a..c47828f 100644 > --- a/net/netfilter/ipvs/ip_vs_conn.c > +++ b/net/netfilter/ipvs/ip_vs_conn.c > @@ -47,7 +47,7 @@ > > /* > * Connection hash size. Default is what was selected at compile time. > -*/ > + */ > int ip_vs_conn_tab_bits = CONFIG_IP_VS_TAB_BITS; > module_param_named(conn_tab_bits, ip_vs_conn_tab_bits, int, 0444); > MODULE_PARM_DESC(conn_tab_bits, "Set connections' hash size"); This fragment is not needed. > @@ -56,23 +56,12 @@ MODULE_PARM_DESC(conn_tab_bits, "Set connections' hash size"); > int ip_vs_conn_tab_size; > int ip_vs_conn_tab_mask; > > -/* > - * Connection hash table: for input and output packets lookups of IPVS > - */ > -static struct list_head *ip_vs_conn_tab; > - > -/* 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); > - > /* random value for IPVS connection hash */ > static unsigned int ip_vs_conn_rnd; > > +/* cache name cnt */ > +static atomic_t conn_cache_nr = ATOMIC_INIT(0); > + > /* > * Fine locking granularity for big connection hash table > */ > @@ -153,7 +142,7 @@ static unsigned int ip_vs_conn_hashkey(int af, unsigned proto, > * Hashes ip_vs_conn in ip_vs_conn_tab by proto,addr,port. > * returns bool success. > */ > -static inline int ip_vs_conn_hash(struct ip_vs_conn *cp) > +static inline int ip_vs_conn_hash(struct net *net, struct ip_vs_conn *cp) > { > unsigned hash; > int ret; > @@ -168,7 +157,7 @@ static inline int ip_vs_conn_hash(struct ip_vs_conn *cp) > spin_lock(&cp->lock); > > if (!(cp->flags & IP_VS_CONN_F_HASHED)) { > - list_add(&cp->c_list, &ip_vs_conn_tab[hash]); > + list_add(&cp->c_list, &net->ipvs->conn_tab[hash]); > cp->flags |= IP_VS_CONN_F_HASHED; > atomic_inc(&cp->refcnt); > ret = 1; > @@ -221,18 +210,20 @@ static inline int ip_vs_conn_unhash(struct ip_vs_conn *cp) > * s_addr, s_port: pkt source address (foreign host) > * d_addr, d_port: pkt dest address (load balancer) > */ > -static inline struct ip_vs_conn *__ip_vs_conn_in_get > -(int af, int protocol, const union nf_inet_addr *s_addr, __be16 s_port, > - const union nf_inet_addr *d_addr, __be16 d_port) > +static inline struct ip_vs_conn * > +__ip_vs_conn_in_get(struct net *net, int af, int protocol, > + const union nf_inet_addr *s_addr, __be16 s_port, > + const union nf_inet_addr *d_addr, __be16 d_port) > { > unsigned hash; > struct ip_vs_conn *cp; > + struct netns_ipvs *ipvs = net->ipvs; > > hash = ip_vs_conn_hashkey(af, protocol, s_addr, s_port); > > ct_read_lock(hash); > > - list_for_each_entry(cp, &ip_vs_conn_tab[hash], c_list) { > + list_for_each_entry(cp, &ipvs->conn_tab[hash], c_list) { > if (cp->af == af && > ip_vs_addr_equal(af, s_addr, &cp->caddr) && > ip_vs_addr_equal(af, d_addr, &cp->vaddr) && > @@ -251,16 +242,18 @@ static inline struct ip_vs_conn *__ip_vs_conn_in_get > return NULL; > } > > -struct ip_vs_conn *ip_vs_conn_in_get > -(int af, int protocol, const union nf_inet_addr *s_addr, __be16 s_port, > - const union nf_inet_addr *d_addr, __be16 d_port) > +struct ip_vs_conn * > +ip_vs_conn_in_get(struct net *net, int af, int protocol, > + const union nf_inet_addr *s_addr, __be16 s_port, > + const union nf_inet_addr *d_addr, __be16 d_port) > { > struct ip_vs_conn *cp; > > - cp = __ip_vs_conn_in_get(af, protocol, s_addr, s_port, d_addr, d_port); > - if (!cp && atomic_read(&ip_vs_conn_no_cport_cnt)) > - cp = __ip_vs_conn_in_get(af, protocol, s_addr, 0, d_addr, > - d_port); > + cp = __ip_vs_conn_in_get(net, af, protocol, > + s_addr, s_port, d_addr, d_port); > + if (!cp && atomic_read(&net->ipvs->conn_no_cport_cnt)) > + cp = __ip_vs_conn_in_get(net, af, protocol, > + s_addr, 0, d_addr, d_port); > > IP_VS_DBG_BUF(9, "lookup/in %s %s:%d->%s:%d %s\n", > ip_vs_proto_name(protocol), > @@ -278,35 +271,41 @@ ip_vs_conn_in_get_proto(int af, const struct sk_buff *skb, > unsigned int proto_off, int inverse) > { > __be16 _ports[2], *pptr; > + struct net *net = dev_net(skb->dev); > > pptr = skb_header_pointer(skb, proto_off, sizeof(_ports), _ports); > if (pptr == NULL) > return NULL; > > + BUG_ON(!net); Can you explain why BUG_ON is here? > if (likely(!inverse)) > - return ip_vs_conn_in_get(af, iph->protocol, > + return ip_vs_conn_in_get(net, af, iph->protocol, > &iph->saddr, pptr[0], > &iph->daddr, pptr[1]); > else > - return ip_vs_conn_in_get(af, iph->protocol, > + return ip_vs_conn_in_get(net, af, iph->protocol, > &iph->daddr, pptr[1], > &iph->saddr, pptr[0]); > } > EXPORT_SYMBOL_GPL(ip_vs_conn_in_get_proto); > > -/* Get reference to connection template */ > -struct ip_vs_conn *ip_vs_ct_in_get > -(int af, int protocol, const union nf_inet_addr *s_addr, __be16 s_port, > - const union nf_inet_addr *d_addr, __be16 d_port) > +/* > + * Get reference to connection template > + */ > +struct ip_vs_conn * > +ip_vs_ct_in_get(struct net *net, int af, int protocol, > + const union nf_inet_addr *s_addr, __be16 s_port, > + const union nf_inet_addr *d_addr, __be16 d_port) > { > unsigned hash; > struct ip_vs_conn *cp; > + struct netns_ipvs *ipvs = net->ipvs; > > hash = ip_vs_conn_hashkey(af, protocol, s_addr, s_port); > > ct_read_lock(hash); > > - list_for_each_entry(cp, &ip_vs_conn_tab[hash], c_list) { > + list_for_each_entry(cp, &ipvs->conn_tab[hash], c_list) { > if (cp->af == af && > ip_vs_addr_equal(af, s_addr, &cp->caddr) && > /* protocol should only be IPPROTO_IP if > @@ -341,12 +340,14 @@ struct ip_vs_conn *ip_vs_ct_in_get > * s_addr, s_port: pkt source address (inside host) > * d_addr, d_port: pkt dest address (foreign host) > */ > -struct ip_vs_conn *ip_vs_conn_out_get > -(int af, int protocol, const union nf_inet_addr *s_addr, __be16 s_port, > - const union nf_inet_addr *d_addr, __be16 d_port) > +struct ip_vs_conn * > +ip_vs_conn_out_get(struct net *net, int af, int protocol, > + const union nf_inet_addr *s_addr, __be16 s_port, > + const union nf_inet_addr *d_addr, __be16 d_port) > { > unsigned hash; > struct ip_vs_conn *cp, *ret=NULL; > + struct netns_ipvs *ipvs = net->ipvs; > > /* > * Check for "full" addressed entries > @@ -355,7 +356,7 @@ struct ip_vs_conn *ip_vs_conn_out_get > > ct_read_lock(hash); > > - list_for_each_entry(cp, &ip_vs_conn_tab[hash], c_list) { > + list_for_each_entry(cp, &ipvs->conn_tab[hash], c_list) { > if (cp->af == af && > ip_vs_addr_equal(af, d_addr, &cp->caddr) && > ip_vs_addr_equal(af, s_addr, &cp->daddr) && > @@ -386,17 +387,19 @@ ip_vs_conn_out_get_proto(int af, const struct sk_buff *skb, > unsigned int proto_off, int inverse) > { > __be16 _ports[2], *pptr; > + struct net *net = dev_net(skb->dev); > > pptr = skb_header_pointer(skb, proto_off, sizeof(_ports), _ports); > if (pptr == NULL) > return NULL; > > + BUG_ON(!net); > if (likely(!inverse)) > - return ip_vs_conn_out_get(af, iph->protocol, > + return ip_vs_conn_out_get(net, af, iph->protocol, > &iph->saddr, pptr[0], > &iph->daddr, pptr[1]); > else > - return ip_vs_conn_out_get(af, iph->protocol, > + return ip_vs_conn_out_get(net, af, iph->protocol, > &iph->daddr, pptr[1], > &iph->saddr, pptr[0]); > } > @@ -408,7 +411,7 @@ EXPORT_SYMBOL_GPL(ip_vs_conn_out_get_proto); > void ip_vs_conn_put(struct ip_vs_conn *cp) > { > unsigned long t = (cp->flags & IP_VS_CONN_F_ONE_PACKET) ? > - 0 : cp->timeout; > + 0 : cp->timeout; > mod_timer(&cp->timer, jiffies+t); > > __ip_vs_conn_put(cp); > @@ -418,19 +421,19 @@ void ip_vs_conn_put(struct ip_vs_conn *cp) > /* > * Fill a no_client_port connection with a client port number > */ > -void ip_vs_conn_fill_cport(struct ip_vs_conn *cp, __be16 cport) > +void ip_vs_conn_fill_cport(struct net *net, struct ip_vs_conn *cp, __be16 cport) > { > if (ip_vs_conn_unhash(cp)) { > spin_lock(&cp->lock); > if (cp->flags & IP_VS_CONN_F_NO_CPORT) { > - atomic_dec(&ip_vs_conn_no_cport_cnt); > + atomic_dec(&net->ipvs->conn_no_cport_cnt); > cp->flags &= ~IP_VS_CONN_F_NO_CPORT; > cp->cport = cport; > } > spin_unlock(&cp->lock); > > /* hash on new dport */ > - ip_vs_conn_hash(cp); > + ip_vs_conn_hash(net, cp); > } > } > > @@ -561,12 +564,12 @@ ip_vs_bind_dest(struct ip_vs_conn *cp, struct ip_vs_dest *dest) > * Check if there is a destination for the connection, if so > * bind the connection to the destination. > */ > -struct ip_vs_dest *ip_vs_try_bind_dest(struct ip_vs_conn *cp) > +struct ip_vs_dest *ip_vs_try_bind_dest(struct net *net, struct ip_vs_conn *cp) > { > struct ip_vs_dest *dest; > > if ((cp) && (!cp->dest)) { > - dest = ip_vs_find_dest(cp->af, &cp->daddr, cp->dport, > + dest = ip_vs_find_dest(net, cp->af, &cp->daddr, cp->dport, > &cp->vaddr, cp->vport, > cp->protocol); > ip_vs_bind_dest(cp, dest); > @@ -638,7 +641,7 @@ static inline void ip_vs_unbind_dest(struct ip_vs_conn *cp) > * If available, return 1, otherwise invalidate this connection > * template and return 0. > */ > -int ip_vs_check_template(struct ip_vs_conn *ct) > +int ip_vs_check_template(struct net *net, struct ip_vs_conn *ct) > { > struct ip_vs_dest *dest = ct->dest; > > @@ -647,7 +650,7 @@ int ip_vs_check_template(struct ip_vs_conn *ct) > */ > if ((dest == NULL) || > !(dest->flags & IP_VS_DEST_F_AVAILABLE) || > - (sysctl_ip_vs_expire_quiescent_template && > + (net->ipvs->sysctl_expire_quiescent_template && > (atomic_read(&dest->weight) == 0))) { > IP_VS_DBG_BUF(9, "check_template: dest not available for " > "protocol %s s:%s:%d v:%s:%d " > @@ -668,7 +671,7 @@ int ip_vs_check_template(struct ip_vs_conn *ct) > ct->dport = htons(0xffff); > ct->vport = htons(0xffff); > ct->cport = 0; > - ip_vs_conn_hash(ct); > + ip_vs_conn_hash(net, ct); > } > } > > @@ -720,16 +723,17 @@ static void ip_vs_conn_expire(unsigned long data) > if (unlikely(cp->app != NULL)) > ip_vs_unbind_app(cp); > ip_vs_unbind_dest(cp); > + BUG_ON(!cp->net); > 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(&cp->net->ipvs->conn_no_cport_cnt); > + atomic_dec(&cp->net->ipvs->conn_count); > > - kmem_cache_free(ip_vs_conn_cachep, cp); > + kmem_cache_free(cp->net->ipvs->conn_cachep, cp); > return; > } > > /* hash it back to the table */ > - ip_vs_conn_hash(cp); > + ip_vs_conn_hash(cp->net, cp); > > expire_later: > IP_VS_DBG(7, "delayed: conn->refcnt-1=%d conn->n_control=%d\n", > @@ -748,18 +752,22 @@ 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 > + * Create a new connection entry and hash it into the ip_vs_conn_tab, > + * netns ptr will be stored in ip_vs_con here. > */ > struct ip_vs_conn * > -ip_vs_conn_new(int af, int proto, const union nf_inet_addr *caddr, __be16 cport, > +ip_vs_conn_new(struct net *net, int af, int proto, > + const union nf_inet_addr *caddr, __be16 cport, > const union nf_inet_addr *vaddr, __be16 vport, > - const union nf_inet_addr *daddr, __be16 dport, unsigned flags, > - struct ip_vs_dest *dest) > + const union nf_inet_addr *daddr, __be16 dport, > + unsigned flags, struct ip_vs_dest *dest) > { > struct ip_vs_conn *cp; > - struct ip_vs_protocol *pp = ip_vs_proto_get(proto); > + struct ip_vs_proto_data *pd = ip_vs_proto_data_get(net, proto); > + struct ip_vs_protocol *pp; > + struct netns_ipvs *ipvs = net->ipvs; > > - cp = kmem_cache_zalloc(ip_vs_conn_cachep, GFP_ATOMIC); > + cp = kmem_cache_zalloc(ipvs->conn_cachep, GFP_ATOMIC); > if (cp == NULL) { > IP_VS_ERR_RL("%s(): no memory\n", __func__); > return NULL; > @@ -790,9 +798,9 @@ ip_vs_conn_new(int af, int proto, const union nf_inet_addr *caddr, __be16 cport, > 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); > + atomic_inc(&ipvs->conn_no_cport_cnt); > > /* Bind the connection with a destination server */ > ip_vs_bind_dest(cp, dest); > @@ -808,12 +816,14 @@ ip_vs_conn_new(int af, int proto, const union nf_inet_addr *caddr, __be16 cport, > else > #endif > ip_vs_bind_xmit(cp); > - > - if (unlikely(pp && atomic_read(&pp->appcnt))) > - ip_vs_bind_app(cp, pp); > - > + cp->net = net; /* netns ptr needed in timer */ > + if( pd ) { > + pp = pd->pp; > + if (unlikely(pp && atomic_read(&pd->appcnt))) > + ip_vs_bind_app(net, cp, pp); > + } > /* Hash it in the ip_vs_conn_tab finally */ > - ip_vs_conn_hash(cp); > + ip_vs_conn_hash(net, cp); > > return cp; > } > @@ -824,16 +834,33 @@ ip_vs_conn_new(int af, int proto, const union nf_inet_addr *caddr, __be16 cport, > */ > #ifdef CONFIG_PROC_FS > > +struct ipvs_private { > + struct seq_net_private p; > + void *private; > +}; > + > +static inline void ipvs_seq_priv_set(struct seq_file *seq, void *data) > +{ > + struct ipvs_private *ipriv=(struct ipvs_private *)seq->private; > + ipriv->private = data; > +} > +static inline void *ipvs_seq_priv_get(struct seq_file *seq) > +{ > + return ((struct ipvs_private *)seq->private)->private; > +} > + > static void *ip_vs_conn_array(struct seq_file *seq, loff_t pos) > { > int idx; > struct ip_vs_conn *cp; > + struct net *net = seq_file_net(seq); > + struct netns_ipvs *ipvs = net->ipvs; > > 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) { > + list_for_each_entry(cp, &ipvs->conn_tab[idx], c_list) { > if (pos-- == 0) { > - seq->private = &ip_vs_conn_tab[idx]; > + ipvs_seq_priv_set(seq, &ipvs->conn_tab[idx]); > return cp; > } > } > @@ -845,15 +872,17 @@ 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; > + ipvs_seq_priv_set(seq, NULL); > return *pos ? ip_vs_conn_array(seq, *pos - 1) :SEQ_START_TOKEN; > } > - > + /* netns: conn_tab OK */ > 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 list_head *e, *l = ipvs_seq_priv_get(seq); > int idx; > + struct net *net = seq_file_net(seq); > + struct netns_ipvs *ipvs = net->ipvs; > > ++*pos; > if (v == SEQ_START_TOKEN) > @@ -863,27 +892,28 @@ static void *ip_vs_conn_seq_next(struct seq_file *seq, void *v, loff_t *pos) > if ((e = cp->c_list.next) != l) > return list_entry(e, struct ip_vs_conn, c_list); > > - idx = l - ip_vs_conn_tab; > + idx = l - ipvs->conn_tab; > ct_read_unlock_bh(idx); > > 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]; > + list_for_each_entry(cp, &ipvs->conn_tab[idx], c_list) { > + ipvs_seq_priv_set(seq, &ipvs->conn_tab[idx]); > return cp; > } > ct_read_unlock_bh(idx); > } > - seq->private = NULL; > + ipvs_seq_priv_set(seq, NULL); > return NULL; > } > - > +/* netns: conn_tab OK */ > static void ip_vs_conn_seq_stop(struct seq_file *seq, void *v) > { > - struct list_head *l = seq->private; > + struct list_head *l = ipvs_seq_priv_get(seq); > + struct net *net = seq_file_net(seq); > > if (l) > - ct_read_unlock_bh(l - ip_vs_conn_tab); > + ct_read_unlock_bh(l - net->ipvs->conn_tab); > } > > static int ip_vs_conn_seq_show(struct seq_file *seq, void *v) > @@ -928,7 +958,16 @@ 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); > + int ret; > + struct ipvs_private *priv; > + > + ret = seq_open_net(inode, file, &ip_vs_conn_seq_ops, > + sizeof(struct ipvs_private)); > + if (!ret) { > + priv = ((struct seq_file *)file->private_data)->private; > + priv->private = NULL; > + } > + return ret; > } > > static const struct file_operations ip_vs_conn_fops = { > @@ -936,7 +975,8 @@ static const struct file_operations ip_vs_conn_fops = { > .open = ip_vs_conn_open, > .read = seq_read, > .llseek = seq_lseek, > - .release = seq_release, > + .release = seq_release_private, > + > }; > > static const char *ip_vs_origin_name(unsigned flags) > @@ -991,7 +1031,17 @@ 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); > + int ret; > + struct ipvs_private *ipriv; > + > + ret = seq_open_net(inode, file, &ip_vs_conn_sync_seq_ops, > + sizeof(struct ipvs_private)); > + if (!ret) { > + ipriv = ((struct seq_file *)file->private_data)->private; > + ipriv->private = NULL; > + } > + return ret; > +// return seq_open(file, &ip_vs_conn_sync_seq_ops); > } > > static const struct file_operations ip_vs_conn_sync_fops = { > @@ -999,7 +1049,7 @@ static const struct file_operations ip_vs_conn_sync_fops = { > .open = ip_vs_conn_sync_open, > .read = seq_read, > .llseek = seq_lseek, > - .release = seq_release, > + .release = seq_release_private, > }; > > #endif > @@ -1036,11 +1086,14 @@ static inline int todrop_entry(struct ip_vs_conn *cp) > return 1; > } > > -/* Called from keventd and must protect itself from softirqs */ > -void ip_vs_random_dropentry(void) > +/* Called from keventd and must protect itself from softirqs > + * netns: conn_tab OK > + */ > +void ip_vs_random_dropentry(struct net *net) > { > int idx; > struct ip_vs_conn *cp; > + struct netns_ipvs *ipvs = net->ipvs; > > /* > * Randomly scan 1/32 of the whole table every second > @@ -1053,7 +1106,7 @@ void ip_vs_random_dropentry(void) > */ > ct_write_lock_bh(hash); > > - list_for_each_entry(cp, &ip_vs_conn_tab[hash], c_list) { > + list_for_each_entry(cp, &ipvs->conn_tab[hash], c_list) { > if (cp->flags & IP_VS_CONN_F_TEMPLATE) > /* connection template */ > continue; > @@ -1091,11 +1144,13 @@ void ip_vs_random_dropentry(void) > > /* > * Flush all the connection entries in the ip_vs_conn_tab > + * netns: conn_tab OK > */ > -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; > > flush_again: > for (idx = 0; idx < ip_vs_conn_tab_size; idx++) { > @@ -1104,7 +1159,7 @@ static void ip_vs_conn_flush(void) > */ > ct_write_lock_bh(idx); > > - list_for_each_entry(cp, &ip_vs_conn_tab[idx], c_list) { > + list_for_each_entry(cp, &ipvs->conn_tab[idx], c_list) { > > IP_VS_DBG(4, "del connection\n"); > ip_vs_conn_expire_now(cp); > @@ -1118,16 +1173,17 @@ 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; > } > } > > > -int __init ip_vs_conn_init(void) > +int __net_init __ip_vs_conn_init(struct net *net) > { > int idx; > + struct netns_ipvs *ipvs = net->ipvs; > > /* Compute size and mask */ > ip_vs_conn_tab_size = 1 << ip_vs_conn_tab_bits; > @@ -1136,19 +1192,26 @@ int __init ip_vs_conn_init(void) > /* > * Allocate the connection hash table and initialize its list heads > */ > - ip_vs_conn_tab = vmalloc(ip_vs_conn_tab_size * > + ipvs->conn_tab = vmalloc(ip_vs_conn_tab_size * > sizeof(struct list_head)); > - if (!ip_vs_conn_tab) > + if (!ipvs->conn_tab) > return -ENOMEM; > > /* Allocate ip_vs_conn slab cache */ > - ip_vs_conn_cachep = kmem_cache_create("ip_vs_conn", > + /* Todo: find a better way to name the cache */ > + snprintf(ipvs->conn_cname, sizeof(ipvs->conn_cname)-1, > + "ipvs_conn_%d", atomic_read(&conn_cache_nr) ); > + atomic_inc(&conn_cache_nr); > + > + ipvs->conn_cachep = kmem_cache_create(ipvs->conn_cname, > sizeof(struct ip_vs_conn), 0, > SLAB_HWCACHE_ALIGN, NULL); > - if (!ip_vs_conn_cachep) { > - vfree(ip_vs_conn_tab); > + if (!ipvs->conn_cachep) { > + vfree(ipvs->conn_tab); > return -ENOMEM; > } > + atomic_set(&ipvs->conn_count, 0); > + atomic_set(&ipvs->conn_no_cport_cnt, 0); > > pr_info("Connection hash table configured " > "(size=%d, memory=%ldKbytes)\n", > @@ -1158,31 +1221,46 @@ int __init ip_vs_conn_init(void) > sizeof(struct ip_vs_conn)); > > for (idx = 0; idx < ip_vs_conn_tab_size; idx++) { > - INIT_LIST_HEAD(&ip_vs_conn_tab[idx]); > + INIT_LIST_HEAD(&ipvs->conn_tab[idx]); > } > > for (idx = 0; idx < CT_LOCKARRAY_SIZE; idx++) { > rwlock_init(&__ip_vs_conntbl_lock_array[idx].l); > } > > - 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)); > + 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) { > > + /* flush all the connection entries first */ > + ip_vs_conn_flush(net); > + /* Release the empty cache */ > + kmem_cache_destroy(net->ipvs->conn_cachep); > + proc_net_remove(net, "ip_vs_conn"); > + proc_net_remove(net, "ip_vs_conn_sync"); > + vfree(net->ipvs->conn_tab); > +} > +static struct pernet_operations ipvs_conn_ops = { > + .init = __ip_vs_conn_init, > + .exit = __ip_vs_conn_cleanup, > +}; > > -void ip_vs_conn_cleanup(void) > +int __init ip_vs_conn_init(void) > { > - /* flush all the connection entries first */ > - ip_vs_conn_flush(); > + int rv; > > - /* 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); > + rv = register_pernet_subsys(&ipvs_conn_ops); > + > + /* calculate the random value for connection hash */ > + get_random_bytes(&ip_vs_conn_rnd, sizeof(ip_vs_conn_rnd)); > + return rv; > +} > + > +void ip_vs_conn_cleanup(void) > +{ > + unregister_pernet_subsys(&ipvs_conn_ops); > } > > -- > Regards > Hans Schillstrom <hans.schillstrom@ericsson.com> > -- > To unsubscribe from this list: send the line "unsubscribe lvs-devel" in > the body of a message to majordomo@vger.kernel.org > More majordomo info at http://vger.kernel.org/majordomo-info.html > -- To unsubscribe from this list: send the line "unsubscribe netdev" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
On Wednesday 20 October 2010 16:03:24 Simon Horman wrote: > On Fri, Oct 08, 2010 at 01:16:57PM +0200, Hans Schillstrom wrote: > > > > This patch just contains ip_vs_conn.c > > and does the normal > > - moving to vars to struct ipvs > > - adding per netns init and exit > > > > proc_fs required some extra work with adding/chaning private data to get the net ptr. > > I am currently working on rebasing this patch against the > current nf-next-2.6 tree with includes persistence engines > and I noticed a few things. > > > Signed-off-by:Hans Schillstrom <hans.schillstrom@ericsson.com> > > > > diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c > > index b71c69a..c47828f 100644 > > --- a/net/netfilter/ipvs/ip_vs_conn.c > > +++ b/net/netfilter/ipvs/ip_vs_conn.c > > @@ -47,7 +47,7 @@ > > > > /* > > * Connection hash size. Default is what was selected at compile time. > > -*/ > > + */ > > int ip_vs_conn_tab_bits = CONFIG_IP_VS_TAB_BITS; > > module_param_named(conn_tab_bits, ip_vs_conn_tab_bits, int, 0444); > > MODULE_PARM_DESC(conn_tab_bits, "Set connections' hash size"); > > This fragment is not needed. OK > > > @@ -56,23 +56,12 @@ MODULE_PARM_DESC(conn_tab_bits, "Set connections' hash size"); > > int ip_vs_conn_tab_size; > > int ip_vs_conn_tab_mask; > > > > -/* > > - * Connection hash table: for input and output packets lookups of IPVS > > - */ > > -static struct list_head *ip_vs_conn_tab; > > - > > -/* 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); > > - > > /* random value for IPVS connection hash */ > > static unsigned int ip_vs_conn_rnd; > > > > +/* cache name cnt */ > > +static atomic_t conn_cache_nr = ATOMIC_INIT(0); > > + > > /* > > * Fine locking granularity for big connection hash table > > */ > > @@ -153,7 +142,7 @@ static unsigned int ip_vs_conn_hashkey(int af, unsigned proto, > > * Hashes ip_vs_conn in ip_vs_conn_tab by proto,addr,port. > > * returns bool success. > > */ > > -static inline int ip_vs_conn_hash(struct ip_vs_conn *cp) > > +static inline int ip_vs_conn_hash(struct net *net, struct ip_vs_conn *cp) > > { > > unsigned hash; > > int ret; > > @@ -168,7 +157,7 @@ static inline int ip_vs_conn_hash(struct ip_vs_conn *cp) > > spin_lock(&cp->lock); > > > > if (!(cp->flags & IP_VS_CONN_F_HASHED)) { > > - list_add(&cp->c_list, &ip_vs_conn_tab[hash]); > > + list_add(&cp->c_list, &net->ipvs->conn_tab[hash]); > > cp->flags |= IP_VS_CONN_F_HASHED; > > atomic_inc(&cp->refcnt); > > ret = 1; > > @@ -221,18 +210,20 @@ static inline int ip_vs_conn_unhash(struct ip_vs_conn *cp) > > * s_addr, s_port: pkt source address (foreign host) > > * d_addr, d_port: pkt dest address (load balancer) > > */ > > -static inline struct ip_vs_conn *__ip_vs_conn_in_get > > -(int af, int protocol, const union nf_inet_addr *s_addr, __be16 s_port, > > - const union nf_inet_addr *d_addr, __be16 d_port) > > +static inline struct ip_vs_conn * > > +__ip_vs_conn_in_get(struct net *net, int af, int protocol, > > + const union nf_inet_addr *s_addr, __be16 s_port, > > + const union nf_inet_addr *d_addr, __be16 d_port) > > { > > unsigned hash; > > struct ip_vs_conn *cp; > > + struct netns_ipvs *ipvs = net->ipvs; > > > > hash = ip_vs_conn_hashkey(af, protocol, s_addr, s_port); > > > > ct_read_lock(hash); > > > > - list_for_each_entry(cp, &ip_vs_conn_tab[hash], c_list) { > > + list_for_each_entry(cp, &ipvs->conn_tab[hash], c_list) { > > if (cp->af == af && > > ip_vs_addr_equal(af, s_addr, &cp->caddr) && > > ip_vs_addr_equal(af, d_addr, &cp->vaddr) && > > @@ -251,16 +242,18 @@ static inline struct ip_vs_conn *__ip_vs_conn_in_get > > return NULL; > > } > > > > -struct ip_vs_conn *ip_vs_conn_in_get > > -(int af, int protocol, const union nf_inet_addr *s_addr, __be16 s_port, > > - const union nf_inet_addr *d_addr, __be16 d_port) > > +struct ip_vs_conn * > > +ip_vs_conn_in_get(struct net *net, int af, int protocol, > > + const union nf_inet_addr *s_addr, __be16 s_port, > > + const union nf_inet_addr *d_addr, __be16 d_port) > > { > > struct ip_vs_conn *cp; > > > > - cp = __ip_vs_conn_in_get(af, protocol, s_addr, s_port, d_addr, d_port); > > - if (!cp && atomic_read(&ip_vs_conn_no_cport_cnt)) > > - cp = __ip_vs_conn_in_get(af, protocol, s_addr, 0, d_addr, > > - d_port); > > + cp = __ip_vs_conn_in_get(net, af, protocol, > > + s_addr, s_port, d_addr, d_port); > > + if (!cp && atomic_read(&net->ipvs->conn_no_cport_cnt)) > > + cp = __ip_vs_conn_in_get(net, af, protocol, > > + s_addr, 0, d_addr, d_port); > > > > IP_VS_DBG_BUF(9, "lookup/in %s %s:%d->%s:%d %s\n", > > ip_vs_proto_name(protocol), > > @@ -278,35 +271,41 @@ ip_vs_conn_in_get_proto(int af, const struct sk_buff *skb, > > unsigned int proto_off, int inverse) > > { > > __be16 _ports[2], *pptr; > > + struct net *net = dev_net(skb->dev); > > > > pptr = skb_header_pointer(skb, proto_off, sizeof(_ports), _ports); > > if (pptr == NULL) > > return NULL; > > > > + BUG_ON(!net); > > Can you explain why BUG_ON is here? Yes, I forgot to remove it. I had them every where to make sure that net ptr was set, - don't call me paranoid ;-) > > > if (likely(!inverse)) > > - return ip_vs_conn_in_get(af, iph->protocol, > > + return ip_vs_conn_in_get(net, af, iph->protocol, > > &iph->saddr, pptr[0], > > &iph->daddr, pptr[1]); > > else > > - return ip_vs_conn_in_get(af, iph->protocol, > > + return ip_vs_conn_in_get(net, af, iph->protocol, > > &iph->daddr, pptr[1], > > &iph->saddr, pptr[0]); > > } > > EXPORT_SYMBOL_GPL(ip_vs_conn_in_get_proto); > > > > -/* Get reference to connection template */ > > -struct ip_vs_conn *ip_vs_ct_in_get > > -(int af, int protocol, const union nf_inet_addr *s_addr, __be16 s_port, > > - const union nf_inet_addr *d_addr, __be16 d_port) > > +/* > > + * Get reference to connection template > > + */ > > +struct ip_vs_conn * > > +ip_vs_ct_in_get(struct net *net, int af, int protocol, > > + const union nf_inet_addr *s_addr, __be16 s_port, > > + const union nf_inet_addr *d_addr, __be16 d_port) > > { > > unsigned hash; > > struct ip_vs_conn *cp; > > + struct netns_ipvs *ipvs = net->ipvs; > > > > hash = ip_vs_conn_hashkey(af, protocol, s_addr, s_port); > > > > ct_read_lock(hash); > > > > - list_for_each_entry(cp, &ip_vs_conn_tab[hash], c_list) { > > + list_for_each_entry(cp, &ipvs->conn_tab[hash], c_list) { > > if (cp->af == af && > > ip_vs_addr_equal(af, s_addr, &cp->caddr) && > > /* protocol should only be IPPROTO_IP if > > @@ -341,12 +340,14 @@ struct ip_vs_conn *ip_vs_ct_in_get > > * s_addr, s_port: pkt source address (inside host) > > * d_addr, d_port: pkt dest address (foreign host) > > */ > > -struct ip_vs_conn *ip_vs_conn_out_get > > -(int af, int protocol, const union nf_inet_addr *s_addr, __be16 s_port, > > - const union nf_inet_addr *d_addr, __be16 d_port) > > +struct ip_vs_conn * > > +ip_vs_conn_out_get(struct net *net, int af, int protocol, > > + const union nf_inet_addr *s_addr, __be16 s_port, > > + const union nf_inet_addr *d_addr, __be16 d_port) > > { > > unsigned hash; > > struct ip_vs_conn *cp, *ret=NULL; > > + struct netns_ipvs *ipvs = net->ipvs; > > > > /* > > * Check for "full" addressed entries > > @@ -355,7 +356,7 @@ struct ip_vs_conn *ip_vs_conn_out_get > > > > ct_read_lock(hash); > > > > - list_for_each_entry(cp, &ip_vs_conn_tab[hash], c_list) { > > + list_for_each_entry(cp, &ipvs->conn_tab[hash], c_list) { > > if (cp->af == af && > > ip_vs_addr_equal(af, d_addr, &cp->caddr) && > > ip_vs_addr_equal(af, s_addr, &cp->daddr) && > > @@ -386,17 +387,19 @@ ip_vs_conn_out_get_proto(int af, const struct sk_buff *skb, > > unsigned int proto_off, int inverse) > > { > > __be16 _ports[2], *pptr; > > + struct net *net = dev_net(skb->dev); > > > > pptr = skb_header_pointer(skb, proto_off, sizeof(_ports), _ports); > > if (pptr == NULL) > > return NULL; > > > > + BUG_ON(!net); > > if (likely(!inverse)) > > - return ip_vs_conn_out_get(af, iph->protocol, > > + return ip_vs_conn_out_get(net, af, iph->protocol, > > &iph->saddr, pptr[0], > > &iph->daddr, pptr[1]); > > else > > - return ip_vs_conn_out_get(af, iph->protocol, > > + return ip_vs_conn_out_get(net, af, iph->protocol, > > &iph->daddr, pptr[1], > > &iph->saddr, pptr[0]); > > } > > @@ -408,7 +411,7 @@ EXPORT_SYMBOL_GPL(ip_vs_conn_out_get_proto); > > void ip_vs_conn_put(struct ip_vs_conn *cp) > > { > > unsigned long t = (cp->flags & IP_VS_CONN_F_ONE_PACKET) ? > > - 0 : cp->timeout; > > + 0 : cp->timeout; > > mod_timer(&cp->timer, jiffies+t); > > > > __ip_vs_conn_put(cp); > > @@ -418,19 +421,19 @@ void ip_vs_conn_put(struct ip_vs_conn *cp) > > /* > > * Fill a no_client_port connection with a client port number > > */ > > -void ip_vs_conn_fill_cport(struct ip_vs_conn *cp, __be16 cport) > > +void ip_vs_conn_fill_cport(struct net *net, struct ip_vs_conn *cp, __be16 cport) > > { > > if (ip_vs_conn_unhash(cp)) { > > spin_lock(&cp->lock); > > if (cp->flags & IP_VS_CONN_F_NO_CPORT) { > > - atomic_dec(&ip_vs_conn_no_cport_cnt); > > + atomic_dec(&net->ipvs->conn_no_cport_cnt); > > cp->flags &= ~IP_VS_CONN_F_NO_CPORT; > > cp->cport = cport; > > } > > spin_unlock(&cp->lock); > > > > /* hash on new dport */ > > - ip_vs_conn_hash(cp); > > + ip_vs_conn_hash(net, cp); > > } > > } > > > > @@ -561,12 +564,12 @@ ip_vs_bind_dest(struct ip_vs_conn *cp, struct ip_vs_dest *dest) > > * Check if there is a destination for the connection, if so > > * bind the connection to the destination. > > */ > > -struct ip_vs_dest *ip_vs_try_bind_dest(struct ip_vs_conn *cp) > > +struct ip_vs_dest *ip_vs_try_bind_dest(struct net *net, struct ip_vs_conn *cp) > > { > > struct ip_vs_dest *dest; > > > > if ((cp) && (!cp->dest)) { > > - dest = ip_vs_find_dest(cp->af, &cp->daddr, cp->dport, > > + dest = ip_vs_find_dest(net, cp->af, &cp->daddr, cp->dport, > > &cp->vaddr, cp->vport, > > cp->protocol); > > ip_vs_bind_dest(cp, dest); > > @@ -638,7 +641,7 @@ static inline void ip_vs_unbind_dest(struct ip_vs_conn *cp) > > * If available, return 1, otherwise invalidate this connection > > * template and return 0. > > */ > > -int ip_vs_check_template(struct ip_vs_conn *ct) > > +int ip_vs_check_template(struct net *net, struct ip_vs_conn *ct) > > { > > struct ip_vs_dest *dest = ct->dest; > > > > @@ -647,7 +650,7 @@ int ip_vs_check_template(struct ip_vs_conn *ct) > > */ > > if ((dest == NULL) || > > !(dest->flags & IP_VS_DEST_F_AVAILABLE) || > > - (sysctl_ip_vs_expire_quiescent_template && > > + (net->ipvs->sysctl_expire_quiescent_template && > > (atomic_read(&dest->weight) == 0))) { > > IP_VS_DBG_BUF(9, "check_template: dest not available for " > > "protocol %s s:%s:%d v:%s:%d " > > @@ -668,7 +671,7 @@ int ip_vs_check_template(struct ip_vs_conn *ct) > > ct->dport = htons(0xffff); > > ct->vport = htons(0xffff); > > ct->cport = 0; > > - ip_vs_conn_hash(ct); > > + ip_vs_conn_hash(net, ct); > > } > > } > > > > @@ -720,16 +723,17 @@ static void ip_vs_conn_expire(unsigned long data) > > if (unlikely(cp->app != NULL)) > > ip_vs_unbind_app(cp); > > ip_vs_unbind_dest(cp); > > + BUG_ON(!cp->net); > > 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(&cp->net->ipvs->conn_no_cport_cnt); > > + atomic_dec(&cp->net->ipvs->conn_count); > > > > - kmem_cache_free(ip_vs_conn_cachep, cp); > > + kmem_cache_free(cp->net->ipvs->conn_cachep, cp); > > return; > > } > > > > /* hash it back to the table */ > > - ip_vs_conn_hash(cp); > > + ip_vs_conn_hash(cp->net, cp); > > > > expire_later: > > IP_VS_DBG(7, "delayed: conn->refcnt-1=%d conn->n_control=%d\n", > > @@ -748,18 +752,22 @@ 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 > > + * Create a new connection entry and hash it into the ip_vs_conn_tab, > > + * netns ptr will be stored in ip_vs_con here. > > */ > > struct ip_vs_conn * > > -ip_vs_conn_new(int af, int proto, const union nf_inet_addr *caddr, __be16 cport, > > +ip_vs_conn_new(struct net *net, int af, int proto, > > + const union nf_inet_addr *caddr, __be16 cport, > > const union nf_inet_addr *vaddr, __be16 vport, > > - const union nf_inet_addr *daddr, __be16 dport, unsigned flags, > > - struct ip_vs_dest *dest) > > + const union nf_inet_addr *daddr, __be16 dport, > > + unsigned flags, struct ip_vs_dest *dest) > > { > > struct ip_vs_conn *cp; > > - struct ip_vs_protocol *pp = ip_vs_proto_get(proto); > > + struct ip_vs_proto_data *pd = ip_vs_proto_data_get(net, proto); > > + struct ip_vs_protocol *pp; > > + struct netns_ipvs *ipvs = net->ipvs; > > > > - cp = kmem_cache_zalloc(ip_vs_conn_cachep, GFP_ATOMIC); > > + cp = kmem_cache_zalloc(ipvs->conn_cachep, GFP_ATOMIC); > > if (cp == NULL) { > > IP_VS_ERR_RL("%s(): no memory\n", __func__); > > return NULL; > > @@ -790,9 +798,9 @@ ip_vs_conn_new(int af, int proto, const union nf_inet_addr *caddr, __be16 cport, > > 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); > > + atomic_inc(&ipvs->conn_no_cport_cnt); > > > > /* Bind the connection with a destination server */ > > ip_vs_bind_dest(cp, dest); > > @@ -808,12 +816,14 @@ ip_vs_conn_new(int af, int proto, const union nf_inet_addr *caddr, __be16 cport, > > else > > #endif > > ip_vs_bind_xmit(cp); > > - > > - if (unlikely(pp && atomic_read(&pp->appcnt))) > > - ip_vs_bind_app(cp, pp); > > - > > + cp->net = net; /* netns ptr needed in timer */ > > + if( pd ) { > > + pp = pd->pp; > > + if (unlikely(pp && atomic_read(&pd->appcnt))) > > + ip_vs_bind_app(net, cp, pp); > > + } > > /* Hash it in the ip_vs_conn_tab finally */ > > - ip_vs_conn_hash(cp); > > + ip_vs_conn_hash(net, cp); > > > > return cp; > > } > > @@ -824,16 +834,33 @@ ip_vs_conn_new(int af, int proto, const union nf_inet_addr *caddr, __be16 cport, > > */ > > #ifdef CONFIG_PROC_FS > > > > +struct ipvs_private { > > + struct seq_net_private p; > > + void *private; > > +}; > > + > > +static inline void ipvs_seq_priv_set(struct seq_file *seq, void *data) > > +{ > > + struct ipvs_private *ipriv=(struct ipvs_private *)seq->private; > > + ipriv->private = data; > > +} > > +static inline void *ipvs_seq_priv_get(struct seq_file *seq) > > +{ > > + return ((struct ipvs_private *)seq->private)->private; > > +} > > + > > static void *ip_vs_conn_array(struct seq_file *seq, loff_t pos) > > { > > int idx; > > struct ip_vs_conn *cp; > > + struct net *net = seq_file_net(seq); > > + struct netns_ipvs *ipvs = net->ipvs; > > > > 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) { > > + list_for_each_entry(cp, &ipvs->conn_tab[idx], c_list) { > > if (pos-- == 0) { > > - seq->private = &ip_vs_conn_tab[idx]; > > + ipvs_seq_priv_set(seq, &ipvs->conn_tab[idx]); > > return cp; > > } > > } > > @@ -845,15 +872,17 @@ 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; > > + ipvs_seq_priv_set(seq, NULL); > > return *pos ? ip_vs_conn_array(seq, *pos - 1) :SEQ_START_TOKEN; > > } > > - > > + /* netns: conn_tab OK */ > > 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 list_head *e, *l = ipvs_seq_priv_get(seq); > > int idx; > > + struct net *net = seq_file_net(seq); > > + struct netns_ipvs *ipvs = net->ipvs; > > > > ++*pos; > > if (v == SEQ_START_TOKEN) > > @@ -863,27 +892,28 @@ static void *ip_vs_conn_seq_next(struct seq_file *seq, void *v, loff_t *pos) > > if ((e = cp->c_list.next) != l) > > return list_entry(e, struct ip_vs_conn, c_list); > > > > - idx = l - ip_vs_conn_tab; > > + idx = l - ipvs->conn_tab; > > ct_read_unlock_bh(idx); > > > > 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]; > > + list_for_each_entry(cp, &ipvs->conn_tab[idx], c_list) { > > + ipvs_seq_priv_set(seq, &ipvs->conn_tab[idx]); > > return cp; > > } > > ct_read_unlock_bh(idx); > > } > > - seq->private = NULL; > > + ipvs_seq_priv_set(seq, NULL); > > return NULL; > > } > > - > > +/* netns: conn_tab OK */ > > static void ip_vs_conn_seq_stop(struct seq_file *seq, void *v) > > { > > - struct list_head *l = seq->private; > > + struct list_head *l = ipvs_seq_priv_get(seq); > > + struct net *net = seq_file_net(seq); > > > > if (l) > > - ct_read_unlock_bh(l - ip_vs_conn_tab); > > + ct_read_unlock_bh(l - net->ipvs->conn_tab); > > } > > > > static int ip_vs_conn_seq_show(struct seq_file *seq, void *v) > > @@ -928,7 +958,16 @@ 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); > > + int ret; > > + struct ipvs_private *priv; > > + > > + ret = seq_open_net(inode, file, &ip_vs_conn_seq_ops, > > + sizeof(struct ipvs_private)); > > + if (!ret) { > > + priv = ((struct seq_file *)file->private_data)->private; > > + priv->private = NULL; > > + } > > + return ret; > > } > > > > static const struct file_operations ip_vs_conn_fops = { > > @@ -936,7 +975,8 @@ static const struct file_operations ip_vs_conn_fops = { > > .open = ip_vs_conn_open, > > .read = seq_read, > > .llseek = seq_lseek, > > - .release = seq_release, > > + .release = seq_release_private, > > + > > }; > > > > static const char *ip_vs_origin_name(unsigned flags) > > @@ -991,7 +1031,17 @@ 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); > > + int ret; > > + struct ipvs_private *ipriv; > > + > > + ret = seq_open_net(inode, file, &ip_vs_conn_sync_seq_ops, > > + sizeof(struct ipvs_private)); > > + if (!ret) { > > + ipriv = ((struct seq_file *)file->private_data)->private; > > + ipriv->private = NULL; > > + } > > + return ret; > > +// return seq_open(file, &ip_vs_conn_sync_seq_ops); > > } > > > > static const struct file_operations ip_vs_conn_sync_fops = { > > @@ -999,7 +1049,7 @@ static const struct file_operations ip_vs_conn_sync_fops = { > > .open = ip_vs_conn_sync_open, > > .read = seq_read, > > .llseek = seq_lseek, > > - .release = seq_release, > > + .release = seq_release_private, > > }; > > > > #endif > > @@ -1036,11 +1086,14 @@ static inline int todrop_entry(struct ip_vs_conn *cp) > > return 1; > > } > > > > -/* Called from keventd and must protect itself from softirqs */ > > -void ip_vs_random_dropentry(void) > > +/* Called from keventd and must protect itself from softirqs > > + * netns: conn_tab OK > > + */ > > +void ip_vs_random_dropentry(struct net *net) > > { > > int idx; > > struct ip_vs_conn *cp; > > + struct netns_ipvs *ipvs = net->ipvs; > > > > /* > > * Randomly scan 1/32 of the whole table every second > > @@ -1053,7 +1106,7 @@ void ip_vs_random_dropentry(void) > > */ > > ct_write_lock_bh(hash); > > > > - list_for_each_entry(cp, &ip_vs_conn_tab[hash], c_list) { > > + list_for_each_entry(cp, &ipvs->conn_tab[hash], c_list) { > > if (cp->flags & IP_VS_CONN_F_TEMPLATE) > > /* connection template */ > > continue; > > @@ -1091,11 +1144,13 @@ void ip_vs_random_dropentry(void) > > > > /* > > * Flush all the connection entries in the ip_vs_conn_tab > > + * netns: conn_tab OK > > */ > > -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; > > > > flush_again: > > for (idx = 0; idx < ip_vs_conn_tab_size; idx++) { > > @@ -1104,7 +1159,7 @@ static void ip_vs_conn_flush(void) > > */ > > ct_write_lock_bh(idx); > > > > - list_for_each_entry(cp, &ip_vs_conn_tab[idx], c_list) { > > + list_for_each_entry(cp, &ipvs->conn_tab[idx], c_list) { > > > > IP_VS_DBG(4, "del connection\n"); > > ip_vs_conn_expire_now(cp); > > @@ -1118,16 +1173,17 @@ 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; > > } > > } > > > > > > -int __init ip_vs_conn_init(void) > > +int __net_init __ip_vs_conn_init(struct net *net) > > { > > int idx; > > + struct netns_ipvs *ipvs = net->ipvs; > > > > /* Compute size and mask */ > > ip_vs_conn_tab_size = 1 << ip_vs_conn_tab_bits; > > @@ -1136,19 +1192,26 @@ int __init ip_vs_conn_init(void) > > /* > > * Allocate the connection hash table and initialize its list heads > > */ > > - ip_vs_conn_tab = vmalloc(ip_vs_conn_tab_size * > > + ipvs->conn_tab = vmalloc(ip_vs_conn_tab_size * > > sizeof(struct list_head)); > > - if (!ip_vs_conn_tab) > > + if (!ipvs->conn_tab) > > return -ENOMEM; > > > > /* Allocate ip_vs_conn slab cache */ > > - ip_vs_conn_cachep = kmem_cache_create("ip_vs_conn", > > + /* Todo: find a better way to name the cache */ > > + snprintf(ipvs->conn_cname, sizeof(ipvs->conn_cname)-1, > > + "ipvs_conn_%d", atomic_read(&conn_cache_nr) ); > > + atomic_inc(&conn_cache_nr); > > + > > + ipvs->conn_cachep = kmem_cache_create(ipvs->conn_cname, > > sizeof(struct ip_vs_conn), 0, > > SLAB_HWCACHE_ALIGN, NULL); > > - if (!ip_vs_conn_cachep) { > > - vfree(ip_vs_conn_tab); > > + if (!ipvs->conn_cachep) { > > + vfree(ipvs->conn_tab); > > return -ENOMEM; > > } > > + atomic_set(&ipvs->conn_count, 0); > > + atomic_set(&ipvs->conn_no_cport_cnt, 0); > > > > pr_info("Connection hash table configured " > > "(size=%d, memory=%ldKbytes)\n", > > @@ -1158,31 +1221,46 @@ int __init ip_vs_conn_init(void) > > sizeof(struct ip_vs_conn)); > > > > for (idx = 0; idx < ip_vs_conn_tab_size; idx++) { > > - INIT_LIST_HEAD(&ip_vs_conn_tab[idx]); > > + INIT_LIST_HEAD(&ipvs->conn_tab[idx]); > > } > > > > for (idx = 0; idx < CT_LOCKARRAY_SIZE; idx++) { > > rwlock_init(&__ip_vs_conntbl_lock_array[idx].l); > > } > > > > - 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)); > > + 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) { > > > > + /* flush all the connection entries first */ > > + ip_vs_conn_flush(net); > > + /* Release the empty cache */ > > + kmem_cache_destroy(net->ipvs->conn_cachep); > > + proc_net_remove(net, "ip_vs_conn"); > > + proc_net_remove(net, "ip_vs_conn_sync"); > > + vfree(net->ipvs->conn_tab); > > +} > > +static struct pernet_operations ipvs_conn_ops = { > > + .init = __ip_vs_conn_init, > > + .exit = __ip_vs_conn_cleanup, > > +}; > > > > -void ip_vs_conn_cleanup(void) > > +int __init ip_vs_conn_init(void) > > { > > - /* flush all the connection entries first */ > > - ip_vs_conn_flush(); > > + int rv; > > > > - /* 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); > > + rv = register_pernet_subsys(&ipvs_conn_ops); > > + > > + /* calculate the random value for connection hash */ > > + get_random_bytes(&ip_vs_conn_rnd, sizeof(ip_vs_conn_rnd)); > > + return rv; > > +} > > + > > +void ip_vs_conn_cleanup(void) > > +{ > > + unregister_pernet_subsys(&ipvs_conn_ops); > > } > > > > -- > > Regards > > Hans Schillstrom <hans.schillstrom@ericsson.com> > > -- > > To unsubscribe from this list: send the line "unsubscribe lvs-devel" in > > the body of a message to majordomo@vger.kernel.org > > More majordomo info at http://vger.kernel.org/majordomo-info.html > > > -- Regards Hans Schillstrom <hans.schillstrom@ericsson.com> -- To unsubscribe from this list: send the line "unsubscribe netdev" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
On Thu, Oct 21, 2010 at 09:51:40AM +0200, Hans Schillstrom wrote: > On Wednesday 20 October 2010 16:03:24 Simon Horman wrote: > > On Fri, Oct 08, 2010 at 01:16:57PM +0200, Hans Schillstrom wrote: [ snip ] > > > @@ -278,35 +271,41 @@ ip_vs_conn_in_get_proto(int af, const struct sk_buff *skb, > > > unsigned int proto_off, int inverse) > > > { > > > __be16 _ports[2], *pptr; > > > + struct net *net = dev_net(skb->dev); > > > > > > pptr = skb_header_pointer(skb, proto_off, sizeof(_ports), _ports); > > > if (pptr == NULL) > > > return NULL; > > > > > > + BUG_ON(!net); > > > > Can you explain why BUG_ON is here? > > Yes, I forgot to remove it. > I had them every where to make sure that net ptr was set, > - don't call me paranoid ;-) Thanks, I thought it was something like that. I'll remove them as part of my rebase. [ strip ] -- To unsubscribe from this list: send the line "unsubscribe netdev" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c index b71c69a..c47828f 100644 --- a/net/netfilter/ipvs/ip_vs_conn.c +++ b/net/netfilter/ipvs/ip_vs_conn.c @@ -47,7 +47,7 @@ /* * Connection hash size. Default is what was selected at compile time. -*/ + */ int ip_vs_conn_tab_bits = CONFIG_IP_VS_TAB_BITS; module_param_named(conn_tab_bits, ip_vs_conn_tab_bits, int, 0444); MODULE_PARM_DESC(conn_tab_bits, "Set connections' hash size"); @@ -56,23 +56,12 @@ MODULE_PARM_DESC(conn_tab_bits, "Set connections' hash size"); int ip_vs_conn_tab_size; int ip_vs_conn_tab_mask; -/* - * Connection hash table: for input and output packets lookups of IPVS - */ -static struct list_head *ip_vs_conn_tab; - -/* 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); - /* random value for IPVS connection hash */ static unsigned int ip_vs_conn_rnd; +/* cache name cnt */ +static atomic_t conn_cache_nr = ATOMIC_INIT(0); + /* * Fine locking granularity for big connection hash table */ @@ -153,7 +142,7 @@ static unsigned int ip_vs_conn_hashkey(int af, unsigned proto, * Hashes ip_vs_conn in ip_vs_conn_tab by proto,addr,port. * returns bool success. */ -static inline int ip_vs_conn_hash(struct ip_vs_conn *cp) +static inline int ip_vs_conn_hash(struct net *net, struct ip_vs_conn *cp) { unsigned hash; int ret; @@ -168,7 +157,7 @@ static inline int ip_vs_conn_hash(struct ip_vs_conn *cp) spin_lock(&cp->lock); if (!(cp->flags & IP_VS_CONN_F_HASHED)) { - list_add(&cp->c_list, &ip_vs_conn_tab[hash]); + list_add(&cp->c_list, &net->ipvs->conn_tab[hash]); cp->flags |= IP_VS_CONN_F_HASHED; atomic_inc(&cp->refcnt); ret = 1; @@ -221,18 +210,20 @@ static inline int ip_vs_conn_unhash(struct ip_vs_conn *cp) * s_addr, s_port: pkt source address (foreign host) * d_addr, d_port: pkt dest address (load balancer) */ -static inline struct ip_vs_conn *__ip_vs_conn_in_get -(int af, int protocol, const union nf_inet_addr *s_addr, __be16 s_port, - const union nf_inet_addr *d_addr, __be16 d_port) +static inline struct ip_vs_conn * +__ip_vs_conn_in_get(struct net *net, int af, int protocol, + const union nf_inet_addr *s_addr, __be16 s_port, + const union nf_inet_addr *d_addr, __be16 d_port) { unsigned hash; struct ip_vs_conn *cp; + struct netns_ipvs *ipvs = net->ipvs; hash = ip_vs_conn_hashkey(af, protocol, s_addr, s_port); ct_read_lock(hash); - list_for_each_entry(cp, &ip_vs_conn_tab[hash], c_list) { + list_for_each_entry(cp, &ipvs->conn_tab[hash], c_list) { if (cp->af == af && ip_vs_addr_equal(af, s_addr, &cp->caddr) && ip_vs_addr_equal(af, d_addr, &cp->vaddr) && @@ -251,16 +242,18 @@ static inline struct ip_vs_conn *__ip_vs_conn_in_get return NULL; } -struct ip_vs_conn *ip_vs_conn_in_get -(int af, int protocol, const union nf_inet_addr *s_addr, __be16 s_port, - const union nf_inet_addr *d_addr, __be16 d_port) +struct ip_vs_conn * +ip_vs_conn_in_get(struct net *net, int af, int protocol, + const union nf_inet_addr *s_addr, __be16 s_port, + const union nf_inet_addr *d_addr, __be16 d_port) { struct ip_vs_conn *cp; - cp = __ip_vs_conn_in_get(af, protocol, s_addr, s_port, d_addr, d_port); - if (!cp && atomic_read(&ip_vs_conn_no_cport_cnt)) - cp = __ip_vs_conn_in_get(af, protocol, s_addr, 0, d_addr, - d_port); + cp = __ip_vs_conn_in_get(net, af, protocol, + s_addr, s_port, d_addr, d_port); + if (!cp && atomic_read(&net->ipvs->conn_no_cport_cnt)) + cp = __ip_vs_conn_in_get(net, af, protocol, + s_addr, 0, d_addr, d_port); IP_VS_DBG_BUF(9, "lookup/in %s %s:%d->%s:%d %s\n", ip_vs_proto_name(protocol), @@ -278,35 +271,41 @@ ip_vs_conn_in_get_proto(int af, const struct sk_buff *skb, unsigned int proto_off, int inverse) { __be16 _ports[2], *pptr; + struct net *net = dev_net(skb->dev); pptr = skb_header_pointer(skb, proto_off, sizeof(_ports), _ports); if (pptr == NULL) return NULL; + BUG_ON(!net); if (likely(!inverse)) - return ip_vs_conn_in_get(af, iph->protocol, + return ip_vs_conn_in_get(net, af, iph->protocol, &iph->saddr, pptr[0], &iph->daddr, pptr[1]); else - return ip_vs_conn_in_get(af, iph->protocol, + return ip_vs_conn_in_get(net, af, iph->protocol, &iph->daddr, pptr[1], &iph->saddr, pptr[0]); } EXPORT_SYMBOL_GPL(ip_vs_conn_in_get_proto); -/* Get reference to connection template */ -struct ip_vs_conn *ip_vs_ct_in_get -(int af, int protocol, const union nf_inet_addr *s_addr, __be16 s_port, - const union nf_inet_addr *d_addr, __be16 d_port) +/* + * Get reference to connection template + */ +struct ip_vs_conn * +ip_vs_ct_in_get(struct net *net, int af, int protocol, + const union nf_inet_addr *s_addr, __be16 s_port, + const union nf_inet_addr *d_addr, __be16 d_port) { unsigned hash; struct ip_vs_conn *cp; + struct netns_ipvs *ipvs = net->ipvs; hash = ip_vs_conn_hashkey(af, protocol, s_addr, s_port); ct_read_lock(hash); - list_for_each_entry(cp, &ip_vs_conn_tab[hash], c_list) { + list_for_each_entry(cp, &ipvs->conn_tab[hash], c_list) { if (cp->af == af && ip_vs_addr_equal(af, s_addr, &cp->caddr) && /* protocol should only be IPPROTO_IP if @@ -341,12 +340,14 @@ struct ip_vs_conn *ip_vs_ct_in_get * s_addr, s_port: pkt source address (inside host) * d_addr, d_port: pkt dest address (foreign host) */ -struct ip_vs_conn *ip_vs_conn_out_get -(int af, int protocol, const union nf_inet_addr *s_addr, __be16 s_port, - const union nf_inet_addr *d_addr, __be16 d_port) +struct ip_vs_conn * +ip_vs_conn_out_get(struct net *net, int af, int protocol, + const union nf_inet_addr *s_addr, __be16 s_port, + const union nf_inet_addr *d_addr, __be16 d_port) { unsigned hash; struct ip_vs_conn *cp, *ret=NULL; + struct netns_ipvs *ipvs = net->ipvs; /* * Check for "full" addressed entries @@ -355,7 +356,7 @@ struct ip_vs_conn *ip_vs_conn_out_get ct_read_lock(hash); - list_for_each_entry(cp, &ip_vs_conn_tab[hash], c_list) { + list_for_each_entry(cp, &ipvs->conn_tab[hash], c_list) { if (cp->af == af && ip_vs_addr_equal(af, d_addr, &cp->caddr) && ip_vs_addr_equal(af, s_addr, &cp->daddr) && @@ -386,17 +387,19 @@ ip_vs_conn_out_get_proto(int af, const struct sk_buff *skb, unsigned int proto_off, int inverse) { __be16 _ports[2], *pptr; + struct net *net = dev_net(skb->dev); pptr = skb_header_pointer(skb, proto_off, sizeof(_ports), _ports); if (pptr == NULL) return NULL; + BUG_ON(!net); if (likely(!inverse)) - return ip_vs_conn_out_get(af, iph->protocol, + return ip_vs_conn_out_get(net, af, iph->protocol, &iph->saddr, pptr[0], &iph->daddr, pptr[1]); else - return ip_vs_conn_out_get(af, iph->protocol, + return ip_vs_conn_out_get(net, af, iph->protocol, &iph->daddr, pptr[1], &iph->saddr, pptr[0]); } @@ -408,7 +411,7 @@ EXPORT_SYMBOL_GPL(ip_vs_conn_out_get_proto); void ip_vs_conn_put(struct ip_vs_conn *cp) { unsigned long t = (cp->flags & IP_VS_CONN_F_ONE_PACKET) ? - 0 : cp->timeout; + 0 : cp->timeout; mod_timer(&cp->timer, jiffies+t); __ip_vs_conn_put(cp); @@ -418,19 +421,19 @@ void ip_vs_conn_put(struct ip_vs_conn *cp) /* * Fill a no_client_port connection with a client port number */ -void ip_vs_conn_fill_cport(struct ip_vs_conn *cp, __be16 cport) +void ip_vs_conn_fill_cport(struct net *net, struct ip_vs_conn *cp, __be16 cport) { if (ip_vs_conn_unhash(cp)) { spin_lock(&cp->lock); if (cp->flags & IP_VS_CONN_F_NO_CPORT) { - atomic_dec(&ip_vs_conn_no_cport_cnt); + atomic_dec(&net->ipvs->conn_no_cport_cnt); cp->flags &= ~IP_VS_CONN_F_NO_CPORT; cp->cport = cport; } spin_unlock(&cp->lock); /* hash on new dport */ - ip_vs_conn_hash(cp); + ip_vs_conn_hash(net, cp); } } @@ -561,12 +564,12 @@ ip_vs_bind_dest(struct ip_vs_conn *cp, struct ip_vs_dest *dest) * Check if there is a destination for the connection, if so * bind the connection to the destination. */ -struct ip_vs_dest *ip_vs_try_bind_dest(struct ip_vs_conn *cp) +struct ip_vs_dest *ip_vs_try_bind_dest(struct net *net, struct ip_vs_conn *cp) { struct ip_vs_dest *dest; if ((cp) && (!cp->dest)) { - dest = ip_vs_find_dest(cp->af, &cp->daddr, cp->dport, + dest = ip_vs_find_dest(net, cp->af, &cp->daddr, cp->dport, &cp->vaddr, cp->vport, cp->protocol); ip_vs_bind_dest(cp, dest); @@ -638,7 +641,7 @@ static inline void ip_vs_unbind_dest(struct ip_vs_conn *cp) * If available, return 1, otherwise invalidate this connection * template and return 0. */ -int ip_vs_check_template(struct ip_vs_conn *ct) +int ip_vs_check_template(struct net *net, struct ip_vs_conn *ct) { struct ip_vs_dest *dest = ct->dest; @@ -647,7 +650,7 @@ int ip_vs_check_template(struct ip_vs_conn *ct) */ if ((dest == NULL) || !(dest->flags & IP_VS_DEST_F_AVAILABLE) || - (sysctl_ip_vs_expire_quiescent_template && + (net->ipvs->sysctl_expire_quiescent_template && (atomic_read(&dest->weight) == 0))) { IP_VS_DBG_BUF(9, "check_template: dest not available for " "protocol %s s:%s:%d v:%s:%d " @@ -668,7 +671,7 @@ int ip_vs_check_template(struct ip_vs_conn *ct) ct->dport = htons(0xffff); ct->vport = htons(0xffff); ct->cport = 0; - ip_vs_conn_hash(ct); + ip_vs_conn_hash(net, ct); } } @@ -720,16 +723,17 @@ static void ip_vs_conn_expire(unsigned long data) if (unlikely(cp->app != NULL)) ip_vs_unbind_app(cp); ip_vs_unbind_dest(cp); + BUG_ON(!cp->net); 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(&cp->net->ipvs->conn_no_cport_cnt); + atomic_dec(&cp->net->ipvs->conn_count); - kmem_cache_free(ip_vs_conn_cachep, cp); + kmem_cache_free(cp->net->ipvs->conn_cachep, cp); return; } /* hash it back to the table */ - ip_vs_conn_hash(cp); + ip_vs_conn_hash(cp->net, cp); expire_later: IP_VS_DBG(7, "delayed: conn->refcnt-1=%d conn->n_control=%d\n", @@ -748,18 +752,22 @@ 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 + * Create a new connection entry and hash it into the ip_vs_conn_tab, + * netns ptr will be stored in ip_vs_con here. */ struct ip_vs_conn * -ip_vs_conn_new(int af, int proto, const union nf_inet_addr *caddr, __be16 cport, +ip_vs_conn_new(struct net *net, int af, int proto, + const union nf_inet_addr *caddr, __be16 cport, const union nf_inet_addr *vaddr, __be16 vport, - const union nf_inet_addr *daddr, __be16 dport, unsigned flags, - struct ip_vs_dest *dest) + const union nf_inet_addr *daddr, __be16 dport, + unsigned flags, struct ip_vs_dest *dest) { struct ip_vs_conn *cp; - struct ip_vs_protocol *pp = ip_vs_proto_get(proto); + struct ip_vs_proto_data *pd = ip_vs_proto_data_get(net, proto); + struct ip_vs_protocol *pp; + struct netns_ipvs *ipvs = net->ipvs; - cp = kmem_cache_zalloc(ip_vs_conn_cachep, GFP_ATOMIC); + cp = kmem_cache_zalloc(ipvs->conn_cachep, GFP_ATOMIC); if (cp == NULL) { IP_VS_ERR_RL("%s(): no memory\n", __func__); return NULL; @@ -790,9 +798,9 @@ ip_vs_conn_new(int af, int proto, const union nf_inet_addr *caddr, __be16 cport, 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); + atomic_inc(&ipvs->conn_no_cport_cnt); /* Bind the connection with a destination server */ ip_vs_bind_dest(cp, dest); @@ -808,12 +816,14 @@ ip_vs_conn_new(int af, int proto, const union nf_inet_addr *caddr, __be16 cport, else #endif ip_vs_bind_xmit(cp); - - if (unlikely(pp && atomic_read(&pp->appcnt))) - ip_vs_bind_app(cp, pp); - + cp->net = net; /* netns ptr needed in timer */ + if( pd ) { + pp = pd->pp; + if (unlikely(pp && atomic_read(&pd->appcnt))) + ip_vs_bind_app(net, cp, pp); + } /* Hash it in the ip_vs_conn_tab finally */ - ip_vs_conn_hash(cp); + ip_vs_conn_hash(net, cp); return cp; } @@ -824,16 +834,33 @@ ip_vs_conn_new(int af, int proto, const union nf_inet_addr *caddr, __be16 cport, */ #ifdef CONFIG_PROC_FS +struct ipvs_private { + struct seq_net_private p; + void *private; +}; + +static inline void ipvs_seq_priv_set(struct seq_file *seq, void *data) +{ + struct ipvs_private *ipriv=(struct ipvs_private *)seq->private; + ipriv->private = data; +} +static inline void *ipvs_seq_priv_get(struct seq_file *seq) +{ + return ((struct ipvs_private *)seq->private)->private; +} + static void *ip_vs_conn_array(struct seq_file *seq, loff_t pos) { int idx; struct ip_vs_conn *cp; + struct net *net = seq_file_net(seq); + struct netns_ipvs *ipvs = net->ipvs; 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) { + list_for_each_entry(cp, &ipvs->conn_tab[idx], c_list) { if (pos-- == 0) { - seq->private = &ip_vs_conn_tab[idx]; + ipvs_seq_priv_set(seq, &ipvs->conn_tab[idx]); return cp; } } @@ -845,15 +872,17 @@ 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; + ipvs_seq_priv_set(seq, NULL); return *pos ? ip_vs_conn_array(seq, *pos - 1) :SEQ_START_TOKEN; } - + /* netns: conn_tab OK */ 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 list_head *e, *l = ipvs_seq_priv_get(seq); int idx; + struct net *net = seq_file_net(seq); + struct netns_ipvs *ipvs = net->ipvs; ++*pos; if (v == SEQ_START_TOKEN) @@ -863,27 +892,28 @@ static void *ip_vs_conn_seq_next(struct seq_file *seq, void *v, loff_t *pos) if ((e = cp->c_list.next) != l) return list_entry(e, struct ip_vs_conn, c_list); - idx = l - ip_vs_conn_tab; + idx = l - ipvs->conn_tab; ct_read_unlock_bh(idx); 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]; + list_for_each_entry(cp, &ipvs->conn_tab[idx], c_list) { + ipvs_seq_priv_set(seq, &ipvs->conn_tab[idx]); return cp; } ct_read_unlock_bh(idx); } - seq->private = NULL; + ipvs_seq_priv_set(seq, NULL); return NULL; } - +/* netns: conn_tab OK */ static void ip_vs_conn_seq_stop(struct seq_file *seq, void *v) { - struct list_head *l = seq->private; + struct list_head *l = ipvs_seq_priv_get(seq); + struct net *net = seq_file_net(seq); if (l) - ct_read_unlock_bh(l - ip_vs_conn_tab); + ct_read_unlock_bh(l - net->ipvs->conn_tab); } static int ip_vs_conn_seq_show(struct seq_file *seq, void *v) @@ -928,7 +958,16 @@ 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); + int ret; + struct ipvs_private *priv; + + ret = seq_open_net(inode, file, &ip_vs_conn_seq_ops, + sizeof(struct ipvs_private)); + if (!ret) { + priv = ((struct seq_file *)file->private_data)->private; + priv->private = NULL; + } + return ret; } static const struct file_operations ip_vs_conn_fops = { @@ -936,7 +975,8 @@ static const struct file_operations ip_vs_conn_fops = { .open = ip_vs_conn_open, .read = seq_read, .llseek = seq_lseek, - .release = seq_release, + .release = seq_release_private, + }; static const char *ip_vs_origin_name(unsigned flags) @@ -991,7 +1031,17 @@ 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); + int ret; + struct ipvs_private *ipriv; + + ret = seq_open_net(inode, file, &ip_vs_conn_sync_seq_ops, + sizeof(struct ipvs_private)); + if (!ret) { + ipriv = ((struct seq_file *)file->private_data)->private; + ipriv->private = NULL; + } + return ret; +// return seq_open(file, &ip_vs_conn_sync_seq_ops); } static const struct file_operations ip_vs_conn_sync_fops = { @@ -999,7 +1049,7 @@ static const struct file_operations ip_vs_conn_sync_fops = { .open = ip_vs_conn_sync_open, .read = seq_read, .llseek = seq_lseek, - .release = seq_release, + .release = seq_release_private, }; #endif @@ -1036,11 +1086,14 @@ static inline int todrop_entry(struct ip_vs_conn *cp) return 1; } -/* Called from keventd and must protect itself from softirqs */ -void ip_vs_random_dropentry(void) +/* Called from keventd and must protect itself from softirqs + * netns: conn_tab OK + */ +void ip_vs_random_dropentry(struct net *net) { int idx; struct ip_vs_conn *cp; + struct netns_ipvs *ipvs = net->ipvs; /* * Randomly scan 1/32 of the whole table every second @@ -1053,7 +1106,7 @@ void ip_vs_random_dropentry(void) */ ct_write_lock_bh(hash); - list_for_each_entry(cp, &ip_vs_conn_tab[hash], c_list) { + list_for_each_entry(cp, &ipvs->conn_tab[hash], c_list) { if (cp->flags & IP_VS_CONN_F_TEMPLATE) /* connection template */ continue; @@ -1091,11 +1144,13 @@ void ip_vs_random_dropentry(void) /* * Flush all the connection entries in the ip_vs_conn_tab + * netns: conn_tab OK */ -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; flush_again: for (idx = 0; idx < ip_vs_conn_tab_size; idx++) { @@ -1104,7 +1159,7 @@ static void ip_vs_conn_flush(void) */ ct_write_lock_bh(idx); - list_for_each_entry(cp, &ip_vs_conn_tab[idx], c_list) { + list_for_each_entry(cp, &ipvs->conn_tab[idx], c_list) { IP_VS_DBG(4, "del connection\n"); ip_vs_conn_expire_now(cp); @@ -1118,16 +1173,17 @@ 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; } } -int __init ip_vs_conn_init(void) +int __net_init __ip_vs_conn_init(struct net *net) { int idx; + struct netns_ipvs *ipvs = net->ipvs; /* Compute size and mask */ ip_vs_conn_tab_size = 1 << ip_vs_conn_tab_bits; @@ -1136,19 +1192,26 @@ int __init ip_vs_conn_init(void) /* * Allocate the connection hash table and initialize its list heads */ - ip_vs_conn_tab = vmalloc(ip_vs_conn_tab_size * + ipvs->conn_tab = vmalloc(ip_vs_conn_tab_size * sizeof(struct list_head)); - if (!ip_vs_conn_tab) + if (!ipvs->conn_tab) return -ENOMEM; /* Allocate ip_vs_conn slab cache */ - ip_vs_conn_cachep = kmem_cache_create("ip_vs_conn", + /* Todo: find a better way to name the cache */ + snprintf(ipvs->conn_cname, sizeof(ipvs->conn_cname)-1, + "ipvs_conn_%d", atomic_read(&conn_cache_nr) ); + atomic_inc(&conn_cache_nr); + + ipvs->conn_cachep = kmem_cache_create(ipvs->conn_cname, sizeof(struct ip_vs_conn), 0, SLAB_HWCACHE_ALIGN, NULL); - if (!ip_vs_conn_cachep) { - vfree(ip_vs_conn_tab); + if (!ipvs->conn_cachep) { + vfree(ipvs->conn_tab); return -ENOMEM; } + atomic_set(&ipvs->conn_count, 0); + atomic_set(&ipvs->conn_no_cport_cnt, 0); pr_info("Connection hash table configured " "(size=%d, memory=%ldKbytes)\n", @@ -1158,31 +1221,46 @@ int __init ip_vs_conn_init(void) sizeof(struct ip_vs_conn)); for (idx = 0; idx < ip_vs_conn_tab_size; idx++) { - INIT_LIST_HEAD(&ip_vs_conn_tab[idx]); + INIT_LIST_HEAD(&ipvs->conn_tab[idx]); } for (idx = 0; idx < CT_LOCKARRAY_SIZE; idx++) { rwlock_init(&__ip_vs_conntbl_lock_array[idx].l); } - 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)); + 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) { + /* flush all the connection entries first */ + ip_vs_conn_flush(net); + /* Release the empty cache */ + kmem_cache_destroy(net->ipvs->conn_cachep); + proc_net_remove(net, "ip_vs_conn"); + proc_net_remove(net, "ip_vs_conn_sync"); + vfree(net->ipvs->conn_tab); +} +static struct pernet_operations ipvs_conn_ops = { + .init = __ip_vs_conn_init, + .exit = __ip_vs_conn_cleanup, +}; -void ip_vs_conn_cleanup(void) +int __init ip_vs_conn_init(void) { - /* flush all the connection entries first */ - ip_vs_conn_flush(); + int rv; - /* 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); + rv = register_pernet_subsys(&ipvs_conn_ops); + + /* calculate the random value for connection hash */ + get_random_bytes(&ip_vs_conn_rnd, sizeof(ip_vs_conn_rnd)); + return rv; +} + +void ip_vs_conn_cleanup(void) +{ + unregister_pernet_subsys(&ipvs_conn_ops); }