leandrof/linux
1
0
Fork 0
forked from Minki/linux
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Merge tag 'ipvs2-for-v4.4' of https://git.kernel.org/pub/scm/linux/kernel/git/horms/ipvs-next

Browse Source 
Simon Horman says:

====================
Second Round of IPVS Updates for v4.4

please consider these bug fixes and extensive clean-ups of IPVS
from Eric Biederman for v4.4.

His excellent description of the changes, which is part of an even larger
set of clean-up work, is as follows:

  I am gradually working my way through the netfilter stack passing struct
  down into the netfilter hooks and from the netfilter hooks and from there
  down into the functions that actually care.  This removes the need for
  netfilter functions to guess how to figure out how to compute which
  network namespace they are in and instead provides a simple and reliable
  method to do so.

  The cleanups stand on their own but this is part of a larger effort to
  have routes with an output device that is not in the current network
  namespace.

  The IPVS code has been a bit more of a challenge than most.  Just passing
  struct net through to where it is needed did not feel clean to me.  The
  practical issue is that the ipvs code in most places actually wants
  struct netns_ipvs and not struct net.

  So as part of this process I have turned the relationship between struct
  net and the structs netns_ipvs, ip_vs_conn_param, ip_vs_conn, and
  ip_vs_service inside out.  I have modified the ipvs functions to take a
  struct netns_ipvs not a struct net.  The net is code with fewer
  conversions from one type of structure to another.  I did wind up adding
  a struct netns_ipvs parameter to quite a few functions that did not have
  it before so I could pass the structure down from the netfilter hooks to
  where it is actually needed to avoid guessing.

  I have broken up the work in a bunch of small patches so there is at
  least a chance and reviewing that each step I took is correct.  The
  series compiles at each step so bisecting it should not be a problem if
  something weird comes up.

  The first two changes in this series are actually bug fixes.  The first
  is a compile fix for a bug in sctp that came in, in the last round of
  ipvs changes merged into nf-next.  The second fixes an older bug where in
  pathological circumstances the wrong network namespace could be used when
  a proc file is written to.

  The rest of the patchset is a bunch of boring changes getting pushing
  struct netns_ipvs (and by extension ipvs->net) where it needs to be.
  Either by replacing struct net pointers or adding new struct netns_ipvs
  pointers.  With a handful of other minor cleanups (like removing
  skb_net).

I have decided include the bug fixes in this pull request. Patch one
relates to a bug that was added to nf-next recently and is thus not
applicable to nf . Patch two could arguably be promoted to a fix for v4.3
and stable though it does not appear to be severe enough to warrant that
course of action; let me know if you would like me to reconsider.
====================

Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
This commit is contained in:
Pablo Neira Ayuso 2015-09-25 01:37:21 +02:00
commit c3456026ad
18 changed files with 501 additions and 638 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

179
include/net/ip_vs.h
View File

@ -38,59 +38,6 @@ static inline struct netns_ipvs *net_ipvs(struct net* net)
return net->ipvs;
}
/* Get net ptr from skb in traffic cases
* use skb_sknet when call is from userland (ioctl or netlink)
*/
static inline struct net *skb_net(const struct sk_buff *skb)
{
#ifdef CONFIG_NET_NS
#ifdef CONFIG_IP_VS_DEBUG
/*
* This is used for debug only.
* Start with the most likely hit
* End with BUG
*/
if (likely(skb->dev && dev_net(skb->dev)))
return dev_net(skb->dev);
if (skb_dst(skb) && skb_dst(skb)->dev)
return dev_net(skb_dst(skb)->dev);
WARN(skb->sk, "Maybe skb_sknet should be used in %s() at line:%d\n",
__func__, __LINE__);
if (likely(skb->sk && sock_net(skb->sk)))
return sock_net(skb->sk);
pr_err("There is no net ptr to find in the skb in %s() line:%d\n",
__func__, __LINE__);
BUG();
#else
return dev_net(skb->dev ? : skb_dst(skb)->dev);
#endif
#else
return &init_net;
#endif
}
static inline struct net *skb_sknet(const struct sk_buff *skb)
{
#ifdef CONFIG_NET_NS
#ifdef CONFIG_IP_VS_DEBUG
/* Start with the most likely hit */
if (likely(skb->sk && sock_net(skb->sk)))
return sock_net(skb->sk);
WARN(skb->dev, "Maybe skb_net should be used instead in %s() line:%d\n",
__func__, __LINE__);
if (likely(skb->dev && dev_net(skb->dev)))
return dev_net(skb->dev);
pr_err("There is no net ptr to find in the skb in %s() line:%d\n",
__func__, __LINE__);
BUG();
#else
return sock_net(skb->sk);
#endif
#else
return &init_net;
#endif
}
/* This one needed for single_open_net since net is stored directly in
* private not as a struct i.e. seq_file_net can't be used.
*/
@ -483,22 +430,25 @@ struct ip_vs_protocol {
void (*exit)(struct ip_vs_protocol *pp);
int (*init_netns)(struct net *net, struct ip_vs_proto_data *pd);
int (*init_netns)(struct netns_ipvs *ipvs, struct ip_vs_proto_data *pd);
void (*exit_netns)(struct net *net, struct ip_vs_proto_data *pd);
void (*exit_netns)(struct netns_ipvs *ipvs, struct ip_vs_proto_data *pd);
int (*conn_schedule)(int af, struct sk_buff *skb,
int (*conn_schedule)(struct netns_ipvs *ipvs,
int af, struct sk_buff *skb,
struct ip_vs_proto_data *pd,
int *verdict, struct ip_vs_conn **cpp,
struct ip_vs_iphdr *iph);
struct ip_vs_conn *
(*conn_in_get)(int af,
(*conn_in_get)(struct netns_ipvs *ipvs,
int af,
const struct sk_buff *skb,
const struct ip_vs_iphdr *iph);
struct ip_vs_conn *
(*conn_out_get)(int af,
(*conn_out_get)(struct netns_ipvs *ipvs,
int af,
const struct sk_buff *skb,
const struct ip_vs_iphdr *iph);
@ -517,9 +467,9 @@ struct ip_vs_protocol {
const struct sk_buff *skb,
struct ip_vs_proto_data *pd);
int (*register_app)(struct net *net, struct ip_vs_app *inc);
int (*register_app)(struct netns_ipvs *ipvs, struct ip_vs_app *inc);
void (*unregister_app)(struct net *net, struct ip_vs_app *inc);
void (*unregister_app)(struct netns_ipvs *ipvs, struct ip_vs_app *inc);
int (*app_conn_bind)(struct ip_vs_conn *cp);
@ -541,11 +491,11 @@ struct ip_vs_proto_data {
};
struct ip_vs_protocol *ip_vs_proto_get(unsigned short proto);
struct ip_vs_proto_data *ip_vs_proto_data_get(struct net *net,
struct ip_vs_proto_data *ip_vs_proto_data_get(struct netns_ipvs *ipvs,
unsigned short proto);
struct ip_vs_conn_param {
struct net *net;
struct netns_ipvs *ipvs;
const union nf_inet_addr *caddr;
const union nf_inet_addr *vaddr;
__be16 cport;
@ -572,9 +522,7 @@ struct ip_vs_conn {
volatile __u32 flags; /* status flags */
__u16 protocol; /* Which protocol (TCP/UDP) */
__u16 daf; /* Address family of the dest */
#ifdef CONFIG_NET_NS
struct net *net; /* Name space */
#endif
struct netns_ipvs *ipvs;
/* counter and timer */
atomic_t refcnt; /* reference count */
@ -621,33 +569,6 @@ struct ip_vs_conn {
struct rcu_head rcu_head;
};
/* 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 ip_vs_dest_user
* for IPv6 support.
*
@ -707,7 +628,7 @@ struct ip_vs_service {
unsigned int flags; /* service status flags */
unsigned int timeout; /* persistent timeout in ticks */
__be32 netmask; /* grouping granularity, mask/plen */
struct net *net;
struct netns_ipvs *ipvs;
struct list_head destinations; /* real server d-linked list */
__u32 num_dests; /* number of servers */
@ -1127,6 +1048,11 @@ static inline int sysctl_ignore_tunneled(struct netns_ipvs *ipvs)
return ipvs->sysctl_ignore_tunneled;
}
static inline int sysctl_cache_bypass(struct netns_ipvs *ipvs)
{
return ipvs->sysctl_cache_bypass;
}
#else
static inline int sysctl_sync_threshold(struct netns_ipvs *ipvs)
@ -1209,6 +1135,11 @@ static inline int sysctl_ignore_tunneled(struct netns_ipvs *ipvs)
return 0;
}
static inline int sysctl_cache_bypass(struct netns_ipvs *ipvs)
{
return 0;
}
#endif
/* IPVS core functions
@ -1230,14 +1161,14 @@ enum {
IP_VS_DIR_LAST,
};
static inline void ip_vs_conn_fill_param(struct net *net, int af, int protocol,
static inline void ip_vs_conn_fill_param(struct netns_ipvs *ipvs, 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->ipvs = ipvs;
p->af = af;
p->protocol = protocol;
p->caddr = caddr;
@ -1251,12 +1182,14 @@ static inline void ip_vs_conn_fill_param(struct net *net, int af, int protocol,
struct ip_vs_conn *ip_vs_conn_in_get(const struct ip_vs_conn_param *p);
struct ip_vs_conn *ip_vs_ct_in_get(const struct ip_vs_conn_param *p);
struct ip_vs_conn * ip_vs_conn_in_get_proto(int af, const struct sk_buff *skb,
struct ip_vs_conn * ip_vs_conn_in_get_proto(struct netns_ipvs *ipvs, int af,
const struct sk_buff *skb,
const struct ip_vs_iphdr *iph);
struct ip_vs_conn *ip_vs_conn_out_get(const struct ip_vs_conn_param *p);
struct ip_vs_conn * ip_vs_conn_out_get_proto(int af, const struct sk_buff *skb,
struct ip_vs_conn * ip_vs_conn_out_get_proto(struct netns_ipvs *ipvs, int af,
const struct sk_buff *skb,
const struct ip_vs_iphdr *iph);
/* Get reference to gain full access to conn.
@ -1285,9 +1218,9 @@ void ip_vs_conn_expire_now(struct ip_vs_conn *cp);
const char *ip_vs_state_name(__u16 proto, int state);
void ip_vs_tcp_conn_listen(struct net *net, struct ip_vs_conn *cp);
void ip_vs_tcp_conn_listen(struct ip_vs_conn *cp);
int ip_vs_check_template(struct ip_vs_conn *ct);
void ip_vs_random_dropentry(struct net *net);
void ip_vs_random_dropentry(struct netns_ipvs *ipvs);
int ip_vs_conn_init(void);
void ip_vs_conn_cleanup(void);
@ -1352,29 +1285,29 @@ ip_vs_control_add(struct ip_vs_conn *cp, struct ip_vs_conn *ctl_cp)
}
/* IPVS netns init & cleanup functions */
int ip_vs_estimator_net_init(struct net *net);
int ip_vs_control_net_init(struct net *net);
int ip_vs_protocol_net_init(struct net *net);
int ip_vs_app_net_init(struct net *net);
int ip_vs_conn_net_init(struct net *net);
int ip_vs_sync_net_init(struct net *net);
void ip_vs_conn_net_cleanup(struct net *net);
void ip_vs_app_net_cleanup(struct net *net);
void ip_vs_protocol_net_cleanup(struct net *net);
void ip_vs_control_net_cleanup(struct net *net);
void ip_vs_estimator_net_cleanup(struct net *net);
void ip_vs_sync_net_cleanup(struct net *net);
void ip_vs_service_net_cleanup(struct net *net);
int ip_vs_estimator_net_init(struct netns_ipvs *ipvs);
int ip_vs_control_net_init(struct netns_ipvs *ipvs);
int ip_vs_protocol_net_init(struct netns_ipvs *ipvs);
int ip_vs_app_net_init(struct netns_ipvs *ipvs);
int ip_vs_conn_net_init(struct netns_ipvs *ipvs);
int ip_vs_sync_net_init(struct netns_ipvs *ipvs);
void ip_vs_conn_net_cleanup(struct netns_ipvs *ipvs);
void ip_vs_app_net_cleanup(struct netns_ipvs *ipvs);
void ip_vs_protocol_net_cleanup(struct netns_ipvs *ipvs);
void ip_vs_control_net_cleanup(struct netns_ipvs *ipvs);
void ip_vs_estimator_net_cleanup(struct netns_ipvs *ipvs);
void ip_vs_sync_net_cleanup(struct netns_ipvs *ipvs);
void ip_vs_service_net_cleanup(struct netns_ipvs *ipvs);
/* IPVS application functions
* (from ip_vs_app.c)
*/
#define IP_VS_APP_MAX_PORTS 8
struct ip_vs_app *register_ip_vs_app(struct net *net, struct ip_vs_app *app);
void unregister_ip_vs_app(struct net *net, struct ip_vs_app *app);
struct ip_vs_app *register_ip_vs_app(struct netns_ipvs *ipvs, struct ip_vs_app *app);
void unregister_ip_vs_app(struct netns_ipvs *ipvs, struct ip_vs_app *app);
int ip_vs_bind_app(struct ip_vs_conn *cp, struct ip_vs_protocol *pp);
void ip_vs_unbind_app(struct ip_vs_conn *cp);
int register_ip_vs_app_inc(struct net *net, struct ip_vs_app *app, __u16 proto,
int register_ip_vs_app_inc(struct netns_ipvs *ipvs, struct ip_vs_app *app, __u16 proto,
__u16 port);
int ip_vs_app_inc_get(struct ip_vs_app *inc);
void ip_vs_app_inc_put(struct ip_vs_app *inc);
@ -1439,10 +1372,10 @@ extern struct ip_vs_stats ip_vs_stats;
extern int sysctl_ip_vs_sync_ver;
struct ip_vs_service *
ip_vs_service_find(struct net *net, int af, __u32 fwmark, __u16 protocol,
ip_vs_service_find(struct netns_ipvs *ipvs, int af, __u32 fwmark, __u16 protocol,
const union nf_inet_addr *vaddr, __be16 vport);
bool ip_vs_has_real_service(struct net *net, int af, __u16 protocol,
bool ip_vs_has_real_service(struct netns_ipvs *ipvs, int af, __u16 protocol,
const union nf_inet_addr *daddr, __be16 dport);
int ip_vs_use_count_inc(void);
@ -1452,7 +1385,7 @@ void ip_vs_unregister_nl_ioctl(void);
int ip_vs_control_init(void);
void ip_vs_control_cleanup(void);
struct ip_vs_dest *
ip_vs_find_dest(struct net *net, int svc_af, int dest_af,
ip_vs_find_dest(struct netns_ipvs *ipvs, int svc_af, int dest_af,
const union nf_inet_addr *daddr, __be16 dport,
const union nf_inet_addr *vaddr, __be16 vport,
__u16 protocol, __u32 fwmark, __u32 flags);
@ -1478,14 +1411,14 @@ static inline void ip_vs_dest_put_and_free(struct ip_vs_dest *dest)
/* IPVS sync daemon data and function prototypes
* (from ip_vs_sync.c)
*/
int start_sync_thread(struct net *net, struct ipvs_sync_daemon_cfg *cfg,
int start_sync_thread(struct netns_ipvs *ipvs, struct ipvs_sync_daemon_cfg *cfg,
int state);
int stop_sync_thread(struct net *net, int state);
void ip_vs_sync_conn(struct net *net, struct ip_vs_conn *cp, int pkts);
int stop_sync_thread(struct netns_ipvs *ipvs, int state);
void ip_vs_sync_conn(struct netns_ipvs *ipvs, struct ip_vs_conn *cp, int pkts);
/* IPVS rate estimator prototypes (from ip_vs_est.c) */
void ip_vs_start_estimator(struct net *net, struct ip_vs_stats *stats);
void ip_vs_stop_estimator(struct net *net, struct ip_vs_stats *stats);
void ip_vs_start_estimator(struct netns_ipvs *ipvs, struct ip_vs_stats *stats);
void ip_vs_stop_estimator(struct netns_ipvs *ipvs, struct ip_vs_stats *stats);
void ip_vs_zero_estimator(struct ip_vs_stats *stats);
void ip_vs_read_estimator(struct ip_vs_kstats *dst, struct ip_vs_stats *stats);

36
net/netfilter/ipvs/ip_vs_app.c
View File

@ -75,7 +75,7 @@ static void ip_vs_app_inc_rcu_free(struct rcu_head *head)
* Allocate/initialize app incarnation and register it in proto apps.
*/
static int
ip_vs_app_inc_new(struct net *net, struct ip_vs_app *app, __u16 proto,
ip_vs_app_inc_new(struct netns_ipvs *ipvs, struct ip_vs_app *app, __u16 proto,
__u16 port)
{
struct ip_vs_protocol *pp;
@ -107,7 +107,7 @@ ip_vs_app_inc_new(struct net *net, struct ip_vs_app *app, __u16 proto,
}
}
ret = pp->register_app(net, inc);
ret = pp->register_app(ipvs, inc);
if (ret)
goto out;
@ -127,7 +127,7 @@ ip_vs_app_inc_new(struct net *net, struct ip_vs_app *app, __u16 proto,
* Release app incarnation
*/
static void
ip_vs_app_inc_release(struct net *net, struct ip_vs_app *inc)
ip_vs_app_inc_release(struct netns_ipvs *ipvs, struct ip_vs_app *inc)
{
struct ip_vs_protocol *pp;
@ -135,7 +135,7 @@ ip_vs_app_inc_release(struct net *net, struct ip_vs_app *inc)
return;
if (pp->unregister_app)
pp->unregister_app(net, inc);
pp->unregister_app(ipvs, inc);
IP_VS_DBG(9, "%s App %s:%u unregistered\n",
pp->name, inc->name, ntohs(inc->port));
@ -175,14 +175,14 @@ void ip_vs_app_inc_put(struct ip_vs_app *inc)
* Register an application incarnation in protocol applications
*/
int
register_ip_vs_app_inc(struct net *net, struct ip_vs_app *app, __u16 proto,
register_ip_vs_app_inc(struct netns_ipvs *ipvs, struct ip_vs_app *app, __u16 proto,
__u16 port)
{
int result;
mutex_lock(&__ip_vs_app_mutex);
result = ip_vs_app_inc_new(net, app, proto, port);
result = ip_vs_app_inc_new(ipvs, app, proto, port);
mutex_unlock(&__ip_vs_app_mutex);
@ -191,15 +191,11 @@ register_ip_vs_app_inc(struct net *net, struct ip_vs_app *app, __u16 proto,
/* Register application for netns */
struct ip_vs_app *register_ip_vs_app(struct net *net, struct ip_vs_app *app)
struct ip_vs_app *register_ip_vs_app(struct netns_ipvs *ipvs, struct ip_vs_app *app)
{
struct netns_ipvs *ipvs = net_ipvs(net);
struct ip_vs_app *a;
int err = 0;
if (!ipvs)
return ERR_PTR(-ENOENT);
mutex_lock(&__ip_vs_app_mutex);
list_for_each_entry(a, &ipvs->app_list, a_list) {
@ -230,21 +226,17 @@ out_unlock:
* We are sure there are no app incarnations attached to services
* Caller should use synchronize_rcu() or rcu_barrier()
*/
void unregister_ip_vs_app(struct net *net, struct ip_vs_app *app)
void unregister_ip_vs_app(struct netns_ipvs *ipvs, struct ip_vs_app *app)
{
struct netns_ipvs *ipvs = net_ipvs(net);
struct ip_vs_app *a, *anxt, *inc, *nxt;
if (!ipvs)
return;
mutex_lock(&__ip_vs_app_mutex);
list_for_each_entry_safe(a, anxt, &ipvs->app_list, a_list) {
if (app && strcmp(app->name, a->name))
continue;
list_for_each_entry_safe(inc, nxt, &a->incs_list, a_list) {
ip_vs_app_inc_release(net, inc);
ip_vs_app_inc_release(ipvs, inc);
}
list_del(&a->a_list);
@ -611,17 +603,19 @@ static const struct file_operations ip_vs_app_fops = {
};
#endif
int __net_init ip_vs_app_net_init(struct net *net)
int __net_init ip_vs_app_net_init(struct netns_ipvs *ipvs)
{
struct netns_ipvs *ipvs = net_ipvs(net);
struct net *net = ipvs->net;
INIT_LIST_HEAD(&ipvs->app_list);
proc_create("ip_vs_app", 0, net->proc_net, &ip_vs_app_fops);
return 0;
}
void __net_exit ip_vs_app_net_cleanup(struct net *net)
void __net_exit ip_vs_app_net_cleanup(struct netns_ipvs *ipvs)
{
unregister_ip_vs_app(net, NULL /* all */);
struct net *net = ipvs->net;
unregister_ip_vs_app(ipvs, NULL /* all */);
remove_proc_entry("ip_vs_app", net->proc_net);
}

76
net/netfilter/ipvs/ip_vs_conn.c
View File

@ -108,7 +108,7 @@ static inline void ct_write_unlock_bh(unsigned int key)
/*
* Returns hash value for IPVS connection entry
*/
static unsigned int ip_vs_conn_hashkey(struct net *net, int af, unsigned int proto,
static unsigned int ip_vs_conn_hashkey(struct netns_ipvs *ipvs, int af, unsigned int proto,
const union nf_inet_addr *addr,
__be16 port)
{
@ -116,11 +116,11 @@ static unsigned int ip_vs_conn_hashkey(struct net *net, int af, unsigned int pro
if (af == AF_INET6)
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;
((size_t)ipvs>>8)) & ip_vs_conn_tab_mask;
#endif
return (jhash_3words((__force u32)addr->ip, (__force u32)port, proto,
ip_vs_conn_rnd) ^
((size_t)net>>8)) & ip_vs_conn_tab_mask;
((size_t)ipvs>>8)) & ip_vs_conn_tab_mask;
}
static unsigned int ip_vs_conn_hashkey_param(const struct ip_vs_conn_param *p,
@ -141,14 +141,14 @@ static unsigned int ip_vs_conn_hashkey_param(const struct ip_vs_conn_param *p,
port = p->vport;
}
return ip_vs_conn_hashkey(p->net, p->af, p->protocol, addr, port);
return ip_vs_conn_hashkey(p->ipvs, 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(ip_vs_conn_net(cp), cp->af, cp->protocol,
ip_vs_conn_fill_param(cp->ipvs, cp->af, cp->protocol,
&cp->caddr, cp->cport, NULL, 0, &p);
if (cp->pe) {
@ -279,7 +279,7 @@ __ip_vs_conn_in_get(const struct ip_vs_conn_param *p)
ip_vs_addr_equal(p->af, p->vaddr, &cp->vaddr) &&
((!p->cport) ^ (!(cp->flags & IP_VS_CONN_F_NO_CPORT))) &&
p->protocol == cp->protocol &&
ip_vs_conn_net_eq(cp, p->net)) {
cp->ipvs == p->ipvs) {
if (!__ip_vs_conn_get(cp))
continue;
/* HIT */
@ -314,33 +314,34 @@ struct ip_vs_conn *ip_vs_conn_in_get(const struct ip_vs_conn_param *p)
}
static int
ip_vs_conn_fill_param_proto(int af, const struct sk_buff *skb,
ip_vs_conn_fill_param_proto(struct netns_ipvs *ipvs,
int af, const struct sk_buff *skb,
const struct ip_vs_iphdr *iph,
struct ip_vs_conn_param *p)
{
__be16 _ports[2], *pptr;
struct net *net = skb_net(skb);
pptr = frag_safe_skb_hp(skb, iph->len, sizeof(_ports), _ports, iph);
if (pptr == NULL)
return 1;
if (likely(!ip_vs_iph_inverse(iph)))
ip_vs_conn_fill_param(net, af, iph->protocol, &iph->saddr,
ip_vs_conn_fill_param(ipvs, af, iph->protocol, &iph->saddr,
pptr[0], &iph->daddr, pptr[1], p);
else
ip_vs_conn_fill_param(net, af, iph->protocol, &iph->daddr,
ip_vs_conn_fill_param(ipvs, af, iph->protocol, &iph->daddr,
pptr[1], &iph->saddr, pptr[0], p);
return 0;
}
struct ip_vs_conn *
ip_vs_conn_in_get_proto(int af, const struct sk_buff *skb,
ip_vs_conn_in_get_proto(struct netns_ipvs *ipvs, int af,
const struct sk_buff *skb,
const struct ip_vs_iphdr *iph)
{
struct ip_vs_conn_param p;
if (ip_vs_conn_fill_param_proto(af, skb, iph, &p))
if (ip_vs_conn_fill_param_proto(ipvs, af, skb, iph, &p))
return NULL;
return ip_vs_conn_in_get(&p);
@ -359,7 +360,7 @@ struct ip_vs_conn *ip_vs_ct_in_get(const struct ip_vs_conn_param *p)
hlist_for_each_entry_rcu(cp, &ip_vs_conn_tab[hash], c_list) {
if (unlikely(p->pe_data && p->pe->ct_match)) {
if (!ip_vs_conn_net_eq(cp, p->net))
if (cp->ipvs != p->ipvs)
continue;
if (p->pe == cp->pe && p->pe->ct_match(p, cp)) {
if (__ip_vs_conn_get(cp))
@ -377,7 +378,7 @@ struct ip_vs_conn *ip_vs_ct_in_get(const struct ip_vs_conn_param *p)
p->vport == cp->vport && p->cport == cp->cport &&
cp->flags & IP_VS_CONN_F_TEMPLATE &&
p->protocol == cp->protocol &&
ip_vs_conn_net_eq(cp, p->net)) {
cp->ipvs == p->ipvs) {
if (__ip_vs_conn_get(cp))
goto out;
}
@ -418,7 +419,7 @@ struct ip_vs_conn *ip_vs_conn_out_get(const struct ip_vs_conn_param *p)
ip_vs_addr_equal(p->af, p->vaddr, &cp->caddr) &&
ip_vs_addr_equal(p->af, p->caddr, &cp->daddr) &&
p->protocol == cp->protocol &&
ip_vs_conn_net_eq(cp, p->net)) {
cp->ipvs == p->ipvs) {
if (!__ip_vs_conn_get(cp))
continue;
/* HIT */
@ -439,12 +440,13 @@ struct ip_vs_conn *ip_vs_conn_out_get(const struct ip_vs_conn_param *p)
}
struct ip_vs_conn *
ip_vs_conn_out_get_proto(int af, const struct sk_buff *skb,
ip_vs_conn_out_get_proto(struct netns_ipvs *ipvs, int af,
const struct sk_buff *skb,
const struct ip_vs_iphdr *iph)
{
struct ip_vs_conn_param p;
if (ip_vs_conn_fill_param_proto(af, skb, iph, &p))
if (ip_vs_conn_fill_param_proto(ipvs, af, skb, iph, &p))
return NULL;
return ip_vs_conn_out_get(&p);
@ -638,7 +640,7 @@ void ip_vs_try_bind_dest(struct ip_vs_conn *cp)
* so we can make the assumption that the svc_af is the same as the
* dest_af
*/
dest = ip_vs_find_dest(ip_vs_conn_net(cp), cp->af, cp->af, &cp->daddr,
dest = ip_vs_find_dest(cp->ipvs, cp->af, cp->af, &cp->daddr,
cp->dport, &cp->vaddr, cp->vport,
cp->protocol, cp->fwmark, cp->flags);
if (dest) {
@ -668,7 +670,7 @@ void ip_vs_try_bind_dest(struct ip_vs_conn *cp)
#endif
ip_vs_bind_xmit(cp);
pd = ip_vs_proto_data_get(ip_vs_conn_net(cp), cp->protocol);
pd = ip_vs_proto_data_get(cp->ipvs, cp->protocol);
if (pd && atomic_read(&pd->appcnt))
ip_vs_bind_app(cp, pd->pp);
}
@ -746,7 +748,7 @@ static int expire_quiescent_template(struct netns_ipvs *ipvs,
int ip_vs_check_template(struct ip_vs_conn *ct)
{
struct ip_vs_dest *dest = ct->dest;
struct netns_ipvs *ipvs = net_ipvs(ip_vs_conn_net(ct));
struct netns_ipvs *ipvs = ct->ipvs;
/*
* Checking the dest server status.
@ -800,8 +802,7 @@ static void ip_vs_conn_rcu_free(struct rcu_head *head)
static void ip_vs_conn_expire(unsigned long data)
{
struct ip_vs_conn *cp = (struct ip_vs_conn *)data;
struct net *net = ip_vs_conn_net(cp);
struct netns_ipvs *ipvs = net_ipvs(net);
struct netns_ipvs *ipvs = cp->ipvs;
/*
* do I control anybody?
@ -847,7 +848,7 @@ static void ip_vs_conn_expire(unsigned long data)
cp->timeout = 60*HZ;
if (ipvs->sync_state & IP_VS_STATE_MASTER)
ip_vs_sync_conn(net, cp, sysctl_sync_threshold(ipvs));
ip_vs_sync_conn(ipvs, cp, sysctl_sync_threshold(ipvs));
ip_vs_conn_put(cp);
}
@ -875,8 +876,8 @@ ip_vs_conn_new(const struct ip_vs_conn_param *p, int dest_af,
struct ip_vs_dest *dest, __u32 fwmark)
{
struct ip_vs_conn *cp;
struct netns_ipvs *ipvs = net_ipvs(p->net);
struct ip_vs_proto_data *pd = ip_vs_proto_data_get(p->net,
struct netns_ipvs *ipvs = p->ipvs;
struct ip_vs_proto_data *pd = ip_vs_proto_data_get(p->ipvs,
p->protocol);
cp = kmem_cache_alloc(ip_vs_conn_cachep, GFP_ATOMIC);
@ -887,7 +888,7 @@ ip_vs_conn_new(const struct ip_vs_conn_param *p, int dest_af,
INIT_HLIST_NODE(&cp->c_list);
setup_timer(&cp->timer, ip_vs_conn_expire, (unsigned long)cp);
ip_vs_conn_net_set(cp, p->net);
cp->ipvs = ipvs;
cp->af = p->af;
cp->daf = dest_af;
cp->protocol = p->protocol;
@ -1061,7 +1062,7 @@ static int ip_vs_conn_seq_show(struct seq_file *seq, void *v)
size_t len = 0;
char dbuf[IP_VS_ADDRSTRLEN];
if (!ip_vs_conn_net_eq(cp, net))
if (!net_eq(cp->ipvs->net, net))
return 0;
if (cp->pe_data) {
pe_data[0] = ' ';
@ -1146,7 +1147,7 @@ static int ip_vs_conn_sync_seq_show(struct seq_file *seq, void *v)
const struct ip_vs_conn *cp = v;
struct net *net = seq_file_net(seq);
if (!ip_vs_conn_net_eq(cp, net))
if (!net_eq(cp->ipvs->net, net))
return 0;
#ifdef CONFIG_IP_VS_IPV6
@ -1240,7 +1241,7 @@ static inline int todrop_entry(struct ip_vs_conn *cp)
}
/* Called from keventd and must protect itself from softirqs */
void ip_vs_random_dropentry(struct net *net)
void ip_vs_random_dropentry(struct netns_ipvs *ipvs)
{
int idx;
struct ip_vs_conn *cp, *cp_c;
@ -1256,7 +1257,7 @@ void ip_vs_random_dropentry(struct net *net)
if (cp->flags & IP_VS_CONN_F_TEMPLATE)
/* connection template */
continue;
if (!ip_vs_conn_net_eq(cp, net))
if (cp->ipvs != ipvs)
continue;
if (cp->protocol == IPPROTO_TCP) {
switch(cp->state) {
@ -1308,18 +1309,17 @@ void ip_vs_random_dropentry(struct net *net)
/*
* Flush all the connection entries in the ip_vs_conn_tab
*/
static void ip_vs_conn_flush(struct net *net)
static void ip_vs_conn_flush(struct netns_ipvs *ipvs)
{
int idx;
struct ip_vs_conn *cp, *cp_c;
struct netns_ipvs *ipvs = net_ipvs(net);
flush_again:
rcu_read_lock();
for (idx = 0; idx < ip_vs_conn_tab_size; idx++) {
hlist_for_each_entry_rcu(cp, &ip_vs_conn_tab[idx], c_list) {
if (!ip_vs_conn_net_eq(cp, net))
if (cp->ipvs != ipvs)
continue;
IP_VS_DBG(4, "del connection\n");
ip_vs_conn_expire_now(cp);
@ -1345,9 +1345,9 @@ flush_again:
/*
* per netns init and exit
*/
int __net_init ip_vs_conn_net_init(struct net *net)
int __net_init ip_vs_conn_net_init(struct netns_ipvs *ipvs)
{
struct netns_ipvs *ipvs = net_ipvs(net);
struct net *net = ipvs->net;
atomic_set(&ipvs->conn_count, 0);
@ -1356,10 +1356,12 @@ int __net_init ip_vs_conn_net_init(struct net *net)
return 0;
}
void __net_exit ip_vs_conn_net_cleanup(struct net *net)
void __net_exit ip_vs_conn_net_cleanup(struct netns_ipvs *ipvs)
{
struct net *net = ipvs->net;
/* flush all the connection entries first */
ip_vs_conn_flush(net);
ip_vs_conn_flush(ipvs);
remove_proc_entry("ip_vs_conn", net->proc_net);
remove_proc_entry("ip_vs_conn_sync", net->proc_net);
}

228
net/netfilter/ipvs/ip_vs_core.c
View File

@ -112,7 +112,7 @@ static inline void
ip_vs_in_stats(struct ip_vs_conn *cp, struct sk_buff *skb)
{
struct ip_vs_dest *dest = cp->dest;
struct netns_ipvs *ipvs = net_ipvs(skb_net(skb));
struct netns_ipvs *ipvs = cp->ipvs;
if (dest && (dest->flags & IP_VS_DEST_F_AVAILABLE)) {
struct ip_vs_cpu_stats *s;
@ -146,7 +146,7 @@ static inline void
ip_vs_out_stats(struct ip_vs_conn *cp, struct sk_buff *skb)
{
struct ip_vs_dest *dest = cp->dest;
struct netns_ipvs *ipvs = net_ipvs(skb_net(skb));
struct netns_ipvs *ipvs = cp->ipvs;
if (dest && (dest->flags & IP_VS_DEST_F_AVAILABLE)) {
struct ip_vs_cpu_stats *s;
@ -179,7 +179,7 @@ ip_vs_out_stats(struct ip_vs_conn *cp, struct sk_buff *skb)
static inline void
ip_vs_conn_stats(struct ip_vs_conn *cp, struct ip_vs_service *svc)
{
struct netns_ipvs *ipvs = net_ipvs(svc->net);
struct netns_ipvs *ipvs = svc->ipvs;
struct ip_vs_cpu_stats *s;
s = this_cpu_ptr(cp->dest->stats.cpustats);
@ -215,7 +215,7 @@ 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->net, svc->af, protocol, caddr, cport, vaddr,
ip_vs_conn_fill_param(svc->ipvs, svc->af, protocol, caddr, cport, vaddr,
vport, p);
p->pe = rcu_dereference(svc->pe);
if (p->pe && p->pe->fill_param)
@ -376,7 +376,7 @@ ip_vs_sched_persist(struct ip_vs_service *svc,
/*
* Create a new connection according to the template
*/
ip_vs_conn_fill_param(svc->net, svc->af, iph->protocol, src_addr,
ip_vs_conn_fill_param(svc->ipvs, svc->af, iph->protocol, src_addr,
src_port, dst_addr, dst_port, &param);
cp = ip_vs_conn_new(&param, dest->af, &dest->addr, dport, flags, dest,
@ -469,7 +469,7 @@ ip_vs_schedule(struct ip_vs_service *svc, struct sk_buff *skb,
*/
if ((!skb->dev || skb->dev->flags & IFF_LOOPBACK)) {
iph->hdr_flags ^= IP_VS_HDR_INVERSE;
cp = pp->conn_in_get(svc->af, skb, iph);
cp = pp->conn_in_get(svc->ipvs, svc->af, skb, iph);
iph->hdr_flags ^= IP_VS_HDR_INVERSE;
if (cp) {
@ -524,7 +524,7 @@ ip_vs_schedule(struct ip_vs_service *svc, struct sk_buff *skb,
{
struct ip_vs_conn_param p;
ip_vs_conn_fill_param(svc->net, svc->af, iph->protocol,
ip_vs_conn_fill_param(svc->ipvs, svc->af, iph->protocol,
caddr, cport, vaddr, vport, &p);
cp = ip_vs_conn_new(&p, dest->af, &dest->addr,
dest->port ? dest->port : vport,
@ -568,25 +568,18 @@ int ip_vs_leave(struct ip_vs_service *svc, struct sk_buff *skb,
struct ip_vs_proto_data *pd, struct ip_vs_iphdr *iph)
{
__be16 _ports[2], *pptr, dport;
#ifdef CONFIG_SYSCTL
struct net *net;
struct netns_ipvs *ipvs;
#endif
struct netns_ipvs *ipvs = svc->ipvs;
struct net *net = ipvs->net;
pptr = frag_safe_skb_hp(skb, iph->len, sizeof(_ports), _ports, iph);
if (!pptr)
return NF_DROP;
dport = likely(!ip_vs_iph_inverse(iph)) ? pptr[1] : pptr[0];
#ifdef CONFIG_SYSCTL
net = skb_net(skb);
/* if it is fwmark-based service, the cache_bypass sysctl is up
and the destination is a non-local unicast, then create
a cache_bypass connection entry */
ipvs = net_ipvs(net);
if (ipvs->sysctl_cache_bypass && svc->fwmark &&
if (sysctl_cache_bypass(ipvs) && svc->fwmark &&
!(iph->hdr_flags & (IP_VS_HDR_INVERSE | IP_VS_HDR_ICMP)) &&
ip_vs_addr_is_unicast(net, svc->af, &iph->daddr)) {
int ret;
@ -600,7 +593,7 @@ 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->net, svc->af, iph->protocol,
ip_vs_conn_fill_param(svc->ipvs, svc->af, iph->protocol,
&iph->saddr, pptr[0],
&iph->daddr, pptr[1], &p);
cp = ip_vs_conn_new(&p, svc->af, &daddr, 0,
@ -624,7 +617,6 @@ int ip_vs_leave(struct ip_vs_service *svc, struct sk_buff *skb,
ip_vs_conn_put(cp);
return ret;
}
#endif
/*
* When the virtual ftp service is presented, packets destined
@ -647,11 +639,8 @@ int ip_vs_leave(struct ip_vs_service *svc, struct sk_buff *skb,
*/
#ifdef CONFIG_IP_VS_IPV6
if (svc->af == AF_INET6) {
if (!skb->dev) {
struct net *net_ = dev_net(skb_dst(skb)->dev);
skb->dev = net_->loopback_dev;
}
if (!skb->dev)
skb->dev = net->loopback_dev;
icmpv6_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_PORT_UNREACH, 0);
} else
#endif
@ -662,15 +651,13 @@ int ip_vs_leave(struct ip_vs_service *svc, struct sk_buff *skb,
#ifdef CONFIG_SYSCTL
static int sysctl_snat_reroute(struct sk_buff *skb)
static int sysctl_snat_reroute(struct netns_ipvs *ipvs)
{
struct netns_ipvs *ipvs = net_ipvs(skb_net(skb));
return ipvs->sysctl_snat_reroute;
}
static int sysctl_nat_icmp_send(struct net *net)
static int sysctl_nat_icmp_send(struct netns_ipvs *ipvs)
{
struct netns_ipvs *ipvs = net_ipvs(net);
return ipvs->sysctl_nat_icmp_send;
}
@ -681,8 +668,8 @@ static int sysctl_expire_nodest_conn(struct netns_ipvs *ipvs)
#else
static int sysctl_snat_reroute(struct sk_buff *skb) { return 0; }
static int sysctl_nat_icmp_send(struct net *net) { return 0; }
static int sysctl_snat_reroute(struct netns_ipvs *ipvs) { return 0; }
static int sysctl_nat_icmp_send(struct netns_ipvs *ipvs) { return 0; }
static int sysctl_expire_nodest_conn(struct netns_ipvs *ipvs) { return 0; }
#endif
@ -701,7 +688,8 @@ static inline enum ip_defrag_users ip_vs_defrag_user(unsigned int hooknum)
return IP_DEFRAG_VS_OUT;
}
static inline int ip_vs_gather_frags(struct sk_buff *skb, u_int32_t user)
static inline int ip_vs_gather_frags(struct netns_ipvs *ipvs,
struct sk_buff *skb, u_int32_t user)
{
int err;
@ -714,10 +702,10 @@ static inline int ip_vs_gather_frags(struct sk_buff *skb, u_int32_t user)
return err;
}
static int ip_vs_route_me_harder(int af, struct sk_buff *skb,
unsigned int hooknum)
static int ip_vs_route_me_harder(struct netns_ipvs *ipvs, int af,
struct sk_buff *skb, unsigned int hooknum)
{
if (!sysctl_snat_reroute(skb))
if (!sysctl_snat_reroute(ipvs))
return 0;
/* Reroute replies only to remote clients (FORWARD and LOCAL_OUT) */
if (NF_INET_LOCAL_IN == hooknum)
@ -885,7 +873,7 @@ static int handle_response_icmp(int af, struct sk_buff *skb,
#endif
ip_vs_nat_icmp(skb, pp, cp, 1);
if (ip_vs_route_me_harder(af, skb, hooknum))
if (ip_vs_route_me_harder(cp->ipvs, af, skb, hooknum))
goto out;
/* do the statistics and put it back */
@ -909,8 +897,8 @@ out:
* Find any that might be relevant, check against existing connections.
* Currently handles error types - unreachable, quench, ttl exceeded.
*/
static int ip_vs_out_icmp(struct sk_buff *skb, int *related,
unsigned int hooknum)
static int ip_vs_out_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb,
int *related, unsigned int hooknum)
{
struct iphdr *iph;
struct icmphdr _icmph, *ic;
@ -925,7 +913,7 @@ static int ip_vs_out_icmp(struct sk_buff *skb, int *related,
/* reassemble IP fragments */
if (ip_is_fragment(ip_hdr(skb))) {
if (ip_vs_gather_frags(skb, ip_vs_defrag_user(hooknum)))
if (ip_vs_gather_frags(ipvs, skb, ip_vs_defrag_user(hooknum)))
return NF_STOLEN;
}
@ -974,7 +962,7 @@ static int ip_vs_out_icmp(struct sk_buff *skb, int *related,
ip_vs_fill_iph_skb_icmp(AF_INET, skb, offset, true, &ciph);
/* The embedded headers contain source and dest in reverse order */
cp = pp->conn_out_get(AF_INET, skb, &ciph);
cp = pp->conn_out_get(ipvs, AF_INET, skb, &ciph);
if (!cp)
return NF_ACCEPT;
@ -984,8 +972,9 @@ static int ip_vs_out_icmp(struct sk_buff *skb, int *related,
}
#ifdef CONFIG_IP_VS_IPV6
static int ip_vs_out_icmp_v6(struct sk_buff *skb, int *related,
unsigned int hooknum, struct ip_vs_iphdr *ipvsh)
static int ip_vs_out_icmp_v6(struct netns_ipvs *ipvs, struct sk_buff *skb,
int *related, unsigned int hooknum,
struct ip_vs_iphdr *ipvsh)
{
struct icmp6hdr _icmph, *ic;
struct ip_vs_iphdr ciph = {.flags = 0, .fragoffs = 0};/*Contained IP */
@ -1029,7 +1018,7 @@ static int ip_vs_out_icmp_v6(struct sk_buff *skb, int *related,
return NF_ACCEPT;
/* The embedded headers contain source and dest in reverse order */
cp = pp->conn_out_get(AF_INET6, skb, &ciph);
cp = pp->conn_out_get(ipvs, AF_INET6, skb, &ciph);
if (!cp)
return NF_ACCEPT;
@ -1155,7 +1144,7 @@ handle_response(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd,
* if it came from this machine itself. So re-compute
* the routing information.
*/
if (ip_vs_route_me_harder(af, skb, hooknum))
if (ip_vs_route_me_harder(cp->ipvs, af, skb, hooknum))
goto drop;
IP_VS_DBG_PKT(10, af, pp, skb, iph->off, "After SNAT");
@ -1183,9 +1172,9 @@ drop:
* Check if outgoing packet belongs to the established ip_vs_conn.
*/
static unsigned int
ip_vs_out(unsigned int hooknum, struct sk_buff *skb, int af)
ip_vs_out(struct netns_ipvs *ipvs, unsigned int hooknum, struct sk_buff *skb, int af)
{
struct net *net = NULL;
struct net *net = ipvs->net;
struct ip_vs_iphdr iph;
struct ip_vs_protocol *pp;
struct ip_vs_proto_data *pd;
@ -1210,8 +1199,7 @@ ip_vs_out(unsigned int hooknum, struct sk_buff *skb, int af)
if (unlikely(!skb_dst(skb)))
return NF_ACCEPT;
net = skb_net(skb);
if (!net_ipvs(net)->enable)
if (!ipvs->enable)
return NF_ACCEPT;
ip_vs_fill_iph_skb(af, skb, false, &iph);
@ -1219,7 +1207,7 @@ ip_vs_out(unsigned int hooknum, struct sk_buff *skb, int af)
if (af == AF_INET6) {
if (unlikely(iph.protocol == IPPROTO_ICMPV6)) {
int related;
int verdict = ip_vs_out_icmp_v6(skb, &related,
int verdict = ip_vs_out_icmp_v6(ipvs, skb, &related,
hooknum, &iph);
if (related)
@ -1229,13 +1217,13 @@ ip_vs_out(unsigned int hooknum, struct sk_buff *skb, int af)
#endif
if (unlikely(iph.protocol == IPPROTO_ICMP)) {
int related;
int verdict = ip_vs_out_icmp(skb, &related, hooknum);
int verdict = ip_vs_out_icmp(ipvs, skb, &related, hooknum);
if (related)
return verdict;
}
pd = ip_vs_proto_data_get(net, iph.protocol);
pd = ip_vs_proto_data_get(ipvs, iph.protocol);
if (unlikely(!pd))
return NF_ACCEPT;
pp = pd->pp;
@ -1245,7 +1233,7 @@ ip_vs_out(unsigned int hooknum, struct sk_buff *skb, int af)
if (af == AF_INET)
#endif
if (unlikely(ip_is_fragment(ip_hdr(skb)) && !pp->dont_defrag)) {
if (ip_vs_gather_frags(skb,
if (ip_vs_gather_frags(ipvs, skb,
ip_vs_defrag_user(hooknum)))
return NF_STOLEN;
@ -1255,11 +1243,11 @@ ip_vs_out(unsigned int hooknum, struct sk_buff *skb, int af)
/*
* Check if the packet belongs to an existing entry
*/
cp = pp->conn_out_get(af, skb, &iph);
cp = pp->conn_out_get(ipvs, af, skb, &iph);
if (likely(cp))
return handle_response(af, skb, pd, cp, &iph, hooknum);
if (sysctl_nat_icmp_send(net) &&
if (sysctl_nat_icmp_send(ipvs) &&
(pp->protocol == IPPROTO_TCP ||
pp->protocol == IPPROTO_UDP ||
pp->protocol == IPPROTO_SCTP)) {
@ -1269,7 +1257,7 @@ ip_vs_out(unsigned int hooknum, struct sk_buff *skb, int af)
sizeof(_ports), _ports, &iph);
if (pptr == NULL)
return NF_ACCEPT; /* Not for me */
if (ip_vs_has_real_service(net, af, iph.protocol, &iph.saddr,
if (ip_vs_has_real_service(ipvs, af, iph.protocol, &iph.saddr,
pptr[0])) {
/*
* Notify the real server: there is no
@ -1314,7 +1302,7 @@ static unsigned int
ip_vs_reply4(void *priv, struct sk_buff *skb,
const struct nf_hook_state *state)
{
return ip_vs_out(state->hook, skb, AF_INET);
return ip_vs_out(net_ipvs(state->net), state->hook, skb, AF_INET);
}
/*
@ -1325,7 +1313,7 @@ static unsigned int
ip_vs_local_reply4(void *priv, struct sk_buff *skb,
const struct nf_hook_state *state)
{
return ip_vs_out(state->hook, skb, AF_INET);
return ip_vs_out(net_ipvs(state->net), state->hook, skb, AF_INET);
}
#ifdef CONFIG_IP_VS_IPV6
@ -1339,7 +1327,7 @@ static unsigned int
ip_vs_reply6(void *priv, struct sk_buff *skb,
const struct nf_hook_state *state)
{
return ip_vs_out(state->hook, skb, AF_INET6);
return ip_vs_out(net_ipvs(state->net), state->hook, skb, AF_INET6);
}
/*
@ -1350,13 +1338,14 @@ static unsigned int
ip_vs_local_reply6(void *priv, struct sk_buff *skb,
const struct nf_hook_state *state)
{
return ip_vs_out(state->hook, skb, AF_INET6);
return ip_vs_out(net_ipvs(state->net), state->hook, skb, AF_INET6);
}
#endif
static unsigned int
ip_vs_try_to_schedule(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd,
ip_vs_try_to_schedule(struct netns_ipvs *ipvs, int af, struct sk_buff *skb,
struct ip_vs_proto_data *pd,
int *verdict, struct ip_vs_conn **cpp,
struct ip_vs_iphdr *iph)
{
@ -1368,7 +1357,7 @@ ip_vs_try_to_schedule(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd,
*/
/* Schedule and create new connection entry into cpp */
if (!pp->conn_schedule(af, skb, pd, verdict, cpp, iph))
if (!pp->conn_schedule(ipvs, af, skb, pd, verdict, cpp, iph))
return 0;
}
@ -1398,9 +1387,9 @@ ip_vs_try_to_schedule(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd,
* Currently handles error types - unreachable, quench, ttl exceeded.
*/
static int
ip_vs_in_icmp(struct sk_buff *skb, int *related, unsigned int hooknum)
ip_vs_in_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, int *related,
unsigned int hooknum)
{
struct net *net = NULL;
struct iphdr *iph;
struct icmphdr _icmph, *ic;
struct iphdr _ciph, *cih; /* The ip header contained within the ICMP */
@ -1415,7 +1404,7 @@ ip_vs_in_icmp(struct sk_buff *skb, int *related, unsigned int hooknum)
/* reassemble IP fragments */
if (ip_is_fragment(ip_hdr(skb))) {
if (ip_vs_gather_frags(skb, ip_vs_defrag_user(hooknum)))
if (ip_vs_gather_frags(ipvs, skb, ip_vs_defrag_user(hooknum)))
return NF_STOLEN;
}
@ -1449,8 +1438,6 @@ ip_vs_in_icmp(struct sk_buff *skb, int *related, unsigned int hooknum)
if (cih == NULL)
return NF_ACCEPT; /* The packet looks wrong, ignore */
net = skb_net(skb);
/* Special case for errors for IPIP packets */
ipip = false;
if (cih->protocol == IPPROTO_IPIP) {
@ -1466,7 +1453,7 @@ ip_vs_in_icmp(struct sk_buff *skb, int *related, unsigned int hooknum)
ipip = true;
}
pd = ip_vs_proto_data_get(net, cih->protocol);
pd = ip_vs_proto_data_get(ipvs, cih->protocol);
if (!pd)
return NF_ACCEPT;
pp = pd->pp;
@ -1486,15 +1473,15 @@ ip_vs_in_icmp(struct sk_buff *skb, int *related, unsigned int hooknum)
/* The embedded headers contain source and dest in reverse order.
* For IPIP this is error for request, not for reply.
*/
cp = pp->conn_in_get(AF_INET, skb, &ciph);
cp = pp->conn_in_get(ipvs, AF_INET, skb, &ciph);
if (!cp) {
int v;
if (!sysctl_schedule_icmp(net_ipvs(net)))
if (!sysctl_schedule_icmp(ipvs))
return NF_ACCEPT;
if (!ip_vs_try_to_schedule(AF_INET, skb, pd, &v, &cp, &ciph))
if (!ip_vs_try_to_schedule(ipvs, AF_INET, skb, pd, &v, &cp, &ciph))
return v;
new_cp = true;
}
@ -1528,7 +1515,7 @@ ip_vs_in_icmp(struct sk_buff *skb, int *related, unsigned int hooknum)
skb_reset_network_header(skb);
IP_VS_DBG(12, "ICMP for IPIP %pI4->%pI4: mtu=%u\n",
&ip_hdr(skb)->saddr, &ip_hdr(skb)->daddr, mtu);
ipv4_update_pmtu(skb, dev_net(skb->dev),
ipv4_update_pmtu(skb, ipvs->net,
mtu, 0, 0, 0, 0);
/* Client uses PMTUD? */
if (!(frag_off & htons(IP_DF)))
@ -1583,10 +1570,10 @@ out:
}
#ifdef CONFIG_IP_VS_IPV6
static int ip_vs_in_icmp_v6(struct sk_buff *skb, int *related,
unsigned int hooknum, struct ip_vs_iphdr *iph)
static int ip_vs_in_icmp_v6(struct netns_ipvs *ipvs, struct sk_buff *skb,
int *related, unsigned int hooknum,
struct ip_vs_iphdr *iph)
{
struct net *net = NULL;
struct icmp6hdr _icmph, *ic;
struct ip_vs_iphdr ciph = {.flags = 0, .fragoffs = 0};/*Contained IP */
struct ip_vs_conn *cp;
@ -1626,8 +1613,7 @@ static int ip_vs_in_icmp_v6(struct sk_buff *skb, int *related,
if (!ip_vs_fill_iph_skb_icmp(AF_INET6, skb, offset, true, &ciph))
return NF_ACCEPT;
net = skb_net(skb);
pd = ip_vs_proto_data_get(net, ciph.protocol);
pd = ip_vs_proto_data_get(ipvs, ciph.protocol);
if (!pd)
return NF_ACCEPT;
pp = pd->pp;
@ -1642,15 +1628,15 @@ static int ip_vs_in_icmp_v6(struct sk_buff *skb, int *related,
/* The embedded headers contain source and dest in reverse order
* if not from localhost
*/
cp = pp->conn_in_get(AF_INET6, skb, &ciph);
cp = pp->conn_in_get(ipvs, AF_INET6, skb, &ciph);
if (!cp) {
int v;
if (!sysctl_schedule_icmp(net_ipvs(net)))
if (!sysctl_schedule_icmp(ipvs))
return NF_ACCEPT;
if (!ip_vs_try_to_schedule(AF_INET6, skb, pd, &v, &cp, &ciph))
if (!ip_vs_try_to_schedule(ipvs, AF_INET6, skb, pd, &v, &cp, &ciph))
return v;
new_cp = true;
@ -1690,15 +1676,13 @@ out:
* and send it on its way...
*/
static unsigned int
ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af)
ip_vs_in(struct netns_ipvs *ipvs, unsigned int hooknum, struct sk_buff *skb, int af)
{
struct net *net;
struct ip_vs_iphdr iph;
struct ip_vs_protocol *pp;
struct ip_vs_proto_data *pd;
struct ip_vs_conn *cp;
int ret, pkts;
struct netns_ipvs *ipvs;
int conn_reuse_mode;
/* Already marked as IPVS request or reply? */
@ -1721,8 +1705,6 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af)
return NF_ACCEPT;
}
/* ipvs enabled in this netns ? */
net = skb_net(skb);
ipvs = net_ipvs(net);
if (unlikely(sysctl_backup_only(ipvs) || !ipvs->enable))
return NF_ACCEPT;
@ -1742,8 +1724,8 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af)
if (af == AF_INET6) {
if (unlikely(iph.protocol == IPPROTO_ICMPV6)) {
int related;
int verdict = ip_vs_in_icmp_v6(skb, &related, hooknum,
&iph);
int verdict = ip_vs_in_icmp_v6(ipvs, skb, &related,
hooknum, &iph);
if (related)
return verdict;
@ -1752,14 +1734,15 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af)
#endif
if (unlikely(iph.protocol == IPPROTO_ICMP)) {
int related;
int verdict = ip_vs_in_icmp(skb, &related, hooknum);
int verdict = ip_vs_in_icmp(ipvs, skb, &related,
hooknum);
if (related)
return verdict;
}
/* Protocol supported? */
pd = ip_vs_proto_data_get(net, iph.protocol);
pd = ip_vs_proto_data_get(ipvs, iph.protocol);
if (unlikely(!pd)) {
/* The only way we'll see this packet again is if it's
* encapsulated, so mark it with ipvs_property=1 so we
@ -1774,7 +1757,7 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af)
/*
* Check if the packet belongs to an existing connection entry
*/
cp = pp->conn_in_get(af, skb, &iph);
cp = pp->conn_in_get(ipvs, af, skb, &iph);
conn_reuse_mode = sysctl_conn_reuse_mode(ipvs);
if (conn_reuse_mode && !iph.fragoffs &&
@ -1791,7 +1774,7 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af)
if (unlikely(!cp)) {
int v;
if (!ip_vs_try_to_schedule(af, skb, pd, &v, &cp, &iph))
if (!ip_vs_try_to_schedule(ipvs, af, skb, pd, &v, &cp, &iph))
return v;
}
@ -1836,7 +1819,7 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af)
pkts = atomic_add_return(1, &cp->in_pkts);
if (ipvs->sync_state & IP_VS_STATE_MASTER)
ip_vs_sync_conn(net, cp, pkts);
ip_vs_sync_conn(ipvs, cp, pkts);
ip_vs_conn_put(cp);
return ret;
@ -1850,7 +1833,7 @@ static unsigned int
ip_vs_remote_request4(void *priv, struct sk_buff *skb,
const struct nf_hook_state *state)
{
return ip_vs_in(state->hook, skb, AF_INET);
return ip_vs_in(net_ipvs(state->net), state->hook, skb, AF_INET);
}
/*
@ -1861,7 +1844,7 @@ static unsigned int
ip_vs_local_request4(void *priv, struct sk_buff *skb,
const struct nf_hook_state *state)
{
return ip_vs_in(state->hook, skb, AF_INET);
return ip_vs_in(net_ipvs(state->net), state->hook, skb, AF_INET);
}
#ifdef CONFIG_IP_VS_IPV6
@ -1874,7 +1857,7 @@ static unsigned int
ip_vs_remote_request6(void *priv, struct sk_buff *skb,
const struct nf_hook_state *state)
{
return ip_vs_in(state->hook, skb, AF_INET6);
return ip_vs_in(net_ipvs(state->net), state->hook, skb, AF_INET6);
}
/*
@ -1885,7 +1868,7 @@ static unsigned int
ip_vs_local_request6(void *priv, struct sk_buff *skb,
const struct nf_hook_state *state)
{
return ip_vs_in(state->hook, skb, AF_INET6);
return ip_vs_in(net_ipvs(state->net), state->hook, skb, AF_INET6);
}
#endif
@ -1905,19 +1888,16 @@ ip_vs_forward_icmp(void *priv, struct sk_buff *skb,
const struct nf_hook_state *state)
{
int r;
struct net *net;
struct netns_ipvs *ipvs;
struct netns_ipvs *ipvs = net_ipvs(state->net);
if (ip_hdr(skb)->protocol != IPPROTO_ICMP)
return NF_ACCEPT;
/* ipvs enabled in this netns ? */
net = skb_net(skb);
ipvs = net_ipvs(net);
if (unlikely(sysctl_backup_only(ipvs) || !ipvs->enable))
return NF_ACCEPT;
return ip_vs_in_icmp(skb, &r, state->hook);
return ip_vs_in_icmp(ipvs, skb, &r, state->hook);
}
#ifdef CONFIG_IP_VS_IPV6
@ -1926,8 +1906,7 @@ ip_vs_forward_icmp_v6(void *priv, struct sk_buff *skb,
const struct nf_hook_state *state)
{
int r;
struct net *net;
struct netns_ipvs *ipvs;
struct netns_ipvs *ipvs = net_ipvs(state->net);
struct ip_vs_iphdr iphdr;
ip_vs_fill_iph_skb(AF_INET6, skb, false, &iphdr);
@ -1935,12 +1914,10 @@ ip_vs_forward_icmp_v6(void *priv, struct sk_buff *skb,
return NF_ACCEPT;
/* ipvs enabled in this netns ? */
net = skb_net(skb);
ipvs = net_ipvs(net);
if (unlikely(sysctl_backup_only(ipvs) || !ipvs->enable))
return NF_ACCEPT;
return ip_vs_in_icmp_v6(skb, &r, state->hook, &iphdr);
return ip_vs_in_icmp_v6(ipvs, skb, &r, state->hook, &iphdr);
}
#endif
@ -2070,22 +2047,22 @@ static int __net_init __ip_vs_init(struct net *net)
atomic_inc(&ipvs_netns_cnt);
net->ipvs = ipvs;
if (ip_vs_estimator_net_init(net) < 0)
if (ip_vs_estimator_net_init(ipvs) < 0)
goto estimator_fail;
if (ip_vs_control_net_init(net) < 0)
if (ip_vs_control_net_init(ipvs) < 0)
goto control_fail;
if (ip_vs_protocol_net_init(net) < 0)
if (ip_vs_protocol_net_init(ipvs) < 0)
goto protocol_fail;
if (ip_vs_app_net_init(net) < 0)
if (ip_vs_app_net_init(ipvs) < 0)
goto app_fail;
if (ip_vs_conn_net_init(net) < 0)
if (ip_vs_conn_net_init(ipvs) < 0)
goto conn_fail;
if (ip_vs_sync_net_init(net) < 0)
if (ip_vs_sync_net_init(ipvs) < 0)
goto sync_fail;
printk(KERN_INFO "IPVS: Creating netns size=%zu id=%d\n",
@ -2096,15 +2073,15 @@ static int __net_init __ip_vs_init(struct net *net)
*/
sync_fail:
ip_vs_conn_net_cleanup(net);
ip_vs_conn_net_cleanup(ipvs);
conn_fail:
ip_vs_app_net_cleanup(net);
ip_vs_app_net_cleanup(ipvs);
app_fail:
ip_vs_protocol_net_cleanup(net);
ip_vs_protocol_net_cleanup(ipvs);
protocol_fail:
ip_vs_control_net_cleanup(net);
ip_vs_control_net_cleanup(ipvs);
control_fail:
ip_vs_estimator_net_cleanup(net);
ip_vs_estimator_net_cleanup(ipvs);
estimator_fail:
net->ipvs = NULL;
return -ENOMEM;
@ -2112,22 +2089,25 @@ estimator_fail:
static void __net_exit __ip_vs_cleanup(struct net *net)
{
ip_vs_service_net_cleanup(net); /* ip_vs_flush() with locks */
ip_vs_conn_net_cleanup(net);
ip_vs_app_net_cleanup(net);
ip_vs_protocol_net_cleanup(net);
ip_vs_control_net_cleanup(net);
ip_vs_estimator_net_cleanup(net);
IP_VS_DBG(2, "ipvs netns %d released\n", net_ipvs(net)->gen);
struct netns_ipvs *ipvs = net_ipvs(net);
ip_vs_service_net_cleanup(ipvs); /* ip_vs_flush() with locks */
ip_vs_conn_net_cleanup(ipvs);
ip_vs_app_net_cleanup(ipvs);
ip_vs_protocol_net_cleanup(ipvs);
ip_vs_control_net_cleanup(ipvs);
ip_vs_estimator_net_cleanup(ipvs);
IP_VS_DBG(2, "ipvs netns %d released\n", ipvs->gen);
net->ipvs = NULL;
}
static void __net_exit __ip_vs_dev_cleanup(struct net *net)
{
struct netns_ipvs *ipvs = net_ipvs(net);
EnterFunction(2);
net_ipvs(net)->enable = 0; /* Disable packet reception */
ipvs->enable = 0; /* Disable packet reception */
smp_wmb();
ip_vs_sync_net_cleanup(net);
ip_vs_sync_net_cleanup(ipvs);
LeaveFunction(2);
}

276
net/netfilter/ipvs/ip_vs_ctl.c
View File

@ -228,7 +228,7 @@ static void defense_work_handler(struct work_struct *work)
update_defense_level(ipvs);
if (atomic_read(&ipvs->dropentry))
ip_vs_random_dropentry(ipvs->net);
ip_vs_random_dropentry(ipvs);
schedule_delayed_work(&ipvs->defense_work, DEFENSE_TIMER_PERIOD);
}
#endif
@ -263,7 +263,7 @@ static struct hlist_head ip_vs_svc_fwm_table[IP_VS_SVC_TAB_SIZE];
* Returns hash value for virtual service
*/
static inline unsigned int
ip_vs_svc_hashkey(struct net *net, int af, unsigned int proto,
ip_vs_svc_hashkey(struct netns_ipvs *ipvs, int af, unsigned int proto,
const union nf_inet_addr *addr, __be16 port)
{
register unsigned int porth = ntohs(port);
@ -276,7 +276,7 @@ ip_vs_svc_hashkey(struct net *net, int af, unsigned int proto,
addr->ip6[2]^addr->ip6[3];
#endif
ahash = ntohl(addr_fold);
ahash ^= ((size_t) net >> 8);
ahash ^= ((size_t) ipvs >> 8);
return (proto ^ ahash ^ (porth >> IP_VS_SVC_TAB_BITS) ^ porth) &
IP_VS_SVC_TAB_MASK;
@ -285,9 +285,9 @@ ip_vs_svc_hashkey(struct net *net, int af, unsigned int proto,
/*
* Returns hash value of fwmark for virtual service lookup
*/
static inline unsigned int ip_vs_svc_fwm_hashkey(struct net *net, __u32 fwmark)
static inline unsigned int ip_vs_svc_fwm_hashkey(struct netns_ipvs *ipvs, __u32 fwmark)
{
return (((size_t)net>>8) ^ fwmark) & IP_VS_SVC_TAB_MASK;
return (((size_t)ipvs>>8) ^ fwmark) & IP_VS_SVC_TAB_MASK;
}
/*
@ -309,14 +309,14 @@ static int ip_vs_svc_hash(struct ip_vs_service *svc)
/*
* Hash it by <netns,protocol,addr,port> in ip_vs_svc_table
*/
hash = ip_vs_svc_hashkey(svc->net, svc->af, svc->protocol,
hash = ip_vs_svc_hashkey(svc->ipvs, svc->af, svc->protocol,
&svc->addr, svc->port);
hlist_add_head_rcu(&svc->s_list, &ip_vs_svc_table[hash]);
} else {
/*
* Hash it by fwmark in svc_fwm_table
*/
hash = ip_vs_svc_fwm_hashkey(svc->net, svc->fwmark);
hash = ip_vs_svc_fwm_hashkey(svc->ipvs, svc->fwmark);
hlist_add_head_rcu(&svc->f_list, &ip_vs_svc_fwm_table[hash]);
}
@ -357,21 +357,21 @@ static int ip_vs_svc_unhash(struct ip_vs_service *svc)
* Get service by {netns, proto,addr,port} in the service table.
*/
static inline struct ip_vs_service *
__ip_vs_service_find(struct net *net, int af, __u16 protocol,
__ip_vs_service_find(struct netns_ipvs *ipvs, int af, __u16 protocol,
const union nf_inet_addr *vaddr, __be16 vport)
{
unsigned int hash;
struct ip_vs_service *svc;
/* Check for "full" addressed entries */
hash = ip_vs_svc_hashkey(net, af, protocol, vaddr, vport);
hash = ip_vs_svc_hashkey(ipvs, af, protocol, vaddr, vport);
hlist_for_each_entry_rcu(svc, &ip_vs_svc_table[hash], s_list) {
if ((svc->af == af)
&& ip_vs_addr_equal(af, &svc->addr, vaddr)
&& (svc->port == vport)
&& (svc->protocol == protocol)
&& net_eq(svc->net, net)) {
&& (svc->ipvs == ipvs)) {
/* HIT */
return svc;
}
@ -385,17 +385,17 @@ __ip_vs_service_find(struct net *net, int af, __u16 protocol,
* Get service by {fwmark} in the service table.
*/
static inline struct ip_vs_service *
__ip_vs_svc_fwm_find(struct net *net, int af, __u32 fwmark)
__ip_vs_svc_fwm_find(struct netns_ipvs *ipvs, int af, __u32 fwmark)
{
unsigned int hash;
struct ip_vs_service *svc;
/* Check for fwmark addressed entries */
hash = ip_vs_svc_fwm_hashkey(net, fwmark);
hash = ip_vs_svc_fwm_hashkey(ipvs, fwmark);
hlist_for_each_entry_rcu(svc, &ip_vs_svc_fwm_table[hash], f_list) {
if (svc->fwmark == fwmark && svc->af == af
&& net_eq(svc->net, net)) {
&& (svc->ipvs == ipvs)) {
/* HIT */
return svc;
}
@ -406,17 +406,16 @@ __ip_vs_svc_fwm_find(struct net *net, int af, __u32 fwmark)
/* Find service, called under RCU lock */
struct ip_vs_service *
ip_vs_service_find(struct net *net, int af, __u32 fwmark, __u16 protocol,
ip_vs_service_find(struct netns_ipvs *ipvs, int af, __u32 fwmark, __u16 protocol,
const union nf_inet_addr *vaddr, __be16 vport)
{
struct ip_vs_service *svc;
struct netns_ipvs *ipvs = net_ipvs(net);
/*
* Check the table hashed by fwmark first
*/
if (fwmark) {
svc = __ip_vs_svc_fwm_find(net, af, fwmark);
svc = __ip_vs_svc_fwm_find(ipvs, af, fwmark);
if (svc)
goto out;
}
@ -425,7 +424,7 @@ ip_vs_service_find(struct net *net, int af, __u32 fwmark, __u16 protocol,
* Check the table hashed by <protocol,addr,port>
* for "full" addressed entries
*/
svc = __ip_vs_service_find(net, af, protocol, vaddr, vport);
svc = __ip_vs_service_find(ipvs, af, protocol, vaddr, vport);
if (svc == NULL
&& protocol == IPPROTO_TCP
@ -435,7 +434,7 @@ ip_vs_service_find(struct net *net, int af, __u32 fwmark, __u16 protocol,
* Check if ftp service entry exists, the packet
* might belong to FTP data connections.
*/
svc = __ip_vs_service_find(net, af, protocol, vaddr, FTPPORT);
svc = __ip_vs_service_find(ipvs, af, protocol, vaddr, FTPPORT);
}
if (svc == NULL
@ -443,7 +442,7 @@ ip_vs_service_find(struct net *net, int af, __u32 fwmark, __u16 protocol,
/*
* Check if the catch-all port (port zero) exists
*/
svc = __ip_vs_service_find(net, af, protocol, vaddr, 0);
svc = __ip_vs_service_find(ipvs, af, protocol, vaddr, 0);
}
out:
@ -543,10 +542,9 @@ static void ip_vs_rs_unhash(struct ip_vs_dest *dest)
}
/* Check if real service by <proto,addr,port> is present */
bool ip_vs_has_real_service(struct net *net, int af, __u16 protocol,
bool ip_vs_has_real_service(struct netns_ipvs *ipvs, int af, __u16 protocol,
const union nf_inet_addr *daddr, __be16 dport)
{
struct netns_ipvs *ipvs = net_ipvs(net);
unsigned int hash;
struct ip_vs_dest *dest;
@ -601,7 +599,7 @@ ip_vs_lookup_dest(struct ip_vs_service *svc, int dest_af,
* on the backup.
* Called under RCU lock, no refcnt is returned.
*/
struct ip_vs_dest *ip_vs_find_dest(struct net *net, int svc_af, int dest_af,
struct ip_vs_dest *ip_vs_find_dest(struct netns_ipvs *ipvs, int svc_af, int dest_af,
const union nf_inet_addr *daddr,
__be16 dport,
const union nf_inet_addr *vaddr,
@ -612,7 +610,7 @@ struct ip_vs_dest *ip_vs_find_dest(struct net *net, int svc_af, int dest_af,
struct ip_vs_service *svc;
__be16 port = dport;
svc = ip_vs_service_find(net, svc_af, fwmark, protocol, vaddr, vport);
svc = ip_vs_service_find(ipvs, svc_af, fwmark, protocol, vaddr, vport);
if (!svc)
return NULL;
if (fwmark && (flags & IP_VS_CONN_F_FWD_MASK) != IP_VS_CONN_F_MASQ)
@ -660,7 +658,7 @@ ip_vs_trash_get_dest(struct ip_vs_service *svc, int dest_af,
const union nf_inet_addr *daddr, __be16 dport)
{
struct ip_vs_dest *dest;
struct netns_ipvs *ipvs = net_ipvs(svc->net);
struct netns_ipvs *ipvs = svc->ipvs;
/*
* Find the destination in trash
@ -715,10 +713,9 @@ static void ip_vs_dest_free(struct ip_vs_dest *dest)
* are expired, and the refcnt of each destination in the trash must
* be 0, so we simply release them here.
*/
static void ip_vs_trash_cleanup(struct net *net)
static void ip_vs_trash_cleanup(struct netns_ipvs *ipvs)
{
struct ip_vs_dest *dest, *nxt;
struct netns_ipvs *ipvs = net_ipvs(net);
del_timer_sync(&ipvs->dest_trash_timer);
/* No need to use dest_trash_lock */
@ -788,7 +785,7 @@ static void
__ip_vs_update_dest(struct ip_vs_service *svc, struct ip_vs_dest *dest,
struct ip_vs_dest_user_kern *udest, int add)
{
struct netns_ipvs *ipvs = net_ipvs(svc->net);
struct netns_ipvs *ipvs = svc->ipvs;
struct ip_vs_service *old_svc;
struct ip_vs_scheduler *sched;
int conn_flags;
@ -843,7 +840,7 @@ __ip_vs_update_dest(struct ip_vs_service *svc, struct ip_vs_dest *dest,
spin_unlock_bh(&dest->dst_lock);
if (add) {
ip_vs_start_estimator(svc->net, &dest->stats);
ip_vs_start_estimator(svc->ipvs, &dest->stats);
list_add_rcu(&dest->n_list, &svc->destinations);
svc->num_dests++;
sched = rcu_dereference_protected(svc->scheduler, 1);
@ -874,12 +871,12 @@ ip_vs_new_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest,
atype = ipv6_addr_type(&udest->addr.in6);
if ((!(atype & IPV6_ADDR_UNICAST) ||
atype & IPV6_ADDR_LINKLOCAL) &&
!__ip_vs_addr_is_local_v6(svc->net, &udest->addr.in6))
!__ip_vs_addr_is_local_v6(svc->ipvs->net, &udest->addr.in6))
return -EINVAL;
} else
#endif
{
atype = inet_addr_type(svc->net, udest->addr.ip);
atype = inet_addr_type(svc->ipvs->net, udest->addr.ip);
if (atype != RTN_LOCAL && atype != RTN_UNICAST)
return -EINVAL;
}
@ -1036,12 +1033,10 @@ ip_vs_edit_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest)
/*
* Delete a destination (must be already unlinked from the service)
*/
static void __ip_vs_del_dest(struct net *net, struct ip_vs_dest *dest,
static void __ip_vs_del_dest(struct netns_ipvs *ipvs, struct ip_vs_dest *dest,
bool cleanup)
{
struct netns_ipvs *ipvs = net_ipvs(net);
ip_vs_stop_estimator(net, &dest->stats);
ip_vs_stop_estimator(ipvs, &dest->stats);
/*
* Remove it from the d-linked list with the real services.
@ -1079,7 +1074,7 @@ static void __ip_vs_unlink_dest(struct ip_vs_service *svc,
svc->num_dests--;
if (dest->af != svc->af)
net_ipvs(svc->net)->mixed_address_family_dests--;
svc->ipvs->mixed_address_family_dests--;
if (svcupd) {
struct ip_vs_scheduler *sched;
@ -1120,7 +1115,7 @@ ip_vs_del_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest)
/*
* Delete the destination
*/
__ip_vs_del_dest(svc->net, dest, false);
__ip_vs_del_dest(svc->ipvs, dest, false);
LeaveFunction(2);
@ -1129,8 +1124,7 @@ ip_vs_del_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest)
static void ip_vs_dest_trash_expire(unsigned long data)
{
struct net *net = (struct net *) data;
struct netns_ipvs *ipvs = net_ipvs(net);
struct netns_ipvs *ipvs = (struct netns_ipvs *)data;
struct ip_vs_dest *dest, *next;
unsigned long now = jiffies;
@ -1163,14 +1157,13 @@ static void ip_vs_dest_trash_expire(unsigned long data)
* Add a service into the service hash table
*/
static int
ip_vs_add_service(struct net *net, struct ip_vs_service_user_kern *u,
ip_vs_add_service(struct netns_ipvs *ipvs, struct ip_vs_service_user_kern *u,
struct ip_vs_service **svc_p)
{
int ret = 0, i;
struct ip_vs_scheduler *sched = NULL;
struct ip_vs_pe *pe = NULL;
struct ip_vs_service *svc = NULL;
struct netns_ipvs *ipvs = net_ipvs(net);
/* increase the module use count */
ip_vs_use_count_inc();
@ -1237,7 +1230,7 @@ ip_vs_add_service(struct net *net, struct ip_vs_service_user_kern *u,
svc->flags = u->flags;
svc->timeout = u->timeout * HZ;
svc->netmask = u->netmask;
svc->net = net;
svc->ipvs = ipvs;
INIT_LIST_HEAD(&svc->destinations);
spin_lock_init(&svc->sched_lock);
@ -1261,7 +1254,7 @@ ip_vs_add_service(struct net *net, struct ip_vs_service_user_kern *u,
else if (svc->port == 0)
atomic_inc(&ipvs->nullsvc_counter);
ip_vs_start_estimator(net, &svc->stats);
ip_vs_start_estimator(ipvs, &svc->stats);
/* Count only IPv4 services for old get/setsockopt interface */
if (svc->af == AF_INET)
@ -1381,7 +1374,7 @@ static void __ip_vs_del_service(struct ip_vs_service *svc, bool cleanup)
struct ip_vs_dest *dest, *nxt;
struct ip_vs_scheduler *old_sched;
struct ip_vs_pe *old_pe;
struct netns_ipvs *ipvs = net_ipvs(svc->net);
struct netns_ipvs *ipvs = svc->ipvs;
pr_info("%s: enter\n", __func__);
@ -1389,7 +1382,7 @@ static void __ip_vs_del_service(struct ip_vs_service *svc, bool cleanup)
if (svc->af == AF_INET)
ipvs->num_services--;
ip_vs_stop_estimator(svc->net, &svc->stats);
ip_vs_stop_estimator(svc->ipvs, &svc->stats);
/* Unbind scheduler */
old_sched = rcu_dereference_protected(svc->scheduler, 1);
@ -1405,7 +1398,7 @@ static void __ip_vs_del_service(struct ip_vs_service *svc, bool cleanup)
*/
list_for_each_entry_safe(dest, nxt, &svc->destinations, n_list) {
__ip_vs_unlink_dest(svc, dest, 0);
__ip_vs_del_dest(svc->net, dest, cleanup);
__ip_vs_del_dest(svc->ipvs, dest, cleanup);
}
/*
@ -1456,7 +1449,7 @@ static int ip_vs_del_service(struct ip_vs_service *svc)
/*
* Flush all the virtual services
*/
static int ip_vs_flush(struct net *net, bool cleanup)
static int ip_vs_flush(struct netns_ipvs *ipvs, bool cleanup)
{
int idx;
struct ip_vs_service *svc;
@ -1468,7 +1461,7 @@ static int ip_vs_flush(struct net *net, bool cleanup)
for(idx = 0; idx < IP_VS_SVC_TAB_SIZE; idx++) {
hlist_for_each_entry_safe(svc, n, &ip_vs_svc_table[idx],
s_list) {
if (net_eq(svc->net, net))
if (svc->ipvs == ipvs)
ip_vs_unlink_service(svc, cleanup);
}
}
@ -1479,7 +1472,7 @@ static int ip_vs_flush(struct net *net, bool cleanup)
for(idx = 0; idx < IP_VS_SVC_TAB_SIZE; idx++) {
hlist_for_each_entry_safe(svc, n, &ip_vs_svc_fwm_table[idx],
f_list) {
if (net_eq(svc->net, net))
if (svc->ipvs == ipvs)
ip_vs_unlink_service(svc, cleanup);
}
}
@ -1491,12 +1484,12 @@ static int ip_vs_flush(struct net *net, bool cleanup)
* Delete service by {netns} in the service table.
* Called by __ip_vs_cleanup()
*/
void ip_vs_service_net_cleanup(struct net *net)
void ip_vs_service_net_cleanup(struct netns_ipvs *ipvs)
{
EnterFunction(2);
/* Check for "full" addressed entries */
mutex_lock(&__ip_vs_mutex);
ip_vs_flush(net, true);
ip_vs_flush(ipvs, true);
mutex_unlock(&__ip_vs_mutex);
LeaveFunction(2);
}
@ -1540,7 +1533,7 @@ static int ip_vs_dst_event(struct notifier_block *this, unsigned long event,
mutex_lock(&__ip_vs_mutex);
for (idx = 0; idx < IP_VS_SVC_TAB_SIZE; idx++) {
hlist_for_each_entry(svc, &ip_vs_svc_table[idx], s_list) {
if (net_eq(svc->net, net)) {
if (svc->ipvs == ipvs) {
list_for_each_entry(dest, &svc->destinations,
n_list) {
ip_vs_forget_dev(dest, dev);
@ -1549,7 +1542,7 @@ static int ip_vs_dst_event(struct notifier_block *this, unsigned long event,
}
hlist_for_each_entry(svc, &ip_vs_svc_fwm_table[idx], f_list) {
if (net_eq(svc->net, net)) {
if (svc->ipvs == ipvs) {
list_for_each_entry(dest, &svc->destinations,
n_list) {
ip_vs_forget_dev(dest, dev);
@ -1583,26 +1576,26 @@ static int ip_vs_zero_service(struct ip_vs_service *svc)
return 0;
}
static int ip_vs_zero_all(struct net *net)
static int ip_vs_zero_all(struct netns_ipvs *ipvs)
{
int idx;
struct ip_vs_service *svc;
for(idx = 0; idx < IP_VS_SVC_TAB_SIZE; idx++) {
hlist_for_each_entry(svc, &ip_vs_svc_table[idx], s_list) {
if (net_eq(svc->net, net))
if (svc->ipvs == ipvs)
ip_vs_zero_service(svc);
}
}
for(idx = 0; idx < IP_VS_SVC_TAB_SIZE; idx++) {
hlist_for_each_entry(svc, &ip_vs_svc_fwm_table[idx], f_list) {
if (net_eq(svc->net, net))
if (svc->ipvs == ipvs)
ip_vs_zero_service(svc);
}
}
ip_vs_zero_stats(&net_ipvs(net)->tot_stats);
ip_vs_zero_stats(&ipvs->tot_stats);
return 0;
}
@ -1615,7 +1608,7 @@ static int
proc_do_defense_mode(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos)
{
struct net *net = current->nsproxy->net_ns;
struct netns_ipvs *ipvs = table->extra2;
int *valp = table->data;
int val = *valp;
int rc;
@ -1626,7 +1619,7 @@ proc_do_defense_mode(struct ctl_table *table, int write,
/* Restore the correct value */
*valp = val;
} else {
update_defense_level(net_ipvs(net));
update_defense_level(ipvs);
}
}
return rc;
@ -1901,6 +1894,7 @@ static inline const char *ip_vs_fwd_name(unsigned int flags)
static struct ip_vs_service *ip_vs_info_array(struct seq_file *seq, loff_t pos)
{
struct net *net = seq_file_net(seq);
struct netns_ipvs *ipvs = net_ipvs(net);
struct ip_vs_iter *iter = seq->private;
int idx;
struct ip_vs_service *svc;
@ -1908,7 +1902,7 @@ static struct ip_vs_service *ip_vs_info_array(struct seq_file *seq, loff_t pos)
/* look in hash by protocol */
for (idx = 0; idx < IP_VS_SVC_TAB_SIZE; idx++) {
hlist_for_each_entry_rcu(svc, &ip_vs_svc_table[idx], s_list) {
if (net_eq(svc->net, net) && pos-- == 0) {
if ((svc->ipvs == ipvs) && pos-- == 0) {
iter->table = ip_vs_svc_table;
iter->bucket = idx;
return svc;
@ -1920,7 +1914,7 @@ static struct ip_vs_service *ip_vs_info_array(struct seq_file *seq, loff_t pos)
for (idx = 0; idx < IP_VS_SVC_TAB_SIZE; idx++) {
hlist_for_each_entry_rcu(svc, &ip_vs_svc_fwm_table[idx],
f_list) {
if (net_eq(svc->net, net) && pos-- == 0) {
if ((svc->ipvs == ipvs) && pos-- == 0) {
iter->table = ip_vs_svc_fwm_table;
iter->bucket = idx;
return svc;
@ -2208,7 +2202,7 @@ static const struct file_operations ip_vs_stats_percpu_fops = {
/*
* Set timeout values for tcp tcpfin udp in the timeout_table.
*/
static int ip_vs_set_timeout(struct net *net, struct ip_vs_timeout_user *u)
static int ip_vs_set_timeout(struct netns_ipvs *ipvs, struct ip_vs_timeout_user *u)
{
#if defined(CONFIG_IP_VS_PROTO_TCP) || defined(CONFIG_IP_VS_PROTO_UDP)
struct ip_vs_proto_data *pd;
@ -2221,13 +2215,13 @@ static int ip_vs_set_timeout(struct net *net, struct ip_vs_timeout_user *u)
#ifdef CONFIG_IP_VS_PROTO_TCP
if (u->tcp_timeout) {
pd = ip_vs_proto_data_get(net, IPPROTO_TCP);
pd = ip_vs_proto_data_get(ipvs, IPPROTO_TCP);
pd->timeout_table[IP_VS_TCP_S_ESTABLISHED]
= u->tcp_timeout * HZ;
}
if (u->tcp_fin_timeout) {
pd = ip_vs_proto_data_get(net, IPPROTO_TCP);
pd = ip_vs_proto_data_get(ipvs, IPPROTO_TCP);
pd->timeout_table[IP_VS_TCP_S_FIN_WAIT]
= u->tcp_fin_timeout * HZ;
}
@ -2235,7 +2229,7 @@ static int ip_vs_set_timeout(struct net *net, struct ip_vs_timeout_user *u)
#ifdef CONFIG_IP_VS_PROTO_UDP
if (u->udp_timeout) {
pd = ip_vs_proto_data_get(net, IPPROTO_UDP);
pd = ip_vs_proto_data_get(ipvs, IPPROTO_UDP);
pd->timeout_table[IP_VS_UDP_S_NORMAL]
= u->udp_timeout * HZ;
}
@ -2356,12 +2350,12 @@ do_ip_vs_set_ctl(struct sock *sk, int cmd, void __user *user, unsigned int len)
cfg.syncid = dm->syncid;
rtnl_lock();
mutex_lock(&ipvs->sync_mutex);
ret = start_sync_thread(net, &cfg, dm->state);
ret = start_sync_thread(ipvs, &cfg, dm->state);
mutex_unlock(&ipvs->sync_mutex);
rtnl_unlock();
} else {
mutex_lock(&ipvs->sync_mutex);
ret = stop_sync_thread(net, dm->state);
ret = stop_sync_thread(ipvs, dm->state);
mutex_unlock(&ipvs->sync_mutex);
}
goto out_dec;
@ -2370,11 +2364,11 @@ do_ip_vs_set_ctl(struct sock *sk, int cmd, void __user *user, unsigned int len)
mutex_lock(&__ip_vs_mutex);
if (cmd == IP_VS_SO_SET_FLUSH) {
/* Flush the virtual service */
ret = ip_vs_flush(net, false);
ret = ip_vs_flush(ipvs, false);
goto out_unlock;
} else if (cmd == IP_VS_SO_SET_TIMEOUT) {
/* Set timeout values for (tcp tcpfin udp) */
ret = ip_vs_set_timeout(net, (struct ip_vs_timeout_user *)arg);
ret = ip_vs_set_timeout(ipvs, (struct ip_vs_timeout_user *)arg);
goto out_unlock;
}
@ -2389,7 +2383,7 @@ do_ip_vs_set_ctl(struct sock *sk, int cmd, void __user *user, unsigned int len)
if (cmd == IP_VS_SO_SET_ZERO) {
/* if no service address is set, zero counters in all */
if (!usvc.fwmark && !usvc.addr.ip && !usvc.port) {
ret = ip_vs_zero_all(net);
ret = ip_vs_zero_all(ipvs);
goto out_unlock;
}
}
@ -2407,10 +2401,10 @@ do_ip_vs_set_ctl(struct sock *sk, int cmd, void __user *user, unsigned int len)
/* Lookup the exact service by <protocol, addr, port> or fwmark */
rcu_read_lock();
if (usvc.fwmark == 0)
svc = __ip_vs_service_find(net, usvc.af, usvc.protocol,
svc = __ip_vs_service_find(ipvs, usvc.af, usvc.protocol,
&usvc.addr, usvc.port);
else
svc = __ip_vs_svc_fwm_find(net, usvc.af, usvc.fwmark);
svc = __ip_vs_svc_fwm_find(ipvs, usvc.af, usvc.fwmark);
rcu_read_unlock();
if (cmd != IP_VS_SO_SET_ADD
@ -2424,7 +2418,7 @@ do_ip_vs_set_ctl(struct sock *sk, int cmd, void __user *user, unsigned int len)
if (svc != NULL)
ret = -EEXIST;
else
ret = ip_vs_add_service(net, &usvc, &svc);
ret = ip_vs_add_service(ipvs, &usvc, &svc);
break;
case IP_VS_SO_SET_EDIT:
ret = ip_vs_edit_service(svc, &usvc);
@ -2483,7 +2477,7 @@ ip_vs_copy_service(struct ip_vs_service_entry *dst, struct ip_vs_service *src)
}
static inline int
__ip_vs_get_service_entries(struct net *net,
__ip_vs_get_service_entries(struct netns_ipvs *ipvs,
const struct ip_vs_get_services *get,
struct ip_vs_get_services __user *uptr)
{
@ -2495,7 +2489,7 @@ __ip_vs_get_service_entries(struct net *net,
for (idx = 0; idx < IP_VS_SVC_TAB_SIZE; idx++) {
hlist_for_each_entry(svc, &ip_vs_svc_table[idx], s_list) {
/* Only expose IPv4 entries to old interface */
if (svc->af != AF_INET || !net_eq(svc->net, net))
if (svc->af != AF_INET || (svc->ipvs != ipvs))
continue;
if (count >= get->num_services)
@ -2514,7 +2508,7 @@ __ip_vs_get_service_entries(struct net *net,
for (idx = 0; idx < IP_VS_SVC_TAB_SIZE; idx++) {
hlist_for_each_entry(svc, &ip_vs_svc_fwm_table[idx], f_list) {
/* Only expose IPv4 entries to old interface */
if (svc->af != AF_INET || !net_eq(svc->net, net))
if (svc->af != AF_INET || (svc->ipvs != ipvs))
continue;
if (count >= get->num_services)
@ -2534,7 +2528,7 @@ out:
}
static inline int
__ip_vs_get_dest_entries(struct net *net, const struct ip_vs_get_dests *get,
__ip_vs_get_dest_entries(struct netns_ipvs *ipvs, const struct ip_vs_get_dests *get,
struct ip_vs_get_dests __user *uptr)
{
struct ip_vs_service *svc;
@ -2543,9 +2537,9 @@ __ip_vs_get_dest_entries(struct net *net, const struct ip_vs_get_dests *get,
rcu_read_lock();
if (get->fwmark)
svc = __ip_vs_svc_fwm_find(net, AF_INET, get->fwmark);
svc = __ip_vs_svc_fwm_find(ipvs, AF_INET, get->fwmark);
else
svc = __ip_vs_service_find(net, AF_INET, get->protocol, &addr,
svc = __ip_vs_service_find(ipvs, AF_INET, get->protocol, &addr,
get->port);
rcu_read_unlock();
@ -2590,7 +2584,7 @@ __ip_vs_get_dest_entries(struct net *net, const struct ip_vs_get_dests *get,
}
static inline void
__ip_vs_get_timeouts(struct net *net, struct ip_vs_timeout_user *u)
__ip_vs_get_timeouts(struct netns_ipvs *ipvs, struct ip_vs_timeout_user *u)
{
#if defined(CONFIG_IP_VS_PROTO_TCP) || defined(CONFIG_IP_VS_PROTO_UDP)
struct ip_vs_proto_data *pd;
@ -2599,12 +2593,12 @@ __ip_vs_get_timeouts(struct net *net, struct ip_vs_timeout_user *u)
memset(u, 0, sizeof (*u));
#ifdef CONFIG_IP_VS_PROTO_TCP
pd = ip_vs_proto_data_get(net, IPPROTO_TCP);
pd = ip_vs_proto_data_get(ipvs, IPPROTO_TCP);
u->tcp_timeout = pd->timeout_table[IP_VS_TCP_S_ESTABLISHED] / HZ;
u->tcp_fin_timeout = pd->timeout_table[IP_VS_TCP_S_FIN_WAIT] / HZ;
#endif
#ifdef CONFIG_IP_VS_PROTO_UDP
pd = ip_vs_proto_data_get(net, IPPROTO_UDP);
pd = ip_vs_proto_data_get(ipvs, IPPROTO_UDP);
u->udp_timeout =
pd->timeout_table[IP_VS_UDP_S_NORMAL] / HZ;
#endif
@ -2723,7 +2717,7 @@ do_ip_vs_get_ctl(struct sock *sk, int cmd, void __user *user, int *len)
ret = -EINVAL;
goto out;
}
ret = __ip_vs_get_service_entries(net, get, user);
ret = __ip_vs_get_service_entries(ipvs, get, user);
}
break;
@ -2737,9 +2731,9 @@ do_ip_vs_get_ctl(struct sock *sk, int cmd, void __user *user, int *len)
addr.ip = entry->addr;
rcu_read_lock();
if (entry->fwmark)
svc = __ip_vs_svc_fwm_find(net, AF_INET, entry->fwmark);
svc = __ip_vs_svc_fwm_find(ipvs, AF_INET, entry->fwmark);
else
svc = __ip_vs_service_find(net, AF_INET,
svc = __ip_vs_service_find(ipvs, AF_INET,
entry->protocol, &addr,
entry->port);
rcu_read_unlock();
@ -2765,7 +2759,7 @@ do_ip_vs_get_ctl(struct sock *sk, int cmd, void __user *user, int *len)
ret = -EINVAL;
goto out;
}
ret = __ip_vs_get_dest_entries(net, get, user);
ret = __ip_vs_get_dest_entries(ipvs, get, user);
}
break;
@ -2773,7 +2767,7 @@ do_ip_vs_get_ctl(struct sock *sk, int cmd, void __user *user, int *len)
{
struct ip_vs_timeout_user t;
__ip_vs_get_timeouts(net, &t);
__ip_vs_get_timeouts(ipvs, &t);
if (copy_to_user(user, &t, sizeof(t)) != 0)
ret = -EFAULT;
}
@ -3008,12 +3002,13 @@ static int ip_vs_genl_dump_services(struct sk_buff *skb,
int idx = 0, i;
int start = cb->args[0];
struct ip_vs_service *svc;
struct net *net = skb_sknet(skb);
struct net *net = sock_net(skb->sk);
struct netns_ipvs *ipvs = net_ipvs(net);
mutex_lock(&__ip_vs_mutex);
for (i = 0; i < IP_VS_SVC_TAB_SIZE; i++) {
hlist_for_each_entry(svc, &ip_vs_svc_table[i], s_list) {
if (++idx <= start || !net_eq(svc->net, net))
if (++idx <= start || (svc->ipvs != ipvs))
continue;
if (ip_vs_genl_dump_service(skb, svc, cb) < 0) {
idx--;
@ -3024,7 +3019,7 @@ static int ip_vs_genl_dump_services(struct sk_buff *skb,
for (i = 0; i < IP_VS_SVC_TAB_SIZE; i++) {
hlist_for_each_entry(svc, &ip_vs_svc_fwm_table[i], f_list) {
if (++idx <= start || !net_eq(svc->net, net))
if (++idx <= start || (svc->ipvs != ipvs))
continue;
if (ip_vs_genl_dump_service(skb, svc, cb) < 0) {
idx--;
@ -3040,7 +3035,7 @@ nla_put_failure:
return skb->len;
}
static int ip_vs_genl_parse_service(struct net *net,
static int ip_vs_genl_parse_service(struct netns_ipvs *ipvs,
struct ip_vs_service_user_kern *usvc,
struct nlattr *nla, int full_entry,
struct ip_vs_service **ret_svc)
@ -3085,9 +3080,9 @@ static int ip_vs_genl_parse_service(struct net *net,
rcu_read_lock();
if (usvc->fwmark)
svc = __ip_vs_svc_fwm_find(net, usvc->af, usvc->fwmark);
svc = __ip_vs_svc_fwm_find(ipvs, usvc->af, usvc->fwmark);
else
svc = __ip_vs_service_find(net, usvc->af, usvc->protocol,
svc = __ip_vs_service_find(ipvs, usvc->af, usvc->protocol,
&usvc->addr, usvc->port);
rcu_read_unlock();
*ret_svc = svc;
@ -3125,14 +3120,14 @@ static int ip_vs_genl_parse_service(struct net *net,
return 0;
}
static struct ip_vs_service *ip_vs_genl_find_service(struct net *net,
static struct ip_vs_service *ip_vs_genl_find_service(struct netns_ipvs *ipvs,
struct nlattr *nla)
{
struct ip_vs_service_user_kern usvc;
struct ip_vs_service *svc;
int ret;
ret = ip_vs_genl_parse_service(net, &usvc, nla, 0, &svc);
ret = ip_vs_genl_parse_service(ipvs, &usvc, nla, 0, &svc);
return ret ? ERR_PTR(ret) : svc;
}
@ -3207,7 +3202,8 @@ static int ip_vs_genl_dump_dests(struct sk_buff *skb,
struct ip_vs_service *svc;
struct ip_vs_dest *dest;
struct nlattr *attrs[IPVS_CMD_ATTR_MAX + 1];
struct net *net = skb_sknet(skb);
struct net *net = sock_net(skb->sk);
struct netns_ipvs *ipvs = net_ipvs(net);
mutex_lock(&__ip_vs_mutex);
@ -3217,7 +3213,7 @@ static int ip_vs_genl_dump_dests(struct sk_buff *skb,
goto out_err;
svc = ip_vs_genl_find_service(net, attrs[IPVS_CMD_ATTR_SERVICE]);
svc = ip_vs_genl_find_service(ipvs, attrs[IPVS_CMD_ATTR_SERVICE]);
if (IS_ERR(svc) || svc == NULL)
goto out_err;
@ -3353,7 +3349,7 @@ nla_put_failure:
static int ip_vs_genl_dump_daemons(struct sk_buff *skb,
struct netlink_callback *cb)
{
struct net *net = skb_sknet(skb);
struct net *net = sock_net(skb->sk);
struct netns_ipvs *ipvs = net_ipvs(net);
mutex_lock(&ipvs->sync_mutex);
@ -3379,9 +3375,8 @@ nla_put_failure:
return skb->len;
}
static int ip_vs_genl_new_daemon(struct net *net, struct nlattr **attrs)
static int ip_vs_genl_new_daemon(struct netns_ipvs *ipvs, struct nlattr **attrs)
{
struct netns_ipvs *ipvs = net_ipvs(net);
struct ipvs_sync_daemon_cfg c;
struct nlattr *a;
int ret;
@ -3438,33 +3433,32 @@ static int ip_vs_genl_new_daemon(struct net *net, struct nlattr **attrs)
rtnl_lock();
mutex_lock(&ipvs->sync_mutex);
ret = start_sync_thread(net, &c,
ret = start_sync_thread(ipvs, &c,
nla_get_u32(attrs[IPVS_DAEMON_ATTR_STATE]));
mutex_unlock(&ipvs->sync_mutex);
rtnl_unlock();
return ret;
}
static int ip_vs_genl_del_daemon(struct net *net, struct nlattr **attrs)
static int ip_vs_genl_del_daemon(struct netns_ipvs *ipvs, struct nlattr **attrs)
{
struct netns_ipvs *ipvs = net_ipvs(net);
int ret;
if (!attrs[IPVS_DAEMON_ATTR_STATE])
return -EINVAL;
mutex_lock(&ipvs->sync_mutex);
ret = stop_sync_thread(net,
ret = stop_sync_thread(ipvs,
nla_get_u32(attrs[IPVS_DAEMON_ATTR_STATE]));
mutex_unlock(&ipvs->sync_mutex);
return ret;
}
static int ip_vs_genl_set_config(struct net *net, struct nlattr **attrs)
static int ip_vs_genl_set_config(struct netns_ipvs *ipvs, struct nlattr **attrs)
{
struct ip_vs_timeout_user t;
__ip_vs_get_timeouts(net, &t);
__ip_vs_get_timeouts(ipvs, &t);
if (attrs[IPVS_CMD_ATTR_TIMEOUT_TCP])
t.tcp_timeout = nla_get_u32(attrs[IPVS_CMD_ATTR_TIMEOUT_TCP]);
@ -3476,17 +3470,15 @@ static int ip_vs_genl_set_config(struct net *net, struct nlattr **attrs)
if (attrs[IPVS_CMD_ATTR_TIMEOUT_UDP])
t.udp_timeout = nla_get_u32(attrs[IPVS_CMD_ATTR_TIMEOUT_UDP]);
return ip_vs_set_timeout(net, &t);
return ip_vs_set_timeout(ipvs, &t);
}
static int ip_vs_genl_set_daemon(struct sk_buff *skb, struct genl_info *info)
{
int ret = -EINVAL, cmd;
struct net *net;
struct netns_ipvs *ipvs;
struct net *net = sock_net(skb->sk);
struct netns_ipvs *ipvs = net_ipvs(net);
net = skb_sknet(skb);
ipvs = net_ipvs(net);
cmd = info->genlhdr->cmd;
if (cmd == IPVS_CMD_NEW_DAEMON || cmd == IPVS_CMD_DEL_DAEMON) {
@ -3499,9 +3491,9 @@ static int ip_vs_genl_set_daemon(struct sk_buff *skb, struct genl_info *info)
goto out;
if (cmd == IPVS_CMD_NEW_DAEMON)
ret = ip_vs_genl_new_daemon(net, daemon_attrs);
ret = ip_vs_genl_new_daemon(ipvs, daemon_attrs);
else
ret = ip_vs_genl_del_daemon(net, daemon_attrs);
ret = ip_vs_genl_del_daemon(ipvs, daemon_attrs);
}
out:
@ -3515,22 +3507,22 @@ static int ip_vs_genl_set_cmd(struct sk_buff *skb, struct genl_info *info)
struct ip_vs_dest_user_kern udest;
int ret = 0, cmd;
int need_full_svc = 0, need_full_dest = 0;
struct net *net;
struct net *net = sock_net(skb->sk);
struct netns_ipvs *ipvs = net_ipvs(net);
net = skb_sknet(skb);
cmd = info->genlhdr->cmd;
mutex_lock(&__ip_vs_mutex);
if (cmd == IPVS_CMD_FLUSH) {
ret = ip_vs_flush(net, false);
ret = ip_vs_flush(ipvs, false);
goto out;
} else if (cmd == IPVS_CMD_SET_CONFIG) {
ret = ip_vs_genl_set_config(net, info->attrs);
ret = ip_vs_genl_set_config(ipvs, info->attrs);
goto out;
} else if (cmd == IPVS_CMD_ZERO &&
!info->attrs[IPVS_CMD_ATTR_SERVICE]) {
ret = ip_vs_zero_all(net);
ret = ip_vs_zero_all(ipvs);
goto out;
}
@ -3540,7 +3532,7 @@ static int ip_vs_genl_set_cmd(struct sk_buff *skb, struct genl_info *info)
if (cmd == IPVS_CMD_NEW_SERVICE || cmd == IPVS_CMD_SET_SERVICE)
need_full_svc = 1;
ret = ip_vs_genl_parse_service(net, &usvc,
ret = ip_vs_genl_parse_service(ipvs, &usvc,
info->attrs[IPVS_CMD_ATTR_SERVICE],
need_full_svc, &svc);
if (ret)
@ -3579,7 +3571,7 @@ static int ip_vs_genl_set_cmd(struct sk_buff *skb, struct genl_info *info)
/* The synchronization protocol is incompatible
* with mixed family services
*/
if (net_ipvs(net)->sync_state) {
if (ipvs->sync_state) {
ret = -EINVAL;
goto out;
}
@ -3599,7 +3591,7 @@ static int ip_vs_genl_set_cmd(struct sk_buff *skb, struct genl_info *info)
switch (cmd) {
case IPVS_CMD_NEW_SERVICE:
if (svc == NULL)
ret = ip_vs_add_service(net, &usvc, &svc);
ret = ip_vs_add_service(ipvs, &usvc, &svc);
else
ret = -EEXIST;
break;
@ -3637,9 +3629,9 @@ static int ip_vs_genl_get_cmd(struct sk_buff *skb, struct genl_info *info)
struct sk_buff *msg;
void *reply;
int ret, cmd, reply_cmd;
struct net *net;
struct net *net = sock_net(skb->sk);
struct netns_ipvs *ipvs = net_ipvs(net);
net = skb_sknet(skb);
cmd = info->genlhdr->cmd;
if (cmd == IPVS_CMD_GET_SERVICE)
@ -3668,7 +3660,7 @@ static int ip_vs_genl_get_cmd(struct sk_buff *skb, struct genl_info *info)
{
struct ip_vs_service *svc;
svc = ip_vs_genl_find_service(net,
svc = ip_vs_genl_find_service(ipvs,
info->attrs[IPVS_CMD_ATTR_SERVICE]);
if (IS_ERR(svc)) {
ret = PTR_ERR(svc);
@ -3689,7 +3681,7 @@ static int ip_vs_genl_get_cmd(struct sk_buff *skb, struct genl_info *info)
{
struct ip_vs_timeout_user t;
__ip_vs_get_timeouts(net, &t);
__ip_vs_get_timeouts(ipvs, &t);
#ifdef CONFIG_IP_VS_PROTO_TCP
if (nla_put_u32(msg, IPVS_CMD_ATTR_TIMEOUT_TCP,
t.tcp_timeout) ||
@ -3844,10 +3836,10 @@ static void ip_vs_genl_unregister(void)
* per netns intit/exit func.
*/
#ifdef CONFIG_SYSCTL
static int __net_init ip_vs_control_net_init_sysctl(struct net *net)
static int __net_init ip_vs_control_net_init_sysctl(struct netns_ipvs *ipvs)
{
struct net *net = ipvs->net;
int idx;
struct netns_ipvs *ipvs = net_ipvs(net);
struct ctl_table *tbl;
atomic_set(&ipvs->dropentry, 0);
@ -3866,6 +3858,10 @@ static int __net_init ip_vs_control_net_init_sysctl(struct net *net)
} else
tbl = vs_vars;
/* Initialize sysctl defaults */
for (idx = 0; idx < ARRAY_SIZE(vs_vars); idx++) {
if (tbl[idx].proc_handler == proc_do_defense_mode)
tbl[idx].extra2 = ipvs;
}
idx = 0;
ipvs->sysctl_amemthresh = 1024;
tbl[idx++].data = &ipvs->sysctl_amemthresh;
@ -3916,7 +3912,7 @@ static int __net_init ip_vs_control_net_init_sysctl(struct net *net)
kfree(tbl);
return -ENOMEM;
}
ip_vs_start_estimator(net, &ipvs->tot_stats);
ip_vs_start_estimator(ipvs, &ipvs->tot_stats);
ipvs->sysctl_tbl = tbl;
/* Schedule defense work */
INIT_DELAYED_WORK(&ipvs->defense_work, defense_work_handler);
@ -3925,14 +3921,14 @@ static int __net_init ip_vs_control_net_init_sysctl(struct net *net)
return 0;
}
static void __net_exit ip_vs_control_net_cleanup_sysctl(struct net *net)
static void __net_exit ip_vs_control_net_cleanup_sysctl(struct netns_ipvs *ipvs)
{
struct netns_ipvs *ipvs = net_ipvs(net);
struct net *net = ipvs->net;
cancel_delayed_work_sync(&ipvs->defense_work);
cancel_work_sync(&ipvs->defense_work.work);
unregister_net_sysctl_table(ipvs->sysctl_hdr);
ip_vs_stop_estimator(net, &ipvs->tot_stats);
ip_vs_stop_estimator(ipvs, &ipvs->tot_stats);
if (!net_eq(net, &init_net))
kfree(ipvs->sysctl_tbl);
@ -3940,8 +3936,8 @@ static void __net_exit ip_vs_control_net_cleanup_sysctl(struct net *net)
#else
static int __net_init ip_vs_control_net_init_sysctl(struct net *net) { return 0; }
static void __net_exit ip_vs_control_net_cleanup_sysctl(struct net *net) { }
static int __net_init ip_vs_control_net_init_sysctl(struct netns_ipvs *ipvs) { return 0; }
static void __net_exit ip_vs_control_net_cleanup_sysctl(struct netns_ipvs *ipvs) { }
#endif
@ -3949,10 +3945,10 @@ static struct notifier_block ip_vs_dst_notifier = {
.notifier_call = ip_vs_dst_event,
};
int __net_init ip_vs_control_net_init(struct net *net)
int __net_init ip_vs_control_net_init(struct netns_ipvs *ipvs)
{
struct net *net = ipvs->net;
int i, idx;
struct netns_ipvs *ipvs = net_ipvs(net);
/* Initialize rs_table */
for (idx = 0; idx < IP_VS_RTAB_SIZE; idx++)
@ -3961,7 +3957,7 @@ int __net_init ip_vs_control_net_init(struct net *net)
INIT_LIST_HEAD(&ipvs->dest_trash);
spin_lock_init(&ipvs->dest_trash_lock);
setup_timer(&ipvs->dest_trash_timer, ip_vs_dest_trash_expire,
(unsigned long) net);
(unsigned long) ipvs);
atomic_set(&ipvs->ftpsvc_counter, 0);
atomic_set(&ipvs->nullsvc_counter, 0);
@ -3983,7 +3979,7 @@ int __net_init ip_vs_control_net_init(struct net *net)
proc_create("ip_vs_stats_percpu", 0, net->proc_net,
&ip_vs_stats_percpu_fops);
if (ip_vs_control_net_init_sysctl(net))
if (ip_vs_control_net_init_sysctl(ipvs))
goto err;
return 0;
@ -3993,12 +3989,12 @@ err:
return -ENOMEM;
}
void __net_exit ip_vs_control_net_cleanup(struct net *net)
void __net_exit ip_vs_control_net_cleanup(struct netns_ipvs *ipvs)
{
struct netns_ipvs *ipvs = net_ipvs(net);
struct net *net = ipvs->net;
ip_vs_trash_cleanup(net);
ip_vs_control_net_cleanup_sysctl(net);
ip_vs_trash_cleanup(ipvs);
ip_vs_control_net_cleanup_sysctl(ipvs);
remove_proc_entry("ip_vs_stats_percpu", net->proc_net);
remove_proc_entry("ip_vs_stats", net->proc_net);
remove_proc_entry("ip_vs", net->proc_net);

20
net/netfilter/ipvs/ip_vs_est.c
View File

@ -102,10 +102,8 @@ static void estimation_timer(unsigned long arg)
struct ip_vs_estimator *e;
struct ip_vs_stats *s;
u64 rate;
struct net *net = (struct net *)arg;
struct netns_ipvs *ipvs;
struct netns_ipvs *ipvs = (struct netns_ipvs *)arg;
ipvs = net_ipvs(net);
spin_lock(&ipvs->est_lock);
list_for_each_entry(e, &ipvs->est_list, list) {
s = container_of(e, struct ip_vs_stats, est);
@ -140,9 +138,8 @@ static void estimation_timer(unsigned long arg)
mod_timer(&ipvs->est_timer, jiffies + 2*HZ);
}
void ip_vs_start_estimator(struct net *net, struct ip_vs_stats *stats)
void ip_vs_start_estimator(struct netns_ipvs *ipvs, struct ip_vs_stats *stats)
{
struct netns_ipvs *ipvs = net_ipvs(net);
struct ip_vs_estimator *est = &stats->est;
INIT_LIST_HEAD(&est->list);
@ -152,9 +149,8 @@ void ip_vs_start_estimator(struct net *net, struct ip_vs_stats *stats)
spin_unlock_bh(&ipvs->est_lock);
}
void ip_vs_stop_estimator(struct net *net, struct ip_vs_stats *stats)
void ip_vs_stop_estimator(struct netns_ipvs *ipvs, struct ip_vs_stats *stats)
{
struct netns_ipvs *ipvs = net_ipvs(net);
struct ip_vs_estimator *est = &stats->est;
spin_lock_bh(&ipvs->est_lock);
@ -192,18 +188,16 @@ void ip_vs_read_estimator(struct ip_vs_kstats *dst, struct ip_vs_stats *stats)
dst->outbps = (e->outbps + 0xF) >> 5;
}
int __net_init ip_vs_estimator_net_init(struct net *net)
int __net_init ip_vs_estimator_net_init(struct netns_ipvs *ipvs)
{
struct netns_ipvs *ipvs = net_ipvs(net);
INIT_LIST_HEAD(&ipvs->est_list);
spin_lock_init(&ipvs->est_lock);
setup_timer(&ipvs->est_timer, estimation_timer, (unsigned long)net);
setup_timer(&ipvs->est_timer, estimation_timer, (unsigned long)ipvs);
mod_timer(&ipvs->est_timer, jiffies + 2 * HZ);
return 0;
}
void __net_exit ip_vs_estimator_net_cleanup(struct net *net)
void __net_exit ip_vs_estimator_net_cleanup(struct netns_ipvs *ipvs)
{
del_timer_sync(&net_ipvs(net)->est_timer);
del_timer_sync(&ipvs->est_timer);
}

27
net/netfilter/ipvs/ip_vs_ftp.c
View File

@ -181,7 +181,6 @@ static int ip_vs_ftp_out(struct ip_vs_app *app, struct ip_vs_conn *cp,
int ret = 0;
enum ip_conntrack_info ctinfo;
struct nf_conn *ct;
struct net *net;
*diff = 0;
@ -223,14 +222,14 @@ 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(ip_vs_conn_net(cp), AF_INET,
ip_vs_conn_fill_param(cp->ipvs, 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(ip_vs_conn_net(cp),
ip_vs_conn_fill_param(cp->ipvs,
AF_INET, IPPROTO_TCP, &cp->caddr,
0, &cp->vaddr, port, &p);
/* As above, this is ipv4 only */
@ -289,9 +288,8 @@ static int ip_vs_ftp_out(struct ip_vs_app *app, struct ip_vs_conn *cp,
* would be adjusted twice.
*/
net = skb_net(skb);
cp->app_data = NULL;
ip_vs_tcp_conn_listen(net, n_cp);
ip_vs_tcp_conn_listen(n_cp);
ip_vs_conn_put(n_cp);
return ret;
}
@ -320,7 +318,6 @@ static int ip_vs_ftp_in(struct ip_vs_app *app, struct ip_vs_conn *cp,
union nf_inet_addr to;
__be16 port;
struct ip_vs_conn *n_cp;
struct net *net;
/* no diff required for incoming packets */
*diff = 0;
@ -392,7 +389,7 @@ 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(ip_vs_conn_net(cp), AF_INET,
ip_vs_conn_fill_param(cp->ipvs, AF_INET,
iph->protocol, &to, port, &cp->vaddr,
htons(ntohs(cp->vport)-1), &p);
n_cp = ip_vs_conn_in_get(&p);
@ -413,8 +410,7 @@ static int ip_vs_ftp_in(struct ip_vs_app *app, struct ip_vs_conn *cp,
/*
* Move tunnel to listen state
*/
net = skb_net(skb);
ip_vs_tcp_conn_listen(net, n_cp);
ip_vs_tcp_conn_listen(n_cp);
ip_vs_conn_put(n_cp);
return 1;
@ -447,14 +443,14 @@ static int __net_init __ip_vs_ftp_init(struct net *net)
if (!ipvs)
return -ENOENT;
app = register_ip_vs_app(net, &ip_vs_ftp);
app = register_ip_vs_app(ipvs, &ip_vs_ftp);
if (IS_ERR(app))
return PTR_ERR(app);
for (i = 0; i < ports_count; i++) {
if (!ports[i])
continue;
ret = register_ip_vs_app_inc(net, app, app->protocol, ports[i]);
ret = register_ip_vs_app_inc(ipvs, app, app->protocol, ports[i]);
if (ret)
goto err_unreg;
pr_info("%s: loaded support on port[%d] = %d\n",
@ -463,7 +459,7 @@ static int __net_init __ip_vs_ftp_init(struct net *net)
return 0;
err_unreg:
unregister_ip_vs_app(net, &ip_vs_ftp);
unregister_ip_vs_app(ipvs, &ip_vs_ftp);
return ret;
}
/*
@ -471,7 +467,12 @@ err_unreg:
*/
static void __ip_vs_ftp_exit(struct net *net)
{
unregister_ip_vs_app(net, &ip_vs_ftp);
struct netns_ipvs *ipvs = net_ipvs(net);
if (!ipvs)
return;
unregister_ip_vs_app(ipvs, &ip_vs_ftp);
}
static struct pernet_operations ip_vs_ftp_ops = {

3
net/netfilter/ipvs/ip_vs_lblc.c
View File

@ -250,8 +250,7 @@ static void ip_vs_lblc_flush(struct ip_vs_service *svc)
static int sysctl_lblc_expiration(struct ip_vs_service *svc)
{
#ifdef CONFIG_SYSCTL
struct netns_ipvs *ipvs = net_ipvs(svc->net);
return ipvs->sysctl_lblc_expiration;
return svc->ipvs->sysctl_lblc_expiration;
#else
return DEFAULT_EXPIRATION;
#endif

3
net/netfilter/ipvs/ip_vs_lblcr.c
View File

@ -415,8 +415,7 @@ static void ip_vs_lblcr_flush(struct ip_vs_service *svc)
static int sysctl_lblcr_expiration(struct ip_vs_service *svc)
{
#ifdef CONFIG_SYSCTL
struct netns_ipvs *ipvs = net_ipvs(svc->net);
return ipvs->sysctl_lblcr_expiration;
return svc->ipvs->sysctl_lblcr_expiration;
#else
return DEFAULT_EXPIRATION;
#endif

5
net/netfilter/ipvs/ip_vs_nfct.c
View File

@ -161,7 +161,7 @@ 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(net, exp->tuple.src.l3num, orig->dst.protonum,
ip_vs_conn_fill_param(net_ipvs(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);
@ -274,8 +274,7 @@ 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(ip_vs_conn_net(cp), &nf_ct_zone_dflt,
&tuple);
h = nf_conntrack_find_get(cp->ipvs->net, &nf_ct_zone_dflt, &tuple);
if (h) {
ct = nf_ct_tuplehash_to_ctrack(h);
/* Show what happens instead of calling nf_ct_kill() */

33
net/netfilter/ipvs/ip_vs_proto.c
View File

@ -63,9 +63,8 @@ static int __used __init register_ip_vs_protocol(struct ip_vs_protocol *pp)
* register an ipvs protocols netns related data
*/
static int
register_ip_vs_proto_netns(struct net *net, struct ip_vs_protocol *pp)
register_ip_vs_proto_netns(struct netns_ipvs *ipvs, struct ip_vs_protocol *pp)
{
struct netns_ipvs *ipvs = net_ipvs(net);
unsigned int hash = IP_VS_PROTO_HASH(pp->protocol);
struct ip_vs_proto_data *pd =
kzalloc(sizeof(struct ip_vs_proto_data), GFP_KERNEL);
@ -79,7 +78,7 @@ register_ip_vs_proto_netns(struct net *net, struct ip_vs_protocol *pp)
atomic_set(&pd->appcnt, 0); /* Init app counter */
if (pp->init_netns != NULL) {
int ret = pp->init_netns(net, pd);
int ret = pp->init_netns(ipvs, pd);
if (ret) {
/* unlink an free proto data */
ipvs->proto_data_table[hash] = pd->next;
@ -116,9 +115,8 @@ static int unregister_ip_vs_protocol(struct ip_vs_protocol *pp)
* unregister an ipvs protocols netns data
*/
static int
unregister_ip_vs_proto_netns(struct net *net, struct ip_vs_proto_data *pd)
unregister_ip_vs_proto_netns(struct netns_ipvs *ipvs, struct ip_vs_proto_data *pd)
{
struct netns_ipvs *ipvs = net_ipvs(net);
struct ip_vs_proto_data **pd_p;
unsigned int hash = IP_VS_PROTO_HASH(pd->pp->protocol);
@ -127,7 +125,7 @@ unregister_ip_vs_proto_netns(struct net *net, struct ip_vs_proto_data *pd)
if (*pd_p == pd) {
*pd_p = pd->next;
if (pd->pp->exit_netns != NULL)
pd->pp->exit_netns(net, pd);
pd->pp->exit_netns(ipvs, pd);
kfree(pd);
return 0;
}
@ -156,8 +154,8 @@ EXPORT_SYMBOL(ip_vs_proto_get);
/*
* get ip_vs_protocol object data by netns and proto
*/
static struct ip_vs_proto_data *
__ipvs_proto_data_get(struct netns_ipvs *ipvs, unsigned short proto)
struct ip_vs_proto_data *
ip_vs_proto_data_get(struct netns_ipvs *ipvs, unsigned short proto)
{
struct ip_vs_proto_data *pd;
unsigned int hash = IP_VS_PROTO_HASH(proto);
@ -169,14 +167,6 @@ __ipvs_proto_data_get(struct netns_ipvs *ipvs, unsigned short proto)
return NULL;
}
struct ip_vs_proto_data *
ip_vs_proto_data_get(struct net *net, unsigned short proto)
{
struct netns_ipvs *ipvs = net_ipvs(net);
return __ipvs_proto_data_get(ipvs, proto);
}
EXPORT_SYMBOL(ip_vs_proto_data_get);
/*
@ -317,7 +307,7 @@ ip_vs_tcpudp_debug_packet(int af, struct ip_vs_protocol *pp,
/*
* per network name-space init
*/
int __net_init ip_vs_protocol_net_init(struct net *net)
int __net_init ip_vs_protocol_net_init(struct netns_ipvs *ipvs)
{
int i, ret;
static struct ip_vs_protocol *protos[] = {
@ -339,27 +329,26 @@ int __net_init ip_vs_protocol_net_init(struct net *net)
};
for (i = 0; i < ARRAY_SIZE(protos); i++) {
ret = register_ip_vs_proto_netns(net, protos[i]);
ret = register_ip_vs_proto_netns(ipvs, protos[i]);
if (ret < 0)
goto cleanup;
}
return 0;
cleanup:
ip_vs_protocol_net_cleanup(net);
ip_vs_protocol_net_cleanup(ipvs);
return ret;
}
void __net_exit ip_vs_protocol_net_cleanup(struct net *net)
void __net_exit ip_vs_protocol_net_cleanup(struct netns_ipvs *ipvs)
{
struct netns_ipvs *ipvs = net_ipvs(net);
struct ip_vs_proto_data *pd;
int i;
/* unregister all the ipvs proto data for this netns */
for (i = 0; i < IP_VS_PROTO_TAB_SIZE; i++) {
while ((pd = ipvs->proto_data_table[i]) != NULL)
unregister_ip_vs_proto_netns(net, pd);
unregister_ip_vs_proto_netns(ipvs, pd);
}
}

19
net/netfilter/ipvs/ip_vs_proto_ah_esp.c
View File

@ -41,29 +41,28 @@ struct isakmp_hdr {
#define PORT_ISAKMP 500
static void
ah_esp_conn_fill_param_proto(struct net *net, int af,
ah_esp_conn_fill_param_proto(struct netns_ipvs *ipvs, int af,
const struct ip_vs_iphdr *iph,
struct ip_vs_conn_param *p)
{
if (likely(!ip_vs_iph_inverse(iph)))
ip_vs_conn_fill_param(net, af, IPPROTO_UDP,
ip_vs_conn_fill_param(ipvs, af, IPPROTO_UDP,
&iph->saddr, htons(PORT_ISAKMP),
&iph->daddr, htons(PORT_ISAKMP), p);
else
ip_vs_conn_fill_param(net, af, IPPROTO_UDP,
ip_vs_conn_fill_param(ipvs, af, IPPROTO_UDP,
&iph->daddr, htons(PORT_ISAKMP),
&iph->saddr, htons(PORT_ISAKMP), p);
}
static struct ip_vs_conn *
ah_esp_conn_in_get(int af, const struct sk_buff *skb,
ah_esp_conn_in_get(struct netns_ipvs *ipvs, int af, const struct sk_buff *skb,
const struct ip_vs_iphdr *iph)
{
struct ip_vs_conn *cp;
struct ip_vs_conn_param p;
struct net *net = skb_net(skb);
ah_esp_conn_fill_param_proto(net, af, iph, &p);
ah_esp_conn_fill_param_proto(ipvs, af, iph, &p);
cp = ip_vs_conn_in_get(&p);
if (!cp) {
/*
@ -83,14 +82,13 @@ ah_esp_conn_in_get(int af, const struct sk_buff *skb,
static struct ip_vs_conn *
ah_esp_conn_out_get(int af, const struct sk_buff *skb,
ah_esp_conn_out_get(struct netns_ipvs *ipvs, int af, const struct sk_buff *skb,
const struct ip_vs_iphdr *iph)
{
struct ip_vs_conn *cp;
struct ip_vs_conn_param p;
struct net *net = skb_net(skb);
ah_esp_conn_fill_param_proto(net, af, iph, &p);
ah_esp_conn_fill_param_proto(ipvs, af, iph, &p);
cp = ip_vs_conn_out_get(&p);
if (!cp) {
IP_VS_DBG_BUF(12, "Unknown ISAKMP entry for inout packet "
@ -106,7 +104,8 @@ ah_esp_conn_out_get(int af, const struct sk_buff *skb,
static int
ah_esp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd,
ah_esp_conn_schedule(struct netns_ipvs *ipvs, int af, struct sk_buff *skb,
struct ip_vs_proto_data *pd,
int *verdict, struct ip_vs_conn **cpp,
struct ip_vs_iphdr *iph)
{

28
net/netfilter/ipvs/ip_vs_proto_sctp.c
View File

@ -9,13 +9,12 @@
#include <net/ip_vs.h>
static int
sctp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd,
sctp_conn_schedule(struct netns_ipvs *ipvs, int af, struct sk_buff *skb,
struct ip_vs_proto_data *pd,
int *verdict, struct ip_vs_conn **cpp,
struct ip_vs_iphdr *iph)
{
struct net *net;
struct ip_vs_service *svc;
struct netns_ipvs *ipvs;
sctp_chunkhdr_t _schunkh, *sch;
sctp_sctphdr_t *sh, _sctph;
__be16 _ports[2], *ports = NULL;
@ -40,14 +39,12 @@ sctp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd,
return 0;
}
net = skb_net(skb);
ipvs = net_ipvs(net);
rcu_read_lock();
if (likely(!ip_vs_iph_inverse(iph)))
svc = ip_vs_service_find(net, af, skb->mark, iph->protocol,
svc = ip_vs_service_find(ipvs, af, skb->mark, iph->protocol,
&iph->daddr, ports[1]);
else
svc = ip_vs_service_find(net, af, skb->mark, iph->protocol,
svc = ip_vs_service_find(ipvs, af, skb->mark, iph->protocol,
&iph->saddr, ports[0]);
if (svc) {
int ignored;
@ -486,14 +483,13 @@ static inline __u16 sctp_app_hashkey(__be16 port)
& SCTP_APP_TAB_MASK;
}
static int sctp_register_app(struct net *net, struct ip_vs_app *inc)
static int sctp_register_app(struct netns_ipvs *ipvs, struct ip_vs_app *inc)
{
struct ip_vs_app *i;
__u16 hash;
__be16 port = inc->port;
int ret = 0;
struct netns_ipvs *ipvs = net_ipvs(net);
struct ip_vs_proto_data *pd = ip_vs_proto_data_get(net, IPPROTO_SCTP);
struct ip_vs_proto_data *pd = ip_vs_proto_data_get(ipvs, IPPROTO_SCTP);
hash = sctp_app_hashkey(port);
@ -510,9 +506,9 @@ out:
return ret;
}
static void sctp_unregister_app(struct net *net, struct ip_vs_app *inc)
static void sctp_unregister_app(struct netns_ipvs *ipvs, struct ip_vs_app *inc)
{
struct ip_vs_proto_data *pd = ip_vs_proto_data_get(net, IPPROTO_SCTP);
struct ip_vs_proto_data *pd = ip_vs_proto_data_get(ipvs, IPPROTO_SCTP);
atomic_dec(&pd->appcnt);
list_del_rcu(&inc->p_list);
@ -520,7 +516,7 @@ 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(ip_vs_conn_net(cp));
struct netns_ipvs *ipvs = cp->ipvs;
int hash;
struct ip_vs_app *inc;
int result = 0;
@ -561,10 +557,8 @@ out:
* timeouts is netns related now.
* ---------------------------------------------
*/
static int __ip_vs_sctp_init(struct net *net, struct ip_vs_proto_data *pd)
static int __ip_vs_sctp_init(struct netns_ipvs *ipvs, struct ip_vs_proto_data *pd)
{
struct netns_ipvs *ipvs = net_ipvs(net);
ip_vs_init_hash_table(ipvs->sctp_apps, SCTP_APP_TAB_SIZE);
pd->timeout_table = ip_vs_create_timeout_table((int *)sctp_timeouts,
sizeof(sctp_timeouts));
@ -573,7 +567,7 @@ static int __ip_vs_sctp_init(struct net *net, struct ip_vs_proto_data *pd)
return 0;
}
static void __ip_vs_sctp_exit(struct net *net, struct ip_vs_proto_data *pd)
static void __ip_vs_sctp_exit(struct netns_ipvs *ipvs, struct ip_vs_proto_data *pd)
{
kfree(pd->timeout_table);
}

33
net/netfilter/ipvs/ip_vs_proto_tcp.c
View File

@ -32,19 +32,15 @@
#include <net/ip_vs.h>
static int
tcp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd,
tcp_conn_schedule(struct netns_ipvs *ipvs, int af, struct sk_buff *skb,
struct ip_vs_proto_data *pd,
int *verdict, struct ip_vs_conn **cpp,
struct ip_vs_iphdr *iph)
{
struct net *net;
struct ip_vs_service *svc;
struct tcphdr _tcph, *th;
struct netns_ipvs *ipvs;
__be16 _ports[2], *ports = NULL;
net = skb_net(skb);
ipvs = net_ipvs(net);
/* In the event of icmp, we're only guaranteed to have the first 8
* bytes of the transport header, so we only check the rest of the
* TCP packet for non-ICMP packets
@ -70,10 +66,10 @@ tcp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd,
rcu_read_lock();
if (likely(!ip_vs_iph_inverse(iph)))
svc = ip_vs_service_find(net, af, skb->mark, iph->protocol,
svc = ip_vs_service_find(ipvs, af, skb->mark, iph->protocol,
&iph->daddr, ports[1]);
else
svc = ip_vs_service_find(net, af, skb->mark, iph->protocol,
svc = ip_vs_service_find(ipvs, af, skb->mark, iph->protocol,
&iph->saddr, ports[0]);
if (svc) {
@ -595,14 +591,13 @@ static inline __u16 tcp_app_hashkey(__be16 port)
}
static int tcp_register_app(struct net *net, struct ip_vs_app *inc)
static int tcp_register_app(struct netns_ipvs *ipvs, struct ip_vs_app *inc)
{
struct ip_vs_app *i;
__u16 hash;
__be16 port = inc->port;
int ret = 0;
struct netns_ipvs *ipvs = net_ipvs(net);
struct ip_vs_proto_data *pd = ip_vs_proto_data_get(net, IPPROTO_TCP);
struct ip_vs_proto_data *pd = ip_vs_proto_data_get(ipvs, IPPROTO_TCP);
hash = tcp_app_hashkey(port);
@ -621,9 +616,9 @@ static int tcp_register_app(struct net *net, struct ip_vs_app *inc)
static void
tcp_unregister_app(struct net *net, struct ip_vs_app *inc)
tcp_unregister_app(struct netns_ipvs *ipvs, struct ip_vs_app *inc)
{
struct ip_vs_proto_data *pd = ip_vs_proto_data_get(net, IPPROTO_TCP);
struct ip_vs_proto_data *pd = ip_vs_proto_data_get(ipvs, IPPROTO_TCP);
atomic_dec(&pd->appcnt);
list_del_rcu(&inc->p_list);
@ -633,7 +628,7 @@ 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(ip_vs_conn_net(cp));
struct netns_ipvs *ipvs = cp->ipvs;
int hash;
struct ip_vs_app *inc;
int result = 0;
@ -677,9 +672,9 @@ tcp_app_conn_bind(struct ip_vs_conn *cp)
/*
* Set LISTEN timeout. (ip_vs_conn_put will setup timer)
*/
void ip_vs_tcp_conn_listen(struct net *net, struct ip_vs_conn *cp)
void ip_vs_tcp_conn_listen(struct ip_vs_conn *cp)
{
struct ip_vs_proto_data *pd = ip_vs_proto_data_get(net, IPPROTO_TCP);
struct ip_vs_proto_data *pd = ip_vs_proto_data_get(cp->ipvs, IPPROTO_TCP);
spin_lock_bh(&cp->lock);
cp->state = IP_VS_TCP_S_LISTEN;
@ -692,10 +687,8 @@ void ip_vs_tcp_conn_listen(struct net *net, struct ip_vs_conn *cp)
* timeouts is netns related now.
* ---------------------------------------------
*/
static int __ip_vs_tcp_init(struct net *net, struct ip_vs_proto_data *pd)
static int __ip_vs_tcp_init(struct netns_ipvs *ipvs, struct ip_vs_proto_data *pd)
{
struct netns_ipvs *ipvs = net_ipvs(net);
ip_vs_init_hash_table(ipvs->tcp_apps, TCP_APP_TAB_SIZE);
pd->timeout_table = ip_vs_create_timeout_table((int *)tcp_timeouts,
sizeof(tcp_timeouts));
@ -705,7 +698,7 @@ static int __ip_vs_tcp_init(struct net *net, struct ip_vs_proto_data *pd)
return 0;
}
static void __ip_vs_tcp_exit(struct net *net, struct ip_vs_proto_data *pd)
static void __ip_vs_tcp_exit(struct netns_ipvs *ipvs, struct ip_vs_proto_data *pd)
{
kfree(pd->timeout_table);
}

28
net/netfilter/ipvs/ip_vs_proto_udp.c
View File

@ -29,11 +29,11 @@
#include <net/ip6_checksum.h>
static int
udp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd,
udp_conn_schedule(struct netns_ipvs *ipvs, int af, struct sk_buff *skb,
struct ip_vs_proto_data *pd,
int *verdict, struct ip_vs_conn **cpp,
struct ip_vs_iphdr *iph)
{
struct net *net;
struct ip_vs_service *svc;
struct udphdr _udph, *uh;
__be16 _ports[2], *ports = NULL;
@ -53,19 +53,18 @@ udp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd,
return 0;
}
net = skb_net(skb);
rcu_read_lock();
if (likely(!ip_vs_iph_inverse(iph)))
svc = ip_vs_service_find(net, af, skb->mark, iph->protocol,
svc = ip_vs_service_find(ipvs, af, skb->mark, iph->protocol,
&iph->daddr, ports[1]);
else
svc = ip_vs_service_find(net, af, skb->mark, iph->protocol,
svc = ip_vs_service_find(ipvs, af, skb->mark, iph->protocol,
&iph->saddr, ports[0]);
if (svc) {
int ignored;
if (ip_vs_todrop(net_ipvs(net))) {
if (ip_vs_todrop(ipvs)) {
/*
* It seems that we are very loaded.
* We have to drop this packet :(
@ -363,14 +362,13 @@ static inline __u16 udp_app_hashkey(__be16 port)
}
static int udp_register_app(struct net *net, struct ip_vs_app *inc)
static int udp_register_app(struct netns_ipvs *ipvs, struct ip_vs_app *inc)
{
struct ip_vs_app *i;
__u16 hash;
__be16 port = inc->port;
int ret = 0;
struct netns_ipvs *ipvs = net_ipvs(net);
struct ip_vs_proto_data *pd = ip_vs_proto_data_get(net, IPPROTO_UDP);
struct ip_vs_proto_data *pd = ip_vs_proto_data_get(ipvs, IPPROTO_UDP);
hash = udp_app_hashkey(port);
@ -389,9 +387,9 @@ static int udp_register_app(struct net *net, struct ip_vs_app *inc)
static void
udp_unregister_app(struct net *net, struct ip_vs_app *inc)
udp_unregister_app(struct netns_ipvs *ipvs, struct ip_vs_app *inc)
{
struct ip_vs_proto_data *pd = ip_vs_proto_data_get(net, IPPROTO_UDP);
struct ip_vs_proto_data *pd = ip_vs_proto_data_get(ipvs, IPPROTO_UDP);
atomic_dec(&pd->appcnt);
list_del_rcu(&inc->p_list);
@ -400,7 +398,7 @@ 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(ip_vs_conn_net(cp));
struct netns_ipvs *ipvs = cp->ipvs;
int hash;
struct ip_vs_app *inc;
int result = 0;
@ -471,10 +469,8 @@ udp_state_transition(struct ip_vs_conn *cp, int direction,
cp->timeout = pd->timeout_table[IP_VS_UDP_S_NORMAL];
}
static int __udp_init(struct net *net, struct ip_vs_proto_data *pd)
static int __udp_init(struct netns_ipvs *ipvs, struct ip_vs_proto_data *pd)
{
struct netns_ipvs *ipvs = net_ipvs(net);
ip_vs_init_hash_table(ipvs->udp_apps, UDP_APP_TAB_SIZE);
pd->timeout_table = ip_vs_create_timeout_table((int *)udp_timeouts,
sizeof(udp_timeouts));
@ -483,7 +479,7 @@ static int __udp_init(struct net *net, struct ip_vs_proto_data *pd)
return 0;
}
static void __udp_exit(struct net *net, struct ip_vs_proto_data *pd)
static void __udp_exit(struct netns_ipvs *ipvs, struct ip_vs_proto_data *pd)
{
kfree(pd->timeout_table);
}

87
net/netfilter/ipvs/ip_vs_sync.c
View File

@ -193,7 +193,7 @@ union ip_vs_sync_conn {
#define IPVS_OPT_F_PARAM (1 << (IPVS_OPT_PARAM-1))
struct ip_vs_sync_thread_data {
struct net *net;
struct netns_ipvs *ipvs;
struct socket *sock;
char *buf;
int id;
@ -533,10 +533,9 @@ set:
* Version 0 , could be switched in by sys_ctl.
* Add an ip_vs_conn information into the current sync_buff.
*/
static void ip_vs_sync_conn_v0(struct net *net, struct ip_vs_conn *cp,
static void ip_vs_sync_conn_v0(struct netns_ipvs *ipvs, struct ip_vs_conn *cp,
int pkts)
{
struct netns_ipvs *ipvs = net_ipvs(net);
struct ip_vs_sync_mesg_v0 *m;
struct ip_vs_sync_conn_v0 *s;
struct ip_vs_sync_buff *buff;
@ -615,7 +614,7 @@ static void ip_vs_sync_conn_v0(struct net *net, struct ip_vs_conn *cp,
pkts = atomic_add_return(1, &cp->in_pkts);
else
pkts = sysctl_sync_threshold(ipvs);
ip_vs_sync_conn(net, cp, pkts);
ip_vs_sync_conn(ipvs, cp, pkts);
}
}
@ -624,9 +623,8 @@ static void ip_vs_sync_conn_v0(struct net *net, struct ip_vs_conn *cp,
* Called by ip_vs_in.
* Sending Version 1 messages
*/
void ip_vs_sync_conn(struct net *net, struct ip_vs_conn *cp, int pkts)
void ip_vs_sync_conn(struct netns_ipvs *ipvs, struct ip_vs_conn *cp, int pkts)
{
struct netns_ipvs *ipvs = net_ipvs(net);
struct ip_vs_sync_mesg *m;
union ip_vs_sync_conn *s;
struct ip_vs_sync_buff *buff;
@ -637,7 +635,7 @@ void ip_vs_sync_conn(struct net *net, struct ip_vs_conn *cp, int pkts)
/* Handle old version of the protocol */
if (sysctl_sync_ver(ipvs) == 0) {
ip_vs_sync_conn_v0(net, cp, pkts);
ip_vs_sync_conn_v0(ipvs, cp, pkts);
return;
}
/* Do not sync ONE PACKET */
@ -784,21 +782,21 @@ control:
* fill_param used by version 1
*/
static inline int
ip_vs_conn_fill_param_sync(struct net *net, int af, union ip_vs_sync_conn *sc,
ip_vs_conn_fill_param_sync(struct netns_ipvs *ipvs, 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(net, af, sc->v6.protocol,
ip_vs_conn_fill_param(ipvs, 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(net, af, sc->v4.protocol,
ip_vs_conn_fill_param(ipvs, af, sc->v4.protocol,
(const union nf_inet_addr *)&sc->v4.caddr,
sc->v4.cport,
(const union nf_inet_addr *)&sc->v4.vaddr,
@ -837,7 +835,7 @@ ip_vs_conn_fill_param_sync(struct net *net, int af, union ip_vs_sync_conn *sc,
* Param: ...
* timeout is in sec.
*/
static void ip_vs_proc_conn(struct net *net, struct ip_vs_conn_param *param,
static void ip_vs_proc_conn(struct netns_ipvs *ipvs, struct ip_vs_conn_param *param,
unsigned int flags, unsigned int state,
unsigned int protocol, unsigned int type,
const union nf_inet_addr *daddr, __be16 dport,
@ -846,7 +844,6 @@ static void ip_vs_proc_conn(struct net *net, struct ip_vs_conn_param *param,
{
struct ip_vs_dest *dest;
struct ip_vs_conn *cp;
struct netns_ipvs *ipvs = net_ipvs(net);
if (!(flags & IP_VS_CONN_F_TEMPLATE)) {
cp = ip_vs_conn_in_get(param);
@ -904,7 +901,7 @@ static void ip_vs_proc_conn(struct net *net, struct ip_vs_conn_param *param,
* with synchronization, so we can make the assumption that
* the svc_af is the same as the dest_af
*/
dest = ip_vs_find_dest(net, type, type, daddr, dport,
dest = ip_vs_find_dest(ipvs, type, type, daddr, dport,
param->vaddr, param->vport, protocol,
fwmark, flags);
@ -941,7 +938,7 @@ static void ip_vs_proc_conn(struct net *net, struct ip_vs_conn_param *param,
} else {
struct ip_vs_proto_data *pd;
pd = ip_vs_proto_data_get(net, protocol);
pd = ip_vs_proto_data_get(ipvs, protocol);
if (!(flags & IP_VS_CONN_F_TEMPLATE) && pd && pd->timeout_table)
cp->timeout = pd->timeout_table[state];
else
@ -953,7 +950,7 @@ static void ip_vs_proc_conn(struct net *net, struct ip_vs_conn_param *param,
/*
* Process received multicast message for Version 0
*/
static void ip_vs_process_message_v0(struct net *net, const char *buffer,
static void ip_vs_process_message_v0(struct netns_ipvs *ipvs, const char *buffer,
const size_t buflen)
{
struct ip_vs_sync_mesg_v0 *m = (struct ip_vs_sync_mesg_v0 *)buffer;
@ -1009,14 +1006,14 @@ static void ip_vs_process_message_v0(struct net *net, const char *buffer,
}
}
ip_vs_conn_fill_param(net, AF_INET, s->protocol,
ip_vs_conn_fill_param(ipvs, AF_INET, s->protocol,
(const union nf_inet_addr *)&s->caddr,
s->cport,
(const union nf_inet_addr *)&s->vaddr,
s->vport, &param);
/* Send timeout as Zero */
ip_vs_proc_conn(net, &param, flags, state, s->protocol, AF_INET,
ip_vs_proc_conn(ipvs, &param, flags, state, s->protocol, AF_INET,
(union nf_inet_addr *)&s->daddr, s->dport,
0, 0, opt);
}
@ -1067,7 +1064,7 @@ static int ip_vs_proc_str(__u8 *p, unsigned int plen, unsigned int *data_len,
/*
* Process a Version 1 sync. connection
*/
static inline int ip_vs_proc_sync_conn(struct net *net, __u8 *p, __u8 *msg_end)
static inline int ip_vs_proc_sync_conn(struct netns_ipvs *ipvs, __u8 *p, __u8 *msg_end)
{
struct ip_vs_sync_conn_options opt;
union ip_vs_sync_conn *s;
@ -1171,21 +1168,21 @@ 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(net, af, s, &param, pe_data,
if (ip_vs_conn_fill_param_sync(ipvs, af, s, &param, pe_data,
pe_data_len, pe_name, pe_name_len)) {
retc = 50;
goto out;
}
/* If only IPv4, just silent skip IPv6 */
if (af == AF_INET)
ip_vs_proc_conn(net, &param, flags, state, s->v4.protocol, af,
ip_vs_proc_conn(ipvs, &param, flags, state, s->v4.protocol, af,
(union nf_inet_addr *)&s->v4.daddr, s->v4.dport,
ntohl(s->v4.timeout), ntohl(s->v4.fwmark),
(opt_flags & IPVS_OPT_F_SEQ_DATA ? &opt : NULL)
);
#ifdef CONFIG_IP_VS_IPV6
else
ip_vs_proc_conn(net, &param, flags, state, s->v6.protocol, af,
ip_vs_proc_conn(ipvs, &param, flags, state, s->v6.protocol, af,
(union nf_inet_addr *)&s->v6.daddr, s->v6.dport,
ntohl(s->v6.timeout), ntohl(s->v6.fwmark),
(opt_flags & IPVS_OPT_F_SEQ_DATA ? &opt : NULL)
@ -1204,10 +1201,9 @@ out:
* ip_vs_conn entries.
* Handles Version 0 & 1
*/
static void ip_vs_process_message(struct net *net, __u8 *buffer,
static void ip_vs_process_message(struct netns_ipvs *ipvs, __u8 *buffer,
const size_t buflen)
{
struct netns_ipvs *ipvs = net_ipvs(net);
struct ip_vs_sync_mesg *m2 = (struct ip_vs_sync_mesg *)buffer;
__u8 *p, *msg_end;
int i, nr_conns;
@ -1257,7 +1253,7 @@ static void ip_vs_process_message(struct net *net, __u8 *buffer,
return;
}
/* Process a single sync_conn */
retc = ip_vs_proc_sync_conn(net, p, msg_end);
retc = ip_vs_proc_sync_conn(ipvs, p, msg_end);
if (retc < 0) {
IP_VS_ERR_RL("BACKUP, Dropping buffer, Err: %d in decoding\n",
retc);
@ -1268,7 +1264,7 @@ static void ip_vs_process_message(struct net *net, __u8 *buffer,
}
} else {
/* Old type of message */
ip_vs_process_message_v0(net, buffer, buflen);
ip_vs_process_message_v0(ipvs, buffer, buflen);
return;
}
}
@ -1493,16 +1489,15 @@ static void get_mcast_sockaddr(union ipvs_sockaddr *sa, int *salen,
/*
* Set up sending multicast socket over UDP
*/
static struct socket *make_send_sock(struct net *net, int id)
static struct socket *make_send_sock(struct netns_ipvs *ipvs, int id)
{
struct netns_ipvs *ipvs = net_ipvs(net);
/* multicast addr */
union ipvs_sockaddr mcast_addr;
struct socket *sock;
int result, salen;
/* First create a socket */
result = sock_create_kern(net, ipvs->mcfg.mcast_af, SOCK_DGRAM,
result = sock_create_kern(ipvs->net, ipvs->mcfg.mcast_af, SOCK_DGRAM,
IPPROTO_UDP, &sock);
if (result < 0) {
pr_err("Error during creation of socket; terminating\n");
@ -1550,16 +1545,15 @@ error:
/*
* Set up receiving multicast socket over UDP
*/
static struct socket *make_receive_sock(struct net *net, int id)
static struct socket *make_receive_sock(struct netns_ipvs *ipvs, int id)
{
struct netns_ipvs *ipvs = net_ipvs(net);
/* multicast addr */
union ipvs_sockaddr mcast_addr;
struct socket *sock;
int result, salen;
/* First create a socket */
result = sock_create_kern(net, ipvs->bcfg.mcast_af, SOCK_DGRAM,
result = sock_create_kern(ipvs->net, ipvs->bcfg.mcast_af, SOCK_DGRAM,
IPPROTO_UDP, &sock);
if (result < 0) {
pr_err("Error during creation of socket; terminating\n");
@ -1687,7 +1681,7 @@ next_sync_buff(struct netns_ipvs *ipvs, struct ipvs_master_sync_state *ms)
static int sync_thread_master(void *data)
{
struct ip_vs_sync_thread_data *tinfo = data;
struct netns_ipvs *ipvs = net_ipvs(tinfo->net);
struct netns_ipvs *ipvs = tinfo->ipvs;
struct ipvs_master_sync_state *ms = &ipvs->ms[tinfo->id];
struct sock *sk = tinfo->sock->sk;
struct ip_vs_sync_buff *sb;
@ -1743,7 +1737,7 @@ done:
static int sync_thread_backup(void *data)
{
struct ip_vs_sync_thread_data *tinfo = data;
struct netns_ipvs *ipvs = net_ipvs(tinfo->net);
struct netns_ipvs *ipvs = tinfo->ipvs;
int len;
pr_info("sync thread started: state = BACKUP, mcast_ifn = %s, "
@ -1765,7 +1759,7 @@ static int sync_thread_backup(void *data)
break;
}
ip_vs_process_message(tinfo->net, tinfo->buf, len);
ip_vs_process_message(ipvs, tinfo->buf, len);
}
}
@ -1778,13 +1772,12 @@ static int sync_thread_backup(void *data)
}
int start_sync_thread(struct net *net, struct ipvs_sync_daemon_cfg *c,
int start_sync_thread(struct netns_ipvs *ipvs, struct ipvs_sync_daemon_cfg *c,
int state)
{
struct ip_vs_sync_thread_data *tinfo;
struct task_struct **array = NULL, *task;
struct socket *sock;
struct netns_ipvs *ipvs = net_ipvs(net);
struct net_device *dev;
char *name;
int (*threadfn)(void *data);
@ -1811,7 +1804,7 @@ int start_sync_thread(struct net *net, struct ipvs_sync_daemon_cfg *c,
if (!c->mcast_ttl)
c->mcast_ttl = 1;
dev = __dev_get_by_name(net, c->mcast_ifn);
dev = __dev_get_by_name(ipvs->net, c->mcast_ifn);
if (!dev) {
pr_err("Unknown mcast interface: %s\n", c->mcast_ifn);
return -ENODEV;
@ -1873,9 +1866,9 @@ int start_sync_thread(struct net *net, struct ipvs_sync_daemon_cfg *c,
tinfo = NULL;
for (id = 0; id < count; id++) {
if (state == IP_VS_STATE_MASTER)
sock = make_send_sock(net, id);
sock = make_send_sock(ipvs, id);
else
sock = make_receive_sock(net, id);
sock = make_receive_sock(ipvs, id);
if (IS_ERR(sock)) {
result = PTR_ERR(sock);
goto outtinfo;
@ -1883,7 +1876,7 @@ int start_sync_thread(struct net *net, struct ipvs_sync_daemon_cfg *c,
tinfo = kmalloc(sizeof(*tinfo), GFP_KERNEL);
if (!tinfo)
goto outsocket;
tinfo->net = net;
tinfo->ipvs = ipvs;
tinfo->sock = sock;
if (state == IP_VS_STATE_BACKUP) {
tinfo->buf = kmalloc(ipvs->bcfg.sync_maxlen,
@ -1947,9 +1940,8 @@ out:
}
int stop_sync_thread(struct net *net, int state)
int stop_sync_thread(struct netns_ipvs *ipvs, int state)
{
struct netns_ipvs *ipvs = net_ipvs(net);
struct task_struct **array;
int id;
int retc = -EINVAL;
@ -2015,27 +2007,24 @@ int stop_sync_thread(struct net *net, int state)
/*
* Initialize data struct for each netns
*/
int __net_init ip_vs_sync_net_init(struct net *net)
int __net_init ip_vs_sync_net_init(struct netns_ipvs *ipvs)
{
struct netns_ipvs *ipvs = net_ipvs(net);
__mutex_init(&ipvs->sync_mutex, "ipvs->sync_mutex", &__ipvs_sync_key);
spin_lock_init(&ipvs->sync_lock);
spin_lock_init(&ipvs->sync_buff_lock);
return 0;
}
void ip_vs_sync_net_cleanup(struct net *net)
void ip_vs_sync_net_cleanup(struct netns_ipvs *ipvs)
{
int retc;
struct netns_ipvs *ipvs = net_ipvs(net);
mutex_lock(&ipvs->sync_mutex);
retc = stop_sync_thread(net, IP_VS_STATE_MASTER);
retc = stop_sync_thread(ipvs, IP_VS_STATE_MASTER);
if (retc && retc != -ESRCH)
pr_err("Failed to stop Master Daemon\n");
retc = stop_sync_thread(net, IP_VS_STATE_BACKUP);
retc = stop_sync_thread(ipvs, IP_VS_STATE_BACKUP);
if (retc && retc != -ESRCH)
pr_err("Failed to stop Backup Daemon\n");
mutex_unlock(&ipvs->sync_mutex);

55
net/netfilter/ipvs/ip_vs_xmit.c
View File

@ -212,13 +212,14 @@ static inline void maybe_update_pmtu(int skb_af, struct sk_buff *skb, int mtu)
ort->dst.ops->update_pmtu(&ort->dst, sk, NULL, mtu);
}
static inline bool ensure_mtu_is_adequate(int skb_af, int rt_mode,
static inline bool ensure_mtu_is_adequate(struct netns_ipvs *ipvs, int skb_af,
int rt_mode,
struct ip_vs_iphdr *ipvsh,
struct sk_buff *skb, int mtu)
{
#ifdef CONFIG_IP_VS_IPV6
if (skb_af == AF_INET6) {
struct net *net = dev_net(skb_dst(skb)->dev);
struct net *net = ipvs->net;
if (unlikely(__mtu_check_toobig_v6(skb, mtu))) {
if (!skb->dev)
@ -233,8 +234,6 @@ static inline bool ensure_mtu_is_adequate(int skb_af, int rt_mode,
} else
#endif
{
struct netns_ipvs *ipvs = net_ipvs(skb_net(skb));
/* If we're going to tunnel the packet and pmtu discovery
* is disabled, we'll just fragment it anyway
*/
@ -257,11 +256,12 @@ static inline bool ensure_mtu_is_adequate(int skb_af, int rt_mode,
/* Get route to destination or remote server */
static int
__ip_vs_get_out_rt(int skb_af, struct sk_buff *skb, struct ip_vs_dest *dest,
__ip_vs_get_out_rt(struct netns_ipvs *ipvs, int skb_af, struct sk_buff *skb,
struct ip_vs_dest *dest,
__be32 daddr, int rt_mode, __be32 *ret_saddr,
struct ip_vs_iphdr *ipvsh)
{
struct net *net = dev_net(skb_dst(skb)->dev);
struct net *net = ipvs->net;
struct ip_vs_dest_dst *dest_dst;
struct rtable *rt; /* Route to the other host */
int mtu;
@ -337,7 +337,7 @@ __ip_vs_get_out_rt(int skb_af, struct sk_buff *skb, struct ip_vs_dest *dest,
maybe_update_pmtu(skb_af, skb, mtu);
}
if (!ensure_mtu_is_adequate(skb_af, rt_mode, ipvsh, skb, mtu))
if (!ensure_mtu_is_adequate(ipvs, skb_af, rt_mode, ipvsh, skb, mtu))
goto err_put;
skb_dst_drop(skb);
@ -403,11 +403,12 @@ out_err:
* Get route to destination or remote server
*/
static int
__ip_vs_get_out_rt_v6(int skb_af, struct sk_buff *skb, struct ip_vs_dest *dest,
__ip_vs_get_out_rt_v6(struct netns_ipvs *ipvs, int skb_af, struct sk_buff *skb,
struct ip_vs_dest *dest,
struct in6_addr *daddr, struct in6_addr *ret_saddr,
struct ip_vs_iphdr *ipvsh, int do_xfrm, int rt_mode)
{
struct net *net = dev_net(skb_dst(skb)->dev);
struct net *net = ipvs->net;
struct ip_vs_dest_dst *dest_dst;
struct rt6_info *rt; /* Route to the other host */
struct dst_entry *dst;
@ -485,7 +486,7 @@ __ip_vs_get_out_rt_v6(int skb_af, struct sk_buff *skb, struct ip_vs_dest *dest,
maybe_update_pmtu(skb_af, skb, mtu);
}
if (!ensure_mtu_is_adequate(skb_af, rt_mode, ipvsh, skb, mtu))
if (!ensure_mtu_is_adequate(ipvs, skb_af, rt_mode, ipvsh, skb, mtu))
goto err_put;
skb_dst_drop(skb);
@ -574,7 +575,7 @@ static inline int ip_vs_nat_send_or_cont(int pf, struct sk_buff *skb,
skb_forward_csum(skb);
if (!skb->sk)
skb_sender_cpu_clear(skb);
NF_HOOK(pf, NF_INET_LOCAL_OUT, ip_vs_conn_net(cp), NULL, skb,
NF_HOOK(pf, NF_INET_LOCAL_OUT, cp->ipvs->net, NULL, skb,
NULL, skb_dst(skb)->dev, dst_output_okfn);
} else
ret = NF_ACCEPT;
@ -596,7 +597,7 @@ static inline int ip_vs_send_or_cont(int pf, struct sk_buff *skb,
skb_forward_csum(skb);
if (!skb->sk)
skb_sender_cpu_clear(skb);
NF_HOOK(pf, NF_INET_LOCAL_OUT, ip_vs_conn_net(cp), NULL, skb,
NF_HOOK(pf, NF_INET_LOCAL_OUT, cp->ipvs->net, NULL, skb,
NULL, skb_dst(skb)->dev, dst_output_okfn);
} else
ret = NF_ACCEPT;
@ -630,7 +631,7 @@ ip_vs_bypass_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
EnterFunction(10);
rcu_read_lock();
if (__ip_vs_get_out_rt(cp->af, skb, NULL, iph->daddr,
if (__ip_vs_get_out_rt(cp->ipvs, cp->af, skb, NULL, iph->daddr,
IP_VS_RT_MODE_NON_LOCAL, NULL, ipvsh) < 0)
goto tx_error;
@ -662,7 +663,8 @@ ip_vs_bypass_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
EnterFunction(10);
rcu_read_lock();
if (__ip_vs_get_out_rt_v6(cp->af, skb, NULL, &iph->daddr, NULL,
if (__ip_vs_get_out_rt_v6(cp->ipvs, cp->af, skb, NULL,
&iph->daddr, NULL,
ipvsh, 0, IP_VS_RT_MODE_NON_LOCAL) < 0)
goto tx_error;
@ -709,7 +711,7 @@ ip_vs_nat_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
}
was_input = rt_is_input_route(skb_rtable(skb));
local = __ip_vs_get_out_rt(cp->af, skb, cp->dest, cp->daddr.ip,
local = __ip_vs_get_out_rt(cp->ipvs, cp->af, skb, cp->dest, cp->daddr.ip,
IP_VS_RT_MODE_LOCAL |
IP_VS_RT_MODE_NON_LOCAL |
IP_VS_RT_MODE_RDR, NULL, ipvsh);
@ -798,7 +800,8 @@ ip_vs_nat_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
IP_VS_DBG(10, "filled cport=%d\n", ntohs(*p));
}
local = __ip_vs_get_out_rt_v6(cp->af, skb, cp->dest, &cp->daddr.in6,
local = __ip_vs_get_out_rt_v6(cp->ipvs, cp->af, skb, cp->dest,
&cp->daddr.in6,
NULL, ipvsh, 0,
IP_VS_RT_MODE_LOCAL |
IP_VS_RT_MODE_NON_LOCAL |
@ -971,8 +974,8 @@ int
ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
struct ip_vs_protocol *pp, struct ip_vs_iphdr *ipvsh)
{
struct net *net = skb_net(skb);
struct netns_ipvs *ipvs = net_ipvs(net);
struct netns_ipvs *ipvs = cp->ipvs;
struct net *net = ipvs->net;
struct rtable *rt; /* Route to the other host */
__be32 saddr; /* Source for tunnel */
struct net_device *tdev; /* Device to other host */
@ -988,7 +991,7 @@ ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
EnterFunction(10);
rcu_read_lock();
local = __ip_vs_get_out_rt(cp->af, skb, cp->dest, cp->daddr.ip,
local = __ip_vs_get_out_rt(ipvs, cp->af, skb, cp->dest, cp->daddr.ip,
IP_VS_RT_MODE_LOCAL |
IP_VS_RT_MODE_NON_LOCAL |
IP_VS_RT_MODE_CONNECT |
@ -1082,7 +1085,8 @@ ip_vs_tunnel_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
EnterFunction(10);
rcu_read_lock();
local = __ip_vs_get_out_rt_v6(cp->af, skb, cp->dest, &cp->daddr.in6,
local = __ip_vs_get_out_rt_v6(cp->ipvs, cp->af, skb, cp->dest,
&cp->daddr.in6,
&saddr, ipvsh, 1,
IP_VS_RT_MODE_LOCAL |
IP_VS_RT_MODE_NON_LOCAL |
@ -1169,7 +1173,7 @@ ip_vs_dr_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
EnterFunction(10);
rcu_read_lock();
local = __ip_vs_get_out_rt(cp->af, skb, cp->dest, cp->daddr.ip,
local = __ip_vs_get_out_rt(cp->ipvs, cp->af, skb, cp->dest, cp->daddr.ip,
IP_VS_RT_MODE_LOCAL |
IP_VS_RT_MODE_NON_LOCAL |
IP_VS_RT_MODE_KNOWN_NH, NULL, ipvsh);
@ -1208,7 +1212,8 @@ ip_vs_dr_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
EnterFunction(10);
rcu_read_lock();
local = __ip_vs_get_out_rt_v6(cp->af, skb, cp->dest, &cp->daddr.in6,
local = __ip_vs_get_out_rt_v6(cp->ipvs, cp->af, skb, cp->dest,
&cp->daddr.in6,
NULL, ipvsh, 0,
IP_VS_RT_MODE_LOCAL |
IP_VS_RT_MODE_NON_LOCAL |
@ -1277,7 +1282,7 @@ ip_vs_icmp_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
IP_VS_RT_MODE_LOCAL | IP_VS_RT_MODE_NON_LOCAL |
IP_VS_RT_MODE_RDR : IP_VS_RT_MODE_NON_LOCAL;
rcu_read_lock();
local = __ip_vs_get_out_rt(cp->af, skb, cp->dest, cp->daddr.ip, rt_mode,
local = __ip_vs_get_out_rt(cp->ipvs, cp->af, skb, cp->dest, cp->daddr.ip, rt_mode,
NULL, iph);
if (local < 0)
goto tx_error;
@ -1369,8 +1374,8 @@ ip_vs_icmp_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
IP_VS_RT_MODE_LOCAL | IP_VS_RT_MODE_NON_LOCAL |
IP_VS_RT_MODE_RDR : IP_VS_RT_MODE_NON_LOCAL;
rcu_read_lock();
local = __ip_vs_get_out_rt_v6(cp->af, skb, cp->dest, &cp->daddr.in6,
NULL, ipvsh, 0, rt_mode);
local = __ip_vs_get_out_rt_v6(cp->ipvs, cp->af, skb, cp->dest,
&cp->daddr.in6, NULL, ipvsh, 0, rt_mode);
if (local < 0)
goto tx_error;
rt = (struct rt6_info *) skb_dst(skb);

3
net/netfilter/xt_ipvs.c
View File

@ -48,6 +48,7 @@ static bool
ipvs_mt(const struct sk_buff *skb, struct xt_action_param *par)
{
const struct xt_ipvs_mtinfo *data = par->matchinfo;
struct netns_ipvs *ipvs = net_ipvs(par->net);
/* ipvs_mt_check ensures that family is only NFPROTO_IPV[46]. */
const u_int8_t family = par->family;
struct ip_vs_iphdr iph;
@ -85,7 +86,7 @@ ipvs_mt(const struct sk_buff *skb, struct xt_action_param *par)
/*
* Check if the packet belongs to an existing entry
*/
cp = pp->conn_out_get(family, skb, &iph);
cp = pp->conn_out_get(ipvs, family, skb, &iph);
if (unlikely(cp == NULL)) {
match = false;
goto out;