extern unsigned int nf_conntrack_hash_rnd;
void init_nf_conntrack_hash_rnd(void);
-void nf_conntrack_tmpl_insert(struct net *net, struct nf_conn *tmpl);
+struct nf_conn *nf_ct_tmpl_alloc(struct net *net, u16 zone, gfp_t flags);
#define NF_CT_STAT_INC(net, count) __this_cpu_inc((net)->ct.stat->count)
#define NF_CT_STAT_INC_ATOMIC(net, count) this_cpu_inc((net)->ct.stat->count)
spinlock_t lock;
struct hlist_nulls_head unconfirmed;
struct hlist_nulls_head dying;
- struct hlist_nulls_head tmpl;
};
struct netns_ct {
* return *ignored=0 i.e. ICMP and NF_DROP
*/
sched = rcu_dereference(svc->scheduler);
- dest = sched->schedule(svc, skb, iph);
+ if (sched) {
+ /* read svc->sched_data after svc->scheduler */
+ smp_rmb();
+ dest = sched->schedule(svc, skb, iph);
+ } else {
+ dest = NULL;
+ }
if (!dest) {
IP_VS_DBG(1, "p-schedule: no dest found.\n");
kfree(param.pe_data);
}
sched = rcu_dereference(svc->scheduler);
- dest = sched->schedule(svc, skb, iph);
+ if (sched) {
+ /* read svc->sched_data after svc->scheduler */
+ smp_rmb();
+ dest = sched->schedule(svc, skb, iph);
+ } else {
+ dest = NULL;
+ }
if (dest == NULL) {
IP_VS_DBG(1, "Schedule: no dest found.\n");
return NULL;
__ip_vs_dst_cache_reset(dest);
spin_unlock_bh(&dest->dst_lock);
- sched = rcu_dereference_protected(svc->scheduler, 1);
if (add) {
ip_vs_start_estimator(svc->net, &dest->stats);
list_add_rcu(&dest->n_list, &svc->destinations);
svc->num_dests++;
- if (sched->add_dest)
+ sched = rcu_dereference_protected(svc->scheduler, 1);
+ if (sched && sched->add_dest)
sched->add_dest(svc, dest);
} else {
- if (sched->upd_dest)
+ sched = rcu_dereference_protected(svc->scheduler, 1);
+ if (sched && sched->upd_dest)
sched->upd_dest(svc, dest);
}
}
struct ip_vs_scheduler *sched;
sched = rcu_dereference_protected(svc->scheduler, 1);
- if (sched->del_dest)
+ if (sched && sched->del_dest)
sched->del_dest(svc, dest);
}
}
ip_vs_use_count_inc();
/* Lookup the scheduler by 'u->sched_name' */
- sched = ip_vs_scheduler_get(u->sched_name);
- if (sched == NULL) {
- pr_info("Scheduler module ip_vs_%s not found\n", u->sched_name);
- ret = -ENOENT;
- goto out_err;
+ if (strcmp(u->sched_name, "none")) {
+ sched = ip_vs_scheduler_get(u->sched_name);
+ if (!sched) {
+ pr_info("Scheduler module ip_vs_%s not found\n",
+ u->sched_name);
+ ret = -ENOENT;
+ goto out_err;
+ }
}
if (u->pe_name && *u->pe_name) {
spin_lock_init(&svc->stats.lock);
/* Bind the scheduler */
- ret = ip_vs_bind_scheduler(svc, sched);
- if (ret)
- goto out_err;
- sched = NULL;
+ if (sched) {
+ ret = ip_vs_bind_scheduler(svc, sched);
+ if (ret)
+ goto out_err;
+ sched = NULL;
+ }
/* Bind the ct retriever */
RCU_INIT_POINTER(svc->pe, pe);
static int
ip_vs_edit_service(struct ip_vs_service *svc, struct ip_vs_service_user_kern *u)
{
- struct ip_vs_scheduler *sched, *old_sched;
+ struct ip_vs_scheduler *sched = NULL, *old_sched;
struct ip_vs_pe *pe = NULL, *old_pe = NULL;
int ret = 0;
/*
* Lookup the scheduler, by 'u->sched_name'
*/
- sched = ip_vs_scheduler_get(u->sched_name);
- if (sched == NULL) {
- pr_info("Scheduler module ip_vs_%s not found\n", u->sched_name);
- return -ENOENT;
+ if (strcmp(u->sched_name, "none")) {
+ sched = ip_vs_scheduler_get(u->sched_name);
+ if (!sched) {
+ pr_info("Scheduler module ip_vs_%s not found\n",
+ u->sched_name);
+ return -ENOENT;
+ }
}
old_sched = sched;
old_sched = rcu_dereference_protected(svc->scheduler, 1);
if (sched != old_sched) {
+ if (old_sched) {
+ ip_vs_unbind_scheduler(svc, old_sched);
+ RCU_INIT_POINTER(svc->scheduler, NULL);
+ /* Wait all svc->sched_data users */
+ synchronize_rcu();
+ }
/* Bind the new scheduler */
- ret = ip_vs_bind_scheduler(svc, sched);
- if (ret) {
- old_sched = sched;
- goto out;
+ if (sched) {
+ ret = ip_vs_bind_scheduler(svc, sched);
+ if (ret) {
+ ip_vs_scheduler_put(sched);
+ goto out;
+ }
}
- /* Unbind the old scheduler on success */
- ip_vs_unbind_scheduler(svc, old_sched);
}
/*
const struct ip_vs_iter *iter = seq->private;
const struct ip_vs_dest *dest;
struct ip_vs_scheduler *sched = rcu_dereference(svc->scheduler);
+ char *sched_name = sched ? sched->name : "none";
if (iter->table == ip_vs_svc_table) {
#ifdef CONFIG_IP_VS_IPV6
ip_vs_proto_name(svc->protocol),
&svc->addr.in6,
ntohs(svc->port),
- sched->name);
+ sched_name);
else
#endif
seq_printf(seq, "%s %08X:%04X %s %s ",
ip_vs_proto_name(svc->protocol),
ntohl(svc->addr.ip),
ntohs(svc->port),
- sched->name,
+ sched_name,
(svc->flags & IP_VS_SVC_F_ONEPACKET)?"ops ":"");
} else {
seq_printf(seq, "FWM %08X %s %s",
- svc->fwmark, sched->name,
+ svc->fwmark, sched_name,
(svc->flags & IP_VS_SVC_F_ONEPACKET)?"ops ":"");
}
{
struct ip_vs_scheduler *sched;
struct ip_vs_kstats kstats;
+ char *sched_name;
sched = rcu_dereference_protected(src->scheduler, 1);
+ sched_name = sched ? sched->name : "none";
dst->protocol = src->protocol;
dst->addr = src->addr.ip;
dst->port = src->port;
dst->fwmark = src->fwmark;
- strlcpy(dst->sched_name, sched->name, sizeof(dst->sched_name));
+ strlcpy(dst->sched_name, sched_name, sizeof(dst->sched_name));
dst->flags = src->flags;
dst->timeout = src->timeout / HZ;
dst->netmask = src->netmask;
struct ip_vs_flags flags = { .flags = svc->flags,
.mask = ~0 };
struct ip_vs_kstats kstats;
+ char *sched_name;
nl_service = nla_nest_start(skb, IPVS_CMD_ATTR_SERVICE);
if (!nl_service)
}
sched = rcu_dereference_protected(svc->scheduler, 1);
+ sched_name = sched ? sched->name : "none";
pe = rcu_dereference_protected(svc->pe, 1);
- if (nla_put_string(skb, IPVS_SVC_ATTR_SCHED_NAME, sched->name) ||
+ if (nla_put_string(skb, IPVS_SVC_ATTR_SCHED_NAME, sched_name) ||
(pe && nla_put_string(skb, IPVS_SVC_ATTR_PE_NAME, pe->name)) ||
nla_put(skb, IPVS_SVC_ATTR_FLAGS, sizeof(flags), &flags) ||
nla_put_u32(skb, IPVS_SVC_ATTR_TIMEOUT, svc->timeout / HZ) ||
if (sched->done_service)
sched->done_service(svc);
- /* svc->scheduler can not be set to NULL */
+ /* svc->scheduler can be set to NULL only by caller */
}
void ip_vs_scheduler_err(struct ip_vs_service *svc, const char *msg)
{
- struct ip_vs_scheduler *sched;
+ struct ip_vs_scheduler *sched = rcu_dereference(svc->scheduler);
+ char *sched_name = sched ? sched->name : "none";
- sched = rcu_dereference(svc->scheduler);
if (svc->fwmark) {
IP_VS_ERR_RL("%s: FWM %u 0x%08X - %s\n",
- sched->name, svc->fwmark, svc->fwmark, msg);
+ sched_name, svc->fwmark, svc->fwmark, msg);
#ifdef CONFIG_IP_VS_IPV6
} else if (svc->af == AF_INET6) {
IP_VS_ERR_RL("%s: %s [%pI6c]:%d - %s\n",
- sched->name, ip_vs_proto_name(svc->protocol),
+ sched_name, ip_vs_proto_name(svc->protocol),
&svc->addr.in6, ntohs(svc->port), msg);
#endif
} else {
IP_VS_ERR_RL("%s: %s %pI4:%d - %s\n",
- sched->name, ip_vs_proto_name(svc->protocol),
+ sched_name, ip_vs_proto_name(svc->protocol),
&svc->addr.ip, ntohs(svc->port), msg);
}
}
pkts = atomic_add_return(1, &cp->in_pkts);
else
pkts = sysctl_sync_threshold(ipvs);
- ip_vs_sync_conn(net, cp->control, pkts);
+ ip_vs_sync_conn(net, cp, pkts);
}
}
memset(&fl4, 0, sizeof(fl4));
fl4.daddr = daddr;
- fl4.saddr = (rt_mode & IP_VS_RT_MODE_CONNECT) ? *saddr : 0;
fl4.flowi4_flags = (rt_mode & IP_VS_RT_MODE_KNOWN_NH) ?
FLOWI_FLAG_KNOWN_NH : 0;
return -1;
err_unreach:
+ /* The ip6_link_failure function requires the dev field to be set
+ * in order to get the net (further for the sake of fwmark
+ * reflection).
+ */
+ if (!skb->dev)
+ skb->dev = skb_dst(skb)->dev;
+
dst_link_failure(skb);
return -1;
}
if (ret == NF_ACCEPT) {
nf_reset(skb);
skb_forward_csum(skb);
+ if (!skb->sk)
+ skb_sender_cpu_clear(skb);
}
return ret;
}
+/* In the event of a remote destination, it's possible that we would have
+ * matches against an old socket (particularly a TIME-WAIT socket). This
+ * causes havoc down the line (ip_local_out et. al. expect regular sockets
+ * and invalid memory accesses will happen) so simply drop the association
+ * in this case.
+*/
+static inline void ip_vs_drop_early_demux_sk(struct sk_buff *skb)
+{
+ /* If dev is set, the packet came from the LOCAL_IN callback and
+ * not from a local TCP socket.
+ */
+ if (skb->dev)
+ skb_orphan(skb);
+}
+
/* return NF_STOLEN (sent) or NF_ACCEPT if local=1 (not sent) */
static inline int ip_vs_nat_send_or_cont(int pf, struct sk_buff *skb,
struct ip_vs_conn *cp, int local)
ip_vs_notrack(skb);
else
ip_vs_update_conntrack(skb, cp, 1);
+
+ /* Remove the early_demux association unless it's bound for the
+ * exact same port and address on this host after translation.
+ */
+ if (!local || cp->vport != cp->dport ||
+ !ip_vs_addr_equal(cp->af, &cp->vaddr, &cp->daddr))
+ ip_vs_drop_early_demux_sk(skb);
+
if (!local) {
skb_forward_csum(skb);
+ if (!skb->sk)
+ skb_sender_cpu_clear(skb);
NF_HOOK(pf, NF_INET_LOCAL_OUT, NULL, skb,
NULL, skb_dst(skb)->dev, dst_output_sk);
} else
ret = NF_ACCEPT;
+
return ret;
}
if (likely(!(cp->flags & IP_VS_CONN_F_NFCT)))
ip_vs_notrack(skb);
if (!local) {
+ ip_vs_drop_early_demux_sk(skb);
skb_forward_csum(skb);
+ if (!skb->sk)
+ skb_sender_cpu_clear(skb);
NF_HOOK(pf, NF_INET_LOCAL_OUT, NULL, skb,
NULL, skb_dst(skb)->dev, dst_output_sk);
} else
struct ipv6hdr *old_ipv6h = NULL;
#endif
+ ip_vs_drop_early_demux_sk(skb);
+
if (skb_headroom(skb) < max_headroom || skb_cloned(skb)) {
new_skb = skb_realloc_headroom(skb, max_headroom);
if (!new_skb)
spin_unlock(&pcpu->lock);
}
+/* Released via destroy_conntrack() */
+struct nf_conn *nf_ct_tmpl_alloc(struct net *net, u16 zone, gfp_t flags)
+{
+ struct nf_conn *tmpl;
+
+ tmpl = kzalloc(sizeof(struct nf_conn), GFP_KERNEL);
+ if (tmpl == NULL)
+ return NULL;
+
+ tmpl->status = IPS_TEMPLATE;
+ write_pnet(&tmpl->ct_net, net);
+
+#ifdef CONFIG_NF_CONNTRACK_ZONES
+ if (zone) {
+ struct nf_conntrack_zone *nf_ct_zone;
+
+ nf_ct_zone = nf_ct_ext_add(tmpl, NF_CT_EXT_ZONE, GFP_ATOMIC);
+ if (!nf_ct_zone)
+ goto out_free;
+ nf_ct_zone->id = zone;
+ }
+#endif
+ atomic_set(&tmpl->ct_general.use, 0);
+
+ return tmpl;
+#ifdef CONFIG_NF_CONNTRACK_ZONES
+out_free:
+ kfree(tmpl);
+ return NULL;
+#endif
+}
+EXPORT_SYMBOL_GPL(nf_ct_tmpl_alloc);
+
+static void nf_ct_tmpl_free(struct nf_conn *tmpl)
+{
+ nf_ct_ext_destroy(tmpl);
+ nf_ct_ext_free(tmpl);
+ kfree(tmpl);
+}
+
static void
destroy_conntrack(struct nf_conntrack *nfct)
{
NF_CT_ASSERT(atomic_read(&nfct->use) == 0);
NF_CT_ASSERT(!timer_pending(&ct->timeout));
+ if (unlikely(nf_ct_is_template(ct))) {
+ nf_ct_tmpl_free(ct);
+ return;
+ }
rcu_read_lock();
l4proto = __nf_ct_l4proto_find(nf_ct_l3num(ct), nf_ct_protonum(ct));
if (l4proto && l4proto->destroy)
}
EXPORT_SYMBOL_GPL(nf_conntrack_hash_check_insert);
-/* deletion from this larval template list happens via nf_ct_put() */
-void nf_conntrack_tmpl_insert(struct net *net, struct nf_conn *tmpl)
-{
- struct ct_pcpu *pcpu;
-
- __set_bit(IPS_TEMPLATE_BIT, &tmpl->status);
- __set_bit(IPS_CONFIRMED_BIT, &tmpl->status);
- nf_conntrack_get(&tmpl->ct_general);
-
- /* add this conntrack to the (per cpu) tmpl list */
- local_bh_disable();
- tmpl->cpu = smp_processor_id();
- pcpu = per_cpu_ptr(nf_ct_net(tmpl)->ct.pcpu_lists, tmpl->cpu);
-
- spin_lock(&pcpu->lock);
- /* Overload tuple linked list to put us in template list. */
- hlist_nulls_add_head_rcu(&tmpl->tuplehash[IP_CT_DIR_ORIGINAL].hnnode,
- &pcpu->tmpl);
- spin_unlock_bh(&pcpu->lock);
-}
-EXPORT_SYMBOL_GPL(nf_conntrack_tmpl_insert);
-
/* Confirm a connection given skb; places it in hash table */
int
__nf_conntrack_confirm(struct sk_buff *skb)
spin_lock_init(&pcpu->lock);
INIT_HLIST_NULLS_HEAD(&pcpu->unconfirmed, UNCONFIRMED_NULLS_VAL);
INIT_HLIST_NULLS_HEAD(&pcpu->dying, DYING_NULLS_VAL);
- INIT_HLIST_NULLS_HEAD(&pcpu->tmpl, TEMPLATE_NULLS_VAL);
}
net->ct.stat = alloc_percpu(struct ip_conntrack_stat);
a->mask.src.u3.all[count] & b->mask.src.u3.all[count];
}
- return nf_ct_tuple_mask_cmp(&a->tuple, &b->tuple, &intersect_mask);
+ return nf_ct_tuple_mask_cmp(&a->tuple, &b->tuple, &intersect_mask) &&
+ nf_ct_zone(a->master) == nf_ct_zone(b->master);
}
static inline int expect_matches(const struct nf_conntrack_expect *a,
}
err = nf_ct_expect_related_report(exp, portid, report);
- if (err < 0)
- goto err_exp;
-
- return 0;
-err_exp:
nf_ct_expect_put(exp);
err_ct:
nf_ct_put(ct);
static int __net_init synproxy_net_init(struct net *net)
{
struct synproxy_net *snet = synproxy_pernet(net);
- struct nf_conntrack_tuple t;
struct nf_conn *ct;
int err = -ENOMEM;
- memset(&t, 0, sizeof(t));
- ct = nf_conntrack_alloc(net, 0, &t, &t, GFP_KERNEL);
+ ct = nf_ct_tmpl_alloc(net, 0, GFP_KERNEL);
if (IS_ERR(ct)) {
err = PTR_ERR(ct);
goto err1;
if (!nfct_synproxy_ext_add(ct))
goto err2;
- nf_conntrack_tmpl_insert(net, ct);
+ __set_bit(IPS_CONFIRMED_BIT, &ct->status);
+ nf_conntrack_get(&ct->ct_general);
snet->tmpl = ct;
snet->stats = alloc_percpu(struct synproxy_stats);
static int xt_ct_tg_check(const struct xt_tgchk_param *par,
struct xt_ct_target_info_v1 *info)
{
- struct nf_conntrack_tuple t;
struct nf_conn *ct;
int ret = -EOPNOTSUPP;
if (ret < 0)
goto err1;
- memset(&t, 0, sizeof(t));
- ct = nf_conntrack_alloc(par->net, info->zone, &t, &t, GFP_KERNEL);
+ ct = nf_ct_tmpl_alloc(par->net, info->zone, GFP_KERNEL);
ret = PTR_ERR(ct);
if (IS_ERR(ct))
goto err2;
if (ret < 0)
goto err3;
}
-
- nf_conntrack_tmpl_insert(par->net, ct);
+ __set_bit(IPS_CONFIRMED_BIT, &ct->status);
+ nf_conntrack_get(&ct->ct_general);
out:
info->ct = ct;
return 0;
goto out;
}
+ sysfs_attr_init(&info->timer->attr.attr);
info->timer->attr.attr.name = kstrdup(info->label, GFP_KERNEL);
if (!info->timer->attr.attr.name) {
ret = -ENOMEM;