aboutsummaryrefslogtreecommitdiff
path: root/net/netfilter
diff options
context:
space:
mode:
Diffstat (limited to 'net/netfilter')
-rw-r--r--net/netfilter/core.c1
-rw-r--r--net/netfilter/ipvs/ip_vs_core.c16
-rw-r--r--net/netfilter/ipvs/ip_vs_ctl.c78
-rw-r--r--net/netfilter/ipvs/ip_vs_pe_sip.c2
-rw-r--r--net/netfilter/ipvs/ip_vs_sched.c12
-rw-r--r--net/netfilter/ipvs/ip_vs_sync.c2
-rw-r--r--net/netfilter/ipvs/ip_vs_xmit.c28
-rw-r--r--net/netfilter/nf_conntrack_core.c4
-rw-r--r--net/netfilter/nf_conntrack_expect.c3
-rw-r--r--net/netfilter/nf_conntrack_netlink.c5
-rw-r--r--net/netfilter/nf_internals.h1
-rw-r--r--net/netfilter/nf_log.c30
-rw-r--r--net/netfilter/nf_queue.c17
-rw-r--r--net/netfilter/nf_tables_api.c5
-rw-r--r--net/netfilter/nfnetlink.c8
-rw-r--r--net/netfilter/nfnetlink_cthelper.c7
-rw-r--r--net/netfilter/nfnetlink_queue_core.c24
-rw-r--r--net/netfilter/nft_compat.c38
-rw-r--r--net/netfilter/x_tables.c295
-rw-r--r--net/netfilter/xt_cgroup.c2
20 files changed, 502 insertions, 76 deletions
diff --git a/net/netfilter/core.c b/net/netfilter/core.c
index 656b5ebb0eff..942479a61b61 100644
--- a/net/netfilter/core.c
+++ b/net/netfilter/core.c
@@ -94,6 +94,7 @@ void nf_unregister_hook(struct nf_hook_ops *reg)
static_key_slow_dec(&nf_hooks_needed[reg->pf][reg->hooknum]);
#endif
synchronize_net();
+ nf_queue_nf_hook_drop(reg);
}
EXPORT_SYMBOL(nf_unregister_hook);
diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
index 990decba1fe4..3a2fa9c044f8 100644
--- a/net/netfilter/ipvs/ip_vs_core.c
+++ b/net/netfilter/ipvs/ip_vs_core.c
@@ -313,7 +313,13 @@ ip_vs_sched_persist(struct ip_vs_service *svc,
* 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);
@@ -461,7 +467,13 @@ ip_vs_schedule(struct ip_vs_service *svc, struct sk_buff *skb,
}
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;
diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index ac7ba689efe7..9b1452e8e868 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -828,15 +828,16 @@ __ip_vs_update_dest(struct ip_vs_service *svc, struct ip_vs_dest *dest,
__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);
}
}
@@ -1070,7 +1071,7 @@ static void __ip_vs_unlink_dest(struct ip_vs_service *svc,
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);
}
}
@@ -1161,11 +1162,14 @@ ip_vs_add_service(struct net *net, struct ip_vs_service_user_kern *u,
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) {
@@ -1226,10 +1230,12 @@ ip_vs_add_service(struct net *net, struct ip_vs_service_user_kern *u,
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);
@@ -1277,17 +1283,20 @@ ip_vs_add_service(struct net *net, struct ip_vs_service_user_kern *u,
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;
@@ -1315,14 +1324,20 @@ ip_vs_edit_service(struct ip_vs_service *svc, struct ip_vs_service_user_kern *u)
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);
}
/*
@@ -1962,6 +1977,7 @@ static int ip_vs_info_seq_show(struct seq_file *seq, void *v)
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
@@ -1970,18 +1986,18 @@ static int ip_vs_info_seq_show(struct seq_file *seq, void *v)
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 ":"");
}
@@ -2401,13 +2417,15 @@ static void
ip_vs_copy_service(struct ip_vs_service_entry *dst, struct ip_vs_service *src)
{
struct ip_vs_scheduler *sched;
+ 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;
@@ -2836,6 +2854,7 @@ static int ip_vs_genl_fill_service(struct sk_buff *skb,
struct nlattr *nl_service;
struct ip_vs_flags flags = { .flags = svc->flags,
.mask = ~0 };
+ char *sched_name;
nl_service = nla_nest_start(skb, IPVS_CMD_ATTR_SERVICE);
if (!nl_service)
@@ -2854,8 +2873,9 @@ static int ip_vs_genl_fill_service(struct sk_buff *skb,
}
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) ||
diff --git a/net/netfilter/ipvs/ip_vs_pe_sip.c b/net/netfilter/ipvs/ip_vs_pe_sip.c
index bed5f7042529..bb318e4623a3 100644
--- a/net/netfilter/ipvs/ip_vs_pe_sip.c
+++ b/net/netfilter/ipvs/ip_vs_pe_sip.c
@@ -88,7 +88,7 @@ ip_vs_sip_fill_param(struct ip_vs_conn_param *p, struct sk_buff *skb)
dptr = skb->data + dataoff;
datalen = skb->len - dataoff;
- if (get_callid(dptr, dataoff, datalen, &matchoff, &matchlen))
+ if (get_callid(dptr, 0, datalen, &matchoff, &matchlen))
return -EINVAL;
/* N.B: pe_data is only set on success,
diff --git a/net/netfilter/ipvs/ip_vs_sched.c b/net/netfilter/ipvs/ip_vs_sched.c
index 4dbcda6258bc..21b6b515a09c 100644
--- a/net/netfilter/ipvs/ip_vs_sched.c
+++ b/net/netfilter/ipvs/ip_vs_sched.c
@@ -74,7 +74,7 @@ void ip_vs_unbind_scheduler(struct ip_vs_service *svc,
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 */
}
@@ -148,21 +148,21 @@ void ip_vs_scheduler_put(struct ip_vs_scheduler *scheduler)
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);
}
}
diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c
index 7162c86fd50d..72fac696c85e 100644
--- a/net/netfilter/ipvs/ip_vs_sync.c
+++ b/net/netfilter/ipvs/ip_vs_sync.c
@@ -612,7 +612,7 @@ 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->control, pkts);
+ ip_vs_sync_conn(net, cp, pkts);
}
}
diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c
index bd90bf8107da..72f030878e7a 100644
--- a/net/netfilter/ipvs/ip_vs_xmit.c
+++ b/net/netfilter/ipvs/ip_vs_xmit.c
@@ -130,7 +130,6 @@ static struct rtable *do_output_route4(struct net *net, __be32 daddr,
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;
@@ -524,6 +523,21 @@ static inline int ip_vs_tunnel_xmit_prepare(struct sk_buff *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)
@@ -535,12 +549,21 @@ static inline int ip_vs_nat_send_or_cont(int pf, struct sk_buff *skb,
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);
NF_HOOK(pf, NF_INET_LOCAL_OUT, skb, NULL, skb_dst(skb)->dev,
dst_output);
} else
ret = NF_ACCEPT;
+
return ret;
}
@@ -554,6 +577,7 @@ static inline int ip_vs_send_or_cont(int pf, struct sk_buff *skb,
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);
NF_HOOK(pf, NF_INET_LOCAL_OUT, skb, NULL, skb_dst(skb)->dev,
dst_output);
@@ -842,6 +866,8 @@ ip_vs_prepare_tunneled_skb(struct sk_buff *skb, int skb_af,
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)
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index c5880124ec0d..98cd0e78c94c 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -1739,6 +1739,7 @@ void nf_conntrack_init_end(void)
int nf_conntrack_init_net(struct net *net)
{
+ static atomic64_t unique_id;
int ret = -ENOMEM;
int cpu;
@@ -1762,7 +1763,8 @@ int nf_conntrack_init_net(struct net *net)
if (!net->ct.stat)
goto err_pcpu_lists;
- net->ct.slabname = kasprintf(GFP_KERNEL, "nf_conntrack_%p", net);
+ net->ct.slabname = kasprintf(GFP_KERNEL, "nf_conntrack_%llu",
+ (u64)atomic64_inc_return(&unique_id));
if (!net->ct.slabname)
goto err_slabname;
diff --git a/net/netfilter/nf_conntrack_expect.c b/net/netfilter/nf_conntrack_expect.c
index 91a1837acd0e..26af45193ab7 100644
--- a/net/netfilter/nf_conntrack_expect.c
+++ b/net/netfilter/nf_conntrack_expect.c
@@ -219,7 +219,8 @@ static inline int expect_clash(const struct nf_conntrack_expect *a,
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,
diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c
index 1bd9ed9e62f6..d3ea2999d0dc 100644
--- a/net/netfilter/nf_conntrack_netlink.c
+++ b/net/netfilter/nf_conntrack_netlink.c
@@ -2956,11 +2956,6 @@ ctnetlink_create_expect(struct net *net, u16 zone,
}
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);
diff --git a/net/netfilter/nf_internals.h b/net/netfilter/nf_internals.h
index 61a3c927e63c..aba1d7dac17c 100644
--- a/net/netfilter/nf_internals.h
+++ b/net/netfilter/nf_internals.h
@@ -24,6 +24,7 @@ int nf_queue(struct sk_buff *skb, struct nf_hook_ops *elem, u_int8_t pf,
unsigned int hook, struct net_device *indev,
struct net_device *outdev, int (*okfn)(struct sk_buff *),
unsigned int queuenum);
+void nf_queue_nf_hook_drop(struct nf_hook_ops *ops);
int __init netfilter_queue_init(void);
/* nf_log.c */
diff --git a/net/netfilter/nf_log.c b/net/netfilter/nf_log.c
index d7197649dba6..cfe93c2227c5 100644
--- a/net/netfilter/nf_log.c
+++ b/net/netfilter/nf_log.c
@@ -19,6 +19,9 @@
static struct nf_logger __rcu *loggers[NFPROTO_NUMPROTO][NF_LOG_TYPE_MAX] __read_mostly;
static DEFINE_MUTEX(nf_log_mutex);
+#define nft_log_dereference(logger) \
+ rcu_dereference_protected(logger, lockdep_is_held(&nf_log_mutex))
+
static struct nf_logger *__find_logger(int pf, const char *str_logger)
{
struct nf_logger *log;
@@ -28,8 +31,7 @@ static struct nf_logger *__find_logger(int pf, const char *str_logger)
if (loggers[pf][i] == NULL)
continue;
- log = rcu_dereference_protected(loggers[pf][i],
- lockdep_is_held(&nf_log_mutex));
+ log = nft_log_dereference(loggers[pf][i]);
if (!strncasecmp(str_logger, log->name, strlen(log->name)))
return log;
}
@@ -45,8 +47,7 @@ void nf_log_set(struct net *net, u_int8_t pf, const struct nf_logger *logger)
return;
mutex_lock(&nf_log_mutex);
- log = rcu_dereference_protected(net->nf.nf_loggers[pf],
- lockdep_is_held(&nf_log_mutex));
+ log = nft_log_dereference(net->nf.nf_loggers[pf]);
if (log == NULL)
rcu_assign_pointer(net->nf.nf_loggers[pf], logger);
@@ -61,8 +62,7 @@ void nf_log_unset(struct net *net, const struct nf_logger *logger)
mutex_lock(&nf_log_mutex);
for (i = 0; i < NFPROTO_NUMPROTO; i++) {
- log = rcu_dereference_protected(net->nf.nf_loggers[i],
- lockdep_is_held(&nf_log_mutex));
+ log = nft_log_dereference(net->nf.nf_loggers[i]);
if (log == logger)
RCU_INIT_POINTER(net->nf.nf_loggers[i], NULL);
}
@@ -97,12 +97,17 @@ EXPORT_SYMBOL(nf_log_register);
void nf_log_unregister(struct nf_logger *logger)
{
+ const struct nf_logger *log;
int i;
mutex_lock(&nf_log_mutex);
- for (i = 0; i < NFPROTO_NUMPROTO; i++)
- RCU_INIT_POINTER(loggers[i][logger->type], NULL);
+ for (i = 0; i < NFPROTO_NUMPROTO; i++) {
+ log = nft_log_dereference(loggers[i][logger->type]);
+ if (log == logger)
+ RCU_INIT_POINTER(loggers[i][logger->type], NULL);
+ }
mutex_unlock(&nf_log_mutex);
+ synchronize_rcu();
}
EXPORT_SYMBOL(nf_log_unregister);
@@ -297,8 +302,7 @@ static int seq_show(struct seq_file *s, void *v)
int i, ret;
struct net *net = seq_file_net(s);
- logger = rcu_dereference_protected(net->nf.nf_loggers[*pos],
- lockdep_is_held(&nf_log_mutex));
+ logger = nft_log_dereference(net->nf.nf_loggers[*pos]);
if (!logger)
ret = seq_printf(s, "%2lld NONE (", *pos);
@@ -312,8 +316,7 @@ static int seq_show(struct seq_file *s, void *v)
if (loggers[*pos][i] == NULL)
continue;
- logger = rcu_dereference_protected(loggers[*pos][i],
- lockdep_is_held(&nf_log_mutex));
+ logger = nft_log_dereference(loggers[*pos][i]);
ret = seq_printf(s, "%s", logger->name);
if (ret < 0)
return ret;
@@ -385,8 +388,7 @@ static int nf_log_proc_dostring(struct ctl_table *table, int write,
mutex_unlock(&nf_log_mutex);
} else {
mutex_lock(&nf_log_mutex);
- logger = rcu_dereference_protected(net->nf.nf_loggers[tindex],
- lockdep_is_held(&nf_log_mutex));
+ logger = nft_log_dereference(net->nf.nf_loggers[tindex]);
if (!logger)
table->data = "NONE";
else
diff --git a/net/netfilter/nf_queue.c b/net/netfilter/nf_queue.c
index 4c8b68e5fa16..77ee2d4d5046 100644
--- a/net/netfilter/nf_queue.c
+++ b/net/netfilter/nf_queue.c
@@ -95,6 +95,23 @@ bool nf_queue_entry_get_refs(struct nf_queue_entry *entry)
}
EXPORT_SYMBOL_GPL(nf_queue_entry_get_refs);
+void nf_queue_nf_hook_drop(struct nf_hook_ops *ops)
+{
+ const struct nf_queue_handler *qh;
+ struct net *net;
+
+ rtnl_lock();
+ rcu_read_lock();
+ qh = rcu_dereference(queue_handler);
+ if (qh) {
+ for_each_net(net) {
+ qh->nf_hook_drop(net, ops);
+ }
+ }
+ rcu_read_unlock();
+ rtnl_unlock();
+}
+
/*
* Any packet that leaves via this function must come back
* through nf_reinject().
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 71b574c7bde9..9fe2baa01fbe 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -1221,7 +1221,10 @@ static int nf_tables_newchain(struct sock *nlsk, struct sk_buff *skb,
if (nla[NFTA_CHAIN_POLICY]) {
if ((chain != NULL &&
- !(chain->flags & NFT_BASE_CHAIN)) ||
+ !(chain->flags & NFT_BASE_CHAIN)))
+ return -EOPNOTSUPP;
+
+ if (chain == NULL &&
nla[NFTA_CHAIN_HOOK] == NULL)
return -EOPNOTSUPP;
diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c
index 1aa7049c93f5..e41bab38a3ca 100644
--- a/net/netfilter/nfnetlink.c
+++ b/net/netfilter/nfnetlink.c
@@ -433,6 +433,7 @@ done:
static void nfnetlink_rcv(struct sk_buff *skb)
{
struct nlmsghdr *nlh = nlmsg_hdr(skb);
+ u_int16_t res_id;
int msglen;
if (nlh->nlmsg_len < NLMSG_HDRLEN ||
@@ -457,7 +458,12 @@ static void nfnetlink_rcv(struct sk_buff *skb)
nfgenmsg = nlmsg_data(nlh);
skb_pull(skb, msglen);
- nfnetlink_rcv_batch(skb, nlh, nfgenmsg->res_id);
+ /* Work around old nft using host byte order */
+ if (nfgenmsg->res_id == NFNL_SUBSYS_NFTABLES)
+ res_id = NFNL_SUBSYS_NFTABLES;
+ else
+ res_id = ntohs(nfgenmsg->res_id);
+ nfnetlink_rcv_batch(skb, nlh, res_id);
} else {
netlink_rcv_skb(skb, &nfnetlink_rcv_msg);
}
diff --git a/net/netfilter/nfnetlink_cthelper.c b/net/netfilter/nfnetlink_cthelper.c
index 9e287cb56a04..54330fb5efaf 100644
--- a/net/netfilter/nfnetlink_cthelper.c
+++ b/net/netfilter/nfnetlink_cthelper.c
@@ -77,6 +77,9 @@ nfnl_cthelper_parse_tuple(struct nf_conntrack_tuple *tuple,
if (!tb[NFCTH_TUPLE_L3PROTONUM] || !tb[NFCTH_TUPLE_L4PROTONUM])
return -EINVAL;
+ /* Not all fields are initialized so first zero the tuple */
+ memset(tuple, 0, sizeof(struct nf_conntrack_tuple));
+
tuple->src.l3num = ntohs(nla_get_be16(tb[NFCTH_TUPLE_L3PROTONUM]));
tuple->dst.protonum = nla_get_u8(tb[NFCTH_TUPLE_L4PROTONUM]);
@@ -86,7 +89,7 @@ nfnl_cthelper_parse_tuple(struct nf_conntrack_tuple *tuple,
static int
nfnl_cthelper_from_nlattr(struct nlattr *attr, struct nf_conn *ct)
{
- const struct nf_conn_help *help = nfct_help(ct);
+ struct nf_conn_help *help = nfct_help(ct);
if (attr == NULL)
return -EINVAL;
@@ -94,7 +97,7 @@ nfnl_cthelper_from_nlattr(struct nlattr *attr, struct nf_conn *ct)
if (help->helper->data_len == 0)
return -EINVAL;
- memcpy(&help->data, nla_data(attr), help->helper->data_len);
+ memcpy(help->data, nla_data(attr), help->helper->data_len);
return 0;
}
diff --git a/net/netfilter/nfnetlink_queue_core.c b/net/netfilter/nfnetlink_queue_core.c
index 7c60ccd61a3e..8add272654f6 100644
--- a/net/netfilter/nfnetlink_queue_core.c
+++ b/net/netfilter/nfnetlink_queue_core.c
@@ -815,6 +815,27 @@ static struct notifier_block nfqnl_dev_notifier = {
.notifier_call = nfqnl_rcv_dev_event,
};
+static int nf_hook_cmp(struct nf_queue_entry *entry, unsigned long ops_ptr)
+{
+ return entry->elem == (struct nf_hook_ops *)ops_ptr;
+}
+
+static void nfqnl_nf_hook_drop(struct net *net, struct nf_hook_ops *hook)
+{
+ struct nfnl_queue_net *q = nfnl_queue_pernet(net);
+ int i;
+
+ rcu_read_lock();
+ for (i = 0; i < INSTANCE_BUCKETS; i++) {
+ struct nfqnl_instance *inst;
+ struct hlist_head *head = &q->instance_table[i];
+
+ hlist_for_each_entry_rcu(inst, head, hlist)
+ nfqnl_flush(inst, nf_hook_cmp, (unsigned long)hook);
+ }
+ rcu_read_unlock();
+}
+
static int
nfqnl_rcv_nl_event(struct notifier_block *this,
unsigned long event, void *ptr)
@@ -1022,7 +1043,8 @@ static const struct nla_policy nfqa_cfg_policy[NFQA_CFG_MAX+1] = {
};
static const struct nf_queue_handler nfqh = {
- .outfn = &nfqnl_enqueue_packet,
+ .outfn = &nfqnl_enqueue_packet,
+ .nf_hook_drop = &nfqnl_nf_hook_drop,
};
static int
diff --git a/net/netfilter/nft_compat.c b/net/netfilter/nft_compat.c
index 265e190f2218..ff6f35971ea2 100644
--- a/net/netfilter/nft_compat.c
+++ b/net/netfilter/nft_compat.c
@@ -97,6 +97,9 @@ nft_target_set_tgchk_param(struct xt_tgchk_param *par,
entry->e4.ip.invflags = inv ? IPT_INV_PROTO : 0;
break;
case AF_INET6:
+ if (proto)
+ entry->e6.ipv6.flags |= IP6T_F_PROTO;
+
entry->e6.ipv6.proto = proto;
entry->e6.ipv6.invflags = inv ? IP6T_INV_PROTO : 0;
break;
@@ -304,6 +307,9 @@ nft_match_set_mtchk_param(struct xt_mtchk_param *par, const struct nft_ctx *ctx,
entry->e4.ip.invflags = inv ? IPT_INV_PROTO : 0;
break;
case AF_INET6:
+ if (proto)
+ entry->e6.ipv6.flags |= IP6T_F_PROTO;
+
entry->e6.ipv6.proto = proto;
entry->e6.ipv6.invflags = inv ? IP6T_INV_PROTO : 0;
break;
@@ -555,6 +561,13 @@ struct nft_xt {
static struct nft_expr_type nft_match_type;
+static bool nft_match_cmp(const struct xt_match *match,
+ const char *name, u32 rev, u32 family)
+{
+ return strcmp(match->name, name) == 0 && match->revision == rev &&
+ (match->family == NFPROTO_UNSPEC || match->family == family);
+}
+
static const struct nft_expr_ops *
nft_match_select_ops(const struct nft_ctx *ctx,
const struct nlattr * const tb[])
@@ -562,7 +575,7 @@ nft_match_select_ops(const struct nft_ctx *ctx,
struct nft_xt *nft_match;
struct xt_match *match;
char *mt_name;
- __u32 rev, family;
+ u32 rev, family;
if (tb[NFTA_MATCH_NAME] == NULL ||
tb[NFTA_MATCH_REV] == NULL ||
@@ -577,9 +590,12 @@ nft_match_select_ops(const struct nft_ctx *ctx,
list_for_each_entry(nft_match, &nft_match_list, head) {
struct xt_match *match = nft_match->ops.data;
- if (strcmp(match->name, mt_name) == 0 &&
- match->revision == rev && match->family == family)
+ if (nft_match_cmp(match, mt_name, rev, family)) {
+ if (!try_module_get(match->me))
+ return ERR_PTR(-ENOENT);
+
return &nft_match->ops;
+ }
}
match = xt_request_find_match(family, mt_name, rev);
@@ -625,6 +641,13 @@ static LIST_HEAD(nft_target_list);
static struct nft_expr_type nft_target_type;
+static bool nft_target_cmp(const struct xt_target *tg,
+ const char *name, u32 rev, u32 family)
+{
+ return strcmp(tg->name, name) == 0 && tg->revision == rev &&
+ (tg->family == NFPROTO_UNSPEC || tg->family == family);
+}
+
static const struct nft_expr_ops *
nft_target_select_ops(const struct nft_ctx *ctx,
const struct nlattr * const tb[])
@@ -632,7 +655,7 @@ nft_target_select_ops(const struct nft_ctx *ctx,
struct nft_xt *nft_target;
struct xt_target *target;
char *tg_name;
- __u32 rev, family;
+ u32 rev, family;
if (tb[NFTA_TARGET_NAME] == NULL ||
tb[NFTA_TARGET_REV] == NULL ||
@@ -647,9 +670,12 @@ nft_target_select_ops(const struct nft_ctx *ctx,
list_for_each_entry(nft_target, &nft_target_list, head) {
struct xt_target *target = nft_target->ops.data;
- if (strcmp(target->name, tg_name) == 0 &&
- target->revision == rev && target->family == family)
+ if (nft_target_cmp(target, tg_name, rev, family)) {
+ if (!try_module_get(target->me))
+ return ERR_PTR(-ENOENT);
+
return &nft_target->ops;
+ }
}
target = xt_request_find_target(family, tg_name, rev);
diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c
index 133eb4772f12..489899325bf7 100644
--- a/net/netfilter/x_tables.c
+++ b/net/netfilter/x_tables.c
@@ -418,6 +418,47 @@ int xt_check_match(struct xt_mtchk_param *par,
}
EXPORT_SYMBOL_GPL(xt_check_match);
+/** xt_check_entry_match - check that matches end before start of target
+ *
+ * @match: beginning of xt_entry_match
+ * @target: beginning of this rules target (alleged end of matches)
+ * @alignment: alignment requirement of match structures
+ *
+ * Validates that all matches add up to the beginning of the target,
+ * and that each match covers at least the base structure size.
+ *
+ * Return: 0 on success, negative errno on failure.
+ */
+static int xt_check_entry_match(const char *match, const char *target,
+ const size_t alignment)
+{
+ const struct xt_entry_match *pos;
+ int length = target - match;
+
+ if (length == 0) /* no matches */
+ return 0;
+
+ pos = (struct xt_entry_match *)match;
+ do {
+ if ((unsigned long)pos % alignment)
+ return -EINVAL;
+
+ if (length < (int)sizeof(struct xt_entry_match))
+ return -EINVAL;
+
+ if (pos->u.match_size < sizeof(struct xt_entry_match))
+ return -EINVAL;
+
+ if (pos->u.match_size > length)
+ return -EINVAL;
+
+ length -= pos->u.match_size;
+ pos = ((void *)((char *)(pos) + (pos)->u.match_size));
+ } while (length > 0);
+
+ return 0;
+}
+
#ifdef CONFIG_COMPAT
int xt_compat_add_offset(u_int8_t af, unsigned int offset, int delta)
{
@@ -487,13 +528,14 @@ int xt_compat_match_offset(const struct xt_match *match)
}
EXPORT_SYMBOL_GPL(xt_compat_match_offset);
-int xt_compat_match_from_user(struct xt_entry_match *m, void **dstptr,
- unsigned int *size)
+void xt_compat_match_from_user(struct xt_entry_match *m, void **dstptr,
+ unsigned int *size)
{
const struct xt_match *match = m->u.kernel.match;
struct compat_xt_entry_match *cm = (struct compat_xt_entry_match *)m;
int pad, off = xt_compat_match_offset(match);
u_int16_t msize = cm->u.user.match_size;
+ char name[sizeof(m->u.user.name)];
m = *dstptr;
memcpy(m, cm, sizeof(*cm));
@@ -507,10 +549,12 @@ int xt_compat_match_from_user(struct xt_entry_match *m, void **dstptr,
msize += off;
m->u.user.match_size = msize;
+ strlcpy(name, match->name, sizeof(name));
+ module_put(match->me);
+ strncpy(m->u.user.name, name, sizeof(m->u.user.name));
*size += off;
*dstptr += msize;
- return 0;
}
EXPORT_SYMBOL_GPL(xt_compat_match_from_user);
@@ -541,8 +585,175 @@ int xt_compat_match_to_user(const struct xt_entry_match *m,
return 0;
}
EXPORT_SYMBOL_GPL(xt_compat_match_to_user);
+
+/* non-compat version may have padding after verdict */
+struct compat_xt_standard_target {
+ struct compat_xt_entry_target t;
+ compat_uint_t verdict;
+};
+
+int xt_compat_check_entry_offsets(const void *base, const char *elems,
+ unsigned int target_offset,
+ unsigned int next_offset)
+{
+ long size_of_base_struct = elems - (const char *)base;
+ const struct compat_xt_entry_target *t;
+ const char *e = base;
+
+ if (target_offset < size_of_base_struct)
+ return -EINVAL;
+
+ if (target_offset + sizeof(*t) > next_offset)
+ return -EINVAL;
+
+ t = (void *)(e + target_offset);
+ if (t->u.target_size < sizeof(*t))
+ return -EINVAL;
+
+ if (target_offset + t->u.target_size > next_offset)
+ return -EINVAL;
+
+ if (strcmp(t->u.user.name, XT_STANDARD_TARGET) == 0 &&
+ COMPAT_XT_ALIGN(target_offset + sizeof(struct compat_xt_standard_target)) != next_offset)
+ return -EINVAL;
+
+ /* compat_xt_entry match has less strict aligment requirements,
+ * otherwise they are identical. In case of padding differences
+ * we need to add compat version of xt_check_entry_match.
+ */
+ BUILD_BUG_ON(sizeof(struct compat_xt_entry_match) != sizeof(struct xt_entry_match));
+
+ return xt_check_entry_match(elems, base + target_offset,
+ __alignof__(struct compat_xt_entry_match));
+}
+EXPORT_SYMBOL(xt_compat_check_entry_offsets);
#endif /* CONFIG_COMPAT */
+/**
+ * xt_check_entry_offsets - validate arp/ip/ip6t_entry
+ *
+ * @base: pointer to arp/ip/ip6t_entry
+ * @elems: pointer to first xt_entry_match, i.e. ip(6)t_entry->elems
+ * @target_offset: the arp/ip/ip6_t->target_offset
+ * @next_offset: the arp/ip/ip6_t->next_offset
+ *
+ * validates that target_offset and next_offset are sane and that all
+ * match sizes (if any) align with the target offset.
+ *
+ * This function does not validate the targets or matches themselves, it
+ * only tests that all the offsets and sizes are correct, that all
+ * match structures are aligned, and that the last structure ends where
+ * the target structure begins.
+ *
+ * Also see xt_compat_check_entry_offsets for CONFIG_COMPAT version.
+ *
+ * The arp/ip/ip6t_entry structure @base must have passed following tests:
+ * - it must point to a valid memory location
+ * - base to base + next_offset must be accessible, i.e. not exceed allocated
+ * length.
+ *
+ * A well-formed entry looks like this:
+ *
+ * ip(6)t_entry match [mtdata] match [mtdata] target [tgdata] ip(6)t_entry
+ * e->elems[]-----' | |
+ * matchsize | |
+ * matchsize | |
+ * | |
+ * target_offset---------------------------------' |
+ * next_offset---------------------------------------------------'
+ *
+ * elems[]: flexible array member at end of ip(6)/arpt_entry struct.
+ * This is where matches (if any) and the target reside.
+ * target_offset: beginning of target.
+ * next_offset: start of the next rule; also: size of this rule.
+ * Since targets have a minimum size, target_offset + minlen <= next_offset.
+ *
+ * Every match stores its size, sum of sizes must not exceed target_offset.
+ *
+ * Return: 0 on success, negative errno on failure.
+ */
+int xt_check_entry_offsets(const void *base,
+ const char *elems,
+ unsigned int target_offset,
+ unsigned int next_offset)
+{
+ long size_of_base_struct = elems - (const char *)base;
+ const struct xt_entry_target *t;
+ const char *e = base;
+
+ /* target start is within the ip/ip6/arpt_entry struct */
+ if (target_offset < size_of_base_struct)
+ return -EINVAL;
+
+ if (target_offset + sizeof(*t) > next_offset)
+ return -EINVAL;
+
+ t = (void *)(e + target_offset);
+ if (t->u.target_size < sizeof(*t))
+ return -EINVAL;
+
+ if (target_offset + t->u.target_size > next_offset)
+ return -EINVAL;
+
+ if (strcmp(t->u.user.name, XT_STANDARD_TARGET) == 0 &&
+ XT_ALIGN(target_offset + sizeof(struct xt_standard_target)) != next_offset)
+ return -EINVAL;
+
+ return xt_check_entry_match(elems, base + target_offset,
+ __alignof__(struct xt_entry_match));
+}
+EXPORT_SYMBOL(xt_check_entry_offsets);
+
+/**
+ * xt_alloc_entry_offsets - allocate array to store rule head offsets
+ *
+ * @size: number of entries
+ *
+ * Return: NULL or kmalloc'd or vmalloc'd array
+ */
+unsigned int *xt_alloc_entry_offsets(unsigned int size)
+{
+ unsigned int *off;
+
+ off = kcalloc(size, sizeof(unsigned int), GFP_KERNEL | __GFP_NOWARN);
+
+ if (off)
+ return off;
+
+ if (size < (SIZE_MAX / sizeof(unsigned int)))
+ off = vmalloc(size * sizeof(unsigned int));
+
+ return off;
+}
+EXPORT_SYMBOL(xt_alloc_entry_offsets);
+
+/**
+ * xt_find_jump_offset - check if target is a valid jump offset
+ *
+ * @offsets: array containing all valid rule start offsets of a rule blob
+ * @target: the jump target to search for
+ * @size: entries in @offset
+ */
+bool xt_find_jump_offset(const unsigned int *offsets,
+ unsigned int target, unsigned int size)
+{
+ int m, low = 0, hi = size;
+
+ while (hi > low) {
+ m = (low + hi) / 2u;
+
+ if (offsets[m] > target)
+ hi = m;
+ else if (offsets[m] < target)
+ low = m + 1;
+ else
+ return true;
+ }
+
+ return false;
+}
+EXPORT_SYMBOL(xt_find_jump_offset);
+
int xt_check_target(struct xt_tgchk_param *par,
unsigned int size, u_int8_t proto, bool inv_proto)
{
@@ -593,6 +804,80 @@ int xt_check_target(struct xt_tgchk_param *par,
}
EXPORT_SYMBOL_GPL(xt_check_target);
+/**
+ * xt_copy_counters_from_user - copy counters and metadata from userspace
+ *
+ * @user: src pointer to userspace memory
+ * @len: alleged size of userspace memory
+ * @info: where to store the xt_counters_info metadata
+ * @compat: true if we setsockopt call is done by 32bit task on 64bit kernel
+ *
+ * Copies counter meta data from @user and stores it in @info.
+ *
+ * vmallocs memory to hold the counters, then copies the counter data
+ * from @user to the new memory and returns a pointer to it.
+ *
+ * If @compat is true, @info gets converted automatically to the 64bit
+ * representation.
+ *
+ * The metadata associated with the counters is stored in @info.
+ *
+ * Return: returns pointer that caller has to test via IS_ERR().
+ * If IS_ERR is false, caller has to vfree the pointer.
+ */
+void *xt_copy_counters_from_user(const void __user *user, unsigned int len,
+ struct xt_counters_info *info, bool compat)
+{
+ void *mem;
+ u64 size;
+
+#ifdef CONFIG_COMPAT
+ if (compat) {
+ /* structures only differ in size due to alignment */
+ struct compat_xt_counters_info compat_tmp;
+
+ if (len <= sizeof(compat_tmp))
+ return ERR_PTR(-EINVAL);
+
+ len -= sizeof(compat_tmp);
+ if (copy_from_user(&compat_tmp, user, sizeof(compat_tmp)) != 0)
+ return ERR_PTR(-EFAULT);
+
+ strlcpy(info->name, compat_tmp.name, sizeof(info->name));
+ info->num_counters = compat_tmp.num_counters;
+ user += sizeof(compat_tmp);
+ } else
+#endif
+ {
+ if (len <= sizeof(*info))
+ return ERR_PTR(-EINVAL);
+
+ len -= sizeof(*info);
+ if (copy_from_user(info, user, sizeof(*info)) != 0)
+ return ERR_PTR(-EFAULT);
+
+ info->name[sizeof(info->name) - 1] = '\0';
+ user += sizeof(*info);
+ }
+
+ size = sizeof(struct xt_counters);
+ size *= info->num_counters;
+
+ if (size != (u64)len)
+ return ERR_PTR(-EINVAL);
+
+ mem = vmalloc(len);
+ if (!mem)
+ return ERR_PTR(-ENOMEM);
+
+ if (copy_from_user(mem, user, len) == 0)
+ return mem;
+
+ vfree(mem);
+ return ERR_PTR(-EFAULT);
+}
+EXPORT_SYMBOL_GPL(xt_copy_counters_from_user);
+
#ifdef CONFIG_COMPAT
int xt_compat_target_offset(const struct xt_target *target)
{
@@ -608,6 +893,7 @@ void xt_compat_target_from_user(struct xt_entry_target *t, void **dstptr,
struct compat_xt_entry_target *ct = (struct compat_xt_entry_target *)t;
int pad, off = xt_compat_target_offset(target);
u_int16_t tsize = ct->u.user.target_size;
+ char name[sizeof(t->u.user.name)];
t = *dstptr;
memcpy(t, ct, sizeof(*ct));
@@ -621,6 +907,9 @@ void xt_compat_target_from_user(struct xt_entry_target *t, void **dstptr,
tsize += off;
t->u.user.target_size = tsize;
+ strlcpy(name, target->name, sizeof(name));
+ module_put(target->me);
+ strncpy(t->u.user.name, name, sizeof(t->u.user.name));
*size += off;
*dstptr += tsize;
diff --git a/net/netfilter/xt_cgroup.c b/net/netfilter/xt_cgroup.c
index 7198d660b4de..a1d126f29463 100644
--- a/net/netfilter/xt_cgroup.c
+++ b/net/netfilter/xt_cgroup.c
@@ -39,7 +39,7 @@ cgroup_mt(const struct sk_buff *skb, struct xt_action_param *par)
{
const struct xt_cgroup_info *info = par->matchinfo;
- if (skb->sk == NULL)
+ if (skb->sk == NULL || !sk_fullsock(skb->sk))
return false;
return (info->id == skb->sk->sk_classid) ^ info->invert;
generated by cgit v1.2.3 (git 2.25.1) at 2024-05-26 15:46:42 +0000