aboutsummaryrefslogtreecommitdiffstats
path: root/net/netfilter
diff options
context:
space:
mode:
Diffstat (limited to 'net/netfilter')
-rw-r--r--net/netfilter/nf_conntrack_core.c46
-rw-r--r--net/netfilter/nf_conntrack_expect.c4
-rw-r--r--net/netfilter/nf_conntrack_extend.c2
-rw-r--r--net/netfilter/nf_conntrack_proto_tcp.c6
-rw-r--r--net/netfilter/nf_log.c16
-rw-r--r--net/netfilter/xt_NFQUEUE.c8
-rw-r--r--net/netfilter/xt_RATEEST.c2
-rw-r--r--net/netfilter/xt_cluster.c8
-rw-r--r--net/netfilter/xt_conntrack.c66
-rw-r--r--net/netfilter/xt_osf.c5
-rw-r--r--net/netfilter/xt_quota.c3
-rw-r--r--net/netfilter/xt_rateest.c2
12 files changed, 131 insertions, 37 deletions
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index 5f72b94b4918..b5869b9574b0 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -335,7 +335,8 @@ begin:
h = __nf_conntrack_find(net, tuple);
if (h) {
ct = nf_ct_tuplehash_to_ctrack(h);
- if (unlikely(!atomic_inc_not_zero(&ct->ct_general.use)))
+ if (unlikely(nf_ct_is_dying(ct) ||
+ !atomic_inc_not_zero(&ct->ct_general.use)))
h = NULL;
else {
if (unlikely(!nf_ct_tuple_equal(tuple, &h->tuple))) {
@@ -425,7 +426,6 @@ __nf_conntrack_confirm(struct sk_buff *skb)
/* Remove from unconfirmed list */
hlist_nulls_del_rcu(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode);
- __nf_conntrack_hash_insert(ct, hash, repl_hash);
/* Timer relative to confirmation time, not original
setting time, otherwise we'd get timer wrap in
weird delay cases. */
@@ -433,8 +433,16 @@ __nf_conntrack_confirm(struct sk_buff *skb)
add_timer(&ct->timeout);
atomic_inc(&ct->ct_general.use);
set_bit(IPS_CONFIRMED_BIT, &ct->status);
+
+ /* Since the lookup is lockless, hash insertion must be done after
+ * starting the timer and setting the CONFIRMED bit. The RCU barriers
+ * guarantee that no other CPU can find the conntrack before the above
+ * stores are visible.
+ */
+ __nf_conntrack_hash_insert(ct, hash, repl_hash);
NF_CT_STAT_INC(net, insert);
spin_unlock_bh(&nf_conntrack_lock);
+
help = nfct_help(ct);
if (help && help->helper)
nf_conntrack_event_cache(IPCT_HELPER, ct);
@@ -503,7 +511,8 @@ static noinline int early_drop(struct net *net, unsigned int hash)
cnt++;
}
- if (ct && unlikely(!atomic_inc_not_zero(&ct->ct_general.use)))
+ if (ct && unlikely(nf_ct_is_dying(ct) ||
+ !atomic_inc_not_zero(&ct->ct_general.use)))
ct = NULL;
if (ct || cnt >= NF_CT_EVICTION_RANGE)
break;
@@ -552,23 +561,38 @@ struct nf_conn *nf_conntrack_alloc(struct net *net,
}
}
- ct = kmem_cache_zalloc(nf_conntrack_cachep, gfp);
+ /*
+ * Do not use kmem_cache_zalloc(), as this cache uses
+ * SLAB_DESTROY_BY_RCU.
+ */
+ ct = kmem_cache_alloc(nf_conntrack_cachep, gfp);
if (ct == NULL) {
pr_debug("nf_conntrack_alloc: Can't alloc conntrack.\n");
atomic_dec(&net->ct.count);
return ERR_PTR(-ENOMEM);
}
-
+ /*
+ * Let ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode.next
+ * and ct->tuplehash[IP_CT_DIR_REPLY].hnnode.next unchanged.
+ */
+ memset(&ct->tuplehash[IP_CT_DIR_MAX], 0,
+ sizeof(*ct) - offsetof(struct nf_conn, tuplehash[IP_CT_DIR_MAX]));
spin_lock_init(&ct->lock);
- atomic_set(&ct->ct_general.use, 1);
ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple = *orig;
+ ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode.pprev = NULL;
ct->tuplehash[IP_CT_DIR_REPLY].tuple = *repl;
+ ct->tuplehash[IP_CT_DIR_REPLY].hnnode.pprev = NULL;
/* Don't set timer yet: wait for confirmation */
setup_timer(&ct->timeout, death_by_timeout, (unsigned long)ct);
#ifdef CONFIG_NET_NS
ct->ct_net = net;
#endif
+ /*
+ * changes to lookup keys must be done before setting refcnt to 1
+ */
+ smp_wmb();
+ atomic_set(&ct->ct_general.use, 1);
return ct;
}
EXPORT_SYMBOL_GPL(nf_conntrack_alloc);
@@ -1267,13 +1291,19 @@ err_cache:
return ret;
}
+/*
+ * We need to use special "null" values, not used in hash table
+ */
+#define UNCONFIRMED_NULLS_VAL ((1<<30)+0)
+#define DYING_NULLS_VAL ((1<<30)+1)
+
static int nf_conntrack_init_net(struct net *net)
{
int ret;
atomic_set(&net->ct.count, 0);
- INIT_HLIST_NULLS_HEAD(&net->ct.unconfirmed, 0);
- INIT_HLIST_NULLS_HEAD(&net->ct.dying, 0);
+ INIT_HLIST_NULLS_HEAD(&net->ct.unconfirmed, UNCONFIRMED_NULLS_VAL);
+ INIT_HLIST_NULLS_HEAD(&net->ct.dying, DYING_NULLS_VAL);
net->ct.stat = alloc_percpu(struct ip_conntrack_stat);
if (!net->ct.stat) {
ret = -ENOMEM;
diff --git a/net/netfilter/nf_conntrack_expect.c b/net/netfilter/nf_conntrack_expect.c
index afde8f991646..2032dfe25ca8 100644
--- a/net/netfilter/nf_conntrack_expect.c
+++ b/net/netfilter/nf_conntrack_expect.c
@@ -617,8 +617,10 @@ err1:
void nf_conntrack_expect_fini(struct net *net)
{
exp_proc_remove(net);
- if (net_eq(net, &init_net))
+ if (net_eq(net, &init_net)) {
+ rcu_barrier(); /* Wait for call_rcu() before destroy */
kmem_cache_destroy(nf_ct_expect_cachep);
+ }
nf_ct_free_hashtable(net->ct.expect_hash, net->ct.expect_vmalloc,
nf_ct_expect_hsize);
}
diff --git a/net/netfilter/nf_conntrack_extend.c b/net/netfilter/nf_conntrack_extend.c
index 4b2c769d555f..fef95be334bd 100644
--- a/net/netfilter/nf_conntrack_extend.c
+++ b/net/netfilter/nf_conntrack_extend.c
@@ -186,6 +186,6 @@ void nf_ct_extend_unregister(struct nf_ct_ext_type *type)
rcu_assign_pointer(nf_ct_ext_types[type->id], NULL);
update_alloc_size(type);
mutex_unlock(&nf_ct_ext_type_mutex);
- synchronize_rcu();
+ rcu_barrier(); /* Wait for completion of call_rcu()'s */
}
EXPORT_SYMBOL_GPL(nf_ct_extend_unregister);
diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c
index 33fc0a443f3d..97a82ba75376 100644
--- a/net/netfilter/nf_conntrack_proto_tcp.c
+++ b/net/netfilter/nf_conntrack_proto_tcp.c
@@ -720,8 +720,8 @@ static bool tcp_in_window(const struct nf_conn *ct,
/* Caller must linearize skb at tcp header. */
void nf_conntrack_tcp_update(const struct sk_buff *skb,
unsigned int dataoff,
- struct nf_conn *ct,
- int dir)
+ struct nf_conn *ct, int dir,
+ s16 offset)
{
const struct tcphdr *tcph = (const void *)skb->data + dataoff;
const struct ip_ct_tcp_state *sender = &ct->proto.tcp.seen[dir];
@@ -734,7 +734,7 @@ void nf_conntrack_tcp_update(const struct sk_buff *skb,
/*
* We have to worry for the ack in the reply packet only...
*/
- if (after(end, ct->proto.tcp.seen[dir].td_end))
+ if (ct->proto.tcp.seen[dir].td_end + offset == end)
ct->proto.tcp.seen[dir].td_end = end;
ct->proto.tcp.last_end = end;
spin_unlock_bh(&ct->lock);
diff --git a/net/netfilter/nf_log.c b/net/netfilter/nf_log.c
index 2fefe147750a..4e620305f28c 100644
--- a/net/netfilter/nf_log.c
+++ b/net/netfilter/nf_log.c
@@ -47,7 +47,6 @@ int nf_log_register(u_int8_t pf, struct nf_logger *logger)
mutex_lock(&nf_log_mutex);
if (pf == NFPROTO_UNSPEC) {
- int i;
for (i = NFPROTO_UNSPEC; i < NFPROTO_NUMPROTO; i++)
list_add_tail(&(logger->list[i]), &(nf_loggers_l[i]));
} else {
@@ -216,7 +215,7 @@ static const struct file_operations nflog_file_ops = {
#endif /* PROC_FS */
#ifdef CONFIG_SYSCTL
-struct ctl_path nf_log_sysctl_path[] = {
+static struct ctl_path nf_log_sysctl_path[] = {
{ .procname = "net", .ctl_name = CTL_NET, },
{ .procname = "netfilter", .ctl_name = NET_NETFILTER, },
{ .procname = "nf_log", .ctl_name = CTL_UNNUMBERED, },
@@ -228,19 +227,26 @@ static struct ctl_table nf_log_sysctl_table[NFPROTO_NUMPROTO+1];
static struct ctl_table_header *nf_log_dir_header;
static int nf_log_proc_dostring(ctl_table *table, int write, struct file *filp,
- void *buffer, size_t *lenp, loff_t *ppos)
+ void __user *buffer, size_t *lenp, loff_t *ppos)
{
const struct nf_logger *logger;
+ char buf[NFLOGGER_NAME_LEN];
+ size_t size = *lenp;
int r = 0;
int tindex = (unsigned long)table->extra1;
if (write) {
- if (!strcmp(buffer, "NONE")) {
+ if (size > sizeof(buf))
+ size = sizeof(buf);
+ if (copy_from_user(buf, buffer, size))
+ return -EFAULT;
+
+ if (!strcmp(buf, "NONE")) {
nf_log_unbind_pf(tindex);
return 0;
}
mutex_lock(&nf_log_mutex);
- logger = __find_logger(tindex, buffer);
+ logger = __find_logger(tindex, buf);
if (logger == NULL) {
mutex_unlock(&nf_log_mutex);
return -ENOENT;
diff --git a/net/netfilter/xt_NFQUEUE.c b/net/netfilter/xt_NFQUEUE.c
index 498b45101df7..f28f6a5fc02d 100644
--- a/net/netfilter/xt_NFQUEUE.c
+++ b/net/netfilter/xt_NFQUEUE.c
@@ -40,12 +40,12 @@ nfqueue_tg(struct sk_buff *skb, const struct xt_target_param *par)
static u32 hash_v4(const struct sk_buff *skb)
{
const struct iphdr *iph = ip_hdr(skb);
- u32 ipaddr;
+ __be32 ipaddr;
/* packets in either direction go into same queue */
ipaddr = iph->saddr ^ iph->daddr;
- return jhash_2words(ipaddr, iph->protocol, jhash_initval);
+ return jhash_2words((__force u32)ipaddr, iph->protocol, jhash_initval);
}
static unsigned int
@@ -63,14 +63,14 @@ nfqueue_tg4_v1(struct sk_buff *skb, const struct xt_target_param *par)
static u32 hash_v6(const struct sk_buff *skb)
{
const struct ipv6hdr *ip6h = ipv6_hdr(skb);
- u32 addr[4];
+ __be32 addr[4];
addr[0] = ip6h->saddr.s6_addr32[0] ^ ip6h->daddr.s6_addr32[0];
addr[1] = ip6h->saddr.s6_addr32[1] ^ ip6h->daddr.s6_addr32[1];
addr[2] = ip6h->saddr.s6_addr32[2] ^ ip6h->daddr.s6_addr32[2];
addr[3] = ip6h->saddr.s6_addr32[3] ^ ip6h->daddr.s6_addr32[3];
- return jhash2(addr, ARRAY_SIZE(addr), jhash_initval);
+ return jhash2((__force u32 *)addr, ARRAY_SIZE(addr), jhash_initval);
}
static unsigned int
diff --git a/net/netfilter/xt_RATEEST.c b/net/netfilter/xt_RATEEST.c
index 43f5676b1af4..d80b8192e0d4 100644
--- a/net/netfilter/xt_RATEEST.c
+++ b/net/netfilter/xt_RATEEST.c
@@ -74,7 +74,7 @@ static unsigned int
xt_rateest_tg(struct sk_buff *skb, const struct xt_target_param *par)
{
const struct xt_rateest_target_info *info = par->targinfo;
- struct gnet_stats_basic *stats = &info->est->bstats;
+ struct gnet_stats_basic_packed *stats = &info->est->bstats;
spin_lock_bh(&info->est->lock);
stats->bytes += skb->len;
diff --git a/net/netfilter/xt_cluster.c b/net/netfilter/xt_cluster.c
index 69a639f35403..225ee3ecd69d 100644
--- a/net/netfilter/xt_cluster.c
+++ b/net/netfilter/xt_cluster.c
@@ -15,14 +15,14 @@
#include <net/netfilter/nf_conntrack.h>
#include <linux/netfilter/xt_cluster.h>
-static inline u_int32_t nf_ct_orig_ipv4_src(const struct nf_conn *ct)
+static inline u32 nf_ct_orig_ipv4_src(const struct nf_conn *ct)
{
- return ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.u3.ip;
+ return (__force u32)ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.u3.ip;
}
-static inline const void *nf_ct_orig_ipv6_src(const struct nf_conn *ct)
+static inline const u32 *nf_ct_orig_ipv6_src(const struct nf_conn *ct)
{
- return ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.u3.ip6;
+ return (__force u32 *)ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.u3.ip6;
}
static inline u_int32_t
diff --git a/net/netfilter/xt_conntrack.c b/net/netfilter/xt_conntrack.c
index 0b7139f3dd78..fc581800698e 100644
--- a/net/netfilter/xt_conntrack.c
+++ b/net/netfilter/xt_conntrack.c
@@ -129,7 +129,7 @@ conntrack_addrcmp(const union nf_inet_addr *kaddr,
static inline bool
conntrack_mt_origsrc(const struct nf_conn *ct,
- const struct xt_conntrack_mtinfo1 *info,
+ const struct xt_conntrack_mtinfo2 *info,
u_int8_t family)
{
return conntrack_addrcmp(&ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.u3,
@@ -138,7 +138,7 @@ conntrack_mt_origsrc(const struct nf_conn *ct,
static inline bool
conntrack_mt_origdst(const struct nf_conn *ct,
- const struct xt_conntrack_mtinfo1 *info,
+ const struct xt_conntrack_mtinfo2 *info,
u_int8_t family)
{
return conntrack_addrcmp(&ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.u3,
@@ -147,7 +147,7 @@ conntrack_mt_origdst(const struct nf_conn *ct,
static inline bool
conntrack_mt_replsrc(const struct nf_conn *ct,
- const struct xt_conntrack_mtinfo1 *info,
+ const struct xt_conntrack_mtinfo2 *info,
u_int8_t family)
{
return conntrack_addrcmp(&ct->tuplehash[IP_CT_DIR_REPLY].tuple.src.u3,
@@ -156,7 +156,7 @@ conntrack_mt_replsrc(const struct nf_conn *ct,
static inline bool
conntrack_mt_repldst(const struct nf_conn *ct,
- const struct xt_conntrack_mtinfo1 *info,
+ const struct xt_conntrack_mtinfo2 *info,
u_int8_t family)
{
return conntrack_addrcmp(&ct->tuplehash[IP_CT_DIR_REPLY].tuple.dst.u3,
@@ -164,7 +164,7 @@ conntrack_mt_repldst(const struct nf_conn *ct,
}
static inline bool
-ct_proto_port_check(const struct xt_conntrack_mtinfo1 *info,
+ct_proto_port_check(const struct xt_conntrack_mtinfo2 *info,
const struct nf_conn *ct)
{
const struct nf_conntrack_tuple *tuple;
@@ -204,7 +204,7 @@ ct_proto_port_check(const struct xt_conntrack_mtinfo1 *info,
static bool
conntrack_mt(const struct sk_buff *skb, const struct xt_match_param *par)
{
- const struct xt_conntrack_mtinfo1 *info = par->matchinfo;
+ const struct xt_conntrack_mtinfo2 *info = par->matchinfo;
enum ip_conntrack_info ctinfo;
const struct nf_conn *ct;
unsigned int statebit;
@@ -278,6 +278,16 @@ conntrack_mt(const struct sk_buff *skb, const struct xt_match_param *par)
return true;
}
+static bool
+conntrack_mt_v1(const struct sk_buff *skb, const struct xt_match_param *par)
+{
+ const struct xt_conntrack_mtinfo2 *const *info = par->matchinfo;
+ struct xt_match_param newpar = *par;
+
+ newpar.matchinfo = *info;
+ return conntrack_mt(skb, &newpar);
+}
+
static bool conntrack_mt_check(const struct xt_mtchk_param *par)
{
if (nf_ct_l3proto_try_module_get(par->family) < 0) {
@@ -288,11 +298,45 @@ static bool conntrack_mt_check(const struct xt_mtchk_param *par)
return true;
}
+static bool conntrack_mt_check_v1(const struct xt_mtchk_param *par)
+{
+ struct xt_conntrack_mtinfo1 *info = par->matchinfo;
+ struct xt_conntrack_mtinfo2 *up;
+ int ret = conntrack_mt_check(par);
+
+ if (ret < 0)
+ return ret;
+
+ up = kmalloc(sizeof(*up), GFP_KERNEL);
+ if (up == NULL) {
+ nf_ct_l3proto_module_put(par->family);
+ return -ENOMEM;
+ }
+
+ /*
+ * The strategy here is to minimize the overhead of v1 matching,
+ * by prebuilding a v2 struct and putting the pointer into the
+ * v1 dataspace.
+ */
+ memcpy(up, info, offsetof(typeof(*info), state_mask));
+ up->state_mask = info->state_mask;
+ up->status_mask = info->status_mask;
+ *(void **)info = up;
+ return true;
+}
+
static void conntrack_mt_destroy(const struct xt_mtdtor_param *par)
{
nf_ct_l3proto_module_put(par->family);
}
+static void conntrack_mt_destroy_v1(const struct xt_mtdtor_param *par)
+{
+ struct xt_conntrack_mtinfo2 **info = par->matchinfo;
+ kfree(*info);
+ conntrack_mt_destroy(par);
+}
+
#ifdef CONFIG_COMPAT
struct compat_xt_conntrack_info
{
@@ -363,6 +407,16 @@ static struct xt_match conntrack_mt_reg[] __read_mostly = {
.revision = 1,
.family = NFPROTO_UNSPEC,
.matchsize = sizeof(struct xt_conntrack_mtinfo1),
+ .match = conntrack_mt_v1,
+ .checkentry = conntrack_mt_check_v1,
+ .destroy = conntrack_mt_destroy_v1,
+ .me = THIS_MODULE,
+ },
+ {
+ .name = "conntrack",
+ .revision = 2,
+ .family = NFPROTO_UNSPEC,
+ .matchsize = sizeof(struct xt_conntrack_mtinfo2),
.match = conntrack_mt,
.checkentry = conntrack_mt_check,
.destroy = conntrack_mt_destroy,
diff --git a/net/netfilter/xt_osf.c b/net/netfilter/xt_osf.c
index 863e40977a4d..0f482e2440b4 100644
--- a/net/netfilter/xt_osf.c
+++ b/net/netfilter/xt_osf.c
@@ -330,7 +330,8 @@ static bool xt_osf_match_packet(const struct sk_buff *skb,
fcount++;
if (info->flags & XT_OSF_LOG)
- nf_log_packet(p->hooknum, 0, skb, p->in, p->out, NULL,
+ nf_log_packet(p->family, p->hooknum, skb,
+ p->in, p->out, NULL,
"%s [%s:%s] : %pi4:%d -> %pi4:%d hops=%d\n",
f->genre, f->version, f->subtype,
&ip->saddr, ntohs(tcp->source),
@@ -345,7 +346,7 @@ static bool xt_osf_match_packet(const struct sk_buff *skb,
rcu_read_unlock();
if (!fcount && (info->flags & XT_OSF_LOG))
- nf_log_packet(p->hooknum, 0, skb, p->in, p->out, NULL,
+ nf_log_packet(p->family, p->hooknum, skb, p->in, p->out, NULL,
"Remote OS is not known: %pi4:%u -> %pi4:%u\n",
&ip->saddr, ntohs(tcp->source),
&ip->daddr, ntohs(tcp->dest));
diff --git a/net/netfilter/xt_quota.c b/net/netfilter/xt_quota.c
index 01dd07b764ec..390b7d09fe51 100644
--- a/net/netfilter/xt_quota.c
+++ b/net/netfilter/xt_quota.c
@@ -52,8 +52,9 @@ static bool quota_mt_check(const struct xt_mtchk_param *par)
q->master = kmalloc(sizeof(*q->master), GFP_KERNEL);
if (q->master == NULL)
- return -ENOMEM;
+ return false;
+ q->master->quota = q->quota;
return true;
}
diff --git a/net/netfilter/xt_rateest.c b/net/netfilter/xt_rateest.c
index 220a1d588ee0..4fc6a917f6de 100644
--- a/net/netfilter/xt_rateest.c
+++ b/net/netfilter/xt_rateest.c
@@ -66,7 +66,7 @@ xt_rateest_mt(const struct sk_buff *skb, const struct xt_match_param *par)
if (info->flags & XT_RATEEST_MATCH_BPS)
ret &= bps1 == bps2;
if (info->flags & XT_RATEEST_MATCH_PPS)
- ret &= pps2 == pps2;
+ ret &= pps1 == pps2;
break;
}
Copyright © 1996 – 2023 Jason A. Donenfeld. All Rights Reverse Engineered.