summaryrefslogtreecommitdiff
path: root/net/netfilter
diff options
context:
space:
mode:
Diffstat (limited to 'net/netfilter')
-rw-r--r--net/netfilter/core.c13
-rw-r--r--net/netfilter/ipset/ip_set_core.c92
-rw-r--r--net/netfilter/ipset/ip_set_list_set.c30
-rw-r--r--net/netfilter/nf_conntrack_standalone.c15
-rw-r--r--net/netfilter/nf_hooks_lwtunnel.c70
-rw-r--r--net/netfilter/nf_internals.h6
-rw-r--r--net/netfilter/nf_tables_api.c11
-rw-r--r--net/netfilter/nft_lookup.c3
-rw-r--r--net/netfilter/nft_meta.c3
-rw-r--r--net/netfilter/nft_payload.c4
10 files changed, 167 insertions, 80 deletions
diff --git a/net/netfilter/core.c b/net/netfilter/core.c
index 3126911f5042..b00fc285b334 100644
--- a/net/netfilter/core.c
+++ b/net/netfilter/core.c
@@ -815,12 +815,21 @@ int __init netfilter_init(void)
if (ret < 0)
goto err;
+#ifdef CONFIG_LWTUNNEL
+ ret = netfilter_lwtunnel_init();
+ if (ret < 0)
+ goto err_lwtunnel_pernet;
+#endif
ret = netfilter_log_init();
if (ret < 0)
- goto err_pernet;
+ goto err_log_pernet;
return 0;
-err_pernet:
+err_log_pernet:
+#ifdef CONFIG_LWTUNNEL
+ netfilter_lwtunnel_fini();
+err_lwtunnel_pernet:
+#endif
unregister_pernet_subsys(&netfilter_net_ops);
err:
return ret;
diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c
index 3184cc6be4c9..61431690cbd5 100644
--- a/net/netfilter/ipset/ip_set_core.c
+++ b/net/netfilter/ipset/ip_set_core.c
@@ -53,12 +53,13 @@ MODULE_DESCRIPTION("core IP set support");
MODULE_ALIAS_NFNL_SUBSYS(NFNL_SUBSYS_IPSET);
/* When the nfnl mutex or ip_set_ref_lock is held: */
-#define ip_set_dereference(p) \
- rcu_dereference_protected(p, \
+#define ip_set_dereference(inst) \
+ rcu_dereference_protected((inst)->ip_set_list, \
lockdep_nfnl_is_held(NFNL_SUBSYS_IPSET) || \
- lockdep_is_held(&ip_set_ref_lock))
+ lockdep_is_held(&ip_set_ref_lock) || \
+ (inst)->is_deleted)
#define ip_set(inst, id) \
- ip_set_dereference((inst)->ip_set_list)[id]
+ ip_set_dereference(inst)[id]
#define ip_set_ref_netlink(inst,id) \
rcu_dereference_raw((inst)->ip_set_list)[id]
#define ip_set_dereference_nfnl(p) \
@@ -1133,7 +1134,7 @@ static int ip_set_create(struct sk_buff *skb, const struct nfnl_info *info,
if (!list)
goto cleanup;
/* nfnl mutex is held, both lists are valid */
- tmp = ip_set_dereference(inst->ip_set_list);
+ tmp = ip_set_dereference(inst);
memcpy(list, tmp, sizeof(struct ip_set *) * inst->ip_set_max);
rcu_assign_pointer(inst->ip_set_list, list);
/* Make sure all current packets have passed through */
@@ -1172,23 +1173,50 @@ ip_set_setname_policy[IPSET_ATTR_CMD_MAX + 1] = {
.len = IPSET_MAXNAMELEN - 1 },
};
+/* In order to return quickly when destroying a single set, it is split
+ * into two stages:
+ * - Cancel garbage collector
+ * - Destroy the set itself via call_rcu()
+ */
+
static void
-ip_set_destroy_set(struct ip_set *set)
+ip_set_destroy_set_rcu(struct rcu_head *head)
{
- pr_debug("set: %s\n", set->name);
+ struct ip_set *set = container_of(head, struct ip_set, rcu);
- /* Must call it without holding any lock */
set->variant->destroy(set);
module_put(set->type->me);
kfree(set);
}
static void
-ip_set_destroy_set_rcu(struct rcu_head *head)
+_destroy_all_sets(struct ip_set_net *inst)
{
- struct ip_set *set = container_of(head, struct ip_set, rcu);
+ struct ip_set *set;
+ ip_set_id_t i;
+ bool need_wait = false;
- ip_set_destroy_set(set);
+ /* First cancel gc's: set:list sets are flushed as well */
+ for (i = 0; i < inst->ip_set_max; i++) {
+ set = ip_set(inst, i);
+ if (set) {
+ set->variant->cancel_gc(set);
+ if (set->type->features & IPSET_TYPE_NAME)
+ need_wait = true;
+ }
+ }
+ /* Must wait for flush to be really finished */
+ if (need_wait)
+ rcu_barrier();
+ for (i = 0; i < inst->ip_set_max; i++) {
+ set = ip_set(inst, i);
+ if (set) {
+ ip_set(inst, i) = NULL;
+ set->variant->destroy(set);
+ module_put(set->type->me);
+ kfree(set);
+ }
+ }
}
static int ip_set_destroy(struct sk_buff *skb, const struct nfnl_info *info,
@@ -1202,11 +1230,10 @@ static int ip_set_destroy(struct sk_buff *skb, const struct nfnl_info *info,
if (unlikely(protocol_min_failed(attr)))
return -IPSET_ERR_PROTOCOL;
-
/* Commands are serialized and references are
* protected by the ip_set_ref_lock.
* External systems (i.e. xt_set) must call
- * ip_set_put|get_nfnl_* functions, that way we
+ * ip_set_nfnl_get_* functions, that way we
* can safely check references here.
*
* list:set timer can only decrement the reference
@@ -1214,8 +1241,6 @@ static int ip_set_destroy(struct sk_buff *skb, const struct nfnl_info *info,
* without holding the lock.
*/
if (!attr[IPSET_ATTR_SETNAME]) {
- /* Must wait for flush to be really finished in list:set */
- rcu_barrier();
read_lock_bh(&ip_set_ref_lock);
for (i = 0; i < inst->ip_set_max; i++) {
s = ip_set(inst, i);
@@ -1226,15 +1251,7 @@ static int ip_set_destroy(struct sk_buff *skb, const struct nfnl_info *info,
}
inst->is_destroyed = true;
read_unlock_bh(&ip_set_ref_lock);
- for (i = 0; i < inst->ip_set_max; i++) {
- s = ip_set(inst, i);
- if (s) {
- ip_set(inst, i) = NULL;
- /* Must cancel garbage collectors */
- s->variant->cancel_gc(s);
- ip_set_destroy_set(s);
- }
- }
+ _destroy_all_sets(inst);
/* Modified by ip_set_destroy() only, which is serialized */
inst->is_destroyed = false;
} else {
@@ -1255,12 +1272,12 @@ static int ip_set_destroy(struct sk_buff *skb, const struct nfnl_info *info,
features = s->type->features;
ip_set(inst, i) = NULL;
read_unlock_bh(&ip_set_ref_lock);
+ /* Must cancel garbage collectors */
+ s->variant->cancel_gc(s);
if (features & IPSET_TYPE_NAME) {
/* Must wait for flush to be really finished */
rcu_barrier();
}
- /* Must cancel garbage collectors */
- s->variant->cancel_gc(s);
call_rcu(&s->rcu, ip_set_destroy_set_rcu);
}
return 0;
@@ -2365,30 +2382,25 @@ ip_set_net_init(struct net *net)
}
static void __net_exit
-ip_set_net_exit(struct net *net)
+ip_set_net_pre_exit(struct net *net)
{
struct ip_set_net *inst = ip_set_pernet(net);
- struct ip_set *set = NULL;
- ip_set_id_t i;
-
inst->is_deleted = true; /* flag for ip_set_nfnl_put */
+}
- nfnl_lock(NFNL_SUBSYS_IPSET);
- for (i = 0; i < inst->ip_set_max; i++) {
- set = ip_set(inst, i);
- if (set) {
- ip_set(inst, i) = NULL;
- set->variant->cancel_gc(set);
- ip_set_destroy_set(set);
- }
- }
- nfnl_unlock(NFNL_SUBSYS_IPSET);
+static void __net_exit
+ip_set_net_exit(struct net *net)
+{
+ struct ip_set_net *inst = ip_set_pernet(net);
+
+ _destroy_all_sets(inst);
kvfree(rcu_dereference_protected(inst->ip_set_list, 1));
}
static struct pernet_operations ip_set_net_ops = {
.init = ip_set_net_init,
+ .pre_exit = ip_set_net_pre_exit,
.exit = ip_set_net_exit,
.id = &ip_set_net_id,
.size = sizeof(struct ip_set_net),
diff --git a/net/netfilter/ipset/ip_set_list_set.c b/net/netfilter/ipset/ip_set_list_set.c
index 54e2a1dd7f5f..bfae7066936b 100644
--- a/net/netfilter/ipset/ip_set_list_set.c
+++ b/net/netfilter/ipset/ip_set_list_set.c
@@ -79,7 +79,7 @@ list_set_kadd(struct ip_set *set, const struct sk_buff *skb,
struct set_elem *e;
int ret;
- list_for_each_entry(e, &map->members, list) {
+ list_for_each_entry_rcu(e, &map->members, list) {
if (SET_WITH_TIMEOUT(set) &&
ip_set_timeout_expired(ext_timeout(e, set)))
continue;
@@ -99,7 +99,7 @@ list_set_kdel(struct ip_set *set, const struct sk_buff *skb,
struct set_elem *e;
int ret;
- list_for_each_entry(e, &map->members, list) {
+ list_for_each_entry_rcu(e, &map->members, list) {
if (SET_WITH_TIMEOUT(set) &&
ip_set_timeout_expired(ext_timeout(e, set)))
continue;
@@ -188,9 +188,10 @@ list_set_utest(struct ip_set *set, void *value, const struct ip_set_ext *ext,
struct list_set *map = set->data;
struct set_adt_elem *d = value;
struct set_elem *e, *next, *prev = NULL;
- int ret;
+ int ret = 0;
- list_for_each_entry(e, &map->members, list) {
+ rcu_read_lock();
+ list_for_each_entry_rcu(e, &map->members, list) {
if (SET_WITH_TIMEOUT(set) &&
ip_set_timeout_expired(ext_timeout(e, set)))
continue;
@@ -201,6 +202,7 @@ list_set_utest(struct ip_set *set, void *value, const struct ip_set_ext *ext,
if (d->before == 0) {
ret = 1;
+ goto out;
} else if (d->before > 0) {
next = list_next_entry(e, list);
ret = !list_is_last(&e->list, &map->members) &&
@@ -208,9 +210,11 @@ list_set_utest(struct ip_set *set, void *value, const struct ip_set_ext *ext,
} else {
ret = prev && prev->id == d->refid;
}
- return ret;
+ goto out;
}
- return 0;
+out:
+ rcu_read_unlock();
+ return ret;
}
static void
@@ -239,7 +243,7 @@ list_set_uadd(struct ip_set *set, void *value, const struct ip_set_ext *ext,
/* Find where to add the new entry */
n = prev = next = NULL;
- list_for_each_entry(e, &map->members, list) {
+ list_for_each_entry_rcu(e, &map->members, list) {
if (SET_WITH_TIMEOUT(set) &&
ip_set_timeout_expired(ext_timeout(e, set)))
continue;
@@ -316,9 +320,9 @@ list_set_udel(struct ip_set *set, void *value, const struct ip_set_ext *ext,
{
struct list_set *map = set->data;
struct set_adt_elem *d = value;
- struct set_elem *e, *next, *prev = NULL;
+ struct set_elem *e, *n, *next, *prev = NULL;
- list_for_each_entry(e, &map->members, list) {
+ list_for_each_entry_safe(e, n, &map->members, list) {
if (SET_WITH_TIMEOUT(set) &&
ip_set_timeout_expired(ext_timeout(e, set)))
continue;
@@ -424,14 +428,8 @@ static void
list_set_destroy(struct ip_set *set)
{
struct list_set *map = set->data;
- struct set_elem *e, *n;
- list_for_each_entry_safe(e, n, &map->members, list) {
- list_del(&e->list);
- ip_set_put_byindex(map->net, e->id);
- ip_set_ext_destroy(set, e);
- kfree(e);
- }
+ WARN_ON_ONCE(!list_empty(&map->members));
kfree(map);
set->data = NULL;
diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c
index 74112e9c5dab..6c40bdf8b05a 100644
--- a/net/netfilter/nf_conntrack_standalone.c
+++ b/net/netfilter/nf_conntrack_standalone.c
@@ -22,9 +22,6 @@
#include <net/netfilter/nf_conntrack_acct.h>
#include <net/netfilter/nf_conntrack_zones.h>
#include <net/netfilter/nf_conntrack_timestamp.h>
-#ifdef CONFIG_LWTUNNEL
-#include <net/netfilter/nf_hooks_lwtunnel.h>
-#endif
#include <linux/rculist_nulls.h>
static bool enable_hooks __read_mostly;
@@ -612,9 +609,6 @@ enum nf_ct_sysctl_index {
NF_SYSCTL_CT_PROTO_TIMEOUT_GRE,
NF_SYSCTL_CT_PROTO_TIMEOUT_GRE_STREAM,
#endif
-#ifdef CONFIG_LWTUNNEL
- NF_SYSCTL_CT_LWTUNNEL,
-#endif
NF_SYSCTL_CT_LAST_SYSCTL,
};
@@ -946,15 +940,6 @@ static struct ctl_table nf_ct_sysctl_table[] = {
.proc_handler = proc_dointvec_jiffies,
},
#endif
-#ifdef CONFIG_LWTUNNEL
- [NF_SYSCTL_CT_LWTUNNEL] = {
- .procname = "nf_hooks_lwtunnel",
- .data = NULL,
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = nf_hooks_lwtunnel_sysctl_handler,
- },
-#endif
};
static struct ctl_table nf_ct_netfilter_table[] = {
diff --git a/net/netfilter/nf_hooks_lwtunnel.c b/net/netfilter/nf_hooks_lwtunnel.c
index 00e89ffd78f6..d8ebebc9775d 100644
--- a/net/netfilter/nf_hooks_lwtunnel.c
+++ b/net/netfilter/nf_hooks_lwtunnel.c
@@ -3,6 +3,9 @@
#include <linux/sysctl.h>
#include <net/lwtunnel.h>
#include <net/netfilter/nf_hooks_lwtunnel.h>
+#include <linux/netfilter.h>
+
+#include "nf_internals.h"
static inline int nf_hooks_lwtunnel_get(void)
{
@@ -50,4 +53,71 @@ int nf_hooks_lwtunnel_sysctl_handler(struct ctl_table *table, int write,
return ret;
}
EXPORT_SYMBOL_GPL(nf_hooks_lwtunnel_sysctl_handler);
+
+static struct ctl_table nf_lwtunnel_sysctl_table[] = {
+ {
+ .procname = "nf_hooks_lwtunnel",
+ .data = NULL,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = nf_hooks_lwtunnel_sysctl_handler,
+ },
+};
+
+static int __net_init nf_lwtunnel_net_init(struct net *net)
+{
+ struct ctl_table_header *hdr;
+ struct ctl_table *table;
+
+ table = nf_lwtunnel_sysctl_table;
+ if (!net_eq(net, &init_net)) {
+ table = kmemdup(nf_lwtunnel_sysctl_table,
+ sizeof(nf_lwtunnel_sysctl_table),
+ GFP_KERNEL);
+ if (!table)
+ goto err_alloc;
+ }
+
+ hdr = register_net_sysctl_sz(net, "net/netfilter", table,
+ ARRAY_SIZE(nf_lwtunnel_sysctl_table));
+ if (!hdr)
+ goto err_reg;
+
+ net->nf.nf_lwtnl_dir_header = hdr;
+
+ return 0;
+err_reg:
+ if (!net_eq(net, &init_net))
+ kfree(table);
+err_alloc:
+ return -ENOMEM;
+}
+
+static void __net_exit nf_lwtunnel_net_exit(struct net *net)
+{
+ const struct ctl_table *table;
+
+ table = net->nf.nf_lwtnl_dir_header->ctl_table_arg;
+ unregister_net_sysctl_table(net->nf.nf_lwtnl_dir_header);
+ if (!net_eq(net, &init_net))
+ kfree(table);
+}
+
+static struct pernet_operations nf_lwtunnel_net_ops = {
+ .init = nf_lwtunnel_net_init,
+ .exit = nf_lwtunnel_net_exit,
+};
+
+int __init netfilter_lwtunnel_init(void)
+{
+ return register_pernet_subsys(&nf_lwtunnel_net_ops);
+}
+
+void netfilter_lwtunnel_fini(void)
+{
+ unregister_pernet_subsys(&nf_lwtunnel_net_ops);
+}
+#else
+int __init netfilter_lwtunnel_init(void) { return 0; }
+void netfilter_lwtunnel_fini(void) {}
#endif /* CONFIG_SYSCTL */
diff --git a/net/netfilter/nf_internals.h b/net/netfilter/nf_internals.h
index 832ae64179f0..25403023060b 100644
--- a/net/netfilter/nf_internals.h
+++ b/net/netfilter/nf_internals.h
@@ -29,6 +29,12 @@ void nf_queue_nf_hook_drop(struct net *net);
/* nf_log.c */
int __init netfilter_log_init(void);
+#ifdef CONFIG_LWTUNNEL
+/* nf_hooks_lwtunnel.c */
+int __init netfilter_lwtunnel_init(void);
+void netfilter_lwtunnel_fini(void);
+#endif
+
/* core.c */
void nf_hook_entries_delete_raw(struct nf_hook_entries __rcu **pp,
const struct nf_hook_ops *reg);
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index be3b4c90d2ed..081c08536d0f 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -5740,8 +5740,7 @@ static int nf_tables_fill_setelem(struct sk_buff *skb,
if (nft_set_ext_exists(ext, NFT_SET_EXT_DATA) &&
nft_data_dump(skb, NFTA_SET_ELEM_DATA, nft_set_ext_data(ext),
- set->dtype == NFT_DATA_VERDICT ? NFT_DATA_VERDICT : NFT_DATA_VALUE,
- set->dlen) < 0)
+ nft_set_datatype(set), set->dlen) < 0)
goto nla_put_failure;
if (nft_set_ext_exists(ext, NFT_SET_EXT_EXPRESSIONS) &&
@@ -11073,6 +11072,9 @@ static int nft_validate_register_store(const struct nft_ctx *ctx,
return 0;
default:
+ if (type != NFT_DATA_VALUE)
+ return -EINVAL;
+
if (reg < NFT_REG_1 * NFT_REG_SIZE / NFT_REG32_SIZE)
return -EINVAL;
if (len == 0)
@@ -11081,8 +11083,6 @@ static int nft_validate_register_store(const struct nft_ctx *ctx,
sizeof_field(struct nft_regs, data))
return -ERANGE;
- if (data != NULL && type != NFT_DATA_VALUE)
- return -EINVAL;
return 0;
}
}
@@ -11483,8 +11483,7 @@ static int nft_rcv_nl_event(struct notifier_block *this, unsigned long event,
gc_seq = nft_gc_seq_begin(nft_net);
- if (!list_empty(&nf_tables_destroy_list))
- nf_tables_trans_destroy_flush_work();
+ nf_tables_trans_destroy_flush_work();
again:
list_for_each_entry(table, &nft_net->tables, list) {
if (nft_table_has_owner(table) &&
diff --git a/net/netfilter/nft_lookup.c b/net/netfilter/nft_lookup.c
index b314ca728a29..f3080fa1b226 100644
--- a/net/netfilter/nft_lookup.c
+++ b/net/netfilter/nft_lookup.c
@@ -132,7 +132,8 @@ static int nft_lookup_init(const struct nft_ctx *ctx,
return -EINVAL;
err = nft_parse_register_store(ctx, tb[NFTA_LOOKUP_DREG],
- &priv->dreg, NULL, set->dtype,
+ &priv->dreg, NULL,
+ nft_set_datatype(set),
set->dlen);
if (err < 0)
return err;
diff --git a/net/netfilter/nft_meta.c b/net/netfilter/nft_meta.c
index ba0d3683a45d..9139ce38ea7b 100644
--- a/net/netfilter/nft_meta.c
+++ b/net/netfilter/nft_meta.c
@@ -839,6 +839,9 @@ static int nft_meta_inner_init(const struct nft_ctx *ctx,
struct nft_meta *priv = nft_expr_priv(expr);
unsigned int len;
+ if (!tb[NFTA_META_KEY] || !tb[NFTA_META_DREG])
+ return -EINVAL;
+
priv->key = ntohl(nla_get_be32(tb[NFTA_META_KEY]));
switch (priv->key) {
case NFT_META_PROTOCOL:
diff --git a/net/netfilter/nft_payload.c b/net/netfilter/nft_payload.c
index 0c43d748e23a..50429cbd42da 100644
--- a/net/netfilter/nft_payload.c
+++ b/net/netfilter/nft_payload.c
@@ -650,6 +650,10 @@ static int nft_payload_inner_init(const struct nft_ctx *ctx,
struct nft_payload *priv = nft_expr_priv(expr);
u32 base;
+ if (!tb[NFTA_PAYLOAD_BASE] || !tb[NFTA_PAYLOAD_OFFSET] ||
+ !tb[NFTA_PAYLOAD_LEN] || !tb[NFTA_PAYLOAD_DREG])
+ return -EINVAL;
+
base = ntohl(nla_get_be32(tb[NFTA_PAYLOAD_BASE]));
switch (base) {
case NFT_PAYLOAD_TUN_HEADER:
generated by cgit v1.2.3-70-g09d2 (git 2.47.1) at 2025-02-04 23:32:10 +0000