summaryrefslogtreecommitdiff
path: root/net/sched
diff options
context:
space:
mode:
Diffstat (limited to 'net/sched')
-rw-r--r--net/sched/act_ct.c124
-rw-r--r--net/sched/act_skbedit.c14
-rw-r--r--net/sched/cls_api.c7
3 files changed, 118 insertions, 27 deletions
diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c
index 4c7f7861ea96..dd5ae7551956 100644
--- a/net/sched/act_ct.c
+++ b/net/sched/act_ct.c
@@ -33,6 +33,7 @@
#include <net/netfilter/nf_conntrack_acct.h>
#include <net/netfilter/ipv6/nf_defrag_ipv6.h>
#include <net/netfilter/nf_conntrack_act_ct.h>
+#include <net/netfilter/nf_conntrack_seqadj.h>
#include <uapi/linux/netfilter/nf_nat.h>
static struct workqueue_struct *act_ct_wq;
@@ -345,11 +346,9 @@ static void tcf_ct_flow_table_cleanup_work(struct work_struct *work)
module_put(THIS_MODULE);
}
-static void tcf_ct_flow_table_put(struct tcf_ct_params *params)
+static void tcf_ct_flow_table_put(struct tcf_ct_flow_table *ct_ft)
{
- struct tcf_ct_flow_table *ct_ft = params->ct_ft;
-
- if (refcount_dec_and_test(&params->ct_ft->ref)) {
+ if (refcount_dec_and_test(&ct_ft->ref)) {
rhashtable_remove_fast(&zones_ht, &ct_ft->node, zones_params);
INIT_RCU_WORK(&ct_ft->rwork, tcf_ct_flow_table_cleanup_work);
queue_rcu_work(act_ct_wq, &ct_ft->rwork);
@@ -657,7 +656,7 @@ struct tc_ct_action_net {
/* Determine whether skb->_nfct is equal to the result of conntrack lookup. */
static bool tcf_ct_skb_nfct_cached(struct net *net, struct sk_buff *skb,
- u16 zone_id, bool force)
+ struct tcf_ct_params *p)
{
enum ip_conntrack_info ctinfo;
struct nf_conn *ct;
@@ -667,11 +666,19 @@ static bool tcf_ct_skb_nfct_cached(struct net *net, struct sk_buff *skb,
return false;
if (!net_eq(net, read_pnet(&ct->ct_net)))
goto drop_ct;
- if (nf_ct_zone(ct)->id != zone_id)
+ if (nf_ct_zone(ct)->id != p->zone)
goto drop_ct;
+ if (p->helper) {
+ struct nf_conn_help *help;
+
+ help = nf_ct_ext_find(ct, NF_CT_EXT_HELPER);
+ if (help && rcu_access_pointer(help->helper) != p->helper)
+ goto drop_ct;
+ }
/* Force conntrack entry direction. */
- if (force && CTINFO2DIR(ctinfo) != IP_CT_DIR_ORIGINAL) {
+ if ((p->ct_action & TCA_CT_ACT_FORCE) &&
+ CTINFO2DIR(ctinfo) != IP_CT_DIR_ORIGINAL) {
if (nf_ct_is_confirmed(ct))
nf_ct_kill(ct);
@@ -832,18 +839,30 @@ out_free:
return err;
}
-static void tcf_ct_params_free(struct rcu_head *head)
+static void tcf_ct_params_free(struct tcf_ct_params *params)
{
- struct tcf_ct_params *params = container_of(head,
- struct tcf_ct_params, rcu);
-
- tcf_ct_flow_table_put(params);
-
+ if (params->helper) {
+#if IS_ENABLED(CONFIG_NF_NAT)
+ if (params->ct_action & TCA_CT_ACT_NAT)
+ nf_nat_helper_put(params->helper);
+#endif
+ nf_conntrack_helper_put(params->helper);
+ }
+ if (params->ct_ft)
+ tcf_ct_flow_table_put(params->ct_ft);
if (params->tmpl)
nf_ct_put(params->tmpl);
kfree(params);
}
+static void tcf_ct_params_free_rcu(struct rcu_head *head)
+{
+ struct tcf_ct_params *params;
+
+ params = container_of(head, struct tcf_ct_params, rcu);
+ tcf_ct_params_free(params);
+}
+
#if IS_ENABLED(CONFIG_NF_NAT)
/* Modelled after nf_nat_ipv[46]_fn().
* range is only used for new, uninitialized NAT state.
@@ -1023,13 +1042,14 @@ static int tcf_ct_act(struct sk_buff *skb, const struct tc_action *a,
struct tcf_result *res)
{
struct net *net = dev_net(skb->dev);
- bool cached, commit, clear, force;
enum ip_conntrack_info ctinfo;
struct tcf_ct *c = to_ct(a);
struct nf_conn *tmpl = NULL;
struct nf_hook_state state;
+ bool cached, commit, clear;
int nh_ofs, err, retval;
struct tcf_ct_params *p;
+ bool add_helper = false;
bool skip_add = false;
bool defrag = false;
struct nf_conn *ct;
@@ -1040,7 +1060,6 @@ static int tcf_ct_act(struct sk_buff *skb, const struct tc_action *a,
retval = READ_ONCE(c->tcf_action);
commit = p->ct_action & TCA_CT_ACT_COMMIT;
clear = p->ct_action & TCA_CT_ACT_CLEAR;
- force = p->ct_action & TCA_CT_ACT_FORCE;
tmpl = p->tmpl;
tcf_lastuse_update(&c->tcf_tm);
@@ -1083,7 +1102,7 @@ static int tcf_ct_act(struct sk_buff *skb, const struct tc_action *a,
* actually run the packet through conntrack twice unless it's for a
* different zone.
*/
- cached = tcf_ct_skb_nfct_cached(net, skb, p->zone, force);
+ cached = tcf_ct_skb_nfct_cached(net, skb, p);
if (!cached) {
if (tcf_ct_flow_table_lookup(p, skb, family)) {
skip_add = true;
@@ -1116,6 +1135,22 @@ do_nat:
if (err != NF_ACCEPT)
goto drop;
+ if (!nf_ct_is_confirmed(ct) && commit && p->helper && !nfct_help(ct)) {
+ err = __nf_ct_try_assign_helper(ct, p->tmpl, GFP_ATOMIC);
+ if (err)
+ goto drop;
+ add_helper = true;
+ if (p->ct_action & TCA_CT_ACT_NAT && !nfct_seqadj(ct)) {
+ if (!nfct_seqadj_ext_add(ct))
+ goto drop;
+ }
+ }
+
+ if (nf_ct_is_confirmed(ct) ? ((!cached && !skip_add) || add_helper) : commit) {
+ if (nf_ct_helper(skb, ct, ctinfo, family) != NF_ACCEPT)
+ goto drop;
+ }
+
if (commit) {
tcf_ct_act_set_mark(ct, p->mark, p->mark_mask);
tcf_ct_act_set_labels(ct, p->labels, p->labels_mask);
@@ -1164,6 +1199,9 @@ static const struct nla_policy ct_policy[TCA_CT_MAX + 1] = {
[TCA_CT_NAT_IPV6_MAX] = NLA_POLICY_EXACT_LEN(sizeof(struct in6_addr)),
[TCA_CT_NAT_PORT_MIN] = { .type = NLA_U16 },
[TCA_CT_NAT_PORT_MAX] = { .type = NLA_U16 },
+ [TCA_CT_HELPER_NAME] = { .type = NLA_STRING, .len = NF_CT_HELPER_NAME_LEN },
+ [TCA_CT_HELPER_FAMILY] = { .type = NLA_U8 },
+ [TCA_CT_HELPER_PROTO] = { .type = NLA_U8 },
};
static int tcf_ct_fill_params_nat(struct tcf_ct_params *p,
@@ -1253,8 +1291,9 @@ static int tcf_ct_fill_params(struct net *net,
{
struct tc_ct_action_net *tn = net_generic(net, act_ct_ops.net_id);
struct nf_conntrack_zone zone;
+ int err, family, proto, len;
struct nf_conn *tmpl;
- int err;
+ char *name;
p->zone = NF_CT_DEFAULT_ZONE_ID;
@@ -1315,10 +1354,31 @@ static int tcf_ct_fill_params(struct net *net,
NL_SET_ERR_MSG_MOD(extack, "Failed to allocate conntrack template");
return -ENOMEM;
}
- __set_bit(IPS_CONFIRMED_BIT, &tmpl->status);
p->tmpl = tmpl;
+ if (tb[TCA_CT_HELPER_NAME]) {
+ name = nla_data(tb[TCA_CT_HELPER_NAME]);
+ len = nla_len(tb[TCA_CT_HELPER_NAME]);
+ if (len > 16 || name[len - 1] != '\0') {
+ NL_SET_ERR_MSG_MOD(extack, "Failed to parse helper name.");
+ err = -EINVAL;
+ goto err;
+ }
+ family = tb[TCA_CT_HELPER_FAMILY] ? nla_get_u8(tb[TCA_CT_HELPER_FAMILY]) : AF_INET;
+ proto = tb[TCA_CT_HELPER_PROTO] ? nla_get_u8(tb[TCA_CT_HELPER_PROTO]) : IPPROTO_TCP;
+ err = nf_ct_add_helper(tmpl, name, family, proto,
+ p->ct_action & TCA_CT_ACT_NAT, &p->helper);
+ if (err) {
+ NL_SET_ERR_MSG_MOD(extack, "Failed to add helper");
+ goto err;
+ }
+ }
+ __set_bit(IPS_CONFIRMED_BIT, &tmpl->status);
return 0;
+err:
+ nf_ct_put(p->tmpl);
+ p->tmpl = NULL;
+ return err;
}
static int tcf_ct_init(struct net *net, struct nlattr *nla,
@@ -1390,7 +1450,7 @@ static int tcf_ct_init(struct net *net, struct nlattr *nla,
err = tcf_ct_flow_table_get(net, params);
if (err)
- goto cleanup_params;
+ goto cleanup;
spin_lock_bh(&c->tcf_lock);
goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch);
@@ -1401,17 +1461,15 @@ static int tcf_ct_init(struct net *net, struct nlattr *nla,
if (goto_ch)
tcf_chain_put_by_act(goto_ch);
if (params)
- call_rcu(&params->rcu, tcf_ct_params_free);
+ call_rcu(&params->rcu, tcf_ct_params_free_rcu);
return res;
-cleanup_params:
- if (params->tmpl)
- nf_ct_put(params->tmpl);
cleanup:
if (goto_ch)
tcf_chain_put_by_act(goto_ch);
- kfree(params);
+ if (params)
+ tcf_ct_params_free(params);
tcf_idr_release(*a, bind);
return err;
}
@@ -1423,7 +1481,7 @@ static void tcf_ct_cleanup(struct tc_action *a)
params = rcu_dereference_protected(c->params, 1);
if (params)
- call_rcu(&params->rcu, tcf_ct_params_free);
+ call_rcu(&params->rcu, tcf_ct_params_free_rcu);
}
static int tcf_ct_dump_key_val(struct sk_buff *skb,
@@ -1489,6 +1547,19 @@ static int tcf_ct_dump_nat(struct sk_buff *skb, struct tcf_ct_params *p)
return 0;
}
+static int tcf_ct_dump_helper(struct sk_buff *skb, struct nf_conntrack_helper *helper)
+{
+ if (!helper)
+ return 0;
+
+ if (nla_put_string(skb, TCA_CT_HELPER_NAME, helper->name) ||
+ nla_put_u8(skb, TCA_CT_HELPER_FAMILY, helper->tuple.src.l3num) ||
+ nla_put_u8(skb, TCA_CT_HELPER_PROTO, helper->tuple.dst.protonum))
+ return -1;
+
+ return 0;
+}
+
static inline int tcf_ct_dump(struct sk_buff *skb, struct tc_action *a,
int bind, int ref)
{
@@ -1541,6 +1612,9 @@ static inline int tcf_ct_dump(struct sk_buff *skb, struct tc_action *a,
if (tcf_ct_dump_nat(skb, p))
goto nla_put_failure;
+ if (tcf_ct_dump_helper(skb, p->helper))
+ goto nla_put_failure;
+
skip_dump:
if (nla_put(skb, TCA_CT_PARMS, sizeof(opt), &opt))
goto nla_put_failure;
diff --git a/net/sched/act_skbedit.c b/net/sched/act_skbedit.c
index 7f598784fd30..1710780c908a 100644
--- a/net/sched/act_skbedit.c
+++ b/net/sched/act_skbedit.c
@@ -148,6 +148,11 @@ static int tcf_skbedit_init(struct net *net, struct nlattr *nla,
}
if (tb[TCA_SKBEDIT_QUEUE_MAPPING] != NULL) {
+ if (is_tcf_skbedit_ingress(act_flags) &&
+ !(act_flags & TCA_ACT_FLAGS_SKIP_SW)) {
+ NL_SET_ERR_MSG_MOD(extack, "\"queue_mapping\" option on receive side is hardware only, use skip_sw");
+ return -EOPNOTSUPP;
+ }
flags |= SKBEDIT_F_QUEUE_MAPPING;
queue_mapping = nla_data(tb[TCA_SKBEDIT_QUEUE_MAPPING]);
}
@@ -374,9 +379,12 @@ static int tcf_skbedit_offload_act_setup(struct tc_action *act, void *entry_data
} else if (is_tcf_skbedit_priority(act)) {
entry->id = FLOW_ACTION_PRIORITY;
entry->priority = tcf_skbedit_priority(act);
- } else if (is_tcf_skbedit_queue_mapping(act)) {
- NL_SET_ERR_MSG_MOD(extack, "Offload not supported when \"queue_mapping\" option is used");
+ } else if (is_tcf_skbedit_tx_queue_mapping(act)) {
+ NL_SET_ERR_MSG_MOD(extack, "Offload not supported when \"queue_mapping\" option is used on transmit side");
return -EOPNOTSUPP;
+ } else if (is_tcf_skbedit_rx_queue_mapping(act)) {
+ entry->id = FLOW_ACTION_RX_QUEUE_MAPPING;
+ entry->rx_queue = tcf_skbedit_rx_queue_mapping(act);
} else if (is_tcf_skbedit_inheritdsfield(act)) {
NL_SET_ERR_MSG_MOD(extack, "Offload not supported when \"inheritdsfield\" option is used");
return -EOPNOTSUPP;
@@ -394,6 +402,8 @@ static int tcf_skbedit_offload_act_setup(struct tc_action *act, void *entry_data
fl_action->id = FLOW_ACTION_PTYPE;
else if (is_tcf_skbedit_priority(act))
fl_action->id = FLOW_ACTION_PRIORITY;
+ else if (is_tcf_skbedit_rx_queue_mapping(act))
+ fl_action->id = FLOW_ACTION_RX_QUEUE_MAPPING;
else
return -EOPNOTSUPP;
}
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index 50566db45949..23d1cfa4f58c 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -1953,6 +1953,11 @@ static void tfilter_put(struct tcf_proto *tp, void *fh)
tp->ops->put(tp, fh);
}
+static bool is_qdisc_ingress(__u32 classid)
+{
+ return (TC_H_MIN(classid) == TC_H_MIN(TC_H_MIN_INGRESS));
+}
+
static int tc_new_tfilter(struct sk_buff *skb, struct nlmsghdr *n,
struct netlink_ext_ack *extack)
{
@@ -2144,6 +2149,8 @@ replay:
flags |= TCA_ACT_FLAGS_REPLACE;
if (!rtnl_held)
flags |= TCA_ACT_FLAGS_NO_RTNL;
+ if (is_qdisc_ingress(parent))
+ flags |= TCA_ACT_FLAGS_AT_INGRESS;
err = tp->ops->change(net, skb, tp, cl, t->tcm_handle, tca, &fh,
flags, extack);
if (err == 0) {
generated by cgit v1.2.3-70-g09d2 (git 2.47.1) at 2025-01-14 06:02:46 +0000