@@ -239,6 +239,29 @@ int tcf_action_check_ctrlact(int action, struct tcf_proto *tp,
struct netlink_ext_ack *newchain);
struct tcf_chain *tcf_action_set_ctrlact(struct tc_action *a, int action,
struct tcf_chain *newchain);
+
+#if IS_ENABLED(CONFIG_NET_ACT_FRAG)
+int tcf_exec_frag_xmit_hook(struct sk_buff *skb, int (*xmit)(struct sk_buff *skb));
+void tcf_set_frag_xmit_hook(void);
+void tcf_clear_frag_xmit_hook(void);
+bool tcf_frag_xmit_hook_enabled(void);
+#else
+static inline int tcf_exec_frag_xmit_hook(struct sk_buff *skb, int (*xmit)(struct sk_buff *skb))
+{
+ return 0;
+}
+static inline void tcf_set_frag_xmit_hook(void)
+{
+}
+static inline void tcf_clear_frag_xmit_hook(void)
+{
+}
+static inline bool tcf_frag_xmit_hook_enabled(void)
+{
+ return false;
+}
+#endif
+
#endif /* CONFIG_NET_CLS_ACT */
static inline void tcf_action_stats_update(struct tc_action *a, u64 bytes,
@@ -974,9 +974,21 @@ config NET_ACT_TUNNEL_KEY
To compile this code as a module, choose M here: the
module will be called act_tunnel_key.
+config NET_ACT_FRAG
+ tristate "send packets do frag"
+ depends on NET_CLS_ACT
+ help
+ Say Y here to allow sending the packets to do frag
+
+ If unsure, say N.
+
+ To compile this code as a module, choose M here: the
+ module will be called act_frag.
+
config NET_ACT_CT
tristate "connection tracking tc action"
depends on NET_CLS_ACT && NF_CONNTRACK && NF_NAT && NF_FLOW_TABLE
+ depends on NET_ACT_FRAG
help
Say Y here to allow sending the packets to conntrack module.
@@ -29,6 +29,7 @@ obj-$(CONFIG_NET_IFE_SKBMARK) += act_meta_mark.o
obj-$(CONFIG_NET_IFE_SKBPRIO) += act_meta_skbprio.o
obj-$(CONFIG_NET_IFE_SKBTCINDEX) += act_meta_skbtcindex.o
obj-$(CONFIG_NET_ACT_TUNNEL_KEY)+= act_tunnel_key.o
+obj-$(CONFIG_NET_ACT_FRAG) += act_frag.o
obj-$(CONFIG_NET_ACT_CT) += act_ct.o
obj-$(CONFIG_NET_ACT_GATE) += act_gate.o
obj-$(CONFIG_NET_SCH_FIFO) += sch_fifo.o
@@ -1541,6 +1541,8 @@ static int __init ct_init_module(void)
if (err)
goto err_register;
+ tcf_set_frag_xmit_hook();
+
return 0;
err_register:
@@ -1552,6 +1554,7 @@ static int __init ct_init_module(void)
static void __exit ct_cleanup_module(void)
{
+ tcf_clear_frag_xmit_hook();
tcf_unregister_action(&act_ct_ops, &ct_net_ops);
tcf_ct_flow_tables_uninit();
destroy_workqueue(act_ct_wq);
new file mode 100644
@@ -0,0 +1,207 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+#include <net/netlink.h>
+#include <net/act_api.h>
+#include <net/dst.h>
+#include <net/ip.h>
+#include <net/ip6_fib.h>
+
+static int tcf_frag_hook(struct sk_buff *skb, int (*xmit)(struct sk_buff *skb));
+
+static int (*tcf_frag_xmit_hook)(struct sk_buff *skb,
+ int (*xmit)(struct sk_buff *skb));
+static DEFINE_STATIC_KEY_FALSE(tcf_frag_xmit_hook_in_use);
+
+static void tcf_inc_frag_xmit_hook(void)
+{
+ static_branch_inc(&tcf_frag_xmit_hook_in_use);
+}
+
+static void tcf_dec_frag_xmit_hook(void)
+{
+ static_branch_dec(&tcf_frag_xmit_hook_in_use);
+}
+
+bool tcf_frag_xmit_hook_enabled(void)
+{
+ return static_branch_unlikely(&tcf_frag_xmit_hook_in_use);
+}
+EXPORT_SYMBOL_GPL(tcf_frag_xmit_hook_enabled);
+
+void tcf_set_frag_xmit_hook(void)
+{
+ if (!tcf_frag_xmit_hook_enabled())
+ tcf_frag_xmit_hook = tcf_frag_hook;
+
+ tcf_inc_frag_xmit_hook();
+}
+EXPORT_SYMBOL_GPL(tcf_set_frag_xmit_hook);
+
+void tcf_clear_frag_xmit_hook(void)
+{
+ tcf_dec_frag_xmit_hook();
+
+ if (!tcf_frag_xmit_hook_enabled())
+ tcf_frag_xmit_hook = NULL;
+}
+EXPORT_SYMBOL_GPL(tcf_clear_frag_xmit_hook);
+
+int tcf_exec_frag_xmit_hook(struct sk_buff *skb, int (*xmit)(struct sk_buff *skb))
+{
+ return tcf_frag_xmit_hook(skb, xmit);
+}
+EXPORT_SYMBOL_GPL(tcf_exec_frag_xmit_hook);
+
+struct tcf_frag_data {
+ unsigned long dst;
+ struct qdisc_skb_cb cb;
+ __be16 inner_protocol;
+ u16 vlan_tci;
+ __be16 vlan_proto;
+ unsigned int l2_len;
+ u8 l2_data[VLAN_ETH_HLEN];
+ int (*xmit)(struct sk_buff *skb);
+};
+
+static DEFINE_PER_CPU(struct tcf_frag_data, tcf_frag_data_storage);
+
+static int tcf_frag_xmit(struct net *net, struct sock *sk, struct sk_buff *skb)
+{
+ struct tcf_frag_data *data = this_cpu_ptr(&tcf_frag_data_storage);
+
+ if (skb_cow_head(skb, data->l2_len) < 0) {
+ kfree_skb(skb);
+ return -ENOMEM;
+ }
+
+ __skb_dst_copy(skb, data->dst);
+ *qdisc_skb_cb(skb) = data->cb;
+ skb->inner_protocol = data->inner_protocol;
+ if (data->vlan_tci & VLAN_CFI_MASK)
+ __vlan_hwaccel_put_tag(skb, data->vlan_proto, data->vlan_tci & ~VLAN_CFI_MASK);
+ else
+ __vlan_hwaccel_clear_tag(skb);
+
+ /* Reconstruct the MAC header. */
+ skb_push(skb, data->l2_len);
+ memcpy(skb->data, &data->l2_data, data->l2_len);
+ skb_postpush_rcsum(skb, skb->data, data->l2_len);
+ skb_reset_mac_header(skb);
+
+ data->xmit(skb);
+
+ return 0;
+}
+
+static void tcf_frag_prepare_frag(struct sk_buff *skb,
+ int (*xmit)(struct sk_buff *skb))
+{
+ unsigned int hlen = skb_network_offset(skb);
+ struct tcf_frag_data *data;
+
+ data = this_cpu_ptr(&tcf_frag_data_storage);
+ data->dst = skb->_skb_refdst;
+ data->cb = *qdisc_skb_cb(skb);
+ data->xmit = xmit;
+ data->inner_protocol = skb->inner_protocol;
+ if (skb_vlan_tag_present(skb))
+ data->vlan_tci = skb_vlan_tag_get(skb) | VLAN_CFI_MASK;
+ else
+ data->vlan_tci = 0;
+ data->vlan_proto = skb->vlan_proto;
+ data->l2_len = hlen;
+ memcpy(&data->l2_data, skb->data, hlen);
+
+ memset(IPCB(skb), 0, sizeof(struct inet_skb_parm));
+ skb_pull(skb, hlen);
+}
+
+static unsigned int
+tcf_frag_dst_get_mtu(const struct dst_entry *dst)
+{
+ return dst->dev->mtu;
+}
+
+static struct dst_ops tcf_frag_dst_ops = {
+ .family = AF_UNSPEC,
+ .mtu = tcf_frag_dst_get_mtu,
+};
+
+static int tcf_fragment(struct net *net, struct sk_buff *skb,
+ u16 mru, int (*xmit)(struct sk_buff *skb))
+{
+ if (skb_network_offset(skb) > VLAN_ETH_HLEN) {
+ net_warn_ratelimited("L2 header too long to fragment\n");
+ goto err;
+ }
+
+ if (skb->protocol == htons(ETH_P_IP)) {
+ struct dst_entry tcf_frag_dst;
+ unsigned long orig_dst;
+
+ tcf_frag_prepare_frag(skb, xmit);
+ dst_init(&tcf_frag_dst, &tcf_frag_dst_ops, NULL, 1,
+ DST_OBSOLETE_NONE, DST_NOCOUNT);
+ tcf_frag_dst.dev = skb->dev;
+
+ orig_dst = skb->_skb_refdst;
+ skb_dst_set_noref(skb, &tcf_frag_dst);
+ IPCB(skb)->frag_max_size = mru;
+
+ ip_do_fragment(net, skb->sk, skb, tcf_frag_xmit);
+ refdst_drop(orig_dst);
+ } else if (skb->protocol == htons(ETH_P_IPV6)) {
+ unsigned long orig_dst;
+ struct rt6_info tcf_frag_rt;
+
+ tcf_frag_prepare_frag(skb, xmit);
+ memset(&tcf_frag_rt, 0, sizeof(tcf_frag_rt));
+ dst_init(&tcf_frag_rt.dst, &tcf_frag_dst_ops, NULL, 1,
+ DST_OBSOLETE_NONE, DST_NOCOUNT);
+ tcf_frag_rt.dst.dev = skb->dev;
+
+ orig_dst = skb->_skb_refdst;
+ skb_dst_set_noref(skb, &tcf_frag_rt.dst);
+ IP6CB(skb)->frag_max_size = mru;
+
+ ipv6_stub->ipv6_fragment(net, skb->sk, skb, tcf_frag_xmit);
+ refdst_drop(orig_dst);
+ } else {
+ net_warn_ratelimited("Failed fragment ->%s: eth=%04x, MRU=%d, MTU=%d.\n",
+ netdev_name(skb->dev), ntohs(skb->protocol),
+ mru, skb->dev->mtu);
+ goto err;
+ }
+
+ qdisc_skb_cb(skb)->mru = 0;
+ return 0;
+err:
+ kfree_skb(skb);
+ return -1;
+}
+
+static int tcf_frag_hook(struct sk_buff *skb, int (*xmit)(struct sk_buff *skb))
+{
+ u16 mru = qdisc_skb_cb(skb)->mru;
+ int err;
+
+ if (mru && skb->len > mru + skb->dev->hard_header_len)
+ err = tcf_fragment(dev_net(skb->dev), skb, mru, xmit);
+ else
+ err = xmit(skb);
+
+ return err;
+}
+
+static int __init frag_init_module(void)
+{
+ return 0;
+}
+
+static void __exit frag_cleanup_module(void)
+{
+}
+
+module_init(frag_init_module);
+module_exit(frag_cleanup_module);
+MODULE_AUTHOR("wenxu <wenxu@ucloud.cn>");
+MODULE_LICENSE("GPL v2");
@@ -209,10 +209,14 @@ static int tcf_mirred_forward(bool want_ingress, struct sk_buff *skb)
{
int err;
- if (!want_ingress)
- err = dev_queue_xmit(skb);
- else
+ if (!want_ingress) {
+ if (tcf_frag_xmit_hook_enabled())
+ err = tcf_exec_frag_xmit_hook(skb, dev_queue_xmit);
+ else
+ err = dev_queue_xmit(skb);
+ } else {
err = netif_receive_skb(skb);
+ }
return err;
}