net/sched: sch_frag: add generic packet fragment support.

Currently kernel tc subsystem can do conntrack in cat_ct. But when several
fragment packets go through the act_ct, function tcf_ct_handle_fragments
will defrag the packets to a big one. But the last action will redirect
mirred to a device which maybe lead the reassembly big packet over the mtu
of target device.

This patch add support for a xmit hook to mirred, that gets executed before
xmiting the packet. Then, when act_ct gets loaded, it configs that hook.
The frag xmit hook maybe reused by other modules.

Signed-off-by: wenxu <wenxu@ucloud.cn>
Acked-by: Cong Wang <cong.wang@bytedance.com>
Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

5 files changed, 171 insertions, 1 deletions

diff --git a/net/sched/Makefile b/net/sched/Makefile
index 66bbf9a98f9e..dd14ef413fda 100644
--- a/net/sched/Makefile
+++ b/net/sched/Makefile
@@ -5,6 +5,7 @@
 
 obj-y	:= sch_generic.o sch_mq.o
 
+obj-$(CONFIG_INET)		+= sch_frag.o
 obj-$(CONFIG_NET_SCHED)		+= sch_api.o sch_blackhole.o
 obj-$(CONFIG_NET_CLS)		+= cls_api.o
 obj-$(CONFIG_NET_CLS_ACT)	+= act_api.o
diff --git a/net/sched/act_api.c b/net/sched/act_api.c
index 99db1c77426b..2e85b636b27b 100644
--- a/net/sched/act_api.c
+++ b/net/sched/act_api.c
@@ -22,6 +22,22 @@
 #include <net/act_api.h>
 #include <net/netlink.h>
 
+#ifdef CONFIG_INET
+DEFINE_STATIC_KEY_FALSE(tcf_frag_xmit_count);
+EXPORT_SYMBOL_GPL(tcf_frag_xmit_count);
+#endif
+
+int tcf_dev_queue_xmit(struct sk_buff *skb, int (*xmit)(struct sk_buff *skb))
+{
+#ifdef CONFIG_INET
+	if (static_branch_unlikely(&tcf_frag_xmit_count))
+		return sch_frag_xmit_hook(skb, xmit);
+#endif
+
+	return xmit(skb);
+}
+EXPORT_SYMBOL_GPL(tcf_dev_queue_xmit);
+
 static void tcf_action_goto_chain_exec(const struct tc_action *a,
 				       struct tcf_result *res)
 {
diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c
index aba3cd85f284..61092c5d646c 100644
--- a/net/sched/act_ct.c
+++ b/net/sched/act_ct.c
@@ -1541,6 +1541,8 @@ static int __init ct_init_module(void)
 	if (err)
 		goto err_register;
 
+	static_branch_inc(&tcf_frag_xmit_count);
+
 	return 0;
 
 err_register:
@@ -1552,6 +1554,7 @@ err_tbl_init:
 
 static void __exit ct_cleanup_module(void)
 {
+	static_branch_dec(&tcf_frag_xmit_count);
 	tcf_unregister_action(&act_ct_ops, &ct_net_ops);
 	tcf_ct_flow_tables_uninit();
 	destroy_workqueue(act_ct_wq);
diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c
index 17d00958047e..7153c67f641e 100644
--- a/net/sched/act_mirred.c
+++ b/net/sched/act_mirred.c
@@ -210,7 +210,7 @@ static int tcf_mirred_forward(bool want_ingress, struct sk_buff *skb)
 	int err;
 
 	if (!want_ingress)
-		err = dev_queue_xmit(skb);
+		err = tcf_dev_queue_xmit(skb, dev_queue_xmit);
 	else
 		err = netif_receive_skb(skb);
 
diff --git a/net/sched/sch_frag.c b/net/sched/sch_frag.c
new file mode 100644
index 000000000000..e1e77d3fb6c0
--- /dev/null
+++ b/net/sched/sch_frag.c
@@ -0,0 +1,150 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+#include <net/netlink.h>
+#include <net/sch_generic.h>
+#include <net/dst.h>
+#include <net/ip.h>
+#include <net/ip6_fib.h>
+
+struct sch_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 sch_frag_data, sch_frag_data_storage);
+
+static int sch_frag_xmit(struct net *net, struct sock *sk, struct sk_buff *skb)
+{
+	struct sch_frag_data *data = this_cpu_ptr(&sch_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);
+
+	return data->xmit(skb);
+}
+
+static void sch_frag_prepare_frag(struct sk_buff *skb,
+				  int (*xmit)(struct sk_buff *skb))
+{
+	unsigned int hlen = skb_network_offset(skb);
+	struct sch_frag_data *data;
+
+	data = this_cpu_ptr(&sch_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
+sch_frag_dst_get_mtu(const struct dst_entry *dst)
+{
+	return dst->dev->mtu;
+}
+
+static struct dst_ops sch_frag_dst_ops = {
+	.family = AF_UNSPEC,
+	.mtu = sch_frag_dst_get_mtu,
+};
+
+static int sch_fragment(struct net *net, struct sk_buff *skb,
+			u16 mru, int (*xmit)(struct sk_buff *skb))
+{
+	int ret = -1;
+
+	if (skb_network_offset(skb) > VLAN_ETH_HLEN) {
+		net_warn_ratelimited("L2 header too long to fragment\n");
+		goto err;
+	}
+
+	if (skb_protocol(skb, true) == htons(ETH_P_IP)) {
+		struct dst_entry sch_frag_dst;
+		unsigned long orig_dst;
+
+		sch_frag_prepare_frag(skb, xmit);
+		dst_init(&sch_frag_dst, &sch_frag_dst_ops, NULL, 1,
+			 DST_OBSOLETE_NONE, DST_NOCOUNT);
+		sch_frag_dst.dev = skb->dev;
+
+		orig_dst = skb->_skb_refdst;
+		skb_dst_set_noref(skb, &sch_frag_dst);
+		IPCB(skb)->frag_max_size = mru;
+
+		ret = ip_do_fragment(net, skb->sk, skb, sch_frag_xmit);
+		refdst_drop(orig_dst);
+	} else if (skb_protocol(skb, true) == htons(ETH_P_IPV6)) {
+		unsigned long orig_dst;
+		struct rt6_info sch_frag_rt;
+
+		sch_frag_prepare_frag(skb, xmit);
+		memset(&sch_frag_rt, 0, sizeof(sch_frag_rt));
+		dst_init(&sch_frag_rt.dst, &sch_frag_dst_ops, NULL, 1,
+			 DST_OBSOLETE_NONE, DST_NOCOUNT);
+		sch_frag_rt.dst.dev = skb->dev;
+
+		orig_dst = skb->_skb_refdst;
+		skb_dst_set_noref(skb, &sch_frag_rt.dst);
+		IP6CB(skb)->frag_max_size = mru;
+
+		ret = ipv6_stub->ipv6_fragment(net, skb->sk, skb,
+					       sch_frag_xmit);
+		refdst_drop(orig_dst);
+	} else {
+		net_warn_ratelimited("Fail frag %s: eth=%x, MRU=%d, MTU=%d\n",
+				     netdev_name(skb->dev),
+				     ntohs(skb_protocol(skb, true)), mru,
+				     skb->dev->mtu);
+		goto err;
+	}
+
+	return ret;
+err:
+	kfree_skb(skb);
+	return ret;
+}
+
+int sch_frag_xmit_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 = sch_fragment(dev_net(skb->dev), skb, mru, xmit);
+	else
+		err = xmit(skb);
+
+	return err;
+}
+EXPORT_SYMBOL_GPL(sch_frag_xmit_hook);