diff --git a/include/net/act_api.h b/include/net/act_api.h
index 87214927314a1ed2f084b43b4e227263f2079225..55dab604861fe5f3afa41c25dbd0b2222596d8d4 100644
--- a/include/net/act_api.h
+++ b/include/net/act_api.h
@@ -239,6 +239,12 @@ 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);
+
+#ifdef CONFIG_INET
+DECLARE_STATIC_KEY_FALSE(tcf_frag_xmit_count);
+#endif
+
+int tcf_dev_queue_xmit(struct sk_buff *skb, int (*xmit)(struct sk_buff *skb));
#endif /* CONFIG_NET_CLS_ACT */
static inline void tcf_action_stats_update(struct tc_action *a, u64 bytes,
diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index d8fd8676fc724110630904909f64d7789f3a4b47..162ed6249e8ba1d45ca377372210b3206e20cdef 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -1281,9 +1281,6 @@ void mini_qdisc_pair_init(struct mini_Qdisc_pair *miniqp, struct Qdisc *qdisc,
void mini_qdisc_pair_block_init(struct mini_Qdisc_pair *miniqp,
struct tcf_block *block);
-static inline int skb_tc_reinsert(struct sk_buff *skb, struct tcf_result *res)
-{
- return res->ingress ? netif_receive_skb(skb) : dev_queue_xmit(skb);
-}
+int sch_frag_xmit_hook(struct sk_buff *skb, int (*xmit)(struct sk_buff *skb));
#endif
diff --git a/net/core/dev.c b/net/core/dev.c
index 3c3070d9d26f8b362144b50f79513b0a9a956374..51b2630761241bf043e2db1d940bcf93fd4e9032 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -3872,6 +3872,7 @@ sch_handle_egress(struct sk_buff *skb, int *ret, struct net_device *dev)
return skb;
/* qdisc_skb_cb(skb)->pkt_len was already set by the caller. */
+ qdisc_skb_cb(skb)->mru = 0;
mini_qdisc_bstats_cpu_update(miniq, skb);
switch (tcf_classify(skb, miniq->filter_list, &cl_res, false)) {
@@ -4959,6 +4960,7 @@ sch_handle_ingress(struct sk_buff *skb, struct packet_type **pt_prev, int *ret,
}
qdisc_skb_cb(skb)->pkt_len = skb->len;
+ qdisc_skb_cb(skb)->mru = 0;
skb->tc_at_ingress = 1;
mini_qdisc_bstats_cpu_update(miniq, skb);
diff --git a/net/sched/Makefile b/net/sched/Makefile
index 66bbf9a98f9ea123edd69c84615b37266d537fed..dd14ef413fdad72b6d32354ade81f9019968e8c4 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 99db1c77426b385e34addbc567509096e0aa2768..2e85b636b27bd53e46b0124d54bce72283ac1167 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 aba3cd85f284f3e49add31fe65e3b791f2386fa1..61092c5d646ce4908663570d65759c999e005481 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 @@ static int __init ct_init_module(void)
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 e24b7e2331cdd24e0d6e1b70bde274767165927f..7153c67f641e1778b2661582e2f58cdb4c6d5a40 100644
--- a/net/sched/act_mirred.c
+++ b/net/sched/act_mirred.c
@@ -205,6 +205,18 @@ static int tcf_mirred_init(struct net *net, struct nlattr *nla,
return err;
}
+static int tcf_mirred_forward(bool want_ingress, struct sk_buff *skb)
+{
+ int err;
+
+ if (!want_ingress)
+ err = tcf_dev_queue_xmit(skb, dev_queue_xmit);
+ else
+ err = netif_receive_skb(skb);
+
+ return err;
+}
+
static int tcf_mirred_act(struct sk_buff *skb, const struct tc_action *a,
struct tcf_result *res)
{
@@ -287,18 +299,15 @@ static int tcf_mirred_act(struct sk_buff *skb, const struct tc_action *a,
/* let's the caller reinsert the packet, if possible */
if (use_reinsert) {
res->ingress = want_ingress;
- if (skb_tc_reinsert(skb, res))
+ err = tcf_mirred_forward(res->ingress, skb);
+ if (err)
tcf_action_inc_overlimit_qstats(&m->common);
__this_cpu_dec(mirred_rec_level);
return TC_ACT_CONSUMED;
}
}
- if (!want_ingress)
- err = dev_queue_xmit(skb2);
- else
- err = netif_receive_skb(skb2);
-
+ err = tcf_mirred_forward(want_ingress, skb2);
if (err) {
out:
tcf_action_inc_overlimit_qstats(&m->common);
diff --git a/net/sched/sch_frag.c b/net/sched/sch_frag.c
new file mode 100644
index 0000000000000000000000000000000000000000..e1e77d3fb6c021eec19476e812f026e739d2eb9a
--- /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);