[PATCH bpf-next v3 3/4] bpf: add bpf_icmp_send_unreach cgroup_skb kfunc

[Mahe Tardy <mahe.tardy@gmail.com>]

This is needed in the context of Tetragon to provide improved feedback
(in contrast to just dropping packets) to east-west traffic when blocked
by policies using cgroup_skb programs.

This reuse concepts from netfilter reject target codepath with the
differences that:
* Packets are cloned since the BPF user can still return SK_PASS from
  the cgroup_skb progs and the current skb need to stay untouched
  (cgroup_skb hooks only allow read-only skb payload).
* Since cgroup_skb programs are called late in the stack, checksums do
  not need to be computed or verified, and IPv4 fragmentation does not
  need to be checked (ip_local_deliver should take care of that
  earlier).

Signed-off-by: Mahe Tardy <mahe.tardy@gmail.com>
---
 net/core/filter.c | 61 +++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 61 insertions(+)

diff --git a/net/core/filter.c b/net/core/filter.c
index 7a72f766aacf..050872324575 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -85,6 +85,10 @@
 #include <linux/un.h>
 #include <net/xdp_sock_drv.h>
 #include <net/inet_dscp.h>
+#include <linux/icmp.h>
+#include <net/icmp.h>
+#include <net/route.h>
+#include <net/ip6_route.h>

 #include "dev.h"

@@ -12148,6 +12152,53 @@ __bpf_kfunc int bpf_sock_ops_enable_tx_tstamp(struct bpf_sock_ops_kern *skops,
 	return 0;
 }

+__bpf_kfunc int bpf_icmp_send_unreach(struct __sk_buff *__skb, int code)
+{
+	struct sk_buff *skb = (struct sk_buff *)__skb;
+	struct sk_buff *nskb;
+
+	switch (skb->protocol) {
+	case htons(ETH_P_IP):
+		if (code < 0 || code > NR_ICMP_UNREACH)
+			return -EINVAL;
+
+		nskb = skb_clone(skb, GFP_ATOMIC);
+		if (!nskb)
+			return -ENOMEM;
+
+		if (ip_route_reply_fetch_dst(nskb) < 0) {
+			kfree_skb(nskb);
+			return -EHOSTUNREACH;
+		}
+
+		icmp_send(nskb, ICMP_DEST_UNREACH, code, 0);
+		kfree_skb(nskb);
+		break;
+#if IS_ENABLED(CONFIG_IPV6)
+	case htons(ETH_P_IPV6):
+		if (code < 0 || code > ICMPV6_REJECT_ROUTE)
+			return -EINVAL;
+
+		nskb = skb_clone(skb, GFP_ATOMIC);
+		if (!nskb)
+			return -ENOMEM;
+
+		if (ip6_route_reply_fetch_dst(nskb) < 0) {
+			kfree_skb(nskb);
+			return -EHOSTUNREACH;
+		}
+
+		icmpv6_send(nskb, ICMPV6_DEST_UNREACH, code, 0);
+		kfree_skb(nskb);
+		break;
+#endif
+	default:
+		return -EPROTONOSUPPORT;
+	}
+
+	return SK_DROP;
+}
+
 __bpf_kfunc_end_defs();

 int bpf_dynptr_from_skb_rdonly(struct __sk_buff *skb, u64 flags,
@@ -12185,6 +12236,10 @@ BTF_KFUNCS_START(bpf_kfunc_check_set_sock_ops)
 BTF_ID_FLAGS(func, bpf_sock_ops_enable_tx_tstamp, KF_TRUSTED_ARGS)
 BTF_KFUNCS_END(bpf_kfunc_check_set_sock_ops)

+BTF_KFUNCS_START(bpf_kfunc_check_set_icmp_send_unreach)
+BTF_ID_FLAGS(func, bpf_icmp_send_unreach, KF_TRUSTED_ARGS)
+BTF_KFUNCS_END(bpf_kfunc_check_set_icmp_send_unreach)
+
 static const struct btf_kfunc_id_set bpf_kfunc_set_skb = {
 	.owner = THIS_MODULE,
 	.set = &bpf_kfunc_check_set_skb,
@@ -12210,6 +12265,11 @@ static const struct btf_kfunc_id_set bpf_kfunc_set_sock_ops = {
 	.set = &bpf_kfunc_check_set_sock_ops,
 };

+static const struct btf_kfunc_id_set bpf_kfunc_set_icmp_send_unreach = {
+	.owner = THIS_MODULE,
+	.set = &bpf_kfunc_check_set_icmp_send_unreach,
+};
+
 static int __init bpf_kfunc_init(void)
 {
 	int ret;
@@ -12229,6 +12289,7 @@ static int __init bpf_kfunc_init(void)
 	ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_CGROUP_SOCK_ADDR,
 					       &bpf_kfunc_set_sock_addr);
 	ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_SCHED_CLS, &bpf_kfunc_set_tcp_reqsk);
+	ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_CGROUP_SKB, &bpf_kfunc_set_icmp_send_unreach);
 	return ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_SOCK_OPS, &bpf_kfunc_set_sock_ops);
 }
 late_initcall(bpf_kfunc_init);
--
2.34.1