Merge branch 'support-defragmenting-ipv-4-6-packets-in-bpf'

Daniel Xu says:

====================
Support defragmenting IPv(4|6) packets in BPF

=== Context ===

In the context of a middlebox, fragmented packets are tricky to handle.
The full 5-tuple of a packet is often only available in the first
fragment which makes enforcing consistent policy difficult. There are
really only two stateless options, neither of which are very nice:

1. Enforce policy on first fragment and accept all subsequent fragments.
   This works but may let in certain attacks or allow data exfiltration.

2. Enforce policy on first fragment and drop all subsequent fragments.
   This does not really work b/c some protocols may rely on
   fragmentation. For example, DNS may rely on oversized UDP packets for
   large responses.

So stateful tracking is the only sane option. RFC 8900 [0] calls this
out as well in section 6.3:

    Middleboxes [...] should process IP fragments in a manner that is
    consistent with [RFC0791] and [RFC8200]. In many cases, middleboxes
    must maintain state in order to achieve this goal.

=== BPF related bits ===

Policy has traditionally been enforced from XDP/TC hooks. Both hooks
run before kernel reassembly facilities. However, with the new
BPF_PROG_TYPE_NETFILTER, we can rather easily hook into existing
netfilter reassembly infra.

The basic idea is we bump a refcnt on the netfilter defrag module and
then run the bpf prog after the defrag module runs. This allows bpf
progs to transparently see full, reassembled packets. The nice thing
about this is that progs don't have to carry around logic to detect
fragments.

=== Changelog ===

Changes from v5:

* Fix defrag disable codepaths

Changes from v4:

* Refactor module handling code to not sleep in rcu_read_lock()
* Also unify the v4 and v6 hook structs so they can share codepaths
* Fixed some checkpatch.pl formatting warnings

Changes from v3:

* Correctly initialize `addrlen` stack var for recvmsg()

Changes from v2:

* module_put() if ->enable() fails
* Fix CI build errors

Changes from v1:

* Drop bpf_program__attach_netfilter() patches
* static -> static const where appropriate
* Fix callback assignment order during registration
* Only request_module() if callbacks are missing
* Fix retval when modprobe fails in userspace
* Fix v6 defrag module name (nf_defrag_ipv6_hooks -> nf_defrag_ipv6)
* Simplify priority checking code
* Add warning if module doesn't assign callbacks in the future
* Take refcnt on module while defrag link is active

[0]: https://datatracker.ietf.org/doc/html/rfc8900
====================

Link: https://lore.kernel.org/r/cover.1689970773.git.dxu@dxuuu.xyzSigned-off-by: Alexei Starovoitov <ast@kernel.org>

include/linux/netfilter.h

@@ -11,6 +11,7 @@
 #include <linux/wait.h>
 #include <linux/list.h>
 #include <linux/static_key.h>
+#include <linux/module.h>
 #include <linux/netfilter_defs.h>
 #include <linux/netdevice.h>
 #include <linux/sockptr.h>
@@ -481,6 +482,15 @@ struct nfnl_ct_hook {
 };
 extern const struct nfnl_ct_hook __rcu *nfnl_ct_hook;
 
+struct nf_defrag_hook {
+	struct module *owner;
+	int (*enable)(struct net *net);
+	void (*disable)(struct net *net);
+};
+
+extern const struct nf_defrag_hook __rcu *nf_defrag_v4_hook;
+extern const struct nf_defrag_hook __rcu *nf_defrag_v6_hook;
+
 /*
  * nf_skb_duplicated - TEE target has sent a packet
  *

include/uapi/linux/bpf.h

@@ -1188,6 +1188,11 @@ enum bpf_perf_event_type {
  */
 #define BPF_F_KPROBE_MULTI_RETURN	(1U << 0)
 
+/* link_create.netfilter.flags used in LINK_CREATE command for
+ * BPF_PROG_TYPE_NETFILTER to enable IP packet defragmentation.
+ */
+#define BPF_F_NETFILTER_IP_DEFRAG (1U << 0)
+
 /* When BPF ldimm64's insn[0].src_reg != 0 then this can have
  * the following extensions:
  *

net/ipv4/netfilter/nf_defrag_ipv4.c

@@ -7,6 +7,7 @@
 #include <linux/ip.h>
 #include <linux/netfilter.h>
 #include <linux/module.h>
+#include <linux/rcupdate.h>
 #include <linux/skbuff.h>
 #include <net/netns/generic.h>
 #include <net/route.h>
@@ -113,17 +114,31 @@ static void __net_exit defrag4_net_exit(struct net *net)
 	}
 }
 
+static const struct nf_defrag_hook defrag_hook = {
+	.owner = THIS_MODULE,
+	.enable = nf_defrag_ipv4_enable,
+	.disable = nf_defrag_ipv4_disable,
+};
+
 static struct pernet_operations defrag4_net_ops = {
 	.exit = defrag4_net_exit,
 };
 
 static int __init nf_defrag_init(void)
 {
-	return register_pernet_subsys(&defrag4_net_ops);
+	int err;
+
+	err = register_pernet_subsys(&defrag4_net_ops);
+	if (err)
+		return err;
+
+	rcu_assign_pointer(nf_defrag_v4_hook, &defrag_hook);
+	return err;
 }
 
 static void __exit nf_defrag_fini(void)
 {
+	rcu_assign_pointer(nf_defrag_v4_hook, NULL);
 	unregister_pernet_subsys(&defrag4_net_ops);
 }
 

net/ipv6/netfilter/nf_defrag_ipv6_hooks.c

@@ -10,6 +10,7 @@
 #include <linux/module.h>
 #include <linux/skbuff.h>
 #include <linux/icmp.h>
+#include <linux/rcupdate.h>
 #include <linux/sysctl.h>
 #include <net/ipv6_frag.h>
 
@@ -96,6 +97,12 @@ static void __net_exit defrag6_net_exit(struct net *net)
 	}
 }
 
+static const struct nf_defrag_hook defrag_hook = {
+	.owner = THIS_MODULE,
+	.enable = nf_defrag_ipv6_enable,
+	.disable = nf_defrag_ipv6_disable,
+};
+
 static struct pernet_operations defrag6_net_ops = {
 	.exit = defrag6_net_exit,
 };
@@ -114,6 +121,9 @@ static int __init nf_defrag_init(void)
 		pr_err("nf_defrag_ipv6: can't register pernet ops\n");
 		goto cleanup_frag6;
 	}
+
+	rcu_assign_pointer(nf_defrag_v6_hook, &defrag_hook);
+
 	return ret;
 
 cleanup_frag6:
@@ -124,6 +134,7 @@ static int __init nf_defrag_init(void)
 
 static void __exit nf_defrag_fini(void)
 {
+	rcu_assign_pointer(nf_defrag_v6_hook, NULL);
 	unregister_pernet_subsys(&defrag6_net_ops);
 	nf_ct_frag6_cleanup();
 }

net/netfilter/core.c

@@ -680,6 +680,12 @@ EXPORT_SYMBOL_GPL(nfnl_ct_hook);
 const struct nf_ct_hook __rcu *nf_ct_hook __read_mostly;
 EXPORT_SYMBOL_GPL(nf_ct_hook);
 
+const struct nf_defrag_hook __rcu *nf_defrag_v4_hook __read_mostly;
+EXPORT_SYMBOL_GPL(nf_defrag_v4_hook);
+
+const struct nf_defrag_hook __rcu *nf_defrag_v6_hook __read_mostly;
+EXPORT_SYMBOL_GPL(nf_defrag_v6_hook);
+
 #if IS_ENABLED(CONFIG_NF_CONNTRACK)
 u8 nf_ctnetlink_has_listener;
 EXPORT_SYMBOL_GPL(nf_ctnetlink_has_listener);

net/netfilter/nf_bpf_link.c

 // SPDX-License-Identifier: GPL-2.0
 #include <linux/bpf.h>
 #include <linux/filter.h>
+#include <linux/kmod.h>
+#include <linux/module.h>
 #include <linux/netfilter.h>
 
 #include <net/netfilter/nf_bpf_link.h>
@@ -23,8 +25,88 @@ struct bpf_nf_link {
 	struct nf_hook_ops hook_ops;
 	struct net *net;
 	u32 dead;
+	const struct nf_defrag_hook *defrag_hook;
 };
 
+static const struct nf_defrag_hook *
+get_proto_defrag_hook(struct bpf_nf_link *link,
+		      const struct nf_defrag_hook __rcu *global_hook,
+		      const char *mod)
+{
+	const struct nf_defrag_hook *hook;
+	int err;
+
+	/* RCU protects us from races against module unloading */
+	rcu_read_lock();
+	hook = rcu_dereference(global_hook);
+	if (!hook) {
+		rcu_read_unlock();
+		err = request_module(mod);
+		if (err)
+			return ERR_PTR(err < 0 ? err : -EINVAL);
+
+		rcu_read_lock();
+		hook = rcu_dereference(global_hook);
+	}
+
+	if (hook && try_module_get(hook->owner)) {
+		/* Once we have a refcnt on the module, we no longer need RCU */
+		hook = rcu_pointer_handoff(hook);
+	} else {
+		WARN_ONCE(!hook, "%s has bad registration", mod);
+		hook = ERR_PTR(-ENOENT);
+	}
+	rcu_read_unlock();
+
+	if (!IS_ERR(hook)) {
+		err = hook->enable(link->net);
+		if (err) {
+			module_put(hook->owner);
+			hook = ERR_PTR(err);
+		}
+	}
+
+	return hook;
+}
+
+static int bpf_nf_enable_defrag(struct bpf_nf_link *link)
+{
+	const struct nf_defrag_hook __maybe_unused *hook;
+
+	switch (link->hook_ops.pf) {
+#if IS_ENABLED(CONFIG_NF_DEFRAG_IPV4)
+	case NFPROTO_IPV4:
+		hook = get_proto_defrag_hook(link, nf_defrag_v4_hook, "nf_defrag_ipv4");
+		if (IS_ERR(hook))
+			return PTR_ERR(hook);
+
+		link->defrag_hook = hook;
+		return 0;
+#endif
+#if IS_ENABLED(CONFIG_NF_DEFRAG_IPV6)
+	case NFPROTO_IPV6:
+		hook = get_proto_defrag_hook(link, nf_defrag_v6_hook, "nf_defrag_ipv6");
+		if (IS_ERR(hook))
+			return PTR_ERR(hook);
+
+		link->defrag_hook = hook;
+		return 0;
+#endif
+	default:
+		return -EAFNOSUPPORT;
+	}
+}
+
+static void bpf_nf_disable_defrag(struct bpf_nf_link *link)
+{
+	const struct nf_defrag_hook *hook = link->defrag_hook;
+
+	if (!hook)
+		return;
+	hook->disable(link->net);
+	module_put(hook->owner);
+}
+
 static void bpf_nf_link_release(struct bpf_link *link)
 {
 	struct bpf_nf_link *nf_link = container_of(link, struct bpf_nf_link, link);
@@ -32,11 +114,11 @@ static void bpf_nf_link_release(struct bpf_link *link)
 	if (nf_link->dead)
 		return;
 
-	/* prevent hook-not-found warning splat from netfilter core when
-	 * .detach was already called
-	 */
-	if (!cmpxchg(&nf_link->dead, 0, 1))
+	/* do not double release in case .detach was already called */
+	if (!cmpxchg(&nf_link->dead, 0, 1)) {
 		nf_unregister_net_hook(nf_link->net, &nf_link->hook_ops);
+		bpf_nf_disable_defrag(nf_link);
+	}
 }
 
 static void bpf_nf_link_dealloc(struct bpf_link *link)
@@ -92,6 +174,8 @@ static const struct bpf_link_ops bpf_nf_link_lops = {
 
 static int bpf_nf_check_pf_and_hooks(const union bpf_attr *attr)
 {
+	int prio;
+
 	switch (attr->link_create.netfilter.pf) {
 	case NFPROTO_IPV4:
 	case NFPROTO_IPV6:
@@ -102,19 +186,18 @@ static int bpf_nf_check_pf_and_hooks(const union bpf_attr *attr)
 		return -EAFNOSUPPORT;
 	}
 
-	if (attr->link_create.netfilter.flags)
+	if (attr->link_create.netfilter.flags & ~BPF_F_NETFILTER_IP_DEFRAG)
 		return -EOPNOTSUPP;
 
-	/* make sure conntrack confirm is always last.
-	 *
-	 * In the future, if userspace can e.g. request defrag, then
-	 * "defrag_requested && prio before NF_IP_PRI_CONNTRACK_DEFRAG"
-	 * should fail.
-	 */
-	switch (attr->link_create.netfilter.priority) {
-	case NF_IP_PRI_FIRST: return -ERANGE; /* sabotage_in and other warts */
-	case NF_IP_PRI_LAST: return -ERANGE; /* e.g. conntrack confirm */
-	}
+	/* make sure conntrack confirm is always last */
+	prio = attr->link_create.netfilter.priority;
+	if (prio == NF_IP_PRI_FIRST)
+		return -ERANGE;  /* sabotage_in and other warts */
+	else if (prio == NF_IP_PRI_LAST)
+		return -ERANGE;  /* e.g. conntrack confirm */
+	else if ((attr->link_create.netfilter.flags & BPF_F_NETFILTER_IP_DEFRAG) &&
+		 prio <= NF_IP_PRI_CONNTRACK_DEFRAG)
+		return -ERANGE;  /* cannot use defrag if prog runs before nf_defrag */
 
 	return 0;
 }
@@ -149,6 +232,7 @@ int bpf_nf_link_attach(const union bpf_attr *attr, struct bpf_prog *prog)
 
 	link->net = net;
 	link->dead = false;
+	link->defrag_hook = NULL;
 
 	err = bpf_link_prime(&link->link, &link_primer);
 	if (err) {
@@ -156,8 +240,17 @@ int bpf_nf_link_attach(const union bpf_attr *attr, struct bpf_prog *prog)
 		return err;
 	}
 
+	if (attr->link_create.netfilter.flags & BPF_F_NETFILTER_IP_DEFRAG) {
+		err = bpf_nf_enable_defrag(link);
+		if (err) {
+			bpf_link_cleanup(&link_primer);
+			return err;
+		}
+	}
+
 	err = nf_register_net_hook(net, &link->hook_ops);
 	if (err) {
+		bpf_nf_disable_defrag(link);
 		bpf_link_cleanup(&link_primer);
 		return err;
 	}

tools/include/uapi/linux/bpf.h

@@ -1188,6 +1188,11 @@ enum bpf_perf_event_type {
  */
 #define BPF_F_KPROBE_MULTI_RETURN	(1U << 0)
 
+/* link_create.netfilter.flags used in LINK_CREATE command for
+ * BPF_PROG_TYPE_NETFILTER to enable IP packet defragmentation.
+ */
+#define BPF_F_NETFILTER_IP_DEFRAG (1U << 0)
+
 /* When BPF ldimm64's insn[0].src_reg != 0 then this can have
  * the following extensions:
  *

tools/testing/selftests/bpf/Makefile

@@ -579,8 +579,8 @@ TRUNNER_EXTRA_SOURCES := test_progs.c cgroup_helpers.c trace_helpers.c	\
 			 network_helpers.c testing_helpers.c		\
 			 btf_helpers.c flow_dissector_load.h		\
 			 cap_helpers.c test_loader.c xsk.c disasm.c	\
-			 json_writer.c unpriv_helpers.c
-
+			 json_writer.c unpriv_helpers.c 		\
+			 ip_check_defrag_frags.h
 TRUNNER_EXTRA_FILES := $(OUTPUT)/urandom_read $(OUTPUT)/bpf_testmod.ko	\
 		       $(OUTPUT)/liburandom_read.so			\
 		       $(OUTPUT)/xdp_synproxy				\

tools/testing/selftests/bpf/generate_udp_fragments.py

+#!/bin/env python3
+# SPDX-License-Identifier: GPL-2.0
+
+"""
+This script helps generate fragmented UDP packets.
+
+While it is technically possible to dynamically generate
+fragmented packets in C, it is much harder to read and write
+said code. `scapy` is relatively industry standard and really
+easy to read / write.
+
+So we choose to write this script that generates a valid C
+header. Rerun script and commit generated file after any
+modifications.
+"""
+
+import argparse
+import os
+
+from scapy.all import *
+
+
+# These constants must stay in sync with `ip_check_defrag.c`
+VETH1_ADDR = "172.16.1.200"
+VETH0_ADDR6 = "fc00::100"
+VETH1_ADDR6 = "fc00::200"
+CLIENT_PORT = 48878
+SERVER_PORT = 48879
+MAGIC_MESSAGE = "THIS IS THE ORIGINAL MESSAGE, PLEASE REASSEMBLE ME"
+
+
+def print_header(f):
+    f.write("// SPDX-License-Identifier: GPL-2.0\n")
+    f.write("/* DO NOT EDIT -- this file is generated */\n")
+    f.write("\n")
+    f.write("#ifndef _IP_CHECK_DEFRAG_FRAGS_H\n")
+    f.write("#define _IP_CHECK_DEFRAG_FRAGS_H\n")
+    f.write("\n")
+    f.write("#include <stdint.h>\n")
+    f.write("\n")
+
+
+def print_frags(f, frags, v6):
+    for idx, frag in enumerate(frags):
+        # 10 bytes per line to keep width in check
+        chunks = [frag[i : i + 10] for i in range(0, len(frag), 10)]
+        chunks_fmted = [", ".join([str(hex(b)) for b in chunk]) for chunk in chunks]
+        suffix = "6" if v6 else ""
+
+        f.write(f"static uint8_t frag{suffix}_{idx}[] = {{\n")
+        for chunk in chunks_fmted:
+            f.write(f"\t{chunk},\n")
+        f.write(f"}};\n")
+
+
+def print_trailer(f):
+    f.write("\n")
+    f.write("#endif /* _IP_CHECK_DEFRAG_FRAGS_H */\n")
+
+
+def main(f):
+    # srcip of 0 is filled in by IP_HDRINCL
+    sip = "0.0.0.0"
+    sip6 = VETH0_ADDR6
+    dip = VETH1_ADDR
+    dip6 = VETH1_ADDR6
+    sport = CLIENT_PORT
+    dport = SERVER_PORT
+    payload = MAGIC_MESSAGE.encode()
+
+    # Disable UDPv4 checksums to keep code simpler
+    pkt = IP(src=sip,dst=dip) / UDP(sport=sport,dport=dport,chksum=0) / Raw(load=payload)
+    # UDPv6 requires a checksum
+    # Also pin the ipv6 fragment header ID, otherwise it's a random value
+    pkt6 = IPv6(src=sip6,dst=dip6) / IPv6ExtHdrFragment(id=0xBEEF) / UDP(sport=sport,dport=dport) / Raw(load=payload)
+
+    frags = [f.build() for f in pkt.fragment(24)]
+    frags6 = [f.build() for f in fragment6(pkt6, 72)]
+
+    print_header(f)
+    print_frags(f, frags, False)
+    print_frags(f, frags6, True)
+    print_trailer(f)
+
+
+if __name__ == "__main__":
+    dir = os.path.dirname(os.path.realpath(__file__))
+    header = f"{dir}/ip_check_defrag_frags.h"
+    with open(header, "w") as f:
+        main(f)

tools/testing/selftests/bpf/ip_check_defrag_frags.h

+// SPDX-License-Identifier: GPL-2.0
+/* DO NOT EDIT -- this file is generated */
+
+#ifndef _IP_CHECK_DEFRAG_FRAGS_H
+#define _IP_CHECK_DEFRAG_FRAGS_H
+
+#include <stdint.h>
+
+static uint8_t frag_0[] = {
+	0x45, 0x0, 0x0, 0x2c, 0x0, 0x1, 0x20, 0x0, 0x40, 0x11,
+	0xac, 0xe8, 0x0, 0x0, 0x0, 0x0, 0xac, 0x10, 0x1, 0xc8,
+	0xbe, 0xee, 0xbe, 0xef, 0x0, 0x3a, 0x0, 0x0, 0x54, 0x48,
+	0x49, 0x53, 0x20, 0x49, 0x53, 0x20, 0x54, 0x48, 0x45, 0x20,
+	0x4f, 0x52, 0x49, 0x47,
+};
+static uint8_t frag_1[] = {
+	0x45, 0x0, 0x0, 0x2c, 0x0, 0x1, 0x20, 0x3, 0x40, 0x11,
+	0xac, 0xe5, 0x0, 0x0, 0x0, 0x0, 0xac, 0x10, 0x1, 0xc8,
+	0x49, 0x4e, 0x41, 0x4c, 0x20, 0x4d, 0x45, 0x53, 0x53, 0x41,
+	0x47, 0x45, 0x2c, 0x20, 0x50, 0x4c, 0x45, 0x41, 0x53, 0x45,
+	0x20, 0x52, 0x45, 0x41,
+};
+static uint8_t frag_2[] = {
+	0x45, 0x0, 0x0, 0x1e, 0x0, 0x1, 0x0, 0x6, 0x40, 0x11,
+	0xcc, 0xf0, 0x0, 0x0, 0x0, 0x0, 0xac, 0x10, 0x1, 0xc8,
+	0x53, 0x53, 0x45, 0x4d, 0x42, 0x4c, 0x45, 0x20, 0x4d, 0x45,
+};
+static uint8_t frag6_0[] = {
+	0x60, 0x0, 0x0, 0x0, 0x0, 0x20, 0x2c, 0x40, 0xfc, 0x0,
+	0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0,
+	0x0, 0x0, 0x1, 0x0, 0xfc, 0x0, 0x0, 0x0, 0x0, 0x0,
+	0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x2, 0x0,
+	0x11, 0x0, 0x0, 0x1, 0x0, 0x0, 0xbe, 0xef, 0xbe, 0xee,
+	0xbe, 0xef, 0x0, 0x3a, 0xd0, 0xf8, 0x54, 0x48, 0x49, 0x53,
+	0x20, 0x49, 0x53, 0x20, 0x54, 0x48, 0x45, 0x20, 0x4f, 0x52,
+	0x49, 0x47,
+};
+static uint8_t frag6_1[] = {
+	0x60, 0x0, 0x0, 0x0, 0x0, 0x20, 0x2c, 0x40, 0xfc, 0x0,
+	0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0,
+	0x0, 0x0, 0x1, 0x0, 0xfc, 0x0, 0x0, 0x0, 0x0, 0x0,
+	0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x2, 0x0,
+	0x11, 0x0, 0x0, 0x19, 0x0, 0x0, 0xbe, 0xef, 0x49, 0x4e,
+	0x41, 0x4c, 0x20, 0x4d, 0x45, 0x53, 0x53, 0x41, 0x47, 0x45,
+	0x2c, 0x20, 0x50, 0x4c, 0x45, 0x41, 0x53, 0x45, 0x20, 0x52,
+	0x45, 0x41,
+};
+static uint8_t frag6_2[] = {
+	0x60, 0x0, 0x0, 0x0, 0x0, 0x12, 0x2c, 0x40, 0xfc, 0x0,
+	0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0,
+	0x0, 0x0, 0x1, 0x0, 0xfc, 0x0, 0x0, 0x0, 0x0, 0x0,
+	0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x2, 0x0,
+	0x11, 0x0, 0x0, 0x30, 0x0, 0x0, 0xbe, 0xef, 0x53, 0x53,
+	0x45, 0x4d, 0x42, 0x4c, 0x45, 0x20, 0x4d, 0x45,
+};
+
+#endif /* _IP_CHECK_DEFRAG_FRAGS_H */

tools/testing/selftests/bpf/network_helpers.c

@@ -270,14 +270,23 @@ int connect_to_fd_opts(int server_fd, const struct network_helper_opts *opts)
 		opts = &default_opts;
 
 	optlen = sizeof(type);
-	if (getsockopt(server_fd, SOL_SOCKET, SO_TYPE, &type, &optlen)) {
-		log_err("getsockopt(SOL_TYPE)");
-		return -1;
+
+	if (opts->type) {
+		type = opts->type;
+	} else {
+		if (getsockopt(server_fd, SOL_SOCKET, SO_TYPE, &type, &optlen)) {
+			log_err("getsockopt(SOL_TYPE)");
+			return -1;
+		}
 	}
 
-	if (getsockopt(server_fd, SOL_SOCKET, SO_PROTOCOL, &protocol, &optlen)) {
-		log_err("getsockopt(SOL_PROTOCOL)");
-		return -1;
+	if (opts->proto) {
+		protocol = opts->proto;
+	} else {
+		if (getsockopt(server_fd, SOL_SOCKET, SO_PROTOCOL, &protocol, &optlen)) {
+			log_err("getsockopt(SOL_PROTOCOL)");
+			return -1;
+		}
 	}
 
 	addrlen = sizeof(addr);
@@ -301,8 +310,9 @@ int connect_to_fd_opts(int server_fd, const struct network_helper_opts *opts)
 		       strlen(opts->cc) + 1))
 		goto error_close;
 
-	if (connect_fd_to_addr(fd, &addr, addrlen, opts->must_fail))
-		goto error_close;
+	if (!opts->noconnect)
+		if (connect_fd_to_addr(fd, &addr, addrlen, opts->must_fail))
+			goto error_close;
 
 	return fd;
 

tools/testing/selftests/bpf/network_helpers.h

@@ -21,6 +21,9 @@ struct network_helper_opts {
 	const char *cc;
 	int timeout_ms;
 	bool must_fail;
+	bool noconnect;
+	int type;
+	int proto;
 };
 
 /* ipv4 test vector */

tools/testing/selftests/bpf/prog_tests/ip_check_defrag.c

+// SPDX-License-Identifier: GPL-2.0
+#include <test_progs.h>
+#include <net/if.h>
+#include <linux/netfilter.h>
+#include <network_helpers.h>
+#include "ip_check_defrag.skel.h"
+#include "ip_check_defrag_frags.h"
+
+/*
+ * This selftest spins up a client and an echo server, each in their own
+ * network namespace. The client will send a fragmented message to the server.
+ * The prog attached to the server will shoot down any fragments. Thus, if
+ * the server is able to correctly echo back the message to the client, we will
+ * have verified that netfilter is reassembling packets for us.
+ *
+ * Topology:
+ * =========
+ *           NS0         |         NS1
+ *                       |
+ *         client        |       server
+ *       ----------      |     ----------
+ *       |  veth0  | --------- |  veth1  |
+ *       ----------    peer    ----------
+ *                       |
+ *                       |       with bpf
+ */
+
+#define NS0		"defrag_ns0"
+#define NS1		"defrag_ns1"
+#define VETH0		"veth0"
+#define VETH1		"veth1"
+#define VETH0_ADDR	"172.16.1.100"
+#define VETH0_ADDR6	"fc00::100"
+/* The following constants must stay in sync with `generate_udp_fragments.py` */
+#define VETH1_ADDR	"172.16.1.200"
+#define VETH1_ADDR6	"fc00::200"
+#define CLIENT_PORT	48878
+#define SERVER_PORT	48879
+#define MAGIC_MESSAGE	"THIS IS THE ORIGINAL MESSAGE, PLEASE REASSEMBLE ME"
+
+static int setup_topology(bool ipv6)
+{
+	bool up;
+	int i;
+
+	SYS(fail, "ip netns add " NS0);
+	SYS(fail, "ip netns add " NS1);
+	SYS(fail, "ip link add " VETH0 " netns " NS0 " type veth peer name " VETH1 " netns " NS1);
+	if (ipv6) {
+		SYS(fail, "ip -6 -net " NS0 " addr add " VETH0_ADDR6 "/64 dev " VETH0 " nodad");
+		SYS(fail, "ip -6 -net " NS1 " addr add " VETH1_ADDR6 "/64 dev " VETH1 " nodad");
+	} else {
+		SYS(fail, "ip -net " NS0 " addr add " VETH0_ADDR "/24 dev " VETH0);
+		SYS(fail, "ip -net " NS1 " addr add " VETH1_ADDR "/24 dev " VETH1);
+	}
+	SYS(fail, "ip -net " NS0 " link set dev " VETH0 " up");
+	SYS(fail, "ip -net " NS1 " link set dev " VETH1 " up");
+
+	/* Wait for up to 5s for links to come up */
+	for (i = 0; i < 5; ++i) {
+		if (ipv6)
+			up = !system("ip netns exec " NS0 " ping -6 -c 1 -W 1 " VETH1_ADDR6 " &>/dev/null");
+		else
+			up = !system("ip netns exec " NS0 " ping -c 1 -W 1 " VETH1_ADDR " &>/dev/null");
+
+		if (up)
+			break;
+	}
+
+	return 0;
+fail:
+	return -1;
+}
+
+static void cleanup_topology(void)
+{
+	SYS_NOFAIL("test -f /var/run/netns/" NS0 " && ip netns delete " NS0);
+	SYS_NOFAIL("test -f /var/run/netns/" NS1 " && ip netns delete " NS1);
+}
+
+static int attach(struct ip_check_defrag *skel, bool ipv6)
+{
+	LIBBPF_OPTS(bpf_netfilter_opts, opts,
+		    .pf = ipv6 ? NFPROTO_IPV6 : NFPROTO_IPV4,
+		    .priority = 42,
+		    .flags = BPF_F_NETFILTER_IP_DEFRAG);
+	struct nstoken *nstoken;
+	int err = -1;
+
+	nstoken = open_netns(NS1);
+
+	skel->links.defrag = bpf_program__attach_netfilter(skel->progs.defrag, &opts);
+	if (!ASSERT_OK_PTR(skel->links.defrag, "program attach"))
+		goto out;
+
+	err = 0;
+out:
+	close_netns(nstoken);
+	return err;
+}
+
+static int send_frags(int client)
+{
+	struct sockaddr_storage saddr;
+	struct sockaddr *saddr_p;
+	socklen_t saddr_len;
+	int err;
+
+	saddr_p = (struct sockaddr *)&saddr;
+	err = make_sockaddr(AF_INET, VETH1_ADDR, SERVER_PORT, &saddr, &saddr_len);
+	if (!ASSERT_OK(err, "make_sockaddr"))
+		return -1;
+
+	err = sendto(client, frag_0, sizeof(frag_0), 0, saddr_p, saddr_len);
+	if (!ASSERT_GE(err, 0, "sendto frag_0"))
+		return -1;
+
+	err = sendto(client, frag_1, sizeof(frag_1), 0, saddr_p, saddr_len);
+	if (!ASSERT_GE(err, 0, "sendto frag_1"))
+		return -1;
+
+	err = sendto(client, frag_2, sizeof(frag_2), 0, saddr_p, saddr_len);
+	if (!ASSERT_GE(err, 0, "sendto frag_2"))
+		return -1;
+
+	return 0;
+}
+
+static int send_frags6(int client)
+{
+	struct sockaddr_storage saddr;
+	struct sockaddr *saddr_p;
+	socklen_t saddr_len;
+	int err;
+
+	saddr_p = (struct sockaddr *)&saddr;
+	/* Port needs to be set to 0 for raw ipv6 socket for some reason */
+	err = make_sockaddr(AF_INET6, VETH1_ADDR6, 0, &saddr, &saddr_len);
+	if (!ASSERT_OK(err, "make_sockaddr"))
+		return -1;
+
+	err = sendto(client, frag6_0, sizeof(frag6_0), 0, saddr_p, saddr_len);
+	if (!ASSERT_GE(err, 0, "sendto frag6_0"))
+		return -1;
+
+	err = sendto(client, frag6_1, sizeof(frag6_1), 0, saddr_p, saddr_len);
+	if (!ASSERT_GE(err, 0, "sendto frag6_1"))
+		return -1;
+
+	err = sendto(client, frag6_2, sizeof(frag6_2), 0, saddr_p, saddr_len);
+	if (!ASSERT_GE(err, 0, "sendto frag6_2"))
+		return -1;
+
+	return 0;
+}
+
+void test_bpf_ip_check_defrag_ok(bool ipv6)
+{
+	struct network_helper_opts rx_opts = {
+		.timeout_ms = 1000,
+		.noconnect = true,
+	};
+	struct network_helper_opts tx_ops = {
+		.timeout_ms = 1000,
+		.type = SOCK_RAW,
+		.proto = IPPROTO_RAW,
+		.noconnect = true,
+	};
+	struct sockaddr_storage caddr;
+	struct ip_check_defrag *skel;
+	struct nstoken *nstoken;
+	int client_tx_fd = -1;
+	int client_rx_fd = -1;
+	socklen_t caddr_len;
+	int srv_fd = -1;
+	char buf[1024];
+	int len, err;
+
+	skel = ip_check_defrag__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel_open"))
+		return;
+
+	if (!ASSERT_OK(setup_topology(ipv6), "setup_topology"))
+		goto out;
+
+	if (!ASSERT_OK(attach(skel, ipv6), "attach"))
+		goto out;
+
+	/* Start server in ns1 */
+	nstoken = open_netns(NS1);
+	if (!ASSERT_OK_PTR(nstoken, "setns ns1"))
+		goto out;
+	srv_fd = start_server(ipv6 ? AF_INET6 : AF_INET, SOCK_DGRAM, NULL, SERVER_PORT, 0);
+	close_netns(nstoken);
+	if (!ASSERT_GE(srv_fd, 0, "start_server"))
+		goto out;
+
+	/* Open tx raw socket in ns0 */
+	nstoken = open_netns(NS0);
+	if (!ASSERT_OK_PTR(nstoken, "setns ns0"))
+		goto out;
+	client_tx_fd = connect_to_fd_opts(srv_fd, &tx_ops);
+	close_netns(nstoken);
+	if (!ASSERT_GE(client_tx_fd, 0, "connect_to_fd_opts"))
+		goto out;
+
+	/* Open rx socket in ns0 */
+	nstoken = open_netns(NS0);
+	if (!ASSERT_OK_PTR(nstoken, "setns ns0"))
+		goto out;
+	client_rx_fd = connect_to_fd_opts(srv_fd, &rx_opts);
+	close_netns(nstoken);
+	if (!ASSERT_GE(client_rx_fd, 0, "connect_to_fd_opts"))
+		goto out;
+
+	/* Bind rx socket to a premeditated port */
+	memset(&caddr, 0, sizeof(caddr));
+	nstoken = open_netns(NS0);
+	if (!ASSERT_OK_PTR(nstoken, "setns ns0"))
+		goto out;
+	if (ipv6) {
+		struct sockaddr_in6 *c = (struct sockaddr_in6 *)&caddr;
+
+		c->sin6_family = AF_INET6;
+		inet_pton(AF_INET6, VETH0_ADDR6, &c->sin6_addr);
+		c->sin6_port = htons(CLIENT_PORT);
+		err = bind(client_rx_fd, (struct sockaddr *)c, sizeof(*c));
+	} else {
+		struct sockaddr_in *c = (struct sockaddr_in *)&caddr;
+
+		c->sin_family = AF_INET;
+		inet_pton(AF_INET, VETH0_ADDR, &c->sin_addr);
+		c->sin_port = htons(CLIENT_PORT);
+		err = bind(client_rx_fd, (struct sockaddr *)c, sizeof(*c));
+	}
+	close_netns(nstoken);
+	if (!ASSERT_OK(err, "bind"))
+		goto out;
+
+	/* Send message in fragments */
+	if (ipv6) {
+		if (!ASSERT_OK(send_frags6(client_tx_fd), "send_frags6"))
+			goto out;
+	} else {
+		if (!ASSERT_OK(send_frags(client_tx_fd), "send_frags"))
+			goto out;
+	}
+
+	if (!ASSERT_EQ(skel->bss->shootdowns, 0, "shootdowns"))
+		goto out;
+
+	/* Receive reassembled msg on server and echo back to client */
+	caddr_len = sizeof(caddr);
+	len = recvfrom(srv_fd, buf, sizeof(buf), 0, (struct sockaddr *)&caddr, &caddr_len);
+	if (!ASSERT_GE(len, 0, "server recvfrom"))
+		goto out;
+	len = sendto(srv_fd, buf, len, 0, (struct sockaddr *)&caddr, caddr_len);
+	if (!ASSERT_GE(len, 0, "server sendto"))
+		goto out;
+
+	/* Expect reassembed message to be echoed back */
+	len = recvfrom(client_rx_fd, buf, sizeof(buf), 0, NULL, NULL);
+	if (!ASSERT_EQ(len, sizeof(MAGIC_MESSAGE) - 1, "client short read"))
+		goto out;
+
+out:
+	if (client_rx_fd != -1)
+		close(client_rx_fd);
+	if (client_tx_fd != -1)
+		close(client_tx_fd);
+	if (srv_fd != -1)
+		close(srv_fd);
+	cleanup_topology();
+	ip_check_defrag__destroy(skel);
+}
+
+void test_bpf_ip_check_defrag(void)
+{
+	if (test__start_subtest("v4"))
+		test_bpf_ip_check_defrag_ok(false);
+	if (test__start_subtest("v6"))
+		test_bpf_ip_check_defrag_ok(true);
+}

tools/testing/selftests/bpf/progs/ip_check_defrag.c

+// SPDX-License-Identifier: GPL-2.0-only
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
+#include "bpf_tracing_net.h"
+
+#define NF_DROP			0
+#define NF_ACCEPT		1
+#define ETH_P_IP		0x0800
+#define ETH_P_IPV6		0x86DD
+#define IP_MF			0x2000
+#define IP_OFFSET		0x1FFF
+#define NEXTHDR_FRAGMENT	44
+
+extern int bpf_dynptr_from_skb(struct sk_buff *skb, __u64 flags,
+			      struct bpf_dynptr *ptr__uninit) __ksym;
+extern void *bpf_dynptr_slice(const struct bpf_dynptr *ptr, uint32_t offset,
+			      void *buffer, uint32_t buffer__sz) __ksym;
+
+volatile int shootdowns = 0;
+
+static bool is_frag_v4(struct iphdr *iph)
+{
+	int offset;
+	int flags;
+
+	offset = bpf_ntohs(iph->frag_off);
+	flags = offset & ~IP_OFFSET;
+	offset &= IP_OFFSET;
+	offset <<= 3;
+
+	return (flags & IP_MF) || offset;
+}
+
+static bool is_frag_v6(struct ipv6hdr *ip6h)
+{
+	/* Simplifying assumption that there are no extension headers
+	 * between fixed header and fragmentation header. This assumption
+	 * is only valid in this test case. It saves us the hassle of
+	 * searching all potential extension headers.
+	 */
+	return ip6h->nexthdr == NEXTHDR_FRAGMENT;
+}
+
+static int handle_v4(struct sk_buff *skb)
+{
+	struct bpf_dynptr ptr;
+	u8 iph_buf[20] = {};
+	struct iphdr *iph;
+
+	if (bpf_dynptr_from_skb(skb, 0, &ptr))
+		return NF_DROP;
+
+	iph = bpf_dynptr_slice(&ptr, 0, iph_buf, sizeof(iph_buf));
+	if (!iph)
+		return NF_DROP;
+
+	/* Shootdown any frags */
+	if (is_frag_v4(iph)) {
+		shootdowns++;
+		return NF_DROP;
+	}
+
+	return NF_ACCEPT;
+}
+
+static int handle_v6(struct sk_buff *skb)
+{
+	struct bpf_dynptr ptr;
+	struct ipv6hdr *ip6h;
+	u8 ip6h_buf[40] = {};
+
+	if (bpf_dynptr_from_skb(skb, 0, &ptr))
+		return NF_DROP;
+
+	ip6h = bpf_dynptr_slice(&ptr, 0, ip6h_buf, sizeof(ip6h_buf));
+	if (!ip6h)
+		return NF_DROP;
+
+	/* Shootdown any frags */
+	if (is_frag_v6(ip6h)) {
+		shootdowns++;
+		return NF_DROP;
+	}
+
+	return NF_ACCEPT;
+}
+
+SEC("netfilter")
+int defrag(struct bpf_nf_ctx *ctx)
+{
+	struct sk_buff *skb = ctx->skb;
+
+	switch (bpf_ntohs(skb->protocol)) {
+	case ETH_P_IP:
+		return handle_v4(skb);
+	case ETH_P_IPV6:
+		return handle_v6(skb);
+	default:
+		return NF_ACCEPT;
+	}
+}
+
+char _license[] SEC("license") = "GPL";