Skip to contentSkip to conversation

net: clear the dst when performing encap / decap

PATCH Applied Jakub Kicinski 5 participants 8 messages Mar 29 – Mar 31

Subsystems (6)
lore
Share & tools
lore

Jakub Kicinski

author maintainer
#0 lore raw

PATCH v2 1/2 net: clear the dst when performing encap / decap

Commit ba9db6f907ac ("net: clear the dst when changing skb protocol") added dst clearing when a BPF program changes the skb protocol (e.g. IPv4 to IPv6). Since that was a fix we only cleared the dst when the L3 protocol actually changes to keep it minimal. As suggested during the discussion (see Link) encap or decap operation which wraps or unwraps a same-protocol header may also render the existing dst incorrect - even if that doesn't result in a crash, just the wrong route for the now-outermost IP dst.

Make dropping dst unconditional for bpf_skb_change_proto() and all L3 encap / decap ops.

---
v2:
- move the pointer recalc
v1: https://lore.kernel.org/[email protected]

---
 net/core/filter.c | 50 +++++++++++++++++++++++++----------------------
 1 file changed, 27 insertions(+), 23 deletions(-)
net/core/filter.c +27 -23
index 78b548158fb0..8a352257656e 100644
@@ -3257,13 +3257,6 @@ static const struct bpf_func_proto bpf_skb_vlan_pop_proto = {
 	.arg1_type      = ARG_PTR_TO_CTX,
 };
 
-static void bpf_skb_change_protocol(struct sk_buff *skb, u16 proto)
-{
-	skb->protocol = htons(proto);
-	if (skb_valid_dst(skb))
-		skb_dst_drop(skb);
-}
-
 static int bpf_skb_generic_push(struct sk_buff *skb, u32 off, u32 len)
 {
 	/* Caller already did skb_cow() with meta_len+len as headroom,
@@ -3362,7 +3355,7 @@ static int bpf_skb_proto_4_to_6(struct sk_buff *skb)
 		shinfo->gso_type |=  SKB_GSO_DODGY;
 	}
 
-	bpf_skb_change_protocol(skb, ETH_P_IPV6);
+	skb->protocol = htons(ETH_P_IPV6);
 	skb_clear_hash(skb);
 
 	return 0;
@@ -3393,7 +3386,7 @@ static int bpf_skb_proto_6_to_4(struct sk_buff *skb)
 		shinfo->gso_type |=  SKB_GSO_DODGY;
 	}
 
-	bpf_skb_change_protocol(skb, ETH_P_IP);
+	skb->protocol = htons(ETH_P_IP);
 	skb_clear_hash(skb);
 
 	return 0;
@@ -3441,7 +3434,13 @@ BPF_CALL_3(bpf_skb_change_proto, struct sk_buff *, skb, __be16, proto,
 	 */
 	ret = bpf_skb_proto_xlat(skb, proto);
 	bpf_compute_data_pointers(skb);
-	return ret;
+	if (ret)
+		return ret;
+
+	if (skb_valid_dst(skb))
+		skb_dst_drop(skb);
+
+	return 0;
 }
 
 static const struct bpf_func_proto bpf_skb_change_proto_proto = {
@@ -3583,12 +3582,13 @@ static int bpf_skb_net_grow(struct sk_buff *skb, u32 off, u32 len_diff,
 		}
 
 		/* Match skb->protocol to new outer l3 protocol */
-		if (skb->protocol == htons(ETH_P_IP) &&
-		    flags & BPF_F_ADJ_ROOM_ENCAP_L3_IPV6)
-			bpf_skb_change_protocol(skb, ETH_P_IPV6);
-		else if (skb->protocol == htons(ETH_P_IPV6) &&
-			 flags & BPF_F_ADJ_ROOM_ENCAP_L3_IPV4)
-			bpf_skb_change_protocol(skb, ETH_P_IP);
+		if (flags & BPF_F_ADJ_ROOM_ENCAP_L3_IPV6)
+			skb->protocol = htons(ETH_P_IPV6);
+		else if (flags & BPF_F_ADJ_ROOM_ENCAP_L3_IPV4)
+			skb->protocol = htons(ETH_P_IP);
+
+		if (skb_valid_dst(skb))
+			skb_dst_drop(skb);
 	}
 
 	if (skb_is_gso(skb)) {
@@ -3616,6 +3616,7 @@ static int bpf_skb_net_grow(struct sk_buff *skb, u32 off, u32 len_diff,
 static int bpf_skb_net_shrink(struct sk_buff *skb, u32 off, u32 len_diff,
 			      u64 flags)
 {
+	bool decap = flags & BPF_F_ADJ_ROOM_DECAP_L3_MASK;
 	int ret;
 
 	if (unlikely(flags & ~(BPF_F_ADJ_ROOM_FIXED_GSO |
@@ -3638,13 +3639,16 @@ static int bpf_skb_net_shrink(struct sk_buff *skb, u32 off, u32 len_diff,
 	if (unlikely(ret < 0))
 		return ret;
 
-	/* Match skb->protocol to new outer l3 protocol */
-	if (skb->protocol == htons(ETH_P_IP) &&
-	    flags & BPF_F_ADJ_ROOM_DECAP_L3_IPV6)
-		bpf_skb_change_protocol(skb, ETH_P_IPV6);
-	else if (skb->protocol == htons(ETH_P_IPV6) &&
-		 flags & BPF_F_ADJ_ROOM_DECAP_L3_IPV4)
-		bpf_skb_change_protocol(skb, ETH_P_IP);
+	if (decap) {
+		/* Match skb->protocol to new outer l3 protocol */
+		if (flags & BPF_F_ADJ_ROOM_DECAP_L3_IPV6)
+			skb->protocol = htons(ETH_P_IPV6);
+		else if (flags & BPF_F_ADJ_ROOM_DECAP_L3_IPV4)
+			skb->protocol = htons(ETH_P_IP);
+
+		if (skb_valid_dst(skb))
+			skb_dst_drop(skb);
+	}
 
 	if (skb_is_gso(skb)) {
 		struct skb_shared_info *shinfo = skb_shinfo(skb);
Signature · 1 line
2.53.0
author maintainer
#1 lore raw

PATCH v2 2/2 selftests/bpf: test that dst is cleared on same-protocol encap

Verify that bpf_skb_adjust_room() clears the routing dst even when the encap L3 protocol matches the original packet (e.g. IPIP). The dst selected for the inner packet is not valid for the encapsulated result; a stale dst could lead to misrouting.

---
CC: [email protected]
CC: [email protected]
CC: [email protected]
CC: [email protected]
CC: [email protected]
CC: [email protected]
CC: [email protected]
CC: [email protected]
CC: [email protected]
CC: [email protected]
CC: [email protected]
CC: [email protected]
CC: [email protected]
CC: [email protected]
CC: [email protected]

---
 .../selftests/bpf/prog_tests/test_dst_clear.c | 75 +++++++++++++++++++
 .../selftests/bpf/progs/test_dst_clear.c      | 57 ++++++++++++++
 2 files changed, 132 insertions(+)
 create mode 100644 tools/testing/selftests/bpf/prog_tests/test_dst_clear.c
 create mode 100644 tools/testing/selftests/bpf/progs/test_dst_clear.c
tools/testing/selftests/bpf/prog_tests/test_dst_clear.c new file +75 -0
new file mode 100644
index 000000000000..8190c56556fb
@@ -0,0 +1,75 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2026 Meta Platforms, Inc. and affiliates. */
+
+#include <sys/types.h>
+#include <sys/socket.h>
+#include <net/if.h>
+
+#include "test_progs.h"
+#include "network_helpers.h"
+#include "test_dst_clear.skel.h"
+
+#define NS_TEST "dst_clear_ns"
+#define IPV4_IFACE_ADDR "1.0.0.1"
+#define UDP_TEST_PORT 7777
+
+void test_dst_clear(void)
+{
+	LIBBPF_OPTS(bpf_tc_hook, qdisc_hook, .attach_point = BPF_TC_EGRESS);
+	LIBBPF_OPTS(bpf_tc_opts, tc_attach);
+	struct nstoken *nstoken = NULL;
+	struct test_dst_clear *skel;
+	struct sockaddr_in addr;
+	socklen_t addrlen;
+	char buf[128] = {};
+	int sockfd, err;
+
+	skel = test_dst_clear__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel open_and_load"))
+		return;
+
+	SYS(fail, "ip netns add %s", NS_TEST);
+	SYS(fail, "ip -net %s addr add %s/8 dev lo", NS_TEST, IPV4_IFACE_ADDR);
+	SYS(fail, "ip -net %s link set dev lo up", NS_TEST);
+
+	nstoken = open_netns(NS_TEST);
+	if (!ASSERT_OK_PTR(nstoken, "open_netns"))
+		goto fail;
+
+	qdisc_hook.ifindex = if_nametoindex("lo");
+	if (!ASSERT_GT(qdisc_hook.ifindex, 0, "if_nametoindex lo"))
+		goto fail;
+
+	err = bpf_tc_hook_create(&qdisc_hook);
+	if (!ASSERT_OK(err, "create qdisc hook"))
+		goto fail;
+
+	tc_attach.prog_fd = bpf_program__fd(skel->progs.dst_clear);
+	err = bpf_tc_attach(&qdisc_hook, &tc_attach);
+	if (!ASSERT_OK(err, "attach filter"))
+		goto fail;
+
+	addrlen = sizeof(addr);
+	err = make_sockaddr(AF_INET, IPV4_IFACE_ADDR, UDP_TEST_PORT,
+			    (void *)&addr, &addrlen);
+	if (!ASSERT_OK(err, "make_sockaddr"))
+		goto fail;
+	sockfd = socket(AF_INET, SOCK_DGRAM, 0);
+	if (!ASSERT_NEQ(sockfd, -1, "socket"))
+		goto fail;
+	err = sendto(sockfd, buf, sizeof(buf), 0, (void *)&addr, addrlen);
+	close(sockfd);
+	if (!ASSERT_EQ(err, sizeof(buf), "send"))
+		goto fail;
+
+	ASSERT_TRUE(skel->bss->had_dst, "had_dst");
+	ASSERT_TRUE(skel->bss->dst_cleared, "dst_cleared");
+
+fail:
+	if (nstoken) {
+		bpf_tc_hook_destroy(&qdisc_hook);
+		close_netns(nstoken);
+	}
+	SYS_NOFAIL("ip netns del " NS_TEST);
+	test_dst_clear__destroy(skel);
+}
tools/testing/selftests/bpf/progs/test_dst_clear.c new file +57 -0

57 lines not on this page · raw message

Signature · 1 line
2.53.0
maintainer Acked-by on v2 1/2
#5 lore raw
In reply to Jakub Kicinski
Quoted 9 lines · Jakub Kicinski

Commit ba9db6f907ac ("net: clear the dst when changing skb protocol") added dst clearing when a BPF program changes the skb protocol (e.g. IPv4 to IPv6). Since that was a fix we only cleared the dst when the L3 protocol actually changes to keep it minimal. As suggested during the discussion (see Link) encap or decap operation which wraps or unwraps a same-protocol header may also render the existing dst incorrect - even if that doesn't result in a crash, just the wrong route for the now-outermost IP dst.

Quoted 5 lines

Make dropping dst unconditional for bpf_skb_change_proto() and all L3 encap / decap ops.

maintainer Acked-by on v2 2/2
#2 lore raw

Re: [PATCH bpf-next v2 2/2] selftests/bpf: test that dst is cleared on same-protocol encap

In reply to Jakub Kicinski
Quoted 6 lines · Jakub Kicinski

Verify that bpf_skb_adjust_room() clears the routing dst even when the encap L3 protocol matches the original packet (e.g. IPIP). The dst selected for the inner packet is not valid for the encapsulated result; a stale dst could lead to misrouting.

For new tests we should ideally only be using tcx links and not the old qdisc approach unless there is specifc reason to. Any objections if I fold this in while applying?

 .../selftests/bpf/prog_tests/test_dst_clear.c | 23 ++++++-------------
 .../selftests/bpf/progs/test_dst_clear.c      |  2 +-
 2 files changed, 8 insertions(+), 17 deletions(-)
tools/testing/selftests/bpf/prog_tests/test_dst_clear.c +7 -16
index 8190c56556fb..c8e9c6947a2c 100644
@@ -15,11 +15,11 @@
 
 void test_dst_clear(void)
 {
-	LIBBPF_OPTS(bpf_tc_hook, qdisc_hook, .attach_point = BPF_TC_EGRESS);
-	LIBBPF_OPTS(bpf_tc_opts, tc_attach);
+	LIBBPF_OPTS(bpf_tcx_opts, tcx_opts);
 	struct nstoken *nstoken = NULL;
 	struct test_dst_clear *skel;
 	struct sockaddr_in addr;
+	struct bpf_link *link;
 	socklen_t addrlen;
 	char buf[128] = {};
 	int sockfd, err;
@@ -36,18 +36,11 @@ void test_dst_clear(void)
 	if (!ASSERT_OK_PTR(nstoken, "open_netns"))
 		goto fail;
 
-	qdisc_hook.ifindex = if_nametoindex("lo");
-	if (!ASSERT_GT(qdisc_hook.ifindex, 0, "if_nametoindex lo"))
-		goto fail;
-
-	err = bpf_tc_hook_create(&qdisc_hook);
-	if (!ASSERT_OK(err, "create qdisc hook"))
-		goto fail;
-
-	tc_attach.prog_fd = bpf_program__fd(skel->progs.dst_clear);
-	err = bpf_tc_attach(&qdisc_hook, &tc_attach);
-	if (!ASSERT_OK(err, "attach filter"))
+	link = bpf_program__attach_tcx(skel->progs.dst_clear,
+				       if_nametoindex("lo"), &tcx_opts);
+	if (!ASSERT_OK_PTR(link, "attach_tcx"))
 		goto fail;
+	skel->links.dst_clear = link;
 
 	addrlen = sizeof(addr);
 	err = make_sockaddr(AF_INET, IPV4_IFACE_ADDR, UDP_TEST_PORT,
@@ -66,10 +59,8 @@ void test_dst_clear(void)
 	ASSERT_TRUE(skel->bss->dst_cleared, "dst_cleared");
 
 fail:
-	if (nstoken) {
-		bpf_tc_hook_destroy(&qdisc_hook);
+	if (nstoken)
 		close_netns(nstoken);
-	}
 	SYS_NOFAIL("ip netns del " NS_TEST);
 	test_dst_clear__destroy(skel);
 }
tools/testing/selftests/bpf/progs/test_dst_clear.c +1 -1
index 7ac9604fd99c..c22a6eeb4798 100644
@@ -13,7 +13,7 @@ void *bpf_cast_to_kern_ctx(void *) __ksym;
 bool had_dst = false;
 bool dst_cleared = false;
 
-SEC("tc")
+SEC("tc/egress")
 int dst_clear(struct __sk_buff *skb)
 {
 	struct sk_buff *kskb;
Signature · 1 line
2.43.0
Reviewed-by on v2 1/2
#6 lore raw
In reply to Jakub Kicinski
Quoted 9 lines · Jakub Kicinski

Commit ba9db6f907ac ("net: clear the dst when changing skb protocol") added dst clearing when a BPF program changes the skb protocol (e.g. IPv4 to IPv6). Since that was a fix we only cleared the dst when the L3 protocol actually changes to keep it minimal. As suggested during the discussion (see Link) encap or decap operation which wraps or unwraps a same-protocol header may also render the existing dst incorrect - even if that doesn't result in a crash, just the wrong route for the now-outermost IP dst.

Quoted 5 lines

Make dropping dst unconditional for bpf_skb_change_proto() and all L3 encap / decap ops.

#7 lore raw
In reply to Jakub Kicinski
This series was applied to bpf/bpf-next.git (net) by Martin KaFai Lau <[email protected]>:

Hello:

This series was applied to bpf/bpf-next.git (net)
by Martin KaFai Lau <[email protected]>:

Quoted 10 lines · On Sun, 29 Mar 2026 11:04:27 -0700 you wrote:

Commit ba9db6f907ac ("net: clear the dst when changing skb protocol") added dst clearing when a BPF program changes the skb protocol (e.g. IPv4 to IPv6). Since that was a fix we only cleared the dst when the L3 protocol actually changes to keep it minimal. As suggested during the discussion (see Link) encap or decap operation which wraps or unwraps a same-protocol header may also render the existing dst incorrect - even if that doesn't result in a crash, just the wrong route for the now-outermost IP dst.

[...]

Here is the summary with links:
- [bpf-next,v2,1/2] net: clear the dst when performing encap / decap

    https://git.kernel.org/bpf/bpf-next/c/648c1bc05997
  - [bpf-next,v2,2/2] selftests/bpf: test that dst is cleared on same-protocol encap
    https://git.kernel.org/bpf/bpf-next/c/660735c4182c

You are awesome, thank you!

Signature · 2 lines
Deet-doot-dot, I am a bot.
https://korg.docs.kernel.org/patchwork/pwbot.html
author maintainer
#3 lore raw

Re: [PATCH bpf-next v2 2/2] selftests/bpf: test that dst is cleared on same-protocol encap

In reply to Daniel Borkmann
Quoted 6 lines · On Mon, 30 Mar 2026 10:03:46 +0200 Daniel Borkmann wrote:
Quoted 5 lines · Jakub Kicinski

Verify that bpf_skb_adjust_room() clears the routing dst even when the encap L3 protocol matches the original packet (e.g. IPIP). The dst selected for the inner packet is not valid for the encapsulated result; a stale dst could lead to misrouting.

Quoted 7 lines
Quoted 1 line

For new tests we should ideally only be using tcx links and not the old qdisc approach unless there is specifc reason to. Any objections if I fold this in while applying?

Sorry for a late reply, of course don't mind, thanks for handling it!

#4 lore raw

Re: [PATCH bpf-next v2 2/2] selftests/bpf: test that dst is cleared on same-protocol encap

Quoted 9 lines · Jakub Kicinski
Quoted 8 lines · On Mon, 30 Mar 2026 10:03:46 +0200 Daniel Borkmann wrote:
Quoted 6 lines · Jakub Kicinski

Verify that bpf_skb_adjust_room() clears the routing dst even when the encap L3 protocol matches the original packet (e.g. IPIP). The dst selected for the inner packet is not valid for the encapsulated result; a stale dst could lead to misrouting.

Quoted 7 lines
Quoted 5 lines

For new tests we should ideally only be using tcx links and not the old qdisc approach unless there is specifc reason to. Any objections if I fold this in while applying?

Sorry for a late reply, of course don't mind, thanks for handling it!

I have folded Daniel's changes to the selftest. Applied. Thanks.