net/bpf/test_run.c | 47 ++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 47 insertions(+)
From: Feng Yang <yangfeng@kylinos.cn>
The bpf_lwt_xmit_push_encap helper needs to access skb_dst(skb)->dev to
calculate the needed headroom:
err = skb_cow_head(skb,
len + LL_RESERVED_SPACE(skb_dst(skb)->dev));
But skb->_skb_refdst may not be initialized when the skb is set up by
bpf_prog_test_run_skb function. Executing bpf_lwt_push_ip_encap function
in this scenario will trigger null pointer dereference, causing a kernel
crash as Yinhao reported:
[ 105.186365] BUG: kernel NULL pointer dereference, address: 0000000000000000
[ 105.186382] #PF: supervisor read access in kernel mode
[ 105.186388] #PF: error_code(0x0000) - not-present page
[ 105.186393] PGD 121d3d067 P4D 121d3d067 PUD 106c83067 PMD 0
[ 105.186404] Oops: 0000 [#1] PREEMPT SMP NOPTI
[ 105.186412] CPU: 3 PID: 3250 Comm: poc Kdump: loaded Not tainted 6.19.0-rc5 #1
[ 105.186423] Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.16.3-debian-1.16.3-2 04/01/2014
[ 105.186427] RIP: 0010:bpf_lwt_push_ip_encap+0x1eb/0x520
[ 105.186443] Code: 0f 84 de 01 00 00 0f b7 4a 04 66 85 c9 0f 85 47 01 00 00 31 c0 5b 5d 41 5c 41 5d 41 5e c3 cc cc cc cc 48 8b 73 58 48 83 e6 fe <48> 8b 36 0f b7 be ec 00 00 00 0f b7 b6 e6 00 00 00 01 fe 83 e6 f0
[ 105.186449] RSP: 0018:ffffbb0e0387bc50 EFLAGS: 00010246
[ 105.186455] RAX: 000000000000004e RBX: ffff94c74e036500 RCX: ffff94c74874da00
[ 105.186460] RDX: 0000000000000000 RSI: 0000000000000000 RDI: ffff94c74e036500
[ 105.186463] RBP: 0000000000000001 R08: 0000000000000002 R09: 0000000000000000
[ 105.186467] R10: ffffbb0e0387bd50 R11: 0000000000000000 R12: ffffbb0e0387bc98
[ 105.186471] R13: 0000000000000014 R14: 0000000000000000 R15: 0000000000000002
[ 105.186484] FS: 00007f166aa4d680(0000) GS:ffff94c8b7780000(0000) knlGS:0000000000000000
[ 105.186490] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[ 105.186494] CR2: 0000000000000000 CR3: 000000015eade001 CR4: 0000000000770ee0
[ 105.186499] PKRU: 55555554
[ 105.186502] Call Trace:
[ 105.186507] <TASK>
[ 105.186513] bpf_lwt_xmit_push_encap+0x2b/0x40
[ 105.186522] bpf_prog_a75eaad51e517912+0x41/0x49
[ 105.186536] ? kvm_clock_get_cycles+0x18/0x30
[ 105.186547] ? ktime_get+0x3c/0xa0
[ 105.186554] bpf_test_run+0x195/0x320
[ 105.186563] ? bpf_test_run+0x10f/0x320
[ 105.186579] bpf_prog_test_run_skb+0x2f5/0x4f0
[ 105.186590] __sys_bpf+0x69c/0xa40
[ 105.186603] __x64_sys_bpf+0x1e/0x30
[ 105.186611] do_syscall_64+0x59/0x110
[ 105.186620] entry_SYSCALL_64_after_hwframe+0x76/0xe0
[ 105.186649] RIP: 0033:0x7f166a97455d
Temporarily add the setting of skb->_skb_refdst before bpf_test_run to resolve the issue.
Fixes: 52f278774e79 ("bpf: implement BPF_LWT_ENCAP_IP mode in bpf_lwt_push_encap")
Reported-by: Yinhao Hu <dddddd@hust.edu.cn>
Reported-by: Kaiyan Mei <M202472210@hust.edu.cn>
Closes: https://groups.google.com/g/hust-os-kernel-patches/c/8-a0kPpBW2s
Signed-off-by: Yun Lu <luyun@kylinos.cn>
Signed-off-by: Feng Yang <yangfeng@kylinos.cn>
Tested-by: syzbot@syzkaller.appspotmail.com
---
Changes in v5:
- Refer to the bpf_lwt_xmit_reroute function to configure the dst parameter.
- Link to v4: https://lore.kernel.org/all/20260209015111.28144-1-yangfeng59949@163.com/
Changes in v4:
- add rcu lock
- Link to v3: https://lore.kernel.org/all/20260206055113.63476-1-yangfeng59949@163.com/
Changes in v3:
- use dst_init
- Link to v2: https://lore.kernel.org/all/20260205092227.126665-1-yangfeng59949@163.com/
Changes in v2:
- Link to v1: https://lore.kernel.org/all/20260127084520.13890-1-luyun_611@163.com/
---
net/bpf/test_run.c | 47 ++++++++++++++++++++++++++++++++++++++++++++++
1 file changed, 47 insertions(+)
diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c
index 178c4738e63b..dbd2c44da7e5 100644
--- a/net/bpf/test_run.c
+++ b/net/bpf/test_run.c
@@ -24,6 +24,7 @@
#include <net/netdev_rx_queue.h>
#include <net/xdp.h>
#include <net/netfilter/nf_bpf_link.h>
+#include <net/ip6_route.h>
#define CREATE_TRACE_POINTS
#include <trace/events/bpf_test_run.h>
@@ -992,6 +993,7 @@ int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr,
u32 headroom = NET_SKB_PAD + NET_IP_ALIGN;
u32 linear_sz = kattr->test.data_size_in;
u32 repeat = kattr->test.repeat;
+ struct dst_entry *dst = NULL;
struct __sk_buff *ctx = NULL;
struct sk_buff *skb = NULL;
struct sock *sk = NULL;
@@ -1156,6 +1158,51 @@ int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr,
skb->ip_summed = CHECKSUM_COMPLETE;
}
+ if (prog->type == BPF_PROG_TYPE_LWT_XMIT && !skb_dst(skb)) {
+ struct flowi4 fl4 = {};
+ struct flowi6 fl6 = {};
+ struct rtable *rt;
+
+ switch (skb->protocol) {
+ case htons(ETH_P_IP):
+ if (sizeof(struct iphdr) <= skb_headlen(skb)) {
+ fl4.saddr = ip_hdr(skb)->saddr;
+ fl4.daddr = ip_hdr(skb)->daddr;
+ }
+
+ rt = ip_route_output_key(net, &fl4);
+ if (IS_ERR(rt)) {
+ ret = PTR_ERR(rt);
+ goto out;
+ }
+ dst = &rt->dst;
+ break;
+#if IS_ENABLED(CONFIG_IPV6)
+ case htons(ETH_P_IPV6):
+ if (sizeof(struct ipv6hdr) <= skb_headlen(skb)) {
+ fl6.saddr = ipv6_hdr(skb)->saddr;
+ fl6.daddr = ipv6_hdr(skb)->daddr;
+ }
+
+ dst = ip6_route_output(net, NULL, &fl6);
+ if (IS_ERR(dst)) {
+ ret = PTR_ERR(dst);
+ goto out;
+ }
+ break;
+#endif
+ default:
+ ret = -EINVAL;
+ goto out;
+ }
+
+ if (unlikely(dst->error)) {
+ ret = dst->error;
+ dst_release(dst);
+ goto out;
+ }
+ skb_dst_set(skb, dst);
+ }
ret = bpf_test_run(prog, skb, repeat, &retval, &duration, false);
if (ret)
goto out;
--
2.43.0© 2016 - 2026 Red Hat, Inc.