1. Patchew
  2. linux
  3. View series

[PATCH v3] bpf: test_run: Fix the null pointer dereference issue in bpf_lwt_xmit_push_encap

Feng Yang posted 1 patch 1 day, 4 hours ago 
net/bpf/test_run.c | 7 +++++++
1 file changed, 7 insertions(+)
[PATCH v3] bpf: test_run: Fix the null pointer dereference issue in bpf_lwt_xmit_push_encap
Posted by Feng Yang 1 day, 4 hours ago 
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>
Signed-off-by: Yun Lu <luyun@kylinos.cn>
Signed-off-by: Feng Yang <yangfeng@kylinos.cn>
---
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 | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c
index 178c4738e63b..3e1c47d53b82 100644
--- a/net/bpf/test_run.c
+++ b/net/bpf/test_run.c
@@ -989,6 +989,7 @@ int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr,
 	u32 tailroom = SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
 	struct net *net = current->nsproxy->net_ns;
 	struct net_device *dev = net->loopback_dev;
+	struct dst_entry bpf_test_run_lwt_xmit_dst;
 	u32 headroom = NET_SKB_PAD + NET_IP_ALIGN;
 	u32 linear_sz = kattr->test.data_size_in;
 	u32 repeat = kattr->test.repeat;
@@ -1156,6 +1157,12 @@ 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) {
+		dst_init(&bpf_test_run_lwt_xmit_dst, NULL, NULL,
+			 DST_OBSOLETE_NONE, DST_NOCOUNT);
+		bpf_test_run_lwt_xmit_dst.dev = dev;
+		skb_dst_set_noref(skb, &bpf_test_run_lwt_xmit_dst);
+	}
 	ret = bpf_test_run(prog, skb, repeat, &retval, &duration, false);
 	if (ret)
 		goto out;
-- 
2.43.0
[syzbot ci] Re: bpf: test_run: Fix the null pointer dereference issue in bpf_lwt_xmit_push_encap
Posted by syzbot ci 23 hours ago 
syzbot ci has tested the following series

[v3] bpf: test_run: Fix the null pointer dereference issue in bpf_lwt_xmit_push_encap
https://lore.kernel.org/all/20260206055113.63476-1-yangfeng59949@163.com
* [PATCH v3] bpf: test_run: Fix the null pointer dereference issue in bpf_lwt_xmit_push_encap

and found the following issue:
WARNING in skb_dst_set_noref

Full report is available here:
https://ci.syzbot.org/series/ebdff606-6251-4db9-ab50-448f5433094a

***

WARNING in skb_dst_set_noref

tree:      bpf-next
URL:       https://kernel.googlesource.com/pub/scm/linux/kernel/git/bpf/bpf-next.git
base:      1ace9bac1ad2bc6a0a70baaa16d22b7e783e88c5
arch:      amd64
compiler:  Debian clang version 21.1.8 (++20251221033036+2078da43e25a-1~exp1~20251221153213.50), Debian LLD 21.1.8
config:    https://ci.syzbot.org/builds/673700c1-fa90-4aa2-8342-e6b397961829/config
C repro:   https://ci.syzbot.org/findings/ad5a5f81-3d84-45ac-90ec-9a169eb16405/c_repro
syz repro: https://ci.syzbot.org/findings/ad5a5f81-3d84-45ac-90ec-9a169eb16405/syz_repro

------------[ cut here ]------------
!rcu_read_lock_held() && !rcu_read_lock_bh_held()
WARNING: ./include/linux/skbuff.h:1235 at skb_dst_set_noref+0x14a/0x1a0 include/linux/skbuff.h:1235, CPU#1: syz.0.17/5979
Modules linked in:
CPU: 1 UID: 0 PID: 5979 Comm: syz.0.17 Not tainted syzkaller #0 PREEMPT(full) 
Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.16.2-debian-1.16.2-1 04/01/2014
RIP: 0010:skb_dst_set_noref+0x14a/0x1a0 include/linux/skbuff.h:1235
Code: 5d 00 48 83 c4 08 5b 41 5c 41 5d 41 5e 41 5f 5d e9 9b 80 e9 01 cc e8 95 58 30 f8 90 0f 0b 90 e9 2f ff ff ff e8 87 58 30 f8 90 <0f> 0b 90 e9 5d ff ff ff 44 89 e1 80 e1 07 38 c1 0f 8c 76 ff ff ff
RSP: 0018:ffffc90004487a20 EFLAGS: 00010293
RAX: ffffffff89923f99 RBX: ffffc90004487ba0 RCX: ffff888103713a80
RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000000000
RBP: 0000000000000000 R08: ffffc90004487be3 R09: 1ffff92000890f7c
R10: dffffc0000000000 R11: fffff52000890f7d R12: 0000000000000000
R13: ffff88817331d858 R14: 1ffff1102e663b0b R15: ffff88817331d800
FS:  0000555590ae6500(0000) GS:ffff8882a9928000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 0000001b2fb63fff CR3: 00000001139cc000 CR4: 00000000000006f0
Call Trace:
 <TASK>
 bpf_prog_test_run_skb+0xed8/0x1eb0 net/bpf/test_run.c:1164
 bpf_prog_test_run+0x2c7/0x340 kernel/bpf/syscall.c:4721
 __sys_bpf+0x643/0x950 kernel/bpf/syscall.c:6246
 __do_sys_bpf kernel/bpf/syscall.c:6341 [inline]
 __se_sys_bpf kernel/bpf/syscall.c:6339 [inline]
 __x64_sys_bpf+0x7c/0x90 kernel/bpf/syscall.c:6339
 do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline]
 do_syscall_64+0xe2/0xf80 arch/x86/entry/syscall_64.c:94
 entry_SYSCALL_64_after_hwframe+0x77/0x7f
RIP: 0033:0x7f21c579acb9
Code: ff c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 e8 ff ff ff f7 d8 64 89 01 48
RSP: 002b:00007fff4c8461d8 EFLAGS: 00000246 ORIG_RAX: 0000000000000141
RAX: ffffffffffffffda RBX: 00007f21c5a15fa0 RCX: 00007f21c579acb9
RDX: 0000000000000050 RSI: 0000200000000780 RDI: 000000000000000a
RBP: 00007f21c5808bf7 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000
R13: 00007f21c5a15fac R14: 00007f21c5a15fa0 R15: 00007f21c5a15fa0
 </TASK>


***

If these findings have caused you to resend the series or submit a
separate fix, please add the following tag to your commit message:
  Tested-by: syzbot@syzkaller.appspotmail.com

---
This report is generated by a bot. It may contain errors.
syzbot ci engineers can be reached at syzkaller@googlegroups.com.
Re: [PATCH v3] bpf: test_run: Fix the null pointer dereference issue in bpf_lwt_xmit_push_encap
Posted by bot+bpf-ci@kernel.org 1 day, 3 hours ago 
> diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c
> --- a/net/bpf/test_run.c
> +++ b/net/bpf/test_run.c
> @@ -989,6 +989,7 @@ int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr,
>  	u32 tailroom = SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
>  	struct net *net = current->nsproxy->net_ns;
>  	struct net_device *dev = net->loopback_dev;
> +	struct dst_entry bpf_test_run_lwt_xmit_dst;
>  	u32 headroom = NET_SKB_PAD + NET_IP_ALIGN;

[ ... ]

> @@ -1156,6 +1157,12 @@
>  		skb->ip_summed = CHECKSUM_COMPLETE;
>  	}
>
> +	if (prog->type == BPF_PROG_TYPE_LWT_XMIT) {
> +		dst_init(&bpf_test_run_lwt_xmit_dst, NULL, NULL,
> +			 DST_OBSOLETE_NONE, DST_NOCOUNT);
> +		bpf_test_run_lwt_xmit_dst.dev = dev;
> +		skb_dst_set_noref(skb, &bpf_test_run_lwt_xmit_dst);
> +	}

Will skb_dst_set_noref() trigger a WARN_ON here? Looking at the function
in include/linux/skbuff.h:

    static inline void skb_dst_set_noref(struct sk_buff *skb, struct dst_entry *dst)
    {
        skb_dst_check_unset(skb);
        WARN_ON(!rcu_read_lock_held() && !rcu_read_lock_bh_held());
        ...
    }

This code runs from syscall context in bpf_prog_test_run_skb() before
bpf_test_run() is called. At this point, neither rcu_read_lock() nor
local_bh_disable() is held - local_bh_disable() is only called inside
bpf_test_run().

Should the dst setup be wrapped with rcu_read_lock()/rcu_read_unlock(),
or moved inside bpf_test_run() where RCU-bh context is already held?


---
AI reviewed your patch. Please fix the bug or email reply why it's not a bug.
See: https://github.com/kernel-patches/vmtest/blob/master/ci/claude/README.md

CI run summary: https://github.com/kernel-patches/bpf/actions/runs/21740645384

AI-authorship-score: low
AI-authorship-explanation: The commit shows human authorship with real bug reporters from HUST, actual crash stack trace, self-aware comment using Temporarily, and author from kylinos.cn Linux distribution company.
issues-found: 1
issue-severity-score: low
issue-severity-explanation: WARN_ON will trigger in skb_dst_set_noref due to missing RCU context, causing kernel log warnings but no functional impact.

Patchew 2.1-devel-b67e4c2

© 2016 - 2026 Red Hat, Inc.