Raw packet from PF_PACKET socket ontop of an IPv6-backed ipvlan device will
hit WARN_ON_ONCE() in sk_mc_loop() through sch_direct_xmit() path.
WARNING: CPU: 2 PID: 0 at net/core/sock.c:775 sk_mc_loop+0x2d/0x70
Modules linked in: sch_netem ipvlan rfkill cirrus drm_shmem_helper sg drm_kms_helper
CPU: 2 PID: 0 Comm: swapper/2 Kdump: loaded Not tainted 6.9.0+ #279
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.15.0-1 04/01/2014
RIP: 0010:sk_mc_loop+0x2d/0x70
Code: fa 0f 1f 44 00 00 65 0f b7 15 f7 96 a3 4f 31 c0 66 85 d2 75 26 48 85 ff 74 1c
RSP: 0018:ffffa9584015cd78 EFLAGS: 00010212
RAX: 0000000000000011 RBX: ffff91e585793e00 RCX: 0000000002c6a001
RDX: 0000000000000000 RSI: 0000000000000040 RDI: ffff91e589c0f000
RBP: ffff91e5855bd100 R08: 0000000000000000 R09: 3d00545216f43d00
R10: ffff91e584fdcc50 R11: 00000060dd8616f4 R12: ffff91e58132d000
R13: ffff91e584fdcc68 R14: ffff91e5869ce800 R15: ffff91e589c0f000
FS: 0000000000000000(0000) GS:ffff91e898100000(0000) knlGS:0000000000000000
CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00007f788f7c44c0 CR3: 0000000008e1a000 CR4: 00000000000006f0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
Call Trace:
<IRQ>
? __warn (kernel/panic.c:693)
? sk_mc_loop (net/core/sock.c:760)
? report_bug (lib/bug.c:201 lib/bug.c:219)
? handle_bug (arch/x86/kernel/traps.c:239)
? exc_invalid_op (arch/x86/kernel/traps.c:260 (discriminator 1))
? asm_exc_invalid_op (./arch/x86/include/asm/idtentry.h:621)
? sk_mc_loop (net/core/sock.c:760)
ip6_finish_output2 (net/ipv6/ip6_output.c:83 (discriminator 1))
? nf_hook_slow (net/netfilter/core.c:626)
ip6_finish_output (net/ipv6/ip6_output.c:222)
? __pfx_ip6_finish_output (net/ipv6/ip6_output.c:215)
ipvlan_xmit_mode_l3 (drivers/net/ipvlan/ipvlan_core.c:602) ipvlan
ipvlan_start_xmit (drivers/net/ipvlan/ipvlan_main.c:226) ipvlan
dev_hard_start_xmit (net/core/dev.c:3594)
sch_direct_xmit (net/sched/sch_generic.c:343)
__qdisc_run (net/sched/sch_generic.c:416)
net_tx_action (net/core/dev.c:5286)
handle_softirqs (kernel/softirq.c:555)
__irq_exit_rcu (kernel/softirq.c:589)
sysvec_apic_timer_interrupt (arch/x86/kernel/apic/apic.c:1043)
The warning triggers as this:
packet_sendmsg
packet_snd //skb->sk is packet sk
__dev_queue_xmit
__dev_xmit_skb //q->enqueue is not NULL
__qdisc_run
sch_direct_xmit
dev_hard_start_xmit
ipvlan_start_xmit
ipvlan_xmit_mode_l3 //l3 mode
ipvlan_process_outbound //vepa flag
ipvlan_process_v6_outbound
ip6_local_out
__ip6_finish_output
ip6_finish_output2 //multicast packet
sk_mc_loop //sk->sk_family is AF_PACKET
Call ip{6}_local_out() with NULL sk in ipvlan as other tunnels to fix this.
Fixes: f60e5990d9c1 ("ipv6: protect skb->sk accesses from recursive dereference inside the stack")
Suggested-by: Eric Dumazet <[email protected]>
Signed-off-by: Yue Haibing <[email protected]>
---
drivers/net/ipvlan/ipvlan_core.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers/net/ipvlan/ipvlan_core.c b/drivers/net/ipvlan/ipvlan_core.c
index 2d5b021b4ea6..fef4eff7753a 100644
--- a/drivers/net/ipvlan/ipvlan_core.c
+++ b/drivers/net/ipvlan/ipvlan_core.c
@@ -439,7 +439,7 @@ static noinline_for_stack int ipvlan_process_v4_outbound(struct sk_buff *skb)
memset(IPCB(skb), 0, sizeof(*IPCB(skb)));
- err = ip_local_out(net, skb->sk, skb);
+ err = ip_local_out(net, NULL, skb);
if (unlikely(net_xmit_eval(err)))
DEV_STATS_INC(dev, tx_errors);
else
@@ -494,7 +494,7 @@ static int ipvlan_process_v6_outbound(struct sk_buff *skb)
memset(IP6CB(skb), 0, sizeof(*IP6CB(skb)));
- err = ip6_local_out(dev_net(dev), skb->sk, skb);
+ err = ip6_local_out(dev_net(dev), NULL, skb);
if (unlikely(net_xmit_eval(err)))
DEV_STATS_INC(dev, tx_errors);
else
--
2.34.1
On Sat, 2024-05-25 at 11:42 +0800, Yue Haibing wrote:
> Raw packet from PF_PACKET socket ontop of an IPv6-backed ipvlan device will
> hit WARN_ON_ONCE() in sk_mc_loop() through sch_direct_xmit() path.
>
> WARNING: CPU: 2 PID: 0 at net/core/sock.c:775 sk_mc_loop+0x2d/0x70
> Modules linked in: sch_netem ipvlan rfkill cirrus drm_shmem_helper sg drm_kms_helper
> CPU: 2 PID: 0 Comm: swapper/2 Kdump: loaded Not tainted 6.9.0+ #279
> Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.15.0-1 04/01/2014
> RIP: 0010:sk_mc_loop+0x2d/0x70
> Code: fa 0f 1f 44 00 00 65 0f b7 15 f7 96 a3 4f 31 c0 66 85 d2 75 26 48 85 ff 74 1c
> RSP: 0018:ffffa9584015cd78 EFLAGS: 00010212
> RAX: 0000000000000011 RBX: ffff91e585793e00 RCX: 0000000002c6a001
> RDX: 0000000000000000 RSI: 0000000000000040 RDI: ffff91e589c0f000
> RBP: ffff91e5855bd100 R08: 0000000000000000 R09: 3d00545216f43d00
> R10: ffff91e584fdcc50 R11: 00000060dd8616f4 R12: ffff91e58132d000
> R13: ffff91e584fdcc68 R14: ffff91e5869ce800 R15: ffff91e589c0f000
> FS: 0000000000000000(0000) GS:ffff91e898100000(0000) knlGS:0000000000000000
> CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
> CR2: 00007f788f7c44c0 CR3: 0000000008e1a000 CR4: 00000000000006f0
> DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
> DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
> Call Trace:
> <IRQ>
> ? __warn (kernel/panic.c:693)
> ? sk_mc_loop (net/core/sock.c:760)
> ? report_bug (lib/bug.c:201 lib/bug.c:219)
> ? handle_bug (arch/x86/kernel/traps.c:239)
> ? exc_invalid_op (arch/x86/kernel/traps.c:260 (discriminator 1))
> ? asm_exc_invalid_op (./arch/x86/include/asm/idtentry.h:621)
> ? sk_mc_loop (net/core/sock.c:760)
> ip6_finish_output2 (net/ipv6/ip6_output.c:83 (discriminator 1))
> ? nf_hook_slow (net/netfilter/core.c:626)
> ip6_finish_output (net/ipv6/ip6_output.c:222)
> ? __pfx_ip6_finish_output (net/ipv6/ip6_output.c:215)
> ipvlan_xmit_mode_l3 (drivers/net/ipvlan/ipvlan_core.c:602) ipvlan
> ipvlan_start_xmit (drivers/net/ipvlan/ipvlan_main.c:226) ipvlan
> dev_hard_start_xmit (net/core/dev.c:3594)
> sch_direct_xmit (net/sched/sch_generic.c:343)
> __qdisc_run (net/sched/sch_generic.c:416)
> net_tx_action (net/core/dev.c:5286)
> handle_softirqs (kernel/softirq.c:555)
> __irq_exit_rcu (kernel/softirq.c:589)
> sysvec_apic_timer_interrupt (arch/x86/kernel/apic/apic.c:1043)
>
> The warning triggers as this:
> packet_sendmsg
> packet_snd //skb->sk is packet sk
> __dev_queue_xmit
> __dev_xmit_skb //q->enqueue is not NULL
> __qdisc_run
> sch_direct_xmit
> dev_hard_start_xmit
> ipvlan_start_xmit
> ipvlan_xmit_mode_l3 //l3 mode
> ipvlan_process_outbound //vepa flag
> ipvlan_process_v6_outbound
> ip6_local_out
> __ip6_finish_output
> ip6_finish_output2 //multicast packet
> sk_mc_loop //sk->sk_family is AF_PACKET
>
> Call ip{6}_local_out() with NULL sk in ipvlan as other tunnels to fix this.
>
> Fixes: f60e5990d9c1 ("ipv6: protect skb->sk accesses from recursive dereference inside the stack")
The patch LGTM, but the above fixes tag looks incorrect, I think the
reproducer should splat even before such commit as the relevant warning
will be still there and should be still reachable.
Cheers,
Paolo
On 2024/5/28 19:15, Paolo Abeni wrote:
> On Sat, 2024-05-25 at 11:42 +0800, Yue Haibing wrote:
>> Raw packet from PF_PACKET socket ontop of an IPv6-backed ipvlan device will
>> hit WARN_ON_ONCE() in sk_mc_loop() through sch_direct_xmit() path.
>>
>> WARNING: CPU: 2 PID: 0 at net/core/sock.c:775 sk_mc_loop+0x2d/0x70
>> Modules linked in: sch_netem ipvlan rfkill cirrus drm_shmem_helper sg drm_kms_helper
>> CPU: 2 PID: 0 Comm: swapper/2 Kdump: loaded Not tainted 6.9.0+ #279
>> Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.15.0-1 04/01/2014
>> RIP: 0010:sk_mc_loop+0x2d/0x70
>> Code: fa 0f 1f 44 00 00 65 0f b7 15 f7 96 a3 4f 31 c0 66 85 d2 75 26 48 85 ff 74 1c
>> RSP: 0018:ffffa9584015cd78 EFLAGS: 00010212
>> RAX: 0000000000000011 RBX: ffff91e585793e00 RCX: 0000000002c6a001
>> RDX: 0000000000000000 RSI: 0000000000000040 RDI: ffff91e589c0f000
>> RBP: ffff91e5855bd100 R08: 0000000000000000 R09: 3d00545216f43d00
>> R10: ffff91e584fdcc50 R11: 00000060dd8616f4 R12: ffff91e58132d000
>> R13: ffff91e584fdcc68 R14: ffff91e5869ce800 R15: ffff91e589c0f000
>> FS: 0000000000000000(0000) GS:ffff91e898100000(0000) knlGS:0000000000000000
>> CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
>> CR2: 00007f788f7c44c0 CR3: 0000000008e1a000 CR4: 00000000000006f0
>> DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
>> DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
>> Call Trace:
>> <IRQ>
>> ? __warn (kernel/panic.c:693)
>> ? sk_mc_loop (net/core/sock.c:760)
>> ? report_bug (lib/bug.c:201 lib/bug.c:219)
>> ? handle_bug (arch/x86/kernel/traps.c:239)
>> ? exc_invalid_op (arch/x86/kernel/traps.c:260 (discriminator 1))
>> ? asm_exc_invalid_op (./arch/x86/include/asm/idtentry.h:621)
>> ? sk_mc_loop (net/core/sock.c:760)
>> ip6_finish_output2 (net/ipv6/ip6_output.c:83 (discriminator 1))
>> ? nf_hook_slow (net/netfilter/core.c:626)
>> ip6_finish_output (net/ipv6/ip6_output.c:222)
>> ? __pfx_ip6_finish_output (net/ipv6/ip6_output.c:215)
>> ipvlan_xmit_mode_l3 (drivers/net/ipvlan/ipvlan_core.c:602) ipvlan
>> ipvlan_start_xmit (drivers/net/ipvlan/ipvlan_main.c:226) ipvlan
>> dev_hard_start_xmit (net/core/dev.c:3594)
>> sch_direct_xmit (net/sched/sch_generic.c:343)
>> __qdisc_run (net/sched/sch_generic.c:416)
>> net_tx_action (net/core/dev.c:5286)
>> handle_softirqs (kernel/softirq.c:555)
>> __irq_exit_rcu (kernel/softirq.c:589)
>> sysvec_apic_timer_interrupt (arch/x86/kernel/apic/apic.c:1043)
>>
>> The warning triggers as this:
>> packet_sendmsg
>> packet_snd //skb->sk is packet sk
>> __dev_queue_xmit
>> __dev_xmit_skb //q->enqueue is not NULL
>> __qdisc_run
>> sch_direct_xmit
>> dev_hard_start_xmit
>> ipvlan_start_xmit
>> ipvlan_xmit_mode_l3 //l3 mode
>> ipvlan_process_outbound //vepa flag
>> ipvlan_process_v6_outbound
>> ip6_local_out
>> __ip6_finish_output
>> ip6_finish_output2 //multicast packet
>> sk_mc_loop //sk->sk_family is AF_PACKET
>>
>> Call ip{6}_local_out() with NULL sk in ipvlan as other tunnels to fix this.
>>
>> Fixes: f60e5990d9c1 ("ipv6: protect skb->sk accesses from recursive dereference inside the stack")
>
> The patch LGTM, but the above fixes tag looks incorrect, I think the
> reproducer should splat even before such commit as the relevant warning
> will be still there and should be still reachable.
Yes, it should be Fixes: 2ad7bf363841 ("ipvlan: Initial check-in of the IPVLAN driver."), will post v2.
>
> Cheers,
>
> Paolo
>
> .
>