skbuff: skb_under_panic warning in 3.10rc7+

skbuff: skb_under_panic warning in 3.10rc7+

[Dave Jones]

skbuff: skb_under_panic: text:ffffffff816765f6 len:48 put:40 head:ffff88013deb6df0 data:ffff88013deb6dec tail:0x2c end:0xc0 dev:<NULL>
------------[ cut here ]------------
kernel BUG at net/core/skbuff.c:126!
invalid opcode: 0000 [#1] PREEMPT SMP DEBUG_PAGEALLOC
Modules linked in: dccp_ipv4 dccp 8021q garp bridge stp dlci mpoa snd_seq_dummy sctp fuse hidp tun bnep nfnetlink scsi_transport_iscsi rfcomm can_raw can_bcm af_802154 appletalk caif_socket can caif ipt_ULOG x25 rose af_key pppoe pppox ipx phonet irda llc2 ppp_generic slhc p8023 psnap p8022 llc crc_ccitt atm bluetooth netrom ax25 nfc rfkill rds af_rxrpc coretemp hwmon kvm_intel kvm crc32c_intel snd_hda_codec_realtek ghash_clmulni_intel microcode pcspkr snd_hda_codec_hdmi snd_hda_intel snd_hda_codec snd_hwdep usb_debug snd_seq snd_seq_device snd_pcm e1000e snd_page_alloc snd_timer ptp snd pps_core soundcore xfs libcrc32c
CPU: 2 PID: 8095 Comm: trinity-child2 Not tainted 3.10.0-rc7+ #37 
task: ffff8801f52c2520 ti: ffff8801e6430000 task.ti: ffff8801e6430000
RIP: 0010:[<ffffffff816e759c>]  [<ffffffff816e759c>] skb_panic+0x63/0x65
RSP: 0018:ffff8801e6431de8  EFLAGS: 00010282
RAX: 0000000000000086 RBX: ffff8802353d3cc0 RCX: 0000000000000006
RDX: 0000000000003b90 RSI: ffff8801f52c2ca0 RDI: ffff8801f52c2520
RBP: ffff8801e6431e08 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000001 R11: 0000000000000001 R12: ffff88022ea0c800
R13: ffff88022ea0cdf8 R14: ffff8802353ecb40 R15: ffffffff81cc7800
FS:  00007f5720a10740(0000) GS:ffff880244c00000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 0000000005862000 CR3: 000000022843c000 CR4: 00000000001407e0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000600
Stack:
 ffff88013deb6dec 000000000000002c 00000000000000c0 ffffffff81a3f6e4
 ffff8801e6431e18 ffffffff8159a9aa ffff8801e6431e90 ffffffff816765f6
 ffffffff810b756b 0000000700000002 ffff8801e6431e40 0000fea9292aa8c0
Call Trace:
 [<ffffffff8159a9aa>] skb_push+0x3a/0x40
 [<ffffffff816765f6>] ip6_push_pending_frames+0x1f6/0x4d0
 [<ffffffff810b756b>] ? mark_held_locks+0xbb/0x140
 [<ffffffff81694919>] udp_v6_push_pending_frames+0x2b9/0x3d0
 [<ffffffff81694660>] ? udplite_getfrag+0x20/0x20
 [<ffffffff8162092a>] udp_lib_setsockopt+0x1aa/0x1f0
 [<ffffffff811cc5e7>] ? fget_light+0x387/0x4f0
 [<ffffffff816958a4>] udpv6_setsockopt+0x34/0x40
 [<ffffffff815949f4>] sock_common_setsockopt+0x14/0x20
 [<ffffffff81593c31>] SyS_setsockopt+0x71/0xd0
 [<ffffffff816f5d54>] tracesys+0xdd/0xe2
Code: 00 00 48 89 44 24 10 8b 87 d8 00 00 00 48 89 44 24 08 48 8b 87 e8 00 00 00 48 c7 c7 c0 04 aa 81 48 89 04 24 31 c0 e8 e1 7e ff ff <0f> 0b 55 48 89 e5 0f 0b 55 48 89 e5 0f 0b 55 48 89 e5 0f 0b 55 
RIP  [<ffffffff816e759c>] skb_panic+0x63/0x65
 RSP <ffff8801e6431de8>

Re: skbuff: skb_under_panic warning in 3.10rc7+

[Hannes Frederic Sowa]

On Sun, Jun 30, 2013 at 12:02:46PM -0400, Dave Jones wrote:
> skbuff: skb_under_panic: text:ffffffff816765f6 len:48 put:40 head:ffff88013deb6df0 data:ffff88013deb6dec tail:0x2c end:0xc0 dev:<NULL>
> ------------[ cut here ]------------
> kernel BUG at net/core/skbuff.c:126!
> invalid opcode: 0000 [#1] PREEMPT SMP DEBUG_PAGEALLOC
> Modules linked in: dccp_ipv4 dccp 8021q garp bridge stp dlci mpoa snd_seq_dummy sctp fuse hidp tun bnep nfnetlink scsi_transport_iscsi rfcomm can_raw can_bcm af_802154 appletalk caif_socket can caif ipt_ULOG x25 rose af_key pppoe pppox ipx phonet irda llc2 ppp_generic slhc p8023 psnap p8022 llc crc_ccitt atm bluetooth netrom ax25 nfc rfkill rds af_rxrpc coretemp hwmon kvm_intel kvm crc32c_intel snd_hda_codec_realtek ghash_clmulni_intel microcode pcspkr snd_hda_codec_hdmi snd_hda_intel snd_hda_codec snd_hwdep usb_debug snd_seq snd_seq_device snd_pcm e1000e snd_page_alloc snd_timer ptp snd pps_core soundcore xfs libcrc32c
> CPU: 2 PID: 8095 Comm: trinity-child2 Not tainted 3.10.0-rc7+ #37 
> task: ffff8801f52c2520 ti: ffff8801e6430000 task.ti: ffff8801e6430000
> RIP: 0010:[<ffffffff816e759c>]  [<ffffffff816e759c>] skb_panic+0x63/0x65
> RSP: 0018:ffff8801e6431de8  EFLAGS: 00010282
> RAX: 0000000000000086 RBX: ffff8802353d3cc0 RCX: 0000000000000006
> RDX: 0000000000003b90 RSI: ffff8801f52c2ca0 RDI: ffff8801f52c2520
> RBP: ffff8801e6431e08 R08: 0000000000000000 R09: 0000000000000000
> R10: 0000000000000001 R11: 0000000000000001 R12: ffff88022ea0c800
> R13: ffff88022ea0cdf8 R14: ffff8802353ecb40 R15: ffffffff81cc7800
> FS:  00007f5720a10740(0000) GS:ffff880244c00000(0000) knlGS:0000000000000000
> CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
> CR2: 0000000005862000 CR3: 000000022843c000 CR4: 00000000001407e0
> DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
> DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000600
> Stack:
>  ffff88013deb6dec 000000000000002c 00000000000000c0 ffffffff81a3f6e4
>  ffff8801e6431e18 ffffffff8159a9aa ffff8801e6431e90 ffffffff816765f6
>  ffffffff810b756b 0000000700000002 ffff8801e6431e40 0000fea9292aa8c0
> Call Trace:
>  [<ffffffff8159a9aa>] skb_push+0x3a/0x40
>  [<ffffffff816765f6>] ip6_push_pending_frames+0x1f6/0x4d0
>  [<ffffffff810b756b>] ? mark_held_locks+0xbb/0x140
>  [<ffffffff81694919>] udp_v6_push_pending_frames+0x2b9/0x3d0
>  [<ffffffff81694660>] ? udplite_getfrag+0x20/0x20
>  [<ffffffff8162092a>] udp_lib_setsockopt+0x1aa/0x1f0
>  [<ffffffff811cc5e7>] ? fget_light+0x387/0x4f0
>  [<ffffffff816958a4>] udpv6_setsockopt+0x34/0x40
>  [<ffffffff815949f4>] sock_common_setsockopt+0x14/0x20
>  [<ffffffff81593c31>] SyS_setsockopt+0x71/0xd0
>  [<ffffffff816f5d54>] tracesys+0xdd/0xe2
> Code: 00 00 48 89 44 24 10 8b 87 d8 00 00 00 48 89 44 24 08 48 8b 87 e8 00 00 00 48 c7 c7 c0 04 aa 81 48 89 04 24 31 c0 e8 e1 7e ff ff <0f> 0b 55 48 89 e5 0f 0b 55 48 89 e5 0f 0b 55 48 89 e5 0f 0b 55 
> RIP  [<ffffffff816e759c>] skb_panic+0x63/0x65
>  RSP <ffff8801e6431de8>

We need to add some logic to reallocate skbs in case of UDP_CORK and if
extension headers are in use. A small test with UDP_CORK and IPV6_DSTOPTS
resulted in this (some lines below your crash in ip6_append_data):

[37598.993962] ------------[ cut here ]------------
[37598.994008] kernel BUG at net/core/skbuff.c:2064!
[37598.994008] invalid opcode: 0000 [#1] SMP 
[37598.994008] Modules linked in: tcp_lp uvcvideo videobuf2_vmalloc videobuf2_memops videobuf2_core videodev media vfat fat usb_storage fuse ebtable_nat xt_CHECKSUM bridge stp llc ipt_MASQUERADE nf_conntrack_netbios_ns nf_conntrack_broadcast ip6table_mangle ip6t_REJECT nf_conntrack_ipv6 nf_defrag_ipv6 iptable_nat nf_nat_ipv4 nf_nat iptable_mangle nf_conntrack_ipv4 nf_defrag_ipv4 xt_conntrack nf_conntrack ebtable_filter ebtables ip6table_filter ip6_tables be2iscsi iscsi_boot_sysfs bnx2i cnic uio cxgb4i cxgb4 cxgb3i cxgb3 mdio libcxgbi ib_iser rdma_cm ib_addr iw_cm ib_cm ib_sa ib_mad ib_core iscsi_tcp libiscsi_tcp libiscsi scsi_transport_iscsi rfcomm bnep iTCO_wdt iTCO_vendor_support snd_hda_codec_conexant arc4 iwldvm mac80211 snd_hda_intel acpi_cpufreq mperf coretemp snd_hda_codec microcode
  cdc_wdm cdc_acm
[37598.994008]  snd_hwdep cdc_ether snd_seq snd_seq_device usbnet mii joydev btusb snd_pcm bluetooth i2c_i801 e1000e lpc_ich mfd_core ptp iwlwifi pps_core snd_page_alloc mei cfg80211 snd_timer thinkpad_acpi snd tpm_tis soundcore rfkill tpm tpm_bios vhost_net tun macvtap macvlan kvm_intel kvm uinput binfmt_misc dm_crypt i915 i2c_algo_bit drm_kms_helper drm i2c_core wmi video
[37598.994008] CPU 0 
[37598.994008] Pid: 27320, comm: t2 Not tainted 3.9.6-200.fc18.x86_64 #1 LENOVO 27744PG/27744PG
[37598.994008] RIP: 0010:[<ffffffff815443a5>]  [<ffffffff815443a5>] skb_copy_and_csum_bits+0x325/0x330
[37598.994008] RSP: 0018:ffff88003670da18  EFLAGS: 00010202
[37598.994008] RAX: ffff88018105c018 RBX: 0000000000000004 RCX: 00000000000006c0
[37598.994008] RDX: ffff88018105a6c0 RSI: ffff88018105a000 RDI: ffff8801e1b0aa00
[37598.994008] RBP: ffff88003670da78 R08: 0000000000000000 R09: ffff88018105c040
[37598.994008] R10: ffff8801e1b0aa00 R11: 0000000000000000 R12: 000000000000fff8
[37598.994008] R13: 00000000000004fc R14: 00000000ffff0504 R15: 0000000000000000
[37598.994008] FS:  00007f28eea59740(0000) GS:ffff88023bc00000(0000) knlGS:0000000000000000
[37598.994008] CS:  0010 DS: 0000 ES: 0000 CR0: 000000008005003b
[37598.994008] CR2: 0000003d935789e0 CR3: 00000000365cb000 CR4: 00000000000407f0
[37598.994008] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[37598.994008] DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400
[37598.994008] Process t2 (pid: 27320, threadinfo ffff88003670c000, task ffff88022c162ee0)
[37598.994008] Stack:
[37598.994008]  ffff88022e098a00 ffff88020f973fc0 0000000000000008 00000000000004c8
[37598.994008]  ffff88020f973fc0 00000000000004c4 ffff88003670da78 ffff8801e1b0a200
[37598.994008]  0000000000000018 00000000000004c8 ffff88020f973fc0 00000000000004c4
[37598.994008] Call Trace:
[37598.994008]  [<ffffffff815fc21f>] ip6_append_data+0xccf/0xfe0
[37598.994008]  [<ffffffff8158d9f0>] ? ip_copy_metadata+0x1a0/0x1a0
[37598.994008]  [<ffffffff81661f66>] ? _raw_spin_lock_bh+0x16/0x40
[37598.994008]  [<ffffffff8161548d>] udpv6_sendmsg+0x1ed/0xc10
[37598.994008]  [<ffffffff812a2845>] ? sock_has_perm+0x75/0x90
[37598.994008]  [<ffffffff815c3693>] inet_sendmsg+0x63/0xb0
[37598.994008]  [<ffffffff812a2973>] ? selinux_socket_sendmsg+0x23/0x30
[37598.994008]  [<ffffffff8153a450>] sock_sendmsg+0xb0/0xe0
[37598.994008]  [<ffffffff810135d1>] ? __switch_to+0x181/0x4a0
[37598.994008]  [<ffffffff8153d97d>] sys_sendto+0x12d/0x180
[37598.994008]  [<ffffffff810dfb64>] ? __audit_syscall_entry+0x94/0xf0
[37598.994008]  [<ffffffff81020ed1>] ? syscall_trace_enter+0x231/0x240
[37598.994008]  [<ffffffff8166a7e7>] tracesys+0xdd/0xe2
[37598.994008] Code: fe 07 00 00 48 c7 c7 04 28 a6 81 89 45 a0 4c 89 4d b8 44 89 5d a8 e8 1b ac b1 ff 44 8b 5d a8 4c 8b 4d b8 8b 45 a0 e9 cf fe ff ff <0f> 0b 66 0f 1f 84 00 00 00 00 00 66 66 66 66 90 55 48 89 e5 48 
[37598.994008] RIP  [<ffffffff815443a5>] skb_copy_and_csum_bits+0x325/0x330
[37598.994008]  RSP <ffff88003670da18>
[37599.007323] ---[ end trace d69f6a17f8ac8eee ]---

Re: skbuff: skb_under_panic warning in 3.10rc7+

[Hannes Frederic Sowa]

On Sun, Jun 30, 2013 at 08:29:11PM +0200, Hannes Frederic Sowa wrote:
> On Sun, Jun 30, 2013 at 12:02:46PM -0400, Dave Jones wrote:
> We need to add some logic to reallocate skbs in case of UDP_CORK and if
> extension headers are in use. A small test with UDP_CORK and IPV6_DSTOPTS
> resulted in this (some lines below your crash in ip6_append_data):

I actually had a fragment header in there, too.

Re: skbuff: skb_under_panic warning in 3.10rc7+

[Hannes Frederic Sowa]

On Sun, Jun 30, 2013 at 12:02:46PM -0400, Dave Jones wrote:
> skbuff: skb_under_panic: text:ffffffff816765f6 len:48 put:40 head:ffff88013deb6df0 data:ffff88013deb6dec tail:0x2c end:0xc0 dev:<NULL>
> ------------[ cut here ]------------
> kernel BUG at net/core/skbuff.c:126!
> invalid opcode: 0000 [#1] PREEMPT SMP DEBUG_PAGEALLOC
> Modules linked in: dccp_ipv4 dccp 8021q garp bridge stp dlci mpoa snd_seq_dummy sctp fuse hidp tun bnep nfnetlink scsi_transport_iscsi rfcomm can_raw can_bcm af_802154 appletalk caif_socket can caif ipt_ULOG x25 rose af_key pppoe pppox ipx phonet irda llc2 ppp_generic slhc p8023 psnap p8022 llc crc_ccitt atm bluetooth netrom ax25 nfc rfkill rds af_rxrpc coretemp hwmon kvm_intel kvm crc32c_intel snd_hda_codec_realtek ghash_clmulni_intel microcode pcspkr snd_hda_codec_hdmi snd_hda_intel snd_hda_codec snd_hwdep usb_debug snd_seq snd_seq_device snd_pcm e1000e snd_page_alloc snd_timer ptp snd pps_core soundcore xfs libcrc32c
> CPU: 2 PID: 8095 Comm: trinity-child2 Not tainted 3.10.0-rc7+ #37 
> task: ffff8801f52c2520 ti: ffff8801e6430000 task.ti: ffff8801e6430000
> RIP: 0010:[<ffffffff816e759c>]  [<ffffffff816e759c>] skb_panic+0x63/0x65
> RSP: 0018:ffff8801e6431de8  EFLAGS: 00010282
> RAX: 0000000000000086 RBX: ffff8802353d3cc0 RCX: 0000000000000006
> RDX: 0000000000003b90 RSI: ffff8801f52c2ca0 RDI: ffff8801f52c2520
> RBP: ffff8801e6431e08 R08: 0000000000000000 R09: 0000000000000000
> R10: 0000000000000001 R11: 0000000000000001 R12: ffff88022ea0c800
> R13: ffff88022ea0cdf8 R14: ffff8802353ecb40 R15: ffffffff81cc7800
> FS:  00007f5720a10740(0000) GS:ffff880244c00000(0000) knlGS:0000000000000000
> CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
> CR2: 0000000005862000 CR3: 000000022843c000 CR4: 00000000001407e0
> DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
> DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000600
> Stack:
>  ffff88013deb6dec 000000000000002c 00000000000000c0 ffffffff81a3f6e4
>  ffff8801e6431e18 ffffffff8159a9aa ffff8801e6431e90 ffffffff816765f6
>  ffffffff810b756b 0000000700000002 ffff8801e6431e40 0000fea9292aa8c0
> Call Trace:
>  [<ffffffff8159a9aa>] skb_push+0x3a/0x40
>  [<ffffffff816765f6>] ip6_push_pending_frames+0x1f6/0x4d0
>  [<ffffffff810b756b>] ? mark_held_locks+0xbb/0x140
>  [<ffffffff81694919>] udp_v6_push_pending_frames+0x2b9/0x3d0
>  [<ffffffff81694660>] ? udplite_getfrag+0x20/0x20
>  [<ffffffff8162092a>] udp_lib_setsockopt+0x1aa/0x1f0
>  [<ffffffff811cc5e7>] ? fget_light+0x387/0x4f0
>  [<ffffffff816958a4>] udpv6_setsockopt+0x34/0x40
>  [<ffffffff815949f4>] sock_common_setsockopt+0x14/0x20
>  [<ffffffff81593c31>] SyS_setsockopt+0x71/0xd0
>  [<ffffffff816f5d54>] tracesys+0xdd/0xe2
> Code: 00 00 48 89 44 24 10 8b 87 d8 00 00 00 48 89 44 24 08 48 8b 87 e8 00 00 00 48 c7 c7 c0 04 aa 81 48 89 04 24 31 c0 e8 e1 7e ff ff <0f> 0b 55 48 89 e5 0f 0b 55 48 89 e5 0f 0b 55 48 89 e5 0f 0b 55 
> RIP  [<ffffffff816e759c>] skb_panic+0x63/0x65
>  RSP <ffff8801e6431de8>

Dave, could you try to reproduce this Eric's patch

https://git.kernel.org/cgit/linux/kernel/git/davem/net-next.git/commit/net/ipv6/ip6_output.c?id=284041ef21fdf2e0d216ab6b787bc9072b4eb58a

cherry-picked from net-next? I could just test net-next with my testcase and
at least my BUG does not occur any more.

Thanks,

  Hannes

Re: skbuff: skb_under_panic warning in 3.10rc7+

[Hannes Frederic Sowa]

On Mon, Jul 01, 2013 at 12:13:22AM +0200, Hannes Frederic Sowa wrote:
> On Sun, Jun 30, 2013 at 12:02:46PM -0400, Dave Jones wrote:
> > skbuff: skb_under_panic: text:ffffffff816765f6 len:48 put:40 head:ffff88013deb6df0 data:ffff88013deb6dec tail:0x2c end:0xc0 dev:<NULL>
> > ------------[ cut here ]------------
> > kernel BUG at net/core/skbuff.c:126!
> > invalid opcode: 0000 [#1] PREEMPT SMP DEBUG_PAGEALLOC
> > Modules linked in: dccp_ipv4 dccp 8021q garp bridge stp dlci mpoa snd_seq_dummy sctp fuse hidp tun bnep nfnetlink scsi_transport_iscsi rfcomm can_raw can_bcm af_802154 appletalk caif_socket can caif ipt_ULOG x25 rose af_key pppoe pppox ipx phonet irda llc2 ppp_generic slhc p8023 psnap p8022 llc crc_ccitt atm bluetooth netrom ax25 nfc rfkill rds af_rxrpc coretemp hwmon kvm_intel kvm crc32c_intel snd_hda_codec_realtek ghash_clmulni_intel microcode pcspkr snd_hda_codec_hdmi snd_hda_intel snd_hda_codec snd_hwdep usb_debug snd_seq snd_seq_device snd_pcm e1000e snd_page_alloc snd_timer ptp snd pps_core soundcore xfs libcrc32c
> > CPU: 2 PID: 8095 Comm: trinity-child2 Not tainted 3.10.0-rc7+ #37 
> > task: ffff8801f52c2520 ti: ffff8801e6430000 task.ti: ffff8801e6430000
> > RIP: 0010:[<ffffffff816e759c>]  [<ffffffff816e759c>] skb_panic+0x63/0x65
> > RSP: 0018:ffff8801e6431de8  EFLAGS: 00010282
> > RAX: 0000000000000086 RBX: ffff8802353d3cc0 RCX: 0000000000000006
> > RDX: 0000000000003b90 RSI: ffff8801f52c2ca0 RDI: ffff8801f52c2520
> > RBP: ffff8801e6431e08 R08: 0000000000000000 R09: 0000000000000000
> > R10: 0000000000000001 R11: 0000000000000001 R12: ffff88022ea0c800
> > R13: ffff88022ea0cdf8 R14: ffff8802353ecb40 R15: ffffffff81cc7800
> > FS:  00007f5720a10740(0000) GS:ffff880244c00000(0000) knlGS:0000000000000000
> > CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
> > CR2: 0000000005862000 CR3: 000000022843c000 CR4: 00000000001407e0
> > DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
> > DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000600
> > Stack:
> >  ffff88013deb6dec 000000000000002c 00000000000000c0 ffffffff81a3f6e4
> >  ffff8801e6431e18 ffffffff8159a9aa ffff8801e6431e90 ffffffff816765f6
> >  ffffffff810b756b 0000000700000002 ffff8801e6431e40 0000fea9292aa8c0
> > Call Trace:
> >  [<ffffffff8159a9aa>] skb_push+0x3a/0x40
> >  [<ffffffff816765f6>] ip6_push_pending_frames+0x1f6/0x4d0
> >  [<ffffffff810b756b>] ? mark_held_locks+0xbb/0x140
> >  [<ffffffff81694919>] udp_v6_push_pending_frames+0x2b9/0x3d0
> >  [<ffffffff81694660>] ? udplite_getfrag+0x20/0x20
> >  [<ffffffff8162092a>] udp_lib_setsockopt+0x1aa/0x1f0
> >  [<ffffffff811cc5e7>] ? fget_light+0x387/0x4f0
> >  [<ffffffff816958a4>] udpv6_setsockopt+0x34/0x40
> >  [<ffffffff815949f4>] sock_common_setsockopt+0x14/0x20
> >  [<ffffffff81593c31>] SyS_setsockopt+0x71/0xd0
> >  [<ffffffff816f5d54>] tracesys+0xdd/0xe2
> > Code: 00 00 48 89 44 24 10 8b 87 d8 00 00 00 48 89 44 24 08 48 8b 87 e8 00 00 00 48 c7 c7 c0 04 aa 81 48 89 04 24 31 c0 e8 e1 7e ff ff <0f> 0b 55 48 89 e5 0f 0b 55 48 89 e5 0f 0b 55 48 89 e5 0f 0b 55 
> > RIP  [<ffffffff816e759c>] skb_panic+0x63/0x65
> >  RSP <ffff8801e6431de8>
> 
> Dave, could you try to reproduce this Eric's patch
> 
> https://git.kernel.org/cgit/linux/kernel/git/davem/net-next.git/commit/net/ipv6/ip6_output.c?id=284041ef21fdf2e0d216ab6b787bc9072b4eb58a
> 
> cherry-picked from net-next? I could just test net-next with my testcase and
> at least my BUG does not occur any more.

Sorry, I am a bit too tired. The patch is already in net. I could again
reproduce at least my crash with net-next, it just needs a bit more load
and retries to do so. I do think those BUGs are somehow connected.

Here is my test program:

-- 8< --

#include <sys/types.h>
#include <sys/socket.h>
#include <netinet/in.h>
#include <linux/udp.h>
#include <errno.h>
#include <unistd.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <stdbool.h>

int main(int argc, char **argv)
{
	int on = 1;
	int mtu = 1280;
	char buf[1220] = {0};
	
	int sockfd = socket(AF_INET6, SOCK_DGRAM, 0);
	if (sockfd < 0) {
		perror("socket");
		exit(EXIT_FAILURE);
	}
	
	if (setsockopt(sockfd, IPPROTO_UDP, UDP_CORK, &on, sizeof(on))) {
		perror("setsockopt");
		exit(EXIT_FAILURE);
	}
	
	if (setsockopt(sockfd, IPPROTO_IPV6, IPV6_MTU, &mtu, sizeof(mtu))) {
		perror("setsockopt");
		exit(EXIT_FAILURE);
	}
	
	
	struct sockaddr_in6 sa6 = {0};
	sa6.sin6_family = AF_INET6;
	sa6.sin6_port = 678;
	if (!inet_pton(AF_INET6, "::1", &sa6.sin6_addr)) {
		perror("inet_pton");
		exit(EXIT_FAILURE);
	}
	
	while (true) {
		const char dstops[8] = {0};
		if (setsockopt(sockfd, IPPROTO_IPV6, IPV6_DSTOPTS, &dstops, sizeof(dstops))) {
			perror("setsockopt");
			exit(EXIT_FAILURE);
		}
		
		if (sendto(sockfd, buf, sizeof(buf), MSG_MORE, (struct sockaddr *)&sa6,
				sizeof(sa6)) == -1) {
			perror("sendto");
			exit(EXIT_FAILURE);
		}
	}
	
	if (close(sockfd)) {
		perror("close");
		exit(EXIT_FAILURE);
	}
}

-- >8 --

What is a bit strange but I did not investiage, yet:

If the size of buf is strict smaller than 1217 I get a message too big error.
If the size of the buffer is between (inclusive) 1217 and 1224 I can trigger the bug.
If the buffer is larger than 1225 I get a message error too big, too.

I'll look at it again tomorrow.

Greetings,

  Hannes

Re: skbuff: skb_under_panic warning in 3.10rc7+

[Hannes Frederic Sowa]

On Mon, Jul 01, 2013 at 01:23:08AM +0200, Hannes Frederic Sowa wrote:
> I'll look at it again tomorrow.

[Cc Gao feng because of commit 0c1833797a5a6ec23ea9261d979aa18078720b74
("ipv6: fix incorrect ipsec fragment")]

Just a small update:

The following diff fixes the UDP_CORK case for me. I just traced the various
len variables and brought ip6_append_data_mtu in line with the initial
initialization when the first call to ip6_append_data happens.

I'll have to do more research on this and check if this correlates
somehow with Dave's report.

--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -1097,7 +1097,9 @@ static void ip6_append_data_mtu(int *mtu,
                                int *maxfraglen,
                                unsigned int fragheaderlen,
                                struct sk_buff *skb,
-                               struct rt6_info *rt)
+                               struct rt6_info *rt,
+                               __u32 frag_size,
+                               bool pmtudisc)
 {
        if (!(rt->dst.flags & DST_XFRM_TUNNEL)) {
                if (skb == NULL) {
@@ -1109,7 +1111,9 @@ static void ip6_append_data_mtu(int *mtu,
                         * this fragment is not first, the headers
                         * space is regarded as data space.
                         */
-                       *mtu = dst_mtu(rt->dst.path);
+                       *mtu = pmtudisc ? rt->dst.dev->mtu : dst_mtu(rt->dst.path);
+                       if (frag_size && frag_size < *mtu)
+                               *mtu = frag_size;
                }
                *maxfraglen = ((*mtu - fragheaderlen) & ~7)
                              + fragheaderlen - sizeof(struct frag_hdr);
@@ -1287,7 +1291,8 @@ alloc_new_skb:
                        /* update mtu and maxfraglen if necessary */
                        if (skb == NULL || skb_prev == NULL)
                                ip6_append_data_mtu(&mtu, &maxfraglen,
-                                                   fragheaderlen, skb, rt);
+                                               fragheaderlen, skb, rt, np->frag_size,
+                                               np->pmtudisc == IPV6_PMTUDISC_PROBE);
 
                        skb_prev = skb;
 

Re: skbuff: skb_under_panic warning in 3.10rc7+

[Hannes Frederic Sowa]

On Mon, Jul 01, 2013 at 10:24:40AM +0200, Hannes Frederic Sowa wrote:
> On Mon, Jul 01, 2013 at 01:23:08AM +0200, Hannes Frederic Sowa wrote:
> > I'll look at it again tomorrow.
> 
> [Cc Gao feng because of commit 0c1833797a5a6ec23ea9261d979aa18078720b74
> ("ipv6: fix incorrect ipsec fragment")]
> 
> Just a small update:

I could reproduce Dave's exact bug and this fixes it for me:

--- a/include/net/udp.h
+++ b/include/net/udp.h
@@ -182,6 +182,7 @@ extern void udp_err(struct sk_buff *, u32);
 extern int udp_sendmsg(struct kiocb *iocb, struct sock *sk,
                            struct msghdr *msg, size_t len);
 extern void udp_flush_pending_frames(struct sock *sk);
+extern int udp_push_pending_frames(struct sock *sk);
 extern int udp_rcv(struct sk_buff *skb);
 extern int udp_ioctl(struct sock *sk, int cmd, unsigned long arg);
 extern int udp_disconnect(struct sock *sk, int flags);
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 959502a..6b270e5 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -800,7 +800,7 @@ send:
 /*
  * Push out all pending data as one UDP datagram. Socket is locked.
  */
-static int udp_push_pending_frames(struct sock *sk)
+int udp_push_pending_frames(struct sock *sk)
 {
        struct udp_sock  *up = udp_sk(sk);
        struct inet_sock *inet = inet_sk(sk);
@@ -819,6 +819,7 @@ out:
        up->pending = 0;
        return err;
 }
+EXPORT_SYMBOL(udp_push_pending_frames);
 
 int udp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
                size_t len)
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index f77e34c..748046c 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -1322,7 +1322,9 @@ int udpv6_setsockopt(struct sock *sk, int level, int optname,
 {
        if (level == SOL_UDP  ||  level == SOL_UDPLITE)
                return udp_lib_setsockopt(sk, level, optname, optval, optlen,
-                                         udp_v6_push_pending_frames);
+                                       udp_sk(sk)->pending == AF_INET6 ?
+                                       udp_v6_push_pending_frames :
+                                       udp_push_pending_frames);
        return ipv6_setsockopt(sk, level, optname, optval, optlen);
 }
 
@@ -1332,7 +1334,9 @@ int compat_udpv6_setsockopt(struct sock *sk, int level, int optname,
 {
        if (level == SOL_UDP  ||  level == SOL_UDPLITE)
                return udp_lib_setsockopt(sk, level, optname, optval, optlen,
-                                         udp_v6_push_pending_frames);
+                                       udp_sk(sk)->pending == AF_INET6 ?
+                                       udp_v6_push_pending_frames :
+                                       udp_push_pending_frames);
        return compat_ipv6_setsockopt(sk, level, optname, optval, optlen);
 }
 #endif

We call udp_v6_push_pending_frames on a socket which pending data is
actually AF_INET only. I would beautify the above patches (and perhaps
move the call to udp_push_pending_frames into udp_v6_push_pending_frames,
whatever looks nicer) and would do proper patch submissions then.

Greetings,

  Hannes