tracing/net_sched: NULL pointer dereference in perf_trace_qdisc_reset() ...
In the TRACE_EVENT(qdisc_reset) NULL dereference occurred from
qdisc->dev_queue->dev <NULL> ->name
This situation simulated from bunch of veths and Bluetooth disconnection
and reconnection.
During qdisc initialization, qdisc was being set to noop_queue.
In veth_init_queue, the initial tx_num was reduced back to one,
causing the qdisc reset to be called with noop, which led to the kernel
panic.
I've attached the GitHub gist link that C converted syz-execprogram
source code and 3 log of reproduced vmcore-dmesg.
https://gist.github.com/yskelg/cc64562873ce249cdd0d5a358b77d740
Yeoreum and I use two fuzzing tool simultaneously.
One process with syz-executor : https://github.com/google/syzkaller
$ ./syz-execprog -executor=./syz-executor -repeat=1 -sandbox=setuid \
-enable=none -collide=false log1
The other process with perf fuzzer:
https://github.com/deater/perf_event_tests/tree/master/fuzzer
$ perf_event_tests/fuzzer/perf_fuzzer
I think this will happen on the kernel version.
Linux kernel version +v6.7.10, +v6.8, +v6.9 and it could happen in v6.10.
This occurred from 51270d573a#1 ] SMP
…
[ 5301.596076] CPU: 2 PID: 102769 Comm:
syz-executor.3 Kdump: loaded Tainted:
G W ------- --- 6.10.0-0.rc2.20240608gitdc772f8237f9.29.fc41.aarch64+debug #1
[ 5301.596080] Hardware name: VMware, Inc. VMware20,1/VBSA,
BIOS VMW201.00V.21805430.BA64.2305221830 05/22/2023
[ 5301.596082] pstate: 01400005 (nzcv daif +PAN -UAO -TCO +DIT -SSBS BTYPE=--)
[ 5301.596085] pc : strnlen+0x40/0x88
[ 5301.596114] lr : trace_event_get_offsets_qdisc_reset+0x6c/0x2b0
[ 5301.596124] sp : ffff8000beef6b40
[ 5301.596126] x29: ffff8000beef6b40 x28: dfff800000000000 x27: 0000000000000001
[ 5301.596131] x26: 6de1800082c62bd0 x25: 1ffff000110aa9e0 x24: ffff800088554f00
[ 5301.596136] x23: ffff800088554ec0 x22: 0000000000000130 x21: 0000000000000140
[ 5301.596140] x20: dfff800000000000 x19: ffff8000beef6c60 x18: ffff7000115106d8
[ 5301.596143] x17: ffff800121bad000 x16: ffff800080020000 x15: 0000000000000006
[ 5301.596147] x14: 0000000000000002 x13: ffff0001f3ed8d14 x12: ffff700017ddeda5
[ 5301.596151] x11: 1ffff00017ddeda4 x10: ffff700017ddeda4 x9 : ffff800082cc5eec
[ 5301.596155] x8 : 0000000000000004 x7 : 00000000f1f1f1f1 x6 : 00000000f2f2f200
[ 5301.596158] x5 : 00000000f3f3f3f3 x4 : ffff700017dded80 x3 : 00000000f204f1f1
[ 5301.596162] x2 : 0000000000000026 x1 : 0000000000000000 x0 : 0000000000000130
[ 5301.596166] Call trace:
[ 5301.596175] strnlen+0x40/0x88
[ 5301.596179] trace_event_get_offsets_qdisc_reset+0x6c/0x2b0
[ 5301.596182] perf_trace_qdisc_reset+0xb0/0x538
[ 5301.596184] __traceiter_qdisc_reset+0x68/0xc0
[ 5301.596188] qdisc_reset+0x43c/0x5e8
[ 5301.596190] netif_set_real_num_tx_queues+0x288/0x770
[ 5301.596194] veth_init_queues+0xfc/0x130 [veth]
[ 5301.596198] veth_newlink+0x45c/0x850 [veth]
[ 5301.596202] rtnl_newlink_create+0x2c8/0x798
[ 5301.596205] __rtnl_newlink+0x92c/0xb60
[ 5301.596208] rtnl_newlink+0xd8/0x130
[ 5301.596211] rtnetlink_rcv_msg+0x2e0/0x890
[ 5301.596214] netlink_rcv_skb+0x1c4/0x380
[ 5301.596225] rtnetlink_rcv+0x20/0x38
[ 5301.596227] netlink_unicast+0x3c8/0x640
[ 5301.596231] netlink_sendmsg+0x658/0xa60
[ 5301.596234] __sock_sendmsg+0xd0/0x180
[ 5301.596243] __sys_sendto+0x1c0/0x280
[ 5301.596246] __arm64_sys_sendto+0xc8/0x150
[ 5301.596249] invoke_syscall+0xdc/0x268
[ 5301.596256] el0_svc_common.constprop.0+0x16c/0x240
[ 5301.596259] do_el0_svc+0x48/0x68
[ 5301.596261] el0_svc+0x50/0x188
[ 5301.596265] el0t_64_sync_handler+0x120/0x130
[ 5301.596268] el0t_64_sync+0x194/0x198
[ 5301.596272] Code: eb15001f 54000120 d343fc02 12000801 (38f46842)
[ 5301.596285] SMP: stopping secondary CPUs
[ 5301.597053] Starting crashdump kernel...
[ 5301.597057] Bye!
After applying our patch, I didn't find any kernel panic errors.
We've found a simple reproducer
# echo 1 > /sys/kernel/debug/tracing/events/qdisc/qdisc_reset/enable
# ip link add veth0 type veth peer name veth1
Error: Unknown device type.
However, without our patch applied, I tested upstream 6.10.0-rc3 kernel
using the qdisc_reset event and the ip command on my qemu virtual machine.
This 2 commands makes always kernel panic.
Linux version: 6.10.0-rc3
[ 0.000000] Linux version 6.10.0-rc3-00164-g44ef20baed8e-dirty
(paran@fedora) (gcc (GCC) 14.1.1 20240522 (Red Hat 14.1.1-4), GNU ld
version 2.41-34.fc40) #20 SMP PREEMPT Sat Jun 15 16:51:25 KST 2024
Kernel panic message:
[ 615.236484] Internal error: Oops: 0000000096000005 [#1 ] PREEMPT SMP
[ 615.237250] Dumping ftrace buffer:
[ 615.237679] (ftrace buffer empty)
[ 615.238097] Modules linked in: veth crct10dif_ce virtio_gpu
virtio_dma_buf drm_shmem_helper drm_kms_helper zynqmp_fpga xilinx_can
xilinx_spi xilinx_selectmap xilinx_core xilinx_pr_decoupler versal_fpga
uvcvideo uvc videobuf2_vmalloc videobuf2_memops videobuf2_v4l2 videodev
videobuf2_common mc usbnet deflate zstd ubifs ubi rcar_canfd rcar_can
omap_mailbox ntb_msi_test ntb_hw_epf lattice_sysconfig_spi
lattice_sysconfig ice40_spi gpio_xilinx dwmac_altr_socfpga mdio_regmap
stmmac_platform stmmac pcs_xpcs dfl_fme_region dfl_fme_mgr dfl_fme_br
dfl_afu dfl fpga_region fpga_bridge can can_dev br_netfilter bridge stp
llc atl1c ath11k_pci mhi ath11k_ahb ath11k qmi_helpers ath10k_sdio
ath10k_pci ath10k_core ath mac80211 libarc4 cfg80211 drm fuse backlight ipv6
Jun 22 02:36:5[3 6k152.62-4sm98k4-0k]v kCePUr:n e1l :P IUDn:a b4le6
8t oC ohmma: nidpl eN oketr nteali nptaedg i6n.g1 0re.0q-urecs3t- 0at0
1v6i4r-tgu4a4le fa2d0dbraeeds0se-dir tyd f#f2f08
615.252376] Hardware name: linux,dummy-virt (DT)
[ 615.253220] pstate: 80400005 (Nzcv daif +PAN -UAO -TCO -DIT -SSBS
BTYPE=--)
[ 615.254433] pc : strnlen+0x6c/0xe0
[ 615.255096] lr : trace_event_get_offsets_qdisc_reset+0x94/0x3d0
[ 615.256088] sp : ffff800080b269a0
[ 615.256615] x29: ffff800080b269a0 x28: ffffc070f3f98500 x27:
0000000000000001
[ 615.257831] x26: 0000000000000010 x25: ffffc070f3f98540 x24:
ffffc070f619cf60
[ 615.259020] x23: 0000000000000128 x22: 0000000000000138 x21:
dfff800000000000
[ 615.260241] x20: ffffc070f631ad00 x19: 0000000000000128 x18:
ffffc070f448b800
[ 615.261454] x17: 0000000000000000 x16: 0000000000000001 x15:
ffffc070f4ba2a90
[ 615.262635] x14: ffff700010164d73 x13: 1ffff80e1e8d5eb3 x12:
1ffff00010164d72
[ 615.263877] x11: ffff700010164d72 x10: dfff800000000000 x9 :
ffffc070e85d6184
[ 615.265047] x8 : ffffc070e4402070 x7 : 000000000000f1f1 x6 :
000000001504a6d3
[ 615.266336] x5 : ffff28ca21122140 x4 : ffffc070f5043ea8 x3 :
0000000000000000
[ 615.267528] x2 : 0000000000000025 x1 : 0000000000000000 x0 :
0000000000000000
[ 615.268747] Call trace:
[ 615.269180] strnlen+0x6c/0xe0
[ 615.269767] trace_event_get_offsets_qdisc_reset+0x94/0x3d0
[ 615.270716] trace_event_raw_event_qdisc_reset+0xe8/0x4e8
[ 615.271667] __traceiter_qdisc_reset+0xa0/0x140
[ 615.272499] qdisc_reset+0x554/0x848
[ 615.273134] netif_set_real_num_tx_queues+0x360/0x9a8
[ 615.274050] veth_init_queues+0x110/0x220 [veth]
[ 615.275110] veth_newlink+0x538/0xa50 [veth]
[ 615.276172] __rtnl_newlink+0x11e4/0x1bc8
[ 615.276944] rtnl_newlink+0xac/0x120
[ 615.277657] rtnetlink_rcv_msg+0x4e4/0x1370
[ 615.278409] netlink_rcv_skb+0x25c/0x4f0
[ 615.279122] rtnetlink_rcv+0x48/0x70
[ 615.279769] netlink_unicast+0x5a8/0x7b8
[ 615.280462] netlink_sendmsg+0xa70/0x1190
Yeoreum and I don't know if the patch we wrote will fix the underlying
cause, but we think that priority is to prevent kernel panic happening.
So, we're sending this patch.
Fixes: 51270d573ahttps://lore.kernel.org/lkml/20240229143432.273b4871@gandalf.local.home/t/
Cc: netdev@vger.kernel.org
Tested-by: Yunseong Kim <yskelg@gmail.com>
Signed-off-by: Yunseong Kim <yskelg@gmail.com>
Signed-off-by: Yeoreum Yun <yeoreum.yun@arm.com>
Link: https://lore.kernel.org/r/20240624173320.24945-4-yskelg@gmail.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
bab4923132