Hi Paolo, On 6/27/24 6:14 오후, Paolo Abeni wrote: > On Tue, 2024-06-25 at 02:33 +0900, yskelg@xxxxxxxxx wrote: >> From: Yunseong Kim <yskelg@xxxxxxxxx> >> >> 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 51270d573a8d. I think this patch is absolutely >> necessary. Previously, It was showing not intended string value of name. >> >> I've reproduced 3 time from my fedora 40 Debug Kernel with any other module >> or patched. >> >> version: 6.10.0-0.rc2.20240608gitdc772f8237f9.29.fc41.aarch64+debug >> >> [ 5301.595872] KASAN: null-ptr-deref in range [0x0000000000000130-0x0000000000000137] >> [ 5301.595877] Mem abort info: >> [ 5301.595881] ESR = 0x0000000096000006 >> [ 5301.595885] EC = 0x25: DABT (current EL), IL = 32 bits >> [ 5301.595889] SET = 0, FnV = 0 >> [ 5301.595893] EA = 0, S1PTW = 0 >> [ 5301.595896] FSC = 0x06: level 2 translation fault >> [ 5301.595900] Data abort info: >> [ 5301.595903] ISV = 0, ISS = 0x00000006, ISS2 = 0x00000000 >> [ 5301.595907] CM = 0, WnR = 0, TnD = 0, TagAccess = 0 >> [ 5301.595911] GCS = 0, Overlay = 0, DirtyBit = 0, Xs = 0 >> [ 5301.595915] [dfff800000000026] address between user and kernel address ranges >> [ 5301.595971] Internal error: Oops: 0000000096000006 [#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. >> >> Fixes: 51270d573a8d ("tracing/net_sched: Fix tracepoints that save qdisc_dev() as a string") >> Link: https://lore.kernel.org/lkml/20240229143432.273b4871@xxxxxxxxxxxxxxxxxx/t/ >> Cc: netdev@xxxxxxxxxxxxxxx >> Cc: stable@xxxxxxxxxxxxxxx # +v6.7.10, +v6.8 >> Tested-by: Yunseong Kim <yskelg@xxxxxxxxx> >> Signed-off-by: Yunseong Kim <yskelg@xxxxxxxxx> >> Signed-off-by: Yeoreum Yun <yeoreum.yun@xxxxxxx> > > I took the liberty of dropping the stable tag when applying, because as > noted from Petro this patch will not address the issue on v6.7.10 nor > on +v6.8, as they lack the upstream commit 2c92ca849fcc > ("tracing/treewide: Remove second parameter of __assign_str()") and a > we need slightly different fix on such trees, including the > TP_fast_assign() chunk. > > Could you please take care of such backport? > > Thanks, > > Paolo Thank you Paolo for your hard work. Yes, I'll try Pedro's review for +v6.7.10, test it and submit a backport patch. Link: https://lore.kernel.org/all/06d0ea61-47ee-4e54-9dfa-a711c5bc07d0@xxxxxxxxxxxx/ Warm regards, Yunseong Kim
