Message-ID: <f2ff57c9-1c10-429f-8739-39743bf58daf@mojatatu.com>
Date: Fri, 21 Jun 2024 11:24:37 -0300
From: Pedro Tammela <pctammela@...atatu.com>
To: yskelg@...il.com, Steven Rostedt <rostedt@...dmis.org>,
 Masami Hiramatsu <mhiramat@...nel.org>,
 Mathieu Desnoyers <mathieu.desnoyers@...icios.com>,
 Takashi Iwai <tiwai@...e.de>, "David S. Miller" <davem@...emloft.net>,
 Thomas Hellström <thomas.hellstrom@...ux.intel.com>,
 "Rafael J. Wysocki" <rafael@...nel.org>, Jamal Hadi Salim
 <jhs@...atatu.com>, Cong Wang <xiyou.wangcong@...il.com>,
 Jiri Pirko <jiri@...nulli.us>, Eric Dumazet <edumazet@...gle.com>,
 Jakub Kicinski <kuba@...nel.org>, Paolo Abeni <pabeni@...hat.com>
Cc: Taehee Yoo <ap420073@...il.com>, Austin Kim <austindh.kim@...il.com>,
 shjy180909@...il.com, linux-kernel@...r.kernel.org,
 linux-trace-kernel@...r.kernel.org, netdev@...r.kernel.org,
 pbuk5246@...il.com
Subject: Re: [PATCH] qdisc: fix NULL pointer dereference in
 perf_trace_qdisc_reset()

On 21/06/2024 08:45, yskelg@...il.com wrote:
> From: Yunseong Kim <yskelg@...il.com>
> 
> 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 dis/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 think this will happen on the kernel version.
>   Linux kernel version ≥ v6.7.10, ≥ v6.8 ≥ v6.9 and 6.10

You should tag your patch for the net tree

> 
> This occurred from 51270d573a8d. I think this patch is absolutely
> necessary. Previously, It was showing not intended string value of name.
Add a 'Fixes:' tag with this commit

> 
> I've reproduced 3 time from my fedora 40 Debug Kernel with any other module
> and patched.
> 
> version: 6.10.0-0.rc2.20240608gitdc772f8237f9.29.fc41.aarch64+debug
> 
> [ 5287.164555] veth0_vlan: left promiscuous mode
> [ 5287.164929] veth1_macvtap: left promiscuous mode
> [ 5287.164950] veth0_macvtap: left promiscuous mode
> [ 5287.164983] veth1_vlan: left promiscuous mode
> [ 5287.165008] veth0_vlan: left promiscuous mode
> [ 5287.165450] veth1_macvtap: left promiscuous mode
> [ 5287.165472] veth0_macvtap: left promiscuous mode
> [ 5287.165502] veth1_vlan: left promiscuous mode
> …
> [ 5297.598240] bridge0: port 2(bridge_slave_1) entered blocking state
> [ 5297.598262] bridge0: port 2(bridge_slave_1) entered forwarding state
> [ 5297.598296] bridge0: port 1(bridge_slave_0) entered blocking state
> [ 5297.598313] bridge0: port 1(bridge_slave_0) entered forwarding state
> [ 5297.616090] 8021q: adding VLAN 0 to HW filter on device bond0
> [ 5297.620405] bridge0: port 1(bridge_slave_0) entered disabled state
> [ 5297.620730] bridge0: port 2(bridge_slave_1) entered disabled state
> [ 5297.627247] 8021q: adding VLAN 0 to HW filter on device team0
> [ 5297.629636] bridge0: port 1(bridge_slave_0) entered blocking state
> …
> [ 5298.002798] bridge_slave_0: left promiscuous mode
> [ 5298.002869] bridge0: port 1(bridge_slave_0) entered disabled state
> [ 5298.309444] bond0 (unregistering): (slave bond_slave_0): Releasing backup interface
> [ 5298.315206] bond0 (unregistering): (slave bond_slave_1): Releasing backup interface
> [ 5298.320207] bond0 (unregistering): Released all slaves
> [ 5298.354296] hsr_slave_0: left promiscuous mode
> [ 5298.360750] hsr_slave_1: left promiscuous mode
> [ 5298.374889] veth1_macvtap: left promiscuous mode
> [ 5298.374931] veth0_macvtap: left promiscuous mode
> [ 5298.374988] veth1_vlan: left promiscuous mode
> [ 5298.375024] veth0_vlan: left promiscuous mode
> [ 5299.109741] team0 (unregistering): Port device team_slave_1 removed
> [ 5299.185870] team0 (unregistering): Port device team_slave_0 removed
> …
> [ 5300.155443] Bluetooth: hci3: unexpected cc 0x0c03 length: 249 > 1
> [ 5300.155724] Bluetooth: hci3: unexpected cc 0x1003 length: 249 > 9
> [ 5300.155988] Bluetooth: hci3: unexpected cc 0x1001 length: 249 > 9
> ….
> [ 5301.075531] team0: Port device team_slave_1 added
> [ 5301.085515] bridge0: port 1(bridge_slave_0) entered blocking state
> [ 5301.085531] bridge0: port 1(bridge_slave_0) entered disabled state
> [ 5301.085588] bridge_slave_0: entered allmulticast mode
> [ 5301.085800] bridge_slave_0: entered promiscuous mode
> [ 5301.095617] bridge0: port 1(bridge_slave_0) entered blocking state
> [ 5301.095633] bridge0: port 1(bridge_slave_0) entered disabled state
> …
> [ 5301.149734] bond0: (slave bond_slave_0): Enslaving as an active interface with an up link
> [ 5301.173234] bond0: (slave bond_slave_0): Enslaving as an active interface with an up link
> [ 5301.180517] bond0: (slave bond_slave_1): Enslaving as an active interface with an up link
> [ 5301.193481] hsr_slave_0: entered promiscuous mode
> [ 5301.204425] hsr_slave_1: entered promiscuous mode
> [ 5301.210172] debugfs: Directory 'hsr0' with parent 'hsr' already present!
> [ 5301.210185] Cannot create hsr debugfs directory
> [ 5301.224061] bond0: (slave bond_slave_1): Enslaving as an active interface with an up link
> [ 5301.246901] bond0: (slave bond_slave_0): Enslaving as an active interface with an up link
> [ 5301.255934] team0: Port device team_slave_0 added
> [ 5301.256480] team0: Port device team_slave_1 added
> [ 5301.256948] team0: Port device team_slave_0 added
> …
> [ 5301.435928] hsr_slave_0: entered promiscuous mode
> [ 5301.446029] hsr_slave_1: entered promiscuous mode
> [ 5301.455872] debugfs: Directory 'hsr0' with parent 'hsr' already present!
> [ 5301.455884] Cannot create hsr debugfs directory
> [ 5301.502664] hsr_slave_0: entered promiscuous mode
> [ 5301.513675] hsr_slave_1: entered promiscuous mode
> [ 5301.526155] debugfs: Directory 'hsr0' with parent 'hsr' already present!
> [ 5301.526164] Cannot create hsr debugfs directory
> [ 5301.563662] hsr_slave_0: entered promiscuous mode
> [ 5301.576129] hsr_slave_1: entered promiscuous mode
> [ 5301.580259] debugfs: Directory 'hsr0' with parent 'hsr' already present!
> [ 5301.580270] Cannot create hsr debugfs directory
> [ 5301.590269] 8021q: adding VLAN 0 to HW filter on device bond0
> 
> [ 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!
> 
> 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
> 
> 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.
> 
> I can attach a sys-execprog's executing program, kernel dump and dmesg
> if someone need it, but I'm not sure how to safely attach large vmcore with vmlinux.

The syzkaller program + C reproducer is usually enough, please make it 
visible somewhere

> 
> Signed-off-by: Yunseong Kim <yskelg@...il.com>, Yeoreum Yun <yeoreum.yun@....com>

Should be two SoB tags

> ---
>   include/trace/events/qdisc.h | 2 +-
>   1 file changed, 1 insertion(+), 1 deletion(-)
> 
> diff --git a/include/trace/events/qdisc.h b/include/trace/events/qdisc.h
> index f1b5e816e7e5..170b51fbe47a 100644
> --- a/include/trace/events/qdisc.h
> +++ b/include/trace/events/qdisc.h
> @@ -81,7 +81,7 @@ TRACE_EVENT(qdisc_reset,
>   	TP_ARGS(q),
>   
>   	TP_STRUCT__entry(
> -		__string(	dev,		qdisc_dev(q)->name	)
> +		__string(dev, qdisc_dev(q) ? qdisc_dev(q)->name : "noop_queue")
>   		__string(	kind,		q->ops->id		)
>   		__field(	u32,		parent			)
>   		__field(	u32,		handle			)

Powered by blists - more mailing lists