mirror of https://gitee.com/openkylin/linux.git
9799c50372
As long as there is still a reference for a hard interface held, there might
still be a forwarding packet relying on its attributes.
Therefore avoid setting hard_iface->soft_iface to NULL when disabling a hard
interface.
This fixes the following, potential splat:
batman_adv: bat0: Interface deactivated: eth1
batman_adv: bat0: Removing interface: eth1
cgroup: new mount options do not match the existing superblock, will be ignored
batman_adv: bat0: Interface deactivated: eth3
batman_adv: bat0: Removing interface: eth3
------------[ cut here ]------------
WARNING: CPU: 3 PID: 1986 at ./net/batman-adv/bat_iv_ogm.c:549 batadv_iv_send_outstanding_bat_ogm_packet+0x145/0x643 [batman_adv]
Modules linked in: batman_adv(O-) <...>
CPU: 3 PID: 1986 Comm: kworker/u8:2 Tainted: G W O 4.6.0-rc6+ #1
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.7.5-20140531_083030-gandalf 04/01/2014
Workqueue: bat_events batadv_iv_send_outstanding_bat_ogm_packet [batman_adv]
0000000000000000 ffff88001d93bca0 ffffffff8126c26b 0000000000000000
0000000000000000 ffff88001d93bcf0 ffffffff81051615 ffff88001f19f818
000002251d93bd68 0000000000000046 ffff88001dc04a00 ffff88001becbe48
Call Trace:
[<ffffffff8126c26b>] dump_stack+0x67/0x90
[<ffffffff81051615>] __warn+0xc7/0xe5
[<ffffffff8105164b>] warn_slowpath_null+0x18/0x1a
[<ffffffffa0356f24>] batadv_iv_send_outstanding_bat_ogm_packet+0x145/0x643 [batman_adv]
[<ffffffff8108b01f>] ? __lock_is_held+0x32/0x54
[<ffffffff810689a2>] process_one_work+0x2a8/0x4f5
[<ffffffff81068856>] ? process_one_work+0x15c/0x4f5
[<ffffffff81068df2>] worker_thread+0x1d5/0x2c0
[<ffffffff81068c1d>] ? process_scheduled_works+0x2e/0x2e
[<ffffffff81068c1d>] ? process_scheduled_works+0x2e/0x2e
[<ffffffff8106dd90>] kthread+0xc0/0xc8
[<ffffffff8144de82>] ret_from_fork+0x22/0x40
[<ffffffff8106dcd0>] ? __init_kthread_worker+0x55/0x55
---[ end trace 647f9f325123dc05 ]---
What happened here is, that there was still a forw_packet (here: a BATMAN IV
OGM) in the queue of eth3 with the forw_packet->if_incoming set to eth1 and the
forw_packet->if_outgoing set to eth3.
When eth3 is to be deactivated and removed, then this thread waits for the
forw_packet queued on eth3 to finish. Because eth1 was deactivated and removed
earlier and by that had forw_packet->if_incoming->soft_iface, set to NULL, the
splat when trying to send/flush the OGM on eth3 occures.
Fixes:
|
||
|---|---|---|
| .. | ||
| Kconfig | ||
| Makefile | ||
| bat_algo.c | ||
| bat_algo.h | ||
| bat_iv_ogm.c | ||
| bat_iv_ogm.h | ||
| bat_v.c | ||
| bat_v.h | ||
| bat_v_elp.c | ||
| bat_v_elp.h | ||
| bat_v_ogm.c | ||
| bat_v_ogm.h | ||
| bitarray.c | ||
| bitarray.h | ||
| bridge_loop_avoidance.c | ||
| bridge_loop_avoidance.h | ||
| debugfs.c | ||
| debugfs.h | ||
| distributed-arp-table.c | ||
| distributed-arp-table.h | ||
| fragmentation.c | ||
| fragmentation.h | ||
| gateway_client.c | ||
| gateway_client.h | ||
| gateway_common.c | ||
| gateway_common.h | ||
| hard-interface.c | ||
| hard-interface.h | ||
| hash.c | ||
| hash.h | ||
| icmp_socket.c | ||
| icmp_socket.h | ||
| log.c | ||
| log.h | ||
| main.c | ||
| main.h | ||
| multicast.c | ||
| multicast.h | ||
| netlink.c | ||
| netlink.h | ||
| network-coding.c | ||
| network-coding.h | ||
| originator.c | ||
| originator.h | ||
| packet.h | ||
| routing.c | ||
| routing.h | ||
| send.c | ||
| send.h | ||
| soft-interface.c | ||
| soft-interface.h | ||
| sysfs.c | ||
| sysfs.h | ||
| tp_meter.c | ||
| tp_meter.h | ||
| translation-table.c | ||
| translation-table.h | ||
| tvlv.c | ||
| tvlv.h | ||
| types.h | ||