Fixed
Created: Mar 16, 2014
Updated: Dec 3, 2018
Resolved Date: Mar 16, 2014
Previous ID: LIN5-18325
Found In Version: 6.0
Fix Version: 6.0.0.5
Severity: Severe
Applicable for: Wind River Linux 6
Component/s: Kernel
Architecture: QorIQ
When you try TIPC betwween 2 fsl-b4860 boards, it will kill network on boards with a call stack like this, and network is down ! We have to reboot boards !
[ 129.199217] TIPC: Resetting link <1.1.9:eth1-1.1.1:eth1>, peer not responding
[ 129.206364] TIPC: Lost link <1.1.9:eth1-1.1.1:eth1> on network plane A
[ 129.212896] TIPC: Lost contact with <1.1.1>
[ 362.285208] INFO: task rcub/0:10 blocked for more than 120 seconds.
[ 362.291483] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
[ 362.299935] rcub/0 D 0000000000000000 0 10 2 0x00000000
[ 362.307369] Call Trace:
[ 362.310152] [c0000000516775e0] [c000000051677690] 0xc000000051677690 (unreliable)
[ 362.317662] [c0000000516777b0] [c00000000000a08c] .__switch_to+0xfc/0x1d0
[ 362.324784] [c000000051677840] [c00000000075b024] .__schedule+0x304/0x700
[ 362.331921] [c000000051677ab0] [c00000000075b4d8] .schedule+0x38/0xf0
[ 362.338872] [c000000051677b30] [c00000000075c68c] .__rt_mutex_slowlock+0x9c/0x190
[ 362.346691] [c000000051677be0] [c00000000075c840] .rt_mutex_slowlock+0xc0/0x270
[ 362.354521] [c000000051677cf0] [c00000000075ca50] .rt_mutex_lock+0x60/0x80
[ 362.361740] [c000000051677d70] [c0000000000e4780] .rcu_boost_kthread+0x180/0x510
[ 362.369487] [c000000051677ea0] [c00000000008b980] .kthread+0xc0/0xd0
[ 362.376205] [c000000051677f90] [c0000000000189bc] .original_kernel_thread+0x54/0x70
[ 362.384266] INFO: task irq/152-QMan po:217 blocked for more than 120 seconds.
[ 362.391955] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
[ 362.399992] irq/152-QMan po D 0000000000000000 0 217 2 0x00000000
[ 362.407363] Call Trace:
[ 362.410156] [c000000051e0af50] [c000000051e0b000] 0xc000000051e0b000 (unreliable)
[ 362.417659] [c000000051e0b120] [c00000000000a08c] .__switch_to+0xfc/0x1d0
[ 362.425098] [c000000051e0b1b0] [c00000000075b024] .__schedule+0x304/0x700
[ 362.432255] [c000000051e0b420] [c00000000075b4d8] .schedule+0x38/0xf0
[ 362.439053] [c000000051e0b4a0] [c00000000075cdd0] .rt_spin_lock_slowlock+0x244/0x3a8
[ 362.447130] [c000000051e0b5e0] [c00000000075d1a4] .rt_spin_lock+0x54/0x80
[ 362.454256] [c000000051e0b660] [c000000000751170] .tipc_ref_lock+0x80/0xf0
[ 362.461488] [c000000051e0b700] [c00000000074f5fc] .tipc_port_recv_msg+0x4c/0x100
[ 362.469632] [c000000051e0b790] [c000000000746828] .tipc_recv_msg+0x398/0xae0
[ 362.476692] [c000000051e0b8b0] [c000000000755418] .recv_msg+0x58/0x90
[ 362.483478] [c000000051e0b940] [c0000000005a1aec] .__netif_receive_skb+0x2dc/0x580
[ 362.491587] [c000000051e0ba10] [c0000000005a405c] .netif_receive_skb+0x6c/0x1c0
[ 362.499513] [c000000051e0bae0] [c0000000004dabc4] ._dpa_rx+0x234/0x3b0
[ 362.506440] [c000000051e0bbb0] [c0000000004dadb8] .ingress_rx_default_dqrr+0x78/0x150
[ 362.514629] [c000000051e0bc60] [c0000000005462b0] .portal_isr+0x210/0x2c0
[ 362.521846] [c000000051e0bd20] [c0000000000db6e4] .irq_forced_thread_fn+0x54/0xd0
[ 362.529664] [c000000051e0bdb0] [c0000000000db1f8] .irq_thread+0x158/0x2b0
[ 362.536787] [c000000051e0bea0] [c00000000008b980] .kthread+0xc0/0xd0
[ 362.543477] [c000000051e0bf90] [c0000000000189bc] .original_kernel_thread+0x54/0x70
[ 362.551528] INFO: task pubsubQ00001150:4581 blocked for more than 120 seconds.
[ 362.559506] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
[ 362.567554] pubsubQ00001150 D 00000000f78a72d8 0 4581 4027 0x00000012
[ 362.575081] Call Trace:
[ 362.577894] [c000000048dd3100] [c000000048dd31b0] 0xc000000048dd31b0 (unreliable)
[ 362.585399] [c000000048dd32d0] [c00000000000a08c] .__switch_to+0xfc/0x1d0
[ 362.592538] [c000000048dd3360] [c00000000075b024] .__schedule+0x304/0x700
[ 362.599645] [c000000048dd35d0] [c00000000075b4d8] .schedule+0x38/0xf0
[ 362.606443] [c000000048dd3650] [c00000000075cdd0] .rt_spin_lock_slowlock+0x244/0x3a8
[ 362.614519] [c000000048dd3790] [c00000000075d274] .__rt_spin_lock+0x54/0x80
[ 362.621821] [c000000048dd3810] [c00000000075d428] .rt_read_lock+0x38/0x60
[ 362.628967] [c000000048dd3890] [c000000000744848] .tipc_link_send+0x58/0x160
[ 362.636495] [c000000048dd3930] [c000000000748cc4] .named_cluster_distribute+0xa4/0xf0
[ 362.644714] [c000000048dd39c0] [c000000000748dd8] .tipc_named_publish+0xc8/0x110
[ 362.652672] [c000000048dd3a40] [c00000000074b7bc] .tipc_nametbl_publish+0xcc/0x160
[ 362.660615] [c000000048dd3b00] [c00000000074eeb0] .tipc_publish+0x90/0x120
[ 362.667837] [c000000048dd3ba0] [c000000000752120] .bind+0xa0/0x110
[ 362.674348] [c000000048dd3c30] [c00000000058af44] .SyS_bind+0xb4/0x200
[ 362.681611] [c000000048dd3d80] [c0000000005c9dcc] .compat_sys_socketcall+0x15c/0x400
[ 362.689374] [c000000048dd3e30] [c000000000000598] syscall_exit+0x0/0x74
[ 452.737171] INFO: rcu_preempt detected stalls on CPUs/tasks: {} (detected by 0, t=105012 jiffies)
[ 452.737181] INFO: Stall ended before state dump start
Boot 2 boards and configure TIPC this way:
One 1st one:
modprobe tipc
tipc-config -netid=1234 -a=1.1.1 -be=eth:eth0
tipcTS -v -v
One 2nd one
modprobe tipc
tipc-config -netid=1234 -a=1.1.2 -be=eth:eth0
tipcTC 1000
