BUG:
The COM can't input anything, continue to print RCU stall .....，CPU 0 -1 idle 100%
NFO: rcu_sched self-detected stall on CPU { 2} (t=147027 jiffies g=208668 c=208667 q=3605260)
CPU: 2 PID: 26689 Comm: bash Tainted: P O 3.12.37-rt51 #1
Call Trace:
[c0000003f0016eb0][c000000000008c54] .show_stack+0x7c/0x1cc
[c0000003f0016f80] [c0000000007b4e7c] .dump_stack+0x8c/0xb8
[c0000003f0017000] [c0000000000b06e0] .rcu_check_callbacks+0x410/0x864
[c0000003f0017140] [c000000000048540] .update_process_times+0x58/0x9c
[c0000003f00171d0] [c000000000094c14] .tick_sched_handle.isra.18+0x3c/0x50
[c0000003f0017240] [c000000000094c84] .tick_sched_timer+0x5c/0x98
[c0000003f00172e0] [c0000000000629dc] .__run_hrtimer.isra.32+0x80/0x164
[c0000003f0017370] [c000000000063340] .hrtimer_interrupt+0x140/0x33c
[c0000003f0017480] [c0000000000106a8] .timer_interrupt+0x104/0x198
[c0000003f0017510] [c000000000019054] exc_0x900_common+0x104/0x108
--- Exception: 901 at .smp_call_function_many+0x330/0x3c0
LR = .smp_call_function_many+0x2ec/0x3c0
[c0000003f0017800] [c00000000009bf04] .smp_call_function_many+0x2c8/0x3c0 (unreliable)
[c0000003f00178e0] [c000000000027448] .__flush_tlb_page+0xf4/0x1bc
[c0000003f00179a0] [c000000000025294] .ptep_set_access_flags+0x90/0x14c
[c0000003f0017a40] [c0000000000e8e1c] .do_wp_page+0x4c8/0xac0
[c0000003f0017b20] [c0000000000ebb1c] .handle_mm_fault+0x6c0/0xad8
[c0000003f0017c00] [c000000000024514] .do_page_fault+0x340/0x748
[c0000003f0017e30] [c00000000001a1d4] storage_fault_common+0x20/0x44
BRIEF INFOMATIONl:
CPU:T2080 E6500 (8 CORE)
KERNEL VERSION: LINUX PPC64 3.12.37-rt51
HZ = 250
TEST METHED:
input raw IP traffic to device by spirent what make CPU soft interrupt more than 90% , about three hours to stop the traffic ,problem can appear.(rcu CPU stall)
@yipingwang help
similar issue:
T2080RDB cpu core hang problem - NXP Community
Thanks everyone, The problem has puzzled me for a long time.
I tried everything I could think of. ex:
memory;RCU param;disk;net irq;sched……………………
