Hi, I am using a VM on Digital Ocean with RXE enabled to develop RDMA applications. I have met warning message when attach gdb to my RDMA application: Message from syslogd@debian at May 18 04:14:07 ... kernel:[1347458.773373] watchdog: BUG: soft lockup - CPU#1 stuck for 22s! [rpc_service_tes:8416] And dmesg: [1347522.866269] Code: 16 00 00 83 f8 21 0f 8e 6f 14 00 00 83 e8 26 83 f8 01 0f 87 34 16 00 00 83 ea 27 80 fa 03 19 db 83 e3 f0 83 c3 14 e9 f7 fe ff ff <8b> 45 24 41 2b 86 40 04 00 00 41 8b 96 ec 00 00 00 c1 e0 08 83 [1347530.171418] INFO: rcu_sched self-detected stall on CPU [1347530.173098] 1-....: (1 GPs behind) idle=626/140000000000001/0 softirq=41800093/41800094 fqs=32408 [1347530.175474] (t=68262 jiffies g=39514398 c=39514397 q=127891) [1347530.177192] NMI backtrace for cpu 1 [1347530.178459] CPU: 1 PID: 8416 Comm: rpc_service_tes Tainted: P O L 4.15.0-3-amd64 #1 Debian 4.15.17-1 [1347530.181099] Hardware name: DigitalOcean Droplet, BIOS 20171212 12/12/2017 [1347530.182984] Call Trace: [1347530.183975] <IRQ> [1347530.184878] dump_stack+0x5c/0x85 [1347530.186034] nmi_cpu_backtrace+0xbf/0xd0 [1347530.187315] ? lapic_can_unplug_cpu+0xa0/0xa0 [1347530.188690] nmi_trigger_cpumask_backtrace+0xf4/0x130 [1347530.190218] rcu_dump_cpu_stacks+0x9e/0xd0 [1347530.191538] rcu_check_callbacks+0x6bb/0x900 [1347530.192888] ? tick_sched_do_timer+0x40/0x40 [1347530.194247] update_process_times+0x28/0x50 [1347530.195549] tick_sched_handle+0x22/0x70 [1347530.196793] tick_sched_timer+0x34/0x70 [1347530.198049] __hrtimer_run_queues+0xde/0x230 [1347530.199366] hrtimer_interrupt+0xa6/0x1f0 [1347530.200647] smp_apic_timer_interrupt+0x62/0x120 [1347530.202043] apic_timer_interrupt+0x7d/0x90 [1347530.203325] </IRQ> [1347530.204196] RIP: 0010:__alloc_skb+0xb2/0x1e0 [1347530.205503] RSP: 0018:ffffb6fd025a7bb8 EFLAGS: 00010246 ORIG_RAX: ffffffffffffff11 [1347530.207501] RAX: 0000000000000000 RBX: ffff8e947686f300 RCX: 0000000000000008 [1347530.209445] RDX: ffff8e96511194c0 RSI: 0000000000000200 RDI: ffff8e947686f380 [1347530.211429] RBP: ffff8e9651119400 R08: 00000000000000c0 R09: ffff8e9657003080 [1347530.213410] R10: ffff8e9657003080 R11: 0000000000001200 R12: ffff8e9657003200 [1347530.215352] R13: 0000000000000000 R14: 0000000001080020 R15: 00000000ffffffff [1347530.217339] ? __alloc_skb+0x96/0x1e0 [1347530.218591] rxe_init_packet+0x5f/0x100 [rdma_rxe] [1347530.220211] rxe_requester+0x2fa/0x1210 [rdma_rxe] [1347530.221668] ? get_page_from_freelist+0x1009/0x1270 [1347530.223184] rxe_do_task+0x83/0x100 [rdma_rxe] [1347530.224545] rxe_post_send+0x32c/0x580 [rdma_rxe] [1347530.225964] ? lookup_get_idr_uobject+0x1b/0x80 [ib_uverbs] [1347530.227588] ib_uverbs_post_send+0x534/0x670 [ib_uverbs] [1347530.229125] ib_uverbs_write+0x1d2/0x3c0 [ib_uverbs] [1347530.230565] ? common_file_perm+0x4a/0x140 [1347530.231887] vfs_write+0xad/0x1a0 [1347530.233022] SyS_write+0x52/0xc0 [1347530.234155] do_syscall_64+0x6e/0x130 [1347530.235346] entry_SYSCALL_64_after_hwframe+0x3d/0xa2 [1347530.236847] RIP: 0033:0x7ffff6963937 [1347530.238025] RSP: 002b:00007fffedd021e0 EFLAGS: 00000293 ORIG_RAX: 0000000000000001 [1347530.240017] RAX: ffffffffffffffda RBX: 0000000000000012 RCX: 00007ffff6963937 [1347530.241921] RDX: 0000000000000020 RSI: 00007fffedd02240 RDI: 0000000000000012 [1347530.243788] RBP: 00007fffedd02240 R08: 0000000000000000 R09: 0000000000000000 [1347530.245639] R10: 00007ffff7ff1250 R11: 0000000000000293 R12: 0000000000000020 [1347530.247521] R13: 00005555558fad00 R14: 00007fffffffe470 R15: 0000000000000000 I am using kernel 4.15.17-1 from latest Debian unstable. Any idea why this happen?-- To unsubscribe from this list: send the line "unsubscribe linux-rdma" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
