Hard lockup occurs due to an infinite loop encountered in distribute_cfs_runtime()

Issue

• Hard lockup occurs due to an infinite loop encountered in distribute_cfs_runtime()

[ 1432.242810] Kernel panic - not syncing: Hard LOCKUP
[ 1432.242829] CPU: 25 PID: 0 Comm: swapper/25 Not tainted 3.10.0-514.el7.x86_64 #1
[ 1432.242855] Hardware name: Cisco Systems Inc UCSC-C220-M4S/UCSC-C220-M4S, BIOS C220M4.2.0.3d.0.111120141447 11/11/2014
[ 1432.242891]  ffffffff818d9764 b7b1a7a2bef0fc23 ffff88105f445b18 ffffffff81685eac
[ 1432.242921]  ffff88105f445b98 ffffffff8167f2b3 0000000000000010 ffff88105f445ba8
[ 1432.242951]  ffff88105f445b48 b7b1a7a2bef0fc23 ffff88105f445ba8 ffffffff818d946a
[ 1432.242980] Call Trace:
[ 1432.242991]  <NMI>  [<ffffffff81685eac>] dump_stack+0x19/0x1b
[ 1432.243018]  [<ffffffff8167f2b3>] panic+0xe3/0x1f2
[ 1432.243039]  [<ffffffff8108562f>] nmi_panic+0x3f/0x40
[ 1432.243059]  [<ffffffff8112f0e6>] watchdog_overflow_callback+0xf6/0x100
[ 1432.243085]  [<ffffffff8117465e>] __perf_event_overflow+0x8e/0x1f0
[ 1432.243108]  [<ffffffff811752a4>] perf_event_overflow+0x14/0x20
[ 1432.243132]  [<ffffffff81009d88>] intel_pmu_handle_irq+0x1f8/0x4e0
[ 1432.243156]  [<ffffffff81319d7c>] ? ioremap_page_range+0x27c/0x3e0
[ 1432.243179]  [<ffffffff811bedf4>] ? vunmap_page_range+0x1c4/0x310
[ 1432.243202]  [<ffffffff811bef51>] ? unmap_kernel_range_noflush+0x11/0x20
[ 1432.243227]  [<ffffffff813c93d4>] ? ghes_copy_tofrom_phys+0x124/0x210
[ 1432.243252]  [<ffffffff813c9560>] ? ghes_read_estatus+0xa0/0x190
[ 1432.243275]  [<ffffffff8168daeb>] perf_event_nmi_handler+0x2b/0x50
[ 1432.243298]  [<ffffffff8168ef19>] nmi_handle.isra.0+0x69/0xb0
[ 1432.243320]  [<ffffffff8168f093>] do_nmi+0x133/0x410
[ 1432.243339]  [<ffffffff8168e353>] end_repeat_nmi+0x1e/0x2e
[ 1432.243360]  [<ffffffff8168d812>] ? _raw_spin_lock+0x32/0x50
[ 1432.243381]  [<ffffffff8168d812>] ? _raw_spin_lock+0x32/0x50
[ 1432.243402]  [<ffffffff8168d812>] ? _raw_spin_lock+0x32/0x50
[ 1432.243422]  <<EOE>>  <IRQ>  [<ffffffff810d100b>] unthrottle_cfs_rq+0x4b/0x170
[ 1432.243453]  [<ffffffff810d12e2>] distribute_cfs_runtime+0xf2/0x100
[ 1432.243476]  [<ffffffff810d147f>] sched_cfs_period_timer+0xcf/0x160
[ 1432.243499]  [<ffffffff810d13b0>] ? sched_cfs_slack_timer+0xc0/0xc0
[ 1432.243523]  [<ffffffff810b4862>] __hrtimer_run_queues+0xd2/0x260
[ 1432.243546]  [<ffffffff810b4e00>] hrtimer_interrupt+0xb0/0x1e0
[ 1432.243569]  [<ffffffff810510d7>] local_apic_timer_interrupt+0x37/0x60
[ 1432.243594]  [<ffffffff81698bcf>] smp_apic_timer_interrupt+0x3f/0x60
[ 1432.243617]  [<ffffffff8169711d>] apic_timer_interrupt+0x6d/0x80
[ 1432.243638]  <EOI>  [<ffffffff81513f52>] ? cpuidle_enter_state+0x52/0xc0
[ 1432.243665]  [<ffffffff81514099>] cpuidle_idle_call+0xd9/0x210
[ 1432.243688]  [<ffffffff8103516e>] arch_cpu_idle+0xe/0x30
[ 1432.243709]  [<ffffffff810e7c95>] cpu_startup_entry+0x245/0x290
[ 1432.243732]  [<ffffffff8104f12a>] start_secondary+0x1ba/0x230

• The following backtrace observed from the panic task:

crash> bt
PID: 0      TASK: ffff8808fce38fb0  CPU: 25  COMMAND: "swapper/25"
 #0 [ffff88105f4459f0] machine_kexec at ffffffff81059cdb
 #1 [ffff88105f445a50] __crash_kexec at ffffffff81105182
 #2 [ffff88105f445b20] panic at ffffffff8167f2ba
 #3 [ffff88105f445ba0] nmi_panic at ffffffff8108562f
 #4 [ffff88105f445bb0] watchdog_overflow_callback at ffffffff8112f0e6
 #5 [ffff88105f445bc8] __perf_event_overflow at ffffffff8117465e
 #6 [ffff88105f445c00] perf_event_overflow at ffffffff811752a4
 #7 [ffff88105f445c10] intel_pmu_handle_irq at ffffffff81009d88
 #8 [ffff88105f445e48] perf_event_nmi_handler at ffffffff8168daeb
 #9 [ffff88105f445e68] nmi_handle at ffffffff8168ef19
#10 [ffff88105f445eb0] do_nmi at ffffffff8168f093
#11 [ffff88105f445ef0] end_repeat_nmi at ffffffff8168e353
    [exception RIP: _raw_spin_lock+50]
    RIP: ffffffff8168d812  RSP: ffff88105f443e18  RFLAGS: 00000012
    RAX: 0000000000007f72  RBX: ffff88105aab1b00  RCX: 0000000000003f34
    RDX: 0000000000003f42  RSI: 0000000000003f42  RDI: ffff881058a79d48
    RBP: ffff88105f443e18   R8: 0000000000800008   R9: 0000000000000001
    R10: 0000000000018695  R11: 0000000000000000  R12: ffff8810537cd400
    R13: ffff88105f2d6c40  R14: ffff881058a79c00  R15: ffff881058a79d48
    ORIG_RAX: ffffffffffffffff  CS: 0010  SS: 0018
--- <NMI exception stack> ---
#12 [ffff88105f443e18] _raw_spin_lock at ffffffff8168d812
#13 [ffff88105f443e20] unthrottle_cfs_rq at ffffffff810d100b
#14 [ffff88105f443e58] distribute_cfs_runtime at ffffffff810d12e2
#15 [ffff88105f443ea0] sched_cfs_period_timer at ffffffff810d147f
#16 [ffff88105f443ed8] __hrtimer_run_queues at ffffffff810b4862
#17 [ffff88105f443f30] hrtimer_interrupt at ffffffff810b4e00
#18 [ffff88105f443f80] local_apic_timer_interrupt at ffffffff810510d7
#19 [ffff88105f443f98] smp_apic_timer_interrupt at ffffffff81698bcf
#20 [ffff88105f443fb0] apic_timer_interrupt at ffffffff8169711d
--- <IRQ stack> ---
#21 [ffff8808fce47da8] apic_timer_interrupt at ffffffff8169711d
    [exception RIP: cpuidle_enter_state+82]
    RIP: ffffffff81513f52  RSP: ffff8808fce47e50  RFLAGS: 00000206
    RAX: 0000014aa48e9400  RBX: 000000000000f8a0  RCX: 0000000000000018
    RDX: 0000000225c17d03  RSI: ffff8808fce47fd8  RDI: 0000014aa48e9400
    RBP: ffff8808fce47e78   R8: 000000000000608f   R9: 0000000000000018
    R10: 0000000000018695  R11: 0000000000000000  R12: ffff8808fce47e20
    R13: ffff88105f44f8e0  R14: 0000000000000082  R15: ffff88105f44f8e0
    ORIG_RAX: ffffffffffffff10  CS: 0010  SS: 0018
#22 [ffff8808fce47e80] cpuidle_idle_call at ffffffff81514099
#23 [ffff8808fce47ec0] arch_cpu_idle at ffffffff8103516e
#24 [ffff8808fce47ed0] cpu_startup_entry at ffffffff810e7c95
#25 [ffff8808fce47f28] start_secondary at ffffffff8104f12a