Prev: How to reserved all the CPU time for the private computing
Next: Need to intercept open&write calls for vdi file when VirtualBox is working.
From: Li Zefan on 24 Mar 2010 02:00 Anyone have a look at this bug ? Li Zefan wrote: > An idea came to me that running perf-sched with a fork "bomb" might > reveal some bug. > > So I wrote a program (attached), and did the following test: > > # gcc fork.c > # ./a.out & > # perf sched record > > After a few seconds, the machine froze, without printing any message. > > I've tried the test both on v2.6.34-rc1 and v2.6.34-rc1-tip+. > > I'll send you any other information you need. -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo(a)vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
From: Mike Galbraith on 24 Mar 2010 03:40 On Wed, 2010-03-24 at 13:52 +0800, Li Zefan wrote: > Anyone have a look at this bug ? > > Li Zefan wrote: > > An idea came to me that running perf-sched with a fork "bomb" might > > reveal some bug. > > > > So I wrote a program (attached), and did the following test: > > > > # gcc fork.c > > # ./a.out & > > # perf sched record > > > > After a few seconds, the machine froze, without printing any message. > > > > I've tried the test both on v2.6.34-rc1 and v2.6.34-rc1-tip+. > > > > I'll send you any other information you need. I just saw this, hunted down your testcase and tried it here. Looks like perf_output_lock() wedged box. [ 212.439223] BUG: NMI Watchdog detected LOCKUP on CPU2, ip ffffffff81078ca2, registers: [ 212.439223] CPU 2 [ 212.439223] Modules linked in: cpufreq_conservative cpufreq_ondemand cpufreq_userspace cpufreq_powersave acpi_cpufreq snd_pcm_oss snd_mixer_oss microcode snd_seq snd_seq_device fuse loop dm_mod snd_hda_codec_realtek snd_hda_intel snd_hda_codec snd_hwdep snd_pcm snd_timer firewire_ohci firewire_core crc_itu_t usb_storage snd ohci1394 soundcore snd_page_alloc usb_libusual rtc_cmos ieee1394 thermal button processor rtc_core sr_mod rtc_lib e1000e i2c_i801 cdrom sg usbhid hid uhci_hcd ehci_hcd sd_mod usbcore edd fan ext3 ext2 mbcache jbd ahci libata scsi_mod [ 212.439223] [ 212.439223] Pid: 0, comm: swapper Not tainted 2.6.34-smpx #1475 MS-7502/MS-7502 [ 212.439223] RIP: 0010:[<ffffffff81078ca2>] [<ffffffff81078ca2>] perf_output_begin+0x81/0x191 [ 212.439223] RSP: 0018:ffff880001703af0 EFLAGS: 00000086 [ 212.439223] RAX: 0000000000000000 RBX: 0000000000000002 RCX: 0000000000000002 [ 212.439223] RDX: 0000000000000058 RSI: ffff88003715c000 RDI: ffff880001703b40 [ 212.439223] RBP: 0000000000000000 R08: 0000000000000001 R09: ffff8800bb81fc00 [ 212.439223] R10: 0000000000000200 R11: 0000000000000000 R12: 0000000000000001 [ 212.439223] R13: ffff88000170f9e0 R14: ffff880001703c90 R15: ffff880001703b70 [ 212.439223] FS: 0000000000000000(0000) GS:ffff880001700000(0000) knlGS:0000000000000000 [ 212.439223] CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b [ 212.439223] CR2: 00007f1b2e3aa4a8 CR3: 0000000001420000 CR4: 00000000000006e0 [ 212.439223] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 212.439223] DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 [ 212.439223] Process swapper (pid: 0, threadinfo ffff8800bf892000, task ffff8800bf843450) [ 212.439223] Stack: [ 212.439223] ffff880001703b70 ffffffff810797a3 ffff8800bf843450 ffff880000000000 [ 212.439223] <0> 00000000ffffffff 0000000000000002 ffff88000170f9e0 ffff8800bfb1c800 [ 212.439223] <0> 0000000000000000 ffffffff81079a14 ffff8800bb81fc00 ffff88003715c000 [ 212.439223] Call Trace: [ 212.439223] <IRQ> [ 212.439223] [<ffffffff810797a3>] ? perf_prepare_sample+0xa6/0x1ba [ 212.439223] [<ffffffff81079a14>] ? __perf_event_overflow+0x15d/0x199 [ 212.439223] [<ffffffff81079a9e>] ? perf_swevent_overflow+0x4e/0x68 [ 212.439223] [<ffffffff81079be1>] ? perf_swevent_ctx_event+0xda/0xeb [ 212.439223] [<ffffffff81079c3b>] ? do_perf_sw_event+0x49/0x85 [ 212.439223] [<ffffffff81079ca8>] ? perf_tp_event+0x31/0x36 [ 212.439223] [<ffffffff81023332>] ? perf_trace_templ_sched_wakeup_template+0xbe/0xd1 [ 212.439223] [<ffffffff8102b366>] ? try_to_wake_up+0x160/0x21f [ 212.439223] [<ffffffff8102cde5>] ? load_balance+0x3b8/0x467 [ 212.439223] [<ffffffff8110cad1>] ? __blk_run_queue+0x77/0x133 [ 212.439223] [<ffffffffa00056e7>] ? scsi_run_queue+0x2d0/0x367 [scsi_mod] [ 212.439223] [<ffffffff8102cf6a>] ? rebalance_domains+0xd6/0x144 [ 212.439223] [<ffffffff8102d013>] ? run_rebalance_domains+0x3b/0xc6 [ 212.439223] [<ffffffff81036270>] ? __do_softirq+0xd6/0x193 [ 212.439223] [<ffffffff810791cb>] ? perf_ctx_adjust_freq+0x10/0xec [ 212.439223] [<ffffffff81002d0c>] ? call_softirq+0x1c/0x28 [ 212.439223] [<ffffffff81004942>] ? do_softirq+0x31/0x67 [ 212.439223] [<ffffffff810363bb>] ? irq_exit+0x36/0x7f [ 212.439223] [<ffffffff81015e92>] ? smp_apic_timer_interrupt+0x87/0x97 [ 212.439223] [<ffffffff810027d3>] ? apic_timer_interrupt+0x13/0x20 [ 212.439223] <EOI> [ 212.439223] [<ffffffff810090b1>] ? mwait_idle+0x9a/0x9f [ 212.439223] [<ffffffff81000747>] ? cpu_idle+0x4f/0x6b [ 212.439223] Code: c7 47 28 00 00 00 00 0f 45 d0 65 8b 0c 25 58 d1 00 00 c7 44 24 20 ff ff ff ff 89 4c 24 28 8b 5c 24 28 8b 44 24 20 f0 0f b1 5e 38 <89> 44 24 18 8b 44 24 18 83 f8 ff 75 09 c7 47 28 01 00 00 00 eb [ 212.439223] ---[ end trace f8a4ceb8268dbe33 ]--- [ 212.439228] BUG: NMI Watchdog detected LOCKUP on CPU1, ip ffffffff81078ca2, registers: [ 212.439228] CPU 1 [ 212.439228] Modules linked in: cpufreq_conservative cpufreq_ondemand cpufreq_userspace cpufreq_powersave acpi_cpufreq snd_pcm_oss snd_mixer_oss microcode snd_seq snd_seq_device fuse loop dm_mod snd_hda_codec_realtek snd_hda_intel snd_hda_codec snd_hwdep snd_pcm snd_timer firewire_ohci firewire_core crc_itu_t usb_storage snd ohci1394 soundcore snd_page_alloc usb_libusual rtc_cmos ieee1394 thermal button processor rtc_core sr_mod rtc_lib e1000e i2c_i801 cdrom sg usbhid hid uhci_hcd ehci_hcd sd_mod usbcore edd fan ext3 ext2 mbcache jbd ahci libata scsi_mod [ 212.439228] [ 212.439228] Pid: 9149, comm: forkbomb Tainted: G D 2.6.34-smpx #1475 MS-7502/MS-7502 [ 212.439228] RIP: 0010:[<ffffffff81078ca2>] [<ffffffff81078ca2>] perf_output_begin+0x81/0x191 [ 212.439228] RSP: 0018:ffff880001683c68 EFLAGS: 00000086 [ 212.439228] RAX: 0000000000000000 RBX: 0000000000000001 RCX: 0000000000000001 [ 212.439228] RDX: 0000000000000060 RSI: ffff88003715c000 RDI: ffff880001683cb8 [ 212.439228] RBP: 0000000000000000 R08: 0000000000000001 R09: ffff8800bb81fc00 [ 212.439228] R10: dead000000100100 R11: 0000000000000000 R12: 0000000000000001 [ 212.439228] R13: ffff88000168f9e0 R14: ffff880001683e08 R15: ffff880001683ce8 [ 212.439228] FS: 00007f1b2e582700(0000) GS:ffff880001680000(0000) knlGS:0000000000000000 [ 212.439228] CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b [ 212.439228] CR2: 00007f1b2e3abe04 CR3: 00000000bc5a7000 CR4: 00000000000006e0 [ 212.439228] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 212.439228] DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 [ 212.439228] Process forkbomb (pid: 9149, threadinfo ffff8800b839a000, task ffff8800b9719170) [ 212.439228] Stack: [ 212.439228] ffff880001683ce8 ffffffff810797a3 ffffffff81079a31 ffff880000000000 [ 212.439228] <0> 00000000ffffffff 0000000000000001 ffff88000168f9e0 ffff8800ba313000 [ 212.439228] <0> 0000000000000000 ffffffff81079a14 ffff8800bb81fc00 ffff88003715c000 [ 212.439228] Call Trace: [ 212.439228] <IRQ> [ 212.439228] [<ffffffff810797a3>] ? perf_prepare_sample+0xa6/0x1ba [ 212.439228] [<ffffffff81079a31>] ? __perf_event_overflow+0x17a/0x199 [ 212.439228] [<ffffffff81079a14>] ? __perf_event_overflow+0x15d/0x199 [ 212.439228] [<ffffffff81079a9e>] ? perf_swevent_overflow+0x4e/0x68 [ 212.439228] [<ffffffff81079a9e>] ? perf_swevent_overflow+0x4e/0x68 [ 212.439228] [<ffffffff81079be1>] ? perf_swevent_ctx_event+0xda/0xeb [ 212.439228] [<ffffffff81079c3b>] ? do_perf_sw_event+0x49/0x85 [ 212.439228] [<ffffffff81079c3b>] ? do_perf_sw_event+0x49/0x85 [ 212.439228] [<ffffffff81079ca8>] ? perf_tp_event+0x31/0x36 [ 212.439228] [<ffffffff81079ca8>] ? perf_tp_event+0x31/0x36 [ 212.439228] [<ffffffff810239ab>] ? perf_trace_sched_stat_runtime+0xbb/0xd0 [ 212.439228] [<ffffffff8102539e>] ? update_curr+0x86/0xca [ 212.439228] [<ffffffff81025522>] ? task_tick_fair+0x3d/0x107 [ 212.439228] [<ffffffff8102dba2>] ? scheduler_tick+0xd0/0x1d8 [ 212.439228] [<ffffffff8103d7dd>] ? update_process_times+0x40/0x4c [ 212.439228] [<ffffffff81051e1d>] ? tick_handle_periodic+0x18/0x5f [ 212.439228] [<ffffffff81015e8d>] ? smp_apic_timer_interrupt+0x82/0x97 [ 212.439228] [<ffffffff810027d3>] ? apic_timer_interrupt+0x13/0x20 [ 212.439228] <EOI> [ 212.439228] [<ffffffff811212b7>] ? clear_page_c+0x7/0x10 [ 212.439228] [<ffffffff81080c11>] ? get_page_from_freelist+0x373/0x3fc [ 212.439228] [<ffffffff81080da9>] ? __alloc_pages_nodemask+0x10f/0x601 [ 212.439228] [<ffffffff8104c9b0>] ? sched_clock_local+0x10/0x75 [ 212.439228] [<ffffffff81080c11>] ? get_page_from_freelist+0x373/0x3fc [ 212.439228] [<ffffffff810812ad>] ? __get_free_pages+0x12/0x52 [ 212.439228] [<ffffffff810905a7>] ? __pmd_alloc+0x14/0x71 [ 212.439228] [<ffffffff81091cfa>] ? copy_page_range+0x22a/0x6c4 [ 212.439228] [<ffffffff81079c3b>] ? do_perf_sw_event+0x49/0x85 [ 212.439228] [<ffffffff8102f17a>] ? dup_mm+0x2c0/0x44c [ 212.439228] [<ffffffff8102faae>] ? copy_process+0x762/0xe05 [ 212.439228] [<ffffffff81090c6a>] ? handle_mm_fault+0x666/0x6ad [ 212.439228] [<ffffffff810302cd>] ? do_fork+0x155/0x2ac [ 212.439228] [<ffffffff8101c1da>] ? do_page_fault+0x264/0x282 [ 212.439228] [<ffffffff81002153>] ? stub_clone+0x13/0x20 [ 212.439228] [<ffffffff81001eeb>] ? system_call_fastpath+0x16/0x1b [ 212.439228] Code: c7 47 28 00 00 00 00 0f 45 d0 65 8b 0c 25 58 d1 00 00 c7 44 24 20 ff ff ff ff 89 4c 24 28 8b 5c 24 28 8b 44 24 20 f0 0f b1 5e 38 <89> 44 24 18 8b 44 24 18 83 f8 ff 75 09 c7 47 28 01 00 00 00 eb [ 212.439228] ---[ end trace f8a4ceb8268dbe34 ]--- [ 212.439219] BUG: NMI Watchdog detected LOCKUP on CPU3, ip ffffffff81078ca2, registers: [ 212.439219] CPU 3 [ 212.439219] Modules linked in: cpufreq_conservative cpufreq_ondemand cpufreq_userspace cpufreq_powersave acpi_cpufreq snd_pcm_oss snd_mixer_oss microcode snd_seq snd_seq_device fuse loop dm_mod snd_hda_codec_realtek snd_hda_intel snd_hda_codec snd_hwdep snd_pcm snd_timer firewire_ohci firewire_core crc_itu_t usb_storage snd ohci1394 soundcore snd_page_alloc usb_libusual rtc_cmos ieee1394 thermal button processor rtc_core sr_mod rtc_lib e1000e i2c_i801 cdrom sg usbhid hid uhci_hcd ehci_hcd sd_mod usbcore edd fan ext3 ext2 mbcache jbd ahci libata scsi_mod [ 212.439219] [ 212.439219] Pid: 7184, comm: forkbomb Tainted: G D 2.6.34-smpx #1475 MS-7502/MS-7502 [ 212.439219] RIP: 0010:[<ffffffff81078ca2>] [<ffffffff81078ca2>] perf_output_begin+0x81/0x191 [ 212.439219] RSP: 0000:ffff880001783b70 EFLAGS: 00000086 [ 212.439219] RAX: 0000000000000000 RBX: 0000000000000003 RCX: 0000000000000003 [ 212.439219] RDX: 0000000000000060 RSI: ffff88003715c000 RDI: ffff880001783bc0 [ 212.439219] RBP: 0000000000000000 R08: 0000000000000001 R09: ffff8800bb81fc00 [ 212.439219] R10: 0000000000000034 R11: 0000000000000000 R12: 0000000000000001 [ 212.439219] R13: ffff88000178f9e0 R14: ffff880001783d10 R15: ffff880001783bf0 [ 212.439219] FS: 00007f1b2e582700(0000) GS:ffff880001780000(0000) knlGS:0000000000000000 [ 212.439219] CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b [ 212.439219] CR2: 00007f1b2e5cf980 CR3: 00000000bb914000 CR4: 00000000000006e0 [ 212.439219] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 212.439219] DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 [ 212.439219] Process forkbomb (pid: 7184, threadinfo ffff8800bbdb4000, task ffff8800b0097440) [ 212.439219] Stack: [ 212.439219] ffff880001783bf0 ffffffff810797a3 ffffffff810796f2 ffff880000000000 [ 212.439219] <0> 00000000ffffffff 0000000000000003 ffff88000178f9e0 ffff8800b0e00000 [ 212.439219] <0> 0000000000000000 ffffffff81079a14 ffff8800bb81fc00 ffff88003715c000 [ 212.439219] Call Trace: [ 212.439219] <IRQ> [ 212.439219] [<ffffffff810797a3>] ? perf_prepare_sample+0xa6/0x1ba [ 212.439219] [<ffffffff810796f2>] ? perf_output_sample+0x16f/0x17a [ 212.439219] [<ffffffff81079a14>] ? __perf_event_overflow+0x15d/0x199 [ 212.439219] [<ffffffff81079a9e>] ? perf_swevent_overflow+0x4e/0x68 [ 212.439219] [<ffffffff81079be1>] ? perf_swevent_ctx_event+0xda/0xeb [ 212.439219] [<ffffffff81079be1>] ? perf_swevent_ctx_event+0xda/0xeb [ 212.439219] [<ffffffff81079c3b>] ? do_perf_sw_event+0x49/0x85 [ 212.439219] [<ffffffff81079ca8>] ? perf_tp_event+0x31/0x36 [ 212.439219] [<ffffffff810239ab>] ? perf_trace_sched_stat_runtime+0xbb/0xd0 [ 212.439219] [<ffffffff8102539e>] ? update_curr+0x86/0xca [ 212.439219] [<ffffffff8102695b>] ? enqueue_task_fair+0x82/0x180 [ 212.439219] [<ffffffff81028b04>] ? enqueue_task+0x42/0x52 [ 212.439219] [<ffffffff81028b36>] ? activate_task+0x22/0x28 [ 212.439219] [<ffffffff8102b344>] ? try_to_wake_up+0x13e/0x21f [ 212.439219] [<ffffffff8103632b>] ? __do_softirq+0x191/0x193 [ 212.439219] [<ffffffff81052413>] ? tick_handle_periodic_broadcast+0xe/0x44 [ 212.439219] [<ffffffff810362e4>] ? __do_softirq+0x14a/0x193 [ 212.439219] [<ffffffff8105f82b>] ? handle_IRQ_event+0x53/0x102 [ 212.439219] [<ffffffff81002d0c>] ? call_softirq+0x1c/0x28 [ 212.439219] [<ffffffff81004942>] ? do_softirq+0x31/0x67 [ 212.439219] [<ffffffff810363bb>] ? irq_exit+0x36/0x7f [ 212.439219] [<ffffffff8100469e>] ? do_IRQ+0xa3/0xbc [ 212.439219] [<ffffffff812a3dd3>] ? ret_from_intr+0x0/0xa [ 212.439219] <EOI> [ 212.439219] [<ffffffff8101bff4>] ? do_page_fault+0x7e/0x282 [ 212.439219] [<ffffffff8101c1da>] ? do_page_fault+0x264/0x282 [ 212.439219] [<ffffffff81121b6d>] ? __put_user_4+0x1d/0x30 [ 212.439219] [<ffffffff812a3fdf>] ? page_fault+0x1f/0x30 [ 212.439219] Code: c7 47 28 00 00 00 00 0f 45 d0 65 8b 0c 25 58 d1 00 00 c7 44 24 20 ff ff ff ff 89 4c 24 28 8b 5c 24 28 8b 44 24 20 f0 0f b1 5e 38 <89> 44 24 18 8b 44 24 18 83 f8 ff 75 09 c7 47 28 01 00 00 00 eb [ 212.439219] ---[ end trace f8a4ceb8268dbe35 ]--- [ 212.439228] BUG: NMI Watchdog detected LOCKUP on CPU0, ip ffffffff812a3a29, registers: [ 212.439228] CPU 0 [ 212.439228] Modules linked in: cpufreq_conservative cpufreq_ondemand cpufreq_userspace cpufreq_powersave acpi_cpufreq snd_pcm_oss snd_mixer_oss microcode snd_seq snd_seq_device fuse loop dm_mod snd_hda_codec_realtek snd_hda_intel snd_hda_codec snd_hwdep snd_pcm snd_timer firewire_ohci firewire_core crc_itu_t usb_storage snd ohci1394 soundcore snd_page_alloc usb_libusual rtc_cmos ieee1394 thermal button processor rtc_core sr_mod rtc_lib e1000e i2c_i801 cdrom sg usbhid hid uhci_hcd ehci_hcd sd_mod usbcore edd fan ext3 ext2 mbcache jbd ahci libata scsi_mod [ 212.439228] [ 212.439228] Pid: 7183, comm: forkbomb Tainted: G D 2.6.34-smpx #1475 MS-7502/MS-7502 [ 212.439228] RIP: 0010:[<ffffffff812a3a29>] [<ffffffff812a3a29>] _raw_spin_lock+0x10/0x15 [ 212.439228] RSP: 0018:ffff880001603e68 EFLAGS: 00000097 [ 212.439228] RAX: 0000000000000504 RBX: ffff8800bf841170 RCX: ffffffffffffd809 [ 212.439228] RDX: 0000000000000000 RSI: ffff880001603ea8 RDI: ffff880001612e40 [ 212.439228] RBP: ffff880001612e40 R08: 00000000242d7b68 R09: 0000000000000034 [ 212.439228] R10: 0000000000000034 R11: ffff88003715c000 R12: 0000000000012e40 [ 212.439228] R13: ffff880001603ea8 R14: 0000000000000000 R15: 000000000000e200 [ 212.439228] FS: 0000000000000000(0000) GS:ffff880001600000(0000) knlGS:0000000000000000 [ 212.439228] CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b [ 212.439228] CR2: 00007f1b2e3aa4a8 CR3: 0000000001420000 CR4: 00000000000006f0 [ 212.439228] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 212.439228] DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 [ 212.439228] Process forkbomb (pid: 7183, threadinfo ffff8800b774a000, task ffff8800b0097a10) [ 212.439228] Stack: [ 212.439228] ffffffff810252fe ffffffff81432580 ffff8800bf841170 0000000000000000 [ 212.439228] <0> 000000000000000f 0000000000000100 ffffffff8102b227 ffff8800b774bfd8 [ 212.439228] <0> 0000000000000083 ffffffff8140c0c8 ffff8800b774bfd8 0000000000000009 [ 212.439228] Call Trace: [ 212.439228] <IRQ> [ 212.439228] [<ffffffff810252fe>] ? task_rq_lock+0x7a/0x94 [ 212.439228] [<ffffffff8102b227>] ? try_to_wake_up+0x21/0x21f [ 212.439228] [<ffffffff8103632b>] ? __do_softirq+0x191/0x193 [ 212.439228] [<ffffffff810791cb>] ? perf_ctx_adjust_freq+0x10/0xec [ 212.439228] [<ffffffff81002d0c>] ? call_softirq+0x1c/0x28 [ 212.439228] [<ffffffff81004942>] ? do_softirq+0x31/0x67 [ 212.439228] [<ffffffff810363bb>] ? irq_exit+0x36/0x7f [ 212.439228] [<ffffffff81015e92>] ? smp_apic_timer_interrupt+0x87/0x97 [ 212.439228] [<ffffffff810027d3>] ? apic_timer_interrupt+0x13/0x20 [ 212.439228] <EOI> [ 212.439228] [<ffffffff810788dc>] ? perf_output_unlock+0x3d/0x12e [ 212.439228] [<ffffffff81078ea2>] ? perf_event_task_ctx+0xb1/0x101 [ 212.439228] [<ffffffff81078f81>] ? perf_event_task+0x8f/0xbd [ 212.439228] [<ffffffff81033a03>] ? do_exit+0x261/0x664 [ 212.439228] [<ffffffff8101c1da>] ? do_page_fault+0x264/0x282 [ 212.439228] [<ffffffff81121b6d>] ? __put_user_4+0x1d/0x30 [ 212.439228] [<ffffffff81034083>] ? do_group_exit+0x6c/0x93 [ 212.439228] [<ffffffff810340bc>] ? sys_exit_group+0x12/0x19 [ 212.439228] [<ffffffff81001eeb>] ? system_call_fastpath+0x16/0x1b [ 212.439228] Code: 90 00 01 00 00 75 05 f0 66 0f b1 17 0f 94 c2 0f b6 c2 85 c0 0f 95 c0 0f b6 c0 c3 b8 00 01 00 00 f0 66 0f c1 07 38 e0 74 06 f3 90 <8a> 07 eb f6 c3 9c 58 fa ba 00 01 00 00 f0 66 0f c1 17 38 f2 74 [ 212.439228] ---[ end trace f8a4ceb8268dbe36 ]--- [ 212.439223] Kernel panic - not syncing: Aiee, killing interrupt handler! [ 212.439223] Pid: 0, comm: swapper Tainted: G D 2.6.34-smpx #1475 [ 212.439223] Call Trace: [ 212.439223] <NMI> [<ffffffff812a1956>] ? panic+0x77/0xe5 [ 212.439223] [<ffffffff8104bfe1>] ? notifier_call_chain+0x2e/0x5b [ 212.439223] [<ffffffff8104c416>] ? notify_die+0x2d/0x33 [ 212.439223] [<ffffffff81016b73>] ? nmi_watchdog_tick+0x38/0x191 [ 212.439223] [<ffffffff810037d3>] ? do_nmi+0x215/0x23c [ 212.439223] [<ffffffff811a9ba4>] ? serial8250_console_putchar+0x0/0x28 [ 212.439223] [<ffffffff812a423a>] ? nmi+0x1a/0x20 [ 212.439223] [<ffffffff811a9ba4>] ? serial8250_console_putchar+0x0/0x28 [ 212.439223] [<ffffffff81121881>] ? delay_tsc+0x32/0x4d [ 212.439223] <<EOE>> [ 212.439228] BUG: NMI Watchdog detected LOCKUP on CPU0, ip ffffffff812a3a29, registers: [ 212.439228] CPU 0 [ 212.439228] Modules linked in: cpufreq_conservative cpufreq_ondemand cpufreq_userspace cpufreq_powersave acpi_cpufreq snd_pcm_oss snd_mixer_oss microcode snd_seq snd_seq_device fuse loop dm_mod snd_hda_codec_realtek snd_hda_intel snd_hda_codec snd_hwdep snd_pcm snd_timer firewire_ohci firewire_core crc_itu_t usb_storage snd ohci1394 soundcore snd_page_alloc usb_libusual rtc_cmos ieee1394 thermal button processor rtc_core sr_mod rtc_lib e1000e i2c_i801 cdrom sg usbhid hid uhci_hcd ehci_hcd sd_mod usbcore edd fan ext3 ext2 mbcache jbd ahci libata scsi_mod [ 212.439228] [ 212.439228] Pid: 7183, comm: forkbomb Tainted: G D 2.6.34-smpx #1475 MS-7502/MS-7502 [ 212.439228] RIP: 0010:[<ffffffff812a3a29>] [<ffffffff812a3a29>] _raw_spin_lock+0x10/0x15 [ 212.439228] RSP: 0018:ffff8800016077b8 EFLAGS: 00000093 [ 212.439228] RAX: 0000000000000604 RBX: ffff8800bf8a0000 RCX: 0000000000000000 [ 212.439228] RDX: 0000000000000000 RSI: ffff8800016077f8 RDI: ffff880001612e40 [ 212.439228] RBP: ffff880001612e40 R08: 0000000000000000 R09: 000000000000007f [ 212.439228] R10: 00000000003604e2 R11: ffffffff815658d8 R12: 0000000000012e40 [ 212.439228] R13: ffff8800016077f8 R14: 0000000000000000 R15: ffff880001615ae0 [ 212.439228] FS: 0000000000000000(0000) GS:ffff880001600000(0000) knlGS:0000000000000000 [ 212.439228] CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b [ 212.439228] CR2: 00007f1b2e3aa4a8 CR3: 0000000001420000 CR4: 00000000000006f0 [ 212.439228] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 212.439228] DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 [ 212.439228] Process forkbomb (pid: 7183, threadinfo ffff8800b774a000, task ffff8800b0097a10) [ 212.439228] Stack: [ 212.439228] ffffffff810252fe 0000000000000000 ffff8800bf8a0000 0000000000000000 [ 212.439228] <0> 0000000000000003 0000000000000000 ffffffff8102b227 0000000000000000 [ 212.439228] <0> 0000000000000083 ffff8800bf89fe80 0000000000000003 ffff880001615ac8 [ 212.439228] Call Trace: [ 212.439228] <NMI> [ 212.439228] [<ffffffff810252fe>] ? task_rq_lock+0x7a/0x94 [ 212.439228] [<ffffffff8102b227>] ? try_to_wake_up+0x21/0x21f [ 212.439228] [<ffffffff810482ee>] ? autoremove_wake_function+0x9/0x2a [ 212.439228] [<ffffffff810220bf>] ? __wake_up_common+0x41/0x78 [ 212.439228] [<ffffffff8114f42e>] ? bit_putcs+0x4de/0x55c [ 212.439228] [<ffffffff81120aef>] ? vsnprintf+0x413/0x44c [ 212.439228] [<ffffffff8114ef32>] ? bit_cursor+0x4c7/0x4e5 [ 212.439228] [<ffffffff8114f704>] ? soft_cursor+0x19c/0x1b0 [ 212.439228] [<ffffffff8114ef32>] ? bit_cursor+0x4c7/0x4e5 [ 212.439228] [<ffffffff8114ef50>] ? bit_putcs+0x0/0x55c [ 212.439228] [<ffffffff8114c5de>] ? fbcon_scroll+0x5bd/0xad8 [ 212.439228] [<ffffffff811a9b59>] ? wait_for_xmitr+0x3d/0x88 [ 212.439228] [<ffffffff811a9bb9>] ? serial8250_console_putchar+0x15/0x28 [ 212.439228] [<ffffffff811a9b59>] ? wait_for_xmitr+0x3d/0x88 [ 212.439228] [<ffffffff81030ed4>] ? __call_console_drivers+0x64/0x78 [ 212.439228] [<ffffffff8104be0a>] ? up+0xe/0x39 [ 212.439228] [<ffffffff81031886>] ? release_console_sem+0x177/0x195 [ 212.439228] [<ffffffff81031886>] ? release_console_sem+0x177/0x195 [ 212.439228] [<ffffffff812a1a04>] ? printk+0x40/0x4c [ 212.439228] [<ffffffff81058810>] ? __module_text_address+0x9/0x55 [ 212.439228] [<ffffffff81058810>] ? __module_text_address+0x9/0x55 [ 212.439228] [<ffffffff81046388>] ? __kernel_text_address+0x1f/0x45 [ 212.439228] [<ffffffff810059ed>] ? print_context_stack+0xa1/0xbd [ 212.439228] [<ffffffff810059ed>] ? print_context_stack+0xa1/0xbd [ 212.439228] [<ffffffff81004af5>] ? dump_trace+0x17d/0x23e [ 212.439228] [<ffffffff81004cc2>] ? show_stack_log_lvl+0x10c/0x11b [ 212.439228] [<ffffffff81004d84>] ? show_registers+0xb3/0x213 [ 212.439228] [<ffffffff81005da9>] ? die_nmi+0x7a/0xdd [ 212.439228] [<ffffffff81016c60>] ? nmi_watchdog_tick+0x125/0x191 [ 212.439228] [<ffffffff81003661>] ? do_nmi+0xa3/0x23c [ 212.439228] [<ffffffff812a423a>] ? nmi+0x1a/0x20 [ 212.439228] [<ffffffff812a3a29>] ? _raw_spin_lock+0x10/0x15 [ 212.439228] <<EOE>> [ 212.439228] Code: 90 00 01 00 00 75 05 f0 66 0f b1 17 0f 94 c2 0f b6 c2 85 c0 0f 95 c0 0f b6 c0 c3 b8 00 01 00 00 f0 66 0f c1 07 38 e0 74 06 f3 90 <8a> 07 eb f6 c3 9c 58 fa ba 00 01 00 00 f0 66 0f c1 17 38 f2 74 [ 212.439228] ---[ end trace f8a4ceb8268dbe37 ]--- -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo(a)vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
From: Mike Galbraith on 24 Mar 2010 04:20 On Wed, 2010-03-24 at 08:32 +0100, Mike Galbraith wrote: > I just saw this, hunted down your testcase and tried it here. Looks > like perf_output_lock() wedged box. (turns on frame pointers, and adds noinline) [ 90.276644] BUG: NMI Watchdog detected LOCKUP on CPU2, ip ffffffff812b54a8, registers: [ 90.276644] CPU 2 [ 90.276644] Modules linked in: cpufreq_conservative cpufreq_ondemand cpufreq_userspace cpufreq_powersave acpi_cpufreq snd_pcm_oss snd_mixer_oss microcode snd_seq snd_seq_device fuse loop dm_mod snd_hda_codec_realtek snd_hda_intel firewire_ohci firewire_core snd_hda_codec usbmouse crc_itu_t snd_hwdep snd_pcm usb_storage snd_timer sr_mod usbhid ohci1394 snd rtc_cmos soundcore rtc_core ieee1394 usb_libusual thermal i2c_i801 processor button e1000e snd_page_alloc cdrom rtc_lib hid sg uhci_hcd ehci_hcd sd_mod usbcore edd fan ext3 ext2 mbcache jbd ahci libata scsi_mod [ 90.276644] [ 90.276644] Pid: 20237, comm: forkbomb Not tainted 2.6.34-smpx #1477 MS-7502/MS-7502 [ 90.276644] RIP: 0010:[<ffffffff812b54a8>] [<ffffffff812b54a8>] _raw_spin_lock+0x12/0x1a [ 90.276644] RSP: 0018:ffff880001703ee8 EFLAGS: 00000097 [ 90.276644] RAX: 000000000000c3c2 RBX: ffff880001712e40 RCX: 0000001504ab3a62 [ 90.276644] RDX: 0000001504ab3b83 RSI: 0000000000000026 RDI: ffff880001712e40 [ 90.276644] RBP: ffff880001703ee8 R08: 000000001ba05e30 R09: ffff880001703f88 [ 90.276644] R10: 0000000000000038 R11: 0000000000000038 R12: 0000000000000002 [ 90.276644] R13: ffff8800b48de2d0 R14: 0000000000000038 R15: 00000000ffffffe4 [ 90.276644] FS: 0000000000000000(0000) GS:ffff880001700000(0000) knlGS:0000000000000000 [ 90.276644] CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b [ 90.276644] CR2: 00007ff05702a4a8 CR3: 0000000001430000 CR4: 00000000000006e0 [ 90.276644] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 90.276644] DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 [ 90.276644] Process forkbomb (pid: 20237, threadinfo ffff8800bd3f8000, task ffff8800b48de2d0) [ 90.276644] Stack: [ 90.276644] ffff880001703f18 ffffffff8102ecc4 ffff8800b48de2d0 ffff8800b48de2d0 [ 90.276644] <0> 0000000000000000 0000000000000002 ffff880001703f48 ffffffff8103f082 [ 90.276644] <0> ffffea00029f9ee0 ffff88000170d170 ffff88000170d170 0000000000000002 [ 90.276644] Call Trace: [ 90.276644] <IRQ> [ 90.276644] [<ffffffff8102ecc4>] scheduler_tick+0x3c/0x1e6 [ 90.276644] [<ffffffff8103f082>] update_process_times+0x4b/0x5b [ 90.276644] [<ffffffff81054229>] tick_periodic+0x5d/0x5f [ 90.276644] [<ffffffff8105428e>] tick_handle_periodic+0x21/0x6e [ 90.276644] [<ffffffff810167a7>] smp_apic_timer_interrupt+0x83/0x96 [ 90.276644] [<ffffffff81002813>] apic_timer_interrupt+0x13/0x20 [ 90.276644] <EOI> [ 90.276644] [<ffffffff8107c1df>] ? perf_output_unlock+0x27/0x122 [ 90.276644] [<ffffffff8107d45f>] ? perf_swevent_overflow+0x58/0x76 [ 90.276644] [<ffffffff8107c6c6>] perf_output_begin+0x16e/0x180 [ 90.276644] [<ffffffff8107d5a2>] ? perf_swevent_ctx_event+0xdd/0xee [ 90.276644] [<ffffffff8107c80d>] perf_event_task_ctx+0xf8/0x110 [ 90.276644] [<ffffffff8104ed00>] ? sched_clock_cpu+0xc0/0xce [ 90.276644] [<ffffffff8107c8b7>] perf_event_task+0x92/0xc3 [ 90.276644] [<ffffffff8107e25e>] perf_event_exit_task+0x27/0x112 [ 90.276644] [<ffffffff810c6dca>] ? free_fs_struct+0x2d/0x31 [ 90.276644] [<ffffffff81034e4e>] do_exit+0x264/0x67a [ 90.276644] [<ffffffff8101cd6f>] ? do_page_fault+0x222/0x253 [ 90.276644] [<ffffffff810354e7>] do_group_exit+0x6f/0x98 [ 90.276644] [<ffffffff81035522>] sys_exit_group+0x12/0x16 [ 90.276644] [<ffffffff81001f2b>] system_call_fastpath+0x16/0x1b [ 90.276644] Code: 00 00 75 05 f0 66 0f b1 17 0f 94 c2 0f b6 c2 85 c0 c9 0f 95 c0 0f b6 c0 c3 55 b8 00 01 00 00 48 89 e5 f0 66 0f c1 07 38 e0 74 06 <f3> 90 8a 07 eb f6 c9 c3 55 48 89 e5 9c 58 fa ba 00 01 00 00 f0 [ 90.276639] BUG: NMI Watchdog detected LOCKUP [ 90.276644] ---[ end trace ef30915e055ad1b9 ]--- [ 90.276639] on CPU1, ip ffffffff81079014, registers: [ 90.276639] CPU 1 [ 90.276639] Modules linked in: cpufreq_conservative cpufreq_ondemand cpufreq_userspace cpufreq_powersave acpi_cpufreq snd_pcm_oss snd_mixer_oss microcode snd_seq snd_seq_device fuse loop dm_mod snd_hda_codec_realtek snd_hda_intel firewire_ohci firewire_core snd_hda_codec usbmouse crc_itu_t snd_hwdep snd_pcm usb_storage snd_timer sr_mod usbhid ohci1394 snd rtc_cmos soundcore rtc_core ieee1394 usb_libusual thermal i2c_i801 processor button e1000e snd_page_alloc cdrom rtc_lib hid sg uhci_hcd ehci_hcd sd_mod usbcore edd fan ext3 ext2 mbcache jbd ahci libata scsi_mod [ 90.276639] [ 90.276639] Pid: 0, comm: swapper Tainted: G D 2.6.34-smpx #1477 MS-7502/MS-7502 [ 90.276639] RIP: 0010:[<ffffffff81079014>] [<ffffffff81079014>] perf_output_lock+0x30/0x4e [ 90.276639] RSP: 0018:ffff880001683a00 EFLAGS: 00000082 [ 90.276639] RAX: 0000000000000002 RBX: ffff880001683ab0 RCX: ffff8800bc454000 [ 90.276639] RDX: 0000000000000001 RSI: 0000000000000001 RDI: ffff880001683ab0 [ 90.276639] RBP: ffff880001683a10 R08: 0000000000000001 R09: ffff880001683ae0 [ 90.276639] R10: 0000000000000200 R11: 0000000000000000 R12: ffff8800bc454000 [ 90.276639] R13: ffff880037788000 R14: 0000000000000070 R15: 00000000ffffffe4 [ 90.276639] FS: 0000000000000000(0000) GS:ffff880001680000(0000) knlGS:0000000000000000 [ 90.276639] CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b [ 90.276639] CR2: 00007ff05702a4a8 CR3: 0000000001430000 CR4: 00000000000006e0 [ 90.276639] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 90.276639] DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 [ 90.276639] Process swapper (pid: 0, threadinfo ffff8800bf888000, task ffff8800bf8422e0) [ 90.276639] Stack: [ 90.276639] 00000001374fb210 00000002ffffffff ffff880001683a90 ffffffff8107c5cf [ 90.276639] <0> ffff880001683a40 000000000002b3c6 ffff880001683a40 ffff880001683ae0 [ 90.276639] <0> ffff880001683a90 ffffffff8107d13c ffffffff8104eb6b ffff8800bf8422e0 [ 90.276639] Call Trace: [ 90.276639] <IRQ> [ 90.276639] [<ffffffff8107c5cf>] perf_output_begin+0x77/0x180 [ 90.276639] [<ffffffff8107d13c>] ? perf_prepare_sample+0xb5/0x1d3 [ 90.276639] [<ffffffff8104eb6b>] ? sched_clock_local+0x12/0x75 [ 90.276639] [<ffffffff8107d3c5>] __perf_event_overflow+0x16b/0x1ad [ 90.276639] [<ffffffff8107d13c>] ? perf_prepare_sample+0xb5/0x1d3 [ 90.276639] [<ffffffff8107d45f>] perf_swevent_overflow+0x58/0x76 [ 90.276639] [<ffffffff8107d4c3>] perf_swevent_add+0x46/0x48 [ 90.276639] [<ffffffff8107d5a2>] perf_swevent_ctx_event+0xdd/0xee [ 90.276639] [<ffffffff8107d601>] do_perf_sw_event+0x4e/0x8c [ 90.276639] [<ffffffff8107d670>] perf_tp_event+0x31/0x33 [ 90.276639] [<ffffffff8102c425>] ? try_to_wake_up+0x165/0x226 [ 90.276639] [<ffffffff810752e6>] ? perf_trace_buf_prepare+0x8e/0xb5 [ 90.276639] [<ffffffff81024142>] perf_trace_templ_sched_wakeup_template+0xca/0xe0 [ 90.276639] [<ffffffff81024167>] perf_trace_sched_wakeup+0xf/0x11 [ 90.276639] [<ffffffff8102c425>] try_to_wake_up+0x165/0x226 [ 90.276639] [<ffffffff8102c505>] wake_up_process+0x10/0x12 [ 90.276639] [<ffffffff8102df50>] load_balance+0x3d3/0x47f [ 90.276639] [<ffffffff8107cc69>] ? perf_event_task_tick+0x6e/0x124 [ 90.276639] [<ffffffff8102e0d6>] rebalance_domains+0xda/0x14a [ 90.276639] [<ffffffff8102e18a>] run_rebalance_domains+0x44/0xd4 [ 90.276639] [<ffffffff810377e7>] __do_softirq+0xd7/0x193 [ 90.276639] [<ffffffff810050a5>] ? timer_interrupt+0x19/0x20 [ 90.276639] [<ffffffff81002d4c>] call_softirq+0x1c/0x28 [ 90.276639] [<ffffffff810049fa>] do_softirq+0x33/0x69 [ 90.276639] [<ffffffff8103793d>] irq_exit+0x36/0x78 [ 90.276639] [<ffffffff81004733>] do_IRQ+0xa7/0xbe [ 90.276639] [<ffffffff812b5893>] ret_from_intr+0x0/0xa [ 90.276639] <EOI> [ 90.276639] [<ffffffff810093ca>] ? mwait_idle+0xa2/0xa9 [ 90.276639] [<ffffffff8104e1b2>] ? atomic_notifier_call_chain+0x13/0x15 [ 90.276639] [<ffffffff81000736>] cpu_idle+0x52/0x6f [ 90.276639] [<ffffffff812b0d53>] start_secondary+0x1ae/0x1b2 [ 90.276639] Code: 83 ec 10 c7 47 28 00 00 00 00 48 8b 4f 08 65 8b 14 25 58 d1 00 00 c7 45 f8 ff ff ff ff 89 55 f4 8b 75 f4 8b 45 f8 f0 0f b1 71 38 <89> 45 fc 8b 45 fc 83 f8 ff 75 09 c7 47 28 01 00 00 00 eb 08 39 [ 90.276639] ---[ end trace ef30915e055ad1ba ]--- [ 90.276644] BUG: NMI Watchdog detected LOCKUP on CPU3, ip ffffffff81079014, registers: [ 90.276644] CPU 3 [ 90.276644] Modules linked in: cpufreq_conservative cpufreq_ondemand cpufreq_userspace cpufreq_powersave acpi_cpufreq snd_pcm_oss snd_mixer_oss microcode snd_seq snd_seq_device fuse loop dm_mod snd_hda_codec_realtek snd_hda_intel firewire_ohci firewire_core snd_hda_codec usbmouse crc_itu_t snd_hwdep snd_pcm usb_storage snd_timer sr_mod usbhid ohci1394 snd rtc_cmos soundcore rtc_core ieee1394 usb_libusual thermal i2c_i801 processor button e1000e snd_page_alloc cdrom rtc_lib hid sg uhci_hcd ehci_hcd sd_mod usbcore edd fan ext3 ext2 mbcache jbd ahci libata scsi_mod [ 90.276644] [ 90.276644] Pid: 5146, comm: forkbomb Tainted: G D 2.6.34-smpx #1477 MS-7502/MS-7502 [ 90.276644] RIP: 0010:[<ffffffff81079014>] [<ffffffff81079014>] perf_output_lock+0x30/0x4e [ 90.276644] RSP: 0018:ffff880001783b88 EFLAGS: 00000082 [ 90.276644] RAX: 0000000000000002 RBX: ffff880001783c38 RCX: ffff8800bc454000 [ 90.276644] RDX: 0000000000000003 RSI: 0000000000000003 RDI: ffff880001783c38 [ 90.276644] RBP: ffff880001783b98 R08: 0000000000000001 R09: ffff880001783c68 [ 90.276644] R10: 0000000000000003 R11: 0000000000000246 R12: ffff8800bc454000 [ 90.276644] R13: ffff880037788000 R14: 0000000000000078 R15: 00000000ffffffe4 [ 90.276644] FS: 00007ff057202700(0000) GS:ffff880001780000(0000) knlGS:0000000000000000 [ 90.276644] CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b [ 90.276644] CR2: 00007ff05702be04 CR3: 00000000bf8c4000 CR4: 00000000000006e0 [ 90.276644] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 90.276644] DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 [ 90.276644] Process forkbomb (pid: 5146, threadinfo ffff8800bbebc000, task ffff8800bc128000) [ 90.276644] Stack: [ 90.276644] 000000030178f9e0 00000002ffffffff ffff880001783c18 ffffffff8107c5cf [ 90.276644] <0> ffff880001783bc8 000000000002b3c6 ffff880001783bc8 ffff880001783c68 [ 90.276644] <0> ffff880001783c18 ffffffff8107d13c ffff880001783be8 ffff8800bc128000 [ 90.276644] Call Trace: [ 90.276644] <IRQ> [ 90.276644] [<ffffffff8107c5cf>] perf_output_begin+0x77/0x180 [ 90.276644] [<ffffffff8107d13c>] ? perf_prepare_sample+0xb5/0x1d3 [ 90.276644] [<ffffffff8107d3c5>] __perf_event_overflow+0x16b/0x1ad [ 90.276644] [<ffffffff8107d45f>] perf_swevent_overflow+0x58/0x76 [ 90.276644] [<ffffffff8107d4c3>] perf_swevent_add+0x46/0x48 [ 90.276644] [<ffffffff8107d5a2>] perf_swevent_ctx_event+0xdd/0xee [ 90.276644] [<ffffffff8107d601>] do_perf_sw_event+0x4e/0x8c [ 90.276644] [<ffffffff8107d670>] perf_tp_event+0x31/0x33 [ 90.276644] [<ffffffff810263b8>] ? task_tick_fair+0x47/0x103 [ 90.276644] [<ffffffff810752e6>] ? perf_trace_buf_prepare+0x8e/0xb5 [ 90.276644] [<ffffffff810247ff>] perf_trace_sched_stat_runtime+0xc4/0xdc [ 90.276644] [<ffffffff81026227>] update_curr+0x87/0xc8 [ 90.276644] [<ffffffff810263b8>] task_tick_fair+0x47/0x103 [ 90.276644] [<ffffffff8102ed61>] scheduler_tick+0xd9/0x1e6 [ 90.276644] [<ffffffff8103f082>] update_process_times+0x4b/0x5b [ 90.276644] [<ffffffff81054229>] tick_periodic+0x5d/0x5f [ 90.276644] [<ffffffff8105428e>] tick_handle_periodic+0x21/0x6e [ 90.276644] [<ffffffff810167a7>] smp_apic_timer_interrupt+0x83/0x96 [ 90.276644] [<ffffffff81002813>] apic_timer_interrupt+0x13/0x20 [ 90.276644] <EOI> [ 90.276644] [<ffffffff810a493a>] ? kmem_cache_alloc+0x6a/0xdc [ 90.276644] [<ffffffff8109ba31>] anon_vma_fork+0x40/0xca [ 90.276644] [<ffffffff81030377>] dup_mm+0x206/0x43f [ 90.276644] [<ffffffff81030dac>] copy_process+0x7b2/0xea9 [ 90.276644] [<ffffffff81031625>] do_fork+0x15e/0x2b4 [ 90.276644] [<ffffffff8101cd6f>] ? do_page_fault+0x222/0x253 [ 90.276644] [<ffffffff81009a6f>] sys_clone+0x23/0x25 [ 90.276644] [<ffffffff81002193>] stub_clone+0x13/0x20 [ 90.276644] [<ffffffff81001f2b>] ? system_call_fastpath+0x16/0x1b [ 90.276644] Code: 83 ec 10 c7 47 28 00 00 00 00 48 8b 4f 08 65 8b 14 25 58 d1 00 00 c7 45 f8 ff ff ff ff 89 55 f4 8b 75 f4 8b 45 f8 f0 0f b1 71 38 <89> 45 fc 8b 45 fc 83 f8 ff 75 09 c7 47 28 01 00 00 00 eb 08 39 [ 90.276644] ---[ end trace ef30915e055ad1bb ]--- [ 90.276643] BUG: NMI Watchdog detected LOCKUP on CPU0, ip ffffffff81079014, registers: [ 90.276643] CPU 0 [ 90.276643] Modules linked in: cpufreq_conservative cpufreq_ondemand cpufreq_userspace cpufreq_powersave [ 90.276644] Kernel panic - not syncing: Aiee, killing interrupt handler! [ 90.276643] acpi_cpufreqPid: 5146, comm: forkbomb Tainted: G D 2.6.34-smpx #1477 [ 90.276643] snd_pcm_ossCall Trace: [ 90.276643] snd_mixer_oss <NMI> microcode snd_seq [<ffffffff812b3364>] panic+0x73/0xe1 [ 90.276643] snd_seq_device fuse [<ffffffff8103794f>] ? irq_exit+0x48/0x78 [ 90.276643] loop dm_mod [<ffffffff81034c57>] do_exit+0x6d/0x67a [ 90.276643] snd_hda_codec_realtek snd_hda_intel [<ffffffff8104e164>] ? notifier_call_chain+0x32/0x5e [ 90.276643] firewire_ohci firewire_core [<ffffffff81005f8c>] die_nmi+0xd2/0xde [ 90.276643] snd_hda_codec usbmouse [<ffffffff8101751d>] nmi_watchdog_tick+0x41/0x19d [ 90.276643] crc_itu_t snd_hwdep [<ffffffff81003812>] do_nmi+0x222/0x24c [ 90.276643] snd_pcm usb_storage [<ffffffff812b5cfa>] nmi+0x1a/0x20 [ 90.276643] snd_timer sr_mod [<ffffffff81005f87>] ? die_nmi+0xcd/0xde [ 90.276643] usbhid <<EOE>> ohci1394 snd rtc_cmos soundcore rtc_core ieee1394 usb_libusual thermal i2c_i801 processor button e1000e snd_page_alloc cdrom rtc_lib hid sg uhci_hcd ehci_hcd sd_mod usbcore edd fan ext3 ext2 mbcache jbd ahci libata scsi_mod [ 90.276643] [ 90.276643] Pid: 20238, comm: forkbomb Tainted: G D 2.6.34-smpx #1477 MS-7502/MS-7502 [ 90.276643] RIP: 0010:[<ffffffff81079014>] [<ffffffff81079014>] perf_output_lock+0x30/0x4e [ 90.276643] RSP: 0000:ffff880001603b88 EFLAGS: 00000082 [ 90.276643] RAX: 0000000000000002 RBX: ffff880001603c38 RCX: ffff8800bc454000 [ 90.276643] RDX: 0000000000000000 RSI: 0000000000000000 RDI: ffff880001603c38 [ 90.276643] RBP: ffff880001603b98 R08: 0000000000000001 R09: ffff880001603c68 [ 90.276643] R10: 0000000000000000 R11: 0000000000000000 R12: ffff8800bc454000 [ 90.276643] R13: ffff880037788000 R14: 0000000000000078 R15: 00000000ffffffe4 [ 90.276643] FS: 00007ff057202700(0000) GS:ffff880001600000(0000) knlGS:0000000000000000 [ 90.276643] CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b [ 90.276643] CR2: 00007ff056d05510 CR3: 00000000bd9f7000 CR4: 00000000000006f0 [ 90.276643] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 90.276643] DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 [ 90.276643] Process forkbomb (pid: 20238, threadinfo ffff8800bd3fa000, task ffff8800b48de8a0) [ 90.276643] Stack: [ 90.276643] 00000000071cf224 00000002ffffffff ffff880001603c18 ffffffff8107c5cf [ 90.276643] <0> ffff880001603bc8 000000000002b3c6 ffff880001603bc8 ffff880001603c68 [ 90.276643] <0> ffff880001603c18 ffffffff8107d13c ffff8800bc690888 ffff8800b48de8a0 [ 90.276643] Call Trace: [ 90.276643] <IRQ> [ 90.276643] [<ffffffff8107c5cf>] perf_output_begin+0x77/0x180 [ 90.276643] [<ffffffff8107d13c>] ? perf_prepare_sample+0xb5/0x1d3 [ 90.276643] [<ffffffff8107d3c5>] __perf_event_overflow+0x16b/0x1ad [ 90.276643] [<ffffffff8107d45f>] perf_swevent_overflow+0x58/0x76 [ 90.276643] [<ffffffff8107d4c3>] perf_swevent_add+0x46/0x48 [ 90.276643] [<ffffffff8107d5a2>] perf_swevent_ctx_event+0xdd/0xee [ 90.276643] [<ffffffff8107d601>] do_perf_sw_event+0x4e/0x8c [ 90.276643] [<ffffffff811b8f9e>] ? put_device+0x12/0x14 [ 90.276643] [<ffffffff8107d670>] perf_tp_event+0x31/0x33 [ 90.276643] [<ffffffff810263b8>] ? task_tick_fair+0x47/0x103 [ 90.276643] [<ffffffff810752e6>] ? perf_trace_buf_prepare+0x8e/0xb5 [ 90.276643] [<ffffffff810247ff>] perf_trace_sched_stat_runtime+0xc4/0xdc [ 90.276643] [<ffffffffa0000773>] ? scsi_finish_command+0xec/0xf5 [scsi_mod] [ 90.276643] [<ffffffff81026227>] update_curr+0x87/0xc8 [ 90.276643] [<ffffffff810263b8>] task_tick_fair+0x47/0x103 [ 90.276643] [<ffffffff8102ed61>] scheduler_tick+0xd9/0x1e6 [ 90.276643] [<ffffffff8103f082>] update_process_times+0x4b/0x5b [ 90.276643] [<ffffffff81054229>] tick_periodic+0x5d/0x5f [ 90.276643] [<ffffffff8105428e>] tick_handle_periodic+0x21/0x6e [ 90.276643] [<ffffffff810167a7>] smp_apic_timer_interrupt+0x83/0x96 [ 90.276643] [<ffffffff81002813>] apic_timer_interrupt+0x13/0x20 [ 90.276643] <EOI> [ 90.276643] [<ffffffff8101cbd1>] ? do_page_fault+0x84/0x253 [ 90.276643] [<ffffffff8101cd6f>] ? do_page_fault+0x222/0x253 [ 90.276643] [<ffffffff812b5a9f>] page_fault+0x1f/0x30 [ 90.276643] Code: 83 ec 10 c7 47 28 00 00 00 00 48 8b 4f 08 65 8b 14 25 58 d1 00 00 c7 45 f8 ff ff ff ff 89 55 f4 8b 75 f4 8b 45 f8 f0 0f b1 71 38 <89> 45 fc 8b 45 fc 83 f8 ff 75 09 c7 47 28 01 00 00 00 eb 08 39 [ 90.276643] ---[ end trace ef30915e055ad1bc ]--- -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo(a)vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
From: Li Zefan on 25 Mar 2010 04:10 Mike Galbraith wrote: > On Wed, 2010-03-24 at 08:32 +0100, Mike Galbraith wrote: > >> I just saw this, hunted down your testcase and tried it here. Looks >> like perf_output_lock() wedged box. > > (turns on frame pointers, and adds noinline) > Thanks! Then who's going to fix this... --Li > [ 90.276644] BUG: NMI Watchdog detected LOCKUP on CPU2, ip ffffffff812b54a8, registers: > [ 90.276644] CPU 2 > [ 90.276644] Modules linked in: cpufreq_conservative cpufreq_ondemand cpufreq_userspace cpufreq_powersave acpi_cpufreq snd_pcm_oss snd_mixer_oss microcode snd_seq snd_seq_device fuse loop dm_mod snd_hda_codec_realtek snd_hda_intel firewire_ohci firewire_core snd_hda_codec usbmouse crc_itu_t snd_hwdep snd_pcm usb_storage snd_timer sr_mod usbhid ohci1394 snd rtc_cmos soundcore rtc_core ieee1394 usb_libusual thermal i2c_i801 processor button e1000e snd_page_alloc cdrom rtc_lib hid sg uhci_hcd ehci_hcd sd_mod usbcore edd fan ext3 ext2 mbcache jbd ahci libata scsi_mod > [ 90.276644] > [ 90.276644] Pid: 20237, comm: forkbomb Not tainted 2.6.34-smpx #1477 MS-7502/MS-7502 > [ 90.276644] RIP: 0010:[<ffffffff812b54a8>] [<ffffffff812b54a8>] _raw_spin_lock+0x12/0x1a > [ 90.276644] RSP: 0018:ffff880001703ee8 EFLAGS: 00000097 > [ 90.276644] RAX: 000000000000c3c2 RBX: ffff880001712e40 RCX: 0000001504ab3a62 > [ 90.276644] RDX: 0000001504ab3b83 RSI: 0000000000000026 RDI: ffff880001712e40 > [ 90.276644] RBP: ffff880001703ee8 R08: 000000001ba05e30 R09: ffff880001703f88 > [ 90.276644] R10: 0000000000000038 R11: 0000000000000038 R12: 0000000000000002 > [ 90.276644] R13: ffff8800b48de2d0 R14: 0000000000000038 R15: 00000000ffffffe4 > [ 90.276644] FS: 0000000000000000(0000) GS:ffff880001700000(0000) knlGS:0000000000000000 > [ 90.276644] CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b > [ 90.276644] CR2: 00007ff05702a4a8 CR3: 0000000001430000 CR4: 00000000000006e0 > [ 90.276644] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 > [ 90.276644] DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 > [ 90.276644] Process forkbomb (pid: 20237, threadinfo ffff8800bd3f8000, task ffff8800b48de2d0) > [ 90.276644] Stack: > [ 90.276644] ffff880001703f18 ffffffff8102ecc4 ffff8800b48de2d0 ffff8800b48de2d0 > [ 90.276644] <0> 0000000000000000 0000000000000002 ffff880001703f48 ffffffff8103f082 > [ 90.276644] <0> ffffea00029f9ee0 ffff88000170d170 ffff88000170d170 0000000000000002 > [ 90.276644] Call Trace: > [ 90.276644] <IRQ> > [ 90.276644] [<ffffffff8102ecc4>] scheduler_tick+0x3c/0x1e6 > [ 90.276644] [<ffffffff8103f082>] update_process_times+0x4b/0x5b > [ 90.276644] [<ffffffff81054229>] tick_periodic+0x5d/0x5f > [ 90.276644] [<ffffffff8105428e>] tick_handle_periodic+0x21/0x6e > [ 90.276644] [<ffffffff810167a7>] smp_apic_timer_interrupt+0x83/0x96 > [ 90.276644] [<ffffffff81002813>] apic_timer_interrupt+0x13/0x20 > [ 90.276644] <EOI> > [ 90.276644] [<ffffffff8107c1df>] ? perf_output_unlock+0x27/0x122 > [ 90.276644] [<ffffffff8107d45f>] ? perf_swevent_overflow+0x58/0x76 > [ 90.276644] [<ffffffff8107c6c6>] perf_output_begin+0x16e/0x180 > [ 90.276644] [<ffffffff8107d5a2>] ? perf_swevent_ctx_event+0xdd/0xee > [ 90.276644] [<ffffffff8107c80d>] perf_event_task_ctx+0xf8/0x110 > [ 90.276644] [<ffffffff8104ed00>] ? sched_clock_cpu+0xc0/0xce > [ 90.276644] [<ffffffff8107c8b7>] perf_event_task+0x92/0xc3 > [ 90.276644] [<ffffffff8107e25e>] perf_event_exit_task+0x27/0x112 > [ 90.276644] [<ffffffff810c6dca>] ? free_fs_struct+0x2d/0x31 > [ 90.276644] [<ffffffff81034e4e>] do_exit+0x264/0x67a > [ 90.276644] [<ffffffff8101cd6f>] ? do_page_fault+0x222/0x253 > [ 90.276644] [<ffffffff810354e7>] do_group_exit+0x6f/0x98 > [ 90.276644] [<ffffffff81035522>] sys_exit_group+0x12/0x16 > [ 90.276644] [<ffffffff81001f2b>] system_call_fastpath+0x16/0x1b > [ 90.276644] Code: 00 00 75 05 f0 66 0f b1 17 0f 94 c2 0f b6 c2 85 c0 c9 0f 95 c0 0f b6 c0 c3 55 b8 00 01 00 00 48 89 e5 f0 66 0f c1 07 38 e0 74 06 <f3> 90 8a 07 eb f6 c9 c3 55 48 89 e5 9c 58 fa ba 00 01 00 00 f0 > [ 90.276639] BUG: NMI Watchdog detected LOCKUP > [ 90.276644] ---[ end trace ef30915e055ad1b9 ]--- > [ 90.276639] on CPU1, ip ffffffff81079014, registers: > [ 90.276639] CPU 1 > [ 90.276639] Modules linked in: cpufreq_conservative cpufreq_ondemand cpufreq_userspace cpufreq_powersave acpi_cpufreq snd_pcm_oss snd_mixer_oss microcode snd_seq snd_seq_device fuse loop dm_mod snd_hda_codec_realtek snd_hda_intel firewire_ohci firewire_core snd_hda_codec usbmouse crc_itu_t snd_hwdep snd_pcm usb_storage snd_timer sr_mod usbhid ohci1394 snd rtc_cmos soundcore rtc_core ieee1394 usb_libusual thermal i2c_i801 processor button e1000e snd_page_alloc cdrom rtc_lib hid sg uhci_hcd ehci_hcd sd_mod usbcore edd fan ext3 ext2 mbcache jbd ahci libata scsi_mod > [ 90.276639] > [ 90.276639] Pid: 0, comm: swapper Tainted: G D 2.6.34-smpx #1477 MS-7502/MS-7502 > [ 90.276639] RIP: 0010:[<ffffffff81079014>] [<ffffffff81079014>] perf_output_lock+0x30/0x4e > [ 90.276639] RSP: 0018:ffff880001683a00 EFLAGS: 00000082 > [ 90.276639] RAX: 0000000000000002 RBX: ffff880001683ab0 RCX: ffff8800bc454000 > [ 90.276639] RDX: 0000000000000001 RSI: 0000000000000001 RDI: ffff880001683ab0 > [ 90.276639] RBP: ffff880001683a10 R08: 0000000000000001 R09: ffff880001683ae0 > [ 90.276639] R10: 0000000000000200 R11: 0000000000000000 R12: ffff8800bc454000 > [ 90.276639] R13: ffff880037788000 R14: 0000000000000070 R15: 00000000ffffffe4 > [ 90.276639] FS: 0000000000000000(0000) GS:ffff880001680000(0000) knlGS:0000000000000000 > [ 90.276639] CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b > [ 90.276639] CR2: 00007ff05702a4a8 CR3: 0000000001430000 CR4: 00000000000006e0 > [ 90.276639] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 > [ 90.276639] DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 > [ 90.276639] Process swapper (pid: 0, threadinfo ffff8800bf888000, task ffff8800bf8422e0) > [ 90.276639] Stack: > [ 90.276639] 00000001374fb210 00000002ffffffff ffff880001683a90 ffffffff8107c5cf > [ 90.276639] <0> ffff880001683a40 000000000002b3c6 ffff880001683a40 ffff880001683ae0 > [ 90.276639] <0> ffff880001683a90 ffffffff8107d13c ffffffff8104eb6b ffff8800bf8422e0 > [ 90.276639] Call Trace: > [ 90.276639] <IRQ> > [ 90.276639] [<ffffffff8107c5cf>] perf_output_begin+0x77/0x180 > [ 90.276639] [<ffffffff8107d13c>] ? perf_prepare_sample+0xb5/0x1d3 > [ 90.276639] [<ffffffff8104eb6b>] ? sched_clock_local+0x12/0x75 > [ 90.276639] [<ffffffff8107d3c5>] __perf_event_overflow+0x16b/0x1ad > [ 90.276639] [<ffffffff8107d13c>] ? perf_prepare_sample+0xb5/0x1d3 > [ 90.276639] [<ffffffff8107d45f>] perf_swevent_overflow+0x58/0x76 > [ 90.276639] [<ffffffff8107d4c3>] perf_swevent_add+0x46/0x48 > [ 90.276639] [<ffffffff8107d5a2>] perf_swevent_ctx_event+0xdd/0xee > [ 90.276639] [<ffffffff8107d601>] do_perf_sw_event+0x4e/0x8c > [ 90.276639] [<ffffffff8107d670>] perf_tp_event+0x31/0x33 > [ 90.276639] [<ffffffff8102c425>] ? try_to_wake_up+0x165/0x226 > [ 90.276639] [<ffffffff810752e6>] ? perf_trace_buf_prepare+0x8e/0xb5 > [ 90.276639] [<ffffffff81024142>] perf_trace_templ_sched_wakeup_template+0xca/0xe0 > [ 90.276639] [<ffffffff81024167>] perf_trace_sched_wakeup+0xf/0x11 > [ 90.276639] [<ffffffff8102c425>] try_to_wake_up+0x165/0x226 > [ 90.276639] [<ffffffff8102c505>] wake_up_process+0x10/0x12 > [ 90.276639] [<ffffffff8102df50>] load_balance+0x3d3/0x47f > [ 90.276639] [<ffffffff8107cc69>] ? perf_event_task_tick+0x6e/0x124 > [ 90.276639] [<ffffffff8102e0d6>] rebalance_domains+0xda/0x14a > [ 90.276639] [<ffffffff8102e18a>] run_rebalance_domains+0x44/0xd4 > [ 90.276639] [<ffffffff810377e7>] __do_softirq+0xd7/0x193 > [ 90.276639] [<ffffffff810050a5>] ? timer_interrupt+0x19/0x20 > [ 90.276639] [<ffffffff81002d4c>] call_softirq+0x1c/0x28 > [ 90.276639] [<ffffffff810049fa>] do_softirq+0x33/0x69 > [ 90.276639] [<ffffffff8103793d>] irq_exit+0x36/0x78 > [ 90.276639] [<ffffffff81004733>] do_IRQ+0xa7/0xbe > [ 90.276639] [<ffffffff812b5893>] ret_from_intr+0x0/0xa > [ 90.276639] <EOI> > [ 90.276639] [<ffffffff810093ca>] ? mwait_idle+0xa2/0xa9 > [ 90.276639] [<ffffffff8104e1b2>] ? atomic_notifier_call_chain+0x13/0x15 > [ 90.276639] [<ffffffff81000736>] cpu_idle+0x52/0x6f > [ 90.276639] [<ffffffff812b0d53>] start_secondary+0x1ae/0x1b2 > [ 90.276639] Code: 83 ec 10 c7 47 28 00 00 00 00 48 8b 4f 08 65 8b 14 25 58 d1 00 00 c7 45 f8 ff ff ff ff 89 55 f4 8b 75 f4 8b 45 f8 f0 0f b1 71 38 <89> 45 fc 8b 45 fc 83 f8 ff 75 09 c7 47 28 01 00 00 00 eb 08 39 > [ 90.276639] ---[ end trace ef30915e055ad1ba ]--- > [ 90.276644] BUG: NMI Watchdog detected LOCKUP on CPU3, ip ffffffff81079014, registers: > [ 90.276644] CPU 3 > [ 90.276644] Modules linked in: cpufreq_conservative cpufreq_ondemand cpufreq_userspace cpufreq_powersave acpi_cpufreq snd_pcm_oss snd_mixer_oss microcode snd_seq snd_seq_device fuse loop dm_mod snd_hda_codec_realtek snd_hda_intel firewire_ohci firewire_core snd_hda_codec usbmouse crc_itu_t snd_hwdep snd_pcm usb_storage snd_timer sr_mod usbhid ohci1394 snd rtc_cmos soundcore rtc_core ieee1394 usb_libusual thermal i2c_i801 processor button e1000e snd_page_alloc cdrom rtc_lib hid sg uhci_hcd ehci_hcd sd_mod usbcore edd fan ext3 ext2 mbcache jbd ahci libata scsi_mod > [ 90.276644] > [ 90.276644] Pid: 5146, comm: forkbomb Tainted: G D 2.6.34-smpx #1477 MS-7502/MS-7502 > [ 90.276644] RIP: 0010:[<ffffffff81079014>] [<ffffffff81079014>] perf_output_lock+0x30/0x4e > [ 90.276644] RSP: 0018:ffff880001783b88 EFLAGS: 00000082 > [ 90.276644] RAX: 0000000000000002 RBX: ffff880001783c38 RCX: ffff8800bc454000 > [ 90.276644] RDX: 0000000000000003 RSI: 0000000000000003 RDI: ffff880001783c38 > [ 90.276644] RBP: ffff880001783b98 R08: 0000000000000001 R09: ffff880001783c68 > [ 90.276644] R10: 0000000000000003 R11: 0000000000000246 R12: ffff8800bc454000 > [ 90.276644] R13: ffff880037788000 R14: 0000000000000078 R15: 00000000ffffffe4 > [ 90.276644] FS: 00007ff057202700(0000) GS:ffff880001780000(0000) knlGS:0000000000000000 > [ 90.276644] CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b > [ 90.276644] CR2: 00007ff05702be04 CR3: 00000000bf8c4000 CR4: 00000000000006e0 > [ 90.276644] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 > [ 90.276644] DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 > [ 90.276644] Process forkbomb (pid: 5146, threadinfo ffff8800bbebc000, task ffff8800bc128000) > [ 90.276644] Stack: > [ 90.276644] 000000030178f9e0 00000002ffffffff ffff880001783c18 ffffffff8107c5cf > [ 90.276644] <0> ffff880001783bc8 000000000002b3c6 ffff880001783bc8 ffff880001783c68 > [ 90.276644] <0> ffff880001783c18 ffffffff8107d13c ffff880001783be8 ffff8800bc128000 > [ 90.276644] Call Trace: > [ 90.276644] <IRQ> > [ 90.276644] [<ffffffff8107c5cf>] perf_output_begin+0x77/0x180 > [ 90.276644] [<ffffffff8107d13c>] ? perf_prepare_sample+0xb5/0x1d3 > [ 90.276644] [<ffffffff8107d3c5>] __perf_event_overflow+0x16b/0x1ad > [ 90.276644] [<ffffffff8107d45f>] perf_swevent_overflow+0x58/0x76 > [ 90.276644] [<ffffffff8107d4c3>] perf_swevent_add+0x46/0x48 > [ 90.276644] [<ffffffff8107d5a2>] perf_swevent_ctx_event+0xdd/0xee > [ 90.276644] [<ffffffff8107d601>] do_perf_sw_event+0x4e/0x8c > [ 90.276644] [<ffffffff8107d670>] perf_tp_event+0x31/0x33 > [ 90.276644] [<ffffffff810263b8>] ? task_tick_fair+0x47/0x103 > [ 90.276644] [<ffffffff810752e6>] ? perf_trace_buf_prepare+0x8e/0xb5 > [ 90.276644] [<ffffffff810247ff>] perf_trace_sched_stat_runtime+0xc4/0xdc > [ 90.276644] [<ffffffff81026227>] update_curr+0x87/0xc8 > [ 90.276644] [<ffffffff810263b8>] task_tick_fair+0x47/0x103 > [ 90.276644] [<ffffffff8102ed61>] scheduler_tick+0xd9/0x1e6 > [ 90.276644] [<ffffffff8103f082>] update_process_times+0x4b/0x5b > [ 90.276644] [<ffffffff81054229>] tick_periodic+0x5d/0x5f > [ 90.276644] [<ffffffff8105428e>] tick_handle_periodic+0x21/0x6e > [ 90.276644] [<ffffffff810167a7>] smp_apic_timer_interrupt+0x83/0x96 > [ 90.276644] [<ffffffff81002813>] apic_timer_interrupt+0x13/0x20 > [ 90.276644] <EOI> > [ 90.276644] [<ffffffff810a493a>] ? kmem_cache_alloc+0x6a/0xdc > [ 90.276644] [<ffffffff8109ba31>] anon_vma_fork+0x40/0xca > [ 90.276644] [<ffffffff81030377>] dup_mm+0x206/0x43f > [ 90.276644] [<ffffffff81030dac>] copy_process+0x7b2/0xea9 > [ 90.276644] [<ffffffff81031625>] do_fork+0x15e/0x2b4 > [ 90.276644] [<ffffffff8101cd6f>] ? do_page_fault+0x222/0x253 > [ 90.276644] [<ffffffff81009a6f>] sys_clone+0x23/0x25 > [ 90.276644] [<ffffffff81002193>] stub_clone+0x13/0x20 > [ 90.276644] [<ffffffff81001f2b>] ? system_call_fastpath+0x16/0x1b > [ 90.276644] Code: 83 ec 10 c7 47 28 00 00 00 00 48 8b 4f 08 65 8b 14 25 58 d1 00 00 c7 45 f8 ff ff ff ff 89 55 f4 8b 75 f4 8b 45 f8 f0 0f b1 71 38 <89> 45 fc 8b 45 fc 83 f8 ff 75 09 c7 47 28 01 00 00 00 eb 08 39 > [ 90.276644] ---[ end trace ef30915e055ad1bb ]--- > [ 90.276643] BUG: NMI Watchdog detected LOCKUP on CPU0, ip ffffffff81079014, registers: > [ 90.276643] CPU 0 > [ 90.276643] Modules linked in: cpufreq_conservative cpufreq_ondemand cpufreq_userspace cpufreq_powersave > [ 90.276644] Kernel panic - not syncing: Aiee, killing interrupt handler! > [ 90.276643] acpi_cpufreqPid: 5146, comm: forkbomb Tainted: G D 2.6.34-smpx #1477 > [ 90.276643] snd_pcm_ossCall Trace: > [ 90.276643] snd_mixer_oss <NMI> microcode snd_seq [<ffffffff812b3364>] panic+0x73/0xe1 > [ 90.276643] snd_seq_device fuse [<ffffffff8103794f>] ? irq_exit+0x48/0x78 > [ 90.276643] loop dm_mod [<ffffffff81034c57>] do_exit+0x6d/0x67a > [ 90.276643] snd_hda_codec_realtek snd_hda_intel [<ffffffff8104e164>] ? notifier_call_chain+0x32/0x5e > [ 90.276643] firewire_ohci firewire_core [<ffffffff81005f8c>] die_nmi+0xd2/0xde > [ 90.276643] snd_hda_codec usbmouse [<ffffffff8101751d>] nmi_watchdog_tick+0x41/0x19d > [ 90.276643] crc_itu_t snd_hwdep [<ffffffff81003812>] do_nmi+0x222/0x24c > [ 90.276643] snd_pcm usb_storage [<ffffffff812b5cfa>] nmi+0x1a/0x20 > [ 90.276643] snd_timer sr_mod [<ffffffff81005f87>] ? die_nmi+0xcd/0xde > [ 90.276643] usbhid <<EOE>> ohci1394 snd rtc_cmos soundcore rtc_core ieee1394 usb_libusual thermal i2c_i801 processor button e1000e snd_page_alloc cdrom rtc_lib hid sg uhci_hcd ehci_hcd sd_mod usbcore edd fan ext3 ext2 mbcache jbd ahci libata scsi_mod > [ 90.276643] > [ 90.276643] Pid: 20238, comm: forkbomb Tainted: G D 2.6.34-smpx #1477 MS-7502/MS-7502 > [ 90.276643] RIP: 0010:[<ffffffff81079014>] [<ffffffff81079014>] perf_output_lock+0x30/0x4e > [ 90.276643] RSP: 0000:ffff880001603b88 EFLAGS: 00000082 > [ 90.276643] RAX: 0000000000000002 RBX: ffff880001603c38 RCX: ffff8800bc454000 > [ 90.276643] RDX: 0000000000000000 RSI: 0000000000000000 RDI: ffff880001603c38 > [ 90.276643] RBP: ffff880001603b98 R08: 0000000000000001 R09: ffff880001603c68 > [ 90.276643] R10: 0000000000000000 R11: 0000000000000000 R12: ffff8800bc454000 > [ 90.276643] R13: ffff880037788000 R14: 0000000000000078 R15: 00000000ffffffe4 > [ 90.276643] FS: 00007ff057202700(0000) GS:ffff880001600000(0000) knlGS:0000000000000000 > [ 90.276643] CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b > [ 90.276643] CR2: 00007ff056d05510 CR3: 00000000bd9f7000 CR4: 00000000000006f0 > [ 90.276643] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 > [ 90.276643] DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 > [ 90.276643] Process forkbomb (pid: 20238, threadinfo ffff8800bd3fa000, task ffff8800b48de8a0) > [ 90.276643] Stack: > [ 90.276643] 00000000071cf224 00000002ffffffff ffff880001603c18 ffffffff8107c5cf > [ 90.276643] <0> ffff880001603bc8 000000000002b3c6 ffff880001603bc8 ffff880001603c68 > [ 90.276643] <0> ffff880001603c18 ffffffff8107d13c ffff8800bc690888 ffff8800b48de8a0 > [ 90.276643] Call Trace: > [ 90.276643] <IRQ> > [ 90.276643] [<ffffffff8107c5cf>] perf_output_begin+0x77/0x180 > [ 90.276643] [<ffffffff8107d13c>] ? perf_prepare_sample+0xb5/0x1d3 > [ 90.276643] [<ffffffff8107d3c5>] __perf_event_overflow+0x16b/0x1ad > [ 90.276643] [<ffffffff8107d45f>] perf_swevent_overflow+0x58/0x76 > [ 90.276643] [<ffffffff8107d4c3>] perf_swevent_add+0x46/0x48 > [ 90.276643] [<ffffffff8107d5a2>] perf_swevent_ctx_event+0xdd/0xee > [ 90.276643] [<ffffffff8107d601>] do_perf_sw_event+0x4e/0x8c > [ 90.276643] [<ffffffff811b8f9e>] ? put_device+0x12/0x14 > [ 90.276643] [<ffffffff8107d670>] perf_tp_event+0x31/0x33 > [ 90.276643] [<ffffffff810263b8>] ? task_tick_fair+0x47/0x103 > [ 90.276643] [<ffffffff810752e6>] ? perf_trace_buf_prepare+0x8e/0xb5 > [ 90.276643] [<ffffffff810247ff>] perf_trace_sched_stat_runtime+0xc4/0xdc > [ 90.276643] [<ffffffffa0000773>] ? scsi_finish_command+0xec/0xf5 [scsi_mod] > [ 90.276643] [<ffffffff81026227>] update_curr+0x87/0xc8 > [ 90.276643] [<ffffffff810263b8>] task_tick_fair+0x47/0x103 > [ 90.276643] [<ffffffff8102ed61>] scheduler_tick+0xd9/0x1e6 > [ 90.276643] [<ffffffff8103f082>] update_process_times+0x4b/0x5b > [ 90.276643] [<ffffffff81054229>] tick_periodic+0x5d/0x5f > [ 90.276643] [<ffffffff8105428e>] tick_handle_periodic+0x21/0x6e > [ 90.276643] [<ffffffff810167a7>] smp_apic_timer_interrupt+0x83/0x96 > [ 90.276643] [<ffffffff81002813>] apic_timer_interrupt+0x13/0x20 > [ 90.276643] <EOI> > [ 90.276643] [<ffffffff8101cbd1>] ? do_page_fault+0x84/0x253 > [ 90.276643] [<ffffffff8101cd6f>] ? do_page_fault+0x222/0x253 > [ 90.276643] [<ffffffff812b5a9f>] page_fault+0x1f/0x30 > [ 90.276643] Code: 83 ec 10 c7 47 28 00 00 00 00 48 8b 4f 08 65 8b 14 25 58 d1 00 00 c7 45 f8 ff ff ff ff 89 55 f4 8b 75 f4 8b 45 f8 f0 0f b1 71 38 <89> 45 fc 8b 45 fc 83 f8 ff 75 09 c7 47 28 01 00 00 00 eb 08 39 > [ 90.276643] ---[ end trace ef30915e055ad1bc ]--- > -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo(a)vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
From: Mike Galbraith on 26 Mar 2010 06:20
On Thu, 2010-03-25 at 10:27 +0100, Mike Galbraith wrote: > On Thu, 2010-03-25 at 16:04 +0800, Li Zefan wrote: > > Mike Galbraith wrote: > > > On Wed, 2010-03-24 at 08:32 +0100, Mike Galbraith wrote: > > > > > >> I just saw this, hunted down your testcase and tried it here. Looks > > >> like perf_output_lock() wedged box. > > > > > > (turns on frame pointers, and adds noinline) > > > > > > > Thanks! Then who's going to fix this... > > Well, that kinda depends on whether I figure out how the heck it's all > supposed to work before somebody else whacks it or not. This seems to work, in contrast to everything I tried yesterday. Not exactly a thing of beauty, but at least it's an option, so... perf: fix perf sched record forkbomb deadlock perf sched record can deadlock a box should the holder of handle->data->lock take an interrupt, and then attempt to acquire an rq lock held by a CPU trying to acquire the same lock. Disable interrupts. Signed-off-by: Mike Galbraith <efault(a)gmx.de> Cc: Ingo Molnar <mingo(a)elte.hu> Cc: Peter Zijlstra <a.p.zijlstra(a)chello.nl> Cc: Arnaldo Carvalho de Melo <acme(a)redhat.com> Cc: Frederic Weisbecker <fweisbec(a)gmail.com> Reported-by: Li Zefan <lizf(a)cn.fujitsu.com> LKML-Reference: <new-submission> diff --git a/kernel/perf_event.c b/kernel/perf_event.c index 574ee58..2ba2e9f 100644 --- a/kernel/perf_event.c +++ b/kernel/perf_event.c @@ -3378,15 +3378,23 @@ static void perf_event_task_output(struct perf_event *event, struct perf_task_event *task_event) { struct perf_output_handle handle; - int size; struct task_struct *task = task_event->task; - int ret; + unsigned long flags; + int size, ret; + + /* + * If this CPU attempts to acquire an rq lock held by a CPU spinning + * in perf_output_lock() from interrupt context, it's game over. + */ + local_irq_save(flags); size = task_event->event_id.header.size; ret = perf_output_begin(&handle, event, size, 0, 0); - if (ret) + if (ret) { + local_irq_restore(flags); return; + } task_event->event_id.pid = perf_event_pid(event, task); task_event->event_id.ppid = perf_event_pid(event, current); @@ -3397,6 +3405,7 @@ static void perf_event_task_output(struct perf_event *event, perf_output_put(&handle, task_event->event_id); perf_output_end(&handle); + local_irq_restore(flags); } static int perf_event_task_match(struct perf_event *event) -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo(a)vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/ |