Bug 43971

Summary:	WARNING: at arch/x86/kernel/apic/ipi.c:109 default_send_IPI_mask_logical+0x97/0xc7() - ProLiant DL360 G4
Product:	Platform Specific/Hardware	Reporter:	Ralf Hildebrandt (ralf.hildebrandt)
Component:	i386	Assignee:	H. Peter Anvin (hpa)
Status:	ASSIGNED ---
Severity:	low	CC:	fzachi, lenb, smf-linux
Priority:	P1
Hardware:	All
OS:	Linux
Kernel Version:	3.6.7	Subsystem:
Regression:	No	Bisected commit-id:

Description Ralf Hildebrandt 2012-06-29 13:37:35 UTC

Jun 26 12:42:49 mail2 kernel: [436077.350389] ------------[ cut here ]------------
Jun 26 12:42:49 mail2 kernel: [436077.350417] WARNING: at arch/x86/kernel/apic/ipi.c:109 default_send_IPI_mask_logical+0x97/0xc7()
Jun 26 12:42:49 mail2 kernel: [436077.350423] Hardware name: ProLiant DL360 G4
Jun 26 12:42:49 mail2 kernel: [436077.350426] empty IPI mask
Jun 26 12:42:49 mail2 kernel: [436077.350428] Modules linked in: nfnetlink_log nfnetlink ipv6 tg3 microcode hpwdt rng_core psmouse container i6300esb button thermal processor
Jun 26 12:42:49 mail2 kernel: [436077.350457] Pid: 20792, comm: /usr/sbin/amavi Not tainted 3.4.3 #1
Jun 26 12:42:49 mail2 kernel: [436077.350462] Call Trace:
Jun 26 12:42:49 mail2 kernel: [436077.350477]  [<c1024334>] warn_slowpath_common+0x67/0x8e
Jun 26 12:42:49 mail2 kernel: [436077.350484]  [<c1018795>] ? default_send_IPI_mask_logical+0x97/0xc7
Jun 26 12:42:49 mail2 kernel: [436077.350490]  [<c1018795>] ? default_send_IPI_mask_logical+0x97/0xc7
Jun 26 12:42:49 mail2 kernel: [436077.350496]  [<c10243d7>] warn_slowpath_fmt+0x2e/0x30
Jun 26 12:42:49 mail2 kernel: [436077.350502]  [<c1018795>] default_send_IPI_mask_logical+0x97/0xc7
Jun 26 12:42:49 mail2 kernel: [436077.350510]  [<c107007b>] ? put_callchain_buffers+0x1b/0x3d
Jun 26 12:42:49 mail2 kernel: [436077.350516]  [<c10173ad>] native_send_call_func_ipi+0x42/0x54
Jun 26 12:42:49 mail2 kernel: [436077.350525]  [<c1055ae7>] smp_call_function_many+0x15c/0x1d5
Jun 26 12:42:49 mail2 kernel: [436077.350534]  [<c107713b>] ? drain_pages+0x62/0x62
Jun 26 12:42:49 mail2 kernel: [436077.350540]  [<c1055b85>] on_each_cpu_mask+0x25/0x3d
Jun 26 12:42:49 mail2 kernel: [436077.350545]  [<c107713b>] ? drain_pages+0x62/0x62
Jun 26 12:42:49 mail2 kernel: [436077.350550]  [<c10751fa>] drain_all_pages+0x89/0x90
Jun 26 12:42:49 mail2 kernel: [436077.350555]  [<c10774f3>] __alloc_pages_nodemask+0x3a8/0x651
Jun 26 12:42:49 mail2 kernel: [436077.350567]  [<c10a0ace>] do_huge_pmd_wp_page+0x1bc/0x567
Jun 26 12:42:49 mail2 kernel: [436077.350574]  [<c1044787>] ? __enqueue_entity+0x67/0x6f
Jun 26 12:42:49 mail2 kernel: [436077.350582]  [<c1089972>] handle_mm_fault+0x14a/0x206
Jun 26 12:42:49 mail2 kernel: [436077.350588]  [<c101d725>] ? vmalloc_sync_all+0x5/0x5
Jun 26 12:42:49 mail2 kernel: [436077.350593]  [<c101d818>] do_page_fault+0xf3/0x3ab
Jun 26 12:42:49 mail2 kernel: [436077.350604]  [<c1008fbc>] ? sys_clone+0x2b/0x32
Jun 26 12:42:49 mail2 kernel: [436077.350609]  [<c101d725>] ? vmalloc_sync_all+0x5/0x5
Jun 26 12:42:49 mail2 kernel: [436077.350620]  [<c12873bf>] error_code+0x67/0x6c
Jun 26 12:42:49 mail2 kernel: [436077.350625] ---[ end trace 402a702d5527abf9 ]---

Comment 1 Ralf Hildebrandt 2012-10-02 18:02:59 UTC

It's that time of the year when you search for a bug and find your own bug, from years ago...

It's even from the same machine!

Oct  2 10:49:33 mail2 kernel: [62773.643261] ------------[ cut here ]------------
Oct  2 10:49:33 mail2 kernel: [62773.643289] WARNING: at arch/x86/kernel/apic/ipi.c:109
default_send_IPI_mask_logical+0x97/0xc7()
Oct  2 10:49:33 mail2 kernel: [62773.643296] Hardware name: ProLiant DL360 G4
Oct  2 10:49:33 mail2 kernel: [62773.643301] empty IPI mask
Oct  2 10:49:33 mail2 kernel: [62773.643306] Modules linked in: nfnetlink_log nfnetlink ipv6 tg3 microcode rng_core psmouse
hpwdt container thermal button processor i6300esb
Oct  2 10:49:33 mail2 kernel: [62773.643349] Pid: 22582, comm: clamd Not tainted 3.6.0 #1
Oct  2 10:49:33 mail2 kernel: [62773.643352] Call Trace:
Oct  2 10:49:33 mail2 kernel: [62773.643362]  [<c1027f94>] warn_slowpath_common+0x67/0x8e
Oct  2 10:49:33 mail2 kernel: [62773.643368]  [<c101beef>] ? default_send_IPI_mask_logical+0x97/0xc7
Oct  2 10:49:33 mail2 kernel: [62773.643373]  [<c101beef>] ? default_send_IPI_mask_logical+0x97/0xc7
Oct  2 10:49:33 mail2 kernel: [62773.643378]  [<c1028037>] warn_slowpath_fmt+0x2e/0x30
Oct  2 10:49:33 mail2 kernel: [62773.643383]  [<c101beef>] default_send_IPI_mask_logical+0x97/0xc7
Oct  2 10:49:33 mail2 kernel: [62773.643391]  [<c101aac4>] native_send_call_func_ipi+0x42/0x54
Oct  2 10:49:33 mail2 kernel: [62773.643398]  [<c105c56a>] smp_call_function_many+0x160/0x1dd
Oct  2 10:49:33 mail2 kernel: [62773.643403]  [<c1024fe7>] native_flush_tlb_others+0x26/0x28
Oct  2 10:49:33 mail2 kernel: [62773.643408]  [<c1025218>] flush_tlb_page+0x49/0x73
Oct  2 10:49:33 mail2 kernel: [62773.643416]  [<c109c420>] ptep_clear_flush+0x18/0x20
Oct  2 10:49:33 mail2 kernel: [62773.643427]  [<c108fe26>] do_wp_page+0x1f4/0x72f
Oct  2 10:49:33 mail2 kernel: [62773.643438]  [<c104ab0c>] ? __enqueue_entity+0x6b/0x73
Oct  2 10:49:33 mail2 kernel: [62773.643447]  [<c10917c4>] handle_pte_fault+0x47a/0x8d8
Oct  2 10:49:33 mail2 kernel: [62773.643452]  [<c105c7eb>] ? generic_smp_call_function_interrupt+0x6c/0x150
Oct  2 10:49:33 mail2 kernel: [62773.643457]  [<c105c842>] ? generic_smp_call_function_interrupt+0xc3/0x150
Oct  2 10:49:33 mail2 kernel: [62773.643462]  [<c10928e1>] handle_mm_fault+0x19c/0x211
Oct  2 10:49:33 mail2 kernel: [62773.643471]  [<c1020fe5>] ? vmalloc_sync_all+0x5/0x5
Oct  2 10:49:33 mail2 kernel: [62773.643476]  [<c10210d8>] do_page_fault+0xf3/0x3ab
Oct  2 10:49:33 mail2 kernel: [62773.643483]  [<c105c842>] ? generic_smp_call_function_interrupt+0xc3/0x150
Oct  2 10:49:33 mail2 kernel: [62773.643494]  [<c116a593>] ? radix_tree_lookup_slot+0xd/0xf
Oct  2 10:49:33 mail2 kernel: [62773.643502]  [<c10793fd>] ? find_get_page+0x1b/0x70
Oct  2 10:49:33 mail2 kernel: [62773.643511]  [<c1020fe5>] ? vmalloc_sync_all+0x5/0x5
Oct  2 10:49:33 mail2 kernel: [62773.643523]  [<c129f7a3>] error_code+0x67/0x6c
Oct  2 10:49:33 mail2 kernel: [62773.643531]  [<c107914e>] ? file_read_actor+0x25/0xb8
Oct  2 10:49:33 mail2 kernel: [62773.643540]  [<c1088e4b>] shmem_file_aio_read+0xf1/0x2bb
Oct  2 10:49:33 mail2 kernel: [62773.643552]  [<c10abb31>] do_sync_read+0x8f/0xbf
Oct  2 10:49:33 mail2 kernel: [62773.643558]  [<c10abaa2>] ? do_sync_write+0xbf/0xbf
Oct  2 10:49:33 mail2 kernel: [62773.643558]  [<c10abaa2>] ? do_sync_write+0xbf/0xbf
Oct  2 10:49:33 mail2 kernel: [62773.643563]  [<c10ac450>] vfs_read+0x80/0x13e
Oct  2 10:49:33 mail2 kernel: [62773.643568]  [<c10abaa2>] ? do_sync_write+0xbf/0xbf
Oct  2 10:49:33 mail2 kernel: [62773.643573]  [<c10ac636>] sys_pread64+0x4e/0x7c
Oct  2 10:49:33 mail2 kernel: [62773.643578]  [<c129fa17>] sysenter_do_call+0x12/0x26
Oct  2 10:49:33 mail2 kernel: [62773.643582] ---[ end trace 5b941cf88518b699 ]---

Comment 2 Frank Zacharias 2012-10-14 11:55:34 UTC

I get the same WARNING here, but with 3.6.y only (intel z68 chipset on asus board, x86 32bit). Suprisingly, it is triggered by desktop monitoring application conky.

Comment 3 Stuart Foster 2012-10-20 21:14:43 UTC

(In reply to comment #2)
> I get the same WARNING here, but with 3.6.y only (intel z68 chipset on asus
> board, x86 32bit). Suprisingly, it is triggered by desktop monitoring
> application conky.

------------[ cut here ]------------
WARNING: at arch/x86/kernel/apic/ipi.c:109 default_send_IPI_mask_logical+0xa6/0xe0()
Hardware name: To be filled by O.E.M.
empty IPI mask
Modules linked in: nfsv3 tbs62x0fe(PO) ir_lirc_codec(O) lirc_dev(O) ir_mce_kbd_decoder(O) ir_sony_decoder(O) ir_jvc_decoder(O) usbhid rc_tbs_nec(O) microcode ir_rc6_decoder(O) psmouse saa716x_tbs_dvb(O) sata_via tbs6982fe(PO) tbs6680fe(PO) ir_rc5_decoder(O) tbs6991fe(PO) tbs6618fe(PO) saa716x_core(O) i2c_piix4 tbs6922fe(PO) ir_nec_decoder(O) sr_mod tbs6928fe(PO) ohci_hcd stv090x(O) cdrom dvb_core(O) rc_core(O) r8169 rtc_cmos button xhci_hcd cifs dm_mod fuse aes_generic md5 ecryptfs nfs nfsd lockd sunrpc vboxnetflt(O) fifo splitter vboxnetadp(O) snd_hda_codec_hdmi snd_hda_codec_realtek snd_hda_intel snd_hda_codec snd_seq_dummy snd_seq_oss snd_seq_midi_event snd_seq snd_seq_device snd_pcm_oss snd_mixer_oss snd_hwdep snd_pcm snd_page_alloc snd_timer snd soundcore brd loop k10temp powernow_k8 mperf processor thermal_sys pata_atiixp vboxdrv(O) eeprom usb_storage fscache
Pid: 5151, comm: carousel Tainted: P           O 3.6.2 #1
Call Trace:
 [<c105dd6c>] ? warn_slowpath_common+0x6c/0xa0
 [<c104fe66>] ? default_send_IPI_mask_logical+0xa6/0xe0
 [<c104fe66>] ? default_send_IPI_mask_logical+0xa6/0xe0
 [<c105a7e0>] ? do_flush_tlb_all+0x60/0x60
 [<c105de33>] ? warn_slowpath_fmt+0x33/0x40
 [<c104fe66>] ? default_send_IPI_mask_logical+0xa6/0xe0
 [<c105a7e0>] ? do_flush_tlb_all+0x60/0x60
 [<c104e1df>] ? native_send_call_func_ipi+0x3f/0x60
 [<c109a0a3>] ? smp_call_function_many+0x163/0x200
 [<c105a888>] ? native_flush_tlb_others+0x28/0x40
 [<c105aae6>] ? flush_tlb_page+0x46/0x80
 [<c10e2a55>] ? ptep_clear_flush+0x15/0x20
 [<c10d4b3a>] ? do_wp_page+0x21a/0x760
 [<c10d6728>] ? handle_pte_fault+0x4a8/0x980
 [<c109a35d>] ? generic_smp_call_function_interrupt+0xbd/0x140
 [<c1055c80>] ? vmalloc_sync_all+0x20/0x20
 [<c13edf5a>] ? call_function_interrupt+0x2a/0x30
 [<c10d7252>] ? handle_mm_fault+0x1d2/0x260
 [<c1055c80>] ? vmalloc_sync_all+0x20/0x20
 [<c1055d7b>] ? do_page_fault+0xfb/0x3c0
 [<c10952c1>] ? tick_program_event+0x21/0x40
 [<c10990dd>] ? sys_futex+0x7d/0x160
 [<c109a313>] ? generic_smp_call_function_interrupt+0x73/0x140
 [<c1055c80>] ? vmalloc_sync_all+0x20/0x20
 [<c13ee206>] ? error_code+0x5a/0x60
 [<c1055c80>] ? vmalloc_sync_all+0x20/0x20
---[ end trace 678ffcec38a7a317 ]---

I think this is the same issue reported by a ASUS M5A97 PRO with AMD Phenom(tm) II X6 1100T Processor (3.6.2 kerne)l. The machine was idle at the time running xscreensaver app. This is the second time I have seen the issue in the last 3 days.

Comment 4 Ralf Hildebrandt 2012-11-21 14:00:08 UTC

# uname -a
Linux mail2.charite.de 3.6.7 #1 SMP Sun Nov 18 19:49:09 CET 2012 i686 GNU/Linux

Nov 19 10:54:16 mail2 kernel: [52464.940539] ------------[ cut here ]------------
Nov 19 10:54:16 mail2 kernel: [52464.940566] WARNING: at arch/x86/kernel/apic/ipi.c:109 default_send_IPI_mask_logical+0x97/0xc7()
Nov 19 10:54:16 mail2 kernel: [52464.940570] Hardware name: ProLiant DL360 G4
Nov 19 10:54:16 mail2 kernel: [52464.940573] empty IPI mask
Nov 19 10:54:16 mail2 kernel: [52464.940576] Modules linked in: nfnetlink_log nfnetlink ipv6 microcode psmouse container hpwdt tg3 thermal rng_core i6300esb button processor
Nov 19 10:54:16 mail2 kernel: [52464.940603] Pid: 27794, comm: clamd Not tainted 3.6.7 #1
Nov 19 10:54:16 mail2 kernel: [52464.940606] Call Trace:
Nov 19 10:54:16 mail2 kernel: [52464.940620]  [<c1027f84>] warn_slowpath_common+0x67/0x8e
Nov 19 10:54:16 mail2 kernel: [52464.940627]  [<c101beef>] ? default_send_IPI_mask_logical+0x97/0xc7
Nov 19 10:54:16 mail2 kernel: [52464.940631]  [<c101beef>] ? default_send_IPI_mask_logical+0x97/0xc7
Nov 19 10:54:16 mail2 kernel: [52464.940636]  [<c1028027>] warn_slowpath_fmt+0x2e/0x30
Nov 19 10:54:16 mail2 kernel: [52464.940641]  [<c101beef>] default_send_IPI_mask_logical+0x97/0xc7
Nov 19 10:54:16 mail2 kernel: [52464.940650]  [<c101aac4>] native_send_call_func_ipi+0x42/0x54
Nov 19 10:54:16 mail2 kernel: [52464.940657]  [<c105c5fa>] smp_call_function_many+0x160/0x1dd
Nov 19 10:54:16 mail2 kernel: [52464.940663]  [<c1024fe7>] native_flush_tlb_others+0x26/0x28
Nov 19 10:54:16 mail2 kernel: [52464.940667]  [<c1025087>] flush_tlb_mm_range+0x4f/0x18e
Nov 19 10:54:16 mail2 kernel: [52464.940676]  [<c108f706>] tlb_flush_mmu+0x7a/0x7c
Nov 19 10:54:16 mail2 kernel: [52464.940681]  [<c108f71a>] tlb_finish_mmu+0x12/0x33
Nov 19 10:54:16 mail2 kernel: [52464.940686]  [<c109473f>] unmap_region+0x88/0x9e
Nov 19 10:54:16 mail2 kernel: [52464.940691]  [<c1095bb9>] do_munmap+0x1bb/0x2aa
Nov 19 10:54:16 mail2 kernel: [52464.940696]  [<c1095cda>] vm_munmap+0x32/0x45
Nov 19 10:54:16 mail2 kernel: [52464.940700]  [<c10967e6>] sys_munmap+0xe/0x10
Nov 19 10:54:16 mail2 kernel: [52464.940710]  [<c129ff17>] sysenter_do_call+0x12/0x26
Nov 19 10:54:16 mail2 kernel: [52464.940713] ---[ end trace a5fffac357fb1c34 ]---

Comment 5 Ralf Hildebrandt 2012-11-21 14:00:32 UTC

Changed affected kernel version...

Comment 6 Stuart Foster 2012-12-28 22:48:50 UTC

(In reply to comment #3)
> (In reply to comment #2)
> > I get the same WARNING here, but with 3.6.y only (intel z68 chipset on asus
> > board, x86 32bit). Suprisingly, it is triggered by desktop monitoring
> > application conky.
> 
> ------------[ cut here ]------------
> WARNING: at arch/x86/kernel/apic/ipi.c:109
> default_send_IPI_mask_logical+0xa6/0xe0()
> Hardware name: To be filled by O.E.M.
> empty IPI mask
> Modules linked in: nfsv3 tbs62x0fe(PO) ir_lirc_codec(O) lirc_dev(O)
> ir_mce_kbd_decoder(O) ir_sony_decoder(O) ir_jvc_decoder(O) usbhid
> rc_tbs_nec(O)
> microcode ir_rc6_decoder(O) psmouse saa716x_tbs_dvb(O) sata_via tbs6982fe(PO)
> tbs6680fe(PO) ir_rc5_decoder(O) tbs6991fe(PO) tbs6618fe(PO) saa716x_core(O)
> i2c_piix4 tbs6922fe(PO) ir_nec_decoder(O) sr_mod tbs6928fe(PO) ohci_hcd
> stv090x(O) cdrom dvb_core(O) rc_core(O) r8169 rtc_cmos button xhci_hcd cifs
> dm_mod fuse aes_generic md5 ecryptfs nfs nfsd lockd sunrpc vboxnetflt(O) fifo
> splitter vboxnetadp(O) snd_hda_codec_hdmi snd_hda_codec_realtek snd_hda_intel
> snd_hda_codec snd_seq_dummy snd_seq_oss snd_seq_midi_event snd_seq
> snd_seq_device snd_pcm_oss snd_mixer_oss snd_hwdep snd_pcm snd_page_alloc
> snd_timer snd soundcore brd loop k10temp powernow_k8 mperf processor
> thermal_sys pata_atiixp vboxdrv(O) eeprom usb_storage fscache
> Pid: 5151, comm: carousel Tainted: P           O 3.6.2 #1
> Call Trace:
>  [<c105dd6c>] ? warn_slowpath_common+0x6c/0xa0
>  [<c104fe66>] ? default_send_IPI_mask_logical+0xa6/0xe0
>  [<c104fe66>] ? default_send_IPI_mask_logical+0xa6/0xe0
>  [<c105a7e0>] ? do_flush_tlb_all+0x60/0x60
>  [<c105de33>] ? warn_slowpath_fmt+0x33/0x40
>  [<c104fe66>] ? default_send_IPI_mask_logical+0xa6/0xe0
>  [<c105a7e0>] ? do_flush_tlb_all+0x60/0x60
>  [<c104e1df>] ? native_send_call_func_ipi+0x3f/0x60
>  [<c109a0a3>] ? smp_call_function_many+0x163/0x200
>  [<c105a888>] ? native_flush_tlb_others+0x28/0x40
>  [<c105aae6>] ? flush_tlb_page+0x46/0x80
>  [<c10e2a55>] ? ptep_clear_flush+0x15/0x20
>  [<c10d4b3a>] ? do_wp_page+0x21a/0x760
>  [<c10d6728>] ? handle_pte_fault+0x4a8/0x980
>  [<c109a35d>] ? generic_smp_call_function_interrupt+0xbd/0x140
>  [<c1055c80>] ? vmalloc_sync_all+0x20/0x20
>  [<c13edf5a>] ? call_function_interrupt+0x2a/0x30
>  [<c10d7252>] ? handle_mm_fault+0x1d2/0x260
>  [<c1055c80>] ? vmalloc_sync_all+0x20/0x20
>  [<c1055d7b>] ? do_page_fault+0xfb/0x3c0
>  [<c10952c1>] ? tick_program_event+0x21/0x40
>  [<c10990dd>] ? sys_futex+0x7d/0x160
>  [<c109a313>] ? generic_smp_call_function_interrupt+0x73/0x140
>  [<c1055c80>] ? vmalloc_sync_all+0x20/0x20
>  [<c13ee206>] ? error_code+0x5a/0x60
>  [<c1055c80>] ? vmalloc_sync_all+0x20/0x20
> ---[ end trace 678ffcec38a7a317 ]---
> 
> I think this is the same issue reported by a ASUS M5A97 PRO with AMD
> Phenom(tm)
> II X6 1100T Processor (3.6.2 kerne)l. The machine was idle at the time
> running
> xscreensaver app. This is the second time I have seen the issue in the last 3
> days.

Just had the kernel report the same warning with 3.7.1 kernel

Comment 7 Len Brown 2013-01-29 04:35:07 UTC

This appears to be an x86 interrupt issue, rather than an ACPI issue.