Bug 5203

Summary:	Badness in send_IPI_mask_bitmask at arch/i386/kernel/smp.c:168
Product:	Platform Specific/Hardware	Reporter:	Stephen Hemminger (stephen)
Component:	i386	Assignee:	Zwane Mwaikambo (zwane)
Status:	CLOSED CODE_FIX
Severity:	normal	CC:	akpm, bunk, jgcc, wolfgang.schnitker
Priority:	P2
Hardware:	i386
OS:	Linux
Kernel Version:	2.6.13	Subsystem:
Regression:	---	Bisected commit-id:

Description Stephen Hemminger 2005-09-07 15:15:02 UTC

Most recent kernel where this bug did not occur: 2.6.13
Distribution: redhat
Hardware Environment: P4 one cpu (HT)
Software Environment: 2.6.13 custom built kernel
Problem Description:

Steps to reproduce:

During shutdown (halt -p) got this console message.

Badness in send_IPI_mask_bitmask at arch/i386/kernel/smp.c:168
 [<c0103cd7>] dump_stack+0x17/0x20
 [<c0112286>] send_IPI_mask_bitmask+0x86/0x90
 [<c0112689>] smp_send_reschedule+0x19/0x20
 [<c0117e9b>] resched_task+0x6b/0x90
 [<c01186cb>] try_to_wake_up+0x2db/0x310
 [<c011872a>] wake_up_state+0xa/0x10
 [<c012832b>] signal_wake_up+0x2b/0x40
 [<c0128be0>] __group_complete_signal+0x210/0x250
 [<c0128cb3>] __group_send_sig_info+0x93/0xd0
 [<c0129561>] do_notify_parent+0xe1/0x1c0
 [<c01206b6>] exit_notify+0x366/0x830
 [<c0120e14>] do_exit+0x294/0x3a0
 [<c012b5ef>] sys_reboot+0xcf/0x160
 [<c0102ded>] syscall_call+0x7/0xb

Comment 1 Zwane Mwaikambo 2005-11-26 23:27:43 UTC

It looks like there is a window before the system reboots when the other
processors have taken themselves offline and there are still tasks with those
processors still in the cpus_possible map. I should be posting a patch for it.

Comment 2 Dave Jones 2005-11-29 15:33:16 UTC

https://bugzilla.redhat.com/bugzilla/show_bug.cgi?id=169700
 has another report of this problem, that's still present in a 2.6.14.3 based
kernel.

Comment 3 Zwane Mwaikambo 2005-12-02 12:08:01 UTC

Eric has a patch, i'll ping him to send it to Andrew.

Comment 4 Adrian Bunk 2006-01-05 03:41:32 UTC

*** Bug 5831 has been marked as a duplicate of this bug. ***

Comment 5 Adrian Bunk 2006-01-05 03:44:19 UTC

Is this problem still present in 2.6.15?

@Zwane:
What/Where is this patch you are talking about?

@Andrew:
http://lkml.org/lkml/2005/9/11/21
http://lkml.org/lkml/2005/11/1/92

Comment 6 Wolfgang Schnitker 2006-01-05 07:49:48 UTC

I just tested 2.6.15 linux-image from backports.org on my machine. The bug has 
gone, no IPI left. Normal behaviour. Wolfgang Schnitker

Comment 7 Zwane Mwaikambo 2006-01-05 10:17:01 UTC

This should be fixed now.