commit f5f293a4e3d0a0c52cec31de6762c95050156516
Author: Eric Dumazet <dada1@cosmosbay.com>
Date:   Wed Apr 29 14:44:49 2009 +0200

    sched: account system time properly
    
    Andrew Gallatin reported that IRQ and SOFTIRQ times were
    sometime not reported correctly on recent kernels, and even
    bisected to commit 457533a7d3402d1d91fbc125c8bd1bd16dcd3cd4
    ([PATCH] fix scaled & unscaled cputime accounting) as the first
    bad commit.
    
    Further analysis pointed that commit
    79741dd35713ff4f6fd0eafd59fa94e8a4ba922d ([PATCH] idle cputime
    accounting) was the real cause of the problem.
    
    account_process_tick() was not taking into account timer IRQ
    interrupting the idle task servicing a hard or soft irq.
    
    On mostly idle cpu, irqs were thus not accounted and top or
    mpstat could tell user/admin that cpu was 100 % idle, 0.00 %
    irq, 0.00 % softirq, while it was not.
    
    [ Impact: fix occasionally incorrect CPU statistics in top/mpstat ]
    
    Reported-by: Andrew Gallatin <gallatin@myri.com>
    Re-reported-by: Andrew Morton <akpm@linux-foundation.org>
    Signed-off-by: Eric Dumazet <dada1@cosmosbay.com>
    Acked-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
    Cc: rick.jones2@hp.com
    Cc: brice@myri.com
    Cc: Paul Mackerras <paulus@samba.org>
    Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
    LKML-Reference: <49F84BC1.7080602@cosmosbay.com>
    Signed-off-by: Ingo Molnar <mingo@elte.hu>

diff -udrNp linux-2.6.27.orig/kernel/sched.c linux-2.6.27/kernel/sched.c
--- linux-2.6.27.orig/kernel/sched.c	2009-10-02 05:14:57.590579107 -0500
+++ linux-2.6.27/kernel/sched.c	2009-10-02 05:15:19.947578991 -0500
@@ -4187,7 +4187,7 @@ void account_process_tick(struct task_st
 
 	if (user_tick)
 		account_user_time(p, one_jiffy, one_jiffy_scaled);
-	else if (p != rq->idle)
+	else if ((p != rq->idle) || (irq_count() != HARDIRQ_OFFSET))
 		account_system_time(p, HARDIRQ_OFFSET, one_jiffy,
 				    one_jiffy_scaled);
 	else