Re: [BUG 2.6.21-rc2] divide error: 0000

[Thomas Gleixner <tglx@linutronix.de>]

On Fri, 2007-03-02 at 07:11 +0100, Willy Tarreau wrote:
> > Call Trace:
> >  [<c0127d49>] posix_cpu_clock_get+0x47/0xdc
> >  [<c0125bf3>] sys_clock_gettime+0x80/0x82
> >  [<c0103bfc>] syscall_call+0x7/0xb
> >  [<c02f0000>] svc_ioctl+0xc2/0x261
> >  =======================
> > Code: 0b eb fe 57 56 53 89 cb 89 d1 8b 74 24 10 83 e0 03 83 f8 02 74 0c 89 f2 89 c8 5b 5e 5f e9 ee 3f ff ff bf 00 ca 9a 3b 89 d0 89 da <f7> f7 89 56 04 89 06 5b 5e 5f c3 55 57 56 53 89 c7 89 d6 89 cb
> > EIP: [<c0126a07>] sample_to_timespec+0x28/0x33 SS:ESP 0068:d4a56f74
> > 
> > The instruction is:
> > 
> > 	div %edi
> > 
> > And edi is 1e9 (0x3b9aca00). I don't understand why this results in an 
> > divide error. 
> 
> It does this because 'div' does an unsigned divide of edx:eax by edi.
> Here, edx=fffffffa and eax is 63b5a669. Clearly, such a number cannot
> be divided by 1e9 to return a 32 bits value.
> 
> Given the values we see here, I suspect the code should have used an
> integer divide (idiv). This means that something in the code implies
> that the result is unsigned while it should be signed.

The question is why do we have this negative value in the dividend. I
suspect this is related to

http://marc.theaimsgroup.com/?l=linux-kernel&m=117210430112543&w=2

Sean, can you please retest with that patch applied, which hit mainline
after 2.6.21-rc2

	tglx