While(1) in kernel space

While(1) in kernel space

[Paolo Doz]

[-- Attachment #1: Type: text/plain, Size: 491 bytes --]

Hi folks,
I'm developing a custom SPI driver (char device) on a MPC5200b, the
microcontroller linked as slave implements a protocol that must follow
strict timing constraints. I need to receive and send messages every 6msec.
Actually there is a user space program that synchronizes the two units, but
I would prefer to eliminate it and move the relative code into the kernel
space. Is it possible to have a non returning function, with a sort of
while(1) inside?

Thanks for the help

Paolo

[-- Attachment #2: Type: text/html, Size: 515 bytes --]

Re: While(1) in kernel space

[Grant Likely]

On Tue, Jul 8, 2008 at 1:55 AM, Paolo Doz <paolo.doz@gmail.com> wrote:
> Hi folks,
> I'm developing a custom SPI driver (char device) on a MPC5200b, the
> microcontroller linked as slave implements a protocol that must follow
> strict timing constraints. I need to receive and send messages every 6msec.
> Actually there is a user space program that synchronizes the two units, but
> I would prefer to eliminate it and move the relative code into the kernel
> space. Is it possible to have a non returning function, with a sort of
> while(1) inside?
>
> Thanks for the help

You can use a kernel thread.

I'm not sure how accurate this is, but here is some information about them:

http://www.linuxquestions.org/linux/articles/Technical/Linux_Kernel_Thread

Re: While(1) in kernel space

[Arnd Bergmann]

On Tuesday 08 July 2008, Grant Likely wrote:

> 
> You can use a kernel thread.
> 
> I'm not sure how accurate this is, but here is some information about them:
> 
> http://www.linuxquestions.org/linux/articles/Technical/Linux_Kernel_Thread

Not accurate at all. New code should use kthread_create, as documented in

http://lwn.net/Articles/65178/

	Arnd <><

Re: While(1) in kernel space

[Grant Likely]

On Tue, Jul 8, 2008 at 8:45 AM, Arnd Bergmann <arnd@arndb.de> wrote:
> On Tuesday 08 July 2008, Grant Likely wrote:
>
>>
>> You can use a kernel thread.
>>
>> I'm not sure how accurate this is, but here is some information about them:
>>
>> http://www.linuxquestions.org/linux/articles/Technical/Linux_Kernel_Thread
>
> Not accurate at all. New code should use kthread_create, as documented in
>
> http://lwn.net/Articles/65178/

Teach me to blindly use google.  Thanks Arnd.

g.

-- 
Grant Likely, B.Sc., P.Eng.
Secret Lab Technologies Ltd.

Re: While(1) in kernel space

[Paolo Doz]

[-- Attachment #1: Type: text/plain, Size: 888 bytes --]

Thanks for the infos, I'll try kernel thread or timer/softirq in the next
days.
I'll let you know which of them fit my problems.

I actually have about +/- 1msec of freedom (but still require more
investigation).

Paolo

On Tue, Jul 8, 2008 at 4:47 PM, Grant Likely <grant.likely@secretlab.ca>
wrote:

> On Tue, Jul 8, 2008 at 8:45 AM, Arnd Bergmann <arnd@arndb.de> wrote:
> > On Tuesday 08 July 2008, Grant Likely wrote:
> >
> >>
> >> You can use a kernel thread.
> >>
> >> I'm not sure how accurate this is, but here is some information about
> them:
> >>
> >>
> http://www.linuxquestions.org/linux/articles/Technical/Linux_Kernel_Thread
> >
> > Not accurate at all. New code should use kthread_create, as documented in
> >
> > http://lwn.net/Articles/65178/
>
> Teach me to blindly use google.  Thanks Arnd.
>
> g.
>
> --
> Grant Likely, B.Sc., P.Eng.
> Secret Lab Technologies Ltd.
>

[-- Attachment #2: Type: text/html, Size: 1539 bytes --]

Re: While(1) in kernel space

[Chris Friesen]

Paolo Doz wrote:
> Hi folks,
> I'm developing a custom SPI driver (char device) on a MPC5200b, the 
> microcontroller linked as slave implements a protocol that must follow 
> strict timing constraints. I need to receive and send messages every 
> 6msec.

What are your timing requirements?  How much over/under 6ms can the 
protocol handle?

Kernel threads might work, but then you're at the mercy of the 
scheduler.  You'd probably be better off using a timer or softirq.

If the latency requirements are really strict, your best bet would 
probably be to use the -rt patches for the kernel.  That requires 
building a custom kernel though.

Chris