Re: [RFC][Patch] fix for irq_affinity_write_proc v2.5

[William Lee Irwin III]

On Maw, 2003-05-06 at 20:03, Keith Mannthey wrote:
>>   irq_affinity_write_proc currently directly calls set_ioapic_affinity
>> which writes to the ioapic.  This undermines the work done by kirqd by
>> writing a cpu mask directly to the ioapic. I propose the following patch
>> to tie the /proc affinity writes into the same code path as kirqd. 
>> Kirqd will enforce the affinity requested by the user.   

On Tue, May 06, 2003 at 08:54:35PM +0100, Alan Cox wrote:
> Why should the kernel be enforcing policy here. You have to be root to 
> do this, and root should have the ability to configure apparently stupid
> things because they may find them useful.

It's basically not working as specified for clustered hierarchical, and
in truth the specification can never be met. As it stands most calls to
it are lethal on such systems, especially those using physical destmod.

I'd prefer to have it redesigned for some validity checking and error
returns as on such systems the impossible destinations serve no purpose
but raising MCE's and/or deadlocking the box.

-- wli