Re: cpu-2.5.64-1

[Keith Owens <kaos@ocs.com.au>]

On Sun, 16 Mar 2003 00:36:09 -0800, 
William Lee Irwin III <wli@holomorphy.com> wrote:
>On Mon, 10 Mar 2003 20:24:57 -0800, William Lee Irwin III wrote:
>>> Enable NUMA-Q's to run with more than 32 cpus by introducing a bitmap
>> Any main line code that explicitly refers to cpu_online_map is an
>> ongoing maintenance problem.  Nothing should refer to cpu_online_map
>> except the encapsulating macros such as cpu_online().
>
>That was a bit too braindead of a translation, yes. But it is x86 arch
>code so it shouldn't be that large of an issue for big MIPS boxen etc.
>I'll search & replace for stuff of this kind and wipe it out anyway.

Good, it lets us optimize for 1/32/64/lots of cpus.  NR_CPUS > 8 *
sizeof(unsigned long) is the interesting case, it needs arrays.

>This suggests a "cpumask strategy". Care to share more, like your take
>on such things as
>	p = req->task;
>	cpu_dest = __ffs(p->cpus_allowed & cpu_online_map);
>	rq_dest = cpu_rq(cpu_dest);
>in kernel/sched.c?

That definitely needs encapsulation to handle cpus_allowed etc. being
arrays.  A function to generate the logical and of p->cpus_allowed and
cpu_online_map and return cpumask_t * is easy.  Doing ffs on that
result will not work, it assumes NR_CPUS fits in a word.  Add
ffs_cpumask(cpumask_t *).