Dynamically allocate per-cpu scheduler state

[jeff]

Summary

We want to allocate scheduler state dynamically so that it can be allocated to the correct NUMA domain. This also eliminates a global and statically sized MAXCPU state array.

I added a per-cpu variable to point at dpcpu allocated memory to keep the instruction bloat down. This actually makes TDQ_SELF() more efficient than it was before but TDQ_CPU() is less efficient.

[kib]

Can you re-upload the diff with the full context added, please ?

[gallatin]

Much cleaner, as usual, than the hack I gave you to start with.

[markj]

In D19315#413467, @kib wrote:

Can you re-upload the diff with the full context added, please ?

+1, it is painful to review diffs without context.

Am I right that in head, dpcpu area allocations are not yet NUMA-affinitized?

kern/sched_ule.c

315 ↗

(On Diff #54278)

It's called "id" in the definition.

[kib]

In D19315#415445, @markj wrote:

Am I right that in head, dpcpu area allocations are not yet NUMA-affinitized?

Yes, it is just kmem_malloc() in mp_machdep.c:native_start_all_aps().