On Thu, 27 Jun 2019, Thomas Gleixner wrote:OK. I will also add the extra optimization for other architectures.
On Wed, 26 Jun 2019, subhra mazumdar wrote:Aside of that the right ordering is to introduce the default fallback in a
Introduce a per-cpu variable to keep the number of HT siblings of a cpu.Why? The number of siblings is constant at least today unless you play
This will be used for quick lookup in select_idle_cpu to determine the
limits of search.
silly cpu hotplug games. A bit more justification for adding yet another
random storage would be appreciated.
This patch does it only for x86.# grep 'This patch' Documentation/process/submitting-patches.rst
IOW, we all know already that this is a patch and from the subject prefix
and the diffstat it's pretty obvious that this is x86 only.
So instead of documenting the obvious, please add proper context to justify
the change.
separate patch, which explains the reasoning and then in the next one add
the x86 optimized version.
Thanks,
tglx