Messages in this thread | | | Date | Mon, 25 Jan 2016 11:08:05 +0530 | From | Gautham R Shenoy <> | Subject | Re: [PATCH v6 2/5] cpufreq: powernv: Remove cpu_to_chip_id() from hot-path |
| |
Hello Balbir,
On Sat, Jan 23, 2016 at 07:59:20PM +1100, Balbir Singh wrote: > On Fri, 22 Jan 2016 12:49:02 +0530 > Shilpasri G Bhat <shilpa.bhat@linux.vnet.ibm.com> wrote: > > > cpu_to_chip_id() does a DT walk through to find out the chip id by > > taking a contended device tree lock. This adds an unnecessary overhead > > in a hot path. So instead of calling cpu_to_chip_id() everytime cache > > the chip ids for all cores in the array 'core_to_chip_map' and use it > > in the hotpath. > > > > Reported-by: Anton Blanchard <anton@samba.org> > > Signed-off-by: Shilpasri G Bhat <shilpa.bhat@linux.vnet.ibm.com> > > Reviewed-by: Gautham R. Shenoy <ego@linux.vnet.ibm.com> > > snip > > Does the core_to_chip_map need to be updated/refreshed on/after/ a > cpu (core) hotplug? I presume id's don't change
No, the id's don't change on cpu/core hotplug. The core_to_chip_map is initialized in init_chip_info() where we use for_each_possible_cpu().
Thanks for the review! > > Balbir > -- Thanks and Regards gautham.
| |