On Wed, Mar 13, 2013 at 1:25 AM, Tejun Heo <[email protected]> wrote: > Hello, > > On Tue, Mar 12, 2013 at 07:44:55PM +0800, Ming Lei wrote: >> On Tue, Mar 12, 2013 at 7:30 PM, Russell King - ARM Linux >> <[email protected]> wrote: >> >> >> >> Ingo and Peter, what is your opinion on the problem? >> > >> > Having discussed this with Ben Herrenschmidt, it seems that we do need >> > to have a more complex patch to sort this out - we need to setup our >> > private pointer inside setup_per_cpu_areas(). >> >> Suppose so, seems the patch is still needed to make CPU0 see >> static variables in '.data..percpu' section correctly. > > If my memory serves me right, x86 also has places where CPU0 accesses > its per-cpu data in .data.percpu. While those existed (not sure > they're still there but probably they're) mostly due to historical > reasons rather than by design, as long as the data is in consistent > state by and during percpu setup, nothing will break.
Tejun, thanks for your input, yes, nothing will break. For lockdep, the percpu variables in non-boot-CPUs may be initialized again after percpu area is set up. Thanks, -- Ming Lei -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to [email protected] More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
