Re: [PATCH v4 3/6] smp: add function to execute a function synchronously on a cpu

2016-04-05 Thread Juergen Gross
On 05/04/16 10:11, Peter Zijlstra wrote: > On Tue, Apr 05, 2016 at 07:10:04AM +0200, Juergen Gross wrote: >> +int smp_call_on_cpu(unsigned int cpu, bool pin, int (*func)(void *), void >> *par) > > Why .pin and not .phys? .pin does not (to me) reflect the > hypervisor/physical-cpu thing. I don't

Re: [PATCH v4 3/6] smp: add function to execute a function synchronously on a cpu

2016-04-05 Thread Peter Zijlstra
On Tue, Apr 05, 2016 at 07:10:04AM +0200, Juergen Gross wrote: > +int smp_call_on_cpu(unsigned int cpu, bool pin, int (*func)(void *), void > *par) Why .pin and not .phys? .pin does not (to me) reflect the hypervisor/physical-cpu thing. Also, as per smp_call_function_single() would it not be mor

[PATCH v4 3/6] smp: add function to execute a function synchronously on a cpu

2016-04-04 Thread Juergen Gross
On some hardware models (e.g. Dell Studio 1555 laptop) some hardware related functions (e.g. SMIs) are to be executed on physical cpu 0 only. Instead of open coding such a functionality multiple times in the kernel add a service function for this purpose. This will enable the possibility to take sp