Re: [RFC 0/2] x86, vdso, pvclock: Cleanups and speedups

2014-12-23 Thread Paolo Bonzini
On 23/12/2014 09:16, Andy Lutomirski wrote: > Any thoughts as to whether it should be tagged for stable? I haven't > looked closely enough at the old pvclock code or the generated code to > have much of an opinion there. It'll be a big speedup for non-pvclock > users at least. Yes, please. Pa

Re: [RFC 0/2] x86, vdso, pvclock: Cleanups and speedups

2014-12-23 Thread Andy Lutomirski
On Mon, Dec 22, 2014 at 11:21 PM, Paolo Bonzini wrote: > > > On 23/12/2014 01:39, Andy Lutomirski wrote: >> This is a dramatic simplification and speedup of the vdso pvclock read >> code. Is it correct? >> >> Andy Lutomirski (2): >> x86, vdso: Use asm volatile in __getcpu >> x86, vdso, pvcloc

Re: [RFC 0/2] x86, vdso, pvclock: Cleanups and speedups

2014-12-22 Thread Paolo Bonzini
On 23/12/2014 01:39, Andy Lutomirski wrote: > This is a dramatic simplification and speedup of the vdso pvclock read > code. Is it correct? > > Andy Lutomirski (2): > x86, vdso: Use asm volatile in __getcpu > x86, vdso, pvclock: Simplify and speed up the vdso pvclock reader Patch 1 is ok,

[RFC 0/2] x86, vdso, pvclock: Cleanups and speedups

2014-12-22 Thread Andy Lutomirski
This is a dramatic simplification and speedup of the vdso pvclock read code. Is it correct? Andy Lutomirski (2): x86, vdso: Use asm volatile in __getcpu x86, vdso, pvclock: Simplify and speed up the vdso pvclock reader arch/x86/include/asm/vgtod.h | 6 ++-- arch/x86/vdso/vclock_gettime.c