Re: [PATCH 1/2] perf: Introduce new perf_save_regs() for hot regs snapshot

[Frederic Weisbecker <fweisbec@gmail.com>]

On Fri, Mar 05, 2010 at 12:08:19PM -0500, Masami Hiramatsu wrote:
> Frederic Weisbecker wrote:
> > On Fri, Mar 05, 2010 at 10:08:07AM -0500, Masami Hiramatsu wrote:
> >>> +void perf_arch_save_regs(struct pt_regs *regs, unsigned long ip, int skip)
> >>
> >> Hmm, why would you call it 'save_regs' ?
> >> It seems that this function is just for fixing registers 
> >> instead of saving it into somewhere...
> >>
> >> Thank you,
> > 
> > 
> > Hmm, save_regs() describes what it does: you pass
> > a pt_regs and it saves registers inside. But it
> > has also a kind of fixup thing as it also rewinds.
> 
> Ah, I see. so this saves current register values
> into pt_regs. :)
> 
> > 
> > I'm not sure using a fixup thing for the naming
> > is correct as we are not starting with initial
> > regs passed to the function (just a raw buffer).
> > 
> > What about perf_save_caller_regs() ?
> > 
> 
> Hmm, I think, it might be better perf_get_caller_regs()
> or something like that (fetch ?). 


perf_fetch_caller_regs() looks fine. I'll update my
patch accordingly, thanks.