Re: [PATCH v2 1/2] x86/numa: Introduce numa_fill_memblks()

[Peter Zijlstra]

On Wed, Jun 14, 2023 at 05:27:39AM -0700, Dan Williams wrote:
> Wilczynski, Michal wrote:
> > On 6/14/2023 6:35 AM, alison.schofield@xxxxxxxxx wrote:

> > > +static int __init cmp_memblk(const void *a, const void *b)
> > > +{
> > > +	const struct numa_memblk *ma = *(const struct numa_memblk **)a;
> > > +	const struct numa_memblk *mb = *(const struct numa_memblk **)b;
> > 
> > Is this casting necessary  ?
> 
> This is idiomatic for sort() comparison handlers.

Aside of that, it *is* actually required, since sort() does indirect
calls to it's cmp_func_t argument the Control Flow Integrity (CFI, not
to be confused with Call-Frame-Information) stuff has a hard requirement
that function signatures match.

At the very least clang builds should warn if you do indirect calls with
non-matching signatures these days. And kCFI enabled builds will get you
a runtime error if you manage to ignore that warning.

> > > +
> > > +	if (ma->start != mb->start)
> > > +		return (ma->start < mb->start) ? -1 : 1;
> > > +
> > > +	/* Caller handles duplicate start addresses */
> > > +	return 0;
> > > +}