Re: [RFC v4 3/3] xpfo: add support for hugepages

[Tycho Andersen <tycho@docker.com>]

Hi Laura,

Thanks for taking a look.

On Fri, Jun 09, 2017 at 05:23:06PM -0700, Laura Abbott wrote:
> > -	set_pte_atomic(pte, pfn_pte(page_to_pfn(page), canon_pgprot(prot)));
> > +
> > +	BUG_ON(!pte);
> > +
> > +	switch (level) {
> > +	case PG_LEVEL_4K:
> > +		set_pte_atomic(pte, pfn_pte(page_to_pfn(page), canon_pgprot(prot)));
> > +		break;
> > +	case PG_LEVEL_2M:
> > +	case PG_LEVEL_1G: {
> > +		struct cpa_data cpa;
> > +		int do_split;
> > +
> > +		memset(&cpa, 0, sizeof(cpa));
> > +		cpa.vaddr = kaddr;
> > +		cpa.pages = &page;
> > +		cpa.mask_set = prot;
> > +		pgprot_val(cpa.mask_clr) = ~pgprot_val(prot);
> > +		cpa.numpages = 1;
> > +		cpa.flags = 0;
> > +		cpa.curpage = 0;
> > +		cpa.force_split = 0;
> > +
> > +		do_split = try_preserve_large_page(pte, (unsigned long)kaddr, &cpa);
> > +		if (do_split < 0)
> 
> I can't reproduce the failure you describe in the cover letter but are you sure this
> check is correct?

The check seems to only happen when splitting up a large page,
indicating that...

> It looks like try_preserve_large_page can return 1 on failure
> and you still need to call split_large_page.

...yes, you're absolutely right. When I fix this, it now fails to
boot, stalling on unpacking the initramfs. So it seems something else
is wrong too.

Cheers,

Tycho

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>