On Wed, Feb 01, 2023 at 05:38:39PM +0000, Matthew Wilcox wrote:
> On Wed, Feb 01, 2023 at 04:17:36PM +0800, Yin Fengwei wrote:
> > do_set_pte_range() allows to setup page table entries for a
> > specific range. It calls page_add_file_rmap_range() to take
> > advantage of batched rmap update for large folio.
>
> How about something more like this? Yes, we need to define
> flush_icache_pages() and PTE_STRIDE.
Never mind about PTE_STRIDE. I forgot that pte_t isn't an integer
type. Instead, we'll want each architecture to define
/* This should be right for x86 */
static inline pte_next(pte_t pte)
{
return __pte(pte_val(pte) + PAGE_SIZE);
}
> + for (i = 0; i < nr; i++) {
> + set_pte_at(vma->vm_mm, addr, vmf->pte + i, entry);
> + /* no need to invalidate: a not-present page won't be cached */
> + update_mmu_cache(vma, addr, vmf->pte + i);
> + addr += PAGE_SIZE;
> + entry += PTE_STRIDE;
entry = pte_next(entry);
