> +
> +static int do_set_pmd(struct fault_env *fe, struct page *page)
> +{
> + struct vm_area_struct *vma = fe->vma;
> + bool write = fe->flags & FAULT_FLAG_WRITE;
> + unsigned long haddr = fe->address & HPAGE_PMD_MASK;
> + pmd_t entry;
> + int i, ret;
> +
> + if (!transhuge_vma_suitable(vma, haddr))
> + return VM_FAULT_FALLBACK;
> +
> + ret = VM_FAULT_FALLBACK;
> + page = compound_head(page);
> +
> + fe->ptl = pmd_lock(vma->vm_mm, fe->pmd);
> + if (unlikely(!pmd_none(*fe->pmd)))
> + goto out;
Can we reply to the caller that fault is handled correctly(by
resetting ret to zero before jump)?
> +
> + for (i = 0; i < HPAGE_PMD_NR; i++)
> + flush_icache_page(vma, page + i);
> +
> + entry = mk_huge_pmd(page, vma->vm_page_prot);
> + if (write)
> + entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma);
> +
> + add_mm_counter(vma->vm_mm, MM_FILEPAGES, HPAGE_PMD_NR);
> + page_add_file_rmap(page, true);
> +
> + set_pmd_at(vma->vm_mm, haddr, fe->pmd, entry);
> +
> + update_mmu_cache_pmd(vma, haddr, fe->pmd);
> +
> + /* fault is handled */
> + ret = 0;
> +out:
> + spin_unlock(fe->ptl);
> + return ret;
> +}
> +#else
> +static int do_set_pmd(struct fault_env *fe, struct page *page)
> +{
> + BUILD_BUG();
> + return 0;
> +}
> +#endif
> +
> /**
> * alloc_set_pte - setup new PTE entry for given page and add reverse page
> * mapping. If needed, the fucntion allocates page table or use
> pre-allocated.
> @@ -2940,9 +3000,19 @@ int alloc_set_pte(struct fault_env *fe, struct
> mem_cgroup *memcg,
> struct vm_area_struct *vma = fe->vma;
> bool write = fe->flags & FAULT_FLAG_WRITE;
> pte_t entry;
> + int ret;
> +
> + if (pmd_none(*fe->pmd) && PageTransCompound(page)) {
> + /* THP on COW? */
> + VM_BUG_ON_PAGE(memcg, page);
> +
> + ret = do_set_pmd(fe, page);
> + if (ret != VM_FAULT_FALLBACK)
> + return ret;
> + }
>
> if (!fe->pte) {
> - int ret = pte_alloc_one_map(fe);
> + ret = pte_alloc_one_map(fe);
> if (ret)
> return ret;
> }
> diff --git a/mm/migrate.c b/mm/migrate.c
