On 8/8/19 11:55 AM, Bharath Vedartham wrote:
...
> static int gru_vtop(struct gru_thread_state *gts, unsigned long vaddr,
> int write, int atomic, unsigned long *gpa, int *pageshift)
> {
> struct mm_struct *mm = gts->ts_mm;
> struct vm_area_struct *vma;
> unsigned long paddr;
> - int ret, ps;
> + int ret;
> + struct page *page;
>
> vma = find_vma(mm, vaddr);
> if (!vma)
> @@ -263,21 +187,33 @@ static int gru_vtop(struct gru_thread_state *gts, unsigned long vaddr,
>
> /*
> * Atomic lookup is faster & usually works even if called in non-atomic
> - * context.
> + * context. get_user_pages_fast does atomic lookup before falling back to
> + * slow gup.
> */
> rmb(); /* Must/check ms_range_active before loading PTEs */
> - ret = atomic_pte_lookup(vma, vaddr, write, &paddr, &ps);
> - if (ret) {
> - if (atomic)
> + if (atomic) {
> + ret = __get_user_pages_fast(vaddr, 1, write, &page);
> + if (!ret)
> goto upm;
> - if (non_atomic_pte_lookup(vma, vaddr, write, &paddr, &ps))
> + } else {
> + ret = get_user_pages_fast(vaddr, 1, write ? FOLL_WRITE : 0, &page);
> + if (!ret)
> goto inval;
> }
> +
> + paddr = page_to_phys(page);
> + put_user_page(page);
> +
> + if (unlikely(is_vm_hugetlb_page(vma)))
> + *pageshift = HPAGE_SHIFT;
> + else
> + *pageshift = PAGE_SHIFT;
> +
> if (is_gru_paddr(paddr))
> goto inval;
> - paddr = paddr & ~((1UL << ps) - 1);
> + paddr = paddr & ~((1UL << *pageshift) - 1);
> *gpa = uv_soc_phys_ram_to_gpa(paddr);
> - *pageshift = ps;
Why are you no longer setting *pageshift? There are a couple of callers
that both use this variable.
thanks,
--
John Hubbard
NVIDIA
