On Tue, Feb 19, 2019 at 01:54:38PM -0700, Jason Gunthorpe wrote:
> On Tue, Feb 19, 2019 at 08:57:45AM -0600, Shiraz Saleem wrote:
> > The drivers i40iw and bnxt_re no longer dependent on the
> > hugetlb flag. So remove this flag from ib_umem structure.
> >
> > Reviewed-by: Michael J. Ruhl <michael.j.ruhl@xxxxxxxxx>
> > Signed-off-by: Shiraz Saleem <shiraz.saleem@xxxxxxxxx>
> > drivers/infiniband/core/umem.c | 15 ---------------
> > drivers/infiniband/core/umem_odp.c | 3 ---
> > include/rdma/ib_umem.h | 1 -
> > 3 files changed, 19 deletions(-)
> >
> > diff --git a/drivers/infiniband/core/umem.c b/drivers/infiniband/core/umem.c
> > index 8c3ec1b..3e2a262 100644
> > +++ b/drivers/infiniband/core/umem.c
> > @@ -329,7 +329,6 @@ struct ib_umem *ib_umem_get(struct ib_udata *udata, unsigned long addr,
> > struct mm_struct *mm;
> > unsigned long npages;
> > int ret;
> > - int i;
> > unsigned long dma_attrs = 0;
> > struct scatterlist *sg;
> > unsigned int gup_flags = FOLL_WRITE;
> > @@ -378,9 +377,6 @@ struct ib_umem *ib_umem_get(struct ib_udata *udata, unsigned long addr,
> > return umem;
> > }
> >
> > - /* We assume the memory is from hugetlb until proved otherwise */
> > - umem->hugetlb = 1;
> > -
> > page_list = (struct page **) __get_free_page(GFP_KERNEL);
> > if (!page_list) {
> > ret = -ENOMEM;
> > @@ -392,8 +388,6 @@ struct ib_umem *ib_umem_get(struct ib_udata *udata, unsigned long addr,
> > * just assume the memory is not hugetlb memory
> > */
> > vma_list = (struct vm_area_struct **) __get_free_page(GFP_KERNEL);
> > - if (!vma_list)
> > - umem->hugetlb = 0;
> >
> > npages = ib_umem_num_pages(umem);
> > if (npages == 0 || npages > UINT_MAX) {
> > @@ -437,15 +431,6 @@ struct ib_umem *ib_umem_get(struct ib_udata *udata, unsigned long addr,
> > npages -= ret;
> >
> > sg = ib_umem_add_sg_table(sg, page_list, ret, &umem->sg_nents);
> > -
> > - /* Continue to hold the mmap_sem as vma_list access
> > - * needs to be protected.
> > - */
> > - for (i = 0; i < ret && umem->hugetlb; i++) {
> > - if (vma_list && !is_vm_hugetlb_page(vma_list[i]))
> > - umem->hugetlb = 0;
> > - }
>
> This is the only place that reads the vma_list, so please delete it as
> well.
>
Sure.
