RE: [PATCH 36/41] IB/hfi1: add low level page locking

["Marciniszyn, Mike" <mike.marciniszyn@xxxxxxxxx>]

> > + * hfi1_get_user_pages - lock user pages into memory
> > + * @start_page: the start page
> > + * @num_pages: the number of pages
> > + * @p: the output page structures
> > + *
> > + * This function takes a given start page (page aligned user virtual
> > + * address) and pins it and the following specified number of pages.
> > +For
> > + * now, num_pages is always 1, but that will probably change at some
> > +point
> > + * (because caller is doing expected sends on a single virtually
> > +contiguous
> > + * buffer, so we can do all pages at once).
> > + */
> > +int hfi1_get_user_pages(unsigned long start_page, size_t num_pages,
> > +                       struct page **p) {
> > +       int ret;
> > +
> > +       down_write(&current->mm->mmap_sem);
> > +
> > +       ret = __hfi1_get_user_pages(start_page, num_pages, p);
> > +
> > +       up_write(&current->mm->mmap_sem);
> > +
> > +       return ret;
> > +}
> > +
> 
> anything wrong with the umem services provided by the IB core that
> requires this implementation? what?
> 

We are currently investigating this.

Mike
��.n��������+%������w��{.n�����{���fk��ܨ}���Ơz�j:+v�����w����ޙ��&�)ߡ�a����z�ޗ���ݢj��w�f