[ofa-general] MTHCA driver from OFED 1.3a package

[Or Gerlitz]

On 11/26/07, Lukas Hejtmanek <xhejtman at ics.muni.cz> wrote:
> On Mon, Nov 26, 2007 at 01:22:39PM +0200, Or Gerlitz wrote:
> > Can you please clarify what is the patch in OFED 1.2 which once
> > deployed to OFED 1.3 makes it work for you?

> none of them. I did my personal patch

> struct mthca_icm *mthca_alloc_icm(struct mthca_dev *dev, int npages,
>                                   gfp_t gfp_mask, int coherent)
> {
>         struct mthca_icm *icm;
>         struct mthca_icm_chunk *chunk = NULL;
>         int cur_order;
>         int ret;
>
> +        coherent = 1;
>         /* We use sg_set_buf for coherent allocs, which assumes low memory */
> +        //BUG_ON(coherent && (gfp_mask & __GFP_HIGHMEM));

OK, I see. So what's needed in order to fix the problem for the
upstream code, it seems the code is ready to take the path of using
mthca_alloc_icm_coherent, and your patch just forces it to use this
practice, correct? Why its correct to remove this assertion?

Or.