page fault in igb on 8.1

[Jack Vogel]

There is one case in igb_dma_malloc() where its still IGB_DBA_ALIGN, but the
cases where its allocating TX and RX bufs the alignment is 1, that code is
the
same in 8.1, or head as far as I can see.

Jack


On Thu, Jul 8, 2010 at 2:36 PM, Chris Buechler <cbuechler at gmail.com> wrote:

> On Thu, Jul 8, 2010 at 5:03 PM, Jack Vogel <jfvogel at gmail.com> wrote:
> > Am confused, does not the code in 8.1 have that fix, looked to me like it
> > did?
> >
>
> Maybe I'm confused, but it looks like RELENG_8_1 has the IGB_DBA_ALIGN
> rather than 1.
>
> -                IGB_DBA_ALIGN, 0,    /* alignment, bounds */
> +                1, 0,            /* alignment, bounds */
>
>
> http://svn.freebsd.org/viewvc/base/releng/8.1/sys/dev/e1000/if_igb.c?revision=209145&view=markup
>
> It was reverted back in this commit.
>
> http://svn.freebsd.org/viewvc/base/releng/8.1/sys/dev/e1000/if_igb.c?r1=205283&r2=206211
>
> Chris
>