On Fri, Dec 18, 2015 at 12:04:48PM +0530, Jerin Jacob wrote:
> > > # either we need to modify kernel
> > > - Make sure all the non-x86 arch to support mapping for
> > > iopci region (i.e. pci_mmap_page_range). I don;t think its a correct
> > > approach though.
> > > or
> > > - include /dev/ioport char-mem device file who could do
> > > more than byte operation, Note that this implementation does not exist
> > > in kernel. I could send an RFC to lkml.
> >
> > Maybe you could propose the two to lkml, to get some feedbacks from
> > those kernel/ARM gurus? Please cc me if you do so.
>
> IMO, We need to support DPDK-ARM for the old kernels also. If there is no
> means
> to expose iomap region to userspace in the existing kernel then we add that
> support through out-of-tree driver like igb_uio and when make become part of
> the kernel then we can turn off of the out-of-tree driver based
> on the kernel major and minor version numbers.
Agreed.
(BTW, I have no idea why the CC list of my last reply was shortened
to Santosh only. I double checked with my sent box, the mail header
sent out looks normal:
Date: Fri, 18 Dec 2015 13:30:53 +0800
From: Yuanhan Liu
<yuanhan.liu at linux.intel.com>
To: Santosh Shukla <sshukla at mvista.com>
Cc: Thomas Monjalon <thomas.monjalon at 6wind.com>, dev at dpdk.org, David
Marchand <david.marchand at 6wind.com>
Not sure it's a bug from my mutt email client, or the mailing list)
--yliu
