Re: [PATCH 1/2] net/mlx5: replace memory barrier type

On Thu, Aug 24, 2017 at 06:56:11AM +0000, Shahaf Shuler wrote:

Wednesday, August 23, 2017 4:12 PM, Bruce Richardson:

quoted

On Wed, Aug 23, 2017 at 01:39:08PM +0200, Nélio Laranjeiro wrote:

quoted

On Mon, Aug 21, 2017 at 10:47:01AM +0300, Sagi Grimberg wrote:

Acked-by: Nelio Laranjeiro <redacted>

While a compiler barrier may do on platforms with strong ordering, I'm
wondering if the rte_smp_wmb() macro may be needed here to give
compiler barrier or actual memory barrier depending on platform?

Thanks for the catch!

However, the description of rte_smp_wmb() not seems to fit our case here.
We don't try to sync between different lcores, rather between the device and a single lcore. 

Maybe rte_io_wmb fits better? 

Yep. Looks about right.

/Bruce