On Tue, Mar 14, 2017 at 10:06:48PM +0800, Ding Tianhong wrote:

On 2017/3/13 21:31, Robin Murphy wrote:

quoted

On 13/03/17 12:03, Ding Tianhong wrote:

quoted

diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 8c7c244..36249a3 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig

@@ -115,6 +115,7 @@ config ARM64
 	select SPARSE_IRQ
 	select SYSCTL_EXCEPTION_TRACE
 	select THREAD_INFO_IN_TASK
+	select ARCH_WANT_RELAX_ORDER

I'd say the first order of business is to rename this config option to
IXBGE_82599_WANT_RELAXED_ORDER so that it's not entirely misleading and

not only for 82599, including 82598, 82576....

quoted

ambiguous. At first glance it looks far more like something scary to do
with memory barriers than a network driver option. Howcome this isn't
just in drivers/net/intel/Kconfig as a "default y if SPARC" bool anyway?

didn't see any essential differences, and I still need to get some Acked by arm maintainer.

quoted

Yes, more memory barriers always affect the performance especially for
some architecture not just like sparc, any optimization should be taken seriously
especially for aarch64.

If this is a legitimate optimisation to apply (which nobody seems to be sure
about), then I'd *much* rather it was handled entirely in the driver and
predicated on CONFIG_ARM64. I can't select ARCH_WANT_RELAX_ORDER without
some notion of what on Earth that means, and whether or not other drivers
can also use that to infer some property about the arm64 ordering model.

Will