From mboxrd@z Thu Jan 1 00:00:00 1970 From: okaya@codeaurora.org (okaya at codeaurora.org) Date: Wed, 14 Mar 2018 08:06:32 -0400 Subject: [PATCH 3/7] RDMA/qedr: eliminate duplicate barriers on weakly-ordered archs In-Reply-To: <20180314041249.GA18314@ziepe.ca> References: <1520997629-17361-1-git-send-email-okaya@codeaurora.org> <1520997629-17361-3-git-send-email-okaya@codeaurora.org> <20180314041249.GA18314@ziepe.ca> Message-ID: To: linux-arm-kernel@lists.infradead.org List-Id: linux-arm-kernel.lists.infradead.org On 2018-03-14 00:12, Jason Gunthorpe wrote: > On Tue, Mar 13, 2018 at 11:20:24PM -0400, Sinan Kaya wrote: >> Code includes wmb() followed by writel() in multiple places. writel() >> already has a barrier on some architectures like arm64. >> >> This ends up CPU observing two barriers back to back before executing >> the >> register write. >> >> Since code already has an explicit barrier call, changing writel() to >> writel_relaxed(). >> >> Signed-off-by: Sinan Kaya >> drivers/infiniband/hw/qedr/verbs.c | 4 ++-- >> 1 file changed, 2 insertions(+), 2 deletions(-) > > Sure matches my understanding of writel_relaxed > > This is part of a series, should we take just this patch through the > rdma tree? If not: > > Acked-by: Jason Gunthorpe Feel free to take pieces. > > Thanks, > Jason