Re: [PATCH v4 6/6] RDMA/qedr: eliminate duplicate barriers on weakly-ordered archs #2

2018-03-20 Thread Jason Gunthorpe
On Mon, Mar 19, 2018 at 10:47:48PM -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

Re: [PATCH v4 6/6] RDMA/qedr: eliminate duplicate barriers on weakly-ordered archs #2

2018-03-20 Thread Jason Gunthorpe
On Mon, Mar 19, 2018 at 10:47:48PM -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

RE: [PATCH v4 6/6] RDMA/qedr: eliminate duplicate barriers on weakly-ordered archs #2

2018-03-20 Thread Kalderon, Michal
> From: Sinan Kaya [mailto:ok...@codeaurora.org] > Sent: Tuesday, March 20, 2018 4:48 AM > > 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

RE: [PATCH v4 6/6] RDMA/qedr: eliminate duplicate barriers on weakly-ordered archs #2

2018-03-20 Thread Kalderon, Michal
> From: Sinan Kaya [mailto:ok...@codeaurora.org] > Sent: Tuesday, March 20, 2018 4:48 AM > > 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