From mboxrd@z Thu Jan 1 00:00:00 1970 From: Jason Gunthorpe Subject: Re: [PATCH 1/2] IB/mad: Agent registration is process context only Date: Tue, 12 Jun 2018 14:38:28 -0600 Message-ID: <20180612203828.GH6314@ziepe.ca> References: <20180608174218.32455-1-willy@infradead.org> <20180608174218.32455-2-willy@infradead.org> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Return-path: Content-Disposition: inline In-Reply-To: <20180608174218.32455-2-willy@infradead.org> Sender: linux-kernel-owner@vger.kernel.org To: Matthew Wilcox Cc: hans.westgaard.ry@oracle.com, Doug Ledford , Matthew Wilcox , linux-rdma@vger.kernel.org, =?utf-8?B?SMOla29u?= Bugge , Parav Pandit , Jack Morgenstein , Pravin Shedge , linux-kernel@vger.kernel.org List-Id: linux-rdma@vger.kernel.org On Fri, Jun 08, 2018 at 10:42:17AM -0700, Matthew Wilcox wrote: > From: Matthew Wilcox > > Document this (it's implicitly true due to sleeping operations already > in use in both registration and deregistration). Use this fact to use > spin_lock_irq instead of spin_lock_irqsave. This improves performance > slightly. > > Signed-off-by: Matthew Wilcox > --- > drivers/infiniband/core/mad.c | 16 +++++++++------- > 1 file changed, 9 insertions(+), 7 deletions(-) In the mean time, this patch is straightfoward, applied to the interm for-next.. Jason