-----"Jason Gunthorpe" <jgg@xxxxxxxx> wrote: ----- >To: "Bernard Metzler" <BMT@xxxxxxxxxxxxxx> >From: "Jason Gunthorpe" <jgg@xxxxxxxx> >Date: 07/12/2019 07:45PM >Cc: "Arnd Bergmann" <arnd@xxxxxxxx>, "Doug Ledford" ><dledford@xxxxxxxxxx>, "Peter Zijlstra" <peterz@xxxxxxxxxxxxx>, >linux-rdma@xxxxxxxxxxxxxxx, linux-kernel@xxxxxxxxxxxxxxx >Subject: [EXTERNAL] Re: Re: Re: Re: Re: [PATCH] rdma/siw: avoid >smp_store_mb() on a u64 > >On Fri, Jul 12, 2019 at 05:40:43PM +0000, Bernard Metzler wrote: > >> It is because there are two levels a CQ can be armed: >> >> #include <infiniband/verbs.h> >> >> int ibv_req_notify_cq(struct ibv_cq *cq, int >solicited_only); >> >> If we kick the CQ handler, we have to clear the whole >> thing. The user later again decides how he wants to get it >> re-armed...SOLICITED completions only, or ALL signaled. > >Arrange it so only one of the two bits is ever set and do two >test-and-set bits when a SOLICITED CQE comes in? > right, but that's too easy ;) I'll probably do it along those lines. Many thanks, Bernard.
