From mboxrd@z Thu Jan 1 00:00:00 1970 From: Jakub Kicinski Subject: Re: [RFC PATCH 3/3] net: ethernet: ti: cpsw: add XDP support Date: Thu, 18 Apr 2019 10:41:11 -0700 Message-ID: <20190418104111.559a0e74@cakuba.netronome.com> References: <20190417174942.11811-1-ivan.khoronzhuk@linaro.org> <20190417174942.11811-4-ivan.khoronzhuk@linaro.org> <20190418094008.GB27879@khorivan> Mime-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Return-path: In-Reply-To: <20190418094008.GB27879@khorivan> Sender: linux-kernel-owner@vger.kernel.org To: Ivan Khoronzhuk Cc: grygorii.strashko@ti.com, linux-omap@vger.kernel.org, LKML , Linux Netdev List , ilias.apalodimas@linaro.org, hawk@kernel.org, xdp-newbies@vger.kernel.org, Alexei Starovoitov , aniel@iogearbox.net, John Fastabend List-Id: linux-omap@vger.kernel.org On Thu, 18 Apr 2019 12:40:10 +0300, Ivan Khoronzhuk wrote: > >work? The stack's TX ring has a lock, and can be used from any CPU, > >while XDP TX rings are per-PCU, no? > Yes and no. > am572 has more queues then CPU num, How I can choose tx queue not based on CPU > num? It's always shared and has to have lock, and cpdma is done in this way. Oh, I see, you already have another lock. > Here another thing bothering me, I send it to queue 0 always, instead of > taking cpu num. Not sure about this, but I expect to have some tx queue > not bind to cpu and didn't find a way it can be changed dynamically in > redirect. Not sure I understand :)