From mboxrd@z Thu Jan 1 00:00:00 1970 From: "Leonidas P. Papadakos" Subject: Re: [PATCH] arm64: dts: rockchip: improve rk3328-roc-cc rgmii performance. Date: Sat, 15 Jun 2019 00:27:11 +0300 Message-ID: <1560547631.1367.4@gmail.com> References: <20190607123731.8737-1-pgwipeout@gmail.com> <1559912295.22520.0@gmail.com> Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii"; Format="flowed" Content-Transfer-Encoding: 7bit Return-path: In-Reply-To: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Sender: "linux-arm-kernel" Errors-To: linux-arm-kernel-bounces+linux-arm-kernel=m.gmane.org@lists.infradead.org To: Peter Geis Cc: Jose Abreu , devicetree@vger.kernel.org, Heiko Stuebner , linux-rockchip@lists.infradead.org, Rob Herring , Robin Murphy , linux-arm-kernel@lists.infradead.org List-Id: devicetree@vger.kernel.org > The big change was actually snps,aal. > As per the TRM, DMA channels not address aligned have severe > limitations, if they work at all. > > Setting the DMA ops as address aligned fixed my 30mbps TX issue when > combined with your snps,txpbl = <0x4>. Honestly, I don't notice any difference either way with aal. So what happens without it? If You only use the 0x4 txpbl and having removed thresh dma mode, (2 things then) do you get bad tx?