From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Date: Mon, 22 Apr 2019 09:40:22 +0300 From: "Leonidas P. Papadakos" Subject: Re: [PATCH] arm64: dts: rockchip: set TX PBL for rk3328-roc-cc gmac Message-Id: <1555915222.1262.0@gmail.com> In-Reply-To: <8865b046-fb3a-4071-335c-66abb344d7f4@gmail.com> References: <20190417210059.26262-1-papadakospan@gmail.com> <8865b046-fb3a-4071-335c-66abb344d7f4@gmail.com> MIME-Version: 1.0 Content-Type: multipart/alternative; boundary="=-AxW4ihTRDv//G8uHH2zd" To: Peter Geis Cc: Rob Herring , Heiko Stuebner , Jose Abreu , Robin Murphy , devicetree@vger.kernel.org, linux-arm-kernel@lists.infradead.org, linux-rockchip@lists.infradead.org List-ID: --=-AxW4ihTRDv//G8uHH2zd Content-Type: text/plain; charset=UTF-8; format=flowed Content-Transfer-Encoding: quoted-printable =CE=A3=CF=84=CE=B9=CF=82 =CE=9A=CF=85=CF=81, 21 =CE=91=CF=80=CF=81, 2019 at= 7:00 =CE=9C=CE=9C, =CE=BF/=CE=B7 Peter Geis=20 =CE=AD=CE=B3=CF=81=CE=B1=CF=88=CE=B5: > Thanks for sharing that thread, it's nice to finally have an answer=20 > to why we have these issues. > I've tested this on *my* Firefly rk3328-roc-cc, and while this patch=20 > succeeds in preventing the tx lockup, iperf3 drops to a delightful=20 > 15mbps. >=20 > It would seem we have significant differences between manufacturing=20 > runs of the various boards. > The auto adjustment feature that was discussed in that thread is=20 > probably the only thing that will solve this for all boards. > Until then I don't think we are going to get a solution that works=20 > for all. Indeed that feature would be optimal. Just to confirm, you have=20 replaced force_thresh_dma_mode with this txpbl thing, right? That is the only ethernet modification I have in the dts, done though=20 u-boot. That is on linux 5.1 > fdt rm /ethernet@ff540000 snps,force_thresh_dma_mode > fdt set /ethernet@ff540000 snps,txpbl <0x4> = --=-AxW4ihTRDv//G8uHH2zd Content-Type: text/html; charset=UTF-8 Content-Transfer-Encoding: quoted-printable


=CE=A3=CF=84=CE=B9=CF=82 =CE=9A=CF=85=CF=81, 21 =CE= =91=CF=80=CF=81, 2019 at 7:00 =CE=9C=CE=9C, =CE=BF/=CE=B7 Peter Geis <pg= wipeout@gmail.com> =CE=AD=CE=B3=CF=81=CE=B1=CF=88=CE=B5:
Tha= nks for sharing that thread, it's nice to finally have an answer to why we = have these issues. I've tested this on *my* Firefly rk3328-roc-cc, and while this patch succee= ds in preventing the tx lockup, iperf3 drops to a delightful 15mbps. It would seem we have significant differences between manufacturing runs of= the various boards. The auto adjustment feature that was discussed in that thread is probably t= he only thing that will solve this for all boards. Until then I don't think we are going to get a solution that works for all.=

<= span style=3D"white-space: pre-wrap;">Indeed that feature would be optimal.= Just to confirm, you have replaced force_thresh_dma_mode with this txpbl t= hing, right?
That i= s the only ethernet modification I have in the dts, done though u-boot. Tha= t is on linux 5.1
<= br>
fdt rm /ethernet@ff540000 snps,force_thresh_dma_mode
fdt set /ethernet@ff540000 snps,txpbl <0x4>
= --=-AxW4ihTRDv//G8uHH2zd--