From mboxrd@z Thu Jan 1 00:00:00 1970 From: Veaceslav Falico Subject: [PATCH 0/3] pch_gbe: fix CRC errors and improve speed Date: Mon, 22 Oct 2012 16:43:22 +0200 Message-ID: <1350917005-26350-1-git-send-email-vfalico@redhat.com> Cc: davem@davemloft.net, richardcochran@gmail.com, tshimizu818@gmail.com, andy.cress@us.kontron.com, erwan.velu@zodiacaerospace.com, agospoda@redhat.com To: netdev@vger.kernel.org Return-path: Received: from mx1.redhat.com ([209.132.183.28]:17817 "EHLO mx1.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1754116Ab2JVOng (ORCPT ); Mon, 22 Oct 2012 10:43:36 -0400 Sender: netdev-owner@vger.kernel.org List-ID: This patch series tries to get rid of CRC errors and other instability caused by wrong RX_FIFO overrun processing. It also cleans the code a bit. Now (without the patch applied) on high number of incoming packets and/or stressed system pch_gbe driver reports CRC errors and huge numbers of RX_FIFO_ERR (overruns). It also sometimes just freezes (caused by not waiting enough on DMA_RX to stop before issuing a reset on MAC_RX logic). This patchset removes the unneeded (as per datasheet) MAC_RX reset and corrects the processing of RX_FIFO_ERR in pch_gbe_napi_poll(). With the patchset applied there are no more CRC errors, sane number of RX_FIFO_ERR and improved speed/stability. The patchset was tested on Informix SYS940X and Kontron Tunnel Creek EG20T on 1gbps direct-connected link and different rx/tx descriptors count. .../net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c | 99 +++++-------------- 1 files changed, 26 insertions(+), 73 deletions(-)