From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752229AbeBHQEf (ORCPT ); Thu, 8 Feb 2018 11:04:35 -0500 Received: from fllnx209.ext.ti.com ([198.47.19.16]:22463 "EHLO fllnx209.ext.ti.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1750929AbeBHQEd (ORCPT ); Thu, 8 Feb 2018 11:04:33 -0500 Subject: Re: [PATCH] net: ethernet: ti: cpsw: fix net watchdog timeout To: David Miller CC: , , , References: <20180207011706.13393-1-grygorii.strashko@ti.com> <20180207.215735.1518454397358783732.davem@davemloft.net> From: Grygorii Strashko Message-ID: Date: Thu, 8 Feb 2018 10:04:31 -0600 User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:52.0) Gecko/20100101 Thunderbird/52.6.0 MIME-Version: 1.0 In-Reply-To: <20180207.215735.1518454397358783732.davem@davemloft.net> Content-Type: text/plain; charset="utf-8"; format=flowed Content-Language: en-US Content-Transfer-Encoding: 7bit X-Originating-IP: [128.247.59.147] Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On 02/07/2018 08:57 PM, David Miller wrote: > From: Grygorii Strashko > Date: Tue, 6 Feb 2018 19:17:06 -0600 > >> It was discovered that simple program which indefinitely sends 200b UDP >> packets and runs on TI AM574x SoC (SMP) under RT Kernel triggers network >> watchdog timeout in TI CPSW driver (<6 hours run). The network watchdog >> timeout is triggered due to race between cpsw_ndo_start_xmit() and >> cpsw_tx_handler() [NAPI] >> >> cpsw_ndo_start_xmit() >> if (unlikely(!cpdma_check_free_tx_desc(txch))) { >> txq = netdev_get_tx_queue(ndev, q_idx); >> netif_tx_stop_queue(txq); >> >> ^^ as per [1] barier has to be used after set_bit() otherwise new value >> might not be visible to other cpus >> } >> >> cpsw_tx_handler() >> if (unlikely(netif_tx_queue_stopped(txq))) >> netif_tx_wake_queue(txq); >> >> and when it happens ndev TX queue became disabled forever while driver's HW >> TX queue is empty. >> >> Fix this, by adding smp_mb__after_atomic() after netif_tx_stop_queue() >> calls and double check for free TX descriptors after stopping ndev TX queue >> - if there are free TX descriptors wake up ndev TX queue. >> >> [1] https://www.kernel.org/doc/html/latest/core-api/atomic_ops.html >> Signed-off-by: Grygorii Strashko > > Applied, thanks. > Thank you David. Could this be marked as stable material 4.9+? -- regards, -grygorii