[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-Id: <20180207.215735.1518454397358783732.davem@davemloft.net>
Date: Wed, 07 Feb 2018 21:57:35 -0500 (EST)
From: David Miller <davem@...emloft.net>
To: grygorii.strashko@...com
Cc: netdev@...r.kernel.org, nsekhar@...com,
linux-kernel@...r.kernel.org, linux-omap@...r.kernel.org
Subject: Re: [PATCH] net: ethernet: ti: cpsw: fix net watchdog timeout
From: Grygorii Strashko <grygorii.strashko@...com>
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 <grygorii.strashko@...com>
Applied, thanks.
Powered by blists - more mailing lists