From mboxrd@z Thu Jan  1 00:00:00 1970
From: David Miller <davem@davemloft.net>
Subject: Re: [PATCH 1/3] net: macb: fix random memory corruption on RX with
 64-bit DMA
Date: Wed, 05 Dec 2018 12:32:45 -0800 (PST)
Message-ID: <20181205.123245.1075111432564395434.davem@davemloft.net>
References: <20181130182137.27974-1-anssi.hannula@bitwise.fi>
        <20181130182137.27974-2-anssi.hannula@bitwise.fi>
Mime-Version: 1.0
Content-Type: Text/Plain; charset=us-ascii
Content-Transfer-Encoding: 7bit
Cc: nicolas.ferre@microchip.com, netdev@vger.kernel.org,
        harini.katakam@xilinx.com, michal.simek@xilinx.com
To: anssi.hannula@bitwise.fi
Return-path: <netdev-owner@vger.kernel.org>
Received: from shards.monkeyblade.net ([23.128.96.9]:44244 "EHLO
        shards.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org
        with ESMTP id S1727402AbeLEUeL (ORCPT
        <rfc822;netdev@vger.kernel.org>); Wed, 5 Dec 2018 15:34:11 -0500
In-Reply-To: <20181130182137.27974-2-anssi.hannula@bitwise.fi>
Sender: netdev-owner@vger.kernel.org
List-ID: <netdev.vger.kernel.org>

From: Anssi Hannula <anssi.hannula@bitwise.fi>
Date: Fri, 30 Nov 2018 20:21:35 +0200

> @@ -682,6 +682,11 @@ static void macb_set_addr(struct macb *bp, struct macb_dma_desc *desc, dma_addr_
>  	if (bp->hw_dma_cap & HW_DMA_CAP_64B) {
>  		desc_64 = macb_64b_desc(bp, desc);
>  		desc_64->addrh = upper_32_bits(addr);
> +		/* The low bits of RX address contain the RX_USED bit, clearing
> +		 * of which allows packet RX. Make sure the high bits are also
> +		 * visible to HW at that point.
> +		 */
> +		dma_wmb();
>  	}

I agree with that dma_wmb() is what should be used here.

We are ordering CPU stores with DMA visibility, which is exactly what
the dma_*() are for.

If it doesn't work properly on some architecture's implementation of dma_*(),
those should be fixed rather than papering over it in the drivers.