Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
Date:   Thu, 13 Dec 2018 09:17:56 -0600
From:   Bjorn Helgaas <helgaas@kernel.org>
To:     Wesley Sheng <wesley.sheng@microchip.com>
Cc:     kurt.schwemmer@microsemi.com, logang@deltatee.com,
        linux-pci@vger.kernel.org, linux-kernel@vger.kernel.org,
        wesleyshenggit@sina.com
Subject: Re: [PATCH 5/5] switchtec: MRPC DMA mode implementation
Message-ID: <20181213151756.GD4701@google.com>
References: <1544433144-7563-1-git-send-email-wesley.sheng@microchip.com>
 <1544433144-7563-6-git-send-email-wesley.sheng@microchip.com>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <1544433144-7563-6-git-send-email-wesley.sheng@microchip.com>
User-Agent: Mutt/1.10.1 (2018-07-13)
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

On Mon, Dec 10, 2018 at 05:12:24PM +0800, Wesley Sheng wrote:
> MRPC normal mode requires the host to read the MRPC command status and
> output data from BAR. This results in high latency responses from the
> Memory Read TLP and potential Completion Timeout (CTO).
> 
> MRPC DMA mode implementation includes:
> Macro definitions for registers and data structures corresponding to
> MRPC DMA mode.
> 
> Add module parameter use_dma_mrpc to select between MRPC DMA mode and
> MRPC normal mode.
> 
> Add MRPC mode functionality to:
> * Retrieve MRPC DMA mode version
> * Allocate DMA buffer, ISR registration, and enable DMA function during
>   initialization
> * Check MRPC execution status and collect execution results from DMA buffer
> * Release DMA buffer and disable DMA function when unloading module
> 
> MRPC DMA mode is a new feature of firmware and the driver will fall back
> to MRPC normal mode if there is no support in the legacy firmware.
> 
> Include <linux/io-64-nonatomic-lo-hi.h> so that readq/writeq is replaced
> by two readl/writel on systems that do not support it.
> 
> Signed-off-by: Wesley Sheng <wesley.sheng@microchip.com>
> Reviewed-by: Logan Gunthorpe <logang@deltatee.com>

>  static void init_pff(struct switchtec_dev *stdev)
> @@ -1294,6 +1367,19 @@ static int switchtec_init_pci(struct switchtec_dev *stdev,
>  
>  	pci_set_drvdata(pdev, stdev);
>  
> +	if (!use_dma_mrpc)
> +		return 0;
> +
> +	if (!(ioread32(&stdev->mmio_mrpc->dma_ver) ? true : false))
> +		return 0;

This is ... harder to decode than necessary.  It's obvious that the
intent is to return if the adapter firmware doesn't support DMA, but I
lost interest before I could verify that it works as intended.

Bjorn