linux-kernel - Re: [PATCH 2/4] spi: spi-fsl-dspi: Use non-coherent memory for DMA

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <5b21c4c9-0ef7-41e5-a3bb-5a48a0c73644@linaro.org>
Date: Thu, 12 Jun 2025 15:28:37 +0100
From: James Clark <james.clark@...aro.org>
To: Vladimir Oltean <vladimir.oltean@....com>
Cc: Arnd Bergmann <arnd@...db.de>, Frank Li <Frank.li@....com>,
 Vladimir Oltean <olteanv@...il.com>, Mark Brown <broonie@...nel.org>,
 linux-spi@...r.kernel.org, imx@...ts.linux.dev, linux-kernel@...r.kernel.org
Subject: Re: [PATCH 2/4] spi: spi-fsl-dspi: Use non-coherent memory for DMA



On 12/06/2025 3:23 pm, Vladimir Oltean wrote:
> On Thu, Jun 12, 2025 at 03:14:32PM +0100, James Clark wrote:
>>> That's why I don't like the DMA mode in DSPI, it's still CPU-bound,
>>> because the DMA buffers are very small (you can only provide one TX FIFO
>>> worth of data per DMA transfer, rather than the whole buffer).
>>
>> Is that right? The FIFO size isn't used in any of the DMA codepaths, it
>> looks like the whole DMA buffer is filled before initiating the transfer.
>> And we increase the buffer to 4k in this patchset to fully use the existing
>> allocation.
> 
> Uhm, yeah, no?
> 
> dspi_dma_xfer():
> 
> 	while (dspi->len) {
> 		dspi->words_in_flight = dspi->len / dspi->oper_word_size;
> 		if (dspi->words_in_flight > dspi->devtype_data->fifo_size)
> 			dspi->words_in_flight = dspi->devtype_data->fifo_size;
> 		dspi_next_xfer_dma_submit();
> 	}

Right but that's before the change in this patchset to use the whole 
page that was allocated, hence the next bit:

 > And we increase the buffer to 4k in this patchset to fully use the
   existing allocation.

We were allocating for the size of the FIFO (multiplied by two to hold 
the control words), but dma_alloc_coherent() will be backed by a whole 
page anyway, even if you only ask for a few bytes.

After changing that to make use of the full allocation the FIFO length 
is no longer involved.