[RFC PATCH] mmc: meson-mx-sdhc: add DMA bounce buffer support
Martin Blumenstingl
martin.blumenstingl at googlemail.com
Sun Nov 1 14:52:04 PST 2026
Hi,
On Sun, Nov 1, 2026 at 9:55 AM HELPMEEADICE <yuanzhenpeng210 at gmail.com> wrote:
>
> Hi Martin,
>
> Thank you again for your feedback!
>
> I've completed the comparison between the original driver,
> MMC_CAP2_MERGE_CAPABLE, and the 128 KiB bounce buffer implementation
> on my Xunlei OneCloud (Amlogic S805).
>
> The results show that MMC_CAP2_MERGE_CAPABLE alone does not improve
> performance on this platform.
>
> Runtime instrumentation confirmed that:
>
> - dma_get_merge_boundary() returns 0.
> - host->can_dma_map_merge remains 0.
I see, so that will prevent it from doing anything.
> - The block queue's max_segments remains 1.
> - The merge-only variant behaves essentially the same as the original driver.
>
> Here are the sequential read results (MiB/s, mean of 5 runs):
>
> Baseline Merge-only Bounce
> 4 KiB 11.81 12.20 13.01
> 64 KiB 12.88 12.80 57.52
> 128 KiB 12.97 12.80 67.68
> 1 MiB 13.11 13.05 69.43
>
> The bounce buffer improves sequential read throughput by up to 5.3x
> and sequential write throughput by up to 2.1x.
Let's wait for Ulf's feedback in the next few days if it's something
that should go into MMC core (either by default or opt-in) or if we
should keep it driver specific.
Best regards,
Martin
More information about the linux-arm-kernel
mailing list