linux-kernel - Re: [PATCH V12 1/1] dmaengine: amd: qdma: Add AMD QDMA driver

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: <CAMuHMdXVoTx8K+Vppt07s06OE6R=4BxoBbgtp1WWkCi8DwqgSA@mail.gmail.com>
Date: Tue, 3 Sep 2024 11:20:52 +0200
From: Geert Uytterhoeven <geert@...ux-m68k.org>
To: Lizhi Hou <lizhi.hou@....com>, nishad.saraf@....com
Cc: vkoul@...nel.org, dmaengine@...r.kernel.org, linux-kernel@...r.kernel.org, 
	Nishad Saraf <nishads@....com>, sonal.santan@....com, max.zhen@....com
Subject: Re: [PATCH V12 1/1] dmaengine: amd: qdma: Add AMD QDMA driver

Hi Lizhi, Nishad,

On Thu, Apr 18, 2024 at 7:51 PM Lizhi Hou <lizhi.hou@....com> wrote:
> From: Nishad Saraf <nishads@....com>
>
> Adds driver to enable PCIe board which uses AMD QDMA (the Queue-based
> Direct Memory Access) subsystem. For example, Xilinx Alveo V70 AI
> Accelerator devices.
>     https://www.xilinx.com/applications/data-center/v70.html
>
> The QDMA subsystem is used in conjunction with the PCI Express IP block
> to provide high performance data transfer between host memory and the
> card's DMA subsystem.
>
>             +-------+       +-------+       +-----------+
>    PCIe     |       |       |       |       |           |
>    Tx/Rx    |       |       |       |  AXI  |           |
>  <=======>  | PCIE  | <===> | QDMA  | <====>| User Logic|
>             |       |       |       |       |           |
>             +-------+       +-------+       +-----------+
>
> The primary mechanism to transfer data using the QDMA is for the QDMA
> engine to operate on instructions (descriptors) provided by the host
> operating system. Using the descriptors, the QDMA can move data in both
> the Host to Card (H2C) direction, or the Card to Host (C2H) direction.
> The QDMA provides a per-queue basis option whether DMA traffic goes
> to an AXI4 memory map (MM) interface or to an AXI4-Stream interface.
>
> The hardware detail is provided by
>     https://docs.xilinx.com/r/en-US/pg302-qdma
>
> Implements dmaengine APIs to support MM DMA transfers.
> - probe the available DMA channels
> - use dma_slave_map for channel lookup
> - use virtual channel to manage dmaengine tx descriptors
> - implement device_prep_slave_sg callback to handle host scatter gather
>   list
>
> Signed-off-by: Nishad Saraf <nishads@....com>
> Signed-off-by: Lizhi Hou <lizhi.hou@....com>

Thanks for your patch, which is now commit 73d5fc92a11cacb7
("dmaengine: amd: qdma: Add AMD QDMA driver") in dmaengine/next.

> --- /dev/null
> +++ b/drivers/dma/amd/Kconfig
> @@ -0,0 +1,14 @@
> +# SPDX-License-Identifier: GPL-2.0-only
> +
> +config AMD_QDMA
> +       tristate "AMD Queue-based DMA"
> +       depends on HAS_IOMEM

Any other subsystem or platform dependencies, to prevent asking the
user about this driver when configuring a kernel for a system which
cannot possibly have this hardware?
E.g. depends on PCI, or can this be used with other transports than PCIe?

> --- /dev/null
> +++ b/drivers/dma/amd/qdma/qdma-comm-regs.c

> +static struct platform_driver amd_qdma_driver = {
> +       .driver         = {
> +               .name = "amd-qdma",

Which code is responsible for creating "amd-qdma" platform devices?

> +       },
> +       .probe          = amd_qdma_probe,
> +       .remove_new     = amd_qdma_remove,
> +};
> +
> +module_platform_driver(amd_qdma_driver);

Gr{oetje,eeting}s,

                        Geert

-- 
Geert Uytterhoeven -- There's lots of Linux beyond ia32 -- geert@...ux-m68k.org

In personal conversations with technical people, I call myself a hacker. But
when I'm talking to journalists I just say "programmer" or something like that.
                                -- Linus Torvalds