linux-kernel - Re: [PATCH v1 2/2] dmaengine: dw-edma: Add non-LL mode

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] [day] [month] [year] [list]

Message-ID: <20250912153358.GA1625522@bhelgaas>
Date: Fri, 12 Sep 2025 10:33:58 -0500
From: Bjorn Helgaas <helgaas@...nel.org>
To: "Verma, Devendra" <Devendra.Verma@....com>
Cc: "bhelgaas@...gle.com" <bhelgaas@...gle.com>,
	"mani@...nel.org" <mani@...nel.org>,
	"vkoul@...nel.org" <vkoul@...nel.org>,
	"dmaengine@...r.kernel.org" <dmaengine@...r.kernel.org>,
	"linux-pci@...r.kernel.org" <linux-pci@...r.kernel.org>,
	"linux-kernel@...r.kernel.org" <linux-kernel@...r.kernel.org>,
	"Simek, Michal" <michal.simek@....com>
Subject: Re: [PATCH v1 2/2] dmaengine: dw-edma: Add non-LL mode

On Fri, Sep 12, 2025 at 09:35:56AM +0000, Verma, Devendra wrote:
> > -----Original Message-----
> > From: Bjorn Helgaas <helgaas@...nel.org>

[redundant headers removed]

> > On Thu, Sep 11, 2025 at 05:14:51PM +0530, Devendra K Verma wrote:
> > > AMD MDB IP supports Linked List (LL) mode as well as non-LL mode.
> > > The current code does not have the mechanisms to enable the DMA
> > > transactions using the non-LL mode. The following two cases are added
> > > with this patch:
> > > - When a valid physical base address is not configured via the
> > >   Xilinx VSEC capability then the IP can still be used in non-LL
> > >   mode. The default mode for all the DMA transactions and for all
> > >   the DMA channels then is non-LL mode.
> > > - When a valid physical base address is configured but the client
> > >   wants to use the non-LL mode for DMA transactions then also the
> > >   flexibility is provided via the peripheral_config struct member of
> > >   dma_slave_config. In this case the channels can be individually
> > >   configured in non-LL mode. This use case is desirable for single
> > >   DMA transfer of a chunk, this saves the effort of preparing the
> > >   Link List.
> >
> > > +static pci_bus_addr_t dw_edma_get_phys_addr(struct pci_dev *pdev,
> > > +                                         struct dw_edma_pcie_data *pdata,
> > > +                                         enum pci_barno bar) {
> > > +     if (pdev->vendor == PCI_VENDOR_ID_XILINX)
> > > +             return pdata->devmem_phys_off;
> > > +     return pci_bus_address(pdev, bar);
> >
> > Does this imply that non-Xilinx devices don't have the iATU that
> > translates a PCI bus address to an internal device address?
> 
> Non-Xilinx devices can have iATU enabled or bypassed as well. In
> bypass mode no translation is done and the TLPs are simply forwarded
> untranslated.

What happens on a non-Xilinx device with iATU enabled?  Does
pci_bus_address() return the correct address in that case?

I can't figure out what's different about Xilinx that requires this
special handling.