linux-kernel - RE: [PATCH] PCI: xilinx-nwl: Enable coherenct PCIe traffic using CCI

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]

Date:   Wed, 27 Jan 2021 05:03:12 +0000
From:   Bharat Kumar Gogada <bharatku@...inx.com>
To:     Bjorn Helgaas <helgaas@...nel.org>
CC:     "linux-pci@...r.kernel.org" <linux-pci@...r.kernel.org>,
        "linux-kernel@...r.kernel.org" <linux-kernel@...r.kernel.org>,
        "bhelgaas@...gle.com" <bhelgaas@...gle.com>,
        Rob Herring <robh@...nel.org>
Subject: RE: [PATCH] PCI: xilinx-nwl: Enable coherenct PCIe traffic using CCI

> [+cc Rob]
> 
> s/coherenct/coherent/ in subject
> s/traffic/DMA/ (this applies specifically to DMA, not to MMIO)
> 
> On Thu, Jan 21, 2021 at 03:29:16PM +0530, Bharat Kumar Gogada wrote:
> > - Add support for routing PCIe traffic coherently when  Cache Coherent
> > Interconnect(CCI) is enabled in the system.
> 
> s/- Add/Add/
> s/Interconnect(CCI)/Interconnect (CCI)/
> 
Thanks Bjorn for corrections.
Here is the CCI spec 
https://developer.arm.com/documentation/ddi0470/k/preface

> Can you include a URL to a CCI spec?  I'm not familiar with it.  I guess this is
> something upstream from the host bridge, i.e., between the CPU and the
> host bridge, so it's outside the PCI domain?
> 
> I'd like to mention the DT "dma-coherent" property in the commit log to
> help connect this with the knob that controls it.
Yes will add it. 
> 
> The "dma-coherent" property is mentioned several places in
> Documentation/devicetree/bindings/pci/ (but not anything obviously related
> to xilinx-nwl).  Should it be moved to something like
> Documentation/devicetree/bindings/pci/pci.txt to make it more generic?
> 
I will update this property in documentation as optional property.
Rob can confirm if this can be moved to generic. 
> > Signed-off-by: Bharat Kumar Gogada <bharat.kumar.gogada@...inx.com>
> > ---
> >  drivers/pci/controller/pcie-xilinx-nwl.c | 8 ++++++++
> >  1 file changed, 8 insertions(+)
> >
> > diff --git a/drivers/pci/controller/pcie-xilinx-nwl.c
> > b/drivers/pci/controller/pcie-xilinx-nwl.c
> > index 07e3666..08e06057 100644
> > --- a/drivers/pci/controller/pcie-xilinx-nwl.c
> > +++ b/drivers/pci/controller/pcie-xilinx-nwl.c
> > @@ -26,6 +26,7 @@
> >
> >  /* Bridge core config registers */
> >  #define BRCFG_PCIE_RX0			0x00000000
> > +#define BRCFG_PCIE_RX1			0x00000004
> >  #define BRCFG_INTERRUPT			0x00000010
> >  #define BRCFG_PCIE_RX_MSG_FILTER	0x00000020
> >
> > @@ -128,6 +129,7 @@
> >  #define NWL_ECAM_VALUE_DEFAULT		12
> >
> >  #define CFG_DMA_REG_BAR			GENMASK(2, 0)
> > +#define CFG_PCIE_CACHE			GENMASK(7, 0)
> >
> >  #define INT_PCI_MSI_NR			(2 * 32)
> >
> > @@ -675,6 +677,12 @@ static int nwl_pcie_bridge_init(struct nwl_pcie
> *pcie)
> >  	nwl_bridge_writel(pcie, CFG_ENABLE_MSG_FILTER_MASK,
> >  			  BRCFG_PCIE_RX_MSG_FILTER);
> >
> > +	/* This routes the PCIe DMA traffic to go through CCI path */
> > +	if (of_dma_is_coherent(dev->of_node)) {
> > +		nwl_bridge_writel(pcie, nwl_bridge_readl(pcie,
> BRCFG_PCIE_RX1) |
> > +				  CFG_PCIE_CACHE, BRCFG_PCIE_RX1);
> > +	}
> > +
> >  	err = nwl_wait_for_link(pcie);
> >  	if (err)
> >  		return err;
> > --
> > 2.7.4
> >