Linux PCI subsystem development
 help / color / mirror / Atom feed
From: Vidya Sagar <vidyas@nvidia.com>
To: Shawn Guo <shawn.guo@linaro.org>, <linux-pci@vger.kernel.org>
Cc: Jingoo Han <jingoohan1@gmail.com>,
	Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>,
	Bjorn Helgaas <bhelgaas@google.com>,
	Gustavo Pimentel <gustavo.pimentel@synopsys.com>,
	Pratyush Anand <pratyush.anand@gmail.com>,
	Zaihai Yu <yuzaihai@hisilicon.com>,
	<linux-arm-kernel@lists.infradead.org>
Subject: Re: [PATCH] PCI: dwc: Separate CFG0 and CFG1 into different ATU regions
Date: Thu, 9 Jan 2020 23:04:01 +0530	[thread overview]
Message-ID: <beda8923-a3b7-47eb-7cf1-19a3bacf1e34@nvidia.com> (raw)
In-Reply-To: <20200109060657.1953-1-shawn.guo@linaro.org>



On 1/9/2020 11:36 AM, Shawn Guo wrote:
> External email: Use caution opening links or attachments
> 
> 
> Some platform has 4 (or more) viewports.  In that case, CFG0 and CFG1
> can be separated into different ATU regions.
Is there any specific benefit with this scheme?

- Vidya Sagar
> 
> Signed-off-by: Shawn Guo <shawn.guo@linaro.org>
> ---
>  .../pci/controller/dwc/pcie-designware-host.c    | 16 +++++++++++++++-
>  drivers/pci/controller/dwc/pcie-designware.h     |  1 +
>  2 files changed, 16 insertions(+), 1 deletion(-)
> 
> diff --git a/drivers/pci/controller/dwc/pcie-designware-host.c b/drivers/pci/controller/dwc/pcie-designware-host.c
> index 0f36a926059a..504d2a192bba 100644
> --- a/drivers/pci/controller/dwc/pcie-designware-host.c
> +++ b/drivers/pci/controller/dwc/pcie-designware-host.c
> @@ -532,6 +532,7 @@ static int dw_pcie_access_other_conf(struct pcie_port *pp, struct pci_bus *bus,
>         u64 cpu_addr;
>         void __iomem *va_cfg_base;
>         struct dw_pcie *pci = to_dw_pcie_from_pp(pp);
> +       int index = PCIE_ATU_REGION_INDEX1;
> 
>         busdev = PCIE_ATU_BUS(bus->number) | PCIE_ATU_DEV(PCI_SLOT(devfn)) |
>                  PCIE_ATU_FUNC(PCI_FUNC(devfn));
> @@ -548,7 +549,20 @@ static int dw_pcie_access_other_conf(struct pcie_port *pp, struct pci_bus *bus,
>                 va_cfg_base = pp->va_cfg1_base;
>         }
> 
> -       dw_pcie_prog_outbound_atu(pci, PCIE_ATU_REGION_INDEX1,
> +       if (pci->num_viewport >= 4) {
> +               /*
> +                * If there are 4 (or more) viewports, we can separate
> +                * CFG0 and CFG1 into different ATU regions:
> +                *  - region0: MEM
> +                *  - region1: CFG0
> +                *  - region2: IO
> +                *  - region3: CFG1
> +                */
> +               if (type == PCIE_ATU_TYPE_CFG1)
> +                       index = PCIE_ATU_REGION_INDEX3;
> +       }
> +
> +       dw_pcie_prog_outbound_atu(pci, index,
>                                   type, cpu_addr,
>                                   busdev, cfg_size);
>         if (write)
> diff --git a/drivers/pci/controller/dwc/pcie-designware.h b/drivers/pci/controller/dwc/pcie-designware.h
> index 5a18e94e52c8..86225804f1e7 100644
> --- a/drivers/pci/controller/dwc/pcie-designware.h
> +++ b/drivers/pci/controller/dwc/pcie-designware.h
> @@ -63,6 +63,7 @@
>  #define PCIE_ATU_VIEWPORT              0x900
>  #define PCIE_ATU_REGION_INBOUND                BIT(31)
>  #define PCIE_ATU_REGION_OUTBOUND       0
> +#define PCIE_ATU_REGION_INDEX3         0x3
>  #define PCIE_ATU_REGION_INDEX2         0x2
>  #define PCIE_ATU_REGION_INDEX1         0x1
>  #define PCIE_ATU_REGION_INDEX0         0x0
> --
> 2.17.1
> 

  parent reply	other threads:[~2020-01-09 17:34 UTC|newest]

Thread overview: 8+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-01-09  6:06 [PATCH] PCI: dwc: Separate CFG0 and CFG1 into different ATU regions Shawn Guo
2020-01-09 10:37 ` Gustavo Pimentel
2020-01-09 11:14   ` Shawn Guo
2020-01-09 11:28     ` Russell King - ARM Linux admin
2020-01-09 12:24     ` Gustavo Pimentel
2020-01-09 18:29       ` Bjorn Helgaas
2020-01-09 17:34 ` Vidya Sagar [this message]
2020-01-10  8:56   ` Shawn Guo

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=beda8923-a3b7-47eb-7cf1-19a3bacf1e34@nvidia.com \
    --to=vidyas@nvidia.com \
    --cc=bhelgaas@google.com \
    --cc=gustavo.pimentel@synopsys.com \
    --cc=jingoohan1@gmail.com \
    --cc=linux-arm-kernel@lists.infradead.org \
    --cc=linux-pci@vger.kernel.org \
    --cc=lorenzo.pieralisi@arm.com \
    --cc=pratyush.anand@gmail.com \
    --cc=shawn.guo@linaro.org \
    --cc=yuzaihai@hisilicon.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox