public inbox for linux-kernel@vger.kernel.org
 help / color / mirror / Atom feed
From: Bjorn Helgaas <helgaas@kernel.org>
To: Stewart Hildebrand <stewart.hildebrand@amd.com>
Cc: Bjorn Helgaas <bhelgaas@google.com>,
	linux-pci@vger.kernel.org, linux-kernel@vger.kernel.org
Subject: Re: [PATCH 6/6] PCI: align small (<4k) BARs
Date: Tue, 9 Jul 2024 11:21:54 -0500	[thread overview]
Message-ID: <20240709162154.GA175839@bhelgaas> (raw)
In-Reply-To: <20240709133610.1089420-7-stewart.hildebrand@amd.com>

On Tue, Jul 09, 2024 at 09:36:03AM -0400, Stewart Hildebrand wrote:
> Issues observed when small (<4k) BARs are not 4k aligned are:
> 
> 1. Devices to be passed through (to e.g. a Xen HVM guest) with small
> (<4k) BARs require each memory BAR to be page aligned. Currently, the
> only way to guarantee this alignment from a user perspective is to fake
> the size of the BARs using the pci=resource_alignment= option. This is a
> bad user experience, and faking the BAR size is not always desirable.
> See the comment in drivers/pci/pci.c:pci_request_resource_alignment()
> for further discussion.

Include the relevant part of this discussion directly here so this log
is self-contained.  Someday that function will change, which will make
this commit log less useful.

> 2. Devices with multiple small (<4k) BARs could have the MSI-X tables
> located in one of its small (<4k) BARs. This may lead to the MSI-X
> tables being mapped in the same 4k region as other data. The PCIe 6.1
> specification (section 7.7.2 MSI-X Capability and Table Structure) says
> we probably shouldn't do that.
> 
> To improve the user experience, and increase conformance to PCIe spec,
> set the default minimum resource alignment of memory BARs to 4k. Choose
> 4k (rather than PAGE_SIZE) for the alignment value in the common code,
> since that is the value called out in the PCIe 6.1 spec, section 7.7.2.
> The new default alignment may be overridden by arches by implementing
> pcibios_default_alignment(), or by the user with the
> pci=resource_alignment= option.
> 
> Signed-off-by: Stewart Hildebrand <stewart.hildebrand@amd.com>
> ---
> Preparatory patches in this series are prerequisites to this patch.
> ---
>  drivers/pci/pci.c | 7 ++++++-
>  1 file changed, 6 insertions(+), 1 deletion(-)
> 
> diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
> index 9f7894538334..e7b648304383 100644
> --- a/drivers/pci/pci.c
> +++ b/drivers/pci/pci.c
> @@ -6453,7 +6453,12 @@ struct pci_dev __weak *pci_real_dma_dev(struct pci_dev *dev)
>  
>  resource_size_t __weak pcibios_default_alignment(void)
>  {
> -	return 0;
> +	/*
> +	 * Avoid MSI-X tables being mapped in the same 4k region as other data
> +	 * according to PCIe 6.1 specification section 7.7.2 MSI-X Capability
> +	 * and Table Structure.
> +	 */
> +	return 4 * 1024;
>  }
>  
>  /*
> -- 
> 2.45.2
> 

  reply	other threads:[~2024-07-09 16:21 UTC|newest]

Thread overview: 24+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2024-07-09 13:35 [PATCH 0/6] PCI: align small (<4k) BARs Stewart Hildebrand
2024-07-09 13:35 ` [PATCH 1/6] PCI: don't clear already cleared bit Stewart Hildebrand
2024-07-09 13:35 ` [PATCH 2/6] PCI: restore resource alignment Stewart Hildebrand
2024-07-09 13:36 ` [PATCH 3/6] PCI: restore memory decoding after reallocation Stewart Hildebrand
2024-07-09 16:16   ` Bjorn Helgaas
2024-07-10 20:31     ` Stewart Hildebrand
2024-07-09 13:36 ` [RFC PATCH 4/6] x86: PCI: preserve IORESOURCE_STARTALIGN alignment Stewart Hildebrand
2024-07-09 16:19   ` Bjorn Helgaas
2024-07-10 16:16     ` Stewart Hildebrand
2024-07-10 21:24       ` Bjorn Helgaas
2024-07-10 22:49         ` Stewart Hildebrand
2024-07-11 18:40           ` Bjorn Helgaas
2024-07-11 18:58             ` Stewart Hildebrand
2024-07-11 20:35               ` Bjorn Helgaas
2024-07-15 17:26         ` Stewart Hildebrand
2024-07-10 14:05   ` Ilpo Järvinen
2024-07-15 17:30     ` Stewart Hildebrand
2024-07-09 13:36 ` [PATCH 5/6] PCI: don't reassign resources that are already aligned Stewart Hildebrand
2024-07-09 13:36 ` [PATCH 6/6] PCI: align small (<4k) BARs Stewart Hildebrand
2024-07-09 16:21   ` Bjorn Helgaas [this message]
2024-07-10 16:35     ` Stewart Hildebrand
2024-07-10 13:56   ` Ilpo Järvinen
2024-07-10 16:28     ` Stewart Hildebrand
2024-07-10 23:26 ` [PATCH 0/6] " Stewart Hildebrand

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=20240709162154.GA175839@bhelgaas \
    --to=helgaas@kernel.org \
    --cc=bhelgaas@google.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-pci@vger.kernel.org \
    --cc=stewart.hildebrand@amd.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