From: "Ilpo Järvinen" <ilpo.jarvinen@linux.intel.com>
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: Wed, 10 Jul 2024 16:56:15 +0300 (EEST) [thread overview]
Message-ID: <302bd9a7-41cb-7b04-4acd-a4a96d5dfe2f@linux.intel.com> (raw)
In-Reply-To: <20240709133610.1089420-7-stewart.hildebrand@amd.com>
On Tue, 9 Jul 2024, 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.
>
> 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;
SZ_4K
+ add #include for it if its not yet included by the .c file.
--
i.
next prev parent reply other threads:[~2024-07-10 13:56 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
2024-07-10 16:35 ` Stewart Hildebrand
2024-07-10 13:56 ` Ilpo Järvinen [this message]
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=302bd9a7-41cb-7b04-4acd-a4a96d5dfe2f@linux.intel.com \
--to=ilpo.jarvinen@linux.intel.com \
--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;
as well as URLs for NNTP newsgroup(s).