From: Bjorn Helgaas <helgaas@kernel.org>
To: Jiri Slaby <jirislaby@kernel.org>
Cc: Vidya Sagar <vidyas@nvidia.com>,
corbet@lwn.net, bhelgaas@google.com, galshalom@nvidia.com,
leonro@nvidia.com, jgg@nvidia.com, treding@nvidia.com,
jonathanh@nvidia.com, mmoshrefjava@nvidia.com,
shahafs@nvidia.com, vsethi@nvidia.com, sdonthineni@nvidia.com,
jan@nvidia.com, tdave@nvidia.com, linux-doc@vger.kernel.org,
linux-pci@vger.kernel.org, linux-kernel@vger.kernel.org,
kthota@nvidia.com, mmaddireddy@nvidia.com, sagar.tv@gmail.com
Subject: Re: [PATCH V4] PCI: Extend ACS configurability
Date: Mon, 7 Oct 2024 15:43:52 -0500 [thread overview]
Message-ID: <20241007204352.GA449721@bhelgaas> (raw)
In-Reply-To: <e89107da-ac99-4d3a-9527-a4df9986e120@kernel.org>
On Wed, Sep 25, 2024 at 07:06:41AM +0200, Jiri Slaby wrote:
> On 25. 06. 24, 17:31, Vidya Sagar wrote:
> > PCIe ACS settings control the level of isolation and the possible P2P
> > paths between devices. With greater isolation the kernel will create
> > smaller iommu_groups and with less isolation there is more HW that
> > can achieve P2P transfers. From a virtualization perspective all
> > devices in the same iommu_group must be assigned to the same VM as
> > they lack security isolation.
> >
> > There is no way for the kernel to automatically know the correct
> > ACS settings for any given system and workload. Existing command line
> > options (ex:- disable_acs_redir) allow only for large scale change,
> > disabling all isolation, but this is not sufficient for more complex cases.
> >
> > Add a kernel command-line option 'config_acs' to directly control all the
> > ACS bits for specific devices, which allows the operator to setup the
> > right level of isolation to achieve the desired P2P configuration.
> > The definition is future proof, when new ACS bits are added to the spec
> > the open syntax can be extended.
> >
> > ACS needs to be setup early in the kernel boot as the ACS settings
> > effect how iommu_groups are formed. iommu_group formation is a one
> > time event during initial device discovery, changing ACS bits after
> > kernel boot can result in an inaccurate view of the iommu_groups
> > compared to the current isolation configuration.
> >
> > ACS applies to PCIe Downstream Ports and multi-function devices.
> > The default ACS settings are strict and deny any direct traffic
> > between two functions. This results in the smallest iommu_group the
> > HW can support. Frequently these values result in slow or
> > non-working P2PDMA.
> >
> > ACS offers a range of security choices controlling how traffic is
> > allowed to go directly between two devices. Some popular choices:
> > - Full prevention
> > - Translated requests can be direct, with various options
> > - Asymmetric direct traffic, A can reach B but not the reverse
> > - All traffic can be direct
> > Along with some other less common ones for special topologies.
> >
> > The intention is that this option would be used with expert knowledge
> > of the HW capability and workload to achieve the desired
> > configuration.
>
> Hi,
>
> this breaks ACS on some platforms (in 6.11). See:
> https://bugzilla.suse.com/show_bug.cgi?id=1229019
#regzbot introduced: 47c8846a ("PCI: Extend ACS configurability")
#regzbot link: https://bugzilla.suse.com/show_bug.cgi?id=1229019
prev parent reply other threads:[~2024-10-07 20:43 UTC|newest]
Thread overview: 28+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-05-21 11:09 [PATCH V2] PCI: Extend ACS configurability Vidya Sagar
2024-05-21 15:44 ` kernel test robot
2024-05-23 6:35 ` [PATCH V3] " Vidya Sagar
2024-05-23 14:59 ` Bjorn Helgaas
2024-05-23 15:16 ` Jason Gunthorpe
2024-06-03 7:50 ` Vidya Sagar
2024-06-07 19:30 ` Bjorn Helgaas
2024-06-10 11:38 ` Jason Gunthorpe
2024-06-12 21:29 ` Bjorn Helgaas
2024-06-12 23:23 ` Jason Gunthorpe
2024-06-13 22:05 ` Bjorn Helgaas
2024-06-13 23:36 ` Jason Gunthorpe
2024-06-13 22:38 ` Alex Williamson
2024-06-12 12:19 ` Jason Gunthorpe
2024-06-25 15:31 ` [PATCH V4] " Vidya Sagar
2024-06-25 16:26 ` Lukas Wunner
2024-06-25 16:39 ` Jason Gunthorpe
2024-06-26 6:02 ` Leon Romanovsky
2024-06-26 7:40 ` Tian, Kevin
2024-06-26 11:50 ` Jason Gunthorpe
2024-07-08 14:39 ` Jason Gunthorpe
2024-07-12 21:57 ` Bjorn Helgaas
2024-09-25 5:06 ` Jiri Slaby
2024-09-25 5:29 ` Jiri Slaby
2024-09-25 5:49 ` Jiri Slaby
2024-10-01 19:33 ` Jason Gunthorpe
2024-10-07 16:36 ` Steffen Dirkwinkel
2024-10-07 20:43 ` Bjorn Helgaas [this message]
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=20241007204352.GA449721@bhelgaas \
--to=helgaas@kernel.org \
--cc=bhelgaas@google.com \
--cc=corbet@lwn.net \
--cc=galshalom@nvidia.com \
--cc=jan@nvidia.com \
--cc=jgg@nvidia.com \
--cc=jirislaby@kernel.org \
--cc=jonathanh@nvidia.com \
--cc=kthota@nvidia.com \
--cc=leonro@nvidia.com \
--cc=linux-doc@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-pci@vger.kernel.org \
--cc=mmaddireddy@nvidia.com \
--cc=mmoshrefjava@nvidia.com \
--cc=sagar.tv@gmail.com \
--cc=sdonthineni@nvidia.com \
--cc=shahafs@nvidia.com \
--cc=tdave@nvidia.com \
--cc=treding@nvidia.com \
--cc=vidyas@nvidia.com \
--cc=vsethi@nvidia.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).