mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: Lukas Wunner <lukas@wunner.de>
To: Vidya Sagar <vidyas@nvidia.com>
Cc: 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: Tue, 25 Jun 2024 18:26:00 +0200	[thread overview]
Message-ID: <ZnrvmGBw-Ss-oOO6@wunner.de> (raw)
In-Reply-To: <20240625153150.159310-1-vidyas@nvidia.com>

On Tue, Jun 25, 2024 at 09:01:50PM +0530, Vidya Sagar wrote:
> 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.

An example wouldn't hurt, here and in kernel-parameters.txt.


> 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.

I'm wondering whether it would make more sense to let users choose
between those "higher-level" options, instead of giving direct access
to bits (and thus risking users to choose an incorrect setting).

Also, would it be possible to automatically change ACS settings
when enabling or disabling P2PDMA?

The representation chosen here (as a command line option) seems
questionable:

We're going to add more user-controllable options going forward.
E.g., when introducing IDE, we'll have to let user space choose
whether encryption should be enabled for certain PCIe devices.
That's because encryption isn't for free, so can't be enabled
opportunistically.  (The number of crypto engines on a CPU is
limited and enabling encryption consumes energy.)

What about exposing such user configurable settings with sysctl?
The networking subsystem has per-interface sysctl settings,
we could have per-PCI-device settings.

So just like this...

net.ipv4.conf.default.arp_accept = 0
net.ipv4.conf.eth0.arp_accept = 0
net.ipv4.conf.eth1.arp_accept = 0

... we could have...

pci.0000:03:00.0.acs = full_prevention
pci.0000:03:00.0.ide = 1
pci.0000:03:01.0.acs = all_traffic
pci.0000:03:01.0.ide = 0

This isn't hard to do, just call register_sysctl() for each device
on enumeration and unregister_sysctl_table() on pci_destroy_dev().

Thanks,

Lukas

  reply	other threads:[~2024-06-25 16:26 UTC|newest]

Thread overview: 28+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2024-05-21 11:09 [PATCH V2] " 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 [this message]
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

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=ZnrvmGBw-Ss-oOO6@wunner.de \
    --to=lukas@wunner.de \
    --cc=bhelgaas@google.com \
    --cc=corbet@lwn.net \
    --cc=galshalom@nvidia.com \
    --cc=jan@nvidia.com \
    --cc=jgg@nvidia.com \
    --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

Powered by JetHome