Linux RDMA and InfiniBand development
 help / color / mirror / Atom feed
From: Leon Romanovsky <leon@kernel.org>
To: sashiko-reviews@lists.linux.dev
Cc: media-ci@linuxtv.org, dri-devel@lists.freedesktop.org,
	linux-rdma@vger.kernel.org, linux-pci@vger.kernel.org,
	kvm@vger.kernel.org
Subject: Re: [PATCH v10 17/18] PCI/P2PDMA: Evaluate the ATS path for clients with ATS enabled
Date: Mon, 12 Oct 2026 21:08:13 +0300	[thread overview]
Message-ID: <20261012180813.GI219304@unreal> (raw)
In-Reply-To: <sashiko-outbox-168177@kernel.org>

On Mon, Oct 12, 2026 at 01:27:12PM +0000, sashiko-bot@kernel.org wrote:
> Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider:
> - [High] pci: pci_p2pdma_distance_many() evaluates compatibility without applying client ATS constraints
> --
> 
> commit 254b102fe424913edc3d5f94f8d41bc5d0de2b20
> Author: Leon Romanovsky <leon@kernel.org>
> 
> PCI/P2PDMA: Evaluate the ATS path for clients with ATS enabled
> 
> P2PDMA assumes every client issues Untranslated Requests. A device with
> ATS enabled may translate any address it is handed, including a bus
> address, and Translation Blocking can reject its Translated Requests on
> a route the Untranslated answer called usable.
> 
> > diff --git a/drivers/pci/p2pdma.c b/drivers/pci/p2pdma.c
> > index e38081f797611..a5fc622e3114f 100644
> > --- a/drivers/pci/p2pdma.c
> > +++ b/drivers/pci/p2pdma.c
> 
> [ ... ]
> 
> > @@ -1660,10 +1706,10 @@ pci_p2pdma_map_type_tlp(struct p2pdma_provider *provider, struct device *dev,
> >  		 pci_p2pdma_map_type_name(type), type, provider_state);
> >  
> >  	if (type == PCI_P2PDMA_MAP_UNKNOWN)
> > -		return calc_map_type_and_dist(pdev, client, &dist, tlp_flags,
> > +		type = calc_map_type_and_dist(pdev, client, &dist, tlp_flags,
> >  					      true);
> >  
> > -	return type;
> > +	return pci_p2pdma_client_map_type(pdev, client, per_mapping, type);
> >  }
> 
> [Severity: High]
> Does pci_p2pdma_distance_many() also need to apply these new ATS constraints?
> 
> While this patch successfully updates pci_p2pdma_map_type_tlp() to evaluate ATS
> routing constraints for P2PDMA clients, pci_p2pdma_distance_many() continues
> to evaluate mapping compatibility without them:
> 
> drivers/pci/p2pdma.c:pci_p2pdma_distance_many() {
>     ...
> 		pci_client = find_parent_pci_dev(clients[i]);
> 		if (!pci_client) {
>     ...
> 		map = calc_map_type_and_dist(provider, pci_client, &distance, 0,
> 					     verbose);
>     ...
> }
> 
> If a client has ATS enabled and its Untranslated route is usable but its
> Translated route is blocked by Translation Blocking (or lacks a whitelisted
> host bridge), pci_p2pdma_distance_many() evaluates the Untranslated mapping
> with tlp_flags=0, and incorrectly returns success. 
> 
> When the driver subsequently attempts to map memory, the ATS-aware mapping
> logic will return PCI_P2PDMA_MAP_NOT_SUPPORTED and fail unexpectedly at
> runtime, breaking the API contract of the distance validation.

Yes, Sashiko is right, I'll send new version :(.

Thanks

> 
> -- 
> Sashiko AI review · https://sashiko.dev/#/patchset/20261012-fix-p2p-acs-v4-0-v10-0-6ffe7b7a4517@nvidia.com?part=17

  reply	other threads:[~2026-10-12 18:08 UTC|newest]

Thread overview: 38+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-10-12 13:07 [PATCH v10 00/18] PCI/P2PDMA: Route peer-to-peer DMA by TLP class Leon Romanovsky
2026-10-12 13:07 ` [PATCH v10 01/18] PCI/P2PDMA: Document the TLP attribute assumptions Leon Romanovsky
2026-10-12 13:11   ` sashiko-bot
2026-10-12 13:07 ` [PATCH v10 02/18] PCI/P2PDMA: Derive routing from directional ACS controls Leon Romanovsky
2026-10-12 13:16   ` sashiko-bot
2026-10-12 13:07 ` [PATCH v10 03/18] PCI: Reject unreadable ACS controls in isolation checks Leon Romanovsky
2026-10-12 13:20   ` sashiko-bot
2026-10-12 13:07 ` [PATCH v10 04/18] PCI/P2PDMA: Evaluate ACS controls at the path divergence Leon Romanovsky
2026-10-12 13:15   ` sashiko-bot
2026-10-12 13:07 ` [PATCH v10 05/18] PCI/P2PDMA: Document directional ACS routing Leon Romanovsky
2026-10-12 13:15   ` sashiko-bot
2026-10-12 13:07 ` [PATCH v10 06/18] PCI/P2PDMA: Collect the path's ACS controls before deciding Leon Romanovsky
2026-10-12 13:15   ` sashiko-bot
2026-10-12 13:07 ` [PATCH v10 07/18] PCI/P2PDMA: Answer routing per TLP class Leon Romanovsky
2026-10-12 13:18   ` sashiko-bot
2026-10-12 13:07 ` [PATCH v10 08/18] PCI/P2PDMA: Route Relaxed Ordering Completions directly Leon Romanovsky
2026-10-12 13:18   ` sashiko-bot
2026-10-12 13:07 ` [PATCH v10 09/18] PCI/P2PDMA: Reject Translated Requests blocked by Translation Blocking Leon Romanovsky
2026-10-12 13:20   ` sashiko-bot
2026-10-12 13:07 ` [PATCH v10 10/18] PCI/P2PDMA: Route Translated Requests under Direct Translated P2P Leon Romanovsky
2026-10-12 13:15   ` sashiko-bot
2026-10-12 13:07 ` [PATCH v10 11/18] PCI/P2PDMA: Log detailed ACS routing diagnostics Leon Romanovsky
2026-10-12 13:18   ` sashiko-bot
2026-10-12 13:07 ` [PATCH v10 12/18] PCI/P2PDMA: Add KUnit tests for the ACS routing decisions Leon Romanovsky
2026-10-12 13:19   ` sashiko-bot
2026-10-12 13:07 ` [PATCH v10 13/18] PCI/P2PDMA: Test the ACS P2P routing walk Leon Romanovsky
2026-10-12 13:23   ` sashiko-bot
2026-10-12 13:07 ` [PATCH v10 14/18] PCI: Add KUnit coverage for ACS isolation checks Leon Romanovsky
2026-10-12 13:20   ` sashiko-bot
2026-10-12 13:07 ` [PATCH v10 15/18] PCI/P2PDMA: Document TLP-class routing Leon Romanovsky
2026-10-12 13:16   ` sashiko-bot
2026-10-12 13:07 ` [PATCH v10 16/18] PCI/P2PDMA: Let a client declare that it selects ATS per mapping Leon Romanovsky
2026-10-12 13:26   ` sashiko-bot
2026-10-12 13:07 ` [PATCH v10 17/18] PCI/P2PDMA: Evaluate the ATS path for clients with ATS enabled Leon Romanovsky
2026-10-12 13:27   ` sashiko-bot
2026-10-12 18:08     ` Leon Romanovsky [this message]
2026-10-12 13:07 ` [PATCH v10 18/18] PCI/P2PDMA: Test the routing of " Leon Romanovsky
2026-10-12 13:24   ` sashiko-bot

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=20261012180813.GI219304@unreal \
    --to=leon@kernel.org \
    --cc=dri-devel@lists.freedesktop.org \
    --cc=kvm@vger.kernel.org \
    --cc=linux-pci@vger.kernel.org \
    --cc=linux-rdma@vger.kernel.org \
    --cc=media-ci@linuxtv.org \
    --cc=sashiko-reviews@lists.linux.dev \
    /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