From: Robin Murphy <robin.murphy@arm.com>
To: Jean-Philippe Brucker <jean-philippe.brucker@arm.com>,
will.deacon@arm.com, lorenzo.pieralisi@arm.com,
bhelgaas@google.com
Cc: zhongmiao@hisilicon.com, okaya@kernel.org, rjw@rjwysocki.net,
linux-pci@vger.kernel.org, linux-acpi@vger.kernel.org,
iommu@lists.linux-foundation.org, sudeep.holla@arm.com,
linux-arm-kernel@lists.infradead.org, lenb@kernel.org
Subject: Re: [PATCH v3 8/9] iommu/arm-smmu-v3: Add support for PCI ATS
Date: Mon, 1 Jul 2019 18:41:56 +0100 [thread overview]
Message-ID: <7fcd5263-8a20-11cb-0c20-9fee35fe65c1@arm.com> (raw)
In-Reply-To: <20190417182448.12382-9-jean-philippe.brucker@arm.com>
Hi Jean-Philippe,
I realise it's a bit late for a "review", but digging up the original
patch seemed as good a place as any to raise this...
On 17/04/2019 19:24, Jean-Philippe Brucker wrote:
[...]
> @@ -1740,6 +1906,9 @@ static void arm_smmu_detach_dev(struct arm_smmu_master *master)
>
> master->domain = NULL;
> arm_smmu_install_ste_for_dev(master);
> +
> + /* Disabling ATS invalidates all ATC entries */
> + arm_smmu_disable_ats(master);
> }
Is that actually true? I had initially overlooked this entirely while
diagnosing something else and thought that we were missing any ATC
invalidation on detach at all, but even having looked again I'm not
entirely convinced it's bulletproof.
Firstly, the ATS spec only seems to say that *enabling* the ATS
capability invalidates all ATC entries, although I think any corner
cases that that alone opens up should be at best theoretical. More
importantly though, pci_disable_ats() might not actually touch the
capability - given that, it seems possible to move a VF to a new domain,
and if it's not reset, end up preserving now-bogus ATC entries despite
the old domain being torn down and freed. Do we need an explicit ATC
invalidation here to be 100% safe, or is there something else I'm missing?
Robin.
next prev parent reply other threads:[~2019-07-01 17:42 UTC|newest]
Thread overview: 16+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-04-17 18:24 [PATCH v3 0/9] Add PCI ATS support to Arm SMMUv3 Jean-Philippe Brucker
2019-04-17 18:24 ` [PATCH v3 1/9] PCI: Move ATS declarations outside of CONFIG_PCI Jean-Philippe Brucker
2019-04-17 19:47 ` Bjorn Helgaas
2019-04-17 18:24 ` [PATCH v3 2/9] PCI: Add a stub for pci_ats_disabled() Jean-Philippe Brucker
2019-04-17 19:48 ` Bjorn Helgaas
2019-04-17 18:24 ` [PATCH v3 3/9] ACPI/IORT: Check ATS capability in root complex nodes Jean-Philippe Brucker
2019-04-18 11:20 ` Lorenzo Pieralisi
2019-04-17 18:24 ` [PATCH v3 4/9] iommu/arm-smmu-v3: Rename arm_smmu_master_data to arm_smmu_master Jean-Philippe Brucker
2019-04-17 18:24 ` [PATCH v3 5/9] iommu/arm-smmu-v3: Store SteamIDs in master Jean-Philippe Brucker
2019-04-17 18:24 ` [PATCH v3 6/9] iommu/arm-smmu-v3: Add a master->domain pointer Jean-Philippe Brucker
2019-04-17 18:24 ` [PATCH v3 7/9] iommu/arm-smmu-v3: Link domains and devices Jean-Philippe Brucker
2019-04-17 18:24 ` [PATCH v3 8/9] iommu/arm-smmu-v3: Add support for PCI ATS Jean-Philippe Brucker
2019-07-01 17:41 ` Robin Murphy [this message]
2019-07-02 14:59 ` Jean-Philippe Brucker
2019-04-17 18:24 ` [PATCH v3 9/9] iommu/arm-smmu-v3: Disable tagged pointers Jean-Philippe Brucker
2019-04-23 11:21 ` [PATCH v3 0/9] Add PCI ATS support to Arm SMMUv3 Will Deacon
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=7fcd5263-8a20-11cb-0c20-9fee35fe65c1@arm.com \
--to=robin.murphy@arm.com \
--cc=bhelgaas@google.com \
--cc=iommu@lists.linux-foundation.org \
--cc=jean-philippe.brucker@arm.com \
--cc=lenb@kernel.org \
--cc=linux-acpi@vger.kernel.org \
--cc=linux-arm-kernel@lists.infradead.org \
--cc=linux-pci@vger.kernel.org \
--cc=lorenzo.pieralisi@arm.com \
--cc=okaya@kernel.org \
--cc=rjw@rjwysocki.net \
--cc=sudeep.holla@arm.com \
--cc=will.deacon@arm.com \
--cc=zhongmiao@hisilicon.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).