linux-arm-kernel.lists.infradead.org archive mirror
 help / color / mirror / Atom feed
From: Jason Gunthorpe <jgg@nvidia.com>
To: Peter Zijlstra <peterz@infradead.org>
Cc: Nicolin Chen <nicolinc@nvidia.com>,
	will@kernel.org, jean-philippe@linaro.org, robin.murphy@arm.com,
	joro@8bytes.org, balbirs@nvidia.com, miko.lenczewski@arm.com,
	kevin.tian@intel.com, praan@google.com,
	linux-arm-kernel@lists.infradead.org, iommu@lists.linux.dev,
	linux-kernel@vger.kernel.org
Subject: Re: [PATCH v7 6/7] iommu/arm-smmu-v3: Add arm_smmu_invs based arm_smmu_domain_inv_range()
Date: Tue, 16 Dec 2025 10:15:11 -0400	[thread overview]
Message-ID: <20251216141511.GD6079@nvidia.com> (raw)
In-Reply-To: <20251216140410.GV3707837@noisy.programming.kicks-ass.net>

On Tue, Dec 16, 2025 at 03:04:10PM +0100, Peter Zijlstra wrote:
> On Tue, Dec 16, 2025 at 09:56:13AM -0400, Jason Gunthorpe wrote:
> > On Tue, Dec 16, 2025 at 10:09:26AM +0100, Peter Zijlstra wrote:
> > > Anyway, if I understand the above correctly, the smb_mb() is for:
> > > 
> > >   arm_smmu_domain_inv_range() 		arm_smmu_install_new_domain_invs()
> > > 
> > >     [W] IOPTE				  [Wrel] smmu_domain->invs
> > >     smp_mb()				  smp_mb()
> > >     [Lacq] smmu_domain->invs		  [L] IOPTE
> > > 
> > > Right? But I'm not sure about your 'HW sees the new IOPTEs' claim;
> > 
> > Yes, the '[L] IOPTE' would be a DMA from HW.
> > 
> > > that very much depend on what coherency domain the relevant hardware
> > > plays in. For smp_mb() to work, the hardware must be in the ISH
> > > domain, while typically devices are (if I remember my arrrrgh64
> > > correctly) in the OSH.
> > 
> > The '[W] IOPTE' sequence already includes a cache flush if the
> > inner/outer sharable are not coherent. If a cache flush was required
> > then the smp_mb() must also order it, otherwise it just has to order
> > the store.
> > 
> > The page table table code has always relied on this kind of ordering
> > with respect to DMA working, it would be completely broken if the DMA
> > does not order with the barriers.
> > 
> > For example:
> > 
> >             CPU0                         CPU1
> >    store PMD
> >                                         read PMD
> >    store PTE 1                          store PTE 2
> >    	     				dma memory barrier
> >                                         device reads 2
> >    dma memory barrier
> >    device reads 1
> 
> But here you have dma_mb(), which is dmb(osh).

This also has a pre-existing dma_wmb(), a fuller chart would be like this:

   arm_smmu_domain_inv_range() 		arm_smmu_install_new_domain_invs()
 
     [W] IOPTE				  [Wrel] smmu_domain->invs
     smp_mb()				  smp_mb()  <--- arm_smmu_install_new_domain_invs()
					  [build the STE]
					  [post the STE]
					  dma_wmb() <--- arm_smmu_cmdq_issue_cmdlist()
                                          Doorbell Write to Device
     [Lacq] smmu_domain->invs		  [L] IOPTE via DMA

Nicolin, please elabortate more of these details in the comment.

Jason


  reply	other threads:[~2025-12-16 14:15 UTC|newest]

Thread overview: 13+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-12-16  2:09 [PATCH v7 0/7] iommu/arm-smmu-v3: Introduce an RCU-protected invalidation array Nicolin Chen
2025-12-16  2:09 ` [PATCH v7 1/7] iommu/arm-smmu-v3: Explicitly set smmu_domain->stage for SVA Nicolin Chen
2025-12-16  2:09 ` [PATCH v7 2/7] iommu/arm-smmu-v3: Add an inline arm_smmu_domain_free() Nicolin Chen
2025-12-16  2:09 ` [PATCH v7 3/7] iommu/arm-smmu-v3: Introduce a per-domain arm_smmu_invs array Nicolin Chen
2025-12-16  2:09 ` [PATCH v7 4/7] iommu/arm-smmu-v3: Pre-allocate a per-master invalidation array Nicolin Chen
2025-12-16  2:09 ` [PATCH v7 5/7] iommu/arm-smmu-v3: Populate smmu_domain->invs when attaching masters Nicolin Chen
2025-12-16  2:09 ` [PATCH v7 6/7] iommu/arm-smmu-v3: Add arm_smmu_invs based arm_smmu_domain_inv_range() Nicolin Chen
2025-12-16  9:09   ` Peter Zijlstra
2025-12-16 13:56     ` Jason Gunthorpe
2025-12-16 14:04       ` Peter Zijlstra
2025-12-16 14:15         ` Jason Gunthorpe [this message]
2025-12-16 19:14           ` Nicolin Chen
2025-12-16  2:09 ` [PATCH v7 7/7] iommu/arm-smmu-v3: Perform per-domain invalidations using arm_smmu_invs Nicolin Chen

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=20251216141511.GD6079@nvidia.com \
    --to=jgg@nvidia.com \
    --cc=balbirs@nvidia.com \
    --cc=iommu@lists.linux.dev \
    --cc=jean-philippe@linaro.org \
    --cc=joro@8bytes.org \
    --cc=kevin.tian@intel.com \
    --cc=linux-arm-kernel@lists.infradead.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=miko.lenczewski@arm.com \
    --cc=nicolinc@nvidia.com \
    --cc=peterz@infradead.org \
    --cc=praan@google.com \
    --cc=robin.murphy@arm.com \
    --cc=will@kernel.org \
    /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).