All of lore.kernel.org
 help / color / mirror / Atom feed
From: Jason Gunthorpe <jgg@nvidia.com>
To: Alistair Popple <apopple@nvidia.com>
Cc: Andrew Morton <akpm@linux-foundation.org>,
	will@kernel.org, catalin.marinas@arm.com, linux-mm@kvack.org,
	linux-kernel@vger.kernel.org, robin.murphy@arm.com,
	nicolinc@nvidia.com, linux-arm-kernel@lists.infradead.org,
	kvm@vger.kernel.org, John Hubbard <jhubbard@nvidia.com>,
	zhi.wang.linux@gmail.com, Sean Christopherson <seanjc@google.com>
Subject: Re: [PATCH 2/2] arm64: Notify on pte permission upgrades
Date: Tue, 30 May 2023 08:54:39 -0300	[thread overview]
Message-ID: <ZHXj/6Bjraxqk4YR@nvidia.com> (raw)
In-Reply-To: <87pm6ii6qi.fsf@nvidia.com>

On Tue, May 30, 2023 at 06:05:41PM +1000, Alistair Popple wrote:
> 
> >> As no notification is sent and the SMMU does not snoop TLB invalidates
> >> it will continue to return read-only entries to a device even though
> >> the CPU page table contains a writable entry. This leads to a
> >> continually faulting device and no way of handling the fault.
> >
> > Doesn't the fault generate a PRI/etc? If we get a PRI maybe we should
> > just have the iommu driver push an iotlb invalidation command before
> > it acks it? PRI is already really slow so I'm not sure a pipelined
> > invalidation is going to be a problem? Does the SMMU architecture
> > permit negative caching which would suggest we need it anyhow?
> 
> Yes, SMMU architecture (which matches the ARM architecture in regards to
> TLB maintenance requirements) permits negative caching of some mapping
> attributes including the read-only attribute. Hence without the flushing
> we fault continuously.

Sounds like a straight up SMMU bug, invalidate the cache after
resolving the PRI event.

Jason

WARNING: multiple messages have this Message-ID (diff)
From: Jason Gunthorpe <jgg@nvidia.com>
To: Alistair Popple <apopple@nvidia.com>
Cc: Andrew Morton <akpm@linux-foundation.org>,
	will@kernel.org, catalin.marinas@arm.com, linux-mm@kvack.org,
	linux-kernel@vger.kernel.org, robin.murphy@arm.com,
	nicolinc@nvidia.com, linux-arm-kernel@lists.infradead.org,
	kvm@vger.kernel.org, John Hubbard <jhubbard@nvidia.com>,
	zhi.wang.linux@gmail.com, Sean Christopherson <seanjc@google.com>
Subject: Re: [PATCH 2/2] arm64: Notify on pte permission upgrades
Date: Tue, 30 May 2023 08:54:39 -0300	[thread overview]
Message-ID: <ZHXj/6Bjraxqk4YR@nvidia.com> (raw)
In-Reply-To: <87pm6ii6qi.fsf@nvidia.com>

On Tue, May 30, 2023 at 06:05:41PM +1000, Alistair Popple wrote:
> 
> >> As no notification is sent and the SMMU does not snoop TLB invalidates
> >> it will continue to return read-only entries to a device even though
> >> the CPU page table contains a writable entry. This leads to a
> >> continually faulting device and no way of handling the fault.
> >
> > Doesn't the fault generate a PRI/etc? If we get a PRI maybe we should
> > just have the iommu driver push an iotlb invalidation command before
> > it acks it? PRI is already really slow so I'm not sure a pipelined
> > invalidation is going to be a problem? Does the SMMU architecture
> > permit negative caching which would suggest we need it anyhow?
> 
> Yes, SMMU architecture (which matches the ARM architecture in regards to
> TLB maintenance requirements) permits negative caching of some mapping
> attributes including the read-only attribute. Hence without the flushing
> we fault continuously.

Sounds like a straight up SMMU bug, invalidate the cache after
resolving the PRI event.

Jason

_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel

  reply	other threads:[~2023-05-30 11:55 UTC|newest]

Thread overview: 46+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2023-05-24  1:47 [PATCH 1/2] mmu_notifiers: Restore documentation for .invalidate_range() Alistair Popple
2023-05-24  1:47 ` Alistair Popple
2023-05-24  1:47 ` [PATCH 2/2] arm64: Notify on pte permission upgrades Alistair Popple
2023-05-24  1:47   ` Alistair Popple
2023-05-28  0:02   ` Jason Gunthorpe
2023-05-28  0:02     ` Jason Gunthorpe
2023-05-30  8:05     ` Alistair Popple
2023-05-30  8:05       ` Alistair Popple
2023-05-30 11:54       ` Jason Gunthorpe [this message]
2023-05-30 11:54         ` Jason Gunthorpe
2023-05-30 12:14         ` Robin Murphy
2023-05-30 12:14           ` Robin Murphy
2023-05-30 12:52           ` Jason Gunthorpe
2023-05-30 12:52             ` Jason Gunthorpe
2023-05-30 13:44             ` Robin Murphy
2023-05-30 13:44               ` Robin Murphy
2023-05-30 14:06               ` Jason Gunthorpe
2023-05-30 14:06                 ` Jason Gunthorpe
2023-05-30 21:44                 ` Sean Christopherson
2023-05-30 21:44                   ` Sean Christopherson
2023-05-30 23:08                   ` Jason Gunthorpe
2023-05-30 23:08                     ` Jason Gunthorpe
2023-05-31  0:30                     ` Alistair Popple
2023-05-31  0:30                       ` Alistair Popple
2023-05-31  0:32                       ` Jason Gunthorpe
2023-05-31  0:32                         ` Jason Gunthorpe
2023-05-31  2:46                         ` Alistair Popple
2023-05-31  2:46                           ` Alistair Popple
2023-05-31 15:30                           ` Jason Gunthorpe
2023-05-31 15:30                             ` Jason Gunthorpe
2023-05-31 23:56                             ` Alistair Popple
2023-05-31 23:56                               ` Alistair Popple
     [not found]                       ` <31cdd164783fefad4c9ef4a6d33c1e0094405d0f03added523a82dd9febdf15f@mu.id>
2023-06-09  2:06                         ` Alistair Popple
2023-06-09  2:06                           ` Alistair Popple
2023-06-09  6:05                           ` Alistair Popple
2023-06-09  6:05                             ` Alistair Popple
2023-05-24  2:20 ` [PATCH 1/2] mmu_notifiers: Restore documentation for .invalidate_range() John Hubbard
2023-05-24  2:20   ` John Hubbard
2023-05-24  4:45   ` Alistair Popple
2023-05-24  4:45     ` Alistair Popple
2023-05-27 23:56   ` Jason Gunthorpe
2023-05-27 23:56     ` Jason Gunthorpe
2023-05-24  3:48 ` Zhi Wang
2023-05-24  3:48   ` Zhi Wang
2023-05-24  4:57   ` Alistair Popple
2023-05-24  4:57     ` Alistair Popple

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=ZHXj/6Bjraxqk4YR@nvidia.com \
    --to=jgg@nvidia.com \
    --cc=akpm@linux-foundation.org \
    --cc=apopple@nvidia.com \
    --cc=catalin.marinas@arm.com \
    --cc=jhubbard@nvidia.com \
    --cc=kvm@vger.kernel.org \
    --cc=linux-arm-kernel@lists.infradead.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=nicolinc@nvidia.com \
    --cc=robin.murphy@arm.com \
    --cc=seanjc@google.com \
    --cc=will@kernel.org \
    --cc=zhi.wang.linux@gmail.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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.