From: Marc Zyngier <maz@kernel.org>
To: Catalin Marinas <catalin.marinas@arm.com>
Cc: Steven Price <steven.price@arm.com>,
Peter Maydell <peter.maydell@linaro.org>,
Haibo Xu <haibo.xu@linaro.org>,
lkml - Kernel Mailing List <linux-kernel@vger.kernel.org>,
Juan Quintela <quintela@redhat.com>,
Richard Henderson <richard.henderson@linaro.org>,
QEMU Developers <qemu-devel@nongnu.org>,
"Dr. David Alan Gilbert" <dgilbert@redhat.com>,
Thomas Gleixner <tglx@linutronix.de>,
Will Deacon <will@kernel.org>,
kvmarm <kvmarm@lists.cs.columbia.edu>,
arm-mail-list <linux-arm-kernel@lists.infradead.org>,
Dave Martin <Dave.Martin@arm.com>
Subject: Re: [PATCH v5 0/2] MTE support for KVM guest
Date: Mon, 07 Dec 2020 19:03:13 +0000 [thread overview]
Message-ID: <874kkx5thq.wl-maz@kernel.org> (raw)
In-Reply-To: <20201207163405.GD1526@gaia>
On Mon, 07 Dec 2020 16:34:05 +0000,
Catalin Marinas <catalin.marinas@arm.com> wrote:
>
> On Mon, Dec 07, 2020 at 04:05:55PM +0000, Marc Zyngier wrote:
> > What I'd really like to see is a description of how shared memory
> > is, in general, supposed to work with MTE. My gut feeling is that
> > it doesn't, and that you need to turn MTE off when sharing memory
> > (either implicitly or explicitly).
>
> The allocation tag (in-memory tag) is a property assigned to a physical
> address range and it can be safely shared between different processes as
> long as they access it via pointers with the same allocation tag (bits
> 59:56). The kernel enables such tagged shared memory for user processes
> (anonymous, tmpfs, shmem).
I think that's one case where the shared memory scheme breaks, as we
have two kernels in charge of their own tags, and they obviously can't
be synchronised
> What we don't have in the architecture is a memory type which allows
> access to tags but no tag checking. To access the data when the tags
> aren't known, the tag checking would have to be disabled via either a
> prctl() or by setting the PSTATE.TCO bit.
I guess that's point (3) in Steven's taxonomy. It still a bit ugly to
fit in an existing piece of userspace, specially if it wants to use
MTE for its own benefit.
> The kernel accesses the user memory via the linear map using a match-all
> tag 0xf, so no TCO bit toggling. For user, however, we disabled such
> match-all tag and it cannot be enabled at run-time (at least not easily,
> it's cached in the TLB). However, we already have two modes to disable
> tag checking which Qemu could use when migrating data+tags.
I wonder whether we will have to have something kernel side to
dump/reload tags in a way that matches the patterns used by live
migration.
M.
--
Without deviation from the norm, progress is not possible.
WARNING: multiple messages have this Message-ID (diff)
From: Marc Zyngier <maz@kernel.org>
To: Catalin Marinas <catalin.marinas@arm.com>
Cc: Peter Maydell <peter.maydell@linaro.org>,
Juan Quintela <quintela@redhat.com>,
QEMU Developers <qemu-devel@nongnu.org>,
Dave Martin <Dave.Martin@arm.com>,
Richard Henderson <richard.henderson@linaro.org>,
lkml - Kernel Mailing List <linux-kernel@vger.kernel.org>,
Steven Price <steven.price@arm.com>,
arm-mail-list <linux-arm-kernel@lists.infradead.org>,
Haibo Xu <haibo.xu@linaro.org>,
Thomas Gleixner <tglx@linutronix.de>,
Will Deacon <will@kernel.org>,
kvmarm <kvmarm@lists.cs.columbia.edu>,
"Dr. David Alan Gilbert" <dgilbert@redhat.com>
Subject: Re: [PATCH v5 0/2] MTE support for KVM guest
Date: Mon, 07 Dec 2020 19:03:13 +0000 [thread overview]
Message-ID: <874kkx5thq.wl-maz@kernel.org> (raw)
In-Reply-To: <20201207163405.GD1526@gaia>
On Mon, 07 Dec 2020 16:34:05 +0000,
Catalin Marinas <catalin.marinas@arm.com> wrote:
>
> On Mon, Dec 07, 2020 at 04:05:55PM +0000, Marc Zyngier wrote:
> > What I'd really like to see is a description of how shared memory
> > is, in general, supposed to work with MTE. My gut feeling is that
> > it doesn't, and that you need to turn MTE off when sharing memory
> > (either implicitly or explicitly).
>
> The allocation tag (in-memory tag) is a property assigned to a physical
> address range and it can be safely shared between different processes as
> long as they access it via pointers with the same allocation tag (bits
> 59:56). The kernel enables such tagged shared memory for user processes
> (anonymous, tmpfs, shmem).
I think that's one case where the shared memory scheme breaks, as we
have two kernels in charge of their own tags, and they obviously can't
be synchronised
> What we don't have in the architecture is a memory type which allows
> access to tags but no tag checking. To access the data when the tags
> aren't known, the tag checking would have to be disabled via either a
> prctl() or by setting the PSTATE.TCO bit.
I guess that's point (3) in Steven's taxonomy. It still a bit ugly to
fit in an existing piece of userspace, specially if it wants to use
MTE for its own benefit.
> The kernel accesses the user memory via the linear map using a match-all
> tag 0xf, so no TCO bit toggling. For user, however, we disabled such
> match-all tag and it cannot be enabled at run-time (at least not easily,
> it's cached in the TLB). However, we already have two modes to disable
> tag checking which Qemu could use when migrating data+tags.
I wonder whether we will have to have something kernel side to
dump/reload tags in a way that matches the patterns used by live
migration.
M.
--
Without deviation from the norm, progress is not possible.
WARNING: multiple messages have this Message-ID (diff)
From: Marc Zyngier <maz@kernel.org>
To: Catalin Marinas <catalin.marinas@arm.com>
Cc: Juan Quintela <quintela@redhat.com>,
QEMU Developers <qemu-devel@nongnu.org>,
Dave Martin <Dave.Martin@arm.com>,
Richard Henderson <richard.henderson@linaro.org>,
lkml - Kernel Mailing List <linux-kernel@vger.kernel.org>,
Steven Price <steven.price@arm.com>,
arm-mail-list <linux-arm-kernel@lists.infradead.org>,
Thomas Gleixner <tglx@linutronix.de>,
Will Deacon <will@kernel.org>,
kvmarm <kvmarm@lists.cs.columbia.edu>,
"Dr. David Alan Gilbert" <dgilbert@redhat.com>
Subject: Re: [PATCH v5 0/2] MTE support for KVM guest
Date: Mon, 07 Dec 2020 19:03:13 +0000 [thread overview]
Message-ID: <874kkx5thq.wl-maz@kernel.org> (raw)
In-Reply-To: <20201207163405.GD1526@gaia>
On Mon, 07 Dec 2020 16:34:05 +0000,
Catalin Marinas <catalin.marinas@arm.com> wrote:
>
> On Mon, Dec 07, 2020 at 04:05:55PM +0000, Marc Zyngier wrote:
> > What I'd really like to see is a description of how shared memory
> > is, in general, supposed to work with MTE. My gut feeling is that
> > it doesn't, and that you need to turn MTE off when sharing memory
> > (either implicitly or explicitly).
>
> The allocation tag (in-memory tag) is a property assigned to a physical
> address range and it can be safely shared between different processes as
> long as they access it via pointers with the same allocation tag (bits
> 59:56). The kernel enables such tagged shared memory for user processes
> (anonymous, tmpfs, shmem).
I think that's one case where the shared memory scheme breaks, as we
have two kernels in charge of their own tags, and they obviously can't
be synchronised
> What we don't have in the architecture is a memory type which allows
> access to tags but no tag checking. To access the data when the tags
> aren't known, the tag checking would have to be disabled via either a
> prctl() or by setting the PSTATE.TCO bit.
I guess that's point (3) in Steven's taxonomy. It still a bit ugly to
fit in an existing piece of userspace, specially if it wants to use
MTE for its own benefit.
> The kernel accesses the user memory via the linear map using a match-all
> tag 0xf, so no TCO bit toggling. For user, however, we disabled such
> match-all tag and it cannot be enabled at run-time (at least not easily,
> it's cached in the TLB). However, we already have two modes to disable
> tag checking which Qemu could use when migrating data+tags.
I wonder whether we will have to have something kernel side to
dump/reload tags in a way that matches the patterns used by live
migration.
M.
--
Without deviation from the norm, progress is not possible.
_______________________________________________
kvmarm mailing list
kvmarm@lists.cs.columbia.edu
https://lists.cs.columbia.edu/mailman/listinfo/kvmarm
WARNING: multiple messages have this Message-ID (diff)
From: Marc Zyngier <maz@kernel.org>
To: Catalin Marinas <catalin.marinas@arm.com>
Cc: Peter Maydell <peter.maydell@linaro.org>,
Juan Quintela <quintela@redhat.com>,
QEMU Developers <qemu-devel@nongnu.org>,
Dave Martin <Dave.Martin@arm.com>,
Richard Henderson <richard.henderson@linaro.org>,
lkml - Kernel Mailing List <linux-kernel@vger.kernel.org>,
Steven Price <steven.price@arm.com>,
arm-mail-list <linux-arm-kernel@lists.infradead.org>,
Haibo Xu <haibo.xu@linaro.org>,
Thomas Gleixner <tglx@linutronix.de>,
Will Deacon <will@kernel.org>,
kvmarm <kvmarm@lists.cs.columbia.edu>,
"Dr. David Alan Gilbert" <dgilbert@redhat.com>
Subject: Re: [PATCH v5 0/2] MTE support for KVM guest
Date: Mon, 07 Dec 2020 19:03:13 +0000 [thread overview]
Message-ID: <874kkx5thq.wl-maz@kernel.org> (raw)
In-Reply-To: <20201207163405.GD1526@gaia>
On Mon, 07 Dec 2020 16:34:05 +0000,
Catalin Marinas <catalin.marinas@arm.com> wrote:
>
> On Mon, Dec 07, 2020 at 04:05:55PM +0000, Marc Zyngier wrote:
> > What I'd really like to see is a description of how shared memory
> > is, in general, supposed to work with MTE. My gut feeling is that
> > it doesn't, and that you need to turn MTE off when sharing memory
> > (either implicitly or explicitly).
>
> The allocation tag (in-memory tag) is a property assigned to a physical
> address range and it can be safely shared between different processes as
> long as they access it via pointers with the same allocation tag (bits
> 59:56). The kernel enables such tagged shared memory for user processes
> (anonymous, tmpfs, shmem).
I think that's one case where the shared memory scheme breaks, as we
have two kernels in charge of their own tags, and they obviously can't
be synchronised
> What we don't have in the architecture is a memory type which allows
> access to tags but no tag checking. To access the data when the tags
> aren't known, the tag checking would have to be disabled via either a
> prctl() or by setting the PSTATE.TCO bit.
I guess that's point (3) in Steven's taxonomy. It still a bit ugly to
fit in an existing piece of userspace, specially if it wants to use
MTE for its own benefit.
> The kernel accesses the user memory via the linear map using a match-all
> tag 0xf, so no TCO bit toggling. For user, however, we disabled such
> match-all tag and it cannot be enabled at run-time (at least not easily,
> it's cached in the TLB). However, we already have two modes to disable
> tag checking which Qemu could use when migrating data+tags.
I wonder whether we will have to have something kernel side to
dump/reload tags in a way that matches the patterns used by live
migration.
M.
--
Without deviation from the norm, progress is not possible.
_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel
next prev parent reply other threads:[~2020-12-07 19:04 UTC|newest]
Thread overview: 152+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-11-19 15:38 [PATCH v5 0/2] MTE support for KVM guest Steven Price
2020-11-19 15:38 ` Steven Price
2020-11-19 15:38 ` Steven Price
2020-11-19 15:38 ` Steven Price
2020-11-19 15:39 ` [PATCH v5 1/2] arm64: kvm: Save/restore MTE registers Steven Price
2020-11-19 15:39 ` Steven Price
2020-11-19 15:39 ` Steven Price
2020-11-19 15:39 ` Steven Price
2020-11-19 15:39 ` [PATCH v5 2/2] arm64: kvm: Introduce MTE VCPU feature Steven Price
2020-11-19 15:39 ` Steven Price
2020-11-19 15:39 ` Steven Price
2020-11-19 15:39 ` Steven Price
2020-11-19 15:45 ` [PATCH v5 0/2] MTE support for KVM guest Peter Maydell
2020-11-19 15:45 ` Peter Maydell
2020-11-19 15:45 ` Peter Maydell
2020-11-19 15:45 ` Peter Maydell
2020-11-19 15:57 ` Steven Price
2020-11-19 15:57 ` Steven Price
2020-11-19 15:57 ` Steven Price
2020-11-19 15:57 ` Steven Price
2020-11-19 16:39 ` Peter Maydell
2020-11-19 16:39 ` Peter Maydell
2020-11-19 16:39 ` Peter Maydell
2020-11-19 16:39 ` Peter Maydell
2020-11-19 18:42 ` Andrew Jones
2020-11-19 18:42 ` Andrew Jones
2020-11-19 18:42 ` Andrew Jones
2020-11-19 18:42 ` Andrew Jones
2020-11-19 19:11 ` Marc Zyngier
2020-11-19 19:11 ` Marc Zyngier
2020-11-19 19:11 ` Marc Zyngier
2020-11-19 19:11 ` Marc Zyngier
2020-11-20 9:50 ` Steven Price
2020-11-20 9:50 ` Steven Price
2020-11-20 9:50 ` Steven Price
2020-11-20 9:50 ` Steven Price
2020-11-20 9:56 ` Marc Zyngier
2020-11-20 9:56 ` Marc Zyngier
2020-11-20 9:56 ` Marc Zyngier
2020-11-20 9:56 ` Marc Zyngier
2020-11-20 9:58 ` Steven Price
2020-11-20 9:58 ` Steven Price
2020-11-20 9:58 ` Steven Price
2020-11-20 9:58 ` Steven Price
2020-12-04 8:25 ` Haibo Xu
2020-12-04 8:25 ` Haibo Xu
2020-12-04 8:25 ` Haibo Xu
2020-12-04 8:25 ` Haibo Xu
2020-12-07 14:48 ` Steven Price
2020-12-07 14:48 ` Steven Price
2020-12-07 14:48 ` Steven Price
2020-12-07 14:48 ` Steven Price
2020-12-07 15:27 ` Peter Maydell
2020-12-07 15:27 ` Peter Maydell
2020-12-07 15:27 ` Peter Maydell
2020-12-07 15:27 ` Peter Maydell
2020-12-07 15:45 ` Steven Price
2020-12-07 15:45 ` Steven Price
2020-12-07 15:45 ` Steven Price
2020-12-07 15:45 ` Steven Price
2020-12-07 16:05 ` Marc Zyngier
2020-12-07 16:05 ` Marc Zyngier
2020-12-07 16:05 ` Marc Zyngier
2020-12-07 16:05 ` Marc Zyngier
2020-12-07 16:34 ` Catalin Marinas
2020-12-07 16:34 ` Catalin Marinas
2020-12-07 16:34 ` Catalin Marinas
2020-12-07 16:34 ` Catalin Marinas
2020-12-07 19:03 ` Marc Zyngier [this message]
2020-12-07 19:03 ` Marc Zyngier
2020-12-07 19:03 ` Marc Zyngier
2020-12-07 19:03 ` Marc Zyngier
2020-12-08 17:21 ` Catalin Marinas
2020-12-08 17:21 ` Catalin Marinas
2020-12-08 17:21 ` Catalin Marinas
2020-12-08 17:21 ` Catalin Marinas
2020-12-08 18:21 ` Marc Zyngier
2020-12-08 18:21 ` Marc Zyngier
2020-12-08 18:21 ` Marc Zyngier
2020-12-08 18:21 ` Marc Zyngier
2020-12-09 12:44 ` Catalin Marinas
2020-12-09 12:44 ` Catalin Marinas
2020-12-09 12:44 ` Catalin Marinas
2020-12-09 12:44 ` Catalin Marinas
2020-12-09 13:25 ` Marc Zyngier
2020-12-09 13:25 ` Marc Zyngier
2020-12-09 13:25 ` Marc Zyngier
2020-12-09 13:25 ` Marc Zyngier
2020-12-09 15:27 ` Catalin Marinas
2020-12-09 15:27 ` Catalin Marinas
2020-12-09 15:27 ` Catalin Marinas
2020-12-09 15:27 ` Catalin Marinas
2020-12-09 18:27 ` Richard Henderson
2020-12-09 18:27 ` Richard Henderson
2020-12-09 18:27 ` Richard Henderson
2020-12-09 18:27 ` Richard Henderson
2020-12-09 18:39 ` Catalin Marinas
2020-12-09 18:39 ` Catalin Marinas
2020-12-09 18:39 ` Catalin Marinas
2020-12-09 18:39 ` Catalin Marinas
2020-12-09 20:13 ` Richard Henderson
2020-12-09 20:13 ` Richard Henderson
2020-12-09 20:13 ` Richard Henderson
2020-12-09 20:13 ` Richard Henderson
2020-12-09 20:20 ` Peter Maydell
2020-12-09 20:20 ` Peter Maydell
2020-12-09 20:20 ` Peter Maydell
2020-12-09 20:20 ` Peter Maydell
2020-12-07 16:44 ` Dr. David Alan Gilbert
2020-12-07 16:44 ` Dr. David Alan Gilbert
2020-12-07 16:44 ` Dr. David Alan Gilbert
2020-12-07 16:44 ` Dr. David Alan Gilbert
2020-12-07 17:10 ` Peter Maydell
2020-12-07 17:10 ` Peter Maydell
2020-12-07 17:10 ` Peter Maydell
2020-12-07 17:10 ` Peter Maydell
2020-12-07 17:44 ` Dr. David Alan Gilbert
2020-12-07 17:44 ` Dr. David Alan Gilbert
2020-12-07 17:44 ` Dr. David Alan Gilbert
2020-12-07 17:44 ` Dr. David Alan Gilbert
2020-12-08 10:05 ` Haibo Xu
2020-12-08 10:05 ` Haibo Xu
2020-12-08 10:05 ` Haibo Xu
2020-12-08 10:05 ` Haibo Xu
2020-12-08 9:51 ` Haibo Xu
2020-12-08 9:51 ` Haibo Xu
2020-12-08 9:51 ` Haibo Xu
2020-12-08 9:51 ` Haibo Xu
2020-12-08 10:01 ` Marc Zyngier
2020-12-08 10:01 ` Marc Zyngier
2020-12-08 10:01 ` Marc Zyngier
2020-12-08 10:01 ` Marc Zyngier
2020-12-08 10:10 ` Haibo Xu
2020-12-08 10:10 ` Haibo Xu
2020-12-08 10:10 ` Haibo Xu
2020-12-08 10:10 ` Haibo Xu
2020-12-16 7:31 ` Haibo Xu
2020-12-16 7:31 ` Haibo Xu
2020-12-16 7:31 ` Haibo Xu
2020-12-16 7:31 ` Haibo Xu
2020-12-16 10:22 ` Steven Price
2020-12-16 10:22 ` Steven Price
2020-12-16 10:22 ` Steven Price
2020-12-16 10:22 ` Steven Price
2020-12-17 1:47 ` Haibo Xu
2020-12-17 1:47 ` Haibo Xu
2020-12-17 1:47 ` Haibo Xu
2020-12-17 1:47 ` Haibo Xu
2020-11-23 12:16 ` Dr. David Alan Gilbert
2020-11-23 12:16 ` Dr. David Alan Gilbert
2020-11-23 12:16 ` Dr. David Alan Gilbert
2020-11-23 12:16 ` Dr. David Alan Gilbert
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=874kkx5thq.wl-maz@kernel.org \
--to=maz@kernel.org \
--cc=Dave.Martin@arm.com \
--cc=catalin.marinas@arm.com \
--cc=dgilbert@redhat.com \
--cc=haibo.xu@linaro.org \
--cc=kvmarm@lists.cs.columbia.edu \
--cc=linux-arm-kernel@lists.infradead.org \
--cc=linux-kernel@vger.kernel.org \
--cc=peter.maydell@linaro.org \
--cc=qemu-devel@nongnu.org \
--cc=quintela@redhat.com \
--cc=richard.henderson@linaro.org \
--cc=steven.price@arm.com \
--cc=tglx@linutronix.de \
--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 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.