From: Andy Lutomirski <luto@kernel.org>
To: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>,
Russell King <linux@armlinux.org.uk>
Cc: Andy Lutomirski <luto@kernel.org>, x86 <x86@kernel.org>,
linux-kernel <linux-kernel@vger.kernel.org>,
Nicholas Piggin <npiggin@gmail.com>,
Arnd Bergmann <arnd@arndb.de>,
Michael Ellerman <mpe@ellerman.id.au>,
Benjamin Herrenschmidt <benh@kernel.crashing.org>,
Paul Mackerras <paulus@samba.org>,
linuxppc-dev <linuxppc-dev@lists.ozlabs.org>,
Catalin Marinas <catalin.marinas@arm.com>,
Will Deacon <will@kernel.org>,
linux-arm-kernel <linux-arm-kernel@lists.infradead.org>,
stable <stable@vger.kernel.org>
Subject: Re: [RFC please help] membarrier: Rewrite sync_core_before_usermode()
Date: Sun, 27 Dec 2020 13:36:13 -0800 [thread overview]
Message-ID: <CALCETrVdcn2r2Jvd1=-bM=FQ8KbX4aH-v4ytdojL7r7Nb6k8YQ@mail.gmail.com> (raw)
In-Reply-To: <1836294649.3345.1609100294833.JavaMail.zimbra@efficios.com>
On Sun, Dec 27, 2020 at 12:18 PM Mathieu Desnoyers
<mathieu.desnoyers@efficios.com> wrote:
>
> ----- On Dec 27, 2020, at 1:28 PM, Andy Lutomirski luto@kernel.org wrote:
>
> >
> > I admit that I'm rather surprised that the code worked at all on arm64,
> > and I'm suspicious that it has never been very well tested. My apologies
> > for not reviewing this more carefully in the first place.
>
> Please refer to Documentation/features/sched/membarrier-sync-core/arch-support.txt
>
> It clearly states that only arm, arm64, powerpc and x86 support the membarrier
> sync core feature as of now:
Sigh, I missed arm (32). Russell or ARM folks, what's the right
incantation to make the CPU notice instruction changes initiated by
other cores on 32-bit ARM?
>
>
> # Architecture requirements
> #
> # * arm/arm64/powerpc
> #
> # Rely on implicit context synchronization as a result of exception return
> # when returning from IPI handler, and when returning to user-space.
> #
> # * x86
> #
> # x86-32 uses IRET as return from interrupt, which takes care of the IPI.
> # However, it uses both IRET and SYSEXIT to go back to user-space. The IRET
> # instruction is core serializing, but not SYSEXIT.
> #
> # x86-64 uses IRET as return from interrupt, which takes care of the IPI.
> # However, it can return to user-space through either SYSRETL (compat code),
> # SYSRETQ, or IRET.
> #
> # Given that neither SYSRET{L,Q}, nor SYSEXIT, are core serializing, we rely
> # instead on write_cr3() performed by switch_mm() to provide core serialization
> # after changing the current mm, and deal with the special case of kthread ->
> # uthread (temporarily keeping current mm into active_mm) by issuing a
> # sync_core_before_usermode() in that specific case.
>
I need to update that document as part of my series.
> This is based on direct feedback from the architecture maintainers.
>
> You seem to have noticed odd cases on arm64 where this guarantee does not
> match reality. Where exactly can we find this in the code, and which part
> of the architecture manual can you point us to which supports your concern ?
>
> Based on the notes I have, use of `eret` on aarch64 guarantees a context synchronizing
> instruction when returning to user-space.
Based on my reading of the manual, ERET on ARM doesn't synchronize
anything at all. I can't find any evidence that it synchronizes data
or instructions, and I've seen reports that the CPU will happily
speculate right past it.
--Andy
next prev parent reply other threads:[~2020-12-27 21:37 UTC|newest]
Thread overview: 34+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-12-27 18:28 [RFC please help] membarrier: Rewrite sync_core_before_usermode() Andy Lutomirski
2020-12-27 20:18 ` Mathieu Desnoyers
2020-12-27 21:36 ` Andy Lutomirski [this message]
2020-12-28 10:25 ` Russell King - ARM Linux admin
2020-12-28 17:14 ` Andy Lutomirski
2020-12-28 17:23 ` Russell King - ARM Linux admin
2020-12-28 18:10 ` Andy Lutomirski
2020-12-28 18:29 ` Jann Horn
2020-12-28 18:50 ` Andy Lutomirski
2020-12-28 19:08 ` Russell King - ARM Linux admin
2020-12-28 19:44 ` Andy Lutomirski
2020-12-28 20:24 ` Russell King - ARM Linux admin
2020-12-28 20:40 ` Mathieu Desnoyers
2020-12-28 20:32 ` Mathieu Desnoyers
2020-12-28 21:06 ` Andy Lutomirski
2020-12-28 21:26 ` Mathieu Desnoyers
2020-12-29 0:36 ` Nicholas Piggin
2020-12-29 0:56 ` Andy Lutomirski
2020-12-29 3:09 ` Nicholas Piggin
2020-12-29 10:44 ` Russell King - ARM Linux admin
2020-12-30 2:33 ` Nicholas Piggin
2020-12-30 10:00 ` Russell King - ARM Linux admin
2020-12-30 10:58 ` Russell King - ARM Linux admin
2020-12-30 11:57 ` Nicholas Piggin
2020-12-28 21:09 ` Mathieu Desnoyers
2020-12-29 0:30 ` Andy Lutomirski
2020-12-29 0:11 ` Nicholas Piggin
2020-12-29 0:36 ` Andy Lutomirski
2020-12-29 3:31 ` Nicholas Piggin
2021-01-01 18:33 ` David Laight
2021-01-05 13:26 ` Will Deacon
2021-01-05 16:20 ` Andy Lutomirski
2021-01-05 16:37 ` Peter Zijlstra
2021-01-05 22:41 ` 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='CALCETrVdcn2r2Jvd1=-bM=FQ8KbX4aH-v4ytdojL7r7Nb6k8YQ@mail.gmail.com' \
--to=luto@kernel.org \
--cc=arnd@arndb.de \
--cc=benh@kernel.crashing.org \
--cc=catalin.marinas@arm.com \
--cc=linux-arm-kernel@lists.infradead.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux@armlinux.org.uk \
--cc=linuxppc-dev@lists.ozlabs.org \
--cc=mathieu.desnoyers@efficios.com \
--cc=mpe@ellerman.id.au \
--cc=npiggin@gmail.com \
--cc=paulus@samba.org \
--cc=stable@vger.kernel.org \
--cc=will@kernel.org \
--cc=x86@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).