linux-mm.kvack.org archive mirror
 help / color / mirror / Atom feed
From: Szabolcs Nagy <szabolcs.nagy@arm.com>
To: Will Deacon <will@kernel.org>
Cc: Patrick Daly <pdaly@codeaurora.org>,
	Catalin Marinas <catalin.marinas@arm.com>,
	linux-arch@vger.kernel.org,
	Vladimir Murzin <vladimir.murzin@arm.com>,
	Andrey Konovalov <andreyknvl@google.com>,
	Kevin Brodsky <kevin.brodsky@arm.com>,
	Peter Collingbourne <pcc@google.com>,
	linux-mm@kvack.org, Vincenzo Frascino <vincenzo.frascino@arm.com>,
	Dave P Martin <Dave.Martin@arm.com>,
	linux-arm-kernel@lists.infradead.org, nd@arm.com
Subject: Re: [PATCH v4 24/26] arm64: mte: Introduce early param to disable MTE support
Date: Wed, 27 May 2020 11:37:42 +0100	[thread overview]
Message-ID: <20200527103741.GB24512@arm.com> (raw)
In-Reply-To: <20200527095504.GB11111@willie-the-truck>

The 05/27/2020 10:55, Will Deacon wrote:
> On Tue, May 26, 2020 at 07:11:53PM -0700, Patrick Daly wrote:
> > On Fri, May 22, 2020 at 11:37:15AM +0100, Catalin Marinas wrote:
> > > The actual question here is what the on/off behaviour is needed for. We
> > > can figure out the best mechanism for this once we know what we want to
> > > achieve. My wild guess above was performance analysis but that can be
> > > toggled by either kernel boot parameter or run-time sysctl (or just the
> > > Kconfig option).
> > > 
> > > If it is about forcing user space not to use MTE, we may look into some
> > > other sysctl controls (we already have one for the tagged address ABI).
> > 
> > We want to allow the end user to be able to easily "opt out" of MTE in favour
> > of better power, perf and battery life.
> 
> Who is "the end user" in this case?
> 
> If MTE is bad enough for power, performance and battery life that we need a
> kill switch, then perhaps we shouldn't enable it by default and the few
> people that want to use it can build a kernel with it enabled. However, then
> I don't really see what MTE buys you over the existing KASAN implementations.
> 
> I thought the general idea was that you could run in the (cheap) "async"
> mode, and then re-run in the more expensive "sync" mode to further diagnose
> any failures. That model seems to work well with these patches, since
> reporting is disabled by default. Are you saying that there is a
> significant penalty incurred even when reporting is not enabled?
> 
> Anyway, we don't offer global runtime/cmdline switches for the vast majority
> of other architectural features -- instead, we choose a sensible default,
> and I think we should do the same here.

i would not expect mte overhead if userspace processes
don't map anything with PROT_MTE and don't enable tag
checking with prctl. (i.e. userspace runtimes can "opt
out" of mte for better power, perf and battery)

is that not the case?


  reply	other threads:[~2020-05-27 10:38 UTC|newest]

Thread overview: 58+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-05-15 17:15 [PATCH v4 00/26] arm64: Memory Tagging Extension user-space support Catalin Marinas
2020-05-15 17:15 ` [PATCH v4 01/26] arm64: mte: system register definitions Catalin Marinas
2020-05-15 17:15 ` [PATCH v4 02/26] arm64: mte: CPU feature detection and initial sysreg configuration Catalin Marinas
2020-05-15 17:15 ` [PATCH v4 03/26] arm64: mte: Use Normal Tagged attributes for the linear map Catalin Marinas
2020-05-15 17:15 ` [PATCH v4 04/26] arm64: mte: Add specific SIGSEGV codes Catalin Marinas
2020-05-15 17:15 ` [PATCH v4 05/26] arm64: mte: Handle synchronous and asynchronous tag check faults Catalin Marinas
2020-05-15 17:15 ` [PATCH v4 06/26] mm: Add PG_ARCH_2 page flag Catalin Marinas
2020-05-15 17:15 ` [PATCH v4 07/26] arm64: mte: Clear the tags when a page is mapped in user-space with PROT_MTE Catalin Marinas
2020-05-15 17:15 ` [PATCH v4 08/26] arm64: mte: Tags-aware copy_page() implementation Catalin Marinas
2020-05-15 17:15 ` [PATCH v4 09/26] arm64: mte: Tags-aware aware memcmp_pages() implementation Catalin Marinas
2020-05-15 17:15 ` [PATCH v4 10/26] mm: Introduce arch_calc_vm_flag_bits() Catalin Marinas
2020-05-15 17:15 ` [PATCH v4 11/26] arm64: mte: Add PROT_MTE support to mmap() and mprotect() Catalin Marinas
2020-05-27 18:57   ` Peter Collingbourne
2020-05-28  9:14     ` Catalin Marinas
2020-05-28 11:05       ` Szabolcs Nagy
2020-05-28 16:34         ` Catalin Marinas
2020-05-28 18:35           ` Evgenii Stepanov
2020-05-29 11:19             ` Catalin Marinas
2020-06-01  8:55           ` Dave Martin
2020-06-01 14:45             ` Catalin Marinas
2020-06-01 15:04               ` Dave Martin
2020-05-15 17:15 ` [PATCH v4 12/26] mm: Introduce arch_validate_flags() Catalin Marinas
2020-05-15 17:15 ` [PATCH v4 13/26] arm64: mte: Validate the PROT_MTE request via arch_validate_flags() Catalin Marinas
2020-05-15 17:16 ` [PATCH v4 14/26] mm: Allow arm64 mmap(PROT_MTE) on RAM-based files Catalin Marinas
2020-05-15 17:16 ` [PATCH v4 15/26] arm64: mte: Allow user control of the tag check mode via prctl() Catalin Marinas
2020-05-27  7:46   ` Will Deacon
2020-05-27  8:32     ` Dave Martin
2020-05-27  8:48       ` Will Deacon
2020-05-27 11:16       ` Catalin Marinas
2020-05-15 17:16 ` [PATCH v4 16/26] arm64: mte: Allow user control of the generated random tags " Catalin Marinas
2020-05-15 17:16 ` [PATCH v4 17/26] arm64: mte: Restore the GCR_EL1 register after a suspend Catalin Marinas
2020-05-15 17:16 ` [PATCH v4 18/26] arm64: mte: Add PTRACE_{PEEK,POKE}MTETAGS support Catalin Marinas
2020-05-29 21:25   ` Luis Machado
2020-06-01 12:07     ` Catalin Marinas
2020-06-01 15:17       ` Luis Machado
2020-06-01 16:33         ` Catalin Marinas
2020-05-15 17:16 ` [PATCH v4 19/26] fs: Handle intra-page faults in copy_mount_options() Catalin Marinas
2020-05-15 17:16 ` [PATCH v4 20/26] mm: Add arch hooks for saving/restoring tags Catalin Marinas
2020-05-15 17:16 ` [PATCH v4 21/26] arm64: mte: Enable swap of tagged pages Catalin Marinas
2020-05-15 17:16 ` [PATCH v4 22/26] arm64: mte: Save tags when hibernating Catalin Marinas
2020-05-15 17:16 ` [PATCH v4 23/26] arm64: mte: Check the DT memory nodes for MTE support Catalin Marinas
2020-05-15 17:16 ` [PATCH v4 24/26] arm64: mte: Introduce early param to disable " Catalin Marinas
2020-05-18 11:26   ` Vladimir Murzin
2020-05-18 11:31     ` Will Deacon
2020-05-18 17:20       ` Catalin Marinas
2020-05-22  5:57         ` Patrick Daly
2020-05-22 10:37           ` Catalin Marinas
2020-05-27  2:11             ` Patrick Daly
2020-05-27  9:55               ` Will Deacon
2020-05-27 10:37                 ` Szabolcs Nagy [this message]
2020-05-27 11:12                 ` Catalin Marinas
2020-05-19 16:14     ` Catalin Marinas
2021-01-21 19:37   ` Andrey Konovalov
2021-01-22  2:03     ` Andrey Konovalov
2021-01-22 14:41     ` Catalin Marinas
2021-01-22 17:28       ` Andrey Konovalov
2020-05-15 17:16 ` [PATCH v4 25/26] arm64: mte: Kconfig entry Catalin Marinas
2020-05-15 17:16 ` [PATCH v4 26/26] arm64: mte: Add Memory Tagging Extension documentation Catalin Marinas

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=20200527103741.GB24512@arm.com \
    --to=szabolcs.nagy@arm.com \
    --cc=Dave.Martin@arm.com \
    --cc=andreyknvl@google.com \
    --cc=catalin.marinas@arm.com \
    --cc=kevin.brodsky@arm.com \
    --cc=linux-arch@vger.kernel.org \
    --cc=linux-arm-kernel@lists.infradead.org \
    --cc=linux-mm@kvack.org \
    --cc=nd@arm.com \
    --cc=pcc@google.com \
    --cc=pdaly@codeaurora.org \
    --cc=vincenzo.frascino@arm.com \
    --cc=vladimir.murzin@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