From: Will Deacon <will@kernel.org>
To: "Mikołaj Lenczewski" <miko.lenczewski@arm.com>
Cc: ryan.roberts@arm.com, catalin.marinas@arm.com, corbet@lwn.net,
maz@kernel.org, oliver.upton@linux.dev, joey.gouly@arm.com,
suzuki.poulose@arm.com, yuzenghui@huawei.com,
linux-arm-kernel@lists.infradead.org, linux-doc@vger.kernel.org,
linux-kernel@vger.kernel.org, kvmarm@lists.linux.dev
Subject: Re: [RESEND RFC PATCH v1 5/5] arm64/mm: Elide tlbi in contpte_convert() under BBML2
Date: Thu, 19 Dec 2024 16:37:37 +0000 [thread overview]
Message-ID: <20241219163736.GG24724@willie-the-truck> (raw)
In-Reply-To: <20241211160218.41404-6-miko.lenczewski@arm.com>
On Wed, Dec 11, 2024 at 04:01:41PM +0000, Mikołaj Lenczewski wrote:
> If we support BBM level 2, we can potentially avoid an intermediate
> TLB invalidation, as hardware is capable of managing the TLB itself
> in this situation. Hardware will either silently clear out the
> offending entry, or will take a TLB Conflict Abort Exception.
>
> Note that such aborts should not occur on Arm hardware and indeed
> were not seen on any of the benchmarked systems.
>
> Eliding the invalidation results in a 12% improvement on a
> microbenchmark which targeted the worst case of contpte_convert(), which
> represents an 80% reduction in the overhead of contpte_convert().
Can you run something more indicative of real world performance than a
targetted microbenchmark please?
Will
prev parent reply other threads:[~2024-12-19 16:39 UTC|newest]
Thread overview: 27+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-12-11 16:01 [RESEND RFC PATCH v1 0/5] Initial BBML2 support for contpte_convert() Mikołaj Lenczewski
2024-12-11 16:01 ` [RESEND RFC PATCH v1 1/5] arm64: Add TLB Conflict Abort Exception handler to KVM Mikołaj Lenczewski
2024-12-11 17:40 ` Marc Zyngier
2024-12-12 9:23 ` Ryan Roberts
2024-12-12 9:57 ` Marc Zyngier
2024-12-12 10:37 ` Ryan Roberts
2024-12-13 16:24 ` Mikołaj Lenczewski
2024-12-11 16:01 ` [RESEND RFC PATCH v1 2/5] arm64: Add BBM Level 2 cpu feature Mikołaj Lenczewski
2024-12-12 8:25 ` Marc Zyngier
2024-12-12 10:55 ` Ryan Roberts
2024-12-12 14:26 ` Marc Zyngier
2024-12-12 15:05 ` Ryan Roberts
2024-12-12 15:48 ` Marc Zyngier
2024-12-12 16:03 ` Ryan Roberts
2024-12-19 16:45 ` Will Deacon
2025-01-02 12:07 ` Jonathan Cameron
2025-01-02 12:30 ` Marc Zyngier
2025-01-03 15:35 ` Will Deacon
2025-01-03 16:00 ` Ryan Roberts
2025-01-03 18:18 ` Jonathan Cameron
2024-12-13 16:53 ` Mikołaj Lenczewski
2024-12-13 16:49 ` Mikołaj Lenczewski
2024-12-11 16:01 ` [RESEND RFC PATCH v1 3/5] arm64: Add errata and workarounds for systems with broken BBML2 Mikołaj Lenczewski
2024-12-11 16:01 ` [RESEND RFC PATCH v1 4/5] arm64/mm: Delay tlbi in contpte_convert() under BBML2 Mikołaj Lenczewski
2024-12-19 16:36 ` Will Deacon
2024-12-11 16:01 ` [RESEND RFC PATCH v1 5/5] arm64/mm: Elide " Mikołaj Lenczewski
2024-12-19 16:37 ` Will Deacon [this message]
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=20241219163736.GG24724@willie-the-truck \
--to=will@kernel.org \
--cc=catalin.marinas@arm.com \
--cc=corbet@lwn.net \
--cc=joey.gouly@arm.com \
--cc=kvmarm@lists.linux.dev \
--cc=linux-arm-kernel@lists.infradead.org \
--cc=linux-doc@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=maz@kernel.org \
--cc=miko.lenczewski@arm.com \
--cc=oliver.upton@linux.dev \
--cc=ryan.roberts@arm.com \
--cc=suzuki.poulose@arm.com \
--cc=yuzenghui@huawei.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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox