From: "Chang S. Bae" <chang.seok.bae@intel.com>
To: linux-kernel@vger.kernel.org, x86@kernel.org, linux-pm@vger.kernel.org
Cc: tglx@linutronix.de, dave.hansen@linux.intel.com,
peterz@infradead.org, bp@alien8.de, rafael@kernel.org,
ravi.v.shankar@intel.com, chang.seok.bae@intel.com
Subject: [PATCH v2 0/2] x86/fpu: Make AMX state ready for CPU idle
Date: Wed, 9 Mar 2022 14:34:29 -0800 [thread overview]
Message-ID: <20220309223431.26560-1-chang.seok.bae@intel.com> (raw)
AMX state is a large state (at least 8KB or more). Entering CPU idle with
this non-initialized large state may result in shallow states while a
deeper low-power state is available.
We can confirm this behavior is implementation-specific. Section 3.3 in [1]
will be updated to clarify this. Sorry for the delay in this conclusion
and the update here.
Changes from v1 [2]:
* Drop the code to call TILERELEASE from arch_cpu_idle_enter(). Instead,
do it from the intel-idle driver, as the behavior is *not* architectural.
* Simplify the driver code change (Rui).
* Improve the dynamic state flag check in the helper function.
* Drop the new C-state table as it is done by another patchset [3].
* Drop the opcode map changes as tip's x86/misc [4] has merged it already.
With the last two changes, the series depends on these:
* The C-state table update for Sapphire Rapids in linux-pm [3].
* The update of the x86 opcode map in the tip's branch [4].
The series on top of the above is available here:
git://github.com/intel/amx-linux.git tilerelease
Thanks,
Chang
[1]: Intel Architecture Instruction Set Extension Programming Reference
May 2021, https://software.intel.com/content/dam/develop/external/us/en/documents-tps/architecture-instruction-set-extensions-programming-reference.pdf
[2]: https://lore.kernel.org/lkml/20211104225226.5031-1-chang.seok.bae@intel.com/
[3]: https://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm.git/commit/?h=linux-next&id=9edf3c0ffef0ec1bed8300315852b5c6a0997130
[4]: https://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git/commit/?h=x86/misc&id=9dd94df75b30eca03ed2151dd5bbc152a6f19abf
Chang S. Bae (2):
x86/fpu: Add a helper to prepare AMX state for low-power CPU idle
intel_idle: Add a new flag to initialize the AMX state
arch/x86/include/asm/fpu/api.h | 2 ++
arch/x86/include/asm/special_insns.h | 9 +++++++++
arch/x86/kernel/fpu/core.c | 15 +++++++++++++++
drivers/idle/intel_idle.c | 18 ++++++++++++++++--
4 files changed, 42 insertions(+), 2 deletions(-)
--
2.17.1
next reply other threads:[~2022-03-09 22:42 UTC|newest]
Thread overview: 12+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-03-09 22:34 Chang S. Bae [this message]
2022-03-09 22:34 ` [PATCH v2 1/2] x86/fpu: Add a helper to prepare AMX state for low-power CPU idle Chang S. Bae
2022-03-09 22:46 ` Dave Hansen
2022-03-09 23:12 ` Chang S. Bae
2022-03-10 0:24 ` Dave Hansen
2022-03-10 21:00 ` Chang S. Bae
2022-03-22 7:05 ` Chang S. Bae
2022-03-09 22:34 ` [PATCH v2 2/2] intel_idle: Add a new flag to initialize the AMX state Chang S. Bae
2022-03-10 18:34 ` Rafael J. Wysocki
2022-03-10 18:50 ` Chang S. Bae
2022-03-11 7:33 ` Artem Bityutskiy
2022-03-22 7:06 ` Chang S. Bae
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=20220309223431.26560-1-chang.seok.bae@intel.com \
--to=chang.seok.bae@intel.com \
--cc=bp@alien8.de \
--cc=dave.hansen@linux.intel.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-pm@vger.kernel.org \
--cc=peterz@infradead.org \
--cc=rafael@kernel.org \
--cc=ravi.v.shankar@intel.com \
--cc=tglx@linutronix.de \
--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).