From: James Morse <james.morse@arm.com>
To: linux-arm-kernel@lists.infradead.org, linux-pm@vger.kernel.org
Cc: "Rafael J. Wysocki" <rjw@rjwysocki.net>,
Pavel Machek <pavel@ucw.cz>, Will Deacon <will.deacon@arm.com>,
Sudeep Holla <sudeep.holla@arm.com>,
Kevin Kang <kkang@intrinsyc.com>,
Geoff Levand <geoff@infradead.org>,
Catalin Marinas <catalin.marinas@arm.com>,
Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>,
Mark Rutland <mark.rutland@arm.com>,
AKASHI Takahiro <takahiro.akashi@linaro.org>,
wangfei <w.f@huawei.com>, Marc Zyngier <marc.zyngier@arm.com>
Subject: Re: [PATCH v2 10/11] PM / Hibernate: clean cached pages on architectures that require it
Date: Thu, 26 Nov 2015 14:23:37 +0000 [thread overview]
Message-ID: <565715E9.4080805@arm.com> (raw)
In-Reply-To: <1445966960-31724-11-git-send-email-james.morse@arm.com>
On 27/10/15 17:29, James Morse wrote:
> Some architectures require code written to memory as if it were data to be
> 'cleaned' from any data caches so that the processor can fetch them as new
> instructions.
>
> During resume from hibernate, the snapshot code copies some pages directly,
> meaning these architectures do not get a chance to perform their cache
> maintenance. Add a call to flush_icache_range(), which is provided by
> architectures that require it, to perform the maintenance.
>
> This mirrors the kernel's behaviour when loading kernel modules and when
> mapping executable pages to user space.
While trying to benchmark the impact of this patch on 32bit ARM, I've
discovered the fix is in the wrong place! do_copy_page() isn't used on
the resume path for the pages restored 'in place'.
I will produce another version of the series - hopefully later today.
James
WARNING: multiple messages have this Message-ID (diff)
From: james.morse@arm.com (James Morse)
To: linux-arm-kernel@lists.infradead.org
Subject: [PATCH v2 10/11] PM / Hibernate: clean cached pages on architectures that require it
Date: Thu, 26 Nov 2015 14:23:37 +0000 [thread overview]
Message-ID: <565715E9.4080805@arm.com> (raw)
In-Reply-To: <1445966960-31724-11-git-send-email-james.morse@arm.com>
On 27/10/15 17:29, James Morse wrote:
> Some architectures require code written to memory as if it were data to be
> 'cleaned' from any data caches so that the processor can fetch them as new
> instructions.
>
> During resume from hibernate, the snapshot code copies some pages directly,
> meaning these architectures do not get a chance to perform their cache
> maintenance. Add a call to flush_icache_range(), which is provided by
> architectures that require it, to perform the maintenance.
>
> This mirrors the kernel's behaviour when loading kernel modules and when
> mapping executable pages to user space.
While trying to benchmark the impact of this patch on 32bit ARM, I've
discovered the fix is in the wrong place! do_copy_page() isn't used on
the resume path for the pages restored 'in place'.
I will produce another version of the series - hopefully later today.
James
next prev parent reply other threads:[~2015-11-26 14:24 UTC|newest]
Thread overview: 66+ messages / expand[flat|nested] mbox.gz Atom feed top
2015-10-27 17:29 [PATCH v2 00/11] arm64: kernel: Add support for hibernate/suspend-to-disk James Morse
2015-10-27 17:29 ` James Morse
2015-10-27 17:29 ` [PATCH v2 01/11] arm64: kernel: fix tcr_el1.t0sz restore on systems with extended idmap James Morse
2015-10-27 17:29 ` James Morse
2015-10-27 17:29 ` [PATCH v2 02/11] arm64: Fold proc-macros.S into assembler.h James Morse
2015-10-27 17:29 ` James Morse
2015-11-14 21:25 ` Pavel Machek
2015-11-14 21:25 ` Pavel Machek
2015-11-16 18:44 ` Geoff Levand
2015-11-16 18:44 ` Geoff Levand
2015-10-27 17:29 ` [PATCH v2 03/11] arm64: Convert hcalls to use HVC immediate value James Morse
2015-10-27 17:29 ` James Morse
2015-10-27 17:29 ` [PATCH v2 04/11] arm64: Add new hcall HVC_CALL_FUNC James Morse
2015-10-27 17:29 ` James Morse
2015-10-27 17:29 ` [PATCH v2 05/11] arm64: kvm: allows kvm cpu hotplug James Morse
2015-10-27 17:29 ` James Morse
2015-10-27 17:29 ` [PATCH v2 06/11] arm64: kernel: Rework finisher callback out of __cpu_suspend_enter() James Morse
2015-10-27 17:29 ` James Morse
2015-10-27 17:29 ` [PATCH v2 07/11] arm64: Change cpu_resume() to enable mmu early then access sleep_sp by va James Morse
2015-10-27 17:29 ` James Morse
2015-10-27 17:29 ` [PATCH v2 08/11] arm64: kernel: Include _AC definition in page.h James Morse
2015-10-27 17:29 ` James Morse
2015-10-27 17:29 ` [PATCH v2 09/11] arm64: Promote KERNEL_START/KERNEL_END definitions to a header file James Morse
2015-10-27 17:29 ` James Morse
2015-10-27 17:29 ` [PATCH v2 10/11] PM / Hibernate: clean cached pages on architectures that require it James Morse
2015-10-27 17:29 ` James Morse
2015-11-11 11:40 ` Lorenzo Pieralisi
2015-11-11 11:40 ` Lorenzo Pieralisi
2015-11-12 0:48 ` Rafael J. Wysocki
2015-11-12 0:48 ` Rafael J. Wysocki
2015-11-12 11:47 ` Lorenzo Pieralisi
2015-11-12 11:47 ` Lorenzo Pieralisi
2015-11-13 23:38 ` Rafael J. Wysocki
2015-11-13 23:38 ` Rafael J. Wysocki
2015-11-17 12:38 ` Lorenzo Pieralisi
2015-11-17 12:38 ` Lorenzo Pieralisi
2015-11-17 13:13 ` Pavel Machek
2015-11-17 13:13 ` Pavel Machek
2015-11-17 13:43 ` Lorenzo Pieralisi
2015-11-17 13:43 ` Lorenzo Pieralisi
2015-11-12 2:53 ` Chen, Yu C
2015-11-12 2:53 ` Chen, Yu C
2015-11-12 11:52 ` Lorenzo Pieralisi
2015-11-12 11:52 ` Lorenzo Pieralisi
2015-11-14 20:26 ` Pavel Machek
2015-11-14 20:26 ` Pavel Machek
2015-11-16 12:27 ` James Morse
2015-11-16 12:27 ` James Morse
2015-11-16 12:36 ` Pavel Machek
2015-11-16 12:36 ` Pavel Machek
2015-11-26 14:23 ` James Morse [this message]
2015-11-26 14:23 ` James Morse
2015-10-27 17:29 ` [PATCH v2 11/11] arm64: kernel: Add support for hibernate/suspend-to-disk James Morse
2015-10-27 17:29 ` James Morse
2015-11-14 21:34 ` Pavel Machek
2015-11-14 21:34 ` Pavel Machek
2015-11-16 12:29 ` James Morse
2015-11-16 12:29 ` James Morse
2015-11-16 12:41 ` Pavel Machek
2015-11-16 12:41 ` Pavel Machek
2015-11-16 14:01 ` James Morse
2015-11-16 14:01 ` James Morse
2015-11-16 14:23 ` Mark Rutland
2015-11-16 14:23 ` Mark Rutland
2015-11-16 18:01 ` Pavel Machek
2015-11-16 18:01 ` Pavel Machek
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=565715E9.4080805@arm.com \
--to=james.morse@arm.com \
--cc=catalin.marinas@arm.com \
--cc=geoff@infradead.org \
--cc=kkang@intrinsyc.com \
--cc=linux-arm-kernel@lists.infradead.org \
--cc=linux-pm@vger.kernel.org \
--cc=lorenzo.pieralisi@arm.com \
--cc=marc.zyngier@arm.com \
--cc=mark.rutland@arm.com \
--cc=pavel@ucw.cz \
--cc=rjw@rjwysocki.net \
--cc=sudeep.holla@arm.com \
--cc=takahiro.akashi@linaro.org \
--cc=w.f@huawei.com \
--cc=will.deacon@arm.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 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.