All of lore.kernel.org
 help / color / mirror / Atom feed
From: Pavel Tatashin <pasha.tatashin@soleen.com>
To: pasha.tatashin@soleen.com, jmorris@namei.org, sashal@kernel.org,
	ebiederm@xmission.com, kexec@lists.infradead.org,
	linux-kernel@vger.kernel.org, corbet@lwn.net,
	catalin.marinas@arm.com, will@kernel.org,
	linux-arm-kernel@lists.infradead.org, marc.zyngier@arm.com,
	james.morse@arm.com, vladimir.murzin@arm.com,
	matthias.bgg@gmail.com, bhsharma@redhat.com, linux-mm@kvack.org
Subject: [PATCH v2 00/14] arm64: MMU enabled kexec relocation
Date: Fri, 16 Aug 2019 22:46:15 -0400	[thread overview]
Message-ID: <20190817024629.26611-1-pasha.tatashin@soleen.com> (raw)

Changelog:
v2:
	- Fixed hibernate bug reported by James Morse
	- Addressed comments from James Morse:
	  * More incremental changes to trans_table
	  * Removed TRANS_FORCEMAP
	  * Added kexec reboot data for image with 380M in size.

Enable MMU during kexec relocation in order to improve reboot performance.

If kexec functionality is used for a fast system update, with a minimal
downtime, the relocation of kernel + initramfs takes a significant portion
of reboot.

The reason for slow relocation is because it is done without MMU, and thus
not benefiting from D-Cache.

Performance data
----------------
For this experiment, the size of kernel plus initramfs is small, only 25M.
If initramfs was larger, than the improvements would be greater, as time
spent in relocation is proportional to the size of relocation.

Previously:
kernel shutdown	0.022131328s
relocation	0.440510736s
kernel startup	0.294706768s

Relocation was taking: 58.2% of reboot time

Now:
kernel shutdown	0.032066576s
relocation	0.022158152s
kernel startup	0.296055880s

Now: Relocation takes 6.3% of reboot time

Total reboot is x2.16 times faster.

With bigger userland (fitImage 380M), the reboot time is improved by 3.57s,
and is reduced from 3.9s down to 0.33s

Previous approaches and discussions
-----------------------------------
https://lore.kernel.org/lkml/20190801152439.11363-1-pasha.tatashin@soleen.com/
version 1 of this series

https://lore.kernel.org/lkml/20190709182014.16052-1-pasha.tatashin@soleen.com
reserve space for kexec to avoid relocation, involves changes to generic code
to optimize a problem that exists on arm64 only:

https://lore.kernel.org/lkml/20190716165641.6990-1-pasha.tatashin@soleen.com
The first attempt to enable MMU, some bugs that prevented performance
improvement. The page tables unnecessary configured idmap for the whole
physical space.

https://lore.kernel.org/lkml/20190731153857.4045-1-pasha.tatashin@soleen.com
No linear copy, bug with EL2 reboots.

Pavel Tatashin (14):
  kexec: quiet down kexec reboot
  arm64, hibernate: create_safe_exec_page cleanup
  arm64, hibernate: add trans_table public functions
  arm64, hibernate: move page handling function to new trans_table.c
  arm64, trans_table: make trans_table_map_page generic
  arm64, trans_table: add trans_table_create_empty
  arm64, trans_table: adjust trans_table_create_copy interface
  arm64, trans_table: add PUD_SECT_RDONLY
  arm64, trans_table: complete generalization of trans_tables
  kexec: add machine_kexec_post_load()
  arm64, kexec: move relocation function setup and clean up
  arm64, kexec: add expandable argument to relocation function
  arm64, kexec: configure transitional page table for kexec
  arm64, kexec: enable MMU during kexec relocation

 arch/arm64/Kconfig                     |   4 +
 arch/arm64/include/asm/kexec.h         |  51 ++++-
 arch/arm64/include/asm/pgtable-hwdef.h |   1 +
 arch/arm64/include/asm/trans_table.h   |  64 ++++++
 arch/arm64/kernel/asm-offsets.c        |  14 ++
 arch/arm64/kernel/cpu-reset.S          |   4 +-
 arch/arm64/kernel/cpu-reset.h          |   8 +-
 arch/arm64/kernel/hibernate.c          | 261 ++++++-----------------
 arch/arm64/kernel/machine_kexec.c      | 199 ++++++++++++++----
 arch/arm64/kernel/relocate_kernel.S    | 196 +++++++++---------
 arch/arm64/mm/Makefile                 |   1 +
 arch/arm64/mm/trans_table.c            | 274 +++++++++++++++++++++++++
 kernel/kexec.c                         |   4 +
 kernel/kexec_core.c                    |   8 +-
 kernel/kexec_file.c                    |   4 +
 kernel/kexec_internal.h                |   2 +
 16 files changed, 755 insertions(+), 340 deletions(-)
 create mode 100644 arch/arm64/include/asm/trans_table.h
 create mode 100644 arch/arm64/mm/trans_table.c

-- 
2.22.1


WARNING: multiple messages have this Message-ID (diff)
From: Pavel Tatashin <pasha.tatashin@soleen.com>
To: pasha.tatashin@soleen.com, jmorris@namei.org, sashal@kernel.org,
	ebiederm@xmission.com, kexec@lists.infradead.org,
	linux-kernel@vger.kernel.org, corbet@lwn.net,
	catalin.marinas@arm.com, will@kernel.org,
	linux-arm-kernel@lists.infradead.org, marc.zyngier@arm.com,
	james.morse@arm.com, vladimir.murzin@arm.com,
	matthias.bgg@gmail.com, bhsharma@redhat.com, linux-mm@kvack.org
Subject: [PATCH v2 00/14] arm64: MMU enabled kexec relocation
Date: Fri, 16 Aug 2019 22:46:15 -0400	[thread overview]
Message-ID: <20190817024629.26611-1-pasha.tatashin@soleen.com> (raw)

Changelog:
v2:
	- Fixed hibernate bug reported by James Morse
	- Addressed comments from James Morse:
	  * More incremental changes to trans_table
	  * Removed TRANS_FORCEMAP
	  * Added kexec reboot data for image with 380M in size.

Enable MMU during kexec relocation in order to improve reboot performance.

If kexec functionality is used for a fast system update, with a minimal
downtime, the relocation of kernel + initramfs takes a significant portion
of reboot.

The reason for slow relocation is because it is done without MMU, and thus
not benefiting from D-Cache.

Performance data
----------------
For this experiment, the size of kernel plus initramfs is small, only 25M.
If initramfs was larger, than the improvements would be greater, as time
spent in relocation is proportional to the size of relocation.

Previously:
kernel shutdown	0.022131328s
relocation	0.440510736s
kernel startup	0.294706768s

Relocation was taking: 58.2% of reboot time

Now:
kernel shutdown	0.032066576s
relocation	0.022158152s
kernel startup	0.296055880s

Now: Relocation takes 6.3% of reboot time

Total reboot is x2.16 times faster.

With bigger userland (fitImage 380M), the reboot time is improved by 3.57s,
and is reduced from 3.9s down to 0.33s

Previous approaches and discussions
-----------------------------------
https://lore.kernel.org/lkml/20190801152439.11363-1-pasha.tatashin@soleen.com/
version 1 of this series

https://lore.kernel.org/lkml/20190709182014.16052-1-pasha.tatashin@soleen.com
reserve space for kexec to avoid relocation, involves changes to generic code
to optimize a problem that exists on arm64 only:

https://lore.kernel.org/lkml/20190716165641.6990-1-pasha.tatashin@soleen.com
The first attempt to enable MMU, some bugs that prevented performance
improvement. The page tables unnecessary configured idmap for the whole
physical space.

https://lore.kernel.org/lkml/20190731153857.4045-1-pasha.tatashin@soleen.com
No linear copy, bug with EL2 reboots.

Pavel Tatashin (14):
  kexec: quiet down kexec reboot
  arm64, hibernate: create_safe_exec_page cleanup
  arm64, hibernate: add trans_table public functions
  arm64, hibernate: move page handling function to new trans_table.c
  arm64, trans_table: make trans_table_map_page generic
  arm64, trans_table: add trans_table_create_empty
  arm64, trans_table: adjust trans_table_create_copy interface
  arm64, trans_table: add PUD_SECT_RDONLY
  arm64, trans_table: complete generalization of trans_tables
  kexec: add machine_kexec_post_load()
  arm64, kexec: move relocation function setup and clean up
  arm64, kexec: add expandable argument to relocation function
  arm64, kexec: configure transitional page table for kexec
  arm64, kexec: enable MMU during kexec relocation

 arch/arm64/Kconfig                     |   4 +
 arch/arm64/include/asm/kexec.h         |  51 ++++-
 arch/arm64/include/asm/pgtable-hwdef.h |   1 +
 arch/arm64/include/asm/trans_table.h   |  64 ++++++
 arch/arm64/kernel/asm-offsets.c        |  14 ++
 arch/arm64/kernel/cpu-reset.S          |   4 +-
 arch/arm64/kernel/cpu-reset.h          |   8 +-
 arch/arm64/kernel/hibernate.c          | 261 ++++++-----------------
 arch/arm64/kernel/machine_kexec.c      | 199 ++++++++++++++----
 arch/arm64/kernel/relocate_kernel.S    | 196 +++++++++---------
 arch/arm64/mm/Makefile                 |   1 +
 arch/arm64/mm/trans_table.c            | 274 +++++++++++++++++++++++++
 kernel/kexec.c                         |   4 +
 kernel/kexec_core.c                    |   8 +-
 kernel/kexec_file.c                    |   4 +
 kernel/kexec_internal.h                |   2 +
 16 files changed, 755 insertions(+), 340 deletions(-)
 create mode 100644 arch/arm64/include/asm/trans_table.h
 create mode 100644 arch/arm64/mm/trans_table.c

-- 
2.22.1


_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel

WARNING: multiple messages have this Message-ID (diff)
From: Pavel Tatashin <pasha.tatashin@soleen.com>
To: pasha.tatashin@soleen.com, jmorris@namei.org, sashal@kernel.org,
	ebiederm@xmission.com, kexec@lists.infradead.org,
	linux-kernel@vger.kernel.org, corbet@lwn.net,
	catalin.marinas@arm.com, will@kernel.org,
	linux-arm-kernel@lists.infradead.org, marc.zyngier@arm.com,
	james.morse@arm.com, vladimir.murzin@arm.com,
	matthias.bgg@gmail.com, bhsharma@redhat.com, linux-mm@kvack.org
Subject: [PATCH v2 00/14] arm64: MMU enabled kexec relocation
Date: Fri, 16 Aug 2019 22:46:15 -0400	[thread overview]
Message-ID: <20190817024629.26611-1-pasha.tatashin@soleen.com> (raw)

Changelog:
v2:
	- Fixed hibernate bug reported by James Morse
	- Addressed comments from James Morse:
	  * More incremental changes to trans_table
	  * Removed TRANS_FORCEMAP
	  * Added kexec reboot data for image with 380M in size.

Enable MMU during kexec relocation in order to improve reboot performance.

If kexec functionality is used for a fast system update, with a minimal
downtime, the relocation of kernel + initramfs takes a significant portion
of reboot.

The reason for slow relocation is because it is done without MMU, and thus
not benefiting from D-Cache.

Performance data
----------------
For this experiment, the size of kernel plus initramfs is small, only 25M.
If initramfs was larger, than the improvements would be greater, as time
spent in relocation is proportional to the size of relocation.

Previously:
kernel shutdown	0.022131328s
relocation	0.440510736s
kernel startup	0.294706768s

Relocation was taking: 58.2% of reboot time

Now:
kernel shutdown	0.032066576s
relocation	0.022158152s
kernel startup	0.296055880s

Now: Relocation takes 6.3% of reboot time

Total reboot is x2.16 times faster.

With bigger userland (fitImage 380M), the reboot time is improved by 3.57s,
and is reduced from 3.9s down to 0.33s

Previous approaches and discussions
-----------------------------------
https://lore.kernel.org/lkml/20190801152439.11363-1-pasha.tatashin@soleen.com/
version 1 of this series

https://lore.kernel.org/lkml/20190709182014.16052-1-pasha.tatashin@soleen.com
reserve space for kexec to avoid relocation, involves changes to generic code
to optimize a problem that exists on arm64 only:

https://lore.kernel.org/lkml/20190716165641.6990-1-pasha.tatashin@soleen.com
The first attempt to enable MMU, some bugs that prevented performance
improvement. The page tables unnecessary configured idmap for the whole
physical space.

https://lore.kernel.org/lkml/20190731153857.4045-1-pasha.tatashin@soleen.com
No linear copy, bug with EL2 reboots.

Pavel Tatashin (14):
  kexec: quiet down kexec reboot
  arm64, hibernate: create_safe_exec_page cleanup
  arm64, hibernate: add trans_table public functions
  arm64, hibernate: move page handling function to new trans_table.c
  arm64, trans_table: make trans_table_map_page generic
  arm64, trans_table: add trans_table_create_empty
  arm64, trans_table: adjust trans_table_create_copy interface
  arm64, trans_table: add PUD_SECT_RDONLY
  arm64, trans_table: complete generalization of trans_tables
  kexec: add machine_kexec_post_load()
  arm64, kexec: move relocation function setup and clean up
  arm64, kexec: add expandable argument to relocation function
  arm64, kexec: configure transitional page table for kexec
  arm64, kexec: enable MMU during kexec relocation

 arch/arm64/Kconfig                     |   4 +
 arch/arm64/include/asm/kexec.h         |  51 ++++-
 arch/arm64/include/asm/pgtable-hwdef.h |   1 +
 arch/arm64/include/asm/trans_table.h   |  64 ++++++
 arch/arm64/kernel/asm-offsets.c        |  14 ++
 arch/arm64/kernel/cpu-reset.S          |   4 +-
 arch/arm64/kernel/cpu-reset.h          |   8 +-
 arch/arm64/kernel/hibernate.c          | 261 ++++++-----------------
 arch/arm64/kernel/machine_kexec.c      | 199 ++++++++++++++----
 arch/arm64/kernel/relocate_kernel.S    | 196 +++++++++---------
 arch/arm64/mm/Makefile                 |   1 +
 arch/arm64/mm/trans_table.c            | 274 +++++++++++++++++++++++++
 kernel/kexec.c                         |   4 +
 kernel/kexec_core.c                    |   8 +-
 kernel/kexec_file.c                    |   4 +
 kernel/kexec_internal.h                |   2 +
 16 files changed, 755 insertions(+), 340 deletions(-)
 create mode 100644 arch/arm64/include/asm/trans_table.h
 create mode 100644 arch/arm64/mm/trans_table.c

-- 
2.22.1


_______________________________________________
kexec mailing list
kexec@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/kexec

             reply	other threads:[~2019-08-17  2:46 UTC|newest]

Thread overview: 66+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-08-17  2:46 Pavel Tatashin [this message]
2019-08-17  2:46 ` [PATCH v2 00/14] arm64: MMU enabled kexec relocation Pavel Tatashin
2019-08-17  2:46 ` Pavel Tatashin
2019-08-17  2:46 ` [PATCH v2 01/14] kexec: quiet down kexec reboot Pavel Tatashin
2019-08-17  2:46   ` Pavel Tatashin
2019-08-17  2:46   ` Pavel Tatashin
2019-08-17  2:46 ` [PATCH v2 02/14] arm64, hibernate: create_safe_exec_page cleanup Pavel Tatashin
2019-08-17  2:46   ` Pavel Tatashin
2019-08-17  2:46   ` Pavel Tatashin
2019-08-19 15:50   ` Mark Rutland
2019-08-19 15:50     ` Mark Rutland
2019-08-19 15:50     ` Mark Rutland
2019-08-19 16:25     ` Pavel Tatashin
2019-08-19 16:25       ` Pavel Tatashin
2019-08-19 16:25       ` Pavel Tatashin
2019-08-19 16:25       ` Pavel Tatashin
2019-08-17  2:46 ` [PATCH v2 03/14] arm64, hibernate: add trans_table public functions Pavel Tatashin
2019-08-17  2:46   ` Pavel Tatashin
2019-08-17  2:46   ` Pavel Tatashin
2019-08-19 15:58   ` Mark Rutland
2019-08-19 15:58     ` Mark Rutland
2019-08-19 15:58     ` Mark Rutland
2019-08-19 16:33     ` Pavel Tatashin
2019-08-19 16:33       ` Pavel Tatashin
2019-08-19 16:33       ` Pavel Tatashin
2019-08-19 16:33       ` Pavel Tatashin
2019-08-20 11:30       ` Mark Rutland
2019-08-20 11:30         ` Mark Rutland
2019-08-20 11:30         ` Mark Rutland
2019-08-20 11:41         ` Pavel Tatashin
2019-08-20 11:41           ` Pavel Tatashin
2019-08-20 11:41           ` Pavel Tatashin
2019-08-20 11:41           ` Pavel Tatashin
2019-08-17  2:46 ` [PATCH v2 04/14] arm64, hibernate: move page handling function to new trans_table.c Pavel Tatashin
2019-08-17  2:46   ` Pavel Tatashin
2019-08-17  2:46   ` Pavel Tatashin
2019-08-17  2:46 ` [PATCH v2 05/14] arm64, trans_table: make trans_table_map_page generic Pavel Tatashin
2019-08-17  2:46   ` Pavel Tatashin
2019-08-17  2:46   ` Pavel Tatashin
2019-08-17  2:46 ` [PATCH v2 06/14] arm64, trans_table: add trans_table_create_empty Pavel Tatashin
2019-08-17  2:46   ` Pavel Tatashin
2019-08-17  2:46   ` Pavel Tatashin
2019-08-17  2:46 ` [PATCH v2 07/14] arm64, trans_table: adjust trans_table_create_copy interface Pavel Tatashin
2019-08-17  2:46   ` Pavel Tatashin
2019-08-17  2:46   ` Pavel Tatashin
2019-08-17  2:46 ` [PATCH v2 08/14] arm64, trans_table: add PUD_SECT_RDONLY Pavel Tatashin
2019-08-17  2:46   ` Pavel Tatashin
2019-08-17  2:46   ` Pavel Tatashin
2019-08-17  2:46 ` [PATCH v2 09/14] arm64, trans_table: complete generalization of trans_tables Pavel Tatashin
2019-08-17  2:46   ` Pavel Tatashin
2019-08-17  2:46   ` Pavel Tatashin
2019-08-17  2:46 ` [PATCH v2 10/14] kexec: add machine_kexec_post_load() Pavel Tatashin
2019-08-17  2:46   ` Pavel Tatashin
2019-08-17  2:46   ` Pavel Tatashin
2019-08-17  2:46 ` [PATCH v2 11/14] arm64, kexec: move relocation function setup and clean up Pavel Tatashin
2019-08-17  2:46   ` Pavel Tatashin
2019-08-17  2:46   ` Pavel Tatashin
2019-08-17  2:46 ` [PATCH v2 12/14] arm64, kexec: add expandable argument to relocation function Pavel Tatashin
2019-08-17  2:46   ` Pavel Tatashin
2019-08-17  2:46   ` Pavel Tatashin
2019-08-17  2:46 ` [PATCH v2 13/14] arm64, kexec: configure transitional page table for kexec Pavel Tatashin
2019-08-17  2:46   ` Pavel Tatashin
2019-08-17  2:46   ` Pavel Tatashin
2019-08-17  2:46 ` [PATCH v2 14/14] arm64, kexec: enable MMU during kexec relocation Pavel Tatashin
2019-08-17  2:46   ` Pavel Tatashin
2019-08-17  2:46   ` Pavel Tatashin

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=20190817024629.26611-1-pasha.tatashin@soleen.com \
    --to=pasha.tatashin@soleen.com \
    --cc=bhsharma@redhat.com \
    --cc=catalin.marinas@arm.com \
    --cc=corbet@lwn.net \
    --cc=ebiederm@xmission.com \
    --cc=james.morse@arm.com \
    --cc=jmorris@namei.org \
    --cc=kexec@lists.infradead.org \
    --cc=linux-arm-kernel@lists.infradead.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=marc.zyngier@arm.com \
    --cc=matthias.bgg@gmail.com \
    --cc=sashal@kernel.org \
    --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 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.