linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Christophe Leroy <christophe.leroy@c-s.fr>
To: Benjamin Herrenschmidt <benh@kernel.crashing.org>,
	Paul Mackerras <paulus@samba.org>,
	Michael Ellerman <mpe@ellerman.id.au>,
	scottwood@freescale.com
Cc: linux-kernel@vger.kernel.org, linuxppc-dev@lists.ozlabs.org
Subject: [PATCH v2 00/25] powerpc/8xx: Use large pages for RAM and IMMR and other improvments
Date: Tue, 22 Sep 2015 18:50:27 +0200 (CEST)	[thread overview]
Message-ID: <cover.1442939410.git.christophe.leroy@c-s.fr> (raw)

The main purpose of this patchset is to dramatically reduce the time
spent in DTLB miss handler. This is achieved by:
1/ Mapping RAM with 8M pages
2/ Mapping IMMR with a fixed 512K page

On a live running system (VoIP gateway for Air Trafic Control), over
a 10 minutes period (with 277s idle), we get 87 millions DTLB misses
and approximatly 35 secondes are spent in DTLB handler.
This represents 5.8% of the overall time and even 10.8% of the
non-idle time.
Among those 87 millions DTLB misses, 15% are on user addresses and
85% are on kernel addresses. And within the kernel addresses, 93%
are on addresses from the linear address space and only 7% are on
addresses from the virtual address space.

Once the full patchset applied, the number of DTLB misses during the
period is reduced to 11.8 millions for a duration of 5.8s, which
represents 2% of the non-idle time.

This patch also includes other miscellaneous improvements:
1/ Handling of CPU6 ERRATA directly in mtspr() C macro to reduce code
specific to PPC8xx
2/ Rewrite of a few non critical ASM functions in C
3/ Removal of some unused items

See related patches for details

Christophe Leroy (25):
  powerpc/8xx: Save r3 all the time in DTLB miss handler
  powerpc/8xx: Map linear kernel RAM with 8M pages
  powerpc: Update documentation for noltlbs kernel parameter
  powerpc/8xx: move setup_initial_memory_limit() into 8xx_mmu.c
  powerpc/8xx: Fix vaddr for IMMR early remap
  powerpc32: iounmap() cannot vunmap() area mapped by TLBCAMs either
  powerpc32: refactor x_mapped_by_bats() and x_mapped_by_tlbcam()
    together
  powerpc/8xx: Map IMMR area with 512k page at a fixed address
  powerpc/8xx: show IMMR area in startup memory layout
  powerpc/8xx: CONFIG_PIN_TLB unneeded for CONFIG_PPC_EARLY_DEBUG_CPM
  powerpc/8xx: map 16M RAM at startup
  powerpc32: Remove useless/wrong MMU:setio progress message
  powerpc/8xx: also use r3 in the ITLB miss in all situations
  powerpc32: remove ioremap_base
  powerpc/8xx: move 8xx SPRN defines into reg_8xx.h and add some missing
    ones
  powerpc/8xx: Handle CPU6 ERRATA directly in mtspr() macro
  powerpc/8xx: remove special handling of CPU6 errata in set_dec()
  powerpc/8xx: rewrite set_context() in C
  powerpc/8xx: rewrite flush_instruction_cache() in C
  powerpc32: Remove clear_pages() and define clear_page() inline
  powerpc: add inline functions for cache related instructions
  powerpc32: move xxxxx_dcache_range() functions inline
  powerpc: Simplify test in __dma_sync()
  powerpc32: small optimisation in flush_icache_range()
  powerpc32: Remove one insn in mulhdu

 Documentation/kernel-parameters.txt         |   2 +-
 arch/powerpc/Kconfig.debug                  |   2 -
 arch/powerpc/include/asm/cache.h            |  19 +++
 arch/powerpc/include/asm/cacheflush.h       |  55 +++++++-
 arch/powerpc/include/asm/mmu-8xx.h          |  26 ++--
 arch/powerpc/include/asm/page_32.h          |  17 ++-
 arch/powerpc/include/asm/pgtable-ppc32.h    |   5 +
 arch/powerpc/include/asm/reg.h              |   2 +
 arch/powerpc/include/asm/reg_8xx.h          | 106 +++++++++++++++
 arch/powerpc/include/asm/time.h             |   6 +-
 arch/powerpc/kernel/head_8xx.S              | 167 ++++++++++++------------
 arch/powerpc/kernel/misc_32.S               | 107 ++--------------
 arch/powerpc/kernel/ppc_ksyms.c             |   2 +
 arch/powerpc/kernel/ppc_ksyms_32.c          |   1 -
 arch/powerpc/mm/8xx_mmu.c                   | 191 ++++++++++++++++++++++++++++
 arch/powerpc/mm/Makefile                    |   1 +
 arch/powerpc/mm/dma-noncoherent.c           |   2 +-
 arch/powerpc/mm/init_32.c                   |  23 ----
 arch/powerpc/mm/mem.c                       |   4 +
 arch/powerpc/mm/mmu_decl.h                  |  16 +--
 arch/powerpc/mm/pgtable_32.c                |  54 +++++++-
 arch/powerpc/platforms/embedded6xx/mpc10x.h |   8 --
 22 files changed, 553 insertions(+), 263 deletions(-)
 create mode 100644 arch/powerpc/mm/8xx_mmu.c

-- 
2.1.0


             reply	other threads:[~2015-09-22 16:50 UTC|newest]

Thread overview: 76+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2015-09-22 16:50 Christophe Leroy [this message]
2015-09-22 16:50 ` [PATCH v2 01/25] powerpc/8xx: Save r3 all the time in DTLB miss handler Christophe Leroy
2015-09-28 22:07   ` Scott Wood
2015-10-06 13:35     ` Christophe Leroy
2015-10-06 16:39       ` Scott Wood
2015-10-06 16:46       ` Scott Wood
2015-10-06 20:30         ` christophe leroy
2015-10-06 20:38           ` Scott Wood
2015-09-22 16:50 ` [PATCH v2 02/25] powerpc/8xx: Map linear kernel RAM with 8M pages Christophe Leroy
2015-09-22 16:50 ` [PATCH v2 03/25] powerpc: Update documentation for noltlbs kernel parameter Christophe Leroy
2015-09-22 16:50 ` [PATCH v2 04/25] powerpc/8xx: move setup_initial_memory_limit() into 8xx_mmu.c Christophe Leroy
2015-09-22 16:50 ` [PATCH v2 05/25] powerpc/8xx: Fix vaddr for IMMR early remap Christophe Leroy
2015-09-28 23:39   ` Scott Wood
2015-10-08 12:34     ` Christophe Leroy
2015-10-08 19:13       ` Scott Wood
2015-09-22 16:50 ` [PATCH v2 06/25] powerpc32: iounmap() cannot vunmap() area mapped by TLBCAMs either Christophe Leroy
2015-09-28 23:41   ` Scott Wood
2015-10-06 13:50     ` Christophe Leroy
2015-09-22 16:50 ` [PATCH v2 07/25] powerpc32: refactor x_mapped_by_bats() and x_mapped_by_tlbcam() together Christophe Leroy
2015-09-28 23:47   ` Scott Wood
2015-10-06 14:02     ` Christophe Leroy
2015-10-06 15:16       ` Scott Wood
2015-09-22 16:50 ` [PATCH v2 08/25] powerpc/8xx: Map IMMR area with 512k page at a fixed address Christophe Leroy
2015-09-24 11:41   ` David Laight
2015-09-24 20:14     ` Scott Wood
2015-09-25 14:46       ` David Laight
2015-09-25 17:09         ` Scott Wood
2015-09-28 23:53   ` Scott Wood
2015-09-22 16:50 ` [PATCH v2 09/25] powerpc/8xx: show IMMR area in startup memory layout Christophe Leroy
2015-09-22 16:50 ` [PATCH v2 10/25] powerpc/8xx: CONFIG_PIN_TLB unneeded for CONFIG_PPC_EARLY_DEBUG_CPM Christophe Leroy
2015-09-22 16:50 ` [PATCH v2 11/25] powerpc/8xx: map 16M RAM at startup Christophe Leroy
2015-09-28 23:58   ` Scott Wood
2015-10-06 14:10     ` Christophe Leroy
2015-10-06 15:17       ` Scott Wood
2015-09-22 16:50 ` [PATCH v2 12/25] powerpc32: Remove useless/wrong MMU:setio progress message Christophe Leroy
2015-09-22 16:50 ` [PATCH v2 13/25] powerpc/8xx: also use r3 in the ITLB miss in all situations Christophe Leroy
2015-09-29  0:00   ` Scott Wood
2015-10-06 14:12     ` Christophe Leroy
2015-10-06 16:48       ` Scott Wood
2015-09-22 16:50 ` [PATCH v2 14/25] powerpc32: remove ioremap_base Christophe Leroy
2015-09-29  0:38   ` Scott Wood
2015-09-22 16:50 ` [PATCH v2 15/25] powerpc/8xx: move 8xx SPRN defines into reg_8xx.h and add some missing ones Christophe Leroy
2015-09-29  0:03   ` Scott Wood
2015-10-06 14:35     ` Christophe Leroy
2015-10-06 16:56       ` Scott Wood
2015-09-22 16:51 ` [PATCH v2 16/25] powerpc/8xx: Handle CPU6 ERRATA directly in mtspr() macro Christophe Leroy
2015-09-22 16:51 ` [PATCH v2 17/25] powerpc/8xx: remove special handling of CPU6 errata in set_dec() Christophe Leroy
2015-09-22 16:51 ` [PATCH v2 18/25] powerpc/8xx: rewrite set_context() in C Christophe Leroy
2015-09-22 16:51 ` [PATCH v2 19/25] powerpc/8xx: rewrite flush_instruction_cache() " Christophe Leroy
2015-09-22 16:51 ` [PATCH v2 20/25] powerpc32: Remove clear_pages() and define clear_page() inline Christophe Leroy
2015-09-22 17:57   ` Joakim Tjernlund
2015-09-29  0:23   ` Scott Wood
2015-09-22 16:51 ` [PATCH v2 21/25] powerpc: add inline functions for cache related instructions Christophe Leroy
2015-09-29  0:25   ` Scott Wood
2015-09-22 16:51 ` [PATCH v2 22/25] powerpc32: move xxxxx_dcache_range() functions inline Christophe Leroy
2015-09-22 18:12   ` Joakim Tjernlund
2015-09-22 18:58     ` Scott Wood
2015-09-22 19:34       ` Joakim Tjernlund
2015-09-22 19:42         ` Scott Wood
2015-09-22 19:55           ` Joakim Tjernlund
2015-09-22 20:07             ` Joakim Tjernlund
2015-09-22 20:14             ` Scott Wood
2015-09-22 20:32               ` Joakim Tjernlund
2015-09-22 20:35                 ` Scott Wood
2015-09-22 20:38                   ` Joakim Tjernlund
2015-09-22 20:57                     ` Christophe Leroy
2015-09-22 22:34                       ` Scott Wood
2015-09-22 22:49                         ` Christophe Leroy
2015-09-22 22:52                           ` Scott Wood
2015-09-29  0:29   ` Scott Wood
2015-10-07 12:49     ` Christophe Leroy
2015-10-08 19:12       ` Scott Wood
2015-10-12 18:08         ` christophe leroy
2015-09-22 16:51 ` [PATCH v2 23/25] powerpc: Simplify test in __dma_sync() Christophe Leroy
2015-09-22 16:51 ` [PATCH v2 24/25] powerpc32: small optimisation in flush_icache_range() Christophe Leroy
2015-09-22 16:51 ` [PATCH v2 25/25] powerpc32: Remove one insn in mulhdu Christophe Leroy

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=cover.1442939410.git.christophe.leroy@c-s.fr \
    --to=christophe.leroy@c-s.fr \
    --cc=benh@kernel.crashing.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linuxppc-dev@lists.ozlabs.org \
    --cc=mpe@ellerman.id.au \
    --cc=paulus@samba.org \
    --cc=scottwood@freescale.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;
as well as URLs for NNTP newsgroup(s).