From: Scott Wood <scottwood@freescale.com>
To: David Laight <David.Laight@ACULAB.COM>
Cc: 'Christophe Leroy' <christophe.leroy@c-s.fr>,
Benjamin Herrenschmidt <benh@kernel.crashing.org>,
Paul Mackerras <paulus@samba.org>,
"Michael Ellerman" <mpe@ellerman.id.au>,
"linuxppc-dev@lists.ozlabs.org" <linuxppc-dev@lists.ozlabs.org>,
"linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>
Subject: Re: [PATCH v2 08/25] powerpc/8xx: Map IMMR area with 512k page at a fixed address
Date: Thu, 24 Sep 2015 15:14:23 -0500 [thread overview]
Message-ID: <1443125663.32298.32.camel@freescale.com> (raw)
In-Reply-To: <063D6719AE5E284EB5DD2968C1650D6D1CBA15B8@AcuExch.aculab.com>
On Thu, 2015-09-24 at 11:41 +0000, David Laight wrote:
> From: Christophe Leroy
> > Sent: 22 September 2015 17:51
> ...
> > Traditionaly, each driver manages one computer board which has its
> > own components with its own memory maps.
> > But on embedded chips like the MPC8xx, the SOC has all registers
> > located in the same IO area.
> >
> > When looking at ioremaps done during startup, we see that
> > many drivers are re-mapping small parts of the IMMR for their own use
> > and all those small pieces gets their own 4k page, amplifying the
> > number of TLB misses: in our system we get 0xff000000 mapped 31 times
> > and 0xff003000 mapped 9 times.
>
> Isn't this a more general problem?
>
> If there are multiple remap requests for the same physical page
> shouldn't the kernel be just increasing a reference count somewhere
> and returning address in the same virtual page?
> This should probably happen regardless of the address.
> I presume it must be done for cacheable mappings.
Why would you assume that?
-Scott
next prev parent reply other threads:[~2015-09-24 20:14 UTC|newest]
Thread overview: 76+ messages / expand[flat|nested] mbox.gz Atom feed top
2015-09-22 16:50 [PATCH v2 00/25] powerpc/8xx: Use large pages for RAM and IMMR and other improvments Christophe Leroy
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 [this message]
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=1443125663.32298.32.camel@freescale.com \
--to=scottwood@freescale.com \
--cc=David.Laight@ACULAB.COM \
--cc=benh@kernel.crashing.org \
--cc=christophe.leroy@c-s.fr \
--cc=linux-kernel@vger.kernel.org \
--cc=linuxppc-dev@lists.ozlabs.org \
--cc=mpe@ellerman.id.au \
--cc=paulus@samba.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).