linux-arch.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Catalin Marinas <catalin.marinas@arm.com>
To: Steve Capper <steve.capper@linaro.org>
Cc: "linux-mm@kvack.org" <linux-mm@kvack.org>,
	"x86@kernel.org" <x86@kernel.org>,
	"linux-arch@vger.kernel.org" <linux-arch@vger.kernel.org>,
	"linux-arm-kernel@lists.infradead.org"
	<linux-arm-kernel@lists.infradead.org>,
	Michal Hocko <mhocko@suse.cz>, Ken Chen <kenchen@google.com>,
	Mel Gorman <mgorman@suse.de>, Will Deacon <Will.Deacon@arm.com>
Subject: Re: [RFC PATCH 8/9] ARM64: mm: Introduce MAX_ZONE_ORDER for 64K and THP.
Date: Thu, 2 May 2013 11:00:00 +0100	[thread overview]
Message-ID: <20130502100000.GB20730@arm.com> (raw)
In-Reply-To: <1367339448-21727-9-git-send-email-steve.capper@linaro.org>

On Tue, Apr 30, 2013 at 05:30:47PM +0100, Steve Capper wrote:
> The buddy allocator has a default order of 11, which is too low to
> allocate enough memory for 512MB Transparent HugePages if our base
> page size is 64K. For any order less than 13, the combination of
> THP with 64K pages will cause a compile error.
> 
> This patch introduces the MAX_ZONE_ORDER config option that allows
> one to explicitly override the order of the buddy allocator. If
> 64K pages and THP are enabled the minimum value is set to 13.
> 
> Signed-off-by: Steve Capper <steve.capper@linaro.org>
> ---
>  arch/arm64/Kconfig | 17 +++++++++++++++++
>  1 file changed, 17 insertions(+)
> 
> diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
> index 16aa780..908fd95 100644
> --- a/arch/arm64/Kconfig
> +++ b/arch/arm64/Kconfig
> @@ -196,6 +196,23 @@ config ARCH_WANT_HUGE_PMD_SHARE
>  
>  source "mm/Kconfig"
>  
> +config FORCE_MAX_ZONEORDER
> +	int "Maximum zone order"
> +	range 11 64 if !(ARM64_64K_PAGES && TRANSPARENT_HUGEPAGE)
> +	range 13 64 if ARM64_64K_PAGES && TRANSPARENT_HUGEPAGE
> +	default "11" if !(ARM64_64K_PAGES && TRANSPARENT_HUGEPAGE)
> +	default "13" if (ARM64_64K_PAGES && TRANSPARENT_HUGEPAGE)

Can we just keep some sane defaults here without giving too much choice
to the user? Something like:

config FORCE_MAX_ZONEORDER
	int
	default "13" if (ARM64_64K_PAGES && TRANSPARENT_HUGEPAGE)
	default "11"

We can extend it later if people need this but I'm aiming for a single
config on a multitude of boards.

-- 
Catalin

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

WARNING: multiple messages have this Message-ID (diff)
From: Catalin Marinas <catalin.marinas@arm.com>
To: Steve Capper <steve.capper@linaro.org>
Cc: "linux-mm@kvack.org" <linux-mm@kvack.org>,
	"x86@kernel.org" <x86@kernel.org>,
	"linux-arch@vger.kernel.org" <linux-arch@vger.kernel.org>,
	"linux-arm-kernel@lists.infradead.org"
	<linux-arm-kernel@lists.infradead.org>,
	Michal Hocko <mhocko@suse.cz>, Ken Chen <kenchen@google.com>,
	Mel Gorman <mgorman@suse.de>, Will Deacon <Will.Deacon@arm.com>
Subject: Re: [RFC PATCH 8/9] ARM64: mm: Introduce MAX_ZONE_ORDER for 64K and THP.
Date: Thu, 2 May 2013 11:00:00 +0100	[thread overview]
Message-ID: <20130502100000.GB20730@arm.com> (raw)
Message-ID: <20130502100000.lmTt88mxJdx1jIx_lwvf_pZkVPx8LtwS_BrtZs5tBiU@z> (raw)
In-Reply-To: <1367339448-21727-9-git-send-email-steve.capper@linaro.org>

On Tue, Apr 30, 2013 at 05:30:47PM +0100, Steve Capper wrote:
> The buddy allocator has a default order of 11, which is too low to
> allocate enough memory for 512MB Transparent HugePages if our base
> page size is 64K. For any order less than 13, the combination of
> THP with 64K pages will cause a compile error.
> 
> This patch introduces the MAX_ZONE_ORDER config option that allows
> one to explicitly override the order of the buddy allocator. If
> 64K pages and THP are enabled the minimum value is set to 13.
> 
> Signed-off-by: Steve Capper <steve.capper@linaro.org>
> ---
>  arch/arm64/Kconfig | 17 +++++++++++++++++
>  1 file changed, 17 insertions(+)
> 
> diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
> index 16aa780..908fd95 100644
> --- a/arch/arm64/Kconfig
> +++ b/arch/arm64/Kconfig
> @@ -196,6 +196,23 @@ config ARCH_WANT_HUGE_PMD_SHARE
>  
>  source "mm/Kconfig"
>  
> +config FORCE_MAX_ZONEORDER
> +	int "Maximum zone order"
> +	range 11 64 if !(ARM64_64K_PAGES && TRANSPARENT_HUGEPAGE)
> +	range 13 64 if ARM64_64K_PAGES && TRANSPARENT_HUGEPAGE
> +	default "11" if !(ARM64_64K_PAGES && TRANSPARENT_HUGEPAGE)
> +	default "13" if (ARM64_64K_PAGES && TRANSPARENT_HUGEPAGE)

Can we just keep some sane defaults here without giving too much choice
to the user? Something like:

config FORCE_MAX_ZONEORDER
	int
	default "13" if (ARM64_64K_PAGES && TRANSPARENT_HUGEPAGE)
	default "11"

We can extend it later if people need this but I'm aiming for a single
config on a multitude of boards.

-- 
Catalin

  parent reply	other threads:[~2013-05-02 10:00 UTC|newest]

Thread overview: 30+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2013-04-30 16:30 [RFC PATCH 0/9] HugeTLB and THP support for ARM64 Steve Capper
2013-04-30 16:30 ` [RFC PATCH 1/9] mm: hugetlb: Copy huge_pmd_share from x86 to mm Steve Capper
2013-04-30 16:30 ` [RFC PATCH 2/9] x86: mm: Remove x86 version of huge_pmd_share Steve Capper
2013-04-30 16:30 ` [RFC PATCH 3/9] mm: hugetlb: Copy general hugetlb code from x86 to mm Steve Capper
2013-04-30 16:30   ` Steve Capper
2013-04-30 16:48   ` Catalin Marinas
2013-04-30 16:48     ` Catalin Marinas
2013-04-30 16:30 ` [RFC PATCH 4/9] x86: mm: Remove general hugetlb code from x86 Steve Capper
2013-04-30 16:30 ` [RFC PATCH 5/9] ARM64: mm: Add support for flushing huge pages Steve Capper
2013-05-01 11:05   ` Will Deacon
2013-05-01 11:05     ` Will Deacon
2013-05-01 11:31     ` Catalin Marinas
2013-05-01 11:31       ` Catalin Marinas
2013-04-30 16:30 ` [RFC PATCH 6/9] ARM64: mm: Restore memblock limit when map_mem finished Steve Capper
2013-04-30 16:30 ` [RFC PATCH 7/9] ARM64: mm: HugeTLB support Steve Capper
2013-04-30 16:30   ` Steve Capper
2013-05-01 11:42   ` Will Deacon
2013-05-01 11:42     ` Will Deacon
2013-05-01 13:04     ` Steve Capper
2013-05-01 16:21   ` Catalin Marinas
2013-05-01 16:21     ` Catalin Marinas
2013-04-30 16:30 ` [RFC PATCH 8/9] ARM64: mm: Introduce MAX_ZONE_ORDER for 64K and THP Steve Capper
2013-04-30 16:30   ` Steve Capper
2013-05-02 10:00   ` Catalin Marinas [this message]
2013-05-02 10:00     ` Catalin Marinas
2013-05-02 10:05     ` Steve Capper
2013-05-02 10:05       ` Steve Capper
2013-04-30 16:30 ` [RFC PATCH 9/9] ARM64: mm: THP support Steve Capper
2013-05-01 14:16   ` Steve Capper
2013-05-01 14:16     ` Steve Capper

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=20130502100000.GB20730@arm.com \
    --to=catalin.marinas@arm.com \
    --cc=Will.Deacon@arm.com \
    --cc=kenchen@google.com \
    --cc=linux-arch@vger.kernel.org \
    --cc=linux-arm-kernel@lists.infradead.org \
    --cc=linux-mm@kvack.org \
    --cc=mgorman@suse.de \
    --cc=mhocko@suse.cz \
    --cc=steve.capper@linaro.org \
    --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).