From: Steve Capper <steve.capper@linaro.org>
To: "Kirill A. Shutemov" <kirill@shutemov.name>
Cc: linux-mm@kvack.org, x86@kernel.org, linux-arch@vger.kernel.org,
linux-arm-kernel@lists.infradead.org,
Michal Hocko <mhocko@suse.cz>, Ken Chen <kenchen@google.com>,
Mel Gorman <mgorman@suse.de>,
Catalin Marinas <catalin.marinas@arm.com>,
Will Deacon <will.deacon@arm.com>,
patches@linaro.org
Subject: Re: [RFC PATCH v2 05/11] mm: thp: Correct the HPAGE_PMD_ORDER check.
Date: Wed, 8 May 2013 13:03:08 +0100 [thread overview]
Message-ID: <20130508120307.GA1407@linaro.org> (raw)
In-Reply-To: <20130508124417.GA29631@shutemov.name>
On Wed, May 08, 2013 at 03:44:17PM +0300, Kirill A. Shutemov wrote:
> On Wed, May 08, 2013 at 10:52:37AM +0100, Steve Capper wrote:
> > All Transparent Huge Pages are allocated by the buddy allocator.
> >
> > A compile time check is in place that fails when the order of a
> > transparent huge page is too large to be allocated by the buddy
> > allocator. Unfortunately that compile time check passes when:
> > HPAGE_PMD_ORDER == MAX_ORDER
> > ( which is incorrect as the buddy allocator can only allocate
> > memory of order strictly less than MAX_ORDER. )
>
> It looks confusing to me. Shouldn't we fix what MAX_ORDER means instead?
>
It confused me as I originally had 13 as the order and couldn't
allocate any 512MB THPs :-).
MAX_ORDER appears to be used quite a lot so I think it would be
safer to change the use case here rather than its meaning.
Cheers,
--
Steve
--
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: Steve Capper <steve.capper@linaro.org>
To: "Kirill A. Shutemov" <kirill@shutemov.name>
Cc: linux-mm@kvack.org, x86@kernel.org, linux-arch@vger.kernel.org,
linux-arm-kernel@lists.infradead.org,
Michal Hocko <mhocko@suse.cz>, Ken Chen <kenchen@google.com>,
Mel Gorman <mgorman@suse.de>,
Catalin Marinas <catalin.marinas@arm.com>,
Will Deacon <will.deacon@arm.com>,
patches@linaro.org
Subject: Re: [RFC PATCH v2 05/11] mm: thp: Correct the HPAGE_PMD_ORDER check.
Date: Wed, 8 May 2013 13:03:08 +0100 [thread overview]
Message-ID: <20130508120307.GA1407@linaro.org> (raw)
Message-ID: <20130508120308.u_gMv8XmGOCYiLmJsI9QlOsUpoZ2ia1qywDDctTfXNM@z> (raw)
In-Reply-To: <20130508124417.GA29631@shutemov.name>
On Wed, May 08, 2013 at 03:44:17PM +0300, Kirill A. Shutemov wrote:
> On Wed, May 08, 2013 at 10:52:37AM +0100, Steve Capper wrote:
> > All Transparent Huge Pages are allocated by the buddy allocator.
> >
> > A compile time check is in place that fails when the order of a
> > transparent huge page is too large to be allocated by the buddy
> > allocator. Unfortunately that compile time check passes when:
> > HPAGE_PMD_ORDER == MAX_ORDER
> > ( which is incorrect as the buddy allocator can only allocate
> > memory of order strictly less than MAX_ORDER. )
>
> It looks confusing to me. Shouldn't we fix what MAX_ORDER means instead?
>
It confused me as I originally had 13 as the order and couldn't
allocate any 512MB THPs :-).
MAX_ORDER appears to be used quite a lot so I think it would be
safer to change the use case here rather than its meaning.
Cheers,
--
Steve
WARNING: multiple messages have this Message-ID (diff)
From: steve.capper@linaro.org (Steve Capper)
To: linux-arm-kernel@lists.infradead.org
Subject: [RFC PATCH v2 05/11] mm: thp: Correct the HPAGE_PMD_ORDER check.
Date: Wed, 8 May 2013 13:03:08 +0100 [thread overview]
Message-ID: <20130508120307.GA1407@linaro.org> (raw)
In-Reply-To: <20130508124417.GA29631@shutemov.name>
On Wed, May 08, 2013 at 03:44:17PM +0300, Kirill A. Shutemov wrote:
> On Wed, May 08, 2013 at 10:52:37AM +0100, Steve Capper wrote:
> > All Transparent Huge Pages are allocated by the buddy allocator.
> >
> > A compile time check is in place that fails when the order of a
> > transparent huge page is too large to be allocated by the buddy
> > allocator. Unfortunately that compile time check passes when:
> > HPAGE_PMD_ORDER == MAX_ORDER
> > ( which is incorrect as the buddy allocator can only allocate
> > memory of order strictly less than MAX_ORDER. )
>
> It looks confusing to me. Shouldn't we fix what MAX_ORDER means instead?
>
It confused me as I originally had 13 as the order and couldn't
allocate any 512MB THPs :-).
MAX_ORDER appears to be used quite a lot so I think it would be
safer to change the use case here rather than its meaning.
Cheers,
--
Steve
next prev parent reply other threads:[~2013-05-08 12:03 UTC|newest]
Thread overview: 78+ messages / expand[flat|nested] mbox.gz Atom feed top
2013-05-08 9:52 [RFC PATCH v2 00/11] HugeTLB and THP support for ARM64 Steve Capper
2013-05-08 9:52 ` Steve Capper
2013-05-08 9:52 ` Steve Capper
2013-05-08 9:52 ` [RFC PATCH v2 01/11] mm: hugetlb: Copy huge_pmd_share from x86 to mm Steve Capper
2013-05-08 9:52 ` Steve Capper
2013-05-08 9:52 ` Steve Capper
2013-05-08 9:52 ` [RFC PATCH v2 02/11] x86: mm: Remove x86 version of huge_pmd_share Steve Capper
2013-05-08 9:52 ` Steve Capper
2013-05-08 9:52 ` Steve Capper
2013-05-08 9:52 ` [RFC PATCH v2 03/11] mm: hugetlb: Copy general hugetlb code from x86 to mm Steve Capper
2013-05-08 9:52 ` Steve Capper
2013-05-08 9:52 ` Steve Capper
2013-05-08 9:52 ` [RFC PATCH v2 04/11] x86: mm: Remove general hugetlb code from x86 Steve Capper
2013-05-08 9:52 ` Steve Capper
2013-05-08 9:52 ` Steve Capper
2013-05-08 9:52 ` [RFC PATCH v2 05/11] mm: thp: Correct the HPAGE_PMD_ORDER check Steve Capper
2013-05-08 9:52 ` Steve Capper
2013-05-08 9:52 ` Steve Capper
2013-05-08 12:44 ` Kirill A. Shutemov
2013-05-08 12:44 ` Kirill A. Shutemov
2013-05-08 12:44 ` Kirill A. Shutemov
2013-05-08 12:03 ` Steve Capper [this message]
2013-05-08 12:03 ` Steve Capper
2013-05-08 12:03 ` Steve Capper
2013-05-08 9:52 ` [RFC PATCH v2 06/11] ARM64: mm: Restore memblock limit when map_mem finished Steve Capper
2013-05-08 9:52 ` Steve Capper
2013-05-08 9:52 ` Steve Capper
2013-05-16 13:52 ` Catalin Marinas
2013-05-16 13:52 ` Catalin Marinas
2013-05-16 13:52 ` Catalin Marinas
2013-05-08 9:52 ` [RFC PATCH v2 07/11] ARM64: mm: Make PAGE_NONE pages read only and no-execute Steve Capper
2013-05-08 9:52 ` Steve Capper
2013-05-08 9:52 ` Steve Capper
2013-05-08 16:43 ` Will Deacon
2013-05-08 16:43 ` Will Deacon
2013-05-08 16:43 ` Will Deacon
2013-05-09 8:27 ` Steve Capper
2013-05-09 8:27 ` Steve Capper
2013-05-09 8:27 ` Steve Capper
2013-05-08 9:52 ` [RFC PATCH v2 08/11] ARM64: mm: Swap PTE_FILE and PTE_PROT_NONE bits Steve Capper
2013-05-08 9:52 ` Steve Capper
2013-05-08 9:52 ` Steve Capper
2013-05-08 16:17 ` Christopher Covington
2013-05-08 16:17 ` Christopher Covington
2013-05-08 16:17 ` Christopher Covington
2013-05-09 8:15 ` Steve Capper
2013-05-09 8:15 ` Steve Capper
2013-05-09 8:15 ` Steve Capper
2013-05-08 16:40 ` Will Deacon
2013-05-08 16:40 ` Will Deacon
2013-05-08 16:40 ` Will Deacon
2013-05-09 8:22 ` Steve Capper
2013-05-09 8:22 ` Steve Capper
2013-05-09 8:22 ` Steve Capper
2013-05-16 14:58 ` Catalin Marinas
2013-05-16 14:58 ` Catalin Marinas
2013-05-16 14:58 ` Catalin Marinas
2013-05-08 9:52 ` [RFC PATCH v2 09/11] ARM64: mm: HugeTLB support Steve Capper
2013-05-08 9:52 ` Steve Capper
2013-05-08 9:52 ` Steve Capper
2013-05-16 14:32 ` Catalin Marinas
2013-05-16 14:32 ` Catalin Marinas
2013-05-16 14:32 ` Catalin Marinas
2013-05-17 8:41 ` Steve Capper
2013-05-17 8:41 ` Steve Capper
2013-05-17 8:41 ` Steve Capper
2013-05-08 9:52 ` [RFC PATCH v2 10/11] ARM64: mm: Raise MAX_ORDER for 64KB pages and THP Steve Capper
2013-05-08 9:52 ` Steve Capper
2013-05-08 9:52 ` Steve Capper
2013-05-16 14:59 ` Catalin Marinas
2013-05-16 14:59 ` Catalin Marinas
2013-05-16 14:59 ` Catalin Marinas
2013-05-08 9:52 ` [RFC PATCH v2 11/11] ARM64: mm: THP support Steve Capper
2013-05-08 9:52 ` Steve Capper
2013-05-08 9:52 ` Steve Capper
2013-05-16 15:01 ` Catalin Marinas
2013-05-16 15:01 ` Catalin Marinas
2013-05-16 15:01 ` Catalin Marinas
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=20130508120307.GA1407@linaro.org \
--to=steve.capper@linaro.org \
--cc=catalin.marinas@arm.com \
--cc=kenchen@google.com \
--cc=kirill@shutemov.name \
--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=patches@linaro.org \
--cc=will.deacon@arm.com \
--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 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.