linux-mm.kvack.org archive mirror
 help / color / mirror / Atom feed
From: "Raslan, KarimAllah" <karahmed@amazon.de>
To: Michal Hocko <mhocko@kernel.org>
Cc: "linux-mm@kvack.org" <linux-mm@kvack.org>,
	"linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
	Andrew Morton <akpm@linux-foundation.org>,
	Mel Gorman <mgorman@techsingularity.net>,
	Vlastimil Babka <vbabka@suse.cz>,
	Johannes Weiner <hannes@cmpxchg.org>,
	Yaowei Bai <baiyaowei@cmss.chinamobile.com>,
	Dan Williams <dan.j.williams@intel.com>,
	Joe Perches <joe@perches.com>, Tejun Heo <tj@kernel.org>,
	"Liguori, Anthony" <aliguori@amazon.com>,
	"Schoenherr, Jan H." <jschoenh@amazon.de>
Subject: Re: [PATCH] sparse: Track the boundaries of memory sections for accurate checks
Date: Wed, 14 Sep 2016 21:40:39 +0000	[thread overview]
Message-ID: <8B91B5C5-4506-40CB-B7F0-0990A37F95AA@amazon.de> (raw)
In-Reply-To: <20160620082339.GC4340@dhcp22.suse.cz>

[-- Warning: decoded text below may be mangled, UTF-8 assumed --]
[-- Attachment #1: Type: text/plain; charset="utf-8", Size: 6348 bytes --]



On 6/20/16, 10:23 AM, "Michal Hocko" <mhocko@kernel.org> wrote:

    On Sat 18-06-16 12:11:19, KarimAllah Ahmed wrote:
    > When sparse memory model is used an array of memory sections is created to
    > track each block of contiguous physical pages. Each element of this array
    > contains PAGES_PER_SECTION pages. During the creation of this array the actual
    > boundaries of the memory block is lost, so the whole block is either considered
    > as present or not.
    > 
    > pfn_valid() in the sparse memory configuration checks which memory sections the
    > pfn belongs to then checks whether it's present or not. This yields sub-optimal
    > results when the available memory doesn't cover the whole memory section,
    > because pfn_valid will return 'true' even for the unavailable pfns at the
    > boundaries of the memory section.
    
    Please be more verbose of _why_ the patch is needed. Why those
    "sub-optimal results" matter?

Does this make sense to you ?
    
    > Cc: Andrew Morton <akpm@linux-foundation.org>
    > Cc: Mel Gorman <mgorman@techsingularity.net>
    > Cc: Vlastimil Babka <vbabka@suse.cz>
    > Cc: Michal Hocko <mhocko@suse.com>
    > Cc: Johannes Weiner <hannes@cmpxchg.org>
    > Cc: Yaowei Bai <baiyaowei@cmss.chinamobile.com>
    > Cc: Dan Williams <dan.j.williams@intel.com>
    > Cc: Joe Perches <joe@perches.com>
    > Cc: Tejun Heo <tj@kernel.org>
    > Cc: Anthony Liguori <aliguori@amazon.com>
    > Cc: linux-mm@kvack.org
    > Cc: linux-kernel@vger.kernel.org
    > Signed-off-by: KarimAllah Ahmed <karahmed@amazon.de>
    > Signed-off-by: Jan H. Schönherr <jschoenh@amazon.de>
    > ---
    >  include/linux/mmzone.h | 22 ++++++++++++++++------
    >  mm/sparse.c            | 37 ++++++++++++++++++++++++++++++++++++-
    >  2 files changed, 52 insertions(+), 7 deletions(-)
    > 
    > diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
    > index 02069c2..f76a0e1 100644
    > --- a/include/linux/mmzone.h
    > +++ b/include/linux/mmzone.h
    > @@ -1067,8 +1067,12 @@ struct mem_section {
    >  	 * section. (see page_ext.h about this.)
    >  	 */
    >  	struct page_ext *page_ext;
    > -	unsigned long pad;
    > +	unsigned long pad[3];
    >  #endif
    > +
    > +	unsigned long first_pfn;
    > +	unsigned long last_pfn;
    > +
    >  	/*
    >  	 * WARNING: mem_section must be a power-of-2 in size for the
    >  	 * calculation and use of SECTION_ROOT_MASK to make sense.
    > @@ -1140,23 +1144,29 @@ static inline int valid_section_nr(unsigned long nr)
    >  
    >  static inline struct mem_section *__pfn_to_section(unsigned long pfn)
    >  {
    > +	if (pfn_to_section_nr(pfn) >= NR_MEM_SECTIONS)
    > +		return NULL;
    > +
    >  	return __nr_to_section(pfn_to_section_nr(pfn));
    >  }
    >  
    >  #ifndef CONFIG_HAVE_ARCH_PFN_VALID
    >  static inline int pfn_valid(unsigned long pfn)
    >  {
    > -	if (pfn_to_section_nr(pfn) >= NR_MEM_SECTIONS)
    > +	struct mem_section *ms;
    > +
    > +	ms = __pfn_to_section(pfn);
    > +
    > +	if (ms && !(ms->first_pfn <= pfn && ms->last_pfn >= pfn))
    >  		return 0;
    > -	return valid_section(__nr_to_section(pfn_to_section_nr(pfn)));
    > +
    > +	return valid_section(ms);
    >  }
    >  #endif
    >  
    >  static inline int pfn_present(unsigned long pfn)
    >  {
    > -	if (pfn_to_section_nr(pfn) >= NR_MEM_SECTIONS)
    > -		return 0;
    > -	return present_section(__nr_to_section(pfn_to_section_nr(pfn)));
    > +	return present_section(__pfn_to_section(pfn));
    >  }
    >  
    >  /*
    > diff --git a/mm/sparse.c b/mm/sparse.c
    > index 5d0cf45..3c91837 100644
    > --- a/mm/sparse.c
    > +++ b/mm/sparse.c
    > @@ -166,24 +166,59 @@ void __meminit mminit_validate_memmodel_limits(unsigned long *start_pfn,
    >  	}
    >  }
    >  
    > +static int __init
    > +overlaps(u64 start1, u64 end1, u64 start2, u64 end2)
    > +{
    > +	u64 start, end;
    > +
    > +	start = max(start1, start2);
    > +	end = min(end1, end2);
    > +	return start <= end;
    > +}
    > +
    >  /* Record a memory area against a node. */
    >  void __init memory_present(int nid, unsigned long start, unsigned long end)
    >  {
    > +	unsigned long first_pfn = start;
    >  	unsigned long pfn;
    >  
    >  	start &= PAGE_SECTION_MASK;
    >  	mminit_validate_memmodel_limits(&start, &end);
    >  	for (pfn = start; pfn < end; pfn += PAGES_PER_SECTION) {
    >  		unsigned long section = pfn_to_section_nr(pfn);
    > +		unsigned long last_pfn = min(pfn + PAGES_PER_SECTION, end) - 1;
    >  		struct mem_section *ms;
    >  
    >  		sparse_index_init(section, nid);
    >  		set_section_nid(section, nid);
    >  
    >  		ms = __nr_to_section(section);
    > -		if (!ms->section_mem_map)
    > +		if (!ms->section_mem_map) {
    >  			ms->section_mem_map = sparse_encode_early_nid(nid) |
    >  							SECTION_MARKED_PRESENT;
    > +		} else {
    > +			/* Merge the two regions */
    > +			WARN_ON(sparse_early_nid(ms) != nid);
    > +
    > +			/*
    > +			 * If they don't overlap there will be a hole in
    > +			 * between where meta-data says it's valid even though
    > +			 * it's not.
    > +			 */
    > +			if (!overlaps(first_pfn, last_pfn + 1,
    > +				      ms->first_pfn, ms->last_pfn + 1))	{
    > +				pr_info("Merging non-contiguous pfn ranges 0x%lx-0x%lx and 0x%lx-0x%lx\n",
    > +					ms->first_pfn, ms->last_pfn,
    > +					first_pfn, last_pfn);
    > +			}
    > +			first_pfn = min(first_pfn, ms->first_pfn);
    > +			last_pfn = max(last_pfn, ms->last_pfn);
    > +		}
    > +
    > +		ms->first_pfn = first_pfn;
    > +		ms->last_pfn = last_pfn;
    > +
    > +		first_pfn = pfn + PAGES_PER_SECTION;
    >  	}
    >  }
    >  
    > -- 
    > 2.8.2
    > 
    
    -- 
    Michal Hocko
    SUSE Labs
    
    



Amazon Development Center Germany GmbH
Berlin - Dresden - Aachen
main office: Krausenstr. 38, 10117 Berlin
Geschaeftsfuehrer: Dr. Ralf Herbrich, Christian Schlaeger
Ust-ID: DE289237879
Eingetragen am Amtsgericht Charlottenburg HRB 149173 B
N‹§²æìr¸›zǧu©ž²Æ {\b­†éì¹»\x1c®&Þ–)îÆi¢žØ^n‡r¶‰šŽŠÝ¢j$½§$¢¸\x05¢¹¨­è§~Š'.)îÄÃ,yèm¶ŸÿÃ\f%Š{±šj+ƒðèž×¦j)Z†·Ÿ

  parent reply	other threads:[~2016-09-14 21:40 UTC|newest]

Thread overview: 8+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2016-06-18 10:11 KarimAllah Ahmed
2016-06-20  8:23 ` Michal Hocko
2016-06-21 14:33   ` [PATCH v2] " KarimAllah Ahmed
2016-09-14 21:40   ` Raslan, KarimAllah [this message]
2016-09-14 22:05     ` [PATCH] " Dan Williams
2016-09-14 22:11       ` Raslan, KarimAllah
2016-09-14 22:53         ` Dan Williams
2016-09-15  0:05 ` Dave Hansen

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=8B91B5C5-4506-40CB-B7F0-0990A37F95AA@amazon.de \
    --to=karahmed@amazon.de \
    --cc=akpm@linux-foundation.org \
    --cc=aliguori@amazon.com \
    --cc=baiyaowei@cmss.chinamobile.com \
    --cc=dan.j.williams@intel.com \
    --cc=hannes@cmpxchg.org \
    --cc=joe@perches.com \
    --cc=jschoenh@amazon.de \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=mgorman@techsingularity.net \
    --cc=mhocko@kernel.org \
    --cc=tj@kernel.org \
    --cc=vbabka@suse.cz \
    /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