lists.openwall.net   lists  /  announce  owl-users  owl-dev  john-users  john-dev  passwdqc-users  yescrypt  popa3d-users  /  oss-security  kernel-hardening  musl  sabotage  tlsify  passwords  /  crypt-dev  xvendor  /  Bugtraq  Full-Disclosure  linux-kernel  linux-netdev  linux-ext4  linux-hardening  linux-cve-announce  PHC 
Open Source and information security mailing list archives
 
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Date:	Wed, 14 Jul 2010 09:23:01 +0900
From:	KAMEZAWA Hiroyuki <kamezawa.hiroyu@...fujitsu.com>
To:	Minchan Kim <minchan.kim@...il.com>
Cc:	Dave Hansen <dave@...ux.vnet.ibm.com>,
	Johannes Weiner <hannes@...xchg.org>, linux@....linux.org.uk,
	Yinghai Lu <yinghai@...nel.org>,
	"H. Peter Anvin" <hpa@...or.com>,
	Andrew Morton <akpm@...ux-foundation.org>,
	Shaohua Li <shaohua.li@...el.com>,
	Yakui Zhao <yakui.zhao@...el.com>,
	linux-kernel@...r.kernel.org, linux-mm@...ck.org,
	arm-kernel@...ts.infradead.org, kgene.kim@...sung.com,
	Mel Gorman <mel@....ul.ie>
Subject: Re: [RFC] Tight check of pfn_valid on sparsemem

On Wed, 14 Jul 2010 01:44:23 +0900
Minchan Kim <minchan.kim@...il.com> wrote:
 
> > If you _really_ can't make the section size smaller, and the vast
> > majority of the sections are fully populated, you could hack something
> > in.  We could, for instance, have a global list that's mostly readonly
> > which tells you which sections need to be have their sizes closely
> > inspected.  That would work OK if, for instance, you only needed to
> > check a couple of memory sections in the system.  It'll start to suck if
> > you made the lists very long.
> 
> Thanks for advise. As I say, I hope Russell accept 16M section. 
> 

It seems what I needed was good sleep....
How about this if 16M section is not acceptable ?

== NOT TESTED AT ALL, EVEN NOT COMPILED ==

register address of mem_section to memmap itself's page struct's pg->private field.
This means the page is used for memmap of the section.
Otherwise, the page is used for other purpose and memmap has a hole.

---
 arch/arm/mm/init.c     |   11 ++++++++++-
 include/linux/mmzone.h |   19 ++++++++++++++++++-
 mm/sparse.c            |   37 +++++++++++++++++++++++++++++++++++++
 3 files changed, 65 insertions(+), 2 deletions(-)

Index: mmotm-2.6.35-0701/include/linux/mmzone.h
===================================================================
--- mmotm-2.6.35-0701.orig/include/linux/mmzone.h
+++ mmotm-2.6.35-0701/include/linux/mmzone.h
@@ -1047,11 +1047,28 @@ static inline struct mem_section *__pfn_
 	return __nr_to_section(pfn_to_section_nr(pfn));
 }
 
+#ifdef CONFIG_SPARSEMEM_HAS_PIT
+void mark_memmap_pit(unsigned long start, unsigned long end, bool valid);
+static inline int page_valid(struct mem_section *ms, unsigned long pfn)
+{
+	struct page *page = pfn_to_page(pfn);
+	struct page *__pg = virt_to_page(page);
+	return __pg->private == ms;
+}
+#else
+static inline int page_valid(struct mem_section *ms, unsigned long pfn)
+{
+	return 1;
+}
+#endif
+
 static inline int pfn_valid(unsigned long pfn)
 {
+	struct mem_section *ms;
 	if (pfn_to_section_nr(pfn) >= NR_MEM_SECTIONS)
 		return 0;
-	return valid_section(__nr_to_section(pfn_to_section_nr(pfn)));
+	ms = __nr_to_section(pfn_to_section_nr(pfn));
+	return valid_section(ms) && page_valid(ms, pfn);
 }
 
 static inline int pfn_present(unsigned long pfn)
Index: mmotm-2.6.35-0701/mm/sparse.c
===================================================================
--- mmotm-2.6.35-0701.orig/mm/sparse.c
+++ mmotm-2.6.35-0701/mm/sparse.c
@@ -615,6 +615,43 @@ void __init sparse_init(void)
 	free_bootmem(__pa(usemap_map), size);
 }
 
+#ifdef CONFIT_SPARSEMEM_HAS_PIT
+/*
+ * Fill memmap's pg->private with a pointer to mem_section.
+ * pfn_valid() will check this later. (see include/linux/mmzone.h)
+ * The caller should call 
+ * 	mark_memmap_pit(start, end, true) # for all allocated mem_map
+ * 	and, after that,
+ * 	mark_memmap_pit(start, end, false) # for all pits in mem_map.
+ * please see usage in ARM.
+ */
+void mark_memmap_pit(unsigned long start, unsigned long end, bool valid)
+{
+	struct mem_section *ms;
+	unsigned long pos, next;
+	struct page *pg;
+	void *memmap, *end;
+	unsigned long mapsize = sizeof(struct page) * PAGES_PER_SECTION;
+
+	for (pos = start;
+	     pos < end; pos = next) {
+		next = (pos + PAGES_PER_SECTION) & PAGE_SECTION_MASK;
+		ms = __pfn_to_section(pos);
+		if (!valid_section(ms))
+			continue;
+		for (memmap = pfn_to_page(pfn), end = pfn_to_page(next-1);
+		     memmap != end + 1;
+		     memmap += PAGE_SIZE) {
+			pg = virt_to_page(memmap);
+			if (valid)
+				pg->private = ms;
+			else
+				pg->private = NULL;
+		}
+	}
+}
+#endif
+
 #ifdef CONFIG_MEMORY_HOTPLUG
 #ifdef CONFIG_SPARSEMEM_VMEMMAP
 static inline struct page *kmalloc_section_memmap(unsigned long pnum, int nid,
Index: mmotm-2.6.35-0701/arch/arm/mm/init.c
===================================================================
--- mmotm-2.6.35-0701.orig/arch/arm/mm/init.c
+++ mmotm-2.6.35-0701/arch/arm/mm/init.c
@@ -234,6 +234,13 @@ static void __init arm_bootmem_free(stru
 	arch_adjust_zones(zone_size, zhole_size);
 
 	free_area_init_node(0, zone_size, min, zhole_size);
+
+#ifdef CONFIG_SPARSEMEM
+	for_each_bank(i, mi) {
+		mark_memmap_pit(bank_start_pfn(mi->bank[i]),
+				bank_end_pfn(mi->bank[i]), true);
+	}
+#endif
 }
 
 #ifndef CONFIG_SPARSEMEM
@@ -386,8 +393,10 @@ free_memmap(unsigned long start_pfn, uns
 	 * If there are free pages between these,
 	 * free the section of the memmap array.
 	 */
-	if (pg < pgend)
+	if (pg < pgend) {
+		mark_memap_pit(pg >> PAGE_SHIFT, pgend >> PAGE_SHIFT, false);
 		free_bootmem(pg, pgend - pg);
+	}
 }
 
 /*

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/

Powered by blists - more mailing lists

Powered by Openwall GNU/*/Linux Powered by OpenVZ