[RESEND][PATCH] memcg: bugfix for memory hotplug

[RESEND][PATCH] memcg: bugfix for memory hotplug

[KAMEZAWA Hiroyuki]

Although Badari reported another? bug on rc4, this patch is necessary, anyway.
I still chasing that bug but I haven't reproduced yet.
 
I'm now asking Badari for more information and to try mmotm.
(memcg's migration code is much simplified.)

If it's better to stack this on my queue until all problems are fixed,
I'll do so.

Thanks,
-Kame
==
start pfn calculation of page_cgroup's memory hotplug notifier chain
is wrong.

Tested-by: Badari Pulavarty <pbadari@us.ibm.com>
Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>


 mm/page_cgroup.c |    4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

Index: mmotm-2.6.28-Oct30/mm/page_cgroup.c
===================================================================
--- mmotm-2.6.28-Oct30.orig/mm/page_cgroup.c
+++ mmotm-2.6.28-Oct30/mm/page_cgroup.c
@@ -165,7 +165,7 @@ int online_page_cgroup(unsigned long sta
 	unsigned long start, end, pfn;
 	int fail = 0;
 
-	start = start_pfn & (PAGES_PER_SECTION - 1);
+	start = start_pfn & ~(PAGES_PER_SECTION - 1);
 	end = ALIGN(start_pfn + nr_pages, PAGES_PER_SECTION);
 
 	for (pfn = start; !fail && pfn < end; pfn += PAGES_PER_SECTION) {
@@ -188,7 +188,7 @@ int offline_page_cgroup(unsigned long st
 {
 	unsigned long start, end, pfn;
 
-	start = start_pfn & (PAGES_PER_SECTION - 1);
+	start = start_pfn & ~(PAGES_PER_SECTION - 1);
 	end = ALIGN(start_pfn + nr_pages, PAGES_PER_SECTION);
 
 	for (pfn = start; pfn < end; pfn += PAGES_PER_SECTION)

--
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>