memory-hotplug: try to offline the memory twice to avoid dependence

memory can't be offlined when CONFIG_MEMCG is selected. For example: there is a memory device on node 1. The address range is [1G, 1.5G). You will find 4 new directories memory8, memory9, memory10, and memory11 under the directory /sys/devices/system/memory/. If CONFIG_MEMCG is selected, we will allocate memory to store page cgroup when we online pages. When we online memory8, the memory stored page cgroup is not provided by this memory device. But when we online memory9, the memory stored page cgroup may be provided by memory8. So we can't offline memory8 now. We should offline the memory in the reversed order. When the memory device is hotremoved, we will auto offline memory provided by this memory device. But we don't know which memory is onlined first, so offlining memory may fail. In such case, iterate twice to offline the memory. 1st iterate: offline every non primary memory block. 2nd iterate: offline primary (i.e. first added) memory block. This idea is suggested by KOSAKI Motohiro. Signed-off-by: Wen Congyang <wency@cn.fujitsu.com> Signed-off-by: Tang Chen <tangchen@cn.fujitsu.com> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Jiang Liu <jiang.liu@huawei.com> Cc: Jianguo Wu <wujianguo@huawei.com> Cc: Kamezawa Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Lai Jiangshan <laijs@cn.fujitsu.com> Cc: Wu Jianguo <wujianguo@huawei.com> Cc: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: "H. Peter Anvin" <hpa@zytor.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

memory-hotplug: try to offline the memory twice to avoid dependence
memory can't be offlined when CONFIG_MEMCG is selected. For example: there is a memory device on node 1. The address range is [1G, 1.5G). You will find 4 new directories memory8, memory9, memory10, and memory11 under the directory /sys/devices/system/memory/. If CONFIG_MEMCG is selected, we will allocate memory to store page cgroup when we online pages. When we online memory8, the memory stored page cgroup is not provided by this memory device. But when we online memory9, the memory stored page cgroup may be provided by memory8. So we can't offline memory8 now. We should offline the memory in the reversed order. When the memory device is hotremoved, we will auto offline memory provided by this memory device. But we don't know which memory is onlined first, so offlining memory may fail. In such case, iterate twice to offline the memory. 1st iterate: offline every non primary memory block. 2nd iterate: offline primary (i.e. first added) memory block. This idea is suggested by KOSAKI Motohiro. Signed-off-by: Wen Congyang <wency@cn.fujitsu.com> Signed-off-by: Tang Chen <tangchen@cn.fujitsu.com> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Jiang Liu <jiang.liu@huawei.com> Cc: Jianguo Wu <wujianguo@huawei.com> Cc: Kamezawa Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Lai Jiangshan <laijs@cn.fujitsu.com> Cc: Wu Jianguo <wujianguo@huawei.com> Cc: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: "H. Peter Anvin" <hpa@zytor.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Wen Congyang · Linus Torvalds
1 parent a864b9d06c
Showing 1 changed file with 14 additions and 2 deletions Side-by-side Diff
mm/memory_hotplug.c
@@ -1387,10 +1387,13 @@
 	unsigned long start_pfn, end_pfn;
 	unsigned long pfn, section_nr;
 	int ret;
+	int return_on_error = 0;
+	int retry = 0;
  
 	start_pfn = PFN_DOWN(start);
 	end_pfn = start_pfn + PFN_DOWN(size);
  
+repeat:
 	for (pfn = start_pfn; pfn < end_pfn; pfn += PAGES_PER_SECTION) {
 		section_nr = pfn_to_section_nr(pfn);
 		if (!present_section_nr(section_nr))
  
@@ -1409,13 +1412,22 @@
  
 		ret = offline_memory_block(mem);
 		if (ret) {
-			kobject_put(&mem->dev.kobj);
-			return ret;
+			if (return_on_error) {
+				kobject_put(&mem->dev.kobj);
+				return ret;
+			} else {
+				retry = 1;
+			}
 		}
 	}
  
 	if (mem)
 		kobject_put(&mem->dev.kobj);
+
+	if (retry) {
+		return_on_error = 1;
+		goto repeat;
+	}
  
 	return 0;
 }
...	...	@@ -1387,10 +1387,13 @@
1387	1387	unsigned long start_pfn, end_pfn;
1388	1388	unsigned long pfn, section_nr;
1389	1389	int ret;
	1390	+ int return_on_error = 0;
	1391	+ int retry = 0;
1390	1392
1391	1393	start_pfn = PFN_DOWN(start);
1392	1394	end_pfn = start_pfn + PFN_DOWN(size);
1393	1395
	1396	+repeat:
1394	1397	for (pfn = start_pfn; pfn < end_pfn; pfn += PAGES_PER_SECTION) {
1395	1398	section_nr = pfn_to_section_nr(pfn);
1396	1399	if (!present_section_nr(section_nr))
1397	1400
...	...	@@ -1409,13 +1412,22 @@
1409	1412
1410	1413	ret = offline_memory_block(mem);
1411	1414	if (ret) {
1412		- kobject_put(&mem->dev.kobj);
1413		- return ret;
	1415	+ if (return_on_error) {
	1416	+ kobject_put(&mem->dev.kobj);
	1417	+ return ret;
	1418	+ } else {
	1419	+ retry = 1;
	1420	+ }
1414	1421	}
1415	1422	}
1416	1423
1417	1424	if (mem)
1418	1425	kobject_put(&mem->dev.kobj);
	1426	+
	1427	+ if (retry) {
	1428	+ return_on_error = 1;
	1429	+ goto repeat;
	1430	+ }
1419	1431
1420	1432	return 0;
1421	1433	}