Commit 79605093 authored by Michal Hocko's avatar Michal Hocko Committed by Linus Torvalds
Browse files

mm, memory_hotplug: print reason for the offlining failure 

The memory offlining failure reporting is inconsistent and insufficient.
Some error paths simply do not report the failure to the log at all.  When
we do report there are no details about the reason of the failure and
there are several of them which makes memory offlining failures hard to
debug.

Make sure that the
	memory offlining [mem %#010llx-%#010llx] failed
message is printed for all failures and also provide a short textual
reason for the failure e.g.

[ 1984.506184] rac1 kernel: memory offlining [mem 0x82600000000-0x8267fffffff] failed due to signal backoff

this tells us that the offlining has failed because of a signal pending
aka user intervention.

[akpm@linux-foundation.org: tweak messages a bit]
Link: http://lkml.kernel.org/r/20181107101830.17405-5-mhocko@kernel.org


Signed-off-by: default avatarMichal Hocko <mhocko@suse.com>
Reviewed-by: default avatarAndrew Morton <akpm@linux-foundation.org>
Reviewed-by: default avatarOscar Salvador <osalvador@suse.de>
Reviewed-by: default avatarAnshuman Khandual <anshuman.khandual@arm.com>
Cc: Baoquan He <bhe@redhat.com>
Cc: Oscar Salvador <OSalvador@suse.com>
Cc: William Kucharski <william.kucharski@oracle.com>
Signed-off-by: default avatarAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: default avatarLinus Torvalds <torvalds@linux-foundation.org>
parent 6cc2baf6

mm/memory_hotplug.c

+23 −11
Original line number Diff line number Diff line
@@ -1553,6 +1553,7 @@ static int __ref __offline_pages(unsigned long start_pfn, 
	unsigned long valid_start, valid_end;

	struct zone *zone;

	struct memory_notify arg;

	char *reason;



	mem_hotplug_begin();
@@ -1561,7 +1562,9 @@ static int __ref __offline_pages(unsigned long start_pfn, 
	if (!test_pages_in_a_zone(start_pfn, end_pfn, &valid_start,

				  &valid_end)) {

		mem_hotplug_done();

		return -EINVAL;

		ret = -EINVAL;

		reason = "multizone range";

		goto failed_removal;

	}



	zone = page_zone(pfn_to_page(valid_start));
@@ -1573,7 +1576,8 @@ static int __ref __offline_pages(unsigned long start_pfn, 
				       MIGRATE_MOVABLE, true);

	if (ret) {

		mem_hotplug_done();

		return ret;

		reason = "failure to isolate range";

		goto failed_removal;

	}



	arg.start_pfn = start_pfn;
@@ -1582,15 +1586,19 @@ static int __ref __offline_pages(unsigned long start_pfn, 


	ret = memory_notify(MEM_GOING_OFFLINE, &arg);

	ret = notifier_to_errno(ret);

	if (ret)

		goto failed_removal;

	if (ret) {

		reason = "notifier failure";

		goto failed_removal_isolated;

	}



	pfn = start_pfn;

repeat:

	/* start memory hot removal */

	ret = -EINTR;

	if (signal_pending(current))

		goto failed_removal;

	if (signal_pending(current)) {

		reason = "signal backoff";

		goto failed_removal_isolated;

	}



	cond_resched();

	lru_add_drain_all();
@@ -1607,8 +1615,10 @@ repeat: 
	 * actually in order to make hugetlbfs's object counting consistent.

	 */

	ret = dissolve_free_huge_pages(start_pfn, end_pfn);

	if (ret)

		goto failed_removal;

	if (ret) {

		reason = "failure to dissolve huge pages";

		goto failed_removal_isolated;

	}

	/* check again */

	offlined_pages = check_pages_isolated(start_pfn, end_pfn);

	if (offlined_pages < 0)
@@ -1648,13 +1658,15 @@ repeat: 
	mem_hotplug_done();

	return 0;



failed_removal_isolated:

	undo_isolate_page_range(start_pfn, end_pfn, MIGRATE_MOVABLE);

failed_removal:

	pr_debug("memory offlining [mem %#010llx-%#010llx] failed\n",

	pr_debug("memory offlining [mem %#010llx-%#010llx] failed due to %s\n",

		 (unsigned long long) start_pfn << PAGE_SHIFT,

		 ((unsigned long long) end_pfn << PAGE_SHIFT) - 1);

		 ((unsigned long long) end_pfn << PAGE_SHIFT) - 1,

		 reason);

	memory_notify(MEM_CANCEL_OFFLINE, &arg);

	/* pushback to free area */

	undo_isolate_page_range(start_pfn, end_pfn, MIGRATE_MOVABLE);

	mem_hotplug_done();

	return ret;

}

CRA Git | Maintained and supported by SUSTech CRA and CCSE