linux-mm.kvack.org archive mirror
 help / color / mirror / Atom feed
From: Qian Cai <cai@lca.pw>
To: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Cc: linux-kernel@vger.kernel.org, linux-mm@kvack.org,
	David Hildenbrand <david@redhat.com>,
	Michal Hocko <mhocko@kernel.org>,
	Mike Kravetz <mike.kravetz@oracle.com>
Subject: memory offline infinite loop after soft offline
Date: Fri, 11 Oct 2019 17:32:44 -0400	[thread overview]
Message-ID: <1570829564.5937.36.camel@lca.pw> (raw)

# /opt/ltp/runtest/bin/move_pages12
move_pages12.c:263: INFO: Free RAM 258988928 kB
move_pages12.c:281: INFO: Increasing 2048kB hugepages pool on node 0 to 4
move_pages12.c:291: INFO: Increasing 2048kB hugepages pool on node 8 to 4
move_pages12.c:207: INFO: Allocating and freeing 4 hugepages on node 0
move_pages12.c:207: INFO: Allocating and freeing 4 hugepages on node 8
move_pages12.c:197: PASS: Bug not reproduced
move_pages12.c:197: PASS: Bug not reproduced

for mem in $(ls -d /sys/devices/system/memory/memory*); do
        echo offline > $mem/state
        echo online > $mem/state
done

That LTP move_pages12 test will first madvise(MADV_SOFT_OFFLINE) for a range.
Then, one of "echo offline" will trigger an infinite loop in __offline_pages()
here,

		/* check again */
		ret = walk_system_ram_range(start_pfn, end_pfn - start_pfn,
					    NULL, check_pages_isolated_cb);
	} while (ret);

because check_pages_isolated_cb() always return -EBUSY from
test_pages_isolated(),


	pfn = __test_page_isolated_in_pageblock(start_pfn, end_pfn,
						skip_hwpoisoned_pages);
        ...
        return pfn < end_pfn ? -EBUSY : 0;

The root cause is in __test_page_isolated_in_pageblock() where "pfn" is always
less than "end_pfn" because the associated page is not a PageBuddy.

	while (pfn < end_pfn) {
	...
		else
			break;

	return pfn;

Adding a dump_page() for that pfn shows,

[  101.665160][ T8885] pfn = 77501, end_pfn = 78000
[  101.665245][ T8885] page:c00c000001dd4040 refcount:0 mapcount:0
mapping:0000000000000000 index:0x0
[  101.665329][ T8885] flags: 0x3fffc000000000()
[  101.665391][ T8885] raw: 003fffc000000000 0000000000000000 ffffffff01dd0500
0000000000000000
[  101.665498][ T8885] raw: 0000000000000000 0000000000000000 00000000ffffffff
0000000000000000
[  101.665588][ T8885] page dumped because: soft_offline
[  101.665639][ T8885] page_owner tracks the page as freed
[  101.665697][ T8885] page last allocated via order 5, migratetype Movable,
gfp_mask
0x346cca(GFP_HIGHUSER_MOVABLE|__GFP_NOWARN|__GFP_RETRY_MAYFAIL|__GFP_COMP|__GFP_
THISNODE)
[  101.665924][ T8885]  prep_new_page+0x3c0/0x440
[  101.665962][ T8885]  get_page_from_freelist+0x2568/0x2bb0
[  101.666059][ T8885]  __alloc_pages_nodemask+0x1b4/0x670
[  101.666115][ T8885]  alloc_fresh_huge_page+0x244/0x6e0
[  101.666183][ T8885]  alloc_migrate_huge_page+0x30/0x70
[  101.666254][ T8885]  alloc_new_node_page+0xc4/0x380
[  101.666325][ T8885]  migrate_pages+0x3b4/0x19e0
[  101.666375][ T8885]  do_move_pages_to_node.isra.29.part.30+0x44/0xa0
[  101.666464][ T8885]  kernel_move_pages+0x498/0xfc0
[  101.666520][ T8885]  sys_move_pages+0x28/0x40
[  101.666643][ T8885]  system_call+0x5c/0x68
[  101.666665][ T8885] page last free stack trace:
[  101.666704][ T8885]  __free_pages_ok+0xa4c/0xd40
[  101.666773][ T8885]  update_and_free_page+0x2dc/0x5b0
[  101.666821][ T8885]  free_huge_page+0x2dc/0x740
[  101.666875][ T8885]  __put_compound_page+0x64/0xc0
[  101.666926][ T8885]  putback_active_hugepage+0x228/0x390
[  101.666990][ T8885]  migrate_pages+0xa78/0x19e0
[  101.667048][ T8885]  soft_offline_page+0x314/0x1050
[  101.667117][ T8885]  sys_madvise+0x1068/0x1080
[  101.667185][ T8885]  system_call+0x5c/0x68


             reply	other threads:[~2019-10-11 21:32 UTC|newest]

Thread overview: 25+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-10-11 21:32 Qian Cai [this message]
2019-10-12 10:30 ` memory offline infinite loop after soft offline osalvador
2019-10-14  8:39 ` Michal Hocko
2019-10-17  9:34   ` Naoya Horiguchi
2019-10-17 10:01     ` Michal Hocko
2019-10-17 10:03       ` David Hildenbrand
2019-10-17 18:07       ` Qian Cai
2019-10-17 18:27         ` Michal Hocko
2019-10-18  2:19           ` Naoya Horiguchi
2019-10-18  6:06             ` Michal Hocko
2019-10-18  6:32               ` Naoya Horiguchi
2019-10-18  7:33                 ` Michal Hocko
2019-10-18  8:46                   ` Naoya Horiguchi
2019-10-18 11:56                 ` Qian Cai
2019-10-21  3:16                   ` Naoya Horiguchi
2020-05-15  2:46                     ` Qian Cai
2020-05-15  3:48                       ` HORIGUCHI NAOYA(堀口 直也)
2019-10-18  8:13             ` David Hildenbrand
2019-10-18  8:24               ` Michal Hocko
2019-10-18  8:38                 ` David Hildenbrand
2019-10-18  8:55                   ` Michal Hocko
2019-10-18 11:00                     ` David Hildenbrand
2019-10-18 11:05                       ` David Hildenbrand
2019-10-18 11:34                       ` Michal Hocko
2019-10-18 11:51                         ` David Hildenbrand

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=1570829564.5937.36.camel@lca.pw \
    --to=cai@lca.pw \
    --cc=david@redhat.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=mhocko@kernel.org \
    --cc=mike.kravetz@oracle.com \
    --cc=n-horiguchi@ah.jp.nec.com \
    /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;
as well as URLs for NNTP newsgroup(s).