From: Alex Shi <alex.shi@linux.alibaba.com>
To: akpm@linux-foundation.org, mgorman@techsingularity.net,
tj@kernel.org, hughd@google.com, khlebnikov@yandex-team.ru,
daniel.m.jordan@oracle.com, willy@infradead.org,
hannes@cmpxchg.org, lkp@intel.com, linux-mm@kvack.org,
linux-kernel@vger.kernel.org, cgroups@vger.kernel.org,
shakeelb@google.com, iamjoonsoo.kim@lge.com,
richard.weiyang@gmail.com, kirill@shutemov.name,
alexander.duyck@gmail.com, rong.a.chen@intel.com,
mhocko@suse.com, vdavydov.dev@gmail.com, shy828301@gmail.com
Subject: [PATCH v21 15/19] mm/compaction: do page isolation first in compaction
Date: Thu, 5 Nov 2020 16:55:45 +0800 [thread overview]
Message-ID: <1604566549-62481-16-git-send-email-alex.shi@linux.alibaba.com> (raw)
In-Reply-To: <1604566549-62481-1-git-send-email-alex.shi@linux.alibaba.com>
Currently, compaction would get the lru_lock and then do page isolation
which works fine with pgdat->lru_lock, since any page isoltion would
compete for the lru_lock. If we want to change to memcg lru_lock, we
have to isolate the page before getting lru_lock, thus isoltion would
block page's memcg change which relay on page isoltion too. Then we
could safely use per memcg lru_lock later.
The new page isolation use previous introduced TestClearPageLRU() +
pgdat lru locking which will be changed to memcg lru lock later.
Hugh Dickins <hughd@google.com> fixed following bugs in this patch's
early version:
Fix lots of crashes under compaction load: isolate_migratepages_block()
must clean up appropriately when rejecting a page, setting PageLRU again
if it had been cleared; and a put_page() after get_page_unless_zero()
cannot safely be done while holding locked_lruvec - it may turn out to
be the final put_page(), which will take an lruvec lock when PageLRU.
And move __isolate_lru_page_prepare back after get_page_unless_zero to
make trylock_page() safe:
trylock_page() is not safe to use at this time: its setting PG_locked
can race with the page being freed or allocated ("Bad page"), and can
also erase flags being set by one of those "sole owners" of a freshly
allocated page who use non-atomic __SetPageFlag().
Suggested-by: Johannes Weiner <hannes@cmpxchg.org>
Signed-off-by: Alex Shi <alex.shi@linux.alibaba.com>
Acked-by: Hugh Dickins <hughd@google.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: linux-kernel@vger.kernel.org
Cc: linux-mm@kvack.org
---
include/linux/swap.h | 2 +-
mm/compaction.c | 42 +++++++++++++++++++++++++++++++++---------
mm/vmscan.c | 43 ++++++++++++++++++++++---------------------
3 files changed, 56 insertions(+), 31 deletions(-)
diff --git a/include/linux/swap.h b/include/linux/swap.h
index 5e1e967c225f..596bc2f4d9b0 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -356,7 +356,7 @@ extern void lru_cache_add_inactive_or_unevictable(struct page *page,
extern unsigned long zone_reclaimable_pages(struct zone *zone);
extern unsigned long try_to_free_pages(struct zonelist *zonelist, int order,
gfp_t gfp_mask, nodemask_t *mask);
-extern int __isolate_lru_page(struct page *page, isolate_mode_t mode);
+extern int __isolate_lru_page_prepare(struct page *page, isolate_mode_t mode);
extern unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg,
unsigned long nr_pages,
gfp_t gfp_mask,
diff --git a/mm/compaction.c b/mm/compaction.c
index ee1f8439369e..7b1cf48884dd 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -886,6 +886,7 @@ static bool too_many_isolated(pg_data_t *pgdat)
if (!valid_page && IS_ALIGNED(low_pfn, pageblock_nr_pages)) {
if (!cc->ignore_skip_hint && get_pageblock_skip(page)) {
low_pfn = end_pfn;
+ page = NULL;
goto isolate_abort;
}
valid_page = page;
@@ -967,6 +968,21 @@ static bool too_many_isolated(pg_data_t *pgdat)
if (!(cc->gfp_mask & __GFP_FS) && page_mapping(page))
goto isolate_fail;
+ /*
+ * Be careful not to clear PageLRU until after we're
+ * sure the page is not being freed elsewhere -- the
+ * page release code relies on it.
+ */
+ if (unlikely(!get_page_unless_zero(page)))
+ goto isolate_fail;
+
+ if (__isolate_lru_page_prepare(page, isolate_mode) != 0)
+ goto isolate_fail_put;
+
+ /* Try isolate the page */
+ if (!TestClearPageLRU(page))
+ goto isolate_fail_put;
+
/* If we already hold the lock, we can skip some rechecking */
if (!locked) {
locked = compact_lock_irqsave(&pgdat->lru_lock,
@@ -979,10 +995,6 @@ static bool too_many_isolated(pg_data_t *pgdat)
goto isolate_abort;
}
- /* Recheck PageLRU and PageCompound under lock */
- if (!PageLRU(page))
- goto isolate_fail;
-
/*
* Page become compound since the non-locked check,
* and it's on LRU. It can only be a THP so the order
@@ -990,16 +1002,13 @@ static bool too_many_isolated(pg_data_t *pgdat)
*/
if (unlikely(PageCompound(page) && !cc->alloc_contig)) {
low_pfn += compound_nr(page) - 1;
- goto isolate_fail;
+ SetPageLRU(page);
+ goto isolate_fail_put;
}
}
lruvec = mem_cgroup_page_lruvec(page, pgdat);
- /* Try isolate the page */
- if (__isolate_lru_page(page, isolate_mode) != 0)
- goto isolate_fail;
-
/* The whole page is taken off the LRU; skip the tail pages. */
if (PageCompound(page))
low_pfn += compound_nr(page) - 1;
@@ -1028,6 +1037,15 @@ static bool too_many_isolated(pg_data_t *pgdat)
}
continue;
+
+isolate_fail_put:
+ /* Avoid potential deadlock in freeing page under lru_lock */
+ if (locked) {
+ spin_unlock_irqrestore(&pgdat->lru_lock, flags);
+ locked = false;
+ }
+ put_page(page);
+
isolate_fail:
if (!skip_on_failure)
continue;
@@ -1064,9 +1082,15 @@ static bool too_many_isolated(pg_data_t *pgdat)
if (unlikely(low_pfn > end_pfn))
low_pfn = end_pfn;
+ page = NULL;
+
isolate_abort:
if (locked)
spin_unlock_irqrestore(&pgdat->lru_lock, flags);
+ if (page) {
+ SetPageLRU(page);
+ put_page(page);
+ }
/*
* Updated the cached scanner pfn once the pageblock has been scanned
diff --git a/mm/vmscan.c b/mm/vmscan.c
index ab7a0104d1e1..0be55d875fde 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1540,7 +1540,7 @@ unsigned int reclaim_clean_pages_from_list(struct zone *zone,
*
* returns 0 on success, -ve errno on failure.
*/
-int __isolate_lru_page(struct page *page, isolate_mode_t mode)
+int __isolate_lru_page_prepare(struct page *page, isolate_mode_t mode)
{
int ret = -EBUSY;
@@ -1592,22 +1592,9 @@ int __isolate_lru_page(struct page *page, isolate_mode_t mode)
if ((mode & ISOLATE_UNMAPPED) && page_mapped(page))
return ret;
- if (likely(get_page_unless_zero(page))) {
- /*
- * Be careful not to clear PageLRU until after we're
- * sure the page is not being freed elsewhere -- the
- * page release code relies on it.
- */
- if (TestClearPageLRU(page))
- ret = 0;
- else
- put_page(page);
- }
-
- return ret;
+ return 0;
}
-
/*
* Update LRU sizes after isolating pages. The LRU size updates must
* be complete before mem_cgroup_update_lru_size due to a sanity check.
@@ -1687,20 +1674,34 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
* only when the page is being freed somewhere else.
*/
scan += nr_pages;
- switch (__isolate_lru_page(page, mode)) {
+ switch (__isolate_lru_page_prepare(page, mode)) {
case 0:
+ /*
+ * Be careful not to clear PageLRU until after we're
+ * sure the page is not being freed elsewhere -- the
+ * page release code relies on it.
+ */
+ if (unlikely(!get_page_unless_zero(page)))
+ goto busy;
+
+ if (!TestClearPageLRU(page)) {
+ /*
+ * This page may in other isolation path,
+ * but we still hold lru_lock.
+ */
+ put_page(page);
+ goto busy;
+ }
+
nr_taken += nr_pages;
nr_zone_taken[page_zonenum(page)] += nr_pages;
list_move(&page->lru, dst);
break;
- case -EBUSY:
+ default:
+busy:
/* else it is being freed elsewhere */
list_move(&page->lru, src);
- continue;
-
- default:
- BUG();
}
}
--
1.8.3.1
next prev parent reply other threads:[~2020-11-05 8:56 UTC|newest]
Thread overview: 59+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-11-05 8:55 [PATCH v21 00/19] per memcg lru lock Alex Shi
2020-11-05 8:55 ` [PATCH v21 01/19] mm/thp: move lru_add_page_tail func to huge_memory.c Alex Shi
2020-11-05 8:55 ` [PATCH v21 02/19] mm/thp: use head for head page in lru_add_page_tail Alex Shi
2020-11-05 8:55 ` [PATCH v21 03/19] mm/thp: Simplify lru_add_page_tail() Alex Shi
2020-11-05 8:55 ` [PATCH v21 04/19] mm/thp: narrow lru locking Alex Shi
2020-11-05 8:55 ` [PATCH v21 05/19] mm/vmscan: remove unnecessary lruvec adding Alex Shi
2020-11-11 12:36 ` Vlastimil Babka
2020-11-05 8:55 ` [PATCH v21 06/19] mm/rmap: stop store reordering issue on page->mapping Alex Shi
2020-11-06 1:20 ` Alex Shi
2020-11-10 19:06 ` Johannes Weiner
2020-11-11 7:41 ` Hugh Dickins
2020-11-05 8:55 ` [PATCH v21 07/19] mm: page_idle_get_page() does not need lru_lock Alex Shi
2020-11-10 19:01 ` Johannes Weiner
2020-11-11 8:17 ` huang ying
2020-11-11 12:52 ` Vlastimil Babka
2020-11-05 8:55 ` [PATCH v21 08/19] mm/memcg: add debug checking in lock_page_memcg Alex Shi
2020-11-05 8:55 ` [PATCH v21 09/19] mm/swap.c: fold vm event PGROTATED into pagevec_move_tail_fn Alex Shi
2020-11-05 8:55 ` [PATCH v21 10/19] mm/lru: move lock into lru_note_cost Alex Shi
2020-11-05 8:55 ` [PATCH v21 11/19] mm/vmscan: remove lruvec reget in move_pages_to_lru Alex Shi
2020-11-05 8:55 ` [PATCH v21 12/19] mm/mlock: remove lru_lock on TestClearPageMlocked Alex Shi
2020-11-11 13:03 ` Vlastimil Babka
2020-11-05 8:55 ` [PATCH v21 13/19] mm/mlock: remove __munlock_isolate_lru_page Alex Shi
2020-11-11 13:07 ` Vlastimil Babka
2020-11-05 8:55 ` [PATCH v21 14/19] mm/lru: introduce TestClearPageLRU Alex Shi
2020-11-11 13:36 ` Vlastimil Babka
2020-11-12 2:03 ` Hugh Dickins
2020-11-12 11:24 ` Vlastimil Babka
2020-11-05 8:55 ` Alex Shi [this message]
2020-11-11 17:12 ` [PATCH v21 15/19] mm/compaction: do page isolation first in compaction Vlastimil Babka
2020-11-12 2:28 ` Hugh Dickins
2020-11-12 3:35 ` Alex Shi
2020-11-12 11:25 ` Vlastimil Babka
2020-11-05 8:55 ` [PATCH v21 16/19] mm/swap.c: serialize memcg changes in pagevec_lru_move_fn Alex Shi
2020-11-11 18:00 ` Vlastimil Babka
2020-11-05 8:55 ` [PATCH v21 17/19] mm/lru: replace pgdat lru_lock with lruvec lock Alex Shi
2020-11-05 13:43 ` Alex Shi
2020-11-06 7:48 ` Alex Shi
2020-11-10 18:54 ` Johannes Weiner
2020-11-11 17:46 ` Vlastimil Babka
2020-11-11 17:59 ` Vlastimil Babka
2020-11-12 12:19 ` Vlastimil Babka
2020-11-12 14:19 ` Alex Shi
2020-11-05 8:55 ` [PATCH v21 18/19] mm/lru: introduce the relock_page_lruvec function Alex Shi
2020-11-06 7:50 ` Alex Shi
2020-11-10 18:59 ` Johannes Weiner
2020-11-12 12:31 ` Vlastimil Babka
2020-11-05 8:55 ` [PATCH v21 19/19] mm/lru: revise the comments of lru_lock Alex Shi
2020-11-12 12:37 ` Vlastimil Babka
2020-11-10 12:14 ` [PATCH v21 00/19] per memcg lru lock Alex Shi
2020-11-16 3:45 ` Alex Shi
2020-12-15 0:47 ` Andrew Morton
2020-12-15 2:16 ` Hugh Dickins
2020-12-15 2:28 ` Andrew Morton
2021-01-05 19:30 ` Qian Cai
2021-01-05 19:42 ` Shakeel Butt
2021-01-05 20:11 ` Qian Cai
2021-01-05 21:35 ` Hugh Dickins
2021-01-05 22:01 ` Qian Cai
2021-01-06 3:10 ` Hugh Dickins
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=1604566549-62481-16-git-send-email-alex.shi@linux.alibaba.com \
--to=alex.shi@linux.alibaba.com \
--cc=akpm@linux-foundation.org \
--cc=alexander.duyck@gmail.com \
--cc=cgroups@vger.kernel.org \
--cc=daniel.m.jordan@oracle.com \
--cc=hannes@cmpxchg.org \
--cc=hughd@google.com \
--cc=iamjoonsoo.kim@lge.com \
--cc=khlebnikov@yandex-team.ru \
--cc=kirill@shutemov.name \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=lkp@intel.com \
--cc=mgorman@techsingularity.net \
--cc=mhocko@suse.com \
--cc=richard.weiyang@gmail.com \
--cc=rong.a.chen@intel.com \
--cc=shakeelb@google.com \
--cc=shy828301@gmail.com \
--cc=tj@kernel.org \
--cc=vdavydov.dev@gmail.com \
--cc=willy@infradead.org \
/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).