All of lore.kernel.org
 help / color / mirror / Atom feed
From: Alexander Duyck <alexander.duyck@gmail.com>
To: alex.shi@linux.alibaba.com
Cc: yang.shi@linux.alibaba.com, lkp@intel.com, rong.a.chen@intel.com,
	khlebnikov@yandex-team.ru, kirill@shutemov.name,
	hughd@google.com, linux-kernel@vger.kernel.org,
	alexander.duyck@gmail.com, daniel.m.jordan@oracle.com,
	linux-mm@kvack.org, shakeelb@google.com, willy@infradead.org,
	hannes@cmpxchg.org, tj@kernel.org, cgroups@vger.kernel.org,
	akpm@linux-foundation.org, richard.weiyang@gmail.com,
	mgorman@techsingularity.net, iamjoonsoo.kim@lge.com
Subject: [RFC PATCH 3/3] mm: Identify compound pages sooner in isolate_migratepages_block
Date: Wed, 12 Aug 2020 21:02:40 -0700	[thread overview]
Message-ID: <20200813040240.13054.76770.stgit@localhost.localdomain> (raw)
In-Reply-To: <20200813035100.13054.25671.stgit@localhost.localdomain>

From: Alexander Duyck <alexander.h.duyck@linux.intel.com>

Since we are holding a reference to the page much sooner in
isolate_migratepages_block we could move the PageCompound check out of the
LRU locked section and instead just place it after get_page_unless_zero. By
doing this we can allow any of the items that might trigger a failure to
trigger a failure for the compound page rather than the order 0 page and as
a result we should be able to process the pageblock faster.

In addition by testing for PageCompound sooner we can avoid having the LRU
flag cleared and then reset in the exception case. As a result this should
prevent any possible races where another thread might be attempting to pull
the LRU pages from the list.

Signed-off-by: Alexander Duyck <alexander.h.duyck@linux.intel.com>
---
 mm/compaction.c |   33 ++++++++++++++++++---------------
 1 file changed, 18 insertions(+), 15 deletions(-)

diff --git a/mm/compaction.c b/mm/compaction.c
index c1e9918f9dd4..3803f129fd6a 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -954,6 +954,24 @@ static bool too_many_isolated(pg_data_t *pgdat)
 		if (unlikely(!get_page_unless_zero(page)))
 			goto isolate_fail;
 
+		/*
+		 * Page is compound. We know the order before we know if it is
+		 * on the LRU so we cannot assume it is THP. However since the
+		 * page will have the LRU validated shortly we can use the value
+		 * to skip over this page for now or validate the LRU is set and
+		 * then isolate the entire compound page if we are isolating to
+		 * generate a CMA page.
+		 */
+		if (PageCompound(page)) {
+			const unsigned int order = compound_order(page);
+
+			if (likely(order < MAX_ORDER))
+				low_pfn += (1UL << order) - 1;
+
+			if (!cc->alloc_contig)
+				goto isolate_fail_put;
+		}
+
 		if (__isolate_lru_page_prepare(page, isolate_mode) != 0)
 			goto isolate_fail_put;
 
@@ -978,23 +996,8 @@ static bool too_many_isolated(pg_data_t *pgdat)
 			rcu_read_unlock();
 
 			lruvec_memcg_debug(lruvec, page);
-
-			/*
-			 * Page become compound since the non-locked check,
-			 * and it's on LRU. It can only be a THP so the order
-			 * is safe to read and it's 0 for tail pages.
-			 */
-			if (unlikely(PageCompound(page) && !cc->alloc_contig)) {
-				low_pfn += compound_nr(page) - 1;
-				SetPageLRU(page);
-				goto isolate_fail_put;
-			}
 		}
 
-		/* The whole page is taken off the LRU; skip the tail pages. */
-		if (PageCompound(page))
-			low_pfn += compound_nr(page) - 1;
-
 		/* Successfully isolated */
 		del_page_from_lru_list(page, lruvec, page_lru(page));
 		mod_node_page_state(page_pgdat(page),


WARNING: multiple messages have this Message-ID (diff)
From: Alexander Duyck <alexander.duyck-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org>
To: alex.shi-KPsoFbNs7GizrGE5bRqYAgC/G2K4zDHf@public.gmane.org
Cc: yang.shi-KPsoFbNs7GizrGE5bRqYAgC/G2K4zDHf@public.gmane.org,
	lkp-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org,
	rong.a.chen-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org,
	khlebnikov-XoJtRXgx1JseBXzfvpsJ4g@public.gmane.org,
	kirill-oKw7cIdHH8eLwutG50LtGA@public.gmane.org,
	hughd-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org,
	linux-kernel-u79uwXL29TY76Z2rM5mHXA@public.gmane.org,
	alexander.duyck-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org,
	daniel.m.jordan-QHcLZuEGTsvQT0dZR+AlfA@public.gmane.org,
	linux-mm-Bw31MaZKKs3YtjvyW6yDsg@public.gmane.org,
	shakeelb-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org,
	willy-wEGCiKHe2LqWVfeAwA7xHQ@public.gmane.org,
	hannes-druUgvl0LCNAfugRpC6u6w@public.gmane.org,
	tj-DgEjT+Ai2ygdnm+yROfE0A@public.gmane.org,
	cgroups-u79uwXL29TY76Z2rM5mHXA@public.gmane.org,
	akpm-de/tnXTf+JLsfHDXvbKv3WD2FQJk+8+b@public.gmane.org,
	richard.weiyang-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org,
	mgorman-3eNAlZScCAx27rWaFMvyedHuzzzSOjJt@public.gmane.org,
	iamjoonsoo.kim-Hm3cg6mZ9cc@public.gmane.org
Subject: [RFC PATCH 3/3] mm: Identify compound pages sooner in isolate_migratepages_block
Date: Wed, 12 Aug 2020 21:02:40 -0700	[thread overview]
Message-ID: <20200813040240.13054.76770.stgit@localhost.localdomain> (raw)
In-Reply-To: <20200813035100.13054.25671.stgit-bi+AKbBUZKY6gyzm1THtWbp2dZbC/Bob@public.gmane.org>

From: Alexander Duyck <alexander.h.duyck-VuQAYsv1563Yd54FQh9/CA@public.gmane.org>

Since we are holding a reference to the page much sooner in
isolate_migratepages_block we could move the PageCompound check out of the
LRU locked section and instead just place it after get_page_unless_zero. By
doing this we can allow any of the items that might trigger a failure to
trigger a failure for the compound page rather than the order 0 page and as
a result we should be able to process the pageblock faster.

In addition by testing for PageCompound sooner we can avoid having the LRU
flag cleared and then reset in the exception case. As a result this should
prevent any possible races where another thread might be attempting to pull
the LRU pages from the list.

Signed-off-by: Alexander Duyck <alexander.h.duyck-VuQAYsv1563Yd54FQh9/CA@public.gmane.org>
---
 mm/compaction.c |   33 ++++++++++++++++++---------------
 1 file changed, 18 insertions(+), 15 deletions(-)

diff --git a/mm/compaction.c b/mm/compaction.c
index c1e9918f9dd4..3803f129fd6a 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -954,6 +954,24 @@ static bool too_many_isolated(pg_data_t *pgdat)
 		if (unlikely(!get_page_unless_zero(page)))
 			goto isolate_fail;
 
+		/*
+		 * Page is compound. We know the order before we know if it is
+		 * on the LRU so we cannot assume it is THP. However since the
+		 * page will have the LRU validated shortly we can use the value
+		 * to skip over this page for now or validate the LRU is set and
+		 * then isolate the entire compound page if we are isolating to
+		 * generate a CMA page.
+		 */
+		if (PageCompound(page)) {
+			const unsigned int order = compound_order(page);
+
+			if (likely(order < MAX_ORDER))
+				low_pfn += (1UL << order) - 1;
+
+			if (!cc->alloc_contig)
+				goto isolate_fail_put;
+		}
+
 		if (__isolate_lru_page_prepare(page, isolate_mode) != 0)
 			goto isolate_fail_put;
 
@@ -978,23 +996,8 @@ static bool too_many_isolated(pg_data_t *pgdat)
 			rcu_read_unlock();
 
 			lruvec_memcg_debug(lruvec, page);
-
-			/*
-			 * Page become compound since the non-locked check,
-			 * and it's on LRU. It can only be a THP so the order
-			 * is safe to read and it's 0 for tail pages.
-			 */
-			if (unlikely(PageCompound(page) && !cc->alloc_contig)) {
-				low_pfn += compound_nr(page) - 1;
-				SetPageLRU(page);
-				goto isolate_fail_put;
-			}
 		}
 
-		/* The whole page is taken off the LRU; skip the tail pages. */
-		if (PageCompound(page))
-			low_pfn += compound_nr(page) - 1;
-
 		/* Successfully isolated */
 		del_page_from_lru_list(page, lruvec, page_lru(page));
 		mod_node_page_state(page_pgdat(page),


  parent reply	other threads:[~2020-08-13  4:02 UTC|newest]

Thread overview: 209+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-07-25 12:59 [PATCH v17 00/21] per memcg lru lock Alex Shi
2020-07-25 12:59 ` Alex Shi
2020-07-25 12:59 ` [PATCH v17 01/21] mm/vmscan: remove unnecessary lruvec adding Alex Shi
2020-08-06  3:47   ` Alex Shi
2020-08-06  3:47     ` Alex Shi
2020-07-25 12:59 ` [PATCH v17 02/21] mm/page_idle: no unlikely double check for idle page counting Alex Shi
2020-07-25 12:59 ` [PATCH v17 03/21] mm/compaction: correct the comments of compact_defer_shift Alex Shi
2020-07-27 17:29   ` Alexander Duyck
2020-07-27 17:29     ` Alexander Duyck
2020-07-28 11:59     ` Alex Shi
2020-07-28 11:59       ` Alex Shi
2020-07-28 14:17       ` Alexander Duyck
2020-07-28 14:17         ` Alexander Duyck
2020-07-28 14:17         ` Alexander Duyck
2020-07-25 12:59 ` [PATCH v17 04/21] mm/compaction: rename compact_deferred as compact_should_defer Alex Shi
2020-07-25 12:59   ` Alex Shi
2020-07-25 12:59 ` [PATCH v17 05/21] mm/thp: move lru_add_page_tail func to huge_memory.c Alex Shi
2020-07-25 12:59   ` Alex Shi
2020-07-25 12:59 ` [PATCH v17 06/21] mm/thp: clean up lru_add_page_tail Alex Shi
2020-07-25 12:59 ` [PATCH v17 07/21] mm/thp: remove code path which never got into Alex Shi
2020-07-25 12:59 ` [PATCH v17 08/21] mm/thp: narrow lru locking Alex Shi
2020-07-25 12:59 ` [PATCH v17 09/21] mm/memcg: add debug checking in lock_page_memcg Alex Shi
2020-07-25 12:59   ` Alex Shi
2020-07-25 12:59 ` [PATCH v17 10/21] mm/swap: fold vm event PGROTATED into pagevec_move_tail_fn Alex Shi
2020-07-25 12:59 ` [PATCH v17 11/21] mm/lru: move lru_lock holding in func lru_note_cost_page Alex Shi
2020-08-05 21:18   ` Alexander Duyck
2020-08-05 21:18     ` Alexander Duyck
2020-08-05 21:18     ` Alexander Duyck
2020-07-25 12:59 ` [PATCH v17 12/21] mm/lru: move lock into lru_note_cost Alex Shi
2020-07-25 12:59   ` Alex Shi
2020-07-25 12:59 ` [PATCH v17 13/21] mm/lru: introduce TestClearPageLRU Alex Shi
2020-07-25 12:59   ` Alex Shi
2020-07-29  3:53   ` Alex Shi
2020-07-29  3:53     ` Alex Shi
2020-08-05 22:43     ` Alexander Duyck
2020-08-05 22:43       ` Alexander Duyck
2020-08-06  1:54       ` Alex Shi
2020-08-06  1:54         ` Alex Shi
2020-08-06 14:41         ` Alexander Duyck
2020-08-06 14:41           ` Alexander Duyck
2020-07-25 12:59 ` [PATCH v17 14/21] mm/compaction: do page isolation first in compaction Alex Shi
2020-08-04 21:35   ` Alexander Duyck
2020-08-04 21:35     ` Alexander Duyck
2020-08-04 21:35     ` Alexander Duyck
2020-08-06 18:38   ` Alexander Duyck
2020-08-06 18:38     ` Alexander Duyck
2020-08-06 18:38     ` Alexander Duyck
2020-08-07  3:24     ` Alex Shi
2020-08-07  3:24       ` Alex Shi
2020-08-07 14:51       ` Alexander Duyck
2020-08-07 14:51         ` Alexander Duyck
2020-08-07 14:51         ` Alexander Duyck
2020-08-10 13:10         ` Alex Shi
2020-08-10 13:10           ` Alex Shi
2020-08-10 14:41           ` Alexander Duyck
2020-08-10 14:41             ` Alexander Duyck
2020-08-10 14:41             ` Alexander Duyck
2020-08-11  8:22             ` Alex Shi
2020-08-11 14:47               ` Alexander Duyck
2020-08-11 14:47                 ` Alexander Duyck
2020-08-11 14:47                 ` Alexander Duyck
2020-08-12 11:43                 ` Alex Shi
2020-08-12 12:16                   ` Alex Shi
2020-08-12 12:16                     ` Alex Shi
2020-08-12 16:51                   ` Alexander Duyck
2020-08-12 16:51                     ` Alexander Duyck
2020-08-12 16:51                     ` Alexander Duyck
2020-08-13  1:46                     ` Alex Shi
2020-08-13  2:17                       ` Alexander Duyck
2020-08-13  2:17                         ` Alexander Duyck
2020-08-13  2:17                         ` Alexander Duyck
2020-08-13  3:52                         ` Alex Shi
2020-08-13  3:52                           ` Alex Shi
2020-08-13  4:02                       ` [RFC PATCH 0/3] " Alexander Duyck
2020-08-13  4:02                         ` Alexander Duyck
2020-08-13  4:02                         ` [RFC PATCH 1/3] mm: Drop locked from isolate_migratepages_block Alexander Duyck
2020-08-13  4:02                           ` Alexander Duyck
2020-08-13  6:56                           ` Alex Shi
2020-08-13  6:56                             ` Alex Shi
2020-08-13 14:32                             ` Alexander Duyck
2020-08-13 14:32                               ` Alexander Duyck
2020-08-13 14:32                               ` Alexander Duyck
2020-08-14  7:25                               ` Alex Shi
2020-08-14  7:25                                 ` Alex Shi
2020-08-13  7:44                           ` Alex Shi
2020-08-13  7:44                             ` Alex Shi
2020-08-13 14:26                             ` Alexander Duyck
2020-08-13 14:26                               ` Alexander Duyck
2020-08-13  4:02                         ` [RFC PATCH 2/3] mm: Drop use of test_and_set_skip in favor of just setting skip Alexander Duyck
2020-08-13  4:02                           ` Alexander Duyck
2020-08-14  7:19                           ` Alex Shi
2020-08-14  7:19                             ` Alex Shi
2020-08-14 14:24                             ` Alexander Duyck
2020-08-14 14:24                               ` Alexander Duyck
2020-08-14 14:24                               ` Alexander Duyck
2020-08-14 21:15                               ` Alexander Duyck
2020-08-14 21:15                                 ` Alexander Duyck
2020-08-14 21:15                                 ` Alexander Duyck
2020-08-15  9:49                                 ` Alex Shi
2020-08-17 15:38                                   ` Alexander Duyck
2020-08-17 15:38                                     ` Alexander Duyck
2020-08-17 15:38                                     ` Alexander Duyck
2020-08-18  6:50                           ` Alex Shi
2020-08-18  6:50                             ` Alex Shi
2020-08-13  4:02                         ` Alexander Duyck [this message]
2020-08-13  4:02                           ` [RFC PATCH 3/3] mm: Identify compound pages sooner in isolate_migratepages_block Alexander Duyck
2020-08-14  7:20                           ` Alex Shi
2020-08-14  7:20                             ` Alex Shi
2020-08-17 22:58   ` [PATCH v17 14/21] mm/compaction: do page isolation first in compaction Alexander Duyck
2020-08-17 22:58     ` Alexander Duyck
2020-08-17 22:58     ` Alexander Duyck
2020-07-25 12:59 ` [PATCH v17 15/21] mm/thp: add tail pages into lru anyway in split_huge_page() Alex Shi
2020-07-25 12:59   ` Alex Shi
2020-07-25 12:59 ` [PATCH v17 16/21] mm/swap: serialize memcg changes in pagevec_lru_move_fn Alex Shi
2020-07-25 12:59 ` [PATCH v17 17/21] mm/lru: replace pgdat lru_lock with lruvec lock Alex Shi
2020-07-25 12:59   ` Alex Shi
2020-07-27 23:34   ` Alexander Duyck
2020-07-27 23:34     ` Alexander Duyck
2020-07-27 23:34     ` Alexander Duyck
2020-07-28  7:15     ` Alex Shi
2020-07-28  7:15       ` Alex Shi
2020-07-28 11:19     ` Alex Shi
2020-07-28 11:19       ` Alex Shi
2020-07-28 14:54       ` Alexander Duyck
2020-07-28 14:54         ` Alexander Duyck
2020-07-28 14:54         ` Alexander Duyck
2020-07-29  1:00         ` Alex Shi
2020-07-29  1:27           ` Alexander Duyck
2020-07-29  1:27             ` Alexander Duyck
2020-07-29  1:27             ` Alexander Duyck
2020-07-29  2:27             ` Alex Shi
2020-07-29  2:27               ` Alex Shi
2020-07-28 15:39     ` Alex Shi
2020-07-28 15:39       ` Alex Shi
2020-07-28 15:55       ` Alexander Duyck
2020-07-28 15:55         ` Alexander Duyck
2020-07-28 15:55         ` Alexander Duyck
2020-07-29  0:48         ` Alex Shi
2020-07-29  3:54   ` Alex Shi
2020-08-06  7:41   ` Alex Shi
2020-08-06  7:41     ` Alex Shi
2020-07-25 12:59 ` [PATCH v17 18/21] mm/lru: introduce the relock_page_lruvec function Alex Shi
2020-07-29 17:52   ` Alexander Duyck
2020-07-29 17:52     ` Alexander Duyck
2020-07-29 17:52     ` Alexander Duyck
2020-07-30  6:08     ` Alex Shi
2020-07-30  6:08       ` Alex Shi
2020-07-31 14:20       ` Alexander Duyck
2020-07-31 14:20         ` Alexander Duyck
2020-07-31 14:20         ` Alexander Duyck
2020-07-31 21:14   ` [PATCH RFC] mm: Add function for testing if the current lruvec lock is valid alexander.h.duyck
2020-07-31 21:14     ` alexander.h.duyck-ral2JQCrhuEAvxtiuMwx3w
2020-07-31 23:54     ` Alex Shi
2020-07-31 23:54       ` Alex Shi
2020-08-02 18:20       ` Alexander Duyck
2020-08-02 18:20         ` Alexander Duyck
2020-08-02 18:20         ` Alexander Duyck
2020-08-04  6:13         ` Alex Shi
2020-08-04  6:13           ` Alex Shi
2020-07-25 12:59 ` [PATCH v17 19/21] mm/vmscan: use relock for move_pages_to_lru Alex Shi
2020-08-03 22:49   ` Alexander Duyck
2020-08-03 22:49     ` Alexander Duyck
2020-08-04  6:23     ` Alex Shi
2020-08-04  6:23       ` Alex Shi
2020-07-25 12:59 ` [PATCH v17 20/21] mm/pgdat: remove pgdat lru_lock Alex Shi
2020-08-03 22:42   ` Alexander Duyck
2020-08-03 22:42     ` Alexander Duyck
2020-08-03 22:42     ` Alexander Duyck
2020-08-03 22:45     ` Alexander Duyck
2020-08-03 22:45       ` Alexander Duyck
2020-08-03 22:45       ` Alexander Duyck
2020-08-04  6:22       ` Alex Shi
2020-08-04  6:22         ` Alex Shi
2020-07-25 12:59 ` [PATCH v17 21/21] mm/lru: revise the comments of lru_lock Alex Shi
2020-08-03 22:37   ` Alexander Duyck
2020-08-03 22:37     ` Alexander Duyck
2020-08-04 10:04     ` Alex Shi
2020-08-04 10:04       ` Alex Shi
2020-08-04 14:29       ` Alexander Duyck
2020-08-04 14:29         ` Alexander Duyck
2020-08-04 14:29         ` Alexander Duyck
2020-08-06  1:39         ` Alex Shi
2020-08-06  1:39           ` Alex Shi
2020-08-06 16:27           ` Alexander Duyck
2020-08-06 16:27             ` Alexander Duyck
2020-08-06 16:27             ` Alexander Duyck
2020-07-27  5:40 ` [PATCH v17 00/21] per memcg lru lock Alex Shi
2020-07-27  5:40   ` Alex Shi
2020-07-29 14:49   ` Alex Shi
2020-07-29 14:49     ` Alex Shi
2020-07-29 18:06     ` Hugh Dickins
2020-07-29 18:06       ` Hugh Dickins
2020-07-30  2:16       ` Alex Shi
2020-07-30  2:16         ` Alex Shi
2020-08-03 15:07         ` Michal Hocko
2020-08-03 15:07           ` Michal Hocko
2020-08-04  6:14           ` Alex Shi
2020-08-04  6:14             ` Alex Shi
2020-07-31 21:31 ` Alexander Duyck
2020-07-31 21:31   ` Alexander Duyck
2020-07-31 21:31   ` Alexander Duyck
2020-08-04  8:36 ` Alex Shi
2020-08-04  8:36   ` Alex Shi
2020-08-04  8:36 ` Alex Shi
2020-08-04  8:36   ` Alex Shi
2020-08-04  8:37 ` Alex Shi
2020-08-04  8:37   ` Alex Shi
2020-08-04  8:37 ` Alex Shi
2020-08-04  8:37   ` Alex Shi

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=20200813040240.13054.76770.stgit@localhost.localdomain \
    --to=alexander.duyck@gmail.com \
    --cc=akpm@linux-foundation.org \
    --cc=alex.shi@linux.alibaba.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=richard.weiyang@gmail.com \
    --cc=rong.a.chen@intel.com \
    --cc=shakeelb@google.com \
    --cc=tj@kernel.org \
    --cc=willy@infradead.org \
    --cc=yang.shi@linux.alibaba.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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.