| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-Id: <1402305982-6928-10-git-send-email-vbabka@suse.cz>
Date: Mon, 9 Jun 2014 11:26:22 +0200
From: Vlastimil Babka <vbabka@...e.cz>
To: David Rientjes <rientjes@...gle.com>, linux-mm@...ck.org
Cc: linux-kernel@...r.kernel.org,
Andrew Morton <akpm@...ux-foundation.org>,
Greg Thelen <gthelen@...gle.com>,
Vlastimil Babka <vbabka@...e.cz>,
Minchan Kim <minchan@...nel.org>, Mel Gorman <mgorman@...e.de>,
Joonsoo Kim <iamjoonsoo.kim@....com>,
Michal Nazarewicz <mina86@...a86.com>,
Naoya Horiguchi <n-horiguchi@...jp.nec.com>,
Christoph Lameter <cl@...ux.com>,
Rik van Riel <riel@...hat.com>
Subject: [RFC PATCH 10/10] mm, compaction: do not migrate pages when that cannot satisfy page fault allocation
In direct compaction for a page fault, we want to allocate the high-order page
as soon as possible, so migrating from a cc->order aligned block of pages that
contains also unmigratable pages just adds to page fault latency.
This patch therefore makes the migration scanner skip to the next cc->order
aligned block of pages as soon as it cannot isolate a non-free page. Everything
isolated up to that point is put back.
In this mode, the nr_isolated limit to COMPACT_CLUSTER_MAX is not observed,
allowing the scanner to scan the whole block at once, instead of migrating
COMPACT_CLUSTER_MAX pages and then finding an unmigratable page in the next
call. This might however have some implications on direct reclaimers through
too_many_isolated().
In very preliminary tests, this has reduced migrate_scanned, isolations and
migrations by about 10%, while the success rate of stress-highalloc mmtests
actually improved a bit.
[rientjes@...gle.com: skip_on_failure logic; cleanups]
Signed-off-by: Vlastimil Babka <vbabka@...e.cz>
Cc: Minchan Kim <minchan@...nel.org>
Cc: Mel Gorman <mgorman@...e.de>
Cc: Joonsoo Kim <iamjoonsoo.kim@....com>
Cc: Michal Nazarewicz <mina86@...a86.com>
Cc: Naoya Horiguchi <n-horiguchi@...jp.nec.com>
Cc: Christoph Lameter <cl@...ux.com>
Cc: Rik van Riel <riel@...hat.com>
Cc: David Rientjes <rientjes@...gle.com>
---
mm/compaction.c | 56 ++++++++++++++++++++++++++++++++++++++++----------------
1 file changed, 40 insertions(+), 16 deletions(-)
diff --git a/mm/compaction.c b/mm/compaction.c
index b69ac19..6dda4eb 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -543,6 +543,7 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc,
(unevictable ? ISOLATE_UNEVICTABLE : 0);
unsigned long capture_pfn = 0; /* current candidate for capturing */
unsigned long next_capture_pfn = 0; /* next candidate for capturing */
+ bool skip_on_failure = false; /* skip block when isolation fails */
if (cc->order > PAGE_ALLOC_COSTLY_ORDER
&& gfpflags_to_migratetype(cc->gfp_mask) == MIGRATE_MOVABLE
@@ -550,6 +551,14 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc,
/* This may be outside the zone, but we check that later */
capture_pfn = low_pfn & ~((1UL << cc->order) - 1);
next_capture_pfn = ALIGN(low_pfn + 1, (1UL << cc->order));
+ /*
+ * It is too expensive for compaction to migrate pages from a
+ * cc->order block of pages on page faults, unless the entire
+ * block can become free. But hugepaged should try anyway for
+ * THP so that general defragmentation happens.
+ */
+ skip_on_failure = (cc->gfp_mask & __GFP_NO_KSWAPD)
+ && !(current->flags & PF_KTHREAD);
}
/*
@@ -613,7 +622,7 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc,
}
if (!pfn_valid_within(low_pfn))
- continue;
+ goto isolation_failed;
nr_scanned++;
/*
@@ -624,7 +633,7 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc,
*/
page = pfn_to_page(low_pfn);
if (page_zone(page) != zone)
- continue;
+ goto isolation_failed;
if (!valid_page)
valid_page = page;
@@ -686,7 +695,7 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc,
goto isolate_success;
}
}
- continue;
+ goto isolation_failed;
}
/*
@@ -706,7 +715,7 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc,
if (next_capture_pfn)
next_capture_pfn =
ALIGN(low_pfn + 1, (1UL << cc->order));
- continue;
+ goto isolation_failed;
}
/*
@@ -716,7 +725,7 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc,
*/
if (!page_mapping(page) &&
page_count(page) > page_mapcount(page))
- continue;
+ goto isolation_failed;
/* If we already hold the lock, we can skip some rechecking */
if (!locked) {
@@ -727,11 +736,11 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc,
/* Recheck PageLRU and PageTransHuge under lock */
if (!PageLRU(page))
- continue;
+ goto isolation_failed;
if (PageTransHuge(page)) {
low_pfn += (1 << compound_order(page)) - 1;
next_capture_pfn = low_pfn + 1;
- continue;
+ goto isolation_failed;
}
}
@@ -739,7 +748,7 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc,
/* Try isolate the page */
if (__isolate_lru_page(page, mode) != 0)
- continue;
+ goto isolation_failed;
VM_BUG_ON_PAGE(PageTransCompound(page), page);
@@ -749,11 +758,14 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc,
isolate_success:
cc->finished_update_migrate = true;
list_add(&page->lru, migratelist);
- cc->nr_migratepages++;
nr_isolated++;
- /* Avoid isolating too much */
- if (cc->nr_migratepages == COMPACT_CLUSTER_MAX) {
+ /*
+ * Avoid isolating too much, except if we try to capture a
+ * free page and want to find out at once if it can be done
+ * or we should skip to the next block.
+ */
+ if (!skip_on_failure && nr_isolated == COMPACT_CLUSTER_MAX) {
++low_pfn;
break;
}
@@ -764,6 +776,20 @@ next_pageblock:
low_pfn = ALIGN(low_pfn + 1, pageblock_nr_pages) - 1;
if (next_capture_pfn)
next_capture_pfn = low_pfn + 1;
+
+isolation_failed:
+ if (skip_on_failure) {
+ if (nr_isolated) {
+ if (locked) {
+ spin_unlock_irqrestore(&zone->lru_lock,
+ flags);
+ locked = false;
+ }
+ putback_movable_pages(migratelist);
+ nr_isolated = 0;
+ }
+ low_pfn = next_capture_pfn - 1;
+ }
}
/*
@@ -773,6 +799,7 @@ next_pageblock:
if (unlikely(low_pfn > end_pfn))
low_pfn = end_pfn;
+ cc->nr_migratepages = nr_isolated;
acct_isolated(zone, locked, cc);
if (locked)
@@ -782,7 +809,7 @@ next_pageblock:
* Update the pageblock-skip information and cached scanner pfn,
* if the whole pageblock was scanned without isolating any page.
*/
- if (low_pfn == end_pfn)
+ if (low_pfn == end_pfn && !skip_on_failure)
update_pageblock_skip(cc, valid_page, nr_isolated,
set_unsuitable, true);
@@ -998,7 +1025,7 @@ static isolate_migrate_t isolate_migratepages(struct zone *zone,
cc->migrate_pfn = low_pfn;
- return ISOLATE_SUCCESS;
+ return cc->nr_migratepages ? ISOLATE_SUCCESS : ISOLATE_NONE;
}
/*
@@ -1212,9 +1239,6 @@ static int compact_zone(struct zone *zone, struct compact_control *cc)
;
}
- if (!cc->nr_migratepages)
- continue;
-
err = migrate_pages(&cc->migratepages, compaction_alloc,
compaction_free, (unsigned long)cc, cc->mode,
MR_COMPACTION);
--
1.8.4.5
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists