[AUTOSEL,4.19,43/44] mm: don't miss the last page because of round-off error

Commit Message

Sasha Levin Nov. 13, 2018, 5:49 a.m. UTC

From: Roman Gushchin <[e-mail]>

[ Upstream commit 68600f623d69da428c6163275f97ca126e1a8ec5 ]

I've noticed, that dying memory cgroups are often pinned in memory by a
single pagecache page.  Even under moderate memory pressure they sometimes
stayed in such state for a long time.  That looked strange.

My investigation showed that the problem is caused by applying the LRU
pressure balancing math:

  scan = div64_u64(scan * fraction[lru], denominator),

where

  denominator = fraction[anon] + fraction[file] + 1.

Because fraction[lru] is always less than denominator, if the initial scan
size is 1, the result is always 0.

This means the last page is not scanned and has
no chances to be reclaimed.

Fix this by rounding up the result of the division.

In practice this change significantly improves the speed of dying cgroups
reclaim.

[[e-mail]: prevent double calculation of DIV64_U64_ROUND_UP() arguments]
  Link: http://lkml.kernel.org/r/20180829213311.GA13501@castle
Link: http://lkml.kernel.org/r/[e-mail]
Signed-off-by: Roman Gushchin <[e-mail]>
Reviewed-by: Andrew Morton <[e-mail]>
Cc: Johannes Weiner <[e-mail]>
Cc: Michal Hocko <[e-mail]>
Cc: Tejun Heo <[e-mail]>
Cc: Rik van Riel <[e-mail]>
Cc: Konstantin Khlebnikov <[e-mail]>
Cc: Matthew Wilcox <[e-mail]>
Signed-off-by: Andrew Morton <[e-mail]>
Signed-off-by: Linus Torvalds <[e-mail]>
Signed-off-by: Sasha Levin <[e-mail]>
---
 include/linux/math64.h | 3 +++
 mm/vmscan.c            | 6 ++++--
 2 files changed, 7 insertions(+), 2 deletions(-)

Patch

diff --git a/include/linux/math64.h b/include/linux/math64.h
index 837f2f2d1d34..bb2c84afb80c 100644
--- a/include/linux/math64.h
+++ b/include/linux/math64.h
@@ -281,4 +281,7 @@  static inline u64 mul_u64_u32_div(u64 a, u32 mul, u32 divisor)
 }
 #endif /* mul_u64_u32_div */
 
+#define DIV64_U64_ROUND_UP(ll, d)	\
+	({ u64 _tmp = (d); div64_u64((ll) + _tmp - 1, _tmp); })
+
 #endif /* _LINUX_MATH64_H */
diff --git a/mm/vmscan.c b/mm/vmscan.c
index c5ef7240cbcb..961401c46334 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2456,9 +2456,11 @@  static void get_scan_count(struct lruvec *lruvec, struct mem_cgroup *memcg,
 			/*
 			 * Scan types proportional to swappiness and
 			 * their relative recent reclaim efficiency.
+			 * Make sure we don't miss the last page
+			 * because of a round-off error.
 			 */
-			scan = div64_u64(scan * fraction[file],
-					 denominator);
+			scan = DIV64_U64_ROUND_UP(scan * fraction[file],
+						  denominator);
 			break;
 		case SCAN_FILE:
 		case SCAN_ANON: