linux-kernel - [PATCH 5.11 015/775] zsmalloc: account the number of compacted pages correctly

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

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Date:   Mon,  1 Mar 2021 17:03:03 +0100
From:   Greg Kroah-Hartman <gregkh@...uxfoundation.org>
To:     linux-kernel@...r.kernel.org
Cc:     Greg Kroah-Hartman <gregkh@...uxfoundation.org>,
        stable@...r.kernel.org, Rokudo Yan <wu-yan@....com>,
        Minchan Kim <minchan@...nel.org>,
        Sergey Senozhatsky <sergey.senozhatsky@...il.com>,
        Andrew Morton <akpm@...ux-foundation.org>,
        Linus Torvalds <torvalds@...ux-foundation.org>
Subject: [PATCH 5.11 015/775] zsmalloc: account the number of compacted pages correctly

From: Rokudo Yan <wu-yan@....com>

commit 2395928158059b8f9858365fce7713ce7fef62e4 upstream.

There exists multiple path may do zram compaction concurrently.
1. auto-compaction triggered during memory reclaim
2. userspace utils write zram<id>/compaction node

So, multiple threads may call zs_shrinker_scan/zs_compact concurrently.
But pages_compacted is a per zsmalloc pool variable and modification
of the variable is not serialized(through under class->lock).
There are two issues here:
1. the pages_compacted may not equal to total number of pages
freed(due to concurrently add).
2. zs_shrinker_scan may not return the correct number of pages
freed(issued by current shrinker).

The fix is simple:
1. account the number of pages freed in zs_compact locally.
2. use actomic variable pages_compacted to accumulate total number.

Link: https://lkml.kernel.org/r/20210202122235.26885-1-wu-yan@tcl.com
Fixes: 860c707dca155a56 ("zsmalloc: account the number of compacted pages")
Signed-off-by: Rokudo Yan <wu-yan@....com>
Cc: Minchan Kim <minchan@...nel.org>
Cc: Sergey Senozhatsky <sergey.senozhatsky@...il.com>
Cc: <stable@...r.kernel.org>
Signed-off-by: Andrew Morton <akpm@...ux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@...ux-foundation.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@...uxfoundation.org>
---
 drivers/block/zram/zram_drv.c |    2 +-
 include/linux/zsmalloc.h      |    2 +-
 mm/zsmalloc.c                 |   17 +++++++++++------
 3 files changed, 13 insertions(+), 8 deletions(-)

--- a/drivers/block/zram/zram_drv.c
+++ b/drivers/block/zram/zram_drv.c
@@ -1082,7 +1082,7 @@ static ssize_t mm_stat_show(struct devic
 			zram->limit_pages << PAGE_SHIFT,
 			max_used << PAGE_SHIFT,
 			(u64)atomic64_read(&zram->stats.same_pages),
-			pool_stats.pages_compacted,
+			atomic_long_read(&pool_stats.pages_compacted),
 			(u64)atomic64_read(&zram->stats.huge_pages),
 			(u64)atomic64_read(&zram->stats.huge_pages_since));
 	up_read(&zram->init_lock);
--- a/include/linux/zsmalloc.h
+++ b/include/linux/zsmalloc.h
@@ -35,7 +35,7 @@ enum zs_mapmode {
 
 struct zs_pool_stats {
 	/* How many pages were migrated (freed) */
-	unsigned long pages_compacted;
+	atomic_long_t pages_compacted;
 };
 
 struct zs_pool;
--- a/mm/zsmalloc.c
+++ b/mm/zsmalloc.c
@@ -2213,11 +2213,13 @@ static unsigned long zs_can_compact(stru
 	return obj_wasted * class->pages_per_zspage;
 }
 
-static void __zs_compact(struct zs_pool *pool, struct size_class *class)
+static unsigned long __zs_compact(struct zs_pool *pool,
+				  struct size_class *class)
 {
 	struct zs_compact_control cc;
 	struct zspage *src_zspage;
 	struct zspage *dst_zspage = NULL;
+	unsigned long pages_freed = 0;
 
 	spin_lock(&class->lock);
 	while ((src_zspage = isolate_zspage(class, true))) {
@@ -2247,7 +2249,7 @@ static void __zs_compact(struct zs_pool
 		putback_zspage(class, dst_zspage);
 		if (putback_zspage(class, src_zspage) == ZS_EMPTY) {
 			free_zspage(pool, class, src_zspage);
-			pool->stats.pages_compacted += class->pages_per_zspage;
+			pages_freed += class->pages_per_zspage;
 		}
 		spin_unlock(&class->lock);
 		cond_resched();
@@ -2258,12 +2260,15 @@ static void __zs_compact(struct zs_pool
 		putback_zspage(class, src_zspage);
 
 	spin_unlock(&class->lock);
+
+	return pages_freed;
 }
 
 unsigned long zs_compact(struct zs_pool *pool)
 {
 	int i;
 	struct size_class *class;
+	unsigned long pages_freed = 0;
 
 	for (i = ZS_SIZE_CLASSES - 1; i >= 0; i--) {
 		class = pool->size_class[i];
@@ -2271,10 +2276,11 @@ unsigned long zs_compact(struct zs_pool
 			continue;
 		if (class->index != i)
 			continue;
-		__zs_compact(pool, class);
+		pages_freed += __zs_compact(pool, class);
 	}
+	atomic_long_add(pages_freed, &pool->stats.pages_compacted);
 
-	return pool->stats.pages_compacted;
+	return pages_freed;
 }
 EXPORT_SYMBOL_GPL(zs_compact);
 
@@ -2291,13 +2297,12 @@ static unsigned long zs_shrinker_scan(st
 	struct zs_pool *pool = container_of(shrinker, struct zs_pool,
 			shrinker);
 
-	pages_freed = pool->stats.pages_compacted;
 	/*
 	 * Compact classes and calculate compaction delta.
 	 * Can run concurrently with a manually triggered
 	 * (by user) compaction.
 	 */
-	pages_freed = zs_compact(pool) - pages_freed;
+	pages_freed = zs_compact(pool);
 
 	return pages_freed ? pages_freed : SHRINK_STOP;
 }