From b50da6e9f42ade19141f6cf8870bb2312b055aa3 Mon Sep 17 00:00:00 2001
From: Zhaoyang Huang <huangzhaoyang@gmail.com>
Date: Tue, 15 Dec 2020 20:42:23 -0800
Subject: [PATCH] mm: fix a race on nr_swap_pages

The scenario on which "Free swap = -4kB" happens in my system, which is caused
by several get_swap_pages racing with each other and show_swap_cache_info
happens simutaniously. No need to add a lock on get_swap_page_of_type as we
remove "Presub/PosAdd" here.

ProcessA			ProcessB			ProcessC
ngoals = 1			ngoals = 1
avail = nr_swap_pages(1)	avail = nr_swap_pages(1)
nr_swap_pages(1) -= ngoals
				nr_swap_pages(0) -= ngoals
								nr_swap_pages = -1

Link: https://lkml.kernel.org/r/1607050340-4535-1-git-send-email-zhaoyang.huang@unisoc.com
Signed-off-by: Zhaoyang Huang <zhaoyang.huang@unisoc.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 mm/swapfile.c | 11 ++++++-----
 1 file changed, 6 insertions(+), 5 deletions(-)

diff --git a/mm/swapfile.c b/mm/swapfile.c
index 1c0a829f7311..9fffc5af29d1 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -1042,16 +1042,18 @@ int get_swap_pages(int n_goal, swp_entry_t swp_entries[], int entry_size)
 	/* Only single cluster request supported */
 	WARN_ON_ONCE(n_goal > 1 && size == SWAPFILE_CLUSTER);
 
+	spin_lock(&swap_avail_lock);
+
 	avail_pgs = atomic_long_read(&nr_swap_pages) / size;
-	if (avail_pgs <= 0)
+	if (avail_pgs <= 0) {
+		spin_unlock(&swap_avail_lock);
 		goto noswap;
+	}
 
 	n_goal = min3((long)n_goal, (long)SWAP_BATCH, avail_pgs);
 
 	atomic_long_sub(n_goal * size, &nr_swap_pages);
 
-	spin_lock(&swap_avail_lock);
-
 start_over:
 	node = numa_node_id();
 	plist_for_each_entry_safe(si, next, &swap_avail_heads[node], avail_lists[node]) {
@@ -1125,14 +1127,13 @@ swp_entry_t get_swap_page_of_type(int type)
 
 	spin_lock(&si->lock);
 	if (si->flags & SWP_WRITEOK) {
-		atomic_long_dec(&nr_swap_pages);
 		/* This is called for allocating swap entry, not cache */
 		offset = scan_swap_map(si, 1);
 		if (offset) {
+			atomic_long_dec(&nr_swap_pages);
 			spin_unlock(&si->lock);
 			return swp_entry(type, offset);
 		}
-		atomic_long_inc(&nr_swap_pages);
 	}
 	spin_unlock(&si->lock);
 fail:
-- 
GitLab