diff mbox series

[4/7] mm, swap: don't update the counter up-front

Message ID 20250214175709.76029-5-ryncsn@gmail.com (mailing list archive)
State New
Headers show
Series mm, swap: remove swap slot cache | expand

Commit Message

Kairui Song Feb. 14, 2025, 5:57 p.m. UTC 
From: Kairui Song <kasong@tencent.com>

The counter update before allocation was useful to avoid unnecessary
scan when device is full, so it will abort early if the counter
indicated the device is full. But that is an uncommon case, and now
scanning of a full device is very fast, so the up-front update is not
helpful any more.

Remove it and simplify the slot allocation logic.

Signed-off-by: Kairui Song <kasong@tencent.com>
---
 mm/swapfile.c | 18 ++----------------
 1 file changed, 2 insertions(+), 16 deletions(-)
diff mbox series

Patch

diff --git a/mm/swapfile.c b/mm/swapfile.c
index 449e388a6fec..ae3bd0a862fc 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -1208,22 +1208,10 @@  int get_swap_pages(int n_goal, swp_entry_t swp_entries[], int entry_order)
 	int order = swap_entry_order(entry_order);
 	unsigned long size = 1 << order;
 	struct swap_info_struct *si, *next;
-	long avail_pgs;
 	int n_ret = 0;
 	int node;
 
 	spin_lock(&swap_avail_lock);
-
-	avail_pgs = atomic_long_read(&nr_swap_pages) / size;
-	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);
-
 start_over:
 	node = numa_node_id();
 	plist_for_each_entry_safe(si, next, &swap_avail_heads[node], avail_lists[node]) {
@@ -1257,10 +1245,8 @@  int get_swap_pages(int n_goal, swp_entry_t swp_entries[], int entry_order)
 	spin_unlock(&swap_avail_lock);
 
 check_out:
-	if (n_ret < n_goal)
-		atomic_long_add((long)(n_goal - n_ret) * size,
-				&nr_swap_pages);
-noswap:
+	atomic_long_sub(n_ret * size, &nr_swap_pages);
+
 	return n_ret;
 }