linux-kernel - [PATCH v4 2/3] mm: swap: mTHP allocate swap entries from nonfull list

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 for Android: free password hash cracker in your pocket
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-Id: <20240711-swap-allocator-v4-2-0295a4d4c7aa@kernel.org>
Date: Thu, 11 Jul 2024 00:29:06 -0700
From: Chris Li <chrisl@...nel.org>
To: Andrew Morton <akpm@...ux-foundation.org>
Cc: Kairui Song <kasong@...cent.com>, Hugh Dickins <hughd@...gle.com>, 
 Ryan Roberts <ryan.roberts@....com>, "Huang, Ying" <ying.huang@...el.com>, 
 Kalesh Singh <kaleshsingh@...gle.com>, linux-kernel@...r.kernel.org, 
 linux-mm@...ck.org, Chris Li <chrisl@...nel.org>, 
 Barry Song <baohua@...nel.org>
Subject: [PATCH v4 2/3] mm: swap: mTHP allocate swap entries from nonfull
 list

Track the nonfull cluster as well as the empty cluster
on lists. Each order has one nonfull cluster list.

The cluster will remember which order it was used during
new cluster allocation.

When the cluster has free entry, add to the nonfull[order]
list.  When the free cluster list is empty, also allocate
from the nonempty list of that order.

This improves the mTHP swap allocation success rate.

There are limitations if the distribution of numbers of
different orders of mTHP changes a lot. e.g. there are a lot
of nonfull cluster assign to order A while later time there
are a lot of order B allocation while very little allocation
in order A. Currently the cluster used by order A will not
reused by order B unless the cluster is 100% empty.

Signed-off-by: Chris Li <chrisl@...nel.org>
---
 include/linux/swap.h |  4 ++++
 mm/swapfile.c        | 34 +++++++++++++++++++++++++++++++---
 2 files changed, 35 insertions(+), 3 deletions(-)

diff --git a/include/linux/swap.h b/include/linux/swap.h
index e9be95468fc7..db8d6000c116 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -254,9 +254,11 @@ struct swap_cluster_info {
 				 */
 	u16 count;
 	u8 flags;
+	u8 order;
 	struct list_head list;
 };
 #define CLUSTER_FLAG_FREE 1 /* This cluster is free */
+#define CLUSTER_FLAG_NONFULL 2 /* This cluster is on nonfull list */
 
 
 /*
@@ -296,6 +298,8 @@ struct swap_info_struct {
 	unsigned long *zeromap;		/* vmalloc'ed bitmap to track zero pages */
 	struct swap_cluster_info *cluster_info; /* cluster info. Only for SSD */
 	struct list_head free_clusters; /* free clusters list */
+	struct list_head nonfull_clusters[SWAP_NR_ORDERS];
+					/* list of cluster that contains at least one free slot */
 	unsigned int lowest_bit;	/* index of first free in swap_map */
 	unsigned int highest_bit;	/* index of last free in swap_map */
 	unsigned int pages;		/* total of usable pages of swap */
diff --git a/mm/swapfile.c b/mm/swapfile.c
index f70d25005d2c..e13a33664cfa 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -361,14 +361,21 @@ static void swap_cluster_schedule_discard(struct swap_info_struct *si,
 	memset(si->swap_map + idx * SWAPFILE_CLUSTER,
 			SWAP_MAP_BAD, SWAPFILE_CLUSTER);
 
-	list_add_tail(&ci->list, &si->discard_clusters);
+	if (ci->flags)
+		list_move_tail(&ci->list, &si->discard_clusters);
+	else
+		list_add_tail(&ci->list, &si->discard_clusters);
+	ci->flags = 0;
 	schedule_work(&si->discard_work);
 }
 
 static void __free_cluster(struct swap_info_struct *si, struct swap_cluster_info *ci)
 {
+	if (ci->flags & CLUSTER_FLAG_NONFULL)
+		list_move_tail(&ci->list, &si->free_clusters);
+	else
+		list_add_tail(&ci->list, &si->free_clusters);
 	ci->flags = CLUSTER_FLAG_FREE;
-	list_add_tail(&ci->list, &si->free_clusters);
 }
 
 /*
@@ -491,7 +498,12 @@ static void dec_cluster_info_page(struct swap_info_struct *p, struct swap_cluste
 	ci->count--;
 
 	if (!ci->count)
-		free_cluster(p, ci);
+		return free_cluster(p, ci);
+
+	if (!(ci->flags & CLUSTER_FLAG_NONFULL)) {
+		list_add_tail(&ci->list, &p->nonfull_clusters[ci->order]);
+		ci->flags |= CLUSTER_FLAG_NONFULL;
+	}
 }
 
 /*
@@ -550,6 +562,18 @@ static bool scan_swap_map_try_ssd_cluster(struct swap_info_struct *si,
 	if (tmp == SWAP_NEXT_INVALID) {
 		if (!list_empty(&si->free_clusters)) {
 			ci = list_first_entry(&si->free_clusters, struct swap_cluster_info, list);
+			list_del(&ci->list);
+			spin_lock(&ci->lock);
+			ci->order = order;
+			ci->flags = 0;
+			spin_unlock(&ci->lock);
+			tmp = cluster_index(si, ci) * SWAPFILE_CLUSTER;
+		} else if (!list_empty(&si->nonfull_clusters[order])) {
+			ci = list_first_entry(&si->nonfull_clusters[order], struct swap_cluster_info, list);
+			list_del(&ci->list);
+			spin_lock(&ci->lock);
+			ci->flags = 0;
+			spin_unlock(&ci->lock);
 			tmp = cluster_index(si, ci) * SWAPFILE_CLUSTER;
 		} else if (!list_empty(&si->discard_clusters)) {
 			/*
@@ -964,6 +988,7 @@ static void swap_free_cluster(struct swap_info_struct *si, unsigned long idx)
 	ci = lock_cluster(si, offset);
 	memset(si->swap_map + offset, 0, SWAPFILE_CLUSTER);
 	ci->count = 0;
+	ci->order = 0;
 	ci->flags = 0;
 	free_cluster(si, ci);
 	unlock_cluster(ci);
@@ -2919,6 +2944,9 @@ static int setup_swap_map_and_extents(struct swap_info_struct *p,
 	INIT_LIST_HEAD(&p->free_clusters);
 	INIT_LIST_HEAD(&p->discard_clusters);
 
+	for (i = 0; i < SWAP_NR_ORDERS; i++)
+		INIT_LIST_HEAD(&p->nonfull_clusters[i]);
+
 	for (i = 0; i < swap_header->info.nr_badpages; i++) {
 		unsigned int page_nr = swap_header->info.badpages[i];
 		if (page_nr == 0 || page_nr > swap_header->info.last_page)

-- 
2.45.2.803.g4e1b14247a-goog