[RFC PATCH v3 11/18] mm/swap: remove available list

[Lian Wang <lianux.mm@gmail.com>]

From: Kairui Song <kasong@tencent.com>

Pure cleanup, no functional change.

After the priority queue replaced the allocator's device selection,
swap_avail_head and swap_avail_lock are no longer used. Remove them.

The throttle path now walks swap_active_head under swapon_rwsem.
Check SWP_WRITEOK and the existing off-list state. This preserves the old
priority ordering and does not select a full swap device.

Signed-off-by: Kairui Song <kasong@tencent.com>
Signed-off-by: Lian Wang <lianux.mm@gmail.com>
---
 include/linux/swap.h |  1 -
 mm/swapfile.c        | 33 ++++++---------------------------
 2 files changed, 6 insertions(+), 28 deletions(-)

diff --git a/include/linux/swap.h b/include/linux/swap.h
index 9357a9065f37..17b8ec654ee2 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -287,7 +287,6 @@ struct swap_info_struct {
 	struct work_struct discard_work; /* discard worker */
 	struct work_struct reclaim_work; /* reclaim worker */
 	struct list_head discard_clusters; /* discard clusters list */
-	struct plist_node avail_list;   /* entry in swap_avail_head */
 	const struct swap_ops *ops;
 };
 
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 2065e566b7a3..0a16343a5b03 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -96,21 +96,6 @@ static const char Bad_offset[] = "Bad swap offset entry ";
  */
 static PLIST_HEAD(swap_active_head);
 
-/*
- * all available (active, not full) swap_info_structs
- * protected with swap_avail_lock, ordered by priority.
- * This is used by folio_alloc_swap() instead of swap_active_head
- * because swap_active_head includes all swap_info_structs,
- * but folio_alloc_swap() doesn't need to look at full ones.
- * This uses its own lock instead of swapon_rwsem because when a
- * swap_info_struct changes between not-full/full, it needs to
- * add/remove itself to/from this list, but the swap_info_struct->lock
- * is held and the locking order requires swapon_rwsem to be taken
- * before any swap_info_struct->lock.
- */
-static PLIST_HEAD(swap_avail_head);
-static DEFINE_SPINLOCK(swap_avail_lock);
-
 static inline struct swap_info_struct *__swap_iter(int *i, unsigned long flag)
 {
 	lockdep_assert_held(&swapon_rwsem);
@@ -1652,7 +1637,6 @@ static void del_from_avail_list(struct swap_info_struct *si, bool swapoff)
 {
 	unsigned long pages;
 
-	spin_lock(&swap_avail_lock);
 	spin_lock(&swap_queue_update_lock);
 
 	/*
@@ -1672,10 +1656,8 @@ static void del_from_avail_list(struct swap_info_struct *si, bool swapoff)
 	}
 
 	swap_queue_mask(si);
-	plist_del(&si->avail_list, &swap_avail_head);
 skip:
 	spin_unlock(&swap_queue_update_lock);
-	spin_unlock(&swap_avail_lock);
 }
 
 /* SWAP_USAGE_OFFLIST_BIT can only be cleared by this helper. */
@@ -1684,7 +1666,6 @@ static void add_to_avail_list(struct swap_info_struct *si)
 	long val;
 	unsigned long pages;
 
-	spin_lock(&swap_avail_lock);
 	spin_lock(&swap_queue_update_lock);
 
 	/*
@@ -1715,10 +1696,8 @@ static void add_to_avail_list(struct swap_info_struct *si)
 	}
 
 	swap_queue_unmask(si);
-	plist_add(&si->avail_list, &swap_avail_head);
 skip:
 	spin_unlock(&swap_queue_update_lock);
-	spin_unlock(&swap_avail_lock);
 }
 
 /*
@@ -3844,7 +3823,6 @@ static struct swap_info_struct *alloc_swap_info(void)
 	}
 	p->swap_extent_root = RB_ROOT;
 	plist_node_init(&p->list, 0);
-	plist_node_init(&p->avail_list, 0);
 	p->flags = SWP_USED;
 	percpu_up_write(&swapon_rwsem);
 	if (defer) {
@@ -4260,7 +4238,6 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags)
 	 */
 	si->prio = prio;
 	si->list.prio = -si->prio;
-	si->avail_list.prio = -si->prio;
 
 	/*
 	 * Publish swap_file before making the percpu ref live, then add the device
@@ -4409,14 +4386,16 @@ void __folio_throttle_swaprate(struct folio *folio, gfp_t gfp)
 	if (current->throttle_disk)
 		return;
 
-	spin_lock(&swap_avail_lock);
-	plist_for_each_entry(si, &swap_avail_head, avail_list) {
-		if (si->bdev) {
+	percpu_down_read(&swapon_rwsem);
+	plist_for_each_entry(si, &swap_active_head, list) {
+		if ((si->flags & SWP_WRITEOK) &&
+		    !(atomic_long_read(&si->inuse_pages) &
+		      SWAP_USAGE_OFFLIST_BIT) && si->bdev) {
 			blkcg_schedule_throttle(si->bdev->bd_disk, true);
 			break;
 		}
 	}
-	spin_unlock(&swap_avail_lock);
+	percpu_up_read(&swapon_rwsem);
 }
 #endif