[PATCH v2 1/5] mm: swap: introduce swap_free_nr() for batched swap_free()

[Barry Song <21cnbao@gmail.com>]

From: Chuanhua Han <hanchuanhua@oppo.com>

While swapping in a large folio, we need to free swaps related to the whole
folio. To avoid frequently acquiring and releasing swap locks, it is better
to introduce an API for batched free.

Signed-off-by: Chuanhua Han <hanchuanhua@oppo.com>
Co-developed-by: Barry Song <v-songbaohua@oppo.com>
Signed-off-by: Barry Song <v-songbaohua@oppo.com>
---
 include/linux/swap.h |  5 +++++
 mm/swapfile.c        | 51 ++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 56 insertions(+)

diff --git a/include/linux/swap.h b/include/linux/swap.h
index 11c53692f65f..b7a107e983b8 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -483,6 +483,7 @@ extern void swap_shmem_alloc(swp_entry_t);
 extern int swap_duplicate(swp_entry_t);
 extern int swapcache_prepare(swp_entry_t);
 extern void swap_free(swp_entry_t);
+extern void swap_free_nr(swp_entry_t entry, int nr_pages);
 extern void swapcache_free_entries(swp_entry_t *entries, int n);
 extern void free_swap_and_cache_nr(swp_entry_t entry, int nr);
 int swap_type_of(dev_t device, sector_t offset);
@@ -564,6 +565,10 @@ static inline void swap_free(swp_entry_t swp)
 {
 }
 
+void swap_free_nr(swp_entry_t entry, int nr_pages)
+{
+}
+
 static inline void put_swap_folio(struct folio *folio, swp_entry_t swp)
 {
 }
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 28642c188c93..f4c65aeb088d 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -1356,6 +1356,57 @@ void swap_free(swp_entry_t entry)
 		__swap_entry_free(p, entry);
 }
 
+/*
+ * Free up the maximum number of swap entries at once to limit the
+ * maximum kernel stack usage.
+ */
+#define SWAP_BATCH_NR (SWAPFILE_CLUSTER > 512 ? 512 : SWAPFILE_CLUSTER)
+
+/*
+ * Called after swapping in a large folio, batched free swap entries
+ * for this large folio, entry should be for the first subpage and
+ * its offset is aligned with nr_pages
+ */
+void swap_free_nr(swp_entry_t entry, int nr_pages)
+{
+	int i, j;
+	struct swap_cluster_info *ci;
+	struct swap_info_struct *p;
+	unsigned int type = swp_type(entry);
+	unsigned long offset = swp_offset(entry);
+	int batch_nr, remain_nr;
+	DECLARE_BITMAP(usage, SWAP_BATCH_NR) = { 0 };
+
+	/* all swap entries are within a cluster for mTHP */
+	VM_BUG_ON(offset % SWAPFILE_CLUSTER + nr_pages > SWAPFILE_CLUSTER);
+
+	if (nr_pages == 1) {
+		swap_free(entry);
+		return;
+	}
+
+	remain_nr = nr_pages;
+	p = _swap_info_get(entry);
+	if (p) {
+		for (i = 0; i < nr_pages; i += batch_nr) {
+			batch_nr = min_t(int, SWAP_BATCH_NR, remain_nr);
+
+			ci = lock_cluster_or_swap_info(p, offset);
+			for (j = 0; j < batch_nr; j++) {
+				if (__swap_entry_free_locked(p, offset + i * SWAP_BATCH_NR + j, 1))
+					__bitmap_set(usage, j, 1);
+			}
+			unlock_cluster_or_swap_info(p, ci);
+
+			for_each_clear_bit(j, usage, batch_nr)
+				free_swap_slot(swp_entry(type, offset + i * SWAP_BATCH_NR + j));
+
+			bitmap_clear(usage, 0, SWAP_BATCH_NR);
+			remain_nr -= batch_nr;
+		}
+	}
+}
+
 /*
  * Called after dropping swapcache to decrease refcnt to swap entries.
  */
-- 
2.34.1