diff --git a/include/linux/swap.h b/include/linux/swap.h
index cebabb6db07cbd1ad1f8806b3f8f3c893a59193c..c92fa9a823a77e37d637c50afe600870b78e1f7e 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -468,6 +468,7 @@ extern void __delete_from_swap_cache(struct page *page,
 extern void delete_from_swap_cache(struct page *);
 extern void clear_shadow_from_swap_cache(int type, unsigned long begin,
 				unsigned long end);
+void swapcache_clear(struct swap_info_struct *si, swp_entry_t entry);
 extern void free_page_and_swap_cache(struct page *);
 extern void free_pages_and_swap_cache(struct page **, int);
 extern struct page *lookup_swap_cache(swp_entry_t entry,
@@ -610,6 +611,10 @@ static inline int swap_writepage(struct page *p, struct writeback_control *wbc)
 	return 0;
 }
 
+static inline void swapcache_clear(struct swap_info_struct *si, swp_entry_t entry)
+{
+}
+
 static inline struct page *lookup_swap_cache(swp_entry_t swp,
 					     struct vm_area_struct *vma,
 					     unsigned long addr)
diff --git a/mm/memory.c b/mm/memory.c
index 8e4068ef034b03926507b46ab6221811c6707d1a..68e92af0bfa54159c1a6c7157e49ffe97e76e4b3 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -3364,6 +3364,8 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
 {
 	struct vm_area_struct *vma = vmf->vma;
 	struct page *page = NULL, *swapcache;
+	struct swap_info_struct *si = NULL;
+	bool need_clear_cache = false;
 	swp_entry_t entry;
 	pte_t pte;
 	int locked;
@@ -3429,10 +3431,24 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
 	swapcache = page;
 
 	if (!page) {
-		struct swap_info_struct *si = swp_swap_info(entry);
+		si = swp_swap_info(entry);
 
 		if (data_race(si->flags & SWP_SYNCHRONOUS_IO) &&
 		    __swap_count(entry) == 1) {
+			/*
+			 * Prevent parallel swapin from proceeding with
+			 * the cache flag. Otherwise, another thread may
+			 * finish swapin first, free the entry, and swapout
+			 * reusing the same entry. It's undetectable as
+			 * pte_same() returns true due to entry reuse.
+			 */
+			if (swapcache_prepare(entry)) {
+				/* Relax a bit to prevent rapid repeated page faults */
+				schedule_timeout_uninterruptible(1);
+				goto out;
+			}
+			need_clear_cache = true;
+
 			/* skip swapcache */
 			page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma,
 							vmf->address);
@@ -3601,6 +3617,9 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
 unlock:
 	pte_unmap_unlock(vmf->pte, vmf->ptl);
 out:
+	/* Clear the swap cache pin for direct swapin after PTL unlock */
+	if (need_clear_cache)
+		swapcache_clear(si, entry);
 	return ret;
 out_nomap:
 	pte_unmap_unlock(vmf->pte, vmf->ptl);
@@ -3612,6 +3631,8 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
 		unlock_page(swapcache);
 		put_page(swapcache);
 	}
+	if (need_clear_cache)
+		swapcache_clear(si, entry);
 	return ret;
 }
 
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 9fe12f0b92058760582d28cb3f3f41f1b607a327..3d7b26249f62040d9cdcee2ce2566c1fee3f6c19 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -3561,6 +3561,19 @@ int swapcache_prepare(swp_entry_t entry)
 	return __swap_duplicate(entry, SWAP_HAS_CACHE);
 }
 
+void swapcache_clear(struct swap_info_struct *si, swp_entry_t entry)
+{
+	struct swap_cluster_info *ci;
+	unsigned long offset = swp_offset(entry);
+	unsigned char usage;
+
+	ci = lock_cluster_or_swap_info(si, offset);
+	usage = __swap_entry_free_locked(si, offset, SWAP_HAS_CACHE);
+	unlock_cluster_or_swap_info(si, ci);
+	if (!usage)
+		free_swap_slot(entry);
+}
+
 struct swap_info_struct *swp_swap_info(swp_entry_t entry)
 {
 	return swap_type_to_swap_info(swp_type(entry));