[PATCH v3 4/4] mm: clarify the folio_free_swap() for do_swap_page()

["Barry Song (Xiaomi)" <baohua@kernel.org>]

Since commit 4b34f1d82c654 ("mm, swap: free the swap cache after
folio is mapped"), we have relied on do_wp_page() to handle the
non-exclusive case, where the folio may either be reused or require
CoW.

As a result, using the refcount in do_swap_page() to decide when to
free the swap cache is no longer necessary, since do_wp_page() can
handle this more cleanly and consistently.

We can now simply use FAULT_FLAG_WRITE together with exclusivity to
decide when to free the swap cache in do_swap_page().

Suggested-by: David Hildenbrand (Arm) <david@kernel.org>
Signed-off-by: Barry Song (Xiaomi) <baohua@kernel.org>
---
 mm/memory.c | 20 ++++++++------------
 1 file changed, 8 insertions(+), 12 deletions(-)

diff --git a/mm/memory.c b/mm/memory.c
index 4665405ace5a..a29cd38ad547 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -4516,7 +4516,7 @@ static vm_fault_t remove_device_exclusive_entry(struct vm_fault *vmf)
 static inline bool should_try_to_free_swap(struct swap_info_struct *si,
 					   struct folio *folio,
 					   struct vm_area_struct *vma,
-					   unsigned int extra_refs,
+					   bool exclusive,
 					   unsigned int fault_flags)
 {
 	if (!folio_test_swapcache(folio))
@@ -4532,14 +4532,12 @@ static inline bool should_try_to_free_swap(struct swap_info_struct *si,
 	if (mem_cgroup_swap_full(folio) || (vma->vm_flags & VM_LOCKED) ||
 	    folio_test_mlocked(folio))
 		return true;
+
 	/*
-	 * If we want to map a page that's in the swapcache writable, we
-	 * have to detect via the refcount if we're really the exclusive
-	 * user. Try freeing the swapcache to get rid of the swapcache
-	 * reference only in case it's likely that we'll be the exclusive user.
+	 * Free the swapcache only if we are the exclusive user and
+	 * this is a write fault.
 	 */
-	return (fault_flags & FAULT_FLAG_WRITE) && !folio_test_ksm(folio) &&
-		folio_ref_count(folio) == (extra_refs + folio_nr_pages(folio));
+	return (fault_flags & FAULT_FLAG_WRITE) && exclusive;
 }
 
 static vm_fault_t pte_marker_clear(struct vm_fault *vmf)
@@ -5043,10 +5041,8 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
 		if ((vma->vm_flags & VM_WRITE) && !userfaultfd_pte_wp(vma, pte) &&
 		    !pte_needs_soft_dirty_wp(vma, pte)) {
 			pte = pte_mkwrite(pte, vma);
-			if (vmf->flags & FAULT_FLAG_WRITE) {
+			if (vmf->flags & FAULT_FLAG_WRITE)
 				pte = pte_mkdirty(pte);
-				vmf->flags &= ~FAULT_FLAG_WRITE;
-			}
 		}
 		rmap_flags |= RMAP_EXCLUSIVE;
 	}
@@ -5086,7 +5082,7 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
 	 * Do it after mapping, so raced page faults will likely see the folio
 	 * in swap cache and wait on the folio lock.
 	 */
-	if (should_try_to_free_swap(si, folio, vma, nr_pages, vmf->flags))
+	if (should_try_to_free_swap(si, folio, vma, exclusive, vmf->flags))
 		folio_free_swap(folio);
 
 	folio_unlock(folio);
@@ -5103,7 +5099,7 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
 		folio_put(swapcache);
 	}
 
-	if (vmf->flags & FAULT_FLAG_WRITE) {
+	if ((vmf->flags & FAULT_FLAG_WRITE) && !pte_write(pte)) {
 		ret |= do_wp_page(vmf);
 		if (ret & VM_FAULT_ERROR)
 			ret &= VM_FAULT_ERROR;
-- 
2.39.3 (Apple Git-146)