[PATCH v4 16/19] mm, swap: check swap table directly for checking cache

[Kairui Song <ryncsn@gmail.com>]

From: Kairui Song <kasong@tencent.com>

Instead of looking at the swap map, check swap table directly to tell
if a swap slot is cached. Prepares for the removal of SWAP_HAS_CACHE.

Signed-off-by: Kairui Song <kasong@tencent.com>
---
 mm/swap.h        | 11 ++++++++---
 mm/swap_state.c  | 16 ++++++++++++++++
 mm/swapfile.c    | 55 +++++++++++++++++++++++++++++--------------------------
 mm/userfaultfd.c | 10 +++-------
 4 files changed, 56 insertions(+), 36 deletions(-)

diff --git a/mm/swap.h b/mm/swap.h
index ec1ef7d0c35b..3692e143eeba 100644
--- a/mm/swap.h
+++ b/mm/swap.h
@@ -275,6 +275,7 @@ void __swapcache_clear_cached(struct swap_info_struct *si,
  *   swap entries in the page table, similar to locking swap cache folio.
  * - See the comment of get_swap_device() for more complex usage.
  */
+bool swap_cache_has_folio(swp_entry_t entry);
 struct folio *swap_cache_get_folio(swp_entry_t entry);
 void *swap_cache_get_shadow(swp_entry_t entry);
 void swap_cache_del_folio(struct folio *folio);
@@ -335,8 +336,6 @@ static inline int swap_zeromap_batch(swp_entry_t entry, int max_nr,
 
 static inline int non_swapcache_batch(swp_entry_t entry, int max_nr)
 {
-	struct swap_info_struct *si = __swap_entry_to_info(entry);
-	pgoff_t offset = swp_offset(entry);
 	int i;
 
 	/*
@@ -345,8 +344,9 @@ static inline int non_swapcache_batch(swp_entry_t entry, int max_nr)
 	 * be in conflict with the folio in swap cache.
 	 */
 	for (i = 0; i < max_nr; i++) {
-		if ((si->swap_map[offset + i] & SWAP_HAS_CACHE))
+		if (swap_cache_has_folio(entry))
 			return i;
+		entry.val++;
 	}
 
 	return i;
@@ -449,6 +449,11 @@ static inline int swap_writeout(struct folio *folio,
 	return 0;
 }
 
+static inline bool swap_cache_has_folio(swp_entry_t entry)
+{
+	return false;
+}
+
 static inline struct folio *swap_cache_get_folio(swp_entry_t entry)
 {
 	return NULL;
diff --git a/mm/swap_state.c b/mm/swap_state.c
index f478a16f43e9..6bf7556ca408 100644
--- a/mm/swap_state.c
+++ b/mm/swap_state.c
@@ -103,6 +103,22 @@ struct folio *swap_cache_get_folio(swp_entry_t entry)
 	return NULL;
 }
 
+/**
+ * swap_cache_has_folio - Check if a swap slot has cache.
+ * @entry: swap entry indicating the slot.
+ *
+ * Context: Caller must ensure @entry is valid and protect the swap
+ * device with reference count or locks.
+ */
+bool swap_cache_has_folio(swp_entry_t entry)
+{
+	unsigned long swp_tb;
+
+	swp_tb = swap_table_get(__swap_entry_to_cluster(entry),
+				swp_cluster_offset(entry));
+	return swp_tb_is_folio(swp_tb);
+}
+
 /**
  * swap_cache_get_shadow - Looks up a shadow in the swap cache.
  * @entry: swap entry used for the lookup.
diff --git a/mm/swapfile.c b/mm/swapfile.c
index aaa8790241a8..2cb3bfef3234 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -792,23 +792,18 @@ static bool cluster_reclaim_range(struct swap_info_struct *si,
 	unsigned int nr_pages = 1 << order;
 	unsigned long offset = start, end = start + nr_pages;
 	unsigned char *map = si->swap_map;
-	int nr_reclaim;
+	unsigned long swp_tb;
 
 	spin_unlock(&ci->lock);
 	do {
-		switch (READ_ONCE(map[offset])) {
-		case 0:
+		if (swap_count(READ_ONCE(map[offset])))
 			break;
-		case SWAP_HAS_CACHE:
-			nr_reclaim = __try_to_reclaim_swap(si, offset, TTRS_ANYWAY);
-			if (nr_reclaim < 0)
-				goto out;
-			break;
-		default:
-			goto out;
+		swp_tb = swap_table_get(ci, offset % SWAPFILE_CLUSTER);
+		if (swp_tb_is_folio(swp_tb)) {
+			if (__try_to_reclaim_swap(si, offset, TTRS_ANYWAY) < 0)
+				break;
 		}
 	} while (++offset < end);
-out:
 	spin_lock(&ci->lock);
 
 	/*
@@ -829,37 +824,41 @@ static bool cluster_reclaim_range(struct swap_info_struct *si,
 	 * Recheck the range no matter reclaim succeeded or not, the slot
 	 * could have been be freed while we are not holding the lock.
 	 */
-	for (offset = start; offset < end; offset++)
-		if (READ_ONCE(map[offset]))
+	for (offset = start; offset < end; offset++) {
+		swp_tb = __swap_table_get(ci, offset % SWAPFILE_CLUSTER);
+		if (swap_count(map[offset]) || !swp_tb_is_null(swp_tb))
 			return false;
+	}
 
 	return true;
 }
 
 static bool cluster_scan_range(struct swap_info_struct *si,
 			       struct swap_cluster_info *ci,
-			       unsigned long start, unsigned int nr_pages,
+			       unsigned long offset, unsigned int nr_pages,
 			       bool *need_reclaim)
 {
-	unsigned long offset, end = start + nr_pages;
+	unsigned long end = offset + nr_pages;
 	unsigned char *map = si->swap_map;
+	unsigned long swp_tb;
 
 	if (cluster_is_empty(ci))
 		return true;
 
-	for (offset = start; offset < end; offset++) {
-		switch (READ_ONCE(map[offset])) {
-		case 0:
-			continue;
-		case SWAP_HAS_CACHE:
+	do {
+		if (swap_count(map[offset]))
+			return false;
+		swp_tb = __swap_table_get(ci, offset % SWAPFILE_CLUSTER);
+		if (swp_tb_is_folio(swp_tb)) {
+			WARN_ON_ONCE(!(map[offset] & SWAP_HAS_CACHE));
 			if (!vm_swap_full())
 				return false;
 			*need_reclaim = true;
-			continue;
-		default:
-			return false;
+		} else {
+			/* A entry with no count and no cache must be null */
+			VM_WARN_ON_ONCE(!swp_tb_is_null(swp_tb));
 		}
-	}
+	} while (++offset < end);
 
 	return true;
 }
@@ -1030,7 +1029,8 @@ static void swap_reclaim_full_clusters(struct swap_info_struct *si, bool force)
 		to_scan--;
 
 		while (offset < end) {
-			if (READ_ONCE(map[offset]) == SWAP_HAS_CACHE) {
+			if (!swap_count(READ_ONCE(map[offset])) &&
+			    swp_tb_is_folio(__swap_table_get(ci, offset % SWAPFILE_CLUSTER))) {
 				spin_unlock(&ci->lock);
 				nr_reclaim = __try_to_reclaim_swap(si, offset,
 								   TTRS_ANYWAY);
@@ -1980,6 +1980,7 @@ void swap_put_entries_direct(swp_entry_t entry, int nr)
 	struct swap_info_struct *si;
 	bool any_only_cache = false;
 	unsigned long offset;
+	unsigned long swp_tb;
 
 	si = get_swap_device(entry);
 	if (WARN_ON_ONCE(!si))
@@ -2004,7 +2005,9 @@ void swap_put_entries_direct(swp_entry_t entry, int nr)
 	 */
 	for (offset = start_offset; offset < end_offset; offset += nr) {
 		nr = 1;
-		if (READ_ONCE(si->swap_map[offset]) == SWAP_HAS_CACHE) {
+		swp_tb = swap_table_get(__swap_offset_to_cluster(si, offset),
+					offset % SWAPFILE_CLUSTER);
+		if (!swap_count(READ_ONCE(si->swap_map[offset])) && swp_tb_is_folio(swp_tb)) {
 			/*
 			 * Folios are always naturally aligned in swap so
 			 * advance forward to the next boundary. Zero means no
diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c
index e6dfd5f28acd..3f28aa319988 100644
--- a/mm/userfaultfd.c
+++ b/mm/userfaultfd.c
@@ -1190,17 +1190,13 @@ static int move_swap_pte(struct mm_struct *mm, struct vm_area_struct *dst_vma,
 		 * Check if the swap entry is cached after acquiring the src_pte
 		 * lock. Otherwise, we might miss a newly loaded swap cache folio.
 		 *
-		 * Check swap_map directly to minimize overhead, READ_ONCE is sufficient.
 		 * We are trying to catch newly added swap cache, the only possible case is
 		 * when a folio is swapped in and out again staying in swap cache, using the
 		 * same entry before the PTE check above. The PTL is acquired and released
-		 * twice, each time after updating the swap_map's flag. So holding
-		 * the PTL here ensures we see the updated value. False positive is possible,
-		 * e.g. SWP_SYNCHRONOUS_IO swapin may set the flag without touching the
-		 * cache, or during the tiny synchronization window between swap cache and
-		 * swap_map, but it will be gone very quickly, worst result is retry jitters.
+		 * twice, each time after updating the swap table. So holding
+		 * the PTL here ensures we see the updated value.
 		 */
-		if (READ_ONCE(si->swap_map[swp_offset(entry)]) & SWAP_HAS_CACHE) {
+		if (swap_cache_has_folio(entry)) {
 			double_pt_unlock(dst_ptl, src_ptl);
 			return -EAGAIN;
 		}

-- 
2.52.0