mm, swap: use unified helper for swap cache look up

The swap cache lookup helper swap_cache_get_folio currently does readahead
updates as well, so callers that are not doing swapin from any VMA or
mapping are forced to reuse filemap helpers instead, and have to access
the swap cache space directly.

So decouple readahead update with swap cache lookup.  Move the readahead
update part into a standalone helper.  Let the caller call the readahead
update helper if they do readahead.  And convert all swap cache lookups to
use swap_cache_get_folio.

After this commit, there are only three special cases for accessing swap
cache space now: huge memory splitting, migration, and shmem replacing,
because they need to lock the XArray.  The following commits will wrap
their accesses to the swap cache too, with special helpers.

And worth noting, currently dropbehind is not supported for anon folio,
and we will never see a dropbehind folio in swap cache.  The unified
helper can be updated later to handle that.

While at it, add proper kernedoc for touched helpers.

No functional change.

Link: https://lkml.kernel.org/r/20250916160100.31545-3-ryncsn@gmail.com
Signed-off-by: Kairui Song <kasong@tencent.com>
Reviewed-by: Baolin Wang <baolin.wang@linux.alibaba.com>
Reviewed-by: Barry Song <baohua@kernel.org>
Acked-by: David Hildenbrand <david@redhat.com>
Acked-by: Chris Li <chrisl@kernel.org>
Acked-by: Nhat Pham <nphamcs@gmail.com>
Suggested-by: Chris Li <chrisl@kernel.org>
Cc: Baoquan He <bhe@redhat.com>
Cc: "Huang, Ying" <ying.huang@linux.alibaba.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Kemeng Shi <shikemeng@huaweicloud.com>
Cc: kernel test robot <oliver.sang@intel.com>
Cc: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Yosry Ahmed <yosryahmed@google.com>
Cc: Zi Yan <ziy@nvidia.com>
Cc: SeongJae Park <sj@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

1 files changed, 57 insertions, 52 deletions

diff --git a/mm/swap_state.c b/mm/swap_state.c
index 99513b74b5d8..68ec531d0f2b 100644
--- a/mm/swap_state.c
+++ b/mm/swap_state.c
@@ -69,6 +69,27 @@ void show_swap_cache_info(void)
 	printk("Total swap = %lukB\n", K(total_swap_pages));
 }
 
+/**
+ * swap_cache_get_folio - Looks up a folio in the swap cache.
+ * @entry: swap entry used for the lookup.
+ *
+ * A found folio will be returned unlocked and with its refcount increased.
+ *
+ * Context: Caller must ensure @entry is valid and protect the swap device
+ * with reference count or locks.
+ * Return: Returns the found folio on success, NULL otherwise. The caller
+ * must lock and check if the folio still matches the swap entry before
+ * use.
+ */
+struct folio *swap_cache_get_folio(swp_entry_t entry)
+{
+	struct folio *folio = filemap_get_folio(swap_address_space(entry),
+						swap_cache_index(entry));
+	if (IS_ERR(folio))
+		return NULL;
+	return folio;
+}
+
 void *get_shadow_from_swap_cache(swp_entry_t entry)
 {
 	struct address_space *address_space = swap_address_space(entry);
@@ -272,55 +293,43 @@ static inline bool swap_use_vma_readahead(void)
 	return READ_ONCE(enable_vma_readahead) && !atomic_read(&nr_rotate_swap);
 }
 
-/*
- * Lookup a swap entry in the swap cache. A found folio will be returned
- * unlocked and with its refcount incremented - we rely on the kernel
- * lock getting page table operations atomic even if we drop the folio
- * lock before returning.
- *
- * Caller must lock the swap device or hold a reference to keep it valid.
+/**
+ * swap_update_readahead - Update the readahead statistics of VMA or globally.
+ * @folio: the swap cache folio that just got hit.
+ * @vma: the VMA that should be updated, could be NULL for global update.
+ * @addr: the addr that triggered the swapin, ignored if @vma is NULL.
  */
-struct folio *swap_cache_get_folio(swp_entry_t entry,
-		struct vm_area_struct *vma, unsigned long addr)
+void swap_update_readahead(struct folio *folio, struct vm_area_struct *vma,
+			   unsigned long addr)
 {
-	struct folio *folio;
-
-	folio = filemap_get_folio(swap_address_space(entry), swap_cache_index(entry));
-	if (!IS_ERR(folio)) {
-		bool vma_ra = swap_use_vma_readahead();
-		bool readahead;
+	bool readahead, vma_ra = swap_use_vma_readahead();
 
-		/*
-		 * At the moment, we don't support PG_readahead for anon THP
-		 * so let's bail out rather than confusing the readahead stat.
-		 */
-		if (unlikely(folio_test_large(folio)))
-			return folio;
-
-		readahead = folio_test_clear_readahead(folio);
-		if (vma && vma_ra) {
-			unsigned long ra_val;
-			int win, hits;
-
-			ra_val = GET_SWAP_RA_VAL(vma);
-			win = SWAP_RA_WIN(ra_val);
-			hits = SWAP_RA_HITS(ra_val);
-			if (readahead)
-				hits = min_t(int, hits + 1, SWAP_RA_HITS_MAX);
-			atomic_long_set(&vma->swap_readahead_info,
-					SWAP_RA_VAL(addr, win, hits));
-		}
-
-		if (readahead) {
-			count_vm_event(SWAP_RA_HIT);
-			if (!vma || !vma_ra)
-				atomic_inc(&swapin_readahead_hits);
-		}
-	} else {
-		folio = NULL;
+	/*
+	 * At the moment, we don't support PG_readahead for anon THP
+	 * so let's bail out rather than confusing the readahead stat.
+	 */
+	if (unlikely(folio_test_large(folio)))
+		return;
+
+	readahead = folio_test_clear_readahead(folio);
+	if (vma && vma_ra) {
+		unsigned long ra_val;
+		int win, hits;
+
+		ra_val = GET_SWAP_RA_VAL(vma);
+		win = SWAP_RA_WIN(ra_val);
+		hits = SWAP_RA_HITS(ra_val);
+		if (readahead)
+			hits = min_t(int, hits + 1, SWAP_RA_HITS_MAX);
+		atomic_long_set(&vma->swap_readahead_info,
+				SWAP_RA_VAL(addr, win, hits));
 	}
 
-	return folio;
+	if (readahead) {
+		count_vm_event(SWAP_RA_HIT);
+		if (!vma || !vma_ra)
+			atomic_inc(&swapin_readahead_hits);
+	}
 }
 
 struct folio *__read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
@@ -336,14 +345,10 @@ struct folio *__read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
 	*new_page_allocated = false;
 	for (;;) {
 		int err;
-		/*
-		 * First check the swap cache.  Since this is normally
-		 * called after swap_cache_get_folio() failed, re-calling
-		 * that would confuse statistics.
-		 */
-		folio = filemap_get_folio(swap_address_space(entry),
-					  swap_cache_index(entry));
-		if (!IS_ERR(folio))
+
+		/* Check the swap cache in case the folio is already there */
+		folio = swap_cache_get_folio(entry);
+		if (folio)
 			goto got_folio;
 
 		/*