[PATCH v3 16/20] swap: do not unnecesarily pin readahead swap entries

[Nhat Pham <nphamcs@gmail.com>]

When we perform swap readahead, the target entry is already pinned by
the caller. No need to pin swap entries in the readahead window that
belongs in the same virtual swap cluster as the target swap entry.

Signed-off-by: Nhat Pham <nphamcs@gmail.com>
---
 mm/swap.h       |  1 +
 mm/swap_state.c | 22 +++++++++-------------
 mm/vswap.c      | 10 ++++++++++
 3 files changed, 20 insertions(+), 13 deletions(-)

diff --git a/mm/swap.h b/mm/swap.h
index d41e6a0e70753..08a6369a6dfad 100644
--- a/mm/swap.h
+++ b/mm/swap.h
@@ -213,6 +213,7 @@ void swap_cache_lock(swp_entry_t entry);
 void swap_cache_unlock(swp_entry_t entry);
 void vswap_rmap_set(struct swap_cluster_info *ci, swp_slot_t slot,
 			   unsigned long vswap, int nr);
+bool vswap_same_cluster(swp_entry_t entry1, swp_entry_t entry2);
 
 static inline struct address_space *swap_address_space(swp_entry_t entry)
 {
diff --git a/mm/swap_state.c b/mm/swap_state.c
index ad80bf098b63f..e8e0905c7723f 100644
--- a/mm/swap_state.c
+++ b/mm/swap_state.c
@@ -553,22 +553,18 @@ static struct folio *swap_vma_readahead(swp_entry_t targ_entry, gfp_t gfp_mask,
 		pte_unmap(pte);
 		pte = NULL;
 		/*
-		 * Readahead entry may come from a device that we are not
-		 * holding a reference to, try to grab a reference, or skip.
-		 *
-		 * XXX: for now, always try to pin the swap entries in the
-		 * readahead window to avoid the annoying conversion to physical
-		 * swap slots. Once we move all swap metadata to virtual swap
-		 * layer, we can simply compare the clusters of the target
-		 * swap entry and the current swap entry, and pin the latter
-		 * swap entry's cluster if it differ from the former's.
+		 * The target entry is already pinned - if the readahead entry
+		 * belongs to the same cluster, it's already protected.
 		 */
-		swapoff_locked = tryget_swap_entry(entry, &si);
-		if (!swapoff_locked)
-			continue;
+		if (!vswap_same_cluster(entry, targ_entry)) {
+			swapoff_locked = tryget_swap_entry(entry, &si);
+			if (!swapoff_locked)
+				continue;
+		}
 		folio = __read_swap_cache_async(entry, gfp_mask, mpol, ilx,
 						&page_allocated, false);
-		put_swap_entry(entry, si);
+		if (swapoff_locked)
+			put_swap_entry(entry, si);
 		if (!folio)
 			continue;
 		if (page_allocated) {
diff --git a/mm/vswap.c b/mm/vswap.c
index fb6179ce3ace7..7563107eb8eee 100644
--- a/mm/vswap.c
+++ b/mm/vswap.c
@@ -1503,6 +1503,16 @@ void put_swap_entry(swp_entry_t entry, struct swap_info_struct *si)
 	rcu_read_unlock();
 }
 
+/*
+ * Check if two virtual swap entries belong to the same vswap cluster.
+ * Useful for optimizing readahead when entries in the same cluster
+ * share protection from a pinned target entry.
+ */
+bool vswap_same_cluster(swp_entry_t entry1, swp_entry_t entry2)
+{
+	return VSWAP_CLUSTER_IDX(entry1) == VSWAP_CLUSTER_IDX(entry2);
+}
+
 static int vswap_cpu_dead(unsigned int cpu)
 {
 	struct percpu_vswap_cluster *percpu_cluster;
-- 
2.47.3