[RFC PATCH 05/11] mm, swap: add xswap_try_shrink and shrink trigger on cluster free

[Baoquan He <baoquan.he@linux.dev>]

Add xswap_try_shrink() — the shrink logic that scans backwards from
the tail to find contiguous free clusters, then unmaps full pages
when >= XSWAP_GROW_CLUSTERS free clusters accumulate.

Wire the trigger in __free_cluster(): after a cluster is released to
the free list, call xswap_try_shrink() to attempt tail shrinking.
Also update the XSWAP_GROW_CLUSTERS comment to reflect both grow
and shrink semantics.

Signed-off-by: Baoquan He <baoquan.he@linux.dev>
---
 mm/swapfile.c | 48 ++++++++++++++++++++++++++++++++++++++++++++----
 1 file changed, 44 insertions(+), 4 deletions(-)

diff --git a/mm/swapfile.c b/mm/swapfile.c
index 8a048b2897ce..e0f5fe64de2a 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -51,11 +51,13 @@
 
 #ifdef CONFIG_XSWAP
 /*
- * xswap: dynamically grow the cluster_info array via a VM_SPARSE area.
+ * xswap: dynamically grow and shrink the cluster_info array via a
+ * VM_SPARSE area.
  *
- * XSWAP_GROW_CLUSTERS is the number of clusters to map in one grow
- * operation.  It is set to the number of cluster_info structs that
- * fit in a single page (at least 16), so that the vmalloc page table
+ * XSWAP_GROW_CLUSTERS is the number of clusters to map/unmap in one
+ * grow/shrink operation.  It is set to the number of cluster_info
+ * structs that fit in a single page (at least 16), so that the vmalloc
+ * page table
  * overhead is proportional to the number of clusters mapped.
  */
 #define XSWAP_GROW_CLUSTERS \
@@ -66,6 +68,7 @@ static int xswap_map_clusters(struct swap_info_struct *si,
 static void xswap_unmap_clusters(struct swap_info_struct *si,
 				 unsigned long start_idx, unsigned long nr);
 static int xswap_check_mapped(pte_t *pte, unsigned long addr, void *data);
+static void xswap_try_shrink(struct swap_info_struct *si);
 #endif
 
 static void swap_range_alloc(struct swap_info_struct *si,
@@ -629,6 +632,9 @@ static void __free_cluster(struct swap_info_struct *si, struct swap_cluster_info
 	swap_cluster_free_table(ci);
 	move_cluster(si, ci, &si->free_clusters, CLUSTER_FLAG_FREE);
 	ci->order = 0;
+#ifdef CONFIG_XSWAP
+	xswap_try_shrink(si);
+#endif
 }
 
 /*
@@ -3809,6 +3815,40 @@ static int xswap_check_mapped(pte_t *pte, unsigned long addr, void *data)
 {
 	return 1;
 }
+
+/*
+ * Try to shrink the cluster_info tail: unmap contiguous free clusters
+ * at the end of the mapped range.
+ */
+static void xswap_try_shrink(struct swap_info_struct *si)
+{
+	struct swap_cluster_info *ci;
+	unsigned long last, idx;
+
+	if (!(si->flags & SWP_XSWAP))
+		return;
+	if (READ_ONCE(si->nr_clusters_mapped) <= 1) /* keep cluster 0 */
+		return;
+
+	/* Find the last non-free cluster from the tail */
+	last = READ_ONCE(si->nr_clusters_mapped);
+	while (last > 1) {
+		idx = last - 1;
+		ci = &si->cluster_info[idx];
+		if (ci->count || ci->flags != CLUSTER_FLAG_FREE)
+			break;
+		last = idx;
+	}
+
+	if (last == si->nr_clusters_mapped)
+		return; /* nothing to shrink */
+
+	/* Only unmap if we can free at least one full page of clusters */
+	if (si->nr_clusters_mapped - last < XSWAP_GROW_CLUSTERS)
+		return;
+
+	xswap_unmap_clusters(si, last, si->nr_clusters_mapped - last);
+}
 #endif /* CONFIG_XSWAP */
 
 static int setup_swap_clusters_info(struct swap_info_struct *si,
-- 
2.54.0