[PATCH 07/16] mm, swap: add xswap grow trigger on cluster allocation

[Baoquan He]

When cluster_alloc_swap_entry() fails to find a free cluster and
the xswap device still has room to grow, expand the mapped range
by XSWAP_GROW_CLUSTERS clusters.

Since xswap is always SWP_SOLIDSTATE, no locks need to be dropped
before calling xswap_map_clusters(), global_cluster_lock is never
held on this path.

The grow sequence:
1. Check nr_clusters_mapped < nr_clusters and free list empty
2. Call xswap_map_clusters() to allocate and map more physical pages
3. Add newly mapped clusters to si->free_clusters under si->lock
4. Retry allocation from the fresh free clusters

This makes the xswap cluster space grow transparently as swap usage
increases, without any userspace intervention.

Signed-off-by: Baoquan He <hebaoquan@xxxxxxxxxx>
---
 mm/swapfile.c | 45 +++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 45 insertions(+)

diff --git a/mm/swapfile.c b/mm/swapfile.c
index 1127e3d6596b..c6a01d74298a 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -1273,6 +1273,51 @@ static unsigned long cluster_alloc_swap_entry(struct swap_info_struct *si,
 		if (found)
 			goto done;
 	}
+
+#ifdef CONFIG_XSWAP
+	/*
+	 * For xswap: if no free cluster was found and more clusters
+	 * can be mapped, grow the cluster_info array and retry.
+	 */
+	if (!found && (si->flags & SWP_XSWAP) &&
+	    READ_ONCE(si->nr_clusters_mapped) < READ_ONCE(si->nr_clusters) &&
+	    list_empty(&si->free_clusters)) {
+		unsigned long nr_new = min(READ_ONCE(si->nr_clusters) -
+					  READ_ONCE(si->nr_clusters_mapped),
+					  XSWAP_GROW_CLUSTERS);
+		unsigned long start = READ_ONCE(si->nr_clusters_mapped);
+		unsigned long i;
+
+		if (!xswap_map_clusters(si, start, nr_new)) {
+			unsigned long added = 0;
+
+			for (i = start; i < start + nr_new; i++) {
+				struct swap_cluster_info *ci = &si->cluster_info[i];
+
+				/*
+				 * A concurrent grower may have already added
+				 * these clusters to the free list.  Only add
+				 * clusters that are still off-list (NONE).
+				 * Lock ci->lock first: move_cluster() takes
+				 * si->lock internally.
+				 */
+				spin_lock(&ci->lock);
+				if (ci->flags == CLUSTER_FLAG_NONE) {
+					move_cluster(si, ci, &si->free_clusters,
+						     CLUSTER_FLAG_FREE);
+					added++;
+				}
+				spin_unlock(&ci->lock);
+			}
+			WRITE_ONCE(si->nr_free_tail,
+				   READ_ONCE(si->nr_free_tail) + added);
+
+			/* Retry allocation from the free list */
+			found = alloc_swap_scan_list(si, &si->free_clusters,
+						    folio, false);
+		}
+	}
+#endif
 done:
 	if (!(si->flags & SWP_SOLIDSTATE))
 		spin_unlock(&si->global_cluster_lock);
-- 
2.54.0