[RFC PATCH v2 10/10] mm, swap: defer xswap shrink to workqueue to avoid lock recursion

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

xswap_try_shrink() was called directly from __free_cluster() while
holding ci->lock.  The shrink path calls xswap_unmap_clusters()
which unmaps vmalloc pages backing cluster_info, and on return
swap_cache_del_folio() tries swap_cluster_unlock(ci) on the now-
unmapped address — crashing on a not-present page.

Replace direct calls with schedule_work() so shrink runs in an
independent workqueue context where no cluster locks are held.
Use cancel_work_sync() during swapoff to ensure no pending shrink
work races with the VM area teardown.

Signed-off-by: Baoquan He <baoquan.he@linux.dev>
---
 include/linux/swap.h |  1 +
 mm/swapfile.c        | 19 +++++++++++++------
 2 files changed, 14 insertions(+), 6 deletions(-)

diff --git a/include/linux/swap.h b/include/linux/swap.h
index 4f4583f9a4e5..a5b323374769 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -255,6 +255,7 @@ struct swap_info_struct {
 	unsigned long		nr_clusters_mapped; /* currently mapped cluster count */
 	unsigned long		nr_free_tail;	/* contiguous free clusters at tail */
 	struct dentry		*debugfs_entry;	/* debugfs: type<N>_max_clusters */
+	struct work_struct	xswap_shrink_work; /* deferred shrink trigger */
 	struct mutex		xswap_lock;	/* serialize map/unmap operations */
 #endif
 	struct list_head free_clusters; /* free clusters list */
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 265f2bac1a12..ca406556626e 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -127,11 +127,8 @@ static ssize_t xswap_max_clusters_write(struct file *file,
 		spin_unlock(&swap_lock);
 	}
 
-	/*
-	 * Lowering the ceiling may make tail clusters eligible for
-	 * shrinking.  Trigger an immediate check.
-	 */
-	xswap_try_shrink(si);
+	/* Shrink trigger: lowering the ceiling may free tail clusters. */
+	schedule_work(&si->xswap_shrink_work);
 
 	return count;
 }
@@ -726,7 +723,7 @@ static void __free_cluster(struct swap_info_struct *si, struct swap_cluster_info
 	ci->order = 0;
 #ifdef CONFIG_XSWAP
 	xswap_update_free_tail(si, ci - si->cluster_info);
-	xswap_try_shrink(si);
+	schedule_work(&si->xswap_shrink_work);
 #endif
 }
 
@@ -3236,6 +3233,7 @@ static void free_swap_cluster_info(struct swap_info_struct *si)
 #ifdef CONFIG_XSWAP
 	if (si->flags & SWP_XSWAP) {
 		xswap_debugfs_del(si);
+		cancel_work_sync(&si->xswap_shrink_work);
 		/* Unmap all mapped clusters and free the VM_SPARSE area */
 		if (si->nr_clusters_mapped > 0)
 			xswap_unmap_clusters(si, 0, si->nr_clusters_mapped);
@@ -4057,6 +4055,13 @@ static void xswap_trim_free_tail(struct swap_info_struct *si, unsigned long idx)
 		WRITE_ONCE(si->nr_free_tail, nr_mapped - idx - 1);
 }
 
+static void xswap_shrink_work_fn(struct work_struct *work)
+{
+	struct swap_info_struct *si = container_of(work,
+			struct swap_info_struct, xswap_shrink_work);
+	xswap_try_shrink(si);
+}
+
 /*
  * Try to shrink the cluster_info tail.  Uses si->nr_free_tail which
  * is maintained incrementally during alloc/free — no scanning needed.
@@ -4163,7 +4168,9 @@ static int setup_swap_clusters_info(struct swap_info_struct *si,
 
 		/* All mapped clusters except cluster 0 are free at the tail */
 		si->nr_free_tail = si->nr_clusters_mapped - 1;
+
 		mutex_init(&si->xswap_lock);
+		INIT_WORK(&si->xswap_shrink_work, xswap_shrink_work_fn);
 		xswap_debugfs_add(si);
 		return 0;
 
-- 
2.54.0