mm/vmalloc: defer freeing partly initialized vm_struct

__vmalloc_area_node() may call free_vmap_area() or vfree() on error paths,
both of which can sleep.  This becomes problematic if the function is
invoked from an atomic context, such as when GFP_ATOMIC or GFP_NOWAIT is
passed via gfp_mask.

To fix this, unify error paths and defer the cleanup of partly initialized
vm_struct objects to a workqueue.  This ensures that freeing happens in a
process context and avoids invalid sleeps in atomic regions.

Link: https://lkml.kernel.org/r/20251007122035.56347-5-urezki@gmail.com
Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Reviewed-by: Baoquan He <bhe@redhat.com>
Cc: Alexander Potapenko <glider@google.com>
Cc: Andrey Ryabinin <ryabinin.a.a@gmail.com>
Cc: Marco Elver <elver@google.com>
Cc: Michal Hocko <mhocko@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

2 files changed, 36 insertions, 4 deletions

diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h
index eb54b7b3202f..1e43181369f1 100644
--- a/include/linux/vmalloc.h
+++ b/include/linux/vmalloc.h
@@ -50,7 +50,11 @@ struct iov_iter;		/* in uio.h */
 #endif
 
 struct vm_struct {
-	struct vm_struct	*next;
+	union {
+		struct vm_struct *next;	  /* Early registration of vm_areas. */
+		struct llist_node llnode; /* Asynchronous freeing on error paths. */
+	};
+
 	void			*addr;
 	unsigned long		size;
 	unsigned long		flags;
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index d83c01caaabe..9e29dd767c41 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -3687,6 +3687,35 @@ vm_area_alloc_pages(gfp_t gfp, int nid,
 	return nr_allocated;
 }
 
+static LLIST_HEAD(pending_vm_area_cleanup);
+static void cleanup_vm_area_work(struct work_struct *work)
+{
+	struct vm_struct *area, *tmp;
+	struct llist_node *head;
+
+	head = llist_del_all(&pending_vm_area_cleanup);
+	if (!head)
+		return;
+
+	llist_for_each_entry_safe(area, tmp, head, llnode) {
+		if (!area->pages)
+			free_vm_area(area);
+		else
+			vfree(area->addr);
+	}
+}
+
+/*
+ * Helper for __vmalloc_area_node() to defer cleanup
+ * of partially initialized vm_struct in error paths.
+ */
+static DECLARE_WORK(cleanup_vm_area, cleanup_vm_area_work);
+static void defer_vm_area_cleanup(struct vm_struct *area)
+{
+	if (llist_add(&area->llnode, &pending_vm_area_cleanup))
+		schedule_work(&cleanup_vm_area);
+}
+
 static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask,
 				 pgprot_t prot, unsigned int page_shift,
 				 int node)
@@ -3718,8 +3747,7 @@ static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask,
 		warn_alloc(gfp_mask, NULL,
 			"vmalloc error: size %lu, failed to allocated page array size %lu",
 			nr_small_pages * PAGE_SIZE, array_size);
-		free_vm_area(area);
-		return NULL;
+		goto fail;
 	}
 
 	set_vm_area_page_order(area, page_shift - PAGE_SHIFT);
@@ -3796,7 +3824,7 @@ static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask,
 	return area->addr;
 
 fail:
-	vfree(area->addr);
+	defer_vm_area_cleanup(area);
 	return NULL;
 }