linux-kernel - [PATCH 6/8] mm/vmalloc: Defer freeing partly initialized vm

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-Id: <20250807075810.358714-7-urezki@gmail.com>
Date: Thu,  7 Aug 2025 09:58:08 +0200
From: "Uladzislau Rezki (Sony)" <urezki@...il.com>
To: linux-mm@...ck.org,
	Andrew Morton <akpm@...ux-foundation.org>
Cc: Vlastimil Babka <vbabka@...e.cz>,
	Michal Hocko <mhocko@...nel.org>,
	Baoquan He <bhe@...hat.com>,
	LKML <linux-kernel@...r.kernel.org>,
	Uladzislau Rezki <urezki@...il.com>
Subject: [PATCH 6/8] 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.

Signed-off-by: Uladzislau Rezki (Sony) <urezki@...il.com>
---
 include/linux/vmalloc.h |  6 +++++-
 mm/vmalloc.c            | 34 +++++++++++++++++++++++++++++++---
 2 files changed, 36 insertions(+), 4 deletions(-)

diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h
index fdc9aeb74a44..b1425fae8cbf 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 7f48a54ec108..2424f80d524a 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -3680,6 +3680,35 @@ 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)
@@ -3711,8 +3740,7 @@ 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);
@@ -3789,7 +3817,7 @@ 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;
 }
 
-- 
2.39.5