linux-kernel - [PATCH] mm/z3fold.c: Fix race between migration and destruction

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-next>] [day] [month] [year] [list]

Message-Id: <20190809164643.5978-1-henryburns@google.com>
Date:   Fri,  9 Aug 2019 09:46:43 -0700
From:   Henry Burns <henryburns@...gle.com>
To:     Vitaly Wool <vitalywool@...il.com>,
        Andrew Morton <akpm@...ux-foundation.org>
Cc:     Vitaly Vul <vitaly.vul@...y.com>,
        Shakeel Butt <shakeelb@...gle.com>,
        Jonathan Adams <jwadams@...gle.com>, linux-mm@...ck.org,
        linux-kernel@...r.kernel.org, Henry Burns <henryburns@...gle.com>
Subject: [PATCH] mm/z3fold.c: Fix race between migration and destruction

In z3fold_destroy_pool() we call destroy_workqueue(&pool->compact_wq).
However, we have no guarantee that migration isn't happening in the
background at that time.

Migration directly calls queue_work_on(pool->compact_wq), if destruction
wins that race we are using a destroyed workqueue.

Signed-off-by: Henry Burns <henryburns@...gle.com>
---
 mm/z3fold.c | 51 +++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 51 insertions(+)

diff --git a/mm/z3fold.c b/mm/z3fold.c
index 78447cecfffa..e136d97ce56e 100644
--- a/mm/z3fold.c
+++ b/mm/z3fold.c
@@ -40,6 +40,7 @@
 #include <linux/workqueue.h>
 #include <linux/slab.h>
 #include <linux/spinlock.h>
+#include <linux/wait.h>
 #include <linux/zpool.h>
 
 /*
@@ -161,8 +162,10 @@ struct z3fold_pool {
 	const struct zpool_ops *zpool_ops;
 	struct workqueue_struct *compact_wq;
 	struct workqueue_struct *release_wq;
+	struct wait_queue_head isolate_wait;
 	struct work_struct work;
 	struct inode *inode;
+	int isolated_pages;
 };
 
 /*
@@ -772,6 +775,7 @@ static struct z3fold_pool *z3fold_create_pool(const char *name, gfp_t gfp,
 		goto out_c;
 	spin_lock_init(&pool->lock);
 	spin_lock_init(&pool->stale_lock);
+	init_waitqueue_head(&pool->isolate_wait);
 	pool->unbuddied = __alloc_percpu(sizeof(struct list_head)*NCHUNKS, 2);
 	if (!pool->unbuddied)
 		goto out_pool;
@@ -811,6 +815,15 @@ static struct z3fold_pool *z3fold_create_pool(const char *name, gfp_t gfp,
 	return NULL;
 }
 
+static bool pool_isolated_are_drained(struct z3fold_pool *pool)
+{
+	bool ret;
+
+	spin_lock(&pool->lock);
+	ret = pool->isolated_pages == 0;
+	spin_unlock(&pool->lock);
+	return ret;
+}
 /**
  * z3fold_destroy_pool() - destroys an existing z3fold pool
  * @pool:	the z3fold pool to be destroyed
@@ -821,6 +834,13 @@ static void z3fold_destroy_pool(struct z3fold_pool *pool)
 {
 	kmem_cache_destroy(pool->c_handle);
 
+	/*
+	 * We need to ensure that no pages are being migrated while we destroy
+	 * these workqueues, as migration can queue work on either of the
+	 * workqueues.
+	 */
+	wait_event(pool->isolate_wait, !pool_isolated_are_drained(pool));
+
 	/*
 	 * We need to destroy pool->compact_wq before pool->release_wq,
 	 * as any pending work on pool->compact_wq will call
@@ -1317,6 +1337,28 @@ static u64 z3fold_get_pool_size(struct z3fold_pool *pool)
 	return atomic64_read(&pool->pages_nr);
 }
 
+/*
+ * z3fold_dec_isolated() expects to be called while pool->lock is held.
+ */
+static void z3fold_dec_isolated(struct z3fold_pool *pool)
+{
+	assert_spin_locked(&pool->lock);
+	VM_BUG_ON(pool->isolated_pages <= 0);
+	pool->isolated_pages--;
+
+	/*
+	 * If we have no more isolated pages, we have to see if
+	 * z3fold_destroy_pool() is waiting for a signal.
+	 */
+	if (pool->isolated_pages == 0 && waitqueue_active(&pool->isolate_wait))
+		wake_up_all(&pool->isolate_wait);
+}
+
+static void z3fold_inc_isolated(struct z3fold_pool *pool)
+{
+	pool->isolated_pages++;
+}
+
 static bool z3fold_page_isolate(struct page *page, isolate_mode_t mode)
 {
 	struct z3fold_header *zhdr;
@@ -1343,6 +1385,7 @@ static bool z3fold_page_isolate(struct page *page, isolate_mode_t mode)
 		spin_lock(&pool->lock);
 		if (!list_empty(&page->lru))
 			list_del(&page->lru);
+		z3fold_inc_isolated(pool);
 		spin_unlock(&pool->lock);
 		z3fold_page_unlock(zhdr);
 		return true;
@@ -1417,6 +1460,10 @@ static int z3fold_page_migrate(struct address_space *mapping, struct page *newpa
 
 	queue_work_on(new_zhdr->cpu, pool->compact_wq, &new_zhdr->work);
 
+	spin_lock(&pool->lock);
+	z3fold_dec_isolated(pool);
+	spin_unlock(&pool->lock);
+
 	page_mapcount_reset(page);
 	put_page(page);
 	return 0;
@@ -1436,10 +1483,14 @@ static void z3fold_page_putback(struct page *page)
 	INIT_LIST_HEAD(&page->lru);
 	if (kref_put(&zhdr->refcount, release_z3fold_page_locked)) {
 		atomic64_dec(&pool->pages_nr);
+		spin_lock(&pool->lock);
+		z3fold_dec_isolated(pool);
+		spin_unlock(&pool->lock);
 		return;
 	}
 	spin_lock(&pool->lock);
 	list_add(&page->lru, &pool->lru);
+	z3fold_dec_isolated(pool);
 	spin_unlock(&pool->lock);
 	z3fold_page_unlock(zhdr);
 }
-- 
2.22.0.770.g0f2c4a37fd-goog