[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20220528021235.2120995-3-yukuai3@huawei.com>
Date: Sat, 28 May 2022 10:12:31 +0800
From: Yu Kuai <yukuai3@...wei.com>
To: <josef@...icpanda.com>, <axboe@...nel.dk>, <ming.lei@...hat.com>,
<yukuai3@...wei.com>
CC: <linux-block@...r.kernel.org>, <nbd@...er.debian.org>,
<linux-kernel@...r.kernel.org>, <yi.zhang@...wei.com>
Subject: [PATCH -next v4 2/6] nbd: fix race between nbd_alloc_config() and module removal
When nbd module is being removing, nbd_alloc_config() may be
called concurrently by nbd_genl_connect(), although try_module_get()
will return false, but nbd_alloc_config() doesn't handle it.
The race may lead to the leak of nbd_config and its related
resources (e.g, recv_workq) and oops in nbd_read_stat() due
to the unload of nbd module as shown below:
BUG: kernel NULL pointer dereference, address: 0000000000000040
Oops: 0000 [#1] SMP PTI
CPU: 5 PID: 13840 Comm: kworker/u17:33 Not tainted 5.14.0+ #1
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996)
Workqueue: knbd16-recv recv_work [nbd]
RIP: 0010:nbd_read_stat.cold+0x130/0x1a4 [nbd]
Call Trace:
recv_work+0x3b/0xb0 [nbd]
process_one_work+0x1ed/0x390
worker_thread+0x4a/0x3d0
kthread+0x12a/0x150
ret_from_fork+0x22/0x30
Fixing it by checking the return value of try_module_get()
in nbd_alloc_config(). As nbd_alloc_config() may return ERR_PTR(-ENODEV),
assign nbd->config only when nbd_alloc_config() succeeds to ensure
the value of nbd->config is binary (valid or NULL).
Also adding a debug message to check the reference counter
of nbd_config during module removal.
Signed-off-by: Hou Tao <houtao1@...wei.com>
Signed-off-by: Yu Kuai <yukuai3@...wei.com>
Reviewed-by: Josef Bacik <josef@...icpanda.com>
---
drivers/block/nbd.c | 28 +++++++++++++++++++---------
1 file changed, 19 insertions(+), 9 deletions(-)
diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c
index a73e853f5833..2ee1e376d5c4 100644
--- a/drivers/block/nbd.c
+++ b/drivers/block/nbd.c
@@ -1518,15 +1518,20 @@ static struct nbd_config *nbd_alloc_config(void)
{
struct nbd_config *config;
+ if (!try_module_get(THIS_MODULE))
+ return ERR_PTR(-ENODEV);
+
config = kzalloc(sizeof(struct nbd_config), GFP_NOFS);
- if (!config)
- return NULL;
+ if (!config) {
+ module_put(THIS_MODULE);
+ return ERR_PTR(-ENOMEM);
+ }
+
atomic_set(&config->recv_threads, 0);
init_waitqueue_head(&config->recv_wq);
init_waitqueue_head(&config->conn_wait);
config->blksize_bits = NBD_DEF_BLKSIZE_BITS;
atomic_set(&config->live_connections, 0);
- try_module_get(THIS_MODULE);
return config;
}
@@ -1553,12 +1558,13 @@ static int nbd_open(struct block_device *bdev, fmode_t mode)
mutex_unlock(&nbd->config_lock);
goto out;
}
- config = nbd->config = nbd_alloc_config();
- if (!config) {
- ret = -ENOMEM;
+ config = nbd_alloc_config();
+ if (IS_ERR(config)) {
+ ret = PTR_ERR(config);
mutex_unlock(&nbd->config_lock);
goto out;
}
+ nbd->config = config;
refcount_set(&nbd->config_refs, 1);
refcount_inc(&nbd->refs);
mutex_unlock(&nbd->config_lock);
@@ -1964,13 +1970,14 @@ static int nbd_genl_connect(struct sk_buff *skb, struct genl_info *info)
nbd_put(nbd);
return -EINVAL;
}
- config = nbd->config = nbd_alloc_config();
- if (!nbd->config) {
+ config = nbd_alloc_config();
+ if (IS_ERR(config)) {
mutex_unlock(&nbd->config_lock);
nbd_put(nbd);
printk(KERN_ERR "nbd: couldn't allocate config\n");
- return -ENOMEM;
+ return PTR_ERR(config);
}
+ nbd->config = config;
refcount_set(&nbd->config_refs, 1);
set_bit(NBD_RT_BOUND, &config->runtime_flags);
@@ -2543,6 +2550,9 @@ static void __exit nbd_cleanup(void)
while (!list_empty(&del_list)) {
nbd = list_first_entry(&del_list, struct nbd_device, list);
list_del_init(&nbd->list);
+ if (refcount_read(&nbd->config_refs))
+ printk(KERN_ERR "nbd: possibly leaking nbd_config (ref %d)\n",
+ refcount_read(&nbd->config_refs));
if (refcount_read(&nbd->refs) != 1)
printk(KERN_ERR "nbd: possibly leaking a device\n");
nbd_put(nbd);
--
2.31.1
Powered by blists - more mailing lists