From b232b02bf3c205b13a26dcec08e53baddd8e59ed Mon Sep 17 00:00:00 2001 From: Zhang Wensheng Date: Wed, 18 May 2022 15:45:16 +0800 Subject: driver core: fix deadlock in __device_attach In __device_attach function, The lock holding logic is as follows: ... __device_attach device_lock(dev) // get lock dev async_schedule_dev(__device_attach_async_helper, dev); // func async_schedule_node async_schedule_node_domain(func) entry = kzalloc(sizeof(struct async_entry), GFP_ATOMIC); /* when fail or work limit, sync to execute func, but __device_attach_async_helper will get lock dev as well, which will lead to A-A deadlock. */ if (!entry || atomic_read(&entry_count) > MAX_WORK) { func; else queue_work_node(node, system_unbound_wq, &entry->work) device_unlock(dev) As shown above, when it is allowed to do async probes, because of out of memory or work limit, async work is not allowed, to do sync execute instead. it will lead to A-A deadlock because of __device_attach_async_helper getting lock dev. To fix the deadlock, move the async_schedule_dev outside device_lock, as we can see, in async_schedule_node_domain, the parameter of queue_work_node is system_unbound_wq, so it can accept concurrent operations. which will also not change the code logic, and will not lead to deadlock. Fixes: 765230b5f084 ("driver-core: add asynchronous probing support for drivers") Signed-off-by: Zhang Wensheng Link: https://lore.kernel.org/r/20220518074516.1225580-1-zhangwensheng5@huawei.com Signed-off-by: Greg Kroah-Hartman --- drivers/base/dd.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/base/dd.c b/drivers/base/dd.c index 80039b4a2e86..2fc8507f59ee 100644 --- a/drivers/base/dd.c +++ b/drivers/base/dd.c @@ -967,6 +967,7 @@ out_unlock: static int __device_attach(struct device *dev, bool allow_async) { int ret = 0; + bool async = false; device_lock(dev); if (dev->p->dead) { @@ -1005,7 +1006,7 @@ static int __device_attach(struct device *dev, bool allow_async) */ dev_dbg(dev, "scheduling asynchronous probe\n"); get_device(dev); - async_schedule_dev(__device_attach_async_helper, dev); + async = true; } else { pm_request_idle(dev); } @@ -1015,6 +1016,8 @@ static int __device_attach(struct device *dev, bool allow_async) } out_unlock: device_unlock(dev); + if (async) + async_schedule_dev(__device_attach_async_helper, dev); return ret; } -- cgit v1.2.3