netdevsim: Block until all devices are released

Like other buses, devices on the netdevsim bus have a release callback
that is invoked when the reference count of the device drops to zero.
However, unlike other buses such as PCI, the release callback is not
necessarily built into the kernel, as netdevsim can be built as a
module.

The above is problematic as nothing prevents the module from being
unloaded before the release callback has been invoked, which can happen
asynchronously. One such example can be found in commit a380687200e0
("devlink: take device reference for devlink object") where devlink
calls put_device() from an RCU callback.

The issue is not theoretical and the reproducer in [1] can reliably
crash the kernel. The conclusion of this discussion was that the issue
should be solved in netdevsim, which is what this patch is trying to do.

Add a reference count that is increased when a device is added to the
bus and decreased when a device is released. Signal a completion when
the reference count drops to zero and wait for the completion when
unloading the module so that the module will not be unloaded before all
the devices were released. The reference count is initialized to one so
that completion is only signaled when unloading the module.

With this patch, the reproducer in [1] no longer crashes the kernel.

[1] https://lore.kernel.org/netdev/20230619125015.1541143-2-idosch@nvidia.com/

Fixes: a380687200e0 ("devlink: take device reference for devlink object")
Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Link: https://lore.kernel.org/r/20231026083343.890689-1-idosch@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

1 files changed, 12 insertions, 0 deletions

diff --git a/drivers/net/netdevsim/bus.c b/drivers/net/netdevsim/bus.c
index 0787ad252dd9..bcbc1e19edde 100644
--- a/drivers/net/netdevsim/bus.c
+++ b/drivers/net/netdevsim/bus.c
@@ -3,11 +3,13 @@
  * Copyright (C) 2019 Mellanox Technologies. All rights reserved
  */
 
+#include <linux/completion.h>
 #include <linux/device.h>
 #include <linux/idr.h>
 #include <linux/kernel.h>
 #include <linux/list.h>
 #include <linux/mutex.h>
+#include <linux/refcount.h>
 #include <linux/slab.h>
 #include <linux/sysfs.h>
 
@@ -17,6 +19,8 @@ static DEFINE_IDA(nsim_bus_dev_ids);
 static LIST_HEAD(nsim_bus_dev_list);
 static DEFINE_MUTEX(nsim_bus_dev_list_lock);
 static bool nsim_bus_enable;
+static refcount_t nsim_bus_devs; /* Including the bus itself. */
+static DECLARE_COMPLETION(nsim_bus_devs_released);
 
 static struct nsim_bus_dev *to_nsim_bus_dev(struct device *dev)
 {
@@ -121,6 +125,8 @@ static void nsim_bus_dev_release(struct device *dev)
 
 	nsim_bus_dev = container_of(dev, struct nsim_bus_dev, dev);
 	kfree(nsim_bus_dev);
+	if (refcount_dec_and_test(&nsim_bus_devs))
+		complete(&nsim_bus_devs_released);
 }
 
 static struct device_type nsim_bus_dev_type = {
@@ -170,6 +176,7 @@ new_device_store(const struct bus_type *bus, const char *buf, size_t count)
 		goto err;
 	}
 
+	refcount_inc(&nsim_bus_devs);
 	/* Allow using nsim_bus_dev */
 	smp_store_release(&nsim_bus_dev->init, true);
 
@@ -326,6 +333,7 @@ int nsim_bus_init(void)
 	err = driver_register(&nsim_driver);
 	if (err)
 		goto err_bus_unregister;
+	refcount_set(&nsim_bus_devs, 1);
 	/* Allow using resources */
 	smp_store_release(&nsim_bus_enable, true);
 	return 0;
@@ -341,6 +349,8 @@ void nsim_bus_exit(void)
 
 	/* Disallow using resources */
 	smp_store_release(&nsim_bus_enable, false);
+	if (refcount_dec_and_test(&nsim_bus_devs))
+		complete(&nsim_bus_devs_released);
 
 	mutex_lock(&nsim_bus_dev_list_lock);
 	list_for_each_entry_safe(nsim_bus_dev, tmp, &nsim_bus_dev_list, list) {
@@ -349,6 +359,8 @@ void nsim_bus_exit(void)
 	}
 	mutex_unlock(&nsim_bus_dev_list_lock);
 
+	wait_for_completion(&nsim_bus_devs_released);
+
 	driver_unregister(&nsim_driver);
 	bus_unregister(&nsim_bus);
 }