thunderbolt: Fix NULL dereference in tb_remove_work()grafted

There is a slight race between tb_remove_work() and tb_domain_remove()
which leads to dereferencing a NULL tb->root_switch pointer inside
tb_free_unplugged_xdomains():

        Thread A                            Thread B

  tb_remove_work()
                                    tb_domain_remove()
                                      mutex_lock(&tb->lock)
                                      tb_stop()
                                        /* doesn't cancel a running callback */
                                        cancel_delayed_work(&tcm->remove_work)
                                        ...
                                        tb_switch_remove(tb->root_switch)
                                        tb->root_switch = NULL
                                      mutex_unlock(&tb->lock)
    mutex_lock(&tb->lock)
    ...
    /* without checking ->root_switch */
    tb_free_unplugged_xdomains(tb->root_switch)
    mutex_unlock(&tb->lock)

Commit a8937f35cf39 ("thunderbolt: Remove XDomain from the bus without
holding tb->lock") doesn't seem right to move tb_free_unplugged_xdomains()
out of the &tb->lock section and the check for tb->root_switch, in
particular.  It states:

  For this reason separate removing the XDomain from the topology data
  structures (where we need the lock) from unregistering the device from
  the bus (where remove callbacks of the drivers are being called).

tb_free_unplugged_xdomains() belongs to the former group of functions
requiring the lock.  And it also calls tb_xdomain_remove() which should
only be called with &tb->lock held.

Found by Linux Verification Center (linuxtesting.org) with Svace static
analysis tool.

Fixes: a8937f35cf39 ("thunderbolt: Remove XDomain from the bus without holding tb->lock")
Cc: stable@vger.kernel.org
Signed-off-by: Fedor Pchelkin <pchelkin@ispras.ru>
Signed-off-by: Mika Westerberg <mika.westerberg@linux.intel.com>

1 files changed, 155 insertions, 0 deletions

diff --git a/include/net/netdev_lock.h b/include/net/netdev_lock.h
new file mode 100644
index 000000000..9fb3e9385
--- /dev/null
+++ b/include/net/netdev_lock.h
@@ -0,0 +1,155 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+
+#ifndef _NET_NETDEV_LOCK_H
+#define _NET_NETDEV_LOCK_H
+
+#include <linux/lockdep.h>
+#include <linux/netdevice.h>
+#include <linux/rtnetlink.h>
+
+static inline bool netdev_trylock(struct net_device *dev)
+{
+	return mutex_trylock(&dev->lock);
+}
+
+static inline void netdev_assert_locked(const struct net_device *dev)
+{
+	lockdep_assert_held(&dev->lock);
+}
+
+static inline void
+netdev_assert_locked_or_invisible(const struct net_device *dev)
+{
+	if (dev->reg_state == NETREG_REGISTERED ||
+	    dev->reg_state == NETREG_UNREGISTERING)
+		netdev_assert_locked(dev);
+}
+
+static inline bool netdev_need_ops_lock(const struct net_device *dev)
+{
+	bool ret = dev->request_ops_lock || !!dev->queue_mgmt_ops;
+
+#if IS_ENABLED(CONFIG_NET_SHAPER)
+	ret |= !!dev->netdev_ops->net_shaper_ops;
+#endif
+
+	return ret;
+}
+
+static inline void netdev_lock_ops(struct net_device *dev)
+{
+	if (netdev_need_ops_lock(dev))
+		netdev_lock(dev);
+}
+
+static inline void netdev_unlock_ops(struct net_device *dev)
+{
+	if (netdev_need_ops_lock(dev))
+		netdev_unlock(dev);
+}
+
+static inline void netdev_lock_ops_to_full(struct net_device *dev)
+{
+	if (netdev_need_ops_lock(dev))
+		netdev_assert_locked(dev);
+	else
+		netdev_lock(dev);
+}
+
+static inline void netdev_unlock_full_to_ops(struct net_device *dev)
+{
+	if (netdev_need_ops_lock(dev))
+		netdev_assert_locked(dev);
+	else
+		netdev_unlock(dev);
+}
+
+static inline void netdev_assert_locked_ops_compat(const struct net_device *dev)
+{
+	if (netdev_need_ops_lock(dev))
+		lockdep_assert_held(&dev->lock);
+	else
+		ASSERT_RTNL();
+}
+
+static inline void
+netdev_assert_locked_ops_compat_or_invisible(const struct net_device *dev)
+{
+	if (dev->reg_state == NETREG_REGISTERED ||
+	    dev->reg_state == NETREG_UNREGISTERING)
+		netdev_assert_locked_ops_compat(dev);
+}
+
+static inline void netdev_assert_locked_ops(const struct net_device *dev)
+{
+	if (netdev_need_ops_lock(dev))
+		netdev_assert_locked(dev);
+}
+
+static inline void netdev_lock_ops_compat(struct net_device *dev)
+{
+	if (netdev_need_ops_lock(dev))
+		netdev_lock(dev);
+	else
+		rtnl_lock();
+}
+
+static inline void netdev_unlock_ops_compat(struct net_device *dev)
+{
+	if (netdev_need_ops_lock(dev))
+		netdev_unlock(dev);
+	else
+		rtnl_unlock();
+}
+
+/* Matching "ops protected" category from netdevice.h */
+static inline int netdev_is_locked_ops_compat(const struct net_device *dev)
+{
+	if (netdev_need_ops_lock(dev))
+		return lockdep_is_held(&dev->lock);
+	return lockdep_rtnl_is_held();
+}
+
+static inline int netdev_lock_cmp_fn(const struct lockdep_map *a,
+				     const struct lockdep_map *b)
+{
+	if (a == b)
+		return 0;
+
+	/* Allow locking multiple devices only under rtnl_lock,
+	 * the exact order doesn't matter.
+	 * Note that upper devices don't lock their ops, so nesting
+	 * mostly happens in batched device removal for now.
+	 */
+	return lockdep_rtnl_is_held() ? -1 : 1;
+}
+
+#define netdev_lockdep_set_classes(dev)				\
+{								\
+	static struct lock_class_key qdisc_tx_busylock_key;	\
+	static struct lock_class_key qdisc_xmit_lock_key;	\
+	static struct lock_class_key dev_addr_list_lock_key;	\
+	static struct lock_class_key dev_instance_lock_key;	\
+	unsigned int i;						\
+								\
+	(dev)->qdisc_tx_busylock = &qdisc_tx_busylock_key;	\
+	lockdep_set_class(&(dev)->addr_list_lock,		\
+			  &dev_addr_list_lock_key);		\
+	lockdep_set_class(&(dev)->lock,				\
+			  &dev_instance_lock_key);		\
+	lock_set_cmp_fn(&dev->lock, netdev_lock_cmp_fn, NULL);	\
+	for (i = 0; i < (dev)->num_tx_queues; i++)		\
+		lockdep_set_class(&(dev)->_tx[i]._xmit_lock,	\
+				  &qdisc_xmit_lock_key);	\
+}
+
+#define netdev_lock_dereference(p, dev)				\
+	rcu_dereference_protected(p, lockdep_is_held(&(dev)->lock))
+
+#define netdev_ops_lock_dereference(p, dev)				\
+	rcu_dereference_protected(p, netdev_is_locked_ops_compat(dev))
+
+int netdev_debug_event(struct notifier_block *nb, unsigned long event,
+		       void *ptr);
+
+#endif