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, 49 insertions, 0 deletions

diff --git a/include/net/dropreason.h b/include/net/dropreason.h
new file mode 100644
index 000000000..1df60645f
--- /dev/null
+++ b/include/net/dropreason.h
@@ -0,0 +1,49 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+
+#ifndef _LINUX_DROPREASON_H
+#define _LINUX_DROPREASON_H
+#include <net/dropreason-core.h>
+
+/**
+ * enum skb_drop_reason_subsys - subsystem tag for (extended) drop reasons
+ */
+enum skb_drop_reason_subsys {
+	/** @SKB_DROP_REASON_SUBSYS_CORE: core drop reasons defined above */
+	SKB_DROP_REASON_SUBSYS_CORE,
+
+	/**
+	 * @SKB_DROP_REASON_SUBSYS_MAC80211_UNUSABLE: mac80211 drop reasons
+	 * for unusable frames, see net/mac80211/drop.h
+	 */
+	SKB_DROP_REASON_SUBSYS_MAC80211_UNUSABLE,
+
+	/**
+	 * @SKB_DROP_REASON_SUBSYS_OPENVSWITCH: openvswitch drop reasons,
+	 * see net/openvswitch/drop.h
+	 */
+	SKB_DROP_REASON_SUBSYS_OPENVSWITCH,
+
+	/**
+	 * @SKB_DROP_REASON_SUBSYS_QDISC: TC qdisc drop reasons,
+	 * see include/net/dropreason-qdisc.h
+	 */
+	SKB_DROP_REASON_SUBSYS_QDISC,
+
+	/** @SKB_DROP_REASON_SUBSYS_NUM: number of subsystems defined */
+	SKB_DROP_REASON_SUBSYS_NUM
+};
+
+struct drop_reason_list {
+	const char * const *reasons;
+	size_t n_reasons;
+};
+
+/* Note: due to dynamic registrations, access must be under RCU */
+extern const struct drop_reason_list __rcu *
+drop_reasons_by_subsys[SKB_DROP_REASON_SUBSYS_NUM];
+
+void drop_reasons_register_subsys(enum skb_drop_reason_subsys subsys,
+				  const struct drop_reason_list *list);
+void drop_reasons_unregister_subsys(enum skb_drop_reason_subsys subsys);
+
+#endif