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, 98 insertions, 0 deletions

diff --git a/lib/timerqueue.c b/lib/timerqueue.c
new file mode 100644
index 000000000..e2a1e08cb
--- /dev/null
+++ b/lib/timerqueue.c
@@ -0,0 +1,98 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ *  Generic Timer-queue
+ *
+ *  Manages a simple queue of timers, ordered by expiration time.
+ *  Uses rbtrees for quick list adds and expiration.
+ *
+ *  NOTE: All of the following functions need to be serialized
+ *  to avoid races. No locking is done by this library code.
+ */
+
+#include <linux/bug.h>
+#include <linux/timerqueue.h>
+#include <linux/rbtree.h>
+#include <linux/export.h>
+
+#define __node_2_tq(_n) \
+	rb_entry((_n), struct timerqueue_node, node)
+
+static inline bool __timerqueue_less(struct rb_node *a, const struct rb_node *b)
+{
+	return __node_2_tq(a)->expires < __node_2_tq(b)->expires;
+}
+
+/**
+ * timerqueue_add - Adds timer to timerqueue.
+ *
+ * @head: head of timerqueue
+ * @node: timer node to be added
+ *
+ * Adds the timer node to the timerqueue, sorted by the node's expires
+ * value. Returns true if the newly added timer is the first expiring timer in
+ * the queue.
+ */
+bool timerqueue_add(struct timerqueue_head *head, struct timerqueue_node *node)
+{
+	/* Make sure we don't add nodes that are already added */
+	WARN_ON_ONCE(!RB_EMPTY_NODE(&node->node));
+
+	return rb_add_cached(&node->node, &head->rb_root, __timerqueue_less);
+}
+EXPORT_SYMBOL_GPL(timerqueue_add);
+
+/**
+ * timerqueue_del - Removes a timer from the timerqueue.
+ *
+ * @head: head of timerqueue
+ * @node: timer node to be removed
+ *
+ * Removes the timer node from the timerqueue. Returns true if the queue is
+ * not empty after the remove.
+ */
+bool timerqueue_del(struct timerqueue_head *head, struct timerqueue_node *node)
+{
+	WARN_ON_ONCE(RB_EMPTY_NODE(&node->node));
+
+	rb_erase_cached(&node->node, &head->rb_root);
+	RB_CLEAR_NODE(&node->node);
+
+	return !RB_EMPTY_ROOT(&head->rb_root.rb_root);
+}
+EXPORT_SYMBOL_GPL(timerqueue_del);
+
+/**
+ * timerqueue_iterate_next - Returns the timer after the provided timer
+ *
+ * @node: Pointer to a timer.
+ *
+ * Provides the timer that is after the given node. This is used, when
+ * necessary, to iterate through the list of timers in a timer list
+ * without modifying the list.
+ */
+struct timerqueue_node *timerqueue_iterate_next(struct timerqueue_node *node)
+{
+	struct rb_node *next;
+
+	if (!node)
+		return NULL;
+	next = rb_next(&node->node);
+	if (!next)
+		return NULL;
+	return container_of(next, struct timerqueue_node, node);
+}
+EXPORT_SYMBOL_GPL(timerqueue_iterate_next);
+
+#define __node_2_tq_linked(_n) \
+	container_of(rb_entry((_n), struct rb_node_linked, node), struct timerqueue_linked_node, node)
+
+static __always_inline bool __tq_linked_less(struct rb_node *a, const struct rb_node *b)
+{
+	return __node_2_tq_linked(a)->expires < __node_2_tq_linked(b)->expires;
+}
+
+bool timerqueue_linked_add(struct timerqueue_linked_head *head, struct timerqueue_linked_node *node)
+{
+	return rb_add_linked(&node->node, &head->rb_root, __tq_linked_less);
+}
+EXPORT_SYMBOL_GPL(timerqueue_linked_add);