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, 44 insertions, 0 deletions

diff --git a/include/net/netkit.h b/include/net/netkit.h
new file mode 100644
index 000000000..9ec016373
--- /dev/null
+++ b/include/net/netkit.h
@@ -0,0 +1,44 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2023 Isovalent */
+#ifndef __NET_NETKIT_H
+#define __NET_NETKIT_H
+
+#include <linux/bpf.h>
+
+#ifdef CONFIG_NETKIT
+int netkit_prog_attach(const union bpf_attr *attr, struct bpf_prog *prog);
+int netkit_link_attach(const union bpf_attr *attr, struct bpf_prog *prog);
+int netkit_prog_detach(const union bpf_attr *attr, struct bpf_prog *prog);
+int netkit_prog_query(const union bpf_attr *attr, union bpf_attr __user *uattr);
+INDIRECT_CALLABLE_DECLARE(struct net_device *netkit_peer_dev(struct net_device *dev));
+#else
+static inline int netkit_prog_attach(const union bpf_attr *attr,
+				     struct bpf_prog *prog)
+{
+	return -EINVAL;
+}
+
+static inline int netkit_link_attach(const union bpf_attr *attr,
+				     struct bpf_prog *prog)
+{
+	return -EINVAL;
+}
+
+static inline int netkit_prog_detach(const union bpf_attr *attr,
+				     struct bpf_prog *prog)
+{
+	return -EINVAL;
+}
+
+static inline int netkit_prog_query(const union bpf_attr *attr,
+				    union bpf_attr __user *uattr)
+{
+	return -EINVAL;
+}
+
+static inline struct net_device *netkit_peer_dev(struct net_device *dev)
+{
+	return NULL;
+}
+#endif /* CONFIG_NETKIT */
+#endif /* __NET_NETKIT_H */