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>

2 files changed, 98 insertions, 0 deletions

diff --git a/samples/rpmsg/Makefile b/samples/rpmsg/Makefile
new file mode 100644
index 000000000..ddf9a5d13
--- /dev/null
+++ b/samples/rpmsg/Makefile
@@ -0,0 +1,2 @@
+# SPDX-License-Identifier: GPL-2.0-only
+obj-$(CONFIG_SAMPLE_RPMSG_CLIENT) += rpmsg_client_sample.o
diff --git a/samples/rpmsg/rpmsg_client_sample.c b/samples/rpmsg/rpmsg_client_sample.c
new file mode 100644
index 000000000..ae5081662
--- /dev/null
+++ b/samples/rpmsg/rpmsg_client_sample.c
@@ -0,0 +1,96 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Remote processor messaging - sample client driver
+ *
+ * Copyright (C) 2011 Texas Instruments, Inc.
+ * Copyright (C) 2011 Google, Inc.
+ *
+ * Ohad Ben-Cohen <ohad@wizery.com>
+ * Brian Swetland <swetland@google.com>
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/rpmsg.h>
+
+#define MSG		"hello world!"
+
+static int count = 100;
+module_param(count, int, 0644);
+
+struct instance_data {
+	int rx_count;
+};
+
+static int rpmsg_sample_cb(struct rpmsg_device *rpdev, void *data, int len,
+						void *priv, u32 src)
+{
+	int ret;
+	struct instance_data *idata = dev_get_drvdata(&rpdev->dev);
+
+	dev_info(&rpdev->dev, "incoming msg %d (src: 0x%x)\n",
+		 ++idata->rx_count, src);
+
+	print_hex_dump_debug(__func__, DUMP_PREFIX_NONE, 16, 1, data, len,
+			     true);
+
+	/* samples should not live forever */
+	if (idata->rx_count >= count) {
+		dev_info(&rpdev->dev, "goodbye!\n");
+		return 0;
+	}
+
+	/* send a new message now */
+	ret = rpmsg_send(rpdev->ept, MSG, strlen(MSG));
+	if (ret)
+		dev_err(&rpdev->dev, "rpmsg_send failed: %d\n", ret);
+
+	return 0;
+}
+
+static int rpmsg_sample_probe(struct rpmsg_device *rpdev)
+{
+	int ret;
+	struct instance_data *idata;
+
+	dev_info(&rpdev->dev, "new channel: 0x%x -> 0x%x!\n",
+					rpdev->src, rpdev->dst);
+
+	idata = devm_kzalloc(&rpdev->dev, sizeof(*idata), GFP_KERNEL);
+	if (!idata)
+		return -ENOMEM;
+
+	dev_set_drvdata(&rpdev->dev, idata);
+
+	/* send a message to our remote processor */
+	ret = rpmsg_send(rpdev->ept, MSG, strlen(MSG));
+	if (ret) {
+		dev_err(&rpdev->dev, "rpmsg_send failed: %d\n", ret);
+		return ret;
+	}
+
+	return 0;
+}
+
+static void rpmsg_sample_remove(struct rpmsg_device *rpdev)
+{
+	dev_info(&rpdev->dev, "rpmsg sample client driver is removed\n");
+}
+
+static struct rpmsg_device_id rpmsg_driver_sample_id_table[] = {
+	{ .name	= "rpmsg-client-sample" },
+	{ },
+};
+MODULE_DEVICE_TABLE(rpmsg, rpmsg_driver_sample_id_table);
+
+static struct rpmsg_driver rpmsg_sample_client = {
+	.drv.name	= KBUILD_MODNAME,
+	.id_table	= rpmsg_driver_sample_id_table,
+	.probe		= rpmsg_sample_probe,
+	.callback	= rpmsg_sample_cb,
+	.remove		= rpmsg_sample_remove,
+};
+module_rpmsg_driver(rpmsg_sample_client);
+
+MODULE_DESCRIPTION("Remote processor messaging sample client driver");
+MODULE_LICENSE("GPL v2");