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, 66 insertions, 0 deletions

diff --git a/include/net/libeth/cache.h b/include/net/libeth/cache.h
new file mode 100644
index 000000000..bdb0c043c
--- /dev/null
+++ b/include/net/libeth/cache.h
@@ -0,0 +1,66 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/* Copyright (C) 2024 Intel Corporation */
+
+#ifndef __LIBETH_CACHE_H
+#define __LIBETH_CACHE_H
+
+#include <linux/cache.h>
+
+/**
+ * libeth_cacheline_group_assert - make sure cacheline group size is expected
+ * @type: type of the structure containing the group
+ * @grp: group name inside the struct
+ * @sz: expected group size
+ */
+#if defined(CONFIG_64BIT) && SMP_CACHE_BYTES == 64
+#define libeth_cacheline_group_assert(type, grp, sz)			      \
+	static_assert(offsetof(type, __cacheline_group_end__##grp) -	      \
+		      offsetofend(type, __cacheline_group_begin__##grp) ==    \
+		      (sz))
+#define __libeth_cacheline_struct_assert(type, sz)			      \
+	static_assert(sizeof(type) == (sz))
+#else /* !CONFIG_64BIT || SMP_CACHE_BYTES != 64 */
+#define libeth_cacheline_group_assert(type, grp, sz)			      \
+	static_assert(offsetof(type, __cacheline_group_end__##grp) -	      \
+		      offsetofend(type, __cacheline_group_begin__##grp) <=    \
+		      (sz))
+#define __libeth_cacheline_struct_assert(type, sz)			      \
+	static_assert(sizeof(type) <= (sz))
+#endif /* !CONFIG_64BIT || SMP_CACHE_BYTES != 64 */
+
+#define __libeth_cls1(sz1)	SMP_CACHE_ALIGN(sz1)
+#define __libeth_cls2(sz1, sz2)	(SMP_CACHE_ALIGN(sz1) + SMP_CACHE_ALIGN(sz2))
+#define __libeth_cls3(sz1, sz2, sz3)					      \
+	(SMP_CACHE_ALIGN(sz1) + SMP_CACHE_ALIGN(sz2) + SMP_CACHE_ALIGN(sz3))
+#define __libeth_cls(...)						      \
+	CONCATENATE(__libeth_cls, COUNT_ARGS(__VA_ARGS__))(__VA_ARGS__)
+
+/**
+ * libeth_cacheline_struct_assert - make sure CL-based struct size is expected
+ * @type: type of the struct
+ * @...: from 1 to 3 CL group sizes (read-mostly, read-write, cold)
+ *
+ * When a struct contains several CL groups, it's difficult to predict its size
+ * on different architectures. The macro instead takes sizes of all of the
+ * groups the structure contains and generates the final struct size.
+ */
+#define libeth_cacheline_struct_assert(type, ...)			      \
+	__libeth_cacheline_struct_assert(type, __libeth_cls(__VA_ARGS__));    \
+	static_assert(__alignof(type) >= SMP_CACHE_BYTES)
+
+/**
+ * libeth_cacheline_set_assert - make sure CL-based struct layout is expected
+ * @type: type of the struct
+ * @ro: expected size of the read-mostly group
+ * @rw: expected size of the read-write group
+ * @c: expected size of the cold group
+ *
+ * Check that each group size is expected and then do final struct size check.
+ */
+#define libeth_cacheline_set_assert(type, ro, rw, c)			      \
+	libeth_cacheline_group_assert(type, read_mostly, ro);		      \
+	libeth_cacheline_group_assert(type, read_write, rw);		      \
+	libeth_cacheline_group_assert(type, cold, c);			      \
+	libeth_cacheline_struct_assert(type, ro, rw, c)
+
+#endif /* __LIBETH_CACHE_H */