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>

16 files changed, 1105 insertions, 0 deletions

diff --git a/tools/include/asm-generic/atomic-gcc.h b/tools/include/asm-generic/atomic-gcc.h
new file mode 100644
index 000000000..9b3c528ba
--- /dev/null
+++ b/tools/include/asm-generic/atomic-gcc.h
@@ -0,0 +1,95 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __TOOLS_ASM_GENERIC_ATOMIC_H
+#define __TOOLS_ASM_GENERIC_ATOMIC_H
+
+#include <linux/compiler.h>
+#include <linux/types.h>
+#include <linux/bitops.h>
+
+/*
+ * Atomic operations that C can't guarantee us.  Useful for
+ * resource counting etc..
+ *
+ * Excerpts obtained from the Linux kernel sources.
+ */
+
+#define ATOMIC_INIT(i)	{ (i) }
+
+/**
+ * atomic_read - read atomic variable
+ * @v: pointer of type atomic_t
+ *
+ * Atomically reads the value of @v.
+ */
+static inline int atomic_read(const atomic_t *v)
+{
+	return READ_ONCE((v)->counter);
+}
+
+/**
+ * atomic_set - set atomic variable
+ * @v: pointer of type atomic_t
+ * @i: required value
+ *
+ * Atomically sets the value of @v to @i.
+ */
+static inline void atomic_set(atomic_t *v, int i)
+{
+        v->counter = i;
+}
+
+/**
+ * atomic_inc - increment atomic variable
+ * @v: pointer of type atomic_t
+ *
+ * Atomically increments @v by 1.
+ */
+static inline void atomic_inc(atomic_t *v)
+{
+	__sync_add_and_fetch(&v->counter, 1);
+}
+
+/**
+ * atomic_dec_and_test - decrement and test
+ * @v: pointer of type atomic_t
+ *
+ * Atomically decrements @v by 1 and
+ * returns true if the result is 0, or false for all other
+ * cases.
+ */
+static inline int atomic_dec_and_test(atomic_t *v)
+{
+	return __sync_sub_and_fetch(&v->counter, 1) == 0;
+}
+
+#define cmpxchg(ptr, oldval, newval) \
+	__sync_val_compare_and_swap(ptr, oldval, newval)
+
+static inline int atomic_cmpxchg(atomic_t *v, int oldval, int newval)
+{
+	return cmpxchg(&(v)->counter, oldval, newval);
+}
+
+static inline int test_and_set_bit(long nr, unsigned long *addr)
+{
+	unsigned long mask = BIT_MASK(nr);
+	long old;
+
+	addr += BIT_WORD(nr);
+
+	old = __sync_fetch_and_or(addr, mask);
+	return !!(old & mask);
+}
+
+static inline int test_and_clear_bit(long nr, unsigned long *addr)
+{
+	unsigned long mask = BIT_MASK(nr);
+	long old;
+
+	addr += BIT_WORD(nr);
+
+	old = __sync_fetch_and_and(addr, ~mask);
+	return !!(old & mask);
+}
+
+#endif /* __TOOLS_ASM_GENERIC_ATOMIC_H */
diff --git a/tools/include/asm-generic/barrier.h b/tools/include/asm-generic/barrier.h
new file mode 100644
index 000000000..6ef36e920
--- /dev/null
+++ b/tools/include/asm-generic/barrier.h
@@ -0,0 +1,40 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Copied from the kernel sources to tools/perf/:
+ *
+ * Generic barrier definitions.
+ *
+ * It should be possible to use these on really simple architectures,
+ * but it serves more as a starting point for new ports.
+ *
+ * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ */
+#ifndef __TOOLS_LINUX_ASM_GENERIC_BARRIER_H
+#define __TOOLS_LINUX_ASM_GENERIC_BARRIER_H
+
+#ifndef __ASSEMBLY__
+
+#include <linux/compiler.h>
+
+/*
+ * Force strict CPU ordering. And yes, this is required on UP too when we're
+ * talking to devices.
+ *
+ * Fall back to compiler barriers if nothing better is provided.
+ */
+
+#ifndef mb
+#define mb()	barrier()
+#endif
+
+#ifndef rmb
+#define rmb()	mb()
+#endif
+
+#ifndef wmb
+#define wmb()	mb()
+#endif
+
+#endif /* !__ASSEMBLY__ */
+#endif /* __TOOLS_LINUX_ASM_GENERIC_BARRIER_H */
diff --git a/tools/include/asm-generic/bitops.h b/tools/include/asm-generic/bitops.h
new file mode 100644
index 000000000..9ab313e93
--- /dev/null
+++ b/tools/include/asm-generic/bitops.h
@@ -0,0 +1,31 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __TOOLS_ASM_GENERIC_BITOPS_H
+#define __TOOLS_ASM_GENERIC_BITOPS_H
+
+/*
+ * tools/ copied this from include/asm-generic/bitops.h, bit by bit as it needed
+ * some functions.
+ *
+ * For the benefit of those who are trying to port Linux to another
+ * architecture, here are some C-language equivalents.  You should
+ * recode these in the native assembly language, if at all possible.
+ *
+ * C language equivalents written by Theodore Ts'o, 9/26/92
+ */
+
+#include <asm-generic/bitops/__ffs.h>
+#include <asm-generic/bitops/__ffz.h>
+#include <asm-generic/bitops/fls.h>
+#include <asm-generic/bitops/__fls.h>
+#include <asm-generic/bitops/fls64.h>
+
+#ifndef _TOOLS_LINUX_BITOPS_H_
+#error only <linux/bitops.h> can be included directly
+#endif
+
+#include <asm-generic/bitops/hweight.h>
+
+#include <asm-generic/bitops/atomic.h>
+#include <asm-generic/bitops/non-atomic.h>
+
+#endif /* __TOOLS_ASM_GENERIC_BITOPS_H */
diff --git a/tools/include/asm-generic/bitops/__ffs.h b/tools/include/asm-generic/bitops/__ffs.h
new file mode 100644
index 000000000..2d94c1e9b
--- /dev/null
+++ b/tools/include/asm-generic/bitops/__ffs.h
@@ -0,0 +1,45 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _TOOLS_LINUX_ASM_GENERIC_BITOPS___FFS_H_
+#define _TOOLS_LINUX_ASM_GENERIC_BITOPS___FFS_H_
+
+#include <asm/types.h>
+#include <asm/bitsperlong.h>
+
+/**
+ * __ffs - find first bit in word.
+ * @word: The word to search
+ *
+ * Undefined if no bit exists, so code should check against 0 first.
+ */
+static __always_inline unsigned int __ffs(unsigned long word)
+{
+	unsigned int num = 0;
+
+#if __BITS_PER_LONG == 64
+	if ((word & 0xffffffff) == 0) {
+		num += 32;
+		word >>= 32;
+	}
+#endif
+	if ((word & 0xffff) == 0) {
+		num += 16;
+		word >>= 16;
+	}
+	if ((word & 0xff) == 0) {
+		num += 8;
+		word >>= 8;
+	}
+	if ((word & 0xf) == 0) {
+		num += 4;
+		word >>= 4;
+	}
+	if ((word & 0x3) == 0) {
+		num += 2;
+		word >>= 2;
+	}
+	if ((word & 0x1) == 0)
+		num += 1;
+	return num;
+}
+
+#endif /* _TOOLS_LINUX_ASM_GENERIC_BITOPS___FFS_H_ */
diff --git a/tools/include/asm-generic/bitops/__ffz.h b/tools/include/asm-generic/bitops/__ffz.h
new file mode 100644
index 000000000..6744bd4cd
--- /dev/null
+++ b/tools/include/asm-generic/bitops/__ffz.h
@@ -0,0 +1,12 @@
+#ifndef _ASM_GENERIC_BITOPS_FFZ_H_
+#define _ASM_GENERIC_BITOPS_FFZ_H_
+
+/*
+ * ffz - find first zero in word.
+ * @word: The word to search
+ *
+ * Undefined if no zero exists, so code should check against ~0UL first.
+ */
+#define ffz(x)  __ffs(~(x))
+
+#endif /* _ASM_GENERIC_BITOPS_FFZ_H_ */
diff --git a/tools/include/asm-generic/bitops/__fls.h b/tools/include/asm-generic/bitops/__fls.h
new file mode 100644
index 000000000..35f33780c
--- /dev/null
+++ b/tools/include/asm-generic/bitops/__fls.h
@@ -0,0 +1,48 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_GENERIC_BITOPS___FLS_H_
+#define _ASM_GENERIC_BITOPS___FLS_H_
+
+#include <asm/types.h>
+
+/**
+ * generic___fls - find last (most-significant) set bit in a long word
+ * @word: the word to search
+ *
+ * Undefined if no set bit exists, so code should check against 0 first.
+ */
+static __always_inline __attribute_const__ unsigned int generic___fls(unsigned long word)
+{
+	unsigned int num = BITS_PER_LONG - 1;
+
+#if BITS_PER_LONG == 64
+	if (!(word & (~0ul << 32))) {
+		num -= 32;
+		word <<= 32;
+	}
+#endif
+	if (!(word & (~0ul << (BITS_PER_LONG-16)))) {
+		num -= 16;
+		word <<= 16;
+	}
+	if (!(word & (~0ul << (BITS_PER_LONG-8)))) {
+		num -= 8;
+		word <<= 8;
+	}
+	if (!(word & (~0ul << (BITS_PER_LONG-4)))) {
+		num -= 4;
+		word <<= 4;
+	}
+	if (!(word & (~0ul << (BITS_PER_LONG-2)))) {
+		num -= 2;
+		word <<= 2;
+	}
+	if (!(word & (~0ul << (BITS_PER_LONG-1))))
+		num -= 1;
+	return num;
+}
+
+#ifndef __HAVE_ARCH___FLS
+#define __fls(word) generic___fls(word)
+#endif
+
+#endif /* _ASM_GENERIC_BITOPS___FLS_H_ */
diff --git a/tools/include/asm-generic/bitops/arch_hweight.h b/tools/include/asm-generic/bitops/arch_hweight.h
new file mode 100644
index 000000000..c2705e1d2
--- /dev/null
+++ b/tools/include/asm-generic/bitops/arch_hweight.h
@@ -0,0 +1,26 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_GENERIC_BITOPS_ARCH_HWEIGHT_H_
+#define _ASM_GENERIC_BITOPS_ARCH_HWEIGHT_H_
+
+#include <asm/types.h>
+
+static inline unsigned int __arch_hweight32(unsigned int w)
+{
+	return __sw_hweight32(w);
+}
+
+static inline unsigned int __arch_hweight16(unsigned int w)
+{
+	return __sw_hweight16(w);
+}
+
+static inline unsigned int __arch_hweight8(unsigned int w)
+{
+	return __sw_hweight8(w);
+}
+
+static inline unsigned long __arch_hweight64(__u64 w)
+{
+	return __sw_hweight64(w);
+}
+#endif /* _ASM_GENERIC_BITOPS_HWEIGHT_H_ */
diff --git a/tools/include/asm-generic/bitops/atomic.h b/tools/include/asm-generic/bitops/atomic.h
new file mode 100644
index 000000000..ab37a221b
--- /dev/null
+++ b/tools/include/asm-generic/bitops/atomic.h
@@ -0,0 +1,15 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _TOOLS_LINUX_ASM_GENERIC_BITOPS_ATOMIC_H_
+#define _TOOLS_LINUX_ASM_GENERIC_BITOPS_ATOMIC_H_
+
+#include <asm/types.h>
+#include <asm/bitsperlong.h>
+
+/*
+ * Just alias the test versions, all of the compiler built-in atomics "fetch",
+ * and optimizing compile-time constants on x86 isn't worth the complexity.
+ */
+#define set_bit test_and_set_bit
+#define clear_bit test_and_clear_bit
+
+#endif /* _TOOLS_LINUX_ASM_GENERIC_BITOPS_ATOMIC_H_ */
diff --git a/tools/include/asm-generic/bitops/const_hweight.h b/tools/include/asm-generic/bitops/const_hweight.h
new file mode 100644
index 000000000..149faeeee
--- /dev/null
+++ b/tools/include/asm-generic/bitops/const_hweight.h
@@ -0,0 +1,44 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_GENERIC_BITOPS_CONST_HWEIGHT_H_
+#define _ASM_GENERIC_BITOPS_CONST_HWEIGHT_H_
+
+/*
+ * Compile time versions of __arch_hweightN()
+ */
+#define __const_hweight8(w)		\
+	((unsigned int)			\
+	 ((!!((w) & (1ULL << 0))) +	\
+	  (!!((w) & (1ULL << 1))) +	\
+	  (!!((w) & (1ULL << 2))) +	\
+	  (!!((w) & (1ULL << 3))) +	\
+	  (!!((w) & (1ULL << 4))) +	\
+	  (!!((w) & (1ULL << 5))) +	\
+	  (!!((w) & (1ULL << 6))) +	\
+	  (!!((w) & (1ULL << 7)))))
+
+#define __const_hweight16(w) (__const_hweight8(w)  + __const_hweight8((w)  >> 8 ))
+#define __const_hweight32(w) (__const_hweight16(w) + __const_hweight16((w) >> 16))
+#define __const_hweight64(w) (__const_hweight32(w) + __const_hweight32((w) >> 32))
+
+/*
+ * Generic interface.
+ */
+#define hweight8(w)  (__builtin_constant_p(w) ? __const_hweight8(w)  : __arch_hweight8(w))
+#define hweight16(w) (__builtin_constant_p(w) ? __const_hweight16(w) : __arch_hweight16(w))
+#define hweight32(w) (__builtin_constant_p(w) ? __const_hweight32(w) : __arch_hweight32(w))
+#define hweight64(w) (__builtin_constant_p(w) ? __const_hweight64(w) : __arch_hweight64(w))
+
+/*
+ * Interface for known constant arguments
+ */
+#define HWEIGHT8(w)  (BUILD_BUG_ON_ZERO(!__builtin_constant_p(w)) + __const_hweight8(w))
+#define HWEIGHT16(w) (BUILD_BUG_ON_ZERO(!__builtin_constant_p(w)) + __const_hweight16(w))
+#define HWEIGHT32(w) (BUILD_BUG_ON_ZERO(!__builtin_constant_p(w)) + __const_hweight32(w))
+#define HWEIGHT64(w) (BUILD_BUG_ON_ZERO(!__builtin_constant_p(w)) + __const_hweight64(w))
+
+/*
+ * Type invariant interface to the compile time constant hweight functions.
+ */
+#define HWEIGHT(w)   HWEIGHT64((u64)w)
+
+#endif /* _ASM_GENERIC_BITOPS_CONST_HWEIGHT_H_ */
diff --git a/tools/include/asm-generic/bitops/fls.h b/tools/include/asm-generic/bitops/fls.h
new file mode 100644
index 000000000..8eed3437e
--- /dev/null
+++ b/tools/include/asm-generic/bitops/fls.h
@@ -0,0 +1,46 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_GENERIC_BITOPS_FLS_H_
+#define _ASM_GENERIC_BITOPS_FLS_H_
+
+/**
+ * generic_fls - find last (most-significant) bit set
+ * @x: the word to search
+ *
+ * This is defined the same way as ffs.
+ * Note fls(0) = 0, fls(1) = 1, fls(0x80000000) = 32.
+ */
+
+static __always_inline __attribute_const__ int generic_fls(unsigned int x)
+{
+	int r = 32;
+
+	if (!x)
+		return 0;
+	if (!(x & 0xffff0000u)) {
+		x <<= 16;
+		r -= 16;
+	}
+	if (!(x & 0xff000000u)) {
+		x <<= 8;
+		r -= 8;
+	}
+	if (!(x & 0xf0000000u)) {
+		x <<= 4;
+		r -= 4;
+	}
+	if (!(x & 0xc0000000u)) {
+		x <<= 2;
+		r -= 2;
+	}
+	if (!(x & 0x80000000u)) {
+		x <<= 1;
+		r -= 1;
+	}
+	return r;
+}
+
+#ifndef __HAVE_ARCH_FLS
+#define fls(x) generic_fls(x)
+#endif
+
+#endif /* _ASM_GENERIC_BITOPS_FLS_H_ */
diff --git a/tools/include/asm-generic/bitops/fls64.h b/tools/include/asm-generic/bitops/fls64.h
new file mode 100644
index 000000000..b5f58dd26
--- /dev/null
+++ b/tools/include/asm-generic/bitops/fls64.h
@@ -0,0 +1,37 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_GENERIC_BITOPS_FLS64_H_
+#define _ASM_GENERIC_BITOPS_FLS64_H_
+
+#include <asm/types.h>
+
+/**
+ * fls64 - find last set bit in a 64-bit word
+ * @x: the word to search
+ *
+ * This is defined in a similar way as the libc and compiler builtin
+ * ffsll, but returns the position of the most significant set bit.
+ *
+ * fls64(value) returns 0 if value is 0 or the position of the last
+ * set bit if value is nonzero. The last (most significant) bit is
+ * at position 64.
+ */
+#if BITS_PER_LONG == 32
+static __always_inline __attribute_const__ int fls64(__u64 x)
+{
+	__u32 h = x >> 32;
+	if (h)
+		return fls(h) + 32;
+	return fls(x);
+}
+#elif BITS_PER_LONG == 64
+static __always_inline __attribute_const__ int fls64(__u64 x)
+{
+	if (x == 0)
+		return 0;
+	return __fls(x) + 1;
+}
+#else
+#error BITS_PER_LONG not 32 or 64
+#endif
+
+#endif /* _ASM_GENERIC_BITOPS_FLS64_H_ */
diff --git a/tools/include/asm-generic/bitops/hweight.h b/tools/include/asm-generic/bitops/hweight.h
new file mode 100644
index 000000000..3e681982b
--- /dev/null
+++ b/tools/include/asm-generic/bitops/hweight.h
@@ -0,0 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _TOOLS_LINUX_ASM_GENERIC_BITOPS_HWEIGHT_H_
+#define _TOOLS_LINUX_ASM_GENERIC_BITOPS_HWEIGHT_H_
+
+#include <asm-generic/bitops/arch_hweight.h>
+#include <asm-generic/bitops/const_hweight.h>
+
+#endif /* _TOOLS_LINUX_ASM_GENERIC_BITOPS_HWEIGHT_H_ */
diff --git a/tools/include/asm-generic/bitops/non-atomic.h b/tools/include/asm-generic/bitops/non-atomic.h
new file mode 100644
index 000000000..0c472a833
--- /dev/null
+++ b/tools/include/asm-generic/bitops/non-atomic.h
@@ -0,0 +1,115 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_GENERIC_BITOPS_NON_ATOMIC_H_
+#define _ASM_GENERIC_BITOPS_NON_ATOMIC_H_
+
+#include <linux/bits.h>
+
+/**
+ * ___set_bit - Set a bit in memory
+ * @nr: the bit to set
+ * @addr: the address to start counting from
+ *
+ * Unlike set_bit(), this function is non-atomic and may be reordered.
+ * If it's called on the same region of memory simultaneously, the effect
+ * may be that only one operation succeeds.
+ */
+static __always_inline void
+___set_bit(unsigned long nr, volatile unsigned long *addr)
+{
+	unsigned long mask = BIT_MASK(nr);
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+
+	*p  |= mask;
+}
+
+static __always_inline void
+___clear_bit(unsigned long nr, volatile unsigned long *addr)
+{
+	unsigned long mask = BIT_MASK(nr);
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+
+	*p &= ~mask;
+}
+
+/**
+ * ___change_bit - Toggle a bit in memory
+ * @nr: the bit to change
+ * @addr: the address to start counting from
+ *
+ * Unlike change_bit(), this function is non-atomic and may be reordered.
+ * If it's called on the same region of memory simultaneously, the effect
+ * may be that only one operation succeeds.
+ */
+static __always_inline void
+___change_bit(unsigned long nr, volatile unsigned long *addr)
+{
+	unsigned long mask = BIT_MASK(nr);
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+
+	*p ^= mask;
+}
+
+/**
+ * ___test_and_set_bit - Set a bit and return its old value
+ * @nr: Bit to set
+ * @addr: Address to count from
+ *
+ * This operation is non-atomic and can be reordered.
+ * If two examples of this operation race, one can appear to succeed
+ * but actually fail.  You must protect multiple accesses with a lock.
+ */
+static __always_inline bool
+___test_and_set_bit(unsigned long nr, volatile unsigned long *addr)
+{
+	unsigned long mask = BIT_MASK(nr);
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	unsigned long old = *p;
+
+	*p = old | mask;
+	return (old & mask) != 0;
+}
+
+/**
+ * ___test_and_clear_bit - Clear a bit and return its old value
+ * @nr: Bit to clear
+ * @addr: Address to count from
+ *
+ * This operation is non-atomic and can be reordered.
+ * If two examples of this operation race, one can appear to succeed
+ * but actually fail.  You must protect multiple accesses with a lock.
+ */
+static __always_inline bool
+___test_and_clear_bit(unsigned long nr, volatile unsigned long *addr)
+{
+	unsigned long mask = BIT_MASK(nr);
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	unsigned long old = *p;
+
+	*p = old & ~mask;
+	return (old & mask) != 0;
+}
+
+/* WARNING: non atomic and it can be reordered! */
+static __always_inline bool
+___test_and_change_bit(unsigned long nr, volatile unsigned long *addr)
+{
+	unsigned long mask = BIT_MASK(nr);
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	unsigned long old = *p;
+
+	*p = old ^ mask;
+	return (old & mask) != 0;
+}
+
+/**
+ * _test_bit - Determine whether a bit is set
+ * @nr: bit number to test
+ * @addr: Address to start counting from
+ */
+static __always_inline bool
+_test_bit(unsigned long nr, const volatile unsigned long *addr)
+{
+	return 1UL & (addr[BIT_WORD(nr)] >> (nr & (BITS_PER_LONG-1)));
+}
+
+#endif /* _ASM_GENERIC_BITOPS_NON_ATOMIC_H_ */
diff --git a/tools/include/asm-generic/bitsperlong.h b/tools/include/asm-generic/bitsperlong.h
new file mode 100644
index 000000000..2093d56dd
--- /dev/null
+++ b/tools/include/asm-generic/bitsperlong.h
@@ -0,0 +1,24 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __ASM_GENERIC_BITS_PER_LONG
+#define __ASM_GENERIC_BITS_PER_LONG
+
+#include <uapi/asm-generic/bitsperlong.h>
+
+#ifdef __SIZEOF_LONG__
+#define BITS_PER_LONG (__CHAR_BIT__ * __SIZEOF_LONG__)
+#else
+#define BITS_PER_LONG __WORDSIZE
+#endif
+
+#if BITS_PER_LONG != __BITS_PER_LONG
+#error Inconsistent word size. Check asm/bitsperlong.h
+#endif
+
+#ifndef BITS_PER_LONG_LONG
+#define BITS_PER_LONG_LONG 64
+#endif
+
+#define small_const_nbits(nbits) \
+	(__builtin_constant_p(nbits) && (nbits) <= BITS_PER_LONG && (nbits) > 0)
+
+#endif /* __ASM_GENERIC_BITS_PER_LONG */
diff --git a/tools/include/asm-generic/hugetlb_encode.h b/tools/include/asm-generic/hugetlb_encode.h
new file mode 100644
index 000000000..de687009b
--- /dev/null
+++ b/tools/include/asm-generic/hugetlb_encode.h
@@ -0,0 +1,37 @@
+#ifndef _ASM_GENERIC_HUGETLB_ENCODE_H_
+#define _ASM_GENERIC_HUGETLB_ENCODE_H_
+
+/*
+ * Several system calls take a flag to request "hugetlb" huge pages.
+ * Without further specification, these system calls will use the
+ * system's default huge page size.  If a system supports multiple
+ * huge page sizes, the desired huge page size can be specified in
+ * bits [26:31] of the flag arguments.  The value in these 6 bits
+ * will encode the log2 of the huge page size.
+ *
+ * The following definitions are associated with this huge page size
+ * encoding in flag arguments.  System call specific header files
+ * that use this encoding should include this file.  They can then
+ * provide definitions based on these with their own specific prefix.
+ * for example:
+ * #define MAP_HUGE_SHIFT HUGETLB_FLAG_ENCODE_SHIFT
+ */
+
+#define HUGETLB_FLAG_ENCODE_SHIFT	26
+#define HUGETLB_FLAG_ENCODE_MASK	0x3f
+
+#define HUGETLB_FLAG_ENCODE_16KB	(14U << HUGETLB_FLAG_ENCODE_SHIFT)
+#define HUGETLB_FLAG_ENCODE_64KB	(16U << HUGETLB_FLAG_ENCODE_SHIFT)
+#define HUGETLB_FLAG_ENCODE_512KB	(19U << HUGETLB_FLAG_ENCODE_SHIFT)
+#define HUGETLB_FLAG_ENCODE_1MB		(20U << HUGETLB_FLAG_ENCODE_SHIFT)
+#define HUGETLB_FLAG_ENCODE_2MB		(21U << HUGETLB_FLAG_ENCODE_SHIFT)
+#define HUGETLB_FLAG_ENCODE_8MB		(23U << HUGETLB_FLAG_ENCODE_SHIFT)
+#define HUGETLB_FLAG_ENCODE_16MB	(24U << HUGETLB_FLAG_ENCODE_SHIFT)
+#define HUGETLB_FLAG_ENCODE_32MB	(25U << HUGETLB_FLAG_ENCODE_SHIFT)
+#define HUGETLB_FLAG_ENCODE_256MB	(28U << HUGETLB_FLAG_ENCODE_SHIFT)
+#define HUGETLB_FLAG_ENCODE_512MB	(29U << HUGETLB_FLAG_ENCODE_SHIFT)
+#define HUGETLB_FLAG_ENCODE_1GB		(30U << HUGETLB_FLAG_ENCODE_SHIFT)
+#define HUGETLB_FLAG_ENCODE_2GB		(31U << HUGETLB_FLAG_ENCODE_SHIFT)
+#define HUGETLB_FLAG_ENCODE_16GB	(34U << HUGETLB_FLAG_ENCODE_SHIFT)
+
+#endif /* _ASM_GENERIC_HUGETLB_ENCODE_H_ */
diff --git a/tools/include/asm-generic/io.h b/tools/include/asm-generic/io.h
new file mode 100644
index 000000000..e5a0b07ad
--- /dev/null
+++ b/tools/include/asm-generic/io.h
@@ -0,0 +1,482 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _TOOLS_ASM_GENERIC_IO_H
+#define _TOOLS_ASM_GENERIC_IO_H
+
+#include <asm/barrier.h>
+#include <asm/byteorder.h>
+
+#include <linux/compiler.h>
+#include <linux/kernel.h>
+#include <linux/types.h>
+
+#ifndef mmiowb_set_pending
+#define mmiowb_set_pending() do { } while (0)
+#endif
+
+#ifndef __io_br
+#define __io_br()      barrier()
+#endif
+
+/* prevent prefetching of coherent DMA data ahead of a dma-complete */
+#ifndef __io_ar
+#ifdef rmb
+#define __io_ar(v)      rmb()
+#else
+#define __io_ar(v)      barrier()
+#endif
+#endif
+
+/* flush writes to coherent DMA data before possibly triggering a DMA read */
+#ifndef __io_bw
+#ifdef wmb
+#define __io_bw()      wmb()
+#else
+#define __io_bw()      barrier()
+#endif
+#endif
+
+/* serialize device access against a spin_unlock, usually handled there. */
+#ifndef __io_aw
+#define __io_aw()      mmiowb_set_pending()
+#endif
+
+#ifndef __io_pbw
+#define __io_pbw()     __io_bw()
+#endif
+
+#ifndef __io_paw
+#define __io_paw()     __io_aw()
+#endif
+
+#ifndef __io_pbr
+#define __io_pbr()     __io_br()
+#endif
+
+#ifndef __io_par
+#define __io_par(v)     __io_ar(v)
+#endif
+
+#ifndef _THIS_IP_
+#define _THIS_IP_ 0
+#endif
+
+static inline void log_write_mmio(u64 val, u8 width, volatile void __iomem *addr,
+				  unsigned long caller_addr, unsigned long caller_addr0) {}
+static inline void log_post_write_mmio(u64 val, u8 width, volatile void __iomem *addr,
+				       unsigned long caller_addr, unsigned long caller_addr0) {}
+static inline void log_read_mmio(u8 width, const volatile void __iomem *addr,
+				 unsigned long caller_addr, unsigned long caller_addr0) {}
+static inline void log_post_read_mmio(u64 val, u8 width, const volatile void __iomem *addr,
+				      unsigned long caller_addr, unsigned long caller_addr0) {}
+
+/*
+ * __raw_{read,write}{b,w,l,q}() access memory in native endianness.
+ *
+ * On some architectures memory mapped IO needs to be accessed differently.
+ * On the simple architectures, we just read/write the memory location
+ * directly.
+ */
+
+#ifndef __raw_readb
+#define __raw_readb __raw_readb
+static inline u8 __raw_readb(const volatile void __iomem *addr)
+{
+	return *(const volatile u8 __force *)addr;
+}
+#endif
+
+#ifndef __raw_readw
+#define __raw_readw __raw_readw
+static inline u16 __raw_readw(const volatile void __iomem *addr)
+{
+	return *(const volatile u16 __force *)addr;
+}
+#endif
+
+#ifndef __raw_readl
+#define __raw_readl __raw_readl
+static inline u32 __raw_readl(const volatile void __iomem *addr)
+{
+	return *(const volatile u32 __force *)addr;
+}
+#endif
+
+#ifndef __raw_readq
+#define __raw_readq __raw_readq
+static inline u64 __raw_readq(const volatile void __iomem *addr)
+{
+	return *(const volatile u64 __force *)addr;
+}
+#endif
+
+#ifndef __raw_writeb
+#define __raw_writeb __raw_writeb
+static inline void __raw_writeb(u8 value, volatile void __iomem *addr)
+{
+	*(volatile u8 __force *)addr = value;
+}
+#endif
+
+#ifndef __raw_writew
+#define __raw_writew __raw_writew
+static inline void __raw_writew(u16 value, volatile void __iomem *addr)
+{
+	*(volatile u16 __force *)addr = value;
+}
+#endif
+
+#ifndef __raw_writel
+#define __raw_writel __raw_writel
+static inline void __raw_writel(u32 value, volatile void __iomem *addr)
+{
+	*(volatile u32 __force *)addr = value;
+}
+#endif
+
+#ifndef __raw_writeq
+#define __raw_writeq __raw_writeq
+static inline void __raw_writeq(u64 value, volatile void __iomem *addr)
+{
+	*(volatile u64 __force *)addr = value;
+}
+#endif
+
+/*
+ * {read,write}{b,w,l,q}() access little endian memory and return result in
+ * native endianness.
+ */
+
+#ifndef readb
+#define readb readb
+static inline u8 readb(const volatile void __iomem *addr)
+{
+	u8 val;
+
+	log_read_mmio(8, addr, _THIS_IP_, _RET_IP_);
+	__io_br();
+	val = __raw_readb(addr);
+	__io_ar(val);
+	log_post_read_mmio(val, 8, addr, _THIS_IP_, _RET_IP_);
+	return val;
+}
+#endif
+
+#ifndef readw
+#define readw readw
+static inline u16 readw(const volatile void __iomem *addr)
+{
+	u16 val;
+
+	log_read_mmio(16, addr, _THIS_IP_, _RET_IP_);
+	__io_br();
+	val = __le16_to_cpu((__le16 __force)__raw_readw(addr));
+	__io_ar(val);
+	log_post_read_mmio(val, 16, addr, _THIS_IP_, _RET_IP_);
+	return val;
+}
+#endif
+
+#ifndef readl
+#define readl readl
+static inline u32 readl(const volatile void __iomem *addr)
+{
+	u32 val;
+
+	log_read_mmio(32, addr, _THIS_IP_, _RET_IP_);
+	__io_br();
+	val = __le32_to_cpu((__le32 __force)__raw_readl(addr));
+	__io_ar(val);
+	log_post_read_mmio(val, 32, addr, _THIS_IP_, _RET_IP_);
+	return val;
+}
+#endif
+
+#ifndef readq
+#define readq readq
+static inline u64 readq(const volatile void __iomem *addr)
+{
+	u64 val;
+
+	log_read_mmio(64, addr, _THIS_IP_, _RET_IP_);
+	__io_br();
+	val = __le64_to_cpu((__le64 __force)__raw_readq(addr));
+	__io_ar(val);
+	log_post_read_mmio(val, 64, addr, _THIS_IP_, _RET_IP_);
+	return val;
+}
+#endif
+
+#ifndef writeb
+#define writeb writeb
+static inline void writeb(u8 value, volatile void __iomem *addr)
+{
+	log_write_mmio(value, 8, addr, _THIS_IP_, _RET_IP_);
+	__io_bw();
+	__raw_writeb(value, addr);
+	__io_aw();
+	log_post_write_mmio(value, 8, addr, _THIS_IP_, _RET_IP_);
+}
+#endif
+
+#ifndef writew
+#define writew writew
+static inline void writew(u16 value, volatile void __iomem *addr)
+{
+	log_write_mmio(value, 16, addr, _THIS_IP_, _RET_IP_);
+	__io_bw();
+	__raw_writew((u16 __force)cpu_to_le16(value), addr);
+	__io_aw();
+	log_post_write_mmio(value, 16, addr, _THIS_IP_, _RET_IP_);
+}
+#endif
+
+#ifndef writel
+#define writel writel
+static inline void writel(u32 value, volatile void __iomem *addr)
+{
+	log_write_mmio(value, 32, addr, _THIS_IP_, _RET_IP_);
+	__io_bw();
+	__raw_writel((u32 __force)__cpu_to_le32(value), addr);
+	__io_aw();
+	log_post_write_mmio(value, 32, addr, _THIS_IP_, _RET_IP_);
+}
+#endif
+
+#ifndef writeq
+#define writeq writeq
+static inline void writeq(u64 value, volatile void __iomem *addr)
+{
+	log_write_mmio(value, 64, addr, _THIS_IP_, _RET_IP_);
+	__io_bw();
+	__raw_writeq((u64 __force)__cpu_to_le64(value), addr);
+	__io_aw();
+	log_post_write_mmio(value, 64, addr, _THIS_IP_, _RET_IP_);
+}
+#endif
+
+/*
+ * {read,write}{b,w,l,q}_relaxed() are like the regular version, but
+ * are not guaranteed to provide ordering against spinlocks or memory
+ * accesses.
+ */
+#ifndef readb_relaxed
+#define readb_relaxed readb_relaxed
+static inline u8 readb_relaxed(const volatile void __iomem *addr)
+{
+	u8 val;
+
+	log_read_mmio(8, addr, _THIS_IP_, _RET_IP_);
+	val = __raw_readb(addr);
+	log_post_read_mmio(val, 8, addr, _THIS_IP_, _RET_IP_);
+	return val;
+}
+#endif
+
+#ifndef readw_relaxed
+#define readw_relaxed readw_relaxed
+static inline u16 readw_relaxed(const volatile void __iomem *addr)
+{
+	u16 val;
+
+	log_read_mmio(16, addr, _THIS_IP_, _RET_IP_);
+	val = __le16_to_cpu((__le16 __force)__raw_readw(addr));
+	log_post_read_mmio(val, 16, addr, _THIS_IP_, _RET_IP_);
+	return val;
+}
+#endif
+
+#ifndef readl_relaxed
+#define readl_relaxed readl_relaxed
+static inline u32 readl_relaxed(const volatile void __iomem *addr)
+{
+	u32 val;
+
+	log_read_mmio(32, addr, _THIS_IP_, _RET_IP_);
+	val = __le32_to_cpu((__le32 __force)__raw_readl(addr));
+	log_post_read_mmio(val, 32, addr, _THIS_IP_, _RET_IP_);
+	return val;
+}
+#endif
+
+#if defined(readq) && !defined(readq_relaxed)
+#define readq_relaxed readq_relaxed
+static inline u64 readq_relaxed(const volatile void __iomem *addr)
+{
+	u64 val;
+
+	log_read_mmio(64, addr, _THIS_IP_, _RET_IP_);
+	val = __le64_to_cpu((__le64 __force)__raw_readq(addr));
+	log_post_read_mmio(val, 64, addr, _THIS_IP_, _RET_IP_);
+	return val;
+}
+#endif
+
+#ifndef writeb_relaxed
+#define writeb_relaxed writeb_relaxed
+static inline void writeb_relaxed(u8 value, volatile void __iomem *addr)
+{
+	log_write_mmio(value, 8, addr, _THIS_IP_, _RET_IP_);
+	__raw_writeb(value, addr);
+	log_post_write_mmio(value, 8, addr, _THIS_IP_, _RET_IP_);
+}
+#endif
+
+#ifndef writew_relaxed
+#define writew_relaxed writew_relaxed
+static inline void writew_relaxed(u16 value, volatile void __iomem *addr)
+{
+	log_write_mmio(value, 16, addr, _THIS_IP_, _RET_IP_);
+	__raw_writew((u16 __force)cpu_to_le16(value), addr);
+	log_post_write_mmio(value, 16, addr, _THIS_IP_, _RET_IP_);
+}
+#endif
+
+#ifndef writel_relaxed
+#define writel_relaxed writel_relaxed
+static inline void writel_relaxed(u32 value, volatile void __iomem *addr)
+{
+	log_write_mmio(value, 32, addr, _THIS_IP_, _RET_IP_);
+	__raw_writel((u32 __force)__cpu_to_le32(value), addr);
+	log_post_write_mmio(value, 32, addr, _THIS_IP_, _RET_IP_);
+}
+#endif
+
+#if defined(writeq) && !defined(writeq_relaxed)
+#define writeq_relaxed writeq_relaxed
+static inline void writeq_relaxed(u64 value, volatile void __iomem *addr)
+{
+	log_write_mmio(value, 64, addr, _THIS_IP_, _RET_IP_);
+	__raw_writeq((u64 __force)__cpu_to_le64(value), addr);
+	log_post_write_mmio(value, 64, addr, _THIS_IP_, _RET_IP_);
+}
+#endif
+
+/*
+ * {read,write}s{b,w,l,q}() repeatedly access the same memory address in
+ * native endianness in 8-, 16-, 32- or 64-bit chunks (@count times).
+ */
+#ifndef readsb
+#define readsb readsb
+static inline void readsb(const volatile void __iomem *addr, void *buffer,
+			  unsigned int count)
+{
+	if (count) {
+		u8 *buf = buffer;
+
+		do {
+			u8 x = __raw_readb(addr);
+			*buf++ = x;
+		} while (--count);
+	}
+}
+#endif
+
+#ifndef readsw
+#define readsw readsw
+static inline void readsw(const volatile void __iomem *addr, void *buffer,
+			  unsigned int count)
+{
+	if (count) {
+		u16 *buf = buffer;
+
+		do {
+			u16 x = __raw_readw(addr);
+			*buf++ = x;
+		} while (--count);
+	}
+}
+#endif
+
+#ifndef readsl
+#define readsl readsl
+static inline void readsl(const volatile void __iomem *addr, void *buffer,
+			  unsigned int count)
+{
+	if (count) {
+		u32 *buf = buffer;
+
+		do {
+			u32 x = __raw_readl(addr);
+			*buf++ = x;
+		} while (--count);
+	}
+}
+#endif
+
+#ifndef readsq
+#define readsq readsq
+static inline void readsq(const volatile void __iomem *addr, void *buffer,
+			  unsigned int count)
+{
+	if (count) {
+		u64 *buf = buffer;
+
+		do {
+			u64 x = __raw_readq(addr);
+			*buf++ = x;
+		} while (--count);
+	}
+}
+#endif
+
+#ifndef writesb
+#define writesb writesb
+static inline void writesb(volatile void __iomem *addr, const void *buffer,
+			   unsigned int count)
+{
+	if (count) {
+		const u8 *buf = buffer;
+
+		do {
+			__raw_writeb(*buf++, addr);
+		} while (--count);
+	}
+}
+#endif
+
+#ifndef writesw
+#define writesw writesw
+static inline void writesw(volatile void __iomem *addr, const void *buffer,
+			   unsigned int count)
+{
+	if (count) {
+		const u16 *buf = buffer;
+
+		do {
+			__raw_writew(*buf++, addr);
+		} while (--count);
+	}
+}
+#endif
+
+#ifndef writesl
+#define writesl writesl
+static inline void writesl(volatile void __iomem *addr, const void *buffer,
+			   unsigned int count)
+{
+	if (count) {
+		const u32 *buf = buffer;
+
+		do {
+			__raw_writel(*buf++, addr);
+		} while (--count);
+	}
+}
+#endif
+
+#ifndef writesq
+#define writesq writesq
+static inline void writesq(volatile void __iomem *addr, const void *buffer,
+			   unsigned int count)
+{
+	if (count) {
+		const u64 *buf = buffer;
+
+		do {
+			__raw_writeq(*buf++, addr);
+		} while (--count);
+	}
+}
+#endif
+
+#endif /* _TOOLS_ASM_GENERIC_IO_H */