Rebase locking/kcsan to locking/urgent

Merge the state of the locking kcsan branch before the read/write_once()
and the atomics modifications got merged.

Squash the fallout of the rebase on top of the read/write once and atomic
fallback work into the merge. The history of the original branch is
preserved in tag locking-kcsan-2020-06-02.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

9 files changed, 732 insertions, 23 deletions

diff --git a/include/linux/compiler-clang.h b/include/linux/compiler-clang.h
index 790c0c6b8552..ee37256ec8bd 100644
--- a/include/linux/compiler-clang.h
+++ b/include/linux/compiler-clang.h
@@ -16,7 +16,7 @@
 #define KASAN_ABI_VERSION 5
 
 #if __has_feature(address_sanitizer) || __has_feature(hwaddress_sanitizer)
-/* emulate gcc's __SANITIZE_ADDRESS__ flag */
+/* Emulate GCC's __SANITIZE_ADDRESS__ flag */
 #define __SANITIZE_ADDRESS__
 #define __no_sanitize_address \
 		__attribute__((no_sanitize("address", "hwaddress")))
@@ -24,6 +24,15 @@
 #define __no_sanitize_address
 #endif
 
+#if __has_feature(thread_sanitizer)
+/* emulate gcc's __SANITIZE_THREAD__ flag */
+#define __SANITIZE_THREAD__
+#define __no_sanitize_thread \
+		__attribute__((no_sanitize("thread")))
+#else
+#define __no_sanitize_thread
+#endif
+
 /*
  * Not all versions of clang implement the the type-generic versions
  * of the builtin overflow checkers. Fortunately, clang implements
diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h
index e2f725273261..7dd4e0349ef3 100644
--- a/include/linux/compiler-gcc.h
+++ b/include/linux/compiler-gcc.h
@@ -144,6 +144,12 @@
 #define __no_sanitize_address
 #endif
 
+#if defined(__SANITIZE_THREAD__) && __has_attribute(__no_sanitize_thread__)
+#define __no_sanitize_thread __attribute__((no_sanitize_thread))
+#else
+#define __no_sanitize_thread
+#endif
+
 #if GCC_VERSION >= 50100
 #define COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW 1
 #endif
diff --git a/include/linux/compiler.h b/include/linux/compiler.h
index 33d3a2e5abab..f09ebbf16562 100644
--- a/include/linux/compiler.h
+++ b/include/linux/compiler.h
@@ -250,6 +250,27 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val,
  */
 #include <asm/barrier.h>
 #include <linux/kasan-checks.h>
+#include <linux/kcsan-checks.h>
+
+/**
+ * data_race - mark an expression as containing intentional data races
+ *
+ * This data_race() macro is useful for situations in which data races
+ * should be forgiven.  One example is diagnostic code that accesses
+ * shared variables but is not a part of the core synchronization design.
+ *
+ * This macro *does not* affect normal code generation, but is a hint
+ * to tooling that data races here are to be ignored.
+ */
+#define data_race(expr)							\
+({									\
+	__kcsan_disable_current();					\
+	({								\
+		__unqual_scalar_typeof(({ expr; })) __v = ({ expr; });	\
+		__kcsan_enable_current();				\
+		__v;							\
+	});								\
+})
 
 /*
  * Use __READ_ONCE() instead of READ_ONCE() if you do not require any
@@ -260,7 +281,9 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val,
 
 #define __READ_ONCE_SCALAR(x)						\
 ({									\
-	__unqual_scalar_typeof(x) __x = __READ_ONCE(x);			\
+	typeof(x) *__xp = &(x);						\
+	__unqual_scalar_typeof(x) __x = data_race(__READ_ONCE(*__xp));	\
+	kcsan_check_atomic_read(__xp, sizeof(*__xp));			\
 	smp_read_barrier_depends();					\
 	(typeof(x))__x;							\
 })
@@ -271,15 +294,22 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val,
 	__READ_ONCE_SCALAR(x);						\
 })
 
-#define __WRITE_ONCE(x, val)				\
-do {							\
-	*(volatile typeof(x) *)&(x) = (val);		\
+#define __WRITE_ONCE(x, val)						\
+do {									\
+	*(volatile typeof(x) *)&(x) = (val);				\
+} while (0)
+
+#define __WRITE_ONCE_SCALAR(x, val)					\
+do {									\
+	typeof(x) *__xp = &(x);						\
+	kcsan_check_atomic_write(__xp, sizeof(*__xp));			\
+	data_race(({ __WRITE_ONCE(*__xp, val); 0; }));			\
 } while (0)
 
-#define WRITE_ONCE(x, val)				\
-do {							\
-	compiletime_assert_rwonce_type(x);		\
-	__WRITE_ONCE(x, val);				\
+#define WRITE_ONCE(x, val)						\
+do {									\
+	compiletime_assert_rwonce_type(x);				\
+	__WRITE_ONCE_SCALAR(x, val);					\
 } while (0)
 
 #ifdef CONFIG_KASAN
@@ -290,11 +320,30 @@ do {							\
  * '__maybe_unused' allows us to avoid defined-but-not-used warnings.
  */
 # define __no_kasan_or_inline __no_sanitize_address notrace __maybe_unused
+# define __no_sanitize_or_inline __no_kasan_or_inline
 #else
 # define __no_kasan_or_inline __always_inline
 #endif
 
-static __no_kasan_or_inline
+#define __no_kcsan __no_sanitize_thread
+#ifdef __SANITIZE_THREAD__
+/*
+ * Rely on __SANITIZE_THREAD__ instead of CONFIG_KCSAN, to avoid not inlining in
+ * compilation units where instrumentation is disabled. The attribute 'noinline'
+ * is required for older compilers, where implicit inlining of very small
+ * functions renders __no_sanitize_thread ineffective.
+ */
+# define __no_kcsan_or_inline __no_kcsan noinline notrace __maybe_unused
+# define __no_sanitize_or_inline __no_kcsan_or_inline
+#else
+# define __no_kcsan_or_inline __always_inline
+#endif
+
+#ifndef __no_sanitize_or_inline
+#define __no_sanitize_or_inline __always_inline
+#endif
+
+static __no_sanitize_or_inline
 unsigned long __read_once_word_nocheck(const void *addr)
 {
 	return __READ_ONCE(*(unsigned long *)addr);
@@ -302,8 +351,8 @@ unsigned long __read_once_word_nocheck(const void *addr)
 
 /*
  * Use READ_ONCE_NOCHECK() instead of READ_ONCE() if you need to load a
- * word from memory atomically but without telling KASAN. This is usually
- * used by unwinding code when walking the stack of a running process.
+ * word from memory atomically but without telling KASAN/KCSAN. This is
+ * usually used by unwinding code when walking the stack of a running process.
  */
 #define READ_ONCE_NOCHECK(x)						\
 ({									\
diff --git a/include/linux/instrumented.h b/include/linux/instrumented.h
new file mode 100644
index 000000000000..43e6ea591975
--- /dev/null
+++ b/include/linux/instrumented.h
@@ -0,0 +1,109 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+/*
+ * This header provides generic wrappers for memory access instrumentation that
+ * the compiler cannot emit for: KASAN, KCSAN.
+ */
+#ifndef _LINUX_INSTRUMENTED_H
+#define _LINUX_INSTRUMENTED_H
+
+#include <linux/compiler.h>
+#include <linux/kasan-checks.h>
+#include <linux/kcsan-checks.h>
+#include <linux/types.h>
+
+/**
+ * instrument_read - instrument regular read access
+ *
+ * Instrument a regular read access. The instrumentation should be inserted
+ * before the actual read happens.
+ *
+ * @ptr address of access
+ * @size size of access
+ */
+static __always_inline void instrument_read(const volatile void *v, size_t size)
+{
+	kasan_check_read(v, size);
+	kcsan_check_read(v, size);
+}
+
+/**
+ * instrument_write - instrument regular write access
+ *
+ * Instrument a regular write access. The instrumentation should be inserted
+ * before the actual write happens.
+ *
+ * @ptr address of access
+ * @size size of access
+ */
+static __always_inline void instrument_write(const volatile void *v, size_t size)
+{
+	kasan_check_write(v, size);
+	kcsan_check_write(v, size);
+}
+
+/**
+ * instrument_atomic_read - instrument atomic read access
+ *
+ * Instrument an atomic read access. The instrumentation should be inserted
+ * before the actual read happens.
+ *
+ * @ptr address of access
+ * @size size of access
+ */
+static __always_inline void instrument_atomic_read(const volatile void *v, size_t size)
+{
+	kasan_check_read(v, size);
+	kcsan_check_atomic_read(v, size);
+}
+
+/**
+ * instrument_atomic_write - instrument atomic write access
+ *
+ * Instrument an atomic write access. The instrumentation should be inserted
+ * before the actual write happens.
+ *
+ * @ptr address of access
+ * @size size of access
+ */
+static __always_inline void instrument_atomic_write(const volatile void *v, size_t size)
+{
+	kasan_check_write(v, size);
+	kcsan_check_atomic_write(v, size);
+}
+
+/**
+ * instrument_copy_to_user - instrument reads of copy_to_user
+ *
+ * Instrument reads from kernel memory, that are due to copy_to_user (and
+ * variants). The instrumentation must be inserted before the accesses.
+ *
+ * @to destination address
+ * @from source address
+ * @n number of bytes to copy
+ */
+static __always_inline void
+instrument_copy_to_user(void __user *to, const void *from, unsigned long n)
+{
+	kasan_check_read(from, n);
+	kcsan_check_read(from, n);
+}
+
+/**
+ * instrument_copy_from_user - instrument writes of copy_from_user
+ *
+ * Instrument writes to kernel memory, that are due to copy_from_user (and
+ * variants). The instrumentation should be inserted before the accesses.
+ *
+ * @to destination address
+ * @from source address
+ * @n number of bytes to copy
+ */
+static __always_inline void
+instrument_copy_from_user(const void *to, const void __user *from, unsigned long n)
+{
+	kasan_check_write(to, n);
+	kcsan_check_write(to, n);
+}
+
+#endif /* _LINUX_INSTRUMENTED_H */
diff --git a/include/linux/kcsan-checks.h b/include/linux/kcsan-checks.h
new file mode 100644
index 000000000000..7b0b9c44f5f3
--- /dev/null
+++ b/include/linux/kcsan-checks.h
@@ -0,0 +1,430 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef _LINUX_KCSAN_CHECKS_H
+#define _LINUX_KCSAN_CHECKS_H
+
+/* Note: Only include what is already included by compiler.h. */
+#include <linux/compiler_attributes.h>
+#include <linux/types.h>
+
+/*
+ * ACCESS TYPE MODIFIERS
+ *
+ *   <none>: normal read access;
+ *   WRITE : write access;
+ *   ATOMIC: access is atomic;
+ *   ASSERT: access is not a regular access, but an assertion;
+ *   SCOPED: access is a scoped access;
+ */
+#define KCSAN_ACCESS_WRITE  0x1
+#define KCSAN_ACCESS_ATOMIC 0x2
+#define KCSAN_ACCESS_ASSERT 0x4
+#define KCSAN_ACCESS_SCOPED 0x8
+
+/*
+ * __kcsan_*: Always calls into the runtime when KCSAN is enabled. This may be used
+ * even in compilation units that selectively disable KCSAN, but must use KCSAN
+ * to validate access to an address. Never use these in header files!
+ */
+#ifdef CONFIG_KCSAN
+/**
+ * __kcsan_check_access - check generic access for races
+ *
+ * @ptr: address of access
+ * @size: size of access
+ * @type: access type modifier
+ */
+void __kcsan_check_access(const volatile void *ptr, size_t size, int type);
+
+/**
+ * kcsan_disable_current - disable KCSAN for the current context
+ *
+ * Supports nesting.
+ */
+void kcsan_disable_current(void);
+
+/**
+ * kcsan_enable_current - re-enable KCSAN for the current context
+ *
+ * Supports nesting.
+ */
+void kcsan_enable_current(void);
+void kcsan_enable_current_nowarn(void); /* Safe in uaccess regions. */
+
+/**
+ * kcsan_nestable_atomic_begin - begin nestable atomic region
+ *
+ * Accesses within the atomic region may appear to race with other accesses but
+ * should be considered atomic.
+ */
+void kcsan_nestable_atomic_begin(void);
+
+/**
+ * kcsan_nestable_atomic_end - end nestable atomic region
+ */
+void kcsan_nestable_atomic_end(void);
+
+/**
+ * kcsan_flat_atomic_begin - begin flat atomic region
+ *
+ * Accesses within the atomic region may appear to race with other accesses but
+ * should be considered atomic.
+ */
+void kcsan_flat_atomic_begin(void);
+
+/**
+ * kcsan_flat_atomic_end - end flat atomic region
+ */
+void kcsan_flat_atomic_end(void);
+
+/**
+ * kcsan_atomic_next - consider following accesses as atomic
+ *
+ * Force treating the next n memory accesses for the current context as atomic
+ * operations.
+ *
+ * @n: number of following memory accesses to treat as atomic.
+ */
+void kcsan_atomic_next(int n);
+
+/**
+ * kcsan_set_access_mask - set access mask
+ *
+ * Set the access mask for all accesses for the current context if non-zero.
+ * Only value changes to bits set in the mask will be reported.
+ *
+ * @mask: bitmask
+ */
+void kcsan_set_access_mask(unsigned long mask);
+
+/* Scoped access information. */
+struct kcsan_scoped_access {
+	struct list_head list;
+	const volatile void *ptr;
+	size_t size;
+	int type;
+};
+/*
+ * Automatically call kcsan_end_scoped_access() when kcsan_scoped_access goes
+ * out of scope; relies on attribute "cleanup", which is supported by all
+ * compilers that support KCSAN.
+ */
+#define __kcsan_cleanup_scoped                                                 \
+	__maybe_unused __attribute__((__cleanup__(kcsan_end_scoped_access)))
+
+/**
+ * kcsan_begin_scoped_access - begin scoped access
+ *
+ * Begin scoped access and initialize @sa, which will cause KCSAN to
+ * continuously check the memory range in the current thread until
+ * kcsan_end_scoped_access() is called for @sa.
+ *
+ * Scoped accesses are implemented by appending @sa to an internal list for the
+ * current execution context, and then checked on every call into the KCSAN
+ * runtime.
+ *
+ * @ptr: address of access
+ * @size: size of access
+ * @type: access type modifier
+ * @sa: struct kcsan_scoped_access to use for the scope of the access
+ */
+struct kcsan_scoped_access *
+kcsan_begin_scoped_access(const volatile void *ptr, size_t size, int type,
+			  struct kcsan_scoped_access *sa);
+
+/**
+ * kcsan_end_scoped_access - end scoped access
+ *
+ * End a scoped access, which will stop KCSAN checking the memory range.
+ * Requires that kcsan_begin_scoped_access() was previously called once for @sa.
+ *
+ * @sa: a previously initialized struct kcsan_scoped_access
+ */
+void kcsan_end_scoped_access(struct kcsan_scoped_access *sa);
+
+
+#else /* CONFIG_KCSAN */
+
+static inline void __kcsan_check_access(const volatile void *ptr, size_t size,
+					int type) { }
+
+static inline void kcsan_disable_current(void)		{ }
+static inline void kcsan_enable_current(void)		{ }
+static inline void kcsan_enable_current_nowarn(void)	{ }
+static inline void kcsan_nestable_atomic_begin(void)	{ }
+static inline void kcsan_nestable_atomic_end(void)	{ }
+static inline void kcsan_flat_atomic_begin(void)	{ }
+static inline void kcsan_flat_atomic_end(void)		{ }
+static inline void kcsan_atomic_next(int n)		{ }
+static inline void kcsan_set_access_mask(unsigned long mask) { }
+
+struct kcsan_scoped_access { };
+#define __kcsan_cleanup_scoped __maybe_unused
+static inline struct kcsan_scoped_access *
+kcsan_begin_scoped_access(const volatile void *ptr, size_t size, int type,
+			  struct kcsan_scoped_access *sa) { return sa; }
+static inline void kcsan_end_scoped_access(struct kcsan_scoped_access *sa) { }
+
+#endif /* CONFIG_KCSAN */
+
+#ifdef __SANITIZE_THREAD__
+/*
+ * Only calls into the runtime when the particular compilation unit has KCSAN
+ * instrumentation enabled. May be used in header files.
+ */
+#define kcsan_check_access __kcsan_check_access
+
+/*
+ * Only use these to disable KCSAN for accesses in the current compilation unit;
+ * calls into libraries may still perform KCSAN checks.
+ */
+#define __kcsan_disable_current kcsan_disable_current
+#define __kcsan_enable_current kcsan_enable_current_nowarn
+#else
+static inline void kcsan_check_access(const volatile void *ptr, size_t size,
+				      int type) { }
+static inline void __kcsan_enable_current(void)  { }
+static inline void __kcsan_disable_current(void) { }
+#endif
+
+/**
+ * __kcsan_check_read - check regular read access for races
+ *
+ * @ptr: address of access
+ * @size: size of access
+ */
+#define __kcsan_check_read(ptr, size) __kcsan_check_access(ptr, size, 0)
+
+/**
+ * __kcsan_check_write - check regular write access for races
+ *
+ * @ptr: address of access
+ * @size: size of access
+ */
+#define __kcsan_check_write(ptr, size)                                         \
+	__kcsan_check_access(ptr, size, KCSAN_ACCESS_WRITE)
+
+/**
+ * kcsan_check_read - check regular read access for races
+ *
+ * @ptr: address of access
+ * @size: size of access
+ */
+#define kcsan_check_read(ptr, size) kcsan_check_access(ptr, size, 0)
+
+/**
+ * kcsan_check_write - check regular write access for races
+ *
+ * @ptr: address of access
+ * @size: size of access
+ */
+#define kcsan_check_write(ptr, size)                                           \
+	kcsan_check_access(ptr, size, KCSAN_ACCESS_WRITE)
+
+/*
+ * Check for atomic accesses: if atomic accesses are not ignored, this simply
+ * aliases to kcsan_check_access(), otherwise becomes a no-op.
+ */
+#ifdef CONFIG_KCSAN_IGNORE_ATOMICS
+#define kcsan_check_atomic_read(...)	do { } while (0)
+#define kcsan_check_atomic_write(...)	do { } while (0)
+#else
+#define kcsan_check_atomic_read(ptr, size)                                     \
+	kcsan_check_access(ptr, size, KCSAN_ACCESS_ATOMIC)
+#define kcsan_check_atomic_write(ptr, size)                                    \
+	kcsan_check_access(ptr, size, KCSAN_ACCESS_ATOMIC | KCSAN_ACCESS_WRITE)
+#endif
+
+/**
+ * ASSERT_EXCLUSIVE_WRITER - assert no concurrent writes to @var
+ *
+ * Assert that there are no concurrent writes to @var; other readers are
+ * allowed. This assertion can be used to specify properties of concurrent code,
+ * where violation cannot be detected as a normal data race.
+ *
+ * For example, if we only have a single writer, but multiple concurrent
+ * readers, to avoid data races, all these accesses must be marked; even
+ * concurrent marked writes racing with the single writer are bugs.
+ * Unfortunately, due to being marked, they are no longer data races. For cases
+ * like these, we can use the macro as follows:
+ *
+ * .. code-block:: c
+ *
+ *	void writer(void) {
+ *		spin_lock(&update_foo_lock);
+ *		ASSERT_EXCLUSIVE_WRITER(shared_foo);
+ *		WRITE_ONCE(shared_foo, ...);
+ *		spin_unlock(&update_foo_lock);
+ *	}
+ *	void reader(void) {
+ *		// update_foo_lock does not need to be held!
+ *		... = READ_ONCE(shared_foo);
+ *	}
+ *
+ * Note: ASSERT_EXCLUSIVE_WRITER_SCOPED(), if applicable, performs more thorough
+ * checking if a clear scope where no concurrent writes are expected exists.
+ *
+ * @var: variable to assert on
+ */
+#define ASSERT_EXCLUSIVE_WRITER(var)                                           \
+	__kcsan_check_access(&(var), sizeof(var), KCSAN_ACCESS_ASSERT)
+
+/*
+ * Helper macros for implementation of for ASSERT_EXCLUSIVE_*_SCOPED(). @id is
+ * expected to be unique for the scope in which instances of kcsan_scoped_access
+ * are declared.
+ */
+#define __kcsan_scoped_name(c, suffix) __kcsan_scoped_##c##suffix
+#define __ASSERT_EXCLUSIVE_SCOPED(var, type, id)                               \
+	struct kcsan_scoped_access __kcsan_scoped_name(id, _)                  \
+		__kcsan_cleanup_scoped;                                        \
+	struct kcsan_scoped_access *__kcsan_scoped_name(id, _dummy_p)          \
+		__maybe_unused = kcsan_begin_scoped_access(                    \
+			&(var), sizeof(var), KCSAN_ACCESS_SCOPED | (type),     \
+			&__kcsan_scoped_name(id, _))
+
+/**
+ * ASSERT_EXCLUSIVE_WRITER_SCOPED - assert no concurrent writes to @var in scope
+ *
+ * Scoped variant of ASSERT_EXCLUSIVE_WRITER().
+ *
+ * Assert that there are no concurrent writes to @var for the duration of the
+ * scope in which it is introduced. This provides a better way to fully cover
+ * the enclosing scope, compared to multiple ASSERT_EXCLUSIVE_WRITER(), and
+ * increases the likelihood for KCSAN to detect racing accesses.
+ *
+ * For example, it allows finding race-condition bugs that only occur due to
+ * state changes within the scope itself:
+ *
+ * .. code-block:: c
+ *
+ *	void writer(void) {
+ *		spin_lock(&update_foo_lock);
+ *		{
+ *			ASSERT_EXCLUSIVE_WRITER_SCOPED(shared_foo);
+ *			WRITE_ONCE(shared_foo, 42);
+ *			...
+ *			// shared_foo should still be 42 here!
+ *		}
+ *		spin_unlock(&update_foo_lock);
+ *	}
+ *	void buggy(void) {
+ *		if (READ_ONCE(shared_foo) == 42)
+ *			WRITE_ONCE(shared_foo, 1); // bug!
+ *	}
+ *
+ * @var: variable to assert on
+ */
+#define ASSERT_EXCLUSIVE_WRITER_SCOPED(var)                                    \
+	__ASSERT_EXCLUSIVE_SCOPED(var, KCSAN_ACCESS_ASSERT, __COUNTER__)
+
+/**
+ * ASSERT_EXCLUSIVE_ACCESS - assert no concurrent accesses to @var
+ *
+ * Assert that there are no concurrent accesses to @var (no readers nor
+ * writers). This assertion can be used to specify properties of concurrent
+ * code, where violation cannot be detected as a normal data race.
+ *
+ * For example, where exclusive access is expected after determining no other
+ * users of an object are left, but the object is not actually freed. We can
+ * check that this property actually holds as follows:
+ *
+ * .. code-block:: c
+ *
+ *	if (refcount_dec_and_test(&obj->refcnt)) {
+ *		ASSERT_EXCLUSIVE_ACCESS(*obj);
+ *		do_some_cleanup(obj);
+ *		release_for_reuse(obj);
+ *	}
+ *
+ * Note: ASSERT_EXCLUSIVE_ACCESS_SCOPED(), if applicable, performs more thorough
+ * checking if a clear scope where no concurrent accesses are expected exists.
+ *
+ * Note: For cases where the object is freed, `KASAN <kasan.html>`_ is a better
+ * fit to detect use-after-free bugs.
+ *
+ * @var: variable to assert on
+ */
+#define ASSERT_EXCLUSIVE_ACCESS(var)                                           \
+	__kcsan_check_access(&(var), sizeof(var), KCSAN_ACCESS_WRITE | KCSAN_ACCESS_ASSERT)
+
+/**
+ * ASSERT_EXCLUSIVE_ACCESS_SCOPED - assert no concurrent accesses to @var in scope
+ *
+ * Scoped variant of ASSERT_EXCLUSIVE_ACCESS().
+ *
+ * Assert that there are no concurrent accesses to @var (no readers nor writers)
+ * for the entire duration of the scope in which it is introduced. This provides
+ * a better way to fully cover the enclosing scope, compared to multiple
+ * ASSERT_EXCLUSIVE_ACCESS(), and increases the likelihood for KCSAN to detect
+ * racing accesses.
+ *
+ * @var: variable to assert on
+ */
+#define ASSERT_EXCLUSIVE_ACCESS_SCOPED(var)                                    \
+	__ASSERT_EXCLUSIVE_SCOPED(var, KCSAN_ACCESS_WRITE | KCSAN_ACCESS_ASSERT, __COUNTER__)
+
+/**
+ * ASSERT_EXCLUSIVE_BITS - assert no concurrent writes to subset of bits in @var
+ *
+ * Bit-granular variant of ASSERT_EXCLUSIVE_WRITER().
+ *
+ * Assert that there are no concurrent writes to a subset of bits in @var;
+ * concurrent readers are permitted. This assertion captures more detailed
+ * bit-level properties, compared to the other (word granularity) assertions.
+ * Only the bits set in @mask are checked for concurrent modifications, while
+ * ignoring the remaining bits, i.e. concurrent writes (or reads) to ~mask bits
+ * are ignored.
+ *
+ * Use this for variables, where some bits must not be modified concurrently,
+ * yet other bits are expected to be modified concurrently.
+ *
+ * For example, variables where, after initialization, some bits are read-only,
+ * but other bits may still be modified concurrently. A reader may wish to
+ * assert that this is true as follows:
+ *
+ * .. code-block:: c
+ *
+ *	ASSERT_EXCLUSIVE_BITS(flags, READ_ONLY_MASK);
+ *	foo = (READ_ONCE(flags) & READ_ONLY_MASK) >> READ_ONLY_SHIFT;
+ *
+ * Note: The access that immediately follows ASSERT_EXCLUSIVE_BITS() is assumed
+ * to access the masked bits only, and KCSAN optimistically assumes it is
+ * therefore safe, even in the presence of data races, and marking it with
+ * READ_ONCE() is optional from KCSAN's point-of-view. We caution, however, that
+ * it may still be advisable to do so, since we cannot reason about all compiler
+ * optimizations when it comes to bit manipulations (on the reader and writer
+ * side). If you are sure nothing can go wrong, we can write the above simply
+ * as:
+ *
+ * .. code-block:: c
+ *
+ *	ASSERT_EXCLUSIVE_BITS(flags, READ_ONLY_MASK);
+ *	foo = (flags & READ_ONLY_MASK) >> READ_ONLY_SHIFT;
+ *
+ * Another example, where this may be used, is when certain bits of @var may
+ * only be modified when holding the appropriate lock, but other bits may still
+ * be modified concurrently. Writers, where other bits may change concurrently,
+ * could use the assertion as follows:
+ *
+ * .. code-block:: c
+ *
+ *	spin_lock(&foo_lock);
+ *	ASSERT_EXCLUSIVE_BITS(flags, FOO_MASK);
+ *	old_flags = flags;
+ *	new_flags = (old_flags & ~FOO_MASK) | (new_foo << FOO_SHIFT);
+ *	if (cmpxchg(&flags, old_flags, new_flags) != old_flags) { ... }
+ *	spin_unlock(&foo_lock);
+ *
+ * @var: variable to assert on
+ * @mask: only check for modifications to bits set in @mask
+ */
+#define ASSERT_EXCLUSIVE_BITS(var, mask)                                       \
+	do {                                                                   \
+		kcsan_set_access_mask(mask);                                   \
+		__kcsan_check_access(&(var), sizeof(var), KCSAN_ACCESS_ASSERT);\
+		kcsan_set_access_mask(0);                                      \
+		kcsan_atomic_next(1);                                          \
+	} while (0)
+
+#endif /* _LINUX_KCSAN_CHECKS_H */
diff --git a/include/linux/kcsan.h b/include/linux/kcsan.h
new file mode 100644
index 000000000000..53340d8789f9
--- /dev/null
+++ b/include/linux/kcsan.h
@@ -0,0 +1,59 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef _LINUX_KCSAN_H
+#define _LINUX_KCSAN_H
+
+#include <linux/kcsan-checks.h>
+#include <linux/types.h>
+
+#ifdef CONFIG_KCSAN
+
+/*
+ * Context for each thread of execution: for tasks, this is stored in
+ * task_struct, and interrupts access internal per-CPU storage.
+ */
+struct kcsan_ctx {
+	int disable_count; /* disable counter */
+	int atomic_next; /* number of following atomic ops */
+
+	/*
+	 * We distinguish between: (a) nestable atomic regions that may contain
+	 * other nestable regions; and (b) flat atomic regions that do not keep
+	 * track of nesting. Both (a) and (b) are entirely independent of each
+	 * other, and a flat region may be started in a nestable region or
+	 * vice-versa.
+	 *
+	 * This is required because, for example, in the annotations for
+	 * seqlocks, we declare seqlock writer critical sections as (a) nestable
+	 * atomic regions, but reader critical sections as (b) flat atomic
+	 * regions, but have encountered cases where seqlock reader critical
+	 * sections are contained within writer critical sections (the opposite
+	 * may be possible, too).
+	 *
+	 * To support these cases, we independently track the depth of nesting
+	 * for (a), and whether the leaf level is flat for (b).
+	 */
+	int atomic_nest_count;
+	bool in_flat_atomic;
+
+	/*
+	 * Access mask for all accesses if non-zero.
+	 */
+	unsigned long access_mask;
+
+	/* List of scoped accesses. */
+	struct list_head scoped_accesses;
+};
+
+/**
+ * kcsan_init - initialize KCSAN runtime
+ */
+void kcsan_init(void);
+
+#else /* CONFIG_KCSAN */
+
+static inline void kcsan_init(void)			{ }
+
+#endif /* CONFIG_KCSAN */
+
+#endif /* _LINUX_KCSAN_H */
diff --git a/include/linux/sched.h b/include/linux/sched.h
index c5d96e3e7fff..4ea612e9ad27 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -31,6 +31,7 @@
 #include <linux/task_io_accounting.h>
 #include <linux/posix-timers.h>
 #include <linux/rseq.h>
+#include <linux/kcsan.h>
 
 /* task_struct member predeclarations (sorted alphabetically): */
 struct audit_context;
@@ -1197,6 +1198,9 @@ struct task_struct {
 #ifdef CONFIG_KASAN
 	unsigned int			kasan_depth;
 #endif
+#ifdef CONFIG_KCSAN
+	struct kcsan_ctx		kcsan_ctx;
+#endif
 
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 	/* Index of current stored address in ret_stack: */
diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h
index 0491d963d47e..8b97204f35a7 100644
--- a/include/linux/seqlock.h
+++ b/include/linux/seqlock.h
@@ -37,9 +37,25 @@
 #include <linux/preempt.h>
 #include <linux/lockdep.h>
 #include <linux/compiler.h>
+#include <linux/kcsan-checks.h>
 #include <asm/processor.h>
 
 /*
+ * The seqlock interface does not prescribe a precise sequence of read
+ * begin/retry/end. For readers, typically there is a call to
+ * read_seqcount_begin() and read_seqcount_retry(), however, there are more
+ * esoteric cases which do not follow this pattern.
+ *
+ * As a consequence, we take the following best-effort approach for raw usage
+ * via seqcount_t under KCSAN: upon beginning a seq-reader critical section,
+ * pessimistically mark the next KCSAN_SEQLOCK_REGION_MAX memory accesses as
+ * atomics; if there is a matching read_seqcount_retry() call, no following
+ * memory operations are considered atomic. Usage of seqlocks via seqlock_t
+ * interface is not affected.
+ */
+#define KCSAN_SEQLOCK_REGION_MAX 1000
+
+/*
  * Version using sequence counter only.
  * This can be used when code has its own mutex protecting the
  * updating starting before the write_seqcountbeqin() and ending
@@ -115,6 +131,7 @@ repeat:
 		cpu_relax();
 		goto repeat;
 	}
+	kcsan_atomic_next(KCSAN_SEQLOCK_REGION_MAX);
 	return ret;
 }
 
@@ -131,6 +148,7 @@ static inline unsigned raw_read_seqcount(const seqcount_t *s)
 {
 	unsigned ret = READ_ONCE(s->sequence);
 	smp_rmb();
+	kcsan_atomic_next(KCSAN_SEQLOCK_REGION_MAX);
 	return ret;
 }
 
@@ -183,6 +201,7 @@ static inline unsigned raw_seqcount_begin(const seqcount_t *s)
 {
 	unsigned ret = READ_ONCE(s->sequence);
 	smp_rmb();
+	kcsan_atomic_next(KCSAN_SEQLOCK_REGION_MAX);
 	return ret & ~1;
 }
 
@@ -202,7 +221,8 @@ static inline unsigned raw_seqcount_begin(const seqcount_t *s)
  */
 static inline int __read_seqcount_retry(const seqcount_t *s, unsigned start)
 {
-	return unlikely(s->sequence != start);
+	kcsan_atomic_next(0);
+	return unlikely(READ_ONCE(s->sequence) != start);
 }
 
 /**
@@ -225,6 +245,7 @@ static inline int read_seqcount_retry(const seqcount_t *s, unsigned start)
 
 static inline void raw_write_seqcount_begin(seqcount_t *s)
 {
+	kcsan_nestable_atomic_begin();
 	s->sequence++;
 	smp_wmb();
 }
@@ -233,6 +254,7 @@ static inline void raw_write_seqcount_end(seqcount_t *s)
 {
 	smp_wmb();
 	s->sequence++;
+	kcsan_nestable_atomic_end();
 }
 
 /**
@@ -243,6 +265,13 @@ static inline void raw_write_seqcount_end(seqcount_t *s)
  * usual consistency guarantee. It is one wmb cheaper, because we can
  * collapse the two back-to-back wmb()s.
  *
+ * Note that writes surrounding the barrier should be declared atomic (e.g.
+ * via WRITE_ONCE): a) to ensure the writes become visible to other threads
+ * atomically, avoiding compiler optimizations; b) to document which writes are
+ * meant to propagate to the reader critical section. This is necessary because
+ * neither writes before and after the barrier are enclosed in a seq-writer
+ * critical section that would ensure readers are aware of ongoing writes.
+ *
  *      seqcount_t seq;
  *      bool X = true, Y = false;
  *
@@ -262,18 +291,20 @@ static inline void raw_write_seqcount_end(seqcount_t *s)
  *
  *      void write(void)
  *      {
- *              Y = true;
+ *              WRITE_ONCE(Y, true);
  *
  *              raw_write_seqcount_barrier(seq);
  *
- *              X = false;
+ *              WRITE_ONCE(X, false);
  *      }
  */
 static inline void raw_write_seqcount_barrier(seqcount_t *s)
 {
+	kcsan_nestable_atomic_begin();
 	s->sequence++;
 	smp_wmb();
 	s->sequence++;
+	kcsan_nestable_atomic_end();
 }
 
 static inline int raw_read_seqcount_latch(seqcount_t *s)
@@ -398,7 +429,9 @@ static inline void write_seqcount_end(seqcount_t *s)
 static inline void write_seqcount_invalidate(seqcount_t *s)
 {
 	smp_wmb();
+	kcsan_nestable_atomic_begin();
 	s->sequence+=2;
+	kcsan_nestable_atomic_end();
 }
 
 typedef struct {
@@ -430,11 +463,21 @@ typedef struct {
  */
 static inline unsigned read_seqbegin(const seqlock_t *sl)
 {
-	return read_seqcount_begin(&sl->seqcount);
+	unsigned ret = read_seqcount_begin(&sl->seqcount);
+
+	kcsan_atomic_next(0);  /* non-raw usage, assume closing read_seqretry() */
+	kcsan_flat_atomic_begin();
+	return ret;
 }
 
 static inline unsigned read_seqretry(const seqlock_t *sl, unsigned start)
 {
+	/*
+	 * Assume not nested: read_seqretry() may be called multiple times when
+	 * completing read critical section.
+	 */
+	kcsan_flat_atomic_end();
+
 	return read_seqcount_retry(&sl->seqcount, start);
 }
 
diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h
index dac1db05bf7e..7bcadca22100 100644
--- a/include/linux/uaccess.h
+++ b/include/linux/uaccess.h
@@ -2,9 +2,9 @@
 #ifndef __LINUX_UACCESS_H__
 #define __LINUX_UACCESS_H__
 
+#include <linux/instrumented.h>
 #include <linux/sched.h>
 #include <linux/thread_info.h>
-#include <linux/kasan-checks.h>
 
 #define uaccess_kernel() segment_eq(get_fs(), KERNEL_DS)
 
@@ -58,7 +58,7 @@
 static __always_inline __must_check unsigned long
 __copy_from_user_inatomic(void *to, const void __user *from, unsigned long n)
 {
-	kasan_check_write(to, n);
+	instrument_copy_from_user(to, from, n);
 	check_object_size(to, n, false);
 	return raw_copy_from_user(to, from, n);
 }
@@ -67,7 +67,7 @@ static __always_inline __must_check unsigned long
 __copy_from_user(void *to, const void __user *from, unsigned long n)
 {
 	might_fault();
-	kasan_check_write(to, n);
+	instrument_copy_from_user(to, from, n);
 	check_object_size(to, n, false);
 	return raw_copy_from_user(to, from, n);
 }
@@ -88,7 +88,7 @@ __copy_from_user(void *to, const void __user *from, unsigned long n)
 static __always_inline __must_check unsigned long
 __copy_to_user_inatomic(void __user *to, const void *from, unsigned long n)
 {
-	kasan_check_read(from, n);
+	instrument_copy_to_user(to, from, n);
 	check_object_size(from, n, true);
 	return raw_copy_to_user(to, from, n);
 }
@@ -97,7 +97,7 @@ static __always_inline __must_check unsigned long
 __copy_to_user(void __user *to, const void *from, unsigned long n)
 {
 	might_fault();
-	kasan_check_read(from, n);
+	instrument_copy_to_user(to, from, n);
 	check_object_size(from, n, true);
 	return raw_copy_to_user(to, from, n);
 }
@@ -109,7 +109,7 @@ _copy_from_user(void *to, const void __user *from, unsigned long n)
 	unsigned long res = n;
 	might_fault();
 	if (likely(access_ok(from, n))) {
-		kasan_check_write(to, n);
+		instrument_copy_from_user(to, from, n);
 		res = raw_copy_from_user(to, from, n);
 	}
 	if (unlikely(res))
@@ -127,7 +127,7 @@ _copy_to_user(void __user *to, const void *from, unsigned long n)
 {
 	might_fault();
 	if (access_ok(to, n)) {
-		kasan_check_read(from, n);
+		instrument_copy_to_user(to, from, n);
 		n = raw_copy_to_user(to, from, n);
 	}
 	return n;