compiler*.h: sync include/linux/compiler*.h with Linux 5.7-rc5

Copy these from Linux v5.7-rc5 tag.

This brings in some handy new attributes and is otherwise important to
keep in sync.

We drop the reference to smp_read_barrier_depends() as it is not
relevant on the architectures we support at this time, based on where
it's implemented in Linux today.  We drop the call to kasan_check_read()
as that is not relevant to U-Boot as well.

Cc: Masahiro Yamada <yamada.masahiro@socionext.com>
Signed-off-by: Tom Rini <trini@konsulko.com>

include/linux/compiler.h

@@ -1,127 +1,38 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef __LINUX_COMPILER_H
 #define __LINUX_COMPILER_H
 
+#include <linux/compiler_types.h>
+
 #ifndef __ASSEMBLY__
 
-#ifdef __CHECKER__
-# define __user		__attribute__((noderef, address_space(1)))
-# define __kernel	__attribute__((address_space(0)))
-# define __safe		__attribute__((safe))
-# define __force	__attribute__((force))
-# define __nocast	__attribute__((nocast))
-# define __iomem	__attribute__((noderef, address_space(2)))
-# define __must_hold(x)	__attribute__((context(x,1,1)))
-# define __acquires(x)	__attribute__((context(x,0,1)))
-# define __releases(x)	__attribute__((context(x,1,0)))
-# define __acquire(x)	__context__(x,1)
-# define __release(x)	__context__(x,-1)
-# define __cond_lock(x,c)	((c) ? ({ __acquire(x); 1; }) : 0)
-# define __percpu	__attribute__((noderef, address_space(3)))
-# define __pmem		__attribute__((noderef, address_space(5)))
-#ifdef CONFIG_SPARSE_RCU_POINTER
-# define __rcu		__attribute__((noderef, address_space(4)))
-#else
-# define __rcu
-#endif
-extern void __chk_user_ptr(const volatile void __user *);
-extern void __chk_io_ptr(const volatile void __iomem *);
-#else
-# define __user
-# define __kernel
-# define __safe
-# define __force
-# define __nocast
-# define __iomem
-# define __chk_user_ptr(x) (void)0
-# define __chk_io_ptr(x) (void)0
-# define __builtin_warning(x, y...) (1)
-# define __must_hold(x)
-# define __acquires(x)
-# define __releases(x)
-# define __acquire(x) (void)0
-# define __release(x) (void)0
-# define __cond_lock(x,c) (c)
-# define __percpu
-# define __rcu
-# define __pmem
-#endif
-
-/* Indirect macros required for expanded argument pasting, eg. __LINE__. */
-#define ___PASTE(a,b) a##b
-#define __PASTE(a,b) ___PASTE(a,b)
-
 #ifdef __KERNEL__
 
-#ifdef __GNUC__
-#include <linux/compiler-gcc.h>
-#endif
-
-#if defined(CC_USING_HOTPATCH) && !defined(__CHECKER__)
-#define notrace __attribute__((hotpatch(0,0)))
-#else
-#define notrace __attribute__((no_instrument_function))
-#endif
-
-/* Intel compiler defines __GNUC__. So we will overwrite implementations
- * coming from above header files here
- */
-#ifdef __INTEL_COMPILER
-# include <linux/compiler-intel.h>
-#endif
-
-/* Clang compiler defines __GNUC__. So we will overwrite implementations
- * coming from above header files here
- */
-#ifdef __clang__
-#include <linux/compiler-clang.h>
-#endif
-
-/*
- * Generic compiler-dependent macros required for kernel
- * build go below this comment. Actual compiler/compiler version
- * specific implementations come from the above header files
- */
-
-struct ftrace_branch_data {
-	const char *func;
-	const char *file;
-	unsigned line;
-	union {
-		struct {
-			unsigned long correct;
-			unsigned long incorrect;
-		};
-		struct {
-			unsigned long miss;
-			unsigned long hit;
-		};
-		unsigned long miss_hit[2];
-	};
-};
-
 /*
  * Note: DISABLE_BRANCH_PROFILING can be used by special lowlevel code
  * to disable branch tracing on a per file basis.
  */
 #if defined(CONFIG_TRACE_BRANCH_PROFILING) \
     && !defined(DISABLE_BRANCH_PROFILING) && !defined(__CHECKER__)
-void ftrace_likely_update(struct ftrace_branch_data *f, int val, int expect);
+void ftrace_likely_update(struct ftrace_likely_data *f, int val,
+			  int expect, int is_constant);
 
 #define likely_notrace(x)	__builtin_expect(!!(x), 1)
 #define unlikely_notrace(x)	__builtin_expect(!!(x), 0)
 
-#define __branch_check__(x, expect) ({					\
-			int ______r;					\
-			static struct ftrace_branch_data		\
-				__attribute__((__aligned__(4)))		\
-				__attribute__((section("_ftrace_annotated_branch"))) \
+#define __branch_check__(x, expect, is_constant) ({			\
+			long ______r;					\
+			static struct ftrace_likely_data		\
+				__aligned(4)				\
+				__section(_ftrace_annotated_branch)	\
 				______f = {				\
-				.func = __func__,			\
-				.file = __FILE__,			\
-				.line = __LINE__,			\
+				.data.func = __func__,			\
+				.data.file = __FILE__,			\
+				.data.line = __LINE__,			\
 			};						\
-			______r = likely_notrace(x);			\
-			ftrace_likely_update(&______f, ______r, expect); \
+			______r = __builtin_expect(!!(x), expect);	\
+			ftrace_likely_update(&______f, ______r,		\
+					     expect, is_constant);	\
 			______r;					\
 		})
 
@@ -131,10 +42,10 @@ void ftrace_likely_update(struct ftrace_branch_data *f, int val, int expect);
  * written by Daniel Walker.
  */
 # ifndef likely
-#  define likely(x)	(__builtin_constant_p(x) ? !!(x) : __branch_check__(x, 1))
+#  define likely(x)	(__branch_check__(x, 1, __builtin_constant_p(x)))
 # endif
 # ifndef unlikely
-#  define unlikely(x)	(__builtin_constant_p(x) ? !!(x) : __branch_check__(x, 0))
+#  define unlikely(x)	(__branch_check__(x, 0, __builtin_constant_p(x)))
 # endif
 
 #ifdef CONFIG_PROFILE_ALL_BRANCHES
@@ -142,23 +53,24 @@ void ftrace_likely_update(struct ftrace_branch_data *f, int val, int expect);
  * "Define 'is'", Bill Clinton
  * "Define 'if'", Steven Rostedt
  */
-#define if(cond, ...) __trace_if( (cond , ## __VA_ARGS__) )
-#define __trace_if(cond) \
-	if (__builtin_constant_p(!!(cond)) ? !!(cond) :			\
-	({								\
-		int ______r;						\
-		static struct ftrace_branch_data			\
-			__attribute__((__aligned__(4)))			\
-			__attribute__((section("_ftrace_branch")))	\
-			______f = {					\
-				.func = __func__,			\
-				.file = __FILE__,			\
-				.line = __LINE__,			\
-			};						\
-		______r = !!(cond);					\
-		______f.miss_hit[______r]++;					\
-		______r;						\
-	}))
+#define if(cond, ...) if ( __trace_if_var( !!(cond , ## __VA_ARGS__) ) )
+
+#define __trace_if_var(cond) (__builtin_constant_p(cond) ? (cond) : __trace_if_value(cond))
+
+#define __trace_if_value(cond) ({			\
+	static struct ftrace_branch_data		\
+		__aligned(4)				\
+		__section(_ftrace_branch)		\
+		__if_trace = {				\
+			.func = __func__,		\
+			.file = __FILE__,		\
+			.line = __LINE__,		\
+		};					\
+	(cond) ?					\
+		(__if_trace.miss_hit[1]++,1) :		\
+		(__if_trace.miss_hit[0]++,0);		\
+})
+
 #endif /* CONFIG_PROFILE_ALL_BRANCHES */
 
 #else
@@ -175,9 +87,76 @@ void ftrace_likely_update(struct ftrace_branch_data *f, int val, int expect);
 # define barrier_data(ptr) barrier()
 #endif
 
+/* workaround for GCC PR82365 if needed */
+#ifndef barrier_before_unreachable
+# define barrier_before_unreachable() do { } while (0)
+#endif
+
 /* Unreachable code */
+#ifdef CONFIG_STACK_VALIDATION
+/*
+ * These macros help objtool understand GCC code flow for unreachable code.
+ * The __COUNTER__ based labels are a hack to make each instance of the macros
+ * unique, to convince GCC not to merge duplicate inline asm statements.
+ */
+#define annotate_reachable() ({						\
+	asm volatile("%c0:\n\t"						\
+		     ".pushsection .discard.reachable\n\t"		\
+		     ".long %c0b - .\n\t"				\
+		     ".popsection\n\t" : : "i" (__COUNTER__));		\
+})
+#define annotate_unreachable() ({					\
+	asm volatile("%c0:\n\t"						\
+		     ".pushsection .discard.unreachable\n\t"		\
+		     ".long %c0b - .\n\t"				\
+		     ".popsection\n\t" : : "i" (__COUNTER__));		\
+})
+#define ASM_UNREACHABLE							\
+	"999:\n\t"							\
+	".pushsection .discard.unreachable\n\t"				\
+	".long 999b - .\n\t"						\
+	".popsection\n\t"
+
+/* Annotate a C jump table to allow objtool to follow the code flow */
+#define __annotate_jump_table __section(.rodata..c_jump_table)
+
+#else
+#define annotate_reachable()
+#define annotate_unreachable()
+#define __annotate_jump_table
+#endif
+
+#ifndef ASM_UNREACHABLE
+# define ASM_UNREACHABLE
+#endif
 #ifndef unreachable
-# define unreachable() do { } while (1)
+# define unreachable() do {		\
+	annotate_unreachable();		\
+	__builtin_unreachable();	\
+} while (0)
+#endif
+
+/*
+ * KENTRY - kernel entry point
+ * This can be used to annotate symbols (functions or data) that are used
+ * without their linker symbol being referenced explicitly. For example,
+ * interrupt vector handlers, or functions in the kernel image that are found
+ * programatically.
+ *
+ * Not required for symbols exported with EXPORT_SYMBOL, or initcalls. Those
+ * are handled in their own way (with KEEP() in linker scripts).
+ *
+ * KENTRY can be avoided if the symbols in question are marked as KEEP() in the
+ * linker script. For example an architecture could KEEP() its entire
+ * boot/exception vector code rather than annotate each function and data.
+ */
+#ifndef KENTRY
+# define KENTRY(sym)						\
+	extern typeof(sym) sym;					\
+	static const unsigned long __kentry_##sym		\
+	__used							\
+	__section("___kentry" "+" #sym )			\
+	= (unsigned long)&sym;
 #endif
 
 #ifndef RELOC_HIDE
@@ -188,7 +167,9 @@ void ftrace_likely_update(struct ftrace_branch_data *f, int val, int expect);
 #endif
 
 #ifndef OPTIMIZER_HIDE_VAR
-#define OPTIMIZER_HIDE_VAR(var) barrier()
+/* Make the optimizer believe the variable can be manipulated arbitrarily. */
+#define OPTIMIZER_HIDE_VAR(var)						\
+	__asm__ ("" : "=r" (var) : "0" (var))
 #endif
 
 /* Not-quite-unique ID. */
@@ -220,23 +201,21 @@ void __read_once_size(const volatile void *p, void *res, int size)
 
 #ifdef CONFIG_KASAN
 /*
- * This function is not 'inline' because __no_sanitize_address confilcts
+ * We can't declare function 'inline' because __no_sanitize_address confilcts
  * with inlining. Attempt to inline it may cause a build failure.
  * 	https://gcc.gnu.org/bugzilla/show_bug.cgi?id=67368
  * '__maybe_unused' allows us to avoid defined-but-not-used warnings.
  */
-static __no_sanitize_address __maybe_unused
-void __read_once_size_nocheck(const volatile void *p, void *res, int size)
-{
-	__READ_ONCE_SIZE;
-}
+# define __no_kasan_or_inline __no_sanitize_address notrace __maybe_unused
 #else
-static __always_inline
+# define __no_kasan_or_inline __always_inline
+#endif
+
+static __no_kasan_or_inline
 void __read_once_size_nocheck(const volatile void *p, void *res, int size)
 {
 	__READ_ONCE_SIZE;
 }
-#endif
 
 static __always_inline void __write_once_size(volatile void *p, void *res, int size)
 {
@@ -255,20 +234,21 @@ static __always_inline void __write_once_size(volatile void *p, void *res, int s
 /*
  * Prevent the compiler from merging or refetching reads or writes. The
  * compiler is also forbidden from reordering successive instances of
- * READ_ONCE, WRITE_ONCE and ACCESS_ONCE (see below), but only when the
- * compiler is aware of some particular ordering.  One way to make the
- * compiler aware of ordering is to put the two invocations of READ_ONCE,
- * WRITE_ONCE or ACCESS_ONCE() in different C statements.
+ * READ_ONCE and WRITE_ONCE, but only when the compiler is aware of some
+ * particular ordering. One way to make the compiler aware of ordering is to
+ * put the two invocations of READ_ONCE or WRITE_ONCE in different C
+ * statements.
  *
- * In contrast to ACCESS_ONCE these two macros will also work on aggregate
- * data types like structs or unions. If the size of the accessed data
- * type exceeds the word size of the machine (e.g., 32 bits or 64 bits)
- * READ_ONCE() and WRITE_ONCE()  will fall back to memcpy and print a
- * compile-time warning.
+ * These two macros will also work on aggregate data types like structs or
+ * unions. If the size of the accessed data type exceeds the word size of
+ * the machine (e.g., 32 bits or 64 bits) READ_ONCE() and WRITE_ONCE() will
+ * fall back to memcpy(). There's at least two memcpy()s: one for the
+ * __builtin_memcpy() and then one for the macro doing the copy of variable
+ * - '__u' allocated on the stack.
  *
  * Their two major use cases are: (1) Mediating communication between
  * process-level code and irq/NMI handlers, all running on the same CPU,
- * and (2) Ensuring that the compiler does not  fold, spindle, or otherwise
+ * and (2) Ensuring that the compiler does not fold, spindle, or otherwise
  * mutilate accesses that either do not require ordering or that interact
  * with an explicit memory barrier or atomic instruction that provides the
  * required ordering.
@@ -291,6 +271,12 @@ static __always_inline void __write_once_size(volatile void *p, void *res, int s
  */
 #define READ_ONCE_NOCHECK(x) __READ_ONCE(x, 0)
 
+static __no_kasan_or_inline
+unsigned long read_word_at_a_time(const void *addr)
+{
+	return *(unsigned long *)addr;
+}
+
 #define WRITE_ONCE(x, val) \
 ({							\
 	union { typeof(x) __val; char __c[1]; } __u =	\
@@ -299,159 +285,29 @@ static __always_inline void __write_once_size(volatile void *p, void *res, int s
 	__u.__val;					\
 })
 
-/**
- * smp_cond_acquire() - Spin wait for cond with ACQUIRE ordering
- * @cond: boolean expression to wait for
- *
- * Equivalent to using smp_load_acquire() on the condition variable but employs
- * the control dependency of the wait to reduce the barrier on many platforms.
- *
- * The control dependency provides a LOAD->STORE order, the additional RMB
- * provides LOAD->LOAD order, together they provide LOAD->{LOAD,STORE} order,
- * aka. ACQUIRE.
- */
-#define smp_cond_acquire(cond)	do {		\
-	while (!(cond))				\
-		cpu_relax();			\
-	smp_rmb(); /* ctrl + rmb := acquire */	\
-} while (0)
-
 #endif /* __KERNEL__ */
 
+/*
+ * Force the compiler to emit 'sym' as a symbol, so that we can reference
+ * it from inline assembler. Necessary in case 'sym' could be inlined
+ * otherwise, or eliminated entirely due to lack of references that are
+ * visible to the compiler.
+ */
+#define __ADDRESSABLE(sym) \
+	static void * __section(.discard.addressable) __used \
+		__PASTE(__addressable_##sym, __LINE__) = (void *)&sym;
+
+/**
+ * offset_to_ptr - convert a relative memory offset to an absolute pointer
+ * @off:	the address of the 32-bit offset value
+ */
+static inline void *offset_to_ptr(const int *off)
+{
+	return (void *)((unsigned long)off + *off);
+}
+
 #endif /* __ASSEMBLY__ */
 
-#ifdef __KERNEL__
-/*
- * Allow us to mark functions as 'deprecated' and have gcc emit a nice
- * warning for each use, in hopes of speeding the functions removal.
- * Usage is:
- * 		int __deprecated foo(void)
- */
-#ifndef __deprecated
-# define __deprecated		/* unimplemented */
-#endif
-
-#ifdef MODULE
-#define __deprecated_for_modules __deprecated
-#else
-#define __deprecated_for_modules
-#endif
-
-#ifndef __must_check
-#define __must_check
-#endif
-
-#ifndef CONFIG_ENABLE_MUST_CHECK
-#undef __must_check
-#define __must_check
-#endif
-#ifndef CONFIG_ENABLE_WARN_DEPRECATED
-#undef __deprecated
-#undef __deprecated_for_modules
-#define __deprecated
-#define __deprecated_for_modules
-#endif
-
-/*
- * Allow us to avoid 'defined but not used' warnings on functions and data,
- * as well as force them to be emitted to the assembly file.
- *
- * As of gcc 3.4, static functions that are not marked with attribute((used))
- * may be elided from the assembly file.  As of gcc 3.4, static data not so
- * marked will not be elided, but this may change in a future gcc version.
- *
- * NOTE: Because distributions shipped with a backported unit-at-a-time
- * compiler in gcc 3.3, we must define __used to be __attribute__((used))
- * for gcc >=3.3 instead of 3.4.
- *
- * In prior versions of gcc, such functions and data would be emitted, but
- * would be warned about except with attribute((unused)).
- *
- * Mark functions that are referenced only in inline assembly as __used so
- * the code is emitted even though it appears to be unreferenced.
- */
-#ifndef __used
-# define __used			/* unimplemented */
-#endif
-
-#ifndef __maybe_unused
-# define __maybe_unused		/* unimplemented */
-#endif
-
-#ifndef __always_unused
-# define __always_unused	/* unimplemented */
-#endif
-
-#ifndef noinline
-#define noinline
-#endif
-
-/*
- * Rather then using noinline to prevent stack consumption, use
- * noinline_for_stack instead.  For documentation reasons.
- */
-#define noinline_for_stack noinline
-
-#ifndef __always_inline
-#define __always_inline inline
-#endif
-
-#endif /* __KERNEL__ */
-
-/*
- * From the GCC manual:
- *
- * Many functions do not examine any values except their arguments,
- * and have no effects except the return value.  Basically this is
- * just slightly more strict class than the `pure' attribute above,
- * since function is not allowed to read global memory.
- *
- * Note that a function that has pointer arguments and examines the
- * data pointed to must _not_ be declared `const'.  Likewise, a
- * function that calls a non-`const' function usually must not be
- * `const'.  It does not make sense for a `const' function to return
- * `void'.
- */
-#ifndef __attribute_const__
-# define __attribute_const__	/* unimplemented */
-#endif
-
-/*
- * Tell gcc if a function is cold. The compiler will assume any path
- * directly leading to the call is unlikely.
- */
-
-#ifndef __cold
-#define __cold
-#endif
-
-/* Simple shorthand for a section definition */
-#ifndef __section
-# define __section(S) __attribute__ ((__section__(#S)))
-#endif
-
-#ifndef __visible
-#define __visible
-#endif
-
-/*
- * Assume alignment of return value.
- */
-#ifndef __assume_aligned
-#define __assume_aligned(a, ...)
-#endif
-
-
-/* Are two types/vars the same type (ignoring qualifiers)? */
-#ifndef __same_type
-# define __same_type(a, b) __builtin_types_compatible_p(typeof(a), typeof(b))
-#endif
-
-/* Is this type a native word size -- useful for atomic operations */
-#ifndef __native_word
-# define __native_word(t) (sizeof(t) == sizeof(char) || sizeof(t) == sizeof(short) || sizeof(t) == sizeof(int) || sizeof(t) == sizeof(long))
-#endif
-
 /* Compile time object size, -1 for unknown */
 #ifndef __compiletime_object_size
 # define __compiletime_object_size(obj) -1
@@ -461,29 +317,14 @@ static __always_inline void __write_once_size(volatile void *p, void *res, int s
 #endif
 #ifndef __compiletime_error
 # define __compiletime_error(message)
-/*
- * Sparse complains of variable sized arrays due to the temporary variable in
- * __compiletime_assert. Unfortunately we can't just expand it out to make
- * sparse see a constant array size without breaking compiletime_assert on old
- * versions of GCC (e.g. 4.2.4), so hide the array from sparse altogether.
- */
-# ifndef __CHECKER__
-#  define __compiletime_error_fallback(condition) \
-	do { ((void)sizeof(char[1 - 2 * condition])); } while (0)
-# endif
-#endif
-#ifndef __compiletime_error_fallback
-# define __compiletime_error_fallback(condition) do { } while (0)
 #endif
 
 #ifdef __OPTIMIZE__
 # define __compiletime_assert(condition, msg, prefix, suffix)		\
 	do {								\
-		bool __cond = !(condition);				\
 		extern void prefix ## suffix(void) __compiletime_error(msg); \
-		if (__cond)						\
+		if (!(condition))					\
 			prefix ## suffix();				\
-		__compiletime_error_fallback(__cond);			\
 	} while (0)
 #else
 # define __compiletime_assert(condition, msg, prefix, suffix) do { } while (0)
@@ -502,58 +343,13 @@ static __always_inline void __write_once_size(volatile void *p, void *res, int s
  * compiler has support to do so.
  */
 #define compiletime_assert(condition, msg) \
-	_compiletime_assert(condition, msg, __compiletime_assert_, __LINE__)
+	_compiletime_assert(condition, msg, __compiletime_assert_, __COUNTER__)
 
 #define compiletime_assert_atomic_type(t)				\
 	compiletime_assert(__native_word(t),				\
 		"Need native word sized stores/loads for atomicity.")
 
-/*
- * Prevent the compiler from merging or refetching accesses.  The compiler
- * is also forbidden from reordering successive instances of ACCESS_ONCE(),
- * but only when the compiler is aware of some particular ordering.  One way
- * to make the compiler aware of ordering is to put the two invocations of
- * ACCESS_ONCE() in different C statements.
- *
- * ACCESS_ONCE will only work on scalar types. For union types, ACCESS_ONCE
- * on a union member will work as long as the size of the member matches the
- * size of the union and the size is smaller than word size.
- *
- * The major use cases of ACCESS_ONCE used to be (1) Mediating communication
- * between process-level code and irq/NMI handlers, all running on the same CPU,
- * and (2) Ensuring that the compiler does not  fold, spindle, or otherwise
- * mutilate accesses that either do not require ordering or that interact
- * with an explicit memory barrier or atomic instruction that provides the
- * required ordering.
- *
- * If possible use READ_ONCE()/WRITE_ONCE() instead.
- */
-#define __ACCESS_ONCE(x) ({ \
-	 __maybe_unused typeof(x) __var = (__force typeof(x)) 0; \
-	(volatile typeof(x) *)&(x); })
-#define ACCESS_ONCE(x) (*__ACCESS_ONCE(x))
+/* &a[0] degrades to a pointer: a different type from an array */
+#define __must_be_array(a)	BUILD_BUG_ON_ZERO(__same_type((a), &(a)[0]))
 
-/**
- * lockless_dereference() - safely load a pointer for later dereference
- * @p: The pointer to load
- *
- * Similar to rcu_dereference(), but for situations where the pointed-to
- * object's lifetime is managed by something other than RCU.  That
- * "something other" might be reference counting or simple immortality.
- */
-#define lockless_dereference(p) \
-({ \
-	typeof(p) _________p1 = READ_ONCE(p); \
-	smp_read_barrier_depends(); /* Dependency order vs. p above. */ \
-	(_________p1); \
-})
-
-/* Ignore/forbid kprobes attach on very low level functions marked by this attribute: */
-#ifdef CONFIG_KPROBES
-# define __kprobes	__attribute__((__section__(".kprobes.text")))
-# define nokprobe_inline	__always_inline
-#else
-# define __kprobes
-# define nokprobe_inline	inline
-#endif
 #endif /* __LINUX_COMPILER_H */