shinys000114/linux
1
0
Fork 0
mirror of https://github.com/hardkernel/linux.git synced 2026-03-25 20:10:23 +09:00
Code Issues Packages Projects Releases Wiki Activity
Files
23525fc0ea623006eff32bd6df8753b3d24f5d2b
linux/include/linux/compiler.h
Linus Torvalds f0be4c5dc2 minmax: improve macro expansion and type checking 
[ Upstream commit 22f5468731491e53356ba7c028f0fdea20b18e2c ]

This clarifies the rules for min()/max()/clamp() type checking and makes
them a much more efficient macro expansion.

In particular, we now look at the type and range of the inputs to see
whether they work together, generating a mask of acceptable comparisons,
and then just verifying that the inputs have a shared case:

 - an expression with a signed type can be used for
    (1) signed comparisons
    (2) unsigned comparisons if it is statically known to have a
        non-negative value

 - an expression with an unsigned type can be used for
    (3) unsigned comparison
    (4) signed comparisons if the type is smaller than 'int' and thus
        the C integer promotion rules will make it signed anyway

Here rule (1) and (3) are obvious, and rule (2) is important in order to
allow obvious trivial constants to be used together with unsigned
values.

Rule (4) is not necessarily a good idea, but matches what we used to do,
and we have extant cases of this situation in the kernel.  Notably with
bcachefs having an expression like

	min(bch2_bucket_sectors_dirty(a), ca->mi.bucket_size)

where bch2_bucket_sectors_dirty() returns an 's64', and
'ca->mi.bucket_size' is of type 'u16'.

Technically that bcachefs comparison is clearly sensible on a C type
level, because the 'u16' will go through the normal C integer promotion,
and become 'int', and then we're comparing two signed values and
everything looks sane.

However, it's not entirely clear that a 'min(s64,u16)' operation makes a
lot of conceptual sense, and it's possible that we will remove rule (4).
After all, the _reason_ we have these complicated type checks is exactly
that the C type promotion rules are not very intuitive.

But at least for now the rule is in place for backwards compatibility.

Also note that rule (2) existed before, but is hugely relaxed by this
commit.  It used to be true only for the simplest compile-time
non-negative integer constants.  The new macro model will allow cases
where the compiler can trivially see that an expression is non-negative
even if it isn't necessarily a constant.

For example, the amdgpu driver does

	min_t(size_t, sizeof(fru_info->serial), pia[addr] & 0x3F));

because our old 'min()' macro would see that 'pia[addr] & 0x3F' is of
type 'int' and clearly not a C constant expression, so doing a 'min()'
with a 'size_t' is a signedness violation.

Our new 'min()' macro still sees that 'pia[addr] & 0x3F' is of type
'int', but is smart enough to also see that it is clearly non-negative,
and thus would allow that case without any complaints.

Cc: Arnd Bergmann <arnd@kernel.org>
Cc: David Laight <David.Laight@aculab.com>
Cc: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Eliav Farber <farbere@amazon.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2025-10-02 13:42:55 +02:00

265 lines
8.1 KiB
C
Raw Blame History

/* SPDX-License-Identifier: GPL-2.0 */
#ifndef __LINUX_COMPILER_H
#define __LINUX_COMPILER_H
#include <linux/compiler_types.h>
#ifndef __ASSEMBLY__
#ifdef __KERNEL__
/*
* Note: DISABLE_BRANCH_PROFILING can be used by special lowlevel code
* to disable branch tracing on a per file basis.
*/
void ftrace_likely_update(struct ftrace_likely_data *f, int val,
int expect, int is_constant);
#if defined(CONFIG_TRACE_BRANCH_PROFILING) \
&& !defined(DISABLE_BRANCH_PROFILING) && !defined(__CHECKER__)
#define likely_notrace(x) __builtin_expect(!!(x), 1)
#define unlikely_notrace(x) __builtin_expect(!!(x), 0)
#define __branch_check__(x, expect, is_constant) ({ \
long ______r; \
static struct ftrace_likely_data \
__aligned(4) \
__section("_ftrace_annotated_branch") \
______f = { \
.data.func = __func__, \
.data.file = __FILE__, \
.data.line = __LINE__, \
}; \
______r = __builtin_expect(!!(x), expect); \
ftrace_likely_update(&______f, ______r, \
expect, is_constant); \
______r; \
})
/*
* Using __builtin_constant_p(x) to ignore cases where the return
* value is always the same. This idea is taken from a similar patch
* written by Daniel Walker.
*/
# ifndef likely
# define likely(x) (__branch_check__(x, 1, __builtin_constant_p(x)))
# endif
# ifndef unlikely
# define unlikely(x) (__branch_check__(x, 0, __builtin_constant_p(x)))
# endif
#ifdef CONFIG_PROFILE_ALL_BRANCHES
/*
* "Define 'is'", Bill Clinton
* "Define 'if'", Steven Rostedt
*/
#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
# define likely(x) __builtin_expect(!!(x), 1)
# define unlikely(x) __builtin_expect(!!(x), 0)
# define likely_notrace(x) likely(x)
# define unlikely_notrace(x) unlikely(x)
#endif
/* Optimization barrier */
#ifndef barrier
/* The "volatile" is due to gcc bugs */
# define barrier() __asm__ __volatile__("": : :"memory")
#endif
#ifndef barrier_data
/*
* This version is i.e. to prevent dead stores elimination on @ptr
* where gcc and llvm may behave differently when otherwise using
* normal barrier(): while gcc behavior gets along with a normal
* barrier(), llvm needs an explicit input variable to be assumed
* clobbered. The issue is as follows: while the inline asm might
* access any memory it wants, the compiler could have fit all of
* @ptr into memory registers instead, and since @ptr never escaped
* from that, it proved that the inline asm wasn't touching any of
* it. This version works well with both compilers, i.e. we're telling
* the compiler that the inline asm absolutely may see the contents
* of @ptr. See also: https://llvm.org/bugs/show_bug.cgi?id=15495
*/
# define barrier_data(ptr) __asm__ __volatile__("": :"r"(ptr) :"memory")
#endif
/* workaround for GCC PR82365 if needed */
#ifndef barrier_before_unreachable
# define barrier_before_unreachable() do { } while (0)
#endif
/* Unreachable code */
#ifdef CONFIG_OBJTOOL
/*
* 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 __stringify_label(n) #n
#define __annotate_unreachable(c) ({ \
asm volatile(__stringify_label(c) ":\n\t" \
".pushsection .discard.unreachable\n\t" \
".long " __stringify_label(c) "b - .\n\t" \
".popsection\n\t" : : "i" (c)); \
})
#define annotate_unreachable() __annotate_unreachable(__COUNTER__)
/* Annotate a C jump table to allow objtool to follow the code flow */
#define __annotate_jump_table __section(".rodata..c_jump_table")
#else /* !CONFIG_OBJTOOL */
#define annotate_unreachable()
#define __annotate_jump_table
#endif /* CONFIG_OBJTOOL */
#ifndef unreachable
# 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 \
__attribute__((__section__("___kentry+" #sym))) \
= (unsigned long)&sym;
#endif
#ifndef RELOC_HIDE
# define RELOC_HIDE(ptr, off) \
({ unsigned long __ptr; \
__ptr = (unsigned long) (ptr); \
(typeof(ptr)) (__ptr + (off)); })
#endif
#define absolute_pointer(val) RELOC_HIDE((void *)(val), 0)
#ifndef OPTIMIZER_HIDE_VAR
/* 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. */
#ifndef __UNIQUE_ID
# define __UNIQUE_ID(prefix) __PASTE(__PASTE(__UNIQUE_ID_, prefix), __LINE__)
#endif
/**
* 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) \
({ \
__unqual_scalar_typeof(({ expr; })) __v = ({ \
__kcsan_disable_current(); \
expr; \
}); \
__kcsan_enable_current(); \
__v; \
})
#endif /* __KERNEL__ */
/**
* 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 CONFIG_64BIT
#define ARCH_SEL(a,b) a
#else
#define ARCH_SEL(a,b) b
#endif
/*
* 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, __attrs) \
static void * __used __attrs \
__UNIQUE_ID(__PASTE(__addressable_,sym)) = (void *)&sym;
#define __ADDRESSABLE(sym) \
___ADDRESSABLE(sym, __section(".discard.addressable"))
/* &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]))
/*
* Whether 'type' is a signed type or an unsigned type. Supports scalar types,
* bool and also pointer types.
*/
#define is_signed_type(type) (((type)(-1)) < (__force type)1)
#define is_unsigned_type(type) (!is_signed_type(type))
/*
* Useful shorthand for "is this condition known at compile-time?"
*
* Note that the condition may involve non-constant values,
* but the compiler may know enough about the details of the
* values to determine that the condition is statically true.
*/
#define statically_true(x) (__builtin_constant_p(x) && (x))
/*
* This is needed in functions which generate the stack canary, see
* arch/x86/kernel/smpboot.c::start_secondary() for an example.
*/
#define prevent_tail_call_optimization() mb()
#include <asm/rwonce.h>
#endif /* __LINUX_COMPILER_H */
Reference in New Issue View Git Blame Copy Permalink