linux内核系统调用学习5：SYSCALL_DEFINE＜0-6＞

最新推荐文章于 2024-07-18 13:34:49 发布

千册

最新推荐文章于 2024-07-18 13:34:49 发布

阅读量1.1k

点赞数 1

CC 4.0 BY-SA版权

分类专栏： linux内核文章标签： linux

本文链接：https://blog.csdn.net/yueni_zhao/article/details/131932910

linux内核专栏收录该内容

88 篇文章

订阅专栏

文章详细介绍了Linux内核中系统调用的宏定义方式，如SYSCALL_DEFINE0到SYSCALL_DEFINE6，用于创建不同参数数量的系统调用。这些宏定义在include/linux/syscalls.h文件中，限制了系统调用的最大参数数量为6。同时，文章提到了__MAP宏系列用于处理系统调用的参数，以及SYSCALL_METADATA宏与CONFIG_FTRACE_SYSCALLS配置相关的trace事件功能。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

系统调用最大参数是6，由下面这个宏定义，位于文件include\linux\syscalls.h

#define SYSCALL_DEFINE_MAXARGS	6

SYSCALL_DEFINE0(fork)

fork：系统调用名。

SYSCALL_DEFINE1(set_tid_address, int __user *, tidptr)

set_tid_address：系统调用名

int __user *：第一个参数类型

tidptr：第一个参数。

注意参数类型和参数名之间是用逗号隔开的。后面的2-6也是如此。

COMPAT_SYSCALL_DEFINE2(stat64, const char __user *, filename,
		struct compat_stat64 __user *, statbuf)

SYSCALL_DEFINE3(cacheflush,
		void __user *, addr,
		unsigned long, bytes,
		int, cache)

/*
 * The following function implements the controller interface for
 * the eventpoll file that enables the insertion/removal/change of
 * file descriptors inside the interest set.
 */
SYSCALL_DEFINE4(epoll_ctl, int, epfd, int, op, int, fd,
		struct epoll_event __user *, event)

SYSCALL_DEFINE5(fsconfig,
		int, fd,
		unsigned int, cmd,
		const char __user *, _key,
		const void __user *, _value,
		int, aux)

SYSCALL_DEFINE6(mmap, unsigned long, addr, unsigned long, len,
		unsigned long, prot, unsigned long, flags,
		unsigned long, fd, unsigned long, off)

#define SYSCALL_DEFINE0(sname)					\
	SYSCALL_METADATA(_##sname, 0);				\
	asmlinkage long sys_##sname(void);			\
	ALLOW_ERROR_INJECTION(sys_##sname, ERRNO);		\
	asmlinkage long sys_##sname(void)

#define SYSCALL_DEFINE1(name, ...) SYSCALL_DEFINEx(1, _##name, __VA_ARGS__)
#define SYSCALL_DEFINE2(name, ...) SYSCALL_DEFINEx(2, _##name, __VA_ARGS__)
#define SYSCALL_DEFINE3(name, ...) SYSCALL_DEFINEx(3, _##name, __VA_ARGS__)
#define SYSCALL_DEFINE4(name, ...) SYSCALL_DEFINEx(4, _##name, __VA_ARGS__)
#define SYSCALL_DEFINE5(name, ...) SYSCALL_DEFINEx(5, _##name, __VA_ARGS__)
#define SYSCALL_DEFINE6(name, ...) SYSCALL_DEFINEx(6, _##name, __VA_ARGS__)

#define SYSCALL_DEFINEx(x, sname, ...)				\
	SYSCALL_METADATA(sname, x, __VA_ARGS__)			\
	__SYSCALL_DEFINEx(x, sname, __VA_ARGS__)

#define __SYSCALL_DEFINEx(x, name, ...)					\
	__diag_push();							\
	__diag_ignore(GCC, 8, "-Wattribute-alias",			\
		      "Type aliasing is used to sanitize syscall arguments");\
	asmlinkage long sys##name(__MAP(x,__SC_DECL,__VA_ARGS__))	\
		__attribute__((alias(__stringify(__se_sys##name))));	\
	ALLOW_ERROR_INJECTION(sys##name, ERRNO);			\
	static inline long __do_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__));\
	asmlinkage long __se_sys##name(__MAP(x,__SC_LONG,__VA_ARGS__));	\
	asmlinkage long __se_sys##name(__MAP(x,__SC_LONG,__VA_ARGS__))	\
	{								\
		long ret = __do_sys##name(__MAP(x,__SC_CAST,__VA_ARGS__));\
		__MAP(x,__SC_TEST,__VA_ARGS__);				\
		__PROTECT(x, ret,__MAP(x,__SC_ARGS,__VA_ARGS__));	\
		return ret;						\
	}								\
	__diag_pop();							\
	static inline long __do_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__))

然后看看__MAP宏系列宏

/*
 * __MAP - apply a macro to syscall arguments
 * __MAP(n, m, t1, a1, t2, a2, ..., tn, an) will expand to
 *    m(t1, a1), m(t2, a2), ..., m(tn, an)
 * The first argument must be equal to the amount of type/name
 * pairs given.  Note that this list of pairs (i.e. the arguments
 * of __MAP starting at the third one) is in the same format as
 * for SYSCALL_DEFINE<n>/COMPAT_SYSCALL_DEFINE<n>
 */
#define __MAP0(m,...)
#define __MAP1(m,t,a,...) m(t,a)
#define __MAP2(m,t,a,...) m(t,a), __MAP1(m,__VA_ARGS__)
#define __MAP3(m,t,a,...) m(t,a), __MAP2(m,__VA_ARGS__)
#define __MAP4(m,t,a,...) m(t,a), __MAP3(m,__VA_ARGS__)
#define __MAP5(m,t,a,...) m(t,a), __MAP4(m,__VA_ARGS__)
#define __MAP6(m,t,a,...) m(t,a), __MAP5(m,__VA_ARGS__)
#define __MAP(n,...) __MAP##n(__VA_ARGS__)

__PROTECT宏

#define __PROTECT(...) asmlinkage_protect(__VA_ARGS__)

asmlinkage_protect宏位于文件include\linux\linkage.h

#ifndef __ASSEMBLY__
#ifndef asmlinkage_protect
# define asmlinkage_protect(n, ret, args...)	do { } while (0)
#endif
#endif

SYSCALL_METADATA宏

这个宏由CONFIG_FTRACE_SYSCALLS决定，定义如下

#ifdef CONFIG_FTRACE_SYSCALLS
#define __SC_STR_ADECL(t, a)	#a
#define __SC_STR_TDECL(t, a)	#t

extern struct trace_event_class event_class_syscall_enter;
extern struct trace_event_class event_class_syscall_exit;
extern struct trace_event_functions enter_syscall_print_funcs;
extern struct trace_event_functions exit_syscall_print_funcs;

#define SYSCALL_TRACE_ENTER_EVENT(sname)				\
	static struct syscall_metadata __syscall_meta_##sname;		\
	static struct trace_event_call __used				\
	  event_enter_##sname = {					\
		.class			= &event_class_syscall_enter,	\
		{							\
			.name                   = "sys_enter"#sname,	\
		},							\
		.event.funcs            = &enter_syscall_print_funcs,	\
		.data			= (void *)&__syscall_meta_##sname,\
		.flags                  = TRACE_EVENT_FL_CAP_ANY,	\
	};								\
	static struct trace_event_call __used				\
	  __attribute__((section("_ftrace_events")))			\
	 *__event_enter_##sname = &event_enter_##sname;

#define SYSCALL_TRACE_EXIT_EVENT(sname)					\
	static struct syscall_metadata __syscall_meta_##sname;		\
	static struct trace_event_call __used				\
	  event_exit_##sname = {					\
		.class			= &event_class_syscall_exit,	\
		{							\
			.name                   = "sys_exit"#sname,	\
		},							\
		.event.funcs		= &exit_syscall_print_funcs,	\
		.data			= (void *)&__syscall_meta_##sname,\
		.flags                  = TRACE_EVENT_FL_CAP_ANY,	\
	};								\
	static struct trace_event_call __used				\
	  __attribute__((section("_ftrace_events")))			\
	*__event_exit_##sname = &event_exit_##sname;

#define SYSCALL_METADATA(sname, nb, ...)			\
	static const char *types_##sname[] = {			\
		__MAP(nb,__SC_STR_TDECL,__VA_ARGS__)		\
	};							\
	static const char *args_##sname[] = {			\
		__MAP(nb,__SC_STR_ADECL,__VA_ARGS__)		\
	};							\
	SYSCALL_TRACE_ENTER_EVENT(sname);			\
	SYSCALL_TRACE_EXIT_EVENT(sname);			\
	static struct syscall_metadata __used			\
	  __syscall_meta_##sname = {				\
		.name 		= "sys"#sname,			\
		.syscall_nr	= -1,	/* Filled in at boot */	\
		.nb_args 	= nb,				\
		.types		= nb ? types_##sname : NULL,	\
		.args		= nb ? args_##sname : NULL,	\
		.enter_event	= &event_enter_##sname,		\
		.exit_event	= &event_exit_##sname,		\
		.enter_fields	= LIST_HEAD_INIT(__syscall_meta_##sname.enter_fields), \
	};							\
	static struct syscall_metadata __used			\
	  __attribute__((section("__syscalls_metadata")))	\
	 *__p_syscall_meta_##sname = &__syscall_meta_##sname;

static inline int is_syscall_trace_event(struct trace_event_call *tp_event)
{
	return tp_event->class == &event_class_syscall_enter ||
	       tp_event->class == &event_class_syscall_exit;
}

#else
#define SYSCALL_METADATA(sname, nb, ...)

static inline int is_syscall_trace_event(struct trace_event_call *tp_event)
{
	return 0;
}
#endif

CONFIG_FTRACE_SYSCALLS从名字上看应该是和trace命令相关的功能。