快速鏈接:
.
👉👉👉 個(gè)人博客筆記導(dǎo)讀目錄(全部) 👈👈👈


相關(guān)鏈接:
optee中utee syscall的實(shí)現(xiàn)(系統(tǒng)調(diào)用實(shí)現(xiàn))

文章目錄

• • • • 1、系統(tǒng)調(diào)用在Linux Kernel中的map表(系統(tǒng)調(diào)用的數(shù)組)
      • 2、系統(tǒng)調(diào)用的函數(shù)在Kernel中的實(shí)現(xiàn)
      • 3、系統(tǒng)調(diào)用的流程
      • 4、總結(jié)

1、系統(tǒng)調(diào)用在Linux Kernel中的map表(系統(tǒng)調(diào)用的數(shù)組)

在sys.c中定義了__SYSCALL宏

(kernel-4.19/arch/arm64/kernel/sys.c)#define __SYSCALL(nr, sym) asmlinkage long __arm64_##sym(const struct pt_regs *);

例如：

• __SYSCALL(__NR_flock, sys_flock)，其實(shí)就是定義__arm64_sys_flock函數(shù)
• __SC_COMP(__NR_ioctl, sys_ioctl, compat_sys_ioctl)，其實(shí)就是定義__arm64_compat_sys_ioctl函數(shù)

在sys.c中定義并初始化了系統(tǒng)調(diào)用的tab表

(kernel-4.19/arch/arm64/kernel/sys.c)#undef __SYSCALL #define __SYSCALL(nr, sym) [nr] = __arm64_##sym,const syscall_fn_t sys_call_table[__NR_syscalls] = {[0 ... __NR_syscalls - 1] = __arm64_sys_ni_syscall,#include <asm/unistd.h>};

剖析這段代碼，將asm/unistd.h引進(jìn)來了，其實(shí)等價(jià)于下面這句

(kernel-4.19/arch/arm64/kernel/sys.c)const syscall_fn_t sys_call_table[__NR_syscalls] = {[0 ... __NR_syscalls - 1] = __arm64_sys_ni_syscall,__arm64_compat_sys_io_setup,__arm64_sys_io_destroy,__arm64_compat_sys_io_submit......};

2、系統(tǒng)調(diào)用的函數(shù)在Kernel中的實(shí)現(xiàn)

SYSCALL_DEFINE1(arm64_personality, unsigned int, personality) {if (personality(personality) == PER_LINUX32 &&!system_supports_32bit_el0())return -EINVAL;return ksys_personality(personality); }#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__)

在kernel中使用SYSCALL_DEFINEx定義的地方，都是在定義系統(tǒng)調(diào)用函數(shù)，例如：
這里定義的SYSCALL_DEFINE1(setgid, gid_t, gid)，其實(shí)就是定義__arm64_sys_setgid

SYSCALL_DEFINE1(setgid, gid_t, gid){return __sys_setgid(gid);}

3、系統(tǒng)調(diào)用的流程

由于Userspace中C語(yǔ)言使用的libc庫(kù)代碼，我們?cè)趉ernel中是看不到，所以就不做具體分析了。但可以知道的是，該系統(tǒng)調(diào)用的庫(kù)中，最終是要調(diào)用到svc指令的，使cpu陷入svc異常，進(jìn)而跳轉(zhuǎn)到Linux Kernel中的el0_svc向量表中。

如下展示了系統(tǒng)調(diào)用進(jìn)入Linux Kernel后的具體流程：
el0_svc–> el0_svc_handler() --> el0_svc_common() --> invoke_syscall() --> syscall_fn(), syscall_fn指向系統(tǒng)調(diào)用tab表中的具體函數(shù)

(kernel-4.19/arch/arm64/kernel/entry.S)el0_svc:mov x0, spbl el0_svc_handlerb ret_to_userENDPROC(el0_svc) (kernel-4.19/arch/arm64/kernel/syscall.c) asmlinkage void el0_svc_handler(struct pt_regs *regs) {sve_user_discard();el0_svc_common(regs, regs->regs[8], __NR_syscalls, sys_call_table); }static void el0_svc_common(struct pt_regs *regs, int scno, int sc_nr,const syscall_fn_t syscall_table[]) {unsigned long flags = current_thread_info()->flags;regs->orig_x0 = regs->regs[0];regs->syscallno = scno;cortex_a76_erratum_1463225_svc_handler();local_daif_restore(DAIF_PROCCTX);user_exit();if (has_syscall_work(flags)) {/* set default errno for user-issued syscall(-1) */if (scno == NO_SYSCALL)regs->regs[0] = -ENOSYS;scno = syscall_trace_enter(regs);if (scno == NO_SYSCALL)goto trace_exit;}invoke_syscall(regs, scno, sc_nr, syscall_table);/** The tracing status may have changed under our feet, so we have to* check again. However, if we were tracing entry, then we always trace* exit regardless, as the old entry assembly did.*/if (!has_syscall_work(flags) && !IS_ENABLED(CONFIG_DEBUG_RSEQ)) {local_daif_mask();flags = current_thread_info()->flags;if (!has_syscall_work(flags)) {/** We're off to userspace, where interrupts are* always enabled after we restore the flags from* the SPSR.*/trace_hardirqs_on();return;}local_daif_restore(DAIF_PROCCTX);}trace_exit:syscall_trace_exit(regs); }static void invoke_syscall(struct pt_regs *regs, unsigned int scno,unsigned int sc_nr,const syscall_fn_t syscall_table[]) {long ret;if (scno < sc_nr) {syscall_fn_t syscall_fn;syscall_fn = syscall_table[array_index_nospec(scno, sc_nr)];ret = __invoke_syscall(regs, syscall_fn); //syscall_fn 就是tab表中的函數(shù)} else {ret = do_ni_syscall(regs, scno);}regs->regs[0] = ret; }static long __invoke_syscall(struct pt_regs *regs, syscall_fn_t syscall_fn) {return syscall_fn(regs); //調(diào)用tab表中的函數(shù) }

4、總結(jié)

• 系統(tǒng)調(diào)用在Kernel中的map表，都在 kernel-4.19/include/uapi/asm-generic/unistd.h 中，表的名字是：sys_call_table，表中成員的示例如下：

#define __NR_io_setup 0 __SC_COMP(__NR_io_setup, sys_io_setup, compat_sys_io_setup) #define __NR_io_destroy 1 __SYSCALL(__NR_io_destroy, sys_io_destroy) #define __NR_io_submit 2 __SC_COMP(__NR_io_submit, sys_io_submit, compat_sys_io_submit) #define __NR_io_cancel 3 __SYSCALL(__NR_io_cancel, sys_io_cancel) #define __NR_io_getevents 4 __SC_COMP(__NR_io_getevents, sys_io_getevents, compat_sys_io_getevents)/* fs/xattr.c */ #define __NR_setxattr 5 __SYSCALL(__NR_setxattr, sys_setxattr) #define __NR_lsetxattr 6 __SYSCALL(__NR_lsetxattr, sys_lsetxattr) #define __NR_fsetxattr 7 __SYSCALL(__NR_fsetxattr, sys_fsetxattr) #define __NR_getxattr 8 __SYSCALL(__NR_getxattr, sys_getxattr) #define __NR_lgetxattr 9 __SYSCALL(__NR_lgetxattr, sys_lgetxattr) ......

• 系統(tǒng)調(diào)用函數(shù)的定義，都是以SYSCALL_DEFINEx的宏定義的，例如:

SYSCALL_DEFINE1(setgid, gid_t, gid) {return __sys_setgid(gid); }SYSCALL_DEFINE1(sysctl, struct __sysctl_args __user *, args) {struct __sysctl_args tmp;size_t oldlen = 0;ssize_t result;if (copy_from_user(&tmp, args, sizeof(tmp)))return -EFAULT;if (tmp.oldval && !tmp.oldlenp)return -EFAULT;if (tmp.oldlenp && get_user(oldlen, tmp.oldlenp))return -EFAULT;result = do_sysctl(tmp.name, tmp.nlen, tmp.oldval, oldlen,tmp.newval, tmp.newlen);if (result >= 0) {oldlen = result;result = 0;}if (tmp.oldlenp && put_user(oldlen, tmp.oldlenp))return -EFAULT;return result; }

總結(jié)

以上是生活随笔為你收集整理的Linux Kernel中的系统调用分析的全部?jī)?nèi)容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網(wǎng)站內(nèi)容還不錯(cuò)，歡迎將生活随笔推薦給好友。