我在x86_64上尝试过
针对94836ecf1e7378b64d37624fbb81fe48fbd4c772进行了修补:(也在此处https://github.com/pskocik/linux/tree/supersyscall)
diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl
index 5aef183e2f85..8df2e98eb403 100644
--- a/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/arch/x86/entry/syscalls/syscall_64.tbl
@@ -339,6 +339,7 @@
330 common pkey_alloc sys_pkey_alloc
331 common pkey_free sys_pkey_free
332 common statx sys_statx
+333 common supersyscall sys_supersyscall
#
# x32-specific system call numbers start at 512 to avoid cache impact
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 980c3c9b06f8..c61c14e3ff4e 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -905,5 +905,20 @@ asmlinkage long sys_pkey_alloc(unsigned long flags, unsigned long init_val);
asmlinkage long sys_pkey_free(int pkey);
asmlinkage long sys_statx(int dfd, const char __user *path, unsigned flags,
unsigned mask, struct statx __user *buffer);
-
#endif
+
+struct supersyscall_args {
+ unsigned call_nr;
+ long args[6];
+};
+#define SUPERSYSCALL__abort_on_failure 0
+#define SUPERSYSCALL__continue_on_failure 1
+/*#define SUPERSYSCALL__lock_something 2?*/
+
+
+asmlinkage
+long
+sys_supersyscall(long* Rets,
+ struct supersyscall_args *Args,
+ int Nargs,
+ int Flags);
diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h
index a076cf1a3a23..56184b84530f 100644
--- a/include/uapi/asm-generic/unistd.h
+++ b/include/uapi/asm-generic/unistd.h
@@ -732,9 +732,11 @@ __SYSCALL(__NR_pkey_alloc, sys_pkey_alloc)
__SYSCALL(__NR_pkey_free, sys_pkey_free)
#define __NR_statx 291
__SYSCALL(__NR_statx, sys_statx)
+#define __NR_supersyscall 292
+__SYSCALL(__NR_supersyscall, sys_supersyscall)
#undef __NR_syscalls
-#define __NR_syscalls 292
+#define __NR_syscalls (__NR_supersyscall+1)
/*
* All syscalls below here should go away really,
diff --git a/init/Kconfig b/init/Kconfig
index a92f27da4a27..25f30bf0ebbb 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -2184,4 +2184,9 @@ config ASN1
inform it as to what tags are to be expected in a stream and what
functions to call on what tags.
+config SUPERSYSCALL
+ bool
+ help
+ System call for batching other system calls
+
source "kernel/Kconfig.locks"
diff --git a/kernel/Makefile b/kernel/Makefile
index b302b4731d16..4d86bcf90f90 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -9,7 +9,7 @@ obj-y = fork.o exec_domain.o panic.o \
extable.o params.o \
kthread.o sys_ni.o nsproxy.o \
notifier.o ksysfs.o cred.o reboot.o \
- async.o range.o smpboot.o ucount.o
+ async.o range.o smpboot.o ucount.o supersyscall.o
obj-$(CONFIG_MULTIUSER) += groups.o
diff --git a/kernel/supersyscall.c b/kernel/supersyscall.c
new file mode 100644
index 000000000000..d7fac5d3f970
--- /dev/null
+++ b/kernel/supersyscall.c
@@ -0,0 +1,83 @@
+#include <linux/syscalls.h>
+#include <linux/uaccess.h>
+#include <linux/compiler.h>
+#include <linux/sched/signal.h>
+
+/*TODO: do this properly*/
+/*#include <uapi/asm-generic/unistd.h>*/
+#ifndef __NR_syscalls
+# define __NR_syscalls (__NR_supersyscall+1)
+#endif
+
+#define uif(Cond) if(unlikely(Cond))
+#define lif(Cond) if(likely(Cond))
+
+
+typedef asmlinkage long (*sys_call_ptr_t)(unsigned long, unsigned long,
+ unsigned long, unsigned long,
+ unsigned long, unsigned long);
+extern const sys_call_ptr_t sys_call_table[];
+
+static bool
+syscall__failed(unsigned long Ret)
+{
+ return (Ret > -4096UL);
+}
+
+
+static bool
+syscall(unsigned Nr, long A[6])
+{
+ uif (Nr >= __NR_syscalls )
+ return -ENOSYS;
+ return sys_call_table[Nr](A[0], A[1], A[2], A[3], A[4], A[5]);
+}
+
+
+static int
+segfault(void const *Addr)
+{
+ struct siginfo info[1];
+ info->si_signo = SIGSEGV;
+ info->si_errno = 0;
+ info->si_code = 0;
+ info->si_addr = (void*)Addr;
+ return send_sig_info(SIGSEGV, info, current);
+ //return force_sigsegv(SIGSEGV, current);
+}
+
+asmlinkage long /*Ntried*/
+sys_supersyscall(long* Rets,
+ struct supersyscall_args *Args,
+ int Nargs,
+ int Flags)
+{
+ int i = 0, nfinished = 0;
+ struct supersyscall_args args; /*7 * sizeof(long) */
+
+ for (i = 0; i<Nargs; i++){
+ long ret;
+
+ uif (0!=copy_from_user(&args, Args+i, sizeof(args))){
+ segfault(&Args+i);
+ return nfinished;
+ }
+
+ ret = syscall(args.call_nr, args.args);
+ nfinished++;
+
+ if ((Flags & 1) == SUPERSYSCALL__abort_on_failure
+ && syscall__failed(ret))
+ return nfinished;
+
+
+ uif (0!=put_user(ret, Rets+1)){
+ segfault(Rets+i);
+ return nfinished;
+ }
+ }
+ return nfinished;
+
+}
+
+
diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c
index 8acef8576ce9..c544883d7a13 100644
--- a/kernel/sys_ni.c
+++ b/kernel/sys_ni.c
@@ -258,3 +258,5 @@ cond_syscall(sys_membarrier);
cond_syscall(sys_pkey_mprotect);
cond_syscall(sys_pkey_alloc);
cond_syscall(sys_pkey_free);
+
+cond_syscall(sys_supersyscall);
它似乎可行-我可以通过一个syscall向fd 1问候,向world fd 2问候:
#define _GNU_SOURCE
#include <unistd.h>
#include <sys/syscall.h>
#include <stdio.h>
struct supersyscall_args {
unsigned call_nr;
long args[6];
};
#define SUPERSYSCALL__abort_on_failure 0
#define SUPERSYSCALL__continue_on_failure 1
long
supersyscall(long* Rets,
struct supersyscall_args *Args,
int Nargs,
int Flags);
int main(int c, char**v)
{
puts("HELLO WORLD:");
long r=0;
struct supersyscall_args args[] = {
{SYS_write, {1, (long)"hello\n", 6 }},
{SYS_write, {2, (long)"world\n", 6 }},
};
long rets[sizeof args / sizeof args[0]];
r = supersyscall(rets,
args,
sizeof(rets)/sizeof(rets[0]),
0);
printf("r=%ld\n", r);
printf( 0>r ? "%m\n" : "\n");
puts("");
#if 1
#if SEGFAULT
r = supersyscall(0,
args,
sizeof(rets)/sizeof(rets[0]),
0);
printf("r=%ld\n", r);
printf( 0>r ? "%m\n" : "\n");
#endif
#endif
return 0;
}
long
supersyscall(long* Rets,
struct supersyscall_args *Args,
int Nargs,
int Flags)
{
return syscall(333, Rets, Args, Nargs, Flags);
}
基本上我正在使用:
long a_syscall(long, long, long, long, long, long);
作为通用的syscall原型,这似乎是x86_64上的工作方式,因此我的“超级”系统调用为:
struct supersyscall_args {
unsigned call_nr;
long args[6];
};
#define SUPERSYSCALL__abort_on_failure 0
#define SUPERSYSCALL__continue_on_failure 1
/*#define SUPERSYSCALL__lock_something 2?*/
asmlinkage
long
sys_supersyscall(long* Rets,
struct supersyscall_args *Args,
int Nargs,
int Flags);
它返回尝试的syscall数量(==Nargs
如果SUPERSYSCALL__continue_on_failure
通过了该标志,则返回>0 && <=Nargs
),并且在segfaults而不是通常的segfaults信号指示无法在内核空间和用户空间之间进行复制-EFAULT
。
我不知道这将如何移植到其他体系结构,但是在内核中包含类似的东西肯定会很好。
如果所有拱形都可行,那么我想可能会有一个用户空间包装器通过一些联合和宏来提供类型安全性(它可以根据syscall名称选择一个联合成员,然后所有联合都将转换为6个long或任何相当于6个long的dejour架构)。
batch
系统batch
调用嵌套到系统调用中,可以创建任意系统调用的任意深度的调用树。基本上,您可以将整个应用程序放入单个syscall中。