generic kernel_execve()

based mostly on arm and alpha versions.  Architectures can define
__ARCH_WANT_KERNEL_EXECVE and use it, provided that
	* they have working current_pt_regs(), even for kernel threads.
	* kernel_thread-spawned threads do have space for pt_regs
in the normal location.  Normally that's as simple as switching to
generic kernel_thread() and making sure that kernel threads do *not*
go through return from syscall path; call the payload from equivalent
of ret_from_fork if we are in a kernel thread (or just have separate
ret_from_kernel_thread and make copy_thread() use it instead of
ret_from_fork in kernel thread case).
	* they have ret_from_kernel_execve(); it is called after
successful do_execve() done by kernel_execve() and gets normal
pt_regs location passed to it as argument.  It's essentially
a longjmp() analog - it should set sp, etc. to the situation
expected at the return for syscall and go there.  Eventually
the need for that sucker will disappear, but that'll take some
surgery on kernel_thread() payloads.

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>

diff --git a/fs/exec.c b/fs/exec.c
index d7f9e14..48c5251 100644 (file)
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -2318,3 +2318,25 @@ int dump_seek(struct file *file, loff_t off)
        return ret;
 }
 EXPORT_SYMBOL(dump_seek);
+
+#ifdef __ARCH_WANT_KERNEL_EXECVE
+int kernel_execve(const char *filename,
+                 const char *const argv[],
+                 const char *const envp[])
+{
+       struct pt_regs *p = current_pt_regs();
+       int ret;
+
+       ret = do_execve(filename,
+                       (const char __user *const __user *)argv,
+                       (const char __user *const __user *)envp, p);
+       if (ret < 0)
+               return ret;
+
+       /*
+        * We were successful.  We won't be returning to our caller, but
+        * instead to user space by manipulating the kernel stack.
+        */
+       ret_from_kernel_execve(p);
+}
+#endif

diff --git a/include/linux/binfmts.h b/include/linux/binfmts.h
index 8938bea..f9c9d08 100644 (file)
--- a/include/linux/binfmts.h
+++ b/include/linux/binfmts.h
@@ -19,6 +19,7 @@ struct pt_regs;
 
 #ifdef __KERNEL__
 #include <linux/sched.h>
+#include <linux/unistd.h>
 #include <asm/exec.h>
 
 #define CORENAME_MAX_SIZE 128
@@ -137,5 +138,9 @@ extern void do_coredump(long signr, int exit_code, struct pt_regs *regs);
 extern void set_binfmt(struct linux_binfmt *new);
 extern void free_bprm(struct linux_binprm *);
 
+#ifdef __ARCH_WANT_KERNEL_EXECVE
+extern void ret_from_kernel_execve(struct pt_regs *normal) __noreturn;
+#endif
+
 #endif /* __KERNEL__ */
 #endif /* _LINUX_BINFMTS_H */