infrastructure for saner ret_from_kernel_thread semantics

* allow kernel_execve() leave the actual return to userland to
caller (selected by CONFIG_GENERIC_KERNEL_EXECVE).  Callers
updated accordingly.
* architecture that does select GENERIC_KERNEL_EXECVE in its
Kconfig should have its ret_from_kernel_thread() do this:
	call schedule_tail
	call the callback left for it by copy_thread(); if it ever
returns, that's because it has just done successful kernel_execve()
	jump to return from syscall
IOW, its only difference from ret_from_fork() is that it does call the
callback.
* such an architecture should also get rid of ret_from_kernel_execve()
and __ARCH_WANT_KERNEL_EXECVE

This is the last part of infrastructure patches in that area - from
that point on work on different architectures can live independently.

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

5 files changed, 27 insertions, 8 deletions

diff --git a/arch/Kconfig b/arch/Kconfig
index d397e11d167d..d27efb9bfafd 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -261,6 +261,9 @@ config ARCH_WANT_OLD_COMPAT_IPC
 config GENERIC_KERNEL_THREAD
 	bool
 
+config GENERIC_KERNEL_EXECVE
+	bool
+
 config HAVE_ARCH_SECCOMP_FILTER
 	bool
 	help
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 19439c75c5b2..727f0cd73921 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -827,7 +827,15 @@ asmlinkage long sys_fanotify_mark(int fanotify_fd, unsigned int flags,
 				  const char  __user *pathname);
 asmlinkage long sys_syncfs(int fd);
 
+#ifndef CONFIG_GENERIC_KERNEL_EXECVE
 int kernel_execve(const char *filename, const char *const argv[], const char *const envp[]);
+#else
+#define kernel_execve(filename, argv, envp) \
+	do_execve(filename, \
+		(const char __user *const __user *)argv, \
+		(const char __user *const __user *)envp, \
+		current_pt_regs())
+#endif
 
 
 asmlinkage long sys_perf_event_open(
diff --git a/init/main.c b/init/main.c
index a490ffecb7b9..02df2ddc5f83 100644
--- a/init/main.c
+++ b/init/main.c
@@ -69,6 +69,7 @@
 #include <linux/slab.h>
 #include <linux/perf_event.h>
 #include <linux/file.h>
+#include <linux/ptrace.h>
 
 #include <asm/io.h>
 #include <asm/bugs.h>
@@ -788,10 +789,10 @@ static void __init do_pre_smp_initcalls(void)
 		do_one_initcall(*fn);
 }
 
-static void run_init_process(const char *init_filename)
+static int run_init_process(const char *init_filename)
 {
 	argv_init[0] = init_filename;
-	kernel_execve(init_filename, argv_init, envp_init);
+	return kernel_execve(init_filename, argv_init, envp_init);
 }
 
 static void __init kernel_init_freeable(void);
@@ -810,7 +811,8 @@ static int __ref kernel_init(void *unused)
 	flush_delayed_fput();
 
 	if (ramdisk_execute_command) {
-		run_init_process(ramdisk_execute_command);
+		if (!run_init_process(ramdisk_execute_command))
+			return 0;
 		printk(KERN_WARNING "Failed to execute %s\n",
 				ramdisk_execute_command);
 	}
@@ -822,14 +824,16 @@ static int __ref kernel_init(void *unused)
 	 * trying to recover a really broken machine.
 	 */
 	if (execute_command) {
-		run_init_process(execute_command);
+		if (!run_init_process(execute_command))
+			return 0;
 		printk(KERN_WARNING "Failed to execute %s.  Attempting "
 					"defaults...\n", execute_command);
 	}
-	run_init_process("/sbin/init");
-	run_init_process("/etc/init");
-	run_init_process("/bin/init");
-	run_init_process("/bin/sh");
+	if (!run_init_process("/sbin/init") ||
+	    !run_init_process("/etc/init") ||
+	    !run_init_process("/bin/init") ||
+	    !run_init_process("/bin/sh"))
+		return 0;
 
 	panic("No init found.  Try passing init= option to kernel. "
 	      "See Linux Documentation/init.txt for guidance.");
diff --git a/kernel/kmod.c b/kernel/kmod.c
index b6e5ca9c758a..1c317e386831 100644
--- a/kernel/kmod.c
+++ b/kernel/kmod.c
@@ -37,6 +37,7 @@
 #include <linux/notifier.h>
 #include <linux/suspend.h>
 #include <linux/rwsem.h>
+#include <linux/ptrace.h>
 #include <asm/uaccess.h>
 
 #include <trace/events/module.h>
@@ -221,6 +222,8 @@ static int ____call_usermodehelper(void *data)
 	retval = kernel_execve(sub_info->path,
 			       (const char *const *)sub_info->argv,
 			       (const char *const *)sub_info->envp);
+	if (!retval)
+		return 0;
 
 	/* Exec failed? */
 fail:
diff --git a/kernel/kthread.c b/kernel/kthread.c
index b579af57ea10..7ba65c1aa6b3 100644
--- a/kernel/kthread.c
+++ b/kernel/kthread.c
@@ -16,6 +16,7 @@
 #include <linux/mutex.h>
 #include <linux/slab.h>
 #include <linux/freezer.h>
+#include <linux/ptrace.h>
 #include <trace/events/sched.h>
 
 static DEFINE_SPINLOCK(kthread_create_lock);