Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/signal

Pull big execve/kernel_thread/fork unification series from Al Viro:
 "All architectures are converted to new model.  Quite a bit of that
  stuff is actually shared with architecture trees; in such cases it's
  literally shared branch pulled by both, not a cherry-pick.

  A lot of ugliness and black magic is gone (-3KLoC total in this one):

   - kernel_thread()/kernel_execve()/sys_execve() redesign.

     We don't do syscalls from kernel anymore for either kernel_thread()
     or kernel_execve():

     kernel_thread() is essentially clone(2) with callback run before we
     return to userland, the callbacks either never return or do
     successful do_execve() before returning.

     kernel_execve() is a wrapper for do_execve() - it doesn't need to
     do transition to user mode anymore.

     As a result kernel_thread() and kernel_execve() are
     arch-independent now - they live in kernel/fork.c and fs/exec.c
     resp.  sys_execve() is also in fs/exec.c and it's completely
     architecture-independent.

   - daemonize() is gone, along with its parts in fs/*.c

   - struct pt_regs * is no longer passed to do_fork/copy_process/
     copy_thread/do_execve/search_binary_handler/->load_binary/do_coredump.

   - sys_fork()/sys_vfork()/sys_clone() unified; some architectures
     still need wrappers (ones with callee-saved registers not saved in
     pt_regs on syscall entry), but the main part of those suckers is in
     kernel/fork.c now."

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/signal: (113 commits)
  do_coredump(): get rid of pt_regs argument
  print_fatal_signal(): get rid of pt_regs argument
  ptrace_signal(): get rid of unused arguments
  get rid of ptrace_signal_deliver() arguments
  new helper: signal_pt_regs()
  unify default ptrace_signal_deliver
  flagday: kill pt_regs argument of do_fork()
  death to idle_regs()
  don't pass regs to copy_process()
  flagday: don't pass regs to copy_thread()
  bfin: switch to generic vfork, get rid of pointless wrappers
  xtensa: switch to generic clone()
  openrisc: switch to use of generic fork and clone
  unicore32: switch to generic clone(2)
  score: switch to generic fork/vfork/clone
  c6x: sanitize copy_thread(), get rid of clone(2) wrapper, switch to generic clone()
  take sys_fork/sys_vfork/sys_clone prototypes to linux/syscalls.h
  mn10300: switch to generic fork/vfork/clone
  h8300: switch to generic fork/vfork/clone
  tile: switch to generic clone()
  ...

Conflicts:
	arch/microblaze/include/asm/Kbuild

arch/m32r/Kconfig

@@ -15,6 +15,8 @@ config M32R
 	select GENERIC_ATOMIC64
 	select ARCH_USES_GETTIMEOFFSET
 	select MODULES_USE_ELF_RELA
+	select GENERIC_KERNEL_THREAD
+	select GENERIC_KERNEL_EXECVE
 
 config SBUS
 	bool

arch/m32r/include/asm/processor.h

@@ -118,11 +118,6 @@ struct mm_struct;
 /* Free all resources held by a thread. */
 extern void release_thread(struct task_struct *);
 
-/*
- * create a kernel thread without removing it from tasklists
- */
-extern int kernel_thread(int (*fn)(void *), void * arg, unsigned long flags);
-
 /* Copy and release all segment info associated with a VM */
 extern void copy_segments(struct task_struct *p, struct mm_struct * mm);
 extern void release_segments(struct mm_struct * mm);

arch/m32r/include/asm/ptrace.h

@@ -139,6 +139,8 @@ extern void withdraw_debug_trap(struct pt_regs *regs);
 
 #define task_pt_regs(task) \
         ((struct pt_regs *)(task_stack_page(task) + THREAD_SIZE) - 1)
+#define current_pt_regs() ((struct pt_regs *) \
+	((unsigned long)current_thread_info() + THREAD_SIZE) - 1)
 
 #endif /* __KERNEL */
 

arch/m32r/include/asm/signal.h

@@ -149,10 +149,6 @@ typedef struct sigaltstack {
 
 #undef __HAVE_ARCH_SIG_BITOPS
 
-struct pt_regs;
-
-#define ptrace_signal_deliver(regs, cookie)	do { } while (0)
-
 #endif /* __KERNEL__ */
 
 #endif  /* _ASM_M32R_SIGNAL_H */

arch/m32r/include/asm/unistd.h

@@ -352,6 +352,10 @@
 #define __ARCH_WANT_SYS_OLDUMOUNT
 #define __ARCH_WANT_SYS_RT_SIGACTION
 #define __ARCH_WANT_SYS_RT_SIGSUSPEND
+#define __ARCH_WANT_SYS_EXECVE
+#define __ARCH_WANT_SYS_CLONE
+#define __ARCH_WANT_SYS_FORK
+#define __ARCH_WANT_SYS_VFORK
 
 #define __IGNORE_lchown
 #define __IGNORE_setuid

arch/m32r/kernel/entry.S

@@ -125,6 +125,15 @@
 	and	\reg, sp
 	.endm
 
+ENTRY(ret_from_kernel_thread)
+	pop	r0
+	bl	schedule_tail
+	GET_THREAD_INFO(r8)
+	ld	r0, R0(r8)
+	ld	r1, R1(r8)
+	jl	r1
+	bra	syscall_exit
+
 ENTRY(ret_from_fork)
 	pop	r0
 	bl	schedule_tail

arch/m32r/kernel/m32r_ksyms.c

@@ -21,7 +21,6 @@ EXPORT_SYMBOL(boot_cpu_data);
 EXPORT_SYMBOL(dump_fpu);
 EXPORT_SYMBOL(__ioremap);
 EXPORT_SYMBOL(iounmap);
-EXPORT_SYMBOL(kernel_thread);
 
 EXPORT_SYMBOL(strncpy_from_user);
 EXPORT_SYMBOL(__strncpy_from_user);

arch/m32r/kernel/process.c

@@ -164,41 +164,6 @@ void show_regs(struct pt_regs * regs)
 #endif
 }
 
-/*
- * Create a kernel thread
- */
-
-/*
- * This is the mechanism for creating a new kernel thread.
- *
- * NOTE! Only a kernel-only process(ie the swapper or direct descendants
- * who haven't done an "execve()") should use this: it will work within
- * a system call from a "real" process, but the process memory space will
- * not be free'd until both the parent and the child have exited.
- */
-static void kernel_thread_helper(void *nouse, int (*fn)(void *), void *arg)
-{
-	fn(arg);
-	do_exit(-1);
-}
-
-int kernel_thread(int (*fn)(void *), void *arg, unsigned long flags)
-{
-	struct pt_regs regs;
-
-	memset(&regs, 0, sizeof (regs));
-	regs.r1 = (unsigned long)fn;
-	regs.r2 = (unsigned long)arg;
-
-	regs.bpc = (unsigned long)kernel_thread_helper;
-
-	regs.psw = M32R_PSW_BIE;
-
-	/* Ok, create the new process. */
-	return do_fork(flags | CLONE_VM | CLONE_UNTRACED, 0, &regs, 0, NULL,
-		NULL);
-}
-
 /*
  * Free current thread data structures etc..
  */
@@ -227,88 +192,31 @@ int dump_fpu(struct pt_regs *regs, elf_fpregset_t *fpu)
 }
 
 int copy_thread(unsigned long clone_flags, unsigned long spu,
-	unsigned long unused, struct task_struct *tsk, struct pt_regs *regs)
+	unsigned long arg, struct task_struct *tsk)
 {
 	struct pt_regs *childregs = task_pt_regs(tsk);
 	extern void ret_from_fork(void);
+	extern void ret_from_kernel_thread(void);
 
-	/* Copy registers */
-	*childregs = *regs;
-
-	childregs->spu = spu;
-	childregs->r0 = 0;	/* Child gets zero as return value */
-	regs->r0 = tsk->pid;
+	if (unlikely(tsk->flags & PF_KTHREAD)) {
+		memset(childregs, 0, sizeof(struct pt_regs));
+		childregs->psw = M32R_PSW_BIE;
+		childregs->r1 = spu;	/* fn */
+		childregs->r0 = arg;
+		tsk->thread.lr = (unsigned long)ret_from_kernel_thread;
+	} else {
+		/* Copy registers */
+		*childregs = *current_pt_regs();
+		if (spu)
+			childregs->spu = spu;
+		childregs->r0 = 0;	/* Child gets zero as return value */
+		tsk->thread.lr = (unsigned long)ret_from_fork;
+	}
 	tsk->thread.sp = (unsigned long)childregs;
-	tsk->thread.lr = (unsigned long)ret_from_fork;
 
 	return 0;
 }
 
-asmlinkage int sys_fork(unsigned long r0, unsigned long r1, unsigned long r2,
-	unsigned long r3, unsigned long r4, unsigned long r5, unsigned long r6,
-	struct pt_regs regs)
-{
-#ifdef CONFIG_MMU
-	return do_fork(SIGCHLD, regs.spu, &regs, 0, NULL, NULL);
-#else
-	return -EINVAL;
-#endif /* CONFIG_MMU */
-}
-
-asmlinkage int sys_clone(unsigned long clone_flags, unsigned long newsp,
-			 unsigned long parent_tidptr,
-			 unsigned long child_tidptr,
-			 unsigned long r4, unsigned long r5, unsigned long r6,
-			 struct pt_regs regs)
-{
-	if (!newsp)
-		newsp = regs.spu;
-
-	return do_fork(clone_flags, newsp, &regs, 0,
-		       (int __user *)parent_tidptr, (int __user *)child_tidptr);
-}
-
-/*
- * This is trivial, and on the face of it looks like it
- * could equally well be done in user mode.
- *
- * Not so, for quite unobvious reasons - register pressure.
- * In user mode vfork() cannot have a stack frame, and if
- * done by calling the "clone()" system call directly, you
- * do not have enough call-clobbered registers to hold all
- * the information you need.
- */
-asmlinkage int sys_vfork(unsigned long r0, unsigned long r1, unsigned long r2,
-	unsigned long r3, unsigned long r4, unsigned long r5, unsigned long r6,
-	struct pt_regs regs)
-{
-	return do_fork(CLONE_VFORK | CLONE_VM | SIGCHLD, regs.spu, &regs, 0,
-			NULL, NULL);
-}
-
-/*
- * sys_execve() executes a new program.
- */
-asmlinkage int sys_execve(const char __user *ufilename,
-			  const char __user *const __user *uargv,
-			  const char __user *const __user *uenvp,
-			  unsigned long r3, unsigned long r4, unsigned long r5,
-			  unsigned long r6, struct pt_regs regs)
-{
-	int error;
-	struct filename *filename;
-
-	filename = getname(ufilename);
-	error = PTR_ERR(filename);
-	if (IS_ERR(filename))
-		goto out;
-
-	error = do_execve(filename->name, uargv, uenvp, &regs);
-	putname(filename);
-out:
-	return error;
-}
-
 /*
  * These bracket the sleeping functions..
  */

arch/m32r/kernel/sys_m32r.c

@@ -88,24 +88,3 @@ asmlinkage int sys_cachectl(char *addr, int nbytes, int op)
 	/* Not implemented yet. */
 	return -ENOSYS;
 }
-
-/*
- * Do a system call from kernel instead of calling sys_execve so we
- * end up with proper pt_regs.
- */
-int kernel_execve(const char *filename,
-		  const char *const argv[],
-		  const char *const envp[])
-{
-	register long __scno __asm__ ("r7") = __NR_execve;
-	register long __arg3 __asm__ ("r2") = (long)(envp);
-	register long __arg2 __asm__ ("r1") = (long)(argv);
-	register long __res __asm__ ("r0") = (long)(filename);
-	__asm__ __volatile__ (
-		"trap #" SYSCALL_VECTOR "|| nop"
-		: "=r" (__res)
-		: "r" (__scno), "0" (__res), "r" (__arg2),
-			"r" (__arg3)
-		: "memory");
-	return __res;
-}