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

7 files changed, 34 insertions, 122 deletions

diff --git a/arch/mips/kernel/entry.S b/arch/mips/kernel/entry.S
index 9b00362f32f..e5786858cdb 100644
--- a/arch/mips/kernel/entry.S
+++ b/arch/mips/kernel/entry.S
@@ -70,6 +70,12 @@ need_resched:
 	b	need_resched
 #endif
 
+FEXPORT(ret_from_kernel_thread)
+	jal	schedule_tail		# a0 = struct task_struct *prev
+	move	a0, s1
+	jal	s0
+	j	syscall_exit
+
 FEXPORT(ret_from_fork)
 	jal	schedule_tail		# a0 = struct task_struct *prev
 
diff --git a/arch/mips/kernel/linux32.c b/arch/mips/kernel/linux32.c
index 3a21acedf88..7adab86c632 100644
--- a/arch/mips/kernel/linux32.c
+++ b/arch/mips/kernel/linux32.c
@@ -3,7 +3,6 @@
  *
  * Copyright (C) 2000 Silicon Graphics, Inc.
  * Written by Ulf Carlsson (ulfc@engr.sgi.com)
- * sys32_execve from ia64/ia32 code, Feb 2000, Kanoj Sarcar (kanoj@sgi.com)
  */
 #include <linux/compiler.h>
 #include <linux/mm.h>
@@ -77,26 +76,6 @@ out:
 	return error;
 }
 
-/*
- * sys_execve() executes a new program.
- */
-asmlinkage int sys32_execve(nabi_no_regargs struct pt_regs regs)
-{
-	int error;
-	struct filename *filename;
-
-	filename = getname(compat_ptr(regs.regs[4]));
-	error = PTR_ERR(filename);
-	if (IS_ERR(filename))
-		goto out;
-	error = compat_do_execve(filename->name, compat_ptr(regs.regs[5]),
-				 compat_ptr(regs.regs[6]), &regs);
-	putname(filename);
-
-out:
-	return error;
-}
-
 #define RLIM_INFINITY32	0x7fffffff
 #define RESOURCE32(x) ((x > RLIM_INFINITY32) ? RLIM_INFINITY32 : x)
 
@@ -333,7 +312,7 @@ _sys32_clone(nabi_no_regargs struct pt_regs regs)
 	/* Use __dummy4 instead of getting it off the stack, so that
 	   syscall() works.  */
 	child_tidptr = (int __user *) __dummy4;
-	return do_fork(clone_flags, newsp, &regs, 0,
+	return do_fork(clone_flags, newsp, 0,
 	               parent_tidptr, child_tidptr);
 }
 
diff --git a/arch/mips/kernel/mips_ksyms.c b/arch/mips/kernel/mips_ksyms.c
index 3fc1691110d..2d9304c2b54 100644
--- a/arch/mips/kernel/mips_ksyms.c
+++ b/arch/mips/kernel/mips_ksyms.c
@@ -32,8 +32,6 @@ EXPORT_SYMBOL(memset);
 EXPORT_SYMBOL(memcpy);
 EXPORT_SYMBOL(memmove);
 
-EXPORT_SYMBOL(kernel_thread);
-
 /*
  * Functions that operate on entire pages.  Mostly used by memory management.
  */
diff --git a/arch/mips/kernel/process.c b/arch/mips/kernel/process.c
index e9a5fd7277f..38097652d62 100644
--- a/arch/mips/kernel/process.c
+++ b/arch/mips/kernel/process.c
@@ -84,6 +84,7 @@ void __noreturn cpu_idle(void)
 }
 
 asmlinkage void ret_from_fork(void);
+asmlinkage void ret_from_kernel_thread(void);
 
 void start_thread(struct pt_regs * regs, unsigned long pc, unsigned long sp)
 {
@@ -113,10 +114,10 @@ void flush_thread(void)
 }
 
 int copy_thread(unsigned long clone_flags, unsigned long usp,
-	unsigned long unused, struct task_struct *p, struct pt_regs *regs)
+	unsigned long arg, struct task_struct *p)
 {
 	struct thread_info *ti = task_thread_info(p);
-	struct pt_regs *childregs;
+	struct pt_regs *childregs, *regs = current_pt_regs();
 	unsigned long childksp;
 	p->set_child_tid = p->clear_child_tid = NULL;
 
@@ -136,19 +137,30 @@ int copy_thread(unsigned long clone_flags, unsigned long usp,
 	childregs = (struct pt_regs *) childksp - 1;
 	/*  Put the stack after the struct pt_regs.  */
 	childksp = (unsigned long) childregs;
+	p->thread.cp0_status = read_c0_status() & ~(ST0_CU2|ST0_CU1);
+	if (unlikely(p->flags & PF_KTHREAD)) {
+		unsigned long status = p->thread.cp0_status;
+		memset(childregs, 0, sizeof(struct pt_regs));
+		ti->addr_limit = KERNEL_DS;
+		p->thread.reg16 = usp; /* fn */
+		p->thread.reg17 = arg;
+		p->thread.reg29 = childksp;
+		p->thread.reg31 = (unsigned long) ret_from_kernel_thread;
+#if defined(CONFIG_CPU_R3000) || defined(CONFIG_CPU_TX39XX)
+		status = (status & ~(ST0_KUP | ST0_IEP | ST0_IEC)) |
+			 ((status & (ST0_KUC | ST0_IEC)) << 2);
+#else
+		status |= ST0_EXL;
+#endif
+		childregs->cp0_status = status;
+		return 0;
+	}
 	*childregs = *regs;
 	childregs->regs[7] = 0;	/* Clear error flag */
-
 	childregs->regs[2] = 0;	/* Child gets zero as return value */
+	childregs->regs[29] = usp;
+	ti->addr_limit = USER_DS;
 
-	if (childregs->cp0_status & ST0_CU0) {
-		childregs->regs[28] = (unsigned long) ti;
-		childregs->regs[29] = childksp;
-		ti->addr_limit = KERNEL_DS;
-	} else {
-		childregs->regs[29] = usp;
-		ti->addr_limit = USER_DS;
-	}
 	p->thread.reg29 = (unsigned long) childregs;
 	p->thread.reg31 = (unsigned long) ret_from_fork;
 
@@ -156,7 +168,6 @@ int copy_thread(unsigned long clone_flags, unsigned long usp,
 	 * New tasks lose permission to use the fpu. This accelerates context
 	 * switching for most programs since they don't use the fpu.
 	 */
-	p->thread.cp0_status = read_c0_status() & ~(ST0_CU2|ST0_CU1);
 	childregs->cp0_status &= ~(ST0_CU2|ST0_CU1);
 
 #ifdef CONFIG_MIPS_MT_SMTC
@@ -222,35 +233,6 @@ int dump_task_fpu(struct task_struct *t, elf_fpregset_t *fpr)
 }
 
 /*
- * Create a kernel thread
- */
-static void __noreturn kernel_thread_helper(void *arg, int (*fn)(void *))
-{
-	do_exit(fn(arg));
-}
-
-long kernel_thread(int (*fn)(void *), void *arg, unsigned long flags)
-{
-	struct pt_regs regs;
-
-	memset(&regs, 0, sizeof(regs));
-
-	regs.regs[4] = (unsigned long) arg;
-	regs.regs[5] = (unsigned long) fn;
-	regs.cp0_epc = (unsigned long) kernel_thread_helper;
-	regs.cp0_status = read_c0_status();
-#if defined(CONFIG_CPU_R3000) || defined(CONFIG_CPU_TX39XX)
-	regs.cp0_status = (regs.cp0_status & ~(ST0_KUP | ST0_IEP | ST0_IEC)) |
-			  ((regs.cp0_status & (ST0_KUC | ST0_IEC)) << 2);
-#else
-	regs.cp0_status |= ST0_EXL;
-#endif
-
-	/* Ok, create the new process.. */
-	return do_fork(flags | CLONE_VM | CLONE_UNTRACED, 0, &regs, 0, NULL, NULL);
-}
-
-/*
  *
  */
 struct mips_frame_info {
diff --git a/arch/mips/kernel/scall64-n32.S b/arch/mips/kernel/scall64-n32.S
index 86ec03f0e00..62971914376 100644
--- a/arch/mips/kernel/scall64-n32.S
+++ b/arch/mips/kernel/scall64-n32.S
@@ -167,7 +167,7 @@ EXPORT(sysn32_call_table)
 	PTR	sys_getsockopt
 	PTR	sys_clone			/* 6055 */
 	PTR	sys_fork
-	PTR	sys32_execve
+	PTR	compat_sys_execve
 	PTR	sys_exit
 	PTR	compat_sys_wait4
 	PTR	sys_kill			/* 6060 */
diff --git a/arch/mips/kernel/scall64-o32.S b/arch/mips/kernel/scall64-o32.S
index 53c2d724576..9601be6afa3 100644
--- a/arch/mips/kernel/scall64-o32.S
+++ b/arch/mips/kernel/scall64-o32.S
@@ -203,7 +203,7 @@ sys_call_table:
 	PTR	sys_creat
 	PTR	sys_link
 	PTR	sys_unlink			/* 4010 */
-	PTR	sys32_execve
+	PTR	compat_sys_execve
 	PTR	sys_chdir
 	PTR	compat_sys_time
 	PTR	sys_mknod
diff --git a/arch/mips/kernel/syscall.c b/arch/mips/kernel/syscall.c
index 2bd561bc05a..201cb76b4df 100644
--- a/arch/mips/kernel/syscall.c
+++ b/arch/mips/kernel/syscall.c
@@ -92,7 +92,7 @@ save_static_function(sys_fork);
 static int __used noinline
 _sys_fork(nabi_no_regargs struct pt_regs regs)
 {
-	return do_fork(SIGCHLD, regs.regs[29], &regs, 0, NULL, NULL);
+	return do_fork(SIGCHLD, regs.regs[29], 0, NULL, NULL);
 }
 
 save_static_function(sys_clone);
@@ -123,32 +123,10 @@ _sys_clone(nabi_no_regargs struct pt_regs regs)
 #else
 	child_tidptr = (int __user *) regs.regs[8];
 #endif
-	return do_fork(clone_flags, newsp, &regs, 0,
+	return do_fork(clone_flags, newsp, 0,
 	               parent_tidptr, child_tidptr);
 }
 
-/*
- * sys_execve() executes a new program.
- */
-asmlinkage int sys_execve(nabi_no_regargs struct pt_regs regs)
-{
-	int error;
-	struct filename *filename;
-
-	filename = getname((const char __user *) (long)regs.regs[4]);
-	error = PTR_ERR(filename);
-	if (IS_ERR(filename))
-		goto out;
-	error = do_execve(filename->name,
-			  (const char __user *const __user *) (long)regs.regs[5],
-	                  (const char __user *const __user *) (long)regs.regs[6],
-			  &regs);
-	putname(filename);
-
-out:
-	return error;
-}
-
 SYSCALL_DEFINE1(set_thread_area, unsigned long, addr)
 {
 	struct thread_info *ti = task_thread_info(current);
@@ -313,34 +291,3 @@ asmlinkage void bad_stack(void)
 {
 	do_exit(SIGSEGV);
 }
-
-/*
- * 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 unsigned long __a0 asm("$4") = (unsigned long) filename;
-	register unsigned long __a1 asm("$5") = (unsigned long) argv;
-	register unsigned long __a2 asm("$6") = (unsigned long) envp;
-	register unsigned long __a3 asm("$7");
-	unsigned long __v0;
-
-	__asm__ volatile ("					\n"
-	"	.set	noreorder				\n"
-	"	li	$2, %5		# __NR_execve		\n"
-	"	syscall						\n"
-	"	move	%0, $2					\n"
-	"	.set	reorder					\n"
-	: "=&r" (__v0), "=r" (__a3)
-	: "r" (__a0), "r" (__a1), "r" (__a2), "i" (__NR_execve)
-	: "$2", "$8", "$9", "$10", "$11", "$12", "$13", "$14", "$15", "$24",
-	  "memory");
-
-	if (__a3 == 0)
-		return __v0;
-
-	return -__v0;
-}