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

Pull generic execve() changes from Al Viro:
 "This introduces the generic kernel_thread() and kernel_execve()
  functions, and switches x86, arm, alpha, um and s390 over to them."

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/signal: (26 commits)
  s390: convert to generic kernel_execve()
  s390: switch to generic kernel_thread()
  s390: fold kernel_thread_helper() into ret_from_fork()
  s390: fold execve_tail() into start_thread(), convert to generic sys_execve()
  um: switch to generic kernel_thread()
  x86, um/x86: switch to generic sys_execve and kernel_execve
  x86: split ret_from_fork
  alpha: introduce ret_from_kernel_execve(), switch to generic kernel_execve()
  alpha: switch to generic kernel_thread()
  alpha: switch to generic sys_execve()
  arm: get rid of execve wrapper, switch to generic execve() implementation
  arm: optimized current_pt_regs()
  arm: introduce ret_from_kernel_execve(), switch to generic kernel_execve()
  arm: split ret_from_fork, simplify kernel_thread() [based on patch by rmk]
  generic sys_execve()
  generic kernel_execve()
  new helper: current_pt_regs()
  preparation for generic kernel_thread()
  um: kill thread->forking
  um: let signal_delivered() do SIGTRAP on singlestepping into handler
  ...

9 files changed, 46 insertions, 137 deletions

diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 2867a774230..e40eefb5d32 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -52,6 +52,7 @@ config ARM
 	select GENERIC_STRNCPY_FROM_USER
 	select GENERIC_STRNLEN_USER
 	select DCACHE_WORD_ACCESS if (CPU_V6 || CPU_V6K || CPU_V7) && !CPU_BIG_ENDIAN
+	select GENERIC_KERNEL_THREAD
 	help
 	  The ARM series is a line of low-power-consumption RISC chip designs
 	  licensed by ARM Ltd and targeted at embedded applications and
diff --git a/arch/arm/include/asm/processor.h b/arch/arm/include/asm/processor.h
index 99afa749826..06e7d509eaa 100644
--- a/arch/arm/include/asm/processor.h
+++ b/arch/arm/include/asm/processor.h
@@ -85,11 +85,6 @@ unsigned long get_wchan(struct task_struct *p);
 #define cpu_relax()			barrier()
 #endif
 
-/*
- * Create a new kernel thread
- */
-extern int kernel_thread(int (*fn)(void *), void *arg, unsigned long flags);
-
 #define task_pt_regs(p) \
 	((struct pt_regs *)(THREAD_START_SP + task_stack_page(p)) - 1)
 
diff --git a/arch/arm/include/asm/ptrace.h b/arch/arm/include/asm/ptrace.h
index 355ece523f4..44fe998269d 100644
--- a/arch/arm/include/asm/ptrace.h
+++ b/arch/arm/include/asm/ptrace.h
@@ -254,6 +254,11 @@ static inline unsigned long user_stack_pointer(struct pt_regs *regs)
 	return regs->ARM_sp;
 }
 
+#define current_pt_regs(void) ({				\
+	register unsigned long sp asm ("sp");			\
+	(struct pt_regs *)((sp | (THREAD_SIZE - 1)) - 7) - 1;	\
+})
+
 #endif /* __KERNEL__ */
 
 #endif /* __ASSEMBLY__ */
diff --git a/arch/arm/include/asm/system.h b/arch/arm/include/asm/system.h
index 74542c52f9b..368165e33c1 100644
--- a/arch/arm/include/asm/system.h
+++ b/arch/arm/include/asm/system.h
@@ -2,7 +2,6 @@
 #include <asm/barrier.h>
 #include <asm/compiler.h>
 #include <asm/cmpxchg.h>
-#include <asm/exec.h>
 #include <asm/switch_to.h>
 #include <asm/system_info.h>
 #include <asm/system_misc.h>
diff --git a/arch/arm/include/asm/unistd.h b/arch/arm/include/asm/unistd.h
index d9ff5cc3a50..f259921edfe 100644
--- a/arch/arm/include/asm/unistd.h
+++ b/arch/arm/include/asm/unistd.h
@@ -478,6 +478,8 @@
 #define __ARCH_WANT_OLD_READDIR
 #define __ARCH_WANT_SYS_SOCKETCALL
 #endif
+#define __ARCH_WANT_SYS_EXECVE
+#define __ARCH_WANT_KERNEL_EXECVE
 
 /*
  * "Conditional" syscalls
diff --git a/arch/arm/kernel/calls.S b/arch/arm/kernel/calls.S
index e337879595e..831cd38c8d9 100644
--- a/arch/arm/kernel/calls.S
+++ b/arch/arm/kernel/calls.S
@@ -20,7 +20,7 @@
 		CALL(sys_creat)
 		CALL(sys_link)
 /* 10 */	CALL(sys_unlink)
-		CALL(sys_execve_wrapper)
+		CALL(sys_execve)
 		CALL(sys_chdir)
 		CALL(OBSOLETE(sys_time))	/* used by libc4 */
 		CALL(sys_mknod)
diff --git a/arch/arm/kernel/entry-common.S b/arch/arm/kernel/entry-common.S
index f45987037bf..e340fa1db20 100644
--- a/arch/arm/kernel/entry-common.S
+++ b/arch/arm/kernel/entry-common.S
@@ -91,6 +91,30 @@ ENTRY(ret_from_fork)
 	b	ret_slow_syscall
 ENDPROC(ret_from_fork)
 
+ENTRY(ret_from_kernel_thread)
+ UNWIND(.fnstart)
+ UNWIND(.cantunwind)
+	bl	schedule_tail
+	mov	r0, r4
+	adr	lr, BSYM(1f)	@ kernel threads should not exit
+	mov	pc, r5
+1:	bl	do_exit
+	nop
+ UNWIND(.fnend)
+ENDPROC(ret_from_kernel_thread)
+
+/*
+ * turn a kernel thread into userland process
+ * use: ret_from_kernel_execve(struct pt_regs *normal)
+ */
+ENTRY(ret_from_kernel_execve)
+	mov	why, #0			@ not a syscall
+	str	why, [r0, #S_R0]	@ ... and we want 0 in ->ARM_r0 as well
+	get_thread_info tsk		@ thread structure
+	mov	sp, r0			@ stack pointer just under pt_regs
+	b	ret_slow_syscall
+ENDPROC(ret_from_kernel_execve)
+
 	.equ NR_syscalls,0
 #define CALL(x) .equ NR_syscalls,NR_syscalls+1
 #include "calls.S"
@@ -517,11 +541,6 @@ sys_vfork_wrapper:
 		b	sys_vfork
 ENDPROC(sys_vfork_wrapper)
 
-sys_execve_wrapper:
-		add	r3, sp, #S_OFF
-		b	sys_execve
-ENDPROC(sys_execve_wrapper)
-
 sys_clone_wrapper:
 		add	ip, sp, #S_OFF
 		str	ip, [sp, #4]
diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c
index 04eea22d795..f98c17ff195 100644
--- a/arch/arm/kernel/process.c
+++ b/arch/arm/kernel/process.c
@@ -373,6 +373,7 @@ void release_thread(struct task_struct *dead_task)
 }
 
 asmlinkage void ret_from_fork(void) __asm__("ret_from_fork");
+asmlinkage void ret_from_kernel_thread(void) __asm__("ret_from_kernel_thread");
 
 int
 copy_thread(unsigned long clone_flags, unsigned long stack_start,
@@ -381,13 +382,20 @@ copy_thread(unsigned long clone_flags, unsigned long stack_start,
 	struct thread_info *thread = task_thread_info(p);
 	struct pt_regs *childregs = task_pt_regs(p);
 
-	*childregs = *regs;
-	childregs->ARM_r0 = 0;
-	childregs->ARM_sp = stack_start;
-
 	memset(&thread->cpu_context, 0, sizeof(struct cpu_context_save));
+
+	if (likely(regs)) {
+		*childregs = *regs;
+		childregs->ARM_r0 = 0;
+		childregs->ARM_sp = stack_start;
+		thread->cpu_context.pc = (unsigned long)ret_from_fork;
+	} else {
+		thread->cpu_context.r4 = stk_sz;
+		thread->cpu_context.r5 = stack_start;
+		thread->cpu_context.pc = (unsigned long)ret_from_kernel_thread;
+		childregs->ARM_cpsr = SVC_MODE;
+	}
 	thread->cpu_context.sp = (unsigned long)childregs;
-	thread->cpu_context.pc = (unsigned long)ret_from_fork;
 
 	clear_ptrace_hw_breakpoint(p);
 
@@ -423,63 +431,6 @@ int dump_fpu (struct pt_regs *regs, struct user_fp *fp)
 }
 EXPORT_SYMBOL(dump_fpu);
 
-/*
- * Shuffle the argument into the correct register before calling the
- * thread function.  r4 is the thread argument, r5 is the pointer to
- * the thread function, and r6 points to the exit function.
- */
-extern void kernel_thread_helper(void);
-asm(	".pushsection .text\n"
-"	.align\n"
-"	.type	kernel_thread_helper, #function\n"
-"kernel_thread_helper:\n"
-#ifdef CONFIG_TRACE_IRQFLAGS
-"	bl	trace_hardirqs_on\n"
-#endif
-"	msr	cpsr_c, r7\n"
-"	mov	r0, r4\n"
-"	mov	lr, r6\n"
-"	mov	pc, r5\n"
-"	.size	kernel_thread_helper, . - kernel_thread_helper\n"
-"	.popsection");
-
-#ifdef CONFIG_ARM_UNWIND
-extern void kernel_thread_exit(long code);
-asm(	".pushsection .text\n"
-"	.align\n"
-"	.type	kernel_thread_exit, #function\n"
-"kernel_thread_exit:\n"
-"	.fnstart\n"
-"	.cantunwind\n"
-"	bl	do_exit\n"
-"	nop\n"
-"	.fnend\n"
-"	.size	kernel_thread_exit, . - kernel_thread_exit\n"
-"	.popsection");
-#else
-#define kernel_thread_exit	do_exit
-#endif
-
-/*
- * Create a kernel thread.
- */
-pid_t kernel_thread(int (*fn)(void *), void *arg, unsigned long flags)
-{
-	struct pt_regs regs;
-
-	memset(&regs, 0, sizeof(regs));
-
-	regs.ARM_r4 = (unsigned long)arg;
-	regs.ARM_r5 = (unsigned long)fn;
-	regs.ARM_r6 = (unsigned long)kernel_thread_exit;
-	regs.ARM_r7 = SVC_MODE | PSR_ENDSTATE | PSR_ISETSTATE;
-	regs.ARM_pc = (unsigned long)kernel_thread_helper;
-	regs.ARM_cpsr = regs.ARM_r7 | PSR_I_BIT;
-
-	return do_fork(flags|CLONE_VM|CLONE_UNTRACED, 0, &regs, 0, NULL, NULL);
-}
-EXPORT_SYMBOL(kernel_thread);
-
 unsigned long get_wchan(struct task_struct *p)
 {
 	struct stackframe frame;
diff --git a/arch/arm/kernel/sys_arm.c b/arch/arm/kernel/sys_arm.c
index 76cbb055dd0..c2a898aa57a 100644
--- a/arch/arm/kernel/sys_arm.c
+++ b/arch/arm/kernel/sys_arm.c
@@ -59,69 +59,6 @@ asmlinkage int sys_vfork(struct pt_regs *regs)
 	return do_fork(CLONE_VFORK | CLONE_VM | SIGCHLD, regs->ARM_sp, regs, 0, NULL, NULL);
 }
 
-/* sys_execve() executes a new program.
- * This is called indirectly via a small wrapper
- */
-asmlinkage int sys_execve(const char __user *filenamei,
-			  const char __user *const __user *argv,
-			  const char __user *const __user *envp, struct pt_regs *regs)
-{
-	int error;
-	char * filename;
-
-	filename = getname(filenamei);
-	error = PTR_ERR(filename);
-	if (IS_ERR(filename))
-		goto out;
-	error = do_execve(filename, argv, envp, regs);
-	putname(filename);
-out:
-	return error;
-}
-
-int kernel_execve(const char *filename,
-		  const char *const argv[],
-		  const char *const envp[])
-{
-	struct pt_regs regs;
-	int ret;
-
-	memset(&regs, 0, sizeof(struct pt_regs));
-	ret = do_execve(filename,
-			(const char __user *const __user *)argv,
-			(const char __user *const __user *)envp, &regs);
-	if (ret < 0)
-		goto out;
-
-	/*
-	 * Save argc to the register structure for userspace.
-	 */
-	regs.ARM_r0 = ret;
-
-	/*
-	 * We were successful.  We won't be returning to our caller, but
-	 * instead to user space by manipulating the kernel stack.
-	 */
-	asm(	"add	r0, %0, %1\n\t"
-		"mov	r1, %2\n\t"
-		"mov	r2, %3\n\t"
-		"bl	memmove\n\t"	/* copy regs to top of stack */
-		"mov	r8, #0\n\t"	/* not a syscall */
-		"mov	r9, %0\n\t"	/* thread structure */
-		"mov	sp, r0\n\t"	/* reposition stack pointer */
-		"b	ret_to_user"
-		:
-		: "r" (current_thread_info()),
-		  "Ir" (THREAD_START_SP - sizeof(regs)),
-		  "r" (&regs),
-		  "Ir" (sizeof(regs))
-		: "r0", "r1", "r2", "r3", "r8", "r9", "ip", "lr", "memory");
-
- out:
-	return ret;
-}
-EXPORT_SYMBOL(kernel_execve);
-
 /*
  * Since loff_t is a 64 bit type we avoid a lot of ABI hassle
  * with a different argument ordering.