arm64: Use generic kernel_thread() implementation

This patch enables CONFIG_GENERIC_KERNEL_THREAD on arm64, changes
copy_threads to cope with kernel threads creation and adapts
ret_from_fork accordingly. The arm64-specific kernel_thread
implementation is no longer needed.
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>

arch/arm64/Kconfig

@@ -6,6 +6,7 @@ config ARM64
 	select GENERIC_IOMAP
 	select GENERIC_IRQ_PROBE
 	select GENERIC_IRQ_SHOW
+	select GENERIC_KERNEL_THREAD
 	select GENERIC_SMP_IDLE_THREAD
 	select GENERIC_TIME_VSYSCALL
 	select HARDIRQS_SW_RESEND

arch/arm64/include/asm/processor.h

@@ -136,11 +136,6 @@ unsigned long get_wchan(struct task_struct *p);
 extern struct task_struct *cpu_switch_to(struct task_struct *prev,
 					 struct task_struct *next);
 
-/*
- * 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)
 

arch/arm64/kernel/entry.S

@@ -611,7 +611,10 @@ ENDPROC(ret_to_user)
  */
 ENTRY(ret_from_fork)
 	bl	schedule_tail
-	get_thread_info tsk
+	cbz	x19, 1f				// not a kernel thread
+	mov	x0, x20
+	blr	x19
+1:	get_thread_info tsk
 	b	ret_to_user
 ENDPROC(ret_from_fork)
 

arch/arm64/kernel/process.c

@@ -240,12 +240,14 @@ int copy_thread(unsigned long clone_flags, unsigned long stack_start,
 	struct pt_regs *childregs = task_pt_regs(p);
 	unsigned long tls = p->thread.tp_value;
 
+	memset(&p->thread.cpu_context, 0, sizeof(struct cpu_context));
+
+	if (likely(regs)) {
 		*childregs = *regs;
 		childregs->regs[0] = 0;
-
-	if (is_compat_thread(task_thread_info(p)))
+		if (is_compat_thread(task_thread_info(p))) {
 			childregs->compat_sp = stack_start;
-	else {
+		} else {
 			/*
 			 * Read the current TLS pointer from tpidr_el0 as it may be
 			 * out-of-sync with the saved value.
@@ -253,14 +255,20 @@ int copy_thread(unsigned long clone_flags, unsigned long stack_start,
 			asm("mrs %0, tpidr_el0" : "=r" (tls));
 			childregs->sp = stack_start;
 		}
-
-	memset(&p->thread.cpu_context, 0, sizeof(struct cpu_context));
-	p->thread.cpu_context.sp = (unsigned long)childregs;
-	p->thread.cpu_context.pc = (unsigned long)ret_from_fork;
-
-	/* If a TLS pointer was passed to clone, use that for the new thread. */
+		/*
+		 * If a TLS pointer was passed to clone (4th argument), use it
+		 * for the new thread.
+		 */
 		if (clone_flags & CLONE_SETTLS)
 			tls = regs->regs[3];
+	} else {
+		memset(childregs, 0, sizeof(struct pt_regs));
+		childregs->pstate = PSR_MODE_EL1h;
+		p->thread.cpu_context.x19 = stack_start;
+		p->thread.cpu_context.x20 = stk_sz;
+	}
+	p->thread.cpu_context.pc = (unsigned long)ret_from_fork;
+	p->thread.cpu_context.sp = (unsigned long)childregs;
 	p->thread.tp_value = tls;
 
 	ptrace_hw_copy_thread(p);
@@ -327,43 +335,6 @@ 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.  x1 is the thread argument, x2 is the pointer to
- * the thread function, and x3 points to the exit function.
- */
-extern void kernel_thread_helper(void);
-asm(	".section .text\n"
-"	.align\n"
-"	.type	kernel_thread_helper, #function\n"
-"kernel_thread_helper:\n"
-"	mov	x0, x1\n"
-"	mov	x30, x3\n"
-"	br	x2\n"
-"	.size	kernel_thread_helper, . - kernel_thread_helper\n"
-"	.previous");
-
-#define kernel_thread_exit	do_exit
-
-/*
- * 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.regs[1] = (unsigned long)arg;
-	regs.regs[2] = (unsigned long)fn;
-	regs.regs[3] = (unsigned long)kernel_thread_exit;
-	regs.pc = (unsigned long)kernel_thread_helper;
-	regs.pstate = PSR_MODE_EL1h;
-
-	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;