riscv: entry: Consolidate ret_from_kernel_thread into ret_from_fork

The ret_from_kernel_thread() behaves similarly with ret_from_fork(),
the only difference is whether call the fn(arg) or not, this can be
achieved by testing fn is NULL or not, I.E s0 is 0 or not. Many
architectures have done the same thing, it makes entry.S more clean.

Signed-off-by: Jisheng Zhang <jszhang@kernel.org>
Reviewed-by: Björn Töpel <bjorn@rivosinc.com>
Reviewed-by: Guo Ren <guoren@kernel.org>
Tested-by: Guo Ren <guoren@kernel.org>
Signed-off-by: Guo Ren <guoren@kernel.org>
Link: https://lore.kernel.org/r/20230222033021.983168-7-guoren@kernel.org
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>

Author: xhackerustc

arch/riscv/kernel/entry.S

@@ -132,7 +132,6 @@ SYM_CODE_END(handle_exception)
  * caller list:
  *  - handle_exception
  *  - ret_from_fork
- *  - ret_from_kernel_thread
  */
 SYM_CODE_START_NOALIGN(ret_from_exception)
 	REG_L s0, PT_STATUS(sp)
@@ -334,20 +333,15 @@ SYM_CODE_END(handle_kernel_stack_overflow)
 
 SYM_CODE_START(ret_from_fork)
 	call schedule_tail
-	move a0, sp /* pt_regs */
-	la ra, ret_from_exception
-	tail syscall_exit_to_user_mode
-SYM_CODE_END(ret_from_fork)
-
-SYM_CODE_START(ret_from_kernel_thread)
-	call schedule_tail
+	beqz s0, 1f	/* not from kernel thread */
 	/* Call fn(arg) */
 	move a0, s1
 	jalr s0
+1:
 	move a0, sp /* pt_regs */
 	la ra, ret_from_exception
 	tail syscall_exit_to_user_mode
-SYM_CODE_END(ret_from_kernel_thread)
+SYM_CODE_END(ret_from_fork)
 
 /*
  * Integer register context switch

arch/riscv/kernel/process.c

@@ -34,7 +34,6 @@ EXPORT_SYMBOL(__stack_chk_guard);
 #endif
 
 extern asmlinkage void ret_from_fork(void);
-extern asmlinkage void ret_from_kernel_thread(void);
 
 void arch_cpu_idle(void)
 {
@@ -173,7 +172,6 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 		/* Supervisor/Machine, irqs on: */
 		childregs->status = SR_PP | SR_PIE;
 
-		p->thread.ra = (unsigned long)ret_from_kernel_thread;
 		p->thread.s[0] = (unsigned long)args->fn;
 		p->thread.s[1] = (unsigned long)args->fn_arg;
 	} else {
@@ -183,8 +181,9 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 		if (clone_flags & CLONE_SETTLS)
 			childregs->tp = tls;
 		childregs->a0 = 0; /* Return value of fork() */
-		p->thread.ra = (unsigned long)ret_from_fork;
+		p->thread.s[0] = 0;
 	}
+	p->thread.ra = (unsigned long)ret_from_fork;
 	p->thread.sp = (unsigned long)childregs; /* kernel sp */
 	return 0;
 }