LoongArch: entry: Migrate ret_from_fork() to C

LoongArch is the only architecture that calls syscall_exit_to_user_mode()
from assembly.

Move the call into C so that this function can be inlined across all
architectures.

Signed-off-by: Charlie Jenkins <charlie@rivosinc.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/all/20250320-riscv_optimize_entry-v6-3-63e187e26041@rivosinc.com

Author: charlie-rivos

arch/loongarch/include/asm/asm-prototypes.h

@@ -12,3 +12,11 @@ __int128_t __ashlti3(__int128_t a, int b);
 __int128_t __ashrti3(__int128_t a, int b);
 __int128_t __lshrti3(__int128_t a, int b);
 #endif
+
+asmlinkage void noinstr __no_stack_protector ret_from_fork(struct task_struct *prev,
+							   struct pt_regs *regs);
+
+asmlinkage void noinstr __no_stack_protector ret_from_kernel_thread(struct task_struct *prev,
+								    struct pt_regs *regs,
+								    int (*fn)(void *),
+								    void *fn_arg);

arch/loongarch/kernel/entry.S

@@ -77,24 +77,22 @@ SYM_CODE_START(handle_syscall)
 SYM_CODE_END(handle_syscall)
 _ASM_NOKPROBE(handle_syscall)
 
-SYM_CODE_START(ret_from_fork)
+SYM_CODE_START(ret_from_fork_asm)
 	UNWIND_HINT_REGS
-	bl		schedule_tail		# a0 = struct task_struct *prev
-	move		a0, sp
-	bl 		syscall_exit_to_user_mode
+	move		a1, sp
+	bl 		ret_from_fork
 	RESTORE_STATIC
 	RESTORE_SOME
 	RESTORE_SP_AND_RET
-SYM_CODE_END(ret_from_fork)
+SYM_CODE_END(ret_from_fork_asm)
 
-SYM_CODE_START(ret_from_kernel_thread)
+SYM_CODE_START(ret_from_kernel_thread_asm)
 	UNWIND_HINT_REGS
-	bl		schedule_tail		# a0 = struct task_struct *prev
-	move		a0, s1
-	jirl		ra, s0, 0
-	move		a0, sp
-	bl		syscall_exit_to_user_mode
+	move		a1, sp
+	move		a2, s0
+	move		a3, s1
+	bl		ret_from_kernel_thread
 	RESTORE_STATIC
 	RESTORE_SOME
 	RESTORE_SP_AND_RET
-SYM_CODE_END(ret_from_kernel_thread)
+SYM_CODE_END(ret_from_kernel_thread_asm)

arch/loongarch/kernel/process.c

@@ -14,6 +14,7 @@
 #include <linux/init.h>
 #include <linux/kernel.h>
 #include <linux/errno.h>
+#include <linux/entry-common.h>
 #include <linux/sched.h>
 #include <linux/sched/debug.h>
 #include <linux/sched/task.h>
@@ -33,6 +34,7 @@
 #include <linux/prctl.h>
 #include <linux/nmi.h>
 
+#include <asm/asm-prototypes.h>
 #include <asm/asm.h>
 #include <asm/bootinfo.h>
 #include <asm/cpu.h>
@@ -47,6 +49,7 @@
 #include <asm/pgtable.h>
 #include <asm/processor.h>
 #include <asm/reg.h>
+#include <asm/switch_to.h>
 #include <asm/unwind.h>
 #include <asm/vdso.h>
 
@@ -63,8 +66,9 @@ EXPORT_SYMBOL(__stack_chk_guard);
 unsigned long boot_option_idle_override = IDLE_NO_OVERRIDE;
 EXPORT_SYMBOL(boot_option_idle_override);
 
-asmlinkage void ret_from_fork(void);
-asmlinkage void ret_from_kernel_thread(void);
+asmlinkage void restore_and_ret(void);
+asmlinkage void ret_from_fork_asm(void);
+asmlinkage void ret_from_kernel_thread_asm(void);
 
 void start_thread(struct pt_regs *regs, unsigned long pc, unsigned long sp)
 {
@@ -138,6 +142,23 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
 	return 0;
 }
 
+asmlinkage void noinstr __no_stack_protector ret_from_fork(struct task_struct *prev,
+							   struct pt_regs *regs)
+{
+	schedule_tail(prev);
+	syscall_exit_to_user_mode(regs);
+}
+
+asmlinkage void noinstr __no_stack_protector ret_from_kernel_thread(struct task_struct *prev,
+								    struct pt_regs *regs,
+								    int (*fn)(void *),
+								    void *fn_arg)
+{
+	schedule_tail(prev);
+	fn(fn_arg);
+	syscall_exit_to_user_mode(regs);
+}
+
 /*
  * Copy architecture-specific thread state
  */
@@ -165,8 +186,8 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 		p->thread.reg03 = childksp;
 		p->thread.reg23 = (unsigned long)args->fn;
 		p->thread.reg24 = (unsigned long)args->fn_arg;
-		p->thread.reg01 = (unsigned long)ret_from_kernel_thread;
-		p->thread.sched_ra = (unsigned long)ret_from_kernel_thread;
+		p->thread.reg01 = (unsigned long)ret_from_kernel_thread_asm;
+		p->thread.sched_ra = (unsigned long)ret_from_kernel_thread_asm;
 		memset(childregs, 0, sizeof(struct pt_regs));
 		childregs->csr_euen = p->thread.csr_euen;
 		childregs->csr_crmd = p->thread.csr_crmd;
@@ -182,8 +203,8 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 		childregs->regs[3] = usp;
 
 	p->thread.reg03 = (unsigned long) childregs;
-	p->thread.reg01 = (unsigned long) ret_from_fork;
-	p->thread.sched_ra = (unsigned long) ret_from_fork;
+	p->thread.reg01 = (unsigned long) ret_from_fork_asm;
+	p->thread.sched_ra = (unsigned long) ret_from_fork_asm;
 
 	/*
 	 * New tasks lose permission to use the fpu. This accelerates context