x86: Rewrite ret_from_fork() in C

When kCFI is enabled, special handling is needed for the indirect call
to the kernel thread function.  Rewrite the ret_from_fork() function in
C so that the compiler can properly handle the indirect call.
Suggested-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Brian Gerst <brgerst@gmail.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Kees Cook <keescook@chromium.org>
Reviewed-by: Sami Tolvanen <samitolvanen@google.com>
Link: https://lkml.kernel.org/r/20230623225529.34590-3-brgerst@gmail.com

arch/x86/entry/entry_32.S

@@ -727,36 +727,22 @@ SYM_CODE_END(__switch_to_asm)
  * edi: kernel thread arg
  */
 .pushsection .text, "ax"
-SYM_CODE_START(ret_from_fork)
+SYM_CODE_START(ret_from_fork_asm)
+	movl	%esp, %edx	/* regs */
+
 	/* return address for the stack unwinder */
 	pushl	$.Lsyscall_32_done
 
 	FRAME_BEGIN
-	pushl	%eax
-	call	schedule_tail
+	/* prev already in EAX */
+	movl	%ebx, %ecx	/* fn */
+	pushl	%edi		/* fn_arg */
+	call	ret_from_fork
 	addl	$4, %esp
 	FRAME_END
 
-	testl	%ebx, %ebx
-	jnz	1f		/* kernel threads are uncommon */
-
-2:
-	/* When we fork, we trace the syscall return in the child, too. */
-	leal    4(%esp), %eax
-	call    syscall_exit_to_user_mode
 	RET
-
-	/* kernel thread */
-1:	movl	%edi, %eax
-	CALL_NOSPEC ebx
-	/*
-	 * A kernel thread is allowed to return here after successfully
-	 * calling kernel_execve().  Exit to userspace to complete the execve()
-	 * syscall.
-	 */
-	movl	$0, PT_EAX(%esp)
-	jmp	2b
-SYM_CODE_END(ret_from_fork)
+SYM_CODE_END(ret_from_fork_asm)
 .popsection
 
 SYM_ENTRY(__begin_SYSENTER_singlestep_region, SYM_L_GLOBAL, SYM_A_NONE)

arch/x86/entry/entry_64.S

@@ -284,36 +284,19 @@ SYM_FUNC_END(__switch_to_asm)
  * r12: kernel thread arg
  */
 .pushsection .text, "ax"
-	__FUNC_ALIGN
-SYM_CODE_START_NOALIGN(ret_from_fork)
-	UNWIND_HINT_END_OF_STACK
+SYM_CODE_START(ret_from_fork_asm)
+	UNWIND_HINT_REGS
 	ANNOTATE_NOENDBR // copy_thread
 	CALL_DEPTH_ACCOUNT
-	movq	%rax, %rdi
-	call	schedule_tail			/* rdi: 'prev' task parameter */
 
-	testq	%rbx, %rbx			/* from kernel_thread? */
-	jnz	1f				/* kernel threads are uncommon */
+	movq	%rax, %rdi		/* prev */
+	movq	%rsp, %rsi		/* regs */
+	movq	%rbx, %rdx		/* fn */
+	movq	%r12, %rcx		/* fn_arg */
+	call	ret_from_fork
 
-2:
-	UNWIND_HINT_REGS
-	movq	%rsp, %rdi
-	call	syscall_exit_to_user_mode	/* returns with IRQs disabled */
 	jmp	swapgs_restore_regs_and_return_to_usermode
-
-1:
-	/* kernel thread */
-	UNWIND_HINT_END_OF_STACK
-	movq	%r12, %rdi
-	CALL_NOSPEC rbx
-	/*
-	 * A kernel thread is allowed to return here after successfully
-	 * calling kernel_execve().  Exit to userspace to complete the execve()
-	 * syscall.
-	 */
-	movq	$0, RAX(%rsp)
-	jmp	2b
-SYM_CODE_END(ret_from_fork)
+SYM_CODE_END(ret_from_fork_asm)
 .popsection
 
 .macro DEBUG_ENTRY_ASSERT_IRQS_OFF

arch/x86/include/asm/switch_to.h

@@ -12,7 +12,9 @@ struct task_struct *__switch_to_asm(struct task_struct *prev,
 __visible struct task_struct *__switch_to(struct task_struct *prev,
 					  struct task_struct *next);
 
-asmlinkage void ret_from_fork(void);
+asmlinkage void ret_from_fork_asm(void);
+__visible void ret_from_fork(struct task_struct *prev, struct pt_regs *regs,
+			     int (*fn)(void *), void *fn_arg);
 
 /*
  * This is the structure pointed to by thread.sp for an inactive task.  The

arch/x86/kernel/process.c

@@ -28,6 +28,7 @@
 #include <linux/static_call.h>
 #include <trace/events/power.h>
 #include <linux/hw_breakpoint.h>
+#include <linux/entry-common.h>
 #include <asm/cpu.h>
 #include <asm/apic.h>
 #include <linux/uaccess.h>
@@ -134,6 +135,25 @@ static int set_new_tls(struct task_struct *p, unsigned long tls)
 		return do_set_thread_area_64(p, ARCH_SET_FS, tls);
 }
 
+__visible void ret_from_fork(struct task_struct *prev, struct pt_regs *regs,
+				     int (*fn)(void *), void *fn_arg)
+{
+	schedule_tail(prev);
+
+	/* Is this a kernel thread? */
+	if (unlikely(fn)) {
+		fn(fn_arg);
+		/*
+		 * A kernel thread is allowed to return here after successfully
+		 * calling kernel_execve().  Exit to userspace to complete the
+		 * execve() syscall.
+		 */
+		regs->ax = 0;
+	}
+
+	syscall_exit_to_user_mode(regs);
+}
+
 int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 {
 	unsigned long clone_flags = args->flags;
@@ -149,7 +169,7 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 	frame = &fork_frame->frame;
 
 	frame->bp = encode_frame_pointer(childregs);
-	frame->ret_addr = (unsigned long) ret_from_fork;
+	frame->ret_addr = (unsigned long) ret_from_fork_asm;
 	p->thread.sp = (unsigned long) fork_frame;
 	p->thread.io_bitmap = NULL;
 	p->thread.iopl_warn = 0;