ARM: 9390/2: lib: Annotate loop delay instructions for CFI

When we annotate the loop delay code with SYM_TYPED_FUNC_START()
a function prototype signature will be emitted into the object
file above each site called from C, and the delay loop code is
using "fallthroughs" from the different assembly callbacks. This
will not work as the execution flow will run into the prototype
signatures.

Rewrite the code to use explicit branches to the other code
segments and annotate the code using SYM_TYPED_FUNC_START().

Tested on the ARM Versatile which uses the calibrated loop delay.

Tested-by: Kees Cook <[e-mail]>
Reviewed-by: Sami Tolvanen <[e-mail]>
Signed-off-by: Linus Walleij <[e-mail]>
Signed-off-by: Russell King (Oracle) <[e-mail]>

arch/arm/lib/delay-loop.S

···
  *  Copyright (C) 1995, 1996 Russell King
  */
 #include <linux/linkage.h>
+#include <linux/cfi_types.h>
 #include <asm/assembler.h>
 #include <asm/delay.h>
 
···
  * HZ  <= 1000
  */
 
-ENTRY(__loop_udelay)
+SYM_TYPED_FUNC_START(__loop_udelay)
 		ldr	r2, .LC1
 		mul	r0, r2, r0		@ r0 = delay_us * UDELAY_MULT
-ENTRY(__loop_const_udelay)			@ 0 <= r0 <= 0xfffffaf0
+		b	__loop_const_udelay
+SYM_FUNC_END(__loop_udelay)
+
+SYM_TYPED_FUNC_START(__loop_const_udelay)	@ 0 <= r0 <= 0xfffffaf0
 		ldr	r2, .LC0
 		ldr	r2, [r2]
 		umull	r1, r0, r2, r0		@ r0-r1 = r0 * loops_per_jiffy
 		adds	r1, r1, #0xffffffff	@ rounding up ...
 		adcs	r0, r0, r0		@ and right shift by 31
 		reteq	lr
+		b	__loop_delay
+SYM_FUNC_END(__loop_const_udelay)
 
 		.align 3
 
 @ Delay routine
-ENTRY(__loop_delay)
+SYM_TYPED_FUNC_START(__loop_delay)
 		subs	r0, r0, #1
 #if 0
 		retls	lr
···
 #endif
 		bhi	__loop_delay
 		ret	lr
-ENDPROC(__loop_udelay)
-ENDPROC(__loop_const_udelay)
-ENDPROC(__loop_delay)
+SYM_FUNC_END(__loop_delay)