arm: lib: Sync libgcc shift operations

Sync the libgcc shift operations with Linux kernel 4.4.6 , commit
0d1912303e54ed1b2a371be0bba51c384dd57326 . Syncing these three
files is easy, as there is almost no change in them, except the
addition of Thumb support.

This patch also defines CONFIG_THUMB2_KERNEL and CONFIG_ARM_ASM_UNIFIED
which is necessary for correct build of these files both in ARM and
Thumb mode, just like Linux does.
Signed-off-by: NMarek Vasut <marex@denx.de>
Cc: Albert Aribaud <albert.u.boot@aribaud.net>
Cc: Masahiro Yamada <yamada.masahiro@socionext.com>
Cc: Simon Glass <sjg@chromium.org>
Cc: Tom Rini <trini@konsulko.com>
Reviewed-by: NTom Rini <trini@konsulko.com>

arch/arm/lib/ashldi3.S

@@ -5,6 +5,7 @@
  */
 
 #include <linux/linkage.h>
+#include <asm/assembler.h>
 
 #ifdef __ARMEB__
 #define al r1
@@ -14,15 +15,18 @@
 #define ah r1
 #endif
 
-.globl __ashldi3
-__ashldi3:
+ENTRY(__ashldi3)
 ENTRY(__aeabi_llsl)
 
 	subs	r3, r2, #32
 	rsb	ip, r2, #32
 	movmi	ah, ah, lsl r2
 	movpl	ah, al, lsl r3
-	orrmi	ah, ah, al, lsr ip
+ ARM(	orrmi	ah, ah, al, lsr ip	)
+ THUMB(	lsrmi	r3, al, ip		)
+ THUMB(	orrmi	ah, ah, r3		)
 	mov	al, al, lsl r2
-	mov	pc, lr
+	ret	lr
+
+ENDPROC(__ashldi3)
 ENDPROC(__aeabi_llsl)

arch/arm/lib/ashrdi3.S

@@ -5,6 +5,7 @@
  */
 
 #include <linux/linkage.h>
+#include <asm/assembler.h>
 
 #ifdef __ARMEB__
 #define al r1
@@ -14,15 +15,18 @@
 #define ah r1
 #endif
 
-.globl __ashrdi3
-__ashrdi3:
+ENTRY(__ashrdi3)
 ENTRY(__aeabi_lasr)
 
 	subs	r3, r2, #32
 	rsb	ip, r2, #32
 	movmi	al, al, lsr r2
 	movpl	al, ah, asr r3
-	orrmi	al, al, ah, lsl ip
+ ARM(	orrmi	al, al, ah, lsl ip	)
+ THUMB(	lslmi	r3, ah, ip		)
+ THUMB(	orrmi	al, al, r3		)
 	mov	ah, ah, asr r2
-	mov	pc, lr
+	ret	lr
+
+ENDPROC(__ashrdi3)
 ENDPROC(__aeabi_lasr)

arch/arm/lib/lshrdi3.S

@@ -5,6 +5,7 @@
  */
 
 #include <linux/linkage.h>
+#include <asm/assembler.h>
 
 #ifdef __ARMEB__
 #define al r1
@@ -14,15 +15,18 @@
 #define ah r1
 #endif
 
-.globl __lshrdi3
-__lshrdi3:
+ENTRY(__lshrdi3)
 ENTRY(__aeabi_llsr)
 
 	subs	r3, r2, #32
 	rsb	ip, r2, #32
 	movmi	al, al, lsr r2
 	movpl	al, ah, lsr r3
-	orrmi	al, al, ah, lsl ip
+ ARM(	orrmi	al, al, ah, lsl ip	)
+ THUMB(	lslmi	r3, ah, ip		)
+ THUMB(	orrmi	al, al, r3		)
 	mov	ah, ah, lsr r2
-	mov	pc, lr
+	ret	lr
+
+ENDPROC(__lshrdi3)
 ENDPROC(__aeabi_llsr)