ARM: 9169/1: entry: fix Thumb2 bug in iWMMXt exception handling

The Thumb2 version of the FP exception handling entry code treats the
register holding the CP number (R8) differently, resulting in the iWMMXT
CP number check to be incorrect.

Fix this by unifying the ARM and Thumb2 code paths, and switch the
order of the additions of the TI_USED_CP offset and the shifted CP
index.

Cc: <stable@vger.kernel.org>
Fixes: b86040a5 ("Thumb-2: Implementation of the unified start-up and exceptions code")
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>

arch/arm/kernel/entry-armv.S

@@ -596,11 +596,9 @@ call_fpe:
 	tstne	r0, #0x04000000			@ bit 26 set on both ARM and Thumb-2
 	reteq	lr
 	and	r8, r0, #0x00000f00		@ mask out CP number
- THUMB(	lsr	r8, r8, #8		)
 	mov	r7, #1
-	add	r6, r10, #TI_USED_CP
- ARM(	strb	r7, [r6, r8, lsr #8]	)	@ set appropriate used_cp[]
- THUMB(	strb	r7, [r6, r8]		)	@ set appropriate used_cp[]
+	add	r6, r10, r8, lsr #8		@ add used_cp[] array offset first
+	strb	r7, [r6, #TI_USED_CP]		@ set appropriate used_cp[]
 #ifdef CONFIG_IWMMXT
 	@ Test if we need to give access to iWMMXt coprocessors
 	ldr	r5, [r10, #TI_FLAGS]
@@ -609,7 +607,7 @@ call_fpe:
 	bcs	iwmmxt_task_enable
 #endif
  ARM(	add	pc, pc, r8, lsr #6	)
- THUMB(	lsl	r8, r8, #2		)
+ THUMB(	lsr	r8, r8, #6		)
  THUMB(	add	pc, r8			)
 	nop