ARM: 8815/1: V7M: align v7m_dma_inv_range() with v7 counterpart

Chris has discovered and reported that v7_dma_inv_range() may corrupt
memory if address range is not aligned to cache line size.

Since the whole cache-v7m.S was lifted form cache-v7.S the same
observation applies to v7m_dma_inv_range(). So the fix just mirrors
what has been done for v7 with a little specific of M-class.

Cc: Chris Cole <chris@sageembedded.com>
Signed-off-by: Vladimir Murzin <vladimir.murzin@arm.com>
Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>

arch/arm/mm/cache-v7m.S

@@ -73,9 +73,11 @@
 /*
  * dcimvac: Invalidate data cache line by MVA to PoC
  */
-.macro dcimvac, rt, tmp
-	v7m_cacheop \rt, \tmp, V7M_SCB_DCIMVAC
+.irp    c,,eq,ne,cs,cc,mi,pl,vs,vc,hi,ls,ge,lt,gt,le,hs,lo
+.macro dcimvac\c, rt, tmp
+	v7m_cacheop \rt, \tmp, V7M_SCB_DCIMVAC, \c
 .endm
+.endr
 
 /*
  * dccmvau: Clean data cache line by MVA to PoU
@@ -369,14 +371,16 @@ v7m_dma_inv_range:
 	tst	r0, r3
 	bic	r0, r0, r3
 	dccimvacne r0, r3
+	addne	r0, r0, r2
 	subne	r3, r2, #1	@ restore r3, corrupted by v7m's dccimvac
 	tst	r1, r3
 	bic	r1, r1, r3
 	dccimvacne r1, r3
-1:
-	dcimvac r0, r3
-	add	r0, r0, r2
 	cmp	r0, r1
+1:
+	dcimvaclo r0, r3
+	addlo	r0, r0, r2
+	cmplo	r0, r1
 	blo	1b
 	dsb	st
 	ret	lr