ARM: 6528/1: Use CTR for the I-cache line size on ARMv7

The current implementation of the v7_coherent_*_range function assumes
that the D and I cache lines have the same size, which is incorrect
architecturally. This patch adds the icache_line_size macro which reads
the CTR register. The main loop in v7_coherent_*_range is split in two
independent loops or the D and I caches. This also has the performance
advantage that the DSB is moved outside the main loop.

Reported-by: Kevin Sapp <ksapp@quicinc.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
diff --git a/arch/arm/mm/proc-macros.S b/arch/arm/mm/proc-macros.S
index 321555b..b795afd 100644
--- a/arch/arm/mm/proc-macros.S
+++ b/arch/arm/mm/proc-macros.S
@@ -72,6 +72,16 @@
 	mov	\reg, \reg, lsl \tmp		@ actual cache line size
 	.endm
 
+/*
+ * icache_line_size - get the minimum I-cache line size from the CTR register
+ * on ARMv7.
+ */
+	.macro	icache_line_size, reg, tmp
+	mrc	p15, 0, \tmp, c0, c0, 1		@ read ctr
+	and	\tmp, \tmp, #0xf		@ cache line size encoding
+	mov	\reg, #4			@ bytes per word
+	mov	\reg, \reg, lsl \tmp		@ actual cache line size
+	.endm
 
 /*
  * Sanity check the PTE configuration for the code below - which makes