ARM: cache: Move the cp15 CR register read before flushing the cache.

The following is the cleanup sequence in arch/arm/cpu/armv7/cpu.c

int cleanup_before_linux(void)
{
 ...
 ...
 dcache_disable();
 v7_outer_cache_disable();
 invalidate_dcache_all();
}

 1) invalidate_dcache_all call expects that all the caches has been
 flushed, invalidated and there are no dirty entries prior to its
 execution.  In the above sequence dcache_disable() flushes, invalidates
 the caches and turns off the  mmu. But after it cleanups the cache
 and before the mmu is disabled  there is a cp_delay() function which
 has STR instruction. On certain cores like the cortex-a15, cache hit
 and a write can happen to a cache line even when the dcache is
 disabled. So the above mentioned STR instruction creates a dirty entry
 after cleaning. The mmu gets disabled after this.

 2) invalidate_dcache_all invalidates the cache lines. Again on
 cores like cortex-a15, invalidate instruction flushes the dirty
 line as well. So some times the dirty line from sequence 1
 can corrupt the memory resulting in a crash.

 Fixing this by moving the get_cr() and cp_delay() calls before
 cleaning up the cache, thus avoiding the dirty entry.

Signed-off-by: R Sricharan <r.sricharan@ti.com>
diff --git a/arch/arm/lib/cache-cp15.c b/arch/arm/lib/cache-cp15.c
index e6c3eae..939de10 100644
--- a/arch/arm/lib/cache-cp15.c
+++ b/arch/arm/lib/cache-cp15.c
@@ -115,17 +115,17 @@
 {
 	uint32_t reg;
 
+	reg = get_cr();
+	cp_delay();
+
 	if (cache_bit == CR_C) {
 		/* if cache isn;t enabled no need to disable */
-		reg = get_cr();
 		if ((reg & CR_C) != CR_C)
 			return;
 		/* if disabling data cache, disable mmu too */
 		cache_bit |= CR_M;
 		flush_dcache_all();
 	}
-	reg = get_cr();
-	cp_delay();
 	set_cr(reg & ~cache_bit);
 }
 #endif