ARM: l2x0: Optimise the range based operations

For the big buffers which are in excess of cache size, the maintaince
operations by PA are very slow. For such buffers the maintainace
operations can be speeded up by using the WAY based method.
Signed-off-by: NSantosh Shilimkar <santosh.shilimkar@ti.com>
Acked-by: NCatalin Marinas <catalin.marinas@arm.com>
Acked-by: NLinus Walleij <linus.walleij@stericsson.com>

arch/arm/mm/cache-l2x0.c

@@ -125,6 +125,18 @@ static void l2x0_flush_all(void)
 	spin_unlock_irqrestore(&l2x0_lock, flags);
 }
 
+static void l2x0_clean_all(void)
+{
+	unsigned long flags;
+
+	/* clean all ways */
+	spin_lock_irqsave(&l2x0_lock, flags);
+	writel_relaxed(l2x0_way_mask, l2x0_base + L2X0_CLEAN_WAY);
+	cache_wait_way(l2x0_base + L2X0_CLEAN_WAY, l2x0_way_mask);
+	cache_sync();
+	spin_unlock_irqrestore(&l2x0_lock, flags);
+}
+
 static void l2x0_inv_all(void)
 {
 	unsigned long flags;
@@ -183,6 +195,11 @@ static void l2x0_clean_range(unsigned long start, unsigned long end)
 	void __iomem *base = l2x0_base;
 	unsigned long flags;
 
+	if ((end - start) >= l2x0_size) {
+		l2x0_clean_all();
+		return;
+	}
+
 	spin_lock_irqsave(&l2x0_lock, flags);
 	start &= ~(CACHE_LINE_SIZE - 1);
 	while (start < end) {
@@ -208,6 +225,11 @@ static void l2x0_flush_range(unsigned long start, unsigned long end)
 	void __iomem *base = l2x0_base;
 	unsigned long flags;
 
+	if ((end - start) >= l2x0_size) {
+		l2x0_flush_all();
+		return;
+	}
+
 	spin_lock_irqsave(&l2x0_lock, flags);
 	start &= ~(CACHE_LINE_SIZE - 1);
 	while (start < end) {