ARM: Improve the L2 cache performance when PL310 is used

With this L2 cache controller, the cache maintenance by PA and sync
operations are atomic and do not require a "wait" loop. This patch
conditionally defines the cache_wait() function.

Since L2x0 cache controllers do not work with ARMv7 CPUs, the patch
automatically enables CACHE_PL310 when only CPU_V7 is defined.
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>

arch/arm/mm/Kconfig

@@ -779,6 +779,14 @@ config CACHE_L2X0
 	help
 	  This option enables the L2x0 PrimeCell.
 
+config CACHE_PL310
+	bool
+	depends on CACHE_L2X0
+	default y if CPU_V7 && !CPU_V6
+	help
+	  This option enables optimisations for the PL310 cache
+	  controller.
+
 config CACHE_TAUROS2
 	bool "Enable the Tauros2 L2 cache controller"
 	depends on (ARCH_DOVE || ARCH_MMP)

arch/arm/mm/cache-l2x0.c

@@ -29,13 +29,22 @@ static void __iomem *l2x0_base;
 static DEFINE_SPINLOCK(l2x0_lock);
 static uint32_t l2x0_way_mask;	/* Bitmask of active ways */
 
-static inline void cache_wait(void __iomem *reg, unsigned long mask)
+static inline void cache_wait_way(void __iomem *reg, unsigned long mask)
 {
-	/* wait for the operation to complete */
+	/* wait for cache operation by line or way to complete */
 	while (readl_relaxed(reg) & mask)
 		;
 }
 
+#ifdef CONFIG_CACHE_PL310
+static inline void cache_wait(void __iomem *reg, unsigned long mask)
+{
+	/* cache operations by line are atomic on PL310 */
+}
+#else
+#define cache_wait	cache_wait_way
+#endif
+
 static inline void cache_sync(void)
 {
 	void __iomem *base = l2x0_base;
@@ -110,7 +119,7 @@ static inline void l2x0_inv_all(void)
 	/* invalidate all ways */
 	spin_lock_irqsave(&l2x0_lock, flags);
 	writel_relaxed(l2x0_way_mask, l2x0_base + L2X0_INV_WAY);
-	cache_wait(l2x0_base + L2X0_INV_WAY, l2x0_way_mask);
+	cache_wait_way(l2x0_base + L2X0_INV_WAY, l2x0_way_mask);
 	cache_sync();
 	spin_unlock_irqrestore(&l2x0_lock, flags);
 }