ARM: cns3xxx: Add support for L2 Cache Controller

CNS3xxx SOCs have L310-compatible cache controller, so let's use it.

With this patch benchmarking with 'gzip' shows that performance is
doubled, and I'm still able to boot full-fledged userland over NFS
(using PCIe NIC), so the support should be pretty robust.

p.s. While CNS3xxx reports that it has PL310, it still needs to wait
on cache line operations, so we should not select 'CACHE_PL310',
which is a micro-optimization that removes these waits for v7 CPUs.
Someday we'd better rename CACHE_PL310 Kconfig option into
NO_CACHE_WAIT or something less ambiguous.
Signed-off-by: NAnton Vorontsov <avorontsov@mvista.com>

arch/arm/mach-cns3xxx/cns3420vb.c

@@ -170,6 +170,8 @@ static struct platform_device *cns3420_pdevs[] __initdata = {
 
 static void __init cns3420_init(void)
 {
+	cns3xxx_l2x0_init();
+
 	platform_add_devices(cns3420_pdevs, ARRAY_SIZE(cns3420_pdevs));
 
 	cns3xxx_ahci_init();

arch/arm/mach-cns3xxx/core.c

@@ -16,6 +16,7 @@
 #include <asm/mach/time.h>
 #include <asm/mach/irq.h>
 #include <asm/hardware/gic.h>
+#include <asm/hardware/cache-l2x0.h>
 #include <mach/cns3xxx.h>
 #include "core.h"
 
@@ -244,3 +245,45 @@ static void __init cns3xxx_timer_init(void)
 struct sys_timer cns3xxx_timer = {
 	.init = cns3xxx_timer_init,
 };
+
+#ifdef CONFIG_CACHE_L2X0
+
+void __init cns3xxx_l2x0_init(void)
+{
+	void __iomem *base = ioremap(CNS3XXX_L2C_BASE, SZ_4K);
+	u32 val;
+
+	if (WARN_ON(!base))
+		return;
+
+	/*
+	 * Tag RAM Control register
+	 *
+	 * bit[10:8]	- 1 cycle of write accesses latency
+	 * bit[6:4]	- 1 cycle of read accesses latency
+	 * bit[3:0]	- 1 cycle of setup latency
+	 *
+	 * 1 cycle of latency for setup, read and write accesses
+	 */
+	val = readl(base + L2X0_TAG_LATENCY_CTRL);
+	val &= 0xfffff888;
+	writel(val, base + L2X0_TAG_LATENCY_CTRL);
+
+	/*
+	 * Data RAM Control register
+	 *
+	 * bit[10:8]	- 1 cycles of write accesses latency
+	 * bit[6:4]	- 1 cycles of read accesses latency
+	 * bit[3:0]	- 1 cycle of setup latency
+	 *
+	 * 1 cycle of latency for setup, read and write accesses
+	 */
+	val = readl(base + L2X0_DATA_LATENCY_CTRL);
+	val &= 0xfffff888;
+	writel(val, base + L2X0_DATA_LATENCY_CTRL);
+
+	/* 32 KiB, 8-way, parity disable */
+	l2x0_init(base, 0x00540000, 0xfe000fff);
+}
+
+#endif /* CONFIG_CACHE_L2X0 */

arch/arm/mach-cns3xxx/core.h

@@ -13,6 +13,12 @@
 
 extern struct sys_timer cns3xxx_timer;
 
+#ifdef CONFIG_CACHE_L2X0
+void __init cns3xxx_l2x0_init(void);
+#else
+static inline void cns3xxx_l2x0_init(void) {}
+#endif /* CONFIG_CACHE_L2X0 */
+
 void __init cns3xxx_map_io(void);
 void __init cns3xxx_init_irq(void);
 void cns3xxx_power_off(void);

arch/arm/mm/Kconfig

@@ -821,7 +821,7 @@ config CACHE_L2X0
 	depends on REALVIEW_EB_ARM11MP || MACH_REALVIEW_PB11MP || MACH_REALVIEW_PB1176 || \
 		   REALVIEW_EB_A9MP || SOC_IMX35 || SOC_IMX31 || MACH_REALVIEW_PBX || \
 		   ARCH_NOMADIK || ARCH_OMAP4 || ARCH_EXYNOS4 || ARCH_TEGRA || \
-		   ARCH_U8500 || ARCH_VEXPRESS_CA9X4 || ARCH_SHMOBILE
+		   ARCH_U8500 || ARCH_VEXPRESS_CA9X4 || ARCH_SHMOBILE || ARCH_CNS3XXX
 	default y
 	select OUTER_CACHE
 	select OUTER_CACHE_SYNC