csky: Optimize arch_sync_dma_for_cpu/device with dma_inv_range

DMA_FROM_DEVICE only need to read dma data of memory into CPU cache,
so there is no need to clear cache before. Also clear + inv for
DMA_FROM_DEVICE won't cause problem, because the memory range for dma
won't be touched by software during dma working.

Changes for V2:
 - Remove clr cache and ignore the DMA_TO_DEVICE in _for_cpu.
 - Change inv to wbinv cache with DMA_FROM_DEVICE in _for_device.
Signed-off-by: Guo Ren <ren_guo@c-sky.com>
Cc: Arnd Bergmann <arnd@arndb.de>

arch/csky/include/asm/cache.h

@@ -24,6 +24,7 @@ void cache_wbinv_range(unsigned long start, unsigned long end);
 void cache_wbinv_all(void);
 
 void dma_wbinv_range(unsigned long start, unsigned long end);
+void dma_inv_range(unsigned long start, unsigned long end);
 void dma_wb_range(unsigned long start, unsigned long end);
 
 #endif

arch/csky/mm/cachev1.c

@@ -120,7 +120,12 @@ void dma_wbinv_range(unsigned long start, unsigned long end)
 	cache_op_range(start, end, DATA_CACHE|CACHE_CLR|CACHE_INV, 1);
 }
 
+void dma_inv_range(unsigned long start, unsigned long end)
+{
+	cache_op_range(start, end, DATA_CACHE|CACHE_CLR|CACHE_INV, 1);
+}
+
 void dma_wb_range(unsigned long start, unsigned long end)
 {
-	cache_op_range(start, end, DATA_CACHE|CACHE_INV, 1);
+	cache_op_range(start, end, DATA_CACHE|CACHE_CLR|CACHE_INV, 1);
 }

arch/csky/mm/cachev2.c

@@ -69,11 +69,20 @@ void dma_wbinv_range(unsigned long start, unsigned long end)
 	sync_is();
 }
 
+void dma_inv_range(unsigned long start, unsigned long end)
+{
+	unsigned long i = start & ~(L1_CACHE_BYTES - 1);
+
+	for (; i < end; i += L1_CACHE_BYTES)
+		asm volatile("dcache.iva %0\n"::"r"(i):"memory");
+	sync_is();
+}
+
 void dma_wb_range(unsigned long start, unsigned long end)
 {
 	unsigned long i = start & ~(L1_CACHE_BYTES - 1);
 
 	for (; i < end; i += L1_CACHE_BYTES)
-		asm volatile("dcache.civa %0\n"::"r"(i):"memory");
+		asm volatile("dcache.cva %0\n"::"r"(i):"memory");
 	sync_is();
 }

arch/csky/mm/dma-mapping.c

@@ -85,11 +85,10 @@ void arch_sync_dma_for_cpu(struct device *dev, phys_addr_t paddr,
 {
 	switch (dir) {
 	case DMA_TO_DEVICE:
-		cache_op(paddr, size, dma_wb_range);
-		break;
+		return;
 	case DMA_FROM_DEVICE:
 	case DMA_BIDIRECTIONAL:
-		cache_op(paddr, size, dma_wbinv_range);
+		cache_op(paddr, size, dma_inv_range);
 		break;
 	default:
 		BUG();