Blackfin arch: rewrite dma_memcpy() and dma in/out functions

- unify all dma in/out functions (takes ~35 lines of code now)
- unify dma_memcpy with dma in/out functions (1 place that touches MDMA0
  registers)
- add support for 32bit transfers
- cleanup dma_memcpy code to be much more readable
- irqs are disabled only while programming MDMA registers rather than
  the entire transaction
Signed-off-by: Mike Frysinger <vapier.adi@gmail.com>
Signed-off-by: Bryan Wu <cooloney@kernel.org>

arch/blackfin/include/asm/dma.h

@@ -178,6 +178,7 @@ void dma_enable_irq(unsigned int channel);
 void clear_dma_irqstat(unsigned int channel);
 void *dma_memcpy(void *dest, const void *src, size_t count);
 void *safe_dma_memcpy(void *dest, const void *src, size_t count);
+void blackfin_dma_early_init(void);
 
 extern int channel2irq(unsigned int channel);
 extern struct dma_register *dma_io_base_addr[MAX_DMA_CHANNELS];

arch/blackfin/kernel/setup.c

@@ -154,6 +154,8 @@ void __init bfin_relocate_l1_mem(void)
 	unsigned long l1_data_b_length;
 	unsigned long l2_length;
 
+	blackfin_dma_early_init();
+
 	l1_code_length = _etext_l1 - _stext_l1;
 	if (l1_code_length > L1_CODE_LENGTH)
 		panic("L1 Instruction SRAM Overflow\n");