ARC: dma [IOC] Enable per device io coherency

So far the IOC treatment was global on ARC, being turned on (or off)
for all devices in the system. With this patch, this can now be done
per device using the "dma-coherent" DT property; IOW with this patch
we can use both HW-coherent and regular DMA peripherals simultaneously.

The changes involved are too many so enlisting the summary below:

1. common code calls ARC arch_setup_dma_ops() per device.

2. For coherent dma (IOC) it plugs in generic @dma_direct_ops which
   doesn't need any arch specific backend: No need for any explicit
   cache flushes or MMU mappings to provide for uncached access

   - dma_(map|sync)_single* return early as corresponding dma ops callbacks
     are NULL in generic code.
     So arch_sync_dma_*() -> dma_cache_*() need not handle the coherent
     dma case, hence drop ARC __dma_cache_*_ioc() which were no-op anyways

3. For noncoherent dma (non IOC) generic @dma_noncoherent_ops is used
   which in turns calls ARC specific routines

   - arch_dma_alloc() no longer checks for @ioc_enable since this is
     called only for !IOC case.

Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Eugeniy Paltsev <Eugeniy.Paltsev@synopsys.com>
Signed-off-by: Vineet Gupta <vgupta@synopsys.com>
[vgupta: rewrote changelog]

1 files changed, 8 insertions, 15 deletions

diff --git a/arch/arc/mm/cache.c b/arch/arc/mm/cache.c
index 25c631942500..2d389cab46ba 100644
--- a/arch/arc/mm/cache.c
+++ b/arch/arc/mm/cache.c
@@ -65,7 +65,7 @@ char *arc_cache_mumbojumbo(int c, char *buf, int len)
 
 	n += scnprintf(buf + n, len - n, "Peripherals\t: %#lx%s%s\n",
 		       perip_base,
-		       IS_AVAIL3(ioc_exists, ioc_enable, ", IO-Coherency "));
+		       IS_AVAIL3(ioc_exists, ioc_enable, ", IO-Coherency (per-device) "));
 
 	return buf;
 }
@@ -897,15 +897,6 @@ static void __dma_cache_wback_slc(phys_addr_t start, unsigned long sz)
 }
 
 /*
- * DMA ops for systems with IOC
- * IOC hardware snoops all DMA traffic keeping the caches consistent with
- * memory - eliding need for any explicit cache maintenance of DMA buffers
- */
-static void __dma_cache_wback_inv_ioc(phys_addr_t start, unsigned long sz) {}
-static void __dma_cache_inv_ioc(phys_addr_t start, unsigned long sz) {}
-static void __dma_cache_wback_ioc(phys_addr_t start, unsigned long sz) {}
-
-/*
  * Exported DMA API
  */
 void dma_cache_wback_inv(phys_addr_t start, unsigned long sz)
@@ -1264,11 +1255,7 @@ void __init arc_cache_init_master(void)
 	if (is_isa_arcv2() && ioc_enable)
 		arc_ioc_setup();
 
-	if (is_isa_arcv2() && ioc_enable) {
-		__dma_cache_wback_inv = __dma_cache_wback_inv_ioc;
-		__dma_cache_inv = __dma_cache_inv_ioc;
-		__dma_cache_wback = __dma_cache_wback_ioc;
-	} else if (is_isa_arcv2() && l2_line_sz && slc_enable) {
+	if (is_isa_arcv2() && l2_line_sz && slc_enable) {
 		__dma_cache_wback_inv = __dma_cache_wback_inv_slc;
 		__dma_cache_inv = __dma_cache_inv_slc;
 		__dma_cache_wback = __dma_cache_wback_slc;
@@ -1277,6 +1264,12 @@ void __init arc_cache_init_master(void)
 		__dma_cache_inv = __dma_cache_inv_l1;
 		__dma_cache_wback = __dma_cache_wback_l1;
 	}
+	/*
+	 * In case of IOC (say IOC+SLC case), pointers above could still be set
+	 * but end up not being relevant as the first function in chain is not
+	 * called at all for @dma_direct_ops
+	 *     arch_sync_dma_for_cpu() -> dma_cache_*() -> __dma_cache_*()
+	 */
 }
 
 void __ref arc_cache_init(void)