arm64: mm: only initialize swiotlb when necessary

we only initialize swiotlb when swiotlb_force is true or not all system
memory is DMA-able, this trivial optimization saves us 64MB when
swiotlb is not necessary.
Signed-off-by: Jisheng Zhang <jszhang@marvell.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>

arch/arm64/mm/dma-mapping.c

@@ -19,6 +19,7 @@
 
 #include <linux/gfp.h>
 #include <linux/acpi.h>
+#include <linux/bootmem.h>
 #include <linux/export.h>
 #include <linux/slab.h>
 #include <linux/genalloc.h>
@@ -29,6 +30,8 @@
 
 #include <asm/cacheflush.h>
 
+static int swiotlb __read_mostly;
+
 static pgprot_t __get_dma_pgprot(struct dma_attrs *attrs, pgprot_t prot,
 				 bool coherent)
 {
@@ -341,6 +344,13 @@ static int __swiotlb_get_sgtable(struct device *dev, struct sg_table *sgt,
 	return ret;
 }
 
+static int __swiotlb_dma_supported(struct device *hwdev, u64 mask)
+{
+	if (swiotlb)
+		return swiotlb_dma_supported(hwdev, mask);
+	return 1;
+}
+
 static struct dma_map_ops swiotlb_dma_ops = {
 	.alloc = __dma_alloc,
 	.free = __dma_free,
@@ -354,7 +364,7 @@ static struct dma_map_ops swiotlb_dma_ops = {
 	.sync_single_for_device = __swiotlb_sync_single_for_device,
 	.sync_sg_for_cpu = __swiotlb_sync_sg_for_cpu,
 	.sync_sg_for_device = __swiotlb_sync_sg_for_device,
-	.dma_supported = swiotlb_dma_supported,
+	.dma_supported = __swiotlb_dma_supported,
 	.mapping_error = swiotlb_dma_mapping_error,
 };
 
@@ -513,6 +523,9 @@ EXPORT_SYMBOL(dummy_dma_ops);
 
 static int __init arm64_dma_init(void)
 {
+	if (swiotlb_force || max_pfn > (arm64_dma_phys_limit >> PAGE_SHIFT))
+		swiotlb = 1;
+
 	return atomic_pool_init();
 }
 arch_initcall(arm64_dma_init);

arch/arm64/mm/init.c

@@ -403,7 +403,8 @@ static void __init free_unused_memmap(void)
  */
 void __init mem_init(void)
 {
-	swiotlb_init(1);
+	if (swiotlb_force || max_pfn > (arm64_dma_phys_limit >> PAGE_SHIFT))
+		swiotlb_init(1);
 
 	set_max_mapnr(pfn_to_page(max_pfn) - mem_map);