Revisions 181296 and  195779 added the cache fixes.

Below are a few more.

1) vm_machdep.c: remove the dangling allocations so they do not
   un-necessarily turn off the cache in the future.
2) busdma_machdep.c: remove the same amount than shadow mapped.

Index: arm/arm/vm_machdep.c
===================================================================
--- arm/arm/vm_machdep.c	(revision 198246)
+++ arm/arm/vm_machdep.c	(working copy)
@@ -169,6 +169,9 @@ sf_buf_free(struct sf_buf *sf)
 	 if (sf->ref_count == 0) {
 		 TAILQ_INSERT_TAIL(&sf_buf_freelist, sf, free_entry);
 		 nsfbufsused--;
+		 pmap_kremove(sf->kva);
+		 sf->m = NULL;
+		 LIST_REMOVE(sf, list_entry);
 		 if (sf_buf_alloc_want > 0)
 			 wakeup_one(&sf_buf_freelist);
 	 }
@@ -449,9 +452,12 @@ arm_unmap_nocache(void *addr, vm_size_t size)
 
 	size = round_page(size);
 	i = (raddr - arm_nocache_startaddr) / (PAGE_SIZE);
-	for (; size > 0; size -= PAGE_SIZE, i++)
+	for (; size > 0; size -= PAGE_SIZE, i++) {
 		arm_nocache_allocated[i / BITS_PER_INT] &= ~(1 << (i % 
 		    BITS_PER_INT));
+		pmap_kremove(raddr);
+		raddr += PAGE_SIZE;
+	}
 }
 
 #ifdef ARM_USE_SMALL_ALLOC
Index: arm/arm/busdma_machdep.c
===================================================================
--- arm/arm/busdma_machdep.c	(revision 198246)
+++ arm/arm/busdma_machdep.c	(working copy)
@@ -649,7 +649,8 @@ bus_dmamem_free(bus_dma_tag_t dmat, void *vaddr, b
 		KASSERT(map->allocbuffer == vaddr,
 		    ("Trying to freeing the wrong DMA buffer"));
 		vaddr = map->origbuffer;
-		arm_unmap_nocache(map->allocbuffer, dmat->maxsize);
+		arm_unmap_nocache(map->allocbuffer,
+			dmat->maxsize + ((vm_offset_t)vaddr & PAGE_MASK));
 	}
         if (dmat->maxsize <= PAGE_SIZE &&
 	   dmat->alignment < dmat->maxsize &&