Fix swiotlb_sync_single_range()

If the swiotlb maps a multi-slab region, swiotlb_sync_single_range() can be
invoked to sync a sub-region which does not include the first slab.
Unfortunately io_tlb_orig_addr[] is only initialised for the first slab,
and hence the call to sync_single() will read a garbage orig_addr in this
case.

This patch fixes the issue by initialising all mapped slabs in
io_tlb_orig_addr[].  It also correctly adjusts the buffer pointer in
sync_single() to handle the case that the given dma_addr is not aligned on
a slab boundary.

Signed-off-by: Keir Fraser <keir.fraser@cl.cam.ac.uk>
Cc: "Luck, Tony" <tony.luck@intel.com>
Acked-by: Andi Kleen <ak@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
diff --git a/lib/swiotlb.c b/lib/swiotlb.c
index 10c13ad..a7381d5 100644
--- a/lib/swiotlb.c
+++ b/lib/swiotlb.c
@@ -357,7 +357,8 @@
 	 * This is needed when we sync the memory.  Then we sync the buffer if
 	 * needed.
 	 */
-	io_tlb_orig_addr[index] = buffer;
+	for (i = 0; i < nslots; i++)
+		io_tlb_orig_addr[index+i] = buffer + (i << IO_TLB_SHIFT);
 	if (dir == DMA_TO_DEVICE || dir == DMA_BIDIRECTIONAL)
 		memcpy(dma_addr, buffer, size);
 
@@ -418,6 +419,8 @@
 	int index = (dma_addr - io_tlb_start) >> IO_TLB_SHIFT;
 	char *buffer = io_tlb_orig_addr[index];
 
+	buffer += ((unsigned long)dma_addr & ((1 << IO_TLB_SHIFT) - 1));
+
 	switch (target) {
 	case SYNC_FOR_CPU:
 		if (likely(dir == DMA_FROM_DEVICE || dir == DMA_BIDIRECTIONAL))