Merge branch 'stable/for-linus-5.14' of git://git.kernel.org/pub/scm/linux/kernel/git/konrad/swiotlb

Pull swiotlb fix from Konrad Rzeszutek Wilk:
 "A fix for the regression for the DMA operations where the offset was
  ignored and corruptions would appear.

  Going forward there will be a cleanups to make the offset and
  alignment logic more clearer and better test-cases to help with this"

* 'stable/for-linus-5.14' of git://git.kernel.org/pub/scm/linux/kernel/git/konrad/swiotlb:
  swiotlb: manipulate orig_addr when tlb_addr has offset
diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c
index 8ca7d50..e50df8d 100644
--- a/kernel/dma/swiotlb.c
+++ b/kernel/dma/swiotlb.c
@@ -335,6 +335,14 @@ void __init swiotlb_exit(void)
 }
 
 /*
+ * Return the offset into a iotlb slot required to keep the device happy.
+ */
+static unsigned int swiotlb_align_offset(struct device *dev, u64 addr)
+{
+	return addr & dma_get_min_align_mask(dev) & (IO_TLB_SIZE - 1);
+}
+
+/*
  * Bounce: copy the swiotlb buffer from or back to the original dma location
  */
 static void swiotlb_bounce(struct device *dev, phys_addr_t tlb_addr, size_t size,
@@ -346,10 +354,17 @@ static void swiotlb_bounce(struct device *dev, phys_addr_t tlb_addr, size_t size
 	size_t alloc_size = mem->slots[index].alloc_size;
 	unsigned long pfn = PFN_DOWN(orig_addr);
 	unsigned char *vaddr = phys_to_virt(tlb_addr);
+	unsigned int tlb_offset;
 
 	if (orig_addr == INVALID_PHYS_ADDR)
 		return;
 
+	tlb_offset = (tlb_addr & (IO_TLB_SIZE - 1)) -
+		     swiotlb_align_offset(dev, orig_addr);
+
+	orig_addr += tlb_offset;
+	alloc_size -= tlb_offset;
+
 	if (size > alloc_size) {
 		dev_WARN_ONCE(dev, 1,
 			"Buffer overflow detected. Allocation size: %zu. Mapping size: %zu.\n",
@@ -391,14 +406,6 @@ static void swiotlb_bounce(struct device *dev, phys_addr_t tlb_addr, size_t size
 #define slot_addr(start, idx)	((start) + ((idx) << IO_TLB_SHIFT))
 
 /*
- * Return the offset into a iotlb slot required to keep the device happy.
- */
-static unsigned int swiotlb_align_offset(struct device *dev, u64 addr)
-{
-	return addr & dma_get_min_align_mask(dev) & (IO_TLB_SIZE - 1);
-}
-
-/*
  * Carefully handle integer overflow which can occur when boundary_mask == ~0UL.
  */
 static inline unsigned long get_max_slots(unsigned long boundary_mask)