diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index af516c3..0d425e1 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -2630,6 +2630,7 @@
 	 * Don't limit the IOMMU merged segment size.
 	 */
 	dma_set_max_seg_size(dev->dev, 0xffffffff);
+	dma_set_min_align_mask(dev->dev, dev->ctrl.page_size - 1);
 
 	mutex_unlock(&dev->shutdown_lock);
 
diff --git a/include/linux/device.h b/include/linux/device.h
index 3414b5a..4204396 100644
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -993,6 +993,7 @@
 	 * sg limitations.
 	 */
 	unsigned int max_segment_size;
+	unsigned int min_align_mask;
 	unsigned long segment_boundary_mask;
 };
 
diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h
index 4d45067..953e1e3 100644
--- a/include/linux/dma-mapping.h
+++ b/include/linux/dma-mapping.h
@@ -751,6 +751,22 @@
 	return -EIO;
 }
 
+static inline unsigned int dma_get_min_align_mask(struct device *dev)
+{
+	if (dev->dma_parms)
+		return dev->dma_parms->min_align_mask;
+	return 0;
+}
+
+static inline int dma_set_min_align_mask(struct device *dev,
+		unsigned int min_align_mask)
+{
+	if (WARN_ON_ONCE(!dev->dma_parms))
+		return -EIO;
+	dev->dma_parms->min_align_mask = min_align_mask;
+	return 0;
+}
+
 static inline int dma_get_cache_alignment(void)
 {
 #ifdef ARCH_DMA_MINALIGN
diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h
index 0a8fced..f7aadd2 100644
--- a/include/linux/swiotlb.h
+++ b/include/linux/swiotlb.h
@@ -29,6 +29,7 @@
  * controllable.
  */
 #define IO_TLB_SHIFT 11
+#define IO_TLB_SIZE (1 << IO_TLB_SHIFT)
 
 extern void swiotlb_init(int verbose);
 int swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, int verbose);
diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c
index f99b79d..16560a2 100644
--- a/kernel/dma/swiotlb.c
+++ b/kernel/dma/swiotlb.c
@@ -49,9 +49,6 @@
 #define CREATE_TRACE_POINTS
 #include <trace/events/swiotlb.h>
 
-#define OFFSET(val,align) ((unsigned long)	\
-	                   ( (val) & ( (align) - 1)))
-
 #define SLABS_PER_PAGE (1 << (PAGE_SHIFT - IO_TLB_SHIFT))
 
 /*
@@ -177,6 +174,16 @@
 	       bytes >> 20);
 }
 
+static inline unsigned long io_tlb_offset(unsigned long val)
+{
+	return val & (IO_TLB_SEGSIZE - 1);
+}
+
+static inline unsigned long nr_slots(u64 val)
+{
+	return DIV_ROUND_UP(val, IO_TLB_SIZE);
+}
+
 /*
  * Early SWIOTLB allocation may be too early to allow an architecture to
  * perform the desired operations.  This function allows the architecture to
@@ -226,7 +233,7 @@
 		      __func__, alloc_size, PAGE_SIZE);
 
 	for (i = 0; i < io_tlb_nslabs; i++) {
-		io_tlb_list[i] = IO_TLB_SEGSIZE - OFFSET(i, IO_TLB_SEGSIZE);
+		io_tlb_list[i] = IO_TLB_SEGSIZE - io_tlb_offset(i);
 		io_tlb_orig_addr[i] = INVALID_PHYS_ADDR;
 	}
 	io_tlb_index = 0;
@@ -360,7 +367,7 @@
 		goto cleanup4;
 
 	for (i = 0; i < io_tlb_nslabs; i++) {
-		io_tlb_list[i] = IO_TLB_SEGSIZE - OFFSET(i, IO_TLB_SEGSIZE);
+		io_tlb_list[i] = IO_TLB_SEGSIZE - io_tlb_offset(i);
 		io_tlb_orig_addr[i] = INVALID_PHYS_ADDR;
 	}
 	io_tlb_index = 0;
@@ -446,22 +453,121 @@
 	}
 }
 
-phys_addr_t swiotlb_tbl_map_single(struct device *hwdev,
-				   dma_addr_t tbl_dma_addr,
-				   phys_addr_t orig_addr,
-				   size_t mapping_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)
+{
+	if (boundary_mask == ~0UL)
+		return 1UL << (BITS_PER_LONG - IO_TLB_SHIFT);
+	return nr_slots(boundary_mask + 1);
+}
+
+static unsigned int wrap_index(unsigned int index)
+{
+	if (index >= io_tlb_nslabs)
+		return 0;
+	return index;
+}
+
+/*
+ * Find a suitable number of IO TLB entries size that will fit this request and
+ * allocate a buffer from that IO TLB pool.
+ */
+static int find_slots(struct device *dev, phys_addr_t orig_addr,
+		size_t alloc_size)
+{
+	unsigned long boundary_mask = dma_get_seg_boundary(dev);
+	dma_addr_t tbl_dma_addr =
+		__phys_to_dma(dev, io_tlb_start) & boundary_mask;
+	unsigned long max_slots = get_max_slots(boundary_mask);
+	unsigned int iotlb_align_mask =
+		dma_get_min_align_mask(dev) & ~(IO_TLB_SIZE - 1);
+	unsigned int nslots = nr_slots(alloc_size), stride;
+	unsigned int index, wrap, count = 0, i;
+	unsigned long flags;
+
+	BUG_ON(!nslots);
+
+	/*
+	 * For mappings with an alignment requirement don't bother looping to
+	 * unaligned slots once we found an aligned one.  For allocations of
+	 * PAGE_SIZE or larger only look for page aligned allocations.
+	 */
+	stride = (iotlb_align_mask >> IO_TLB_SHIFT) + 1;
+	if (alloc_size >= PAGE_SIZE)
+		stride = max(stride, stride << (PAGE_SHIFT - IO_TLB_SHIFT));
+
+	spin_lock_irqsave(&io_tlb_lock, flags);
+	if (unlikely(nslots > io_tlb_nslabs - io_tlb_used))
+		goto not_found;
+
+	index = wrap = wrap_index(ALIGN(io_tlb_index, stride));
+	do {
+		if ((slot_addr(tbl_dma_addr, index) & iotlb_align_mask) !=
+		    (orig_addr & iotlb_align_mask)) {
+			index = wrap_index(index + 1);
+			continue;
+		}
+
+		/*
+		 * If we find a slot that indicates we have 'nslots' number of
+		 * contiguous buffers, we allocate the buffers from that slot
+		 * and mark the entries as '0' indicating unavailable.
+		 */
+		if (!iommu_is_span_boundary(index, nslots,
+					   nr_slots(tbl_dma_addr),
+					   max_slots)) {
+			if (io_tlb_list[index] >= nslots)
+				goto found;
+		}
+		index = wrap_index(index + stride);
+	} while (index != wrap);
+
+not_found:
+	spin_unlock_irqrestore(&io_tlb_lock, flags);
+	return -1;
+
+found:
+	for (i = index; i < index + nslots; i++)
+		io_tlb_list[i] = 0;
+	for (i = index - 1;
+	     io_tlb_offset(i) != IO_TLB_SEGSIZE - 1 &&
+	     io_tlb_list[i]; i--)
+		io_tlb_list[i] = ++count;
+
+	/*
+	 * Update the indices to avoid searching in the next round.
+	 */
+	if (index + nslots < io_tlb_nslabs)
+		io_tlb_index = index + nslots;
+	else
+		io_tlb_index = 0;
+
+	io_tlb_used += nslots;
+
+	spin_unlock_irqrestore(&io_tlb_lock, flags);
+	return index;
+}
+
+phys_addr_t swiotlb_tbl_map_single(struct device *dev, dma_addr_t dma_addr,
+				   phys_addr_t orig_addr, size_t mapping_size,
 				   size_t alloc_size,
 				   enum dma_data_direction dir,
 				   unsigned long attrs)
 {
-	unsigned long flags;
+	unsigned int offset = swiotlb_align_offset(dev, orig_addr);
+	unsigned int index, i;
 	phys_addr_t tlb_addr;
-	unsigned int nslots, stride, index, wrap;
-	int i;
-	unsigned long mask;
-	unsigned long offset_slots;
-	unsigned long max_slots;
-	unsigned long tmp_io_tlb_used;
 
 	if (no_iotlb_memory)
 		panic("Can not allocate SWIOTLB buffer earlier and can't now provide you with the DMA bounce buffer");
@@ -470,107 +576,29 @@
 		pr_warn_once("Memory encryption is active and system is using DMA bounce buffers\n");
 
 	if (mapping_size > alloc_size) {
-		dev_warn_once(hwdev, "Invalid sizes (mapping: %zd bytes, alloc: %zd bytes)",
+		dev_warn_once(dev, "Invalid sizes (mapping: %zd bytes, alloc: %zd bytes)",
 			      mapping_size, alloc_size);
 		return (phys_addr_t)DMA_MAPPING_ERROR;
 	}
 
-	mask = dma_get_seg_boundary(hwdev);
-
-	tbl_dma_addr &= mask;
-
-	offset_slots = ALIGN(tbl_dma_addr, 1 << IO_TLB_SHIFT) >> IO_TLB_SHIFT;
-
-	/*
-	 * Carefully handle integer overflow which can occur when mask == ~0UL.
-	 */
-	max_slots = mask + 1
-		    ? ALIGN(mask + 1, 1 << IO_TLB_SHIFT) >> IO_TLB_SHIFT
-		    : 1UL << (BITS_PER_LONG - IO_TLB_SHIFT);
-
-	/*
-	 * For mappings greater than or equal to a page, we limit the stride
-	 * (and hence alignment) to a page size.
-	 */
-	nslots = ALIGN(alloc_size, 1 << IO_TLB_SHIFT) >> IO_TLB_SHIFT;
-	if (alloc_size >= PAGE_SIZE)
-		stride = (1 << (PAGE_SHIFT - IO_TLB_SHIFT));
-	else
-		stride = 1;
-
-	BUG_ON(!nslots);
-
-	/*
-	 * Find suitable number of IO TLB entries size that will fit this
-	 * request and allocate a buffer from that IO TLB pool.
-	 */
-	spin_lock_irqsave(&io_tlb_lock, flags);
-
-	if (unlikely(nslots > io_tlb_nslabs - io_tlb_used))
-		goto not_found;
-
-	index = ALIGN(io_tlb_index, stride);
-	if (index >= io_tlb_nslabs)
-		index = 0;
-	wrap = index;
-
-	do {
-		while (iommu_is_span_boundary(index, nslots, offset_slots,
-					      max_slots)) {
-			index += stride;
-			if (index >= io_tlb_nslabs)
-				index = 0;
-			if (index == wrap)
-				goto not_found;
-		}
-
-		/*
-		 * If we find a slot that indicates we have 'nslots' number of
-		 * contiguous buffers, we allocate the buffers from that slot
-		 * and mark the entries as '0' indicating unavailable.
-		 */
-		if (io_tlb_list[index] >= nslots) {
-			int count = 0;
-
-			for (i = index; i < (int) (index + nslots); i++)
-				io_tlb_list[i] = 0;
-			for (i = index - 1; (OFFSET(i, IO_TLB_SEGSIZE) != IO_TLB_SEGSIZE - 1) && io_tlb_list[i]; i--)
-				io_tlb_list[i] = ++count;
-			tlb_addr = io_tlb_start + (index << IO_TLB_SHIFT);
-
-			/*
-			 * Update the indices to avoid searching in the next
-			 * round.
-			 */
-			io_tlb_index = ((index + nslots) < io_tlb_nslabs
-					? (index + nslots) : 0);
-
-			goto found;
-		}
-		index += stride;
-		if (index >= io_tlb_nslabs)
-			index = 0;
-	} while (index != wrap);
-
-not_found:
-	tmp_io_tlb_used = io_tlb_used;
-
-	spin_unlock_irqrestore(&io_tlb_lock, flags);
-	if (!(attrs & DMA_ATTR_NO_WARN) && printk_ratelimit())
-		dev_warn(hwdev, "swiotlb buffer is full (sz: %zd bytes), total %lu (slots), used %lu (slots)\n",
-			 alloc_size, io_tlb_nslabs, tmp_io_tlb_used);
-	return (phys_addr_t)DMA_MAPPING_ERROR;
-found:
-	io_tlb_used += nslots;
-	spin_unlock_irqrestore(&io_tlb_lock, flags);
+	index = find_slots(dev, orig_addr, alloc_size + offset);
+	if (index == -1) {
+		if (!(attrs & DMA_ATTR_NO_WARN))
+			dev_warn_ratelimited(dev,
+	"swiotlb buffer is full (sz: %zd bytes), total %lu (slots), used %lu (slots)\n",
+				 alloc_size, io_tlb_nslabs, io_tlb_used);
+		return (phys_addr_t)DMA_MAPPING_ERROR;
+	}
 
 	/*
 	 * Save away the mapping from the original address to the DMA address.
 	 * This is needed when we sync the memory.  Then we sync the buffer if
 	 * needed.
 	 */
-	for (i = 0; i < nslots; i++)
-		io_tlb_orig_addr[index+i] = orig_addr + (i << IO_TLB_SHIFT);
+	for (i = 0; i < nr_slots(alloc_size + offset); i++)
+		io_tlb_orig_addr[index + i] = slot_addr(orig_addr, i);
+
+	tlb_addr = slot_addr(io_tlb_start, index) + offset;
 	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC) &&
 	    (dir == DMA_TO_DEVICE || dir == DMA_BIDIRECTIONAL))
 		swiotlb_bounce(orig_addr, tlb_addr, mapping_size, DMA_TO_DEVICE);
@@ -586,8 +614,9 @@
 			      enum dma_data_direction dir, unsigned long attrs)
 {
 	unsigned long flags;
-	int i, count, nslots = ALIGN(alloc_size, 1 << IO_TLB_SHIFT) >> IO_TLB_SHIFT;
-	int index = (tlb_addr - io_tlb_start) >> IO_TLB_SHIFT;
+	unsigned int offset = swiotlb_align_offset(hwdev, tlb_addr);
+	int i, count, nslots = nr_slots(alloc_size + offset);
+	int index = (tlb_addr - offset - io_tlb_start) >> IO_TLB_SHIFT;
 	phys_addr_t orig_addr = io_tlb_orig_addr[index];
 
 	/*
@@ -605,26 +634,29 @@
 	 * with slots below and above the pool being returned.
 	 */
 	spin_lock_irqsave(&io_tlb_lock, flags);
-	{
-		count = ((index + nslots) < ALIGN(index + 1, IO_TLB_SEGSIZE) ?
-			 io_tlb_list[index + nslots] : 0);
-		/*
-		 * Step 1: return the slots to the free list, merging the
-		 * slots with superceeding slots
-		 */
-		for (i = index + nslots - 1; i >= index; i--) {
-			io_tlb_list[i] = ++count;
-			io_tlb_orig_addr[i] = INVALID_PHYS_ADDR;
-		}
-		/*
-		 * Step 2: merge the returned slots with the preceding slots,
-		 * if available (non zero)
-		 */
-		for (i = index - 1; (OFFSET(i, IO_TLB_SEGSIZE) != IO_TLB_SEGSIZE -1) && io_tlb_list[i]; i--)
-			io_tlb_list[i] = ++count;
+	if (index + nslots < ALIGN(index + 1, IO_TLB_SEGSIZE))
+		count = io_tlb_list[index + nslots];
+	else
+		count = 0;
 
-		io_tlb_used -= nslots;
+	/*
+	 * Step 1: return the slots to the free list, merging the slots with
+	 * superceeding slots
+	 */
+	for (i = index + nslots - 1; i >= index; i--) {
+		io_tlb_list[i] = ++count;
+		io_tlb_orig_addr[i] = INVALID_PHYS_ADDR;
 	}
+
+	/*
+	 * Step 2: merge the returned slots with the preceding slots, if
+	 * available (non zero)
+	 */
+	for (i = index - 1;
+	     io_tlb_offset(i) != IO_TLB_SEGSIZE - 1 && io_tlb_list[i];
+	     i--)
+		io_tlb_list[i] = ++count;
+	io_tlb_used -= nslots;
 	spin_unlock_irqrestore(&io_tlb_lock, flags);
 }
 
@@ -637,7 +669,6 @@
 
 	if (orig_addr == INVALID_PHYS_ADDR)
 		return;
-	orig_addr += (unsigned long)tlb_addr & ((1 << IO_TLB_SHIFT) - 1);
 
 	switch (target) {
 	case SYNC_FOR_CPU:
@@ -693,7 +724,7 @@
 
 size_t swiotlb_max_mapping_size(struct device *dev)
 {
-	return ((size_t)1 << IO_TLB_SHIFT) * IO_TLB_SEGSIZE;
+	return ((size_t)IO_TLB_SIZE) * IO_TLB_SEGSIZE;
 }
 
 bool is_swiotlb_active(void)