diff --git a/arch/x86/include/asm/xen/swiotlb-xen.h b/arch/x86/include/asm/xen/swiotlb-xen.h
index 1be1ab7d6a41..ee52fcac6f72 100644
--- a/arch/x86/include/asm/xen/swiotlb-xen.h
+++ b/arch/x86/include/asm/xen/swiotlb-xen.h
@@ -5,10 +5,12 @@
 extern int xen_swiotlb;
 extern int __init pci_xen_swiotlb_detect(void);
 extern void __init pci_xen_swiotlb_init(void);
+extern int pci_xen_swiotlb_init_late(void);
 #else
 #define xen_swiotlb (0)
 static inline int __init pci_xen_swiotlb_detect(void) { return 0; }
 static inline void __init pci_xen_swiotlb_init(void) { }
+static inline int pci_xen_swiotlb_init_late(void) { return -ENXIO; }
 #endif
 
 #endif /* _ASM_X86_SWIOTLB_XEN_H */
diff --git a/arch/x86/xen/pci-swiotlb-xen.c b/arch/x86/xen/pci-swiotlb-xen.c
index 1c1722761eec..b152640d8388 100644
--- a/arch/x86/xen/pci-swiotlb-xen.c
+++ b/arch/x86/xen/pci-swiotlb-xen.c
@@ -12,7 +12,7 @@
 #include <asm/iommu.h>
 #include <asm/dma.h>
 #endif
-
+#include <linux/export.h>
 int xen_swiotlb __read_mostly;
 
 static struct dma_map_ops xen_swiotlb_dma_ops = {
@@ -69,13 +69,33 @@ int __init pci_xen_swiotlb_detect(void)
 void __init pci_xen_swiotlb_init(void)
 {
 	if (xen_swiotlb) {
-		xen_swiotlb_init(1);
+		xen_swiotlb_init(1, true /* early */);
 		dma_ops = &xen_swiotlb_dma_ops;
 
 		/* Make sure ACS will be enabled */
 		pci_request_acs();
 	}
 }
+
+int pci_xen_swiotlb_init_late(void)
+{
+	int rc;
+
+	if (xen_swiotlb)
+		return 0;
+
+	rc = xen_swiotlb_init(1, false /* late */);
+	if (rc)
+		return rc;
+
+	dma_ops = &xen_swiotlb_dma_ops;
+	/* Make sure ACS will be enabled */
+	pci_request_acs();
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(pci_xen_swiotlb_init_late);
+
 IOMMU_INIT_FINISH(pci_xen_swiotlb_detect,
 		  0,
 		  pci_xen_swiotlb_init,
diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c
index 701b1035fa6f..7461edb5118e 100644
--- a/drivers/xen/swiotlb-xen.c
+++ b/drivers/xen/swiotlb-xen.c
@@ -176,9 +176,9 @@ static const char *xen_swiotlb_error(enum xen_swiotlb_err err)
 	}
 	return "";
 }
-void __init xen_swiotlb_init(int verbose)
+int __ref xen_swiotlb_init(int verbose, bool early)
 {
-	unsigned long bytes;
+	unsigned long bytes, order;
 	int rc = -ENOMEM;
 	enum xen_swiotlb_err m_ret = XEN_SWIOTLB_UNKNOWN;
 	unsigned int repeat = 3;
@@ -186,10 +186,28 @@ void __init xen_swiotlb_init(int verbose)
 	xen_io_tlb_nslabs = swiotlb_nr_tbl();
 retry:
 	bytes = xen_set_nslabs(xen_io_tlb_nslabs);
+	order = get_order(xen_io_tlb_nslabs << IO_TLB_SHIFT);
 	/*
 	 * Get IO TLB memory from any location.
 	 */
-	xen_io_tlb_start = alloc_bootmem_pages(PAGE_ALIGN(bytes));
+	if (early)
+		xen_io_tlb_start = alloc_bootmem_pages(PAGE_ALIGN(bytes));
+	else {
+#define SLABS_PER_PAGE (1 << (PAGE_SHIFT - IO_TLB_SHIFT))
+#define IO_TLB_MIN_SLABS ((1<<20) >> IO_TLB_SHIFT)
+		while ((SLABS_PER_PAGE << order) > IO_TLB_MIN_SLABS) {
+			xen_io_tlb_start = (void *)__get_free_pages(__GFP_NOWARN, order);
+			if (xen_io_tlb_start)
+				break;
+			order--;
+		}
+		if (order != get_order(bytes)) {
+			pr_warn("Warning: only able to allocate %ld MB "
+				"for software IO TLB\n", (PAGE_SIZE << order) >> 20);
+			xen_io_tlb_nslabs = SLABS_PER_PAGE << order;
+			bytes = xen_io_tlb_nslabs << IO_TLB_SHIFT;
+		}
+	}
 	if (!xen_io_tlb_start) {
 		m_ret = XEN_SWIOTLB_ENOMEM;
 		goto error;
@@ -202,14 +220,21 @@ void __init xen_swiotlb_init(int verbose)
 			       bytes,
 			       xen_io_tlb_nslabs);
 	if (rc) {
-		free_bootmem(__pa(xen_io_tlb_start), PAGE_ALIGN(bytes));
+		if (early)
+			free_bootmem(__pa(xen_io_tlb_start), PAGE_ALIGN(bytes));
+		else {
+			free_pages((unsigned long)xen_io_tlb_start, order);
+			xen_io_tlb_start = NULL;
+		}
 		m_ret = XEN_SWIOTLB_EFIXUP;
 		goto error;
 	}
 	start_dma_addr = xen_virt_to_bus(xen_io_tlb_start);
-	swiotlb_init_with_tbl(xen_io_tlb_start, xen_io_tlb_nslabs, verbose);
-
-	return;
+	if (early)
+		swiotlb_init_with_tbl(xen_io_tlb_start, xen_io_tlb_nslabs, verbose);
+	else
+		rc = swiotlb_late_init_with_tbl(xen_io_tlb_start, xen_io_tlb_nslabs);
+	return rc;
 error:
 	if (repeat--) {
 		xen_io_tlb_nslabs = max(1024UL, /* Min is 2MB */
@@ -218,10 +243,13 @@ void __init xen_swiotlb_init(int verbose)
 		      (xen_io_tlb_nslabs << IO_TLB_SHIFT) >> 20);
 		goto retry;
 	}
-	xen_raw_printk("%s (rc:%d)", xen_swiotlb_error(m_ret), rc);
-	panic("%s (rc:%d)", xen_swiotlb_error(m_ret), rc);
+	pr_err("%s (rc:%d)", xen_swiotlb_error(m_ret), rc);
+	if (early)
+		panic("%s (rc:%d)", xen_swiotlb_error(m_ret), rc);
+	else
+		free_pages((unsigned long)xen_io_tlb_start, order);
+	return rc;
 }
-
 void *
 xen_swiotlb_alloc_coherent(struct device *hwdev, size_t size,
 			   dma_addr_t *dma_handle, gfp_t flags,
diff --git a/include/xen/swiotlb-xen.h b/include/xen/swiotlb-xen.h
index 4f4d449f00f6..289ee509bda9 100644
--- a/include/xen/swiotlb-xen.h
+++ b/include/xen/swiotlb-xen.h
@@ -3,7 +3,7 @@
 
 #include <linux/swiotlb.h>
 
-extern void xen_swiotlb_init(int verbose);
+extern int xen_swiotlb_init(int verbose, bool early);
 
 extern void
 *xen_swiotlb_alloc_coherent(struct device *hwdev, size_t size,