diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c
index 7022b7b5c400..1ba9f9f9dbd8 100644
--- a/arch/arm/mm/init.c
+++ b/arch/arm/mm/init.c
@@ -301,7 +301,11 @@ static void __init free_highpages(void)
 void __init mem_init(void)
 {
 #ifdef CONFIG_ARM_LPAE
-	swiotlb_init(1);
+	if (swiotlb_force == SWIOTLB_FORCE ||
+	    max_pfn > arm_dma_pfn_limit)
+		swiotlb_init(1);
+	else
+		swiotlb_force = SWIOTLB_NO_FORCE;
 #endif
 
 	set_max_mapnr(pfn_to_page(max_pfn) - mem_map);
diff --git a/arch/arm/xen/mm.c b/arch/arm/xen/mm.c
index e1b12b242a32..f8f07469d259 100644
--- a/arch/arm/xen/mm.c
+++ b/arch/arm/xen/mm.c
@@ -152,7 +152,7 @@ static int __init xen_mm_init(void)
 	struct gnttab_cache_flush cflush;
 	if (!xen_swiotlb_detect())
 		return 0;
-	xen_swiotlb_init(1, false);
+	xen_swiotlb_init();
 
 	cflush.op = 0;
 	cflush.a.dev_bus_addr = 0;
diff --git a/arch/powerpc/platforms/pseries/svm.c b/arch/powerpc/platforms/pseries/svm.c
index 7b739cc7a8a9..1d829e257996 100644
--- a/arch/powerpc/platforms/pseries/svm.c
+++ b/arch/powerpc/platforms/pseries/svm.c
@@ -55,9 +55,9 @@ void __init svm_swiotlb_init(void)
 	if (vstart && !swiotlb_init_with_tbl(vstart, io_tlb_nslabs, false))
 		return;
 
-	if (io_tlb_start)
-		memblock_free_early(io_tlb_start,
-				    PAGE_ALIGN(io_tlb_nslabs << IO_TLB_SHIFT));
+
+	memblock_free_early(__pa(vstart),
+			    PAGE_ALIGN(io_tlb_nslabs << IO_TLB_SHIFT));
 	panic("SVM: Cannot allocate SWIOTLB buffer");
 }
 
diff --git a/arch/x86/xen/pci-swiotlb-xen.c b/arch/x86/xen/pci-swiotlb-xen.c
index 19ae3e4fe4e9..54f9aa7e8457 100644
--- a/arch/x86/xen/pci-swiotlb-xen.c
+++ b/arch/x86/xen/pci-swiotlb-xen.c
@@ -59,7 +59,7 @@ int __init pci_xen_swiotlb_detect(void)
 void __init pci_xen_swiotlb_init(void)
 {
 	if (xen_swiotlb) {
-		xen_swiotlb_init(1, true /* early */);
+		xen_swiotlb_init_early();
 		dma_ops = &xen_swiotlb_dma_ops;
 
 #ifdef CONFIG_PCI
@@ -76,7 +76,7 @@ int pci_xen_swiotlb_init_late(void)
 	if (xen_swiotlb)
 		return 0;
 
-	rc = xen_swiotlb_init(1, false /* late */);
+	rc = xen_swiotlb_init();
 	if (rc)
 		return rc;
 
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_internal.c b/drivers/gpu/drm/i915/gem/i915_gem_internal.c
index 21cc40897ca8..ce6b664b10aa 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_internal.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_internal.c
@@ -42,7 +42,7 @@ static int i915_gem_object_get_pages_internal(struct drm_i915_gem_object *obj)
 
 	max_order = MAX_ORDER;
 #ifdef CONFIG_SWIOTLB
-	if (swiotlb_nr_tbl()) {
+	if (is_swiotlb_active()) {
 		unsigned int max_segment;
 
 		max_segment = swiotlb_max_segment();
diff --git a/drivers/gpu/drm/nouveau/nouveau_ttm.c b/drivers/gpu/drm/nouveau/nouveau_ttm.c
index b81ae90b8449..e8b506a6685b 100644
--- a/drivers/gpu/drm/nouveau/nouveau_ttm.c
+++ b/drivers/gpu/drm/nouveau/nouveau_ttm.c
@@ -321,7 +321,7 @@ nouveau_ttm_init(struct nouveau_drm *drm)
 	}
 
 #if IS_ENABLED(CONFIG_SWIOTLB) && IS_ENABLED(CONFIG_X86)
-	need_swiotlb = !!swiotlb_nr_tbl();
+	need_swiotlb = is_swiotlb_active();
 #endif
 
 	ret = ttm_device_init(&drm->ttm.bdev, &nouveau_bo_driver, drm->dev->dev,
diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c
index 4dadac3135b0..7bcdd1205535 100644
--- a/drivers/iommu/dma-iommu.c
+++ b/drivers/iommu/dma-iommu.c
@@ -496,8 +496,6 @@ static void __iommu_dma_unmap_swiotlb(struct device *dev, dma_addr_t dma_addr,
 		unsigned long attrs)
 {
 	struct iommu_domain *domain = iommu_get_dma_domain(dev);
-	struct iommu_dma_cookie *cookie = domain->iova_cookie;
-	struct iova_domain *iovad = &cookie->iovad;
 	phys_addr_t phys;
 
 	phys = iommu_iova_to_phys(domain, dma_addr);
@@ -507,8 +505,7 @@ static void __iommu_dma_unmap_swiotlb(struct device *dev, dma_addr_t dma_addr,
 	__iommu_dma_unmap(dev, dma_addr, size);
 
 	if (unlikely(is_swiotlb_buffer(phys)))
-		swiotlb_tbl_unmap_single(dev, phys, size,
-				iova_align(iovad, size), dir, attrs);
+		swiotlb_tbl_unmap_single(dev, phys, size, dir, attrs);
 }
 
 static dma_addr_t __iommu_dma_map(struct device *dev, phys_addr_t phys,
@@ -578,10 +575,8 @@ static dma_addr_t __iommu_dma_map_swiotlb(struct device *dev, phys_addr_t phys,
 	}
 
 	iova = __iommu_dma_map(dev, phys, aligned_size, prot, dma_mask);
-	if ((iova == DMA_MAPPING_ERROR) && is_swiotlb_buffer(phys))
-		swiotlb_tbl_unmap_single(dev, phys, org_size,
-				aligned_size, dir, attrs);
-
+	if (iova == DMA_MAPPING_ERROR && is_swiotlb_buffer(phys))
+		swiotlb_tbl_unmap_single(dev, phys, org_size, dir, attrs);
 	return iova;
 }
 
@@ -787,7 +782,7 @@ static void iommu_dma_sync_single_for_cpu(struct device *dev,
 		arch_sync_dma_for_cpu(phys, size, dir);
 
 	if (is_swiotlb_buffer(phys))
-		swiotlb_tbl_sync_single(dev, phys, size, dir, SYNC_FOR_CPU);
+		swiotlb_sync_single_for_cpu(dev, phys, size, dir);
 }
 
 static void iommu_dma_sync_single_for_device(struct device *dev,
@@ -800,7 +795,7 @@ static void iommu_dma_sync_single_for_device(struct device *dev,
 
 	phys = iommu_iova_to_phys(iommu_get_dma_domain(dev), dma_handle);
 	if (is_swiotlb_buffer(phys))
-		swiotlb_tbl_sync_single(dev, phys, size, dir, SYNC_FOR_DEVICE);
+		swiotlb_sync_single_for_device(dev, phys, size, dir);
 
 	if (!dev_is_dma_coherent(dev))
 		arch_sync_dma_for_device(phys, size, dir);
@@ -821,8 +816,8 @@ static void iommu_dma_sync_sg_for_cpu(struct device *dev,
 			arch_sync_dma_for_cpu(sg_phys(sg), sg->length, dir);
 
 		if (is_swiotlb_buffer(sg_phys(sg)))
-			swiotlb_tbl_sync_single(dev, sg_phys(sg), sg->length,
-						dir, SYNC_FOR_CPU);
+			swiotlb_sync_single_for_cpu(dev, sg_phys(sg),
+						    sg->length, dir);
 	}
 }
 
@@ -838,8 +833,8 @@ static void iommu_dma_sync_sg_for_device(struct device *dev,
 
 	for_each_sg(sgl, sg, nelems, i) {
 		if (is_swiotlb_buffer(sg_phys(sg)))
-			swiotlb_tbl_sync_single(dev, sg_phys(sg), sg->length,
-						dir, SYNC_FOR_DEVICE);
+			swiotlb_sync_single_for_device(dev, sg_phys(sg),
+						       sg->length, dir);
 
 		if (!dev_is_dma_coherent(dev))
 			arch_sync_dma_for_device(sg_phys(sg), sg->length, dir);
diff --git a/drivers/pci/xen-pcifront.c b/drivers/pci/xen-pcifront.c
index 2d7502648219..b7a8f3a1921f 100644
--- a/drivers/pci/xen-pcifront.c
+++ b/drivers/pci/xen-pcifront.c
@@ -693,7 +693,7 @@ static int pcifront_connect_and_init_dma(struct pcifront_device *pdev)
 
 	spin_unlock(&pcifront_dev_lock);
 
-	if (!err && !swiotlb_nr_tbl()) {
+	if (!err && !is_swiotlb_active()) {
 		err = pci_xen_swiotlb_init_late();
 		if (err)
 			dev_err(&pdev->xdev->dev, "Could not setup SWIOTLB!\n");
diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c
index 2b385c1b4a99..4c89afc0df62 100644
--- a/drivers/xen/swiotlb-xen.c
+++ b/drivers/xen/swiotlb-xen.c
@@ -40,14 +40,7 @@
 
 #include <trace/events/swiotlb.h>
 #define MAX_DMA_BITS 32
-/*
- * Used to do a quick range check in swiotlb_tbl_unmap_single and
- * swiotlb_tbl_sync_single_*, to see if the memory was in fact allocated by this
- * API.
- */
 
-static char *xen_io_tlb_start, *xen_io_tlb_end;
-static unsigned long xen_io_tlb_nslabs;
 /*
  * Quick lookup value of the bus address of the IOTLB.
  */
@@ -82,11 +75,6 @@ static inline phys_addr_t xen_dma_to_phys(struct device *dev,
 	return xen_bus_to_phys(dev, dma_to_phys(dev, dma_addr));
 }
 
-static inline dma_addr_t xen_virt_to_bus(struct device *dev, void *address)
-{
-	return xen_phys_to_dma(dev, virt_to_phys(address));
-}
-
 static inline int range_straddles_page_boundary(phys_addr_t p, size_t size)
 {
 	unsigned long next_bfn, xen_pfn = XEN_PFN_DOWN(p);
@@ -111,15 +99,12 @@ static int is_xen_swiotlb_buffer(struct device *dev, dma_addr_t dma_addr)
 	 * have the same virtual address as another address
 	 * in our domain. Therefore _only_ check address within our domain.
 	 */
-	if (pfn_valid(PFN_DOWN(paddr))) {
-		return paddr >= virt_to_phys(xen_io_tlb_start) &&
-		       paddr < virt_to_phys(xen_io_tlb_end);
-	}
+	if (pfn_valid(PFN_DOWN(paddr)))
+		return is_swiotlb_buffer(paddr);
 	return 0;
 }
 
-static int
-xen_swiotlb_fixup(void *buf, size_t size, unsigned long nslabs)
+static int xen_swiotlb_fixup(void *buf, unsigned long nslabs)
 {
 	int i, rc;
 	int dma_bits;
@@ -145,16 +130,6 @@ xen_swiotlb_fixup(void *buf, size_t size, unsigned long nslabs)
 	} while (i < nslabs);
 	return 0;
 }
-static unsigned long xen_set_nslabs(unsigned long nr_tbl)
-{
-	if (!nr_tbl) {
-		xen_io_tlb_nslabs = (64 * 1024 * 1024 >> IO_TLB_SHIFT);
-		xen_io_tlb_nslabs = ALIGN(xen_io_tlb_nslabs, IO_TLB_SEGSIZE);
-	} else
-		xen_io_tlb_nslabs = nr_tbl;
-
-	return xen_io_tlb_nslabs << IO_TLB_SHIFT;
-}
 
 enum xen_swiotlb_err {
 	XEN_SWIOTLB_UNKNOWN = 0,
@@ -177,102 +152,109 @@ static const char *xen_swiotlb_error(enum xen_swiotlb_err err)
 	}
 	return "";
 }
-int __ref xen_swiotlb_init(int verbose, bool early)
+
+#define DEFAULT_NSLABS		ALIGN(SZ_64M >> IO_TLB_SHIFT, IO_TLB_SEGSIZE)
+
+int __ref xen_swiotlb_init(void)
 {
-	unsigned long bytes, order;
-	int rc = -ENOMEM;
 	enum xen_swiotlb_err m_ret = XEN_SWIOTLB_UNKNOWN;
-	unsigned int repeat = 3;
+	unsigned long bytes = swiotlb_size_or_default();
+	unsigned long nslabs = bytes >> IO_TLB_SHIFT;
+	unsigned int order, repeat = 3;
+	int rc = -ENOMEM;
+	char *start;
 
-	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);
-
-	/*
-	 * IO TLB memory already allocated. Just use it.
-	 */
-	if (io_tlb_start != 0) {
-		xen_io_tlb_start = phys_to_virt(io_tlb_start);
-		goto end;
-	}
+	m_ret = XEN_SWIOTLB_ENOMEM;
+	order = get_order(bytes);
 
 	/*
 	 * Get IO TLB memory from any location.
 	 */
-	if (early) {
-		xen_io_tlb_start = memblock_alloc(PAGE_ALIGN(bytes),
-						  PAGE_SIZE);
-		if (!xen_io_tlb_start)
-			panic("%s: Failed to allocate %lu bytes align=0x%lx\n",
-			      __func__, PAGE_ALIGN(bytes), PAGE_SIZE);
-	} 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 *)xen_get_swiotlb_free_pages(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;
-		}
+	while ((SLABS_PER_PAGE << order) > IO_TLB_MIN_SLABS) {
+		start = (void *)xen_get_swiotlb_free_pages(order);
+		if (start)
+			break;
+		order--;
 	}
-	if (!xen_io_tlb_start) {
-		m_ret = XEN_SWIOTLB_ENOMEM;
+	if (!start)
 		goto error;
+	if (order != get_order(bytes)) {
+		pr_warn("Warning: only able to allocate %ld MB for software IO TLB\n",
+			(PAGE_SIZE << order) >> 20);
+		nslabs = SLABS_PER_PAGE << order;
+		bytes = nslabs << IO_TLB_SHIFT;
 	}
+
 	/*
 	 * And replace that memory with pages under 4GB.
 	 */
-	rc = xen_swiotlb_fixup(xen_io_tlb_start,
-			       bytes,
-			       xen_io_tlb_nslabs);
+	rc = xen_swiotlb_fixup(start, nslabs);
 	if (rc) {
-		if (early)
-			memblock_free(__pa(xen_io_tlb_start),
-				      PAGE_ALIGN(bytes));
-		else {
-			free_pages((unsigned long)xen_io_tlb_start, order);
-			xen_io_tlb_start = NULL;
-		}
+		free_pages((unsigned long)start, order);
 		m_ret = XEN_SWIOTLB_EFIXUP;
 		goto error;
 	}
-	if (early) {
-		if (swiotlb_init_with_tbl(xen_io_tlb_start, xen_io_tlb_nslabs,
-			 verbose))
-			panic("Cannot allocate SWIOTLB buffer");
-		rc = 0;
-	} else
-		rc = swiotlb_late_init_with_tbl(xen_io_tlb_start, xen_io_tlb_nslabs);
-
-end:
-	xen_io_tlb_end = xen_io_tlb_start + bytes;
-	if (!rc)
-		swiotlb_set_max_segment(PAGE_SIZE);
-
-	return rc;
+	rc = swiotlb_late_init_with_tbl(start, nslabs);
+	if (rc)
+		return rc;
+	swiotlb_set_max_segment(PAGE_SIZE);
+	return 0;
 error:
 	if (repeat--) {
-		xen_io_tlb_nslabs = max(1024UL, /* Min is 2MB */
-					(xen_io_tlb_nslabs >> 1));
+		/* Min is 2MB */
+		nslabs = max(1024UL, (nslabs >> 1));
 		pr_info("Lowering to %luMB\n",
-			(xen_io_tlb_nslabs << IO_TLB_SHIFT) >> 20);
+			(nslabs << IO_TLB_SHIFT) >> 20);
 		goto retry;
 	}
 	pr_err("%s (rc:%d)\n", 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);
+	free_pages((unsigned long)start, order);
 	return rc;
 }
 
+#ifdef CONFIG_X86
+void __init xen_swiotlb_init_early(void)
+{
+	unsigned long bytes = swiotlb_size_or_default();
+	unsigned long nslabs = bytes >> IO_TLB_SHIFT;
+	unsigned int repeat = 3;
+	char *start;
+	int rc;
+
+retry:
+	/*
+	 * Get IO TLB memory from any location.
+	 */
+	start = memblock_alloc(PAGE_ALIGN(bytes), PAGE_SIZE);
+	if (!start)
+		panic("%s: Failed to allocate %lu bytes align=0x%lx\n",
+		      __func__, PAGE_ALIGN(bytes), PAGE_SIZE);
+
+	/*
+	 * And replace that memory with pages under 4GB.
+	 */
+	rc = xen_swiotlb_fixup(start, nslabs);
+	if (rc) {
+		memblock_free(__pa(start), PAGE_ALIGN(bytes));
+		if (repeat--) {
+			/* Min is 2MB */
+			nslabs = max(1024UL, (nslabs >> 1));
+			bytes = nslabs << IO_TLB_SHIFT;
+			pr_info("Lowering to %luMB\n", bytes >> 20);
+			goto retry;
+		}
+		panic("%s (rc:%d)", xen_swiotlb_error(XEN_SWIOTLB_EFIXUP), rc);
+	}
+
+	if (swiotlb_init_with_tbl(start, nslabs, false))
+		panic("Cannot allocate SWIOTLB buffer");
+	swiotlb_set_max_segment(PAGE_SIZE);
+}
+#endif /* CONFIG_X86 */
+
 static void *
 xen_swiotlb_alloc_coherent(struct device *hwdev, size_t size,
 			   dma_addr_t *dma_handle, gfp_t flags,
@@ -406,7 +388,7 @@ static dma_addr_t xen_swiotlb_map_page(struct device *dev, struct page *page,
 	 * Ensure that the address returned is DMA'ble
 	 */
 	if (unlikely(!dma_capable(dev, dev_addr, size, true))) {
-		swiotlb_tbl_unmap_single(dev, map, size, size, dir,
+		swiotlb_tbl_unmap_single(dev, map, size, dir,
 				attrs | DMA_ATTR_SKIP_CPU_SYNC);
 		return DMA_MAPPING_ERROR;
 	}
@@ -445,7 +427,7 @@ static void xen_swiotlb_unmap_page(struct device *hwdev, dma_addr_t dev_addr,
 
 	/* NOTE: We use dev_addr here, not paddr! */
 	if (is_xen_swiotlb_buffer(hwdev, dev_addr))
-		swiotlb_tbl_unmap_single(hwdev, paddr, size, size, dir, attrs);
+		swiotlb_tbl_unmap_single(hwdev, paddr, size, dir, attrs);
 }
 
 static void
@@ -462,7 +444,7 @@ xen_swiotlb_sync_single_for_cpu(struct device *dev, dma_addr_t dma_addr,
 	}
 
 	if (is_xen_swiotlb_buffer(dev, dma_addr))
-		swiotlb_tbl_sync_single(dev, paddr, size, dir, SYNC_FOR_CPU);
+		swiotlb_sync_single_for_cpu(dev, paddr, size, dir);
 }
 
 static void
@@ -472,7 +454,7 @@ xen_swiotlb_sync_single_for_device(struct device *dev, dma_addr_t dma_addr,
 	phys_addr_t paddr = xen_dma_to_phys(dev, dma_addr);
 
 	if (is_xen_swiotlb_buffer(dev, dma_addr))
-		swiotlb_tbl_sync_single(dev, paddr, size, dir, SYNC_FOR_DEVICE);
+		swiotlb_sync_single_for_device(dev, paddr, size, dir);
 
 	if (!dev_is_dma_coherent(dev)) {
 		if (pfn_valid(PFN_DOWN(dma_to_phys(dev, dma_addr))))
@@ -560,7 +542,7 @@ xen_swiotlb_sync_sg_for_device(struct device *dev, struct scatterlist *sgl,
 static int
 xen_swiotlb_dma_supported(struct device *hwdev, u64 mask)
 {
-	return xen_virt_to_bus(hwdev, xen_io_tlb_end - 1) <= mask;
+	return xen_phys_to_dma(hwdev, io_tlb_default_mem->end - 1) <= mask;
 }
 
 const struct dma_map_ops xen_swiotlb_dma_ops = {
diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h
index 5857a937c637..216854a5e513 100644
--- a/include/linux/swiotlb.h
+++ b/include/linux/swiotlb.h
@@ -6,6 +6,7 @@
 #include <linux/init.h>
 #include <linux/types.h>
 #include <linux/limits.h>
+#include <linux/spinlock.h>
 
 struct device;
 struct page;
@@ -36,20 +37,11 @@ enum swiotlb_force {
 
 extern void swiotlb_init(int verbose);
 int swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, int verbose);
-extern unsigned long swiotlb_nr_tbl(void);
 unsigned long swiotlb_size_or_default(void);
 extern int swiotlb_late_init_with_tbl(char *tlb, unsigned long nslabs);
 extern int swiotlb_late_init_with_default_size(size_t default_size);
 extern void __init swiotlb_update_mem_attributes(void);
 
-/*
- * Enumeration for sync targets
- */
-enum dma_sync_target {
-	SYNC_FOR_CPU = 0,
-	SYNC_FOR_DEVICE = 1,
-};
-
 phys_addr_t swiotlb_tbl_map_single(struct device *hwdev, phys_addr_t phys,
 		size_t mapping_size, size_t alloc_size,
 		enum dma_data_direction dir, unsigned long attrs);
@@ -57,32 +49,70 @@ phys_addr_t swiotlb_tbl_map_single(struct device *hwdev, phys_addr_t phys,
 extern void swiotlb_tbl_unmap_single(struct device *hwdev,
 				     phys_addr_t tlb_addr,
 				     size_t mapping_size,
-				     size_t alloc_size,
 				     enum dma_data_direction dir,
 				     unsigned long attrs);
 
-extern void swiotlb_tbl_sync_single(struct device *hwdev,
-				    phys_addr_t tlb_addr,
-				    size_t size, enum dma_data_direction dir,
-				    enum dma_sync_target target);
-
+void swiotlb_sync_single_for_device(struct device *dev, phys_addr_t tlb_addr,
+		size_t size, enum dma_data_direction dir);
+void swiotlb_sync_single_for_cpu(struct device *dev, phys_addr_t tlb_addr,
+		size_t size, enum dma_data_direction dir);
 dma_addr_t swiotlb_map(struct device *dev, phys_addr_t phys,
 		size_t size, enum dma_data_direction dir, unsigned long attrs);
 
 #ifdef CONFIG_SWIOTLB
 extern enum swiotlb_force swiotlb_force;
-extern phys_addr_t io_tlb_start, io_tlb_end;
+
+/**
+ * struct io_tlb_mem - IO TLB Memory Pool Descriptor
+ *
+ * @start:	The start address of the swiotlb memory pool. Used to do a quick
+ *		range check to see if the memory was in fact allocated by this
+ *		API.
+ * @end:	The end address of the swiotlb memory pool. Used to do a quick
+ *		range check to see if the memory was in fact allocated by this
+ *		API.
+ * @nslabs:	The number of IO TLB blocks (in groups of 64) between @start and
+ *		@end. This is command line adjustable via setup_io_tlb_npages.
+ * @used:	The number of used IO TLB block.
+ * @list:	The free list describing the number of free entries available
+ *		from each index.
+ * @index:	The index to start searching in the next round.
+ * @orig_addr:	The original address corresponding to a mapped entry.
+ * @alloc_size:	Size of the allocated buffer.
+ * @lock:	The lock to protect the above data structures in the map and
+ *		unmap calls.
+ * @debugfs:	The dentry to debugfs.
+ * @late_alloc:	%true if allocated using the page allocator
+ */
+struct io_tlb_mem {
+	phys_addr_t start;
+	phys_addr_t end;
+	unsigned long nslabs;
+	unsigned long used;
+	unsigned int index;
+	spinlock_t lock;
+	struct dentry *debugfs;
+	bool late_alloc;
+	struct io_tlb_slot {
+		phys_addr_t orig_addr;
+		size_t alloc_size;
+		unsigned int list;
+	} slots[];
+};
+extern struct io_tlb_mem *io_tlb_default_mem;
 
 static inline bool is_swiotlb_buffer(phys_addr_t paddr)
 {
-	return paddr >= io_tlb_start && paddr < io_tlb_end;
+	struct io_tlb_mem *mem = io_tlb_default_mem;
+
+	return mem && paddr >= mem->start && paddr < mem->end;
 }
 
 void __init swiotlb_exit(void);
 unsigned int swiotlb_max_segment(void);
 size_t swiotlb_max_mapping_size(struct device *dev);
 bool is_swiotlb_active(void);
-void __init swiotlb_adjust_size(unsigned long new_size);
+void __init swiotlb_adjust_size(unsigned long size);
 #else
 #define swiotlb_force SWIOTLB_NO_FORCE
 static inline bool is_swiotlb_buffer(phys_addr_t paddr)
@@ -106,7 +136,7 @@ static inline bool is_swiotlb_active(void)
 	return false;
 }
 
-static inline void swiotlb_adjust_size(unsigned long new_size)
+static inline void swiotlb_adjust_size(unsigned long size)
 {
 }
 #endif /* CONFIG_SWIOTLB */
diff --git a/include/xen/swiotlb-xen.h b/include/xen/swiotlb-xen.h
index dbc4a4b785f6..b3e647f86e3e 100644
--- a/include/xen/swiotlb-xen.h
+++ b/include/xen/swiotlb-xen.h
@@ -10,7 +10,8 @@ void xen_dma_sync_for_cpu(struct device *dev, dma_addr_t handle,
 void xen_dma_sync_for_device(struct device *dev, dma_addr_t handle,
 			     size_t size, enum dma_data_direction dir);
 
-extern int xen_swiotlb_init(int verbose, bool early);
+int xen_swiotlb_init(void);
+void __init xen_swiotlb_init_early(void);
 extern const struct dma_map_ops xen_swiotlb_dma_ops;
 
 #endif /* __LINUX_SWIOTLB_XEN_H */
diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c
index 002268262c9a..f737e3347059 100644
--- a/kernel/dma/direct.c
+++ b/kernel/dma/direct.c
@@ -344,8 +344,8 @@ void dma_direct_sync_sg_for_device(struct device *dev,
 		phys_addr_t paddr = dma_to_phys(dev, sg_dma_address(sg));
 
 		if (unlikely(is_swiotlb_buffer(paddr)))
-			swiotlb_tbl_sync_single(dev, paddr, sg->length,
-					dir, SYNC_FOR_DEVICE);
+			swiotlb_sync_single_for_device(dev, paddr, sg->length,
+						       dir);
 
 		if (!dev_is_dma_coherent(dev))
 			arch_sync_dma_for_device(paddr, sg->length,
@@ -370,8 +370,8 @@ void dma_direct_sync_sg_for_cpu(struct device *dev,
 			arch_sync_dma_for_cpu(paddr, sg->length, dir);
 
 		if (unlikely(is_swiotlb_buffer(paddr)))
-			swiotlb_tbl_sync_single(dev, paddr, sg->length, dir,
-					SYNC_FOR_CPU);
+			swiotlb_sync_single_for_cpu(dev, paddr, sg->length,
+						    dir);
 
 		if (dir == DMA_FROM_DEVICE)
 			arch_dma_mark_clean(paddr, sg->length);
diff --git a/kernel/dma/direct.h b/kernel/dma/direct.h
index b98615578737..50afc05b6f1d 100644
--- a/kernel/dma/direct.h
+++ b/kernel/dma/direct.h
@@ -57,7 +57,7 @@ static inline void dma_direct_sync_single_for_device(struct device *dev,
 	phys_addr_t paddr = dma_to_phys(dev, addr);
 
 	if (unlikely(is_swiotlb_buffer(paddr)))
-		swiotlb_tbl_sync_single(dev, paddr, size, dir, SYNC_FOR_DEVICE);
+		swiotlb_sync_single_for_device(dev, paddr, size, dir);
 
 	if (!dev_is_dma_coherent(dev))
 		arch_sync_dma_for_device(paddr, size, dir);
@@ -74,7 +74,7 @@ static inline void dma_direct_sync_single_for_cpu(struct device *dev,
 	}
 
 	if (unlikely(is_swiotlb_buffer(paddr)))
-		swiotlb_tbl_sync_single(dev, paddr, size, dir, SYNC_FOR_CPU);
+		swiotlb_sync_single_for_cpu(dev, paddr, size, dir);
 
 	if (dir == DMA_FROM_DEVICE)
 		arch_dma_mark_clean(paddr, size);
@@ -114,6 +114,6 @@ static inline void dma_direct_unmap_page(struct device *dev, dma_addr_t addr,
 		dma_direct_sync_single_for_cpu(dev, addr, size, dir);
 
 	if (unlikely(is_swiotlb_buffer(phys)))
-		swiotlb_tbl_unmap_single(dev, phys, size, size, dir, attrs);
+		swiotlb_tbl_unmap_single(dev, phys, size, dir, attrs);
 }
 #endif /* _KERNEL_DMA_DIRECT_H */
diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c
index c10e855a03bc..8ca7d505d61c 100644
--- a/kernel/dma/swiotlb.c
+++ b/kernel/dma/swiotlb.c
@@ -59,32 +59,11 @@
  */
 #define IO_TLB_MIN_SLABS ((1<<20) >> IO_TLB_SHIFT)
 
+#define INVALID_PHYS_ADDR (~(phys_addr_t)0)
+
 enum swiotlb_force swiotlb_force;
 
-/*
- * Used to do a quick range check in swiotlb_tbl_unmap_single and
- * swiotlb_tbl_sync_single_*, to see if the memory was in fact allocated by this
- * API.
- */
-phys_addr_t io_tlb_start, io_tlb_end;
-
-/*
- * The number of IO TLB blocks (in groups of 64) between io_tlb_start and
- * io_tlb_end.  This is command line adjustable via setup_io_tlb_npages.
- */
-static unsigned long io_tlb_nslabs;
-
-/*
- * The number of used IO TLB block
- */
-static unsigned long io_tlb_used;
-
-/*
- * This is a free list describing the number of free entries available from
- * each index
- */
-static unsigned int *io_tlb_list;
-static unsigned int io_tlb_index;
+struct io_tlb_mem *io_tlb_default_mem;
 
 /*
  * Max segment that we can provide which (if pages are contingous) will
@@ -92,57 +71,30 @@ static unsigned int io_tlb_index;
  */
 static unsigned int max_segment;
 
-/*
- * We need to save away the original address corresponding to a mapped entry
- * for the sync operations.
- */
-#define INVALID_PHYS_ADDR (~(phys_addr_t)0)
-static phys_addr_t *io_tlb_orig_addr;
-
-/*
- * The mapped buffer's size should be validated during a sync operation.
- */
-static size_t *io_tlb_orig_size;
-
-/*
- * Protect the above data structures in the map and unmap calls
- */
-static DEFINE_SPINLOCK(io_tlb_lock);
-
-static int late_alloc;
+static unsigned long default_nslabs = IO_TLB_DEFAULT_SIZE >> IO_TLB_SHIFT;
 
 static int __init
 setup_io_tlb_npages(char *str)
 {
 	if (isdigit(*str)) {
-		io_tlb_nslabs = simple_strtoul(str, &str, 0);
 		/* avoid tail segment of size < IO_TLB_SEGSIZE */
-		io_tlb_nslabs = ALIGN(io_tlb_nslabs, IO_TLB_SEGSIZE);
+		default_nslabs =
+			ALIGN(simple_strtoul(str, &str, 0), IO_TLB_SEGSIZE);
 	}
 	if (*str == ',')
 		++str;
-	if (!strcmp(str, "force")) {
+	if (!strcmp(str, "force"))
 		swiotlb_force = SWIOTLB_FORCE;
-	} else if (!strcmp(str, "noforce")) {
+	else if (!strcmp(str, "noforce"))
 		swiotlb_force = SWIOTLB_NO_FORCE;
-		io_tlb_nslabs = 1;
-	}
 
 	return 0;
 }
 early_param("swiotlb", setup_io_tlb_npages);
 
-static bool no_iotlb_memory;
-
-unsigned long swiotlb_nr_tbl(void)
-{
-	return unlikely(no_iotlb_memory) ? 0 : io_tlb_nslabs;
-}
-EXPORT_SYMBOL_GPL(swiotlb_nr_tbl);
-
 unsigned int swiotlb_max_segment(void)
 {
-	return unlikely(no_iotlb_memory) ? 0 : max_segment;
+	return io_tlb_default_mem ? max_segment : 0;
 }
 EXPORT_SYMBOL_GPL(swiotlb_max_segment);
 
@@ -156,42 +108,34 @@ void swiotlb_set_max_segment(unsigned int val)
 
 unsigned long swiotlb_size_or_default(void)
 {
-	unsigned long size;
-
-	size = io_tlb_nslabs << IO_TLB_SHIFT;
-
-	return size ? size : (IO_TLB_DEFAULT_SIZE);
+	return default_nslabs << IO_TLB_SHIFT;
 }
 
-void __init swiotlb_adjust_size(unsigned long new_size)
+void __init swiotlb_adjust_size(unsigned long size)
 {
-	unsigned long size;
-
 	/*
 	 * If swiotlb parameter has not been specified, give a chance to
 	 * architectures such as those supporting memory encryption to
 	 * adjust/expand SWIOTLB size for their use.
 	 */
-	if (!io_tlb_nslabs) {
-		size = ALIGN(new_size, IO_TLB_SIZE);
-		io_tlb_nslabs = size >> IO_TLB_SHIFT;
-		io_tlb_nslabs = ALIGN(io_tlb_nslabs, IO_TLB_SEGSIZE);
-
-		pr_info("SWIOTLB bounce buffer size adjusted to %luMB", size >> 20);
-	}
+	if (default_nslabs != IO_TLB_DEFAULT_SIZE >> IO_TLB_SHIFT)
+		return;
+	size = ALIGN(size, IO_TLB_SIZE);
+	default_nslabs = ALIGN(size >> IO_TLB_SHIFT, IO_TLB_SEGSIZE);
+	pr_info("SWIOTLB bounce buffer size adjusted to %luMB", size >> 20);
 }
 
 void swiotlb_print_info(void)
 {
-	unsigned long bytes = io_tlb_nslabs << IO_TLB_SHIFT;
+	struct io_tlb_mem *mem = io_tlb_default_mem;
 
-	if (no_iotlb_memory) {
+	if (!mem) {
 		pr_warn("No low mem\n");
 		return;
 	}
 
-	pr_info("mapped [mem %pa-%pa] (%luMB)\n", &io_tlb_start, &io_tlb_end,
-	       bytes >> 20);
+	pr_info("mapped [mem %pa-%pa] (%luMB)\n", &mem->start, &mem->end,
+	       (mem->nslabs << IO_TLB_SHIFT) >> 20);
 }
 
 static inline unsigned long io_tlb_offset(unsigned long val)
@@ -212,64 +156,51 @@ static inline unsigned long nr_slots(u64 val)
  */
 void __init swiotlb_update_mem_attributes(void)
 {
+	struct io_tlb_mem *mem = io_tlb_default_mem;
 	void *vaddr;
 	unsigned long bytes;
 
-	if (no_iotlb_memory || late_alloc)
+	if (!mem || mem->late_alloc)
 		return;
-
-	vaddr = phys_to_virt(io_tlb_start);
-	bytes = PAGE_ALIGN(io_tlb_nslabs << IO_TLB_SHIFT);
+	vaddr = phys_to_virt(mem->start);
+	bytes = PAGE_ALIGN(mem->nslabs << IO_TLB_SHIFT);
 	set_memory_decrypted((unsigned long)vaddr, bytes >> PAGE_SHIFT);
 	memset(vaddr, 0, bytes);
 }
 
 int __init swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, int verbose)
 {
-	unsigned long i, bytes;
+	unsigned long bytes = nslabs << IO_TLB_SHIFT, i;
+	struct io_tlb_mem *mem;
 	size_t alloc_size;
 
-	bytes = nslabs << IO_TLB_SHIFT;
+	if (swiotlb_force == SWIOTLB_NO_FORCE)
+		return 0;
 
-	io_tlb_nslabs = nslabs;
-	io_tlb_start = __pa(tlb);
-	io_tlb_end = io_tlb_start + bytes;
+	/* protect against double initialization */
+	if (WARN_ON_ONCE(io_tlb_default_mem))
+		return -ENOMEM;
 
-	/*
-	 * Allocate and initialize the free list array.  This array is used
-	 * to find contiguous free memory regions of size up to IO_TLB_SEGSIZE
-	 * between io_tlb_start and io_tlb_end.
-	 */
-	alloc_size = PAGE_ALIGN(io_tlb_nslabs * sizeof(int));
-	io_tlb_list = memblock_alloc(alloc_size, PAGE_SIZE);
-	if (!io_tlb_list)
+	alloc_size = PAGE_ALIGN(struct_size(mem, slots, nslabs));
+	mem = memblock_alloc(alloc_size, PAGE_SIZE);
+	if (!mem)
 		panic("%s: Failed to allocate %zu bytes align=0x%lx\n",
 		      __func__, alloc_size, PAGE_SIZE);
-
-	alloc_size = PAGE_ALIGN(io_tlb_nslabs * sizeof(phys_addr_t));
-	io_tlb_orig_addr = memblock_alloc(alloc_size, PAGE_SIZE);
-	if (!io_tlb_orig_addr)
-		panic("%s: Failed to allocate %zu bytes align=0x%lx\n",
-		      __func__, alloc_size, PAGE_SIZE);
-
-	alloc_size = PAGE_ALIGN(io_tlb_nslabs * sizeof(size_t));
-	io_tlb_orig_size = memblock_alloc(alloc_size, PAGE_SIZE);
-	if (!io_tlb_orig_size)
-		panic("%s: Failed to allocate %zu bytes align=0x%lx\n",
-		      __func__, alloc_size, PAGE_SIZE);
-
-	for (i = 0; i < io_tlb_nslabs; i++) {
-		io_tlb_list[i] = IO_TLB_SEGSIZE - io_tlb_offset(i);
-		io_tlb_orig_addr[i] = INVALID_PHYS_ADDR;
-		io_tlb_orig_size[i] = 0;
+	mem->nslabs = nslabs;
+	mem->start = __pa(tlb);
+	mem->end = mem->start + bytes;
+	mem->index = 0;
+	spin_lock_init(&mem->lock);
+	for (i = 0; i < mem->nslabs; i++) {
+		mem->slots[i].list = IO_TLB_SEGSIZE - io_tlb_offset(i);
+		mem->slots[i].orig_addr = INVALID_PHYS_ADDR;
+		mem->slots[i].alloc_size = 0;
 	}
-	io_tlb_index = 0;
-	no_iotlb_memory = false;
 
+	io_tlb_default_mem = mem;
 	if (verbose)
 		swiotlb_print_info();
-
-	swiotlb_set_max_segment(io_tlb_nslabs << IO_TLB_SHIFT);
+	swiotlb_set_max_segment(mem->nslabs << IO_TLB_SHIFT);
 	return 0;
 }
 
@@ -280,29 +211,24 @@ int __init swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, int verbose)
 void  __init
 swiotlb_init(int verbose)
 {
-	size_t default_size = IO_TLB_DEFAULT_SIZE;
-	unsigned char *vstart;
-	unsigned long bytes;
+	size_t bytes = PAGE_ALIGN(default_nslabs << IO_TLB_SHIFT);
+	void *tlb;
 
-	if (!io_tlb_nslabs) {
-		io_tlb_nslabs = (default_size >> IO_TLB_SHIFT);
-		io_tlb_nslabs = ALIGN(io_tlb_nslabs, IO_TLB_SEGSIZE);
-	}
-
-	bytes = io_tlb_nslabs << IO_TLB_SHIFT;
-
-	/* Get IO TLB memory from the low pages */
-	vstart = memblock_alloc_low(PAGE_ALIGN(bytes), PAGE_SIZE);
-	if (vstart && !swiotlb_init_with_tbl(vstart, io_tlb_nslabs, verbose))
+	if (swiotlb_force == SWIOTLB_NO_FORCE)
 		return;
 
-	if (io_tlb_start) {
-		memblock_free_early(io_tlb_start,
-				    PAGE_ALIGN(io_tlb_nslabs << IO_TLB_SHIFT));
-		io_tlb_start = 0;
-	}
+	/* Get IO TLB memory from the low pages */
+	tlb = memblock_alloc_low(bytes, PAGE_SIZE);
+	if (!tlb)
+		goto fail;
+	if (swiotlb_init_with_tbl(tlb, default_nslabs, verbose))
+		goto fail_free_mem;
+	return;
+
+fail_free_mem:
+	memblock_free_early(__pa(tlb), bytes);
+fail:
 	pr_warn("Cannot allocate buffer");
-	no_iotlb_memory = true;
 }
 
 /*
@@ -313,22 +239,22 @@ swiotlb_init(int verbose)
 int
 swiotlb_late_init_with_default_size(size_t default_size)
 {
-	unsigned long bytes, req_nslabs = io_tlb_nslabs;
+	unsigned long nslabs =
+		ALIGN(default_size >> IO_TLB_SHIFT, IO_TLB_SEGSIZE);
+	unsigned long bytes;
 	unsigned char *vstart = NULL;
 	unsigned int order;
 	int rc = 0;
 
-	if (!io_tlb_nslabs) {
-		io_tlb_nslabs = (default_size >> IO_TLB_SHIFT);
-		io_tlb_nslabs = ALIGN(io_tlb_nslabs, IO_TLB_SEGSIZE);
-	}
+	if (swiotlb_force == SWIOTLB_NO_FORCE)
+		return 0;
 
 	/*
 	 * Get IO TLB memory from the low pages
 	 */
-	order = get_order(io_tlb_nslabs << IO_TLB_SHIFT);
-	io_tlb_nslabs = SLABS_PER_PAGE << order;
-	bytes = io_tlb_nslabs << IO_TLB_SHIFT;
+	order = get_order(nslabs << IO_TLB_SHIFT);
+	nslabs = SLABS_PER_PAGE << order;
+	bytes = nslabs << IO_TLB_SHIFT;
 
 	while ((SLABS_PER_PAGE << order) > IO_TLB_MIN_SLABS) {
 		vstart = (void *)__get_free_pages(GFP_DMA | __GFP_NOWARN,
@@ -338,134 +264,99 @@ swiotlb_late_init_with_default_size(size_t default_size)
 		order--;
 	}
 
-	if (!vstart) {
-		io_tlb_nslabs = req_nslabs;
+	if (!vstart)
 		return -ENOMEM;
-	}
+
 	if (order != get_order(bytes)) {
 		pr_warn("only able to allocate %ld MB\n",
 			(PAGE_SIZE << order) >> 20);
-		io_tlb_nslabs = SLABS_PER_PAGE << order;
+		nslabs = SLABS_PER_PAGE << order;
 	}
-	rc = swiotlb_late_init_with_tbl(vstart, io_tlb_nslabs);
+	rc = swiotlb_late_init_with_tbl(vstart, nslabs);
 	if (rc)
 		free_pages((unsigned long)vstart, order);
 
 	return rc;
 }
 
-static void swiotlb_cleanup(void)
-{
-	io_tlb_end = 0;
-	io_tlb_start = 0;
-	io_tlb_nslabs = 0;
-	max_segment = 0;
-}
-
 int
 swiotlb_late_init_with_tbl(char *tlb, unsigned long nslabs)
 {
-	unsigned long i, bytes;
+	unsigned long bytes = nslabs << IO_TLB_SHIFT, i;
+	struct io_tlb_mem *mem;
 
-	bytes = nslabs << IO_TLB_SHIFT;
+	if (swiotlb_force == SWIOTLB_NO_FORCE)
+		return 0;
 
-	io_tlb_nslabs = nslabs;
-	io_tlb_start = virt_to_phys(tlb);
-	io_tlb_end = io_tlb_start + bytes;
+	/* protect against double initialization */
+	if (WARN_ON_ONCE(io_tlb_default_mem))
+		return -ENOMEM;
+
+	mem = (void *)__get_free_pages(GFP_KERNEL,
+		get_order(struct_size(mem, slots, nslabs)));
+	if (!mem)
+		return -ENOMEM;
+
+	mem->nslabs = nslabs;
+	mem->start = virt_to_phys(tlb);
+	mem->end = mem->start + bytes;
+	mem->index = 0;
+	mem->late_alloc = 1;
+	spin_lock_init(&mem->lock);
+	for (i = 0; i < mem->nslabs; i++) {
+		mem->slots[i].list = IO_TLB_SEGSIZE - io_tlb_offset(i);
+		mem->slots[i].orig_addr = INVALID_PHYS_ADDR;
+		mem->slots[i].alloc_size = 0;
+	}
 
 	set_memory_decrypted((unsigned long)tlb, bytes >> PAGE_SHIFT);
 	memset(tlb, 0, bytes);
 
-	/*
-	 * Allocate and initialize the free list array.  This array is used
-	 * to find contiguous free memory regions of size up to IO_TLB_SEGSIZE
-	 * between io_tlb_start and io_tlb_end.
-	 */
-	io_tlb_list = (unsigned int *)__get_free_pages(GFP_KERNEL,
-				      get_order(io_tlb_nslabs * sizeof(int)));
-	if (!io_tlb_list)
-		goto cleanup3;
-
-	io_tlb_orig_addr = (phys_addr_t *)
-		__get_free_pages(GFP_KERNEL,
-				 get_order(io_tlb_nslabs *
-					   sizeof(phys_addr_t)));
-	if (!io_tlb_orig_addr)
-		goto cleanup4;
-
-	io_tlb_orig_size = (size_t *)
-		__get_free_pages(GFP_KERNEL,
-				 get_order(io_tlb_nslabs *
-					   sizeof(size_t)));
-	if (!io_tlb_orig_size)
-		goto cleanup5;
-
-
-	for (i = 0; i < io_tlb_nslabs; i++) {
-		io_tlb_list[i] = IO_TLB_SEGSIZE - io_tlb_offset(i);
-		io_tlb_orig_addr[i] = INVALID_PHYS_ADDR;
-		io_tlb_orig_size[i] = 0;
-	}
-	io_tlb_index = 0;
-	no_iotlb_memory = false;
-
+	io_tlb_default_mem = mem;
 	swiotlb_print_info();
-
-	late_alloc = 1;
-
-	swiotlb_set_max_segment(io_tlb_nslabs << IO_TLB_SHIFT);
-
+	swiotlb_set_max_segment(mem->nslabs << IO_TLB_SHIFT);
 	return 0;
-
-cleanup5:
-	free_pages((unsigned long)io_tlb_orig_addr, get_order(io_tlb_nslabs *
-							      sizeof(phys_addr_t)));
-
-cleanup4:
-	free_pages((unsigned long)io_tlb_list, get_order(io_tlb_nslabs *
-	                                                 sizeof(int)));
-	io_tlb_list = NULL;
-cleanup3:
-	swiotlb_cleanup();
-	return -ENOMEM;
 }
 
 void __init swiotlb_exit(void)
 {
-	if (!io_tlb_orig_addr)
+	struct io_tlb_mem *mem = io_tlb_default_mem;
+	size_t size;
+
+	if (!mem)
 		return;
 
-	if (late_alloc) {
-		free_pages((unsigned long)io_tlb_orig_size,
-			   get_order(io_tlb_nslabs * sizeof(size_t)));
-		free_pages((unsigned long)io_tlb_orig_addr,
-			   get_order(io_tlb_nslabs * sizeof(phys_addr_t)));
-		free_pages((unsigned long)io_tlb_list, get_order(io_tlb_nslabs *
-								 sizeof(int)));
-		free_pages((unsigned long)phys_to_virt(io_tlb_start),
-			   get_order(io_tlb_nslabs << IO_TLB_SHIFT));
-	} else {
-		memblock_free_late(__pa(io_tlb_orig_addr),
-				   PAGE_ALIGN(io_tlb_nslabs * sizeof(phys_addr_t)));
-		memblock_free_late(__pa(io_tlb_orig_size),
-				   PAGE_ALIGN(io_tlb_nslabs * sizeof(size_t)));
-		memblock_free_late(__pa(io_tlb_list),
-				   PAGE_ALIGN(io_tlb_nslabs * sizeof(int)));
-		memblock_free_late(io_tlb_start,
-				   PAGE_ALIGN(io_tlb_nslabs << IO_TLB_SHIFT));
-	}
-	swiotlb_cleanup();
+	size = struct_size(mem, slots, mem->nslabs);
+	if (mem->late_alloc)
+		free_pages((unsigned long)mem, get_order(size));
+	else
+		memblock_free_late(__pa(mem), PAGE_ALIGN(size));
+	io_tlb_default_mem = NULL;
 }
 
 /*
  * Bounce: copy the swiotlb buffer from or back to the original dma location
  */
-static void swiotlb_bounce(phys_addr_t orig_addr, phys_addr_t tlb_addr,
-			   size_t size, enum dma_data_direction dir)
+static void swiotlb_bounce(struct device *dev, phys_addr_t tlb_addr, size_t size,
+			   enum dma_data_direction dir)
 {
+	struct io_tlb_mem *mem = io_tlb_default_mem;
+	int index = (tlb_addr - mem->start) >> IO_TLB_SHIFT;
+	phys_addr_t orig_addr = mem->slots[index].orig_addr;
+	size_t alloc_size = mem->slots[index].alloc_size;
 	unsigned long pfn = PFN_DOWN(orig_addr);
 	unsigned char *vaddr = phys_to_virt(tlb_addr);
 
+	if (orig_addr == INVALID_PHYS_ADDR)
+		return;
+
+	if (size > alloc_size) {
+		dev_WARN_ONCE(dev, 1,
+			"Buffer overflow detected. Allocation size: %zu. Mapping size: %zu.\n",
+			alloc_size, size);
+		size = alloc_size;
+	}
+
 	if (PageHighMem(pfn_to_page(pfn))) {
 		/* The buffer does not have a mapping.  Map it in and copy */
 		unsigned int offset = orig_addr & ~PAGE_MASK;
@@ -517,9 +408,9 @@ static inline unsigned long get_max_slots(unsigned long boundary_mask)
 	return nr_slots(boundary_mask + 1);
 }
 
-static unsigned int wrap_index(unsigned int index)
+static unsigned int wrap_index(struct io_tlb_mem *mem, unsigned int index)
 {
-	if (index >= io_tlb_nslabs)
+	if (index >= mem->nslabs)
 		return 0;
 	return index;
 }
@@ -531,9 +422,10 @@ static unsigned int wrap_index(unsigned int index)
 static int find_slots(struct device *dev, phys_addr_t orig_addr,
 		size_t alloc_size)
 {
+	struct io_tlb_mem *mem = io_tlb_default_mem;
 	unsigned long boundary_mask = dma_get_seg_boundary(dev);
 	dma_addr_t tbl_dma_addr =
-		phys_to_dma_unencrypted(dev, io_tlb_start) & boundary_mask;
+		phys_to_dma_unencrypted(dev, mem->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);
@@ -552,15 +444,15 @@ static int find_slots(struct device *dev, phys_addr_t orig_addr,
 	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))
+	spin_lock_irqsave(&mem->lock, flags);
+	if (unlikely(nslots > mem->nslabs - mem->used))
 		goto not_found;
 
-	index = wrap = wrap_index(ALIGN(io_tlb_index, stride));
+	index = wrap = wrap_index(mem, ALIGN(mem->index, stride));
 	do {
 		if ((slot_addr(tbl_dma_addr, index) & iotlb_align_mask) !=
 		    (orig_addr & iotlb_align_mask)) {
-			index = wrap_index(index + 1);
+			index = wrap_index(mem, index + 1);
 			continue;
 		}
 
@@ -572,34 +464,34 @@ static int find_slots(struct device *dev, phys_addr_t orig_addr,
 		if (!iommu_is_span_boundary(index, nslots,
 					    nr_slots(tbl_dma_addr),
 					    max_slots)) {
-			if (io_tlb_list[index] >= nslots)
+			if (mem->slots[index].list >= nslots)
 				goto found;
 		}
-		index = wrap_index(index + stride);
+		index = wrap_index(mem, index + stride);
 	} while (index != wrap);
 
 not_found:
-	spin_unlock_irqrestore(&io_tlb_lock, flags);
+	spin_unlock_irqrestore(&mem->lock, flags);
 	return -1;
 
 found:
 	for (i = index; i < index + nslots; i++)
-		io_tlb_list[i] = 0;
+		mem->slots[i].list = 0;
 	for (i = index - 1;
 	     io_tlb_offset(i) != IO_TLB_SEGSIZE - 1 &&
-	     io_tlb_list[i]; i--)
-		io_tlb_list[i] = ++count;
+	     mem->slots[i].list; i--)
+		mem->slots[i].list = ++count;
 
 	/*
 	 * Update the indices to avoid searching in the next round.
 	 */
-	if (index + nslots < io_tlb_nslabs)
-		io_tlb_index = index + nslots;
+	if (index + nslots < mem->nslabs)
+		mem->index = index + nslots;
 	else
-		io_tlb_index = 0;
-	io_tlb_used += nslots;
+		mem->index = 0;
+	mem->used += nslots;
 
-	spin_unlock_irqrestore(&io_tlb_lock, flags);
+	spin_unlock_irqrestore(&mem->lock, flags);
 	return index;
 }
 
@@ -607,11 +499,13 @@ phys_addr_t swiotlb_tbl_map_single(struct device *dev, phys_addr_t orig_addr,
 		size_t mapping_size, size_t alloc_size,
 		enum dma_data_direction dir, unsigned long attrs)
 {
+	struct io_tlb_mem *mem = io_tlb_default_mem;
 	unsigned int offset = swiotlb_align_offset(dev, orig_addr);
-	unsigned int index, i;
+	unsigned int i;
+	int index;
 	phys_addr_t tlb_addr;
 
-	if (no_iotlb_memory)
+	if (!mem)
 		panic("Can not allocate SWIOTLB buffer earlier and can't now provide you with the DMA bounce buffer");
 
 	if (mem_encrypt_active())
@@ -628,7 +522,7 @@ phys_addr_t swiotlb_tbl_map_single(struct device *dev, phys_addr_t orig_addr,
 		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);
+				 alloc_size, mem->nslabs, mem->used);
 		return (phys_addr_t)DMA_MAPPING_ERROR;
 	}
 
@@ -638,49 +532,37 @@ phys_addr_t swiotlb_tbl_map_single(struct device *dev, phys_addr_t orig_addr,
 	 * needed.
 	 */
 	for (i = 0; i < nr_slots(alloc_size + offset); i++) {
-		io_tlb_orig_addr[index + i] = slot_addr(orig_addr, i);
-		io_tlb_orig_size[index+i] = alloc_size - (i << IO_TLB_SHIFT);
+		mem->slots[index + i].orig_addr = slot_addr(orig_addr, i);
+		mem->slots[index + i].alloc_size =
+			alloc_size - (i << IO_TLB_SHIFT);
 	}
-	tlb_addr = slot_addr(io_tlb_start, index) + offset;
+	tlb_addr = slot_addr(mem->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);
+		swiotlb_bounce(dev, tlb_addr, mapping_size, DMA_TO_DEVICE);
 	return tlb_addr;
 }
 
-static void validate_sync_size_and_truncate(struct device *hwdev, size_t orig_size, size_t *size)
-{
-	if (*size > orig_size) {
-		/* Warn and truncate mapping_size */
-		dev_WARN_ONCE(hwdev, 1,
-			"Attempt for buffer overflow. Original size: %zu. Mapping size: %zu.\n",
-			orig_size, *size);
-		*size = orig_size;
-	}
-}
-
 /*
  * tlb_addr is the physical address of the bounce buffer to unmap.
  */
 void swiotlb_tbl_unmap_single(struct device *hwdev, phys_addr_t tlb_addr,
-			      size_t mapping_size, size_t alloc_size,
-			      enum dma_data_direction dir, unsigned long attrs)
+			      size_t mapping_size, enum dma_data_direction dir,
+			      unsigned long attrs)
 {
+	struct io_tlb_mem *mem = io_tlb_default_mem;
 	unsigned long flags;
 	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];
-
-	validate_sync_size_and_truncate(hwdev, io_tlb_orig_size[index], &mapping_size);
+	int index = (tlb_addr - offset - mem->start) >> IO_TLB_SHIFT;
+	int nslots = nr_slots(mem->slots[index].alloc_size + offset);
+	int count, i;
 
 	/*
 	 * First, sync the memory before unmapping the entry
 	 */
-	if (orig_addr != INVALID_PHYS_ADDR &&
-	    !(attrs & DMA_ATTR_SKIP_CPU_SYNC) &&
-	    ((dir == DMA_FROM_DEVICE) || (dir == DMA_BIDIRECTIONAL)))
-		swiotlb_bounce(orig_addr, tlb_addr, mapping_size, DMA_FROM_DEVICE);
+	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC) &&
+	    (dir == DMA_FROM_DEVICE || dir == DMA_BIDIRECTIONAL))
+		swiotlb_bounce(hwdev, tlb_addr, mapping_size, DMA_FROM_DEVICE);
 
 	/*
 	 * Return the buffer to the free list by setting the corresponding
@@ -688,9 +570,9 @@ void swiotlb_tbl_unmap_single(struct device *hwdev, phys_addr_t tlb_addr,
 	 * While returning the entries to the free list, we merge the entries
 	 * with slots below and above the pool being returned.
 	 */
-	spin_lock_irqsave(&io_tlb_lock, flags);
+	spin_lock_irqsave(&mem->lock, flags);
 	if (index + nslots < ALIGN(index + 1, IO_TLB_SEGSIZE))
-		count = io_tlb_list[index + nslots];
+		count = mem->slots[index + nslots].list;
 	else
 		count = 0;
 
@@ -699,9 +581,9 @@ void swiotlb_tbl_unmap_single(struct device *hwdev, phys_addr_t tlb_addr,
 	 * superceeding slots
 	 */
 	for (i = index + nslots - 1; i >= index; i--) {
-		io_tlb_list[i] = ++count;
-		io_tlb_orig_addr[i] = INVALID_PHYS_ADDR;
-		io_tlb_orig_size[i] = 0;
+		mem->slots[i].list = ++count;
+		mem->slots[i].orig_addr = INVALID_PHYS_ADDR;
+		mem->slots[i].alloc_size = 0;
 	}
 
 	/*
@@ -709,44 +591,29 @@ void swiotlb_tbl_unmap_single(struct device *hwdev, phys_addr_t tlb_addr,
 	 * available (non zero)
 	 */
 	for (i = index - 1;
-	     io_tlb_offset(i) != IO_TLB_SEGSIZE - 1 && io_tlb_list[i];
+	     io_tlb_offset(i) != IO_TLB_SEGSIZE - 1 && mem->slots[i].list;
 	     i--)
-		io_tlb_list[i] = ++count;
-	io_tlb_used -= nslots;
-	spin_unlock_irqrestore(&io_tlb_lock, flags);
+		mem->slots[i].list = ++count;
+	mem->used -= nslots;
+	spin_unlock_irqrestore(&mem->lock, flags);
 }
 
-void swiotlb_tbl_sync_single(struct device *hwdev, phys_addr_t tlb_addr,
-			     size_t size, enum dma_data_direction dir,
-			     enum dma_sync_target target)
+void swiotlb_sync_single_for_device(struct device *dev, phys_addr_t tlb_addr,
+		size_t size, enum dma_data_direction dir)
 {
-	int index = (tlb_addr - io_tlb_start) >> IO_TLB_SHIFT;
-	size_t orig_size = io_tlb_orig_size[index];
-	phys_addr_t orig_addr = io_tlb_orig_addr[index];
+	if (dir == DMA_TO_DEVICE || dir == DMA_BIDIRECTIONAL)
+		swiotlb_bounce(dev, tlb_addr, size, DMA_TO_DEVICE);
+	else
+		BUG_ON(dir != DMA_FROM_DEVICE);
+}
 
-	if (orig_addr == INVALID_PHYS_ADDR)
-		return;
-
-	validate_sync_size_and_truncate(hwdev, orig_size, &size);
-
-	switch (target) {
-	case SYNC_FOR_CPU:
-		if (likely(dir == DMA_FROM_DEVICE || dir == DMA_BIDIRECTIONAL))
-			swiotlb_bounce(orig_addr, tlb_addr,
-				       size, DMA_FROM_DEVICE);
-		else
-			BUG_ON(dir != DMA_TO_DEVICE);
-		break;
-	case SYNC_FOR_DEVICE:
-		if (likely(dir == DMA_TO_DEVICE || dir == DMA_BIDIRECTIONAL))
-			swiotlb_bounce(orig_addr, tlb_addr,
-				       size, DMA_TO_DEVICE);
-		else
-			BUG_ON(dir != DMA_FROM_DEVICE);
-		break;
-	default:
-		BUG();
-	}
+void swiotlb_sync_single_for_cpu(struct device *dev, phys_addr_t tlb_addr,
+		size_t size, enum dma_data_direction dir)
+{
+	if (dir == DMA_FROM_DEVICE || dir == DMA_BIDIRECTIONAL)
+		swiotlb_bounce(dev, tlb_addr, size, DMA_FROM_DEVICE);
+	else
+		BUG_ON(dir != DMA_TO_DEVICE);
 }
 
 /*
@@ -770,7 +637,7 @@ dma_addr_t swiotlb_map(struct device *dev, phys_addr_t paddr, size_t size,
 	/* Ensure that the address returned is DMA'ble */
 	dma_addr = phys_to_dma_unencrypted(dev, swiotlb_addr);
 	if (unlikely(!dma_capable(dev, dma_addr, size, true))) {
-		swiotlb_tbl_unmap_single(dev, swiotlb_addr, size, size, dir,
+		swiotlb_tbl_unmap_single(dev, swiotlb_addr, size, dir,
 			attrs | DMA_ATTR_SKIP_CPU_SYNC);
 		dev_WARN_ONCE(dev, 1,
 			"swiotlb addr %pad+%zu overflow (mask %llx, bus limit %llx).\n",
@@ -790,22 +657,21 @@ size_t swiotlb_max_mapping_size(struct device *dev)
 
 bool is_swiotlb_active(void)
 {
-	/*
-	 * When SWIOTLB is initialized, even if io_tlb_start points to physical
-	 * address zero, io_tlb_end surely doesn't.
-	 */
-	return io_tlb_end != 0;
+	return io_tlb_default_mem != NULL;
 }
+EXPORT_SYMBOL_GPL(is_swiotlb_active);
 
 #ifdef CONFIG_DEBUG_FS
 
 static int __init swiotlb_create_debugfs(void)
 {
-	struct dentry *root;
+	struct io_tlb_mem *mem = io_tlb_default_mem;
 
-	root = debugfs_create_dir("swiotlb", NULL);
-	debugfs_create_ulong("io_tlb_nslabs", 0400, root, &io_tlb_nslabs);
-	debugfs_create_ulong("io_tlb_used", 0400, root, &io_tlb_used);
+	if (!mem)
+		return 0;
+	mem->debugfs = debugfs_create_dir("swiotlb", NULL);
+	debugfs_create_ulong("io_tlb_nslabs", 0400, mem->debugfs, &mem->nslabs);
+	debugfs_create_ulong("io_tlb_used", 0400, mem->debugfs, &mem->used);
 	return 0;
 }