Merge tag 'v6.0-rc6' into locking/core, to refresh the branch

Signed-off-by: Ingo Molnar <mingo@kernel.org>

6 files changed, 314 insertions, 67 deletions

diff --git a/kernel/dma/coherent.c b/kernel/dma/coherent.c
index 375fb3c9538d..c21abc77c53e 100644
--- a/kernel/dma/coherent.c
+++ b/kernel/dma/coherent.c
@@ -74,7 +74,7 @@ out_unmap_membase:
 	return ERR_PTR(-ENOMEM);
 }
 
-static void dma_release_coherent_memory(struct dma_coherent_mem *mem)
+static void _dma_release_coherent_memory(struct dma_coherent_mem *mem)
 {
 	if (!mem)
 		return;
@@ -126,10 +126,16 @@ int dma_declare_coherent_memory(struct device *dev, phys_addr_t phys_addr,
 
 	ret = dma_assign_coherent_memory(dev, mem);
 	if (ret)
-		dma_release_coherent_memory(mem);
+		_dma_release_coherent_memory(mem);
 	return ret;
 }
 
+void dma_release_coherent_memory(struct device *dev)
+{
+	if (dev)
+		_dma_release_coherent_memory(dev->dma_mem);
+}
+
 static void *__dma_alloc_from_coherent(struct device *dev,
 				       struct dma_coherent_mem *mem,
 				       ssize_t size, dma_addr_t *dma_handle)
diff --git a/kernel/dma/debug.c b/kernel/dma/debug.c
index 2caafd13f8aa..18c93c2276ca 100644
--- a/kernel/dma/debug.c
+++ b/kernel/dma/debug.c
@@ -350,11 +350,10 @@ static struct dma_debug_entry *bucket_find_contain(struct hash_bucket **bucket,
 						   unsigned long *flags)
 {
 
-	unsigned int max_range = dma_get_max_seg_size(ref->dev);
 	struct dma_debug_entry *entry, index = *ref;
-	unsigned int range = 0;
+	int limit = min(HASH_SIZE, (index.dev_addr >> HASH_FN_SHIFT) + 1);
 
-	while (range <= max_range) {
+	for (int i = 0; i < limit; i++) {
 		entry = __hash_bucket_find(*bucket, ref, containing_match);
 
 		if (entry)
@@ -364,7 +363,6 @@ static struct dma_debug_entry *bucket_find_contain(struct hash_bucket **bucket,
 		 * Nothing found, go back a hash bucket
 		 */
 		put_hash_bucket(*bucket, *flags);
-		range          += (1 << HASH_FN_SHIFT);
 		index.dev_addr -= (1 << HASH_FN_SHIFT);
 		*bucket = get_hash_bucket(&index, flags);
 	}
diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c
index 8d0b68a17042..63859a101ed8 100644
--- a/kernel/dma/direct.c
+++ b/kernel/dma/direct.c
@@ -453,29 +453,60 @@ void dma_direct_sync_sg_for_cpu(struct device *dev,
 		arch_sync_dma_for_cpu_all();
 }
 
+/*
+ * Unmaps segments, except for ones marked as pci_p2pdma which do not
+ * require any further action as they contain a bus address.
+ */
 void dma_direct_unmap_sg(struct device *dev, struct scatterlist *sgl,
 		int nents, enum dma_data_direction dir, unsigned long attrs)
 {
 	struct scatterlist *sg;
 	int i;
 
-	for_each_sg(sgl, sg, nents, i)
-		dma_direct_unmap_page(dev, sg->dma_address, sg_dma_len(sg), dir,
-			     attrs);
+	for_each_sg(sgl,  sg, nents, i) {
+		if (sg_is_dma_bus_address(sg))
+			sg_dma_unmark_bus_address(sg);
+		else
+			dma_direct_unmap_page(dev, sg->dma_address,
+					      sg_dma_len(sg), dir, attrs);
+	}
 }
 #endif
 
 int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl, int nents,
 		enum dma_data_direction dir, unsigned long attrs)
 {
-	int i;
+	struct pci_p2pdma_map_state p2pdma_state = {};
+	enum pci_p2pdma_map_type map;
 	struct scatterlist *sg;
+	int i, ret;
 
 	for_each_sg(sgl, sg, nents, i) {
+		if (is_pci_p2pdma_page(sg_page(sg))) {
+			map = pci_p2pdma_map_segment(&p2pdma_state, dev, sg);
+			switch (map) {
+			case PCI_P2PDMA_MAP_BUS_ADDR:
+				continue;
+			case PCI_P2PDMA_MAP_THRU_HOST_BRIDGE:
+				/*
+				 * Any P2P mapping that traverses the PCI
+				 * host bridge must be mapped with CPU physical
+				 * address and not PCI bus addresses. This is
+				 * done with dma_direct_map_page() below.
+				 */
+				break;
+			default:
+				ret = -EREMOTEIO;
+				goto out_unmap;
+			}
+		}
+
 		sg->dma_address = dma_direct_map_page(dev, sg_page(sg),
 				sg->offset, sg->length, dir, attrs);
-		if (sg->dma_address == DMA_MAPPING_ERROR)
+		if (sg->dma_address == DMA_MAPPING_ERROR) {
+			ret = -EIO;
 			goto out_unmap;
+		}
 		sg_dma_len(sg) = sg->length;
 	}
 
@@ -483,7 +514,7 @@ int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl, int nents,
 
 out_unmap:
 	dma_direct_unmap_sg(dev, sgl, i, dir, attrs | DMA_ATTR_SKIP_CPU_SYNC);
-	return -EIO;
+	return ret;
 }
 
 dma_addr_t dma_direct_map_resource(struct device *dev, phys_addr_t paddr,
diff --git a/kernel/dma/direct.h b/kernel/dma/direct.h
index a78c0ba70645..e38ffc5e6bdd 100644
--- a/kernel/dma/direct.h
+++ b/kernel/dma/direct.h
@@ -8,6 +8,7 @@
 #define _KERNEL_DMA_DIRECT_H
 
 #include <linux/dma-direct.h>
+#include <linux/memremap.h>
 
 int dma_direct_get_sgtable(struct device *dev, struct sg_table *sgt,
 		void *cpu_addr, dma_addr_t dma_addr, size_t size,
@@ -87,10 +88,15 @@ static inline dma_addr_t dma_direct_map_page(struct device *dev,
 	phys_addr_t phys = page_to_phys(page) + offset;
 	dma_addr_t dma_addr = phys_to_dma(dev, phys);
 
-	if (is_swiotlb_force_bounce(dev))
+	if (is_swiotlb_force_bounce(dev)) {
+		if (is_pci_p2pdma_page(page))
+			return DMA_MAPPING_ERROR;
 		return swiotlb_map(dev, phys, size, dir, attrs);
+	}
 
 	if (unlikely(!dma_capable(dev, dma_addr, size, true))) {
+		if (is_pci_p2pdma_page(page))
+			return DMA_MAPPING_ERROR;
 		if (is_swiotlb_active(dev))
 			return swiotlb_map(dev, phys, size, dir, attrs);
 
diff --git a/kernel/dma/mapping.c b/kernel/dma/mapping.c
index db7244291b74..27f272381cf2 100644
--- a/kernel/dma/mapping.c
+++ b/kernel/dma/mapping.c
@@ -197,7 +197,7 @@ static int __dma_map_sg_attrs(struct device *dev, struct scatterlist *sg,
 	if (ents > 0)
 		debug_dma_map_sg(dev, sg, nents, ents, dir, attrs);
 	else if (WARN_ON_ONCE(ents != -EINVAL && ents != -ENOMEM &&
-			      ents != -EIO))
+			      ents != -EIO && ents != -EREMOTEIO))
 		return -EIO;
 
 	return ents;
@@ -249,12 +249,15 @@ EXPORT_SYMBOL(dma_map_sg_attrs);
  * Returns 0 on success or a negative error code on error. The following
  * error codes are supported with the given meaning:
  *
- *   -EINVAL	An invalid argument, unaligned access or other error
- *		in usage. Will not succeed if retried.
- *   -ENOMEM	Insufficient resources (like memory or IOVA space) to
- *		complete the mapping. Should succeed if retried later.
- *   -EIO	Legacy error code with an unknown meaning. eg. this is
- *		returned if a lower level call returned DMA_MAPPING_ERROR.
+ *   -EINVAL		An invalid argument, unaligned access or other error
+ *			in usage. Will not succeed if retried.
+ *   -ENOMEM		Insufficient resources (like memory or IOVA space) to
+ *			complete the mapping. Should succeed if retried later.
+ *   -EIO		Legacy error code with an unknown meaning. eg. this is
+ *			returned if a lower level call returned
+ *			DMA_MAPPING_ERROR.
+ *   -EREMOTEIO		The DMA device cannot access P2PDMA memory specified
+ *			in the sg_table. This will not succeed if retried.
  */
 int dma_map_sgtable(struct device *dev, struct sg_table *sgt,
 		    enum dma_data_direction dir, unsigned long attrs)
@@ -704,7 +707,7 @@ int dma_mmap_noncontiguous(struct device *dev, struct vm_area_struct *vma,
 }
 EXPORT_SYMBOL_GPL(dma_mmap_noncontiguous);
 
-int dma_supported(struct device *dev, u64 mask)
+static int dma_supported(struct device *dev, u64 mask)
 {
 	const struct dma_map_ops *ops = get_dma_ops(dev);
 
@@ -718,7 +721,24 @@ int dma_supported(struct device *dev, u64 mask)
 		return 1;
 	return ops->dma_supported(dev, mask);
 }
-EXPORT_SYMBOL(dma_supported);
+
+bool dma_pci_p2pdma_supported(struct device *dev)
+{
+	const struct dma_map_ops *ops = get_dma_ops(dev);
+
+	/* if ops is not set, dma direct will be used which supports P2PDMA */
+	if (!ops)
+		return true;
+
+	/*
+	 * Note: dma_ops_bypass is not checked here because P2PDMA should
+	 * not be used with dma mapping ops that do not have support even
+	 * if the specific device is bypassing them.
+	 */
+
+	return ops->flags & DMA_F_PCI_P2PDMA_SUPPORTED;
+}
+EXPORT_SYMBOL_GPL(dma_pci_p2pdma_supported);
 
 #ifdef CONFIG_ARCH_HAS_DMA_SET_MASK
 void arch_dma_set_mask(struct device *dev, u64 mask);
@@ -773,6 +793,18 @@ size_t dma_max_mapping_size(struct device *dev)
 }
 EXPORT_SYMBOL_GPL(dma_max_mapping_size);
 
+size_t dma_opt_mapping_size(struct device *dev)
+{
+	const struct dma_map_ops *ops = get_dma_ops(dev);
+	size_t size = SIZE_MAX;
+
+	if (ops && ops->opt_mapping_size)
+		size = ops->opt_mapping_size();
+
+	return min(dma_max_mapping_size(dev), size);
+}
+EXPORT_SYMBOL_GPL(dma_opt_mapping_size);
+
 bool dma_need_sync(struct device *dev, dma_addr_t dma_addr)
 {
 	const struct dma_map_ops *ops = get_dma_ops(dev);
diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c
index cb50f8d38360..0ef6b12f961d 100644
--- a/kernel/dma/swiotlb.c
+++ b/kernel/dma/swiotlb.c
@@ -62,6 +62,12 @@
 
 #define INVALID_PHYS_ADDR (~(phys_addr_t)0)
 
+struct io_tlb_slot {
+	phys_addr_t orig_addr;
+	size_t alloc_size;
+	unsigned int list;
+};
+
 static bool swiotlb_force_bounce;
 static bool swiotlb_force_disable;
 
@@ -70,6 +76,62 @@ struct io_tlb_mem io_tlb_default_mem;
 phys_addr_t swiotlb_unencrypted_base;
 
 static unsigned long default_nslabs = IO_TLB_DEFAULT_SIZE >> IO_TLB_SHIFT;
+static unsigned long default_nareas;
+
+/**
+ * struct io_tlb_area - IO TLB memory area descriptor
+ *
+ * This is a single area with a single lock.
+ *
+ * @used:	The number of used IO TLB block.
+ * @index:	The slot index to start searching in this area for next round.
+ * @lock:	The lock to protect the above data structures in the map and
+ *		unmap calls.
+ */
+struct io_tlb_area {
+	unsigned long used;
+	unsigned int index;
+	spinlock_t lock;
+};
+
+/*
+ * Round up number of slabs to the next power of 2. The last area is going
+ * be smaller than the rest if default_nslabs is not power of two.
+ * The number of slot in an area should be a multiple of IO_TLB_SEGSIZE,
+ * otherwise a segment may span two or more areas. It conflicts with free
+ * contiguous slots tracking: free slots are treated contiguous no matter
+ * whether they cross an area boundary.
+ *
+ * Return true if default_nslabs is rounded up.
+ */
+static bool round_up_default_nslabs(void)
+{
+	if (!default_nareas)
+		return false;
+
+	if (default_nslabs < IO_TLB_SEGSIZE * default_nareas)
+		default_nslabs = IO_TLB_SEGSIZE * default_nareas;
+	else if (is_power_of_2(default_nslabs))
+		return false;
+	default_nslabs = roundup_pow_of_two(default_nslabs);
+	return true;
+}
+
+static void swiotlb_adjust_nareas(unsigned int nareas)
+{
+	/* use a single area when non is specified */
+	if (!nareas)
+		nareas = 1;
+	else if (!is_power_of_2(nareas))
+		nareas = roundup_pow_of_two(nareas);
+
+	default_nareas = nareas;
+
+	pr_info("area num %d.\n", nareas);
+	if (round_up_default_nslabs())
+		pr_info("SWIOTLB bounce buffer size roundup to %luMB",
+			(default_nslabs << IO_TLB_SHIFT) >> 20);
+}
 
 static int __init
 setup_io_tlb_npages(char *str)
@@ -81,6 +143,10 @@ setup_io_tlb_npages(char *str)
 	}
 	if (*str == ',')
 		++str;
+	if (isdigit(*str))
+		swiotlb_adjust_nareas(simple_strtoul(str, &str, 0));
+	if (*str == ',')
+		++str;
 	if (!strcmp(str, "force"))
 		swiotlb_force_bounce = true;
 	else if (!strcmp(str, "noforce"))
@@ -112,8 +178,11 @@ void __init swiotlb_adjust_size(unsigned long size)
 	 */
 	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);
+	if (round_up_default_nslabs())
+		size = default_nslabs << IO_TLB_SHIFT;
 	pr_info("SWIOTLB bounce buffer size adjusted to %luMB", size >> 20);
 }
 
@@ -192,7 +261,8 @@ void __init swiotlb_update_mem_attributes(void)
 }
 
 static void swiotlb_init_io_tlb_mem(struct io_tlb_mem *mem, phys_addr_t start,
-		unsigned long nslabs, unsigned int flags, bool late_alloc)
+		unsigned long nslabs, unsigned int flags,
+		bool late_alloc, unsigned int nareas)
 {
 	void *vaddr = phys_to_virt(start);
 	unsigned long bytes = nslabs << IO_TLB_SHIFT, i;
@@ -200,12 +270,18 @@ static void swiotlb_init_io_tlb_mem(struct io_tlb_mem *mem, phys_addr_t start,
 	mem->nslabs = nslabs;
 	mem->start = start;
 	mem->end = mem->start + bytes;
-	mem->index = 0;
 	mem->late_alloc = late_alloc;
+	mem->nareas = nareas;
+	mem->area_nslabs = nslabs / mem->nareas;
 
 	mem->force_bounce = swiotlb_force_bounce || (flags & SWIOTLB_FORCE);
 
-	spin_lock_init(&mem->lock);
+	for (i = 0; i < mem->nareas; i++) {
+		spin_lock_init(&mem->areas[i].lock);
+		mem->areas[i].index = 0;
+		mem->areas[i].used = 0;
+	}
+
 	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;
@@ -232,7 +308,7 @@ void __init swiotlb_init_remap(bool addressing_limit, unsigned int flags,
 		int (*remap)(void *tlb, unsigned long nslabs))
 {
 	struct io_tlb_mem *mem = &io_tlb_default_mem;
-	unsigned long nslabs = default_nslabs;
+	unsigned long nslabs;
 	size_t alloc_size;
 	size_t bytes;
 	void *tlb;
@@ -243,6 +319,14 @@ void __init swiotlb_init_remap(bool addressing_limit, unsigned int flags,
 		return;
 
 	/*
+	 * default_nslabs maybe changed when adjust area number.
+	 * So allocate bounce buffer after adjusting area number.
+	 */
+	if (!default_nareas)
+		swiotlb_adjust_nareas(num_possible_cpus());
+
+	nslabs = default_nslabs;
+	/*
 	 * By default allocate the bounce buffer memory from low memory, but
 	 * allow to pick a location everywhere for hypervisors with guest
 	 * memory encryption.
@@ -274,7 +358,13 @@ retry:
 		panic("%s: Failed to allocate %zu bytes align=0x%lx\n",
 		      __func__, alloc_size, PAGE_SIZE);
 
-	swiotlb_init_io_tlb_mem(mem, __pa(tlb), nslabs, flags, false);
+	mem->areas = memblock_alloc(array_size(sizeof(struct io_tlb_area),
+		default_nareas), SMP_CACHE_BYTES);
+	if (!mem->areas)
+		panic("%s: Failed to allocate mem->areas.\n", __func__);
+
+	swiotlb_init_io_tlb_mem(mem, __pa(tlb), nslabs, flags, false,
+				default_nareas);
 
 	if (flags & SWIOTLB_VERBOSE)
 		swiotlb_print_info();
@@ -282,7 +372,7 @@ retry:
 
 void __init swiotlb_init(bool addressing_limit, unsigned int flags)
 {
-	return swiotlb_init_remap(addressing_limit, flags, NULL);
+	swiotlb_init_remap(addressing_limit, flags, NULL);
 }
 
 /*
@@ -296,7 +386,7 @@ int swiotlb_init_late(size_t size, gfp_t gfp_mask,
 	struct io_tlb_mem *mem = &io_tlb_default_mem;
 	unsigned long nslabs = ALIGN(size >> IO_TLB_SHIFT, IO_TLB_SEGSIZE);
 	unsigned char *vstart = NULL;
-	unsigned int order;
+	unsigned int order, area_order;
 	bool retried = false;
 	int rc = 0;
 
@@ -337,19 +427,34 @@ retry:
 			(PAGE_SIZE << order) >> 20);
 	}
 
+	if (!default_nareas)
+		swiotlb_adjust_nareas(num_possible_cpus());
+
+	area_order = get_order(array_size(sizeof(*mem->areas),
+		default_nareas));
+	mem->areas = (struct io_tlb_area *)
+		__get_free_pages(GFP_KERNEL | __GFP_ZERO, area_order);
+	if (!mem->areas)
+		goto error_area;
+
 	mem->slots = (void *)__get_free_pages(GFP_KERNEL | __GFP_ZERO,
 		get_order(array_size(sizeof(*mem->slots), nslabs)));
-	if (!mem->slots) {
-		free_pages((unsigned long)vstart, order);
-		return -ENOMEM;
-	}
+	if (!mem->slots)
+		goto error_slots;
 
 	set_memory_decrypted((unsigned long)vstart,
 			     (nslabs << IO_TLB_SHIFT) >> PAGE_SHIFT);
-	swiotlb_init_io_tlb_mem(mem, virt_to_phys(vstart), nslabs, 0, true);
+	swiotlb_init_io_tlb_mem(mem, virt_to_phys(vstart), nslabs, 0, true,
+				default_nareas);
 
 	swiotlb_print_info();
 	return 0;
+
+error_slots:
+	free_pages((unsigned long)mem->areas, area_order);
+error_area:
+	free_pages((unsigned long)vstart, order);
+	return -ENOMEM;
 }
 
 void __init swiotlb_exit(void)
@@ -357,6 +462,7 @@ void __init swiotlb_exit(void)
 	struct io_tlb_mem *mem = &io_tlb_default_mem;
 	unsigned long tbl_vaddr;
 	size_t tbl_size, slots_size;
+	unsigned int area_order;
 
 	if (swiotlb_force_bounce)
 		return;
@@ -371,9 +477,14 @@ void __init swiotlb_exit(void)
 
 	set_memory_encrypted(tbl_vaddr, tbl_size >> PAGE_SHIFT);
 	if (mem->late_alloc) {
+		area_order = get_order(array_size(sizeof(*mem->areas),
+			mem->nareas));
+		free_pages((unsigned long)mem->areas, area_order);
 		free_pages(tbl_vaddr, get_order(tbl_size));
 		free_pages((unsigned long)mem->slots, get_order(slots_size));
 	} else {
+		memblock_free_late(__pa(mem->areas),
+			array_size(sizeof(*mem->areas), mem->nareas));
 		memblock_free_late(mem->start, tbl_size);
 		memblock_free_late(__pa(mem->slots), slots_size);
 	}
@@ -464,7 +575,10 @@ 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))
+static inline phys_addr_t slot_addr(phys_addr_t start, phys_addr_t idx)
+{
+	return start + (idx << IO_TLB_SHIFT);
+}
 
 /*
  * Carefully handle integer overflow which can occur when boundary_mask == ~0UL.
@@ -476,9 +590,9 @@ static inline unsigned long get_max_slots(unsigned long boundary_mask)
 	return nr_slots(boundary_mask + 1);
 }
 
-static unsigned int wrap_index(struct io_tlb_mem *mem, unsigned int index)
+static unsigned int wrap_area_index(struct io_tlb_mem *mem, unsigned int index)
 {
-	if (index >= mem->nslabs)
+	if (index >= mem->area_nslabs)
 		return 0;
 	return index;
 }
@@ -487,10 +601,12 @@ static unsigned int wrap_index(struct io_tlb_mem *mem, unsigned int 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 swiotlb_find_slots(struct device *dev, phys_addr_t orig_addr,
-			      size_t alloc_size, unsigned int alloc_align_mask)
+static int swiotlb_do_find_slots(struct device *dev, int area_index,
+		phys_addr_t orig_addr, size_t alloc_size,
+		unsigned int alloc_align_mask)
 {
 	struct io_tlb_mem *mem = dev->dma_io_tlb_mem;
+	struct io_tlb_area *area = mem->areas + area_index;
 	unsigned long boundary_mask = dma_get_seg_boundary(dev);
 	dma_addr_t tbl_dma_addr =
 		phys_to_dma_unencrypted(dev, mem->start) & boundary_mask;
@@ -501,8 +617,11 @@ static int swiotlb_find_slots(struct device *dev, phys_addr_t orig_addr,
 	unsigned int index, wrap, count = 0, i;
 	unsigned int offset = swiotlb_align_offset(dev, orig_addr);
 	unsigned long flags;
+	unsigned int slot_base;
+	unsigned int slot_index;
 
 	BUG_ON(!nslots);
+	BUG_ON(area_index >= mem->nareas);
 
 	/*
 	 * For mappings with an alignment requirement don't bother looping to
@@ -514,16 +633,20 @@ static int swiotlb_find_slots(struct device *dev, phys_addr_t orig_addr,
 		stride = max(stride, stride << (PAGE_SHIFT - IO_TLB_SHIFT));
 	stride = max(stride, (alloc_align_mask >> IO_TLB_SHIFT) + 1);
 
-	spin_lock_irqsave(&mem->lock, flags);
-	if (unlikely(nslots > mem->nslabs - mem->used))
+	spin_lock_irqsave(&area->lock, flags);
+	if (unlikely(nslots > mem->area_nslabs - area->used))
 		goto not_found;
 
-	index = wrap = wrap_index(mem, ALIGN(mem->index, stride));
+	slot_base = area_index * mem->area_nslabs;
+	index = wrap = wrap_area_index(mem, ALIGN(area->index, stride));
+
 	do {
+		slot_index = slot_base + index;
+
 		if (orig_addr &&
-		    (slot_addr(tbl_dma_addr, index) & iotlb_align_mask) !=
-			    (orig_addr & iotlb_align_mask)) {
-			index = wrap_index(mem, index + 1);
+		    (slot_addr(tbl_dma_addr, slot_index) &
+		     iotlb_align_mask) != (orig_addr & iotlb_align_mask)) {
+			index = wrap_area_index(mem, index + 1);
 			continue;
 		}
 
@@ -532,26 +655,26 @@ static int swiotlb_find_slots(struct device *dev, phys_addr_t orig_addr,
 		 * contiguous buffers, we allocate the buffers from that slot
 		 * and mark the entries as '0' indicating unavailable.
 		 */
-		if (!iommu_is_span_boundary(index, nslots,
+		if (!iommu_is_span_boundary(slot_index, nslots,
 					    nr_slots(tbl_dma_addr),
 					    max_slots)) {
-			if (mem->slots[index].list >= nslots)
+			if (mem->slots[slot_index].list >= nslots)
 				goto found;
 		}
-		index = wrap_index(mem, index + stride);
+		index = wrap_area_index(mem, index + stride);
 	} while (index != wrap);
 
 not_found:
-	spin_unlock_irqrestore(&mem->lock, flags);
+	spin_unlock_irqrestore(&area->lock, flags);
 	return -1;
 
 found:
-	for (i = index; i < index + nslots; i++) {
+	for (i = slot_index; i < slot_index + nslots; i++) {
 		mem->slots[i].list = 0;
-		mem->slots[i].alloc_size =
-			alloc_size - (offset + ((i - index) << IO_TLB_SHIFT));
+		mem->slots[i].alloc_size = alloc_size - (offset +
+				((i - slot_index) << IO_TLB_SHIFT));
 	}
-	for (i = index - 1;
+	for (i = slot_index - 1;
 	     io_tlb_offset(i) != IO_TLB_SEGSIZE - 1 &&
 	     mem->slots[i].list; i--)
 		mem->slots[i].list = ++count;
@@ -559,14 +682,42 @@ found:
 	/*
 	 * Update the indices to avoid searching in the next round.
 	 */
-	if (index + nslots < mem->nslabs)
-		mem->index = index + nslots;
+	if (index + nslots < mem->area_nslabs)
+		area->index = index + nslots;
 	else
-		mem->index = 0;
-	mem->used += nslots;
+		area->index = 0;
+	area->used += nslots;
+	spin_unlock_irqrestore(&area->lock, flags);
+	return slot_index;
+}
 
-	spin_unlock_irqrestore(&mem->lock, flags);
-	return index;
+static int swiotlb_find_slots(struct device *dev, phys_addr_t orig_addr,
+		size_t alloc_size, unsigned int alloc_align_mask)
+{
+	struct io_tlb_mem *mem = dev->dma_io_tlb_mem;
+	int start = raw_smp_processor_id() & (mem->nareas - 1);
+	int i = start, index;
+
+	do {
+		index = swiotlb_do_find_slots(dev, i, orig_addr, alloc_size,
+					      alloc_align_mask);
+		if (index >= 0)
+			return index;
+		if (++i >= mem->nareas)
+			i = 0;
+	} while (i != start);
+
+	return -1;
+}
+
+static unsigned long mem_used(struct io_tlb_mem *mem)
+{
+	int i;
+	unsigned long used = 0;
+
+	for (i = 0; i < mem->nareas; i++)
+		used += mem->areas[i].used;
+	return used;
 }
 
 phys_addr_t swiotlb_tbl_map_single(struct device *dev, phys_addr_t orig_addr,
@@ -580,7 +731,7 @@ phys_addr_t swiotlb_tbl_map_single(struct device *dev, phys_addr_t orig_addr,
 	int index;
 	phys_addr_t tlb_addr;
 
-	if (!mem)
+	if (!mem || !mem->nslabs)
 		panic("Can not allocate SWIOTLB buffer earlier and can't now provide you with the DMA bounce buffer");
 
 	if (cc_platform_has(CC_ATTR_MEM_ENCRYPT))
@@ -598,7 +749,7 @@ 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, mem->nslabs, mem->used);
+				 alloc_size, mem->nslabs, mem_used(mem));
 		return (phys_addr_t)DMA_MAPPING_ERROR;
 	}
 
@@ -613,7 +764,7 @@ phys_addr_t swiotlb_tbl_map_single(struct device *dev, phys_addr_t orig_addr,
 	/*
 	 * When dir == DMA_FROM_DEVICE we could omit the copy from the orig
 	 * to the tlb buffer, if we knew for sure the device will
-	 * overwirte the entire current content. But we don't. Thus
+	 * overwrite the entire current content. But we don't. Thus
 	 * unconditional bounce may prevent leaking swiotlb content (i.e.
 	 * kernel memory) to user-space.
 	 */
@@ -628,6 +779,8 @@ static void swiotlb_release_slots(struct device *dev, phys_addr_t tlb_addr)
 	unsigned int offset = swiotlb_align_offset(dev, tlb_addr);
 	int index = (tlb_addr - offset - mem->start) >> IO_TLB_SHIFT;
 	int nslots = nr_slots(mem->slots[index].alloc_size + offset);
+	int aindex = index / mem->area_nslabs;
+	struct io_tlb_area *area = &mem->areas[aindex];
 	int count, i;
 
 	/*
@@ -636,7 +789,9 @@ static void swiotlb_release_slots(struct device *dev, 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(&mem->lock, flags);
+	BUG_ON(aindex >= mem->nareas);
+
+	spin_lock_irqsave(&area->lock, flags);
 	if (index + nslots < ALIGN(index + 1, IO_TLB_SEGSIZE))
 		count = mem->slots[index + nslots].list;
 	else
@@ -660,8 +815,8 @@ static void swiotlb_release_slots(struct device *dev, phys_addr_t tlb_addr)
 	     io_tlb_offset(i) != IO_TLB_SEGSIZE - 1 && mem->slots[i].list;
 	     i--)
 		mem->slots[i].list = ++count;
-	mem->used -= nslots;
-	spin_unlock_irqrestore(&mem->lock, flags);
+	area->used -= nslots;
+	spin_unlock_irqrestore(&area->lock, flags);
 }
 
 /*
@@ -756,6 +911,13 @@ bool is_swiotlb_active(struct device *dev)
 }
 EXPORT_SYMBOL_GPL(is_swiotlb_active);
 
+static int io_tlb_used_get(void *data, u64 *val)
+{
+	*val = mem_used(&io_tlb_default_mem);
+	return 0;
+}
+DEFINE_DEBUGFS_ATTRIBUTE(fops_io_tlb_used, io_tlb_used_get, NULL, "%llu\n");
+
 static void swiotlb_create_debugfs_files(struct io_tlb_mem *mem,
 					 const char *dirname)
 {
@@ -764,7 +926,8 @@ static void swiotlb_create_debugfs_files(struct io_tlb_mem *mem,
 		return;
 
 	debugfs_create_ulong("io_tlb_nslabs", 0400, mem->debugfs, &mem->nslabs);
-	debugfs_create_ulong("io_tlb_used", 0400, mem->debugfs, &mem->used);
+	debugfs_create_file("io_tlb_used", 0400, mem->debugfs, NULL,
+			&fops_io_tlb_used);
 }
 
 static int __init __maybe_unused swiotlb_create_default_debugfs(void)
@@ -815,6 +978,9 @@ static int rmem_swiotlb_device_init(struct reserved_mem *rmem,
 	struct io_tlb_mem *mem = rmem->priv;
 	unsigned long nslabs = rmem->size >> IO_TLB_SHIFT;
 
+	/* Set Per-device io tlb area to one */
+	unsigned int nareas = 1;
+
 	/*
 	 * Since multiple devices can share the same pool, the private data,
 	 * io_tlb_mem struct, will be initialized by the first device attached
@@ -831,10 +997,18 @@ static int rmem_swiotlb_device_init(struct reserved_mem *rmem,
 			return -ENOMEM;
 		}
 
+		mem->areas = kcalloc(nareas, sizeof(*mem->areas),
+				GFP_KERNEL);
+		if (!mem->areas) {
+			kfree(mem->slots);
+			kfree(mem);
+			return -ENOMEM;
+		}
+
 		set_memory_decrypted((unsigned long)phys_to_virt(rmem->base),
 				     rmem->size >> PAGE_SHIFT);
 		swiotlb_init_io_tlb_mem(mem, rmem->base, nslabs, SWIOTLB_FORCE,
-				false);
+					false, nareas);
 		mem->for_alloc = true;
 
 		rmem->priv = mem;