1 files changed, 394 insertions, 189 deletions

diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c
index 8e840fbbed7c..339a990554e7 100644
--- a/kernel/dma/swiotlb.c
+++ b/kernel/dma/swiotlb.c
@@ -21,39 +21,33 @@
 #define pr_fmt(fmt) "software IO TLB: " fmt
 
 #include <linux/cache.h>
+#include <linux/cc_platform.h>
+#include <linux/ctype.h>
+#include <linux/debugfs.h>
 #include <linux/dma-direct.h>
 #include <linux/dma-map-ops.h>
-#include <linux/mm.h>
 #include <linux/export.h>
+#include <linux/gfp.h>
+#include <linux/highmem.h>
+#include <linux/io.h>
+#include <linux/iommu-helper.h>
+#include <linux/init.h>
+#include <linux/memblock.h>
+#include <linux/mm.h>
+#include <linux/pfn.h>
+#include <linux/scatterlist.h>
+#include <linux/set_memory.h>
 #include <linux/spinlock.h>
 #include <linux/string.h>
 #include <linux/swiotlb.h>
-#include <linux/pfn.h>
 #include <linux/types.h>
-#include <linux/ctype.h>
-#include <linux/highmem.h>
-#include <linux/gfp.h>
-#include <linux/scatterlist.h>
-#include <linux/cc_platform.h>
-#include <linux/set_memory.h>
-#ifdef CONFIG_DEBUG_FS
-#include <linux/debugfs.h>
-#endif
 #ifdef CONFIG_DMA_RESTRICTED_POOL
-#include <linux/io.h>
 #include <linux/of.h>
 #include <linux/of_fdt.h>
 #include <linux/of_reserved_mem.h>
 #include <linux/slab.h>
 #endif
 
-#include <asm/io.h>
-#include <asm/dma.h>
-
-#include <linux/init.h>
-#include <linux/memblock.h>
-#include <linux/iommu-helper.h>
-
 #define CREATE_TRACE_POINTS
 #include <trace/events/swiotlb.h>
 
@@ -68,17 +62,76 @@
 
 #define INVALID_PHYS_ADDR (~(phys_addr_t)0)
 
-enum swiotlb_force swiotlb_force;
+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;
 
 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;
+};
+
 /*
- * Max segment that we can provide which (if pages are contingous) will
- * not be bounced (unless SWIOTLB_FORCE is set).
+ * 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 unsigned int max_segment;
+static bool round_up_default_nslabs(void)
+{
+	if (!default_nareas)
+		return false;
 
-static unsigned long default_nslabs = IO_TLB_DEFAULT_SIZE >> IO_TLB_SHIFT;
+	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)
@@ -90,10 +143,14 @@ 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 = SWIOTLB_FORCE;
+		swiotlb_force_bounce = true;
 	else if (!strcmp(str, "noforce"))
-		swiotlb_force = SWIOTLB_NO_FORCE;
+		swiotlb_force_disable = true;
 
 	return 0;
 }
@@ -101,18 +158,12 @@ early_param("swiotlb", setup_io_tlb_npages);
 
 unsigned int swiotlb_max_segment(void)
 {
-	return io_tlb_default_mem.nslabs ? max_segment : 0;
+	if (!io_tlb_default_mem.nslabs)
+		return 0;
+	return rounddown(io_tlb_default_mem.nslabs << IO_TLB_SHIFT, PAGE_SIZE);
 }
 EXPORT_SYMBOL_GPL(swiotlb_max_segment);
 
-void swiotlb_set_max_segment(unsigned int val)
-{
-	if (swiotlb_force == SWIOTLB_FORCE)
-		max_segment = 1;
-	else
-		max_segment = rounddown(val, PAGE_SIZE);
-}
-
 unsigned long swiotlb_size_or_default(void)
 {
 	return default_nslabs << IO_TLB_SHIFT;
@@ -127,8 +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);
 }
 
@@ -156,6 +210,34 @@ static inline unsigned long nr_slots(u64 val)
 }
 
 /*
+ * Remap swioltb memory in the unencrypted physical address space
+ * when swiotlb_unencrypted_base is set. (e.g. for Hyper-V AMD SEV-SNP
+ * Isolation VMs).
+ */
+#ifdef CONFIG_HAS_IOMEM
+static void *swiotlb_mem_remap(struct io_tlb_mem *mem, unsigned long bytes)
+{
+	void *vaddr = NULL;
+
+	if (swiotlb_unencrypted_base) {
+		phys_addr_t paddr = mem->start + swiotlb_unencrypted_base;
+
+		vaddr = memremap(paddr, bytes, MEMREMAP_WB);
+		if (!vaddr)
+			pr_err("Failed to map the unencrypted memory %pa size %lx.\n",
+			       &paddr, bytes);
+	}
+
+	return vaddr;
+}
+#else
+static void *swiotlb_mem_remap(struct io_tlb_mem *mem, unsigned long bytes)
+{
+	return NULL;
+}
+#endif
+
+/*
  * Early SWIOTLB allocation may be too early to allow an architecture to
  * perform the desired operations.  This function allows the architecture to
  * call SWIOTLB when the operations are possible.  It needs to be called
@@ -172,11 +254,15 @@ void __init swiotlb_update_mem_attributes(void)
 	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);
+
+	mem->vaddr = swiotlb_mem_remap(mem, bytes);
+	if (!mem->vaddr)
+		mem->vaddr = vaddr;
 }
 
 static void swiotlb_init_io_tlb_mem(struct io_tlb_mem *mem, phys_addr_t start,
-				    unsigned long nslabs, 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;
@@ -184,72 +270,114 @@ 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);
 
-	if (swiotlb_force == SWIOTLB_FORCE)
-		mem->force_bounce = true;
+	for (i = 0; i < mem->nareas; i++) {
+		spin_lock_init(&mem->areas[i].lock);
+		mem->areas[i].index = 0;
+		mem->areas[i].used = 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;
 	}
+
+	/*
+	 * If swiotlb_unencrypted_base is set, the bounce buffer memory will
+	 * be remapped and cleared in swiotlb_update_mem_attributes.
+	 */
+	if (swiotlb_unencrypted_base)
+		return;
+
 	memset(vaddr, 0, bytes);
+	mem->vaddr = vaddr;
+	return;
 }
 
-int __init swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, int verbose)
+/*
+ * Statically reserve bounce buffer space and initialize bounce buffer data
+ * structures for the software IO TLB used to implement the DMA API.
+ */
+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;
 	size_t alloc_size;
+	size_t bytes;
+	void *tlb;
 
-	if (swiotlb_force == SWIOTLB_NO_FORCE)
-		return 0;
+	if (!addressing_limit && !swiotlb_force_bounce)
+		return;
+	if (swiotlb_force_disable)
+		return;
 
-	/* protect against double initialization */
-	if (WARN_ON_ONCE(mem->nslabs))
-		return -ENOMEM;
+	/*
+	 * 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.
+	 */
+retry:
+	bytes = PAGE_ALIGN(nslabs << IO_TLB_SHIFT);
+	if (flags & SWIOTLB_ANY)
+		tlb = memblock_alloc(bytes, PAGE_SIZE);
+	else
+		tlb = memblock_alloc_low(bytes, PAGE_SIZE);
+	if (!tlb) {
+		pr_warn("%s: failed to allocate tlb structure\n", __func__);
+		return;
+	}
+
+	if (remap && remap(tlb, nslabs) < 0) {
+		memblock_free(tlb, PAGE_ALIGN(bytes));
+
+		nslabs = ALIGN(nslabs >> 1, IO_TLB_SEGSIZE);
+		if (nslabs >= IO_TLB_MIN_SLABS)
+			goto retry;
+
+		pr_warn("%s: Failed to remap %zu bytes\n", __func__, bytes);
+		return;
+	}
 
 	alloc_size = PAGE_ALIGN(array_size(sizeof(*mem->slots), nslabs));
 	mem->slots = memblock_alloc(alloc_size, PAGE_SIZE);
-	if (!mem->slots)
-		panic("%s: Failed to allocate %zu bytes align=0x%lx\n",
-		      __func__, alloc_size, PAGE_SIZE);
+	if (!mem->slots) {
+		pr_warn("%s: Failed to allocate %zu bytes align=0x%lx\n",
+			__func__, alloc_size, PAGE_SIZE);
+		return;
+	}
 
-	swiotlb_init_io_tlb_mem(mem, __pa(tlb), nslabs, false);
+	mem->areas = memblock_alloc(array_size(sizeof(struct io_tlb_area),
+		default_nareas), SMP_CACHE_BYTES);
+	if (!mem->areas) {
+		pr_warn("%s: Failed to allocate mem->areas.\n", __func__);
+		return;
+	}
+
+	swiotlb_init_io_tlb_mem(mem, __pa(tlb), nslabs, flags, false,
+				default_nareas);
 
-	if (verbose)
+	if (flags & SWIOTLB_VERBOSE)
 		swiotlb_print_info();
-	swiotlb_set_max_segment(mem->nslabs << IO_TLB_SHIFT);
-	return 0;
 }
 
-/*
- * Statically reserve bounce buffer space and initialize bounce buffer data
- * structures for the software IO TLB used to implement the DMA API.
- */
-void  __init
-swiotlb_init(int verbose)
+void __init swiotlb_init(bool addressing_limit, unsigned int flags)
 {
-	size_t bytes = PAGE_ALIGN(default_nslabs << IO_TLB_SHIFT);
-	void *tlb;
-
-	if (swiotlb_force == SWIOTLB_NO_FORCE)
-		return;
-
-	/* 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(tlb, bytes);
-fail:
-	pr_warn("Cannot allocate buffer");
+	swiotlb_init_remap(addressing_limit, flags, NULL);
 }
 
 /*
@@ -257,73 +385,81 @@ fail:
  * initialize the swiotlb later using the slab allocator if needed.
  * This should be just like above, but with some error catching.
  */
-int
-swiotlb_late_init_with_default_size(size_t default_size)
+int swiotlb_init_late(size_t size, gfp_t gfp_mask,
+		int (*remap)(void *tlb, unsigned long nslabs))
 {
-	unsigned long nslabs =
-		ALIGN(default_size >> IO_TLB_SHIFT, IO_TLB_SEGSIZE);
-	unsigned long bytes;
+	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;
 
-	if (swiotlb_force == SWIOTLB_NO_FORCE)
+	if (swiotlb_force_disable)
 		return 0;
 
-	/*
-	 * Get IO TLB memory from the low pages
-	 */
+retry:
 	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,
+		vstart = (void *)__get_free_pages(gfp_mask | __GFP_NOWARN,
 						  order);
 		if (vstart)
 			break;
 		order--;
+		nslabs = SLABS_PER_PAGE << order;
+		retried = true;
 	}
 
 	if (!vstart)
 		return -ENOMEM;
 
-	if (order != get_order(bytes)) {
+	if (remap)
+		rc = remap(vstart, nslabs);
+	if (rc) {
+		free_pages((unsigned long)vstart, order);
+
+		nslabs = ALIGN(nslabs >> 1, IO_TLB_SEGSIZE);
+		if (nslabs < IO_TLB_MIN_SLABS)
+			return rc;
+		retried = true;
+		goto retry;
+	}
+
+	if (retried) {
 		pr_warn("only able to allocate %ld MB\n",
 			(PAGE_SIZE << order) >> 20);
-		nslabs = SLABS_PER_PAGE << order;
 	}
-	rc = swiotlb_late_init_with_tbl(vstart, nslabs);
-	if (rc)
-		free_pages((unsigned long)vstart, order);
 
-	return rc;
-}
-
-int
-swiotlb_late_init_with_tbl(char *tlb, unsigned long nslabs)
-{
-	struct io_tlb_mem *mem = &io_tlb_default_mem;
-	unsigned long bytes = nslabs << IO_TLB_SHIFT;
+	if (!default_nareas)
+		swiotlb_adjust_nareas(num_possible_cpus());
 
-	if (swiotlb_force == SWIOTLB_NO_FORCE)
-		return 0;
-
-	/* protect against double initialization */
-	if (WARN_ON_ONCE(mem->nslabs))
-		return -ENOMEM;
+	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)
-		return -ENOMEM;
+		goto error_slots;
 
-	set_memory_decrypted((unsigned long)tlb, bytes >> PAGE_SHIFT);
-	swiotlb_init_io_tlb_mem(mem, virt_to_phys(tlb), nslabs, true);
+	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,
+				default_nareas);
 
 	swiotlb_print_info();
-	swiotlb_set_max_segment(mem->nslabs << IO_TLB_SHIFT);
 	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)
@@ -331,6 +467,10 @@ 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;
 
 	if (!mem->nslabs)
 		return;
@@ -342,9 +482,14 @@ 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);
 	}
@@ -371,7 +516,7 @@ static void swiotlb_bounce(struct device *dev, phys_addr_t tlb_addr, size_t size
 	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);
+	unsigned char *vaddr = mem->vaddr + tlb_addr - mem->start;
 	unsigned int tlb_offset, orig_addr_offset;
 
 	if (orig_addr == INVALID_PHYS_ADDR)
@@ -405,9 +550,8 @@ static void swiotlb_bounce(struct device *dev, phys_addr_t tlb_addr, size_t 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;
-		char *buffer;
+		struct page *page;
 		unsigned int sz = 0;
 		unsigned long flags;
 
@@ -415,12 +559,11 @@ static void swiotlb_bounce(struct device *dev, phys_addr_t tlb_addr, size_t size
 			sz = min_t(size_t, PAGE_SIZE - offset, size);
 
 			local_irq_save(flags);
-			buffer = kmap_atomic(pfn_to_page(pfn));
+			page = pfn_to_page(pfn);
 			if (dir == DMA_TO_DEVICE)
-				memcpy(vaddr, buffer + offset, sz);
+				memcpy_from_page(vaddr, page, offset, sz);
 			else
-				memcpy(buffer + offset, vaddr, sz);
-			kunmap_atomic(buffer);
+				memcpy_to_page(page, offset, vaddr, sz);
 			local_irq_restore(flags);
 
 			size -= sz;
@@ -435,7 +578,10 @@ 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.
@@ -447,9 +593,9 @@ 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;
 }
@@ -458,10 +604,12 @@ 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;
@@ -472,8 +620,11 @@ 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
@@ -485,16 +636,20 @@ 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;
 		}
 
@@ -503,26 +658,26 @@ 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;
@@ -530,14 +685,42 @@ 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,
@@ -551,8 +734,11 @@ phys_addr_t swiotlb_tbl_map_single(struct device *dev, phys_addr_t orig_addr,
 	int index;
 	phys_addr_t tlb_addr;
 
-	if (!mem)
-		panic("Can not allocate SWIOTLB buffer earlier and can't now provide you with the DMA bounce buffer");
+	if (!mem || !mem->nslabs) {
+		dev_warn_ratelimited(dev,
+			"Can not allocate SWIOTLB buffer earlier and can't now provide you with the DMA bounce buffer");
+		return (phys_addr_t)DMA_MAPPING_ERROR;
+	}
 
 	if (cc_platform_has(CC_ATTR_MEM_ENCRYPT))
 		pr_warn_once("Memory encryption is active and system is using DMA bounce buffers\n");
@@ -569,7 +755,7 @@ 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;
 	}
 
@@ -581,9 +767,14 @@ phys_addr_t swiotlb_tbl_map_single(struct device *dev, phys_addr_t orig_addr,
 	for (i = 0; i < nr_slots(alloc_size + offset); i++)
 		mem->slots[index + i].orig_addr = slot_addr(orig_addr, i);
 	tlb_addr = slot_addr(mem->start, index) + offset;
-	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC) &&
-	    (dir == DMA_TO_DEVICE || dir == DMA_BIDIRECTIONAL))
-		swiotlb_bounce(dev, tlb_addr, mapping_size, DMA_TO_DEVICE);
+	/*
+	 * 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
+	 * overwrite the entire current content. But we don't. Thus
+	 * unconditional bounce may prevent leaking swiotlb content (i.e.
+	 * kernel memory) to user-space.
+	 */
+	swiotlb_bounce(dev, tlb_addr, mapping_size, DMA_TO_DEVICE);
 	return tlb_addr;
 }
 
@@ -594,6 +785,8 @@ 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;
 
 	/*
@@ -602,7 +795,9 @@ 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
@@ -626,8 +821,8 @@ 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);
 }
 
 /*
@@ -675,8 +870,7 @@ dma_addr_t swiotlb_map(struct device *dev, phys_addr_t paddr, size_t size,
 	phys_addr_t swiotlb_addr;
 	dma_addr_t dma_addr;
 
-	trace_swiotlb_bounced(dev, phys_to_dma(dev, paddr), size,
-			      swiotlb_force);
+	trace_swiotlb_bounced(dev, phys_to_dma(dev, paddr), size);
 
 	swiotlb_addr = swiotlb_tbl_map_single(dev, paddr, size, size, 0, dir,
 			attrs);
@@ -701,7 +895,18 @@ dma_addr_t swiotlb_map(struct device *dev, phys_addr_t paddr, size_t size,
 
 size_t swiotlb_max_mapping_size(struct device *dev)
 {
-	return ((size_t)IO_TLB_SIZE) * IO_TLB_SEGSIZE;
+	int min_align_mask = dma_get_min_align_mask(dev);
+	int min_align = 0;
+
+	/*
+	 * swiotlb_find_slots() skips slots according to
+	 * min align mask. This affects max mapping size.
+	 * Take it into acount here.
+	 */
+	if (min_align_mask)
+		min_align = roundup(min_align_mask, IO_TLB_SIZE);
+
+	return ((size_t)IO_TLB_SIZE) * IO_TLB_SEGSIZE - min_align;
 }
 
 bool is_swiotlb_active(struct device *dev)
@@ -712,47 +917,37 @@ bool is_swiotlb_active(struct device *dev)
 }
 EXPORT_SYMBOL_GPL(is_swiotlb_active);
 
-#ifdef CONFIG_DEBUG_FS
-static struct dentry *debugfs_dir;
+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)
+static void swiotlb_create_debugfs_files(struct io_tlb_mem *mem,
+					 const char *dirname)
 {
+	mem->debugfs = debugfs_create_dir(dirname, io_tlb_default_mem.debugfs);
+	if (!mem->nslabs)
+		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 swiotlb_create_default_debugfs(void)
+static int __init __maybe_unused swiotlb_create_default_debugfs(void)
 {
-	struct io_tlb_mem *mem = &io_tlb_default_mem;
-
-	debugfs_dir = debugfs_create_dir("swiotlb", NULL);
-	if (mem->nslabs) {
-		mem->debugfs = debugfs_dir;
-		swiotlb_create_debugfs_files(mem);
-	}
+	swiotlb_create_debugfs_files(&io_tlb_default_mem, "swiotlb");
 	return 0;
 }
 
+#ifdef CONFIG_DEBUG_FS
 late_initcall(swiotlb_create_default_debugfs);
-
 #endif
 
 #ifdef CONFIG_DMA_RESTRICTED_POOL
 
-#ifdef CONFIG_DEBUG_FS
-static void rmem_swiotlb_debugfs_init(struct reserved_mem *rmem)
-{
-	struct io_tlb_mem *mem = rmem->priv;
-
-	mem->debugfs = debugfs_create_dir(rmem->name, debugfs_dir);
-	swiotlb_create_debugfs_files(mem);
-}
-#else
-static void rmem_swiotlb_debugfs_init(struct reserved_mem *rmem)
-{
-}
-#endif
-
 struct page *swiotlb_alloc(struct device *dev, size_t size)
 {
 	struct io_tlb_mem *mem = dev->dma_io_tlb_mem;
@@ -789,6 +984,9 @@ 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
@@ -799,22 +997,29 @@ static int rmem_swiotlb_device_init(struct reserved_mem *rmem,
 		if (!mem)
 			return -ENOMEM;
 
-		mem->slots = kzalloc(array_size(sizeof(*mem->slots), nslabs),
-				     GFP_KERNEL);
+		mem->slots = kcalloc(nslabs, sizeof(*mem->slots), GFP_KERNEL);
 		if (!mem->slots) {
 			kfree(mem);
 			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, false);
-		mem->force_bounce = true;
+		swiotlb_init_io_tlb_mem(mem, rmem->base, nslabs, SWIOTLB_FORCE,
+					false, nareas);
 		mem->for_alloc = true;
 
 		rmem->priv = mem;
 
-		rmem_swiotlb_debugfs_init(rmem);
+		swiotlb_create_debugfs_files(mem, rmem->name);
 	}
 
 	dev->dma_io_tlb_mem = mem;