Adding upstream version 5.10.209.upstream/5.10.209upstream

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

16 files changed, 5622 insertions, 0 deletions

diff --git a/kernel/dma.c b/kernel/dma.c
new file mode 100644
index 000000000..40f152936
--- /dev/null
+++ b/kernel/dma.c
@@ -0,0 +1,149 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * linux/kernel/dma.c: A DMA channel allocator. Inspired by linux/kernel/irq.c.
+ *
+ * Written by Hennus Bergman, 1992.
+ *
+ * 1994/12/26: Changes by Alex Nash to fix a minor bug in /proc/dma.
+ *   In the previous version the reported device could end up being wrong,
+ *   if a device requested a DMA channel that was already in use.
+ *   [It also happened to remove the sizeof(char *) == sizeof(int)
+ *   assumption introduced because of those /proc/dma patches. -- Hennus]
+ */
+#include <linux/export.h>
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/spinlock.h>
+#include <linux/string.h>
+#include <linux/seq_file.h>
+#include <linux/proc_fs.h>
+#include <linux/init.h>
+#include <asm/dma.h>
+
+
+
+/* A note on resource allocation:
+ *
+ * All drivers needing DMA channels, should allocate and release them
+ * through the public routines `request_dma()' and `free_dma()'.
+ *
+ * In order to avoid problems, all processes should allocate resources in
+ * the same sequence and release them in the reverse order.
+ *
+ * So, when allocating DMAs and IRQs, first allocate the IRQ, then the DMA.
+ * When releasing them, first release the DMA, then release the IRQ.
+ * If you don't, you may cause allocation requests to fail unnecessarily.
+ * This doesn't really matter now, but it will once we get real semaphores
+ * in the kernel.
+ */
+
+
+DEFINE_SPINLOCK(dma_spin_lock);
+
+/*
+ *	If our port doesn't define this it has no PC like DMA
+ */
+
+#ifdef MAX_DMA_CHANNELS
+
+
+/* Channel n is busy iff dma_chan_busy[n].lock != 0.
+ * DMA0 used to be reserved for DRAM refresh, but apparently not any more...
+ * DMA4 is reserved for cascading.
+ */
+
+struct dma_chan {
+	int  lock;
+	const char *device_id;
+};
+
+static struct dma_chan dma_chan_busy[MAX_DMA_CHANNELS] = {
+	[4] = { 1, "cascade" },
+};
+
+
+/**
+ * request_dma - request and reserve a system DMA channel
+ * @dmanr: DMA channel number
+ * @device_id: reserving device ID string, used in /proc/dma
+ */
+int request_dma(unsigned int dmanr, const char * device_id)
+{
+	if (dmanr >= MAX_DMA_CHANNELS)
+		return -EINVAL;
+
+	if (xchg(&dma_chan_busy[dmanr].lock, 1) != 0)
+		return -EBUSY;
+
+	dma_chan_busy[dmanr].device_id = device_id;
+
+	/* old flag was 0, now contains 1 to indicate busy */
+	return 0;
+} /* request_dma */
+
+/**
+ * free_dma - free a reserved system DMA channel
+ * @dmanr: DMA channel number
+ */
+void free_dma(unsigned int dmanr)
+{
+	if (dmanr >= MAX_DMA_CHANNELS) {
+		printk(KERN_WARNING "Trying to free DMA%d\n", dmanr);
+		return;
+	}
+
+	if (xchg(&dma_chan_busy[dmanr].lock, 0) == 0) {
+		printk(KERN_WARNING "Trying to free free DMA%d\n", dmanr);
+		return;
+	}
+
+} /* free_dma */
+
+#else
+
+int request_dma(unsigned int dmanr, const char *device_id)
+{
+	return -EINVAL;
+}
+
+void free_dma(unsigned int dmanr)
+{
+}
+
+#endif
+
+#ifdef CONFIG_PROC_FS
+
+#ifdef MAX_DMA_CHANNELS
+static int proc_dma_show(struct seq_file *m, void *v)
+{
+	int i;
+
+	for (i = 0 ; i < MAX_DMA_CHANNELS ; i++) {
+		if (dma_chan_busy[i].lock) {
+			seq_printf(m, "%2d: %s\n", i,
+				   dma_chan_busy[i].device_id);
+		}
+	}
+	return 0;
+}
+#else
+static int proc_dma_show(struct seq_file *m, void *v)
+{
+	seq_puts(m, "No DMA\n");
+	return 0;
+}
+#endif /* MAX_DMA_CHANNELS */
+
+static int __init proc_dma_init(void)
+{
+	proc_create_single("dma", 0, NULL, proc_dma_show);
+	return 0;
+}
+
+__initcall(proc_dma_init);
+#endif
+
+EXPORT_SYMBOL(request_dma);
+EXPORT_SYMBOL(free_dma);
+EXPORT_SYMBOL(dma_spin_lock);
diff --git a/kernel/dma/Kconfig b/kernel/dma/Kconfig
new file mode 100644
index 000000000..c99de4a21
--- /dev/null
+++ b/kernel/dma/Kconfig
@@ -0,0 +1,227 @@
+# SPDX-License-Identifier: GPL-2.0-only
+
+config NO_DMA
+	bool
+
+config HAS_DMA
+	bool
+	depends on !NO_DMA
+	default y
+
+config DMA_OPS
+	depends on HAS_DMA
+	bool
+
+#
+# IOMMU drivers that can bypass the IOMMU code and optionally use the direct
+# mapping fast path should select this option and set the dma_ops_bypass
+# flag in struct device where applicable
+#
+config DMA_OPS_BYPASS
+	bool
+
+config NEED_SG_DMA_LENGTH
+	bool
+
+config NEED_DMA_MAP_STATE
+	bool
+
+config ARCH_DMA_ADDR_T_64BIT
+	def_bool 64BIT || PHYS_ADDR_T_64BIT
+
+config ARCH_HAS_DMA_COHERENCE_H
+	bool
+
+config ARCH_HAS_DMA_SET_MASK
+	bool
+
+#
+# Select this option if the architecture needs special handling for
+# DMA_ATTR_WRITE_COMBINE.  Normally the "uncached" mapping should be what
+# people thing of when saying write combine, so very few platforms should
+# need to enable this.
+#
+config ARCH_HAS_DMA_WRITE_COMBINE
+	bool
+
+#
+# Select if the architectures provides the arch_dma_mark_clean hook
+#
+config ARCH_HAS_DMA_MARK_CLEAN
+	bool
+
+config DMA_DECLARE_COHERENT
+	bool
+
+config ARCH_HAS_SETUP_DMA_OPS
+	bool
+
+config ARCH_HAS_TEARDOWN_DMA_OPS
+	bool
+
+config ARCH_HAS_SYNC_DMA_FOR_DEVICE
+	bool
+
+config ARCH_HAS_SYNC_DMA_FOR_CPU
+	bool
+	select NEED_DMA_MAP_STATE
+
+config ARCH_HAS_SYNC_DMA_FOR_CPU_ALL
+	bool
+
+config ARCH_HAS_DMA_PREP_COHERENT
+	bool
+
+config ARCH_HAS_FORCE_DMA_UNENCRYPTED
+	bool
+
+config DMA_VIRT_OPS
+	bool
+	depends on HAS_DMA
+	select DMA_OPS
+
+config SWIOTLB
+	bool
+	select NEED_DMA_MAP_STATE
+
+#
+# Should be selected if we can mmap non-coherent mappings to userspace.
+# The only thing that is really required is a way to set an uncached bit
+# in the pagetables
+#
+config DMA_NONCOHERENT_MMAP
+	default y if !MMU
+	bool
+
+config DMA_COHERENT_POOL
+	select GENERIC_ALLOCATOR
+	bool
+
+config DMA_REMAP
+	bool
+	depends on MMU
+	select DMA_NONCOHERENT_MMAP
+
+config DMA_DIRECT_REMAP
+	bool
+	select DMA_REMAP
+	select DMA_COHERENT_POOL
+
+config DMA_CMA
+	bool "DMA Contiguous Memory Allocator"
+	depends on HAVE_DMA_CONTIGUOUS && CMA
+	help
+	  This enables the Contiguous Memory Allocator which allows drivers
+	  to allocate big physically-contiguous blocks of memory for use with
+	  hardware components that do not support I/O map nor scatter-gather.
+
+	  You can disable CMA by specifying "cma=0" on the kernel's command
+	  line.
+
+	  For more information see <kernel/dma/contiguous.c>.
+	  If unsure, say "n".
+
+if  DMA_CMA
+
+config DMA_PERNUMA_CMA
+	bool "Enable separate DMA Contiguous Memory Area for each NUMA Node"
+	default NUMA && ARM64
+	help
+	  Enable this option to get pernuma CMA areas so that devices like
+	  ARM64 SMMU can get local memory by DMA coherent APIs.
+
+	  You can set the size of pernuma CMA by specifying "cma_pernuma=size"
+	  on the kernel's command line.
+
+comment "Default contiguous memory area size:"
+
+config CMA_SIZE_MBYTES
+	int "Size in Mega Bytes"
+	depends on !CMA_SIZE_SEL_PERCENTAGE
+	default 0 if X86
+	default 16
+	help
+	  Defines the size (in MiB) of the default memory area for Contiguous
+	  Memory Allocator.  If the size of 0 is selected, CMA is disabled by
+	  default, but it can be enabled by passing cma=size[MG] to the kernel.
+
+
+config CMA_SIZE_PERCENTAGE
+	int "Percentage of total memory"
+	depends on !CMA_SIZE_SEL_MBYTES
+	default 0 if X86
+	default 10
+	help
+	  Defines the size of the default memory area for Contiguous Memory
+	  Allocator as a percentage of the total memory in the system.
+	  If 0 percent is selected, CMA is disabled by default, but it can be
+	  enabled by passing cma=size[MG] to the kernel.
+
+choice
+	prompt "Selected region size"
+	default CMA_SIZE_SEL_MBYTES
+
+config CMA_SIZE_SEL_MBYTES
+	bool "Use mega bytes value only"
+
+config CMA_SIZE_SEL_PERCENTAGE
+	bool "Use percentage value only"
+
+config CMA_SIZE_SEL_MIN
+	bool "Use lower value (minimum)"
+
+config CMA_SIZE_SEL_MAX
+	bool "Use higher value (maximum)"
+
+endchoice
+
+config CMA_ALIGNMENT
+	int "Maximum PAGE_SIZE order of alignment for contiguous buffers"
+	range 2 12
+	default 8
+	help
+	  DMA mapping framework by default aligns all buffers to the smallest
+	  PAGE_SIZE order which is greater than or equal to the requested buffer
+	  size. This works well for buffers up to a few hundreds kilobytes, but
+	  for larger buffers it just a memory waste. With this parameter you can
+	  specify the maximum PAGE_SIZE order for contiguous buffers. Larger
+	  buffers will be aligned only to this specified order. The order is
+	  expressed as a power of two multiplied by the PAGE_SIZE.
+
+	  For example, if your system defaults to 4KiB pages, the order value
+	  of 8 means that the buffers will be aligned up to 1MiB only.
+
+	  If unsure, leave the default value "8".
+
+endif
+
+config DMA_API_DEBUG
+	bool "Enable debugging of DMA-API usage"
+	select NEED_DMA_MAP_STATE
+	help
+	  Enable this option to debug the use of the DMA API by device drivers.
+	  With this option you will be able to detect common bugs in device
+	  drivers like double-freeing of DMA mappings or freeing mappings that
+	  were never allocated.
+
+	  This option causes a performance degradation.  Use only if you want to
+	  debug device drivers and dma interactions.
+
+	  If unsure, say N.
+
+config DMA_API_DEBUG_SG
+	bool "Debug DMA scatter-gather usage"
+	default y
+	depends on DMA_API_DEBUG
+	help
+	  Perform extra checking that callers of dma_map_sg() have respected the
+	  appropriate segment length/boundary limits for the given device when
+	  preparing DMA scatterlists.
+
+	  This is particularly likely to have been overlooked in cases where the
+	  dma_map_sg() API is used for general bulk mapping of pages rather than
+	  preparing literal scatter-gather descriptors, where there is a risk of
+	  unexpected behaviour from DMA API implementations if the scatterlist
+	  is technically out-of-spec.
+
+	  If unsure, say N.
diff --git a/kernel/dma/Makefile b/kernel/dma/Makefile
new file mode 100644
index 000000000..dc755ab68
--- /dev/null
+++ b/kernel/dma/Makefile
@@ -0,0 +1,12 @@
+# SPDX-License-Identifier: GPL-2.0
+
+obj-$(CONFIG_HAS_DMA)			+= mapping.o direct.o
+obj-$(CONFIG_DMA_OPS)			+= ops_helpers.o
+obj-$(CONFIG_DMA_OPS)			+= dummy.o
+obj-$(CONFIG_DMA_CMA)			+= contiguous.o
+obj-$(CONFIG_DMA_DECLARE_COHERENT)	+= coherent.o
+obj-$(CONFIG_DMA_VIRT_OPS)		+= virt.o
+obj-$(CONFIG_DMA_API_DEBUG)		+= debug.o
+obj-$(CONFIG_SWIOTLB)			+= swiotlb.o
+obj-$(CONFIG_DMA_COHERENT_POOL)		+= pool.o
+obj-$(CONFIG_DMA_REMAP)			+= remap.o
diff --git a/kernel/dma/coherent.c b/kernel/dma/coherent.c
new file mode 100644
index 000000000..49aaad393
--- /dev/null
+++ b/kernel/dma/coherent.c
@@ -0,0 +1,413 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Coherent per-device memory handling.
+ * Borrowed from i386
+ */
+#include <linux/io.h>
+#include <linux/slab.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/dma-direct.h>
+#include <linux/dma-map-ops.h>
+
+struct dma_coherent_mem {
+	void		*virt_base;
+	dma_addr_t	device_base;
+	unsigned long	pfn_base;
+	int		size;
+	unsigned long	*bitmap;
+	spinlock_t	spinlock;
+	bool		use_dev_dma_pfn_offset;
+};
+
+static struct dma_coherent_mem *dma_coherent_default_memory __ro_after_init;
+
+static inline struct dma_coherent_mem *dev_get_coherent_memory(struct device *dev)
+{
+	if (dev && dev->dma_mem)
+		return dev->dma_mem;
+	return NULL;
+}
+
+static inline dma_addr_t dma_get_device_base(struct device *dev,
+					     struct dma_coherent_mem * mem)
+{
+	if (mem->use_dev_dma_pfn_offset)
+		return phys_to_dma(dev, PFN_PHYS(mem->pfn_base));
+	return mem->device_base;
+}
+
+static int dma_init_coherent_memory(phys_addr_t phys_addr,
+		dma_addr_t device_addr, size_t size,
+		struct dma_coherent_mem **mem)
+{
+	struct dma_coherent_mem *dma_mem = NULL;
+	void *mem_base = NULL;
+	int pages = size >> PAGE_SHIFT;
+	int bitmap_size = BITS_TO_LONGS(pages) * sizeof(long);
+	int ret;
+
+	if (!size) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	mem_base = memremap(phys_addr, size, MEMREMAP_WC);
+	if (!mem_base) {
+		ret = -EINVAL;
+		goto out;
+	}
+	dma_mem = kzalloc(sizeof(struct dma_coherent_mem), GFP_KERNEL);
+	if (!dma_mem) {
+		ret = -ENOMEM;
+		goto out;
+	}
+	dma_mem->bitmap = kzalloc(bitmap_size, GFP_KERNEL);
+	if (!dma_mem->bitmap) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	dma_mem->virt_base = mem_base;
+	dma_mem->device_base = device_addr;
+	dma_mem->pfn_base = PFN_DOWN(phys_addr);
+	dma_mem->size = pages;
+	spin_lock_init(&dma_mem->spinlock);
+
+	*mem = dma_mem;
+	return 0;
+
+out:
+	kfree(dma_mem);
+	if (mem_base)
+		memunmap(mem_base);
+	return ret;
+}
+
+static void _dma_release_coherent_memory(struct dma_coherent_mem *mem)
+{
+	if (!mem)
+		return;
+
+	memunmap(mem->virt_base);
+	kfree(mem->bitmap);
+	kfree(mem);
+}
+
+static int dma_assign_coherent_memory(struct device *dev,
+				      struct dma_coherent_mem *mem)
+{
+	if (!dev)
+		return -ENODEV;
+
+	if (dev->dma_mem)
+		return -EBUSY;
+
+	dev->dma_mem = mem;
+	return 0;
+}
+
+/*
+ * Declare a region of memory to be handed out by dma_alloc_coherent() when it
+ * is asked for coherent memory for this device.  This shall only be used
+ * from platform code, usually based on the device tree description.
+ * 
+ * phys_addr is the CPU physical address to which the memory is currently
+ * assigned (this will be ioremapped so the CPU can access the region).
+ *
+ * device_addr is the DMA address the device needs to be programmed with to
+ * actually address this memory (this will be handed out as the dma_addr_t in
+ * dma_alloc_coherent()).
+ *
+ * size is the size of the area (must be a multiple of PAGE_SIZE).
+ *
+ * As a simplification for the platforms, only *one* such region of memory may
+ * be declared per device.
+ */
+int dma_declare_coherent_memory(struct device *dev, phys_addr_t phys_addr,
+				dma_addr_t device_addr, size_t size)
+{
+	struct dma_coherent_mem *mem;
+	int ret;
+
+	ret = dma_init_coherent_memory(phys_addr, device_addr, size, &mem);
+	if (ret)
+		return ret;
+
+	ret = dma_assign_coherent_memory(dev, mem);
+	if (ret)
+		_dma_release_coherent_memory(mem);
+	return ret;
+}
+
+void dma_release_coherent_memory(struct device *dev)
+{
+	if (dev) {
+		_dma_release_coherent_memory(dev->dma_mem);
+		dev->dma_mem = NULL;
+	}
+}
+
+static void *__dma_alloc_from_coherent(struct device *dev,
+				       struct dma_coherent_mem *mem,
+				       ssize_t size, dma_addr_t *dma_handle)
+{
+	int order = get_order(size);
+	unsigned long flags;
+	int pageno;
+	void *ret;
+
+	spin_lock_irqsave(&mem->spinlock, flags);
+
+	if (unlikely(size > ((dma_addr_t)mem->size << PAGE_SHIFT)))
+		goto err;
+
+	pageno = bitmap_find_free_region(mem->bitmap, mem->size, order);
+	if (unlikely(pageno < 0))
+		goto err;
+
+	/*
+	 * Memory was found in the coherent area.
+	 */
+	*dma_handle = dma_get_device_base(dev, mem) +
+			((dma_addr_t)pageno << PAGE_SHIFT);
+	ret = mem->virt_base + ((dma_addr_t)pageno << PAGE_SHIFT);
+	spin_unlock_irqrestore(&mem->spinlock, flags);
+	memset(ret, 0, size);
+	return ret;
+err:
+	spin_unlock_irqrestore(&mem->spinlock, flags);
+	return NULL;
+}
+
+/**
+ * dma_alloc_from_dev_coherent() - allocate memory from device coherent pool
+ * @dev:	device from which we allocate memory
+ * @size:	size of requested memory area
+ * @dma_handle:	This will be filled with the correct dma handle
+ * @ret:	This pointer will be filled with the virtual address
+ *		to allocated area.
+ *
+ * This function should be only called from per-arch dma_alloc_coherent()
+ * to support allocation from per-device coherent memory pools.
+ *
+ * Returns 0 if dma_alloc_coherent should continue with allocating from
+ * generic memory areas, or !0 if dma_alloc_coherent should return @ret.
+ */
+int dma_alloc_from_dev_coherent(struct device *dev, ssize_t size,
+		dma_addr_t *dma_handle, void **ret)
+{
+	struct dma_coherent_mem *mem = dev_get_coherent_memory(dev);
+
+	if (!mem)
+		return 0;
+
+	*ret = __dma_alloc_from_coherent(dev, mem, size, dma_handle);
+	return 1;
+}
+
+void *dma_alloc_from_global_coherent(struct device *dev, ssize_t size,
+				     dma_addr_t *dma_handle)
+{
+	if (!dma_coherent_default_memory)
+		return NULL;
+
+	return __dma_alloc_from_coherent(dev, dma_coherent_default_memory, size,
+					 dma_handle);
+}
+
+static int __dma_release_from_coherent(struct dma_coherent_mem *mem,
+				       int order, void *vaddr)
+{
+	if (mem && vaddr >= mem->virt_base && vaddr <
+		   (mem->virt_base + ((dma_addr_t)mem->size << PAGE_SHIFT))) {
+		int page = (vaddr - mem->virt_base) >> PAGE_SHIFT;
+		unsigned long flags;
+
+		spin_lock_irqsave(&mem->spinlock, flags);
+		bitmap_release_region(mem->bitmap, page, order);
+		spin_unlock_irqrestore(&mem->spinlock, flags);
+		return 1;
+	}
+	return 0;
+}
+
+/**
+ * dma_release_from_dev_coherent() - free memory to device coherent memory pool
+ * @dev:	device from which the memory was allocated
+ * @order:	the order of pages allocated
+ * @vaddr:	virtual address of allocated pages
+ *
+ * This checks whether the memory was allocated from the per-device
+ * coherent memory pool and if so, releases that memory.
+ *
+ * Returns 1 if we correctly released the memory, or 0 if the caller should
+ * proceed with releasing memory from generic pools.
+ */
+int dma_release_from_dev_coherent(struct device *dev, int order, void *vaddr)
+{
+	struct dma_coherent_mem *mem = dev_get_coherent_memory(dev);
+
+	return __dma_release_from_coherent(mem, order, vaddr);
+}
+
+int dma_release_from_global_coherent(int order, void *vaddr)
+{
+	if (!dma_coherent_default_memory)
+		return 0;
+
+	return __dma_release_from_coherent(dma_coherent_default_memory, order,
+			vaddr);
+}
+
+static int __dma_mmap_from_coherent(struct dma_coherent_mem *mem,
+		struct vm_area_struct *vma, void *vaddr, size_t size, int *ret)
+{
+	if (mem && vaddr >= mem->virt_base && vaddr + size <=
+		   (mem->virt_base + ((dma_addr_t)mem->size << PAGE_SHIFT))) {
+		unsigned long off = vma->vm_pgoff;
+		int start = (vaddr - mem->virt_base) >> PAGE_SHIFT;
+		unsigned long user_count = vma_pages(vma);
+		int count = PAGE_ALIGN(size) >> PAGE_SHIFT;
+
+		*ret = -ENXIO;
+		if (off < count && user_count <= count - off) {
+			unsigned long pfn = mem->pfn_base + start + off;
+			*ret = remap_pfn_range(vma, vma->vm_start, pfn,
+					       user_count << PAGE_SHIFT,
+					       vma->vm_page_prot);
+		}
+		return 1;
+	}
+	return 0;
+}
+
+/**
+ * dma_mmap_from_dev_coherent() - mmap memory from the device coherent pool
+ * @dev:	device from which the memory was allocated
+ * @vma:	vm_area for the userspace memory
+ * @vaddr:	cpu address returned by dma_alloc_from_dev_coherent
+ * @size:	size of the memory buffer allocated
+ * @ret:	result from remap_pfn_range()
+ *
+ * This checks whether the memory was allocated from the per-device
+ * coherent memory pool and if so, maps that memory to the provided vma.
+ *
+ * Returns 1 if @vaddr belongs to the device coherent pool and the caller
+ * should return @ret, or 0 if they should proceed with mapping memory from
+ * generic areas.
+ */
+int dma_mmap_from_dev_coherent(struct device *dev, struct vm_area_struct *vma,
+			   void *vaddr, size_t size, int *ret)
+{
+	struct dma_coherent_mem *mem = dev_get_coherent_memory(dev);
+
+	return __dma_mmap_from_coherent(mem, vma, vaddr, size, ret);
+}
+
+int dma_mmap_from_global_coherent(struct vm_area_struct *vma, void *vaddr,
+				   size_t size, int *ret)
+{
+	if (!dma_coherent_default_memory)
+		return 0;
+
+	return __dma_mmap_from_coherent(dma_coherent_default_memory, vma,
+					vaddr, size, ret);
+}
+
+/*
+ * Support for reserved memory regions defined in device tree
+ */
+#ifdef CONFIG_OF_RESERVED_MEM
+#include <linux/of.h>
+#include <linux/of_fdt.h>
+#include <linux/of_reserved_mem.h>
+
+static struct reserved_mem *dma_reserved_default_memory __initdata;
+
+static int rmem_dma_device_init(struct reserved_mem *rmem, struct device *dev)
+{
+	struct dma_coherent_mem *mem = rmem->priv;
+	int ret;
+
+	if (!mem) {
+		ret = dma_init_coherent_memory(rmem->base, rmem->base,
+					       rmem->size, &mem);
+		if (ret) {
+			pr_err("Reserved memory: failed to init DMA memory pool at %pa, size %ld MiB\n",
+				&rmem->base, (unsigned long)rmem->size / SZ_1M);
+			return ret;
+		}
+	}
+	mem->use_dev_dma_pfn_offset = true;
+	rmem->priv = mem;
+	dma_assign_coherent_memory(dev, mem);
+	return 0;
+}
+
+static void rmem_dma_device_release(struct reserved_mem *rmem,
+				    struct device *dev)
+{
+	if (dev)
+		dev->dma_mem = NULL;
+}
+
+static const struct reserved_mem_ops rmem_dma_ops = {
+	.device_init	= rmem_dma_device_init,
+	.device_release	= rmem_dma_device_release,
+};
+
+static int __init rmem_dma_setup(struct reserved_mem *rmem)
+{
+	unsigned long node = rmem->fdt_node;
+
+	if (of_get_flat_dt_prop(node, "reusable", NULL))
+		return -EINVAL;
+
+#ifdef CONFIG_ARM
+	if (!of_get_flat_dt_prop(node, "no-map", NULL)) {
+		pr_err("Reserved memory: regions without no-map are not yet supported\n");
+		return -EINVAL;
+	}
+
+	if (of_get_flat_dt_prop(node, "linux,dma-default", NULL)) {
+		WARN(dma_reserved_default_memory,
+		     "Reserved memory: region for default DMA coherent area is redefined\n");
+		dma_reserved_default_memory = rmem;
+	}
+#endif
+
+	rmem->ops = &rmem_dma_ops;
+	pr_info("Reserved memory: created DMA memory pool at %pa, size %ld MiB\n",
+		&rmem->base, (unsigned long)rmem->size / SZ_1M);
+	return 0;
+}
+
+static int __init dma_init_reserved_memory(void)
+{
+	const struct reserved_mem_ops *ops;
+	int ret;
+
+	if (!dma_reserved_default_memory)
+		return -ENOMEM;
+
+	ops = dma_reserved_default_memory->ops;
+
+	/*
+	 * We rely on rmem_dma_device_init() does not propagate error of
+	 * dma_assign_coherent_memory() for "NULL" device.
+	 */
+	ret = ops->device_init(dma_reserved_default_memory, NULL);
+
+	if (!ret) {
+		dma_coherent_default_memory = dma_reserved_default_memory->priv;
+		pr_info("DMA: default coherent area is set\n");
+	}
+
+	return ret;
+}
+
+core_initcall(dma_init_reserved_memory);
+
+RESERVEDMEM_OF_DECLARE(dma, "shared-dma-pool", rmem_dma_setup);
+#endif
diff --git a/kernel/dma/contiguous.c b/kernel/dma/contiguous.c
new file mode 100644
index 000000000..16b95ff12
--- /dev/null
+++ b/kernel/dma/contiguous.c
@@ -0,0 +1,444 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * Contiguous Memory Allocator for DMA mapping framework
+ * Copyright (c) 2010-2011 by Samsung Electronics.
+ * Written by:
+ *	Marek Szyprowski <m.szyprowski@samsung.com>
+ *	Michal Nazarewicz <mina86@mina86.com>
+ *
+ * Contiguous Memory Allocator
+ *
+ *   The Contiguous Memory Allocator (CMA) makes it possible to
+ *   allocate big contiguous chunks of memory after the system has
+ *   booted.
+ *
+ * Why is it needed?
+ *
+ *   Various devices on embedded systems have no scatter-getter and/or
+ *   IO map support and require contiguous blocks of memory to
+ *   operate.  They include devices such as cameras, hardware video
+ *   coders, etc.
+ *
+ *   Such devices often require big memory buffers (a full HD frame
+ *   is, for instance, more then 2 mega pixels large, i.e. more than 6
+ *   MB of memory), which makes mechanisms such as kmalloc() or
+ *   alloc_page() ineffective.
+ *
+ *   At the same time, a solution where a big memory region is
+ *   reserved for a device is suboptimal since often more memory is
+ *   reserved then strictly required and, moreover, the memory is
+ *   inaccessible to page system even if device drivers don't use it.
+ *
+ *   CMA tries to solve this issue by operating on memory regions
+ *   where only movable pages can be allocated from.  This way, kernel
+ *   can use the memory for pagecache and when device driver requests
+ *   it, allocated pages can be migrated.
+ */
+
+#define pr_fmt(fmt) "cma: " fmt
+
+#ifdef CONFIG_CMA_DEBUG
+#ifndef DEBUG
+#  define DEBUG
+#endif
+#endif
+
+#include <asm/page.h>
+
+#include <linux/memblock.h>
+#include <linux/err.h>
+#include <linux/sizes.h>
+#include <linux/dma-map-ops.h>
+#include <linux/cma.h>
+
+#ifdef CONFIG_CMA_SIZE_MBYTES
+#define CMA_SIZE_MBYTES CONFIG_CMA_SIZE_MBYTES
+#else
+#define CMA_SIZE_MBYTES 0
+#endif
+
+struct cma *dma_contiguous_default_area;
+
+/*
+ * Default global CMA area size can be defined in kernel's .config.
+ * This is useful mainly for distro maintainers to create a kernel
+ * that works correctly for most supported systems.
+ * The size can be set in bytes or as a percentage of the total memory
+ * in the system.
+ *
+ * Users, who want to set the size of global CMA area for their system
+ * should use cma= kernel parameter.
+ */
+static const phys_addr_t size_bytes __initconst =
+	(phys_addr_t)CMA_SIZE_MBYTES * SZ_1M;
+static phys_addr_t  size_cmdline __initdata = -1;
+static phys_addr_t base_cmdline __initdata;
+static phys_addr_t limit_cmdline __initdata;
+
+static int __init early_cma(char *p)
+{
+	if (!p) {
+		pr_err("Config string not provided\n");
+		return -EINVAL;
+	}
+
+	size_cmdline = memparse(p, &p);
+	if (*p != '@')
+		return 0;
+	base_cmdline = memparse(p + 1, &p);
+	if (*p != '-') {
+		limit_cmdline = base_cmdline + size_cmdline;
+		return 0;
+	}
+	limit_cmdline = memparse(p + 1, &p);
+
+	return 0;
+}
+early_param("cma", early_cma);
+
+#ifdef CONFIG_DMA_PERNUMA_CMA
+
+static struct cma *dma_contiguous_pernuma_area[MAX_NUMNODES];
+static phys_addr_t pernuma_size_bytes __initdata;
+
+static int __init early_cma_pernuma(char *p)
+{
+	pernuma_size_bytes = memparse(p, &p);
+	return 0;
+}
+early_param("cma_pernuma", early_cma_pernuma);
+#endif
+
+#ifdef CONFIG_CMA_SIZE_PERCENTAGE
+
+static phys_addr_t __init __maybe_unused cma_early_percent_memory(void)
+{
+	unsigned long total_pages = PHYS_PFN(memblock_phys_mem_size());
+
+	return (total_pages * CONFIG_CMA_SIZE_PERCENTAGE / 100) << PAGE_SHIFT;
+}
+
+#else
+
+static inline __maybe_unused phys_addr_t cma_early_percent_memory(void)
+{
+	return 0;
+}
+
+#endif
+
+#ifdef CONFIG_DMA_PERNUMA_CMA
+void __init dma_pernuma_cma_reserve(void)
+{
+	int nid;
+
+	if (!pernuma_size_bytes)
+		return;
+
+	for_each_online_node(nid) {
+		int ret;
+		char name[CMA_MAX_NAME];
+		struct cma **cma = &dma_contiguous_pernuma_area[nid];
+
+		snprintf(name, sizeof(name), "pernuma%d", nid);
+		ret = cma_declare_contiguous_nid(0, pernuma_size_bytes, 0, 0,
+						 0, false, name, cma, nid);
+		if (ret) {
+			pr_warn("%s: reservation failed: err %d, node %d", __func__,
+				ret, nid);
+			continue;
+		}
+
+		pr_debug("%s: reserved %llu MiB on node %d\n", __func__,
+			(unsigned long long)pernuma_size_bytes / SZ_1M, nid);
+	}
+}
+#endif
+
+/**
+ * dma_contiguous_reserve() - reserve area(s) for contiguous memory handling
+ * @limit: End address of the reserved memory (optional, 0 for any).
+ *
+ * This function reserves memory from early allocator. It should be
+ * called by arch specific code once the early allocator (memblock or bootmem)
+ * has been activated and all other subsystems have already allocated/reserved
+ * memory.
+ */
+void __init dma_contiguous_reserve(phys_addr_t limit)
+{
+	phys_addr_t selected_size = 0;
+	phys_addr_t selected_base = 0;
+	phys_addr_t selected_limit = limit;
+	bool fixed = false;
+
+	pr_debug("%s(limit %08lx)\n", __func__, (unsigned long)limit);
+
+	if (size_cmdline != -1) {
+		selected_size = size_cmdline;
+		selected_base = base_cmdline;
+		selected_limit = min_not_zero(limit_cmdline, limit);
+		if (base_cmdline + size_cmdline == limit_cmdline)
+			fixed = true;
+	} else {
+#ifdef CONFIG_CMA_SIZE_SEL_MBYTES
+		selected_size = size_bytes;
+#elif defined(CONFIG_CMA_SIZE_SEL_PERCENTAGE)
+		selected_size = cma_early_percent_memory();
+#elif defined(CONFIG_CMA_SIZE_SEL_MIN)
+		selected_size = min(size_bytes, cma_early_percent_memory());
+#elif defined(CONFIG_CMA_SIZE_SEL_MAX)
+		selected_size = max(size_bytes, cma_early_percent_memory());
+#endif
+	}
+
+	if (selected_size && !dma_contiguous_default_area) {
+		pr_debug("%s: reserving %ld MiB for global area\n", __func__,
+			 (unsigned long)selected_size / SZ_1M);
+
+		dma_contiguous_reserve_area(selected_size, selected_base,
+					    selected_limit,
+					    &dma_contiguous_default_area,
+					    fixed);
+	}
+}
+
+void __weak
+dma_contiguous_early_fixup(phys_addr_t base, unsigned long size)
+{
+}
+
+/**
+ * dma_contiguous_reserve_area() - reserve custom contiguous area
+ * @size: Size of the reserved area (in bytes),
+ * @base: Base address of the reserved area optional, use 0 for any
+ * @limit: End address of the reserved memory (optional, 0 for any).
+ * @res_cma: Pointer to store the created cma region.
+ * @fixed: hint about where to place the reserved area
+ *
+ * This function reserves memory from early allocator. It should be
+ * called by arch specific code once the early allocator (memblock or bootmem)
+ * has been activated and all other subsystems have already allocated/reserved
+ * memory. This function allows to create custom reserved areas for specific
+ * devices.
+ *
+ * If @fixed is true, reserve contiguous area at exactly @base.  If false,
+ * reserve in range from @base to @limit.
+ */
+int __init dma_contiguous_reserve_area(phys_addr_t size, phys_addr_t base,
+				       phys_addr_t limit, struct cma **res_cma,
+				       bool fixed)
+{
+	int ret;
+
+	ret = cma_declare_contiguous(base, size, limit, 0, 0, fixed,
+					"reserved", res_cma);
+	if (ret)
+		return ret;
+
+	/* Architecture specific contiguous memory fixup. */
+	dma_contiguous_early_fixup(cma_get_base(*res_cma),
+				cma_get_size(*res_cma));
+
+	return 0;
+}
+
+/**
+ * dma_alloc_from_contiguous() - allocate pages from contiguous area
+ * @dev:   Pointer to device for which the allocation is performed.
+ * @count: Requested number of pages.
+ * @align: Requested alignment of pages (in PAGE_SIZE order).
+ * @no_warn: Avoid printing message about failed allocation.
+ *
+ * This function allocates memory buffer for specified device. It uses
+ * device specific contiguous memory area if available or the default
+ * global one. Requires architecture specific dev_get_cma_area() helper
+ * function.
+ */
+struct page *dma_alloc_from_contiguous(struct device *dev, size_t count,
+				       unsigned int align, bool no_warn)
+{
+	if (align > CONFIG_CMA_ALIGNMENT)
+		align = CONFIG_CMA_ALIGNMENT;
+
+	return cma_alloc(dev_get_cma_area(dev), count, align, no_warn);
+}
+
+/**
+ * dma_release_from_contiguous() - release allocated pages
+ * @dev:   Pointer to device for which the pages were allocated.
+ * @pages: Allocated pages.
+ * @count: Number of allocated pages.
+ *
+ * This function releases memory allocated by dma_alloc_from_contiguous().
+ * It returns false when provided pages do not belong to contiguous area and
+ * true otherwise.
+ */
+bool dma_release_from_contiguous(struct device *dev, struct page *pages,
+				 int count)
+{
+	return cma_release(dev_get_cma_area(dev), pages, count);
+}
+
+static struct page *cma_alloc_aligned(struct cma *cma, size_t size, gfp_t gfp)
+{
+	unsigned int align = min(get_order(size), CONFIG_CMA_ALIGNMENT);
+
+	return cma_alloc(cma, size >> PAGE_SHIFT, align, gfp & __GFP_NOWARN);
+}
+
+/**
+ * dma_alloc_contiguous() - allocate contiguous pages
+ * @dev:   Pointer to device for which the allocation is performed.
+ * @size:  Requested allocation size.
+ * @gfp:   Allocation flags.
+ *
+ * tries to use device specific contiguous memory area if available, or it
+ * tries to use per-numa cma, if the allocation fails, it will fallback to
+ * try default global one.
+ *
+ * Note that it bypass one-page size of allocations from the per-numa and
+ * global area as the addresses within one page are always contiguous, so
+ * there is no need to waste CMA pages for that kind; it also helps reduce
+ * fragmentations.
+ */
+struct page *dma_alloc_contiguous(struct device *dev, size_t size, gfp_t gfp)
+{
+#ifdef CONFIG_DMA_PERNUMA_CMA
+	int nid = dev_to_node(dev);
+#endif
+
+	/* CMA can be used only in the context which permits sleeping */
+	if (!gfpflags_allow_blocking(gfp))
+		return NULL;
+	if (dev->cma_area)
+		return cma_alloc_aligned(dev->cma_area, size, gfp);
+	if (size <= PAGE_SIZE)
+		return NULL;
+
+#ifdef CONFIG_DMA_PERNUMA_CMA
+	if (nid != NUMA_NO_NODE && !(gfp & (GFP_DMA | GFP_DMA32))) {
+		struct cma *cma = dma_contiguous_pernuma_area[nid];
+		struct page *page;
+
+		if (cma) {
+			page = cma_alloc_aligned(cma, size, gfp);
+			if (page)
+				return page;
+		}
+	}
+#endif
+	if (!dma_contiguous_default_area)
+		return NULL;
+
+	return cma_alloc_aligned(dma_contiguous_default_area, size, gfp);
+}
+
+/**
+ * dma_free_contiguous() - release allocated pages
+ * @dev:   Pointer to device for which the pages were allocated.
+ * @page:  Pointer to the allocated pages.
+ * @size:  Size of allocated pages.
+ *
+ * This function releases memory allocated by dma_alloc_contiguous(). As the
+ * cma_release returns false when provided pages do not belong to contiguous
+ * area and true otherwise, this function then does a fallback __free_pages()
+ * upon a false-return.
+ */
+void dma_free_contiguous(struct device *dev, struct page *page, size_t size)
+{
+	unsigned int count = PAGE_ALIGN(size) >> PAGE_SHIFT;
+
+	/* if dev has its own cma, free page from there */
+	if (dev->cma_area) {
+		if (cma_release(dev->cma_area, page, count))
+			return;
+	} else {
+		/*
+		 * otherwise, page is from either per-numa cma or default cma
+		 */
+#ifdef CONFIG_DMA_PERNUMA_CMA
+		if (cma_release(dma_contiguous_pernuma_area[page_to_nid(page)],
+					page, count))
+			return;
+#endif
+		if (cma_release(dma_contiguous_default_area, page, count))
+			return;
+	}
+
+	/* not in any cma, free from buddy */
+	__free_pages(page, get_order(size));
+}
+
+/*
+ * Support for reserved memory regions defined in device tree
+ */
+#ifdef CONFIG_OF_RESERVED_MEM
+#include <linux/of.h>
+#include <linux/of_fdt.h>
+#include <linux/of_reserved_mem.h>
+
+#undef pr_fmt
+#define pr_fmt(fmt) fmt
+
+static int rmem_cma_device_init(struct reserved_mem *rmem, struct device *dev)
+{
+	dev->cma_area = rmem->priv;
+	return 0;
+}
+
+static void rmem_cma_device_release(struct reserved_mem *rmem,
+				    struct device *dev)
+{
+	dev->cma_area = NULL;
+}
+
+static const struct reserved_mem_ops rmem_cma_ops = {
+	.device_init	= rmem_cma_device_init,
+	.device_release = rmem_cma_device_release,
+};
+
+static int __init rmem_cma_setup(struct reserved_mem *rmem)
+{
+	phys_addr_t align = PAGE_SIZE << max(MAX_ORDER - 1, pageblock_order);
+	phys_addr_t mask = align - 1;
+	unsigned long node = rmem->fdt_node;
+	bool default_cma = of_get_flat_dt_prop(node, "linux,cma-default", NULL);
+	struct cma *cma;
+	int err;
+
+	if (size_cmdline != -1 && default_cma) {
+		pr_info("Reserved memory: bypass %s node, using cmdline CMA params instead\n",
+			rmem->name);
+		return -EBUSY;
+	}
+
+	if (!of_get_flat_dt_prop(node, "reusable", NULL) ||
+	    of_get_flat_dt_prop(node, "no-map", NULL))
+		return -EINVAL;
+
+	if ((rmem->base & mask) || (rmem->size & mask)) {
+		pr_err("Reserved memory: incorrect alignment of CMA region\n");
+		return -EINVAL;
+	}
+
+	err = cma_init_reserved_mem(rmem->base, rmem->size, 0, rmem->name, &cma);
+	if (err) {
+		pr_err("Reserved memory: unable to setup CMA region\n");
+		return err;
+	}
+	/* Architecture specific contiguous memory fixup. */
+	dma_contiguous_early_fixup(rmem->base, rmem->size);
+
+	if (default_cma)
+		dma_contiguous_default_area = cma;
+
+	rmem->ops = &rmem_cma_ops;
+	rmem->priv = cma;
+
+	pr_info("Reserved memory: created CMA memory pool at %pa, size %ld MiB\n",
+		&rmem->base, (unsigned long)rmem->size / SZ_1M);
+
+	return 0;
+}
+RESERVEDMEM_OF_DECLARE(cma, "shared-dma-pool", rmem_cma_setup);
+#endif
diff --git a/kernel/dma/debug.c b/kernel/dma/debug.c
new file mode 100644
index 000000000..026398308
--- /dev/null
+++ b/kernel/dma/debug.c
@@ -0,0 +1,1610 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2008 Advanced Micro Devices, Inc.
+ *
+ * Author: Joerg Roedel <joerg.roedel@amd.com>
+ */
+
+#define pr_fmt(fmt)	"DMA-API: " fmt
+
+#include <linux/sched/task_stack.h>
+#include <linux/scatterlist.h>
+#include <linux/dma-map-ops.h>
+#include <linux/sched/task.h>
+#include <linux/stacktrace.h>
+#include <linux/spinlock.h>
+#include <linux/vmalloc.h>
+#include <linux/debugfs.h>
+#include <linux/uaccess.h>
+#include <linux/export.h>
+#include <linux/device.h>
+#include <linux/types.h>
+#include <linux/sched.h>
+#include <linux/ctype.h>
+#include <linux/list.h>
+#include <linux/slab.h>
+#include <asm/sections.h>
+#include "debug.h"
+
+#define HASH_SIZE       16384ULL
+#define HASH_FN_SHIFT   13
+#define HASH_FN_MASK    (HASH_SIZE - 1)
+
+#define PREALLOC_DMA_DEBUG_ENTRIES (1 << 16)
+/* If the pool runs out, add this many new entries at once */
+#define DMA_DEBUG_DYNAMIC_ENTRIES (PAGE_SIZE / sizeof(struct dma_debug_entry))
+
+enum {
+	dma_debug_single,
+	dma_debug_sg,
+	dma_debug_coherent,
+	dma_debug_resource,
+};
+
+enum map_err_types {
+	MAP_ERR_CHECK_NOT_APPLICABLE,
+	MAP_ERR_NOT_CHECKED,
+	MAP_ERR_CHECKED,
+};
+
+#define DMA_DEBUG_STACKTRACE_ENTRIES 5
+
+/**
+ * struct dma_debug_entry - track a dma_map* or dma_alloc_coherent mapping
+ * @list: node on pre-allocated free_entries list
+ * @dev: 'dev' argument to dma_map_{page|single|sg} or dma_alloc_coherent
+ * @size: length of the mapping
+ * @type: single, page, sg, coherent
+ * @direction: enum dma_data_direction
+ * @sg_call_ents: 'nents' from dma_map_sg
+ * @sg_mapped_ents: 'mapped_ents' from dma_map_sg
+ * @pfn: page frame of the start address
+ * @offset: offset of mapping relative to pfn
+ * @map_err_type: track whether dma_mapping_error() was checked
+ * @stacktrace: support backtraces when a violation is detected
+ */
+struct dma_debug_entry {
+	struct list_head list;
+	struct device    *dev;
+	u64              dev_addr;
+	u64              size;
+	int              type;
+	int              direction;
+	int		 sg_call_ents;
+	int		 sg_mapped_ents;
+	unsigned long	 pfn;
+	size_t		 offset;
+	enum map_err_types  map_err_type;
+#ifdef CONFIG_STACKTRACE
+	unsigned int	stack_len;
+	unsigned long	stack_entries[DMA_DEBUG_STACKTRACE_ENTRIES];
+#endif
+} ____cacheline_aligned_in_smp;
+
+typedef bool (*match_fn)(struct dma_debug_entry *, struct dma_debug_entry *);
+
+struct hash_bucket {
+	struct list_head list;
+	spinlock_t lock;
+};
+
+/* Hash list to save the allocated dma addresses */
+static struct hash_bucket dma_entry_hash[HASH_SIZE];
+/* List of pre-allocated dma_debug_entry's */
+static LIST_HEAD(free_entries);
+/* Lock for the list above */
+static DEFINE_SPINLOCK(free_entries_lock);
+
+/* Global disable flag - will be set in case of an error */
+static bool global_disable __read_mostly;
+
+/* Early initialization disable flag, set at the end of dma_debug_init */
+static bool dma_debug_initialized __read_mostly;
+
+static inline bool dma_debug_disabled(void)
+{
+	return global_disable || !dma_debug_initialized;
+}
+
+/* Global error count */
+static u32 error_count;
+
+/* Global error show enable*/
+static u32 show_all_errors __read_mostly;
+/* Number of errors to show */
+static u32 show_num_errors = 1;
+
+static u32 num_free_entries;
+static u32 min_free_entries;
+static u32 nr_total_entries;
+
+/* number of preallocated entries requested by kernel cmdline */
+static u32 nr_prealloc_entries = PREALLOC_DMA_DEBUG_ENTRIES;
+
+/* per-driver filter related state */
+
+#define NAME_MAX_LEN	64
+
+static char                  current_driver_name[NAME_MAX_LEN] __read_mostly;
+static struct device_driver *current_driver                    __read_mostly;
+
+static DEFINE_RWLOCK(driver_name_lock);
+
+static const char *const maperr2str[] = {
+	[MAP_ERR_CHECK_NOT_APPLICABLE] = "dma map error check not applicable",
+	[MAP_ERR_NOT_CHECKED] = "dma map error not checked",
+	[MAP_ERR_CHECKED] = "dma map error checked",
+};
+
+static const char *type2name[] = {
+	[dma_debug_single] = "single",
+	[dma_debug_sg] = "scather-gather",
+	[dma_debug_coherent] = "coherent",
+	[dma_debug_resource] = "resource",
+};
+
+static const char *dir2name[] = {
+	[DMA_BIDIRECTIONAL]	= "DMA_BIDIRECTIONAL",
+	[DMA_TO_DEVICE]		= "DMA_TO_DEVICE",
+	[DMA_FROM_DEVICE]	= "DMA_FROM_DEVICE",
+	[DMA_NONE]		= "DMA_NONE",
+};
+
+/*
+ * The access to some variables in this macro is racy. We can't use atomic_t
+ * here because all these variables are exported to debugfs. Some of them even
+ * writeable. This is also the reason why a lock won't help much. But anyway,
+ * the races are no big deal. Here is why:
+ *
+ *   error_count: the addition is racy, but the worst thing that can happen is
+ *                that we don't count some errors
+ *   show_num_errors: the subtraction is racy. Also no big deal because in
+ *                    worst case this will result in one warning more in the
+ *                    system log than the user configured. This variable is
+ *                    writeable via debugfs.
+ */
+static inline void dump_entry_trace(struct dma_debug_entry *entry)
+{
+#ifdef CONFIG_STACKTRACE
+	if (entry) {
+		pr_warn("Mapped at:\n");
+		stack_trace_print(entry->stack_entries, entry->stack_len, 0);
+	}
+#endif
+}
+
+static bool driver_filter(struct device *dev)
+{
+	struct device_driver *drv;
+	unsigned long flags;
+	bool ret;
+
+	/* driver filter off */
+	if (likely(!current_driver_name[0]))
+		return true;
+
+	/* driver filter on and initialized */
+	if (current_driver && dev && dev->driver == current_driver)
+		return true;
+
+	/* driver filter on, but we can't filter on a NULL device... */
+	if (!dev)
+		return false;
+
+	if (current_driver || !current_driver_name[0])
+		return false;
+
+	/* driver filter on but not yet initialized */
+	drv = dev->driver;
+	if (!drv)
+		return false;
+
+	/* lock to protect against change of current_driver_name */
+	read_lock_irqsave(&driver_name_lock, flags);
+
+	ret = false;
+	if (drv->name &&
+	    strncmp(current_driver_name, drv->name, NAME_MAX_LEN - 1) == 0) {
+		current_driver = drv;
+		ret = true;
+	}
+
+	read_unlock_irqrestore(&driver_name_lock, flags);
+
+	return ret;
+}
+
+#define err_printk(dev, entry, format, arg...) do {			\
+		error_count += 1;					\
+		if (driver_filter(dev) &&				\
+		    (show_all_errors || show_num_errors > 0)) {		\
+			WARN(1, pr_fmt("%s %s: ") format,		\
+			     dev ? dev_driver_string(dev) : "NULL",	\
+			     dev ? dev_name(dev) : "NULL", ## arg);	\
+			dump_entry_trace(entry);			\
+		}							\
+		if (!show_all_errors && show_num_errors > 0)		\
+			show_num_errors -= 1;				\
+	} while (0);
+
+/*
+ * Hash related functions
+ *
+ * Every DMA-API request is saved into a struct dma_debug_entry. To
+ * have quick access to these structs they are stored into a hash.
+ */
+static int hash_fn(struct dma_debug_entry *entry)
+{
+	/*
+	 * Hash function is based on the dma address.
+	 * We use bits 20-27 here as the index into the hash
+	 */
+	return (entry->dev_addr >> HASH_FN_SHIFT) & HASH_FN_MASK;
+}
+
+/*
+ * Request exclusive access to a hash bucket for a given dma_debug_entry.
+ */
+static struct hash_bucket *get_hash_bucket(struct dma_debug_entry *entry,
+					   unsigned long *flags)
+	__acquires(&dma_entry_hash[idx].lock)
+{
+	int idx = hash_fn(entry);
+	unsigned long __flags;
+
+	spin_lock_irqsave(&dma_entry_hash[idx].lock, __flags);
+	*flags = __flags;
+	return &dma_entry_hash[idx];
+}
+
+/*
+ * Give up exclusive access to the hash bucket
+ */
+static void put_hash_bucket(struct hash_bucket *bucket,
+			    unsigned long flags)
+	__releases(&bucket->lock)
+{
+	spin_unlock_irqrestore(&bucket->lock, flags);
+}
+
+static bool exact_match(struct dma_debug_entry *a, struct dma_debug_entry *b)
+{
+	return ((a->dev_addr == b->dev_addr) &&
+		(a->dev == b->dev)) ? true : false;
+}
+
+static bool containing_match(struct dma_debug_entry *a,
+			     struct dma_debug_entry *b)
+{
+	if (a->dev != b->dev)
+		return false;
+
+	if ((b->dev_addr <= a->dev_addr) &&
+	    ((b->dev_addr + b->size) >= (a->dev_addr + a->size)))
+		return true;
+
+	return false;
+}
+
+/*
+ * Search a given entry in the hash bucket list
+ */
+static struct dma_debug_entry *__hash_bucket_find(struct hash_bucket *bucket,
+						  struct dma_debug_entry *ref,
+						  match_fn match)
+{
+	struct dma_debug_entry *entry, *ret = NULL;
+	int matches = 0, match_lvl, last_lvl = -1;
+
+	list_for_each_entry(entry, &bucket->list, list) {
+		if (!match(ref, entry))
+			continue;
+
+		/*
+		 * Some drivers map the same physical address multiple
+		 * times. Without a hardware IOMMU this results in the
+		 * same device addresses being put into the dma-debug
+		 * hash multiple times too. This can result in false
+		 * positives being reported. Therefore we implement a
+		 * best-fit algorithm here which returns the entry from
+		 * the hash which fits best to the reference value
+		 * instead of the first-fit.
+		 */
+		matches += 1;
+		match_lvl = 0;
+		entry->size         == ref->size         ? ++match_lvl : 0;
+		entry->type         == ref->type         ? ++match_lvl : 0;
+		entry->direction    == ref->direction    ? ++match_lvl : 0;
+		entry->sg_call_ents == ref->sg_call_ents ? ++match_lvl : 0;
+
+		if (match_lvl == 4) {
+			/* perfect-fit - return the result */
+			return entry;
+		} else if (match_lvl > last_lvl) {
+			/*
+			 * We found an entry that fits better then the
+			 * previous one or it is the 1st match.
+			 */
+			last_lvl = match_lvl;
+			ret      = entry;
+		}
+	}
+
+	/*
+	 * If we have multiple matches but no perfect-fit, just return
+	 * NULL.
+	 */
+	ret = (matches == 1) ? ret : NULL;
+
+	return ret;
+}
+
+static struct dma_debug_entry *bucket_find_exact(struct hash_bucket *bucket,
+						 struct dma_debug_entry *ref)
+{
+	return __hash_bucket_find(bucket, ref, exact_match);
+}
+
+static struct dma_debug_entry *bucket_find_contain(struct hash_bucket **bucket,
+						   struct dma_debug_entry *ref,
+						   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;
+
+	while (range <= max_range) {
+		entry = __hash_bucket_find(*bucket, ref, containing_match);
+
+		if (entry)
+			return entry;
+
+		/*
+		 * 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);
+	}
+
+	return NULL;
+}
+
+/*
+ * Add an entry to a hash bucket
+ */
+static void hash_bucket_add(struct hash_bucket *bucket,
+			    struct dma_debug_entry *entry)
+{
+	list_add_tail(&entry->list, &bucket->list);
+}
+
+/*
+ * Remove entry from a hash bucket list
+ */
+static void hash_bucket_del(struct dma_debug_entry *entry)
+{
+	list_del(&entry->list);
+}
+
+static unsigned long long phys_addr(struct dma_debug_entry *entry)
+{
+	if (entry->type == dma_debug_resource)
+		return __pfn_to_phys(entry->pfn) + entry->offset;
+
+	return page_to_phys(pfn_to_page(entry->pfn)) + entry->offset;
+}
+
+/*
+ * Dump mapping entries for debugging purposes
+ */
+void debug_dma_dump_mappings(struct device *dev)
+{
+	int idx;
+
+	for (idx = 0; idx < HASH_SIZE; idx++) {
+		struct hash_bucket *bucket = &dma_entry_hash[idx];
+		struct dma_debug_entry *entry;
+		unsigned long flags;
+
+		spin_lock_irqsave(&bucket->lock, flags);
+
+		list_for_each_entry(entry, &bucket->list, list) {
+			if (!dev || dev == entry->dev) {
+				dev_info(entry->dev,
+					 "%s idx %d P=%Lx N=%lx D=%Lx L=%Lx %s %s\n",
+					 type2name[entry->type], idx,
+					 phys_addr(entry), entry->pfn,
+					 entry->dev_addr, entry->size,
+					 dir2name[entry->direction],
+					 maperr2str[entry->map_err_type]);
+			}
+		}
+
+		spin_unlock_irqrestore(&bucket->lock, flags);
+		cond_resched();
+	}
+}
+
+/*
+ * For each mapping (initial cacheline in the case of
+ * dma_alloc_coherent/dma_map_page, initial cacheline in each page of a
+ * scatterlist, or the cacheline specified in dma_map_single) insert
+ * into this tree using the cacheline as the key. At
+ * dma_unmap_{single|sg|page} or dma_free_coherent delete the entry.  If
+ * the entry already exists at insertion time add a tag as a reference
+ * count for the overlapping mappings.  For now, the overlap tracking
+ * just ensures that 'unmaps' balance 'maps' before marking the
+ * cacheline idle, but we should also be flagging overlaps as an API
+ * violation.
+ *
+ * Memory usage is mostly constrained by the maximum number of available
+ * dma-debug entries in that we need a free dma_debug_entry before
+ * inserting into the tree.  In the case of dma_map_page and
+ * dma_alloc_coherent there is only one dma_debug_entry and one
+ * dma_active_cacheline entry to track per event.  dma_map_sg(), on the
+ * other hand, consumes a single dma_debug_entry, but inserts 'nents'
+ * entries into the tree.
+ */
+static RADIX_TREE(dma_active_cacheline, GFP_ATOMIC);
+static DEFINE_SPINLOCK(radix_lock);
+#define ACTIVE_CACHELINE_MAX_OVERLAP ((1 << RADIX_TREE_MAX_TAGS) - 1)
+#define CACHELINE_PER_PAGE_SHIFT (PAGE_SHIFT - L1_CACHE_SHIFT)
+#define CACHELINES_PER_PAGE (1 << CACHELINE_PER_PAGE_SHIFT)
+
+static phys_addr_t to_cacheline_number(struct dma_debug_entry *entry)
+{
+	return (entry->pfn << CACHELINE_PER_PAGE_SHIFT) +
+		(entry->offset >> L1_CACHE_SHIFT);
+}
+
+static int active_cacheline_read_overlap(phys_addr_t cln)
+{
+	int overlap = 0, i;
+
+	for (i = RADIX_TREE_MAX_TAGS - 1; i >= 0; i--)
+		if (radix_tree_tag_get(&dma_active_cacheline, cln, i))
+			overlap |= 1 << i;
+	return overlap;
+}
+
+static int active_cacheline_set_overlap(phys_addr_t cln, int overlap)
+{
+	int i;
+
+	if (overlap > ACTIVE_CACHELINE_MAX_OVERLAP || overlap < 0)
+		return overlap;
+
+	for (i = RADIX_TREE_MAX_TAGS - 1; i >= 0; i--)
+		if (overlap & 1 << i)
+			radix_tree_tag_set(&dma_active_cacheline, cln, i);
+		else
+			radix_tree_tag_clear(&dma_active_cacheline, cln, i);
+
+	return overlap;
+}
+
+static void active_cacheline_inc_overlap(phys_addr_t cln)
+{
+	int overlap = active_cacheline_read_overlap(cln);
+
+	overlap = active_cacheline_set_overlap(cln, ++overlap);
+
+	/* If we overflowed the overlap counter then we're potentially
+	 * leaking dma-mappings.
+	 */
+	WARN_ONCE(overlap > ACTIVE_CACHELINE_MAX_OVERLAP,
+		  pr_fmt("exceeded %d overlapping mappings of cacheline %pa\n"),
+		  ACTIVE_CACHELINE_MAX_OVERLAP, &cln);
+}
+
+static int active_cacheline_dec_overlap(phys_addr_t cln)
+{
+	int overlap = active_cacheline_read_overlap(cln);
+
+	return active_cacheline_set_overlap(cln, --overlap);
+}
+
+static int active_cacheline_insert(struct dma_debug_entry *entry)
+{
+	phys_addr_t cln = to_cacheline_number(entry);
+	unsigned long flags;
+	int rc;
+
+	/* If the device is not writing memory then we don't have any
+	 * concerns about the cpu consuming stale data.  This mitigates
+	 * legitimate usages of overlapping mappings.
+	 */
+	if (entry->direction == DMA_TO_DEVICE)
+		return 0;
+
+	spin_lock_irqsave(&radix_lock, flags);
+	rc = radix_tree_insert(&dma_active_cacheline, cln, entry);
+	if (rc == -EEXIST)
+		active_cacheline_inc_overlap(cln);
+	spin_unlock_irqrestore(&radix_lock, flags);
+
+	return rc;
+}
+
+static void active_cacheline_remove(struct dma_debug_entry *entry)
+{
+	phys_addr_t cln = to_cacheline_number(entry);
+	unsigned long flags;
+
+	/* ...mirror the insert case */
+	if (entry->direction == DMA_TO_DEVICE)
+		return;
+
+	spin_lock_irqsave(&radix_lock, flags);
+	/* since we are counting overlaps the final put of the
+	 * cacheline will occur when the overlap count is 0.
+	 * active_cacheline_dec_overlap() returns -1 in that case
+	 */
+	if (active_cacheline_dec_overlap(cln) < 0)
+		radix_tree_delete(&dma_active_cacheline, cln);
+	spin_unlock_irqrestore(&radix_lock, flags);
+}
+
+/*
+ * Wrapper function for adding an entry to the hash.
+ * This function takes care of locking itself.
+ */
+static void add_dma_entry(struct dma_debug_entry *entry)
+{
+	struct hash_bucket *bucket;
+	unsigned long flags;
+	int rc;
+
+	bucket = get_hash_bucket(entry, &flags);
+	hash_bucket_add(bucket, entry);
+	put_hash_bucket(bucket, flags);
+
+	rc = active_cacheline_insert(entry);
+	if (rc == -ENOMEM) {
+		pr_err_once("cacheline tracking ENOMEM, dma-debug disabled\n");
+		global_disable = true;
+	}
+
+	/* TODO: report -EEXIST errors here as overlapping mappings are
+	 * not supported by the DMA API
+	 */
+}
+
+static int dma_debug_create_entries(gfp_t gfp)
+{
+	struct dma_debug_entry *entry;
+	int i;
+
+	entry = (void *)get_zeroed_page(gfp);
+	if (!entry)
+		return -ENOMEM;
+
+	for (i = 0; i < DMA_DEBUG_DYNAMIC_ENTRIES; i++)
+		list_add_tail(&entry[i].list, &free_entries);
+
+	num_free_entries += DMA_DEBUG_DYNAMIC_ENTRIES;
+	nr_total_entries += DMA_DEBUG_DYNAMIC_ENTRIES;
+
+	return 0;
+}
+
+static struct dma_debug_entry *__dma_entry_alloc(void)
+{
+	struct dma_debug_entry *entry;
+
+	entry = list_entry(free_entries.next, struct dma_debug_entry, list);
+	list_del(&entry->list);
+	memset(entry, 0, sizeof(*entry));
+
+	num_free_entries -= 1;
+	if (num_free_entries < min_free_entries)
+		min_free_entries = num_free_entries;
+
+	return entry;
+}
+
+/*
+ * This should be called outside of free_entries_lock scope to avoid potential
+ * deadlocks with serial consoles that use DMA.
+ */
+static void __dma_entry_alloc_check_leak(u32 nr_entries)
+{
+	u32 tmp = nr_entries % nr_prealloc_entries;
+
+	/* Shout each time we tick over some multiple of the initial pool */
+	if (tmp < DMA_DEBUG_DYNAMIC_ENTRIES) {
+		pr_info("dma_debug_entry pool grown to %u (%u00%%)\n",
+			nr_entries,
+			(nr_entries / nr_prealloc_entries));
+	}
+}
+
+/* struct dma_entry allocator
+ *
+ * The next two functions implement the allocator for
+ * struct dma_debug_entries.
+ */
+static struct dma_debug_entry *dma_entry_alloc(void)
+{
+	bool alloc_check_leak = false;
+	struct dma_debug_entry *entry;
+	unsigned long flags;
+	u32 nr_entries;
+
+	spin_lock_irqsave(&free_entries_lock, flags);
+	if (num_free_entries == 0) {
+		if (dma_debug_create_entries(GFP_ATOMIC)) {
+			global_disable = true;
+			spin_unlock_irqrestore(&free_entries_lock, flags);
+			pr_err("debugging out of memory - disabling\n");
+			return NULL;
+		}
+		alloc_check_leak = true;
+		nr_entries = nr_total_entries;
+	}
+
+	entry = __dma_entry_alloc();
+
+	spin_unlock_irqrestore(&free_entries_lock, flags);
+
+	if (alloc_check_leak)
+		__dma_entry_alloc_check_leak(nr_entries);
+
+#ifdef CONFIG_STACKTRACE
+	entry->stack_len = stack_trace_save(entry->stack_entries,
+					    ARRAY_SIZE(entry->stack_entries),
+					    1);
+#endif
+	return entry;
+}
+
+static void dma_entry_free(struct dma_debug_entry *entry)
+{
+	unsigned long flags;
+
+	active_cacheline_remove(entry);
+
+	/*
+	 * add to beginning of the list - this way the entries are
+	 * more likely cache hot when they are reallocated.
+	 */
+	spin_lock_irqsave(&free_entries_lock, flags);
+	list_add(&entry->list, &free_entries);
+	num_free_entries += 1;
+	spin_unlock_irqrestore(&free_entries_lock, flags);
+}
+
+/*
+ * DMA-API debugging init code
+ *
+ * The init code does two things:
+ *   1. Initialize core data structures
+ *   2. Preallocate a given number of dma_debug_entry structs
+ */
+
+static ssize_t filter_read(struct file *file, char __user *user_buf,
+			   size_t count, loff_t *ppos)
+{
+	char buf[NAME_MAX_LEN + 1];
+	unsigned long flags;
+	int len;
+
+	if (!current_driver_name[0])
+		return 0;
+
+	/*
+	 * We can't copy to userspace directly because current_driver_name can
+	 * only be read under the driver_name_lock with irqs disabled. So
+	 * create a temporary copy first.
+	 */
+	read_lock_irqsave(&driver_name_lock, flags);
+	len = scnprintf(buf, NAME_MAX_LEN + 1, "%s\n", current_driver_name);
+	read_unlock_irqrestore(&driver_name_lock, flags);
+
+	return simple_read_from_buffer(user_buf, count, ppos, buf, len);
+}
+
+static ssize_t filter_write(struct file *file, const char __user *userbuf,
+			    size_t count, loff_t *ppos)
+{
+	char buf[NAME_MAX_LEN];
+	unsigned long flags;
+	size_t len;
+	int i;
+
+	/*
+	 * We can't copy from userspace directly. Access to
+	 * current_driver_name is protected with a write_lock with irqs
+	 * disabled. Since copy_from_user can fault and may sleep we
+	 * need to copy to temporary buffer first
+	 */
+	len = min(count, (size_t)(NAME_MAX_LEN - 1));
+	if (copy_from_user(buf, userbuf, len))
+		return -EFAULT;
+
+	buf[len] = 0;
+
+	write_lock_irqsave(&driver_name_lock, flags);
+
+	/*
+	 * Now handle the string we got from userspace very carefully.
+	 * The rules are:
+	 *         - only use the first token we got
+	 *         - token delimiter is everything looking like a space
+	 *           character (' ', '\n', '\t' ...)
+	 *
+	 */
+	if (!isalnum(buf[0])) {
+		/*
+		 * If the first character userspace gave us is not
+		 * alphanumerical then assume the filter should be
+		 * switched off.
+		 */
+		if (current_driver_name[0])
+			pr_info("switching off dma-debug driver filter\n");
+		current_driver_name[0] = 0;
+		current_driver = NULL;
+		goto out_unlock;
+	}
+
+	/*
+	 * Now parse out the first token and use it as the name for the
+	 * driver to filter for.
+	 */
+	for (i = 0; i < NAME_MAX_LEN - 1; ++i) {
+		current_driver_name[i] = buf[i];
+		if (isspace(buf[i]) || buf[i] == ' ' || buf[i] == 0)
+			break;
+	}
+	current_driver_name[i] = 0;
+	current_driver = NULL;
+
+	pr_info("enable driver filter for driver [%s]\n",
+		current_driver_name);
+
+out_unlock:
+	write_unlock_irqrestore(&driver_name_lock, flags);
+
+	return count;
+}
+
+static const struct file_operations filter_fops = {
+	.read  = filter_read,
+	.write = filter_write,
+	.llseek = default_llseek,
+};
+
+static int dump_show(struct seq_file *seq, void *v)
+{
+	int idx;
+
+	for (idx = 0; idx < HASH_SIZE; idx++) {
+		struct hash_bucket *bucket = &dma_entry_hash[idx];
+		struct dma_debug_entry *entry;
+		unsigned long flags;
+
+		spin_lock_irqsave(&bucket->lock, flags);
+		list_for_each_entry(entry, &bucket->list, list) {
+			seq_printf(seq,
+				   "%s %s %s idx %d P=%llx N=%lx D=%llx L=%llx %s %s\n",
+				   dev_name(entry->dev),
+				   dev_driver_string(entry->dev),
+				   type2name[entry->type], idx,
+				   phys_addr(entry), entry->pfn,
+				   entry->dev_addr, entry->size,
+				   dir2name[entry->direction],
+				   maperr2str[entry->map_err_type]);
+		}
+		spin_unlock_irqrestore(&bucket->lock, flags);
+	}
+	return 0;
+}
+DEFINE_SHOW_ATTRIBUTE(dump);
+
+static int __init dma_debug_fs_init(void)
+{
+	struct dentry *dentry = debugfs_create_dir("dma-api", NULL);
+
+	debugfs_create_bool("disabled", 0444, dentry, &global_disable);
+	debugfs_create_u32("error_count", 0444, dentry, &error_count);
+	debugfs_create_u32("all_errors", 0644, dentry, &show_all_errors);
+	debugfs_create_u32("num_errors", 0644, dentry, &show_num_errors);
+	debugfs_create_u32("num_free_entries", 0444, dentry, &num_free_entries);
+	debugfs_create_u32("min_free_entries", 0444, dentry, &min_free_entries);
+	debugfs_create_u32("nr_total_entries", 0444, dentry, &nr_total_entries);
+	debugfs_create_file("driver_filter", 0644, dentry, NULL, &filter_fops);
+	debugfs_create_file("dump", 0444, dentry, NULL, &dump_fops);
+
+	return 0;
+}
+core_initcall_sync(dma_debug_fs_init);
+
+static int device_dma_allocations(struct device *dev, struct dma_debug_entry **out_entry)
+{
+	struct dma_debug_entry *entry;
+	unsigned long flags;
+	int count = 0, i;
+
+	for (i = 0; i < HASH_SIZE; ++i) {
+		spin_lock_irqsave(&dma_entry_hash[i].lock, flags);
+		list_for_each_entry(entry, &dma_entry_hash[i].list, list) {
+			if (entry->dev == dev) {
+				count += 1;
+				*out_entry = entry;
+			}
+		}
+		spin_unlock_irqrestore(&dma_entry_hash[i].lock, flags);
+	}
+
+	return count;
+}
+
+static int dma_debug_device_change(struct notifier_block *nb, unsigned long action, void *data)
+{
+	struct device *dev = data;
+	struct dma_debug_entry *entry;
+	int count;
+
+	if (dma_debug_disabled())
+		return 0;
+
+	switch (action) {
+	case BUS_NOTIFY_UNBOUND_DRIVER:
+		count = device_dma_allocations(dev, &entry);
+		if (count == 0)
+			break;
+		err_printk(dev, entry, "device driver has pending "
+				"DMA allocations while released from device "
+				"[count=%d]\n"
+				"One of leaked entries details: "
+				"[device address=0x%016llx] [size=%llu bytes] "
+				"[mapped with %s] [mapped as %s]\n",
+			count, entry->dev_addr, entry->size,
+			dir2name[entry->direction], type2name[entry->type]);
+		break;
+	default:
+		break;
+	}
+
+	return 0;
+}
+
+void dma_debug_add_bus(struct bus_type *bus)
+{
+	struct notifier_block *nb;
+
+	if (dma_debug_disabled())
+		return;
+
+	nb = kzalloc(sizeof(struct notifier_block), GFP_KERNEL);
+	if (nb == NULL) {
+		pr_err("dma_debug_add_bus: out of memory\n");
+		return;
+	}
+
+	nb->notifier_call = dma_debug_device_change;
+
+	bus_register_notifier(bus, nb);
+}
+
+static int dma_debug_init(void)
+{
+	int i, nr_pages;
+
+	/* Do not use dma_debug_initialized here, since we really want to be
+	 * called to set dma_debug_initialized
+	 */
+	if (global_disable)
+		return 0;
+
+	for (i = 0; i < HASH_SIZE; ++i) {
+		INIT_LIST_HEAD(&dma_entry_hash[i].list);
+		spin_lock_init(&dma_entry_hash[i].lock);
+	}
+
+	nr_pages = DIV_ROUND_UP(nr_prealloc_entries, DMA_DEBUG_DYNAMIC_ENTRIES);
+	for (i = 0; i < nr_pages; ++i)
+		dma_debug_create_entries(GFP_KERNEL);
+	if (num_free_entries >= nr_prealloc_entries) {
+		pr_info("preallocated %d debug entries\n", nr_total_entries);
+	} else if (num_free_entries > 0) {
+		pr_warn("%d debug entries requested but only %d allocated\n",
+			nr_prealloc_entries, nr_total_entries);
+	} else {
+		pr_err("debugging out of memory error - disabled\n");
+		global_disable = true;
+
+		return 0;
+	}
+	min_free_entries = num_free_entries;
+
+	dma_debug_initialized = true;
+
+	pr_info("debugging enabled by kernel config\n");
+	return 0;
+}
+core_initcall(dma_debug_init);
+
+static __init int dma_debug_cmdline(char *str)
+{
+	if (!str)
+		return -EINVAL;
+
+	if (strncmp(str, "off", 3) == 0) {
+		pr_info("debugging disabled on kernel command line\n");
+		global_disable = true;
+	}
+
+	return 1;
+}
+
+static __init int dma_debug_entries_cmdline(char *str)
+{
+	if (!str)
+		return -EINVAL;
+	if (!get_option(&str, &nr_prealloc_entries))
+		nr_prealloc_entries = PREALLOC_DMA_DEBUG_ENTRIES;
+	return 1;
+}
+
+__setup("dma_debug=", dma_debug_cmdline);
+__setup("dma_debug_entries=", dma_debug_entries_cmdline);
+
+static void check_unmap(struct dma_debug_entry *ref)
+{
+	struct dma_debug_entry *entry;
+	struct hash_bucket *bucket;
+	unsigned long flags;
+
+	bucket = get_hash_bucket(ref, &flags);
+	entry = bucket_find_exact(bucket, ref);
+
+	if (!entry) {
+		/* must drop lock before calling dma_mapping_error */
+		put_hash_bucket(bucket, flags);
+
+		if (dma_mapping_error(ref->dev, ref->dev_addr)) {
+			err_printk(ref->dev, NULL,
+				   "device driver tries to free an "
+				   "invalid DMA memory address\n");
+		} else {
+			err_printk(ref->dev, NULL,
+				   "device driver tries to free DMA "
+				   "memory it has not allocated [device "
+				   "address=0x%016llx] [size=%llu bytes]\n",
+				   ref->dev_addr, ref->size);
+		}
+		return;
+	}
+
+	if (ref->size != entry->size) {
+		err_printk(ref->dev, entry, "device driver frees "
+			   "DMA memory with different size "
+			   "[device address=0x%016llx] [map size=%llu bytes] "
+			   "[unmap size=%llu bytes]\n",
+			   ref->dev_addr, entry->size, ref->size);
+	}
+
+	if (ref->type != entry->type) {
+		err_printk(ref->dev, entry, "device driver frees "
+			   "DMA memory with wrong function "
+			   "[device address=0x%016llx] [size=%llu bytes] "
+			   "[mapped as %s] [unmapped as %s]\n",
+			   ref->dev_addr, ref->size,
+			   type2name[entry->type], type2name[ref->type]);
+	} else if ((entry->type == dma_debug_coherent) &&
+		   (phys_addr(ref) != phys_addr(entry))) {
+		err_printk(ref->dev, entry, "device driver frees "
+			   "DMA memory with different CPU address "
+			   "[device address=0x%016llx] [size=%llu bytes] "
+			   "[cpu alloc address=0x%016llx] "
+			   "[cpu free address=0x%016llx]",
+			   ref->dev_addr, ref->size,
+			   phys_addr(entry),
+			   phys_addr(ref));
+	}
+
+	if (ref->sg_call_ents && ref->type == dma_debug_sg &&
+	    ref->sg_call_ents != entry->sg_call_ents) {
+		err_printk(ref->dev, entry, "device driver frees "
+			   "DMA sg list with different entry count "
+			   "[map count=%d] [unmap count=%d]\n",
+			   entry->sg_call_ents, ref->sg_call_ents);
+	}
+
+	/*
+	 * This may be no bug in reality - but most implementations of the
+	 * DMA API don't handle this properly, so check for it here
+	 */
+	if (ref->direction != entry->direction) {
+		err_printk(ref->dev, entry, "device driver frees "
+			   "DMA memory with different direction "
+			   "[device address=0x%016llx] [size=%llu bytes] "
+			   "[mapped with %s] [unmapped with %s]\n",
+			   ref->dev_addr, ref->size,
+			   dir2name[entry->direction],
+			   dir2name[ref->direction]);
+	}
+
+	/*
+	 * Drivers should use dma_mapping_error() to check the returned
+	 * addresses of dma_map_single() and dma_map_page().
+	 * If not, print this warning message. See Documentation/core-api/dma-api.rst.
+	 */
+	if (entry->map_err_type == MAP_ERR_NOT_CHECKED) {
+		err_printk(ref->dev, entry,
+			   "device driver failed to check map error"
+			   "[device address=0x%016llx] [size=%llu bytes] "
+			   "[mapped as %s]",
+			   ref->dev_addr, ref->size,
+			   type2name[entry->type]);
+	}
+
+	hash_bucket_del(entry);
+	dma_entry_free(entry);
+
+	put_hash_bucket(bucket, flags);
+}
+
+static void check_for_stack(struct device *dev,
+			    struct page *page, size_t offset)
+{
+	void *addr;
+	struct vm_struct *stack_vm_area = task_stack_vm_area(current);
+
+	if (!stack_vm_area) {
+		/* Stack is direct-mapped. */
+		if (PageHighMem(page))
+			return;
+		addr = page_address(page) + offset;
+		if (object_is_on_stack(addr))
+			err_printk(dev, NULL, "device driver maps memory from stack [addr=%p]\n", addr);
+	} else {
+		/* Stack is vmalloced. */
+		int i;
+
+		for (i = 0; i < stack_vm_area->nr_pages; i++) {
+			if (page != stack_vm_area->pages[i])
+				continue;
+
+			addr = (u8 *)current->stack + i * PAGE_SIZE + offset;
+			err_printk(dev, NULL, "device driver maps memory from stack [probable addr=%p]\n", addr);
+			break;
+		}
+	}
+}
+
+static inline bool overlap(void *addr, unsigned long len, void *start, void *end)
+{
+	unsigned long a1 = (unsigned long)addr;
+	unsigned long b1 = a1 + len;
+	unsigned long a2 = (unsigned long)start;
+	unsigned long b2 = (unsigned long)end;
+
+	return !(b1 <= a2 || a1 >= b2);
+}
+
+static void check_for_illegal_area(struct device *dev, void *addr, unsigned long len)
+{
+	if (overlap(addr, len, _stext, _etext) ||
+	    overlap(addr, len, __start_rodata, __end_rodata))
+		err_printk(dev, NULL, "device driver maps memory from kernel text or rodata [addr=%p] [len=%lu]\n", addr, len);
+}
+
+static void check_sync(struct device *dev,
+		       struct dma_debug_entry *ref,
+		       bool to_cpu)
+{
+	struct dma_debug_entry *entry;
+	struct hash_bucket *bucket;
+	unsigned long flags;
+
+	bucket = get_hash_bucket(ref, &flags);
+
+	entry = bucket_find_contain(&bucket, ref, &flags);
+
+	if (!entry) {
+		err_printk(dev, NULL, "device driver tries "
+				"to sync DMA memory it has not allocated "
+				"[device address=0x%016llx] [size=%llu bytes]\n",
+				(unsigned long long)ref->dev_addr, ref->size);
+		goto out;
+	}
+
+	if (ref->size > entry->size) {
+		err_printk(dev, entry, "device driver syncs"
+				" DMA memory outside allocated range "
+				"[device address=0x%016llx] "
+				"[allocation size=%llu bytes] "
+				"[sync offset+size=%llu]\n",
+				entry->dev_addr, entry->size,
+				ref->size);
+	}
+
+	if (entry->direction == DMA_BIDIRECTIONAL)
+		goto out;
+
+	if (ref->direction != entry->direction) {
+		err_printk(dev, entry, "device driver syncs "
+				"DMA memory with different direction "
+				"[device address=0x%016llx] [size=%llu bytes] "
+				"[mapped with %s] [synced with %s]\n",
+				(unsigned long long)ref->dev_addr, entry->size,
+				dir2name[entry->direction],
+				dir2name[ref->direction]);
+	}
+
+	if (to_cpu && !(entry->direction == DMA_FROM_DEVICE) &&
+		      !(ref->direction == DMA_TO_DEVICE))
+		err_printk(dev, entry, "device driver syncs "
+				"device read-only DMA memory for cpu "
+				"[device address=0x%016llx] [size=%llu bytes] "
+				"[mapped with %s] [synced with %s]\n",
+				(unsigned long long)ref->dev_addr, entry->size,
+				dir2name[entry->direction],
+				dir2name[ref->direction]);
+
+	if (!to_cpu && !(entry->direction == DMA_TO_DEVICE) &&
+		       !(ref->direction == DMA_FROM_DEVICE))
+		err_printk(dev, entry, "device driver syncs "
+				"device write-only DMA memory to device "
+				"[device address=0x%016llx] [size=%llu bytes] "
+				"[mapped with %s] [synced with %s]\n",
+				(unsigned long long)ref->dev_addr, entry->size,
+				dir2name[entry->direction],
+				dir2name[ref->direction]);
+
+	if (ref->sg_call_ents && ref->type == dma_debug_sg &&
+	    ref->sg_call_ents != entry->sg_call_ents) {
+		err_printk(ref->dev, entry, "device driver syncs "
+			   "DMA sg list with different entry count "
+			   "[map count=%d] [sync count=%d]\n",
+			   entry->sg_call_ents, ref->sg_call_ents);
+	}
+
+out:
+	put_hash_bucket(bucket, flags);
+}
+
+static void check_sg_segment(struct device *dev, struct scatterlist *sg)
+{
+#ifdef CONFIG_DMA_API_DEBUG_SG
+	unsigned int max_seg = dma_get_max_seg_size(dev);
+	u64 start, end, boundary = dma_get_seg_boundary(dev);
+
+	/*
+	 * Either the driver forgot to set dma_parms appropriately, or
+	 * whoever generated the list forgot to check them.
+	 */
+	if (sg->length > max_seg)
+		err_printk(dev, NULL, "mapping sg segment longer than device claims to support [len=%u] [max=%u]\n",
+			   sg->length, max_seg);
+	/*
+	 * In some cases this could potentially be the DMA API
+	 * implementation's fault, but it would usually imply that
+	 * the scatterlist was built inappropriately to begin with.
+	 */
+	start = sg_dma_address(sg);
+	end = start + sg_dma_len(sg) - 1;
+	if ((start ^ end) & ~boundary)
+		err_printk(dev, NULL, "mapping sg segment across boundary [start=0x%016llx] [end=0x%016llx] [boundary=0x%016llx]\n",
+			   start, end, boundary);
+#endif
+}
+
+void debug_dma_map_single(struct device *dev, const void *addr,
+			    unsigned long len)
+{
+	if (unlikely(dma_debug_disabled()))
+		return;
+
+	if (!virt_addr_valid(addr))
+		err_printk(dev, NULL, "device driver maps memory from invalid area [addr=%p] [len=%lu]\n",
+			   addr, len);
+
+	if (is_vmalloc_addr(addr))
+		err_printk(dev, NULL, "device driver maps memory from vmalloc area [addr=%p] [len=%lu]\n",
+			   addr, len);
+}
+EXPORT_SYMBOL(debug_dma_map_single);
+
+void debug_dma_map_page(struct device *dev, struct page *page, size_t offset,
+			size_t size, int direction, dma_addr_t dma_addr)
+{
+	struct dma_debug_entry *entry;
+
+	if (unlikely(dma_debug_disabled()))
+		return;
+
+	if (dma_mapping_error(dev, dma_addr))
+		return;
+
+	entry = dma_entry_alloc();
+	if (!entry)
+		return;
+
+	entry->dev       = dev;
+	entry->type      = dma_debug_single;
+	entry->pfn	 = page_to_pfn(page);
+	entry->offset	 = offset;
+	entry->dev_addr  = dma_addr;
+	entry->size      = size;
+	entry->direction = direction;
+	entry->map_err_type = MAP_ERR_NOT_CHECKED;
+
+	check_for_stack(dev, page, offset);
+
+	if (!PageHighMem(page)) {
+		void *addr = page_address(page) + offset;
+
+		check_for_illegal_area(dev, addr, size);
+	}
+
+	add_dma_entry(entry);
+}
+
+void debug_dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
+{
+	struct dma_debug_entry ref;
+	struct dma_debug_entry *entry;
+	struct hash_bucket *bucket;
+	unsigned long flags;
+
+	if (unlikely(dma_debug_disabled()))
+		return;
+
+	ref.dev = dev;
+	ref.dev_addr = dma_addr;
+	bucket = get_hash_bucket(&ref, &flags);
+
+	list_for_each_entry(entry, &bucket->list, list) {
+		if (!exact_match(&ref, entry))
+			continue;
+
+		/*
+		 * The same physical address can be mapped multiple
+		 * times. Without a hardware IOMMU this results in the
+		 * same device addresses being put into the dma-debug
+		 * hash multiple times too. This can result in false
+		 * positives being reported. Therefore we implement a
+		 * best-fit algorithm here which updates the first entry
+		 * from the hash which fits the reference value and is
+		 * not currently listed as being checked.
+		 */
+		if (entry->map_err_type == MAP_ERR_NOT_CHECKED) {
+			entry->map_err_type = MAP_ERR_CHECKED;
+			break;
+		}
+	}
+
+	put_hash_bucket(bucket, flags);
+}
+EXPORT_SYMBOL(debug_dma_mapping_error);
+
+void debug_dma_unmap_page(struct device *dev, dma_addr_t addr,
+			  size_t size, int direction)
+{
+	struct dma_debug_entry ref = {
+		.type           = dma_debug_single,
+		.dev            = dev,
+		.dev_addr       = addr,
+		.size           = size,
+		.direction      = direction,
+	};
+
+	if (unlikely(dma_debug_disabled()))
+		return;
+	check_unmap(&ref);
+}
+
+void debug_dma_map_sg(struct device *dev, struct scatterlist *sg,
+		      int nents, int mapped_ents, int direction)
+{
+	struct dma_debug_entry *entry;
+	struct scatterlist *s;
+	int i;
+
+	if (unlikely(dma_debug_disabled()))
+		return;
+
+	for_each_sg(sg, s, nents, i) {
+		check_for_stack(dev, sg_page(s), s->offset);
+		if (!PageHighMem(sg_page(s)))
+			check_for_illegal_area(dev, sg_virt(s), s->length);
+	}
+
+	for_each_sg(sg, s, mapped_ents, i) {
+		entry = dma_entry_alloc();
+		if (!entry)
+			return;
+
+		entry->type           = dma_debug_sg;
+		entry->dev            = dev;
+		entry->pfn	      = page_to_pfn(sg_page(s));
+		entry->offset	      = s->offset;
+		entry->size           = sg_dma_len(s);
+		entry->dev_addr       = sg_dma_address(s);
+		entry->direction      = direction;
+		entry->sg_call_ents   = nents;
+		entry->sg_mapped_ents = mapped_ents;
+
+		check_sg_segment(dev, s);
+
+		add_dma_entry(entry);
+	}
+}
+
+static int get_nr_mapped_entries(struct device *dev,
+				 struct dma_debug_entry *ref)
+{
+	struct dma_debug_entry *entry;
+	struct hash_bucket *bucket;
+	unsigned long flags;
+	int mapped_ents;
+
+	bucket       = get_hash_bucket(ref, &flags);
+	entry        = bucket_find_exact(bucket, ref);
+	mapped_ents  = 0;
+
+	if (entry)
+		mapped_ents = entry->sg_mapped_ents;
+	put_hash_bucket(bucket, flags);
+
+	return mapped_ents;
+}
+
+void debug_dma_unmap_sg(struct device *dev, struct scatterlist *sglist,
+			int nelems, int dir)
+{
+	struct scatterlist *s;
+	int mapped_ents = 0, i;
+
+	if (unlikely(dma_debug_disabled()))
+		return;
+
+	for_each_sg(sglist, s, nelems, i) {
+
+		struct dma_debug_entry ref = {
+			.type           = dma_debug_sg,
+			.dev            = dev,
+			.pfn		= page_to_pfn(sg_page(s)),
+			.offset		= s->offset,
+			.dev_addr       = sg_dma_address(s),
+			.size           = sg_dma_len(s),
+			.direction      = dir,
+			.sg_call_ents   = nelems,
+		};
+
+		if (mapped_ents && i >= mapped_ents)
+			break;
+
+		if (!i)
+			mapped_ents = get_nr_mapped_entries(dev, &ref);
+
+		check_unmap(&ref);
+	}
+}
+
+void debug_dma_alloc_coherent(struct device *dev, size_t size,
+			      dma_addr_t dma_addr, void *virt)
+{
+	struct dma_debug_entry *entry;
+
+	if (unlikely(dma_debug_disabled()))
+		return;
+
+	if (unlikely(virt == NULL))
+		return;
+
+	/* handle vmalloc and linear addresses */
+	if (!is_vmalloc_addr(virt) && !virt_addr_valid(virt))
+		return;
+
+	entry = dma_entry_alloc();
+	if (!entry)
+		return;
+
+	entry->type      = dma_debug_coherent;
+	entry->dev       = dev;
+	entry->offset	 = offset_in_page(virt);
+	entry->size      = size;
+	entry->dev_addr  = dma_addr;
+	entry->direction = DMA_BIDIRECTIONAL;
+
+	if (is_vmalloc_addr(virt))
+		entry->pfn = vmalloc_to_pfn(virt);
+	else
+		entry->pfn = page_to_pfn(virt_to_page(virt));
+
+	add_dma_entry(entry);
+}
+
+void debug_dma_free_coherent(struct device *dev, size_t size,
+			 void *virt, dma_addr_t addr)
+{
+	struct dma_debug_entry ref = {
+		.type           = dma_debug_coherent,
+		.dev            = dev,
+		.offset		= offset_in_page(virt),
+		.dev_addr       = addr,
+		.size           = size,
+		.direction      = DMA_BIDIRECTIONAL,
+	};
+
+	/* handle vmalloc and linear addresses */
+	if (!is_vmalloc_addr(virt) && !virt_addr_valid(virt))
+		return;
+
+	if (is_vmalloc_addr(virt))
+		ref.pfn = vmalloc_to_pfn(virt);
+	else
+		ref.pfn = page_to_pfn(virt_to_page(virt));
+
+	if (unlikely(dma_debug_disabled()))
+		return;
+
+	check_unmap(&ref);
+}
+
+void debug_dma_map_resource(struct device *dev, phys_addr_t addr, size_t size,
+			    int direction, dma_addr_t dma_addr)
+{
+	struct dma_debug_entry *entry;
+
+	if (unlikely(dma_debug_disabled()))
+		return;
+
+	entry = dma_entry_alloc();
+	if (!entry)
+		return;
+
+	entry->type		= dma_debug_resource;
+	entry->dev		= dev;
+	entry->pfn		= PHYS_PFN(addr);
+	entry->offset		= offset_in_page(addr);
+	entry->size		= size;
+	entry->dev_addr		= dma_addr;
+	entry->direction	= direction;
+	entry->map_err_type	= MAP_ERR_NOT_CHECKED;
+
+	add_dma_entry(entry);
+}
+
+void debug_dma_unmap_resource(struct device *dev, dma_addr_t dma_addr,
+			      size_t size, int direction)
+{
+	struct dma_debug_entry ref = {
+		.type           = dma_debug_resource,
+		.dev            = dev,
+		.dev_addr       = dma_addr,
+		.size           = size,
+		.direction      = direction,
+	};
+
+	if (unlikely(dma_debug_disabled()))
+		return;
+
+	check_unmap(&ref);
+}
+
+void debug_dma_sync_single_for_cpu(struct device *dev, dma_addr_t dma_handle,
+				   size_t size, int direction)
+{
+	struct dma_debug_entry ref;
+
+	if (unlikely(dma_debug_disabled()))
+		return;
+
+	ref.type         = dma_debug_single;
+	ref.dev          = dev;
+	ref.dev_addr     = dma_handle;
+	ref.size         = size;
+	ref.direction    = direction;
+	ref.sg_call_ents = 0;
+
+	check_sync(dev, &ref, true);
+}
+
+void debug_dma_sync_single_for_device(struct device *dev,
+				      dma_addr_t dma_handle, size_t size,
+				      int direction)
+{
+	struct dma_debug_entry ref;
+
+	if (unlikely(dma_debug_disabled()))
+		return;
+
+	ref.type         = dma_debug_single;
+	ref.dev          = dev;
+	ref.dev_addr     = dma_handle;
+	ref.size         = size;
+	ref.direction    = direction;
+	ref.sg_call_ents = 0;
+
+	check_sync(dev, &ref, false);
+}
+
+void debug_dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg,
+			       int nelems, int direction)
+{
+	struct scatterlist *s;
+	int mapped_ents = 0, i;
+
+	if (unlikely(dma_debug_disabled()))
+		return;
+
+	for_each_sg(sg, s, nelems, i) {
+
+		struct dma_debug_entry ref = {
+			.type           = dma_debug_sg,
+			.dev            = dev,
+			.pfn		= page_to_pfn(sg_page(s)),
+			.offset		= s->offset,
+			.dev_addr       = sg_dma_address(s),
+			.size           = sg_dma_len(s),
+			.direction      = direction,
+			.sg_call_ents   = nelems,
+		};
+
+		if (!i)
+			mapped_ents = get_nr_mapped_entries(dev, &ref);
+
+		if (i >= mapped_ents)
+			break;
+
+		check_sync(dev, &ref, true);
+	}
+}
+
+void debug_dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg,
+				  int nelems, int direction)
+{
+	struct scatterlist *s;
+	int mapped_ents = 0, i;
+
+	if (unlikely(dma_debug_disabled()))
+		return;
+
+	for_each_sg(sg, s, nelems, i) {
+
+		struct dma_debug_entry ref = {
+			.type           = dma_debug_sg,
+			.dev            = dev,
+			.pfn		= page_to_pfn(sg_page(s)),
+			.offset		= s->offset,
+			.dev_addr       = sg_dma_address(s),
+			.size           = sg_dma_len(s),
+			.direction      = direction,
+			.sg_call_ents   = nelems,
+		};
+		if (!i)
+			mapped_ents = get_nr_mapped_entries(dev, &ref);
+
+		if (i >= mapped_ents)
+			break;
+
+		check_sync(dev, &ref, false);
+	}
+}
+
+static int __init dma_debug_driver_setup(char *str)
+{
+	int i;
+
+	for (i = 0; i < NAME_MAX_LEN - 1; ++i, ++str) {
+		current_driver_name[i] = *str;
+		if (*str == 0)
+			break;
+	}
+
+	if (current_driver_name[0])
+		pr_info("enable driver filter for driver [%s]\n",
+			current_driver_name);
+
+
+	return 1;
+}
+__setup("dma_debug_driver=", dma_debug_driver_setup);
diff --git a/kernel/dma/debug.h b/kernel/dma/debug.h
new file mode 100644
index 000000000..83643b301
--- /dev/null
+++ b/kernel/dma/debug.h
@@ -0,0 +1,122 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2008 Advanced Micro Devices, Inc.
+ *
+ * Author: Joerg Roedel <joerg.roedel@amd.com>
+ */
+
+#ifndef _KERNEL_DMA_DEBUG_H
+#define _KERNEL_DMA_DEBUG_H
+
+#ifdef CONFIG_DMA_API_DEBUG
+extern void debug_dma_map_page(struct device *dev, struct page *page,
+			       size_t offset, size_t size,
+			       int direction, dma_addr_t dma_addr);
+
+extern void debug_dma_unmap_page(struct device *dev, dma_addr_t addr,
+				 size_t size, int direction);
+
+extern void debug_dma_map_sg(struct device *dev, struct scatterlist *sg,
+			     int nents, int mapped_ents, int direction);
+
+extern void debug_dma_unmap_sg(struct device *dev, struct scatterlist *sglist,
+			       int nelems, int dir);
+
+extern void debug_dma_alloc_coherent(struct device *dev, size_t size,
+				     dma_addr_t dma_addr, void *virt);
+
+extern void debug_dma_free_coherent(struct device *dev, size_t size,
+				    void *virt, dma_addr_t addr);
+
+extern void debug_dma_map_resource(struct device *dev, phys_addr_t addr,
+				   size_t size, int direction,
+				   dma_addr_t dma_addr);
+
+extern void debug_dma_unmap_resource(struct device *dev, dma_addr_t dma_addr,
+				     size_t size, int direction);
+
+extern void debug_dma_sync_single_for_cpu(struct device *dev,
+					  dma_addr_t dma_handle, size_t size,
+					  int direction);
+
+extern void debug_dma_sync_single_for_device(struct device *dev,
+					     dma_addr_t dma_handle,
+					     size_t size, int direction);
+
+extern void debug_dma_sync_sg_for_cpu(struct device *dev,
+				      struct scatterlist *sg,
+				      int nelems, int direction);
+
+extern void debug_dma_sync_sg_for_device(struct device *dev,
+					 struct scatterlist *sg,
+					 int nelems, int direction);
+#else /* CONFIG_DMA_API_DEBUG */
+static inline void debug_dma_map_page(struct device *dev, struct page *page,
+				      size_t offset, size_t size,
+				      int direction, dma_addr_t dma_addr)
+{
+}
+
+static inline void debug_dma_unmap_page(struct device *dev, dma_addr_t addr,
+					size_t size, int direction)
+{
+}
+
+static inline void debug_dma_map_sg(struct device *dev, struct scatterlist *sg,
+				    int nents, int mapped_ents, int direction)
+{
+}
+
+static inline void debug_dma_unmap_sg(struct device *dev,
+				      struct scatterlist *sglist,
+				      int nelems, int dir)
+{
+}
+
+static inline void debug_dma_alloc_coherent(struct device *dev, size_t size,
+					    dma_addr_t dma_addr, void *virt)
+{
+}
+
+static inline void debug_dma_free_coherent(struct device *dev, size_t size,
+					   void *virt, dma_addr_t addr)
+{
+}
+
+static inline void debug_dma_map_resource(struct device *dev, phys_addr_t addr,
+					  size_t size, int direction,
+					  dma_addr_t dma_addr)
+{
+}
+
+static inline void debug_dma_unmap_resource(struct device *dev,
+					    dma_addr_t dma_addr, size_t size,
+					    int direction)
+{
+}
+
+static inline void debug_dma_sync_single_for_cpu(struct device *dev,
+						 dma_addr_t dma_handle,
+						 size_t size, int direction)
+{
+}
+
+static inline void debug_dma_sync_single_for_device(struct device *dev,
+						    dma_addr_t dma_handle,
+						    size_t size, int direction)
+{
+}
+
+static inline void debug_dma_sync_sg_for_cpu(struct device *dev,
+					     struct scatterlist *sg,
+					     int nelems, int direction)
+{
+}
+
+static inline void debug_dma_sync_sg_for_device(struct device *dev,
+						struct scatterlist *sg,
+						int nelems, int direction)
+{
+}
+#endif /* CONFIG_DMA_API_DEBUG */
+#endif /* _KERNEL_DMA_DEBUG_H */
diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c
new file mode 100644
index 000000000..2922250f9
--- /dev/null
+++ b/kernel/dma/direct.c
@@ -0,0 +1,546 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2018-2020 Christoph Hellwig.
+ *
+ * DMA operations that map physical memory directly without using an IOMMU.
+ */
+#include <linux/memblock.h> /* for max_pfn */
+#include <linux/export.h>
+#include <linux/mm.h>
+#include <linux/dma-map-ops.h>
+#include <linux/scatterlist.h>
+#include <linux/pfn.h>
+#include <linux/vmalloc.h>
+#include <linux/set_memory.h>
+#include <linux/slab.h>
+#include "direct.h"
+
+/*
+ * Most architectures use ZONE_DMA for the first 16 Megabytes, but some use
+ * it for entirely different regions. In that case the arch code needs to
+ * override the variable below for dma-direct to work properly.
+ */
+unsigned int zone_dma_bits __ro_after_init = 24;
+
+static inline dma_addr_t phys_to_dma_direct(struct device *dev,
+		phys_addr_t phys)
+{
+	if (force_dma_unencrypted(dev))
+		return phys_to_dma_unencrypted(dev, phys);
+	return phys_to_dma(dev, phys);
+}
+
+static inline struct page *dma_direct_to_page(struct device *dev,
+		dma_addr_t dma_addr)
+{
+	return pfn_to_page(PHYS_PFN(dma_to_phys(dev, dma_addr)));
+}
+
+u64 dma_direct_get_required_mask(struct device *dev)
+{
+	phys_addr_t phys = (phys_addr_t)(max_pfn - 1) << PAGE_SHIFT;
+	u64 max_dma = phys_to_dma_direct(dev, phys);
+
+	return (1ULL << (fls64(max_dma) - 1)) * 2 - 1;
+}
+
+static gfp_t dma_direct_optimal_gfp_mask(struct device *dev, u64 dma_mask,
+				  u64 *phys_limit)
+{
+	u64 dma_limit = min_not_zero(dma_mask, dev->bus_dma_limit);
+
+	/*
+	 * Optimistically try the zone that the physical address mask falls
+	 * into first.  If that returns memory that isn't actually addressable
+	 * we will fallback to the next lower zone and try again.
+	 *
+	 * Note that GFP_DMA32 and GFP_DMA are no ops without the corresponding
+	 * zones.
+	 */
+	*phys_limit = dma_to_phys(dev, dma_limit);
+	if (*phys_limit <= DMA_BIT_MASK(zone_dma_bits))
+		return GFP_DMA;
+	if (*phys_limit <= DMA_BIT_MASK(32))
+		return GFP_DMA32;
+	return 0;
+}
+
+static bool dma_coherent_ok(struct device *dev, phys_addr_t phys, size_t size)
+{
+	dma_addr_t dma_addr = phys_to_dma_direct(dev, phys);
+
+	if (dma_addr == DMA_MAPPING_ERROR)
+		return false;
+	return dma_addr + size - 1 <=
+		min_not_zero(dev->coherent_dma_mask, dev->bus_dma_limit);
+}
+
+static struct page *__dma_direct_alloc_pages(struct device *dev, size_t size,
+		gfp_t gfp)
+{
+	int node = dev_to_node(dev);
+	struct page *page = NULL;
+	u64 phys_limit;
+
+	WARN_ON_ONCE(!PAGE_ALIGNED(size));
+
+	gfp |= dma_direct_optimal_gfp_mask(dev, dev->coherent_dma_mask,
+					   &phys_limit);
+	page = dma_alloc_contiguous(dev, size, gfp);
+	if (page && !dma_coherent_ok(dev, page_to_phys(page), size)) {
+		dma_free_contiguous(dev, page, size);
+		page = NULL;
+	}
+again:
+	if (!page)
+		page = alloc_pages_node(node, gfp, get_order(size));
+	if (page && !dma_coherent_ok(dev, page_to_phys(page), size)) {
+		dma_free_contiguous(dev, page, size);
+		page = NULL;
+
+		if (IS_ENABLED(CONFIG_ZONE_DMA32) &&
+		    phys_limit < DMA_BIT_MASK(64) &&
+		    !(gfp & (GFP_DMA32 | GFP_DMA))) {
+			gfp |= GFP_DMA32;
+			goto again;
+		}
+
+		if (IS_ENABLED(CONFIG_ZONE_DMA) && !(gfp & GFP_DMA)) {
+			gfp = (gfp & ~GFP_DMA32) | GFP_DMA;
+			goto again;
+		}
+	}
+
+	return page;
+}
+
+static void *dma_direct_alloc_from_pool(struct device *dev, size_t size,
+		dma_addr_t *dma_handle, gfp_t gfp)
+{
+	struct page *page;
+	u64 phys_mask;
+	void *ret;
+
+	gfp |= dma_direct_optimal_gfp_mask(dev, dev->coherent_dma_mask,
+					   &phys_mask);
+	page = dma_alloc_from_pool(dev, size, &ret, gfp, dma_coherent_ok);
+	if (!page)
+		return NULL;
+	*dma_handle = phys_to_dma_direct(dev, page_to_phys(page));
+	return ret;
+}
+
+void *dma_direct_alloc(struct device *dev, size_t size,
+		dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs)
+{
+	struct page *page;
+	void *ret;
+	int err;
+
+	size = PAGE_ALIGN(size);
+	if (attrs & DMA_ATTR_NO_WARN)
+		gfp |= __GFP_NOWARN;
+
+	if ((attrs & DMA_ATTR_NO_KERNEL_MAPPING) &&
+	    !force_dma_unencrypted(dev)) {
+		page = __dma_direct_alloc_pages(dev, size, gfp & ~__GFP_ZERO);
+		if (!page)
+			return NULL;
+		/* remove any dirty cache lines on the kernel alias */
+		if (!PageHighMem(page))
+			arch_dma_prep_coherent(page, size);
+		*dma_handle = phys_to_dma_direct(dev, page_to_phys(page));
+		/* return the page pointer as the opaque cookie */
+		return page;
+	}
+
+	if (!IS_ENABLED(CONFIG_ARCH_HAS_DMA_SET_UNCACHED) &&
+	    !IS_ENABLED(CONFIG_DMA_DIRECT_REMAP) &&
+	    !dev_is_dma_coherent(dev))
+		return arch_dma_alloc(dev, size, dma_handle, gfp, attrs);
+
+	/*
+	 * Remapping or decrypting memory may block. If either is required and
+	 * we can't block, allocate the memory from the atomic pools.
+	 */
+	if (IS_ENABLED(CONFIG_DMA_COHERENT_POOL) &&
+	    !gfpflags_allow_blocking(gfp) &&
+	    (force_dma_unencrypted(dev) ||
+	     (IS_ENABLED(CONFIG_DMA_DIRECT_REMAP) && !dev_is_dma_coherent(dev))))
+		return dma_direct_alloc_from_pool(dev, size, dma_handle, gfp);
+
+	/* we always manually zero the memory once we are done */
+	page = __dma_direct_alloc_pages(dev, size, gfp & ~__GFP_ZERO);
+	if (!page)
+		return NULL;
+
+	if ((IS_ENABLED(CONFIG_DMA_DIRECT_REMAP) &&
+	     !dev_is_dma_coherent(dev)) ||
+	    (IS_ENABLED(CONFIG_DMA_REMAP) && PageHighMem(page))) {
+		/* remove any dirty cache lines on the kernel alias */
+		arch_dma_prep_coherent(page, size);
+
+		/* create a coherent mapping */
+		ret = dma_common_contiguous_remap(page, size,
+				dma_pgprot(dev, PAGE_KERNEL, attrs),
+				__builtin_return_address(0));
+		if (!ret)
+			goto out_free_pages;
+		if (force_dma_unencrypted(dev)) {
+			err = set_memory_decrypted((unsigned long)ret,
+						   PFN_UP(size));
+			if (err)
+				goto out_free_pages;
+		}
+		memset(ret, 0, size);
+		goto done;
+	}
+
+	if (PageHighMem(page)) {
+		/*
+		 * Depending on the cma= arguments and per-arch setup
+		 * dma_alloc_contiguous could return highmem pages.
+		 * Without remapping there is no way to return them here,
+		 * so log an error and fail.
+		 */
+		dev_info(dev, "Rejecting highmem page from CMA.\n");
+		goto out_free_pages;
+	}
+
+	ret = page_address(page);
+	if (force_dma_unencrypted(dev)) {
+		err = set_memory_decrypted((unsigned long)ret,
+					   PFN_UP(size));
+		if (err)
+			goto out_free_pages;
+	}
+
+	memset(ret, 0, size);
+
+	if (IS_ENABLED(CONFIG_ARCH_HAS_DMA_SET_UNCACHED) &&
+	    !dev_is_dma_coherent(dev)) {
+		arch_dma_prep_coherent(page, size);
+		ret = arch_dma_set_uncached(ret, size);
+		if (IS_ERR(ret))
+			goto out_encrypt_pages;
+	}
+done:
+	*dma_handle = phys_to_dma_direct(dev, page_to_phys(page));
+	return ret;
+
+out_encrypt_pages:
+	if (force_dma_unencrypted(dev)) {
+		err = set_memory_encrypted((unsigned long)page_address(page),
+					   PFN_UP(size));
+		/* If memory cannot be re-encrypted, it must be leaked */
+		if (err)
+			return NULL;
+	}
+out_free_pages:
+	dma_free_contiguous(dev, page, size);
+	return NULL;
+}
+
+void dma_direct_free(struct device *dev, size_t size,
+		void *cpu_addr, dma_addr_t dma_addr, unsigned long attrs)
+{
+	if ((attrs & DMA_ATTR_NO_KERNEL_MAPPING) &&
+	    !force_dma_unencrypted(dev)) {
+		/* cpu_addr is a struct page cookie, not a kernel address */
+		dma_free_contiguous(dev, cpu_addr, size);
+		return;
+	}
+
+	if (!IS_ENABLED(CONFIG_ARCH_HAS_DMA_SET_UNCACHED) &&
+	    !IS_ENABLED(CONFIG_DMA_DIRECT_REMAP) &&
+	    !dev_is_dma_coherent(dev)) {
+		arch_dma_free(dev, size, cpu_addr, dma_addr, attrs);
+		return;
+	}
+
+	/* If cpu_addr is not from an atomic pool, dma_free_from_pool() fails */
+	if (IS_ENABLED(CONFIG_DMA_COHERENT_POOL) &&
+	    dma_free_from_pool(dev, cpu_addr, PAGE_ALIGN(size)))
+		return;
+
+	if (force_dma_unencrypted(dev))
+		set_memory_encrypted((unsigned long)cpu_addr, PFN_UP(size));
+
+	if (IS_ENABLED(CONFIG_DMA_REMAP) && is_vmalloc_addr(cpu_addr))
+		vunmap(cpu_addr);
+	else if (IS_ENABLED(CONFIG_ARCH_HAS_DMA_CLEAR_UNCACHED))
+		arch_dma_clear_uncached(cpu_addr, size);
+
+	dma_free_contiguous(dev, dma_direct_to_page(dev, dma_addr), size);
+}
+
+struct page *dma_direct_alloc_pages(struct device *dev, size_t size,
+		dma_addr_t *dma_handle, enum dma_data_direction dir, gfp_t gfp)
+{
+	struct page *page;
+	void *ret;
+
+	if (IS_ENABLED(CONFIG_DMA_COHERENT_POOL) &&
+	    force_dma_unencrypted(dev) && !gfpflags_allow_blocking(gfp))
+		return dma_direct_alloc_from_pool(dev, size, dma_handle, gfp);
+
+	page = __dma_direct_alloc_pages(dev, size, gfp);
+	if (!page)
+		return NULL;
+	if (PageHighMem(page)) {
+		/*
+		 * Depending on the cma= arguments and per-arch setup
+		 * dma_alloc_contiguous could return highmem pages.
+		 * Without remapping there is no way to return them here,
+		 * so log an error and fail.
+		 */
+		dev_info(dev, "Rejecting highmem page from CMA.\n");
+		goto out_free_pages;
+	}
+
+	ret = page_address(page);
+	if (force_dma_unencrypted(dev)) {
+		if (set_memory_decrypted((unsigned long)ret, PFN_UP(size)))
+			goto out_free_pages;
+	}
+	memset(ret, 0, size);
+	*dma_handle = phys_to_dma_direct(dev, page_to_phys(page));
+	return page;
+out_free_pages:
+	dma_free_contiguous(dev, page, size);
+	return NULL;
+}
+
+void dma_direct_free_pages(struct device *dev, size_t size,
+		struct page *page, dma_addr_t dma_addr,
+		enum dma_data_direction dir)
+{
+	void *vaddr = page_address(page);
+
+	/* If cpu_addr is not from an atomic pool, dma_free_from_pool() fails */
+	if (IS_ENABLED(CONFIG_DMA_COHERENT_POOL) &&
+	    dma_free_from_pool(dev, vaddr, size))
+		return;
+
+	if (force_dma_unencrypted(dev))
+		set_memory_encrypted((unsigned long)vaddr, PFN_UP(size));
+
+	dma_free_contiguous(dev, page, size);
+}
+
+#if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_DEVICE) || \
+    defined(CONFIG_SWIOTLB)
+void dma_direct_sync_sg_for_device(struct device *dev,
+		struct scatterlist *sgl, int nents, enum dma_data_direction dir)
+{
+	struct scatterlist *sg;
+	int i;
+
+	for_each_sg(sgl, sg, nents, i) {
+		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);
+
+		if (!dev_is_dma_coherent(dev))
+			arch_sync_dma_for_device(paddr, sg->length,
+					dir);
+	}
+}
+#endif
+
+#if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU) || \
+    defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU_ALL) || \
+    defined(CONFIG_SWIOTLB)
+void dma_direct_sync_sg_for_cpu(struct device *dev,
+		struct scatterlist *sgl, int nents, enum dma_data_direction dir)
+{
+	struct scatterlist *sg;
+	int i;
+
+	for_each_sg(sgl, sg, nents, i) {
+		phys_addr_t paddr = dma_to_phys(dev, sg_dma_address(sg));
+
+		if (!dev_is_dma_coherent(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);
+
+		if (dir == DMA_FROM_DEVICE)
+			arch_dma_mark_clean(paddr, sg->length);
+	}
+
+	if (!dev_is_dma_coherent(dev))
+		arch_sync_dma_for_cpu_all();
+}
+
+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);
+}
+#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 scatterlist *sg;
+
+	for_each_sg(sgl, sg, nents, i) {
+		sg->dma_address = dma_direct_map_page(dev, sg_page(sg),
+				sg->offset, sg->length, dir, attrs);
+		if (sg->dma_address == DMA_MAPPING_ERROR)
+			goto out_unmap;
+		sg_dma_len(sg) = sg->length;
+	}
+
+	return nents;
+
+out_unmap:
+	dma_direct_unmap_sg(dev, sgl, i, dir, attrs | DMA_ATTR_SKIP_CPU_SYNC);
+	return 0;
+}
+
+dma_addr_t dma_direct_map_resource(struct device *dev, phys_addr_t paddr,
+		size_t size, enum dma_data_direction dir, unsigned long attrs)
+{
+	dma_addr_t dma_addr = paddr;
+
+	if (unlikely(!dma_capable(dev, dma_addr, size, false))) {
+		dev_err_once(dev,
+			     "DMA addr %pad+%zu overflow (mask %llx, bus limit %llx).\n",
+			     &dma_addr, size, *dev->dma_mask, dev->bus_dma_limit);
+		WARN_ON_ONCE(1);
+		return DMA_MAPPING_ERROR;
+	}
+
+	return dma_addr;
+}
+
+int dma_direct_get_sgtable(struct device *dev, struct sg_table *sgt,
+		void *cpu_addr, dma_addr_t dma_addr, size_t size,
+		unsigned long attrs)
+{
+	struct page *page = dma_direct_to_page(dev, dma_addr);
+	int ret;
+
+	ret = sg_alloc_table(sgt, 1, GFP_KERNEL);
+	if (!ret)
+		sg_set_page(sgt->sgl, page, PAGE_ALIGN(size), 0);
+	return ret;
+}
+
+bool dma_direct_can_mmap(struct device *dev)
+{
+	return dev_is_dma_coherent(dev) ||
+		IS_ENABLED(CONFIG_DMA_NONCOHERENT_MMAP);
+}
+
+int dma_direct_mmap(struct device *dev, struct vm_area_struct *vma,
+		void *cpu_addr, dma_addr_t dma_addr, size_t size,
+		unsigned long attrs)
+{
+	unsigned long user_count = vma_pages(vma);
+	unsigned long count = PAGE_ALIGN(size) >> PAGE_SHIFT;
+	unsigned long pfn = PHYS_PFN(dma_to_phys(dev, dma_addr));
+	int ret = -ENXIO;
+
+	vma->vm_page_prot = dma_pgprot(dev, vma->vm_page_prot, attrs);
+
+	if (dma_mmap_from_dev_coherent(dev, vma, cpu_addr, size, &ret))
+		return ret;
+
+	if (vma->vm_pgoff >= count || user_count > count - vma->vm_pgoff)
+		return -ENXIO;
+	return remap_pfn_range(vma, vma->vm_start, pfn + vma->vm_pgoff,
+			user_count << PAGE_SHIFT, vma->vm_page_prot);
+}
+
+int dma_direct_supported(struct device *dev, u64 mask)
+{
+	u64 min_mask = (max_pfn - 1) << PAGE_SHIFT;
+
+	/*
+	 * Because 32-bit DMA masks are so common we expect every architecture
+	 * to be able to satisfy them - either by not supporting more physical
+	 * memory, or by providing a ZONE_DMA32.  If neither is the case, the
+	 * architecture needs to use an IOMMU instead of the direct mapping.
+	 */
+	if (mask >= DMA_BIT_MASK(32))
+		return 1;
+
+	/*
+	 * This check needs to be against the actual bit mask value, so use
+	 * phys_to_dma_unencrypted() here so that the SME encryption mask isn't
+	 * part of the check.
+	 */
+	if (IS_ENABLED(CONFIG_ZONE_DMA))
+		min_mask = min_t(u64, min_mask, DMA_BIT_MASK(zone_dma_bits));
+	return mask >= phys_to_dma_unencrypted(dev, min_mask);
+}
+
+size_t dma_direct_max_mapping_size(struct device *dev)
+{
+	/* If SWIOTLB is active, use its maximum mapping size */
+	if (is_swiotlb_active() &&
+	    (dma_addressing_limited(dev) || swiotlb_force == SWIOTLB_FORCE))
+		return swiotlb_max_mapping_size(dev);
+	return SIZE_MAX;
+}
+
+bool dma_direct_need_sync(struct device *dev, dma_addr_t dma_addr)
+{
+	return !dev_is_dma_coherent(dev) ||
+		is_swiotlb_buffer(dma_to_phys(dev, dma_addr));
+}
+
+/**
+ * dma_direct_set_offset - Assign scalar offset for a single DMA range.
+ * @dev:	device pointer; needed to "own" the alloced memory.
+ * @cpu_start:  beginning of memory region covered by this offset.
+ * @dma_start:  beginning of DMA/PCI region covered by this offset.
+ * @size:	size of the region.
+ *
+ * This is for the simple case of a uniform offset which cannot
+ * be discovered by "dma-ranges".
+ *
+ * It returns -ENOMEM if out of memory, -EINVAL if a map
+ * already exists, 0 otherwise.
+ *
+ * Note: any call to this from a driver is a bug.  The mapping needs
+ * to be described by the device tree or other firmware interfaces.
+ */
+int dma_direct_set_offset(struct device *dev, phys_addr_t cpu_start,
+			 dma_addr_t dma_start, u64 size)
+{
+	struct bus_dma_region *map;
+	u64 offset = (u64)cpu_start - (u64)dma_start;
+
+	if (dev->dma_range_map) {
+		dev_err(dev, "attempt to add DMA range to existing map\n");
+		return -EINVAL;
+	}
+
+	if (!offset)
+		return 0;
+
+	map = kcalloc(2, sizeof(*map), GFP_KERNEL);
+	if (!map)
+		return -ENOMEM;
+	map[0].cpu_start = cpu_start;
+	map[0].dma_start = dma_start;
+	map[0].offset = offset;
+	map[0].size = size;
+	dev->dma_range_map = map;
+	return 0;
+}
+EXPORT_SYMBOL_GPL(dma_direct_set_offset);
diff --git a/kernel/dma/direct.h b/kernel/dma/direct.h
new file mode 100644
index 000000000..c9d380318
--- /dev/null
+++ b/kernel/dma/direct.h
@@ -0,0 +1,120 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2018 Christoph Hellwig.
+ *
+ * DMA operations that map physical memory directly without using an IOMMU.
+ */
+#ifndef _KERNEL_DMA_DIRECT_H
+#define _KERNEL_DMA_DIRECT_H
+
+#include <linux/dma-direct.h>
+
+int dma_direct_get_sgtable(struct device *dev, struct sg_table *sgt,
+		void *cpu_addr, dma_addr_t dma_addr, size_t size,
+		unsigned long attrs);
+bool dma_direct_can_mmap(struct device *dev);
+int dma_direct_mmap(struct device *dev, struct vm_area_struct *vma,
+		void *cpu_addr, dma_addr_t dma_addr, size_t size,
+		unsigned long attrs);
+bool dma_direct_need_sync(struct device *dev, dma_addr_t dma_addr);
+int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl, int nents,
+		enum dma_data_direction dir, unsigned long attrs);
+size_t dma_direct_max_mapping_size(struct device *dev);
+
+#if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_DEVICE) || \
+    defined(CONFIG_SWIOTLB)
+void dma_direct_sync_sg_for_device(struct device *dev, struct scatterlist *sgl,
+		int nents, enum dma_data_direction dir);
+#else
+static inline void dma_direct_sync_sg_for_device(struct device *dev,
+		struct scatterlist *sgl, int nents, enum dma_data_direction dir)
+{
+}
+#endif
+
+#if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU) || \
+    defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU_ALL) || \
+    defined(CONFIG_SWIOTLB)
+void dma_direct_unmap_sg(struct device *dev, struct scatterlist *sgl,
+		int nents, enum dma_data_direction dir, unsigned long attrs);
+void dma_direct_sync_sg_for_cpu(struct device *dev,
+		struct scatterlist *sgl, int nents, enum dma_data_direction dir);
+#else
+static inline void dma_direct_unmap_sg(struct device *dev,
+		struct scatterlist *sgl, int nents, enum dma_data_direction dir,
+		unsigned long attrs)
+{
+}
+static inline void dma_direct_sync_sg_for_cpu(struct device *dev,
+		struct scatterlist *sgl, int nents, enum dma_data_direction dir)
+{
+}
+#endif
+
+static inline void dma_direct_sync_single_for_device(struct device *dev,
+		dma_addr_t addr, size_t size, enum dma_data_direction dir)
+{
+	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);
+
+	if (!dev_is_dma_coherent(dev))
+		arch_sync_dma_for_device(paddr, size, dir);
+}
+
+static inline void dma_direct_sync_single_for_cpu(struct device *dev,
+		dma_addr_t addr, size_t size, enum dma_data_direction dir)
+{
+	phys_addr_t paddr = dma_to_phys(dev, addr);
+
+	if (!dev_is_dma_coherent(dev)) {
+		arch_sync_dma_for_cpu(paddr, size, dir);
+		arch_sync_dma_for_cpu_all();
+	}
+
+	if (unlikely(is_swiotlb_buffer(paddr)))
+		swiotlb_tbl_sync_single(dev, paddr, size, dir, SYNC_FOR_CPU);
+
+	if (dir == DMA_FROM_DEVICE)
+		arch_dma_mark_clean(paddr, size);
+}
+
+static inline dma_addr_t dma_direct_map_page(struct device *dev,
+		struct page *page, unsigned long offset, size_t size,
+		enum dma_data_direction dir, unsigned long attrs)
+{
+	phys_addr_t phys = page_to_phys(page) + offset;
+	dma_addr_t dma_addr = phys_to_dma(dev, phys);
+
+	if (unlikely(swiotlb_force == SWIOTLB_FORCE))
+		return swiotlb_map(dev, phys, size, dir, attrs);
+
+	if (unlikely(!dma_capable(dev, dma_addr, size, true))) {
+		if (swiotlb_force != SWIOTLB_NO_FORCE)
+			return swiotlb_map(dev, phys, size, dir, attrs);
+
+		dev_WARN_ONCE(dev, 1,
+			     "DMA addr %pad+%zu overflow (mask %llx, bus limit %llx).\n",
+			     &dma_addr, size, *dev->dma_mask, dev->bus_dma_limit);
+		return DMA_MAPPING_ERROR;
+	}
+
+	if (!dev_is_dma_coherent(dev) && !(attrs & DMA_ATTR_SKIP_CPU_SYNC))
+		arch_sync_dma_for_device(phys, size, dir);
+	return dma_addr;
+}
+
+static inline void dma_direct_unmap_page(struct device *dev, dma_addr_t addr,
+		size_t size, enum dma_data_direction dir, unsigned long attrs)
+{
+	phys_addr_t phys = dma_to_phys(dev, addr);
+
+	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
+		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 | DMA_ATTR_SKIP_CPU_SYNC);
+}
+#endif /* _KERNEL_DMA_DIRECT_H */
diff --git a/kernel/dma/dummy.c b/kernel/dma/dummy.c
new file mode 100644
index 000000000..eacd4c5b1
--- /dev/null
+++ b/kernel/dma/dummy.c
@@ -0,0 +1,38 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Dummy DMA ops that always fail.
+ */
+#include <linux/dma-map-ops.h>
+
+static int dma_dummy_mmap(struct device *dev, struct vm_area_struct *vma,
+		void *cpu_addr, dma_addr_t dma_addr, size_t size,
+		unsigned long attrs)
+{
+	return -ENXIO;
+}
+
+static dma_addr_t dma_dummy_map_page(struct device *dev, struct page *page,
+		unsigned long offset, size_t size, enum dma_data_direction dir,
+		unsigned long attrs)
+{
+	return DMA_MAPPING_ERROR;
+}
+
+static int dma_dummy_map_sg(struct device *dev, struct scatterlist *sgl,
+		int nelems, enum dma_data_direction dir,
+		unsigned long attrs)
+{
+	return 0;
+}
+
+static int dma_dummy_supported(struct device *hwdev, u64 mask)
+{
+	return 0;
+}
+
+const struct dma_map_ops dma_dummy_ops = {
+	.mmap                   = dma_dummy_mmap,
+	.map_page               = dma_dummy_map_page,
+	.map_sg                 = dma_dummy_map_sg,
+	.dma_supported          = dma_dummy_supported,
+};
diff --git a/kernel/dma/mapping.c b/kernel/dma/mapping.c
new file mode 100644
index 000000000..51bb8fa8e
--- /dev/null
+++ b/kernel/dma/mapping.c
@@ -0,0 +1,644 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * arch-independent dma-mapping routines
+ *
+ * Copyright (c) 2006  SUSE Linux Products GmbH
+ * Copyright (c) 2006  Tejun Heo <teheo@suse.de>
+ */
+#include <linux/memblock.h> /* for max_pfn */
+#include <linux/acpi.h>
+#include <linux/dma-map-ops.h>
+#include <linux/export.h>
+#include <linux/gfp.h>
+#include <linux/of_device.h>
+#include <linux/slab.h>
+#include <linux/vmalloc.h>
+#include "debug.h"
+#include "direct.h"
+
+/*
+ * Managed DMA API
+ */
+struct dma_devres {
+	size_t		size;
+	void		*vaddr;
+	dma_addr_t	dma_handle;
+	unsigned long	attrs;
+};
+
+static void dmam_release(struct device *dev, void *res)
+{
+	struct dma_devres *this = res;
+
+	dma_free_attrs(dev, this->size, this->vaddr, this->dma_handle,
+			this->attrs);
+}
+
+static int dmam_match(struct device *dev, void *res, void *match_data)
+{
+	struct dma_devres *this = res, *match = match_data;
+
+	if (this->vaddr == match->vaddr) {
+		WARN_ON(this->size != match->size ||
+			this->dma_handle != match->dma_handle);
+		return 1;
+	}
+	return 0;
+}
+
+/**
+ * dmam_free_coherent - Managed dma_free_coherent()
+ * @dev: Device to free coherent memory for
+ * @size: Size of allocation
+ * @vaddr: Virtual address of the memory to free
+ * @dma_handle: DMA handle of the memory to free
+ *
+ * Managed dma_free_coherent().
+ */
+void dmam_free_coherent(struct device *dev, size_t size, void *vaddr,
+			dma_addr_t dma_handle)
+{
+	struct dma_devres match_data = { size, vaddr, dma_handle };
+
+	dma_free_coherent(dev, size, vaddr, dma_handle);
+	WARN_ON(devres_destroy(dev, dmam_release, dmam_match, &match_data));
+}
+EXPORT_SYMBOL(dmam_free_coherent);
+
+/**
+ * dmam_alloc_attrs - Managed dma_alloc_attrs()
+ * @dev: Device to allocate non_coherent memory for
+ * @size: Size of allocation
+ * @dma_handle: Out argument for allocated DMA handle
+ * @gfp: Allocation flags
+ * @attrs: Flags in the DMA_ATTR_* namespace.
+ *
+ * Managed dma_alloc_attrs().  Memory allocated using this function will be
+ * automatically released on driver detach.
+ *
+ * RETURNS:
+ * Pointer to allocated memory on success, NULL on failure.
+ */
+void *dmam_alloc_attrs(struct device *dev, size_t size, dma_addr_t *dma_handle,
+		gfp_t gfp, unsigned long attrs)
+{
+	struct dma_devres *dr;
+	void *vaddr;
+
+	dr = devres_alloc(dmam_release, sizeof(*dr), gfp);
+	if (!dr)
+		return NULL;
+
+	vaddr = dma_alloc_attrs(dev, size, dma_handle, gfp, attrs);
+	if (!vaddr) {
+		devres_free(dr);
+		return NULL;
+	}
+
+	dr->vaddr = vaddr;
+	dr->dma_handle = *dma_handle;
+	dr->size = size;
+	dr->attrs = attrs;
+
+	devres_add(dev, dr);
+
+	return vaddr;
+}
+EXPORT_SYMBOL(dmam_alloc_attrs);
+
+static bool dma_go_direct(struct device *dev, dma_addr_t mask,
+		const struct dma_map_ops *ops)
+{
+	if (likely(!ops))
+		return true;
+#ifdef CONFIG_DMA_OPS_BYPASS
+	if (dev->dma_ops_bypass)
+		return min_not_zero(mask, dev->bus_dma_limit) >=
+			    dma_direct_get_required_mask(dev);
+#endif
+	return false;
+}
+
+
+/*
+ * Check if the devices uses a direct mapping for streaming DMA operations.
+ * This allows IOMMU drivers to set a bypass mode if the DMA mask is large
+ * enough.
+ */
+static inline bool dma_alloc_direct(struct device *dev,
+		const struct dma_map_ops *ops)
+{
+	return dma_go_direct(dev, dev->coherent_dma_mask, ops);
+}
+
+static inline bool dma_map_direct(struct device *dev,
+		const struct dma_map_ops *ops)
+{
+	return dma_go_direct(dev, *dev->dma_mask, ops);
+}
+
+dma_addr_t dma_map_page_attrs(struct device *dev, struct page *page,
+		size_t offset, size_t size, enum dma_data_direction dir,
+		unsigned long attrs)
+{
+	const struct dma_map_ops *ops = get_dma_ops(dev);
+	dma_addr_t addr;
+
+	BUG_ON(!valid_dma_direction(dir));
+
+	if (WARN_ON_ONCE(!dev->dma_mask))
+		return DMA_MAPPING_ERROR;
+
+	if (dma_map_direct(dev, ops))
+		addr = dma_direct_map_page(dev, page, offset, size, dir, attrs);
+	else
+		addr = ops->map_page(dev, page, offset, size, dir, attrs);
+	debug_dma_map_page(dev, page, offset, size, dir, addr);
+
+	return addr;
+}
+EXPORT_SYMBOL(dma_map_page_attrs);
+
+void dma_unmap_page_attrs(struct device *dev, dma_addr_t addr, size_t size,
+		enum dma_data_direction dir, unsigned long attrs)
+{
+	const struct dma_map_ops *ops = get_dma_ops(dev);
+
+	BUG_ON(!valid_dma_direction(dir));
+	if (dma_map_direct(dev, ops))
+		dma_direct_unmap_page(dev, addr, size, dir, attrs);
+	else if (ops->unmap_page)
+		ops->unmap_page(dev, addr, size, dir, attrs);
+	debug_dma_unmap_page(dev, addr, size, dir);
+}
+EXPORT_SYMBOL(dma_unmap_page_attrs);
+
+/*
+ * dma_maps_sg_attrs returns 0 on error and > 0 on success.
+ * It should never return a value < 0.
+ */
+int dma_map_sg_attrs(struct device *dev, struct scatterlist *sg, int nents,
+		enum dma_data_direction dir, unsigned long attrs)
+{
+	const struct dma_map_ops *ops = get_dma_ops(dev);
+	int ents;
+
+	BUG_ON(!valid_dma_direction(dir));
+
+	if (WARN_ON_ONCE(!dev->dma_mask))
+		return 0;
+
+	if (dma_map_direct(dev, ops))
+		ents = dma_direct_map_sg(dev, sg, nents, dir, attrs);
+	else
+		ents = ops->map_sg(dev, sg, nents, dir, attrs);
+	BUG_ON(ents < 0);
+	debug_dma_map_sg(dev, sg, nents, ents, dir);
+
+	return ents;
+}
+EXPORT_SYMBOL(dma_map_sg_attrs);
+
+void dma_unmap_sg_attrs(struct device *dev, struct scatterlist *sg,
+				      int nents, enum dma_data_direction dir,
+				      unsigned long attrs)
+{
+	const struct dma_map_ops *ops = get_dma_ops(dev);
+
+	BUG_ON(!valid_dma_direction(dir));
+	debug_dma_unmap_sg(dev, sg, nents, dir);
+	if (dma_map_direct(dev, ops))
+		dma_direct_unmap_sg(dev, sg, nents, dir, attrs);
+	else if (ops->unmap_sg)
+		ops->unmap_sg(dev, sg, nents, dir, attrs);
+}
+EXPORT_SYMBOL(dma_unmap_sg_attrs);
+
+dma_addr_t dma_map_resource(struct device *dev, phys_addr_t phys_addr,
+		size_t size, enum dma_data_direction dir, unsigned long attrs)
+{
+	const struct dma_map_ops *ops = get_dma_ops(dev);
+	dma_addr_t addr = DMA_MAPPING_ERROR;
+
+	BUG_ON(!valid_dma_direction(dir));
+
+	if (WARN_ON_ONCE(!dev->dma_mask))
+		return DMA_MAPPING_ERROR;
+
+	/* Don't allow RAM to be mapped */
+	if (WARN_ON_ONCE(pfn_valid(PHYS_PFN(phys_addr))))
+		return DMA_MAPPING_ERROR;
+
+	if (dma_map_direct(dev, ops))
+		addr = dma_direct_map_resource(dev, phys_addr, size, dir, attrs);
+	else if (ops->map_resource)
+		addr = ops->map_resource(dev, phys_addr, size, dir, attrs);
+
+	debug_dma_map_resource(dev, phys_addr, size, dir, addr);
+	return addr;
+}
+EXPORT_SYMBOL(dma_map_resource);
+
+void dma_unmap_resource(struct device *dev, dma_addr_t addr, size_t size,
+		enum dma_data_direction dir, unsigned long attrs)
+{
+	const struct dma_map_ops *ops = get_dma_ops(dev);
+
+	BUG_ON(!valid_dma_direction(dir));
+	if (!dma_map_direct(dev, ops) && ops->unmap_resource)
+		ops->unmap_resource(dev, addr, size, dir, attrs);
+	debug_dma_unmap_resource(dev, addr, size, dir);
+}
+EXPORT_SYMBOL(dma_unmap_resource);
+
+void dma_sync_single_for_cpu(struct device *dev, dma_addr_t addr, size_t size,
+		enum dma_data_direction dir)
+{
+	const struct dma_map_ops *ops = get_dma_ops(dev);
+
+	BUG_ON(!valid_dma_direction(dir));
+	if (dma_map_direct(dev, ops))
+		dma_direct_sync_single_for_cpu(dev, addr, size, dir);
+	else if (ops->sync_single_for_cpu)
+		ops->sync_single_for_cpu(dev, addr, size, dir);
+	debug_dma_sync_single_for_cpu(dev, addr, size, dir);
+}
+EXPORT_SYMBOL(dma_sync_single_for_cpu);
+
+void dma_sync_single_for_device(struct device *dev, dma_addr_t addr,
+		size_t size, enum dma_data_direction dir)
+{
+	const struct dma_map_ops *ops = get_dma_ops(dev);
+
+	BUG_ON(!valid_dma_direction(dir));
+	if (dma_map_direct(dev, ops))
+		dma_direct_sync_single_for_device(dev, addr, size, dir);
+	else if (ops->sync_single_for_device)
+		ops->sync_single_for_device(dev, addr, size, dir);
+	debug_dma_sync_single_for_device(dev, addr, size, dir);
+}
+EXPORT_SYMBOL(dma_sync_single_for_device);
+
+void dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg,
+		    int nelems, enum dma_data_direction dir)
+{
+	const struct dma_map_ops *ops = get_dma_ops(dev);
+
+	BUG_ON(!valid_dma_direction(dir));
+	if (dma_map_direct(dev, ops))
+		dma_direct_sync_sg_for_cpu(dev, sg, nelems, dir);
+	else if (ops->sync_sg_for_cpu)
+		ops->sync_sg_for_cpu(dev, sg, nelems, dir);
+	debug_dma_sync_sg_for_cpu(dev, sg, nelems, dir);
+}
+EXPORT_SYMBOL(dma_sync_sg_for_cpu);
+
+void dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg,
+		       int nelems, enum dma_data_direction dir)
+{
+	const struct dma_map_ops *ops = get_dma_ops(dev);
+
+	BUG_ON(!valid_dma_direction(dir));
+	if (dma_map_direct(dev, ops))
+		dma_direct_sync_sg_for_device(dev, sg, nelems, dir);
+	else if (ops->sync_sg_for_device)
+		ops->sync_sg_for_device(dev, sg, nelems, dir);
+	debug_dma_sync_sg_for_device(dev, sg, nelems, dir);
+}
+EXPORT_SYMBOL(dma_sync_sg_for_device);
+
+/*
+ * The whole dma_get_sgtable() idea is fundamentally unsafe - it seems
+ * that the intention is to allow exporting memory allocated via the
+ * coherent DMA APIs through the dma_buf API, which only accepts a
+ * scattertable.  This presents a couple of problems:
+ * 1. Not all memory allocated via the coherent DMA APIs is backed by
+ *    a struct page
+ * 2. Passing coherent DMA memory into the streaming APIs is not allowed
+ *    as we will try to flush the memory through a different alias to that
+ *    actually being used (and the flushes are redundant.)
+ */
+int dma_get_sgtable_attrs(struct device *dev, struct sg_table *sgt,
+		void *cpu_addr, dma_addr_t dma_addr, size_t size,
+		unsigned long attrs)
+{
+	const struct dma_map_ops *ops = get_dma_ops(dev);
+
+	if (dma_alloc_direct(dev, ops))
+		return dma_direct_get_sgtable(dev, sgt, cpu_addr, dma_addr,
+				size, attrs);
+	if (!ops->get_sgtable)
+		return -ENXIO;
+	return ops->get_sgtable(dev, sgt, cpu_addr, dma_addr, size, attrs);
+}
+EXPORT_SYMBOL(dma_get_sgtable_attrs);
+
+#ifdef CONFIG_MMU
+/*
+ * Return the page attributes used for mapping dma_alloc_* memory, either in
+ * kernel space if remapping is needed, or to userspace through dma_mmap_*.
+ */
+pgprot_t dma_pgprot(struct device *dev, pgprot_t prot, unsigned long attrs)
+{
+	if (force_dma_unencrypted(dev))
+		prot = pgprot_decrypted(prot);
+	if (dev_is_dma_coherent(dev))
+		return prot;
+#ifdef CONFIG_ARCH_HAS_DMA_WRITE_COMBINE
+	if (attrs & DMA_ATTR_WRITE_COMBINE)
+		return pgprot_writecombine(prot);
+#endif
+	return pgprot_dmacoherent(prot);
+}
+#endif /* CONFIG_MMU */
+
+/**
+ * dma_can_mmap - check if a given device supports dma_mmap_*
+ * @dev: device to check
+ *
+ * Returns %true if @dev supports dma_mmap_coherent() and dma_mmap_attrs() to
+ * map DMA allocations to userspace.
+ */
+bool dma_can_mmap(struct device *dev)
+{
+	const struct dma_map_ops *ops = get_dma_ops(dev);
+
+	if (dma_alloc_direct(dev, ops))
+		return dma_direct_can_mmap(dev);
+	return ops->mmap != NULL;
+}
+EXPORT_SYMBOL_GPL(dma_can_mmap);
+
+/**
+ * dma_mmap_attrs - map a coherent DMA allocation into user space
+ * @dev: valid struct device pointer, or NULL for ISA and EISA-like devices
+ * @vma: vm_area_struct describing requested user mapping
+ * @cpu_addr: kernel CPU-view address returned from dma_alloc_attrs
+ * @dma_addr: device-view address returned from dma_alloc_attrs
+ * @size: size of memory originally requested in dma_alloc_attrs
+ * @attrs: attributes of mapping properties requested in dma_alloc_attrs
+ *
+ * Map a coherent DMA buffer previously allocated by dma_alloc_attrs into user
+ * space.  The coherent DMA buffer must not be freed by the driver until the
+ * user space mapping has been released.
+ */
+int dma_mmap_attrs(struct device *dev, struct vm_area_struct *vma,
+		void *cpu_addr, dma_addr_t dma_addr, size_t size,
+		unsigned long attrs)
+{
+	const struct dma_map_ops *ops = get_dma_ops(dev);
+
+	if (dma_alloc_direct(dev, ops))
+		return dma_direct_mmap(dev, vma, cpu_addr, dma_addr, size,
+				attrs);
+	if (!ops->mmap)
+		return -ENXIO;
+	return ops->mmap(dev, vma, cpu_addr, dma_addr, size, attrs);
+}
+EXPORT_SYMBOL(dma_mmap_attrs);
+
+u64 dma_get_required_mask(struct device *dev)
+{
+	const struct dma_map_ops *ops = get_dma_ops(dev);
+
+	if (dma_alloc_direct(dev, ops))
+		return dma_direct_get_required_mask(dev);
+	if (ops->get_required_mask)
+		return ops->get_required_mask(dev);
+
+	/*
+	 * We require every DMA ops implementation to at least support a 32-bit
+	 * DMA mask (and use bounce buffering if that isn't supported in
+	 * hardware).  As the direct mapping code has its own routine to
+	 * actually report an optimal mask we default to 32-bit here as that
+	 * is the right thing for most IOMMUs, and at least not actively
+	 * harmful in general.
+	 */
+	return DMA_BIT_MASK(32);
+}
+EXPORT_SYMBOL_GPL(dma_get_required_mask);
+
+void *dma_alloc_attrs(struct device *dev, size_t size, dma_addr_t *dma_handle,
+		gfp_t flag, unsigned long attrs)
+{
+	const struct dma_map_ops *ops = get_dma_ops(dev);
+	void *cpu_addr;
+
+	WARN_ON_ONCE(!dev->coherent_dma_mask);
+
+	if (dma_alloc_from_dev_coherent(dev, size, dma_handle, &cpu_addr))
+		return cpu_addr;
+
+	/* let the implementation decide on the zone to allocate from: */
+	flag &= ~(__GFP_DMA | __GFP_DMA32 | __GFP_HIGHMEM);
+
+	if (dma_alloc_direct(dev, ops))
+		cpu_addr = dma_direct_alloc(dev, size, dma_handle, flag, attrs);
+	else if (ops->alloc)
+		cpu_addr = ops->alloc(dev, size, dma_handle, flag, attrs);
+	else
+		return NULL;
+
+	debug_dma_alloc_coherent(dev, size, *dma_handle, cpu_addr);
+	return cpu_addr;
+}
+EXPORT_SYMBOL(dma_alloc_attrs);
+
+void dma_free_attrs(struct device *dev, size_t size, void *cpu_addr,
+		dma_addr_t dma_handle, unsigned long attrs)
+{
+	const struct dma_map_ops *ops = get_dma_ops(dev);
+
+	if (dma_release_from_dev_coherent(dev, get_order(size), cpu_addr))
+		return;
+	/*
+	 * On non-coherent platforms which implement DMA-coherent buffers via
+	 * non-cacheable remaps, ops->free() may call vunmap(). Thus getting
+	 * this far in IRQ context is a) at risk of a BUG_ON() or trying to
+	 * sleep on some machines, and b) an indication that the driver is
+	 * probably misusing the coherent API anyway.
+	 */
+	WARN_ON(irqs_disabled());
+
+	if (!cpu_addr)
+		return;
+
+	debug_dma_free_coherent(dev, size, cpu_addr, dma_handle);
+	if (dma_alloc_direct(dev, ops))
+		dma_direct_free(dev, size, cpu_addr, dma_handle, attrs);
+	else if (ops->free)
+		ops->free(dev, size, cpu_addr, dma_handle, attrs);
+}
+EXPORT_SYMBOL(dma_free_attrs);
+
+struct page *dma_alloc_pages(struct device *dev, size_t size,
+		dma_addr_t *dma_handle, enum dma_data_direction dir, gfp_t gfp)
+{
+	const struct dma_map_ops *ops = get_dma_ops(dev);
+	struct page *page;
+
+	if (WARN_ON_ONCE(!dev->coherent_dma_mask))
+		return NULL;
+	if (WARN_ON_ONCE(gfp & (__GFP_DMA | __GFP_DMA32 | __GFP_HIGHMEM)))
+		return NULL;
+
+	size = PAGE_ALIGN(size);
+	if (dma_alloc_direct(dev, ops))
+		page = dma_direct_alloc_pages(dev, size, dma_handle, dir, gfp);
+	else if (ops->alloc_pages)
+		page = ops->alloc_pages(dev, size, dma_handle, dir, gfp);
+	else
+		return NULL;
+
+	debug_dma_map_page(dev, page, 0, size, dir, *dma_handle);
+
+	return page;
+}
+EXPORT_SYMBOL_GPL(dma_alloc_pages);
+
+void dma_free_pages(struct device *dev, size_t size, struct page *page,
+		dma_addr_t dma_handle, enum dma_data_direction dir)
+{
+	const struct dma_map_ops *ops = get_dma_ops(dev);
+
+	size = PAGE_ALIGN(size);
+	debug_dma_unmap_page(dev, dma_handle, size, dir);
+
+	if (dma_alloc_direct(dev, ops))
+		dma_direct_free_pages(dev, size, page, dma_handle, dir);
+	else if (ops->free_pages)
+		ops->free_pages(dev, size, page, dma_handle, dir);
+}
+EXPORT_SYMBOL_GPL(dma_free_pages);
+
+void *dma_alloc_noncoherent(struct device *dev, size_t size,
+		dma_addr_t *dma_handle, enum dma_data_direction dir, gfp_t gfp)
+{
+	const struct dma_map_ops *ops = get_dma_ops(dev);
+	void *vaddr;
+
+	if (!ops || !ops->alloc_noncoherent) {
+		struct page *page;
+
+		page = dma_alloc_pages(dev, size, dma_handle, dir, gfp);
+		if (!page)
+			return NULL;
+		return page_address(page);
+	}
+
+	size = PAGE_ALIGN(size);
+	vaddr = ops->alloc_noncoherent(dev, size, dma_handle, dir, gfp);
+	if (vaddr)
+		debug_dma_map_page(dev, virt_to_page(vaddr), 0, size, dir,
+				   *dma_handle);
+	return vaddr;
+}
+EXPORT_SYMBOL_GPL(dma_alloc_noncoherent);
+
+void dma_free_noncoherent(struct device *dev, size_t size, void *vaddr,
+		dma_addr_t dma_handle, enum dma_data_direction dir)
+{
+	const struct dma_map_ops *ops = get_dma_ops(dev);
+
+	if (!ops || !ops->free_noncoherent) {
+		dma_free_pages(dev, size, virt_to_page(vaddr), dma_handle, dir);
+		return;
+	}
+
+	size = PAGE_ALIGN(size);
+	debug_dma_unmap_page(dev, dma_handle, size, dir);
+	ops->free_noncoherent(dev, size, vaddr, dma_handle, dir);
+}
+EXPORT_SYMBOL_GPL(dma_free_noncoherent);
+
+int dma_supported(struct device *dev, u64 mask)
+{
+	const struct dma_map_ops *ops = get_dma_ops(dev);
+
+	/*
+	 * ->dma_supported sets the bypass flag, so we must always call
+	 * into the method here unless the device is truly direct mapped.
+	 */
+	if (!ops)
+		return dma_direct_supported(dev, mask);
+	if (!ops->dma_supported)
+		return 1;
+	return ops->dma_supported(dev, mask);
+}
+EXPORT_SYMBOL(dma_supported);
+
+#ifdef CONFIG_ARCH_HAS_DMA_SET_MASK
+void arch_dma_set_mask(struct device *dev, u64 mask);
+#else
+#define arch_dma_set_mask(dev, mask)	do { } while (0)
+#endif
+
+int dma_set_mask(struct device *dev, u64 mask)
+{
+	/*
+	 * Truncate the mask to the actually supported dma_addr_t width to
+	 * avoid generating unsupportable addresses.
+	 */
+	mask = (dma_addr_t)mask;
+
+	if (!dev->dma_mask || !dma_supported(dev, mask))
+		return -EIO;
+
+	arch_dma_set_mask(dev, mask);
+	*dev->dma_mask = mask;
+	return 0;
+}
+EXPORT_SYMBOL(dma_set_mask);
+
+#ifndef CONFIG_ARCH_HAS_DMA_SET_COHERENT_MASK
+int dma_set_coherent_mask(struct device *dev, u64 mask)
+{
+	/*
+	 * Truncate the mask to the actually supported dma_addr_t width to
+	 * avoid generating unsupportable addresses.
+	 */
+	mask = (dma_addr_t)mask;
+
+	if (!dma_supported(dev, mask))
+		return -EIO;
+
+	dev->coherent_dma_mask = mask;
+	return 0;
+}
+EXPORT_SYMBOL(dma_set_coherent_mask);
+#endif
+
+size_t dma_max_mapping_size(struct device *dev)
+{
+	const struct dma_map_ops *ops = get_dma_ops(dev);
+	size_t size = SIZE_MAX;
+
+	if (dma_map_direct(dev, ops))
+		size = dma_direct_max_mapping_size(dev);
+	else if (ops && ops->max_mapping_size)
+		size = ops->max_mapping_size(dev);
+
+	return size;
+}
+EXPORT_SYMBOL_GPL(dma_max_mapping_size);
+
+bool dma_need_sync(struct device *dev, dma_addr_t dma_addr)
+{
+	const struct dma_map_ops *ops = get_dma_ops(dev);
+
+	if (dma_map_direct(dev, ops))
+		return dma_direct_need_sync(dev, dma_addr);
+	return ops->sync_single_for_cpu || ops->sync_single_for_device;
+}
+EXPORT_SYMBOL_GPL(dma_need_sync);
+
+unsigned long dma_get_merge_boundary(struct device *dev)
+{
+	const struct dma_map_ops *ops = get_dma_ops(dev);
+
+	if (!ops || !ops->get_merge_boundary)
+		return 0;	/* can't merge */
+
+	return ops->get_merge_boundary(dev);
+}
+EXPORT_SYMBOL_GPL(dma_get_merge_boundary);
diff --git a/kernel/dma/ops_helpers.c b/kernel/dma/ops_helpers.c
new file mode 100644
index 000000000..af4a6ef48
--- /dev/null
+++ b/kernel/dma/ops_helpers.c
@@ -0,0 +1,93 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Helpers for DMA ops implementations.  These generally rely on the fact that
+ * the allocated memory contains normal pages in the direct kernel mapping.
+ */
+#include <linux/dma-map-ops.h>
+
+static struct page *dma_common_vaddr_to_page(void *cpu_addr)
+{
+	if (is_vmalloc_addr(cpu_addr))
+		return vmalloc_to_page(cpu_addr);
+	return virt_to_page(cpu_addr);
+}
+
+/*
+ * Create scatter-list for the already allocated DMA buffer.
+ */
+int dma_common_get_sgtable(struct device *dev, struct sg_table *sgt,
+		 void *cpu_addr, dma_addr_t dma_addr, size_t size,
+		 unsigned long attrs)
+{
+	struct page *page = dma_common_vaddr_to_page(cpu_addr);
+	int ret;
+
+	ret = sg_alloc_table(sgt, 1, GFP_KERNEL);
+	if (!ret)
+		sg_set_page(sgt->sgl, page, PAGE_ALIGN(size), 0);
+	return ret;
+}
+
+/*
+ * Create userspace mapping for the DMA-coherent memory.
+ */
+int dma_common_mmap(struct device *dev, struct vm_area_struct *vma,
+		void *cpu_addr, dma_addr_t dma_addr, size_t size,
+		unsigned long attrs)
+{
+#ifdef CONFIG_MMU
+	unsigned long user_count = vma_pages(vma);
+	unsigned long count = PAGE_ALIGN(size) >> PAGE_SHIFT;
+	unsigned long off = vma->vm_pgoff;
+	struct page *page = dma_common_vaddr_to_page(cpu_addr);
+	int ret = -ENXIO;
+
+	vma->vm_page_prot = dma_pgprot(dev, vma->vm_page_prot, attrs);
+
+	if (dma_mmap_from_dev_coherent(dev, vma, cpu_addr, size, &ret))
+		return ret;
+
+	if (off >= count || user_count > count - off)
+		return -ENXIO;
+
+	return remap_pfn_range(vma, vma->vm_start,
+			page_to_pfn(page) + vma->vm_pgoff,
+			user_count << PAGE_SHIFT, vma->vm_page_prot);
+#else
+	return -ENXIO;
+#endif /* CONFIG_MMU */
+}
+
+struct page *dma_common_alloc_pages(struct device *dev, size_t size,
+		dma_addr_t *dma_handle, enum dma_data_direction dir, gfp_t gfp)
+{
+	const struct dma_map_ops *ops = get_dma_ops(dev);
+	struct page *page;
+
+	page = dma_alloc_contiguous(dev, size, gfp);
+	if (!page)
+		page = alloc_pages_node(dev_to_node(dev), gfp, get_order(size));
+	if (!page)
+		return NULL;
+
+	*dma_handle = ops->map_page(dev, page, 0, size, dir,
+				    DMA_ATTR_SKIP_CPU_SYNC);
+	if (*dma_handle == DMA_MAPPING_ERROR) {
+		dma_free_contiguous(dev, page, size);
+		return NULL;
+	}
+
+	memset(page_address(page), 0, size);
+	return page;
+}
+
+void dma_common_free_pages(struct device *dev, size_t size, struct page *page,
+		dma_addr_t dma_handle, enum dma_data_direction dir)
+{
+	const struct dma_map_ops *ops = get_dma_ops(dev);
+
+	if (ops->unmap_page)
+		ops->unmap_page(dev, dma_handle, size, dir,
+				DMA_ATTR_SKIP_CPU_SYNC);
+	dma_free_contiguous(dev, page, size);
+}
diff --git a/kernel/dma/pool.c b/kernel/dma/pool.c
new file mode 100644
index 000000000..b9082b572
--- /dev/null
+++ b/kernel/dma/pool.c
@@ -0,0 +1,298 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2012 ARM Ltd.
+ * Copyright (C) 2020 Google LLC
+ */
+#include <linux/cma.h>
+#include <linux/debugfs.h>
+#include <linux/dma-map-ops.h>
+#include <linux/dma-direct.h>
+#include <linux/init.h>
+#include <linux/genalloc.h>
+#include <linux/set_memory.h>
+#include <linux/slab.h>
+#include <linux/workqueue.h>
+
+static struct gen_pool *atomic_pool_dma __ro_after_init;
+static unsigned long pool_size_dma;
+static struct gen_pool *atomic_pool_dma32 __ro_after_init;
+static unsigned long pool_size_dma32;
+static struct gen_pool *atomic_pool_kernel __ro_after_init;
+static unsigned long pool_size_kernel;
+
+/* Size can be defined by the coherent_pool command line */
+static size_t atomic_pool_size;
+
+/* Dynamic background expansion when the atomic pool is near capacity */
+static struct work_struct atomic_pool_work;
+
+static int __init early_coherent_pool(char *p)
+{
+	atomic_pool_size = memparse(p, &p);
+	return 0;
+}
+early_param("coherent_pool", early_coherent_pool);
+
+static void __init dma_atomic_pool_debugfs_init(void)
+{
+	struct dentry *root;
+
+	root = debugfs_create_dir("dma_pools", NULL);
+	if (IS_ERR_OR_NULL(root))
+		return;
+
+	debugfs_create_ulong("pool_size_dma", 0400, root, &pool_size_dma);
+	debugfs_create_ulong("pool_size_dma32", 0400, root, &pool_size_dma32);
+	debugfs_create_ulong("pool_size_kernel", 0400, root, &pool_size_kernel);
+}
+
+static void dma_atomic_pool_size_add(gfp_t gfp, size_t size)
+{
+	if (gfp & __GFP_DMA)
+		pool_size_dma += size;
+	else if (gfp & __GFP_DMA32)
+		pool_size_dma32 += size;
+	else
+		pool_size_kernel += size;
+}
+
+static bool cma_in_zone(gfp_t gfp)
+{
+	unsigned long size;
+	phys_addr_t end;
+	struct cma *cma;
+
+	cma = dev_get_cma_area(NULL);
+	if (!cma)
+		return false;
+
+	size = cma_get_size(cma);
+	if (!size)
+		return false;
+
+	/* CMA can't cross zone boundaries, see cma_activate_area() */
+	end = cma_get_base(cma) + size - 1;
+	if (IS_ENABLED(CONFIG_ZONE_DMA) && (gfp & GFP_DMA))
+		return end <= DMA_BIT_MASK(zone_dma_bits);
+	if (IS_ENABLED(CONFIG_ZONE_DMA32) && (gfp & GFP_DMA32))
+		return end <= DMA_BIT_MASK(32);
+	return true;
+}
+
+static int atomic_pool_expand(struct gen_pool *pool, size_t pool_size,
+			      gfp_t gfp)
+{
+	unsigned int order;
+	struct page *page = NULL;
+	void *addr;
+	int ret = -ENOMEM;
+
+	/* Cannot allocate larger than MAX_ORDER-1 */
+	order = min(get_order(pool_size), MAX_ORDER-1);
+
+	do {
+		pool_size = 1 << (PAGE_SHIFT + order);
+		if (cma_in_zone(gfp))
+			page = dma_alloc_from_contiguous(NULL, 1 << order,
+							 order, false);
+		if (!page)
+			page = alloc_pages(gfp, order);
+	} while (!page && order-- > 0);
+	if (!page)
+		goto out;
+
+	arch_dma_prep_coherent(page, pool_size);
+
+#ifdef CONFIG_DMA_DIRECT_REMAP
+	addr = dma_common_contiguous_remap(page, pool_size,
+					   pgprot_dmacoherent(PAGE_KERNEL),
+					   __builtin_return_address(0));
+	if (!addr)
+		goto free_page;
+#else
+	addr = page_to_virt(page);
+#endif
+	/*
+	 * Memory in the atomic DMA pools must be unencrypted, the pools do not
+	 * shrink so no re-encryption occurs in dma_direct_free().
+	 */
+	ret = set_memory_decrypted((unsigned long)page_to_virt(page),
+				   1 << order);
+	if (ret)
+		goto remove_mapping;
+	ret = gen_pool_add_virt(pool, (unsigned long)addr, page_to_phys(page),
+				pool_size, NUMA_NO_NODE);
+	if (ret)
+		goto encrypt_mapping;
+
+	dma_atomic_pool_size_add(gfp, pool_size);
+	return 0;
+
+encrypt_mapping:
+	ret = set_memory_encrypted((unsigned long)page_to_virt(page),
+				   1 << order);
+	if (WARN_ON_ONCE(ret)) {
+		/* Decrypt succeeded but encrypt failed, purposely leak */
+		goto out;
+	}
+remove_mapping:
+#ifdef CONFIG_DMA_DIRECT_REMAP
+	dma_common_free_remap(addr, pool_size);
+#endif
+free_page: __maybe_unused
+	__free_pages(page, order);
+out:
+	return ret;
+}
+
+static void atomic_pool_resize(struct gen_pool *pool, gfp_t gfp)
+{
+	if (pool && gen_pool_avail(pool) < atomic_pool_size)
+		atomic_pool_expand(pool, gen_pool_size(pool), gfp);
+}
+
+static void atomic_pool_work_fn(struct work_struct *work)
+{
+	if (IS_ENABLED(CONFIG_ZONE_DMA))
+		atomic_pool_resize(atomic_pool_dma,
+				   GFP_KERNEL | GFP_DMA);
+	if (IS_ENABLED(CONFIG_ZONE_DMA32))
+		atomic_pool_resize(atomic_pool_dma32,
+				   GFP_KERNEL | GFP_DMA32);
+	atomic_pool_resize(atomic_pool_kernel, GFP_KERNEL);
+}
+
+static __init struct gen_pool *__dma_atomic_pool_init(size_t pool_size,
+						      gfp_t gfp)
+{
+	struct gen_pool *pool;
+	int ret;
+
+	pool = gen_pool_create(PAGE_SHIFT, NUMA_NO_NODE);
+	if (!pool)
+		return NULL;
+
+	gen_pool_set_algo(pool, gen_pool_first_fit_order_align, NULL);
+
+	ret = atomic_pool_expand(pool, pool_size, gfp);
+	if (ret) {
+		gen_pool_destroy(pool);
+		pr_err("DMA: failed to allocate %zu KiB %pGg pool for atomic allocation\n",
+		       pool_size >> 10, &gfp);
+		return NULL;
+	}
+
+	pr_info("DMA: preallocated %zu KiB %pGg pool for atomic allocations\n",
+		gen_pool_size(pool) >> 10, &gfp);
+	return pool;
+}
+
+static int __init dma_atomic_pool_init(void)
+{
+	int ret = 0;
+
+	/*
+	 * If coherent_pool was not used on the command line, default the pool
+	 * sizes to 128KB per 1GB of memory, min 128KB, max MAX_ORDER-1.
+	 */
+	if (!atomic_pool_size) {
+		unsigned long pages = totalram_pages() / (SZ_1G / SZ_128K);
+		pages = min_t(unsigned long, pages, MAX_ORDER_NR_PAGES);
+		atomic_pool_size = max_t(size_t, pages << PAGE_SHIFT, SZ_128K);
+	}
+	INIT_WORK(&atomic_pool_work, atomic_pool_work_fn);
+
+	atomic_pool_kernel = __dma_atomic_pool_init(atomic_pool_size,
+						    GFP_KERNEL);
+	if (!atomic_pool_kernel)
+		ret = -ENOMEM;
+	if (has_managed_dma()) {
+		atomic_pool_dma = __dma_atomic_pool_init(atomic_pool_size,
+						GFP_KERNEL | GFP_DMA);
+		if (!atomic_pool_dma)
+			ret = -ENOMEM;
+	}
+	if (IS_ENABLED(CONFIG_ZONE_DMA32)) {
+		atomic_pool_dma32 = __dma_atomic_pool_init(atomic_pool_size,
+						GFP_KERNEL | GFP_DMA32);
+		if (!atomic_pool_dma32)
+			ret = -ENOMEM;
+	}
+
+	dma_atomic_pool_debugfs_init();
+	return ret;
+}
+postcore_initcall(dma_atomic_pool_init);
+
+static inline struct gen_pool *dma_guess_pool(struct gen_pool *prev, gfp_t gfp)
+{
+	if (prev == NULL) {
+		if (IS_ENABLED(CONFIG_ZONE_DMA32) && (gfp & GFP_DMA32))
+			return atomic_pool_dma32;
+		if (atomic_pool_dma && (gfp & GFP_DMA))
+			return atomic_pool_dma;
+		return atomic_pool_kernel;
+	}
+	if (prev == atomic_pool_kernel)
+		return atomic_pool_dma32 ? atomic_pool_dma32 : atomic_pool_dma;
+	if (prev == atomic_pool_dma32)
+		return atomic_pool_dma;
+	return NULL;
+}
+
+static struct page *__dma_alloc_from_pool(struct device *dev, size_t size,
+		struct gen_pool *pool, void **cpu_addr,
+		bool (*phys_addr_ok)(struct device *, phys_addr_t, size_t))
+{
+	unsigned long addr;
+	phys_addr_t phys;
+
+	addr = gen_pool_alloc(pool, size);
+	if (!addr)
+		return NULL;
+
+	phys = gen_pool_virt_to_phys(pool, addr);
+	if (phys_addr_ok && !phys_addr_ok(dev, phys, size)) {
+		gen_pool_free(pool, addr, size);
+		return NULL;
+	}
+
+	if (gen_pool_avail(pool) < atomic_pool_size)
+		schedule_work(&atomic_pool_work);
+
+	*cpu_addr = (void *)addr;
+	memset(*cpu_addr, 0, size);
+	return pfn_to_page(__phys_to_pfn(phys));
+}
+
+struct page *dma_alloc_from_pool(struct device *dev, size_t size,
+		void **cpu_addr, gfp_t gfp,
+		bool (*phys_addr_ok)(struct device *, phys_addr_t, size_t))
+{
+	struct gen_pool *pool = NULL;
+	struct page *page;
+
+	while ((pool = dma_guess_pool(pool, gfp))) {
+		page = __dma_alloc_from_pool(dev, size, pool, cpu_addr,
+					     phys_addr_ok);
+		if (page)
+			return page;
+	}
+
+	WARN(1, "Failed to get suitable pool for %s\n", dev_name(dev));
+	return NULL;
+}
+
+bool dma_free_from_pool(struct device *dev, void *start, size_t size)
+{
+	struct gen_pool *pool = NULL;
+
+	while ((pool = dma_guess_pool(pool, 0))) {
+		if (!gen_pool_has_addr(pool, (unsigned long)start, size))
+			continue;
+		gen_pool_free(pool, (unsigned long)start, size);
+		return true;
+	}
+
+	return false;
+}
diff --git a/kernel/dma/remap.c b/kernel/dma/remap.c
new file mode 100644
index 000000000..5bff06199
--- /dev/null
+++ b/kernel/dma/remap.c
@@ -0,0 +1,71 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2014 The Linux Foundation
+ */
+#include <linux/dma-map-ops.h>
+#include <linux/slab.h>
+#include <linux/vmalloc.h>
+
+struct page **dma_common_find_pages(void *cpu_addr)
+{
+	struct vm_struct *area = find_vm_area(cpu_addr);
+
+	if (!area || area->flags != VM_DMA_COHERENT)
+		return NULL;
+	return area->pages;
+}
+
+/*
+ * Remaps an array of PAGE_SIZE pages into another vm_area.
+ * Cannot be used in non-sleeping contexts
+ */
+void *dma_common_pages_remap(struct page **pages, size_t size,
+			 pgprot_t prot, const void *caller)
+{
+	void *vaddr;
+
+	vaddr = vmap(pages, PAGE_ALIGN(size) >> PAGE_SHIFT,
+		     VM_DMA_COHERENT, prot);
+	if (vaddr)
+		find_vm_area(vaddr)->pages = pages;
+	return vaddr;
+}
+
+/*
+ * Remaps an allocated contiguous region into another vm_area.
+ * Cannot be used in non-sleeping contexts
+ */
+void *dma_common_contiguous_remap(struct page *page, size_t size,
+			pgprot_t prot, const void *caller)
+{
+	int count = PAGE_ALIGN(size) >> PAGE_SHIFT;
+	struct page **pages;
+	void *vaddr;
+	int i;
+
+	pages = kvmalloc_array(count, sizeof(struct page *), GFP_KERNEL);
+	if (!pages)
+		return NULL;
+	for (i = 0; i < count; i++)
+		pages[i] = nth_page(page, i);
+	vaddr = vmap(pages, count, VM_DMA_COHERENT, prot);
+	kvfree(pages);
+
+	return vaddr;
+}
+
+/*
+ * Unmaps a range previously mapped by dma_common_*_remap
+ */
+void dma_common_free_remap(void *cpu_addr, size_t size)
+{
+	struct vm_struct *area = find_vm_area(cpu_addr);
+
+	if (!area || area->flags != VM_DMA_COHERENT) {
+		WARN(1, "trying to free invalid coherent area: %p\n", cpu_addr);
+		return;
+	}
+
+	unmap_kernel_range((unsigned long)cpu_addr, PAGE_ALIGN(size));
+	vunmap(cpu_addr);
+}
diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c
new file mode 100644
index 000000000..d897d1613
--- /dev/null
+++ b/kernel/dma/swiotlb.c
@@ -0,0 +1,774 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Dynamic DMA mapping support.
+ *
+ * This implementation is a fallback for platforms that do not support
+ * I/O TLBs (aka DMA address translation hardware).
+ * Copyright (C) 2000 Asit Mallick <Asit.K.Mallick@intel.com>
+ * Copyright (C) 2000 Goutham Rao <goutham.rao@intel.com>
+ * Copyright (C) 2000, 2003 Hewlett-Packard Co
+ *	David Mosberger-Tang <davidm@hpl.hp.com>
+ *
+ * 03/05/07 davidm	Switch from PCI-DMA to generic device DMA API.
+ * 00/12/13 davidm	Rename to swiotlb.c and add mark_clean() to avoid
+ *			unnecessary i-cache flushing.
+ * 04/07/.. ak		Better overflow handling. Assorted fixes.
+ * 05/09/10 linville	Add support for syncing ranges, support syncing for
+ *			DMA_BIDIRECTIONAL mappings, miscellaneous cleanup.
+ * 08/12/11 beckyb	Add highmem support
+ */
+
+#define pr_fmt(fmt) "software IO TLB: " fmt
+
+#include <linux/cache.h>
+#include <linux/dma-direct.h>
+#include <linux/dma-map-ops.h>
+#include <linux/mm.h>
+#include <linux/export.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/mem_encrypt.h>
+#include <linux/set_memory.h>
+#ifdef CONFIG_DEBUG_FS
+#include <linux/debugfs.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>
+
+#define SLABS_PER_PAGE (1 << (PAGE_SHIFT - IO_TLB_SHIFT))
+
+/*
+ * Minimum IO TLB size to bother booting with.  Systems with mainly
+ * 64bit capable cards will only lightly use the swiotlb.  If we can't
+ * allocate a contiguous 1MB, we're probably in trouble anyway.
+ */
+#define IO_TLB_MIN_SLABS ((1<<20) >> IO_TLB_SHIFT)
+
+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;
+
+/*
+ * Max segment that we can provide which (if pages are contingous) will
+ * not be bounced (unless SWIOTLB_FORCE is set).
+ */
+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;
+
+/*
+ * Protect the above data structures in the map and unmap calls
+ */
+static DEFINE_SPINLOCK(io_tlb_lock);
+
+static int late_alloc;
+
+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);
+	}
+	if (*str == ',')
+		++str;
+	if (!strcmp(str, "force")) {
+		swiotlb_force = SWIOTLB_FORCE;
+	} 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;
+}
+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);
+}
+
+/* default to 64MB */
+#define IO_TLB_DEFAULT_SIZE (64UL<<20)
+unsigned long swiotlb_size_or_default(void)
+{
+	unsigned long size;
+
+	size = io_tlb_nslabs << IO_TLB_SHIFT;
+
+	return size ? size : (IO_TLB_DEFAULT_SIZE);
+}
+
+void swiotlb_print_info(void)
+{
+	unsigned long bytes = io_tlb_nslabs << IO_TLB_SHIFT;
+
+	if (no_iotlb_memory) {
+		pr_warn("No low mem\n");
+		return;
+	}
+
+	pr_info("mapped [mem %pa-%pa] (%luMB)\n", &io_tlb_start, &io_tlb_end,
+	       bytes >> 20);
+}
+
+static inline unsigned long io_tlb_offset(unsigned long val)
+{
+	return val & (IO_TLB_SEGSIZE - 1);
+}
+
+static inline unsigned long nr_slots(u64 val)
+{
+	return DIV_ROUND_UP(val, IO_TLB_SIZE);
+}
+
+/*
+ * Early SWIOTLB allocation may be too early to allow an architecture to
+ * perform the desired operations.  This function allows the architecture to
+ * call SWIOTLB when the operations are possible.  It needs to be called
+ * before the SWIOTLB memory is used.
+ */
+void __init swiotlb_update_mem_attributes(void)
+{
+	void *vaddr;
+	unsigned long bytes;
+
+	if (no_iotlb_memory || late_alloc)
+		return;
+
+	vaddr = phys_to_virt(io_tlb_start);
+	bytes = PAGE_ALIGN(io_tlb_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;
+	size_t alloc_size;
+
+	bytes = nslabs << IO_TLB_SHIFT;
+
+	io_tlb_nslabs = nslabs;
+	io_tlb_start = __pa(tlb);
+	io_tlb_end = io_tlb_start + 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.
+	 */
+	alloc_size = PAGE_ALIGN(io_tlb_nslabs * sizeof(int));
+	io_tlb_list = memblock_alloc(alloc_size, PAGE_SIZE);
+	if (!io_tlb_list)
+		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);
+
+	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_index = 0;
+	no_iotlb_memory = false;
+
+	if (verbose)
+		swiotlb_print_info();
+
+	swiotlb_set_max_segment(io_tlb_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)
+{
+	size_t default_size = IO_TLB_DEFAULT_SIZE;
+	unsigned char *vstart;
+	unsigned long bytes;
+
+	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))
+		return;
+
+	if (io_tlb_start) {
+		memblock_free_early(io_tlb_start,
+				    PAGE_ALIGN(io_tlb_nslabs << IO_TLB_SHIFT));
+		io_tlb_start = 0;
+	}
+	pr_warn("Cannot allocate buffer");
+	no_iotlb_memory = true;
+}
+
+/*
+ * Systems with larger DMA zones (those that don't support ISA) can
+ * 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)
+{
+	unsigned long bytes, req_nslabs = io_tlb_nslabs;
+	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);
+	}
+
+	/*
+	 * 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;
+
+	while ((SLABS_PER_PAGE << order) > IO_TLB_MIN_SLABS) {
+		vstart = (void *)__get_free_pages(GFP_DMA | __GFP_NOWARN,
+						  order);
+		if (vstart)
+			break;
+		order--;
+	}
+
+	if (!vstart) {
+		io_tlb_nslabs = req_nslabs;
+		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;
+	}
+	rc = swiotlb_late_init_with_tbl(vstart, io_tlb_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;
+
+	bytes = nslabs << IO_TLB_SHIFT;
+
+	io_tlb_nslabs = nslabs;
+	io_tlb_start = virt_to_phys(tlb);
+	io_tlb_end = io_tlb_start + bytes;
+
+	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;
+
+	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_index = 0;
+	no_iotlb_memory = false;
+
+	swiotlb_print_info();
+
+	late_alloc = 1;
+
+	swiotlb_set_max_segment(io_tlb_nslabs << IO_TLB_SHIFT);
+
+	return 0;
+
+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)
+		return;
+
+	if (late_alloc) {
+		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_list),
+				   PAGE_ALIGN(io_tlb_nslabs * sizeof(int)));
+		memblock_free_late(io_tlb_start,
+				   PAGE_ALIGN(io_tlb_nslabs << IO_TLB_SHIFT));
+	}
+	swiotlb_cleanup();
+}
+
+/*
+ * 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)
+{
+	unsigned long pfn = PFN_DOWN(orig_addr);
+	unsigned char *vaddr = phys_to_virt(tlb_addr);
+
+	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;
+		unsigned int sz = 0;
+		unsigned long flags;
+
+		while (size) {
+			sz = min_t(size_t, PAGE_SIZE - offset, size);
+
+			local_irq_save(flags);
+			buffer = kmap_atomic(pfn_to_page(pfn));
+			if (dir == DMA_TO_DEVICE)
+				memcpy(vaddr, buffer + offset, sz);
+			else
+				memcpy(buffer + offset, vaddr, sz);
+			kunmap_atomic(buffer);
+			local_irq_restore(flags);
+
+			size -= sz;
+			pfn++;
+			vaddr += sz;
+			offset = 0;
+		}
+	} else if (dir == DMA_TO_DEVICE) {
+		memcpy(vaddr, phys_to_virt(orig_addr), size);
+	} else {
+		memcpy(phys_to_virt(orig_addr), vaddr, size);
+	}
+}
+
+static inline phys_addr_t slot_addr(phys_addr_t start, phys_addr_t idx)
+{
+	return start + (idx << IO_TLB_SHIFT);
+}
+
+/*
+ * Return the offset into a iotlb slot required to keep the device happy.
+ */
+static unsigned int swiotlb_align_offset(struct device *dev, u64 addr)
+{
+	return addr & dma_get_min_align_mask(dev) & (IO_TLB_SIZE - 1);
+}
+
+/*
+ * Carefully handle integer overflow which can occur when boundary_mask == ~0UL.
+ */
+static inline unsigned long get_max_slots(unsigned long boundary_mask)
+{
+	if (boundary_mask == ~0UL)
+		return 1UL << (BITS_PER_LONG - IO_TLB_SHIFT);
+	return nr_slots(boundary_mask + 1);
+}
+
+static unsigned int wrap_index(unsigned int index)
+{
+	if (index >= io_tlb_nslabs)
+		return 0;
+	return index;
+}
+
+/*
+ * Find a suitable number of IO TLB entries size that will fit this request and
+ * allocate a buffer from that IO TLB pool.
+ */
+static int find_slots(struct device *dev, phys_addr_t orig_addr,
+		size_t alloc_size)
+{
+	unsigned long boundary_mask = dma_get_seg_boundary(dev);
+	dma_addr_t tbl_dma_addr =
+		phys_to_dma_unencrypted(dev, io_tlb_start) & boundary_mask;
+	unsigned long max_slots = get_max_slots(boundary_mask);
+	unsigned int iotlb_align_mask =
+		dma_get_min_align_mask(dev) & ~(IO_TLB_SIZE - 1);
+	unsigned int nslots = nr_slots(alloc_size), stride;
+	unsigned int index, wrap, count = 0, i;
+	unsigned long flags;
+
+	BUG_ON(!nslots);
+
+	/*
+	 * For mappings with an alignment requirement don't bother looping to
+	 * unaligned slots once we found an aligned one.  For allocations of
+	 * PAGE_SIZE or larger only look for page aligned allocations.
+	 */
+	stride = (iotlb_align_mask >> IO_TLB_SHIFT) + 1;
+	if (alloc_size >= PAGE_SIZE)
+		stride = max(stride, stride << (PAGE_SHIFT - IO_TLB_SHIFT));
+
+	spin_lock_irqsave(&io_tlb_lock, flags);
+	if (unlikely(nslots > io_tlb_nslabs - io_tlb_used))
+		goto not_found;
+
+	index = wrap = wrap_index(ALIGN(io_tlb_index, stride));
+	do {
+		if ((slot_addr(tbl_dma_addr, index) & iotlb_align_mask) !=
+		    (orig_addr & iotlb_align_mask)) {
+			index = wrap_index(index + 1);
+			continue;
+		}
+
+		/*
+		 * If we find a slot that indicates we have 'nslots' number of
+		 * contiguous buffers, we allocate the buffers from that slot
+		 * and mark the entries as '0' indicating unavailable.
+		 */
+		if (!iommu_is_span_boundary(index, nslots,
+					    nr_slots(tbl_dma_addr),
+					    max_slots)) {
+			if (io_tlb_list[index] >= nslots)
+				goto found;
+		}
+		index = wrap_index(index + stride);
+	} while (index != wrap);
+
+not_found:
+	spin_unlock_irqrestore(&io_tlb_lock, flags);
+	return -1;
+
+found:
+	for (i = index; i < index + nslots; i++)
+		io_tlb_list[i] = 0;
+	for (i = index - 1;
+	     io_tlb_offset(i) != IO_TLB_SEGSIZE - 1 &&
+	     io_tlb_list[i]; i--)
+		io_tlb_list[i] = ++count;
+
+	/*
+	 * Update the indices to avoid searching in the next round.
+	 */
+	if (index + nslots < io_tlb_nslabs)
+		io_tlb_index = index + nslots;
+	else
+		io_tlb_index = 0;
+	io_tlb_used += nslots;
+
+	spin_unlock_irqrestore(&io_tlb_lock, flags);
+	return index;
+}
+
+phys_addr_t swiotlb_tbl_map_single(struct device *dev, phys_addr_t orig_addr,
+		size_t mapping_size, size_t alloc_size,
+		enum dma_data_direction dir, unsigned long attrs)
+{
+	unsigned int offset = swiotlb_align_offset(dev, orig_addr);
+	unsigned int i;
+	int index;
+	phys_addr_t tlb_addr;
+
+	if (no_iotlb_memory)
+		panic("Can not allocate SWIOTLB buffer earlier and can't now provide you with the DMA bounce buffer");
+
+	if (mem_encrypt_active())
+		pr_warn_once("Memory encryption is active and system is using DMA bounce buffers\n");
+
+	if (mapping_size > alloc_size) {
+		dev_warn_once(dev, "Invalid sizes (mapping: %zd bytes, alloc: %zd bytes)",
+			      mapping_size, alloc_size);
+		return (phys_addr_t)DMA_MAPPING_ERROR;
+	}
+
+	index = find_slots(dev, orig_addr, alloc_size + offset);
+	if (index == -1) {
+		if (!(attrs & DMA_ATTR_NO_WARN))
+			dev_warn_ratelimited(dev,
+	"swiotlb buffer is full (sz: %zd bytes), total %lu (slots), used %lu (slots)\n",
+				 alloc_size, io_tlb_nslabs, io_tlb_used);
+		return (phys_addr_t)DMA_MAPPING_ERROR;
+	}
+
+	/*
+	 * Save away the mapping from the original address to the DMA address.
+	 * This is needed when we sync the memory.  Then we sync the buffer if
+	 * needed.
+	 */
+	for (i = 0; i < nr_slots(alloc_size + offset); i++)
+		io_tlb_orig_addr[index + i] = slot_addr(orig_addr, i);
+
+	tlb_addr = slot_addr(io_tlb_start, index) + offset;
+	/*
+	 * 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
+	 * unconditional bounce may prevent leaking swiotlb content (i.e.
+	 * kernel memory) to user-space.
+	 */
+	swiotlb_bounce(orig_addr, tlb_addr, mapping_size, DMA_TO_DEVICE);
+	return tlb_addr;
+}
+
+/*
+ * 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)
+{
+	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];
+
+	/*
+	 * 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);
+
+	/*
+	 * Return the buffer to the free list by setting the corresponding
+	 * entries to indicate the number of contiguous entries available.
+	 * 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);
+	if (index + nslots < ALIGN(index + 1, IO_TLB_SEGSIZE))
+		count = io_tlb_list[index + nslots];
+	else
+		count = 0;
+
+	/*
+	 * Step 1: return the slots to the free list, merging the slots with
+	 * superceeding slots
+	 */
+	for (i = index + nslots - 1; i >= index; i--) {
+		io_tlb_list[i] = ++count;
+		io_tlb_orig_addr[i] = INVALID_PHYS_ADDR;
+	}
+
+	/*
+	 * Step 2: merge the returned slots with the preceding slots, if
+	 * available (non zero)
+	 */
+	for (i = index - 1;
+	     io_tlb_offset(i) != IO_TLB_SEGSIZE - 1 && io_tlb_list[i];
+	     i--)
+		io_tlb_list[i] = ++count;
+	io_tlb_used -= nslots;
+	spin_unlock_irqrestore(&io_tlb_lock, flags);
+}
+
+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)
+{
+	int index = (tlb_addr - io_tlb_start) >> IO_TLB_SHIFT;
+	phys_addr_t orig_addr = io_tlb_orig_addr[index];
+
+	if (orig_addr == INVALID_PHYS_ADDR)
+		return;
+
+	orig_addr += (tlb_addr & (IO_TLB_SIZE - 1)) -
+		swiotlb_align_offset(hwdev, orig_addr);
+
+	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();
+	}
+}
+
+/*
+ * Create a swiotlb mapping for the buffer at @paddr, and in case of DMAing
+ * to the device copy the data into it as well.
+ */
+dma_addr_t swiotlb_map(struct device *dev, phys_addr_t paddr, size_t size,
+		enum dma_data_direction dir, unsigned long attrs)
+{
+	phys_addr_t swiotlb_addr;
+	dma_addr_t dma_addr;
+
+	trace_swiotlb_bounced(dev, phys_to_dma(dev, paddr), size,
+			      swiotlb_force);
+
+	swiotlb_addr = swiotlb_tbl_map_single(dev, paddr, size, size, dir,
+			attrs);
+	if (swiotlb_addr == (phys_addr_t)DMA_MAPPING_ERROR)
+		return DMA_MAPPING_ERROR;
+
+	/* 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,
+			attrs | DMA_ATTR_SKIP_CPU_SYNC);
+		dev_WARN_ONCE(dev, 1,
+			"swiotlb addr %pad+%zu overflow (mask %llx, bus limit %llx).\n",
+			&dma_addr, size, *dev->dma_mask, dev->bus_dma_limit);
+		return DMA_MAPPING_ERROR;
+	}
+
+	if (!dev_is_dma_coherent(dev) && !(attrs & DMA_ATTR_SKIP_CPU_SYNC))
+		arch_sync_dma_for_device(swiotlb_addr, size, dir);
+	return dma_addr;
+}
+
+size_t swiotlb_max_mapping_size(struct device *dev)
+{
+	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(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;
+}
+
+#ifdef CONFIG_DEBUG_FS
+
+static int __init swiotlb_create_debugfs(void)
+{
+	struct dentry *root;
+
+	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);
+	return 0;
+}
+
+late_initcall(swiotlb_create_debugfs);
+
+#endif
diff --git a/kernel/dma/virt.c b/kernel/dma/virt.c
new file mode 100644
index 000000000..59d32317d
--- /dev/null
+++ b/kernel/dma/virt.c
@@ -0,0 +1,61 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * DMA operations that map to virtual addresses without flushing memory.
+ */
+#include <linux/export.h>
+#include <linux/mm.h>
+#include <linux/dma-map-ops.h>
+#include <linux/scatterlist.h>
+
+static void *dma_virt_alloc(struct device *dev, size_t size,
+			    dma_addr_t *dma_handle, gfp_t gfp,
+			    unsigned long attrs)
+{
+	void *ret;
+
+	ret = (void *)__get_free_pages(gfp | __GFP_ZERO, get_order(size));
+	if (ret)
+		*dma_handle = (uintptr_t)ret;
+	return ret;
+}
+
+static void dma_virt_free(struct device *dev, size_t size,
+			  void *cpu_addr, dma_addr_t dma_addr,
+			  unsigned long attrs)
+{
+	free_pages((unsigned long)cpu_addr, get_order(size));
+}
+
+static dma_addr_t dma_virt_map_page(struct device *dev, struct page *page,
+				    unsigned long offset, size_t size,
+				    enum dma_data_direction dir,
+				    unsigned long attrs)
+{
+	return (uintptr_t)(page_address(page) + offset);
+}
+
+static int dma_virt_map_sg(struct device *dev, struct scatterlist *sgl,
+			   int nents, enum dma_data_direction dir,
+			   unsigned long attrs)
+{
+	int i;
+	struct scatterlist *sg;
+
+	for_each_sg(sgl, sg, nents, i) {
+		BUG_ON(!sg_page(sg));
+		sg_dma_address(sg) = (uintptr_t)sg_virt(sg);
+		sg_dma_len(sg) = sg->length;
+	}
+
+	return nents;
+}
+
+const struct dma_map_ops dma_virt_ops = {
+	.alloc			= dma_virt_alloc,
+	.free			= dma_virt_free,
+	.map_page		= dma_virt_map_page,
+	.map_sg			= dma_virt_map_sg,
+	.alloc_pages		= dma_common_alloc_pages,
+	.free_pages		= dma_common_free_pages,
+};
+EXPORT_SYMBOL(dma_virt_ops);