Merge branch 'iommu-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip

* 'iommu-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (60 commits)
  dma-debug: make memory range checks more consistent
  dma-debug: warn of unmapping an invalid dma address
  dma-debug: fix dma_debug_add_bus() definition for !CONFIG_DMA_API_DEBUG
  dma-debug/x86: register pci bus for dma-debug leak detection
  dma-debug: add a check dma memory leaks
  dma-debug: add checks for kernel text and rodata
  dma-debug: print stacktrace of mapping path on unmap error
  dma-debug: Documentation update
  dma-debug: x86 architecture bindings
  dma-debug: add function to dump dma mappings
  dma-debug: add checks for sync_single_sg_*
  dma-debug: add checks for sync_single_range_*
  dma-debug: add checks for sync_single_*
  dma-debug: add checking for [alloc|free]_coherent
  dma-debug: add add checking for map/unmap_sg
  dma-debug: add checking for map/unmap_page/single
  dma-debug: add core checking functions
  dma-debug: add debugfs interface
  dma-debug: add kernel command line parameters
  dma-debug: add initialization code
  ...

Fix trivial conflicts due to whitespace changes in arch/x86/kernel/pci-nommu.c

4 files changed, 1007 insertions, 49 deletions

diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index 0626fa4856e..58bfe7e8fab 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -912,6 +912,17 @@ config DYNAMIC_DEBUG
 
 	  See Documentation/dynamic-debug-howto.txt for additional information.
 
+config DMA_API_DEBUG
+	bool "Enable debugging of DMA-API usage"
+	depends on HAVE_DMA_API_DEBUG
+	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 degredation.  Use only if you want
+	  to debug device drivers. If unsure, say N.
+
 source "samples/Kconfig"
 
 source "lib/Kconfig.kgdb"
diff --git a/lib/Makefile b/lib/Makefile
index 051a33a8e02..d6edd6753f4 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -90,6 +90,8 @@ obj-$(CONFIG_DYNAMIC_DEBUG) += dynamic_debug.o
 
 obj-$(CONFIG_NLATTR) += nlattr.o
 
+obj-$(CONFIG_DMA_API_DEBUG) += dma-debug.o
+
 hostprogs-y	:= gen_crc32table
 clean-files	:= crc32table.h
 
diff --git a/lib/dma-debug.c b/lib/dma-debug.c
new file mode 100644
index 00000000000..1a992089486
--- /dev/null
+++ b/lib/dma-debug.c
@@ -0,0 +1,955 @@
+/*
+ * Copyright (C) 2008 Advanced Micro Devices, Inc.
+ *
+ * Author: Joerg Roedel <joerg.roedel@amd.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published
+ * by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
+ */
+
+#include <linux/scatterlist.h>
+#include <linux/dma-mapping.h>
+#include <linux/stacktrace.h>
+#include <linux/dma-debug.h>
+#include <linux/spinlock.h>
+#include <linux/debugfs.h>
+#include <linux/device.h>
+#include <linux/types.h>
+#include <linux/sched.h>
+#include <linux/list.h>
+#include <linux/slab.h>
+
+#include <asm/sections.h>
+
+#define HASH_SIZE       1024ULL
+#define HASH_FN_SHIFT   13
+#define HASH_FN_MASK    (HASH_SIZE - 1)
+
+enum {
+	dma_debug_single,
+	dma_debug_page,
+	dma_debug_sg,
+	dma_debug_coherent,
+};
+
+#define DMA_DEBUG_STACKTRACE_ENTRIES 5
+
+struct dma_debug_entry {
+	struct list_head list;
+	struct device    *dev;
+	int              type;
+	phys_addr_t      paddr;
+	u64              dev_addr;
+	u64              size;
+	int              direction;
+	int		 sg_call_ents;
+	int		 sg_mapped_ents;
+#ifdef CONFIG_STACKTRACE
+	struct		 stack_trace stacktrace;
+	unsigned long	 st_entries[DMA_DEBUG_STACKTRACE_ENTRIES];
+#endif
+};
+
+struct hash_bucket {
+	struct list_head list;
+	spinlock_t lock;
+} ____cacheline_aligned_in_smp;
+
+/* 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;
+
+/* 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;
+
+/* number of preallocated entries requested by kernel cmdline */
+static u32 req_entries;
+
+/* debugfs dentry's for the stuff above */
+static struct dentry *dma_debug_dent        __read_mostly;
+static struct dentry *global_disable_dent   __read_mostly;
+static struct dentry *error_count_dent      __read_mostly;
+static struct dentry *show_all_errors_dent  __read_mostly;
+static struct dentry *show_num_errors_dent  __read_mostly;
+static struct dentry *num_free_entries_dent __read_mostly;
+static struct dentry *min_free_entries_dent __read_mostly;
+
+static const char *type2name[4] = { "single", "page",
+				    "scather-gather", "coherent" };
+
+static const char *dir2name[4] = { "DMA_BIDIRECTIONAL", "DMA_TO_DEVICE",
+				   "DMA_FROM_DEVICE", "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) {
+		printk(KERN_WARNING "Mapped at:\n");
+		print_stack_trace(&entry->stacktrace, 0);
+	}
+#endif
+}
+
+#define err_printk(dev, entry, format, arg...) do {		\
+		error_count += 1;				\
+		if (show_all_errors || show_num_errors > 0) {	\
+			WARN(1, "%s %s: " format,		\
+			     dev_driver_string(dev),		\
+			     dev_name(dev) , ## 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)
+{
+	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)
+{
+	unsigned long __flags = *flags;
+
+	spin_unlock_irqrestore(&bucket->lock, __flags);
+}
+
+/*
+ * 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)
+{
+	struct dma_debug_entry *entry;
+
+	list_for_each_entry(entry, &bucket->list, list) {
+		if ((entry->dev_addr == ref->dev_addr) &&
+		    (entry->dev == ref->dev))
+			return entry;
+	}
+
+	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);
+}
+
+/*
+ * 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 D=%Lx L=%Lx %s\n",
+					 type2name[entry->type], idx,
+					 (unsigned long long)entry->paddr,
+					 entry->dev_addr, entry->size,
+					 dir2name[entry->direction]);
+			}
+		}
+
+		spin_unlock_irqrestore(&bucket->lock, flags);
+	}
+}
+EXPORT_SYMBOL(debug_dma_dump_mappings);
+
+/*
+ * 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;
+
+	bucket = get_hash_bucket(entry, &flags);
+	hash_bucket_add(bucket, entry);
+	put_hash_bucket(bucket, &flags);
+}
+
+/* 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)
+{
+	struct dma_debug_entry *entry = NULL;
+	unsigned long flags;
+
+	spin_lock_irqsave(&free_entries_lock, flags);
+
+	if (list_empty(&free_entries)) {
+		printk(KERN_ERR "DMA-API: debugging out of memory "
+				"- disabling\n");
+		global_disable = true;
+		goto out;
+	}
+
+	entry = list_entry(free_entries.next, struct dma_debug_entry, list);
+	list_del(&entry->list);
+	memset(entry, 0, sizeof(*entry));
+
+#ifdef CONFIG_STACKTRACE
+	entry->stacktrace.max_entries = DMA_DEBUG_STACKTRACE_ENTRIES;
+	entry->stacktrace.entries = entry->st_entries;
+	entry->stacktrace.skip = 2;
+	save_stack_trace(&entry->stacktrace);
+#endif
+	num_free_entries -= 1;
+	if (num_free_entries < min_free_entries)
+		min_free_entries = num_free_entries;
+
+out:
+	spin_unlock_irqrestore(&free_entries_lock, flags);
+
+	return entry;
+}
+
+static void dma_entry_free(struct dma_debug_entry *entry)
+{
+	unsigned long flags;
+
+	/*
+	 * 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 int prealloc_memory(u32 num_entries)
+{
+	struct dma_debug_entry *entry, *next_entry;
+	int i;
+
+	for (i = 0; i < num_entries; ++i) {
+		entry = kzalloc(sizeof(*entry), GFP_KERNEL);
+		if (!entry)
+			goto out_err;
+
+		list_add_tail(&entry->list, &free_entries);
+	}
+
+	num_free_entries = num_entries;
+	min_free_entries = num_entries;
+
+	printk(KERN_INFO "DMA-API: preallocated %d debug entries\n",
+			num_entries);
+
+	return 0;
+
+out_err:
+
+	list_for_each_entry_safe(entry, next_entry, &free_entries, list) {
+		list_del(&entry->list);
+		kfree(entry);
+	}
+
+	return -ENOMEM;
+}
+
+static int dma_debug_fs_init(void)
+{
+	dma_debug_dent = debugfs_create_dir("dma-api", NULL);
+	if (!dma_debug_dent) {
+		printk(KERN_ERR "DMA-API: can not create debugfs directory\n");
+		return -ENOMEM;
+	}
+
+	global_disable_dent = debugfs_create_bool("disabled", 0444,
+			dma_debug_dent,
+			(u32 *)&global_disable);
+	if (!global_disable_dent)
+		goto out_err;
+
+	error_count_dent = debugfs_create_u32("error_count", 0444,
+			dma_debug_dent, &error_count);
+	if (!error_count_dent)
+		goto out_err;
+
+	show_all_errors_dent = debugfs_create_u32("all_errors", 0644,
+			dma_debug_dent,
+			&show_all_errors);
+	if (!show_all_errors_dent)
+		goto out_err;
+
+	show_num_errors_dent = debugfs_create_u32("num_errors", 0644,
+			dma_debug_dent,
+			&show_num_errors);
+	if (!show_num_errors_dent)
+		goto out_err;
+
+	num_free_entries_dent = debugfs_create_u32("num_free_entries", 0444,
+			dma_debug_dent,
+			&num_free_entries);
+	if (!num_free_entries_dent)
+		goto out_err;
+
+	min_free_entries_dent = debugfs_create_u32("min_free_entries", 0444,
+			dma_debug_dent,
+			&min_free_entries);
+	if (!min_free_entries_dent)
+		goto out_err;
+
+	return 0;
+
+out_err:
+	debugfs_remove_recursive(dma_debug_dent);
+
+	return -ENOMEM;
+}
+
+static int device_dma_allocations(struct device *dev)
+{
+	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;
+		}
+		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;
+	int count;
+
+
+	switch (action) {
+	case BUS_NOTIFY_UNBIND_DRIVER:
+		count = device_dma_allocations(dev);
+		if (count == 0)
+			break;
+		err_printk(dev, NULL, "DMA-API: device driver has pending "
+				"DMA allocations while released from device "
+				"[count=%d]\n", count);
+		break;
+	default:
+		break;
+	}
+
+	return 0;
+}
+
+void dma_debug_add_bus(struct bus_type *bus)
+{
+	struct notifier_block *nb;
+
+	nb = kzalloc(sizeof(struct notifier_block), GFP_KERNEL);
+	if (nb == NULL) {
+		printk(KERN_ERR "dma_debug_add_bus: out of memory\n");
+		return;
+	}
+
+	nb->notifier_call = dma_debug_device_change;
+
+	bus_register_notifier(bus, nb);
+}
+
+/*
+ * Let the architectures decide how many entries should be preallocated.
+ */
+void dma_debug_init(u32 num_entries)
+{
+	int i;
+
+	if (global_disable)
+		return;
+
+	for (i = 0; i < HASH_SIZE; ++i) {
+		INIT_LIST_HEAD(&dma_entry_hash[i].list);
+		dma_entry_hash[i].lock = SPIN_LOCK_UNLOCKED;
+	}
+
+	if (dma_debug_fs_init() != 0) {
+		printk(KERN_ERR "DMA-API: error creating debugfs entries "
+				"- disabling\n");
+		global_disable = true;
+
+		return;
+	}
+
+	if (req_entries)
+		num_entries = req_entries;
+
+	if (prealloc_memory(num_entries) != 0) {
+		printk(KERN_ERR "DMA-API: debugging out of memory error "
+				"- disabled\n");
+		global_disable = true;
+
+		return;
+	}
+
+	printk(KERN_INFO "DMA-API: debugging enabled by kernel config\n");
+}
+
+static __init int dma_debug_cmdline(char *str)
+{
+	if (!str)
+		return -EINVAL;
+
+	if (strncmp(str, "off", 3) == 0) {
+		printk(KERN_INFO "DMA-API: debugging disabled on kernel "
+				 "command line\n");
+		global_disable = true;
+	}
+
+	return 0;
+}
+
+static __init int dma_debug_entries_cmdline(char *str)
+{
+	int res;
+
+	if (!str)
+		return -EINVAL;
+
+	res = get_option(&str, &req_entries);
+
+	if (!res)
+		req_entries = 0;
+
+	return 0;
+}
+
+__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;
+
+	if (dma_mapping_error(ref->dev, ref->dev_addr)) {
+		err_printk(ref->dev, NULL, "DMA-API: device driver tries "
+			   "to free an invalid DMA memory address\n");
+		return;
+	}
+
+	bucket = get_hash_bucket(ref, &flags);
+	entry = hash_bucket_find(bucket, ref);
+
+	if (!entry) {
+		err_printk(ref->dev, NULL, "DMA-API: device driver tries "
+			   "to free DMA memory it has not allocated "
+			   "[device address=0x%016llx] [size=%llu bytes]\n",
+			   ref->dev_addr, ref->size);
+		goto out;
+	}
+
+	if (ref->size != entry->size) {
+		err_printk(ref->dev, entry, "DMA-API: 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, "DMA-API: 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) &&
+		   (ref->paddr != entry->paddr)) {
+		err_printk(ref->dev, entry, "DMA-API: device driver frees "
+			   "DMA memory with different CPU address "
+			   "[device address=0x%016llx] [size=%llu bytes] "
+			   "[cpu alloc address=%p] [cpu free address=%p]",
+			   ref->dev_addr, ref->size,
+			   (void *)entry->paddr, (void *)ref->paddr);
+	}
+
+	if (ref->sg_call_ents && ref->type == dma_debug_sg &&
+	    ref->sg_call_ents != entry->sg_call_ents) {
+		err_printk(ref->dev, entry, "DMA-API: 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, "DMA-API: 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]);
+	}
+
+	hash_bucket_del(entry);
+	dma_entry_free(entry);
+
+out:
+	put_hash_bucket(bucket, &flags);
+}
+
+static void check_for_stack(struct device *dev, void *addr)
+{
+	if (object_is_on_stack(addr))
+		err_printk(dev, NULL, "DMA-API: device driver maps memory from"
+				"stack [addr=%p]\n", addr);
+}
+
+static inline bool overlap(void *addr, u64 size, void *start, void *end)
+{
+	void *addr2 = (char *)addr + size;
+
+	return ((addr >= start && addr < end) ||
+		(addr2 >= start && addr2 < end) ||
+		((addr < start) && (addr2 >= end)));
+}
+
+static void check_for_illegal_area(struct device *dev, void *addr, u64 size)
+{
+	if (overlap(addr, size, _text, _etext) ||
+	    overlap(addr, size, __start_rodata, __end_rodata))
+		err_printk(dev, NULL, "DMA-API: device driver maps "
+				"memory from kernel text or rodata "
+				"[addr=%p] [size=%llu]\n", addr, size);
+}
+
+static void check_sync(struct device *dev, dma_addr_t addr,
+		       u64 size, u64 offset, int direction, bool to_cpu)
+{
+	struct dma_debug_entry ref = {
+		.dev            = dev,
+		.dev_addr       = addr,
+		.size           = size,
+		.direction      = direction,
+	};
+	struct dma_debug_entry *entry;
+	struct hash_bucket *bucket;
+	unsigned long flags;
+
+	bucket = get_hash_bucket(&ref, &flags);
+
+	entry = hash_bucket_find(bucket, &ref);
+
+	if (!entry) {
+		err_printk(dev, NULL, "DMA-API: device driver tries "
+				"to sync DMA memory it has not allocated "
+				"[device address=0x%016llx] [size=%llu bytes]\n",
+				addr, size);
+		goto out;
+	}
+
+	if ((offset + size) > entry->size) {
+		err_printk(dev, entry, "DMA-API: device driver syncs"
+				" DMA memory outside allocated range "
+				"[device address=0x%016llx] "
+				"[allocation size=%llu bytes] [sync offset=%llu] "
+				"[sync size=%llu]\n", entry->dev_addr, entry->size,
+				offset, size);
+	}
+
+	if (direction != entry->direction) {
+		err_printk(dev, entry, "DMA-API: device driver syncs "
+				"DMA memory with different direction "
+				"[device address=0x%016llx] [size=%llu bytes] "
+				"[mapped with %s] [synced with %s]\n",
+				addr, entry->size,
+				dir2name[entry->direction],
+				dir2name[direction]);
+	}
+
+	if (entry->direction == DMA_BIDIRECTIONAL)
+		goto out;
+
+	if (to_cpu && !(entry->direction == DMA_FROM_DEVICE) &&
+		      !(direction == DMA_TO_DEVICE))
+		err_printk(dev, entry, "DMA-API: device driver syncs "
+				"device read-only DMA memory for cpu "
+				"[device address=0x%016llx] [size=%llu bytes] "
+				"[mapped with %s] [synced with %s]\n",
+				addr, entry->size,
+				dir2name[entry->direction],
+				dir2name[direction]);
+
+	if (!to_cpu && !(entry->direction == DMA_TO_DEVICE) &&
+		       !(direction == DMA_FROM_DEVICE))
+		err_printk(dev, entry, "DMA-API: device driver syncs "
+				"device write-only DMA memory to device "
+				"[device address=0x%016llx] [size=%llu bytes] "
+				"[mapped with %s] [synced with %s]\n",
+				addr, entry->size,
+				dir2name[entry->direction],
+				dir2name[direction]);
+
+out:
+	put_hash_bucket(bucket, &flags);
+
+}
+
+void debug_dma_map_page(struct device *dev, struct page *page, size_t offset,
+			size_t size, int direction, dma_addr_t dma_addr,
+			bool map_single)
+{
+	struct dma_debug_entry *entry;
+
+	if (unlikely(global_disable))
+		return;
+
+	if (unlikely(dma_mapping_error(dev, dma_addr)))
+		return;
+
+	entry = dma_entry_alloc();
+	if (!entry)
+		return;
+
+	entry->dev       = dev;
+	entry->type      = dma_debug_page;
+	entry->paddr     = page_to_phys(page) + offset;
+	entry->dev_addr  = dma_addr;
+	entry->size      = size;
+	entry->direction = direction;
+
+	if (map_single)
+		entry->type = dma_debug_single;
+
+	if (!PageHighMem(page)) {
+		void *addr = ((char *)page_address(page)) + offset;
+		check_for_stack(dev, addr);
+		check_for_illegal_area(dev, addr, size);
+	}
+
+	add_dma_entry(entry);
+}
+EXPORT_SYMBOL(debug_dma_map_page);
+
+void debug_dma_unmap_page(struct device *dev, dma_addr_t addr,
+			  size_t size, int direction, bool map_single)
+{
+	struct dma_debug_entry ref = {
+		.type           = dma_debug_page,
+		.dev            = dev,
+		.dev_addr       = addr,
+		.size           = size,
+		.direction      = direction,
+	};
+
+	if (unlikely(global_disable))
+		return;
+
+	if (map_single)
+		ref.type = dma_debug_single;
+
+	check_unmap(&ref);
+}
+EXPORT_SYMBOL(debug_dma_unmap_page);
+
+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(global_disable))
+		return;
+
+	for_each_sg(sg, s, mapped_ents, i) {
+		entry = dma_entry_alloc();
+		if (!entry)
+			return;
+
+		entry->type           = dma_debug_sg;
+		entry->dev            = dev;
+		entry->paddr          = sg_phys(s);
+		entry->size           = s->length;
+		entry->dev_addr       = s->dma_address;
+		entry->direction      = direction;
+		entry->sg_call_ents   = nents;
+		entry->sg_mapped_ents = mapped_ents;
+
+		if (!PageHighMem(sg_page(s))) {
+			check_for_stack(dev, sg_virt(s));
+			check_for_illegal_area(dev, sg_virt(s), s->length);
+		}
+
+		add_dma_entry(entry);
+	}
+}
+EXPORT_SYMBOL(debug_dma_map_sg);
+
+void debug_dma_unmap_sg(struct device *dev, struct scatterlist *sglist,
+			int nelems, int dir)
+{
+	struct dma_debug_entry *entry;
+	struct scatterlist *s;
+	int mapped_ents = 0, i;
+	unsigned long flags;
+
+	if (unlikely(global_disable))
+		return;
+
+	for_each_sg(sglist, s, nelems, i) {
+
+		struct dma_debug_entry ref = {
+			.type           = dma_debug_sg,
+			.dev            = dev,
+			.paddr          = sg_phys(s),
+			.dev_addr       = s->dma_address,
+			.size           = s->length,
+			.direction      = dir,
+			.sg_call_ents   = 0,
+		};
+
+		if (mapped_ents && i >= mapped_ents)
+			break;
+
+		if (mapped_ents == 0) {
+			struct hash_bucket *bucket;
+			ref.sg_call_ents = nelems;
+			bucket = get_hash_bucket(&ref, &flags);
+			entry = hash_bucket_find(bucket, &ref);
+			if (entry)
+				mapped_ents = entry->sg_mapped_ents;
+			put_hash_bucket(bucket, &flags);
+		}
+
+		check_unmap(&ref);
+	}
+}
+EXPORT_SYMBOL(debug_dma_unmap_sg);
+
+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(global_disable))
+		return;
+
+	if (unlikely(virt == NULL))
+		return;
+
+	entry = dma_entry_alloc();
+	if (!entry)
+		return;
+
+	entry->type      = dma_debug_coherent;
+	entry->dev       = dev;
+	entry->paddr     = virt_to_phys(virt);
+	entry->size      = size;
+	entry->dev_addr  = dma_addr;
+	entry->direction = DMA_BIDIRECTIONAL;
+
+	add_dma_entry(entry);
+}
+EXPORT_SYMBOL(debug_dma_alloc_coherent);
+
+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,
+		.paddr          = virt_to_phys(virt),
+		.dev_addr       = addr,
+		.size           = size,
+		.direction      = DMA_BIDIRECTIONAL,
+	};
+
+	if (unlikely(global_disable))
+		return;
+
+	check_unmap(&ref);
+}
+EXPORT_SYMBOL(debug_dma_free_coherent);
+
+void debug_dma_sync_single_for_cpu(struct device *dev, dma_addr_t dma_handle,
+				   size_t size, int direction)
+{
+	if (unlikely(global_disable))
+		return;
+
+	check_sync(dev, dma_handle, size, 0, direction, true);
+}
+EXPORT_SYMBOL(debug_dma_sync_single_for_cpu);
+
+void debug_dma_sync_single_for_device(struct device *dev,
+				      dma_addr_t dma_handle, size_t size,
+				      int direction)
+{
+	if (unlikely(global_disable))
+		return;
+
+	check_sync(dev, dma_handle, size, 0, direction, false);
+}
+EXPORT_SYMBOL(debug_dma_sync_single_for_device);
+
+void debug_dma_sync_single_range_for_cpu(struct device *dev,
+					 dma_addr_t dma_handle,
+					 unsigned long offset, size_t size,
+					 int direction)
+{
+	if (unlikely(global_disable))
+		return;
+
+	check_sync(dev, dma_handle, size, offset, direction, true);
+}
+EXPORT_SYMBOL(debug_dma_sync_single_range_for_cpu);
+
+void debug_dma_sync_single_range_for_device(struct device *dev,
+					    dma_addr_t dma_handle,
+					    unsigned long offset,
+					    size_t size, int direction)
+{
+	if (unlikely(global_disable))
+		return;
+
+	check_sync(dev, dma_handle, size, offset, direction, false);
+}
+EXPORT_SYMBOL(debug_dma_sync_single_range_for_device);
+
+void debug_dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg,
+			       int nelems, int direction)
+{
+	struct scatterlist *s;
+	int i;
+
+	if (unlikely(global_disable))
+		return;
+
+	for_each_sg(sg, s, nelems, i) {
+		check_sync(dev, s->dma_address, s->dma_length, 0,
+				direction, true);
+	}
+}
+EXPORT_SYMBOL(debug_dma_sync_sg_for_cpu);
+
+void debug_dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg,
+				  int nelems, int direction)
+{
+	struct scatterlist *s;
+	int i;
+
+	if (unlikely(global_disable))
+		return;
+
+	for_each_sg(sg, s, nelems, i) {
+		check_sync(dev, s->dma_address, s->dma_length, 0,
+				direction, false);
+	}
+}
+EXPORT_SYMBOL(debug_dma_sync_sg_for_device);
+
diff --git a/lib/swiotlb.c b/lib/swiotlb.c
index 1f991acc2a0..32e2bd3b114 100644
--- a/lib/swiotlb.c
+++ b/lib/swiotlb.c
@@ -145,7 +145,7 @@ static void *swiotlb_bus_to_virt(dma_addr_t address)
 	return phys_to_virt(swiotlb_bus_to_phys(address));
 }
 
-int __weak swiotlb_arch_range_needs_mapping(void *ptr, size_t size)
+int __weak swiotlb_arch_range_needs_mapping(phys_addr_t paddr, size_t size)
 {
 	return 0;
 }
@@ -315,9 +315,9 @@ address_needs_mapping(struct device *hwdev, dma_addr_t addr, size_t size)
 	return !is_buffer_dma_capable(dma_get_mask(hwdev), addr, size);
 }
 
-static inline int range_needs_mapping(void *ptr, size_t size)
+static inline int range_needs_mapping(phys_addr_t paddr, size_t size)
 {
-	return swiotlb_force || swiotlb_arch_range_needs_mapping(ptr, size);
+	return swiotlb_force || swiotlb_arch_range_needs_mapping(paddr, size);
 }
 
 static int is_swiotlb_buffer(char *addr)
@@ -636,11 +636,14 @@ swiotlb_full(struct device *dev, size_t size, int dir, int do_panic)
  * Once the device is given the dma address, the device owns this memory until
  * either swiotlb_unmap_single or swiotlb_dma_sync_single is performed.
  */
-dma_addr_t
-swiotlb_map_single_attrs(struct device *hwdev, void *ptr, size_t size,
-			 int dir, struct dma_attrs *attrs)
-{
-	dma_addr_t dev_addr = swiotlb_virt_to_bus(hwdev, ptr);
+dma_addr_t swiotlb_map_page(struct device *dev, struct page *page,
+			    unsigned long offset, size_t size,
+			    enum dma_data_direction dir,
+			    struct dma_attrs *attrs)
+{
+	phys_addr_t phys = page_to_phys(page) + offset;
+	void *ptr = page_address(page) + offset;
+	dma_addr_t dev_addr = swiotlb_phys_to_bus(dev, phys);
 	void *map;
 
 	BUG_ON(dir == DMA_NONE);
@@ -649,37 +652,30 @@ swiotlb_map_single_attrs(struct device *hwdev, void *ptr, size_t size,
 	 * we can safely return the device addr and not worry about bounce
 	 * buffering it.
 	 */
-	if (!address_needs_mapping(hwdev, dev_addr, size) &&
-	    !range_needs_mapping(ptr, size))
+	if (!address_needs_mapping(dev, dev_addr, size) &&
+	    !range_needs_mapping(virt_to_phys(ptr), size))
 		return dev_addr;
 
 	/*
 	 * Oh well, have to allocate and map a bounce buffer.
 	 */
-	map = map_single(hwdev, virt_to_phys(ptr), size, dir);
+	map = map_single(dev, phys, size, dir);
 	if (!map) {
-		swiotlb_full(hwdev, size, dir, 1);
+		swiotlb_full(dev, size, dir, 1);
 		map = io_tlb_overflow_buffer;
 	}
 
-	dev_addr = swiotlb_virt_to_bus(hwdev, map);
+	dev_addr = swiotlb_virt_to_bus(dev, map);
 
 	/*
 	 * Ensure that the address returned is DMA'ble
 	 */
-	if (address_needs_mapping(hwdev, dev_addr, size))
+	if (address_needs_mapping(dev, dev_addr, size))
 		panic("map_single: bounce buffer is not DMA'ble");
 
 	return dev_addr;
 }
-EXPORT_SYMBOL(swiotlb_map_single_attrs);
-
-dma_addr_t
-swiotlb_map_single(struct device *hwdev, void *ptr, size_t size, int dir)
-{
-	return swiotlb_map_single_attrs(hwdev, ptr, size, dir, NULL);
-}
-EXPORT_SYMBOL(swiotlb_map_single);
+EXPORT_SYMBOL_GPL(swiotlb_map_page);
 
 /*
  * Unmap a single streaming mode DMA translation.  The dma_addr and size must
@@ -689,9 +685,9 @@ EXPORT_SYMBOL(swiotlb_map_single);
  * After this call, reads by the cpu to the buffer are guaranteed to see
  * whatever the device wrote there.
  */
-void
-swiotlb_unmap_single_attrs(struct device *hwdev, dma_addr_t dev_addr,
-			   size_t size, int dir, struct dma_attrs *attrs)
+void swiotlb_unmap_page(struct device *hwdev, dma_addr_t dev_addr,
+			size_t size, enum dma_data_direction dir,
+			struct dma_attrs *attrs)
 {
 	char *dma_addr = swiotlb_bus_to_virt(dev_addr);
 
@@ -701,15 +697,7 @@ swiotlb_unmap_single_attrs(struct device *hwdev, dma_addr_t dev_addr,
 	else if (dir == DMA_FROM_DEVICE)
 		dma_mark_clean(dma_addr, size);
 }
-EXPORT_SYMBOL(swiotlb_unmap_single_attrs);
-
-void
-swiotlb_unmap_single(struct device *hwdev, dma_addr_t dev_addr, size_t size,
-		     int dir)
-{
-	return swiotlb_unmap_single_attrs(hwdev, dev_addr, size, dir, NULL);
-}
-EXPORT_SYMBOL(swiotlb_unmap_single);
+EXPORT_SYMBOL_GPL(swiotlb_unmap_page);
 
 /*
  * Make physical memory consistent for a single streaming mode DMA translation
@@ -736,7 +724,7 @@ swiotlb_sync_single(struct device *hwdev, dma_addr_t dev_addr,
 
 void
 swiotlb_sync_single_for_cpu(struct device *hwdev, dma_addr_t dev_addr,
-			    size_t size, int dir)
+			    size_t size, enum dma_data_direction dir)
 {
 	swiotlb_sync_single(hwdev, dev_addr, size, dir, SYNC_FOR_CPU);
 }
@@ -744,7 +732,7 @@ EXPORT_SYMBOL(swiotlb_sync_single_for_cpu);
 
 void
 swiotlb_sync_single_for_device(struct device *hwdev, dma_addr_t dev_addr,
-			       size_t size, int dir)
+			       size_t size, enum dma_data_direction dir)
 {
 	swiotlb_sync_single(hwdev, dev_addr, size, dir, SYNC_FOR_DEVICE);
 }
@@ -769,7 +757,8 @@ swiotlb_sync_single_range(struct device *hwdev, dma_addr_t dev_addr,
 
 void
 swiotlb_sync_single_range_for_cpu(struct device *hwdev, dma_addr_t dev_addr,
-				  unsigned long offset, size_t size, int dir)
+				  unsigned long offset, size_t size,
+				  enum dma_data_direction dir)
 {
 	swiotlb_sync_single_range(hwdev, dev_addr, offset, size, dir,
 				  SYNC_FOR_CPU);
@@ -778,7 +767,8 @@ EXPORT_SYMBOL_GPL(swiotlb_sync_single_range_for_cpu);
 
 void
 swiotlb_sync_single_range_for_device(struct device *hwdev, dma_addr_t dev_addr,
-				     unsigned long offset, size_t size, int dir)
+				     unsigned long offset, size_t size,
+				     enum dma_data_direction dir)
 {
 	swiotlb_sync_single_range(hwdev, dev_addr, offset, size, dir,
 				  SYNC_FOR_DEVICE);
@@ -803,7 +793,7 @@ EXPORT_SYMBOL_GPL(swiotlb_sync_single_range_for_device);
  */
 int
 swiotlb_map_sg_attrs(struct device *hwdev, struct scatterlist *sgl, int nelems,
-		     int dir, struct dma_attrs *attrs)
+		     enum dma_data_direction dir, struct dma_attrs *attrs)
 {
 	struct scatterlist *sg;
 	int i;
@@ -811,10 +801,10 @@ swiotlb_map_sg_attrs(struct device *hwdev, struct scatterlist *sgl, int nelems,
 	BUG_ON(dir == DMA_NONE);
 
 	for_each_sg(sgl, sg, nelems, i) {
-		void *addr = sg_virt(sg);
-		dma_addr_t dev_addr = swiotlb_virt_to_bus(hwdev, addr);
+		phys_addr_t paddr = sg_phys(sg);
+		dma_addr_t dev_addr = swiotlb_phys_to_bus(hwdev, paddr);
 
-		if (range_needs_mapping(addr, sg->length) ||
+		if (range_needs_mapping(paddr, sg->length) ||
 		    address_needs_mapping(hwdev, dev_addr, sg->length)) {
 			void *map = map_single(hwdev, sg_phys(sg),
 					       sg->length, dir);
@@ -850,7 +840,7 @@ EXPORT_SYMBOL(swiotlb_map_sg);
  */
 void
 swiotlb_unmap_sg_attrs(struct device *hwdev, struct scatterlist *sgl,
-		       int nelems, int dir, struct dma_attrs *attrs)
+		       int nelems, enum dma_data_direction dir, struct dma_attrs *attrs)
 {
 	struct scatterlist *sg;
 	int i;
@@ -858,11 +848,11 @@ swiotlb_unmap_sg_attrs(struct device *hwdev, struct scatterlist *sgl,
 	BUG_ON(dir == DMA_NONE);
 
 	for_each_sg(sgl, sg, nelems, i) {
-		if (sg->dma_address != swiotlb_virt_to_bus(hwdev, sg_virt(sg)))
+		if (sg->dma_address != swiotlb_phys_to_bus(hwdev, sg_phys(sg)))
 			unmap_single(hwdev, swiotlb_bus_to_virt(sg->dma_address),
 				     sg->dma_length, dir);
 		else if (dir == DMA_FROM_DEVICE)
-			dma_mark_clean(sg_virt(sg), sg->dma_length);
+			dma_mark_clean(swiotlb_bus_to_virt(sg->dma_address), sg->dma_length);
 	}
 }
 EXPORT_SYMBOL(swiotlb_unmap_sg_attrs);
@@ -892,17 +882,17 @@ swiotlb_sync_sg(struct device *hwdev, struct scatterlist *sgl,
 	BUG_ON(dir == DMA_NONE);
 
 	for_each_sg(sgl, sg, nelems, i) {
-		if (sg->dma_address != swiotlb_virt_to_bus(hwdev, sg_virt(sg)))
+		if (sg->dma_address != swiotlb_phys_to_bus(hwdev, sg_phys(sg)))
 			sync_single(hwdev, swiotlb_bus_to_virt(sg->dma_address),
 				    sg->dma_length, dir, target);
 		else if (dir == DMA_FROM_DEVICE)
-			dma_mark_clean(sg_virt(sg), sg->dma_length);
+			dma_mark_clean(swiotlb_bus_to_virt(sg->dma_address), sg->dma_length);
 	}
 }
 
 void
 swiotlb_sync_sg_for_cpu(struct device *hwdev, struct scatterlist *sg,
-			int nelems, int dir)
+			int nelems, enum dma_data_direction dir)
 {
 	swiotlb_sync_sg(hwdev, sg, nelems, dir, SYNC_FOR_CPU);
 }
@@ -910,7 +900,7 @@ EXPORT_SYMBOL(swiotlb_sync_sg_for_cpu);
 
 void
 swiotlb_sync_sg_for_device(struct device *hwdev, struct scatterlist *sg,
-			   int nelems, int dir)
+			   int nelems, enum dma_data_direction dir)
 {
 	swiotlb_sync_sg(hwdev, sg, nelems, dir, SYNC_FOR_DEVICE);
 }