Merge tag 'nand/for-4.19' of git://git.infradead.org/linux-mtd into mtd/next

Pull NAND updates from Miquel Raynal:

"
 NAND core changes:
 - Add the SPI-NAND framework.
 - Create a helper to find the best ECC configuration.
 - Create NAND controller operations.
 - Allocate dynamically ONFI parameters structure.
 - Add defines for ONFI version bits.
 - Add manufacturer fixup for ONFI parameter page.
 - Add an option to specify NAND chip as a boot device.
 - Add Reed-Solomon error correction algorithm.
 - Better name for the controller structure.
 - Remove unused caller_is_module() definition.
 - Make subop helpers return unsigned values.
 - Expose _notsupp() helpers for raw page accessors.
 - Add default values for dynamic timings.
 - Kill the chip->scan_bbt() hook.
 - Rename nand_default_bbt() into nand_create_bbt().
 - Start to clean the nand_chip structure.
 - Remove stale prototype from rawnand.h.

 Raw NAND controllers drivers changes:
 - Qcom: structuring cleanup.
 - Denali: use core helper to find the best ECC configuration.
 - Possible build of almost all drivers by adding a dependency on
   COMPILE_TEST for almost all of them in Kconfig, implies various
   fixes, Kconfig cleanup, GPIO headers inclusion cleanup, and even
   changes in sparc64 and ia64 architectures.
 - Clean the ->probe() functions error path of a lot of drivers.
 - Migrate all drivers to use nand_scan() instead of
   nand_scan_ident()/nand_scan_tail() pair.
 - Use mtd_device_register() where applicable to simplify the code.
 - Marvell:
   * Handle on-die ECC.
   * Better clocks handling.
   * Remove bogus comment.
   * Add suspend and resume support.
 - Tegra: add NAND controller driver.
 - Atmel:
   * Add module param to avoid using dma.
   * Drop Wenyou Yang from MAINTAINERS.
 - Denali: optimize timings handling.
 - FSMC: Stop using chip->read_buf().
 - FSL:
   * Switch to SPDX license tag identifiers.
   * Fix qualifiers in MXC init functions.

 Raw NAND chip drivers changes:
 - Micron:
   * Add fixup for ONFI revision.
   * Update ecc_stats.corrected.
   * Make ECC activation stateful.
   * Avoid enabling/disabling ECC when it can't be disabled.
   * Get the actual number of bitflips.
   * Allow forced on-die ECC.
   * Support 8/512 on-die ECC.
   * Fix on-die ECC detection logic.
 - Hynix:
   * Fix decoding the OOB size on H27UCG8T2BTR.
   * Use ->exec_op() in hynix_nand_reg_write_op().
"

13 files changed, 48 insertions, 3298 deletions

diff --git a/lib/Kconfig b/lib/Kconfig
index e34b04b56057..706836ec314d 100644
--- a/lib/Kconfig
+++ b/lib/Kconfig
@@ -420,60 +420,15 @@ config HAS_IOPORT_MAP
 	depends on HAS_IOMEM && !NO_IOPORT_MAP
 	default y
 
-config HAS_DMA
-	bool
-	depends on !NO_DMA
-	default y
+source "kernel/dma/Kconfig"
 
 config SGL_ALLOC
 	bool
 	default n
 
-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 IOMMU_HELPER
 	bool
 
-config ARCH_HAS_SYNC_DMA_FOR_DEVICE
-	bool
-
-config ARCH_HAS_SYNC_DMA_FOR_CPU
-	bool
-	select NEED_DMA_MAP_STATE
-
-config DMA_DIRECT_OPS
-	bool
-	depends on HAS_DMA
-
-config DMA_NONCOHERENT_OPS
-	bool
-	depends on HAS_DMA
-	select DMA_DIRECT_OPS
-
-config DMA_NONCOHERENT_MMAP
-	bool
-	depends on DMA_NONCOHERENT_OPS
-
-config DMA_NONCOHERENT_CACHE_SYNC
-	bool
-	depends on DMA_NONCOHERENT_OPS
-
-config DMA_VIRT_OPS
-	bool
-	depends on HAS_DMA
-
-config SWIOTLB
-	bool
-	select DMA_DIRECT_OPS
-	select NEED_DMA_MAP_STATE
-
 config CHECK_SIGNATURE
 	bool
 
diff --git a/lib/Kconfig.kasan b/lib/Kconfig.kasan
index 3d35d062970d..c253c1b46c6b 100644
--- a/lib/Kconfig.kasan
+++ b/lib/Kconfig.kasan
@@ -6,6 +6,7 @@ if HAVE_ARCH_KASAN
 config KASAN
 	bool "KASan: runtime memory debugger"
 	depends on SLUB || (SLAB && !DEBUG_SLAB)
+	select SLUB_DEBUG if SLUB
 	select CONSTRUCTORS
 	select STACKDEPOT
 	help
diff --git a/lib/Makefile b/lib/Makefile
index e1ee1046abf0..d4a3773ce4a6 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -23,15 +23,12 @@ lib-y := ctype.o string.o vsprintf.o cmdline.o \
 	 sha1.o chacha20.o irq_regs.o argv_split.o \
 	 flex_proportions.o ratelimit.o show_mem.o \
 	 is_single_threaded.o plist.o decompress.o kobject_uevent.o \
-	 earlycpio.o seq_buf.o siphash.o \
+	 earlycpio.o seq_buf.o siphash.o dec_and_lock.o \
 	 nmi_backtrace.o nodemask.o win_minmax.o
 
 lib-$(CONFIG_PRINTK) += dump_stack.o
 lib-$(CONFIG_MMU) += ioremap.o
 lib-$(CONFIG_SMP) += cpumask.o
-lib-$(CONFIG_DMA_DIRECT_OPS) += dma-direct.o
-lib-$(CONFIG_DMA_NONCOHERENT_OPS) += dma-noncoherent.o
-lib-$(CONFIG_DMA_VIRT_OPS) += dma-virt.o
 
 lib-y	+= kobject.o klist.o
 obj-y	+= lockref.o
@@ -98,10 +95,6 @@ obj-$(CONFIG_DEBUG_PREEMPT) += smp_processor_id.o
 obj-$(CONFIG_DEBUG_LIST) += list_debug.o
 obj-$(CONFIG_DEBUG_OBJECTS) += debugobjects.o
 
-ifneq ($(CONFIG_HAVE_DEC_LOCK),y)
-  lib-y += dec_and_lock.o
-endif
-
 obj-$(CONFIG_BITREVERSE) += bitrev.o
 obj-$(CONFIG_RATIONAL)	+= rational.o
 obj-$(CONFIG_CRC_CCITT)	+= crc-ccitt.o
@@ -149,7 +142,6 @@ obj-$(CONFIG_SMP) += percpu_counter.o
 obj-$(CONFIG_AUDIT_GENERIC) += audit.o
 obj-$(CONFIG_AUDIT_COMPAT_GENERIC) += compat_audit.o
 
-obj-$(CONFIG_SWIOTLB) += swiotlb.o
 obj-$(CONFIG_IOMMU_HELPER) += iommu-helper.o
 obj-$(CONFIG_FAULT_INJECTION) += fault-inject.o
 obj-$(CONFIG_NOTIFIER_ERROR_INJECTION) += notifier-error-inject.o
@@ -170,8 +162,6 @@ obj-$(CONFIG_NLATTR) += nlattr.o
 
 obj-$(CONFIG_LRU_CACHE) += lru_cache.o
 
-obj-$(CONFIG_DMA_API_DEBUG) += dma-debug.o
-
 obj-$(CONFIG_GENERIC_CSUM) += checksum.o
 
 obj-$(CONFIG_GENERIC_ATOMIC64) += atomic64.o
diff --git a/lib/dec_and_lock.c b/lib/dec_and_lock.c
index 347fa7ac2e8a..9555b68bb774 100644
--- a/lib/dec_and_lock.c
+++ b/lib/dec_and_lock.c
@@ -33,3 +33,19 @@ int _atomic_dec_and_lock(atomic_t *atomic, spinlock_t *lock)
 }
 
 EXPORT_SYMBOL(_atomic_dec_and_lock);
+
+int _atomic_dec_and_lock_irqsave(atomic_t *atomic, spinlock_t *lock,
+				 unsigned long *flags)
+{
+	/* Subtract 1 from counter unless that drops it to 0 (ie. it was 1) */
+	if (atomic_add_unless(atomic, -1, 1))
+		return 0;
+
+	/* Otherwise do it the slow way */
+	spin_lock_irqsave(lock, *flags);
+	if (atomic_dec_and_test(atomic))
+		return 1;
+	spin_unlock_irqrestore(lock, *flags);
+	return 0;
+}
+EXPORT_SYMBOL(_atomic_dec_and_lock_irqsave);
diff --git a/lib/dma-debug.c b/lib/dma-debug.c
deleted file mode 100644
index c007d25bee09..000000000000
--- a/lib/dma-debug.c
+++ /dev/null
@@ -1,1773 +0,0 @@
-/*
- * 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/sched/task_stack.h>
-#include <linux/scatterlist.h>
-#include <linux/dma-mapping.h>
-#include <linux/sched/task.h>
-#include <linux/stacktrace.h>
-#include <linux/dma-debug.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>
-
-#define HASH_SIZE       1024ULL
-#define HASH_FN_SHIFT   13
-#define HASH_FN_MASK    (HASH_SIZE - 1)
-
-/* allow architectures to override this if absolutely required */
-#ifndef PREALLOC_DMA_DEBUG_ENTRIES
-#define PREALLOC_DMA_DEBUG_ENTRIES (1 << 16)
-#endif
-
-enum {
-	dma_debug_single,
-	dma_debug_page,
-	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
- * @type: single, page, sg, coherent
- * @pfn: page frame of the start address
- * @offset: offset of mapping relative to pfn
- * @size: length of the mapping
- * @direction: enum dma_data_direction
- * @sg_call_ents: 'nents' from dma_map_sg
- * @sg_mapped_ents: 'mapped_ents' from dma_map_sg
- * @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;
-	int              type;
-	unsigned long	 pfn;
-	size_t		 offset;
-	u64              dev_addr;
-	u64              size;
-	int              direction;
-	int		 sg_call_ents;
-	int		 sg_mapped_ents;
-	enum map_err_types  map_err_type;
-#ifdef CONFIG_STACKTRACE
-	struct		 stack_trace stacktrace;
-	unsigned long	 st_entries[DMA_DEBUG_STACKTRACE_ENTRIES];
-#endif
-};
-
-typedef bool (*match_fn)(struct dma_debug_entry *, struct dma_debug_entry *);
-
-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;
-
-/* 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;
-
-/* 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 struct dentry *filter_dent           __read_mostly;
-
-/* 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[5] = { "single", "page",
-				    "scather-gather", "coherent",
-				    "resource" };
-
-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) {
-		pr_warning("Mapped at:\n");
-		print_stack_trace(&entry->stacktrace, 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, "%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)
-{
-	unsigned long __flags = *flags;
-
-	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);
-	}
-}
-
-/*
- * 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.
- *
- * At any time debug_dma_assert_idle() can be called to trigger a
- * warning if any cachelines in the given page are in the active set.
- */
-static RADIX_TREE(dma_active_cacheline, GFP_NOWAIT);
-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.  Otherwise, if maps and unmaps are
-	 * balanced then this overflow may cause false negatives in
-	 * debug_dma_assert_idle() as the cacheline may be marked idle
-	 * prematurely.
-	 */
-	WARN_ONCE(overlap > ACTIVE_CACHELINE_MAX_OVERLAP,
-		  "DMA-API: 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);
-}
-
-/**
- * debug_dma_assert_idle() - assert that a page is not undergoing dma
- * @page: page to lookup in the dma_active_cacheline tree
- *
- * Place a call to this routine in cases where the cpu touching the page
- * before the dma completes (page is dma_unmapped) will lead to data
- * corruption.
- */
-void debug_dma_assert_idle(struct page *page)
-{
-	static struct dma_debug_entry *ents[CACHELINES_PER_PAGE];
-	struct dma_debug_entry *entry = NULL;
-	void **results = (void **) &ents;
-	unsigned int nents, i;
-	unsigned long flags;
-	phys_addr_t cln;
-
-	if (dma_debug_disabled())
-		return;
-
-	if (!page)
-		return;
-
-	cln = (phys_addr_t) page_to_pfn(page) << CACHELINE_PER_PAGE_SHIFT;
-	spin_lock_irqsave(&radix_lock, flags);
-	nents = radix_tree_gang_lookup(&dma_active_cacheline, results, cln,
-				       CACHELINES_PER_PAGE);
-	for (i = 0; i < nents; i++) {
-		phys_addr_t ent_cln = to_cacheline_number(ents[i]);
-
-		if (ent_cln == cln) {
-			entry = ents[i];
-			break;
-		} else if (ent_cln >= cln + CACHELINES_PER_PAGE)
-			break;
-	}
-	spin_unlock_irqrestore(&radix_lock, flags);
-
-	if (!entry)
-		return;
-
-	cln = to_cacheline_number(entry);
-	err_printk(entry->dev, entry,
-		   "DMA-API: cpu touching an active dma mapped cacheline [cln=%pa]\n",
-		   &cln);
-}
-
-/*
- * 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("DMA-API: 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 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;
-}
-
-/* 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;
-	unsigned long flags;
-
-	spin_lock_irqsave(&free_entries_lock, flags);
-
-	if (list_empty(&free_entries)) {
-		global_disable = true;
-		spin_unlock_irqrestore(&free_entries_lock, flags);
-		pr_err("DMA-API: debugging out of memory - disabling\n");
-		return NULL;
-	}
-
-	entry = __dma_entry_alloc();
-
-	spin_unlock_irqrestore(&free_entries_lock, flags);
-
-#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
-
-	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);
-}
-
-int dma_debug_resize_entries(u32 num_entries)
-{
-	int i, delta, ret = 0;
-	unsigned long flags;
-	struct dma_debug_entry *entry;
-	LIST_HEAD(tmp);
-
-	spin_lock_irqsave(&free_entries_lock, flags);
-
-	if (nr_total_entries < num_entries) {
-		delta = num_entries - nr_total_entries;
-
-		spin_unlock_irqrestore(&free_entries_lock, flags);
-
-		for (i = 0; i < delta; i++) {
-			entry = kzalloc(sizeof(*entry), GFP_KERNEL);
-			if (!entry)
-				break;
-
-			list_add_tail(&entry->list, &tmp);
-		}
-
-		spin_lock_irqsave(&free_entries_lock, flags);
-
-		list_splice(&tmp, &free_entries);
-		nr_total_entries += i;
-		num_free_entries += i;
-	} else {
-		delta = nr_total_entries - num_entries;
-
-		for (i = 0; i < delta && !list_empty(&free_entries); i++) {
-			entry = __dma_entry_alloc();
-			kfree(entry);
-		}
-
-		nr_total_entries -= i;
-	}
-
-	if (nr_total_entries != num_entries)
-		ret = 1;
-
-	spin_unlock_irqrestore(&free_entries_lock, flags);
-
-	return ret;
-}
-
-/*
- * 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;
-
-	pr_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 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_M