Merge branch 'iommu/fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/linux-2.6-iommu into x86/urgent

20 files changed, 626 insertions, 494 deletions

diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index 2f22cf4576d..25c3ed594c5 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -360,6 +360,7 @@ config DEBUG_KMEMLEAK
 	select DEBUG_FS if SYSFS
 	select STACKTRACE if STACKTRACE_SUPPORT
 	select KALLSYMS
+	select CRC32
 	help
 	  Say Y here if you want to enable the memory leak
 	  detector. The memory allocation/freeing is traced in a way
@@ -575,7 +576,7 @@ config DEBUG_BUGVERBOSE
 	depends on BUG
 	depends on ARM || AVR32 || M32R || M68K || SPARC32 || SPARC64 || \
 		   FRV || SUPERH || GENERIC_BUG || BLACKFIN || MN10300
-	default !EMBEDDED
+	default y
 	help
 	  Say Y here to make BUG() panics output the file name and line number
 	  of the BUG call as well as the EIP and oops trace.  This aids
diff --git a/lib/argv_split.c b/lib/argv_split.c
index 5205a8dae5b..4b1b083f219 100644
--- a/lib/argv_split.c
+++ b/lib/argv_split.c
@@ -4,17 +4,10 @@
 
 #include <linux/kernel.h>
 #include <linux/ctype.h>
+#include <linux/string.h>
 #include <linux/slab.h>
 #include <linux/module.h>
 
-static const char *skip_sep(const char *cp)
-{
-	while (*cp && isspace(*cp))
-		cp++;
-
-	return cp;
-}
-
 static const char *skip_arg(const char *cp)
 {
 	while (*cp && !isspace(*cp))
@@ -28,7 +21,7 @@ static int count_argc(const char *str)
 	int count = 0;
 
 	while (*str) {
-		str = skip_sep(str);
+		str = skip_spaces(str);
 		if (*str) {
 			count++;
 			str = skip_arg(str);
@@ -82,7 +75,7 @@ char **argv_split(gfp_t gfp, const char *str, int *argcp)
 	argvp = argv;
 
 	while (*str) {
-		str = skip_sep(str);
+		str = skip_spaces(str);
 
 		if (*str) {
 			const char *p = str;
diff --git a/lib/bitmap.c b/lib/bitmap.c
index 702565821c9..11bf4975058 100644
--- a/lib/bitmap.c
+++ b/lib/bitmap.c
@@ -271,6 +271,87 @@ int __bitmap_weight(const unsigned long *bitmap, int bits)
 }
 EXPORT_SYMBOL(__bitmap_weight);
 
+#define BITMAP_FIRST_WORD_MASK(start) (~0UL << ((start) % BITS_PER_LONG))
+
+void bitmap_set(unsigned long *map, int start, int nr)
+{
+	unsigned long *p = map + BIT_WORD(start);
+	const int size = start + nr;
+	int bits_to_set = BITS_PER_LONG - (start % BITS_PER_LONG);
+	unsigned long mask_to_set = BITMAP_FIRST_WORD_MASK(start);
+
+	while (nr - bits_to_set >= 0) {
+		*p |= mask_to_set;
+		nr -= bits_to_set;
+		bits_to_set = BITS_PER_LONG;
+		mask_to_set = ~0UL;
+		p++;
+	}
+	if (nr) {
+		mask_to_set &= BITMAP_LAST_WORD_MASK(size);
+		*p |= mask_to_set;
+	}
+}
+EXPORT_SYMBOL(bitmap_set);
+
+void bitmap_clear(unsigned long *map, int start, int nr)
+{
+	unsigned long *p = map + BIT_WORD(start);
+	const int size = start + nr;
+	int bits_to_clear = BITS_PER_LONG - (start % BITS_PER_LONG);
+	unsigned long mask_to_clear = BITMAP_FIRST_WORD_MASK(start);
+
+	while (nr - bits_to_clear >= 0) {
+		*p &= ~mask_to_clear;
+		nr -= bits_to_clear;
+		bits_to_clear = BITS_PER_LONG;
+		mask_to_clear = ~0UL;
+		p++;
+	}
+	if (nr) {
+		mask_to_clear &= BITMAP_LAST_WORD_MASK(size);
+		*p &= ~mask_to_clear;
+	}
+}
+EXPORT_SYMBOL(bitmap_clear);
+
+/*
+ * bitmap_find_next_zero_area - find a contiguous aligned zero area
+ * @map: The address to base the search on
+ * @size: The bitmap size in bits
+ * @start: The bitnumber to start searching at
+ * @nr: The number of zeroed bits we're looking for
+ * @align_mask: Alignment mask for zero area
+ *
+ * The @align_mask should be one less than a power of 2; the effect is that
+ * the bit offset of all zero areas this function finds is multiples of that
+ * power of 2. A @align_mask of 0 means no alignment is required.
+ */
+unsigned long bitmap_find_next_zero_area(unsigned long *map,
+					 unsigned long size,
+					 unsigned long start,
+					 unsigned int nr,
+					 unsigned long align_mask)
+{
+	unsigned long index, end, i;
+again:
+	index = find_next_zero_bit(map, size, start);
+
+	/* Align allocation */
+	index = __ALIGN_MASK(index, align_mask);
+
+	end = index + nr;
+	if (end > size)
+		return end;
+	i = find_next_bit(map, end, index);
+	if (i < end) {
+		start = i + 1;
+		goto again;
+	}
+	return index;
+}
+EXPORT_SYMBOL(bitmap_find_next_zero_area);
+
 /*
  * Bitmap printing & parsing functions: first version by Bill Irwin,
  * second version by Paul Jackson, third by Joe Korty.
diff --git a/lib/checksum.c b/lib/checksum.c
index b2e2fd46846..097508732f3 100644
--- a/lib/checksum.c
+++ b/lib/checksum.c
@@ -37,7 +37,8 @@
 
 #include <asm/byteorder.h>
 
-static inline unsigned short from32to16(unsigned long x)
+#ifndef do_csum
+static inline unsigned short from32to16(unsigned int x)
 {
 	/* add up 16-bit and 16-bit for 16+c bit */
 	x = (x & 0xffff) + (x >> 16);
@@ -49,16 +50,16 @@ static inline unsigned short from32to16(unsigned long x)
 static unsigned int do_csum(const unsigned char *buff, int len)
 {
 	int odd, count;
-	unsigned long result = 0;
+	unsigned int result = 0;
 
 	if (len <= 0)
 		goto out;
 	odd = 1 & (unsigned long) buff;
 	if (odd) {
 #ifdef __LITTLE_ENDIAN
-		result = *buff;
-#else
 		result += (*buff << 8);
+#else
+		result = *buff;
 #endif
 		len--;
 		buff++;
@@ -73,9 +74,9 @@ static unsigned int do_csum(const unsigned char *buff, int len)
 		}
 		count >>= 1;		/* nr of 32-bit words.. */
 		if (count) {
-			unsigned long carry = 0;
+			unsigned int carry = 0;
 			do {
-				unsigned long w = *(unsigned int *) buff;
+				unsigned int w = *(unsigned int *) buff;
 				count--;
 				buff += 4;
 				result += carry;
@@ -102,6 +103,7 @@ static unsigned int do_csum(const unsigned char *buff, int len)
 out:
 	return result;
 }
+#endif
 
 /*
  *	This is a version of ip_compute_csum() optimized for IP headers,
diff --git a/lib/crc32.c b/lib/crc32.c
index 49d1c9e3ce3..02e3b31b3a7 100644
--- a/lib/crc32.c
+++ b/lib/crc32.c
@@ -42,6 +42,48 @@ MODULE_AUTHOR("Matt Domsch <Matt_Domsch@dell.com>");
 MODULE_DESCRIPTION("Ethernet CRC32 calculations");
 MODULE_LICENSE("GPL");
 
+#if CRC_LE_BITS == 8 || CRC_BE_BITS == 8
+
+static inline u32
+crc32_body(u32 crc, unsigned char const *buf, size_t len, const u32 *tab)
+{
+# ifdef __LITTLE_ENDIAN
+#  define DO_CRC(x) crc = tab[(crc ^ (x)) & 255 ] ^ (crc >> 8)
+# else
+#  define DO_CRC(x) crc = tab[((crc >> 24) ^ (x)) & 255] ^ (crc << 8)
+# endif
+	const u32 *b = (const u32 *)buf;
+	size_t    rem_len;
+
+	/* Align it */
+	if (unlikely((long)b & 3 && len)) {
+		u8 *p = (u8 *)b;
+		do {
+			DO_CRC(*p++);
+		} while ((--len) && ((long)p)&3);
+		b = (u32 *)p;
+	}
+	rem_len = len & 3;
+	/* load data 32 bits wide, xor data 32 bits wide. */
+	len = len >> 2;
+	for (--b; len; --len) {
+		crc ^= *++b; /* use pre increment for speed */
+		DO_CRC(0);
+		DO_CRC(0);
+		DO_CRC(0);
+		DO_CRC(0);
+	}
+	len = rem_len;
+	/* And the last few bytes */
+	if (len) {
+		u8 *p = (u8 *)(b + 1) - 1;
+		do {
+			DO_CRC(*++p); /* use pre increment for speed */
+		} while (--len);
+	}
+	return crc;
+}
+#endif
 /**
  * crc32_le() - Calculate bitwise little-endian Ethernet AUTODIN II CRC32
  * @crc: seed value for computation.  ~0 for Ethernet, sometimes 0 for
@@ -72,48 +114,10 @@ u32 __pure crc32_le(u32 crc, unsigned char const *p, size_t len)
 u32 __pure crc32_le(u32 crc, unsigned char const *p, size_t len)
 {
 # if CRC_LE_BITS == 8
-	const u32      *b =(u32 *)p;
 	const u32      *tab = crc32table_le;
 
-# ifdef __LITTLE_ENDIAN
-#  define DO_CRC(x) crc = tab[ (crc ^ (x)) & 255 ] ^ (crc>>8)
-# else
-#  define DO_CRC(x) crc = tab[ ((crc >> 24) ^ (x)) & 255] ^ (crc<<8)
-# endif
-
 	crc = __cpu_to_le32(crc);
-	/* Align it */
-	if(unlikely(((long)b)&3 && len)){
-		do {
-			u8 *p = (u8 *)b;
-			DO_CRC(*p++);
-			b = (void *)p;
-		} while ((--len) && ((long)b)&3 );
-	}
-	if(likely(len >= 4)){
-		/* load data 32 bits wide, xor data 32 bits wide. */
-		size_t save_len = len & 3;
-	        len = len >> 2;
-		--b; /* use pre increment below(*++b) for speed */
-		do {
-			crc ^= *++b;
-			DO_CRC(0);
-			DO_CRC(0);
-			DO_CRC(0);
-			DO_CRC(0);
-		} while (--len);
-		b++; /* point to next byte(s) */
-		len = save_len;
-	}
-	/* And the last few bytes */
-	if(len){
-		do {
-			u8 *p = (u8 *)b;
-			DO_CRC(*p++);
-			b = (void *)p;
-		} while (--len);
-	}
-
+	crc = crc32_body(crc, p, len, tab);
 	return __le32_to_cpu(crc);
 #undef ENDIAN_SHIFT
 #undef DO_CRC
@@ -170,47 +174,10 @@ u32 __pure crc32_be(u32 crc, unsigned char const *p, size_t len)
 u32 __pure crc32_be(u32 crc, unsigned char const *p, size_t len)
 {
 # if CRC_BE_BITS == 8
-	const u32      *b =(u32 *)p;
 	const u32      *tab = crc32table_be;
 
-# ifdef __LITTLE_ENDIAN
-#  define DO_CRC(x) crc = tab[ (crc ^ (x)) & 255 ] ^ (crc>>8)
-# else
-#  define DO_CRC(x) crc = tab[ ((crc >> 24) ^ (x)) & 255] ^ (crc<<8)
-# endif
-
 	crc = __cpu_to_be32(crc);
-	/* Align it */
-	if(unlikely(((long)b)&3 && len)){
-		do {
-			u8 *p = (u8 *)b;
-			DO_CRC(*p++);
-			b = (u32 *)p;
-		} while ((--len) && ((long)b)&3 );
-	}
-	if(likely(len >= 4)){
-		/* load data 32 bits wide, xor data 32 bits wide. */
-		size_t save_len = len & 3;
-	        len = len >> 2;
-		--b; /* use pre increment below(*++b) for speed */
-		do {
-			crc ^= *++b;
-			DO_CRC(0);
-			DO_CRC(0);
-			DO_CRC(0);
-			DO_CRC(0);
-		} while (--len);
-		b++; /* point to next byte(s) */
-		len = save_len;
-	}
-	/* And the last few bytes */
-	if(len){
-		do {
-			u8 *p = (u8 *)b;
-			DO_CRC(*p++);
-			b = (void *)p;
-		} while (--len);
-	}
+	crc = crc32_body(crc, p, len, tab);
 	return __be32_to_cpu(crc);
 #undef ENDIAN_SHIFT
 #undef DO_CRC
diff --git a/lib/ctype.c b/lib/ctype.c
index d02ace14a32..26baa620e95 100644
--- a/lib/ctype.c
+++ b/lib/ctype.c
@@ -7,30 +7,30 @@
 #include <linux/ctype.h>
 #include <linux/module.h>
 
-unsigned char _ctype[] = {
-_C,_C,_C,_C,_C,_C,_C,_C,			/* 0-7 */
-_C,_C|_S,_C|_S,_C|_S,_C|_S,_C|_S,_C,_C,		/* 8-15 */
-_C,_C,_C,_C,_C,_C,_C,_C,			/* 16-23 */
-_C,_C,_C,_C,_C,_C,_C,_C,			/* 24-31 */
-_S|_SP,_P,_P,_P,_P,_P,_P,_P,			/* 32-39 */
-_P,_P,_P,_P,_P,_P,_P,_P,			/* 40-47 */
-_D,_D,_D,_D,_D,_D,_D,_D,			/* 48-55 */
-_D,_D,_P,_P,_P,_P,_P,_P,			/* 56-63 */
-_P,_U|_X,_U|_X,_U|_X,_U|_X,_U|_X,_U|_X,_U,	/* 64-71 */
-_U,_U,_U,_U,_U,_U,_U,_U,			/* 72-79 */
-_U,_U,_U,_U,_U,_U,_U,_U,			/* 80-87 */
-_U,_U,_U,_P,_P,_P,_P,_P,			/* 88-95 */
-_P,_L|_X,_L|_X,_L|_X,_L|_X,_L|_X,_L|_X,_L,	/* 96-103 */
-_L,_L,_L,_L,_L,_L,_L,_L,			/* 104-111 */
-_L,_L,_L,_L,_L,_L,_L,_L,			/* 112-119 */
-_L,_L,_L,_P,_P,_P,_P,_C,			/* 120-127 */
-0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,		/* 128-143 */
-0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,		/* 144-159 */
-_S|_SP,_P,_P,_P,_P,_P,_P,_P,_P,_P,_P,_P,_P,_P,_P,_P,   /* 160-175 */
-_P,_P,_P,_P,_P,_P,_P,_P,_P,_P,_P,_P,_P,_P,_P,_P,       /* 176-191 */
-_U,_U,_U,_U,_U,_U,_U,_U,_U,_U,_U,_U,_U,_U,_U,_U,       /* 192-207 */
-_U,_U,_U,_U,_U,_U,_U,_P,_U,_U,_U,_U,_U,_U,_U,_L,       /* 208-223 */
-_L,_L,_L,_L,_L,_L,_L,_L,_L,_L,_L,_L,_L,_L,_L,_L,       /* 224-239 */
-_L,_L,_L,_L,_L,_L,_L,_P,_L,_L,_L,_L,_L,_L,_L,_L};      /* 240-255 */
+const unsigned char _ctype[] = {
+_C,_C,_C,_C,_C,_C,_C,_C,				/* 0-7 */
+_C,_C|_S,_C|_S,_C|_S,_C|_S,_C|_S,_C,_C,			/* 8-15 */
+_C,_C,_C,_C,_C,_C,_C,_C,				/* 16-23 */
+_C,_C,_C,_C,_C,_C,_C,_C,				/* 24-31 */
+_S|_SP,_P,_P,_P,_P,_P,_P,_P,				/* 32-39 */
+_P,_P,_P,_P,_P,_P,_P,_P,				/* 40-47 */
+_D,_D,_D,_D,_D,_D,_D,_D,				/* 48-55 */
+_D,_D,_P,_P,_P,_P,_P,_P,				/* 56-63 */
+_P,_U|_X,_U|_X,_U|_X,_U|_X,_U|_X,_U|_X,_U,		/* 64-71 */
+_U,_U,_U,_U,_U,_U,_U,_U,				/* 72-79 */
+_U,_U,_U,_U,_U,_U,_U,_U,				/* 80-87 */
+_U,_U,_U,_P,_P,_P,_P,_P,				/* 88-95 */
+_P,_L|_X,_L|_X,_L|_X,_L|_X,_L|_X,_L|_X,_L,		/* 96-103 */
+_L,_L,_L,_L,_L,_L,_L,_L,				/* 104-111 */
+_L,_L,_L,_L,_L,_L,_L,_L,				/* 112-119 */
+_L,_L,_L,_P,_P,_P,_P,_C,				/* 120-127 */
+0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,			/* 128-143 */
+0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,			/* 144-159 */
+_S|_SP,_P,_P,_P,_P,_P,_P,_P,_P,_P,_P,_P,_P,_P,_P,_P,	/* 160-175 */
+_P,_P,_P,_P,_P,_P,_P,_P,_P,_P,_P,_P,_P,_P,_P,_P,	/* 176-191 */
+_U,_U,_U,_U,_U,_U,_U,_U,_U,_U,_U,_U,_U,_U,_U,_U,	/* 192-207 */
+_U,_U,_U,_U,_U,_U,_U,_P,_U,_U,_U,_U,_U,_U,_U,_L,	/* 208-223 */
+_L,_L,_L,_L,_L,_L,_L,_L,_L,_L,_L,_L,_L,_L,_L,_L,	/* 224-239 */
+_L,_L,_L,_L,_L,_L,_L,_P,_L,_L,_L,_L,_L,_L,_L,_L};	/* 240-255 */
 
 EXPORT_SYMBOL(_ctype);
diff --git a/lib/debugobjects.c b/lib/debugobjects.c
index eae56fddfa3..a9a8996d286 100644
--- a/lib/debugobjects.c
+++ b/lib/debugobjects.c
@@ -26,14 +26,14 @@
 
 struct debug_bucket {
 	struct hlist_head	list;
-	spinlock_t		lock;
+	raw_spinlock_t		lock;
 };
 
 static struct debug_bucket	obj_hash[ODEBUG_HASH_SIZE];
 
 static struct debug_obj		obj_static_pool[ODEBUG_POOL_SIZE] __initdata;
 
-static DEFINE_SPINLOCK(pool_lock);
+static DEFINE_RAW_SPINLOCK(pool_lock);
 
 static HLIST_HEAD(obj_pool);
 
@@ -96,10 +96,10 @@ static int fill_pool(void)
 		if (!new)
 			return obj_pool_free;
 
-		spin_lock_irqsave(&pool_lock, flags);
+		raw_spin_lock_irqsave(&pool_lock, flags);
 		hlist_add_head(&new->node, &obj_pool);
 		obj_pool_free++;
-		spin_unlock_irqrestore(&pool_lock, flags);
+		raw_spin_unlock_irqrestore(&pool_lock, flags);
 	}
 	return obj_pool_free;
 }
@@ -133,7 +133,7 @@ alloc_object(void *addr, struct debug_bucket *b, struct debug_obj_descr *descr)
 {
 	struct debug_obj *obj = NULL;
 
-	spin_lock(&pool_lock);
+	raw_spin_lock(&pool_lock);
 	if (obj_pool.first) {
 		obj	    = hlist_entry(obj_pool.first, typeof(*obj), node);
 
@@ -152,7 +152,7 @@ alloc_object(void *addr, struct debug_bucket *b, struct debug_obj_descr *descr)
 		if (obj_pool_free < obj_pool_min_free)
 			obj_pool_min_free = obj_pool_free;
 	}
-	spin_unlock(&pool_lock);
+	raw_spin_unlock(&pool_lock);
 
 	return obj;
 }
@@ -165,7 +165,7 @@ static void free_obj_work(struct work_struct *work)
 	struct debug_obj *obj;
 	unsigned long flags;
 
-	spin_lock_irqsave(&pool_lock, flags);
+	raw_spin_lock_irqsave(&pool_lock, flags);
 	while (obj_pool_free > ODEBUG_POOL_SIZE) {
 		obj = hlist_entry(obj_pool.first, typeof(*obj), node);
 		hlist_del(&obj->node);
@@ -174,11 +174,11 @@ static void free_obj_work(struct work_struct *work)
 		 * We release pool_lock across kmem_cache_free() to
 		 * avoid contention on pool_lock.
 		 */
-		spin_unlock_irqrestore(&pool_lock, flags);
+		raw_spin_unlock_irqrestore(&pool_lock, flags);
 		kmem_cache_free(obj_cache, obj);
-		spin_lock_irqsave(&pool_lock, flags);
+		raw_spin_lock_irqsave(&pool_lock, flags);
 	}
-	spin_unlock_irqrestore(&pool_lock, flags);
+	raw_spin_unlock_irqrestore(&pool_lock, flags);
 }
 
 /*
@@ -190,7 +190,7 @@ static void free_object(struct debug_obj *obj)
 	unsigned long flags;
 	int sched = 0;
 
-	spin_lock_irqsave(&pool_lock, flags);
+	raw_spin_lock_irqsave(&pool_lock, flags);
 	/*
 	 * schedule work when the pool is filled and the cache is
 	 * initialized:
@@ -200,7 +200,7 @@ static void free_object(struct debug_obj *obj)
 	hlist_add_head(&obj->node, &obj_pool);
 	obj_pool_free++;
 	obj_pool_used--;
-	spin_unlock_irqrestore(&pool_lock, flags);
+	raw_spin_unlock_irqrestore(&pool_lock, flags);
 	if (sched)
 		schedule_work(&debug_obj_work);
 }
@@ -221,9 +221,9 @@ static void debug_objects_oom(void)
 	printk(KERN_WARNING "ODEBUG: Out of memory. ODEBUG disabled\n");
 
 	for (i = 0; i < ODEBUG_HASH_SIZE; i++, db++) {
-		spin_lock_irqsave(&db->lock, flags);
+		raw_spin_lock_irqsave(&db->lock, flags);
 		hlist_move_list(&db->list, &freelist);
-		spin_unlock_irqrestore(&db->lock, flags);
+		raw_spin_unlock_irqrestore(&db->lock, flags);
 
 		/* Now free them */
 		hlist_for_each_entry_safe(obj, node, tmp, &freelist, node) {
@@ -303,14 +303,14 @@ __debug_object_init(void *addr, struct debug_obj_descr *descr, int onstack)
 
 	db = get_bucket((unsigned long) addr);
 
-	spin_lock_irqsave(&db->lock, flags);
+	raw_spin_lock_irqsave(&db->lock, flags);
 
 	obj = lookup_object(addr, db);
 	if (!obj) {
 		obj = alloc_object(addr, db, descr);
 		if (!obj) {
 			debug_objects_enabled = 0;
-			spin_unlock_irqrestore(&db->lock, flags);
+			raw_spin_unlock_irqrestore(&db->lock, flags);
 			debug_objects_oom();
 			return;
 		}
@@ -327,7 +327,7 @@ __debug_object_init(void *addr, struct debug_obj_descr *descr, int onstack)
 	case ODEBUG_STATE_ACTIVE:
 		debug_print_object(obj, "init");
 		state = obj->state;
-		spin_unlock_irqrestore(&db->lock, flags);
+		raw_spin_unlock_irqrestore(&db->lock, flags);
 		debug_object_fixup(descr->fixup_init, addr, state);
 		return;
 
@@ -338,7 +338,7 @@ __debug_object_init(void *addr, struct debug_obj_descr *descr, int onstack)
 		break;
 	}
 
-	spin_unlock_irqrestore(&db->lock, flags);
+	raw_spin_unlock_irqrestore(&db->lock, flags);
 }
 
 /**
@@ -385,7 +385,7 @@ void debug_object_activate(void *addr, struct debug_obj_descr *descr)
 
 	db = get_bucket((unsigned long) addr);
 
-	spin_lock_irqsave(&db->lock, flags);
+	raw_spin_lock_irqsave(&db->lock, flags);
 
 	obj = lookup_object(addr, db);
 	if (obj) {
@@ -398,7 +398,7 @@ void debug_object_activate(void *addr, struct debug_obj_descr *descr)
 		case ODEBUG_STATE_ACTIVE:
 			debug_print_object(obj, "activate");
 			state = obj->state;
-			spin_unlock_irqrestore(&db->lock, flags);
+			raw_spin_unlock_irqrestore(&db->lock, flags);
 			debug_object_fixup(descr->fixup_activate, addr, state);
 			return;
 
@@ -408,11 +408,11 @@ void debug_object_activate(void *addr, struct debug_obj_descr *descr)
 		default:
 			break;
 		}
-		spin_unlock_irqrestore(&db->lock, flags);
+		raw_spin_unlock_irqrestore(&db->lock, flags);
 		return;
 	}
 
-	spin_unlock_irqrestore(&db->lock, flags);
+	raw_spin_unlock_irqrestore(&db->lock, flags);
 	/*
 	 * This happens when a static object is activated. We
 	 * let the type specific code decide whether this is
@@ -438,7 +438,7 @@ void debug_object_deactivate(void *addr, struct debug_obj_descr *descr)
 
 	db = get_bucket((unsigned long) addr);
 
-	spin_lock_irqsave(&db->lock, flags);
+	raw_spin_lock_irqsave(&db->lock, flags);
 
 	obj = lookup_object(addr, db);
 	if (obj) {
@@ -463,7 +463,7 @@ void debug_object_deactivate(void *addr, struct debug_obj_descr *descr)
 		debug_print_object(&o, "deactivate");
 	}
 
-	spin_unlock_irqrestore(&db->lock, flags);
+	raw_spin_unlock_irqrestore(&db->lock, flags);
 }
 
 /**
@@ -483,7 +483,7 @@ void debug_object_destroy(void *addr, struct debug_obj_descr *descr)
 
 	db = get_bucket((unsigned long) addr);
 
-	spin_lock_irqsave(&db->lock, flags);
+	raw_spin_lock_irqsave(&db->lock, flags);
 
 	obj = lookup_object(addr, db);
 	if (!obj)
@@ -498,7 +498,7 @@ void debug_object_destroy(void *addr, struct debug_obj_descr *descr)
 	case ODEBUG_STATE_ACTIVE:
 		debug_print_object(obj, "destroy");
 		state = obj->state;
-		spin_unlock_irqrestore(&db->lock, flags);
+		raw_spin_unlock_irqrestore(&db->lock, flags);
 		debug_object_fixup(descr->fixup_destroy, addr, state);
 		return;
 
@@ -509,7 +509,7 @@ void debug_object_destroy(void *addr, struct debug_obj_descr *descr)
 		break;
 	}
 out_unlock:
-	spin_unlock_irqrestore(&db->lock, flags);
+	raw_spin_unlock_irqrestore(&db->lock, flags);
 }
 
 /**
@@ -529,7 +529,7 @@ void debug_object_free(void *addr, struct debug_obj_descr *descr)
 
 	db = get_bucket((unsigned long) addr);
 
-	spin_lock_irqsave(&db->lock, flags);
+	raw_spin_lock_irqsave(&db->lock, flags);
 
 	obj = lookup_object(addr, db);
 	if (!obj)
@@ -539,17 +539,17 @@ void debug_object_free(void *addr, struct debug_obj_descr *descr)
 	case ODEBUG_STATE_ACTIVE:
 		debug_print_object(obj, "free");
 		state = obj->state;
-		spin_unlock_irqrestore(&db->lock, flags);
+		raw_spin_unlock_irqrestore(&db->lock, flags);
 		debug_object_fixup(descr->fixup_free, addr, state);
 		return;
 	default:
 		hlist_del(&obj->node);
-		spin_unlock_irqrestore(&db->lock, flags);
+		raw_spin_unlock_irqrestore(&db->lock, flags);
 		free_object(obj);
 		return;
 	}
 out_unlock:
-	spin_unlock_irqrestore(&db->lock, flags);
+	raw_spin_unlock_irqrestore(&db->lock, flags);
 }
 
 #ifdef CONFIG_DEBUG_OBJECTS_FREE
@@ -575,7 +575,7 @@ static void __debug_check_no_obj_freed(const void *address, unsigned long size)
 
 repeat:
 		cnt = 0;
-		spin_lock_irqsave(&db->lock, flags);
+		raw_spin_lock_irqsave(&db->lock, flags);
 		hlist_for_each_entry_safe(obj, node, tmp, &db->list, node) {
 			cnt++;
 			oaddr = (unsigned long) obj->object;
@@ -587,7 +587,7 @@ repeat:
 				debug_print_object(obj, "free");
 				descr = obj->descr;
 				state = obj->state;
-				spin_unlock_irqrestore(&db->lock, flags);
+				raw_spin_unlock_irqrestore(&db->lock, flags);
 				debug_object_fixup(descr->fixup_free,
 						   (void *) oaddr, state);
 				goto repeat;
@@ -597,7 +597,7 @@ repeat:
 				break;
 			}
 		}
-		spin_unlock_irqrestore(&db->lock, flags);
+		raw_spin_unlock_irqrestore(&db->lock, flags);
 
 		/* Now free them */
 		hlist_for_each_entry_safe(obj, node, tmp, &freelist, node) {
@@ -783,7 +783,7 @@ check_results(void *addr, enum debug_obj_state state, int fixups, int warnings)
 
 	db = get_bucket((unsigned long) addr);
 
-	spin_lock_irqsave(&db->lock, flags);
+	raw_spin_lock_irqsave(&db->lock, flags);
 
 	obj = lookup_object(addr, db);
 	if (!obj && state != ODEBUG_STATE_NONE) {
@@ -807,7 +807,7 @@ check_results(void *addr, enum debug_obj_state state, int fixups, int warnings)
 	}
 	res = 0;
 out:
-	spin_unlock_irqrestore(&db->lock, flags);
+	raw_spin_unlock_irqrestore(&db->lock, flags);
 	if (res)
 		debug_objects_enabled = 0;
 	return res;
@@ -907,7 +907,7 @@ void __init debug_objects_early_init(void)
 	int i;
 
 	for (i = 0; i < ODEBUG_HASH_SIZE; i++)
-		spin_lock_init(&obj_hash[i].lock);
+		raw_spin_lock_init(&obj_hash[i].lock);
 
 	for (i = 0; i < ODEBUG_POOL_SIZE; i++)
 		hlist_add_head(&obj_static_pool[i].node, &obj_pool);
diff --git a/lib/dma-debug.c b/lib/dma-debug.c
index d9b08e0f7f5..739974460c3 100644
--- a/lib/dma-debug.c
+++ b/lib/dma-debug.c
@@ -676,6 +676,8 @@ static int dma_debug_device_change(struct notifier_block *nb,
 	struct device *dev = data;
 	int count;
 
+	if (global_disable)
+		return;
 
 	switch (action) {
 	case BUS_NOTIFY_UNBOUND_DRIVER:
@@ -697,6 +699,9 @@ void dma_debug_add_bus(struct bus_type *bus)
 {
 	struct notifier_block *nb;
 
+	if (global_disable)
+		return;
+
 	nb = kzalloc(sizeof(struct notifier_block), GFP_KERNEL);
 	if (nb == NULL) {
 		pr_err("dma_debug_add_bus: out of memory\n");
diff --git a/lib/dynamic_debug.c b/lib/dynamic_debug.c
index e22c148e4b7..f9350291598 100644
--- a/lib/dynamic_debug.c
+++ b/lib/dynamic_debug.c
@@ -21,6 +21,7 @@
 #include <linux/list.h>
 #include <linux/sysctl.h>
 #include <linux/ctype.h>
+#include <linux/string.h>
 #include <linux/uaccess.h>
 #include <linux/dynamic_debug.h>
 #include <linux/debugfs.h>
@@ -209,8 +210,7 @@ static int ddebug_tokenize(char *buf, char *words[], int maxwords)
 		char *end;
 
 		/* Skip leading whitespace */
-		while (*buf && isspace(*buf))
-			buf++;
+		buf = skip_spaces(buf);
 		if (!*buf)
 			break;	/* oh, it was trailing whitespace */
 
diff --git a/lib/genalloc.c b/lib/genalloc.c
index eed2bdb865e..e67f97495dd 100644
--- a/lib/genalloc.c
+++ b/lib/genalloc.c
@@ -11,6 +11,7 @@
  */
 
 #include <linux/module.h>
+#include <linux/bitmap.h>
 #include <linux/genalloc.h>
 
 
@@ -114,7 +115,7 @@ unsigned long gen_pool_alloc(struct gen_pool *pool, size_t size)
 	struct gen_pool_chunk *chunk;
 	unsigned long addr, flags;
 	int order = pool->min_alloc_order;
-	int nbits, bit, start_bit, end_bit;
+	int nbits, start_bit, end_bit;
 
 	if (size == 0)
 		return 0;
@@ -129,29 +130,19 @@ unsigned long gen_pool_alloc(struct gen_pool *pool, size_t size)
 		end_bit -= nbits + 1;
 
 		spin_lock_irqsave(&chunk->lock, flags);
-		bit = -1;
-		while (bit + 1 < end_bit) {
-			bit = find_next_zero_bit(chunk->bits, end_bit, bit + 1);
-			if (bit >= end_bit)
-				break;
-
-			start_bit = bit;
-			if (nbits > 1) {
-				bit = find_next_bit(chunk->bits, bit + nbits,
-							bit + 1);
-				if (bit - start_bit < nbits)
-					continue;
-			}
-
-			addr = chunk->start_addr +
-					    ((unsigned long)start_bit << order);
-			while (nbits--)
-				__set_bit(start_bit++, chunk->bits);
+		start_bit = bitmap_find_next_zero_area(chunk->bits, end_bit, 0,
+						nbits, 0);
+		if (start_bit >= end_bit) {
 			spin_unlock_irqrestore(&chunk->lock, flags);
-			read_unlock(&pool->lock);
-			return addr;
+			continue;
 		}
+
+		addr = chunk->start_addr + ((unsigned long)start_bit << order);
+
+		bitmap_set(chunk->bits, start_bit, nbits);
 		spin_unlock_irqrestore(&chunk->lock, flags);
+		read_unlock(&pool->lock);
+		return addr;
 	}
 	read_unlock(&pool->lock);
 	return 0;
diff --git a/lib/iommu-helper.c b/lib/iommu-helper.c
index 75dbda03f4f..c0251f4ad08 100644
--- a/lib/iommu-helper.c
+++ b/lib/iommu-helper.c
@@ -3,41 +3,7 @@
  */
 
 #include <linux/module.h>
-#include <linux/bitops.h>
-
-static unsigned long find_next_zero_area(unsigned long *map,
-					 unsigned long size,
-					 unsigned long start,
-					 unsigned int nr,
-					 unsigned long align_mask)
-{
-	unsigned long index, end, i;
-again:
-	index = find_next_zero_bit(map, size, start);
-
-	/* Align allocation */
-	index = (index + align_mask) & ~align_mask;
-
-	end = index + nr;
-	if (end >= size)
-		return -1;
-	for (i = index; i < end; i++) {
-		if (test_bit(i, map)) {
-			start = i+1;
-			goto again;
-		}
-	}
-	return index;
-}
-
-void iommu_area_reserve(unsigned long *map, unsigned long i, int len)
-{
-	unsigned long end = i + len;
-	while (i < end) {
-		__set_bit(i, map);
-		i++;
-	}
-}
+#include <linux/bitmap.h>
 
 int iommu_is_span_boundary(unsigned int index, unsigned int nr,
 			   unsigned long shift,
@@ -55,31 +21,24 @@ unsigned long iommu_area_alloc(unsigned long *map, unsigned long size,
 			       unsigned long align_mask)
 {
 	unsigned long index;
+
+	/* We don't want the last of the limit */
+	size -= 1;
 again:
-	index = find_next_zero_area(map, size, start, nr, align_mask);
-	if (index != -1) {
+	index = bitmap_find_next_zero_area(map, size, start, nr, align_mask);
+	if (index < size) {
 		if (iommu_is_span_boundary(index, nr, shift, boundary_size)) {
 			/* we could do more effectively */
 			start = index + 1;
 			goto again;
 		}
-		iommu_area_reserve(map, index, nr);
+		bitmap_set(map, index, nr);
+		return index;
 	}
-	return index;
+	return -1;
 }
 EXPORT_SYMBOL(iommu_area_alloc);
 
-void iommu_area_free(unsigned long *map, unsigned long start, unsigned int nr)
-{
-	unsigned long end = start + nr;
-
-	while (start < end) {
-		__clear_bit(start, map);
-		start++;
-	}
-}
-EXPORT_SYMBOL(iommu_area_free);
-
 unsigned long iommu_num_pages(unsigned long addr, unsigned long len,
 			      unsigned long io_page_size)
 {
diff --git a/lib/kernel_lock.c b/lib/kernel_lock.c
index 4ebfa5a164d..b135d04aa48 100644
--- a/lib/kernel_lock.c
+++ b/lib/kernel_lock.c
@@ -23,7 +23,7 @@
  *
  * Don't use in new code.
  */
-static  __cacheline_aligned_in_smp DEFINE_SPINLOCK(kernel_flag);
+static  __cacheline_aligned_in_smp DEFINE_RAW_SPINLOCK(kernel_flag);
 
 
 /*
@@ -36,12 +36,12 @@ static  __cacheline_aligned_in_smp DEFINE_SPINLOCK(kernel_flag);
  * If it successfully gets the lock, it should increment
  * the preemption count like any spinlock does.
  *
- * (This works on UP too - _raw_spin_trylock will never
+ * (This works on UP too - do_raw_spin_trylock will never
  * return false in that case)
  */
 int __lockfunc __reacquire_kernel_lock(void)
 {
-	while (!_raw_spin_trylock(&kernel_flag)) {
+	while (!do_raw_spin_trylock(&kernel_flag)) {
 		if (need_resched())
 			return -EAGAIN;
 		cpu_relax();
@@ -52,27 +52,27 @@ int __lockfunc __reacquire_kernel_lock(void)
 
 void __lockfunc __release_kernel_lock(void)
 {
-	_raw_spin_unlock(&kernel_flag);
+	do_raw_spin_unlock(&kernel_flag);
 	preempt_enable_no_resched();
 }
 
 /*
  * These are the BKL spinlocks - we try to be polite a