Manual merge with Linus.

Conflicts:
	arch/powerpc/kernel/setup-common.c
	drivers/input/keyboard/hil_kbd.c
	drivers/input/mouse/hil_ptr.c

14 files changed, 485 insertions, 169 deletions

diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index a314e663d517..d57fd9181b18 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -78,13 +78,17 @@ config SCHEDSTATS
 	  this adds.
 
 config DEBUG_SLAB
-	bool "Debug memory allocations"
+	bool "Debug slab memory allocations"
 	depends on DEBUG_KERNEL && SLAB
 	help
 	  Say Y here to have the kernel do limited verification on memory
 	  allocation as well as poisoning memory on free to catch use of freed
 	  memory. This can make kmalloc/kfree-intensive workloads much slower.
 
+config DEBUG_SLAB_LEAK
+	bool "Memory leak debugging"
+	depends on DEBUG_SLAB
+
 config DEBUG_PREEMPT
 	bool "Debug preemptible kernel"
 	depends on DEBUG_KERNEL && PREEMPT
@@ -153,22 +157,9 @@ config DEBUG_INFO
 
 	  If unsure, say N.
 
-config DEBUG_IOREMAP
-	bool "Enable ioremap() debugging"
-	depends on DEBUG_KERNEL && PARISC
-	help
-	  Enabling this option will cause the kernel to distinguish between
-	  ioremapped and physical addresses.  It will print a backtrace (at
-	  most one every 10 seconds), hopefully allowing you to see which
-	  drivers need work.  Fixing all these problems is a prerequisite
-	  for turning on USE_HPPA_IOREMAP.  The warnings are harmless;
-	  the kernel has enough information to fix the broken drivers
-	  automatically, but we'd like to make it more efficient by not
-	  having to do that.
-
 config DEBUG_FS
 	bool "Debug Filesystem"
-	depends on DEBUG_KERNEL && SYSFS
+	depends on SYSFS
 	help
 	  debugfs is a virtual file system that kernel developers use to put
 	  debugging files into.  Enable this option to be able to read and
@@ -195,6 +186,16 @@ config FRAME_POINTER
 	  some architectures or if you use external debuggers.
 	  If you don't debug the kernel, you can say N.
 
+config UNWIND_INFO
+	bool "Compile the kernel with frame unwind information"
+	depends on !IA64
+	depends on !MODULES || !(MIPS || PARISC || PPC || SUPERH || SPARC64 || V850)
+	help
+	  If you say Y here the resulting kernel image will be slightly larger
+	  but not slower, and it will give very useful debugging information.
+	  If you don't debug the kernel, you can say N, but we may not be able
+	  to solve problems without frame unwind information or frame pointers.
+
 config FORCED_INLINING
 	bool "Force gcc to inline functions marked 'inline'"
 	depends on DEBUG_KERNEL
diff --git a/lib/Makefile b/lib/Makefile
index 648b2c1242fd..b830c9a15541 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -7,6 +7,8 @@ lib-y := errno.o ctype.o string.o vsprintf.o cmdline.o \
 	 idr.o div64.o int_sqrt.o bitmap.o extable.o prio_tree.o \
 	 sha1.o
 
+lib-$(CONFIG_SMP) += cpumask.o
+
 lib-y	+= kobject.o kref.o kobject_uevent.o klist.o
 
 obj-y += sort.o parser.o halfmd4.o iomap_copy.o
@@ -21,6 +23,7 @@ lib-$(CONFIG_RWSEM_GENERIC_SPINLOCK) += rwsem-spinlock.o
 lib-$(CONFIG_RWSEM_XCHGADD_ALGORITHM) += rwsem.o
 lib-$(CONFIG_SEMAPHORE_SLEEPERS) += semaphore-sleepers.o
 lib-$(CONFIG_GENERIC_FIND_NEXT_BIT) += find_next_bit.o
+lib-$(CONFIG_GENERIC_HWEIGHT) += hweight.o
 obj-$(CONFIG_LOCK_KERNEL) += kernel_lock.o
 obj-$(CONFIG_DEBUG_PREEMPT) += smp_processor_id.o
 
diff --git a/lib/bitmap.c b/lib/bitmap.c
index 48e708381d44..ed2ae3b0cd06 100644
--- a/lib/bitmap.c
+++ b/lib/bitmap.c
@@ -253,33 +253,18 @@ int __bitmap_subset(const unsigned long *bitmap1,
 }
 EXPORT_SYMBOL(__bitmap_subset);
 
-#if BITS_PER_LONG == 32
 int __bitmap_weight(const unsigned long *bitmap, int bits)
 {
 	int k, w = 0, lim = bits/BITS_PER_LONG;
 
 	for (k = 0; k < lim; k++)
-		w += hweight32(bitmap[k]);
+		w += hweight_long(bitmap[k]);
 
 	if (bits % BITS_PER_LONG)
-		w += hweight32(bitmap[k] & BITMAP_LAST_WORD_MASK(bits));
+		w += hweight_long(bitmap[k] & BITMAP_LAST_WORD_MASK(bits));
 
 	return w;
 }
-#else
-int __bitmap_weight(const unsigned long *bitmap, int bits)
-{
-	int k, w = 0, lim = bits/BITS_PER_LONG;
-
-	for (k = 0; k < lim; k++)
-		w += hweight64(bitmap[k]);
-
-	if (bits % BITS_PER_LONG)
-		w += hweight64(bitmap[k] & BITMAP_LAST_WORD_MASK(bits));
-
-	return w;
-}
-#endif
 EXPORT_SYMBOL(__bitmap_weight);
 
 /*
@@ -676,84 +661,143 @@ int bitmap_bitremap(int oldbit, const unsigned long *old,
 }
 EXPORT_SYMBOL(bitmap_bitremap);
 
-/**
- *	bitmap_find_free_region - find a contiguous aligned mem region
- *	@bitmap: an array of unsigned longs corresponding to the bitmap
- *	@bits: number of bits in the bitmap
- *	@order: region size to find (size is actually 1<<order)
+/*
+ * Common code for bitmap_*_region() routines.
+ *	bitmap: array of unsigned longs corresponding to the bitmap
+ *	pos: the beginning of the region
+ *	order: region size (log base 2 of number of bits)
+ *	reg_op: operation(s) to perform on that region of bitmap
  *
- * This is used to allocate a memory region from a bitmap.  The idea is
- * that the region has to be 1<<order sized and 1<<order aligned (this
- * makes the search algorithm much faster).
+ * Can set, verify and/or release a region of bits in a bitmap,
+ * depending on which combination of REG_OP_* flag bits is set.
  *
- * The region is marked as set bits in the bitmap if a free one is
- * found.
+ * A region of a bitmap is a sequence of bits in the bitmap, of
+ * some size '1 << order' (a power of two), aligned to that same
+ * '1 << order' power of two.
  *
- * Returns either beginning of region or negative error
+ * Returns 1 if REG_OP_ISFREE succeeds (region is all zero bits).
+ * Returns 0 in all other cases and reg_ops.
  */
-int bitmap_find_free_region(unsigned long *bitmap, int bits, int order)
-{
-	unsigned long mask;
-	int pages = 1 << order;
-	int i;
 
-	if(pages > BITS_PER_LONG)
-		return -EINVAL;
+enum {
+	REG_OP_ISFREE,		/* true if region is all zero bits */
+	REG_OP_ALLOC,		/* set all bits in region */
+	REG_OP_RELEASE,		/* clear all bits in region */
+};
 
-	/* make a mask of the order */
-	mask = (1ul << (pages - 1));
+static int __reg_op(unsigned long *bitmap, int pos, int order, int reg_op)
+{
+	int nbits_reg;		/* number of bits in region */
+	int index;		/* index first long of region in bitmap */
+	int offset;		/* bit offset region in bitmap[index] */
+	int nlongs_reg;		/* num longs spanned by region in bitmap */
+	int nbitsinlong;	/* num bits of region in each spanned long */
+	unsigned long mask;	/* bitmask for one long of region */
+	int i;			/* scans bitmap by longs */
+	int ret = 0;		/* return value */
+
+	/*
+	 * Either nlongs_reg == 1 (for small orders that fit in one long)
+	 * or (offset == 0 && mask == ~0UL) (for larger multiword orders.)
+	 */
+	nbits_reg = 1 << order;
+	index = pos / BITS_PER_LONG;
+	offset = pos - (index * BITS_PER_LONG);
+	nlongs_reg = BITS_TO_LONGS(nbits_reg);
+	nbitsinlong = min(nbits_reg,  BITS_PER_LONG);
+
+	/*
+	 * Can't do "mask = (1UL << nbitsinlong) - 1", as that
+	 * overflows if nbitsinlong == BITS_PER_LONG.
+	 */
+	mask = (1UL << (nbitsinlong - 1));
 	mask += mask - 1;
+	mask <<= offset;
 
-	/* run up the bitmap pages bits at a time */
-	for (i = 0; i < bits; i += pages) {
-		int index = i/BITS_PER_LONG;
-		int offset = i - (index * BITS_PER_LONG);
-		if((bitmap[index] & (mask << offset)) == 0) {
-			/* set region in bimap */
-			bitmap[index] |= (mask << offset);
-			return i;
+	switch (reg_op) {
+	case REG_OP_ISFREE:
+		for (i = 0; i < nlongs_reg; i++) {
+			if (bitmap[index + i] & mask)
+				goto done;
 		}
+		ret = 1;	/* all bits in region free (zero) */
+		break;
+
+	case REG_OP_ALLOC:
+		for (i = 0; i < nlongs_reg; i++)
+			bitmap[index + i] |= mask;
+		break;
+
+	case REG_OP_RELEASE:
+		for (i = 0; i < nlongs_reg; i++)
+			bitmap[index + i] &= ~mask;
+		break;
 	}
-	return -ENOMEM;
+done:
+	return ret;
+}
+
+/**
+ * bitmap_find_free_region - find a contiguous aligned mem region
+ *	@bitmap: array of unsigned longs corresponding to the bitmap
+ *	@bits: number of bits in the bitmap
+ *	@order: region size (log base 2 of number of bits) to find
+ *
+ * Find a region of free (zero) bits in a @bitmap of @bits bits and
+ * allocate them (set them to one).  Only consider regions of length
+ * a power (@order) of two, aligned to that power of two, which
+ * makes the search algorithm much faster.
+ *
+ * Return the bit offset in bitmap of the allocated region,
+ * or -errno on failure.
+ */
+int bitmap_find_free_region(unsigned long *bitmap, int bits, int order)
+{
+	int pos;		/* scans bitmap by regions of size order */
+
+	for (pos = 0; pos < bits; pos += (1 << order))
+		if (__reg_op(bitmap, pos, order, REG_OP_ISFREE))
+			break;
+	if (pos == bits)
+		return -ENOMEM;
+	__reg_op(bitmap, pos, order, REG_OP_ALLOC);
+	return pos;
 }
 EXPORT_SYMBOL(bitmap_find_free_region);
 
 /**
- *	bitmap_release_region - release allocated bitmap region
- *	@bitmap: a pointer to the bitmap
- *	@pos: the beginning of the region
- *	@order: the order of the bits to release (number is 1<<order)
+ * bitmap_release_region - release allocated bitmap region
+ *	@bitmap: array of unsigned longs corresponding to the bitmap
+ *	@pos: beginning of bit region to release
+ *	@order: region size (log base 2 of number of bits) to release
  *
  * This is the complement to __bitmap_find_free_region and releases
  * the found region (by clearing it in the bitmap).
+ *
+ * No return value.
  */
 void bitmap_release_region(unsigned long *bitmap, int pos, int order)
 {
-	int pages = 1 << order;
-	unsigned long mask = (1ul << (pages - 1));
-	int index = pos/BITS_PER_LONG;
-	int offset = pos - (index * BITS_PER_LONG);
-	mask += mask - 1;
-	bitmap[index] &= ~(mask << offset);
+	__reg_op(bitmap, pos, order, REG_OP_RELEASE);
 }
 EXPORT_SYMBOL(bitmap_release_region);
 
+/**
+ * bitmap_allocate_region - allocate bitmap region
+ *	@bitmap: array of unsigned longs corresponding to the bitmap
+ *	@pos: beginning of bit region to allocate
+ *	@order: region size (log base 2 of number of bits) to allocate
+ *
+ * Allocate (set bits in) a specified region of a bitmap.
+ *
+ * Return 0 on success, or -EBUSY if specified region wasn't
+ * free (not all bits were zero).
+ */
 int bitmap_allocate_region(unsigned long *bitmap, int pos, int order)
 {
-	int pages = 1 << order;
-	unsigned long mask = (1ul << (pages - 1));
-	int index = pos/BITS_PER_LONG;
-	int offset = pos - (index * BITS_PER_LONG);
-
-	/* We don't do regions of pages > BITS_PER_LONG.  The
-	 * algorithm would be a simple look for multiple zeros in the
-	 * array, but there's no driver today that needs this.  If you
-	 * trip this BUG(), you get to code it... */
-	BUG_ON(pages > BITS_PER_LONG);
-	mask += mask - 1;
-	if (bitmap[index] & (mask << offset))
+	if (!__reg_op(bitmap, pos, order, REG_OP_ISFREE))
 		return -EBUSY;
-	bitmap[index] |= (mask << offset);
+	__reg_op(bitmap, pos, order, REG_OP_ALLOC);
 	return 0;
 }
 EXPORT_SYMBOL(bitmap_allocate_region);
diff --git a/lib/cpumask.c b/lib/cpumask.c
new file mode 100644
index 000000000000..3a67dc5ada7d
--- /dev/null
+++ b/lib/cpumask.c
@@ -0,0 +1,45 @@
+#include <linux/kernel.h>
+#include <linux/bitops.h>
+#include <linux/cpumask.h>
+#include <linux/module.h>
+
+int __first_cpu(const cpumask_t *srcp)
+{
+	return min_t(int, NR_CPUS, find_first_bit(srcp->bits, NR_CPUS));
+}
+EXPORT_SYMBOL(__first_cpu);
+
+int __next_cpu(int n, const cpumask_t *srcp)
+{
+	return min_t(int, NR_CPUS, find_next_bit(srcp->bits, NR_CPUS, n+1));
+}
+EXPORT_SYMBOL(__next_cpu);
+
+/*
+ * Find the highest possible smp_processor_id()
+ *
+ * Note: if we're prepared to assume that cpu_possible_map never changes
+ * (reasonable) then this function should cache its return value.
+ */
+int highest_possible_processor_id(void)
+{
+	unsigned int cpu;
+	unsigned highest = 0;
+
+	for_each_cpu_mask(cpu, cpu_possible_map)
+		highest = cpu;
+	return highest;
+}
+EXPORT_SYMBOL(highest_possible_processor_id);
+
+int __any_online_cpu(const cpumask_t *mask)
+{
+	int cpu;
+
+	for_each_cpu_mask(cpu, *mask) {
+		if (cpu_online(cpu))
+			break;
+	}
+	return cpu;
+}
+EXPORT_SYMBOL(__any_online_cpu);
diff --git a/lib/extable.c b/lib/extable.c
index 18df57c029df..01c08b5836f5 100644
--- a/lib/extable.c
+++ b/lib/extable.c
@@ -1,5 +1,4 @@
 /*
- * lib/extable.c
  * Derived from arch/ppc/mm/extable.c and arch/i386/mm/extable.c.
  *
  * Copyright (C) 2004 Paul Mackerras, IBM Corp.
diff --git a/lib/find_next_bit.c b/lib/find_next_bit.c
index c05b4b19cf6c..bda0d71a2514 100644
--- a/lib/find_next_bit.c
+++ b/lib/find_next_bit.c
@@ -11,48 +11,171 @@
 
 #include <linux/bitops.h>
 #include <linux/module.h>
+#include <asm/types.h>
+#include <asm/byteorder.h>
 
-int find_next_bit(const unsigned long *addr, int size, int offset)
+#define BITOP_WORD(nr)		((nr) / BITS_PER_LONG)
+
+/**
+ * find_next_bit - find the next set bit in a memory region
+ * @addr: The address to base the search on
+ * @offset: The bitnumber to start searching at
+ * @size: The maximum size to search
+ */
+unsigned long find_next_bit(const unsigned long *addr, unsigned long size,
+		unsigned long offset)
 {
-	const unsigned long *base;
-	const int NBITS = sizeof(*addr) * 8;
+	const unsigned long *p = addr + BITOP_WORD(offset);
+	unsigned long result = offset & ~(BITS_PER_LONG-1);
 	unsigned long tmp;
 
-	base = addr;
+	if (offset >= size)
+		return size;
+	size -= result;
+	offset %= BITS_PER_LONG;
 	if (offset) {
-		int suboffset;
+		tmp = *(p++);
+		tmp &= (~0UL << offset);
+		if (size < BITS_PER_LONG)
+			goto found_first;
+		if (tmp)
+			goto found_middle;
+		size -= BITS_PER_LONG;
+		result += BITS_PER_LONG;
+	}
+	while (size & ~(BITS_PER_LONG-1)) {
+		if ((tmp = *(p++)))
+			goto found_middle;
+		result += BITS_PER_LONG;
+		size -= BITS_PER_LONG;
+	}
+	if (!size)
+		return result;
+	tmp = *p;
 
-		addr += offset / NBITS;
+found_first:
+	tmp &= (~0UL >> (BITS_PER_LONG - size));
+	if (tmp == 0UL)		/* Are any bits set? */
+		return result + size;	/* Nope. */
+found_middle:
+	return result + __ffs(tmp);
+}
 
-		suboffset = offset % NBITS;
-		if (suboffset) {
-			tmp = *addr;
-			tmp >>= suboffset;
-			if (tmp)
-				goto finish;
-		}
+EXPORT_SYMBOL(find_next_bit);
 
-		addr++;
+/*
+ * This implementation of find_{first,next}_zero_bit was stolen from
+ * Linus' asm-alpha/bitops.h.
+ */
+unsigned long find_next_zero_bit(const unsigned long *addr, unsigned long size,
+		unsigned long offset)
+{
+	const unsigned long *p = addr + BITOP_WORD(offset);
+	unsigned long result = offset & ~(BITS_PER_LONG-1);
+	unsigned long tmp;
+
+	if (offset >= size)
+		return size;
+	size -= result;
+	offset %= BITS_PER_LONG;
+	if (offset) {
+		tmp = *(p++);
+		tmp |= ~0UL >> (BITS_PER_LONG - offset);
+		if (size < BITS_PER_LONG)
+			goto found_first;
+		if (~tmp)
+			goto found_middle;
+		size -= BITS_PER_LONG;
+		result += BITS_PER_LONG;
+	}
+	while (size & ~(BITS_PER_LONG-1)) {
+		if (~(tmp = *(p++)))
+			goto found_middle;
+		result += BITS_PER_LONG;
+		size -= BITS_PER_LONG;
 	}
+	if (!size)
+		return result;
+	tmp = *p;
+
+found_first:
+	tmp |= ~0UL << size;
+	if (tmp == ~0UL)	/* Are any bits zero? */
+		return result + size;	/* Nope. */
+found_middle:
+	return result + ffz(tmp);
+}
+
+EXPORT_SYMBOL(find_next_zero_bit);
 
-	while ((tmp = *addr) == 0)
-		addr++;
+#ifdef __BIG_ENDIAN
 
-	offset = (addr - base) * NBITS;
+/* include/linux/byteorder does not support "unsigned long" type */
+static inline unsigned long ext2_swabp(const unsigned long * x)
+{
+#if BITS_PER_LONG == 64
+	return (unsigned long) __swab64p((u64 *) x);
+#elif BITS_PER_LONG == 32
+	return (unsigned long) __swab32p((u32 *) x);
+#else
+#error BITS_PER_LONG not defined
+#endif
+}
+
+/* include/linux/byteorder doesn't support "unsigned long" type */
+static inline unsigned long ext2_swab(const unsigned long y)
+{
+#if BITS_PER_LONG == 64
+	return (unsigned long) __swab64((u64) y);
+#elif BITS_PER_LONG == 32
+	return (unsigned long) __swab32((u32) y);
+#else
+#error BITS_PER_LONG not defined
+#endif
+}
 
- finish:
-	/* count the remaining bits without using __ffs() since that takes a 32-bit arg */
-	while (!(tmp & 0xff)) {
-		offset += 8;
-		tmp >>= 8;
+unsigned long generic_find_next_zero_le_bit(const unsigned long *addr, unsigned
+		long size, unsigned long offset)
+{
+	const unsigned long *p = addr + BITOP_WORD(offset);
+	unsigned long result = offset & ~(BITS_PER_LONG - 1);
+	unsigned long tmp;
+
+	if (offset >= size)
+		return size;
+	size -= result;
+	offset &= (BITS_PER_LONG - 1UL);
+	if (offset) {
+		tmp = ext2_swabp(p++);
+		tmp |= (~0UL >> (BITS_PER_LONG - offset));
+		if (size < BITS_PER_LONG)
+			goto found_first;
+		if (~tmp)
+			goto found_middle;
+		size -= BITS_PER_LONG;
+		result += BITS_PER_LONG;
 	}
 
-	while (!(tmp & 1)) {
-		offset++;
-		tmp >>= 1;
+	while (size & ~(BITS_PER_LONG - 1)) {
+		if (~(tmp = *(p++)))
+			goto found_middle_swap;
+		result += BITS_PER_LONG;
+		size -= BITS_PER_LONG;
 	}
+	if (!size)
+		return result;
+	tmp = ext2_swabp(p);
+found_first:
+	tmp |= ~0UL << size;
+	if (tmp == ~0UL)	/* Are any bits zero? */
+		return result + size; /* Nope. Skip ffz */
+found_middle:
+	return result + ffz(tmp);
 
-	return offset;
+found_middle_swap:
+	return result + ffz(ext2_swab(tmp));
 }
 
-EXPORT_SYMBOL(find_next_bit);
+EXPORT_SYMBOL(generic_find_next_zero_le_bit);
+
+#endif /* __BIG_ENDIAN */
diff --git a/lib/hweight.c b/lib/hweight.c
new file mode 100644
index 000000000000..438257671708
--- /dev/null
+++ b/lib/hweight.c
@@ -0,0 +1,53 @@
+#include <linux/module.h>
+#include <asm/types.h>
+
+/**
+ * hweightN - returns the hamming weight of a N-bit word
+ * @x: the word to weigh
+ *
+ * The Hamming Weight of a number is the total number of bits set in it.
+ */
+
+unsigned int hweight32(unsigned int w)
+{
+	unsigned int res = w - ((w >> 1) & 0x55555555);
+	res = (res & 0x33333333) + ((res >> 2) & 0x33333333);
+	res = (res + (res >> 4)) & 0x0F0F0F0F;
+	res = res + (res >> 8);
+	return (res + (res >> 16)) & 0x000000FF;
+}
+EXPORT_SYMBOL(hweight32);
+
+unsigned int hweight16(unsigned int w)
+{
+	unsigned int res = w - ((w >> 1) & 0x5555);
+	res = (res & 0x3333) + ((res >> 2) & 0x3333);
+	res = (res + (res >> 4)) & 0x0F0F;
+	return (res + (res >> 8)) & 0x00FF;
+}
+EXPORT_SYMBOL(hweight16);
+
+unsigned int hweight8(unsigned int w)
+{
+	unsigned int res = w - ((w >> 1) & 0x55);
+	res = (res & 0x33) + ((res >> 2) & 0x33);
+	return (res + (res >> 4)) & 0x0F;
+}
+EXPORT_SYMBOL(hweight8);
+
+unsigned long hweight64(__u64 w)
+{
+#if BITS_PER_LONG == 32
+	return hweight32((unsigned int)(w >> 32)) + hweight32((unsigned int)w);
+#elif BITS_PER_LONG == 64
+	__u64 res = w - ((w >> 1) & 0x5555555555555555ul);
+	res = (res & 0x3333333333333333ul) + ((res >> 2) & 0x3333333333333333ul);
+	res = (res + (res >> 4)) & 0x0F0F0F0F0F0F0F0Ful;
+	res = res + (res >> 8);
+	res = res + (res >> 16);
+	return (res + (res >> 32)) & 0x00000000000000FFul;
+#else
+#error BITS_PER_LONG not defined
+#endif
+}
+EXPORT_SYMBOL(hweight64);
diff --git a/lib/kobject.c b/lib/kobject.c
index efe67fa96a71..25204a41a9b0 100644
--- a/lib/kobject.c
+++ b/lib/kobject.c
@@ -194,6 +194,17 @@ int kobject_add(struct kobject * kobj)
 		unlink(kobj);
 		if (parent)
 			kobject_put(parent);
+
+		/* be noisy on error issues */
+		if (error == -EEXIST)
+			printk("kobject_add failed for %s with -EEXIST, "
+			       "don't try to register things with the "
+			       "same name in the same directory.\n",
+			       kobject_name(kobj));
+		else
+			printk("kobject_add failed for %s (%d)\n",
+			       kobject_name(kobj), error);
+		dump_stack();
 	}
 
 	return error;
@@ -207,18 +218,13 @@ int kobject_add(struct kobject * kobj)
 
 int kobject_register(struct kobject * kobj)
 {
-	int error = 0;
+	int error = -EINVAL;
 	if (kobj) {
 		kobject_init(kobj);
 		error = kobject_add(kobj);
-		if (error) {
-			printk("kobject_register failed for %s (%d)\n",
-			       kobject_name(kobj),error);
-			dump_stack();
-		} else
+		if (!error)
 			kobject_uevent(kobj, KOBJ_ADD);
-	} else
-		error = -EINVAL;
+	}
 	return error;
 }
 
@@ -379,6 +385,44 @@ void kobject_put(struct kobject * kobj)
 }
 
 
+static void dir_release(struct kobject *kobj)
+{
+	kfree(kobj);
+}
+
+static struct kobj_type dir_ktype = {
+	.release	= dir_release,
+	.sysfs_ops	= NULL,
+	.default_attrs	= NULL,
+};
+
+/**
+ *	kobject_add_dir - add sub directory of object.
+ *	@parent:	object in which a directory is created.
+ *	@name:	directory name.
+ *
+ *	Add a plain directory object as child of given object.
+ */
+struct kobject *kobject_add_dir(struct kobject *parent, const char *name)
+{
+	struct kobject *k;
+
+	if (!parent)
+		return NULL;
+
+	k = kzalloc(sizeof(*k), GFP_KERNEL);
+	if (!k)
+		return NULL;
+
+	k->parent = parent;
+	k->ktype = &dir_ktype;
+	kobject_set_name(k, name);
+	kobject_register(k);
+
+	return k;
+}
+EXPORT_SYMBOL_GPL(kobject_add_dir);
+
 /**
  *	kset_init - initialize a kset for use
  *	@k:	kset 
diff --git a/lib/kobject_uevent.c b/lib/kobject_uevent.c
index 086a0c6e888e..982226daf939 100644
--- a/lib/kobject_uevent.c
+++ b/lib/kobject_uevent.c
@@ -26,6 +26,8 @@
 #define NUM_ENVP	32	/* number of env pointers */
 
 #if defined(CONFIG_HOTPLUG) && defined(CONFIG_NET)
+u64 uevent_seqnum;
+char uevent_helper[UEVENT_HELPER_PATH_LEN] = "/sbin/hotplug";
 static DEFINE_SPINLOCK(sequence_lock);
 static struct sock *uevent_sock;
 
diff --git a/lib/kref.c b/lib/kref.c
index 0d07cc31c818..4a467faf1367 100644
--- a/lib/kref.c
+++ b/lib/kref.c
@@ -52,7 +52,12 @@ int kref_put(struct kref *kref, void (*release)(struct kref *kref))
 	WARN_ON(release == NULL);
 	WARN_ON(release == (void (*)(struct kref *))kfree);
 
-	if (atomic_dec_and_test(&kref->refcount)) {
+	/*
+	 * if current count is one, we are the last user and can release object
+	 * right now, avoiding an atomic operation on 'refcount'
+	 */
+	if ((atomic_read(&kref->refcount) == 1) ||
+	    (atomic_dec_and_test(&kref->refcount))) {
 		release(kref);
 		return 1;
 	}
diff --git a/lib/radix-tree.c b/lib/radix-tree.c
index 1e5b17dc7e3d..7097bb239e40 100644
--- a/lib/radix-tree.c
+++ b/lib/radix-tree.c
@@ -37,7 +37,6 @@
 #else
 #define RADIX_TREE_MAP_SHIFT	3	/* For more stressful testing */
 #endif
-#define RADIX_TREE_TAGS		2
 
 #define RADIX_TREE_MAP_SIZE	(1UL << RADIX_TREE_MAP_SHIFT)
 #define RADIX_TREE_MAP_MASK	(RADIX_TREE_MAP_SIZE-1)
@@ -48,7 +47,7 @@
 struct radix_tree_node {
 	unsigned int	count;
 	void		*slots[RADIX_TREE_MAP_SIZE];
-	unsigned long	tags[RADIX_TREE_TAGS][RADIX_TREE_TAG_LONGS];
+	unsigned long	tags[RADIX_TREE_MAX_TAGS][RADIX_TREE_TAG_LONGS];
 };
 
 struct radix_tree_path {
@@ -135,17 +134,20 @@ out:
 	return ret;
 }
 
-static inline void tag_set(struct radix_tree_node *node, int tag, int offset)
+static inline void tag_set(struct radix_tree_node *node, unsigned int tag,
+		int offset)
 {
 	__set_bit(offset, node->tags[tag]);
 }
 
-static inline void tag_clear(struct radix_tree_node *node, int tag, int offset)
+static inline void tag_clear(struct radix_tree_node *node, unsigned int tag,
+		int offset)
 {
 	__clear_bit(offset, node->tags[tag]);
 }
 
-static inline int tag_get(struct radix_tree_node *node, int tag, int offset)
+static inline int tag_get(struct radix_tree_node *node, unsigned int tag,
+		int offset)
 {
 	return test_bit(offset, node->tags[tag]);
 }
@@ -154,7 +156,7 @@ static inline int tag_get(struct radix_tree_node *node, int tag, int offset)
  * Returns 1 if any slot in the node has this tag set.
  * Otherwise returns 0.
  */
-static inline int any_tag_set(struct radix_tree_node *node, int tag)
+static inline int any_tag_set(struct radix_tree_node *node, unsigned int tag)
 {
 	int idx;
 	for (idx = 0; idx < RADIX_TREE_TAG_LONGS; idx++) {
@@ -180,7 +182,7 @@ static int radix_tree_extend(struct radix_tree_root *root, unsigned long index)
 {
 	struct radix_tree_node *node;
 	unsigned int height;
-	char tags[RADIX_TREE_TAGS];
+	char tags[RADIX_TREE_MAX_TAGS];
 	int tag;
 
 	/* Figure out what the height should be.  */
@@ -197,7 +199,7 @@ static int radix_tree_extend(struct radix_tree_root *root, unsigned long index)
 	 * Prepare the tag status of the top-level node for propagation
 	 * into the newly-pushed top-level node(s)
 	 */
-	for (tag = 0; tag < RADIX_TREE_TAGS; tag++) {
+	for (tag = 0; tag < RADIX_TREE_MAX_TAGS; tag++) {
 		tags[tag] = 0;
 		if (any_tag_set(root->rnode, tag))
 			tags[tag] = 1;
@@ -211,7 +213,7 @@ static int radix_tree_extend(struct radix_tree_root *root, unsigned long index)
 		node->slots[0] = root->rnode;
 
 		/* Propagate the aggregated tag info into the new root */
-		for (tag = 0; tag < RADIX_TREE_TAGS; tag++) {
+		for (tag = 0; tag < RADIX_TREE_MAX_TAGS; tag++) {
 			if (tags[tag])
 				tag_set(node, tag, 0);
 		}
@@ -349,14 +351,15 @@ EXPORT_SYMBOL(radix_tree_lookup);
  *	@index:		index key
  *	@tag: 		tag index
  *
- *	Set the search tag corresponging to @index in the radix tree.  From
+ *	Set the search tag (which must be < RADIX_TREE_MAX_TAGS)
+ *	corresponding to @index in the radix tree.  From
  *	the root all the way down to the leaf node.
  *
  *	Returns the address of the tagged item.   Setting a tag on a not-present
  *	item is a bug.
  */
 void *radix_tree_tag_set(struct radix_tree_root *root,
-			unsigned long index, int tag)
+			unsigned long index, unsigned int tag)
 {
 	unsigned int height, shift;
 	struct radix_tree_node *slot;
@@ -390,7 +393,8 @@ EXPORT_SYMBOL(radix_tree_tag_set);
  *	@index:		index key
  *	@tag: 		tag index
  *
- *	Clear the search tag corresponging to @index in the radix tree.  If
+ *	Clear the search tag (which must be < RADIX_TREE_MAX_TAGS)
+ *	corresponding to @index in the radix tree.  If
  *	this causes the leaf node to have no tags set then clear the tag in the
  *	next-to-leaf node, etc.
  *
@@ -398,7 +402,7 @@ EXPORT_SYMBOL(radix_tree_tag_set);
  *	has the same return value and semantics as radix_tree_lookup().
  */
 void *radix_tree_tag_clear(struct radix_tree_root *root,
-			unsigned long index, int tag)
+			unsigned long index, unsigned int tag)
 {
 	struct radix_tree_path path[RADIX_TREE_MAX_PATH], *pathp = path;
 	struct radix_tree_node *slot;
@@ -450,7 +454,7 @@ EXPORT_SYMBOL(radix_tree_tag_clear);
  * radix_tree_tag_get - get a tag on a radix tree node
  * @root:		radix tree root
  * @index:		index key
- * @tag: 		tag index
+ * @tag: 		tag index (< RADIX_TREE_MAX_TAGS)
  *
  * Return values:
  *
@@ -459,7 +463,7 @@ EXPORT_SYMBOL(radix_tree_tag_clear);
  * -1: tag present, unset
  */
 int radix_tree_tag_get(struct radix_tree_root *root,
-			unsigned long index, int tag)
+			unsigned long index, unsigned int tag)
 {
 	unsigned int height, shift;
 	struct radix_tree_node *slot;
@@ -592,7 +596,7 @@ EXPORT_SYMBOL(radix_tree_gang_lookup);
  */
 static unsigned int
 __lookup_tag(struct radix_tree_root *root, void **results, unsigned long index,
-	unsigned int max_items, unsigned long *next_index, int tag)
+	unsigned int max_items, unsigned long *next_index, unsigned int tag)
 {
 	unsigned int nr_found = 0;
 	unsigned int shift;
@@ -646,7 +650,7 @@ out:
  *	@results:	where the results of the lookup are placed
  *	@first_index:	start the lookup from this key
  *	@max_items:	place up to this many items at *results
- *	@tag:		the tag index
+ *	@tag:		the tag index (< RADIX_TREE_MAX_TAGS)
  *
  *	Performs an index-ascending scan of the tree for present items which
  *	have the tag indexed by @tag set.  Places the items at *@results and
@@ -654,7 +658,8 @@ out:
  */
 unsigned int
 radix_tree_gang_lookup_tag(struct radix_tree_root *root, void **results,
-		unsigned long first_index, unsigned int max_items, int tag)
+		unsigned long first_index, unsigned int max_items,
+		unsigned int tag)
 {
 	const unsigned long max_index = radix_tree_maxindex(root->height);
 	unsigned long cur_index = first_index;
@@ -716,7 +721,7 @@ void *radix_tree_delete(struct radix_tree_root *root, unsigned long index)
 	struct radix_tree_node *slot;
 	unsigned int height, shift;
 	void *ret = NULL;
-	char tags[RADIX_TREE_TAGS];
+	char tags[RADIX_TREE_MAX_TAGS];
 	int nr_cleared_tags;
 	int tag;
 	int offset;
@@ -751,7 +756,7 @@ void *radix_tree_delete(struct radix_tree_root *root, unsigned long index)
 	 * Clear all tags associated with the just-deleted item
 	 */
 	nr_cleared_tags = 0;
-	for (tag = 0; tag < RADIX_TREE_TAGS; tag++) {
+	for (tag = 0; tag < RADIX_TREE_MAX_TAGS; tag++) {
 		tags[tag] = 1;
 		if (tag_get(pathp->node, tag, pathp->offset)) {
 			tag_clear(pathp->node, tag, pathp->offset);
@@ -763,7 +768,7 @@ void *radix_tree_delete(struct radix_tree_root *root, unsigned long index)
 	}
 
 	for (pathp--; nr_cleared_tags && pathp->node; pathp--) {
-		for (tag = 0; tag < RADIX_TREE_TAGS; tag++) {
+		for (tag = 0; tag < RADIX_TREE_MAX_TAGS; tag++) {
 			if (tags[tag])
 				continue;
 
@@ -801,7 +806,7 @@ EXPORT_SYMBOL(radix_tree_delete);
  *	@root:		radix tree root
  *	@tag:		tag to test
  */
-int radix_tree_tagged(struct radix_tree_root *root, int tag)
+int radix_tree_tagged(struct radix_tree_root *root, unsigned int tag)
 {
   	struct radix_tree_node *rnode;
   	rnode = root->rnode;
diff --git a/lib/reed_solomon/reed_solomon.c b/lib/reed_solomon/reed_solomon.c
index f5fef948a415..f8ac9fa95de1 100644
--- a/lib/reed_solomon/reed_solomon.c
+++ b/lib/reed_solomon/reed_solomon.c
@@ -44,12 +44,13 @@
 #include <linux/module.h>
 #include <linux/rslib.h>
 #include <linux/slab.h>
+#include <linux/mutex.h>
 #include <asm/semaphore.h>
 
 /* This list holds all currently allocated rs control structures */
 static LIST_HEAD (rslist);
 /* Protection for the list */
-static DECLARE_MUTEX(rslistlock);
+static DEFINE_MUTEX(rslistlock);
 
 /**
  * rs_init - Initialize a Reed-Solomon codec
@@ -161,7 +162,7 @@ errrs:
  */
 void free_rs(struct rs_control *rs)
 {
-	down(&rslistlock);
+	mutex_lock(&rslistlock);
 	rs->users--;
 	if(!rs->users) {
 		list_del(&rs->list);
@@ -170,7 +171,7 @@ void free_rs(struct rs_control *rs)
 		kfree(rs->genpoly);
 		kfree(rs);
 	}
-	up(&rslistlock);
+	mutex_unlock(&rslistlock);
 }
 
 /**
@@ -201,7 +202,7 @@ struct rs_control *init_rs(int symsize, int gfpoly, int fcr, int prim,
 	if (nroots < 0 || nroots >= (1<<symsize))
 		return NULL;
 
-	down(&rslistlock);
+	mutex_lock(&rslistlock);
 
 	/* Walk through the list and look for a matching entry */
 	list_for_each(tmp, &rslist) {
@@ -228,7 +229,7 @@ struct rs_control *init_rs(int symsize, int gfpoly, int fcr, int prim,
 		list_add(&rs->list, &rslist);
 	}
 out:
-	up(&rslistlock);
+	mutex_unlock(&rslistlock);
 	return rs;
 }
 
diff --git a/lib/string.c b/lib/string.c
index 037a48acedbb..b3c28a3f6332 100644
--- a/lib/string.c
+++ b/lib/string.c
@@ -403,7 +403,6 @@ char *strpbrk(const char *cs, const char *ct)
 	}
 	return NULL;
 }
-EXPORT_SYMBOL(strpbrk);
 #endif
 
 #ifndef __HAVE_ARCH_STRSEP
diff --git a/lib/swiotlb.c b/lib/swiotlb.c
index 0af497b6b9a8..10625785eefd 100644
--- a/lib/swiotlb.c
+++ b/lib/swiotlb.c
@@ -296,8 +296,7 @@ map_single(struct device *hwdev, char *buffer, size_t size, int dir)
 	else
 		stride = 1;
 
-	if (!nslots)
-		BUG();
+	BUG_ON(!nslots);
 
 	/*
 	 * Find suitable number of IO TLB entries size that will fit this
@@ -416,14 +415,14 @@ sync_single(struct device *hwdev, char *dma_addr, size_t size,
 	case SYNC_FOR_CPU:
 		if (likely(dir == DMA_FROM_DEVICE || dir == DMA_BIDIRECTIONAL))
 			memcpy(buffer, dma_addr, size);
-		else if (dir != DMA_TO_DEVICE)
-			BUG();
+		else
+			BUG_ON(dir != DMA_TO_DEVICE);
 		break;
 	case SYNC_FOR_DEVICE:
 		if (likely(dir == DMA_TO_DEVICE || dir == DMA_BIDIRECTIONAL))
 			memcpy(dma_addr, buffer, size);
-		else if (dir != DMA_FROM_DEVICE)
-			BUG();
+		else
+			BUG_ON(dir != DMA_FROM_DEVICE);
 		break;
 	default:
 		BUG();
@@ -529,8 +528,7 @@ swiotlb_map_single(struct device *hwdev, void *ptr, size_t size, int dir)
 	unsigned long dev_addr = virt_to_phys(ptr);
 	void *map;
 
-	if (dir == DMA_NONE)
-		BUG();
+	BUG_ON(dir == DMA_NONE);
 	/*
 	 * If the pointer passed in happens to be in the device's DMA window,
 	 * we can safely return the device addr and not worry about bounce
@@ -592,8 +590,7 @@ swiotlb_unmap_single(struct device *hwdev, dma_addr_t dev_addr, size_t size,
 {
 	char *dma_addr = phys_to_virt(dev_addr);
 
-	if (dir == DMA_NONE)
-		BUG();
+	BUG_ON(dir == DMA_NONE);
 	if (dma_addr >= io_tlb_start && dma_addr < io_tlb_end)
 		unmap_single(hwdev, dma_addr, size, dir);
 	else if (dir == DMA_FROM_DEVICE)
@@ -616,8 +613,7 @@ swiotlb_sync_single(struct device *hwdev, dma_addr_t dev_addr,
 {
 	char *dma_addr = phys_to_virt(dev_addr);
 
-	if (dir == DMA_NONE)
-		BUG();
+	BUG_ON(dir == DMA_NONE);
 	if (dma_addr >= io_tlb_start && dma_addr < io_tlb_end)
 		sync_single(hwdev, dma_addr, size, dir, target);
 	else if (dir == DMA_FROM_DEVICE)
@@ -648,8 +644,7 @@ swiotlb_sync_single_range(struct device *hwdev, dma_addr_t dev_addr,
 {
 	char *dma_addr = phys_to_virt(dev_addr) + offset;
 
-	if (dir == DMA_NONE)
-		BUG();
+	BUG_ON(dir == DMA_NONE);
 	if (dma_addr >= io_tlb_start && dma_addr < io_tlb_end)
 		sync_single(hwdev, dma_addr, size, dir, target);
 	else if (dir == DMA_FROM_DEVICE)
@@ -696,8 +691,7 @@ swiotlb_map_sg(struct device *hwdev, struct scatterlist *sg, int nelems,
 	unsigned long dev_addr;
 	int i;
 
-	if (dir == DMA_NONE)
-		BUG();
+	BUG_ON(dir == DMA_NONE);
 
 	for (i = 0; i < nelems; i++, sg++) {
 		addr = SG_ENT_VIRT_ADDRESS(sg);
@@ -730,8 +724,7 @@ swiotlb_unmap_sg(struct device *hwdev, struct scatterlist *sg, int nelems,
 {
 	int i;
 
-	if (dir == DMA_NONE)
-		BUG();
+	BUG_ON(dir == DMA_NONE);
 
 	for (i = 0; i < nelems; i++, sg++)
 		if (sg->dma_address != SG_ENT_PHYS_ADDRESS(sg))
@@ -753,8 +746,7 @@ swiotlb_sync_sg(struct device *hwdev, struct scatterlist *sg,
 {
 	int i;
 
-	if (dir == DMA_NONE)
-		BUG();
+	BUG_ON(dir == DMA_NONE);
 
 	for (i = 0; i < nelems; i++, sg++)
 		if (sg->dma_address != SG_ENT_PHYS_ADDRESS(sg))