Merge commit 'v2.6.35' into kbuild/kbuild

Conflicts:
	arch/powerpc/Makefile

46 files changed, 2160 insertions, 983 deletions

diff --git a/lib/Kconfig b/lib/Kconfig
index 97b136ff117..5b916bc0fba 100644
--- a/lib/Kconfig
+++ b/lib/Kconfig
@@ -160,6 +160,9 @@ config TEXTSEARCH_BM
 config TEXTSEARCH_FSM
 	tristate
 
+config BTREE
+	boolean
+
 config HAS_IOMEM
 	boolean
 	depends on !NO_IOMEM
@@ -178,9 +181,6 @@ config HAS_DMA
 config CHECK_SIGNATURE
 	bool
 
-config HAVE_LMB
-	boolean
-
 config CPUMASK_OFFSTACK
 	bool "Force CPU masks off stack" if DEBUG_PER_CPU_MAPS
 	help
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index 2af5d84ec82..083b23d211d 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -103,7 +103,8 @@ config HEADERS_CHECK
 
 config DEBUG_SECTION_MISMATCH
 	bool "Enable full Section mismatch analysis"
-	depends on UNDEFINED
+	depends on UNDEFINED || (BLACKFIN)
+	default y
 	# This option is on purpose disabled for now.
 	# It will be enabled when we are down to a reasonable number
 	# of section mismatch warnings (< 10 for an allyesconfig build)
@@ -355,7 +356,7 @@ config SLUB_STATS
 config DEBUG_KMEMLEAK
 	bool "Kernel memory leak detector"
 	depends on DEBUG_KERNEL && EXPERIMENTAL && !MEMORY_HOTPLUG && \
-		(X86 || ARM || PPC || S390)
+		(X86 || ARM || PPC || S390 || SPARC64 || SUPERH || MICROBLAZE)
 
 	select DEBUG_FS if SYSFS
 	select STACKTRACE if STACKTRACE_SUPPORT
@@ -499,6 +500,30 @@ config PROVE_LOCKING
 
 	 For more details, see Documentation/lockdep-design.txt.
 
+config PROVE_RCU
+	bool "RCU debugging: prove RCU correctness"
+	depends on PROVE_LOCKING
+	default n
+	help
+	 This feature enables lockdep extensions that check for correct
+	 use of RCU APIs.  This is currently under development.  Say Y
+	 if you want to debug RCU usage or help work on the PROVE_RCU
+	 feature.
+
+	 Say N if you are unsure.
+
+config PROVE_RCU_REPEATEDLY
+	bool "RCU debugging: don't disable PROVE_RCU on first splat"
+	depends on PROVE_RCU
+	default n
+	help
+	 By itself, PROVE_RCU will disable checking upon issuing the
+	 first warning (or "splat").  This feature prevents such
+	 disabling, allowing multiple RCU-lockdep warnings to be printed
+	 on a single reboot.
+
+	 Say N if you are unsure.
+
 config LOCKDEP
 	bool
 	depends on DEBUG_KERNEL && TRACE_IRQFLAGS_SUPPORT && STACKTRACE_SUPPORT && LOCKDEP_SUPPORT
@@ -520,6 +545,14 @@ config LOCK_STAT
 
 	 For more details, see Documentation/lockstat.txt
 
+	 This also enables lock events required by "perf lock",
+	 subcommand of perf.
+	 If you want to use "perf lock", you also need to turn on
+	 CONFIG_EVENT_TRACING.
+
+	 CONFIG_LOCK_STAT defines "contended" and "acquired" lock events.
+	 (CONFIG_LOCKDEP defines "acquire" and "release" events.)
+
 config DEBUG_LOCKDEP
 	bool "Lock dependency engine debugging"
 	depends on DEBUG_KERNEL && LOCKDEP
@@ -778,10 +811,22 @@ config RCU_CPU_STALL_DETECTOR
 	  CPUs are delaying the current grace period, but only when
 	  the grace period extends for excessive time periods.
 
-	  Say Y if you want RCU to perform such checks.
+	  Say N if you want to disable such checks.
+
+	  Say Y if you are unsure.
+
+config RCU_CPU_STALL_VERBOSE
+	bool "Print additional per-task information for RCU_CPU_STALL_DETECTOR"
+	depends on RCU_CPU_STALL_DETECTOR && TREE_PREEMPT_RCU
+	default y
+	help
+	  This option causes RCU to printk detailed per-task information
+	  for any tasks that are stalling the current RCU grace period.
 
 	  Say N if you are unsure.
 
+	  Say Y if you want to enable such checks.
+
 config KPROBES_SANITY_TEST
 	bool "Kprobes sanity tests"
 	depends on DEBUG_KERNEL
@@ -853,8 +898,7 @@ config DEBUG_FORCE_WEAK_PER_CPU
 
 config LKDTM
 	tristate "Linux Kernel Dump Test Tool Module"
-	depends on DEBUG_KERNEL
-	depends on KPROBES
+	depends on DEBUG_FS
 	depends on BLOCK
 	default n
 	help
@@ -865,7 +909,19 @@ config LKDTM
 	called lkdtm.
 
 	Documentation on how to use the module can be found in
-	drivers/misc/lkdtm.c
+	Documentation/fault-injection/provoke-crashes.txt
+
+config CPU_NOTIFIER_ERROR_INJECT
+	tristate "CPU notifier error injection module"
+	depends on HOTPLUG_CPU && DEBUG_KERNEL
+	help
+	  This option provides a kernel module that can be used to test
+	  the error handling of the cpu notifiers
+
+	  To compile this code as a module, choose M here: the module will
+	  be called cpu-notifier-error-inject.
+
+	  If unsure, say N.
 
 config FAULT_INJECTION
 	bool "Fault-injection framework"
@@ -1008,10 +1064,10 @@ config DYNAMIC_DEBUG
 
 	  Usage:
 
-	  Dynamic debugging is controlled via the 'dynamic_debug/ddebug' file,
+	  Dynamic debugging is controlled via the 'dynamic_debug/control' file,
 	  which is contained in the 'debugfs' filesystem. Thus, the debugfs
 	  filesystem must first be mounted before making use of this feature.
-	  We refer the control file as: <debugfs>/dynamic_debug/ddebug. This
+	  We refer the control file as: <debugfs>/dynamic_debug/control. This
 	  file contains a list of the debug statements that can be enabled. The
 	  format for each line of the file is:
 
@@ -1026,7 +1082,7 @@ config DYNAMIC_DEBUG
 
 	  From a live system:
 
-		nullarbor:~ # cat <debugfs>/dynamic_debug/ddebug
+		nullarbor:~ # cat <debugfs>/dynamic_debug/control
 		# filename:lineno [module]function flags format
 		fs/aio.c:222 [aio]__put_ioctx - "__put_ioctx:\040freeing\040%p\012"
 		fs/aio.c:248 [aio]ioctx_alloc - "ENOMEM:\040nr_events\040too\040high\012"
@@ -1036,23 +1092,23 @@ config DYNAMIC_DEBUG
 
 		// enable the message at line 1603 of file svcsock.c
 		nullarbor:~ # echo -n 'file svcsock.c line 1603 +p' >
-						<debugfs>/dynamic_debug/ddebug
+						<debugfs>/dynamic_debug/control
 
 		// enable all the messages in file svcsock.c
 		nullarbor:~ # echo -n 'file svcsock.c +p' >
-						<debugfs>/dynamic_debug/ddebug
+						<debugfs>/dynamic_debug/control
 
 		// enable all the messages in the NFS server module
 		nullarbor:~ # echo -n 'module nfsd +p' >
-						<debugfs>/dynamic_debug/ddebug
+						<debugfs>/dynamic_debug/control
 
 		// enable all 12 messages in the function svc_process()
 		nullarbor:~ # echo -n 'func svc_process +p' >
-						<debugfs>/dynamic_debug/ddebug
+						<debugfs>/dynamic_debug/control
 
 		// disable all 12 messages in the function svc_process()
 		nullarbor:~ # echo -n 'func svc_process -p' >
-						<debugfs>/dynamic_debug/ddebug
+						<debugfs>/dynamic_debug/control
 
 	  See Documentation/dynamic-debug-howto.txt for additional information.
 
@@ -1067,6 +1123,13 @@ config DMA_API_DEBUG
 	  This option causes a performance degredation.  Use only if you want
 	  to debug device drivers. If unsure, say N.
 
+config ATOMIC64_SELFTEST
+	bool "Perform an atomic64_t self-test at boot"
+	help
+	  Enable this option to test the atomic64_t functions at boot.
+
+	  If unsure, say N.
+
 source "samples/Kconfig"
 
 source "lib/Kconfig.kgdb"
diff --git a/lib/Kconfig.kgdb b/lib/Kconfig.kgdb
index 9b5d1d7f2ef..43cb93fa265 100644
--- a/lib/Kconfig.kgdb
+++ b/lib/Kconfig.kgdb
@@ -3,7 +3,7 @@ config HAVE_ARCH_KGDB
 	bool
 
 menuconfig KGDB
-	bool "KGDB: kernel debugging with remote gdb"
+	bool "KGDB: kernel debugger"
 	depends on HAVE_ARCH_KGDB
 	depends on DEBUG_KERNEL && EXPERIMENTAL
 	help
@@ -57,4 +57,26 @@ config KGDB_TESTS_BOOT_STRING
 	  information about other strings you could use beyond the
 	  default of V1F100.
 
+config KGDB_LOW_LEVEL_TRAP
+       bool "KGDB: Allow debugging with traps in notifiers"
+       depends on X86 || MIPS
+       default n
+       help
+         This will add an extra call back to kgdb for the breakpoint
+         exception handler on which will will allow kgdb to step
+         through a notify handler.
+
+config KGDB_KDB
+	bool "KGDB_KDB: include kdb frontend for kgdb"
+	default n
+	help
+	  KDB frontend for kernel
+
+config KDB_KEYBOARD
+	bool "KGDB_KDB: keyboard as input device"
+	depends on VT && KGDB_KDB
+	default n
+	help
+	  KDB can use a PS/2 type keyboard for an input device
+
 endif # KGDB
diff --git a/lib/Makefile b/lib/Makefile
index 3b0b4a696db..0bfabba1bb3 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -21,7 +21,7 @@ lib-y	+= kobject.o kref.o klist.o
 
 obj-y += bcd.o div64.o sort.o parser.o halfmd4.o debug_locks.o random32.o \
 	 bust_spinlocks.o hexdump.o kasprintf.o bitmap.o scatterlist.o \
-	 string_helpers.o gcd.o list_sort.o
+	 string_helpers.o gcd.o lcm.o list_sort.o uuid.o
 
 ifeq ($(CONFIG_DEBUG_KOBJECT),y)
 CFLAGS_kobject.o += -DDEBUG
@@ -39,8 +39,12 @@ lib-$(CONFIG_RWSEM_XCHGADD_ALGORITHM) += rwsem.o
 lib-$(CONFIG_GENERIC_FIND_FIRST_BIT) += find_next_bit.o
 lib-$(CONFIG_GENERIC_FIND_NEXT_BIT) += find_next_bit.o
 obj-$(CONFIG_GENERIC_FIND_LAST_BIT) += find_last_bit.o
+
+CFLAGS_hweight.o = $(subst $(quote),,$(CONFIG_ARCH_HWEIGHT_CFLAGS))
 obj-$(CONFIG_GENERIC_HWEIGHT) += hweight.o
+
 obj-$(CONFIG_LOCK_KERNEL) += kernel_lock.o
+obj-$(CONFIG_BTREE) += btree.o
 obj-$(CONFIG_DEBUG_PREEMPT) += smp_processor_id.o
 obj-$(CONFIG_DEBUG_LIST) += list_debug.o
 obj-$(CONFIG_DEBUG_OBJECTS) += debugobjects.o
@@ -81,11 +85,10 @@ obj-$(CONFIG_AUDIT_GENERIC) += audit.o
 obj-$(CONFIG_SWIOTLB) += swiotlb.o
 obj-$(CONFIG_IOMMU_HELPER) += iommu-helper.o
 obj-$(CONFIG_FAULT_INJECTION) += fault-inject.o
+obj-$(CONFIG_CPU_NOTIFIER_ERROR_INJECT) += cpu-notifier-error-inject.o
 
 lib-$(CONFIG_GENERIC_BUG) += bug.o
 
-obj-$(CONFIG_HAVE_LMB) += lmb.o
-
 obj-$(CONFIG_HAVE_ARCH_TRACEHOOK) += syscall.o
 
 obj-$(CONFIG_DYNAMIC_DEBUG) += dynamic_debug.o
@@ -100,6 +103,8 @@ obj-$(CONFIG_GENERIC_CSUM) += checksum.o
 
 obj-$(CONFIG_GENERIC_ATOMIC64) += atomic64.o
 
+obj-$(CONFIG_ATOMIC64_SELFTEST) += atomic64_test.o
+
 hostprogs-y	:= gen_crc32table
 clean-files	:= crc32table.h
 
diff --git a/lib/atomic64.c b/lib/atomic64.c
index 8bee16ec752..a21c12bc727 100644
--- a/lib/atomic64.c
+++ b/lib/atomic64.c
@@ -162,12 +162,12 @@ int atomic64_add_unless(atomic64_t *v, long long a, long long u)
 {
 	unsigned long flags;
 	spinlock_t *lock = lock_addr(v);
-	int ret = 1;
+	int ret = 0;
 
 	spin_lock_irqsave(lock, flags);
 	if (v->counter != u) {
 		v->counter += a;
-		ret = 0;
+		ret = 1;
 	}
 	spin_unlock_irqrestore(lock, flags);
 	return ret;
diff --git a/lib/atomic64_test.c b/lib/atomic64_test.c
new file mode 100644
index 00000000000..250ed11d3ed
--- /dev/null
+++ b/lib/atomic64_test.c
@@ -0,0 +1,166 @@
+/*
+ * Testsuite for atomic64_t functions
+ *
+ * Copyright © 2010  Luca Barbieri
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <asm/atomic.h>
+
+#define INIT(c) do { atomic64_set(&v, c); r = c; } while (0)
+static __init int test_atomic64(void)
+{
+	long long v0 = 0xaaa31337c001d00dLL;
+	long long v1 = 0xdeadbeefdeafcafeLL;
+	long long v2 = 0xfaceabadf00df001LL;
+	long long onestwos = 0x1111111122222222LL;
+	long long one = 1LL;
+
+	atomic64_t v = ATOMIC64_INIT(v0);
+	long long r = v0;
+	BUG_ON(v.counter != r);
+
+	atomic64_set(&v, v1);
+	r = v1;
+	BUG_ON(v.counter != r);
+	BUG_ON(atomic64_read(&v) != r);
+
+	INIT(v0);
+	atomic64_add(onestwos, &v);
+	r += onestwos;
+	BUG_ON(v.counter != r);
+
+	INIT(v0);
+	atomic64_add(-one, &v);
+	r += -one;
+	BUG_ON(v.counter != r);
+
+	INIT(v0);
+	r += onestwos;
+	BUG_ON(atomic64_add_return(onestwos, &v) != r);
+	BUG_ON(v.counter != r);
+
+	INIT(v0);
+	r += -one;
+	BUG_ON(atomic64_add_return(-one, &v) != r);
+	BUG_ON(v.counter != r);
+
+	INIT(v0);
+	atomic64_sub(onestwos, &v);
+	r -= onestwos;
+	BUG_ON(v.counter != r);
+
+	INIT(v0);
+	atomic64_sub(-one, &v);
+	r -= -one;
+	BUG_ON(v.counter != r);
+
+	INIT(v0);
+	r -= onestwos;
+	BUG_ON(atomic64_sub_return(onestwos, &v) != r);
+	BUG_ON(v.counter != r);
+
+	INIT(v0);
+	r -= -one;
+	BUG_ON(atomic64_sub_return(-one, &v) != r);
+	BUG_ON(v.counter != r);
+
+	INIT(v0);
+	atomic64_inc(&v);
+	r += one;
+	BUG_ON(v.counter != r);
+
+	INIT(v0);
+	r += one;
+	BUG_ON(atomic64_inc_return(&v) != r);
+	BUG_ON(v.counter != r);
+
+	INIT(v0);
+	atomic64_dec(&v);
+	r -= one;
+	BUG_ON(v.counter != r);
+
+	INIT(v0);
+	r -= one;
+	BUG_ON(atomic64_dec_return(&v) != r);
+	BUG_ON(v.counter != r);
+
+	INIT(v0);
+	BUG_ON(atomic64_xchg(&v, v1) != v0);
+	r = v1;
+	BUG_ON(v.counter != r);
+
+	INIT(v0);
+	BUG_ON(atomic64_cmpxchg(&v, v0, v1) != v0);
+	r = v1;
+	BUG_ON(v.counter != r);
+
+	INIT(v0);
+	BUG_ON(atomic64_cmpxchg(&v, v2, v1) != v0);
+	BUG_ON(v.counter != r);
+
+	INIT(v0);
+	BUG_ON(atomic64_add_unless(&v, one, v0));
+	BUG_ON(v.counter != r);
+
+	INIT(v0);
+	BUG_ON(!atomic64_add_unless(&v, one, v1));
+	r += one;
+	BUG_ON(v.counter != r);
+
+#if defined(CONFIG_X86) || defined(CONFIG_MIPS) || defined(CONFIG_PPC) || \
+    defined(CONFIG_S390) || defined(_ASM_GENERIC_ATOMIC64_H)
+	INIT(onestwos);
+	BUG_ON(atomic64_dec_if_positive(&v) != (onestwos - 1));
+	r -= one;
+	BUG_ON(v.counter != r);
+
+	INIT(0);
+	BUG_ON(atomic64_dec_if_positive(&v) != -one);
+	BUG_ON(v.counter != r);
+
+	INIT(-one);
+	BUG_ON(atomic64_dec_if_positive(&v) != (-one - one));
+	BUG_ON(v.counter != r);
+#else
+#warning Please implement atomic64_dec_if_positive for your architecture, and add it to the IF above
+#endif
+
+	INIT(onestwos);
+	BUG_ON(!atomic64_inc_not_zero(&v));
+	r += one;
+	BUG_ON(v.counter != r);
+
+	INIT(0);
+	BUG_ON(atomic64_inc_not_zero(&v));
+	BUG_ON(v.counter != r);
+
+	INIT(-one);
+	BUG_ON(!atomic64_inc_not_zero(&v));
+	r += one;
+	BUG_ON(v.counter != r);
+
+#ifdef CONFIG_X86
+	printk(KERN_INFO "atomic64 test passed for %s platform %s CX8 and %s SSE\n",
+#ifdef CONFIG_X86_64
+	       "x86-64",
+#elif defined(CONFIG_X86_CMPXCHG64)
+	       "i586+",
+#else
+	       "i386+",
+#endif
+	       boot_cpu_has(X86_FEATURE_CX8) ? "with" : "without",
+	       boot_cpu_has(X86_FEATURE_XMM) ? "with" : "without");
+#else
+	printk(KERN_INFO "atomic64 test passed\n");
+#endif
+
+	return 0;
+}
+
+core_initcall(test_atomic64);
diff --git a/lib/bitmap.c b/lib/bitmap.c
index 11bf4975058..ffb78c916cc 100644
--- a/lib/bitmap.c
+++ b/lib/bitmap.c
@@ -487,7 +487,7 @@ int __bitmap_parse(const char *buf, unsigned int buflen,
 EXPORT_SYMBOL(__bitmap_parse);
 
 /**
- * bitmap_parse_user()
+ * bitmap_parse_user - convert an ASCII hex string in a user buffer into a bitmap
  *
  * @ubuf: pointer to user buffer containing string.
  * @ulen: buffer size in bytes.  If string is smaller than this
@@ -619,7 +619,7 @@ int bitmap_parselist(const char *bp, unsigned long *maskp, int nmaskbits)
 EXPORT_SYMBOL(bitmap_parselist);
 
 /**
- * bitmap_pos_to_ord(buf, pos, bits)
+ * bitmap_pos_to_ord - find ordinal of set bit at given position in bitmap
  *	@buf: pointer to a bitmap
  *	@pos: a bit position in @buf (0 <= @pos < @bits)
  *	@bits: number of valid bit positions in @buf
@@ -655,7 +655,7 @@ static int bitmap_pos_to_ord(const unsigned long *buf, int pos, int bits)
 }
 
 /**
- * bitmap_ord_to_pos(buf, ord, bits)
+ * bitmap_ord_to_pos - find position of n-th set bit in bitmap
  *	@buf: pointer to bitmap
  *	@ord: ordinal bit position (n-th set bit, n >= 0)
  *	@bits: number of valid bit positions in @buf
@@ -733,10 +733,9 @@ void bitmap_remap(unsigned long *dst, const unsigned long *src,
 	bitmap_zero(dst, bits);
 
 	w = bitmap_weight(new, bits);
-	for (oldbit = find_first_bit(src, bits);
-	     oldbit < bits;
-	     oldbit = find_next_bit(src, bits, oldbit + 1)) {
+	for_each_set_bit(oldbit, src, bits) {
 	     	int n = bitmap_pos_to_ord(old, oldbit, bits);
+
 		if (n < 0 || w == 0)
 			set_bit(oldbit, dst);	/* identity map */
 		else
@@ -903,9 +902,7 @@ void bitmap_onto(unsigned long *dst, const unsigned long *orig,
 	 */
 
 	m = 0;
-	for (n = find_first_bit(relmap, bits);
-	     n < bits;
-	     n = find_next_bit(relmap, bits, n + 1)) {
+	for_each_set_bit(n, relmap, bits) {
 		/* m == bitmap_pos_to_ord(relmap, n, bits) */
 		if (test_bit(m, orig))
 			set_bit(n, dst);
@@ -934,9 +931,7 @@ void bitmap_fold(unsigned long *dst, const unsigned long *orig,
 		return;
 	bitmap_zero(dst, bits);
 
-	for (oldbit = find_first_bit(orig, bits);
-	     oldbit < bits;
-	     oldbit = find_next_bit(orig, bits, oldbit + 1))
+	for_each_set_bit(oldbit, orig, bits)
 		set_bit(oldbit % sz, dst);
 }
 EXPORT_SYMBOL(bitmap_fold);
diff --git a/lib/btree.c b/lib/btree.c
new file mode 100644
index 00000000000..c9c6f035152
--- /dev/null
+++ b/lib/btree.c
@@ -0,0 +1,798 @@
+/*
+ * lib/btree.c	- Simple In-memory B+Tree
+ *
+ * As should be obvious for Linux kernel code, license is GPLv2
+ *
+ * Copyright (c) 2007-2008 Joern Engel <joern@logfs.org>
+ * Bits and pieces stolen from Peter Zijlstra's code, which is
+ * Copyright 2007, Red Hat Inc. Peter Zijlstra <pzijlstr@redhat.com>
+ * GPLv2
+ *
+ * see http://programming.kicks-ass.net/kernel-patches/vma_lookup/btree.patch
+ *
+ * A relatively simple B+Tree implementation.  I have written it as a learning
+ * excercise to understand how B+Trees work.  Turned out to be useful as well.
+ *
+ * B+Trees can be used similar to Linux radix trees (which don't have anything
+ * in common with textbook radix trees, beware).  Prerequisite for them working
+ * well is that access to a random tree node is much faster than a large number
+ * of operations within each node.
+ *
+ * Disks have fulfilled the prerequisite for a long time.  More recently DRAM
+ * has gained similar properties, as memory access times, when measured in cpu
+ * cycles, have increased.  Cacheline sizes have increased as well, which also
+ * helps B+Trees.
+ *
+ * Compared to radix trees, B+Trees are more efficient when dealing with a
+ * sparsely populated address space.  Between 25% and 50% of the memory is
+ * occupied with valid pointers.  When densely populated, radix trees contain
+ * ~98% pointers - hard to beat.  Very sparse radix trees contain only ~2%
+ * pointers.
+ *
+ * This particular implementation stores pointers identified by a long value.
+ * Storing NULL pointers is illegal, lookup will return NULL when no entry
+ * was found.
+ *
+ * A tricks was used that is not commonly found in textbooks.  The lowest
+ * values are to the right, not to the left.  All used slots within a node
+ * are on the left, all unused slots contain NUL values.  Most operations
+ * simply loop once over all slots and terminate on the first NUL.
+ */
+
+#include <linux/btree.h>
+#include <linux/cache.h>
+#include <linux/kernel.h>
+#include <linux/slab.h>
+#include <linux/module.h>
+
+#define MAX(a, b) ((a) > (b) ? (a) : (b))
+#define NODESIZE MAX(L1_CACHE_BYTES, 128)
+
+struct btree_geo {
+	int keylen;
+	int no_pairs;
+	int no_longs;
+};
+
+struct btree_geo btree_geo32 = {
+	.keylen = 1,
+	.no_pairs = NODESIZE / sizeof(long) / 2,
+	.no_longs = NODESIZE / sizeof(long) / 2,
+};
+EXPORT_SYMBOL_GPL(btree_geo32);
+
+#define LONG_PER_U64 (64 / BITS_PER_LONG)
+struct btree_geo btree_geo64 = {
+	.keylen = LONG_PER_U64,
+	.no_pairs = NODESIZE / sizeof(long) / (1 + LONG_PER_U64),
+	.no_longs = LONG_PER_U64 * (NODESIZE / sizeof(long) / (1 + LONG_PER_U64)),
+};
+EXPORT_SYMBOL_GPL(btree_geo64);
+
+struct btree_geo btree_geo128 = {
+	.keylen = 2 * LONG_PER_U64,
+	.no_pairs = NODESIZE / sizeof(long) / (1 + 2 * LONG_PER_U64),
+	.no_longs = 2 * LONG_PER_U64 * (NODESIZE / sizeof(long) / (1 + 2 * LONG_PER_U64)),
+};
+EXPORT_SYMBOL_GPL(btree_geo128);
+
+static struct kmem_cache *btree_cachep;
+
+void *btree_alloc(gfp_t gfp_mask, void *pool_data)
+{
+	return kmem_cache_alloc(btree_cachep, gfp_mask);
+}
+EXPORT_SYMBOL_GPL(btree_alloc);
+
+void btree_free(void *element, void *pool_data)
+{
+	kmem_cache_free(btree_cachep, element);
+}
+EXPORT_SYMBOL_GPL(btree_free);
+
+static unsigned long *btree_node_alloc(struct btree_head *head, gfp_t gfp)
+{
+	unsigned long *node;
+
+	node = mempool_alloc(head->mempool, gfp);
+	if (likely(node))
+		memset(node, 0, NODESIZE);
+	return node;
+}
+
+static int longcmp(const unsigned long *l1, const unsigned long *l2, size_t n)
+{
+	size_t i;
+
+	for (i = 0; i < n; i++) {
+		if (l1[i] < l2[i])
+			return -1;
+		if (l1[i] > l2[i])
+			return 1;
+	}
+	return 0;
+}
+
+static unsigned long *longcpy(unsigned long *dest, const unsigned long *src,
+		size_t n)
+{
+	size_t i;
+
+	for (i = 0; i < n; i++)
+		dest[i] = src[i];
+	return dest;
+}
+
+static unsigned long *longset(unsigned long *s, unsigned long c, size_t n)
+{
+	size_t i;
+
+	for (i = 0; i < n; i++)
+		s[i] = c;
+	return s;
+}
+
+static void dec_key(struct btree_geo *geo, unsigned long *key)
+{
+	unsigned long val;
+	int i;
+
+	for (i = geo->keylen - 1; i >= 0; i--) {
+		val = key[i];
+		key[i] = val - 1;
+		if (val)
+			break;
+	}
+}
+
+static unsigned long *bkey(struct btree_geo *geo, unsigned long *node, int n)
+{
+	return &node[n * geo->keylen];
+}
+
+static void *bval(struct btree_geo *geo, unsigned long *node, int n)
+{
+	return (void *)node[geo->no_longs + n];
+}
+
+static void setkey(struct btree_geo *geo, unsigned long *node, int n,
+		   unsigned long *key)
+{
+	longcpy(bkey(geo, node, n), key, geo->keylen);
+}
+
+static void setval(struct btree_geo *geo, unsigned long *node, int n,
+		   void *val)
+{
+	node[geo->no_longs + n] = (unsigned long) val;
+}
+
+static void clearpair(struct btree_geo *geo, unsigned long *node, int n)
+{
+	longset(bkey(geo, node, n), 0, geo->keylen);
+	node[geo->no_longs + n] = 0;
+}
+
+static inline void __btree_init(struct btree_head *head)
+{
+	head->node = NULL;
+	head->height = 0;
+}
+
+void btree_init_mempool(struct btree_head *head, mempool_t *mempool)
+{
+	__btree_init(head);
+	head->mempool = mempool;
+}
+EXPORT_SYMBOL_GPL(btree_init_mempool);
+
+int btree_init(struct btree_head *head)
+{
+	__btree_init(head);
+	head->mempool = mempool_create(0, btree_alloc, btree_free, NULL);
+	if (!head->mempool)
+		return -ENOMEM;
+	return 0;
+}
+EXPORT_SYMBOL_GPL(btree_init);
+
+void btree_destroy(struct btree_head *head)
+{
+	mempool_destroy(head->mempool);
+	head->mempool = NULL;
+}
+EXPORT_SYMBOL_GPL(btree_destroy);
+
+void *btree_last(struct btree_head *head, struct btree_geo *geo,
+		 unsigned long *key)
+{
+	int height = head->height;
+	unsigned long *node = head->node;
+
+	if (height == 0)
+		return NULL;
+
+	for ( ; height > 1; height--)
+		node = bval(geo, node, 0);
+
+	longcpy(key, bkey(geo, node, 0), geo->keylen);
+	return bval(geo, node, 0);
+}
+EXPORT_SYMBOL_GPL(btree_last);
+
+static int keycmp(struct btree_geo *geo, unsigned long *node, int pos,
+		  unsigned long *key)
+{
+	return longcmp(bkey(geo, node, pos), key, geo->keylen);
+}
+
+static int keyzero(struct btree_geo *geo, unsigned long *key)
+{
+	int i;
+
+	for (i = 0; i < geo->keylen; i++)
+		if (key[i])
+			return 0;
+
+	return 1;
+}
+
+void *btree_lookup(struct btree_head *head, struct btree_geo *geo,
+		unsigned long *key)
+{
+	int i, height = head->height;
+	unsigned long *node = head->node;
+
+	if (height == 0)
+		return NULL;
+
+	for ( ; height > 1; height--) {
+		for (i = 0; i < geo->no_pairs; i++)
+			if (keycmp(geo, node, i, key) <= 0)
+				break;
+		if (i == geo->no_pairs)
+			return NULL;
+		node = bval(geo, node, i);
+		if (!node)
+			return NULL;
+	}
+
+	if (!node)
+		return NULL;
+
+	for (i = 0; i < geo->no_pairs; i++)
+		if (keycmp(geo, node, i, key) == 0)
+			return bval(geo, node, i);
+	return NULL;
+}
+EXPORT_SYMBOL_GPL(btree_lookup);
+
+int btree_update(struct btree_head *head, struct btree_geo *geo,
+		 unsigned long *key, void *val)
+{
+	int i, height = head->height;
+	unsigned long *node = head->node;
+
+	if (height == 0)
+		return -ENOENT;
+
+	for ( ; height > 1; height--) {
+		for (i = 0; i < geo->no_pairs; i++)
+			if (keycmp(geo, node, i, key) <= 0)
+				break;
+		if (i == geo->no_pairs)
+			return -ENOENT;
+		node = bval(geo, node, i);
+		if (!node)
+			return -ENOENT;
+	}
+
+	if (!node)
+		return -ENOENT;
+
+	for (i = 0; i < geo->no_pairs; i++)
+		if (keycmp(geo, node, i, key) == 0) {
+			setval(geo, node, i, val);
+			return 0;
+		}
+	return -ENOENT;
+}
+EXPORT_SYMBOL_GPL(btree_update);
+
+/*
+ * Usually this function is quite similar to normal lookup.  But the key of
+ * a parent node may be smaller than the smallest key of all its siblings.
+ * In such a case we cannot just return NULL, as we have only proven that no
+ * key smaller than __key, but larger than this parent key exists.
+ * So we set __key to the parent key and retry.  We have to use the smallest
+ * such parent key, which is the last parent key we encountered.
+ */
+void *btree_get_prev(struct btree_head *head, struct btree_geo *geo,
+		     unsigned long *__key)
+{
+	int i, height;
+	unsigned long *node, *oldnode;
+	unsigned long *retry_key = NULL, key[geo->keylen];
+
+	if (keyzero(geo, __key))
+		return NULL;
+
+	if (head->height == 0)
+		return NULL;
+retry:
+	longcpy(key, __key, geo->keylen);
+	dec_key(geo, key);
+
+	node = head->node;
+	for (height = head->height ; height > 1; height--) {
+		for (i = 0; i < geo->no_pairs; i++)
+			if (keycmp(geo, node, i, key) <= 0)
+				break;
+		if (i == geo->no_pairs)
+			goto miss;
+		oldnode = node;
+		node = bval(geo, node, i);
+		if (!node)
+			goto miss;
+		retry_key = bkey(geo, oldnode, i);
+	}
+
+	if (!node)
+		goto miss;
+
+	for (i = 0; i < geo->no_pairs; i++) {
+		if (keycmp(geo, node, i, key) <= 0) {
+			if (bval(geo, node, i)) {
+				longcpy(__key, bkey(geo, node, i), geo->keylen);
+				return bval(geo, node, i);
+			} else
+				goto miss;
+		}
+	}
+miss:
+	if (retry_key) {
+		__key = retry_key;
+		retry_key = NULL;
+		goto retry;
+	}
+	return NULL;
+}
+
+static int getpos(struct btree_geo *geo, unsigned long *node,
+		unsigned long *key)
+{
+	int i;
+
+	for (i = 0; i < geo->no_pairs; i++) {
+		if (keycmp(geo, node, i, key) <= 0)
+			break;
+	}
+	return i;
+}
+
+static int getfill(struct btree_geo *geo, unsigned long *node, int start)
+{
+	int i;
+
+	for (i = start; i < geo->no_pairs; i++)
+		if (!bval(geo, node, i))
+			break;
+	return i;
+}
+
+/*
+ * locate the correct leaf node in the btree
+ */
+static unsigned long *find_level(struct btree_head *head, struct btree_geo *geo,
+		unsigned long *key, int level)
+{
+	unsigned long *node = head->node;
+	int i, height;
+
+	for (height = head->height; height > level; height--) {
+		for (i = 0; i < geo->no_pairs; i++)
+			if (keycmp(geo, node, i, key) <= 0)
+				break;
+
+		if ((i == geo->no_pairs) || !bval(geo, node, i)) {
+			/* right-most key is too large, update it */
+			/* FIXME: If the right-most key on higher levels is
+			 * always zero, this wouldn't be necessary. */
+			i--;
+			setkey(geo, node, i, key);
+		}
+		BUG_ON(i < 0);
+		node = bval(geo, node, i);
+	}
+	BUG_ON(!node);
+	return node;
+}
+
+static int btree_grow(struct btree_head *head, struct btree_geo *geo,
+		      gfp_t gfp)
+{
+	unsigned long *node;
+	int fill;
+
+	node = btree_node_alloc(head, gfp);
+	if (!node)
+		return -ENOMEM;
+	if (head->node) {
+		fill = getfill(geo, head->node, 0);
+		setkey(geo, node, 0, bkey(geo, head->node, fill - 1));
+		setval(geo, node, 0, head->node);
+	}
+	head->node = node;
+	head->height++;
+	return 0;
+}
+
+static void btree_shrink(struct btree_head *head, struct btree_geo *geo)
+{
+	unsigned long *node;
+	int fill;
+
+	if (head->height <= 1)
+		return;
+
+	node = head->node;
+	fill = getfill(geo, node, 0);
+	BUG_ON(fill > 1);
+	head->node = bval(geo, node, 0);
+	head->height--;
+	mempool_free(node, head->mempool);
+}
+
+static int btree_insert_level(struct btree_head *head, struct btree_geo *geo,
+			      unsigned long *key, void *val, int level,
+			      gfp_t gfp)
+{
+	unsigned long *node;
+	int i, pos, fill, err;
+
+	BUG_ON(!val);
+	if (head->height < level) {
+		err = btree_grow(head, geo, gfp);
+		if (err)
+			return err;
+	}
+
+retry:
+	node = find_level(head, geo, key, level);
+	pos = getpos(geo, node, key);
+	fill = getfill(geo, node, pos);
+	/* two identical keys are not allowed */
+	BUG_ON(pos < fill && keycmp(geo, node, pos, key) == 0);
+
+	if (fill == geo->no_pairs) {
+		/* need to split node */
+		unsigned long *new;
+
+		new = btree_node_alloc(head, gfp);
+		if (!new)
+			return -ENOMEM;
+		err = btree_insert_level(head, geo,
+				bkey(geo, node, fill / 2 - 1),
+				new, level + 1, gfp);
+		if (err) {
+			mempool_free(new, head->mempool);
+			return err;
+		}
+		for (i = 0; i < fill / 2; i++) {
+			setkey(geo, new, i, bkey(geo, node, i));
+			setval(geo, new, i, bval(geo, node, i));
+			setkey(geo, node, i, bkey(geo, node, i + fill / 2));
+			setval(geo, node, i, bval(geo, node, i + fill / 2));
+			clearpair(geo, node, i + fill / 2);
+		}
+		if (fill & 1) {
+			setkey(geo, node, i, bkey(geo, node, fill - 1));
+			setval(geo, node, i, bval(geo, node, fill - 1));
+			clearpair(geo, node, fill - 1);
+		}
+		goto retry;
+	}
+	BUG_ON(fill >= geo->no_pairs);
+
+	/* shift and insert */
+	for (i = fill; i > pos; i--) {
+		setkey(geo, node, i, bkey(geo, node, i - 1));
+		setval(geo, node, i, bval(geo, node, i - 1));
+	}
+	setkey(geo, node, pos, key);
+	setval(geo, node, pos, val);
+
+	return 0;
+}
+
+int btree_insert(struct btree_head *head, struct btree_geo *geo,
+		unsigned long *key, void *val, gfp_t gfp)
+{
+	return btree_insert_level(head, geo, key, val, 1, gfp);
+}
+EXPORT_SYMBOL_GPL(btree_insert);
+
+static void *btree_remove_level(struct btree_head *head, struct btree_geo *geo,
+		unsigned long *key, int level);
+static void merge(struct btree_head *head, struct btree_geo *geo, int level,
+		unsigned long *left, int lfill,
+		unsigned long *right, int rfill,
+		unsigned long *parent, int lpos)
+{
+	int i;
+
+	for (i = 0; i < rfill; i++) {
+		/* Move all keys to the left */
+		setkey(geo, left, lfill + i, bkey(geo, right, i));
+		setval(geo, left, lfill + i, bval(geo, right, i));
+	}
+	/* Exchange left and right child in parent */
+	setval(geo, parent, lpos, right);
+	setval(geo, parent, lpos + 1, left);
+	/* Remove left (formerly right) child from parent */
+	btree_remove_level(head, geo, bkey(geo, parent, lpos), level + 1);
+	mempool_free(right, head->mempool);
+}
+
+static void rebalance(struct btree_head *head, struct btree_geo *geo,
+		unsigned long *key, int level, unsigned long *child, int fill)
+{
+	unsigned long *parent, *left = NULL, *right = NULL;
+	int i, no_left, no_right;
+
+	if (fill == 0) {
+		/* Because we don't steal entries from a neigbour, this case
+		 * can happen.  Parent node contains a single child, this
+		 * node, so merging with a sibling never happens.
+		 */
+		btree_remove_level(head, geo, key, level + 1);
+		mempool_free(child, head->mempool);
+		return;
+	}
+
+	parent = find_level(head, geo, key, level + 1);
+	i = getpos(geo, parent, key);
+	BUG_ON(bval(geo, parent, i) != child);
+
+	if (i > 0) {
+		left = bval(geo, parent, i - 1);
+		no_left = getfill(geo, left, 0);
+		if (fill + no_left <= geo->no_pairs) {
+			merge(head, geo, level,
+					left, no_left,
+					child, fill,
+					parent, i - 1);
+			return;
+		}
+	}
+	if (i + 1 < getfill(geo, parent, i)) {
+		right = bval(geo, parent, i + 1);
+		no_right = getfill(geo, right, 0);
+		if (fill + no_right <= geo->no_pairs) {
+			merge(head, geo, level,
+					child, fill,
+					right, no_right,
+					parent, i);
+			return;
+		}
+	}
+	/*
+	 * We could also try to steal one entry from the left or right
+	 * neighbor.  By not doing so we changed the invariant from
+	 * "all nodes are at least half full" to "no two neighboring
+	 * nodes can be merged".  Which means that the average fill of
+	 * all nodes is still half or better.
+	 */
+}
+
+static void *btree_remove_level(struct btree_head *head, struct btree_geo *geo,
+		unsigned long *key, int level)
+{
+	unsigned long *node;
+	int i, pos, fill;
+	void *ret;
+
+	if (level > head->height) {
+		/* we recursed all the way up */
+		head->height = 0;
+		head->node = NULL;
+		return NULL;
+	}
+
+	node = find_level(head, geo, key, level);
+	pos = getpos(geo, node, key);
+	fill = getfill(geo, node, pos);
+	if ((level == 1) && (keycmp(geo, node, pos, key) != 0))
+		return NULL;
+	ret = bval(geo, node, pos);
+
+	/* remove and shift */
+	for (i = pos; i < fill - 1; i++) {
+		setkey(geo, node, i, bkey(geo, node, i + 1));
+		setval(geo, node, i, bval(geo, node, i + 1));
+	}
+	clearpair(geo, node, fill - 1);
+
+	if (fill - 1 < geo->no_pairs / 2) {
+		if (level < head->height)
+			rebalance(head, geo, key, level, node, fill - 1);
+		else if (fill - 1 == 1)
+			btree_shrink(head, geo);
+	}
+
+	return ret;
+}
+
+void *btree_remove(struct btree_head *head, struct btree_geo *geo,
+		unsigned long *key)
+{
+	if (head->height == 0)
+		return NULL;
+
+	return btree_remove_level(head, geo, key, 1);
+}
+EXPORT_SYMBOL_GPL(btree_remove);
+
+int btree_merge(struct btree_head *target, struct btree_head *victim,
+		struct btree_geo *geo, gfp_t gfp)
+{
+	unsigned long key[geo->keylen];
+	unsigned long dup[geo->keylen];
+	void *val;
+	int err;
+
+	BUG_ON(target == victim);
+
+	if (!(target->node)) {
+		/* target is empty, just copy fields over */
+		target->node = victim->node;
+		target->height = victim->height;
+		__btree_init(victim);
+		return 0;
+	}
+
+	/* TODO: This needs some optimizations.  Currently we do three tree
+	 * walks to remove a single object from the victim.
+	 */
+	for (;;) {
+		if (!btree_last(victim, geo, key))
+			break;
+		val = btree_lookup(victim, geo, key);
+		err = btree_insert(target, geo, key, val, gfp);
+		if (err)
+			return err;
+		/* We must make a copy of the key, as the original will get
+		 * mangled inside btree_remove. */
+		longcpy(dup, key, geo->keylen);
+		btree_remove(victim, geo, dup);
+	}
+	return 0;
+}
+EXPORT_SYMBOL_GPL(btree_merge);
+
+static size_t __btree_for_each(struct btree_head *head, struct btree_geo *geo,
+			       unsigned long *node, unsigned long opaque,
+			       void (*func)(void *elem, unsigned long opaque,
+					    unsigned long *key, size_t index,
+					    void *func2),
+			       void *func2, int reap, int height, size_t count)
+{
+	int i;
+	unsigned long *child;
+
+	for (i = 0; i < geo->no_pairs; i++) {
+		child = bval(geo, node, i);
+		if (!child)
+			break;
+		if (height > 1)
+			count = __btree_for_each(head, geo, child, opaque,
+					func, func2, reap, height - 1, count);
+		else
+			func(child, opaque, bkey(geo, node, i), count++,
+					func2);
+	}
+	if (reap)
+		mempool_free(node, head->mempool);
+	return count;
+}
+
+static void empty(void *elem, unsigned long opaque, unsigned long *key,
+		  size_t index, void *func2)
+{
+}
+
+void visitorl(void *elem, unsigned long opaque, unsigned long *key,
+	      size_t index, void *__func)
+{
+	visitorl_t func = __func;
+
+	func(elem, opaque, *key, index);
+}
+EXPORT_SYMBOL_GPL(visitorl);
+
+void visitor32(void *elem, unsigned long opaque, unsigned long *__key,
+	       size_t index, void *__func)
+{
+	visitor32_t func = __func;
+	u32 *key = (void *)__key;
+
+	func(elem, opaque, *key, index);
+}
+EXPORT_SYMBOL_GPL(visitor32);
+
+void visitor64(void *elem, unsigned long opaque, unsigned long *__key,
+	       size_t index, void *__func)
+{
+	visitor64_t func = __func;
+	u64 *key = (void *)__key;
+
+	func(elem, opaque, *key, index);
+}
+EXPORT_SYMBOL_GPL(visitor64);
+
+void visitor128(void *elem, unsigned long opaque, unsigned long *__key,
+		size_t index, void *__func)
+{
+	visitor128_t func = __func;
+	u64 *key = (void *)__key;
+
+	func(elem, opaque, key[0], key[1], index);
+}
+EXPORT_SYMBOL_GPL(visitor128);
+
+size_t btree_visitor(struct btree_head *head, struct btree_geo *geo,
+		     unsigned long opaque,
+		     void (*func)(void *elem, unsigned long opaque,
+		     		  unsigned long *key,
+		     		  size_t index, void *func2),
+		     void *func2)
+{
+	size_t count = 0;
+
+	if (!func2)
+		func = empty;
+	if (head->node)
+		count = __btree_for_each(head, geo, head->node, opaque, func,
+				func2, 0, head->height, 0);
+	return count;
+}
+EXPORT_SYMBOL_GPL(btree_visitor);
+
+size_t btree_grim_visitor(struct btree_head *head, struct btree_geo *geo,
+			  unsigned long opaque,
+			  void (*func)(void *elem, unsigned long opaque,
+				       unsigned long *key,
+				       size_t index, void *func2),
+			  void *func2)
+{
+	size_t count = 0;
+
+	if (!func2)
+		func = empty;
+	if (head->node)
+		count = __btree_for_each(head, geo, head->node, opaque, func,
+				func2, 1, head->height, 0);
+	__btree_init(head);
+	return count;
+}
+EXPORT_SYMBOL_GPL(btree_grim_visitor);
+
+static int __init btree_module_init(void)
+{
+	btree_cachep = kmem_cache_create("btree_node", NODESIZE, 0,
+			SLAB_HWCACHE_ALIGN, NULL);
+	return 0;
+}
+
+static void __exit btree_module_exit(void)
+{
+	kmem_cache_destroy(btree_cachep);
+}
+
+/* If core code starts using btree, initialization should happen even earlier */
+module_init(btree_module_init);
+module_exit(btree_module_exit);
+
+MODULE_AUTHOR("Joern Engel <joern@logfs.org>");
+MODULE_AUTHOR("Johannes Berg <johannes@sipsolutions.net>");
+MODULE_LICENSE("GPL");
diff --git a/lib/bug.c b/lib/bug.c
index 300e41afbf9..f13daf43521 100644
--- a/lib/bug.c
+++ b/lib/bug.c
@@ -165,7 +165,7 @@ enum bug_trap_type report_bug(unsigned long bugaddr, struct pt_regs *regs)
 			       (void *)bugaddr);
 
 		show_regs(regs);
-		add_taint(TAINT_WARN);
+		add_taint(BUG_GET_TAINT(bug));
 		return BUG_TRAP_TYPE_WARN;
 	}
 
diff --git a/lib/cpu-notifier-error-inject.c b/lib/cpu-notifier-error-inject.c
new file mode 100644
index 00000000000..4dc20321b0d
--- /dev/null
+++ b/lib/cpu-notifier-error-inject.c
@@ -0,0 +1,63 @@
+#include <linux/kernel.h>
+#include <linux/cpu.h>
+#include <linux/module.h>
+#include <linux/notifier.h>
+
+static int priority;
+static int cpu_up_prepare_error;
+static int cpu_down_prepare_error;
+
+module_param(priority, int, 0);
+MODULE_PARM_DESC(priority, "specify cpu notifier priority");
+
+module_param(cpu_up_prepare_error, int, 0644);
+MODULE_PARM_DESC(cpu_up_prepare_error,
+		"specify error code to inject CPU_UP_PREPARE action");
+
+module_param(cpu_down_prepare_error, int, 0644);
+MODULE_PARM_DESC(cpu_down_prepare_error,
+		"specify error code to inject CPU_DOWN_PREPARE action");
+
+static int err_inject_cpu_callback(struct notifier_block *nfb,
+				unsigned long action, void *hcpu)
+{
+	int err = 0;
+
+	switch (action) {
+	case CPU_UP_PREPARE:
+	case CPU_UP_PREPARE_FROZEN:
+		err = cpu_up_prepare_error;
+		break;
+	case CPU_DOWN_PREPARE:
+	case CPU_DOWN_PREPARE_FROZEN:
+		err = cpu_down_prepare_error;
+		break;
+	}
+	if (err)
+		printk(KERN_INFO "Injecting error (%d) at cpu notifier\n", err);
+
+	return notifier_from_errno(err);
+}
+
+static struct notifier_block err_inject_cpu_notifier = {
+	.notifier_call = err_inject_cpu_callback,
+};
+
+static int err_inject_init(void)
+{
+	err_inject_cpu_notifier.priority = priority;
+
+	return register_hotcpu_notifier(&err_inject_cpu_notifier);
+}
+
+static void err_inject_exit(void)
+{
+	unregister_hotcpu_notifier(&err_inject_cpu_notifier);
+}
+
+module_init(err_inject_init);
+module_exit(err_inject_exit);
+
+MODULE_DESCRIPTION("CPU notifier error injection module");
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Akinobu Mita <akinobu.mita@gmail.com>");
diff --git a/lib/cpumask.c b/lib/cpumask.c
index 7bb4142a502..05d6aca7fc1 100644
--- a/lib/cpumask.c
+++ b/lib/cpumask.c
@@ -1,3 +1,4 @@
+#include <linux/slab.h>
 #include <linux/kernel.h>
 #include <linux/bitops.h>
 #include <linux/cpumask.h>
diff --git a/lib/crc32.c b/lib/crc32.c
index 02e3b31b3a7..4855995fcde 100644
--- a/lib/crc32.c
+++ b/lib/crc32.c
@@ -25,16 +25,19 @@
 #include <linux/module.h>
 #include <linux/compiler.h>
 #include <linux/types.h>
-#include <linux/slab.h>
 #include <linux/init.h>
 #include <asm/atomic.h>
 #include "crc32defs.h"
 #if CRC_LE_BITS == 8
-#define tole(x) __constant_cpu_to_le32(x)
-#define tobe(x) __constant_cpu_to_be32(x)
+# define tole(x) __constant_cpu_to_le32(x)
 #else
-#define tole(x) (x)
-#define tobe(x) (x)
+# define tole(x) (x)
+#endif
+
+#if CRC_BE_BITS == 8
+# define tobe(x) __constant_cpu_to_be32(x)
+#else
+# define tobe(x) (x)
 #endif
 #include "crc32table.h"
 
@@ -45,33 +48,37 @@ 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)
+crc32_body(u32 crc, unsigned char const *buf, size_t len, const u32 (*tab)[256])
 {
 # ifdef __LITTLE_ENDIAN
-#  define DO_CRC(x) crc = tab[(crc ^ (x)) & 255 ] ^ (crc >> 8)
+#  define DO_CRC(x) crc = tab[0][(crc ^ (x)) & 255] ^ (crc >> 8)
+#  define DO_CRC4 crc = tab[3][(crc) & 255] ^ \
+		tab[2][(crc >> 8) & 255] ^ \
+		tab[1][(crc >> 16) & 255] ^ \
+		tab[0][(crc >> 24) & 255]
 # else
-#  define DO_CRC(x) crc = tab[((crc >> 24) ^ (x)) & 255] ^ (crc << 8)
+#  define DO_CRC(x) crc = tab[0][((crc >> 24) ^ (x)) & 255] ^ (crc << 8)
+#  define DO_CRC4 crc = tab[0][(crc) & 255] ^ \
+		tab[1][(crc >> 8) & 255] ^ \
+		tab[2][(crc >> 16) & 255] ^ \
+		tab[3][(crc >> 24) & 255]
 # endif
-	const u32 *b = (const u32 *)buf;
+	const u32 *b;
 	size_t    rem_len;
 
 	/* Align it */
-	if (unlikely((long)b & 3 && len)) {
-		u8 *p = (u8 *)b;
+	if (unlikely((long)buf & 3 && len)) {
 		do {
-			DO_CRC(*p++);
-		} while ((--len) && ((long)p)&3);
-		b = (u32 *)p;
+			DO_CRC(*buf++);
+		} while ((--len) && ((long)buf)&3);
 	}
 	rem_len = len & 3;
 	/* load data 32 bits wide, xor data 32 bits wide. */
 	len = len >> 2;
+	b = (const u32 *)buf;
 	for (--b; len; --len) {
 		crc ^= *++b; /* use pre increment for speed */
-		DO_CRC(0);
-		DO_CRC(0);
-		DO_CRC(0);
-		DO_CRC(0);
+		DO_CRC4;
 	}
 	len = rem_len;
 	/* And the last few bytes */
@@ -82,6 +89,8 @@ crc32_body(u32 crc, unsigned char const *buf, size_t len, const u32 *tab)
 		} while (--len);
 	}
 	return crc;
+#undef DO_CRC
+#undef DO_CRC4
 }
 #endif
 /**
@@ -114,14 +123,11 @@ 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      *tab = crc32table_le;
+	const u32      (*tab)[] = crc32table_le;
 
 	crc = __cpu_to_le32(crc);
 	crc = crc32_body(crc, p, len, tab);
 	return __le32_to_cpu(crc);
-#undef ENDIAN_SHIFT
-#undef DO_CRC
-
 # elif CRC_LE_BITS == 4
 	while (len--) {
 		crc ^= *p++;
@@ -174,14 +180,11 @@ 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      *tab = crc32table_be;
+	const u32      (*tab)[] = crc32table_be;
 
 	crc = __cpu_to_be32(crc);
 	crc = crc32_body(crc, p, len, tab);
 	return __be32_to_cpu(crc);
-#undef ENDIAN_SHIFT
-#undef DO_CRC
-
 # elif CRC_BE_BITS == 4
 	while (len--) {
 		crc ^= *p++ << 24;
diff --git a/lib/debug_locks.c b/lib/debug_locks.c
index bc3b11731b9..5bf0020b924 100644
--- a/lib/debug_locks.c
+++ b/lib/debug_locks.c
@@ -23,6 +23,7 @@
  * shut up after that.
  */
 int debug_locks = 1;
+EXPORT_SYMBOL_GPL(debug_locks);
 
 /*
  * The locking-testsuite uses <debug_locks_silent> to get a
diff --git a/lib/debugobjects.c b/lib/debugobjects.c
index a9a8996d286..deebcc57d4e 100644
--- a/lib/debugobjects.c
+++ b/lib/debugobjects.c
@@ -12,6 +12,7 @@
 #include <linux/sched.h>
 #include <linux/seq_file.h>
 #include <linux/debugfs.h>
+#include <linux/slab.h>
 #include <linux/hash.h>
 
 #define ODEBUG_HASH_BITS	14
@@ -140,6 +141,7 @@ alloc_object(void *addr, struct debug_bucket *b, struct debug_obj_descr *descr)
 		obj->object = addr;
 		obj->descr  = descr;
 		obj->state  = ODEBUG_STATE_NONE;
+		obj->astate = 0;
 		hlist_del(&obj->node);
 
 		hlist_add_head(&obj->node, &b->list);
@@ -251,8 +253,10 @@ static void debug_print_object(struct debug_obj *obj, char *msg)
 
 	if (limit < 5 && obj->descr != descr_test) {
 		limit++;
-		WARN(1, KERN_ERR "ODEBUG: %s %s object type: %s\n", msg,
-		       obj_states[obj->state], obj->descr->name);
+		WARN(1, KERN_ERR "ODEBUG: %s %s (active state %u) "
+				 "object type: %s\n",
+			msg, obj_states[obj->state], obj->astate,
+			obj->descr->name);
 	}
 	debug_objects_warnings++;
 }
@@ -446,7 +450,10 @@ void debug_object_deactivate(void *addr, struct debug_obj_descr *descr)
 		case ODEBUG_STATE_INIT:
 		case ODEBUG_STATE_INACTIVE:
 		case ODEBUG_STATE_ACTIVE:
-			obj->state = ODEBUG_STATE_INACTIVE;
+			if (!obj->astate)
+				obj->state = ODEBUG_STATE_INACTIVE;
+			else
+				debug_print_object(obj, "deactivate");
 			break;
 
 		case ODEBUG_STATE_DESTROYED:
@@ -552,6 +559,53 @@ out_unlock:
 	raw_spin_unlock_irqrestore(&db->lock, flags);
 }
 
+/**
+ * debug_object_active_state - debug checks object usage state machine
+ * @addr:	address of the object
+ * @descr:	pointer to an object specific debug description structure
+ * @expect:	expected state
+ * @next:	state to move to if expected state is found
+ */
+void
+debug_object_active_state(void *addr, struct debug_obj_descr *descr,
+			  unsigned int expect, unsigned int next)
+{
+	struct debug_bucket *db;
+	struct debug_obj *obj;
+	unsigned long flags;
+
+	if (!debug_objects_enabled)
+		return;
+
+	db = get_bucket((unsigned long) addr);
+
+	raw_spin_lock_irqsave(&db->lock, flags);
+
+	obj = lookup_object(addr, db);
+	if (obj) {
+		switch (obj->state) {
+		case ODEBUG_STATE_ACTIVE:
+			if (obj->astate == expect)
+				obj->astate = next;
+			else
+				debug_print_object(obj, "active_state");
+			break;
+
+		default:
+			debug_print_object(obj, "active_state");
+			break;
+		}
+	} else {
+		struct debug_obj o = { .object = addr,
+				       .state = ODEBUG_STATE_NOTAVAILABLE,
+				       .descr = descr };
+
+		debug_print_object(&o, "active_state");
+	}
+
+	raw_spin_unlock_irqrestore(&db->lock, flags);
+}
+
 #ifdef CONFIG_DEBUG_OBJECTS_FREE
 static void __debug_check_no_obj_freed(const void *address, unsigned long size)
 {
@@ -773,7 +827,7 @@ static int __init fixup_free(void *addr, enum debug_obj_state state)
 	}
 }
 
-static int
+static int __init
 check_results(void *addr, enum debug_obj_state state, int fixups, int warnings)
 {
 	struct debug_bucket *db;
@@ -916,7 +970,7 @@ void __init debug_objects_early_init(void)
 /*
  * Convert the statically allocated objects to dynamic ones:
  */
-static int debug_objects_replace_static_objects(void)
+static int __init debug_objects_replace_static_objects(void)
 {
 	struct debug_bucket *db = obj_hash;
 	struct hlist_node *node, *tmp;
diff --git a/lib/decompress_unlzo.c b/lib/decompress_unlzo.c
index db521f45626..bcb3a4bd68f 100644
--- a/lib/decompress_unlzo.c
+++ b/lib/decompress_unlzo.c
@@ -97,7 +97,7 @@ STATIC inline int INIT unlzo(u8 *input, int in_len,
 	u32 src_len, dst_len;
 	size_t tmp;
 	u8 *in_buf, *in_buf_save, *out_buf;
-	int obytes_processed = 0;
+	int ret = -1;
 
 	set_error_fn(error_fn);
 
@@ -174,15 +174,22 @@ STATIC inline int INIT unlzo(u8 *input, int in_len,
 
 		/* decompress */
 		tmp = dst_len;
-		r = lzo1x_decompress_safe((u8 *) in_buf, src_len,
+
+		/* When the input data is not compressed at all,
+		 * lzo1x_decompress_safe will fail, so call memcpy()
+		 * instead */
+		if (unlikely(dst_len == src_len))
+			memcpy(out_buf, in_buf, src_len);
+		else {
+			r = lzo1x_decompress_safe((u8 *) in_buf, src_len,
 						out_buf, &tmp);
 
-		if (r != LZO_E_OK || dst_len != tmp) {
-			error("Compressed data violation");
-			goto exit_2;
+			if (r != LZO_E_OK || dst_len != tmp) {
+				error("Compressed data violation");
+				goto exit_2;
+			}
 		}
 
-		obytes_processed += dst_len;
 		if (flush)
 			flush(out_buf, dst_len);
 		if (output)
@@ -196,6 +203,7 @@ STATIC inline int INIT unlzo(u8 *input, int in_len,
 			in_buf += src_len;
 	}
 
+	ret = 0;
 exit_2:
 	if (!input)
 		free(in_buf);
@@ -203,7 +211,7 @@ exit_1:
 	if (!output)
 		free(out_buf);
 exit:
-	return obytes_processed;
+	return ret;
 }
 
 #define decompress unlzo
diff --git a/lib/devres.c b/lib/devres.c
index 72c8909006d..49368608f98 100644
--- a/lib/devres.c
+++ b/lib/devres.c
@@ -1,5 +1,6 @@
 #include <linux/pci.h>
 #include <linux/io.h>
+#include <linux/gfp.h>
 #include <linux/module.h>
 
 void devm_ioremap_release(struct device *dev, void *res)
diff --git a/lib/dma-debug.c b/lib/dma-debug.c
index 7d2f0b33e5a..01e64270e24 100644
--- a/lib/dma-debug.c
+++ b/lib/dma-debug.c
@@ -570,7 +570,7 @@ static ssize_t filter_write(struct file *file, const char __user *userbuf,
 	 * Now parse out the first token and use it as the name for the
 	 * driver to filter for.
 	 */
-	for (i = 0; i < NAME_MAX_LEN; ++i) {
+	for (i = 0; i < NAME_MAX_LEN - 1; ++i) {
 		current_driver_name[i] = buf[i];
 		if (isspace(buf[i]) || buf[i] == ' ' || buf[i] == 0)
 			break;
@@ -587,7 +587,7 @@ out_unlock:
 	return count;
 }
 
-const struct file_operations filter_fops = {
+static const struct file_operations filter_fops = {
 	.read  = filter_read,
 	.write = filter_write,
 };
diff --git a/lib/dynamic_debug.c b/lib/dynamic_debug.c
index f9350291598..02afc253372 100644
--- a/lib/dynamic_debug.c
+++ b/lib/dynamic_debug.c
@@ -25,6 +25,7 @@
 #include <linux/uaccess.h>
 #include <linux/dynamic_debug.h>
 #include <linux/debugfs.h>
+#include <linux/slab.h>
 
 extern struct _ddebug __start___verbose[];
 extern struct _ddebug __stop___verbose[];
@@ -455,7 +456,7 @@ static ssize_t ddebug_proc_write(struct file *file, const char __user *ubuf,
 			__func__, (int)len);
 
 	nwords = ddebug_tokenize(tmpbuf, words, MAXWORDS);
-	if (nwords < 0)
+	if (nwords <= 0)
 		return -EINVAL;
 	if (ddebug_parse_query(words, nwords-1, &query))
 		return -EINVAL;
@@ -691,7 +692,7 @@ static void ddebug_table_free(struct ddebug_table *dt)
  * Called in response to a module being unloaded.  Removes
  * any ddebug_table's which point at the module.
  */
-int ddebug_remove_module(char *mod_name)
+int ddebug_remove_module(const char *mod_name)
 {
 	struct ddebug_table *dt, *nextdt;
 	int ret = -ENOENT;
diff --git a/lib/flex_array.c b/lib/flex_array.c
index 66eef2e4483..41b1804fa72 100644
--- a/lib/flex_array.c
+++ b/lib/flex_array.c
@@ -99,7 +99,7 @@ struct flex_array *flex_array_alloc(int element_size, unsigned int total,
 	ret->element_size = element_size;
 	ret->total_nr_elements = total;
 	if (elements_fit_in_base(ret) && !(flags & __GFP_ZERO))
-		memset(ret->parts[0], FLEX_ARRAY_FREE,
+		memset(&ret->parts[0], FLEX_ARRAY_FREE,
 						FLEX_ARRAY_BASE_BYTES_LEFT);
 	return ret;
 }
diff --git a/lib/gen_crc32table.c b/lib/gen_crc32table.c
index bea5d97df99..85d0e412a04 100644
--- a/lib/gen_crc32table.c
+++ b/lib/gen_crc32table.c
@@ -7,8 +7,8 @@
 #define LE_TABLE_SIZE (1 << CRC_LE_BITS)
 #define BE_TABLE_SIZE (1 << CRC_BE_BITS)
 
-static uint32_t crc32table_le[LE_TABLE_SIZE];
-static uint32_t crc32table_be[BE_TABLE_SIZE];
+static uint32_t crc32table_le[4][LE_TABLE_SIZE];
+static uint32_t crc32table_be[4][BE_TABLE_SIZE];
 
 /**
  * crc32init_le() - allocate and initialize LE table data
@@ -22,12 +22,19 @@ static void crc32init_le(void)
 	unsigned i, j;
 	uint32_t crc = 1;
 
-	crc32table_le[0] = 0;
+	crc32table_le[0][0] = 0;
 
 	for (i = 1 << (CRC_LE_BITS - 1); i; i >>= 1) {
 		crc = (crc >> 1) ^ ((crc & 1) ? CRCPOLY_LE : 0);
 		for (j = 0; j < LE_TABLE_SIZE; j += 2 * i)
-			crc32table_le[i + j] = crc ^ crc32table_le[j];
+			crc32table_le[0][i + j] = crc ^ crc32table_le[0][j];
+	}
+	for (i = 0; i < LE_TABLE_SIZE; i++) {
+		crc = crc32table_le[0][i];
+		for (j = 1; j < 4; j++) {
+			crc = crc32table_le[0][crc & 0xff] ^ (crc >> 8);
+			crc32table_le[j][i] = crc;
+		}
 	}
 }
 
@@ -39,25 +46,35 @@ static void crc32init_be(void)
 	unsigned i, j;
 	uint32_t crc = 0x80000000;
 
-	crc32table_be[0] = 0;
+	crc32table_be[0][0] = 0;
 
 	for (i = 1; i < BE_TABLE_SIZE; i <<= 1) {
 		crc = (crc << 1) ^ ((crc & 0x80000000) ? CRCPOLY_BE : 0);
 		for (j = 0; j < i; j++)
-			crc32table_be[i + j] = crc ^ crc32table_be[j];
+			crc32table_be[0][i + j] = crc ^ crc32table_be[0][j];
+	}
+	for (i = 0; i < BE_TABLE_SIZE; i++) {
+		crc = crc32table_be[0][i];
+		for (j = 1; j < 4; j++) {
+			crc = crc32table_be[0][(crc >> 24) & 0xff] ^ (crc << 8);
+			crc32table_be[j][i] = crc;
+		}
 	}
 }
 
-static void output_table(uint32_t table[], int len, char *trans)
+static void output_table(uint32_t table[4][256], int len, char *trans)
 {
-	int i;
+	int i, j;
 
-	for (i = 0; i < len - 1; i++) {
-		if (i % ENTRIES_PER_LINE == 0)
-			printf("\n");
-		printf("%s(0x%8.8xL), ", trans, table[i]);
+	for (j = 0 ; j < 4; j++) {
+		printf("{");
+		for (i = 0; i < len - 1; i++) {
+			if (i % ENTRIES_PER_LINE == 0)
+				printf("\n");
+			printf("%s(0x%8.8xL), ", trans, table[j][i]);
+		}
+		printf("%s(0x%8.8xL)},\n", trans, table[j][len - 1]);
 	}
-	printf("%s(0x%8.8xL)\n", trans, table[len - 1]);
 }
 
 int main(int argc, char** argv)
@@ -66,14 +83,14 @@ int main(int argc, char** argv)
 
 	if (CRC_LE_BITS > 1) {
 		crc32init_le();
-		printf("static const u32 crc32table_le[] = {");
+		printf("static const u32 crc32table_le[4][256] = {");
 		output_table(crc32table_le, LE_TABLE_SIZE, "tole");
 		printf("};\n");
 	}
 
 	if (CRC_BE_BITS > 1) {
 		crc32init_be();
-		printf("static const u32 crc32table_be[] = {");
+		printf("static const u32 crc32table_be[4][256] = {");
 		output_table(crc32table_be, BE_TABLE_SIZE, "tobe");
 		printf("};\n");
 	}
diff --git a/lib/genalloc.c b/lib/genalloc.c
index e67f97495dd..1923f1490e7 100644
--- a/lib/genalloc.c
+++ b/lib/genalloc.c
@@ -10,6 +10,7 @@
  * Version 2.  See the file COPYING for more details.
  */
 
+#include <linux/slab.h>
 #include <linux/module.h>
 #include <linux/bitmap.h>
 #include <linux/genalloc.h>
@@ -127,7 +128,6 @@ unsigned long gen_pool_alloc(struct gen_pool *pool, size_t size)
 		chunk = list_entry(_chunk, struct gen_pool_chunk, next_chunk);
 
 		end_bit = (chunk->end_addr - chunk->start_addr) >> order;
-		end_bit -= nbits + 1;
 
 		spin_lock_irqsave(&chunk->lock, flags);
 		start_bit = bitmap_find_next_zero_area(chunk->bits, end_bit, 0,
diff --git a/lib/hexdump.c b/lib/hexdump.c
index 39af2560f76..5d7a4802c56 100644
--- a/lib/hexdump.c
+++ b/lib/hexdump.c
@@ -16,6 +16,24 @@ const char hex_asc[] = "0123456789abcdef";
 EXPORT_SYMBOL(hex_asc);
 
 /**
+ * hex_to_bin - convert a hex digit to its real value
+ * @ch: ascii character represents hex digit
+ *
+ * hex_to_bin() converts one hex digit to its actual value or -1 in case of bad
+ * input.
+ */
+int hex_to_bin(char ch)
+{
+	if ((ch >= '0') && (ch <= '9'))
+		return ch - '0';
+	ch = tolower(ch);
+	if ((ch >= 'a') && (ch <= 'f'))
+		return ch - 'a' + 10;
+	return -1;
+}
+EXPORT_SYMBOL(hex_to_bin);
+
+/**
  * hex_dump_to_buffer - convert a blob of data to "hex ASCII" in memory
  * @buf: data blob to dump
  * @len: number of bytes in the @buf
@@ -34,7 +52,7 @@ EXPORT_SYMBOL(hex_asc);
  *
  * E.g.:
  *   hex_dump_to_buffer(frame->data, frame->len, 16, 1,
- *			linebuf, sizeof(linebuf), 1);
+ *			linebuf, sizeof(linebuf), true);
  *
  * example output buffer:
  * 40 41 42 43 44 45 46 47 48 49 4a 4b 4c 4d 4e 4f  @ABCDEFGHIJKLMNO
@@ -65,8 +83,8 @@ void hex_dump_to_buffer(const void *buf, size_t len, int rowsize,
 
 		for (j = 0; j < ngroups; j++)
 			lx += scnprintf(linebuf + lx, linebuflen - lx,
-				"%s%16.16llx", j ? " " : "",
-				(unsigned long long)*(ptr8 + j));
+					"%s%16.16llx", j ? " " : "",
+					(unsigned long long)*(ptr8 + j));
 		ascii_column = 17 * ngroups + 2;
 		break;
 	}
@@ -77,7 +95,7 @@ void hex_dump_to_buffer(const void *buf, size_t len, int rowsize,
 
 		for (j = 0; j < ngroups; j++)
 			lx += scnprintf(linebuf + lx, linebuflen - lx,
-				"%s%8.8x", j ? " " : "", *(ptr4 + j));
+					"%s%8.8x", j ? " " : "", *(ptr4 + j));
 		ascii_column = 9 * ngroups + 2;
 		break;
 	}
@@ -88,7 +106,7 @@ void hex_dump_to_buffer(const void *buf, size_t len, int rowsize,
 
 		for (j = 0; j < ngroups; j++)
 			lx += scnprintf(linebuf + lx, linebuflen - lx,
-				"%s%4.4x", j ? " " : "", *(ptr2 + j));
+					"%s%4.4x", j ? " " : "", *(ptr2 + j));
 		ascii_column = 5 * ngroups + 2;
 		break;
 	}
@@ -111,9 +129,10 @@ void hex_dump_to_buffer(const void *buf, size_t len, int rowsize,
 
 	while (lx < (linebuflen - 1) && lx < (ascii_column - 1))
 		linebuf[lx++] = ' ';
-	for (j = 0; (j < len) && (lx + 2) < linebuflen; j++)
-		linebuf[lx++] = (isascii(ptr[j]) && isprint(ptr[j])) ? ptr[j]
-				: '.';
+	for (j = 0; (j < len) && (lx + 2) < linebuflen; j++) {
+		ch = ptr[j];
+		linebuf[lx++] = (isascii(ch) && isprint(ch)) ? ch : '.';
+	}
 nil:
 	linebuf[lx++] = '\0';
 }
@@ -143,7 +162,7 @@ EXPORT_SYMBOL(hex_dump_to_buffer);
  *
  * E.g.:
  *   print_hex_dump(KERN_DEBUG, "raw data: ", DUMP_PREFIX_ADDRESS,
- *		16, 1, frame->data, frame->len, 1);
+ *		    16, 1, frame->data, frame->len, true);
  *
  * Example output using %DUMP_PREFIX_OFFSET and 1-byte mode:
  * 0009ab42: 40 41 42 43 44 45 46 47 48 49 4a 4b 4c 4d 4e 4f  @ABCDEFGHIJKLMNO
@@ -151,12 +170,12 @@ EXPORT_SYMBOL(hex_dump_to_buffer);
  * ffffffff88089af0: 73727170 77767574 7b7a7978 7f7e7d7c  pqrstuvwxyz{|}~.
  */
 void print_hex_dump(const char *level, const char *prefix_str, int prefix_type,
-			int rowsize, int groupsize,
-			const void *buf, size_t len, bool ascii)
+		    int rowsize, int groupsize,
+		    const void *buf, size_t len, bool ascii)
 {
 	const u8 *ptr = buf;
 	int i, linelen, remaining = len;
-	unsigned char linebuf[200];
+	unsigned char linebuf[32 * 3 + 2 + 32 + 1];
 
 	if (rowsize != 16 && rowsize != 32)
 		rowsize = 16;
@@ -164,13 +183,14 @@ void print_hex_dump(const char *level, const char *prefix_str, int prefix_type,
 	for (i = 0; i < len; i += rowsize) {
 		linelen = min(remaining, rowsize);
 		remaining -= rowsize;
+
 		hex_dump_to_buffer(ptr + i, linelen, rowsize, groupsize,
-				linebuf, sizeof(linebuf), ascii);
+				   linebuf, sizeof(linebuf), ascii);
 
 		switch (prefix_type) {
 		case DUMP_PREFIX_ADDRESS:
-			printk("%s%s%*p: %s\n", level, prefix_str,
-				(int)(2 * sizeof(void *)), ptr + i, linebuf);
+			printk("%s%s%p: %s\n",
+			       level, prefix_str, ptr + i, linebuf);
 			break;
 		case DUMP_PREFIX_OFFSET:
 			printk("%s%s%.8x: %s\n", level, prefix_str, i, linebuf);
@@ -196,9 +216,9 @@ EXPORT_SYMBOL(print_hex_dump);
  * rowsize of 16, groupsize of 1, and ASCII output included.
  */
 void print_hex_dump_bytes(const char *prefix_str, int prefix_type,
-			const void *buf, size_t len)
+			  const void *buf, size_t len)
 {
 	print_hex_dump(KERN_DEBUG, prefix_str, prefix_type, 16, 1,
-			buf, len, 1);
+		       buf, len, true);
 }
 EXPORT_SYMBOL(print_hex_dump_bytes);
diff --git a/lib/hweight.c b/lib/hweight.c
index 389424ecb12..3c79d50814c 100644
--- a/lib/hweight.c
+++ b/lib/hweight.c
@@ -9,37 +9,45 @@
  * The Hamming Weight of a number is the total number of bits set in it.
  */
 
-unsigned int hweight32(unsigned int w)
+unsigned int __sw_hweight32(unsigned int w)
 {
+#ifdef ARCH_HAS_FAST_MULTIPLIER
+	w -= (w >> 1) & 0x55555555;
+	w =  (w & 0x33333333) + ((w >> 2) & 0x33333333);
+	w =  (w + (w >> 4)) & 0x0f0f0f0f;
+	return (w * 0x01010101) >> 24;
+#else
 	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;
+#endif
 }
-EXPORT_SYMBOL(hweight32);
+EXPORT_SYMBOL(__sw_hweight32);
 
-unsigned int hweight16(unsigned int w)
+unsigned int __sw_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);
+EXPORT_SYMBOL(__sw_hweight16);
 
-unsigned int hweight8(unsigned int w)
+unsigned int __sw_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);
+EXPORT_SYMBOL(__sw_hweight8);
 
-unsigned long hweight64(__u64 w)
+unsigned long __sw_hweight64(__u64 w)
 {
 #if BITS_PER_LONG == 32
-	return hweight32((unsigned int)(w >> 32)) + hweight32((unsigned int)w);
+	return __sw_hweight32((unsigned int)(w >> 32)) +
+	       __sw_hweight32((unsigned int)w);
 #elif BITS_PER_LONG == 64
 #ifdef ARCH_HAS_FAST_MULTIPLIER
 	w -= (w >> 1) & 0x5555555555555555ul;
@@ -56,4 +64,4 @@ unsigned long hweight64(__u64 w)
 #endif
 #endif
 }
-EXPORT_SYMBOL(hweight64);
+EXPORT_SYMBOL(__sw_hweight64);
diff --git a/lib/idr.c b/lib/idr.c
index 1cac726c44b..7f1a4f0acf5 100644
--- a/lib/idr.c
+++ b/lib/idr.c
@@ -156,10 +156,12 @@ static int sub_alloc(struct idr *idp, int *starting_id, struct idr_layer **pa)
 			id = (id | ((1 << (IDR_BITS * l)) - 1)) + 1;
 
 			/* if already at the top layer, we need to grow */
-			if (!(p = pa[l])) {
+			if (id >= 1 << (idp->layers * IDR_BITS)) {
 				*starting_id = id;
 				return IDR_NEED_TO_GROW;
 			}
+			p = pa[l];
+			BUG_ON(!p);
 
 			/* If we need to go up one layer, continue the
 			 * loop; otherwise, restart from the top.
@@ -443,6 +445,7 @@ EXPORT_SYMBOL(idr_remove);
 void idr_remove_all(struct idr *idp)
 {
 	int n, id, max;
+	int bt_mask;
 	struct idr_layer *p;
 	struct idr_layer *pa[MAX_LEVEL];
 	struct idr_layer **paa = &pa[0];
@@ -460,8 +463,10 @@ void idr_remove_all(struct idr *idp)
 			p = p->ary[(id >> n) & IDR_MASK];
 		}
 
+		bt_mask = id;
 		id += 1 << n;
-		while (n < fls(id)) {
+		/* Get the highest bit that the above add changed from 0->1. */
+		while (n < fls(id ^ bt_mask)) {
 			if (p)
 				free_layer(p);
 			n += IDR_BITS;
@@ -502,7 +507,7 @@ void *idr_find(struct idr *idp, int id)
 	int n;
 	struct idr_layer *p;
 
-	p = rcu_dereference(idp->top);
+	p = rcu_dereference_raw(idp->top);
 	if (!p)
 		return NULL;
 	n = (p->layer+1) * IDR_BITS;
@@ -517,7 +522,7 @@ void *idr_find(struct idr *idp, int id)
 	while (n > 0 && p) {
 		n -= IDR_BITS;
 		BUG_ON(n != p->layer*IDR_BITS);
-		p = rcu_dereference(p->ary[(id >> n) & IDR_MASK]);
+		p = rcu_dereference_raw(p->ary[(id >> n) & IDR_MASK]);
 	}
 	return((void *)p);
 }
@@ -550,7 +555,7 @@ int idr_for_each(struct idr *idp,
 	struct idr_layer **paa = &pa[0];
 
 	n = idp->layers * IDR_BITS;
-	p = rcu_dereference(idp->top);
+	p = rcu_dereference_raw(idp->top);
 	max = 1 << n;
 
 	id = 0;
@@ -558,7 +563,7 @@ int idr_for_each(struct idr *idp,
 		while (n > 0 && p) {
 			n -= IDR_BITS;
 			*paa++ = p;
-			p = rcu_dereference(p->ary[(id >> n) & IDR_MASK]);
+			p = rcu_dereference_raw(p->ary[(id >> n) & IDR_MASK]);
 		}
 
 		if (p) {
@@ -597,7 +602,7 @@ void *idr_get_next(struct idr *idp, int *nextidp)
 	/* find first ent */
 	n = idp->layers * IDR_BITS;
 	max = 1 << n;
-	p = rcu_dereference(idp->top);
+	p = rcu_dereference_raw(idp->top);
 	if (!p)
 		return NULL;
 
@@ -605,7 +610,7 @@ void *idr_get_next(struct idr *idp, int *nextidp)
 		while (n > 0 && p) {
 			n -= IDR_BITS;
 			*paa++ = p;
-			p = rcu_dereference(p->ary[(id >> n) & IDR_MASK]);
+			p = rcu_dereference_raw(p->ary[(id >> n) & IDR_MASK]);
 		}
 
 		if (p) {
@@ -621,7 +626,7 @@ void *idr_get_next(struct idr *idp, int *nextidp)
 	}
 	return NULL;
 }
-
+EXPORT_SYMBOL(idr_get_next);
 
 
 /**
diff --git a/lib/inflate.c b/lib/inflate.c
index d10255973a9..677b738c220 100644
--- a/lib/inflate.c
+++ b/lib/inflate.c
@@ -103,6 +103,7 @@
       the two sets of lengths.
  */
 #include <linux/compiler.h>
+#include <linux/slab.h>
 
 #ifdef RCSID
 static char rcsid[] = "#Id: inflate.c,v 0.14 1993/06/10 13:27:04 jloup Exp #";
diff --git a/lib/kasprintf.c b/lib/kasprintf.c
index c5ff1fd1003..9c4233b2378 100644
--- a/lib/kasprintf.c
+++ b/lib/kasprintf.c
@@ -6,6 +6,7 @@
 
 #include <stdarg.h>
 #include <linux/module.h>
+#include <linux/slab.h>
 #include <linux/types.h>
 #include <linux/string.h>
 
diff --git a/lib/kobject.c b/lib/kobject.c
index b512b746d2a..f07c57252e8 100644
--- a/lib/kobject.c
+++ b/lib/kobject.c
@@ -700,7 +700,7 @@ static ssize_t kobj_attr_store(struct kobject *kobj, struct attribute *attr,
 	return ret;
 }
 
-struct sysfs_ops kobj_sysfs_ops = {
+const struct sysfs_ops kobj_sysfs_ops = {
 	.show	= kobj_attr_show,
 	.store	= kobj_attr_store,
 };
@@ -789,7 +789,7 @@ static struct kobj_type kset_ktype = {
  * If the kset was not able to be created, NULL will be returned.
  */
 static struct kset *kset_create(const char *name,
-				struct kset_uevent_ops *uevent_ops,
+				const struct kset_uevent_ops *uevent_ops,
 				struct kobject *parent_kobj)
 {
 	struct kset *kset;
@@ -832,7 +832,7 @@ static struct kset *kset_create(const char *name,
  * If the kset was not able to be created, NULL will be returned.
  */
 struct kset *kset_create_and_add(const char *name,
-				 struct kset_uevent_ops *uevent_ops,
+				 const struct kset_uevent_ops *uevent_ops,
 				 struct kobject *parent_kobj)
 {
 	struct kset *kset;
@@ -850,6 +850,121 @@ struct kset *kset_create_and_add(const char *name,
 }
 EXPORT_SYMBOL_GPL(kset_create_and_add);
 
+
+static DEFINE_SPINLOCK(kobj_ns_type_lock);
+static const struct kobj_ns_type_operations *kobj_ns_ops_tbl[KOBJ_NS_TYPES];
+
+int kobj_ns_type_register(const struct kobj_ns_type_operations *ops)
+{
+	enum kobj_ns_type type = ops->type;
+	int error;
+
+	spin_lock(&kobj_ns_type_lock);
+
+	error = -EINVAL;
+	if (type >= KOBJ_NS_TYPES)
+		goto out;
+
+	error = -EINVAL;
+	if (type <= KOBJ_NS_TYPE_NONE)
+		goto out;
+
+	error = -EBUSY;
+	if (kobj_ns_ops_tbl[type])
+		goto out;
+
+	error = 0;
+	kobj_ns_ops_tbl[type] = ops;
+
+out:
+	spin_unlock(&kobj_ns_type_lock);
+	return error;
+}
+
+int kobj_ns_type_registered(enum kobj_ns_type type)
+{
+	int registered = 0;
+
+	spin_lock(&kobj_ns_type_lock);
+	if ((type > KOBJ_NS_TYPE_NONE) && (type < KOBJ_NS_TYPES))
+		registered = kobj_ns_ops_tbl[type] != NULL;
+	spin_unlock(&kobj_ns_type_lock);
+
+	return registered;
+}
+
+const struct kobj_ns_type_operations *kobj_child_ns_ops(struct kobject *parent)
+{
+	const struct kobj_ns_type_operations *ops = NULL;
+
+	if (parent && parent->ktype->child_ns_type)
+		ops = parent->ktype->child_ns_type(parent);
+
+	return ops;
+}
+
+const struct kobj_ns_type_operations *kobj_ns_ops(struct kobject *kobj)
+{
+	return kobj_child_ns_ops(kobj->parent);
+}
+
+
+const void *kobj_ns_current(enum kobj_ns_type type)
+{
+	const void *ns = NULL;
+
+	spin_lock(&kobj_ns_type_lock);
+	if ((type > KOBJ_NS_TYPE_NONE) && (type < KOBJ_NS_TYPES) &&
+	    kobj_ns_ops_tbl[type])
+		ns = kobj_ns_ops_tbl[type]->current_ns();
+	spin_unlock(&kobj_ns_type_lock);
+
+	return ns;
+}
+
+const void *kobj_ns_netlink(enum kobj_ns_type type, struct sock *sk)
+{
+	const void *ns = NULL;
+
+	spin_lock(&kobj_ns_type_lock);
+	if ((type > KOBJ_NS_TYPE_NONE) && (type < KOBJ_NS_TYPES) &&
+	    kobj_ns_ops_tbl[type])
+		ns = kobj_ns_ops_tbl[type]->netlink_ns(sk);
+	spin_unlock(&kobj_ns_type_lock);
+
+	return ns;
+}
+
+const void *kobj_ns_initial(enum kobj_ns_type type)
+{
+	const void *ns = NULL;
+
+	spin_lock(&kobj_ns_type_lock);
+	if ((type > KOBJ_NS_TYPE_NONE) && (type < KOBJ_NS_TYPES) &&
+	    kobj_ns_ops_tbl[type])
+		ns = kobj_ns_ops_tbl[type]->initial_ns();
+	spin_unlock(&kobj_ns_type_lock);
+
+	return ns;
+}
+
+/*
+ * kobj_ns_exit - invalidate a namespace tag
+ *
+ * @type: the namespace type (i.e. KOBJ_NS_TYPE_NET)
+ * @ns: the actual namespace being invalidated
+ *
+ * This is called when a tag is no longer valid.  For instance,
+ * when a network namespace exits, it uses this helper to
+ * make sure no sb's sysfs_info points to the now-invalidated
+ * netns.
+ */
+void kobj_ns_exit(enum kobj_ns_type type, const void *ns)
+{
+	sysfs_exit_ns(type, ns);
+}
+
+
 EXPORT_SYMBOL(kobject_get);
 EXPORT_SYMBOL(kobject_put);
 EXPORT_SYMBOL(kobject_del);
diff --git a/lib/kobject_uevent.c b/lib/kobject_uevent.c
index 920a3ca6e25..b93579504df 100644
--- a/lib/kobject_uevent.c
+++ b/lib/kobject_uevent.c
@@ -18,18 +18,25 @@
 #include <linux/string.h>
 #include <linux/kobject.h>
 #include <linux/module.h>
-
+#include <linux/slab.h>
+#include <linux/user_namespace.h>
 #include <linux/socket.h>
 #include <linux/skbuff.h>
 #include <linux/netlink.h>
 #include <net/sock.h>
+#include <net/net_namespace.h>
 
 
 u64 uevent_seqnum;
 char uevent_helper[UEVENT_HELPER_PATH_LEN] = CONFIG_UEVENT_HELPER_PATH;
 static DEFINE_SPINLOCK(sequence_lock);
-#if defined(CONFIG_NET)
-static struct sock *uevent_sock;
+#ifdef CONFIG_NET
+struct uevent_sock {
+	struct list_head list;
+	struct sock *sk;
+};
+static LIST_HEAD(uevent_sock_list);
+static DEFINE_MUTEX(uevent_sock_mutex);
 #endif
 
 /* the strings here must match the enum in include/linux/kobject.h */
@@ -76,6 +83,39 @@ out:
 	return ret;
 }
 
+#ifdef CONFIG_NET
+static int kobj_bcast_filter(struct sock *dsk, struct sk_buff *skb, void *data)
+{
+	struct kobject *kobj = data;
+	const struct kobj_ns_type_operations *ops;
+
+	ops = kobj_ns_ops(kobj);
+	if (ops) {
+		const void *sock_ns, *ns;
+		ns = kobj->ktype->namespace(kobj);
+		sock_ns = ops->netlink_ns(dsk);
+		return sock_ns != ns;
+	}
+
+	return 0;
+}
+#endif
+
+static int kobj_usermode_filter(struct kobject *kobj)
+{
+	const struct kobj_ns_type_operations *ops;
+
+	ops = kobj_ns_ops(kobj);
+	if (ops) {
+		const void *init_ns, *ns;
+		ns = kobj->ktype->namespace(kobj);
+		init_ns = ops->initial_ns();
+		return ns != init_ns;
+	}
+
+	return 0;
+}
+
 /**
  * kobject_uevent_env - send an uevent with environmental data
  *
@@ -95,10 +135,13 @@ int kobject_uevent_env(struct kobject *kobj, enum kobject_action action,
 	const char *subsystem;
 	struct kobject *top_kobj;
 	struct kset *kset;
-	struct kset_uevent_ops *uevent_ops;
+	const struct kset_uevent_ops *uevent_ops;
 	u64 seq;
 	int i = 0;
 	int retval = 0;
+#ifdef CONFIG_NET
+	struct uevent_sock *ue_sk;
+#endif
 
 	pr_debug("kobject: '%s' (%p): %s\n",
 		 kobject_name(kobj), kobj, __func__);
@@ -210,7 +253,9 @@ int kobject_uevent_env(struct kobject *kobj, enum kobject_action action,
 
 #if defined(CONFIG_NET)
 	/* send netlink message */
-	if (uevent_sock) {
+	mutex_lock(&uevent_sock_mutex);
+	list_for_each_entry(ue_sk, &uevent_sock_list, list) {
+		struct sock *uevent_sock = ue_sk->sk;
 		struct sk_buff *skb;
 		size_t len;
 
@@ -232,18 +277,21 @@ int kobject_uevent_env(struct kobject *kobj, enum kobject_action action,
 			}
 
 			NETLINK_CB(skb).dst_group = 1;
-			retval = netlink_broadcast(uevent_sock, skb, 0, 1,
-						   GFP_KERNEL);
+			retval = netlink_broadcast_filtered(uevent_sock, skb,
+							    0, 1, GFP_KERNEL,
+							    kobj_bcast_filter,
+							    kobj);
 			/* ENOBUFS should be handled in userspace */
 			if (retval == -ENOBUFS)
 				retval = 0;
 		} else
 			retval = -ENOMEM;
 	}
+	mutex_unlock(&uevent_sock_mutex);
 #endif
 
 	/* call uevent_helper, usually only enabled during early boot */
-	if (uevent_helper[0]) {
+	if (uevent_helper[0] && !kobj_usermode_filter(kobj)) {
 		char *argv [3];
 
 		argv [0] = uevent_helper;
@@ -319,18 +367,59 @@ int add_uevent_var(struct kobj_uevent_env *env, const char *format, ...)
 EXPORT_SYMBOL_GPL(add_uevent_var);
 
 #if defined(CONFIG_NET)
-static int __init kobject_uevent_init(void)
+static int uevent_net_init(struct net *net)
 {
-	uevent_sock = netlink_kernel_create(&init_net, NETLINK_KOBJECT_UEVENT,
-					    1, NULL, NULL, THIS_MODULE);
-	if (!uevent_sock) {
+	struct uevent_sock *ue_sk;
+
+	ue_sk = kzalloc(sizeof(*ue_sk), GFP_KERNEL);
+	if (!ue_sk)
+		return -ENOMEM;
+
+	ue_sk->sk = netlink_kernel_create(net, NETLINK_KOBJECT_UEVENT,
+					  1, NULL, NULL, THIS_MODULE);
+	if (!ue_sk->sk) {
 		printk(KERN_ERR
 		       "kobject_uevent: unable to create netlink socket!\n");
+		kfree(ue_sk);
 		return -ENODEV;
 	}
-	netlink_set_nonroot(NETLINK_KOBJECT_UEVENT, NL_NONROOT_RECV);
+	mutex_lock(&uevent_sock_mutex);
+	list_add_tail(&ue_sk->list, &uevent_sock_list);
+	mutex_unlock(&uevent_sock_mutex);
 	return 0;
 }
 
+static void uevent_net_exit(struct net *net)
+{
+	struct uevent_sock *ue_sk;
+
+	mutex_lock(&uevent_sock_mutex);
+	list_for_each_entry(ue_sk, &uevent_sock_list, list) {
+		if (sock_net(ue_sk->sk) == net)
+			goto found;
+	}
+	mutex_unlock(&uevent_sock_mutex);
+	return;
+
+found:
+	list_del(&ue_sk->list);
+	mutex_unlock(&uevent_sock_mutex);
+
+	netlink_kernel_release(ue_sk->sk);
+	kfree(ue_sk);
+}
+
+static struct pernet_operations uevent_net_ops = {
+	.init	= uevent_net_init,
+	.exit	= uevent_net_exit,
+};
+
+static int __init kobject_uevent_init(void)
+{
+	netlink_set_nonroot(NETLINK_KOBJECT_UEVENT, NL_NONROOT_RECV);
+	return register_pernet_subsys(&uevent_net_ops);
+}
+
+
 postcore_initcall(kobject_uevent_init);
 #endif
diff --git a/lib/kref.c b/lib/kref.c
index 9ecd6e86561..d3d227a08a4 100644
--- a/lib/kref.c
+++ b/lib/kref.c
@@ -13,17 +13,7 @@
 
 #include <linux/kref.h>
 #include <linux/module.h>
-
-/**
- * kref_set - initialize object and set refcount to requested number.
- * @kref: object in question.
- * @num: initial reference counter
- */
-void kref_set(struct kref *kref, int num)
-{
-	atomic_set(&kref->refcount, num);
-	smp_mb();
-}
+#include <linux/slab.h>
 
 /**
  * kref_init - initialize object.
@@ -31,7 +21,8 @@ void kref_set(struct kref *kref, int num)
  */
 void kref_init(struct kref *kref)
 {
-	kref_set(kref, 1);
+	atomic_set(&kref->refcount, 1);
+	smp_mb();
 }
 
 /**
@@ -71,7 +62,6 @@ int kref_put(struct kref *kref, void (*release)(struct kref *kref))
 	return 0;
 }
 
-EXPORT_SYMBOL(kref_set);
 EXPORT_SYMBOL(kref_init);
 EXPORT_SYMBOL(kref_get);
 EXPORT_SYMBOL(kref_put);
diff --git a/lib/lcm.c b/lib/lcm.c
new file mode 100644
index 00000000000..157cd88a6ff
--- /dev/null
+++ b/lib/lcm.c
@@ -0,0 +1,15 @@
+#include <linux/kernel.h>
+#include <linux/gcd.h>
+#include <linux/module.h>
+
+/* Lowest common multiple */
+unsigned long lcm(unsigned long a, unsigned long b)
+{
+	if (a && b)
+		return (a * b) / gcd(a, b);
+	else if (b)
+		return b;
+
+	return a;
+}
+EXPORT_SYMBOL_GPL(lcm);
diff --git a/lib/list_sort.c b/lib/list_sort.c
index 19d11e0bb95..4b5cb794c38 100644
--- a/lib/list_sort.c
+++ b/lib/list_sort.c
@@ -4,99 +4,214 @@
 #include <linux/slab.h>
 #include <linux/list.h>
 
+#define MAX_LIST_LENGTH_BITS 20
+
+/*
+ * Returns a list organized in an intermediate format suited
+ * to chaining of merge() calls: null-terminated, no reserved or
+ * sentinel head node, "prev" links not maintained.
+ */
+static struct list_head *merge(void *priv,
+				int (*cmp)(void *priv, struct list_head *a,
+					struct list_head *b),
+				struct list_head *a, struct list_head *b)
+{
+	struct list_head head, *tail = &head;
+
+	while (a && b) {
+		/* if equal, take 'a' -- important for sort stability */
+		if ((*cmp)(priv, a, b) <= 0) {
+			tail->next = a;
+			a = a->next;
+		} else {
+			tail->next = b;
+			b = b->next;
+		}
+		tail = tail->next;
+	}
+	tail->next = a?:b;
+	return head.next;
+}
+
+/*
+ * Combine final list merge with restoration of standard doubly-linked
+ * list structure.  This approach duplicates code from merge(), but
+ * runs faster than the tidier alternatives of either a separate final
+ * prev-link restoration pass, or maintaining the prev links
+ * throughout.
+ */
+static void merge_and_restore_back_links(void *priv,
+				int (*cmp)(void *priv, struct list_head *a,
+					struct list_head *b),
+				struct list_head *head,
+				struct list_head *a, struct list_head *b)
+{
+	struct list_head *tail = head;
+
+	while (a && b) {
+		/* if equal, take 'a' -- important for sort stability */
+		if ((*cmp)(priv, a, b) <= 0) {
+			tail->next = a;
+			a->prev = tail;
+			a = a->next;
+		} else {
+			tail->next = b;
+			b->prev = tail;
+			b = b->next;
+		}
+		tail = tail->next;
+	}
+	tail->next = a ? : b;
+
+	do {
+		/*
+		 * In worst cases this loop may run many iterations.
+		 * Continue callbacks to the client even though no
+		 * element comparison is needed, so the client's cmp()
+		 * routine can invoke cond_resched() periodically.
+		 */
+		(*cmp)(priv, tail, tail);
+
+		tail->next->prev = tail;
+		tail = tail->next;
+	} while (tail->next);
+
+	tail->next = head;
+	head->prev = tail;
+}
+
 /**
- * list_sort - sort a list.
- * @priv: private data, passed to @cmp
+ * list_sort - sort a list
+ * @priv: private data, opaque to list_sort(), passed to @cmp
  * @head: the list to sort
  * @cmp: the elements comparison function
  *
- * This function has been implemented by Mark J Roberts <mjr@znex.org>. It
- * implements "merge sort" which has O(nlog(n)) complexity. The list is sorted
- * in ascending order.
+ * This function implements "merge sort", which has O(nlog(n))
+ * complexity.
  *
- * The comparison function @cmp is supposed to return a negative value if @a is
- * less than @b, and a positive value if @a is greater than @b. If @a and @b
- * are equivalent, then it does not matter what this function returns.
+ * The comparison function @cmp must return a negative value if @a
+ * should sort before @b, and a positive value if @a should sort after
+ * @b. If @a and @b are equivalent, and their original relative
+ * ordering is to be preserved, @cmp must return 0.
  */
 void list_sort(void *priv, struct list_head *head,
-	       int (*cmp)(void *priv, struct list_head *a,
-			  struct list_head *b))
+		int (*cmp)(void *priv, struct list_head *a,
+			struct list_head *b))
 {
-	struct list_head *p, *q, *e, *list, *tail, *oldhead;
-	int insize, nmerges, psize, qsize, i;
+	struct list_head *part[MAX_LIST_LENGTH_BITS+1]; /* sorted partial lists
+						-- last slot is a sentinel */
+	int lev;  /* index into part[] */
+	int max_lev = 0;
+	struct list_head *list;
 
 	if (list_empty(head))
 		return;
 
+	memset(part, 0, sizeof(part));
+
+	head->prev->next = NULL;
 	list = head->next;
-	list_del(head);
-	insize = 1;
-	for (;;) {
-		p = oldhead = list;
-		list = tail = NULL;
-		nmerges = 0;
-
-		while (p) {
-			nmerges++;
-			q = p;
-			psize = 0;
-			for (i = 0; i < insize; i++) {
-				psize++;
-				q = q->next == oldhead ? NULL : q->next;
-				if (!q)
-					break;
-			}
 
-			qsize = insize;
-			while (psize > 0 || (qsize > 0 && q)) {
-				if (!psize) {
-					e = q;
-					q = q->next;
-					qsize--;
-					if (q == oldhead)
-						q = NULL;
-				} else if (!qsize || !q) {
-					e = p;
-					p = p->next;
-					psize--;
-					if (p == oldhead)
-						p = NULL;
-				} else if (cmp(priv, p, q) <= 0) {
-					e = p;
-					p = p->next;
-					psize--;
-					if (p == oldhead)
-						p = NULL;
-				} else {
-					e = q;
-					q = q->next;
-					qsize--;
-					if (q == oldhead)
-						q = NULL;
-				}
-				if (tail)
-					tail->next = e;
-				else
-					list = e;
-				e->prev = tail;
-				tail = e;
+	while (list) {
+		struct list_head *cur = list;
+		list = list->next;
+		cur->next = NULL;
+
+		for (lev = 0; part[lev]; lev++) {
+			cur = merge(priv, cmp, part[lev], cur);
+			part[lev] = NULL;
+		}
+		if (lev > max_lev) {
+			if (unlikely(lev >= ARRAY_SIZE(part)-1)) {
+				printk_once(KERN_DEBUG "list passed to"
+					" list_sort() too long for"
+					" efficiency\n");
+				lev--;
 			}
-			p = q;
+			max_lev = lev;
 		}
+		part[lev] = cur;
+	}
 
-		tail->next = list;
-		list->prev = tail;
+	for (lev = 0; lev < max_lev; lev++)
+		if (part[lev])
+			list = merge(priv, cmp, part[lev], list);
 
-		if (nmerges <= 1)
-			break;
+	merge_and_restore_back_links(priv, cmp, head, part[max_lev], list);
+}
+EXPORT_SYMBOL(list_sort);
 
-		insize *= 2;
-	}
+#ifdef DEBUG_LIST_SORT
+struct debug_el {
+	struct list_head l_h;
+	int value;
+	unsigned serial;
+};
 
-	head->next = list;
-	head->prev = list->prev;
-	list->prev->next = head;
-	list->prev = head;
+static int cmp(void *priv, struct list_head *a, struct list_head *b)
+{
+	return container_of(a, struct debug_el, l_h)->value
+	     - container_of(b, struct debug_el, l_h)->value;
 }
 
-EXPORT_SYMBOL(list_sort);
+/*
+ * The pattern of set bits in the list length determines which cases
+ * are hit in list_sort().
+ */
+#define LIST_SORT_TEST_LENGTH (512+128+2) /* not including head */
+
+static int __init list_sort_test(void)
+{
+	int i, r = 1, count;
+	struct list_head *head = kmalloc(sizeof(*head), GFP_KERNEL);
+	struct list_head *cur;
+
+	printk(KERN_WARNING "testing list_sort()\n");
+
+	cur = head;
+	for (i = 0; i < LIST_SORT_TEST_LENGTH; i++) {
+		struct debug_el *el = kmalloc(sizeof(*el), GFP_KERNEL);
+		BUG_ON(!el);
+		 /* force some equivalencies */
+		el->value = (r = (r * 725861) % 6599) % (LIST_SORT_TEST_LENGTH/3);
+		el->serial = i;
+
+		el->l_h.prev = cur;
+		cur->next = &el->l_h;
+		cur = cur->next;
+	}
+	head->prev = cur;
+
+	list_sort(NULL, head, cmp);
+
+	count = 1;
+	for (cur = head->next; cur->next != head; cur = cur->next) {
+		struct debug_el *el = container_of(cur, struct debug_el, l_h);
+		int cmp_result = cmp(NULL, cur, cur->next);
+		if (cur->next->prev != cur) {
+			printk(KERN_EMERG "list_sort() returned "
+						"a corrupted list!\n");
+			return 1;
+		} else if (cmp_result > 0) {
+			printk(KERN_EMERG "list_sort() failed to sort!\n");
+			return 1;
+		} else if (cmp_result == 0 &&
+				el->serial >= container_of(cur->next,
+					struct debug_el, l_h)->serial) {
+			printk(KERN_EMERG "list_sort() failed to preserve order"
+						 " of equivalent elements!\n");
+			return 1;
+		}
+		kfree(cur->prev);
+		count++;
+	}
+	kfree(cur);
+	if (count != LIST_SORT_TEST_LENGTH) {
+		printk(KERN_EMERG "list_sort() returned list of"
+						"different length!\n");
+		return 1;
+	}
+	return 0;
+}
+module_init(list_sort_test);
+#endif
diff --git a/lib/lmb.c b/lib/lmb.c
deleted file mode 100644
index 9cee17142b2..00000000000
--- a/lib/lmb.c
+++ /dev/null
@@ -1,532 +0,0 @@
-/*
- * Procedures for maintaining information about logical memory blocks.
- *
- * Peter Bergner, IBM Corp.	June 2001.
- * Copyright (C) 2001 Peter Bergner.
- *
- *      This program is free software; you can redistribute it and/or
- *      modify it under the terms of the GNU General Public License
- *      as published by the Free Software Foundation; either version
- *      2 of the License, or (at your option) any later version.
- */
-
-#include <linux/kernel.h>
-#include <linux/init.h>
-#include <linux/bitops.h>
-#include <linux/lmb.h>
-
-#define LMB_ALLOC_ANYWHERE	0
-
-struct lmb lmb;
-
-static int lmb_debug;
-
-static int __init early_lmb(char *p)
-{
-	if (p && strstr(p, "debug"))
-		lmb_debug = 1;
-	return 0;
-}
-early_param("lmb", early_lmb);
-
-static void lmb_dump(struct lmb_region *region, char *name)
-{
-	unsigned long long base, size;
-	int i;
-
-	pr_info(" %s.cnt  = 0x%lx\n", name, region->cnt);
-
-	for (i = 0; i < region->cnt; i++) {
-		base = region->region[i].base;
-		size = region->region[i].size;
-
-		pr_info(" %s[0x%x]\t0x%016llx - 0x%016llx, 0x%llx bytes\n",
-		    name, i, base, base + size - 1, size);
-	}
-}
-
-void lmb_dump_all(void)
-{
-	if (!lmb_debug)
-		return;
-
-	pr_info("LMB configuration:\n");
-	pr_info(" rmo_size    = 0x%llx\n", (unsigned long long)lmb.rmo_size);
-	pr_info(" memory.size = 0x%llx\n", (unsigned long long)lmb.memory.size);
-
-	lmb_dump(&lmb.memory, "memory");
-	lmb_dump(&lmb.reserved, "reserved");
-}
-
-static unsigned long lmb_addrs_overlap(u64 base1, u64 size1, u64 base2,
-					u64 size2)
-{
-	return ((base1 < (base2 + size2)) && (base2 < (base1 + size1)));
-}
-
-static long lmb_addrs_adjacent(u64 base1, u64 size1, u64 base2, u64 size2)
-{
-	if (base2 == base1 + size1)
-		return 1;
-	else if (base1 == base2 + size2)
-		return -1;
-
-	return 0;
-}
-
-static long lmb_regions_adjacent(struct lmb_region *rgn,
-		unsigned long r1, unsigned long r2)
-{
-	u64 base1 = rgn->region[r1].base;
-	u64 size1 = rgn->region[r1].size;
-	u64 base2 = rgn->region[r2].base;
-	u64 size2 = rgn->region[r2].size;
-
-	return lmb_addrs_adjacent(base1, size1, base2, size2);
-}
-
-static void lmb_remove_region(struct lmb_region *rgn, unsigned long r)
-{
-	unsigned long i;
-
-	for (i = r; i < rgn->cnt - 1; i++) {
-		rgn->region[i].base = rgn->region[i + 1].base;
-		rgn->region[i].size = rgn->region[i + 1].size;
-	}
-	rgn->cnt--;
-}
-
-/* Assumption: base addr of region 1 < base addr of region 2 */
-static void lmb_coalesce_regions(struct lmb_region *rgn,
-		unsigned long r1, unsigned long r2)
-{
-	rgn->region[r1].size += rgn->region[r2].size;
-	lmb_remove_region(rgn, r2);
-}
-
-void __init lmb_init(void)
-{
-	/* Create a dummy zero size LMB which will get coalesced away later.
-	 * This simplifies the lmb_add() code below...
-	 */
-	lmb.memory.region[0].base = 0;
-	lmb.memory.region[0].size = 0;
-	lmb.memory.cnt = 1;
-
-	/* Ditto. */
-	lmb.reserved.region[0].base = 0;
-	lmb.reserved.region[0].size = 0;
-	lmb.reserved.cnt = 1;
-}
-
-void __init lmb_analyze(void)
-{
-	int i;
-
-	lmb.memory.size = 0;
-
-	for (i = 0; i < lmb.memory.cnt; i++)
-		lmb.memory.size += lmb.memory.region[i].size;
-}
-
-static long lmb_add_region(struct lmb_region *rgn, u64 base, u64 size)
-{
-	unsigned long coalesced = 0;
-	long adjacent, i;
-
-	if ((rgn->cnt == 1) && (rgn->region[0].size == 0)) {
-		rgn->region[0].base = base;
-		rgn->region[0].size = size;
-		return 0;
-	}
-
-	/* First try and coalesce this LMB with another. */
-	for (i = 0; i < rgn->cnt; i++) {
-		u64 rgnbase = rgn->region[i].base;
-		u64 rgnsize = rgn->region[i].size;
-
-		if ((rgnbase == base) && (rgnsize == size))
-			/* Already have this region, so we're done */
-			return 0;
-
-		adjacent = lmb_addrs_adjacent(base, size, rgnbase, rgnsize);
-		if (adjacent > 0) {
-			rgn->region[i].base -= size;
-			rgn->region[i].size += size;
-			coalesced++;
-			break;
-		} else if (adjacent < 0) {
-			rgn->region[i].size += size;
-			coalesced++;
-			break;
-		}
-	}
-
-	if ((i < rgn->cnt - 1) && lmb_regions_adjacent(rgn, i, i+1)) {
-		lmb_coalesce_regions(rgn, i, i+1);
-		coalesced++;
-	}
-
-	if (coalesced)
-		return coalesced;
-	if (rgn->cnt >= MAX_LMB_REGIONS)
-		return -1;
-
-	/* Couldn't coalesce the LMB, so add it to the sorted table. */
-	for (i = rgn->cnt - 1; i >= 0; i--) {
-		if (base < rgn->region[i].base) {
-			rgn->region[i+1].base = rgn->region[i].base;
-			rgn->region[i+1].size = rgn->region[i].size;
-		} else {
-			rgn->region[i+1].base = base;
-			rgn->region[i+1].size = size;
-			break;
-		}
-	}
-
-	if (base < rgn->region[0].base) {
-		rgn->region[0].base = base;
-		rgn->region[0].size = size;
-	}
-	rgn->cnt++;
-
-	return 0;
-}
-
-long lmb_add(u64 base, u64 size)
-{
-	struct lmb_region *_rgn = &lmb.memory;
-
-	/* On pSeries LPAR systems, the first LMB is our RMO region. */
-	if (base == 0)
-		lmb.rmo_size = size;
-
-	return lmb_add_region(_rgn, base, size);
-
-}
-
-long lmb_remove(u64 base, u64 size)
-{
-	struct lmb_region *rgn = &(lmb.memory);
-	u64 rgnbegin, rgnend;
-	u64 end = base + size;
-	int i;
-
-	rgnbegin = rgnend = 0; /* supress gcc warnings */
-
-	/* Find the region where (base, size) belongs to */
-	for (i=0; i < rgn->cnt; i++) {
-		rgnbegin = rgn->region[i].base;
-		rgnend = rgnbegin + rgn->region[i].size;
-
-		if ((rgnbegin <= base) && (end <= rgnend))
-			break;
-	}
-
-	/* Didn't find the region */
-	if (i == rgn->cnt)
-		return -1;
-
-	/* Check to see if we are removing entire region */
-	if ((rgnbegin == base) && (rgnend == end)) {
-		lmb_remove_region(rgn, i);
-		return 0;
-	}
-
-	/* Check to see if region is matching at the front */
-	if (rgnbegin == base) {
-		rgn->region[i].base = end;
-		rgn->region[i].size -= size;
-		return 0;
-	}
-
-	/* Check to see if the region is matching at the end */
-	if (rgnend == end) {
-		rgn->region[i].size -= size;
-		return 0;
-	}
-
-	/*
-	 * We need to split the entry -  adjust the current one to the
-	 * beginging of the hole and add the region after hole.
-	 */
-	rgn->region[i].size = base - rgn->region[i].base;
-	return lmb_add_region(rgn, end, rgnend - end);
-}
-
-long __init lmb_reserve(u64 base, u64 size)
-{
-	struct lmb_region *_rgn = &lmb.reserved;
-
-	BUG_ON(0 == size);
-
-	return lmb_add_region(_rgn, base, size);
-}
-
-long lmb_overlaps_region(struct lmb_region *rgn, u64 base, u64 size)
-{
-	unsigned long i;
-
-	for (i = 0; i < rgn->cnt; i++) {
-		u64 rgnbase = rgn->region[i].base;
-		u64 rgnsize = rgn->region[i].size;
-		if (lmb_addrs_overlap(base, size, rgnbase, rgnsize))
-			break;
-	}
-
-	return (i < rgn->cnt) ? i : -1;
-}
-
-static u64 lmb_align_down(u64 addr, u64 size)
-{
-	return addr & ~(size - 1);
-}
-
-static u64 lmb_align_up(u64 addr, u64 size)
-{
-	return (addr + (size - 1)) & ~(size - 1);
-}
-
-static u64 __init lmb_alloc_nid_unreserved(u64 start, u64 end,
-					   u64 size, u64 align)
-{
-	u64 base, res_base;
-	long j;
-
-	base = lmb_align_down((end - size), align);
-	while (start <= base) {
-		j = lmb_overlaps_region(&lmb.reserved, base, size);
-		if (j < 0) {
-			/* this area isn't reserved, take it */
-			if (lmb_add_region(&lmb.reserved, base, size) < 0)
-				base = ~(u64)0;
-			return base;
-		}
-		res_base = lmb.reserved.region[j].base;
-		if (res_base < size)
-			break;
-		base = lmb_align_down(res_base - size, align);
-	}
-
-	return ~(u64)0;
-}
-
-static u64 __init lmb_alloc_nid_region(struct lmb_property *mp,
-				       u64 (*nid_range)(u64, u64, int *),
-				       u64 size, u64 align, int nid)
-{
-	u64 start, end;
-
-	start = mp->base;
-	end = start + mp->size;
-
-	start = lmb_align_up(start, align);
-	while (start < end) {
-		u64 this_end;
-		int this_nid;
-
-		this_end = nid_range(start, end, &this_nid);
-		if (this_nid == nid) {
-			u64 ret = lmb_alloc_nid_unreserved(start, this_end,
-							   size, align);
-			if (ret != ~(u64)0)
-				return ret;
-		}
-		start = this_end;
-	}
-
-	return ~(u64)0;
-}
-
-u64 __init lmb_alloc_nid(u64 size, u64 align, int nid,
-			 u64 (*nid_range)(u64 start, u64 end, int *nid))
-{
-	struct lmb_region *mem = &lmb.memory;
-	int i;
-
-	BUG_ON(0 == size);
-
-	size = lmb_align_up(size, align);
-
-	for (i = 0; i < mem->cnt; i++) {
-		u64 ret = lmb_alloc_nid_region(&mem->region[i],
-					       nid_range,
-					       size, align, nid);
-		if (ret != ~(u64)0)
-			return ret;
-	}
-
-	return lmb_alloc(size, align);
-}
-
-u64 __init lmb_alloc(u64 size, u64 align)
-{
-	return lmb_alloc_base(size, align, LMB_ALLOC_ANYWHERE);
-}
-
-u64 __init lmb_alloc_base(u64 size, u64 align, u64 max_addr)
-{
-	u64 alloc;
-
-	alloc = __lmb_alloc_base(size, align, max_addr);
-
-	if (alloc == 0)
-		panic("ERROR: Failed to allocate 0x%llx bytes below 0x%llx.\n",
-		      (unsigned long long) size, (unsigned long long) max_addr);
-
-	return alloc;
-}
-
-u64 __init __lmb_alloc_base(u64 size, u64 align, u64 max_addr)
-{
-	long i, j;
-	u64 base = 0;
-	u64 res_base;
-
-	BUG_ON(0 == size);
-
-	size = lmb_align_up(size, align);
-
-	/* On some platforms, make sure we allocate lowmem */
-	/* Note that LMB_REAL_LIMIT may be LMB_ALLOC_ANYWHERE */
-	if (max_addr == LMB_ALLOC_ANYWHERE)
-		max_addr = LMB_REAL_LIMIT;
-
-	for (i = lmb.memory.cnt - 1; i >= 0; i--) {
-		u64 lmbbase = lmb.memory.region[i].base;
-		u64 lmbsize = lmb.memory.region[i].size;
-
-		if (lmbsize < size)
-			continue;
-		if (max_addr == LMB_ALLOC_ANYWHERE)
-			base = lmb_align_down(lmbbase + lmbsize - size, align);
-		else if (lmbbase < max_addr) {
-			base = min(lmbbase + lmbsize, max_addr);
-			base = lmb_align_down(base - size, align);
-		} else
-			continue;
-
-		while (base && lmbbase <= base) {
-			j = lmb_overlaps_region(&lmb.reserved, base, size);
-			if (j < 0) {
-				/* this area isn't reserved, take it */
-				if (lmb_add_region(&lmb.reserved, base, size) < 0)
-					return 0;
-				return base;
-			}
-			res_base = lmb.reserved.region[j].base;
-			if (res_base < size)
-				break;
-			base = lmb_align_down(res_base - size, align);
-		}
-	}
-	return 0;
-}
-
-/* You must call lmb_analyze() before this. */
-u64 __init lmb_phys_mem_size(void)
-{
-	return lmb.memory.size;
-}
-
-u64 lmb_end_of_DRAM(void)
-{
-	int idx = lmb.memory.cnt - 1;
-
-	return (lmb.memory.region[idx].base + lmb.memory.region[idx].size);
-}
-
-/* You must call lmb_analyze() after this. */
-void __init lmb_enforce_memory_limit(u64 memory_limit)
-{
-	unsigned long i;
-	u64 limit;
-	struct lmb_property *p;
-
-	if (!memory_limit)
-		return;
-
-	/* Truncate the lmb regions to satisfy the memory limit. */
-	limit = memory_limit;
-	for (i = 0; i < lmb.memory.cnt; i++) {
-		if (limit > lmb.memory.region[i].size) {
-			limit -= lmb.memory.region[i].size;
-			continue;
-		}
-
-		lmb.memory.region[i].size = limit;
-		lmb.memory.cnt = i + 1;
-		break;
-	}
-
-	if (lmb.memory.region[0].size < lmb.rmo_size)
-		lmb.rmo_size = lmb.memory.region[0].size;
-
-	memory_limit = lmb_end_of_DRAM();
-
-	/* And truncate any reserves above the limit also. */
-	for (i = 0; i < lmb.reserved.cnt; i++) {
-		p = &lmb.reserved.region[i];
-
-		if (p->base > memory_limit)
-			p->size = 0;
-		else if ((p->base + p->size) > memory_limit)
-			p->size = memory_limit - p->base;
-
-		if (p->size == 0) {
-			lmb_remove_region(&lmb.reserved, i);
-			i--;
-		}
-	}
-}
-
-int __init lmb_is_reserved(u64 addr)
-{
-	int i;
-
-	for (i = 0; i < lmb.reserved.cnt; i++) {
-		u64 upper = lmb.reserved.region[i].base +
-			lmb.reserved.region[i].size - 1;
-		if ((addr >= lmb.reserved.region[i].base) && (addr <= upper))
-			return 1;
-	}
-	return 0;
-}
-
-int lmb_is_region_reserved(u64 base, u64 size)
-{
-	return lmb_overlaps_region(&lmb.reserved, base, size);
-}
-
-/*
- * Given a <base, len>, find which memory regions belong to this range.
- * Adjust the request and return a contiguous chunk.
- */
-int lmb_find(struct lmb_property *res)
-{
-	int i;
-	u64 rstart, rend;
-
-	rstart = res->base;
-	rend = rstart + res->size - 1;
-
-	for (i = 0; i < lmb.memory.cnt; i++) {
-		u64 start = lmb.memory.region[i].base;
-		u64 end = start + lmb.memory.region[i].size - 1;
-
-		if (start > rend)
-			return -1;
-
-		if ((end >= rstart) && (start < rend)) {
-			/* adjust the request */
-			if (rstart < start)
-				rstart = start;
-			if (rend > end)
-				rend = end;
-			res->base = rstart;
-			res->size = rend - rstart + 1;
-			return 0;
-		}
-	}
-	return -1;
-}
diff --git a/lib/radix-tree.c b/lib/radix-tree.c
index 92cdd9936e3..05da38bcc29 100644
--- a/lib/radix-tree.c
+++ b/lib/radix-tree.c
@@ -28,7 +28,6 @@
 #include <linux/slab.h>
 #include <linux/notifier.h>
 #include <linux/cpu.h>
-#include <linux/gfp.h>
 #include <linux/string.h>
 #include <linux/bitops.h>
 #include <linux/rcupdate.h>
@@ -364,7 +363,7 @@ static void *radix_tree_lookup_element(struct radix_tree_root *root,
 	unsigned int height, shift;
 	struct radix_tree_node *node, **slot;
 
-	node = rcu_dereference(root->rnode);
+	node = rcu_dereference_raw(root->rnode);
 	if (node == NULL)
 		return NULL;
 
@@ -384,7 +383,7 @@ static void *radix_tree_lookup_element(struct radix_tree_root *root,
 	do {
 		slot = (struct radix_tree_node **)
 			(node->slots + ((index>>shift) & RADIX_TREE_MAP_MASK));
-		node = rcu_dereference(*slot);
+		node = rcu_dereference_raw(*slot);
 		if (node == NULL)
 			return NULL;
 
@@ -556,6 +555,10 @@ EXPORT_SYMBOL(radix_tree_tag_clear);
  *
  *  0: tag not present or not set
  *  1: tag set
+ *
+ * Note that the return value of this function may not be relied on, even if
+ * the RCU lock is held, unless tag modification and node deletion are excluded
+ * from concurrency.
  */
 int radix_tree_tag_get(struct radix_tree_root *root,
 			unsigned long index, unsigned int tag)
@@ -568,7 +571,7 @@ int radix_tree_tag_get(struct radix_tree_root *root,
 	if (!root_tag_get(root, tag))
 		return 0;
 
-	node = rcu_dereference(root->rnode);
+	node = rcu_dereference_raw(root->rnode);
 	if (node == NULL)
 		return 0;
 
@@ -596,13 +599,9 @@ int radix_tree_tag_get(struct radix_tree_root *root,
 		 */
 		if (!tag_get(node, tag, offset))
 			saw_unset_tag = 1;
-		if (height == 1) {
-			int ret = tag_get(node, tag, offset);
-
-			BUG_ON(ret && saw_unset_tag);
-			return !!ret;
-		}
-		node = rcu_dereference(node->slots[offset]);
+		if (height == 1)
+			return !!tag_get(node, tag, offset);
+		node = rcu_dereference_raw(node->slots[offset]);
 		shift -= RADIX_TREE_MAP_SHIFT;
 		height--;
 	}
@@ -657,7 +656,7 @@ EXPORT_SYMBOL(radix_tree_next_hole);
  *
  *	Returns: the index of the hole if found, otherwise returns an index
  *	outside of the set specified (in which case 'index - return >= max_scan'
- *	will be true). In rare cases of wrap-around, LONG_MAX will be returned.
+ *	will be true). In rare cases of wrap-around, ULONG_MAX will be returned.
  *
  *	radix_tree_next_hole may be called under rcu_read_lock. However, like
  *	radix_tree_gang_lookup, this will not atomically search a snapshot of
@@ -675,7 +674,7 @@ unsigned long radix_tree_prev_hole(struct radix_tree_root *root,
 		if (!radix_tree_lookup(root, index))
 			break;
 		index--;
-		if (index == LONG_MAX)
+		if (index == ULONG_MAX)
 			break;
 	}
 
@@ -711,7 +710,7 @@ __lookup(struct radix_tree_node *slot, void ***results, unsigned long index,
 		}
 
 		shift -= RADIX_TREE_MAP_SHIFT;
-		slot = rcu_dereference(slot->slots[i]);
+		slot = rcu_dereference_raw(slot->slots[i]);
 		if (slot == NULL)
 			goto out;
 	}
@@ -758,7 +757,7 @@ radix_tree_gang_lookup(struct radix_tree_root *root, void **results,
 	unsigned long cur_index = first_index;
 	unsigned int ret;
 
-	node = rcu_dereference(root->rnode);
+	node = rcu_dereference_raw(root->rnode);
 	if (!node)
 		return 0;
 
@@ -787,7 +786,7 @@ radix_tree_gang_lookup(struct radix_tree_root *root, void **results,
 			slot = *(((void ***)results)[ret + i]);
 			if (!slot)
 				continue;
-			results[ret + nr_found] = rcu_dereference(slot);
+			results[ret + nr_found] = rcu_dereference_raw(slot);
 			nr_found++;
 		}
 		ret += nr_found;
@@ -826,7 +825,7 @@ radix_tree_gang_lookup_slot(struct radix_tree_root *root, void ***results,
 	unsigned long cur_index = first_index;
 	unsigned int ret;
 
-	node = rcu_dereference(root->rnode);
+	node = rcu_dereference_raw(root->rnode);
 	if (!node)
 		return 0;
 
@@ -915,7 +914,7 @@ __lookup_tag(struct radix_tree_node *slot, void ***results, unsigned long index,
 			}
 		}
 		shift -= RADIX_TREE_MAP_SHIFT;
-		slot = rcu_dereference(slot->slots[i]);
+		slot = rcu_dereference_raw(slot->slots[i]);
 		if (slot == NULL)
 			break;
 	}
@@ -951,7 +950,7 @@ radix_tree_gang_lookup_tag(struct radix_tree_root *root, void **results,
 	if (!root_tag_get(root, tag))
 		return 0;
 
-	node = rcu_dereference(root->rnode);
+	node = rcu_dereference_raw(root->rnode);
 	if (!node)
 		return 0;
 
@@ -980,7 +979,7 @@ radix_tree_gang_lookup_tag(struct radix_tree_root *root, void **results,
 			slot = *(((void ***)results)[ret + i]);
 			if (!slot)
 				continue;
-			results[ret + nr_found] = rcu_dereference(slot);
+			results[ret + nr_found] = rcu_dereference_raw(slot);
 			nr_found++;
 		}
 		ret += nr_found;
@@ -1020,7 +1019,7 @@ radix_tree_gang_lookup_tag_slot(struct radix_tree_root *root, void ***results,
 	if (!root_tag_get(root, tag))
 		return 0;
 
-	node = rcu_dereference(root->rnode);
+	node = rcu_dereference_raw(root->rnode);
 	if (!node)
 		return 0;
 
diff --git a/lib/random32.c b/lib/random32.c
index 217d5c4b666..870dc3fc0f0 100644
--- a/lib/random32.c
+++ b/lib/random32.c
@@ -39,13 +39,16 @@
 #include <linux/jiffies.h>
 #include <linux/random.h>
 
-struct rnd_state {
-	u32 s1, s2, s3;
-};
-
 static DEFINE_PER_CPU(struct rnd_state, net_rand_state);
 
-static u32 __random32(struct rnd_state *state)
+/**
+ *	prandom32 - seeded pseudo-random number generator.
+ *	@state: pointer to state structure holding seeded state.
+ *
+ *	This is used for pseudo-randomness with no outside seeding.
+ *	For more random results, use random32().
+ */
+u32 prandom32(struct rnd_state *state)
 {
 #define TAUSWORTHE(s,a,b,c,d) ((s&c)<<d) ^ (((s <<a) ^ s)>>b)
 
@@ -55,14 +58,7 @@ static u32 __random32(struct rnd_state *state)
 
 	return (state->s1 ^ state->s2 ^ state->s3);
 }
-
-/*
- * Handle minimum values for seeds
- */
-static inline u32 __seed(u32 x, u32 m)
-{
-	return (x < m) ? x + m : x;
-}
+EXPORT_SYMBOL(prandom32);
 
 /**
  *	random32 - pseudo random number generator
@@ -75,7 +71,7 @@ u32 random32(void)
 {
 	unsigned long r;
 	struct rnd_state *state = &get_cpu_var(net_rand_state);
-	r = __random32(state);
+	r = prandom32(state);
 	put_cpu_var(state);
 	return r;
 }
@@ -118,12 +114,12 @@ static int __init random32_init(void)
 		state->s3 = __seed(LCG(state->s2), 15);
 
 		/* "warm it up" */
-		__random32(state);
-		__random32(state);
-		__random32(state);
-		__random32(state);
-		__random32(state);
-		__random32(state);
+		prandom32(state);
+		prandom32(state);
+		prandom32(state);
+		prandom32(state);
+		prandom32(state);
+		prandom32(state);
 	}
 	return 0;
 }
@@ -147,7 +143,7 @@ static int __init random32_reseed(void)
 		state->s3 = __seed(seeds[2], 15);
 
 		/* mix it in */
-		__random32(state);
+		prandom32(state);
 	}
 	return 0;
 }
diff --git a/lib/ratelimit.c b/lib/ratelimit.c
index 09f5ce1810d..027a03f4c56 100644
--- a/lib/ratelimit.c
+++ b/lib/ratelimit.c
@@ -16,9 +16,14 @@
 /*
  * __ratelimit - rate limiting
  * @rs: ratelimit_state data
+ * @func: name of calling function
  *
- * This enforces a rate limit: not more than @rs->ratelimit_burst callbacks
- * in every @rs->ratelimit_jiffies
+ * This enforces a rate limit: not more than @rs->burst callbacks
+ * in every @rs->interval
+ *
+ * RETURNS:
+ * 0 means callbacks will be suppressed.
+ * 1 means go ahead and do it.
  */
 int ___ratelimit(struct ratelimit_state *rs, const char *func)
 {
@@ -35,7 +40,7 @@ int ___ratelimit(struct ratelimit_state *rs, const char *func)
 	 * the entity that is holding the lock already:
 	 */
 	if (!spin_trylock_irqsave(&rs->lock, flags))
-		return 1;
+		return 0;
 
 	if (!rs->begin)
 		rs->begin = jiffies;
diff --git a/lib/rbtree.c b/lib/rbtree.c
index e2aa3be2985..4693f79195d 100644
--- a/lib/rbtree.c
+++ b/lib/rbtree.c
@@ -283,6 +283,74 @@ void rb_erase(struct rb_node *node, struct rb_root *root)
 }
 EXPORT_SYMBOL(rb_erase);
 
+static void rb_augment_path(struct rb_node *node, rb_augment_f func, void *data)
+{
+	struct rb_node *parent;
+
+up:
+	func(node, data);
+	parent = rb_parent(node);
+	if (!parent)
+		return;
+
+	if (node == parent->rb_left && parent->rb_right)
+		func(parent->rb_right, data);
+	else if (parent->rb_left)
+		func(parent->rb_left, data);
+
+	node = parent;
+	goto up;
+}
+
+/*
+ * after inserting @node into the tree, update the tree to account for
+ * both the new entry and any damage done by rebalance
+ */
+void rb_augment_insert(struct rb_node *node, rb_augment_f func, void *data)
+{
+	if (node->rb_left)
+		node = node->rb_left;
+	else if (node->rb_right)
+		node = node->rb_right;
+
+	rb_augment_path(node, func, data);
+}
+
+/*
+ * before removing the node, find the deepest node on the rebalance path
+ * that will still be there after @node gets removed
+ */
+struct rb_node *rb_augment_erase_begin(struct rb_node *node)
+{
+	struct rb_node *deepest;
+
+	if (!node->rb_right && !node->rb_left)
+		deepest = rb_parent(node);
+	else if (!node->rb_right)
+		deepest = node->rb_left;
+	else if (!node->rb_left)
+		deepest = node->rb_right;
+	else {
+		deepest = rb_next(node);
+		if (deepest->rb_right)
+			deepest = deepest->rb_right;
+		else if (rb_parent(deepest) != node)
+			deepest = rb_parent(deepest);
+	}
+
+	return deepest;
+}
+
+/*
+ * after removal, update the tree to account for the removed entry
+ * and any rebalance damage.
+ */
+void rb_augment_erase_end(struct rb_node *node, rb_augment_f func, void *data)
+{
+	if (node)
+		rb_augment_path(node, func, data);
+}
+
 /*
  * This function returns the first node (in sort order) of the tree.
  */
diff --git a/lib/rwsem-spinlock.c b/lib/rwsem-spinlock.c
index ccf95bff798..ffc9fc7f3b0 100644
--- a/lib/rwsem-spinlock.c
+++ b/lib/rwsem-spinlock.c
@@ -143,13 +143,14 @@ void __sched __down_read(struct rw_semaphore *sem)
 {
 	struct rwsem_waiter waiter;
 	struct task_struct *tsk;
+	unsigned long flags;
 
-	spin_lock_irq(&sem->wait_lock);
+	spin_lock_irqsave(&sem->wait_lock, flags);
 
 	if (sem->activity >= 0 && list_empty(&sem->wait_list)) {
 		/* granted */
 		sem->activity++;
-		spin_unlock_irq(&sem->wait_lock);
+		spin_unlock_irqrestore(&sem->wait_lock, flags);
 		goto out;
 	}
 
@@ -164,7 +165,7 @@ void __sched __down_read(struct rw_semaphore *sem)
 	list_add_tail(&waiter.list, &sem->wait_list);
 
 	/* we don't need to touch the semaphore struct anymore */
-	spin_unlock_irq(&sem->wait_lock);
+	spin_unlock_irqrestore(&sem->wait_lock, flags);
 
 	/* wait to be given the lock */
 	for (;;) {
@@ -209,13 +210,14 @@ void __sched __down_write_nested(struct rw_semaphore *sem, int subclass)
 {
 	struct rwsem_waiter waiter;
 	struct task_struct *tsk;
+	unsigned long flags;
 
-	spin_lock_irq(&sem->wait_lock);
+	spin_lock_irqsave(&sem->wait_lock, flags);
 
 	if (sem->activity == 0 && list_empty(&sem->wait_list)) {
 		/* granted */
 		sem->activity = -1;
-		spin_unlock_irq(&sem->wait_lock);
+		spin_unlock_irqrestore(&sem->wait_lock, flags);
 		goto out;
 	}
 
@@ -230,7 +232,7 @@ void __sched __down_write_nested(struct rw_semaphore *sem, int subclass)
 	list_add_tail(&waiter.list, &sem->wait_list);
 
 	/* we don't need to touch the semaphore struct anymore */
-	spin_unlock_irq(&sem->wait_lock);
+	spin_unlock_irqrestore(&sem->wait_lock, flags);
 
 	/* wait to be given the lock */
 	for (;;) {
diff --git a/lib/rwsem.c b/lib/rwsem.c
index 3e3365e5665..ceba8e28807 100644
--- a/lib/rwsem.c
+++ b/lib/rwsem.c
@@ -136,9 +136,10 @@ __rwsem_do_wake(struct rw_semaphore *sem, int downgrading)
  out:
 	return sem;
 
-	/* undo the change to count, but check for a transition 1->0 */
+	/* undo the change to the active count, but check for a transition
+	 * 1->0 */
  undo:
-	if (rwsem_atomic_update(-RWSEM_ACTIVE_BIAS, sem) != 0)
+	if (rwsem_atomic_update(-RWSEM_ACTIVE_BIAS, sem) & RWSEM_ACTIVE_MASK)
 		goto out;
 	goto try_again;
 }
diff --git a/lib/scatterlist.c b/lib/scatterlist.c
index 0d475d8167b..9afa25b52a8 100644
--- a/lib/scatterlist.c
+++ b/lib/scatterlist.c
@@ -7,6 +7,7 @@
  * Version 2. See the file COPYING for more details.
  */
 #include <linux/module.h>
+#include <linux/slab.h>
 #include <linux/scatterlist.h>
 #include <linux/highmem.h>
 
diff --git a/lib/show_mem.c b/lib/show_mem.c
index 238e72a18ce..fdc77c82f92 100644
--- a/lib/show_mem.c
+++ b/lib/show_mem.c
@@ -15,7 +15,7 @@ void show_mem(void)
 	unsigned long total = 0, reserved = 0, shared = 0,
 		nonshared = 0, highmem = 0;
 
-	printk(KERN_INFO "Mem-Info:\n");
+	printk("Mem-Info:\n");
 	show_free_areas();
 
 	for_each_online_pgdat(pgdat) {
@@ -49,15 +49,15 @@ void show_mem(void)
 		pgdat_resize_unlock(pgdat, &flags);
 	}
 
-	printk(KERN_INFO "%lu pages RAM\n", total);
+	printk("%lu pages RAM\n", total);
 #ifdef CONFIG_HIGHMEM
-	printk(KERN_INFO "%lu pages HighMem\n", highmem);
+	printk("%lu pages HighMem\n", highmem);
 #endif
-	printk(KERN_INFO "%lu pages reserved\n", reserved);
-	printk(KERN_INFO "%lu pages shared\n", shared);
-	printk(KERN_INFO "%lu pages non-shared\n", nonshared);
+	printk("%lu pages reserved\n", reserved);
+	printk("%lu pages shared\n", shared);
+	printk("%lu pages non-shared\n", nonshared);
 #ifdef CONFIG_QUICKLIST
-	printk(KERN_INFO "%lu pages in pagetable cache\n",
+	printk("%lu pages in pagetable cache\n",
 		quicklist_total_size());
 #endif
 }
diff --git a/lib/string.c b/lib/string.c
index a1cdcfcc42d..f71bead1be3 100644
--- a/lib/string.c
+++ b/lib/string.c
@@ -36,25 +36,21 @@ int strnicmp(const char *s1, const char *s2, size_t len)
 	/* Yes, Virginia, it had better be unsigned */
 	unsigned char c1, c2;
 
-	c1 = c2 = 0;
-	if (len) {
-		do {
-			c1 = *s1;
-			c2 = *s2;
-			s1++;
-			s2++;
-			if (!c1)
-				break;
-			if (!c2)
-				break;
-			if (c1 == c2)
-				continue;
-			c1 = tolower(c1);
-			c2 = tolower(c2);
-			if (c1 != c2)
-				break;
-		} while (--len);
-	}
+	if (!len)
+		return 0;
+
+	do {
+		c1 = *s1++;
+		c2 = *s2++;
+		if (!c1 || !c2)
+			break;
+		if (c1 == c2)
+			continue;
+		c1 = tolower(c1);
+		c2 = tolower(c2);
+		if (c1 != c2)
+			break;
+	} while (--len);
 	return (int)c1 - (int)c2;
 }
 EXPORT_SYMBOL(strnicmp);
@@ -693,13 +689,13 @@ EXPORT_SYMBOL(strstr);
  */
 char *strnstr(const char *s1, const char *s2, size_t len)
 {
-	size_t l1 = len, l2;
+	size_t l2;
 
 	l2 = strlen(s2);
 	if (!l2)
 		return (char *)s1;
-	while (l1 >= l2) {
-		l1--;
+	while (len >= l2) {
+		len--;
 		if (!memcmp(s1, s2, l2))
 			return (char *)s1;
 		s1++;
diff --git a/lib/swiotlb.c b/lib/swiotlb.c
index 437eedb5a53..a009055140e 100644
--- a/lib/swiotlb.c
+++ b/lib/swiotlb.c
@@ -28,6 +28,7 @@
 #include <linux/types.h>
 #include <linux/ctype.h>
 #include <linux/highmem.h>
+#include <linux/gfp.h>
 
 #include <asm/io.h>
 #include <asm/dma.h>
@@ -756,37 +757,6 @@ swiotlb_sync_single_for_device(struct device *hwdev, dma_addr_t dev_addr,
 EXPORT_SYMBOL(swiotlb_sync_single_for_device);
 
 /*
- * Same as above, but for a sub-range of the mapping.
- */
-static void
-swiotlb_sync_single_range(struct device *hwdev, dma_addr_t dev_addr,
-			  unsigned long offset, size_t size,
-			  int dir, int target)
-{
-	swiotlb_sync_single(hwdev, dev_addr + offset, size, dir, target);
-}
-
-void
-swiotlb_sync_single_range_for_cpu(struct device *hwdev, dma_addr_t dev_addr,
-				  unsigned long offset, size_t size,
-				  enum dma_data_direction dir)
-{
-	swiotlb_sync_single_range(hwdev, dev_addr, offset, size, dir,
-				  SYNC_FOR_CPU);
-}
-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,
-				     enum dma_data_direction dir)
-{
-	swiotlb_sync_single_range(hwdev, dev_addr, offset, size, dir,
-				  SYNC_FOR_DEVICE);
-}
-EXPORT_SYMBOL_GPL(swiotlb_sync_single_range_for_device);
-
-/*
  * Map a set of buffers described by scatterlist in streaming mode for DMA.
  * This is the scatter-gather version of the above swiotlb_map_page
  * interface.  Here the scatter gather list elements are each tagged with the
diff --git a/lib/textsearch.c b/lib/textsearch.c
index 9fbcb44c554..d608331b3e4 100644
--- a/lib/textsearch.c
+++ b/lib/textsearch.c
@@ -103,6 +103,7 @@
 #include <linux/rcupdate.h>
 #include <linux/err.h>
 #include <linux/textsearch.h>
+#include <linux/slab.h>
 
 static LIST_HEAD(ts_ops);
 static DEFINE_SPINLOCK(ts_mod_lock);
diff --git a/lib/uuid.c b/lib/uuid.c
new file mode 100644
index 00000000000..8fadd7cef46
--- /dev/null
+++ b/lib/uuid.c
@@ -0,0 +1,53 @@
+/*
+ * Unified UUID/GUID definition
+ *
+ * Copyright (C) 2009, Intel Corp.
+ *	Huang Ying <ying.huang@intel.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/kernel.h>
+#include <linux/module.h>
+#include <linux/uuid.h>
+#include <linux/random.h>
+
+static void __uuid_gen_common(__u8 b[16])
+{
+	int i;
+	u32 r;
+
+	for (i = 0; i < 4; i++) {
+		r = random32();
+		memcpy(b + i * 4, &r, 4);
+	}
+	/* reversion 0b10 */
+	b[8] = (b[8] & 0x3F) | 0x80;
+}
+
+void uuid_le_gen(uuid_le *lu)
+{
+	__uuid_gen_common(lu->b);
+	/* version 4 : random generation */
+	lu->b[7] = (lu->b[7] & 0x0F) | 0x40;
+}
+EXPORT_SYMBOL_GPL(uuid_le_gen);
+
+void uuid_be_gen(uuid_be *bu)
+{
+	__uuid_gen_common(bu->b);
+	/* version 4 : random generation */
+	bu->b[6] = (bu->b[6] & 0x0F) | 0x40;
+}
+EXPORT_SYMBOL_GPL(uuid_be_gen);
diff --git a/lib/vsprintf.c b/lib/vsprintf.c
index 3b8aeec4e32..b8a2f549ab0 100644
--- a/lib/vsprintf.c
+++ b/lib/vsprintf.c
@@ -118,6 +118,7 @@ long long simple_strtoll(const char *cp, char **endp, unsigned int base)
 
 	return simple_strtoull(cp, endp, base);
 }
+EXPORT_SYMBOL(simple_strtoll);
 
 /**
  * strict_strtoul - convert a string to an unsigned long strictly
@@ -266,7 +267,8 @@ int strict_strtoll(const char *cp, unsigned int base, long long *res)
 }
 EXPORT_SYMBOL(strict_strtoll);
 
-static int skip_atoi(const char **s)
+static noinline_for_stack
+int skip_atoi(const char **s)
 {
 	int i = 0;
 
@@ -286,7 +288,8 @@ static int skip_atoi(const char **s)
 /* Formats correctly any integer in [0,99999].
  * Outputs from one to five digits depending on input.
  * On i386 gcc 4.1.2 -O2: ~250 bytes of code. */
-static char *put_dec_trunc(char *buf, unsigned q)
+static noinline_for_stack
+char *put_dec_trunc(char *buf, unsigned q)
 {
 	unsigned d3, d2, d1, d0;
 	d1 = (q>>4) & 0xf;
@@ -323,7 +326,8 @@ static char *put_dec_trunc(char *buf, unsigned q)
 	return buf;
 }
 /* Same with if's removed. Always emits five digits */
-static char *put_dec_full(char *buf, unsigned q)
+static noinline_for_stack
+char *put_dec_full(char *buf, unsigned q)
 {
 	/* BTW, if q is in [0,9999], 8-bit ints will be enough, */
 	/* but anyway, gcc produces better code with full-sized ints */
@@ -365,7 +369,8 @@ static char *put_dec_full(char *buf, unsigned q)
 	return buf;
 }
 /* No inlining helps gcc to use registers better */
-static noinline char *put_dec(char *buf, unsigned long long num)
+static noinline_for_stack
+char *put_dec(char *buf, unsigned long long num)
 {
 	while (1) {
 		unsigned rem;
@@ -381,8 +386,8 @@ static noinline char *put_dec(char *buf, unsigned long long num)
 #define PLUS	4		/* show plus */
 #define SPACE	8		/* space if plus */
 #define LEFT	16		/* left justified */
-#define SMALL	32		/* Must be 32 == 0x20 */
-#define SPECIAL	64		/* 0x */
+#define SMALL	32		/* use lowercase in hex (must be 32 == 0x20) */
+#define SPECIAL	64		/* prefix hex with "0x", octal with "0" */
 
 enum format_type {
 	FORMAT_TYPE_NONE, /* Just a string part */
@@ -408,16 +413,17 @@ enum format_type {
 };
 
 struct printf_spec {
-	enum format_type	type;
-	int			flags;		/* flags to number() */
-	int			field_width;	/* width of output field */
-	int			base;
-	int			precision;	/* # of digits/chars */
-	int			qualifier;
+	u8	type;		/* format_type enum */
+	u8	flags;		/* flags to number() */
+	u8	base;		/* number base, 8, 10 or 16 only */
+	u8	qualifier;	/* number qualifier, one of 'hHlLtzZ' */
+	s16	field_width;	/* width of output field */
+	s16	precision;	/* # of digits/chars */
 };
 
-static char *number(char *buf, char *end, unsigned long long num,
-			struct printf_spec spec)
+static noinline_for_stack
+char *number(char *buf, char *end, unsigned long long num,
+	     struct printf_spec spec)
 {
 	/* we are called with base 8, 10 or 16, only, thus don't need "G..."  */
 	static const char digits[16] = "0123456789ABCDEF"; /* "GHIJKLMNOPQRSTUVWXYZ"; */
@@ -536,7 +542,8 @@ static char *number(char *buf, char *end, unsigned long long num,
 	return buf;
 }
 
-static char *string(char *buf, char *end, const char *s, struct printf_spec spec)
+static noinline_for_stack
+char *string(char *buf, char *end, const char *s, struct printf_spec spec)
 {
 	int len, i;
 
@@ -566,8 +573,9 @@ static char *string(char *buf, char *end, const char *s, struct printf_spec spec
 	return buf;
 }
 
-static char *symbol_string(char *buf, char *end, void *ptr,
-				struct printf_spec spec, char ext)
+static noinline_for_stack
+char *symbol_string(char *buf, char *end, void *ptr,
+		    struct printf_spec spec, char ext)
 {
 	unsigned long value = (unsigned long) ptr;
 #ifdef CONFIG_KALLSYMS
@@ -587,8 +595,9 @@ static char *symbol_string(char *buf, char *end, void *ptr,
 #endif
 }
 
-static char *resource_string(char *buf, char *end, struct resource *res,
-				struct printf_spec spec, const char *fmt)
+static noinline_for_stack
+char *resource_string(char *buf, char *end, struct resource *res,
+		      struct printf_spec spec, const char *fmt)
 {
 #ifndef IO_RSRC_PRINTK_SIZE
 #define IO_RSRC_PRINTK_SIZE	6
@@ -597,22 +606,35 @@ static char *resource_string(char *buf, char *end, struct resource *res,
 #ifndef MEM_RSRC_PRINTK_SIZE
 #define MEM_RSRC_PRINTK_SIZE	10
 #endif
-	struct printf_spec hex_spec = {
+	static const struct printf_spec io_spec = {
 		.base = 16,
+		.field_width = IO_RSRC_PRINTK_SIZE,
 		.precision = -1,
 		.flags = SPECIAL | SMALL | ZEROPAD,
 	};
-	struct printf_spec dec_spec = {
+	static const struct printf_spec mem_spec = {
+		.base = 16,
+		.field_width = MEM_RSRC_PRINTK_SIZE,
+		.precision = -1,
+		.flags = SPECIAL | SMALL | ZEROPAD,
+	};
+	static const struct printf_spec bus_spec = {
+		.base = 16,
+		.field_width = 2,
+		.precision = -1,
+		.flags = SMALL | ZEROPAD,
+	};
+	static const struct printf_spec dec_spec = {
 		.base = 10,
 		.precision = -1,
 		.flags = 0,
 	};
-	struct printf_spec str_spec = {
+	static const struct printf_spec str_spec = {
 		.field_width = -1,
 		.precision = 10,
 		.flags = LEFT,
 	};
-	struct printf_spec flag_spec = {
+	static const struct printf_spec flag_spec = {
 		.base = 16,
 		.precision = -1,
 		.flags = SPECIAL | SMALL,
@@ -622,47 +644,48 @@ static char *resource_string(char *buf, char *end, struct resource *res,
 	 * 64-bit res (sizeof==8): 20 chars in dec, 18 in hex ("0x" + 16) */
 #define RSRC_BUF_SIZE		((2 * sizeof(resource_size_t)) + 4)
 #define FLAG_BUF_SIZE		(2 * sizeof(res->flags))
-#define DECODED_BUF_SIZE	sizeof("[mem - 64bit pref disabled]")
+#define DECODED_BUF_SIZE	sizeof("[mem - 64bit pref window disabled]")
 #define RAW_BUF_SIZE		sizeof("[mem - flags 0x]")
 	char sym[max(2*RSRC_BUF_SIZE + DECODED_BUF_SIZE,
 		     2*RSRC_BUF_SIZE + FLAG_BUF_SIZE + RAW_BUF_SIZE)];
 
 	char *p = sym, *pend = sym + sizeof(sym);
-	int size = -1, addr = 0;
 	int decode = (fmt[0] == 'R') ? 1 : 0;
-
-	if (res->flags & IORESOURCE_IO) {
-		size = IO_RSRC_PRINTK_SIZE;
-		addr = 1;
-	} else if (res->flags & IORESOURCE_MEM) {
-		size = MEM_RSRC_PRINTK_SIZE;
-		addr = 1;
-	}
+	const struct printf_spec *specp;
 
 	*p++ = '[';
-	if (res->flags & IORESOURCE_IO)
+	if (res->flags & IORESOURCE_IO) {
 		p = string(p, pend, "io  ", str_spec);
-	else if (res->flags & IORESOURCE_MEM)
+		specp = &io_spec;
+	} else if (res->flags & IORESOURCE_MEM) {
 		p = string(p, pend, "mem ", str_spec);
-	else if (res->flags & IORESOURCE_IRQ)
+		specp = &mem_spec;
+	} else if (res->flags & IORESOURCE_IRQ) {
 		p = string(p, pend, "irq ", str_spec);
-	else if (res->flags & IORESOURCE_DMA)
+		specp = &dec_spec;
+	} else if (res->flags & IORESOURCE_DMA) {
 		p = string(p, pend, "dma ", str_spec);
-	else {
+		specp = &dec_spec;
+	} else if (res->flags & IORESOURCE_BUS) {
+		p = string(p, pend, "bus ", str_spec);
+		specp = &bus_spec;
+	} else {
 		p = string(p, pend, "??? ", str_spec);
+		specp = &mem_spec;
 		decode = 0;
 	}
-	hex_spec.field_width = size;
-	p = number(p, pend, res->start, addr ? hex_spec : dec_spec);
+	p = number(p, pend, res->start, *specp);
 	if (res->start != res->end) {
 		*p++ = '-';
-		p = number(p, pend, res->end, addr ? hex_spec : dec_spec);
+		p = number(p, pend, res->end, *specp);
 	}
 	if (decode) {
 		if (res->flags & IORESOURCE_MEM_64)
 			p = string(p, pend, " 64bit", str_spec);
 		if (res->flags & IORESOURCE_PREFETCH)
 			p = string(p, pend, " pref", str_spec);
+		if (res->flags & IORESOURCE_WINDOW)
+			p = string(p, pend, " window", str_spec);
 		if (res->flags & IORESOURCE_DISABLED)
 			p = string(p, pend, " disabled", str_spec);
 	} else {
@@ -675,30 +698,63 @@ static char *resource_string(char *buf, char *end, struct resource *res,
 	return string(buf, end, sym, spec);
 }
 
-static char *mac_address_string(char *buf, char *end, u8 *addr,
-				struct printf_spec spec, const char *fmt)
+static noinline_for_stack
+char *mac_address_string(char *buf, char *end, u8 *addr,
+			 struct printf_spec spec, const char *fmt)
 {
 	char mac_addr[sizeof("xx:xx:xx:xx:xx:xx")];
 	char *p = mac_addr;
 	int i;
+	char separator;
+
+	if (fmt[1] == 'F') {		/* FDDI canonical format */
+		separator = '-';
+	} else {
+		separator = ':';
+	}
 
 	for (i = 0; i < 6; i++) {
 		p = pack_hex_byte(p, addr[i]);
 		if (fmt[0] == 'M' && i != 5)
-			*p++ = ':';
+			*p++ = separator;
 	}
 	*p = '\0';
 
 	return string(buf, end, mac_addr, spec);
 }
 
-static char *ip4_string(char *p, const u8 *addr, bool leading_zeros)
+static noinline_for_stack
+char *ip4_string(char *p, const u8 *addr, const char *fmt)
 {
 	int i;
-
+	bool leading_zeros = (fmt[0] == 'i');
+	int index;
+	int step;
+
+	switch (fmt[2]) {
+	case 'h':
+#ifdef __BIG_ENDIAN
+		index = 0;
+		step = 1;
+#else
+		index = 3;
+		step = -1;
+#endif
+		break;
+	case 'l':
+		index = 3;
+		step = -1;
+		break;
+	case 'n':
+	case 'b':
+	default:
+		index = 0;
+		step = 1;
+		break;
+	}
 	for (i = 0; i < 4; i++) {
 		char temp[3];	/* hold each IP quad in reverse order */
-		int digits = put_dec_trunc(temp, addr[i]) - temp;
+		int digits = put_dec_trunc(temp, addr[index]) - temp;
 		if (leading_zeros) {
 			if (digits < 3)
 				*p++ = '0';
@@ -710,13 +766,15 @@ static char *ip4_string(char *p, const u8 *addr, bool leading_zeros)
 			*p++ = temp[digits];
 		if (i < 3)
 			*p++ = '.';
+		index += step;
 	}
 	*p = '\0';
 
 	return p;
 }
 
-static char *ip6_compressed_string(char *p, const char *addr)
+static noinline_for_stack
+char *ip6_compressed_string(char *p, const char *addr)
 {
 	int i, j, range;
 	unsigned char zerolength[8];
@@ -789,14 +847,15 @@ static char *ip6_compressed_string(char *p, const char *addr)
 	if (useIPv4) {
 		if (needcolon)
 			*p++ = ':';
-		p = ip4_string(p, &in6.s6_addr[12], false);
+		p = ip4_string(p, &in6.s6_addr[12], "I4");
 	}
 	*p = '\0';
 
 	return p;
 }
 
-static char *ip6_string(char *p, const char *addr, const char *fmt)
+static noinline_for_stack
+char *ip6_string(char *p, const char *addr, const char *fmt)
 {
 	int i;
 
@@ -811,8 +870,9 @@ static char *ip6_string(char *p, const char *addr, const char *fmt)
 	return p;
 }
 
-static char *ip6_addr_string(char *buf, char *end, const u8 *addr,
-			     struct printf_spec spec, const char *fmt)
+static noinline_for_stack
+char *ip6_addr_string(char *buf, char *end, const u8 *addr,
+		      struct printf_spec spec, const char *fmt)
 {
 	char ip6_addr[sizeof("xxxx:xxxx:xxxx:xxxx:xxxx:xxxx:255.255.255.255")];
 
@@ -824,18 +884,20 @@ static char *ip6_addr_string(char *buf, char *end, const u8 *addr,
 	return string(buf, end, ip6_addr, spec);
 }
 
-static char *ip4_addr_string(char *buf, char *end, const u8 *addr,
-			     struct printf_spec spec, const char *fmt)
+static noinline_for_stack
+char *ip4_addr_string(char *buf, char *end, const u8 *addr,
+		      struct printf_spec spec, const char *fmt)
 {
 	char ip4_addr[sizeof("255.255.255.255")];
 
-	ip4_string(ip4_addr, addr, fmt[0] == 'i');
+	ip4_string(ip4_addr, addr, fmt);
 
 	return string(buf, end, ip4_addr, spec);
 }
 
-static char *uuid_string(char *buf, char *end, const u8 *addr,
-			 struct printf_spec spec, const char *fmt)
+static noinline_for_stack
+char *uuid_string(char *buf, char *end, const u8 *addr,
+		  struct printf_spec spec, const char *fmt)
 {
 	char uuid[sizeof("xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx")];
 	char *p = uuid;
@@ -896,12 +958,15 @@ static char *uuid_string(char *buf, char *end, const u8 *addr,
  * - 'M' For a 6-byte MAC address, it prints the address in the
  *       usual colon-separated hex notation
  * - 'm' For a 6-byte MAC address, it prints the hex address without colons
+ * - 'MF' For a 6-byte MAC FDDI address, it prints the address
+ *       with a dash-separated hex notation
  * - 'I' [46] for IPv4/IPv6 addresses printed in the usual way
  *       IPv4 uses dot-separated decimal without leading 0's (1.2.3.4)
  *       IPv6 uses colon separated network-order 16 bit hex with leading 0's
  * - 'i' [46] for 'raw' IPv4/IPv6 addresses
  *       IPv6 omits the colons (01020304...0f)
  *       IPv4 uses dot-separated decimal with leading 0's (010.123.045.006)
+ * - '[Ii]4[hnbl]' IPv4 addresses in host, network, big or little endian order
  * - 'I6c' for IPv6 addresses printed as specified by
  *       http://tools.ietf.org/html/draft-ietf-6man-text-addr-representation-00
  * - 'U' For a 16 byte UUID/GUID, it prints the UUID/GUID in the form
@@ -920,8 +985,9 @@ static char *uuid_string(char *buf, char *end, const u8 *addr,
  * function pointers are really function descriptors, which contain a
  * pointer to the real address.
  */
-static char *pointer(const char *fmt, char *buf, char *end, void *ptr,
-			struct printf_spec spec)
+static noinline_for_stack
+char *pointer(const char *fmt, char *buf, char *end, void *ptr,
+	      struct printf_spec spec)
 {
 	if (!ptr)
 		return string(buf, end, "(null)", spec);
@@ -939,6 +1005,7 @@ static char *pointer(const char *fmt, char *buf, char *end, void *ptr,
 		return resource_string(buf, end, ptr, spec, fmt);
 	case 'M':			/* Colon separated: 00:01:02:03:04:05 */
 	case 'm':			/* Contiguous: 000102030405 */
+					/* [mM]F (FDDI, bit reversed) */
 		return mac_address_string(buf, end, ptr, spec, fmt);
 	case 'I':			/* Formatted IP supported
 					 * 4:	1.2.3.4
@@ -989,7 +1056,8 @@ static char *pointer(const char *fmt, char *buf, char *end, void *ptr,
  * @precision: precision of a number
  * @qualifier: qualifier of a number (long, size_t, ...)
  */
-static int format_decode(const char *fmt, struct printf_spec *spec)
+static noinline_for_stack
+int format_decode(const char *fmt, struct printf_spec *spec)
 {
 	const char *start = fmt;
 
@@ -1297,7 +1365,7 @@ int vsnprintf(char *buf, size_t size, const char *fmt, va_list args)
 			break;
 
 		case FORMAT_TYPE_NRCHARS: {
-			int qualifier = spec.qualifier;
+			u8 qualifier = spec.qualifier;
 
 			if (qualifier == 'l') {
 				long *ip = va_arg(args, long *);
@@ -1583,7 +1651,7 @@ do {									\
 
 		case FORMAT_TYPE_NRCHARS: {
 			/* skip %n 's argument */
-			int qualifier = spec.qualifier;
+			u8 qualifier = spec.qualifier;
 			void *skip_arg;
 			if (qualifier == 'l')
 				skip_arg = va_arg(args, long *);
@@ -1849,7 +1917,9 @@ int vsscanf(const char *buf, const char *fmt, va_list args)
 	char *next;
 	char digit;
 	int num = 0;
-	int qualifier, base, field_width;
+	u8 qualifier;
+	u8 base;
+	s16 field_width;
 	bool is_sign;
 
 	while (*fmt && *str) {
@@ -1927,7 +1997,7 @@ int vsscanf(const char *buf, const char *fmt, va_list args)
 		{
 			char *s = (char *)va_arg(args, char *);
 			if (field_width == -1)
-				field_width = INT_MAX;
+				field_width = SHRT_MAX;
 			/* first, skip leading white space in buffer */
 			str = skip_spaces(str);
 
diff --git a/lib/zlib_inflate/inffast.c b/lib/zlib_inflate/inffast.c
index 215447c5526..2c13ecc5bb2 100644
--- a/lib/zlib_inflate/inffast.c
+++ b/lib/zlib_inflate/inffast.c
@@ -8,21 +8,6 @@
 #include "inflate.h"
 #include "inffast.h"
 
-/* Only do the unaligned "Faster" variant when
- * CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS is set
- *
- * On powerpc, it won't be as we don't include autoconf.h
- * automatically for the boot wrapper, which is intended as
- * we run in an environment where we may not be able to deal
- * with (even rare) alignment faults. In addition, we do not
- * define __KERNEL__ for arch/powerpc/boot unlike x86
- */
-
-#ifdef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
-#include <asm/unaligned.h>
-#include <asm/byteorder.h>
-#endif
-
 #ifndef ASMINF
 
 /* Allow machine dependent optimization for post-increment or pre-increment.
@@ -36,14 +21,31 @@
    - Pentium III (Anderson)
    - M68060 (Nikl)
  */
+union uu {
+	unsigned short us;
+	unsigned char b[2];
+};
+
+/* Endian independed version */
+static inline unsigned short
+get_unaligned16(const unsigned short *p)
+{
+	union uu  mm;
+	unsigned char *b = (unsigned char *)p;
+
+	mm.b[0] = b[0];
+	mm.b[1] = b[1];
+	return mm.us;
+}
+
 #ifdef POSTINC
 #  define OFF 0
 #  define PUP(a) *(a)++
-#  define UP_UNALIGNED(a) get_unaligned((a)++)
+#  define UP_UNALIGNED(a) get_unaligned16((a)++)
 #else
 #  define OFF 1
 #  define PUP(a) *++(a)
-#  define UP_UNALIGNED(a) get_unaligned(++(a))
+#  define UP_UNALIGNED(a) get_unaligned16(++(a))
 #endif
 
 /*
@@ -256,7 +258,6 @@ void inflate_fast(z_streamp strm, unsigned start)
                     }
                 }
                 else {
-#ifdef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
 		    unsigned short *sout;
 		    unsigned long loops;
 
@@ -274,22 +275,25 @@ void inflate_fast(z_streamp strm, unsigned start)
 			sfrom = (unsigned short *)(from - OFF);
 			loops = len >> 1;
 			do
+#ifdef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
+			    PUP(sout) = PUP(sfrom);
+#else
 			    PUP(sout) = UP_UNALIGNED(sfrom);
+#endif
 			while (--loops);
 			out = (unsigned char *)sout + OFF;
 			from = (unsigned char *)sfrom + OFF;
 		    } else { /* dist == 1 or dist == 2 */
 			unsigned short pat16;
 
-			pat16 = *(sout-2+2*OFF);
-			if (dist == 1)
-#if defined(__BIG_ENDIAN)
-			    pat16 = (pat16 & 0xff) | ((pat16 & 0xff) << 8);
-#elif defined(__LITTLE_ENDIAN)
-			    pat16 = (pat16 & 0xff00) | ((pat16 & 0xff00) >> 8);
-#else
-#error __BIG_ENDIAN nor __LITTLE_ENDIAN is defined
-#endif
+			pat16 = *(sout-1+OFF);
+			if (dist == 1) {
+				union uu mm;
+				/* copy one char pattern to both bytes */
+				mm.us = pat16;
+				mm.b[0] = mm.b[1];
+				pat16 = mm.us;
+			}
 			loops = len >> 1;
 			do
 			    PUP(sout) = pat16;
@@ -298,20 +302,6 @@ void inflate_fast(z_streamp strm, unsigned start)
 		    }
 		    if (len & 1)
 			PUP(out) = PUP(from);
-#else /* CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS */
-                    from = out - dist;          /* copy direct from output */
-                    do {                        /* minimum length is three */
-			 PUP(out) = PUP(from);
-			 PUP(out) = PUP(from);
-			 PUP(out) = PUP(from);
-			 len -= 3;
-                    } while (len > 2);
-                    if (len) {
-			 PUP(out) = PUP(from);
-			 if (len > 1)
-			     PUP(out) = PUP(from);
-                    }
-#endif /* !CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS */
                 }
             }
             else if ((op & 64) == 0) {          /* 2nd level distance code */