Merge branch 'linux-2.6'

10 files changed, 995 insertions, 419 deletions

diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index a60109307d32..89f4035b526c 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -79,6 +79,38 @@ config HEADERS_CHECK
 	  exported to $(INSTALL_HDR_PATH) (usually 'usr/include' in
 	  your build tree), to make sure they're suitable.
 
+config DEBUG_SECTION_MISMATCH
+	bool "Enable full Section mismatch analysis"
+	default n
+	help
+	  The section mismatch analysis checks if there are illegal
+	  references from one section to another section.
+	  Linux will during link or during runtime drop some sections
+	  and any use of code/data previously in these sections will
+	  most likely result in an oops.
+	  In the code functions and variables are annotated with
+	  __init, __devinit etc. (see full list in include/linux/init.h)
+	  which result in the code/data being placed in specific sections.
+	  The section mismatch anaylsis are always done after a full
+	  kernel build but enabling this options will in addition
+	  do the following:
+	  - Add the option -fno-inline-functions-called-once to gcc
+	    When inlining a function annotated __init in a non-init
+	    function we would loose the section information and thus
+	    the analysis would not catch the illegal reference.
+	    This options tell gcc to inline less but will also
+	    result in a larger kernel.
+	  - Run the section mismatch analysis for each module/built-in.o
+	    When we run the section mismatch analysis on vmlinux.o we
+	    looses valueable information about where the mismatch was
+	    introduced.
+	    Running the analysis for each module/built-in.o file
+	    will tell where the mismatch happens much closer to the
+	    source. The drawback is that we will report the same
+	    mismatch at least twice.
+	  - Enable verbose reporting from modpost to help solving
+	    the section mismatches reported.
+
 config DEBUG_KERNEL
 	bool "Kernel debugging"
 	help
@@ -462,6 +494,30 @@ config RCU_TORTURE_TEST
 	  Say M if you want the RCU torture tests to build as a module.
 	  Say N if you are unsure.
 
+config KPROBES_SANITY_TEST
+	bool "Kprobes sanity tests"
+	depends on DEBUG_KERNEL
+	depends on KPROBES
+	default n
+	help
+	  This option provides for testing basic kprobes functionality on
+	  boot. A sample kprobe, jprobe and kretprobe are inserted and
+	  verified for functionality.
+
+	  Say N if you are unsure.
+
+config BACKTRACE_SELF_TEST
+	tristate "Self test for the backtrace code"
+	depends on DEBUG_KERNEL
+	default n
+	help
+	  This option provides a kernel module that can be used to test
+	  the kernel stack backtrace code. This option is not useful
+	  for distributions or general kernels, but only for kernel
+	  developers working on architecture code.
+
+	  Say N if you are unsure.
+
 config LKDTM
 	tristate "Linux Kernel Dump Test Tool Module"
 	depends on DEBUG_KERNEL
@@ -517,4 +573,46 @@ config FAULT_INJECTION_STACKTRACE_FILTER
 	help
 	  Provide stacktrace filter for fault-injection capabilities
 
+config LATENCYTOP
+	bool "Latency measuring infrastructure"
+	select FRAME_POINTER if !MIPS
+	select KALLSYMS
+	select KALLSYMS_ALL
+	select STACKTRACE
+	select SCHEDSTATS
+	select SCHED_DEBUG
+	depends on X86 || X86_64
+	help
+	  Enable this option if you want to use the LatencyTOP tool
+	  to find out which userspace is blocking on what kernel operations.
+
+config PROVIDE_OHCI1394_DMA_INIT
+	bool "Provide code for enabling DMA over FireWire early on boot"
+	depends on PCI && X86
+	help
+	  If you want to debug problems which hang or crash the kernel early
+	  on boot and the crashing machine has a FireWire port, you can use
+	  this feature to remotely access the memory of the crashed machine
+	  over FireWire. This employs remote DMA as part of the OHCI1394
+	  specification which is now the standard for FireWire controllers.
+
+	  With remote DMA, you can monitor the printk buffer remotely using
+	  firescope and access all memory below 4GB using fireproxy from gdb.
+	  Even controlling a kernel debugger is possible using remote DMA.
+
+	  Usage:
+
+	  If ohci1394_dma=early is used as boot parameter, it will initialize
+	  all OHCI1394 controllers which are found in the PCI config space.
+
+	  As all changes to the FireWire bus such as enabling and disabling
+	  devices cause a bus reset and thereby disable remote DMA for all
+	  devices, be sure to have the cable plugged and FireWire enabled on
+	  the debugging host before booting the debug target for debugging.
+
+	  This code (~1k) is freed after boot. By then, the firewire stack
+	  in charge of the OHCI-1394 controllers should be used instead.
+
+	  See Documentation/debugging-via-ohci1394.txt for more information.
+
 source "samples/Kconfig"
diff --git a/lib/Makefile b/lib/Makefile
index b6793ed28d84..543f2502b60a 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -6,7 +6,7 @@ lib-y := ctype.o string.o vsprintf.o cmdline.o \
 	 rbtree.o radix-tree.o dump_stack.o \
 	 idr.o int_sqrt.o extable.o prio_tree.o \
 	 sha1.o irq_regs.o reciprocal_div.o argv_split.o \
-	 proportions.o prio_heap.o
+	 proportions.o prio_heap.o scatterlist.o
 
 lib-$(CONFIG_MMU) += ioremap.o
 lib-$(CONFIG_SMP) += cpumask.o
@@ -61,6 +61,7 @@ obj-$(CONFIG_TEXTSEARCH_KMP) += ts_kmp.o
 obj-$(CONFIG_TEXTSEARCH_BM) += ts_bm.o
 obj-$(CONFIG_TEXTSEARCH_FSM) += ts_fsm.o
 obj-$(CONFIG_SMP) += percpu_counter.o
+obj-$(CONFIG_SMP) += pcounter.o
 obj-$(CONFIG_AUDIT_GENERIC) += audit.o
 
 obj-$(CONFIG_SWIOTLB) += swiotlb.o
diff --git a/lib/find_next_bit.c b/lib/find_next_bit.c
index bda0d71a2514..78ccd73a8841 100644
--- a/lib/find_next_bit.c
+++ b/lib/find_next_bit.c
@@ -178,4 +178,47 @@ found_middle_swap:
 
 EXPORT_SYMBOL(generic_find_next_zero_le_bit);
 
+unsigned long generic_find_next_le_bit(const unsigned long *addr, unsigned
+		long size, unsigned long offset)
+{
+	const unsigned long *p = addr + BITOP_WORD(offset);
+	unsigned long result = offset & ~(BITS_PER_LONG - 1);
+	unsigned long tmp;
+
+	if (offset >= size)
+		return size;
+	size -= result;
+	offset &= (BITS_PER_LONG - 1UL);
+	if (offset) {
+		tmp = ext2_swabp(p++);
+		tmp &= (~0UL << offset);
+		if (size < BITS_PER_LONG)
+			goto found_first;
+		if (tmp)
+			goto found_middle;
+		size -= BITS_PER_LONG;
+		result += BITS_PER_LONG;
+	}
+
+	while (size & ~(BITS_PER_LONG - 1)) {
+		tmp = *(p++);
+		if (tmp)
+			goto found_middle_swap;
+		result += BITS_PER_LONG;
+		size -= BITS_PER_LONG;
+	}
+	if (!size)
+		return result;
+	tmp = ext2_swabp(p);
+found_first:
+	tmp &= (~0UL >> (BITS_PER_LONG - size));
+	if (tmp == 0UL)		/* Are any bits set? */
+		return result + size; /* Nope. */
+found_middle:
+	return result + __ffs(tmp);
+
+found_middle_swap:
+	return result + __ffs(ext2_swab(tmp));
+}
+EXPORT_SYMBOL(generic_find_next_le_bit);
 #endif /* __BIG_ENDIAN */
diff --git a/lib/kernel_lock.c b/lib/kernel_lock.c
index f73e2f8c308f..812dbf00844b 100644
--- a/lib/kernel_lock.c
+++ b/lib/kernel_lock.c
@@ -9,7 +9,6 @@
 #include <linux/module.h>
 #include <linux/kallsyms.h>
 
-#ifdef CONFIG_PREEMPT_BKL
 /*
  * The 'big kernel semaphore'
  *
@@ -86,128 +85,6 @@ void __lockfunc unlock_kernel(void)
 		up(&kernel_sem);
 }
 
-#else
-
-/*
- * The 'big kernel lock'
- *
- * This spinlock is taken and released recursively by lock_kernel()
- * and unlock_kernel().  It is transparently dropped and reacquired
- * over schedule().  It is used to protect legacy code that hasn't
- * been migrated to a proper locking design yet.
- *
- * Don't use in new code.
- */
-static  __cacheline_aligned_in_smp DEFINE_SPINLOCK(kernel_flag);
-
-
-/*
- * Acquire/release the underlying lock from the scheduler.
- *
- * This is called with preemption disabled, and should
- * return an error value if it cannot get the lock and
- * TIF_NEED_RESCHED gets set.
- *
- * If it successfully gets the lock, it should increment
- * the preemption count like any spinlock does.
- *
- * (This works on UP too - _raw_spin_trylock will never
- * return false in that case)
- */
-int __lockfunc __reacquire_kernel_lock(void)
-{
-	while (!_raw_spin_trylock(&kernel_flag)) {
-		if (test_thread_flag(TIF_NEED_RESCHED))
-			return -EAGAIN;
-		cpu_relax();
-	}
-	preempt_disable();
-	return 0;
-}
-
-void __lockfunc __release_kernel_lock(void)
-{
-	_raw_spin_unlock(&kernel_flag);
-	preempt_enable_no_resched();
-}
-
-/*
- * These are the BKL spinlocks - we try to be polite about preemption. 
- * If SMP is not on (ie UP preemption), this all goes away because the
- * _raw_spin_trylock() will always succeed.
- */
-#ifdef CONFIG_PREEMPT
-static inline void __lock_kernel(void)
-{
-	preempt_disable();
-	if (unlikely(!_raw_spin_trylock(&kernel_flag))) {
-		/*
-		 * If preemption was disabled even before this
-		 * was called, there's nothing we can be polite
-		 * about - just spin.
-		 */
-		if (preempt_count() > 1) {
-			_raw_spin_lock(&kernel_flag);
-			return;
-		}
-
-		/*
-		 * Otherwise, let's wait for the kernel lock
-		 * with preemption enabled..
-		 */
-		do {
-			preempt_enable();
-			while (spin_is_locked(&kernel_flag))
-				cpu_relax();
-			preempt_disable();
-		} while (!_raw_spin_trylock(&kernel_flag));
-	}
-}
-
-#else
-
-/*
- * Non-preemption case - just get the spinlock
- */
-static inline void __lock_kernel(void)
-{
-	_raw_spin_lock(&kernel_flag);
-}
-#endif
-
-static inline void __unlock_kernel(void)
-{
-	/*
-	 * the BKL is not covered by lockdep, so we open-code the
-	 * unlocking sequence (and thus avoid the dep-chain ops):
-	 */
-	_raw_spin_unlock(&kernel_flag);
-	preempt_enable();
-}
-
-/*
- * Getting the big kernel lock.
- *
- * This cannot happen asynchronously, so we only need to
- * worry about other CPU's.
- */
-void __lockfunc lock_kernel(void)
-{
-	int depth = current->lock_depth+1;
-	if (likely(!depth))
-		__lock_kernel();
-	current->lock_depth = depth;
-}
-
-void __lockfunc unlock_kernel(void)
-{
-	BUG_ON(current->lock_depth < 0);
-	if (likely(--current->lock_depth < 0))
-		__unlock_kernel();
-}
-
-#endif
-
 EXPORT_SYMBOL(lock_kernel);
 EXPORT_SYMBOL(unlock_kernel);
 
diff --git a/lib/kobject.c b/lib/kobject.c
index 3590f022a609..1d63ead1815e 100644
--- a/lib/kobject.c
+++ b/lib/kobject.c
@@ -18,58 +18,57 @@
 #include <linux/stat.h>
 #include <linux/slab.h>
 
-/**
- *	populate_dir - populate directory with attributes.
- *	@kobj:	object we're working on.
- *
- *	Most subsystems have a set of default attributes that 
- *	are associated with an object that registers with them.
- *	This is a helper called during object registration that 
- *	loops through the default attributes of the subsystem 
- *	and creates attributes files for them in sysfs.
+/*
+ * populate_dir - populate directory with attributes.
+ * @kobj: object we're working on.
  *
+ * Most subsystems have a set of default attributes that are associated
+ * with an object that registers with them.  This is a helper called during
+ * object registration that loops through the default attributes of the
+ * subsystem and creates attributes files for them in sysfs.
  */
-
-static int populate_dir(struct kobject * kobj)
+static int populate_dir(struct kobject *kobj)
 {
-	struct kobj_type * t = get_ktype(kobj);
-	struct attribute * attr;
+	struct kobj_type *t = get_ktype(kobj);
+	struct attribute *attr;
 	int error = 0;
 	int i;
-	
+
 	if (t && t->default_attrs) {
 		for (i = 0; (attr = t->default_attrs[i]) != NULL; i++) {
-			if ((error = sysfs_create_file(kobj,attr)))
+			error = sysfs_create_file(kobj, attr);
+			if (error)
 				break;
 		}
 	}
 	return error;
 }
 
-static int create_dir(struct kobject * kobj)
+static int create_dir(struct kobject *kobj)
 {
 	int error = 0;
 	if (kobject_name(kobj)) {
 		error = sysfs_create_dir(kobj);
 		if (!error) {
-			if ((error = populate_dir(kobj)))
+			error = populate_dir(kobj);
+			if (error)
 				sysfs_remove_dir(kobj);
 		}
 	}
 	return error;
 }
 
-static inline struct kobject * to_kobj(struct list_head * entry)
+static inline struct kobject *to_kobj(struct list_head *entry)
 {
-	return container_of(entry,struct kobject,entry);
+	return container_of(entry, struct kobject, entry);
 }
 
 static int get_kobj_path_length(struct kobject *kobj)
 {
 	int length = 1;
-	struct kobject * parent = kobj;
+	struct kobject *parent = kobj;
 
-	/* walk up the ancestors until we hit the one pointing to the 
+	/* walk up the ancestors until we hit the one pointing to the
 	 * root.
 	 * Add 1 to strlen for leading '/' of each level.
 	 */
@@ -84,18 +83,19 @@ static int get_kobj_path_length(struct kobject *kobj)
 
 static void fill_kobj_path(struct kobject *kobj, char *path, int length)
 {
-	struct kobject * parent;
+	struct kobject *parent;
 
 	--length;
 	for (parent = kobj; parent; parent = parent->parent) {
 		int cur = strlen(kobject_name(parent));
 		/* back up enough to print this name with '/' */
 		length -= cur;
-		strncpy (path + length, kobject_name(parent), cur);
+		strncpy(path + length, kobject_name(parent), cur);
 		*(path + --length) = '/';
 	}
 
-	pr_debug("%s: path = '%s'\n",__FUNCTION__,path);
+	pr_debug("kobject: '%s' (%p): %s: path = '%s'\n", kobject_name(kobj),
+		 kobj, __FUNCTION__, path);
 }
 
 /**
@@ -123,179 +123,286 @@ char *kobject_get_path(struct kobject *kobj, gfp_t gfp_mask)
 }
 EXPORT_SYMBOL_GPL(kobject_get_path);
 
-/**
- *	kobject_init - initialize object.
- *	@kobj:	object in question.
- */
-void kobject_init(struct kobject * kobj)
+/* add the kobject to its kset's list */
+static void kobj_kset_join(struct kobject *kobj)
 {
-	if (!kobj)
+	if (!kobj->kset)
 		return;
-	kref_init(&kobj->kref);
-	INIT_LIST_HEAD(&kobj->entry);
-	kobj->kset = kset_get(kobj->kset);
+
+	kset_get(kobj->kset);
+	spin_lock(&kobj->kset->list_lock);
+	list_add_tail(&kobj->entry, &kobj->kset->list);
+	spin_unlock(&kobj->kset->list_lock);
 }
 
+/* remove the kobject from its kset's list */
+static void kobj_kset_leave(struct kobject *kobj)
+{
+	if (!kobj->kset)
+		return;
 
-/**
- *	unlink - remove kobject from kset list.
- *	@kobj:	kobject.
- *
- *	Remove the kobject from the kset list and decrement
- *	its parent's refcount.
- *	This is separated out, so we can use it in both 
- *	kobject_del() and kobject_add() on error.
- */
+	spin_lock(&kobj->kset->list_lock);
+	list_del_init(&kobj->entry);
+	spin_unlock(&kobj->kset->list_lock);
+	kset_put(kobj->kset);
+}
 
-static void unlink(struct kobject * kobj)
+static void kobject_init_internal(struct kobject *kobj)
 {
-	if (kobj->kset) {
-		spin_lock(&kobj->kset->list_lock);
-		list_del_init(&kobj->entry);
-		spin_unlock(&kobj->kset->list_lock);
-	}
-	kobject_put(kobj);
+	if (!kobj)
+		return;
+	kref_init(&kobj->kref);
+	INIT_LIST_HEAD(&kobj->entry);
 }
 
-/**
- *	kobject_add - add an object to the hierarchy.
- *	@kobj:	object.
- */
 
-int kobject_add(struct kobject * kobj)
+static int kobject_add_internal(struct kobject *kobj)
 {
 	int error = 0;
-	struct kobject * parent;
+	struct kobject *parent;
 
-	if (!(kobj = kobject_get(kobj)))
+	if (!kobj)
 		return -ENOENT;
-	if (!kobj->k_name)
-		kobject_set_name(kobj, "NO_NAME");
-	if (!*kobj->k_name) {
-		pr_debug("kobject attempted to be registered with no name!\n");
+
+	if (!kobj->name || !kobj->name[0]) {
+		pr_debug("kobject: (%p): attempted to be registered with empty "
+			 "name!\n", kobj);
 		WARN_ON(1);
-		kobject_put(kobj);
 		return -EINVAL;
 	}
-	parent = kobject_get(kobj->parent);
 
-	pr_debug("kobject %s: registering. parent: %s, set: %s\n",
-		 kobject_name(kobj), parent ? kobject_name(parent) : "<NULL>", 
-		 kobj->kset ? kobject_name(&kobj->kset->kobj) : "<NULL>" );
+	parent = kobject_get(kobj->parent);
 
+	/* join kset if set, use it as parent if we do not already have one */
 	if (kobj->kset) {
-		spin_lock(&kobj->kset->list_lock);
-
 		if (!parent)
 			parent = kobject_get(&kobj->kset->kobj);
-
-		list_add_tail(&kobj->entry,&kobj->kset->list);
-		spin_unlock(&kobj->kset->list_lock);
+		kobj_kset_join(kobj);
 		kobj->parent = parent;
 	}
 
+	pr_debug("kobject: '%s' (%p): %s: parent: '%s', set: '%s'\n",
+		 kobject_name(kobj), kobj, __FUNCTION__,
+		 parent ? kobject_name(parent) : "<NULL>",
+		 kobj->kset ? kobject_name(&kobj->kset->kobj) : "<NULL>");
+
 	error = create_dir(kobj);
 	if (error) {
-		/* unlink does the kobject_put() for us */
-		unlink(kobj);
+		kobj_kset_leave(kobj);
 		kobject_put(parent);
+		kobj->parent = NULL;
 
 		/* be noisy on error issues */
 		if (error == -EEXIST)
-			printk(KERN_ERR "kobject_add failed for %s with "
+			printk(KERN_ERR "%s failed for %s with "
 			       "-EEXIST, don't try to register things with "
 			       "the same name in the same directory.\n",
-			       kobject_name(kobj));
+			       __FUNCTION__, kobject_name(kobj));
 		else
-			printk(KERN_ERR "kobject_add failed for %s (%d)\n",
-			       kobject_name(kobj), error);
+			printk(KERN_ERR "%s failed for %s (%d)\n",
+			       __FUNCTION__, kobject_name(kobj), error);
 		dump_stack();
-	}
+	} else
+		kobj->state_in_sysfs = 1;
 
 	return error;
 }
 
 /**
- *	kobject_register - initialize and add an object.
- *	@kobj:	object in question.
+ * kobject_set_name_vargs - Set the name of an kobject
+ * @kobj: struct kobject to set the name of
+ * @fmt: format string used to build the name
+ * @vargs: vargs to format the string.
  */
-
-int kobject_register(struct kobject * kobj)
+static int kobject_set_name_vargs(struct kobject *kobj, const char *fmt,
+				  va_list vargs)
 {
-	int error = -EINVAL;
-	if (kobj) {
-		kobject_init(kobj);
-		error = kobject_add(kobj);
-		if (!error)
-			kobject_uevent(kobj, KOBJ_ADD);
-	}
-	return error;
-}
+	va_list aq;
+	char *name;
+
+	va_copy(aq, vargs);
+	name = kvasprintf(GFP_KERNEL, fmt, vargs);
+	va_end(aq);
 
+	if (!name)
+		return -ENOMEM;
+
+	/* Free the old name, if necessary. */
+	kfree(kobj->name);
+
+	/* Now, set the new name */
+	kobj->name = name;
+
+	return 0;
+}
 
 /**
  * kobject_set_name - Set the name of a kobject
- * @kobj: kobject to name
+ * @kobj: struct kobject to set the name of
  * @fmt: format string used to build the name
  *
  * This sets the name of the kobject.  If you have already added the
  * kobject to the system, you must call kobject_rename() in order to
  * change the name of the kobject.
  */
-int kobject_set_name(struct kobject * kobj, const char * fmt, ...)
+int kobject_set_name(struct kobject *kobj, const char *fmt, ...)
 {
-	int error = 0;
-	int limit;
-	int need;
 	va_list args;
-	char *name;
+	int retval;
 
-	/* find out how big a buffer we need */
-	name = kmalloc(1024, GFP_KERNEL);
-	if (!name) {
-		error = -ENOMEM;
-		goto done;
-	}
 	va_start(args, fmt);
-	need = vsnprintf(name, 1024, fmt, args);
+	retval = kobject_set_name_vargs(kobj, fmt, args);
 	va_end(args);
-	kfree(name);
 
-	/* Allocate the new space and copy the string in */
-	limit = need + 1;
-	name = kmalloc(limit, GFP_KERNEL);
-	if (!name) {
-		error = -ENOMEM;
-		goto done;
+	return retval;
+}
+EXPORT_SYMBOL(kobject_set_name);
+
+/**
+ * kobject_init - initialize a kobject structure
+ * @kobj: pointer to the kobject to initialize
+ * @ktype: pointer to the ktype for this kobject.
+ *
+ * This function will properly initialize a kobject such that it can then
+ * be passed to the kobject_add() call.
+ *
+ * After this function is called, the kobject MUST be cleaned up by a call
+ * to kobject_put(), not by a call to kfree directly to ensure that all of
+ * the memory is cleaned up properly.
+ */
+void kobject_init(struct kobject *kobj, struct kobj_type *ktype)
+{
+	char *err_str;
+
+	if (!kobj) {
+		err_str = "invalid kobject pointer!";
+		goto error;
+	}
+	if (!ktype) {
+		err_str = "must have a ktype to be initialized properly!\n";
+		goto error;
+	}
+	if (kobj->state_initialized) {
+		/* do not error out as sometimes we can recover */
+		printk(KERN_ERR "kobject (%p): tried to init an initialized "
+		       "object, something is seriously wrong.\n", kobj);
+		dump_stack();
 	}
-	va_start(args, fmt);
-	need = vsnprintf(name, limit, fmt, args);
-	va_end(args);
 
-	/* something wrong with the string we copied? */
-	if (need >= limit) {
-		kfree(name);
-		error = -EFAULT;
-		goto done;
+	kref_init(&kobj->kref);
+	INIT_LIST_HEAD(&kobj->entry);
+	kobj->ktype = ktype;
+	kobj->state_in_sysfs = 0;
+	kobj->state_add_uevent_sent = 0;
+	kobj->state_remove_uevent_sent = 0;
+	kobj->state_initialized = 1;
+	return;
+
+error:
+	printk(KERN_ERR "kobject (%p): %s\n", kobj, err_str);
+	dump_stack();
+}
+EXPORT_SYMBOL(kobject_init);
+
+static int kobject_add_varg(struct kobject *kobj, struct kobject *parent,
+			    const char *fmt, va_list vargs)
+{
+	va_list aq;
+	int retval;
+
+	va_copy(aq, vargs);
+	retval = kobject_set_name_vargs(kobj, fmt, aq);
+	va_end(aq);
+	if (retval) {
+		printk(KERN_ERR "kobject: can not set name properly!\n");
+		return retval;
 	}
+	kobj->parent = parent;
+	return kobject_add_internal(kobj);
+}
 
-	/* Free the old name, if necessary. */
-	kfree(kobj->k_name);
+/**
+ * kobject_add - the main kobject add function
+ * @kobj: the kobject to add
+ * @parent: pointer to the parent of the kobject.
+ * @fmt: format to name the kobject with.
+ *
+ * The kobject name is set and added to the kobject hierarchy in this
+ * function.
+ *
+ * If @parent is set, then the parent of the @kobj will be set to it.
+ * If @parent is NULL, then the parent of the @kobj will be set to the
+ * kobject associted with the kset assigned to this kobject.  If no kset
+ * is assigned to the kobject, then the kobject will be located in the
+ * root of the sysfs tree.
+ *
+ * If this function returns an error, kobject_put() must be called to
+ * properly clean up the memory associated with the object.
+ * Under no instance should the kobject that is passed to this function
+ * be directly freed with a call to kfree(), that can leak memory.
+ *
+ * Note, no "add" uevent will be created with this call, the caller should set
+ * up all of the necessary sysfs files for the object and then call
+ * kobject_uevent() with the UEVENT_ADD parameter to ensure that
+ * userspace is properly notified of this kobject's creation.
+ */
+int kobject_add(struct kobject *kobj, struct kobject *parent,
+		const char *fmt, ...)
+{
+	va_list args;
+	int retval;
 
-	/* Now, set the new name */
-	kobj->k_name = name;
-done:
-	return error;
+	if (!kobj)
+		return -EINVAL;
+
+	if (!kobj->state_initialized) {
+		printk(KERN_ERR "kobject '%s' (%p): tried to add an "
+		       "uninitialized object, something is seriously wrong.\n",
+		       kobject_name(kobj), kobj);
+		dump_stack();
+		return -EINVAL;
+	}
+	va_start(args, fmt);
+	retval = kobject_add_varg(kobj, parent, fmt, args);
+	va_end(args);
+
+	return retval;
 }
-EXPORT_SYMBOL(kobject_set_name);
+EXPORT_SYMBOL(kobject_add);
 
 /**
- *	kobject_rename - change the name of an object
- *	@kobj:	object in question.
- *	@new_name: object's new name
+ * kobject_init_and_add - initialize a kobject structure and add it to the kobject hierarchy
+ * @kobj: pointer to the kobject to initialize
+ * @ktype: pointer to the ktype for this kobject.
+ * @parent: pointer to the parent of this kobject.
+ * @fmt: the name of the kobject.
+ *
+ * This function combines the call to kobject_init() and
+ * kobject_add().  The same type of error handling after a call to
+ * kobject_add() and kobject lifetime rules are the same here.
  */
+int kobject_init_and_add(struct kobject *kobj, struct kobj_type *ktype,
+			 struct kobject *parent, const char *fmt, ...)
+{
+	va_list args;
+	int retval;
+
+	kobject_init(kobj, ktype);
+
+	va_start(args, fmt);
+	retval = kobject_add_varg(kobj, parent, fmt, args);
+	va_end(args);
+
+	return retval;
+}
+EXPORT_SYMBOL_GPL(kobject_init_and_add);
 
-int kobject_rename(struct kobject * kobj, const char *new_name)
+/**
+ * kobject_rename - change the name of an object
+ * @kobj: object in question.
+ * @new_name: object's new name
+ */
+int kobject_rename(struct kobject *kobj, const char *new_name)
 {
 	int error = 0;
 	const char *devpath = NULL;
@@ -334,8 +441,6 @@ int kobject_rename(struct kobject * kobj, const char *new_name)
 	sprintf(devpath_string, "DEVPATH_OLD=%s", devpath);
 	envp[0] = devpath_string;
 	envp[1] = NULL;
-	/* Note : if we want to send the new name alone, not the full path,
-	 * we could probably use kobject_name(kobj); */
 
 	error = sysfs_rename_dir(kobj, new_name);
 
@@ -354,11 +459,10 @@ out:
 }
 
 /**
- *	kobject_move - move object to another parent
- *	@kobj:	object in question.
- *	@new_parent: object's new parent (can be NULL)
+ * kobject_move - move object to another parent
+ * @kobj: object in question.
+ * @new_parent: object's new parent (can be NULL)
  */
-
 int kobject_move(struct kobject *kobj, struct kobject *new_parent)
 {
 	int error;
@@ -406,68 +510,74 @@ out:
 }
 
 /**
- *	kobject_del - unlink kobject from hierarchy.
- * 	@kobj:	object.
+ * kobject_del - unlink kobject from hierarchy.
+ * @kobj: object.
  */
-
-void kobject_del(struct kobject * kobj)
+void kobject_del(struct kobject *kobj)
 {
 	if (!kobj)
 		return;
-	sysfs_remove_dir(kobj);
-	unlink(kobj);
-}
 
-/**
- *	kobject_unregister - remove object from hierarchy and decrement refcount.
- *	@kobj:	object going away.
- */
-
-void kobject_unregister(struct kobject * kobj)
-{
-	if (!kobj)
-		return;
-	pr_debug("kobject %s: unregistering\n",kobject_name(kobj));
-	kobject_uevent(kobj, KOBJ_REMOVE);
-	kobject_del(kobj);
-	kobject_put(kobj);
+	sysfs_remove_dir(kobj);
+	kobj->state_in_sysfs = 0;
+	kobj_kset_leave(kobj);
+	kobject_put(kobj->parent);
+	kobj->parent = NULL;
 }
 
 /**
- *	kobject_get - increment refcount for object.
- *	@kobj:	object.
+ * kobject_get - increment refcount for object.
+ * @kobj: object.
  */
-
-struct kobject * kobject_get(struct kobject * kobj)
+struct kobject *kobject_get(struct kobject *kobj)
 {
 	if (kobj)
 		kref_get(&kobj->kref);
 	return kobj;
 }
 
-/**
- *	kobject_cleanup - free kobject resources. 
- *	@kobj:	object.
+/*
+ * kobject_cleanup - free kobject resources.
+ * @kobj: object to cleanup
  */
-
-void kobject_cleanup(struct kobject * kobj)
+static void kobject_cleanup(struct kobject *kobj)
 {
-	struct kobj_type * t = get_ktype(kobj);
-	struct kset * s = kobj->kset;
-	struct kobject * parent = kobj->parent;
-	const char *name = kobj->k_name;
+	struct kobj_type *t = get_ktype(kobj);
+	const char *name = kobj->name;
+
+	pr_debug("kobject: '%s' (%p): %s\n",
+		 kobject_name(kobj), kobj, __FUNCTION__);
+
+	if (t && !t->release)
+		pr_debug("kobject: '%s' (%p): does not have a release() "
+			 "function, it is broken and must be fixed.\n",
+			 kobject_name(kobj), kobj);
+
+	/* send "remove" if the caller did not do it but sent "add" */
+	if (kobj->state_add_uevent_sent && !kobj->state_remove_uevent_sent) {
+		pr_debug("kobject: '%s' (%p): auto cleanup 'remove' event\n",
+			 kobject_name(kobj), kobj);
+		kobject_uevent(kobj, KOBJ_REMOVE);
+	}
+
+	/* remove from sysfs if the caller did not do it */
+	if (kobj->state_in_sysfs) {
+		pr_debug("kobject: '%s' (%p): auto cleanup kobject_del\n",
+			 kobject_name(kobj), kobj);
+		kobject_del(kobj);
+	}
 
-	pr_debug("kobject %s: cleaning up\n",kobject_name(kobj));
 	if (t && t->release) {
+		pr_debug("kobject: '%s' (%p): calling ktype release\n",
+			 kobject_name(kobj), kobj);
 		t->release(kobj);
-		/* If we have a release function, we can guess that this was
-		 * not a statically allocated kobject, so we should be safe to
-		 * free the name */
+	}
+
+	/* free name if we allocated it */
+	if (name) {
+		pr_debug("kobject: '%s': free name\n", name);
 		kfree(name);
 	}
-	if (s)
-		kset_put(s);
-	kobject_put(parent);
 }
 
 static void kobject_release(struct kref *kref)
@@ -476,107 +586,130 @@ static void kobject_release(struct kref *kref)
 }
 
 /**
- *	kobject_put - decrement refcount for object.
- *	@kobj:	object.
+ * kobject_put - decrement refcount for object.
+ * @kobj: object.
  *
- *	Decrement the refcount, and if 0, call kobject_cleanup().
+ * Decrement the refcount, and if 0, call kobject_cleanup().
  */
-void kobject_put(struct kobject * kobj)
+void kobject_put(struct kobject *kobj)
 {
 	if (kobj)
 		kref_put(&kobj->kref, kobject_release);
 }
 
-
-static void dir_release(struct kobject *kobj)
+static void dynamic_kobj_release(struct kobject *kobj)
 {
+	pr_debug("kobject: (%p): %s\n", kobj, __FUNCTION__);
 	kfree(kobj);
 }
 
-static struct kobj_type dir_ktype = {
-	.release	= dir_release,
-	.sysfs_ops	= NULL,
-	.default_attrs	= NULL,
+static struct kobj_type dynamic_kobj_ktype = {
+	.release	= dynamic_kobj_release,
+	.sysfs_ops	= &kobj_sysfs_ops,
 };
 
 /**
- *	kobject_kset_add_dir - add sub directory of object.
- *	@kset:		kset the directory is belongs to.
- *	@parent:	object in which a directory is created.
- *	@name:	directory name.
+ * kobject_create - create a struct kobject dynamically
  *
- *	Add a plain directory object as child of given object.
+ * This function creates a kobject structure dynamically and sets it up
+ * to be a "dynamic" kobject with a default release function set up.
+ *
+ * If the kobject was not able to be created, NULL will be returned.
+ * The kobject structure returned from here must be cleaned up with a
+ * call to kobject_put() and not kfree(), as kobject_init() has
+ * already been called on this structure.
  */
-struct kobject *kobject_kset_add_dir(struct kset *kset,
-				     struct kobject *parent, const char *name)
+struct kobject *kobject_create(void)
 {
-	struct kobject *k;
-	int ret;
-
-	if (!parent)
-		return NULL;
-
-	k = kzalloc(sizeof(*k), GFP_KERNEL);
-	if (!k)
-		return NULL;
+	struct kobject *kobj;
 
-	k->kset = kset;
-	k->parent = parent;
-	k->ktype = &dir_ktype;
-	kobject_set_name(k, name);
-	ret = kobject_register(k);
-	if (ret < 0) {
-		printk(KERN_WARNING "%s: kobject_register error: %d\n",
-			__func__, ret);
-		kobject_del(k);
+	kobj = kzalloc(sizeof(*kobj), GFP_KERNEL);
+	if (!kobj)
 		return NULL;
-	}
 
-	return k;
+	kobject_init(kobj, &dynamic_kobj_ktype);
+	return kobj;
 }
 
 /**
- *	kobject_add_dir - add sub directory of object.
- *	@parent:	object in which a directory is created.
- *	@name:	directory name.
+ * kobject_create_and_add - create a struct kobject dynamically and register it with sysfs
+ *
+ * @name: the name for the kset
+ * @parent: the parent kobject of this kobject, if any.
+ *
+ * This function creates a kset structure dynamically and registers it
+ * with sysfs.  When you are finished with this structure, call
+ * kobject_put() and the structure will be dynamically freed when
+ * it is no longer being used.
  *
- *	Add a plain directory object as child of given object.
+ * If the kobject was not able to be created, NULL will be returned.
  */
-struct kobject *kobject_add_dir(struct kobject *parent, const char *name)
+struct kobject *kobject_create_and_add(const char *name, struct kobject *parent)
 {
-	return kobject_kset_add_dir(NULL, parent, name);
+	struct kobject *kobj;
+	int retval;
+
+	kobj = kobject_create();
+	if (!kobj)
+		return NULL;
+
+	retval = kobject_add(kobj, parent, "%s", name);
+	if (retval) {
+		printk(KERN_WARNING "%s: kobject_add error: %d\n",
+		       __FUNCTION__, retval);
+		kobject_put(kobj);
+		kobj = NULL;
+	}
+	return kobj;
 }
+EXPORT_SYMBOL_GPL(kobject_create_and_add);
 
 /**
- *	kset_init - initialize a kset for use
- *	@k:	kset 
+ * kset_init - initialize a kset for use
+ * @k: kset
  */
-
-void kset_init(struct kset * k)
+void kset_init(struct kset *k)
 {
-	kobject_init(&k->kobj);
+	kobject_init_internal(&k->kobj);
 	INIT_LIST_HEAD(&k->list);
 	spin_lock_init(&k->list_lock);
 }
 
+/* default kobject attribute operations */
+static ssize_t kobj_attr_show(struct kobject *kobj, struct attribute *attr,
+			      char *buf)
+{
+	struct kobj_attribute *kattr;
+	ssize_t ret = -EIO;
 
-/**
- *	kset_add - add a kset object to the hierarchy.
- *	@k:	kset.
- */
+	kattr = container_of(attr, struct kobj_attribute, attr);
+	if (kattr->show)
+		ret = kattr->show(kobj, kattr, buf);
+	return ret;
+}
 
-int kset_add(struct kset * k)
+static ssize_t kobj_attr_store(struct kobject *kobj, struct attribute *attr,
+			       const char *buf, size_t count)
 {
-	return kobject_add(&k->kobj);
+	struct kobj_attribute *kattr;
+	ssize_t ret = -EIO;
+
+	kattr = container_of(attr, struct kobj_attribute, attr);
+	if (kattr->store)
+		ret = kattr->store(kobj, kattr, buf, count);
+	return ret;
 }
 
+struct sysfs_ops kobj_sysfs_ops = {
+	.show	= kobj_attr_show,
+	.store	= kobj_attr_store,
+};
 
 /**
- *	kset_register - initialize and add a kset.
- *	@k:	kset.
+ * kset_register - initialize and add a kset.
+ * @k: kset.
  */
-
-int kset_register(struct kset * k)
+int kset_register(struct kset *k)
 {
 	int err;
 
@@ -584,46 +717,42 @@ int kset_register(struct kset * k)
 		return -EINVAL;
 
 	kset_init(k);
-	err = kset_add(k);
+	err = kobject_add_internal(&k->kobj);
 	if (err)
 		return err;
 	kobject_uevent(&k->kobj, KOBJ_ADD);
 	return 0;
 }
 
-
 /**
- *	kset_unregister - remove a kset.
- *	@k:	kset.
+ * kset_unregister - remove a kset.
+ * @k: kset.
  */
-
-void kset_unregister(struct kset * k)
+void kset_unregister(struct kset *k)
 {
 	if (!k)
 		return;
-	kobject_unregister(&k->kobj);
+	kobject_put(&k->kobj);
 }
 
-
 /**
- *	kset_find_obj - search for object in kset.
- *	@kset:	kset we're looking in.
- *	@name:	object's name.
+ * kset_find_obj - search for object in kset.
+ * @kset: kset we're looking in.
+ * @name: object's name.
  *
- *	Lock kset via @kset->subsys, and iterate over @kset->list,
- *	looking for a matching kobject. If matching object is found
- *	take a reference and return the object.
+ * Lock kset via @kset->subsys, and iterate over @kset->list,
+ * looking for a matching kobject. If matching object is found
+ * take a reference and return the object.
  */
-
-struct kobject * kset_find_obj(struct kset * kset, const char * name)
+struct kobject *kset_find_obj(struct kset *kset, const char *name)
 {
-	struct list_head * entry;
-	struct kobject * ret = NULL;
+	struct list_head *entry;
+	struct kobject *ret = NULL;
 
 	spin_lock(&kset->list_lock);
-	list_for_each(entry,&kset->list) {
-		struct kobject * k = to_kobj(entry);
-		if (kobject_name(k) && !strcmp(kobject_name(k),name)) {
+	list_for_each(entry, &kset->list) {
+		struct kobject *k = to_kobj(entry);
+		if (kobject_name(k) && !strcmp(kobject_name(k), name)) {
 			ret = kobject_get(k);
 			break;
 		}
@@ -632,47 +761,94 @@ struct kobject * kset_find_obj(struct kset * kset, const char * name)
 	return ret;
 }
 
-int subsystem_register(struct kset *s)
+static void kset_release(struct kobject *kobj)
 {
-	return kset_register(s);
+	struct kset *kset = container_of(kobj, struct kset, kobj);
+	pr_debug("kobject: '%s' (%p): %s\n",
+		 kobject_name(kobj), kobj, __FUNCTION__);
+	kfree(kset);
 }
 
-void subsystem_unregister(struct kset *s)
+static struct kobj_type kset_ktype = {
+	.sysfs_ops	= &kobj_sysfs_ops,
+	.release = kset_release,
+};
+
+/**
+ * kset_create - create a struct kset dynamically
+ *
+ * @name: the name for the kset
+ * @uevent_ops: a struct kset_uevent_ops for the kset
+ * @parent_kobj: the parent kobject of this kset, if any.
+ *
+ * This function creates a kset structure dynamically.  This structure can
+ * then be registered with the system and show up in sysfs with a call to
+ * kset_register().  When you are finished with this structure, if
+ * kset_register() has been called, call kset_unregister() and the
+ * structure will be dynamically freed when it is no longer being used.
+ *
+ * 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,
+				struct kobject *parent_kobj)
 {
-	kset_unregister(s);
+	struct kset *kset;
+
+	kset = kzalloc(sizeof(*kset), GFP_KERNEL);
+	if (!kset)
+		return NULL;
+	kobject_set_name(&kset->kobj, name);
+	kset->uevent_ops = uevent_ops;
+	kset->kobj.parent = parent_kobj;
+
+	/*
+	 * The kobject of this kset will have a type of kset_ktype and belong to
+	 * no kset itself.  That way we can properly free it when it is
+	 * finished being used.
+	 */
+	kset->kobj.ktype = &kset_ktype;
+	kset->kobj.kset = NULL;
+
+	return kset;
 }
 
 /**
- *	subsystem_create_file - export sysfs attribute file.
- *	@s:	subsystem.
- *	@a:	subsystem attribute descriptor.
+ * kset_create_and_add - create a struct kset dynamically and add it to sysfs
+ *
+ * @name: the name for the kset
+ * @uevent_ops: a struct kset_uevent_ops for the kset
+ * @parent_kobj: the parent kobject of this kset, if any.
+ *
+ * This function creates a kset structure dynamically and registers it
+ * with sysfs.  When you are finished with this structure, call
+ * kset_unregister() and the structure will be dynamically freed when it
+ * is no longer being used.
+ *
+ * If the kset was not able to be created, NULL will be returned.
  */
-
-int subsys_create_file(struct kset *s, struct subsys_attribute *a)
+struct kset *kset_create_and_add(const char *name,
+				 struct kset_uevent_ops *uevent_ops,
+				 struct kobject *parent_kobj)
 {
-	int error = 0;
-
-	if (!s || !a)
-		return -EINVAL;
+	struct kset *kset;
+	int error;
 
-	if (kset_get(s)) {
-		error = sysfs_create_file(&s->kobj, &a->attr);
-		kset_put(s);
+	kset = kset_create(name, uevent_ops, parent_kobj);
+	if (!kset)
+		return NULL;
+	error = kset_register(kset);
+	if (error) {
+		kfree(kset);
+		return NULL;
 	}
-	return error;
+	return kset;
 }
+EXPORT_SYMBOL_GPL(kset_create_and_add);
 
-EXPORT_SYMBOL(kobject_init);
-EXPORT_SYMBOL(kobject_register);
-EXPORT_SYMBOL(kobject_unregister);
 EXPORT_SYMBOL(kobject_get);
 EXPORT_SYMBOL(kobject_put);
-EXPORT_SYMBOL(kobject_add);
 EXPORT_SYMBOL(kobject_del);
 
 EXPORT_SYMBOL(kset_register);
 EXPORT_SYMBOL(kset_unregister);
-
-EXPORT_SYMBOL(subsystem_register);
-EXPORT_SYMBOL(subsystem_unregister);
-EXPORT_SYMBOL(subsys_create_file);
diff --git a/lib/kobject_uevent.c b/lib/kobject_uevent.c
index 5886147252d0..5a402e2982af 100644
--- a/lib/kobject_uevent.c
+++ b/lib/kobject_uevent.c
@@ -98,7 +98,8 @@ int kobject_uevent_env(struct kobject *kobj, enum kobject_action action,
 	int i = 0;
 	int retval = 0;
 
-	pr_debug("%s\n", __FUNCTION__);
+	pr_debug("kobject: '%s' (%p): %s\n",
+		 kobject_name(kobj), kobj, __FUNCTION__);
 
 	/* search the kset we belong to */
 	top_kobj = kobj;
@@ -106,7 +107,9 @@ int kobject_uevent_env(struct kobject *kobj, enum kobject_action action,
 		top_kobj = top_kobj->parent;
 
 	if (!top_kobj->kset) {
-		pr_debug("kobject attempted to send uevent without kset!\n");
+		pr_debug("kobject: '%s' (%p): %s: attempted to send uevent "
+			 "without kset!\n", kobject_name(kobj), kobj,
+			 __FUNCTION__);
 		return -EINVAL;
 	}
 
@@ -116,7 +119,9 @@ int kobject_uevent_env(struct kobject *kobj, enum kobject_action action,
 	/* skip the event, if the filter returns zero. */
 	if (uevent_ops && uevent_ops->filter)
 		if (!uevent_ops->filter(kset, kobj)) {
-			pr_debug("kobject filter function caused the event to drop!\n");
+			pr_debug("kobject: '%s' (%p): %s: filter function "
+				 "caused the event to drop!\n",
+				 kobject_name(kobj), kobj, __FUNCTION__);
 			return 0;
 		}
 
@@ -126,7 +131,9 @@ int kobject_uevent_env(struct kobject *kobj, enum kobject_action action,
 	else
 		subsystem = kobject_name(&kset->kobj);
 	if (!subsystem) {
-		pr_debug("unset subsystem caused the event to drop!\n");
+		pr_debug("kobject: '%s' (%p): %s: unset subsystem caused the "
+			 "event to drop!\n", kobject_name(kobj), kobj,
+			 __FUNCTION__);
 		return 0;
 	}
 
@@ -166,12 +173,24 @@ int kobject_uevent_env(struct kobject *kobj, enum kobject_action action,
 	if (uevent_ops && uevent_ops->uevent) {
 		retval = uevent_ops->uevent(kset, kobj, env);
 		if (retval) {
-			pr_debug ("%s - uevent() returned %d\n",
-				  __FUNCTION__, retval);
+			pr_debug("kobject: '%s' (%p): %s: uevent() returned "
+				 "%d\n", kobject_name(kobj), kobj,
+				 __FUNCTION__, retval);
 			goto exit;
 		}
 	}
 
+	/*
+	 * Mark "add" and "remove" events in the object to ensure proper
+	 * events to userspace during automatic cleanup. If the object did
+	 * send an "add" event, "remove" will automatically generated by
+	 * the core, if not already done by the caller.
+	 */
+	if (action == KOBJ_ADD)
+		kobj->state_add_uevent_sent = 1;
+	else if (action == KOBJ_REMOVE)
+		kobj->state_remove_uevent_sent = 1;
+
 	/* we will send an event, so request a new sequence number */
 	spin_lock(&sequence_lock);
 	seq = ++uevent_seqnum;
@@ -219,11 +238,12 @@ int kobject_uevent_env(struct kobject *kobj, enum kobject_action action,
 		retval = add_uevent_var(env, "HOME=/");
 		if (retval)
 			goto exit;
-		retval = add_uevent_var(env, "PATH=/sbin:/bin:/usr/sbin:/usr/bin");
+		retval = add_uevent_var(env,
+					"PATH=/sbin:/bin:/usr/sbin:/usr/bin");
 		if (retval)
 			goto exit;
 
-		call_usermodehelper (argv[0], argv, env->envp, UMH_WAIT_EXEC);
+		call_usermodehelper(argv[0], argv, env->envp, UMH_WAIT_EXEC);
 	}
 
 exit:
@@ -231,7 +251,6 @@ exit:
 	kfree(env);
 	return retval;
 }
-
 EXPORT_SYMBOL_GPL(kobject_uevent_env);
 
 /**
@@ -247,7 +266,6 @@ int kobject_uevent(struct kobject *kobj, enum kobject_action action)
 {
 	return kobject_uevent_env(kobj, action, NULL);
 }
-
 EXPORT_SYMBOL_GPL(kobject_uevent);
 
 /**
diff --git a/lib/kref.c b/lib/kref.c
index a6dc3ec328e0..9ecd6e865610 100644
--- a/lib/kref.c
+++ b/lib/kref.c
@@ -15,13 +15,23 @@
 #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();
+}
+
+/**
  * kref_init - initialize object.
  * @kref: object in question.
  */
 void kref_init(struct kref *kref)
 {
-	atomic_set(&kref->refcount,1);
-	smp_mb();
+	kref_set(kref, 1);
 }
 
 /**
@@ -61,6 +71,7 @@ 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/pcounter.c b/lib/pcounter.c
new file mode 100644
index 000000000000..9b56807da93b
--- /dev/null
+++ b/lib/pcounter.c
@@ -0,0 +1,58 @@
+/*
+ * Define default pcounter functions
+ * Note that often used pcounters use dedicated functions to get a speed increase.
+ * (see DEFINE_PCOUNTER/REF_PCOUNTER_MEMBER)
+ */
+
+#include <linux/module.h>
+#include <linux/pcounter.h>
+#include <linux/smp.h>
+#include <linux/cpumask.h>
+
+static void pcounter_dyn_add(struct pcounter *self, int inc)
+{
+	per_cpu_ptr(self->per_cpu_values, smp_processor_id())[0] += inc;
+}
+
+static int pcounter_dyn_getval(const struct pcounter *self, int cpu)
+{
+	return per_cpu_ptr(self->per_cpu_values, cpu)[0];
+}
+
+int pcounter_getval(const struct pcounter *self)
+{
+	int res = 0, cpu;
+
+	for_each_possible_cpu(cpu)
+		res += self->getval(self, cpu);
+
+	return res;
+}
+EXPORT_SYMBOL_GPL(pcounter_getval);
+
+int pcounter_alloc(struct pcounter *self)
+{
+	int rc = 0;
+	if (self->add == NULL) {
+		self->per_cpu_values = alloc_percpu(int);
+		if (self->per_cpu_values != NULL) {
+			self->add    = pcounter_dyn_add;
+			self->getval = pcounter_dyn_getval;
+		} else
+			rc = 1;
+	}
+	return rc;
+}
+EXPORT_SYMBOL_GPL(pcounter_alloc);
+
+void pcounter_free(struct pcounter *self)
+{
+	if (self->per_cpu_values != NULL) {
+		free_percpu(self->per_cpu_values);
+		self->per_cpu_values = NULL;
+		self->getval = NULL;
+		self->add = NULL;
+	}
+}
+EXPORT_SYMBOL_GPL(pcounter_free);
+
diff --git a/lib/rwsem.c b/lib/rwsem.c
index 7d02700a4b0e..3e3365e5665e 100644
--- a/lib/rwsem.c
+++ b/lib/rwsem.c
@@ -187,7 +187,7 @@ rwsem_down_failed_common(struct rw_semaphore *sem,
 /*
  * wait for the read lock to be granted
  */
-struct rw_semaphore fastcall __sched *
+asmregparm struct rw_semaphore __sched *
 rwsem_down_read_failed(struct rw_semaphore *sem)
 {
 	struct rwsem_waiter waiter;
@@ -201,7 +201,7 @@ rwsem_down_read_failed(struct rw_semaphore *sem)
 /*
  * wait for the write lock to be granted
  */
-struct rw_semaphore fastcall __sched *
+asmregparm struct rw_semaphore __sched *
 rwsem_down_write_failed(struct rw_semaphore *sem)
 {
 	struct rwsem_waiter waiter;
@@ -216,7 +216,7 @@ rwsem_down_write_failed(struct rw_semaphore *sem)
  * handle waking up a waiter on the semaphore
  * - up_read/up_write has decremented the active part of count if we come here
  */
-struct rw_semaphore fastcall *rwsem_wake(struct rw_semaphore *sem)
+asmregparm struct rw_semaphore *rwsem_wake(struct rw_semaphore *sem)
 {
 	unsigned long flags;
 
@@ -236,7 +236,7 @@ struct rw_semaphore fastcall *rwsem_wake(struct rw_semaphore *sem)
  * - caller incremented waiting part of count and discovered it still negative
  * - just wake up any readers at the front of the queue
  */
-struct rw_semaphore fastcall *rwsem_downgrade_wake(struct rw_semaphore *sem)
+asmregparm struct rw_semaphore *rwsem_downgrade_wake(struct rw_semaphore *sem)
 {
 	unsigned long flags;
 
diff --git a/lib/scatterlist.c b/lib/scatterlist.c
new file mode 100644
index 000000000000..acca4901046c
--- /dev/null
+++ b/lib/scatterlist.c
@@ -0,0 +1,294 @@
+/*
+ * Copyright (C) 2007 Jens Axboe <jens.axboe@oracle.com>
+ *
+ * Scatterlist handling helpers.
+ *
+ * This source code is licensed under the GNU General Public License,
+ * Version 2. See the file COPYING for more details.
+ */
+#include <linux/module.h>
+#include <linux/scatterlist.h>
+
+/**
+ * sg_next - return the next scatterlist entry in a list
+ * @sg:		The current sg entry
+ *
+ * Description:
+ *   Usually the next entry will be @sg@ + 1, but if this sg element is part
+ *   of a chained scatterlist, it could jump to the start of a new
+ *   scatterlist array.
+ *
+ **/
+struct scatterlist *sg_next(struct scatterlist *sg)
+{
+#ifdef CONFIG_DEBUG_SG
+	BUG_ON(sg->sg_magic != SG_MAGIC);
+#endif
+	if (sg_is_last(sg))
+		return NULL;
+
+	sg++;
+	if (unlikely(sg_is_chain(sg)))
+		sg = sg_chain_ptr(sg);
+
+	return sg;
+}
+EXPORT_SYMBOL(sg_next);
+
+/**
+ * sg_last - return the last scatterlist entry in a list
+ * @sgl:	First entry in the scatterlist
+ * @nents:	Number of entries in the scatterlist
+ *
+ * Description:
+ *   Should only be used casually, it (currently) scans the entire list
+ *   to get the last entry.
+ *
+ *   Note that the @sgl@ pointer passed in need not be the first one,
+ *   the important bit is that @nents@ denotes the number of entries that
+ *   exist from @sgl@.
+ *
+ **/
+struct scatterlist *sg_last(struct scatterlist *sgl, unsigned int nents)
+{
+#ifndef ARCH_HAS_SG_CHAIN
+	struct scatterlist *ret = &sgl[nents - 1];
+#else
+	struct scatterlist *sg, *ret = NULL;
+	unsigned int i;
+
+	for_each_sg(sgl, sg, nents, i)
+		ret = sg;
+
+#endif
+#ifdef CONFIG_DEBUG_SG
+	BUG_ON(sgl[0].sg_magic != SG_MAGIC);
+	BUG_ON(!sg_is_last(ret));
+#endif
+	return ret;
+}
+EXPORT_SYMBOL(sg_last);
+
+/**
+ * sg_init_table - Initialize SG table
+ * @sgl:	   The SG table
+ * @nents:	   Number of entries in table
+ *
+ * Notes:
+ *   If this is part of a chained sg table, sg_mark_end() should be
+ *   used only on the last table part.
+ *
+ **/
+void sg_init_table(struct scatterlist *sgl, unsigned int nents)
+{
+	memset(sgl, 0, sizeof(*sgl) * nents);
+#ifdef CONFIG_DEBUG_SG
+	{
+		unsigned int i;
+		for (i = 0; i < nents; i++)
+			sgl[i].sg_magic = SG_MAGIC;
+	}
+#endif
+	sg_mark_end(&sgl[nents - 1]);
+}
+EXPORT_SYMBOL(sg_init_table);
+
+/**
+ * sg_init_one - Initialize a single entry sg list
+ * @sg:		 SG entry
+ * @buf:	 Virtual address for IO
+ * @buflen:	 IO length
+ *
+ **/
+void sg_init_one(struct scatterlist *sg, const void *buf, unsigned int buflen)
+{
+	sg_init_table(sg, 1);
+	sg_set_buf(sg, buf, buflen);
+}
+EXPORT_SYMBOL(sg_init_one);
+
+/*
+ * The default behaviour of sg_alloc_table() is to use these kmalloc/kfree
+ * helpers.
+ */
+static struct scatterlist *sg_kmalloc(unsigned int nents, gfp_t gfp_mask)
+{
+	if (nents == SG_MAX_SINGLE_ALLOC)
+		return (struct scatterlist *) __get_free_page(gfp_mask);
+	else
+		return kmalloc(nents * sizeof(struct scatterlist), gfp_mask);
+}
+
+static void sg_kfree(struct scatterlist *sg, unsigned int nents)
+{
+	if (nents == SG_MAX_SINGLE_ALLOC)
+		free_page((unsigned long) sg);
+	else
+		kfree(sg);
+}
+
+/**
+ * __sg_free_table - Free a previously mapped sg table
+ * @table:	The sg table header to use
+ * @max_ents:	The maximum number of entries per single scatterlist
+ * @free_fn:	Free function
+ *
+ *  Description:
+ *    Free an sg table previously allocated and setup with
+ *    __sg_alloc_table().  The @max_ents value must be identical to
+ *    that previously used with __sg_alloc_table().
+ *
+ **/
+void __sg_free_table(struct sg_table *table, unsigned int max_ents,
+		     sg_free_fn *free_fn)
+{
+	struct scatterlist *sgl, *next;
+
+	if (unlikely(!table->sgl))
+		return;
+
+	sgl = table->sgl;
+	while (table->orig_nents) {
+		unsigned int alloc_size = table->orig_nents;
+		unsigned int sg_size;
+
+		/*
+		 * If we have more than max_ents segments left,
+		 * then assign 'next' to the sg table after the current one.
+		 * sg_size is then one less than alloc size, since the last
+		 * element is the chain pointer.
+		 */
+		if (alloc_size > max_ents) {
+			next = sg_chain_ptr(&sgl[max_ents - 1]);
+			alloc_size = max_ents;
+			sg_size = alloc_size - 1;
+		} else {
+			sg_size = alloc_size;
+			next = NULL;
+		}
+
+		table->orig_nents -= sg_size;
+		free_fn(sgl, alloc_size);
+		sgl = next;
+	}
+
+	table->sgl = NULL;
+}
+EXPORT_SYMBOL(__sg_free_table);
+
+/**
+ * sg_free_table - Free a previously allocated sg table
+ * @table:	The mapped sg table header
+ *
+ **/
+void sg_free_table(struct sg_table *table)
+{
+	__sg_free_table(table, SG_MAX_SINGLE_ALLOC, sg_kfree);
+}
+EXPORT_SYMBOL(sg_free_table);
+
+/**
+ * __sg_alloc_table - Allocate and initialize an sg table with given allocator
+ * @table:	The sg table header to use
+ * @nents:	Number of entries in sg list
+ * @max_ents:	The maximum number of entries the allocator returns per call
+ * @gfp_mask:	GFP allocation mask
+ * @alloc_fn:	Allocator to use
+ *
+ * Description:
+ *   This function returns a @table @nents long. The allocator is
+ *   defined to return scatterlist chunks of maximum size @max_ents.
+ *   Thus if @nents is bigger than @max_ents, the scatterlists will be
+ *   chained in units of @max_ents.
+ *
+ * Notes:
+ *   If this function returns non-0 (eg failure), the caller must call
+ *   __sg_free_table() to cleanup any leftover allocations.
+ *
+ **/
+int __sg_alloc_table(struct sg_table *table, unsigned int nents,
+		     unsigned int max_ents, gfp_t gfp_mask,
+		     sg_alloc_fn *alloc_fn)
+{
+	struct scatterlist *sg, *prv;
+	unsigned int left;
+
+#ifndef ARCH_HAS_SG_CHAIN
+	BUG_ON(nents > max_ents);
+#endif
+
+	memset(table, 0, sizeof(*table));
+
+	left = nents;
+	prv = NULL;
+	do {
+		unsigned int sg_size, alloc_size = left;
+
+		if (alloc_size > max_ents) {
+			alloc_size = max_ents;
+			sg_size = alloc_size - 1;
+		} else
+			sg_size = alloc_size;
+
+		left -= sg_size;
+
+		sg = alloc_fn(alloc_size, gfp_mask);
+		if (unlikely(!sg))
+			return -ENOMEM;
+
+		sg_init_table(sg, alloc_size);
+		table->nents = table->orig_nents += sg_size;
+
+		/*
+		 * If this is the first mapping, assign the sg table header.
+		 * If this is not the first mapping, chain previous part.
+		 */
+		if (prv)
+			sg_chain(prv, max_ents, sg);
+		else
+			table->sgl = sg;
+
+		/*
+		 * If no more entries after this one, mark the end
+		 */
+		if (!left)
+			sg_mark_end(&sg[sg_size - 1]);
+
+		/*
+		 * only really needed for mempool backed sg allocations (like
+		 * SCSI), a possible improvement here would be to pass the
+		 * table pointer into the allocator and let that clear these
+		 * flags
+		 */
+		gfp_mask &= ~__GFP_WAIT;
+		gfp_mask |= __GFP_HIGH;
+		prv = sg;
+	} while (left);
+
+	return 0;
+}
+EXPORT_SYMBOL(__sg_alloc_table);
+
+/**
+ * sg_alloc_table - Allocate and initialize an sg table
+ * @table:	The sg table header to use
+ * @nents:	Number of entries in sg list
+ * @gfp_mask:	GFP allocation mask
+ *
+ *  Description:
+ *    Allocate and initialize an sg table. If @nents@ is larger than
+ *    SG_MAX_SINGLE_ALLOC a chained sg table will be setup.
+ *
+ **/
+int sg_alloc_table(struct sg_table *table, unsigned int nents, gfp_t gfp_mask)
+{
+	int ret;
+
+	ret = __sg_alloc_table(table, nents, SG_MAX_SINGLE_ALLOC,
+			       gfp_mask, sg_kmalloc);
+	if (unlikely(ret))
+		__sg_free_table(table, SG_MAX_SINGLE_ALLOC, sg_kfree);
+
+	return ret;
+}
+EXPORT_SYMBOL(sg_alloc_table);