Merge branch 'sh/g3-prep' into sh/for-2.6.33

28 files changed, 697 insertions, 356 deletions

diff --git a/kernel/audit_tree.c b/kernel/audit_tree.c
index 2451dc6f3282..4b05bd9479db 100644
--- a/kernel/audit_tree.c
+++ b/kernel/audit_tree.c
@@ -277,7 +277,7 @@ static void untag_chunk(struct node *p)
 		owner->root = NULL;
 	}
 
-	for (i = j = 0; i < size; i++, j++) {
+	for (i = j = 0; j <= size; i++, j++) {
 		struct audit_tree *s;
 		if (&chunk->owners[j] == p) {
 			list_del_init(&p->list);
@@ -290,7 +290,7 @@ static void untag_chunk(struct node *p)
 		if (!s) /* result of earlier fallback */
 			continue;
 		get_tree(s);
-		list_replace_init(&chunk->owners[i].list, &new->owners[j].list);
+		list_replace_init(&chunk->owners[j].list, &new->owners[i].list);
 	}
 
 	list_replace_rcu(&chunk->hash, &new->hash);
@@ -373,15 +373,17 @@ static int tag_chunk(struct inode *inode, struct audit_tree *tree)
 	for (n = 0; n < old->count; n++) {
 		if (old->owners[n].owner == tree) {
 			spin_unlock(&hash_lock);
-			put_inotify_watch(watch);
+			put_inotify_watch(&old->watch);
 			return 0;
 		}
 	}
 	spin_unlock(&hash_lock);
 
 	chunk = alloc_chunk(old->count + 1);
-	if (!chunk)
+	if (!chunk) {
+		put_inotify_watch(&old->watch);
 		return -ENOMEM;
+	}
 
 	mutex_lock(&inode->inotify_mutex);
 	if (inotify_clone_watch(&old->watch, &chunk->watch) < 0) {
@@ -425,7 +427,8 @@ static int tag_chunk(struct inode *inode, struct audit_tree *tree)
 	spin_unlock(&hash_lock);
 	inotify_evict_watch(&old->watch);
 	mutex_unlock(&inode->inotify_mutex);
-	put_inotify_watch(&old->watch);
+	put_inotify_watch(&old->watch); /* pair to inotify_find_watch */
+	put_inotify_watch(&old->watch); /* and kill it */
 	return 0;
 }
 
diff --git a/kernel/auditsc.c b/kernel/auditsc.c
index 267e484f0198..fc0f928167e7 100644
--- a/kernel/auditsc.c
+++ b/kernel/auditsc.c
@@ -250,7 +250,6 @@ struct audit_context {
 #endif
 };
 
-#define ACC_MODE(x) ("\004\002\006\006"[(x)&O_ACCMODE])
 static inline int open_arg(int flags, int mask)
 {
 	int n = ACC_MODE(flags);
diff --git a/kernel/bounds.c b/kernel/bounds.c
index 3c5301381837..98a51f26c136 100644
--- a/kernel/bounds.c
+++ b/kernel/bounds.c
@@ -12,7 +12,7 @@
 
 void foo(void)
 {
-	/* The enum constants to put into include/linux/bounds.h */
+	/* The enum constants to put into include/generated/bounds.h */
 	DEFINE(NR_PAGEFLAGS, __NR_PAGEFLAGS);
 	DEFINE(MAX_NR_ZONES, __MAX_NR_ZONES);
 	/* End of constants */
diff --git a/kernel/cpu.c b/kernel/cpu.c
index 291ac586f37f..1c8ddd6ee940 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -209,6 +209,7 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen)
 		return -ENOMEM;
 
 	cpu_hotplug_begin();
+	set_cpu_active(cpu, false);
 	err = __raw_notifier_call_chain(&cpu_chain, CPU_DOWN_PREPARE | mod,
 					hcpu, -1, &nr_calls);
 	if (err == NOTIFY_BAD) {
@@ -280,18 +281,6 @@ int __ref cpu_down(unsigned int cpu)
 		goto out;
 	}
 
-	set_cpu_active(cpu, false);
-
-	/*
-	 * Make sure the all cpus did the reschedule and are not
-	 * using stale version of the cpu_active_mask.
-	 * This is not strictly necessary becuase stop_machine()
-	 * that we run down the line already provides the required
-	 * synchronization. But it's really a side effect and we do not
-	 * want to depend on the innards of the stop_machine here.
-	 */
-	synchronize_sched();
-
 	err = _cpu_down(cpu, 0);
 
 out:
@@ -382,19 +371,12 @@ int disable_nonboot_cpus(void)
 		return error;
 	cpu_maps_update_begin();
 	first_cpu = cpumask_first(cpu_online_mask);
-	/* We take down all of the non-boot CPUs in one shot to avoid races
+	/*
+	 * We take down all of the non-boot CPUs in one shot to avoid races
 	 * with the userspace trying to use the CPU hotplug at the same time
 	 */
 	cpumask_clear(frozen_cpus);
 
-	for_each_online_cpu(cpu) {
-		if (cpu == first_cpu)
-			continue;
-		set_cpu_active(cpu, false);
-	}
-
-	synchronize_sched();
-
 	printk("Disabling non-boot CPUs ...\n");
 	for_each_online_cpu(cpu) {
 		if (cpu == first_cpu)
diff --git a/kernel/exit.c b/kernel/exit.c
index 5962d7ccf243..546774a31a66 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -68,10 +68,10 @@ static void __unhash_process(struct task_struct *p)
 		detach_pid(p, PIDTYPE_SID);
 
 		list_del_rcu(&p->tasks);
+		list_del_init(&p->sibling);
 		__get_cpu_var(process_counts)--;
 	}
 	list_del_rcu(&p->thread_group);
-	list_del_init(&p->sibling);
 }
 
 /*
@@ -736,12 +736,9 @@ static struct task_struct *find_new_reaper(struct task_struct *father)
 /*
 * Any that need to be release_task'd are put on the @dead list.
  */
-static void reparent_thread(struct task_struct *father, struct task_struct *p,
+static void reparent_leader(struct task_struct *father, struct task_struct *p,
 				struct list_head *dead)
 {
-	if (p->pdeath_signal)
-		group_send_sig_info(p->pdeath_signal, SEND_SIG_NOINFO, p);
-
 	list_move_tail(&p->sibling, &p->real_parent->children);
 
 	if (task_detached(p))
@@ -780,12 +777,18 @@ static void forget_original_parent(struct task_struct *father)
 	reaper = find_new_reaper(father);
 
 	list_for_each_entry_safe(p, n, &father->children, sibling) {
-		p->real_parent = reaper;
-		if (p->parent == father) {
-			BUG_ON(task_ptrace(p));
-			p->parent = p->real_parent;
-		}
-		reparent_thread(father, p, &dead_children);
+		struct task_struct *t = p;
+		do {
+			t->real_parent = reaper;
+			if (t->parent == father) {
+				BUG_ON(task_ptrace(t));
+				t->parent = t->real_parent;
+			}
+			if (t->pdeath_signal)
+				group_send_sig_info(t->pdeath_signal,
+						    SEND_SIG_NOINFO, t);
+		} while_each_thread(p, t);
+		reparent_leader(father, p, &dead_children);
 	}
 	write_unlock_irq(&tasklist_lock);
 
@@ -1551,14 +1554,9 @@ static int do_wait_thread(struct wait_opts *wo, struct task_struct *tsk)
 	struct task_struct *p;
 
 	list_for_each_entry(p, &tsk->children, sibling) {
-		/*
-		 * Do not consider detached threads.
-		 */
-		if (!task_detached(p)) {
-			int ret = wait_consider_task(wo, 0, p);
-			if (ret)
-				return ret;
-		}
+		int ret = wait_consider_task(wo, 0, p);
+		if (ret)
+			return ret;
 	}
 
 	return 0;
diff --git a/kernel/fork.c b/kernel/fork.c
index 202a0ba63d3c..5b2959b3ffc2 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1291,7 +1291,6 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 	}
 
 	if (likely(p->pid)) {
-		list_add_tail(&p->sibling, &p->real_parent->children);
 		tracehook_finish_clone(p, clone_flags, trace);
 
 		if (thread_group_leader(p)) {
@@ -1303,6 +1302,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 			p->signal->tty = tty_kref_get(current->signal->tty);
 			attach_pid(p, PIDTYPE_PGID, task_pgrp(current));
 			attach_pid(p, PIDTYPE_SID, task_session(current));
+			list_add_tail(&p->sibling, &p->real_parent->children);
 			list_add_tail_rcu(&p->tasks, &init_task.tasks);
 			__get_cpu_var(process_counts)++;
 		}
diff --git a/kernel/kexec.c b/kernel/kexec.c
index 433e9fcc1fc5..a9a93d9ee7a7 100644
--- a/kernel/kexec.c
+++ b/kernel/kexec.c
@@ -21,7 +21,7 @@
 #include <linux/hardirq.h>
 #include <linux/elf.h>
 #include <linux/elfcore.h>
-#include <linux/utsrelease.h>
+#include <generated/utsrelease.h>
 #include <linux/utsname.h>
 #include <linux/numa.h>
 #include <linux/suspend.h>
diff --git a/kernel/kfifo.c b/kernel/kfifo.c
index 3765ff3c1bbe..e92d519f93b1 100644
--- a/kernel/kfifo.c
+++ b/kernel/kfifo.c
@@ -1,6 +1,7 @@
 /*
- * A simple kernel FIFO implementation.
+ * A generic kernel FIFO implementation.
  *
+ * Copyright (C) 2009 Stefani Seibold <stefani@seibold.net>
  * Copyright (C) 2004 Stelian Pop <stelian@popies.net>
  *
  * This program is free software; you can redistribute it and/or modify
@@ -25,50 +26,48 @@
 #include <linux/err.h>
 #include <linux/kfifo.h>
 #include <linux/log2.h>
+#include <linux/uaccess.h>
+
+static void _kfifo_init(struct kfifo *fifo, unsigned char *buffer,
+		unsigned int size)
+{
+	fifo->buffer = buffer;
+	fifo->size = size;
+
+	kfifo_reset(fifo);
+}
 
 /**
- * kfifo_init - allocates a new FIFO using a preallocated buffer
+ * kfifo_init - initialize a FIFO using a preallocated buffer
+ * @fifo: the fifo to assign the buffer
  * @buffer: the preallocated buffer to be used.
  * @size: the size of the internal buffer, this have to be a power of 2.
- * @gfp_mask: get_free_pages mask, passed to kmalloc()
- * @lock: the lock to be used to protect the fifo buffer
  *
- * Do NOT pass the kfifo to kfifo_free() after use! Simply free the
- * &struct kfifo with kfree().
  */
-struct kfifo *kfifo_init(unsigned char *buffer, unsigned int size,
-			 gfp_t gfp_mask, spinlock_t *lock)
+void kfifo_init(struct kfifo *fifo, unsigned char *buffer, unsigned int size)
 {
-	struct kfifo *fifo;
-
 	/* size must be a power of 2 */
 	BUG_ON(!is_power_of_2(size));
 
-	fifo = kmalloc(sizeof(struct kfifo), gfp_mask);
-	if (!fifo)
-		return ERR_PTR(-ENOMEM);
-
-	fifo->buffer = buffer;
-	fifo->size = size;
-	fifo->in = fifo->out = 0;
-	fifo->lock = lock;
-
-	return fifo;
+	_kfifo_init(fifo, buffer, size);
 }
 EXPORT_SYMBOL(kfifo_init);
 
 /**
- * kfifo_alloc - allocates a new FIFO and its internal buffer
- * @size: the size of the internal buffer to be allocated.
+ * kfifo_alloc - allocates a new FIFO internal buffer
+ * @fifo: the fifo to assign then new buffer
+ * @size: the size of the buffer to be allocated, this have to be a power of 2.
  * @gfp_mask: get_free_pages mask, passed to kmalloc()
- * @lock: the lock to be used to protect the fifo buffer
+ *
+ * This function dynamically allocates a new fifo internal buffer
  *
  * The size will be rounded-up to a power of 2.
+ * The buffer will be release with kfifo_free().
+ * Return 0 if no error, otherwise the an error code
  */
-struct kfifo *kfifo_alloc(unsigned int size, gfp_t gfp_mask, spinlock_t *lock)
+int kfifo_alloc(struct kfifo *fifo, unsigned int size, gfp_t gfp_mask)
 {
 	unsigned char *buffer;
-	struct kfifo *ret;
 
 	/*
 	 * round up to the next power of 2, since our 'let the indices
@@ -80,48 +79,91 @@ struct kfifo *kfifo_alloc(unsigned int size, gfp_t gfp_mask, spinlock_t *lock)
 	}
 
 	buffer = kmalloc(size, gfp_mask);
-	if (!buffer)
-		return ERR_PTR(-ENOMEM);
-
-	ret = kfifo_init(buffer, size, gfp_mask, lock);
+	if (!buffer) {
+		_kfifo_init(fifo, 0, 0);
+		return -ENOMEM;
+	}
 
-	if (IS_ERR(ret))
-		kfree(buffer);
+	_kfifo_init(fifo, buffer, size);
 
-	return ret;
+	return 0;
 }
 EXPORT_SYMBOL(kfifo_alloc);
 
 /**
- * kfifo_free - frees the FIFO
+ * kfifo_free - frees the FIFO internal buffer
  * @fifo: the fifo to be freed.
  */
 void kfifo_free(struct kfifo *fifo)
 {
 	kfree(fifo->buffer);
-	kfree(fifo);
 }
 EXPORT_SYMBOL(kfifo_free);
 
 /**
- * __kfifo_put - puts some data into the FIFO, no locking version
+ * kfifo_skip - skip output data
  * @fifo: the fifo to be used.
- * @buffer: the data to be added.
- * @len: the length of the data to be added.
- *
- * This function copies at most @len bytes from the @buffer into
- * the FIFO depending on the free space, and returns the number of
- * bytes copied.
- *
- * Note that with only one concurrent reader and one concurrent
- * writer, you don't need extra locking to use these functions.
+ * @len: number of bytes to skip
  */
-unsigned int __kfifo_put(struct kfifo *fifo,
-			const unsigned char *buffer, unsigned int len)
+void kfifo_skip(struct kfifo *fifo, unsigned int len)
+{
+	if (len < kfifo_len(fifo)) {
+		__kfifo_add_out(fifo, len);
+		return;
+	}
+	kfifo_reset_out(fifo);
+}
+EXPORT_SYMBOL(kfifo_skip);
+
+static inline void __kfifo_in_data(struct kfifo *fifo,
+		const void *from, unsigned int len, unsigned int off)
 {
 	unsigned int l;
 
-	len = min(len, fifo->size - fifo->in + fifo->out);
+	/*
+	 * Ensure that we sample the fifo->out index -before- we
+	 * start putting bytes into the kfifo.
+	 */
+
+	smp_mb();
+
+	off = __kfifo_off(fifo, fifo->in + off);
+
+	/* first put the data starting from fifo->in to buffer end */
+	l = min(len, fifo->size - off);
+	memcpy(fifo->buffer + off, from, l);
+
+	/* then put the rest (if any) at the beginning of the buffer */
+	memcpy(fifo->buffer, from + l, len - l);
+}
+
+static inline void __kfifo_out_data(struct kfifo *fifo,
+		void *to, unsigned int len, unsigned int off)
+{
+	unsigned int l;
+
+	/*
+	 * Ensure that we sample the fifo->in index -before- we
+	 * start removing bytes from the kfifo.
+	 */
+
+	smp_rmb();
+
+	off = __kfifo_off(fifo, fifo->out + off);
+
+	/* first get the data from fifo->out until the end of the buffer */
+	l = min(len, fifo->size - off);
+	memcpy(to, fifo->buffer + off, l);
+
+	/* then get the rest (if any) from the beginning of the buffer */
+	memcpy(to + l, fifo->buffer, len - l);
+}
+
+static inline unsigned int __kfifo_from_user_data(struct kfifo *fifo,
+	 const void __user *from, unsigned int len, unsigned int off)
+{
+	unsigned int l;
+	int ret;
 
 	/*
 	 * Ensure that we sample the fifo->out index -before- we
@@ -130,68 +172,229 @@ unsigned int __kfifo_put(struct kfifo *fifo,
 
 	smp_mb();
 
+	off = __kfifo_off(fifo, fifo->in + off);
+
 	/* first put the data starting from fifo->in to buffer end */
-	l = min(len, fifo->size - (fifo->in & (fifo->size - 1)));
-	memcpy(fifo->buffer + (fifo->in & (fifo->size - 1)), buffer, l);
+	l = min(len, fifo->size - off);
+	ret = copy_from_user(fifo->buffer + off, from, l);
+
+	if (unlikely(ret))
+		return ret + len - l;
 
 	/* then put the rest (if any) at the beginning of the buffer */
-	memcpy(fifo->buffer, buffer + l, len - l);
+	return copy_from_user(fifo->buffer, from + l, len - l);
+}
+
+static inline unsigned int __kfifo_to_user_data(struct kfifo *fifo,
+		void __user *to, unsigned int len, unsigned int off)
+{
+	unsigned int l;
+	int ret;
 
 	/*
-	 * Ensure that we add the bytes to the kfifo -before-
-	 * we update the fifo->in index.
+	 * Ensure that we sample the fifo->in index -before- we
+	 * start removing bytes from the kfifo.
 	 */
 
-	smp_wmb();
+	smp_rmb();
+
+	off = __kfifo_off(fifo, fifo->out + off);
+
+	/* first get the data from fifo->out until the end of the buffer */
+	l = min(len, fifo->size - off);
+	ret = copy_to_user(to, fifo->buffer + off, l);
+
+	if (unlikely(ret))
+		return ret + len - l;
+
+	/* then get the rest (if any) from the beginning of the buffer */
+	return copy_to_user(to + l, fifo->buffer, len - l);
+}
+
+unsigned int __kfifo_in_n(struct kfifo *fifo,
+	const void *from, unsigned int len, unsigned int recsize)
+{
+	if (kfifo_avail(fifo) < len + recsize)
+		return len + 1;
+
+	__kfifo_in_data(fifo, from, len, recsize);
+	return 0;
+}
+EXPORT_SYMBOL(__kfifo_in_n);
 
-	fifo->in += len;
+/**
+ * kfifo_in - puts some data into the FIFO
+ * @fifo: the fifo to be used.
+ * @from: the data to be added.
+ * @len: the length of the data to be added.
+ *
+ * This function copies at most @len bytes from the @from buffer into
+ * the FIFO depending on the free space, and returns the number of
+ * bytes copied.
+ *
+ * Note that with only one concurrent reader and one concurrent
+ * writer, you don't need extra locking to use these functions.
+ */
+unsigned int kfifo_in(struct kfifo *fifo, const unsigned char *from,
+				unsigned int len)
+{
+	len = min(kfifo_avail(fifo), len);
 
+	__kfifo_in_data(fifo, from, len, 0);
+	__kfifo_add_in(fifo, len);
 	return len;
 }
-EXPORT_SYMBOL(__kfifo_put);
+EXPORT_SYMBOL(kfifo_in);
+
+unsigned int __kfifo_in_generic(struct kfifo *fifo,
+	const void *from, unsigned int len, unsigned int recsize)
+{
+	return __kfifo_in_rec(fifo, from, len, recsize);
+}
+EXPORT_SYMBOL(__kfifo_in_generic);
+
+unsigned int __kfifo_out_n(struct kfifo *fifo,
+	void *to, unsigned int len, unsigned int recsize)
+{
+	if (kfifo_len(fifo) < len + recsize)
+		return len;
+
+	__kfifo_out_data(fifo, to, len, recsize);
+	__kfifo_add_out(fifo, len + recsize);
+	return 0;
+}
+EXPORT_SYMBOL(__kfifo_out_n);
 
 /**
- * __kfifo_get - gets some data from the FIFO, no locking version
+ * kfifo_out - gets some data from the FIFO
  * @fifo: the fifo to be used.
- * @buffer: where the data must be copied.
+ * @to: where the data must be copied.
  * @len: the size of the destination buffer.
  *
  * This function copies at most @len bytes from the FIFO into the
- * @buffer and returns the number of copied bytes.
+ * @to buffer and returns the number of copied bytes.
  *
  * Note that with only one concurrent reader and one concurrent
  * writer, you don't need extra locking to use these functions.
  */
-unsigned int __kfifo_get(struct kfifo *fifo,
-			 unsigned char *buffer, unsigned int len)
+unsigned int kfifo_out(struct kfifo *fifo, unsigned char *to, unsigned int len)
 {
-	unsigned int l;
+	len = min(kfifo_len(fifo), len);
 
-	len = min(len, fifo->in - fifo->out);
+	__kfifo_out_data(fifo, to, len, 0);
+	__kfifo_add_out(fifo, len);
 
-	/*
-	 * Ensure that we sample the fifo->in index -before- we
-	 * start removing bytes from the kfifo.
-	 */
+	return len;
+}
+EXPORT_SYMBOL(kfifo_out);
 
-	smp_rmb();
+unsigned int __kfifo_out_generic(struct kfifo *fifo,
+	void *to, unsigned int len, unsigned int recsize,
+	unsigned int *total)
+{
+	return __kfifo_out_rec(fifo, to, len, recsize, total);
+}
+EXPORT_SYMBOL(__kfifo_out_generic);
 
-	/* first get the data from fifo->out until the end of the buffer */
-	l = min(len, fifo->size - (fifo->out & (fifo->size - 1)));
-	memcpy(buffer, fifo->buffer + (fifo->out & (fifo->size - 1)), l);
+unsigned int __kfifo_from_user_n(struct kfifo *fifo,
+	const void __user *from, unsigned int len, unsigned int recsize)
+{
+	if (kfifo_avail(fifo) < len + recsize)
+		return len + 1;
 
-	/* then get the rest (if any) from the beginning of the buffer */
-	memcpy(buffer + l, fifo->buffer, len - l);
+	return __kfifo_from_user_data(fifo, from, len, recsize);
+}
+EXPORT_SYMBOL(__kfifo_from_user_n);
 
-	/*
-	 * Ensure that we remove the bytes from the kfifo -before-
-	 * we update the fifo->out index.
-	 */
+/**
+ * kfifo_from_user - puts some data from user space into the FIFO
+ * @fifo: the fifo to be used.
+ * @from: pointer to the data to be added.
+ * @len: the length of the data to be added.
+ *
+ * This function copies at most @len bytes from the @from into the
+ * FIFO depending and returns the number of copied bytes.
+ *
+ * Note that with only one concurrent reader and one concurrent
+ * writer, you don't need extra locking to use these functions.
+ */
+unsigned int kfifo_from_user(struct kfifo *fifo,
+	const void __user *from, unsigned int len)
+{
+	len = min(kfifo_avail(fifo), len);
+	len -= __kfifo_from_user_data(fifo, from, len, 0);
+	__kfifo_add_in(fifo, len);
+	return len;
+}
+EXPORT_SYMBOL(kfifo_from_user);
 
-	smp_mb();
+unsigned int __kfifo_from_user_generic(struct kfifo *fifo,
+	const void __user *from, unsigned int len, unsigned int recsize)
+{
+	return __kfifo_from_user_rec(fifo, from, len, recsize);
+}
+EXPORT_SYMBOL(__kfifo_from_user_generic);
 
-	fifo->out += len;
+unsigned int __kfifo_to_user_n(struct kfifo *fifo,
+	void __user *to, unsigned int len, unsigned int reclen,
+	unsigned int recsize)
+{
+	unsigned int ret;
+
+	if (kfifo_len(fifo) < reclen + recsize)
+		return len;
+
+	ret = __kfifo_to_user_data(fifo, to, reclen, recsize);
 
+	if (likely(ret == 0))
+		__kfifo_add_out(fifo, reclen + recsize);
+
+	return ret;
+}
+EXPORT_SYMBOL(__kfifo_to_user_n);
+
+/**
+ * kfifo_to_user - gets data from the FIFO and write it to user space
+ * @fifo: the fifo to be used.
+ * @to: where the data must be copied.
+ * @len: the size of the destination buffer.
+ *
+ * This function copies at most @len bytes from the FIFO into the
+ * @to buffer and returns the number of copied bytes.
+ *
+ * Note that with only one concurrent reader and one concurrent
+ * writer, you don't need extra locking to use these functions.
+ */
+unsigned int kfifo_to_user(struct kfifo *fifo,
+	void __user *to, unsigned int len)
+{
+	len = min(kfifo_len(fifo), len);
+	len -= __kfifo_to_user_data(fifo, to, len, 0);
+	__kfifo_add_out(fifo, len);
 	return len;
 }
-EXPORT_SYMBOL(__kfifo_get);
+EXPORT_SYMBOL(kfifo_to_user);
+
+unsigned int __kfifo_to_user_generic(struct kfifo *fifo,
+	void __user *to, unsigned int len, unsigned int recsize,
+	unsigned int *total)
+{
+	return __kfifo_to_user_rec(fifo, to, len, recsize, total);
+}
+EXPORT_SYMBOL(__kfifo_to_user_generic);
+
+unsigned int __kfifo_peek_generic(struct kfifo *fifo, unsigned int recsize)
+{
+	if (recsize == 0)
+		return kfifo_avail(fifo);
+
+	return __kfifo_peek_n(fifo, recsize);
+}
+EXPORT_SYMBOL(__kfifo_peek_generic);
+
+void __kfifo_skip_generic(struct kfifo *fifo, unsigned int recsize)
+{
+	__kfifo_skip_rec(fifo, recsize);
+}
+EXPORT_SYMBOL(__kfifo_skip_generic);
+
diff --git a/kernel/kthread.c b/kernel/kthread.c
index ab7ae57773e1..fbb6222fe7e0 100644
--- a/kernel/kthread.c
+++ b/kernel/kthread.c
@@ -150,6 +150,29 @@ struct task_struct *kthread_create(int (*threadfn)(void *data),
 EXPORT_SYMBOL(kthread_create);
 
 /**
+ * kthread_bind - bind a just-created kthread to a cpu.
+ * @p: thread created by kthread_create().
+ * @cpu: cpu (might not be online, must be possible) for @k to run on.
+ *
+ * Description: This function is equivalent to set_cpus_allowed(),
+ * except that @cpu doesn't need to be online, and the thread must be
+ * stopped (i.e., just returned from kthread_create()).
+ */
+void kthread_bind(struct task_struct *p, unsigned int cpu)
+{
+	/* Must have done schedule() in kthread() before we set_task_cpu */
+	if (!wait_task_inactive(p, TASK_UNINTERRUPTIBLE)) {
+		WARN_ON(1);
+		return;
+	}
+
+	p->cpus_allowed = cpumask_of_cpu(cpu);
+	p->rt.nr_cpus_allowed = 1;
+	p->flags |= PF_THREAD_BOUND;
+}
+EXPORT_SYMBOL(kthread_bind);
+
+/**
  * kthread_stop - stop a thread created by kthread_create().
  * @k: thread created by kthread_create().
  *
diff --git a/kernel/module.c b/kernel/module.c
index a65dc787a27b..e96b8ed1cb6a 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -1910,9 +1910,7 @@ static void kmemleak_load_module(struct module *mod, Elf_Ehdr *hdr,
 	unsigned int i;
 
 	/* only scan the sections containing data */
-	kmemleak_scan_area(mod->module_core, (unsigned long)mod -
-			   (unsigned long)mod->module_core,
-			   sizeof(struct module), GFP_KERNEL);
+	kmemleak_scan_area(mod, sizeof(struct module), GFP_KERNEL);
 
 	for (i = 1; i < hdr->e_shnum; i++) {
 		if (!(sechdrs[i].sh_flags & SHF_ALLOC))
@@ -1921,8 +1919,7 @@ static void kmemleak_load_module(struct module *mod, Elf_Ehdr *hdr,
 		    && strncmp(secstrings + sechdrs[i].sh_name, ".bss", 4) != 0)
 			continue;
 
-		kmemleak_scan_area(mod->module_core, sechdrs[i].sh_addr -
-				   (unsigned long)mod->module_core,
+		kmemleak_scan_area((void *)sechdrs[i].sh_addr,
 				   sechdrs[i].sh_size, GFP_KERNEL);
 	}
 }
@@ -2250,6 +2247,12 @@ static noinline struct module *load_module(void __user *umod,
 					 "_ftrace_events",
 					 sizeof(*mod->trace_events),
 					 &mod->num_trace_events);
+	/*
+	 * This section contains pointers to allocated objects in the trace
+	 * code and not scanning it leads to false positives.
+	 */
+	kmemleak_scan_area(mod->trace_events, sizeof(*mod->trace_events) *
+			   mod->num_trace_events, GFP_KERNEL);
 #endif
 #ifdef CONFIG_FTRACE_MCOUNT_RECORD
 	/* sechdrs[0].sh_size is always zero */
diff --git a/kernel/perf_event.c b/kernel/perf_event.c
index 8ab86988bd24..1f38270f08c7 100644
--- a/kernel/perf_event.c
+++ b/kernel/perf_event.c
@@ -1381,6 +1381,9 @@ static void perf_ctx_adjust_freq(struct perf_event_context *ctx)
 		if (event->state != PERF_EVENT_STATE_ACTIVE)
 			continue;
 
+		if (event->cpu != -1 && event->cpu != smp_processor_id())
+			continue;
+
 		hwc = &event->hw;
 
 		interrupts = hwc->interrupts;
@@ -1614,7 +1617,7 @@ static struct perf_event_context *find_get_context(pid_t pid, int cpu)
 		 * offline CPU and activate it when the CPU comes up, but
 		 * that's for later.
 		 */
-		if (!cpu_isset(cpu, cpu_online_map))
+		if (!cpu_online(cpu))
 			return ERR_PTR(-ENODEV);
 
 		cpuctx = &per_cpu(perf_cpu_context, cpu);
@@ -3265,6 +3268,9 @@ static void perf_event_task_output(struct perf_event *event,
 
 static int perf_event_task_match(struct perf_event *event)
 {
+	if (event->cpu != -1 && event->cpu != smp_processor_id())
+		return 0;
+
 	if (event->attr.comm || event->attr.mmap || event->attr.task)
 		return 1;
 
@@ -3290,12 +3296,11 @@ static void perf_event_task_event(struct perf_task_event *task_event)
 	rcu_read_lock();
 	cpuctx = &get_cpu_var(perf_cpu_context);
 	perf_event_task_ctx(&cpuctx->ctx, task_event);
-	put_cpu_var(perf_cpu_context);
-
 	if (!ctx)
 		ctx = rcu_dereference(task_event->task->perf_event_ctxp);
 	if (ctx)
 		perf_event_task_ctx(ctx, task_event);
+	put_cpu_var(perf_cpu_context);
 	rcu_read_unlock();
 }
 
@@ -3372,6 +3377,9 @@ static void perf_event_comm_output(struct perf_event *event,
 
 static int perf_event_comm_match(struct perf_event *event)
 {
+	if (event->cpu != -1 && event->cpu != smp_processor_id())
+		return 0;
+
 	if (event->attr.comm)
 		return 1;
 
@@ -3408,15 +3416,10 @@ static void perf_event_comm_event(struct perf_comm_event *comm_event)
 	rcu_read_lock();
 	cpuctx = &get_cpu_var(perf_cpu_context);
 	perf_event_comm_ctx(&cpuctx->ctx, comm_event);
-	put_cpu_var(perf_cpu_context);
-
-	/*
-	 * doesn't really matter which of the child contexts the
-	 * events ends up in.
-	 */
 	ctx = rcu_dereference(current->perf_event_ctxp);
 	if (ctx)
 		perf_event_comm_ctx(ctx, comm_event);
+	put_cpu_var(perf_cpu_context);
 	rcu_read_unlock();
 }
 
@@ -3491,6 +3494,9 @@ static void perf_event_mmap_output(struct perf_event *event,
 static int perf_event_mmap_match(struct perf_event *event,
 				   struct perf_mmap_event *mmap_event)
 {
+	if (event->cpu != -1 && eve