Merge branch 'linus' into tracing/hw-branch-tracing

Merge reason: update to latest tracing and ptrace APIs

Signed-off-by: Ingo Molnar <mingo@elte.hu>

107 files changed, 7035 insertions, 2867 deletions

diff --git a/kernel/Makefile b/kernel/Makefile
index e4791b3ba55..bab1dffe37e 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -93,6 +93,7 @@ obj-$(CONFIG_HAVE_GENERIC_DMA_COHERENT) += dma-coherent.o
 obj-$(CONFIG_FUNCTION_TRACER) += trace/
 obj-$(CONFIG_TRACING) += trace/
 obj-$(CONFIG_SMP) += sched_cpupri.o
+obj-$(CONFIG_SLOW_WORK) += slow-work.o
 
 ifneq ($(CONFIG_SCHED_OMIT_FRAME_POINTER),y)
 # According to Alan Modra <alan@linuxcare.com.au>, the -fno-omit-frame-pointer is
diff --git a/kernel/async.c b/kernel/async.c
index f565891f2c9..968ef9457d4 100644
--- a/kernel/async.c
+++ b/kernel/async.c
@@ -49,6 +49,7 @@ asynchronous and synchronous parts of the kernel.
 */
 
 #include <linux/async.h>
+#include <linux/bug.h>
 #include <linux/module.h>
 #include <linux/wait.h>
 #include <linux/sched.h>
@@ -387,20 +388,11 @@ static int async_manager_thread(void *unused)
 
 static int __init async_init(void)
 {
-	if (async_enabled)
-		if (IS_ERR(kthread_run(async_manager_thread, NULL,
-				       "async/mgr")))
-			async_enabled = 0;
-	return 0;
-}
+	async_enabled =
+		!IS_ERR(kthread_run(async_manager_thread, NULL, "async/mgr"));
 
-static int __init setup_async(char *str)
-{
-	async_enabled = 1;
-	return 1;
+	WARN_ON(!async_enabled);
+	return 0;
 }
 
-__setup("fastboot", setup_async);
-
-
 core_initcall(async_init);
diff --git a/kernel/audit.c b/kernel/audit.c
index ce6d8ea3131..9442c3533ba 100644
--- a/kernel/audit.c
+++ b/kernel/audit.c
@@ -766,6 +766,9 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
 
 				audit_log_format(ab, " msg=");
 				size = nlmsg_len(nlh);
+				if (size > 0 &&
+				    ((unsigned char *)data)[size - 1] == '\0')
+					size--;
 				audit_log_n_untrustedstring(ab, data, size);
 			}
 			audit_set_pid(ab, pid);
@@ -1382,7 +1385,7 @@ void audit_log_n_string(struct audit_buffer *ab, const char *string,
 int audit_string_contains_control(const char *string, size_t len)
 {
 	const unsigned char *p;
-	for (p = string; p < (const unsigned char *)string + len && *p; p++) {
+	for (p = string; p < (const unsigned char *)string + len; p++) {
 		if (*p == '"' || *p < 0x21 || *p > 0x7e)
 			return 1;
 	}
@@ -1437,13 +1440,13 @@ void audit_log_d_path(struct audit_buffer *ab, const char *prefix,
 	/* We will allow 11 spaces for ' (deleted)' to be appended */
 	pathname = kmalloc(PATH_MAX+11, ab->gfp_mask);
 	if (!pathname) {
-		audit_log_format(ab, "<no memory>");
+		audit_log_string(ab, "<no_memory>");
 		return;
 	}
 	p = d_path(path, pathname, PATH_MAX+11);
 	if (IS_ERR(p)) { /* Should never happen since we send PATH_MAX */
 		/* FIXME: can we save some information here? */
-		audit_log_format(ab, "<too long>");
+		audit_log_string(ab, "<too_long>");
 	} else
 		audit_log_untrustedstring(ab, p);
 	kfree(pathname);
diff --git a/kernel/audit_tree.c b/kernel/audit_tree.c
index 8ad9545b8db..917ab952556 100644
--- a/kernel/audit_tree.c
+++ b/kernel/audit_tree.c
@@ -385,6 +385,7 @@ static int tag_chunk(struct inode *inode, struct audit_tree *tree)
 	mutex_lock(&inode->inotify_mutex);
 	if (inotify_clone_watch(&old->watch, &chunk->watch) < 0) {
 		mutex_unlock(&inode->inotify_mutex);
+		put_inotify_watch(&old->watch);
 		free_chunk(chunk);
 		return -ENOSPC;
 	}
@@ -394,6 +395,7 @@ static int tag_chunk(struct inode *inode, struct audit_tree *tree)
 		chunk->dead = 1;
 		inotify_evict_watch(&chunk->watch);
 		mutex_unlock(&inode->inotify_mutex);
+		put_inotify_watch(&old->watch);
 		put_inotify_watch(&chunk->watch);
 		return 0;
 	}
diff --git a/kernel/auditfilter.c b/kernel/auditfilter.c
index fbf24d121d9..a6fe71fd5d1 100644
--- a/kernel/auditfilter.c
+++ b/kernel/auditfilter.c
@@ -135,18 +135,18 @@ static void audit_remove_watch(struct audit_watch *watch)
 static inline void audit_free_rule(struct audit_entry *e)
 {
 	int i;
-
+	struct audit_krule *erule = &e->rule;
 	/* some rules don't have associated watches */
-	if (e->rule.watch)
-		audit_put_watch(e->rule.watch);
-	if (e->rule.fields)
-		for (i = 0; i < e->rule.field_count; i++) {
-			struct audit_field *f = &e->rule.fields[i];
+	if (erule->watch)
+		audit_put_watch(erule->watch);
+	if (erule->fields)
+		for (i = 0; i < erule->field_count; i++) {
+			struct audit_field *f = &erule->fields[i];
 			kfree(f->lsm_str);
 			security_audit_rule_free(f->lsm_rule);
 		}
-	kfree(e->rule.fields);
-	kfree(e->rule.filterkey);
+	kfree(erule->fields);
+	kfree(erule->filterkey);
 	kfree(e);
 }
 
diff --git a/kernel/auditsc.c b/kernel/auditsc.c
index 8cbddff6c28..7d6ac7c1f41 100644
--- a/kernel/auditsc.c
+++ b/kernel/auditsc.c
@@ -66,6 +66,7 @@
 #include <linux/syscalls.h>
 #include <linux/inotify.h>
 #include <linux/capability.h>
+#include <linux/fs_struct.h>
 
 #include "audit.h"
 
@@ -328,6 +329,14 @@ static int audit_match_filetype(struct audit_context *ctx, int which)
  */
 
 #ifdef CONFIG_AUDIT_TREE
+static void audit_set_auditable(struct audit_context *ctx)
+{
+	if (!ctx->prio) {
+		ctx->prio = 1;
+		ctx->current_state = AUDIT_RECORD_CONTEXT;
+	}
+}
+
 static int put_tree_ref(struct audit_context *ctx, struct audit_chunk *chunk)
 {
 	struct audit_tree_refs *p = ctx->trees;
@@ -741,17 +750,9 @@ void audit_filter_inodes(struct task_struct *tsk, struct audit_context *ctx)
 	rcu_read_unlock();
 }
 
-static void audit_set_auditable(struct audit_context *ctx)
-{
-	if (!ctx->prio) {
-		ctx->prio = 1;
-		ctx->current_state = AUDIT_RECORD_CONTEXT;
-	}
-}
-
 static inline struct audit_context *audit_get_context(struct task_struct *tsk,
 						      int return_valid,
-						      int return_code)
+						      long return_code)
 {
 	struct audit_context *context = tsk->audit_context;
 
@@ -1023,7 +1024,7 @@ static int audit_log_single_execve_arg(struct audit_context *context,
 {
 	char arg_num_len_buf[12];
 	const char __user *tmp_p = p;
-	/* how many digits are in arg_num? 3 is the length of a=\n */
+	/* how many digits are in arg_num? 3 is the length of " a=" */
 	size_t arg_num_len = snprintf(arg_num_len_buf, 12, "%d", arg_num) + 3;
 	size_t len, len_left, to_send;
 	size_t max_execve_audit_len = MAX_EXECVE_AUDIT_LEN;
@@ -1109,7 +1110,7 @@ static int audit_log_single_execve_arg(struct audit_context *context,
 		 * so we can be sure nothing was lost.
 		 */
 		if ((i == 0) && (too_long))
-			audit_log_format(*ab, "a%d_len=%zu ", arg_num,
+			audit_log_format(*ab, " a%d_len=%zu", arg_num,
 					 has_cntl ? 2*len : len);
 
 		/*
@@ -1129,7 +1130,7 @@ static int audit_log_single_execve_arg(struct audit_context *context,
 		buf[to_send] = '\0';
 
 		/* actually log it */
-		audit_log_format(*ab, "a%d", arg_num);
+		audit_log_format(*ab, " a%d", arg_num);
 		if (too_long)
 			audit_log_format(*ab, "[%d]", i);
 		audit_log_format(*ab, "=");
@@ -1137,7 +1138,6 @@ static int audit_log_single_execve_arg(struct audit_context *context,
 			audit_log_n_hex(*ab, buf, to_send);
 		else
 			audit_log_format(*ab, "\"%s\"", buf);
-		audit_log_format(*ab, "\n");
 
 		p += to_send;
 		len_left -= to_send;
@@ -1165,7 +1165,7 @@ static void audit_log_execve_info(struct audit_context *context,
 
 	p = (const char __user *)axi->mm->arg_start;
 
-	audit_log_format(*ab, "argc=%d ", axi->argc);
+	audit_log_format(*ab, "argc=%d", axi->argc);
 
 	/*
 	 * we need some kernel buffer to hold the userspace args.  Just
@@ -1478,7 +1478,7 @@ static void audit_log_exit(struct audit_context *context, struct task_struct *ts
 			case 0:
 				/* name was specified as a relative path and the
 				 * directory component is the cwd */
-				audit_log_d_path(ab, " name=", &context->pwd);
+				audit_log_d_path(ab, "name=", &context->pwd);
 				break;
 			default:
 				/* log the name's directory component */
@@ -2149,7 +2149,7 @@ int audit_set_loginuid(struct task_struct *task, uid_t loginuid)
  * __audit_mq_open - record audit data for a POSIX MQ open
  * @oflag: open flag
  * @mode: mode bits
- * @u_attr: queue attributes
+ * @attr: queue attributes
  *
  */
 void __audit_mq_open(int oflag, mode_t mode, struct mq_attr *attr)
@@ -2196,7 +2196,7 @@ void __audit_mq_sendrecv(mqd_t mqdes, size_t msg_len, unsigned int msg_prio,
 /**
  * __audit_mq_notify - record audit data for a POSIX MQ notify
  * @mqdes: MQ descriptor
- * @u_notification: Notification event
+ * @notification: Notification event
  *
  */
 
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 9edb5c4b79b..382109b5bae 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -94,7 +94,6 @@ struct cgroupfs_root {
 	char release_agent_path[PATH_MAX];
 };
 
-
 /*
  * The "rootnode" hierarchy is the "dummy hierarchy", reserved for the
  * subsystems that are otherwise unattached - it never has more than a
@@ -102,6 +101,39 @@ struct cgroupfs_root {
  */
 static struct cgroupfs_root rootnode;
 
+/*
+ * CSS ID -- ID per subsys's Cgroup Subsys State(CSS). used only when
+ * cgroup_subsys->use_id != 0.
+ */
+#define CSS_ID_MAX	(65535)
+struct css_id {
+	/*
+	 * The css to which this ID points. This pointer is set to valid value
+	 * after cgroup is populated. If cgroup is removed, this will be NULL.
+	 * This pointer is expected to be RCU-safe because destroy()
+	 * is called after synchronize_rcu(). But for safe use, css_is_removed()
+	 * css_tryget() should be used for avoiding race.
+	 */
+	struct cgroup_subsys_state *css;
+	/*
+	 * ID of this css.
+	 */
+	unsigned short id;
+	/*
+	 * Depth in hierarchy which this ID belongs to.
+	 */
+	unsigned short depth;
+	/*
+	 * ID is freed by RCU. (and lookup routine is RCU safe.)
+	 */
+	struct rcu_head rcu_head;
+	/*
+	 * Hierarchy of CSS ID belongs to.
+	 */
+	unsigned short stack[0]; /* Array of Length (depth+1) */
+};
+
+
 /* The list of hierarchy roots */
 
 static LIST_HEAD(roots);
@@ -185,6 +217,8 @@ struct cg_cgroup_link {
 static struct css_set init_css_set;
 static struct cg_cgroup_link init_css_set_link;
 
+static int cgroup_subsys_init_idr(struct cgroup_subsys *ss);
+
 /* css_set_lock protects the list of css_set objects, and the
  * chain of tasks off each css_set.  Nests outside task->alloc_lock
  * due to cgroup_iter_start() */
@@ -567,6 +601,9 @@ static struct backing_dev_info cgroup_backing_dev_info = {
 	.capabilities	= BDI_CAP_NO_ACCT_AND_WRITEBACK,
 };
 
+static int alloc_css_id(struct cgroup_subsys *ss,
+			struct cgroup *parent, struct cgroup *child);
+
 static struct inode *cgroup_new_inode(mode_t mode, struct super_block *sb)
 {
 	struct inode *inode = new_inode(sb);
@@ -585,13 +622,18 @@ static struct inode *cgroup_new_inode(mode_t mode, struct super_block *sb)
  * Call subsys's pre_destroy handler.
  * This is called before css refcnt check.
  */
-static void cgroup_call_pre_destroy(struct cgroup *cgrp)
+static int cgroup_call_pre_destroy(struct cgroup *cgrp)
 {
 	struct cgroup_subsys *ss;
+	int ret = 0;
+
 	for_each_subsys(cgrp->root, ss)
-		if (ss->pre_destroy)
-			ss->pre_destroy(ss, cgrp);
-	return;
+		if (ss->pre_destroy) {
+			ret = ss->pre_destroy(ss, cgrp);
+			if (ret)
+				break;
+		}
+	return ret;
 }
 
 static void free_cgroup_rcu(struct rcu_head *obj)
@@ -685,6 +727,22 @@ static void cgroup_d_remove_dir(struct dentry *dentry)
 	remove_dir(dentry);
 }
 
+/*
+ * A queue for waiters to do rmdir() cgroup. A tasks will sleep when
+ * cgroup->count == 0 && list_empty(&cgroup->children) && subsys has some
+ * reference to css->refcnt. In general, this refcnt is expected to goes down
+ * to zero, soon.
+ *
+ * CGRP_WAIT_ON_RMDIR flag is modified under cgroup's inode->i_mutex;
+ */
+DECLARE_WAIT_QUEUE_HEAD(cgroup_rmdir_waitq);
+
+static void cgroup_wakeup_rmdir_waiters(const struct cgroup *cgrp)
+{
+	if (unlikely(test_bit(CGRP_WAIT_ON_RMDIR, &cgrp->flags)))
+		wake_up_all(&cgroup_rmdir_waitq);
+}
+
 static int rebind_subsystems(struct cgroupfs_root *root,
 			      unsigned long final_bits)
 {
@@ -857,16 +915,16 @@ static int cgroup_remount(struct super_block *sb, int *flags, char *data)
 	}
 
 	ret = rebind_subsystems(root, opts.subsys_bits);
+	if (ret)
+		goto out_unlock;
 
 	/* (re)populate subsystem files */
-	if (!ret)
-		cgroup_populate_dir(cgrp);
+	cgroup_populate_dir(cgrp);
 
 	if (opts.release_agent)
 		strcpy(root->release_agent_path, opts.release_agent);
  out_unlock:
-	if (opts.release_agent)
-		kfree(opts.release_agent);
+	kfree(opts.release_agent);
 	mutex_unlock(&cgroup_mutex);
 	mutex_unlock(&cgrp->dentry->d_inode->i_mutex);
 	return ret;
@@ -969,15 +1027,13 @@ static int cgroup_get_sb(struct file_system_type *fs_type,
 	/* First find the desired set of subsystems */
 	ret = parse_cgroupfs_options(data, &opts);
 	if (ret) {
-		if (opts.release_agent)
-			kfree(opts.release_agent);
+		kfree(opts.release_agent);
 		return ret;
 	}
 
 	root = kzalloc(sizeof(*root), GFP_KERNEL);
 	if (!root) {
-		if (opts.release_agent)
-			kfree(opts.release_agent);
+		kfree(opts.release_agent);
 		return -ENOMEM;
 	}
 
@@ -1071,7 +1127,8 @@ static int cgroup_get_sb(struct file_system_type *fs_type,
 		mutex_unlock(&cgroup_mutex);
 	}
 
-	return simple_set_mnt(mnt, sb);
+	simple_set_mnt(mnt, sb);
+	return 0;
 
  free_cg_links:
 	free_cg_links(&tmp_cg_links);
@@ -1279,6 +1336,12 @@ int cgroup_attach_task(struct cgroup *cgrp, struct task_struct *tsk)
 	set_bit(CGRP_RELEASABLE, &oldcgrp->flags);
 	synchronize_rcu();
 	put_css_set(cg);
+
+	/*
+	 * wake up rmdir() waiter. the rmdir should fail since the cgroup
+	 * is no longer empty.
+	 */
+	cgroup_wakeup_rmdir_waiters(cgrp);
 	return 0;
 }
 
@@ -1624,10 +1687,10 @@ static struct inode_operations cgroup_dir_inode_operations = {
 	.rename = cgroup_rename,
 };
 
-static int cgroup_create_file(struct dentry *dentry, int mode,
+static int cgroup_create_file(struct dentry *dentry, mode_t mode,
 				struct super_block *sb)
 {
-	static struct dentry_operations cgroup_dops = {
+	static const struct dentry_operations cgroup_dops = {
 		.d_iput = cgroup_diput,
 	};
 
@@ -1670,7 +1733,7 @@ static int cgroup_create_file(struct dentry *dentry, int mode,
  * @mode: mode to set on new directory.
  */
 static int cgroup_create_dir(struct cgroup *cgrp, struct dentry *dentry,
-				int mode)
+				mode_t mode)
 {
 	struct dentry *parent;
 	int error = 0;
@@ -1688,6 +1751,33 @@ static int cgroup_create_dir(struct cgroup *cgrp, struct dentry *dentry,
 	return error;
 }
 
+/**
+ * cgroup_file_mode - deduce file mode of a control file
+ * @cft: the control file in question
+ *
+ * returns cft->mode if ->mode is not 0
+ * returns S_IRUGO|S_IWUSR if it has both a read and a write handler
+ * returns S_IRUGO if it has only a read handler
+ * returns S_IWUSR if it has only a write hander
+ */
+static mode_t cgroup_file_mode(const struct cftype *cft)
+{
+	mode_t mode = 0;
+
+	if (cft->mode)
+		return cft->mode;
+
+	if (cft->read || cft->read_u64 || cft->read_s64 ||
+	    cft->read_map || cft->read_seq_string)
+		mode |= S_IRUGO;
+
+	if (cft->write || cft->write_u64 || cft->write_s64 ||
+	    cft->write_string || cft->trigger)
+		mode |= S_IWUSR;
+
+	return mode;
+}
+
 int cgroup_add_file(struct cgroup *cgrp,
 		       struct cgroup_subsys *subsys,
 		       const struct cftype *cft)
@@ -1695,6 +1785,7 @@ int cgroup_add_file(struct cgroup *cgrp,
 	struct dentry *dir = cgrp->dentry;
 	struct dentry *dentry;
 	int error;
+	mode_t mode;
 
 	char name[MAX_CGROUP_TYPE_NAMELEN + MAX_CFTYPE_NAME + 2] = { 0 };
 	if (subsys && !test_bit(ROOT_NOPREFIX, &cgrp->root->flags)) {
@@ -1705,7 +1796,8 @@ int cgroup_add_file(struct cgroup *cgrp,
 	BUG_ON(!mutex_is_locked(&dir->d_inode->i_mutex));
 	dentry = lookup_one_len(name, dir, strlen(name));
 	if (!IS_ERR(dentry)) {
-		error = cgroup_create_file(dentry, 0644 | S_IFREG,
+		mode = cgroup_file_mode(cft);
+		error = cgroup_create_file(dentry, mode | S_IFREG,
 						cgrp->root->sb);
 		if (!error)
 			dentry->d_fsdata = (void *)cft;
@@ -2287,6 +2379,7 @@ static struct cftype files[] = {
 		.write_u64 = cgroup_tasks_write,
 		.release = cgroup_tasks_release,
 		.private = FILE_TASKLIST,
+		.mode = S_IRUGO | S_IWUSR,
 	},
 
 	{
@@ -2326,6 +2419,17 @@ static int cgroup_populate_dir(struct cgroup *cgrp)
 		if (ss->populate && (err = ss->populate(ss, cgrp)) < 0)
 			return err;
 	}
+	/* This cgroup is ready now */
+	for_each_subsys(cgrp->root, ss) {
+		struct cgroup_subsys_state *css = cgrp->subsys[ss->subsys_id];
+		/*
+		 * Update id->css pointer and make this css visible from
+		 * CSS ID functions. This pointer will be dereferened
+		 * from RCU-read-side without locks.
+		 */
+		if (css->id)
+			rcu_assign_pointer(css->id->css, css);
+	}
 
 	return 0;
 }
@@ -2337,6 +2441,7 @@ static void init_cgroup_css(struct cgroup_subsys_state *css,
 	css->cgroup = cgrp;
 	atomic_set(&css->refcnt, 1);
 	css->flags = 0;
+	css->id = NULL;
 	if (cgrp == dummytop)
 		set_bit(CSS_ROOT, &css->flags);
 	BUG_ON(cgrp->subsys[ss->subsys_id]);
@@ -2375,7 +2480,7 @@ static void cgroup_unlock_hierarchy(struct cgroupfs_root *root)
  * Must be called with the mutex on the parent inode held
  */
 static long cgroup_create(struct cgroup *parent, struct dentry *dentry,
-			     int mode)
+			     mode_t mode)
 {
 	struct cgroup *cgrp;
 	struct cgroupfs_root *root = parent->root;
@@ -2412,6 +2517,10 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry,
 			goto err_destroy;
 		}
 		init_cgroup_css(css, ss, cgrp);
+		if (ss->use_id)
+			if (alloc_css_id(ss, parent, cgrp))
+				goto err_destroy;
+		/* At error, ->destroy() callback has to free assigned ID. */
 	}
 
 	cgroup_lock_hierarchy(root);
@@ -2554,9 +2663,11 @@ static int cgroup_rmdir(struct inode *unused_dir, struct dentry *dentry)
 	struct cgroup *cgrp = dentry->d_fsdata;
 	struct dentry *d;
 	struct cgroup *parent;
+	DEFINE_WAIT(wait);
+	int ret;
 
 	/* the vfs holds both inode->i_mutex already */
-
+again:
 	mutex_lock(&cgroup_mutex);
 	if (atomic_read(&cgrp->count) != 0) {
 		mutex_unlock(&cgroup_mutex);
@@ -2572,17 +2683,39 @@ static int cgroup_rmdir(struct inode *unused_dir, struct dentry *dentry)
 	 * Call pre_destroy handlers of subsys. Notify subsystems
 	 * that rmdir() request comes.
 	 */
-	cgroup_call_pre_destroy(cgrp);
+	ret = cgroup_call_pre_destroy(cgrp);
+	if (ret)
+		return ret;
 
 	mutex_lock(&cgroup_mutex);
 	parent = cgrp->parent;
-
-	if (atomic_read(&cgrp->count)
-	    || !list_empty(&cgrp->children)
-	    || !cgroup_clear_css_refs(cgrp)) {
+	if (atomic_read(&cgrp->count) || !list_empty(&cgrp->children)) {
 		mutex_unlock(&cgroup_mutex);
 		return -EBUSY;
 	}
+	/*
+	 * css_put/get is provided for subsys to grab refcnt to css. In typical
+	 * case, subsystem has no reference after pre_destroy(). But, under
+	 * hierarchy management, some *temporal* refcnt can be hold.
+	 * To avoid returning -EBUSY to a user, waitqueue is used. If subsys
+	 * is really busy, it should return -EBUSY at pre_destroy(). wake_up
+	 * is called when css_put() is called and refcnt goes down to 0.
+	 */
+	set_bit(CGRP_WAIT_ON_RMDIR, &cgrp->flags);
+	prepare_to_wait(&cgroup_rmdir_waitq, &wait, TASK_INTERRUPTIBLE);
+
+	if (!cgroup_clear_css_refs(cgrp)) {
+		mutex_unlock(&cgroup_mutex);
+		schedule();
+		finish_wait(&cgroup_rmdir_waitq, &wait);
+		clear_bit(CGRP_WAIT_ON_RMDIR, &cgrp->flags);
+		if (signal_pending(current))
+			return -EINTR;
+		goto again;
+	}
+	/* NO css_tryget() can success after here. */
+	finish_wait(&cgroup_rmdir_waitq, &wait);
+	clear_bit(CGRP_WAIT_ON_RMDIR, &cgrp->flags);
 
 	spin_lock(&release_list_lock);
 	set_bit(CGRP_REMOVED, &cgrp->flags);
@@ -2707,6 +2840,8 @@ int __init cgroup_init(void)
 		struct cgroup_subsys *ss = subsys[i];
 		if (!ss->early_init)
 			cgroup_init_subsys(ss);
+		if (ss->use_id)
+			cgroup_subsys_init_idr(ss);
 	}
 
 	/* Add init_css_set to the hash table */
@@ -3083,18 +3218,19 @@ int cgroup_clone(struct task_struct *tsk, struct cgroup_subsys *subsys,
 }
 
 /**
- * cgroup_is_descendant - see if @cgrp is a descendant of current task's cgrp
+ * cgroup_is_descendant - see if @cgrp is a descendant of @task's cgrp
  * @cgrp: the cgroup in question
+ * @task: the task in question
  *
- * See if @cgrp is a descendant of the current task's cgroup in
- * the appropriate hierarchy.
+ * See if @cgrp is a descendant of @task's cgroup in the appropriate
+ * hierarchy.
  *
  * If we are sending in dummytop, then presumably we are creating
  * the top cgroup in the subsystem.
  *
  * Called only by the ns (nsproxy) cgroup.
  */
-int cgroup_is_descendant(const struct cgroup *cgrp)
+int cgroup_is_descendant(const struct cgroup *cgrp, struct task_struct *task)
 {
 	int ret;
 	struct cgroup *target;
@@ -3104,7 +3240,7 @@ int cgroup_is_descendant(const struct cgroup *cgrp)
 		return 1;
 
 	get_first_subsys(cgrp, NULL, &subsys_id);
-	target = task_cgroup(current, subsys_id);
+	target = task_cgroup(task, subsys_id);
 	while (cgrp != target && cgrp!= cgrp->top_cgroup)
 		cgrp = cgrp->parent;
 	ret = (cgrp == target);
@@ -3137,10 +3273,12 @@ void __css_put(struct cgroup_subsys_state *css)
 {
 	struct cgroup *cgrp = css->cgroup;
 	rcu_read_lock();
-	if ((atomic_dec_return(&css->refcnt) == 1) &&
-	    notify_on_release(cgrp)) {
-		set_bit(CGRP_RELEASABLE, &cgrp->flags);
-		check_for_release(cgrp);
+	if (atomic_dec_return(&css->refcnt) == 1) {
+		if (notify_on_release(cgrp)) {
+			set_bit(CGRP_RELEASABLE, &cgrp->flags);
+			check_for_release(cgrp);
+		}
+		cgroup_wakeup_rmdir_waiters(cgrp);
 	}
 	rcu_read_unlock();
 }
@@ -3240,3 +3378,232 @@ static int __init cgroup_disable(char *str)
 	return 1;
 }
 __setup("cgroup_disable=", cgroup_disable);
+
+/*
+ * Functons for CSS ID.
+ */
+
+/*
+ *To get ID other than 0, this should be called when !cgroup_is_removed().
+ */
+unsigned short css_id(struct cgroup_subsys_state *css)
+{
+	struct css_id *cssid = rcu_dereference(css->id);
+
+	if (cssid)
+		return cssid->id;
+	return 0;
+}
+
+unsigned short css_depth(struct cgroup_subsys_state *css)
+{
+	struct css_id *cssid = rcu_dereference(css->id);
+
+	if (cssid)
+		return cssid->depth;
+	return 0;
+}
+
+bool css_is_ancestor(struct cgroup_subsys_state *child,
+		    const struct cgroup_subsys_state *root)
+{
+	struct css_id *child_id = rcu_dereference(child->id);
+	struct css_id *root_id = rcu_dereference(root->id);
+
+	if (!child_id || !root_id || (child_id->depth < root_id->depth))
+		return false;
+	return child_id->stack[root_id->depth] == root_id->id;
+}
+
+static void __free_css_id_cb(struct rcu_head *head)
+{
+	struct css_id *id;
+
+	id = container_of(head, struct css_id, rcu_head);
+	kfree(id);
+}
+
+void free_css_id(struct cgroup_subsys *ss, struct cgroup_subsys_state *css)
+{
+	struct css_id *id = css->id;
+	/* When this is called before css_id initialization, id can be NULL */
+	if (!id)
+		return;
+
+	BUG_ON(!ss->use_id);
+
+	rcu_assign_pointer(id->css, NULL);
+	rcu_assign_pointer(css->id, NULL);
+	spin_lock(&ss->id_lock);
+	idr_remove(&ss->idr, id->id);
+	spin_unlock(&ss->id_lock);
+	call_rcu(&id->rcu_head, __free_css_id_cb);
+}
+
+/*
+ * This is called by init or create(). Then, calls to this function are
+ * always serialized (By cgroup_mutex() at create()).
+ */
+
+static struct css_id *get_new_cssid(struct cgroup_subsys *ss, int depth)
+{
+	struct css_id *newid;
+	int myid, error, size;
+
+	BUG_ON(!ss->use_id);
+
+	size = sizeof(*newid) + sizeof(unsigned short) * (depth + 1);
+	newid = kzalloc(size, GFP_KERNEL);
+	if (!newid)
+		return ERR_PTR(-ENOMEM);
+	/* get id */
+	if (unlikely(!idr_pre_get(&ss->idr, GFP_KERNEL))) {
+		error = -ENOMEM;
+		goto err_out;
+	}
+	spin_lock(&ss->id_lock);
+	/* Don't use 0. allocates an ID of 1-65535 */
+	error = idr_get_new_above(&ss->idr, newid, 1, &myid);
+	spin_unlock(&ss->id_lock);
+
+	/* Returns error when there are no free spaces for new ID.*/
+	if (error) {
+		error = -ENOSPC;
+		goto err_out;
+	}
+	if (myid > CSS_ID_MAX)
+		goto remove_idr;
+
+	newid->id = myid;
+	newid->depth = depth;
+	return newid;
+remove_idr:
+	error = -ENOSPC;
+	spin_lock(&ss->id_lock);
+	idr_remove(&ss->idr, myid);
+	spin_unlock(&ss->id_lock);
+err_out:
+	kfree(newid);
+	return ERR_PTR(error);
+
+}
+
+static int __init cgroup_subsys_init_idr(struct cgroup_subsys *ss)
+{
+	struct css_id *newid;
+	struct cgroup_subsys_state *rootcss;
+
+	spin_lock_init(&ss->id_lock);
+	idr_init(&ss->idr);
+
+	rootcss = init_css_set.subsys[ss->subsys_id];
+	newid = get_new_cssid(ss, 0);
+	if (IS_ERR(newid))
+		return PTR_ERR(newid);
+
+	newid->stack[0] = newid->id;
+	newid->css = rootcss;
+	rootcss->id = newid;
+	return 0;
+}
+
+static int alloc_css_id(struct cgroup_subsys *ss, struct cgroup *parent,
+			struct cgroup *child)
+{
+	int subsys_id, i, depth = 0;
+	struct cgroup_subsys_state *parent_css, *child_css;
+	struct css_id *child_id, *parent_id = NULL;
+
+	subsys_id = ss->subsys_id;
+	parent_css = parent->subsys[subsys_id];
+	child_css = child->subsys[subsys_id];
+	depth = css_depth(parent_css) + 1;
+	parent_id = parent_css->id;
+
+	child_id = get_new_cssid(ss, depth);
+	if (IS_ERR(child_id))
+		return PTR_ERR(child_id);
+
+	for (i = 0; i < depth; i++)
+		child_id->stack[i] = parent_id->stack[i];
+	child_id->stack[depth] = child_id->id;
+	/*
+	 * child_id->css pointer will be set after this cgroup is available
+	 * see cgroup_populate_dir()
+	 */
+	rcu_assign_pointer(child_css->id, child_id);
+
+	return 0;
+}
+
+/**
+ * css_lookup - lookup css by id
+ * @ss: cgroup subsys to be looked into.
+ * @id: the id
+ *
+ * Returns pointer to cgroup_subsys_state if there is valid one with id.
+ * NULL if not. Should be called under rcu_read_lock()
+ */
+struct cgroup_subsys_state *css_lookup(struct cgroup_subsys *ss, int id)
+{
+	struct css_id *cssid = NULL;
+
+	BUG_ON(!ss->use_id);
+	cssid = idr_find(&ss->idr, id);
+
+	if (unlikely(!cssid))
+		return NULL;
+
+	return rcu_dereference(cssid->css);
+}
+
+/**
+ * css_get_next - lookup next cgroup under specified hierarchy.
+ * @ss: pointer to subsystem
+ * @id: current position of iteration.
+ * @root: pointer to css. search tree under this.
+ * @foundid: position of found object.
+ *
+ * Search next css under the specified hierarchy of rootid. Calling under
+ * rcu_read_lock() is necessary. Returns NULL if it reaches the end.
+ */
+struct cgroup_subsys_state *
+css_get_next(struct cgroup_subsys *ss, int id,
+	     struct cgroup_subsys_state *root, int *foundid)
+{
+	struct cgroup_subsys_state *ret = NULL;
+	struct css_id *tmp;
+	int tmpid;
+	int rootid = css_id(root);
+	int depth = css_depth(root);
+
+	if (!rootid)
+		return NULL;
+
+	BUG_ON(!ss->use_id);
+	/* fill start point for scan */
+	tmpid = id;
+	while (1) {
+		/*
+		 * scan next entry from bitmap(tree), tmpid is updated after
+		 * idr_get_next().
+		 */
+		spin_lock(&ss->id_lock);
+		tmp = idr_get_next(&ss->idr, &tmpid);
+		spin_unlock(&ss->id_lock);
+
+		if (!tmp)
+			break;
+		if (tmp->depth >= depth && tmp->stack[depth] == rootid) {
+			ret = rcu_dereference(tmp->css);
+			if (ret) {
+				*foundid = tmpid;
+				break;
+			}
+		}
+		/* continue to scan from next id */
+		tmpid = tmpid + 1;
+	}
+	return ret;
+}
+
diff --git a/kernel/cgroup_debug.c b/kernel/cgroup_debug.c
index daca6209202..0c92d797baa 100644
--- a/kernel/cgroup_debug.c
+++ b/kernel/cgroup_debug.c
@@ -40,9 +40,7 @@ static u64 taskcount_read(struct cgroup *cont, struct cftype *cft)
 {
 	u64 count;
 
-	cgroup_lock();
 	count = cgroup_task_count(cont);
-	cgroup_unlock();
 	return count;
 }
 
diff --git a/kernel/cpu.c b/kernel/cpu.c
index 79e40f00dcb..395b6974dc8 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -281,7 +281,7 @@ int __ref cpu_down(unsigned int cpu)
 		goto out;
 	}
 
-	cpu_clear(cpu, cpu_active_map);
+	set_cpu_active(cpu, false);
 
 	/*
 	 * Make sure the all cpus did the reschedule and are not
@@ -296,7 +296,7 @@ int __ref cpu_down(unsigned int cpu)
 	err = _cpu_down(cpu, 0);
 
 	if (cpu_online(cpu))
-		cpu_set(cpu, cpu_active_map);
+		set_cpu_active(cpu, true);
 
 out:
 	cpu_maps_update_done();
@@ -333,7 +333,7 @@ static int __cpuinit _cpu_up(unsigned int cpu, int tasks_frozen)
 		goto out_notify;
 	BUG_ON(!cpu_online(cpu));
 
-	cpu_set(cpu, cpu_active_map);
+	set_cpu_active(cpu, true);
 
 	/* Now call notifier in preparation. */
 	raw_notifier_call_chain(&cpu_chain, CPU_ONLINE | mod, hcpu);
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index f76db9dcaa0..026faccca86 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -128,10 +128,6 @@ static inline struct cpuset *task_cs(struct task_struct *task)
 	return container_of(task_subsys_state(task, cpuset_subsys_id),
 			    struct cpuset, css);
 }
-struct cpuset_hotplug_scanner {
-	struct cgroup_scanner scan;
-	struct cgroup *to;
-};
 
 /* bits in struct cpuset flags field */
 typedef enum {
@@ -521,6 +517,7 @@ static int validate_change(const struct cpuset *cur, const struct cpuset *trial)
 	return 0;
 }
 
+#ifdef CONFIG_SMP
 /*
  * Helper routine for generate_sched_domains().
  * Do cpusets a, b have overlapping cpus_allowed masks?
@@ -815,6 +812,18 @@ static void do_rebuild_sched_domains(struct work_struct *unused)
 
 	put_online_cpus();
 }
+#else /* !CONFIG_SMP */
+static void do_rebuild_sched_domains(struct work_struct *unused)
+{
+}
+
+static int generate_sched_domains(struct cpumask **domains,
+			struct sched_domain_attr **attributes)
+{
+	*domains = NULL;
+	return 1;
+}
+#endif /* CONFIG_SMP */
 
 static DECLARE_WORK(rebuild_sched_domains_work, do_rebuild_sched_domains);
 
@@ -1026,101 +1035,70 @@ static void cpuset_migrate_mm(struct mm_struct *mm, const nodemask_t *from,
 	mutex_unlock(&callback_mutex);
 }
 
+/*
+ * Rebind task's vmas to cpuset's new mems_allowed, and migrate pages to new
+ * nodes if memory_migrate flag is set. Called with cgroup_mutex held.
+ */
+static void cpuset_change_nodemask(struct task_struct *p,
+				   struct cgroup_scanner *scan)
+{
+	struct mm_struct *mm;
+	struct cpuset *cs;
+	int migrate;
+	const nodemask_t *oldmem = scan->data;
+
+	mm = get_task_mm(p);
+	if (!mm)
+		return;
+
+	cs = cgroup_cs(scan->cg);
+	migrate = is_memory_migrate(cs);
+
+	mpol_rebind_mm(mm, &cs->mems_allowed);
+	if (migrate)
+		cpuset_migrate_mm(mm, oldmem, &cs->mems_allowed);
+	mmput(mm);
+}
+
 static void *cpuset_being_rebound;
 
 /**
  * update_tasks_nodemask - Update the nodemasks of tasks in the cpuset.
  * @cs: the cpuset in which each task's mems_allowed mask needs to be changed
  * @oldmem: old mems_allowed of cpuset cs
+ * @heap: if NULL, defer allocating heap memory to cgroup_scan_tasks()
  *
  * Called with cgroup_mutex held
- * Return 0 if successful, -errno if not.
+ * No return value. It's guaranteed that cgroup_scan_tasks() always returns 0
+ * if @heap != NULL.
  */
-static int update_tasks_nodemask(struct cpuset *cs, const nodemask_t *oldmem)
+static void update_tasks_nodemask(struct cpuset *cs, const nodemask_t *oldmem,
+				 struct ptr_heap *heap)
 {
-	struct task_struct *p;
-	struct mm_struct **mmarray;
-	int i, n, ntasks;
-	int migrate;
-	int fudge;
-	struct cgroup_iter it;
-	int retval;
+	struct cgroup_scanner scan;
 
 	cpuset_being_rebound = cs;		/* causes mpol_dup() rebind */
 
-	fudge = 10;				/* spare mmarray[] slots */
-	fudge += cpumask_weight(cs->cpus_allowed);/* imagine 1 fork-bomb/cpu */
-	retval = -ENOMEM;
-
-	/*
-	 * Allocate mmarray[] to hold mm reference for each task
-	 * in cpuset cs.  Can't kmalloc GFP_KERNEL while holding
-	 * tasklist_lock.  We could use GFP_ATOMIC, but with a
-	 * few more lines of code, we can retry until we get a big
-	 * enough mmarray[] w/o using GFP_ATOMIC.
-	 */
-	while (1) {
-		ntasks = cgroup_task_count(cs->css.cgroup);  /* guess */
-		ntasks += fudge;
-		mmarray = kmalloc(ntasks * sizeof(*mmarray), GFP_KERNEL);
-		if (!mmarray)
-			goto done;
-		read_lock(&tasklist_lock);		/* block fork */
-		if (cgroup_task_count(cs->css.cgroup) <= ntasks)
-			break;				/* got enough */
-		read_unlock(&tasklist_lock);		/* try again */
-		kfree(mmarray);
-	}
-
-	n = 0;
-
-	/* Load up mmarray[] with mm reference for each task in cpuset. */
-	cgroup_iter_start(cs->css.cgroup, &it);
-	while ((p = cgroup_iter_next(cs->css.cgroup, &it))) {
-		struct mm_struct *mm;
-
-		if (n >= ntasks) {
-			printk(KERN_WARNING
-				"Cpuset mempolicy rebind incomplete.\n");
-			break;
-		}
-		mm = get_task_mm(p);
-		if (!mm)
-			continue;
-		mmarray[n++] = mm;
-	}
-	cgroup_iter_end(cs->css.cgroup, &it);
-	read_unlock(&tasklist_lock);
+	scan.cg = cs->css.cgroup;
+	scan.test_task = NULL;
+	scan.process_task = cpuset_change_nodemask;
+	scan.heap = heap;
+	scan.data = (nodemask_t *)oldmem;
 
 	/*
-	 * Now that we've dropped the tasklist spinlock, we can
-	 * rebind the vma mempolicies of each mm in mmarray[] to their
-	 * new cpuset, and release that mm.  The mpol_rebind_mm()
-	 * call takes mmap_sem, which we couldn't take while holding
-	 * tasklist_lock.  Forks can happen again now - the mpol_dup()
-	 * cpuset_being_rebound check will catch such forks, and rebind
-	 * their vma mempolicies too.  Because we still hold the global
-	 * cgroup_mutex, we know that no other rebind effort will
-	 * be contending for the global variable cpuset_being_rebound.
+	 * The mpol_rebind_mm() call takes mmap_sem, which we couldn't
+	 * take while holding tasklist_lock.  Forks can happen - the
+	 * mpol_dup() cpuset_being_rebound check will catch such forks,
+	 * and rebind their vma mempolicies too.  Because we still hold
+	 * the global cgroup_mutex, we know that no other rebind effort
+	 * will be contending for the global variable cpuset_being_rebound.
 	 * It's ok if we rebind the same mm twice; mpol_rebind_mm()
 	 * is idempotent.  Also migrate pages in each mm to new nodes.
 	 */
-	migrate = is_memory_migrate(cs);
-	for (i = 0; i < n; i++) {
-		struct mm_struct *mm = mmarray[i];
-
-		mpol_rebind_mm(mm, &cs->mems_allowed);
-		if (migrate)
-			cpuset_migrate_mm(mm, oldmem, &cs->mems_allowed);
-		mmput(mm);
-	}
+	cgroup_scan_tasks(&scan);
 
 	/* We're done rebinding vmas to this cpuset's new mems_allowed. */
-	kfree(mmarray);
 	cpuset_being_rebound = NULL;
-	retval = 0;
-done:
-	return retval;
 }
 
 /*
@@ -1141,6 +1119,7 @@ static int update_nodemask(struct cpuset *cs, struct cpuset *trialcs,
 {
 	nodemask_t oldmem;
 	int retval;
+	struct ptr_heap heap;
 
 	/*
 	 * top_cpuset.mems_allowed tracks node_stats[N_HIGH_MEMORY];
@@ -1175,12 +1154,18 @@ static int update_nodemask(struct cpuset *cs, struct cpuset *trialcs,
 	if (retval < 0)
 		goto done;
 
+	retval = heap_init(&heap, PAGE_SIZE, GFP_KERNEL, NULL);
+	if (retval < 0)
+		goto done;
+
 	mutex_lock(&callback_mutex);
 	cs->mems_allowed = trialcs->mems_allowed;
 	cs->mems_generation = cpuset_mems_generation++;
 	mutex_unlock(&callback_mutex);
 
-	retval = update_tasks_nodemask(cs, &oldmem);
+	update_tasks_nodemask(cs, &oldmem, &heap);
+
+	heap_free(&heap);
 done:
 	return retval;
 }
@@ -1192,8 +1177,10 @@ int current_cpuset_is_being_rebound(void)
 
 static int update_relax_domain_level(struct cpuset *cs, s64 val)
 {
+#ifdef CONFIG_SMP
 	if (val < -1 || val >= SD_LV_MAX)
 		return -EINVAL;
+#endif
 
 	if (val != cs->relax_domain_level) {
 		cs->relax_domain_level = val;
@@ -1355,19 +1342,22 @@ static int cpuset_can_attach(struct cgroup_subsys *ss,
 			     struct cgroup *cont, struct task_struct *tsk)
 {
 	struct cpuset *cs = cgroup_cs(cont);
-	int ret = 0;
 
 	if (cpumask_empty(cs->cpus_allowed) || nodes_empty(cs->mems_allowed))
 		return -ENOSPC;
 
-	if (tsk->flags & PF_THREAD_BOUND) {
-		mutex_lock(&callback_mutex);
-		if (!cpumask_equal(&tsk->cpus_allowed, cs->cpus_allowed))
-			ret = -EINVAL;
-		mutex_unlock(&callback_mutex);
-	}
+	/*
+	 * Kthreads bound to specific cpus cannot be moved to a new cpuset; we
+	 * cannot change their cpu affinity and isolating such threads by their
+	 * set of allowed nodes is unnecessary.  Thus, cpusets are not
+	 * applicable for such threads.  This prevents checking for success of
+	 * set_cpus_allowed_ptr() on all attached tasks before cpus_allowed may
+	 * be changed.
+	 */
+	if (tsk->flags & PF_THREAD_BOUND)
+		return -EINVAL;
 
-	return ret < 0 ? ret : security_task_setscheduler(tsk, 0, NULL);
+	return security_task_setscheduler(tsk, 0, NULL);
 }
 
 static void cpuset_attach(struct cgroup_subsys *ss,
@@ -1706,6 +1696,7 @@ static struct cftype files[] = {
 		.read_u64 = cpuset_read_u64,
 		.write_u64 = cpuset_write_u64,
 		.private = FILE_MEMORY_PRESSURE,
+		.mode = S_IRUGO,
 	},
 
 	{
@@ -1913,10 +1904,9 @@ int __init cpuset_init(void)
 static void cpuset_do_move_task(struct task_struct *tsk,
 				struct cgroup_scanner *scan)
 {
-	struct cpuset_hotplug_scanner *chsp;
+	struct cgroup *new_cgroup = scan->data;
 
-	chsp = container_of(scan, struct cpuset_hotplug_scanner, scan);
-	cgroup_attach_task(chsp->to, tsk);
+	cgroup_attach_task(new_cgroup, tsk);
 }
 
 /**
@@ -1932,15 +1922,15 @@ static void cpuset_do_move_task(struct task_struct *tsk,
  */
 static void move_member_tasks_to_cpuset(struct cpuset *from, struct cpuset *to)
 {
-	struct cpuset_hotplug_scanner scan;
+	struct cgroup_scanner scan;
 
-	scan.scan.cg = from->css.cgroup;
-	scan.scan.test_task = NULL; /* select all tasks in cgroup */
-	scan.scan.process_task = cpuset_do_move_task;
-	scan.scan.heap = NULL;
-	scan.to = to->css.cgroup;
+	scan.cg = from->css.cgroup;
+	scan.test_task = NULL; /* select all tasks in cgroup */
+	scan.process_task = cpuset_do_move_task;
+	scan.heap = NULL;
+	scan.data = to->css.cgroup;
 
-	if (cgroup_scan_tasks(&scan.scan))
+	if (cgroup_scan_tasks(&scan))
 		printk(KERN_ERR "move_member_tasks_to_cpuset: "
 				"cgroup_scan_tasks failed\n");
 }
@@ -2033,7 +2023,7 @@ static void scan_for_empty_cpusets(struct cpuset *root)
 			remove_tasks_in_empty_cpuset(cp);
 		else {
 			update_tasks_cpumask(cp, NULL);
-			update_tasks_nodemask(cp, &oldmems);
+			update_tasks_nodemask(cp, &oldmems, NULL);
 		}
 	}
 }
@@ -2069,7 +2059,9 @@ static int cpuset_track_online_cpus(struct notifier_block *unused_nb,
 	}
 
 	cgroup_lock();
+	mutex_lock(&callback_mutex);
 	cpumask_copy(top_cpuset.cpus_allowed, cpu_online_mask);
+	mutex_unlock(&callback_mutex);
 	scan_for_empty_cpusets(&top_cpuset);
 	ndoms = generate_sched_domains(&doms, &attr);
 	cgroup_unlock();
@@ -2092,11 +2084,12 @@ static int cpuset_track_online_nodes(struct notifier_block *self,
 	cgroup_lock();
 	switch (action) {
 	case MEM_ONLINE:
-		top_cpuset.mems_allowed = node_states[N_HIGH_MEMORY];
-		break;
 	case MEM_OFFLINE:
+		mutex_lock(&callback_mutex);
 		top_cpuset.mems_allowed = node_states[N_HIGH_MEMORY];
-		scan_for_empty_cpusets(&top_cpuset);
+		mutex_unlock(&callback_mutex);
+		if (action == MEM_OFFLINE)
+			scan_for_empty_cpusets(&top_cpuset);
 		break;
 	default:
 		break;
@@ -2206,26 +2199,24 @@ static const struct cpuset *nearest_hardwall_ancestor(const struct cpuset *cs)
 }
 
 /**
- * cpuset_zone_allowed_softwall - Can we allocate on zone z's memory node?
- * @z: is this zone on an allowed node?
+ * cpuset_node_allowed_softwall - Can we allocate on a memory node?
+ * @node: is this an allowed node?
  * @gfp_mask: memory allocation flags
  *
- * If we're in interrupt, yes, we can always allocate.  If
- * __GFP_THISNODE is set, yes, we can always allocate.  If zone
- * z's node is in our tasks mems_allowed, yes.  If it's not a
- * __GFP_HARDWALL request and this zone's nodes is in the nearest
- * hardwalled cpuset ancestor to this tasks cpuset, yes.
- * If the task has been OOM killed and has access to memory reserves
- * as specified by the TIF_MEMDIE flag, yes.
+ * If we're in interrupt, yes, we can always allocate.  If __GFP_THISNODE is
+ * set, yes, we can always allocate.  If node is in our task's mems_allowed,
+ * yes.  If it's not a __GFP_HARDWALL request and this node is in the nearest
+ * hardwalled cpuset ancestor to this task's cpuset, yes.  If the task has been
+ * OOM killed and has access to memory reserves as specified by the TIF_MEMDIE
+ * flag, yes.
  * Otherwise, no.
  *
- * If __GFP_HARDWALL is set, cpuset_zone_allowed_softwall()
- * reduces to cpuset_zone_allowed_hardwall().  Otherwise,
- * cpuset_zone_allowed_softwall() might sleep, and might allow a zone
- * from an enclosing cpuset.
+ * If __GFP_HARDWALL is set, cpuset_node_allowed_softwall() reduces to
+ * cpuset_node_allowed_hardwall().  Otherwise, cpuset_node_allowed_softwall()
+ * might sleep, and might allow a node from an enclosing cpuset.
  *
- * cpuset_zone_allowed_hardwall() only handles the simpler case of
- * hardwall cpusets, and never sleeps.
+ * cpuset_node_allowed_hardwall() only handles the simpler case of hardwall
+ * cpusets, and never sleeps.
  *
  * The __GFP_THISNODE placement logic is really handled elsewhere,
  * by forcibly using a zonelist starting at a specified node, and by
@@ -2264,20 +2255,17 @@ static const struct cpuset *nearest_hardwall_ancestor(const struct cpuset *cs)
  *	GFP_USER     - only nodes in current tasks mems allowed ok.
  *
  * Rule:
- *    Don't call cpuset_zone_allowed_softwall if you can't sleep, unless you
+ *    Don't call cpuset_node_allowed_softwall if you can't sleep, unless you
  *    pass in the __GFP_HARDWALL flag set in gfp_flag, which disables
  *    the code that might scan up ancestor cpusets and sleep.
  */
-
-int __cpuset_zone_allowed_softwall(struct zone *z, gfp_t gfp_mask)
+int __cpuset_node_allowed_softwall(int node, gfp_t gfp_mask)
 {
-	int node;			/* node that zone z is on */
 	const struct cpuset *cs;	/* current cpuset ancestors */
 	int allowed;			/* is allocation in zone z allowed? */
 
 	if (in_interrupt() || (gfp_mask & __GFP_THISNODE))
 		return 1;
-	node = zone_to_nid(z);
 	might_sleep_if(!(gfp_mask & __GFP_HARDWALL));
 	if (node_isset(node, current->mems_allowed))
 		return 1;
@@ -2306,15 +2294,15 @@ int __cpuset_zone_allowed_softwall(struct zone *z, gfp_t gfp_mask)
 }
 
 /*
- * cpuset_zone_allowed_hardwall - Can we allocate on zone z's memory node?
- * @z: is this zone on an allowed node?
+ * cpuset_node_allowed_hardwall - Can we allocate on a memory node?
+ * @node: is this an allowed node?
  * @gfp_mask: memory allocation flags
  *
- * If we're in interrupt, yes, we can always allocate.
- * If __GFP_THISNODE is set, yes, we can always allocate.  If zone
- * z's node is in our tasks mems_allowed, yes.   If the task has been
- * OOM killed and has access to memory reserves as specified by the
- * TIF_MEMDIE flag, yes.  Otherwise, no.
+ * If we're in interrupt, yes, we can always allocate.  If __GFP_THISNODE is
+ * set, yes, we can always allocate.  If node is in our task's mems_allowed,
+ * yes.  If the task has been OOM killed and has access to memory reserves as
+ * specified by the TIF_MEMDIE flag, yes.
+ * Otherwise, no.
  *
  * The __GFP_THISNODE placement logic is really handled elsewhere,
  * by forcibly using a zonelist starting at a specified node, and by
@@ -2322,20 +2310,16 @@ int __cpuset_zone_allowed_softwall(struct zone *z, gfp_t gfp_mask)
  * any node on the zonelist except the first.  By the time any such
  * calls get to this routine, we should just shut up and say 'yes'.
  *
- * Unlike the cpuset_zone_allowed_softwall() variant, above,
- * this variant requires that the zone be in the current tasks
+ * Unlike the cpuset_node_allowed_softwall() variant, above,
+ * this variant requires that the node be in the current task's
  * mems_allowed or that we're in interrupt.  It does not scan up the
  * cpuset hierarchy for the nearest enclosing mem_exclusive cpuset.
  * It never sleeps.
  */
-
-int __cpuset_zone_allowed_hardwall(struct zone *z, gfp_t gfp_mask)
+int __cpuset_node_allowed_hardwall(int node, gfp_t gfp_mask)
 {
-	int node;			/* node that zone z is on */
-
 	if (in_interrupt() || (gfp_mask & __GFP_THISNODE))
 		return 1;
-	node = zone_to_nid(z);
 	if (node_isset(node, current->mems_allowed))
 		return 1;
 	/*
diff --git a/kernel/exec_domain.c b/kernel/exec_domain.c
index 667c841c295..c35452cadde 100644
--- a/kernel/exec_domain.c
+++ b/kernel/exec_domain.c
@@ -18,6 +18,7 @@
 #include <linux/syscalls.h>
 #include <linux/sysctl.h>
 #include <linux/types.h>
+#include <linux/fs_struct.h>
 
 
 static void default_handler(int, struct pt_regs *);
@@ -145,28 +146,6 @@ __set_personality(u_long personality)
 		return 0;
 	}
 
-	if (atomic_read(&current->fs->count) != 1) {
-		struct fs_struct *fsp, *ofsp;
-
-		fsp = copy_fs_struct(current->fs);
-		if (fsp == NULL) {
-			module_put(ep->module);
-			return -ENOMEM;
-		}
-
-		task_lock(current);
-		ofsp = current->fs;
-		current->fs = fsp;
-		task_unlock(current);
-
-		put_fs_struct(ofsp);
-	}
-
-	/*
-	 * At that point we are guaranteed to be the sole owner of
-	 * current->fs.
-	 */
-
 	current->personality = personality;
 	oep = current_thread_info()->exec_domain;
 	current_thread_info()->exec_domain = ep;
diff --git a/kernel/exit.c b/kernel/exit.c
index 167e1e3ad7c..32cbf2607cb 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -46,6 +46,7 @@
 #include <linux/blkdev.h>
 #include <linux/task_io_accounting_ops.h>
 #include <linux/tracehook.h>
+#include <linux/fs_struct.h>
 #include <linux/init_task.h>
 #include <trace/sched.h>
 
@@ -61,11 +62,6 @@ DEFINE_TRACE(sched_process_wait);
 
 static void exit_mm(struct task_struct * tsk);
 
-static inline int task_detached(struct task_struct *p)
-{
-	return p->exit_signal == -1;
-}
-
 static void __unhash_process(struct task_struct *p)
 {
 	nr_threads--;
@@ -362,16 +358,12 @@ static void reparent_to_kthreadd(void)
 void __set_special_pids(struct pid *pid)
 {
 	struct task_struct *curr = current->group_leader;
-	pid_t nr = pid_nr(pid);
 
-	if (task_session(curr) != pid) {
+	if (task_session(curr) != pid)
 		change_pid(curr, PIDTYPE_SID, pid);
-		set_task_session(curr, nr);
-	}
-	if (task_pgrp(curr) != pid) {
+
+	if (task_pgrp(curr) != pid)
 		change_pid(curr, PIDTYPE_PGID, pid);
-		set_task_pgrp(curr, nr);
-	}
 }
 
 static void set_special_pids(struct pid *pid)
@@ -429,7 +421,6 @@ EXPORT_SYMBOL(disallow_signal);
 void daemonize(const char *name, ...)
 {
 	va_list args;
-	struct fs_struct *fs;
 	sigset_t blocked;
 
 	va_start(args, name);
@@ -462,11 +453,7 @@ void daemonize(const char *name, ...)
 
 	/* Become as one with the init task */
 
-	exit_fs(current);	/* current->fs->count--; */
-	fs = init_task.fs;
-	current->fs = fs;
-	atomic_inc(&fs->count);
-
+	daemonize_fs_struct();
 	exit_files(current);
 	current->files = init_task.files;
 	atomic_inc(&current->files->count);
@@ -565,30 +552,6 @@ void exit_files(struct task_struct *tsk)
 	}
 }
 
-void put_fs_struct(struct fs_struct *fs)
-{
-	/* No need to hold fs->lock if we are killing it */
-	if (atomic_dec_and_test(&fs->count)) {
-		path_put(&fs->root);
-		path_put(&fs->pwd);
-		kmem_cache_free(fs_cachep, fs);
-	}
-}
-
-void exit_fs(struct task_struct *tsk)
-{
-	struct fs_struct * fs = tsk->fs;
-
-	if (fs) {
-		task_lock(tsk);
-		tsk->fs = NULL;
-		task_unlock(tsk);
-		put_fs_struct(fs);
-	}
-}
-
-EXPORT_SYMBOL_GPL(exit_fs);
-
 #ifdef CONFIG_MM_OWNER
 /*
  * Task p is exiting and it owned mm, lets find a new owner for it
@@ -732,119 +695,6 @@ static void exit_mm(struct task_struct * tsk)
 }
 
 /*
- * Return nonzero if @parent's children should reap themselves.
- *
- * Called with write_lock_irq(&tasklist_lock) held.
- */
-static int ignoring_children(struct task_struct *parent)
-{
-	int ret;
-	struct sighand_struct *psig = parent->sighand;
-	unsigned long flags;
-	spin_lock_irqsave(&psig->siglock, flags);
-	ret = (psig->action[SIGCHLD-1].sa.sa_handler == SIG_IGN ||
-	       (psig->action[SIGCHLD-1].sa.sa_flags & SA_NOCLDWAIT));
-	spin_unlock_irqrestore(&psig->siglock, flags);
-	return ret;
-}
-
-/*
- * Detach all tasks we were using ptrace on.
- * Any that need to be release_task'd are put on the @dead list.
- *
- * Called with write_lock(&tasklist_lock) held.
- */
-static void ptrace_exit(struct task_struct *parent, struct list_head *dead)
-{
-	struct task_struct *p, *n;
-	int ign = -1;
-
-	list_for_each_entry_safe(p, n, &parent->ptraced, ptrace_entry) {
-		__ptrace_unlink(p);
-
-		if (p->exit_state != EXIT_ZOMBIE)
-			continue;
-
-		/*
-		 * If it's a zombie, our attachedness prevented normal
-		 * parent notification or self-reaping.  Do notification
-		 * now if it would have happened earlier.  If it should
-		 * reap itself, add it to the @dead list.  We can't call
-		 * release_task() here because we already hold tasklist_lock.
-		 *
-		 * If it's our own child, there is no notification to do.
-		 * But if our normal children self-reap, then this child
-		 * was prevented by ptrace and we must reap it now.
-		 */
-		if (!task_detached(p) && thread_group_empty(p)) {
-			if (!same_thread_group(p->real_parent, parent))
-				do_notify_parent(p, p->exit_signal);
-			else {
-				if (ign < 0)
-					ign = ignoring_children(parent);
-				if (ign)
-					p->exit_signal = -1;
-			}
-		}
-
-		if (task_detached(p)) {
-			/*
-			 * Mark it as in the process of being reaped.
-			 */
-			p->exit_state = EXIT_DEAD;
-			list_add(&p->ptrace_entry, dead);
-		}
-	}
-}
-
-/*
- * Finish up exit-time ptrace cleanup.
- *
- * Called without locks.
- */
-static void ptrace_exit_finish(struct task_struct *parent,
-			       struct list_head *dead)
-{
-	struct task_struct *p, *n;
-
-	BUG_ON(!list_empty(&parent->ptraced));
-
-	list_for_each_entry_safe(p, n, dead, ptrace_entry) {
-		list_del_init(&p->ptrace_entry);
-		release_task(p);
-	}
-}
-
-static void reparent_thread(struct task_struct *p, struct task_struct *father)
-{
-	if (p->pdeath_signal)
-		/* We already hold the tasklist_lock here.  */
-		group_send_sig_info(p->pdeath_signal, SEND_SIG_NOINFO, p);
-
-	list_move_tail(&p->sibling, &p->real_parent->children);
-
-	/* If this is a threaded reparent there is no need to
-	 * notify anyone anything has happened.
-	 */
-	if (same_thread_group(p->real_parent, father))
-		return;
-
-	/* We don't want people slaying init.  */
-	if (!task_detached(p))
-		p->exit_signal = SIGCHLD;
-
-	/* If we'd notified the old parent about this child's death,
-	 * also notify the new parent.
-	 */
-	if (!ptrace_reparented(p) &&
-	    p->exit_state == EXIT_ZOMBIE &&
-	    !task_detached(p) && thread_group_empty(p))
-		do_notify_parent(p, p->exit_signal);
-
-	kill_orphaned_pgrp(p, father);
-}
-
-/*
  * When we die, we re-parent all our children.
  * Try to give them to another thread in our thread
  * group, and if no such member exists, give it to
@@ -883,17 +733,51 @@ static struct task_struct *find_new_reaper(struct task_struct *father)
 	return pid_ns->child_reaper;
 }
 
+/*
+* 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,
+				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))
+		return;
+	/*
+	 * If this is a threaded reparent there is no need to
+	 * notify anyone anything has happened.
+	 */
+	if (same_thread_group(p->real_parent, father))
+		return;
+
+	/* We don't want people slaying init.  */
+	p->exit_signal = SIGCHLD;
+
+	/* If it has exited notify the new parent about this child's death. */
+	if (!p->ptrace &&
+	    p->exit_state == EXIT_ZOMBIE && thread_group_empty(p)) {
+		do_notify_parent(p, p->exit_signal);
+		if (task_detached(p)) {
+			p->exit_state = EXIT_DEAD;
+			list_move_tail(&p->sibling, dead);
+		}
+	}
+
+	kill_orphaned_pgrp(p, father);
+}
+
 static void forget_original_parent(struct task_struct *father)
 {
 	struct task_struct *p, *n, *reaper;
-	LIST_HEAD(ptrace_dead);
+	LIST_HEAD(dead_children);
+
+	exit_ptrace(father);
 
 	write_lock_irq(&tasklist_lock);
 	reaper = find_new_reaper(father);
-	/*
-	 * First clean up ptrace if we were using it.
-	 */
-	ptrace_exit(father, &ptrace_dead);
 
 	list_for_each_entry_safe(p, n, &father->children, sibling) {
 		p->real_parent = reaper;
@@ -901,13 +785,16 @@ static void forget_original_parent(struct task_struct *father)
 			BUG_ON(p->ptrace);
 			p->parent = p->real_parent;
 		}
-		reparent_thread(p, father);
+		reparent_thread(father, p, &dead_children);
 	}
-
 	write_unlock_irq(&tasklist_lock);
+
 	BUG_ON(!list_empty(&father->children));
 
-	ptrace_exit_finish(father, &ptrace_dead);
+	list_for_each_entry_safe(p, n, &dead_children, sibling) {
+		list_del_init(&p->sibling);
+		release_task(p);
+	}
 }
 
 /*
@@ -950,8 +837,7 @@ static void exit_notify(struct task_struct *tsk, int group_dead)
 	 */
 	if (tsk->exit_signal != SIGCHLD && !task_detached(tsk) &&
 	    (tsk->parent_exec_id != tsk->real_parent->self_exec_id ||
-	     tsk->self_exec_id != tsk->parent_exec_id) &&
-	    !capable(CAP_KILL))
+	     tsk->self_exec_id != tsk->parent_exec_id))
 		tsk->exit_signal = SIGCHLD;
 
 	signal = tracehook_notify_death(tsk, &cookie, group_dead);
@@ -1417,6 +1303,18 @@ static int wait_task_zombie(struct task_struct *p, int options,
 	return retval;
 }
 
+static int *task_stopped_code(struct task_struct *p, bool ptrace)
+{
+	if (ptrace) {
+		if (task_is_stopped_or_traced(p))
+			return &p->exit_code;
+	} else {
+		if (p->signal->flags & SIGNAL_STOP_STOPPED)
+			return &p->signal->group_exit_code;
+	}
+	return NULL;
+}
+
 /*
  * Handle sys_wait4 work for one task in state TASK_STOPPED.  We hold
  * read_lock(&tasklist_lock) on entry.  If we return zero, we still hold
@@ -1427,7 +1325,7 @@ static int wait_task_stopped(int ptrace, struct task_struct *p,
 			     int options, struct siginfo __user *infop,
 			     int __user *stat_addr, struct rusage __user *ru)
 {
-	int retval, exit_code, why;
+	int retval, exit_code, *p_code, why;
 	uid_t uid = 0; /* unneeded, required by compiler */
 	pid_t pid;
 
@@ -1437,22 +1335,16 @@ static int wait_task_stopped(int ptrace, struct task_struct *p,
 	exit_code = 0;
 	spin_lock_irq(&p->sighand->siglock);
 
-	if (unlikely(!task_is_stopped_or_traced(p)))
-		goto unlock_sig;
-
-	if (!ptrace && p->signal->group_stop_count > 0)
-		/*
-		 * A group stop is in progress and this is the group leader.
-		 * We won't report until all threads have stopped.
-		 */
+	p_code = task_stopped_code(p, ptrace);
+	if (unlikely(!p_code))
 		goto unlock_sig;
 
-	exit_code = p->exit_code;
+	exit_code = *p_code;
 	if (!exit_code)
 		goto unlock_sig;
 
 	if (!unlikely(options & WNOWAIT))
-		p->exit_code = 0;
+		*p_code = 0;
 
 	/* don't need the RCU readlock here as we're holding a spinlock */
 	uid = __task_cred(p)->uid;
@@ -1608,7 +1500,7 @@ static int wait_consider_task(struct task_struct *parent, int ptrace,
 	 */
 	*notask_error = 0;
 
-	if (task_is_stopped_or_traced(p))
+	if (task_stopped_code(p, ptrace))
 		return wait_task_stopped(ptrace, p, options,
 					 infop, stat_addr, ru);
 
@@ -1812,7 +1704,7 @@ SYSCALL_DEFINE4(wait4, pid_t, upid, int __user *, stat_addr,
 		pid = find_get_pid(-upid);
 	} else if (upid == 0) {
 		type = PIDTYPE_PGID;
-		pid = get_pid(task_pgrp(current));
+		pid = get_task_pid(current, PIDTYPE_PGID);
 	} else /* upid > 0 */ {
 		type = PIDTYPE_PID;
 		pid = find_get_pid(upid);
diff --git a/kernel/extable.c b/kernel/extable.c
index 0df6253730b..7f8f263f852 100644
--- a/kernel/extable.c
+++ b/kernel/extable.c
@@ -15,11 +15,22 @@
     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/ftrace.h>
+#include <linux/memory.h>
 #include <linux/module.h>
+#include <linux/mutex.h>
 #include <linux/init.h>
-#include <linux/ftrace.h>
-#include <asm/uaccess.h>
+
 #include <asm/sections.h>
+#include <asm/uaccess.h>
+
+/*
+ * mutex protecting text section modification (dynamic code patching).
+ * some users need to sleep (allocating memory...) while they hold this lock.
+ *
+ * NOT exported to modules - patching kernel text is a really delicate matter.
+ */
+DEFINE_MUTEX(text_mutex);
 
 extern struct exception_table_entry __start___ex_table[];
 extern struct exception_table_entry __stop___ex_table[];
@@ -41,6 +52,14 @@ const struct exception_table_entry *search_exception_tables(unsigned long addr)
 	return e;
 }
 
+static inline int init_kernel_text(unsigned long addr)
+{
+	if (addr >= (unsigned long)_sinittext &&
+	    addr <= (unsigned long)_einittext)
+		return 1;
+	return 0;
+}
+
 int core_kernel_text(unsigned long addr)
 {
 	if (addr >= (unsigned long)_stext &&
@@ -48,8 +67,7 @@ int core_kernel_text(unsigned long addr)
 		return 1;
 
 	if (system_state == SYSTEM_BOOTING &&
-	    addr >= (unsigned long)_sinittext &&
-	    addr <= (unsigned long)_einittext)
+	    init_kernel_text(addr))
 		return 1;
 	return 0;
 }
@@ -58,14 +76,26 @@ int __kernel_text_address(unsigned long addr)
 {
 	if (core_kernel_text(addr))
 		return 1;
-	return __module_text_address(addr) != NULL;
+	if (is_module_text_address(addr))
+		return 1;
+	/*
+	 * There might be init symbols in saved stacktraces.
+	 * Give those symbols a chance to be printed in
+	 * backtraces (such as lockdep traces).
+	 *
+	 * Since we are after the module-symbols check, there's
+	 * no danger of address overlap:
+	 */
+	if (init_kernel_text(addr))
+		return 1;
+	return 0;
 }
 
 int kernel_text_address(unsigned long addr)
 {
 	if (core_kernel_text(addr))
 		return 1;
-	return module_text_address(addr) != NULL;
+	return is_module_text_address(addr);
 }
 
 /*
@@ -81,5 +111,5 @@ int func_ptr_is_kernel_text(void *ptr)
 	addr = (unsigned long) dereference_function_descriptor(ptr);
 	if (core_kernel_text(addr))
 		return 1;
-	return module_text_address(addr) != NULL;
+	return is_module_text_address(addr);
 }
diff --git a/kernel/fork.c b/kernel/fork.c
index 6715ebc3761..660c2b8765b 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -60,6 +60,7 @@
 #include <linux/tty.h>
 #include <linux/proc_fs.h>
 #include <linux/blkdev.h>
+#include <linux/fs_struct.h>
 #include <trace/sched.h>
 #include <linux/magic.h>
 
@@ -284,7 +285,7 @@ static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm)
 	mm->free_area_cache = oldmm->mmap_base;
 	mm->cached_hole_size = ~0UL;
 	mm->map_count = 0;
-	cpus_clear(mm->cpu_vm_mask);
+	cpumask_clear(mm_cpumask(mm));
 	mm->mm_rb = RB_ROOT;
 	rb_link = &mm->mm_rb.rb_node;
 	rb_parent = NULL;
@@ -681,38 +682,21 @@ fail_nomem:
 	return retval;
 }
 
-static struct fs_struct *__copy_fs_struct(struct fs_struct *old)
-{
-	struct fs_struct *fs = kmem_cache_alloc(fs_cachep, GFP_KERNEL);
-	/* We don't need to lock fs - think why ;-) */
-	if (fs) {
-		atomic_set(&fs->count, 1);
-		rwlock_init(&fs->lock);
-		fs->umask = old->umask;
-		read_lock(&old->lock);
-		fs->root = old->root;
-		path_get(&old->root);
-		fs->pwd = old->pwd;
-		path_get(&old->pwd);
-		read_unlock(&old->lock);
-	}
-	return fs;
-}
-
-struct fs_struct *copy_fs_struct(struct fs_struct *old)
-{
-	return __copy_fs_struct(old);
-}
-
-EXPORT_SYMBOL_GPL(copy_fs_struct);
-
 static int copy_fs(unsigned long clone_flags, struct task_struct *tsk)
 {
+	struct fs_struct *fs = current->fs;
 	if (clone_flags & CLONE_FS) {
-		atomic_inc(&current->fs->count);
+		/* tsk->fs is already what we want */
+		write_lock(&fs->lock);
+		if (fs->in_exec) {
+			write_unlock(&fs->lock);
+			return -EAGAIN;
+		}
+		fs->users++;
+		write_unlock(&fs->lock);
 		return 0;
 	}
-	tsk->fs = __copy_fs_struct(current->fs);
+	tsk->fs = copy_fs_struct(fs);
 	if (!tsk->fs)
 		return -ENOMEM;
 	return 0;
@@ -841,6 +825,8 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk)
 	atomic_set(&sig->live, 1);
 	init_waitqueue_head(&sig->wait_chldexit);
 	sig->flags = 0;
+	if (clone_flags & CLONE_NEWPID)
+		sig->flags |= SIGNAL_UNKILLABLE;
 	sig->group_exit_code = 0;
 	sig->group_exit_task = NULL;
 	sig->group_stop_count = 0;
@@ -1125,7 +1111,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 		goto bad_fork_cleanup_mm;
 	if ((retval = copy_io(clone_flags, p)))
 		goto bad_fork_cleanup_namespaces;
-	retval = copy_thread(0, clone_flags, stack_start, stack_size, p, regs);
+	retval = copy_thread(clone_flags, stack_start, stack_size, p, regs);
 	if (retval)
 		goto bad_fork_cleanup_io;
 
@@ -1263,8 +1249,6 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 			p->signal->leader_pid = pid;
 			tty_kref_put(p->signal->tty);
 			p->signal->tty = tty_kref_get(current->signal->tty);
-			set_task_pgrp(p, task_pgrp_nr(current));
-			set_task_session(p, task_session_nr(current));
 			attach_pid(p, PIDTYPE_PGID, task_pgrp(current));
 			attach_pid(p, PIDTYPE_SID, task_session(current));
 			list_add_tail_rcu(&p->tasks, &init_task.tasks);
@@ -1488,6 +1472,7 @@ void __init proc_caches_init(void)
 	mm_cachep = kmem_cache_create("mm_struct",
 			sizeof(struct mm_struct), ARCH_MIN_MMSTRUCT_ALIGN,
 			SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL);
+	vm_area_cachep = KMEM_CACHE(vm_area_struct, SLAB_PANIC);
 	mmap_init();
 }
 
@@ -1543,12 +1528,16 @@ static int unshare_fs(unsigned long unshare_flags, struct fs_struct **new_fsp)
 {
 	struct fs_struct *fs = current->fs;
 
-	if ((unshare_flags & CLONE_FS) &&
-	    (fs && atomic_read(&fs->count) > 1)) {
-		*new_fsp = __copy_fs_struct(current->fs);
-		if (!*new_fsp)
-			return -ENOMEM;
-	}
+	if (!(unshare_flags & CLONE_FS) || !fs)
+		return 0;
+
+	/* don't need lock here; in the worst case we'll do useless copy */
+	if (fs->users == 1)
+		return 0;
+
+	*new_fsp = copy_fs_struct(fs);
+	if (!*new_fsp)
+		return -ENOMEM;
 
 	return 0;
 }
@@ -1664,8 +1653,13 @@ SYSCALL_DEFINE1(unshare, unsigned long, unshare_flags)
 
 		if (new_fs) {
 			fs = current->fs;
+			write_lock(&fs->lock);
 			current->fs = new_fs;
-			new_fs = fs;
+			if (--fs->users)
+				new_fs = NULL;
+			else
+				new_fs = fs;
+			write_unlock(&fs->lock);
 		}
 
 		if (new_mm) {
@@ -1704,7 +1698,7 @@ bad_unshare_cleanup_sigh:
 
 bad_unshare_cleanup_fs:
 	if (new_fs)
-		put_fs_struct(new_fs);
+		free_fs_struct(new_fs);
 
 bad_unshare_cleanup_thread:
 bad_unshare_out:
diff --git a/kernel/futex.c b/kernel/futex.c
index 438701adce2..6b50a024bca 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -114,7 +114,9 @@ struct futex_q {
 };
 
 /*
- * Split the global futex_lock into every hash list lock.
+ * Hash buckets are shared by all the futex_keys that hash to the same
+ * location.  Each key may have multiple futex_q structures, one for each task
+ * waiting on a futex.
  */
 struct futex_hash_bucket {
 	spinlock_t lock;
@@ -189,8 +191,7 @@ static void drop_futex_key_refs(union futex_key *key)
 /**
  * get_futex_key - Get parameters which are the keys for a futex.
  * @uaddr: virtual address of the futex
- * @shared: NULL for a PROCESS_PRIVATE futex,
- *	&current->mm->mmap_sem for a PROCESS_SHARED futex
+ * @fshared: 0 for a PROCESS_PRIVATE futex, 1 for PROCESS_SHARED
  * @key: address where result is stored.
  *
  * Returns a negative error code or 0
@@ -200,9 +201,7 @@ static void drop_futex_key_refs(union futex_key *key)
  * offset_within_page).  For private mappings, it's (uaddr, current->mm).
  * We can usually work out the index without swapping in the page.
  *
- * fshared is NULL for PROCESS_PRIVATE futexes
- * For other futexes, it points to &current->mm->mmap_sem and
- * caller must have taken the reader lock. but NOT any spinlocks.
+ * lock_page() might sleep, the caller should not hold a spinlock.
  */
 static int get_futex_key(u32 __user *uaddr, int fshared, union futex_key *key)
 {
@@ -299,41 +298,6 @@ static int get_futex_value_locked(u32 *dest, u32 __user *from)
 	return ret ? -EFAULT : 0;
 }
 
-/*
- * Fault handling.
- */
-static int futex_handle_fault(unsigned long address, int attempt)
-{
-	struct vm_area_struct * vma;
-	struct mm_struct *mm = current->mm;
-	int ret = -EFAULT;
-
-	if (attempt > 2)
-		return ret;
-
-	down_read(&mm->mmap_sem);
-	vma = find_vma(mm, address);
-	if (vma && address >= vma->vm_start &&
-	    (vma->vm_flags & VM_WRITE)) {
-		int fault;
-		fault = handle_mm_fault(mm, vma, address, 1);
-		if (unlikely((fault & VM_FAULT_ERROR))) {
-#if 0
-			/* XXX: let's do this when we verify it is OK */
-			if (ret & VM_FAULT_OOM)
-				ret = -ENOMEM;
-#endif
-		} else {
-			ret = 0;
-			if (fault & VM_FAULT_MAJOR)
-				current->maj_flt++;
-			else
-				current->min_flt++;
-		}
-	}
-	up_read(&mm->mmap_sem);
-	return ret;
-}
 
 /*
  * PI code:
@@ -589,10 +553,9 @@ static void wake_futex(struct futex_q *q)
 	 * The waiting task can free the futex_q as soon as this is written,
 	 * without taking any locks.  This must come last.
 	 *
-	 * A memory barrier is required here to prevent the following store
-	 * to lock_ptr from getting ahead of the wakeup. Clearing the lock
-	 * at the end of wake_up_all() does not prevent this store from
-	 * moving.
+	 * A memory barrier is required here to prevent the following store to
+	 * lock_ptr from getting ahead of the wakeup. Clearing the lock at the
+	 * end of wake_up() does not prevent this store from moving.
 	 */
 	smp_wmb();
 	q->lock_ptr = NULL;
@@ -692,9 +655,16 @@ double_lock_hb(struct futex_hash_bucket *hb1, struct futex_hash_bucket *hb2)
 	}
 }
 
+static inline void
+double_unlock_hb(struct futex_hash_bucket *hb1, struct futex_hash_bucket *hb2)
+{
+	spin_unlock(&hb1->lock);
+	if (hb1 != hb2)
+		spin_unlock(&hb2->lock);
+}
+
 /*
- * Wake up all waiters hashed on the physical page that is mapped
- * to this virtual address:
+ * Wake up waiters matching bitset queued on this futex (uaddr).
  */
 static int futex_wake(u32 __user *uaddr, int fshared, int nr_wake, u32 bitset)
 {
@@ -750,9 +720,9 @@ futex_wake_op(u32 __user *uaddr1, int fshared, u32 __user *uaddr2,
 	struct futex_hash_bucket *hb1, *hb2;
 	struct plist_head *head;
 	struct futex_q *this, *next;
-	int ret, op_ret, attempt = 0;
+	int ret, op_ret;
 
-retryfull:
+retry:
 	ret = get_futex_key(uaddr1, fshared, &key1);
 	if (unlikely(ret != 0))
 		goto out;
@@ -763,16 +733,13 @@ retryfull:
 	hb1 = hash_futex(&key1);
 	hb2 = hash_futex(&key2);
 
-retry:
 	double_lock_hb(hb1, hb2);
-
+retry_private:
 	op_ret = futex_atomic_op_inuser(op, uaddr2);
 	if (unlikely(op_ret < 0)) {
 		u32 dummy;
 
-		spin_unlock(&hb1->lock);
-		if (hb1 != hb2)
-			spin_unlock(&hb2->lock);
+		double_unlock_hb(hb1, hb2);
 
 #ifndef CONFIG_MMU
 		/*
@@ -788,26 +755,16 @@ retry:
 			goto out_put_keys;
 		}
 
-		/*
-		 * futex_atomic_op_inuser needs to both read and write
-		 * *(int __user *)uaddr2, but we can't modify it
-		 * non-atomically.  Therefore, if get_user below is not
-		 * enough, we need to handle the fault ourselves, while
-		 * still holding the mmap_sem.
-		 */
-		if (attempt++) {
-			ret = futex_handle_fault((unsigned long)uaddr2,
-						 attempt);
-			if (ret)
-				goto out_put_keys;
-			goto retry;
-		}
-
 		ret = get_user(dummy, uaddr2);
 		if (ret)
-			return ret;
+			goto out_put_keys;
+
+		if (!fshared)
+			goto retry_private;
 
-		goto retryfull;
+		put_futex_key(fshared, &key2);
+		put_futex_key(fshared, &key1);
+		goto retry;
 	}
 
 	head = &hb1->chain;
@@ -834,9 +791,7 @@ retry:
 		ret += op_ret;
 	}
 
-	spin_unlock(&hb1->lock);
-	if (hb1 != hb2)
-		spin_unlock(&hb2->lock);
+	double_unlock_hb(hb1, hb2);
 out_put_keys:
 	put_futex_key(fshared, &key2);
 out_put_key1:
@@ -869,6 +824,7 @@ retry:
 	hb1 = hash_futex(&key1);
 	hb2 = hash_futex(&key2);
 
+retry_private:
 	double_lock_hb(hb1, hb2);
 
 	if (likely(cmpval != NULL)) {
@@ -877,16 +833,18 @@ retry:
 		ret = get_futex_value_locked(&curval, uaddr1);
 
 		if (unlikely(ret)) {
-			spin_unlock(&hb1->lock);
-			if (hb1 != hb2)
-				spin_unlock(&hb2->lock);
+			double_unlock_hb(hb1, hb2);
 
 			ret = get_user(curval, uaddr1);
+			if (ret)
+				goto out_put_keys;
 
-			if (!ret)
-				goto retry;
+			if (!fshared)
+				goto retry_private;
 
-			goto out_put_keys;
+			put_futex_key(fshared, &key2);
+			put_futex_key(fshared, &key1);
+			goto retry;
 		}
 		if (curval != *cmpval) {
 			ret = -EAGAIN;
@@ -923,9 +881,7 @@ retry:
 	}
 
 out_unlock:
-	spin_unlock(&hb1->lock);
-	if (hb1 != hb2)
-		spin_unlock(&hb2->lock);
+	double_unlock_hb(hb1, hb2);
 
 	/* drop_futex_key_refs() must be called outside the spinlocks. */
 	while (--drop_count >= 0)
@@ -1063,7 +1019,7 @@ static int fixup_pi_state_owner(u32 __user *uaddr, struct futex_q *q,
 	struct futex_pi_state *pi_state = q->pi_state;
 	struct task_struct *oldowner = pi_state->owner;
 	u32 uval, curval, newval;
-	int ret, attempt = 0;
+	int ret;
 
 	/* Owner died? */
 	if (!pi_state->owner)
@@ -1076,11 +1032,9 @@ static int fixup_pi_state_owner(u32 __user *uaddr, struct futex_q *q,
 	 * in the user space variable. This must be atomic as we have
 	 * to preserve the owner died bit here.
 	 *
-	 * Note: We write the user space value _before_ changing the
-	 * pi_state because we can fault here. Imagine swapped out
-	 * pages or a fork, which was running right before we acquired
-	 * mmap_sem, that marked all the anonymous memory readonly for
-	 * cow.
+	 * Note: We write the user space value _before_ changing the pi_state
+	 * because we can fault here. Imagine swapped out pages or a fork
+	 * that marked all the anonymous memory readonly for cow.
 	 *
 	 * Modifying pi_state _before_ the user space value would
 	 * leave the pi_state in an inconsistent state when we fault
@@ -1136,7 +1090,7 @@ retry:
 handle_fault:
 	spin_unlock(q->lock_ptr);
 
-	ret = futex_handle_fault((unsigned long)uaddr, attempt++);
+	ret = get_user(uval, uaddr);
 
 	spin_lock(q->lock_ptr);
 
@@ -1185,10 +1139,11 @@ retry:
 	if (unlikely(ret != 0))
 		goto out;
 
+retry_private:
 	hb = queue_lock(&q);
 
 	/*
-	 * Access the page AFTER the futex is queued.
+	 * Access the page AFTER the hash-bucket is locked.
 	 * Order is important:
 	 *
 	 *   Userspace waiter: val = var; if (cond(val)) futex_wait(&var, val);
@@ -1204,20 +1159,23 @@ retry:
 	 * a wakeup when *uaddr != val on entry to the syscall.  This is
 	 * rare, but normal.
 	 *
-	 * for shared futexes, we hold the mmap semaphore, so the mapping
+	 * For shared futexes, we hold the mmap semaphore, so the mapping
 	 * cannot have changed since we looked it up in get_futex_key.
 	 */
 	ret = get_futex_value_locked(&uval, uaddr);
 
 	if (unlikely(ret)) {
 		queue_unlock(&q, hb);
-		put_futex_key(fshared, &q.key);
 
 		ret = get_user(uval, uaddr);
+		if (ret)
+			goto out_put_key;
 
-		if (!ret)
-			goto retry;
-		goto out;
+		if (!fshared)
+			goto retry_private;
+
+		put_futex_key(fshared, &q.key);
+		goto retry;
 	}
 	ret = -EWOULDBLOCK;
 	if (unlikely(uval != val)) {
@@ -1248,16 +1206,13 @@ retry:
 		if (!abs_time)
 			schedule();
 		else {
-			unsigned long slack;
-			slack = current->timer_slack_ns;
-			if (rt_task(current))
-				slack = 0;
 			hrtimer_init_on_stack(&t.timer,
 					      clockrt ? CLOCK_REALTIME :
 					      CLOCK_MONOTONIC,
 					      HRTIMER_MODE_ABS);
 			hrtimer_init_sleeper(&t, current);
-			hrtimer_set_expires_range_ns(&t.timer, *abs_time, slack);
+			hrtimer_set_expires_range_ns(&t.timer, *abs_time,
+						     current->timer_slack_ns);
 
 			hrtimer_start_expires(&t.timer, HRTIMER_MODE_ABS);
 			if (!hrtimer_active(&t.timer))
@@ -1354,7 +1309,7 @@ static int futex_lock_pi(u32 __user *uaddr, int fshared,
 	struct futex_hash_bucket *hb;
 	u32 uval, newval, curval;
 	struct futex_q q;
-	int ret, lock_taken, ownerdied = 0, attempt = 0;
+	int ret, lock_taken, ownerdied = 0;
 
 	if (refill_pi_state_cache())
 		return -ENOMEM;
@@ -1374,7 +1329,7 @@ retry:
 	if (unlikely(ret != 0))
 		goto out;
 
-retry_unlocked:
+retry_private:
 	hb = queue_lock(&q);
 
 retry_locked:
@@ -1458,6 +1413,7 @@ retry_locked:
 			 * exit to complete.
 			 */
 			queue_unlock(&q, hb);
+			put_futex_key(fshared, &q.key);
 			cond_resched();
 			goto retry;
 
@@ -1564,6 +1520,13 @@ retry_locked:
 		}
 	}
 
+	/*
+	 * If fixup_pi_state_owner() faulted and was unable to handle the
+	 * fault, unlock it and return the fault to userspace.
+	 */
+	if (ret && (rt_mutex_owner(&q.pi_state->pi_mutex) == current))
+		rt_mutex_unlock(&q.pi_state->pi_mutex);
+
 	/* Unqueue and drop the lock */
 	unqueue_me_pi(&q);
 
@@ -1591,22 +1554,18 @@ uaddr_faulted:
 	 */
 	queue_unlock(&q, hb);
 
-	if (attempt++) {
-		ret = futex_handle_fault((unsigned long)uaddr, attempt);
-		if (ret)
-			goto out_put_key;
-		goto retry_unlocked;
-	}
-
 	ret = get_user(uval, uaddr);
-	if (!ret)
-		goto retry;
+	if (ret)
+		goto out_put_key;
 
-	if (to)
-		destroy_hrtimer_on_stack(&to->timer);
-	return ret;
+	if (!fshared)
+		goto retry_private;
+
+	put_futex_key(fshared, &q.key);
+	goto retry;
 }
 
+
 /*
  * Userspace attempted a TID -> 0 atomic transition, and failed.
  * This is the in-kernel slowpath: we look up the PI state (if any),
@@ -1619,7 +1578,7 @@ static int futex_unlock_pi(u32 __user *uaddr, int fshared)
 	u32 uval;
 	struct plist_head *head;
 	union futex_key key = FUTEX_KEY_INIT;
-	int ret, attempt = 0;
+	int ret;
 
 retry:
 	if (get_user(uval, uaddr))
@@ -1635,7 +1594,6 @@ retry:
 		goto out;
 
 	hb = hash_futex(&key);
-retry_unlocked:
 	spin_lock(&hb->lock);
 
 	/*
@@ -1700,14 +1658,7 @@ pi_faulted:
 	 * we have to drop the mmap_sem in order to call get_user().
 	 */
 	spin_unlock(&hb->lock);
-
-	if (attempt++) {
-		ret = futex_handle_fault((unsigned long)uaddr, attempt);
-		if (ret)
-			goto out;
-		uval = 0;
-		goto retry_unlocked;
-	}
+	put_futex_key(fshared, &key);
 
 	ret = get_user(uval, uaddr);
 	if (!ret)
diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c
index f394d2a42ca..cb8a15c1958 100644
--- a/kernel/hrtimer.c
+++ b/kernel/hrtimer.c
@@ -651,14 +651,20 @@ static inline void hrtimer_init_timer_hres(struct hrtimer *timer)
  * and expiry check is done in the hrtimer_interrupt or in the softirq.
  */
 static inline int hrtimer_enqueue_reprogram(struct hrtimer *timer,
-					    struct hrtimer_clock_base *base)
+					    struct hrtimer_clock_base *base,
+					    int wakeup)
 {
 	if (base->cpu_base->hres_active && hrtimer_reprogram(timer, base)) {
-		spin_unlock(&base->cpu_base->lock);
-		raise_softirq_irqoff(HRTIMER_SOFTIRQ);
-		spin_lock(&base->cpu_base->lock);
+		if (wakeup) {
+			spin_unlock(&base->cpu_base->lock);
+			raise_softirq_irqoff(HRTIMER_SOFTIRQ);
+			spin_lock(&base->cpu_base->lock);
+		} else
+			__raise_softirq_irqoff(HRTIMER_SOFTIRQ);
+
 		return 1;
 	}
+
 	return 0;
 }
 
@@ -703,7 +709,8 @@ static inline int hrtimer_is_hres_enabled(void) { return 0; }
 static inline int hrtimer_switch_to_hres(void) { return 0; }
 static inline void hrtimer_force_reprogram(struct hrtimer_cpu_base *base) { }
 static inline int hrtimer_enqueue_reprogram(struct hrtimer *timer,
-					    struct hrtimer_clock_base *base)
+					    struct hrtimer_clock_base *base,
+					    int wakeup)
 {
 	return 0;
 }
@@ -886,20 +893,9 @@ remove_hrtimer(struct hrtimer *timer, struct hrtimer_clock_base *base)
 	return 0;
 }
 
-/**
- * hrtimer_start_range_ns - (re)start an hrtimer on the current CPU
- * @timer:	the timer to be added
- * @tim:	expiry time
- * @delta_ns:	"slack" range for the timer
- * @mode:	expiry mode: absolute (HRTIMER_ABS) or relative (HRTIMER_REL)
- *
- * Returns:
- *  0 on success
- *  1 when the timer was active
- */
-int
-hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim, unsigned long delta_ns,
-			const enum hrtimer_mode mode)
+int __hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim,
+		unsigned long delta_ns, const enum hrtimer_mode mode,
+		int wakeup)
 {
 	struct hrtimer_clock_base *base, *new_base;
 	unsigned long flags;
@@ -940,12 +936,29 @@ hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim, unsigned long delta_n
 	 * XXX send_remote_softirq() ?
 	 */
 	if (leftmost && new_base->cpu_base == &__get_cpu_var(hrtimer_bases))
-		hrtimer_enqueue_reprogram(timer, new_base);
+		hrtimer_enqueue_reprogram(timer, new_base, wakeup);
 
 	unlock_hrtimer_base(timer, &flags);
 
 	return ret;
 }
+
+/**
+ * hrtimer_start_range_ns - (re)start an hrtimer on the current CPU
+ * @timer:	the timer to be added
+ * @tim:	expiry time
+ * @delta_ns:	"slack" range for the timer
+ * @mode:	expiry mode: absolute (HRTIMER_ABS) or relative (HRTIMER_REL)
+ *
+ * Returns:
+ *  0 on success
+ *  1 when the timer was active
+ */
+int hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim,
+		unsigned long delta_ns, const enum hrtimer_mode mode)
+{
+	return __hrtimer_start_range_ns(timer, tim, delta_ns, mode, 1);
+}
 EXPORT_SYMBOL_GPL(hrtimer_start_range_ns);
 
 /**
@@ -961,7 +974,7 @@ EXPORT_SYMBOL_GPL(hrtimer_start_range_ns);
 int
 hrtimer_start(struct hrtimer *timer, ktime_t tim, const enum hrtimer_mode mode)
 {
-	return hrtimer_start_range_ns(timer, tim, 0, mode);
+	return __hrtimer_start_range_ns(timer, tim, 0, mode, 1);
 }
 EXPORT_SYMBOL_GPL(hrtimer_start);
 
diff --git a/kernel/irq/Makefile b/kernel/irq/Makefile
index 4dd5b1edac9..3394f8f5296 100644
--- a/kernel/irq/Makefile
+++ b/kernel/irq/Makefile
@@ -4,3 +4,4 @@ obj-$(CONFIG_GENERIC_IRQ_PROBE) += autoprobe.o
 obj-$(CONFIG_PROC_FS) += proc.o
 obj-$(CONFIG_GENERIC_PENDING_IRQ) += migration.o
 obj-$(CONFIG_NUMA_MIGRATE_IRQ_DESC) += numa_migrate.o
+obj-$(CONFIG_PM_SLEEP) += pm.o
diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c
index 122fef4b0bd..c687ba4363f 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -81,6 +81,7 @@ void dynamic_irq_cleanup(unsigned int irq)
 	desc->handle_irq = handle_bad_irq;
 	desc->chip = &no_irq_chip;
 	desc->name = NULL;
+	clear_kstat_irqs(desc);
 	spin_unlock_irqrestore(&desc->lock, flags);
 }
 
@@ -293,7 +294,8 @@ static inline void mask_ack_irq(struct irq_desc *desc, int irq)
 		desc->chip->mask_ack(irq);
 	else {
 		desc->chip->mask(irq);
-		desc->chip->ack(irq);
+		if (desc->chip->ack)
+			desc->chip->ack(irq);
 	}
 }
 
@@ -479,7 +481,8 @@ handle_edge_irq(unsigned int irq, struct irq_desc *desc)
 	kstat_incr_irqs_this_cpu(irq, desc);
 
 	/* Start handling the irq */
-	desc->chip->ack(irq);
+	if (desc->chip->ack)
+		desc->chip->ack(irq);
 	desc = irq_remap_to_desc(irq, desc);
 
 	/* Mark the IRQ currently in progress.*/
diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c
index 412370ab9a3..343acecae62 100644
--- a/kernel/irq/handle.c
+++ b/kernel/irq/handle.c
@@ -83,19 +83,21 @@ static struct irq_desc irq_desc_init = {
 
 void init_kstat_irqs(struct irq_desc *desc, int cpu, int nr)
 {
-	unsigned long bytes;
-	char *ptr;
 	int node;
-
-	/* Compute how many bytes we need per irq and allocate them */
-	bytes = nr * sizeof(unsigned int);
+	void *ptr;
 
 	node = cpu_to_node(cpu);
-	ptr = kzalloc_node(bytes, GFP_ATOMIC, node);
-	printk(KERN_DEBUG "  alloc kstat_irqs on cpu %d node %d\n", cpu, node);
+	ptr = kzalloc_node(nr * sizeof(*desc->kstat_irqs), GFP_ATOMIC, node);
 
-	if (ptr)
-		desc->kstat_irqs = (unsigned int *)ptr;
+	/*
+	 * don't overwite if can not get new one
+	 * init_copy_kstat_irqs() could still use old one
+	 */
+	if (ptr) {
+		printk(KERN_DEBUG "  alloc kstat_irqs on cpu %d node %d\n",
+			 cpu, node);
+		desc->kstat_irqs = ptr;
+	}
 }
 
 static void init_one_irq_desc(int irq, struct irq_desc *desc, int cpu)
@@ -238,6 +240,7 @@ struct irq_desc irq_desc[NR_IRQS] __cacheline_aligned_in_smp = {
 	}
 };
 
+static unsigned int kstat_irqs_all[NR_IRQS][NR_CPUS];
 int __init early_irq_init(void)
 {
 	struct irq_desc *desc;
@@ -254,6 +257,7 @@ int __init early_irq_init(void)
 	for (i = 0; i < count; i++) {
 		desc[i].irq = i;
 		init_alloc_desc_masks(&desc[i], 0, true);
+		desc[i].kstat_irqs = kstat_irqs_all[i];
 	}
 	return arch_early_irq_init();
 }
@@ -269,6 +273,11 @@ struct irq_desc *irq_to_desc_alloc_cpu(unsigned int irq, int cpu)
 }
 #endif /* !CONFIG_SPARSE_IRQ */
 
+void clear_kstat_irqs(struct irq_desc *desc)
+{
+	memset(desc->kstat_irqs, 0, nr_cpu_ids * sizeof(*(desc->kstat_irqs)));
+}
+
 /*
  * What should we do if we get a hw irq event on an illegal vector?
  * Each architecture has to answer this themself.
@@ -345,6 +354,8 @@ irqreturn_t handle_IRQ_event(unsigned int irq, struct irqaction *action)
 	irqreturn_t ret, retval = IRQ_NONE;
 	unsigned int status = 0;
 
+	WARN_ONCE(!in_irq(), "BUG: IRQ handler called from non-hardirq context!");
+
 	if (!(action->flags & IRQF_DISABLED))
 		local_irq_enable_in_hardirq();
 
@@ -366,6 +377,11 @@ irqreturn_t handle_IRQ_event(unsigned int irq, struct irqaction *action)
 }
 
 #ifndef CONFIG_GENERIC_HARDIRQS_NO__DO_IRQ
+
+#ifdef CONFIG_ENABLE_WARN_DEPRECATED
+# warning __do_IRQ is deprecated. Please convert to proper flow handlers
+#endif
+
 /**
  * __do_IRQ - original all in one highlevel IRQ handler
  * @irq:	the interrupt number
@@ -486,12 +502,10 @@ void early_init_irq_lock_class(void)
 	}
 }
 
-#ifdef CONFIG_SPARSE_IRQ
 unsigned int kstat_irqs_cpu(unsigned int irq, int cpu)
 {
 	struct irq_desc *desc = irq_to_desc(irq);
 	return desc ? desc->kstat_irqs[cpu] : 0;
 }
-#endif
 EXPORT_SYMBOL(kstat_irqs_cpu);
 
diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h
index 40416a81a0f..01ce20eab38 100644
--- a/kernel/irq/internals.h
+++ b/kernel/irq/internals.h
@@ -12,9 +12,12 @@ extern void compat_irq_chip_set_default_handler(struct irq_desc *desc);
 
 extern int __irq_set_trigger(struct irq_desc *desc, unsigned int irq,
 		unsigned long flags);
+extern void __disable_irq(struct irq_desc *desc, unsigned int irq, bool susp);
+extern void __enable_irq(struct irq_desc *desc, unsigned int irq, bool resume);
 
 extern struct lock_class_key irq_desc_lock_class;
 extern void init_kstat_irqs(struct irq_desc *desc, int cpu, int nr);
+extern void clear_kstat_irqs(struct irq_desc *desc);
 extern spinlock_t sparse_irq_lock;
 
 #ifdef CONFIG_SPARSE_IRQ
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index a3a5dc9ef34..1516ab77355 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -109,7 +109,7 @@ int irq_set_affinity(unsigned int irq, const struct cpumask *cpumask)
 /*
  * Generic version of the affinity autoselector.
  */
-int do_irq_select_affinity(unsigned int irq, struct irq_desc *desc)
+static int setup_affinity(unsigned int irq, struct irq_desc *desc)
 {
 	if (!irq_can_set_affinity(irq))
 		return 0;
@@ -133,7 +133,7 @@ set_affinity:
 	return 0;
 }
 #else
-static inline int do_irq_select_affinity(unsigned int irq, struct irq_desc *d)
+static inline int setup_affinity(unsigned int irq, struct irq_desc *d)
 {
 	return irq_select_affinity(irq);
 }
@@ -149,19 +149,33 @@ int irq_select_affinity_usr(unsigned int irq)
 	int ret;
 
 	spin_lock_irqsave(&desc->lock, flags);
-	ret = do_irq_select_affinity(irq, desc);
+	ret = setup_affinity(irq, desc);
 	spin_unlock_irqrestore(&desc->lock, flags);
 
 	return ret;
 }
 
 #else
-static inline int do_irq_select_affinity(int irq, struct irq_desc *desc)
+static inline int setup_affinity(unsigned int irq, struct irq_desc *desc)
 {
 	return 0;
 }
 #endif
 
+void __disable_irq(struct irq_desc *desc, unsigned int irq, bool suspend)
+{
+	if (suspend) {
+		if (!desc->action || (desc->action->flags & IRQF_TIMER))
+			return;
+		desc->status |= IRQ_SUSPENDED;
+	}
+
+	if (!desc->depth++) {
+		desc->status |= IRQ_DISABLED;
+		desc->chip->disable(irq);
+	}
+}
+
 /**
  *	disable_irq_nosync - disable an irq without waiting
  *	@irq: Interrupt to disable
@@ -182,10 +196,7 @@ void disable_irq_nosync(unsigned int irq)
 		return;
 
 	spin_lock_irqsave(&desc->lock, flags);
-	if (!desc->depth++) {
-		desc->status |= IRQ_DISABLED;
-		desc->chip->disable(irq);
-	}
+	__disable_irq(desc, irq, false);
 	spin_unlock_irqrestore(&desc->lock, flags);
 }
 EXPORT_SYMBOL(disable_irq_nosync);
@@ -215,15 +226,21 @@ void disable_irq(unsigned int irq)
 }
 EXPORT_SYMBOL(disable_irq);
 
-static void __enable_irq(struct irq_desc *desc, unsigned int irq)
+void __enable_irq(struct irq_desc *desc, unsigned int irq, bool resume)
 {
+	if (resume)
+		desc->status &= ~IRQ_SUSPENDED;
+
 	switch (desc->depth) {
 	case 0:
+ err_out:
 		WARN(1, KERN_WARNING "Unbalanced enable for IRQ %d\n", irq);
 		break;
 	case 1: {
 		unsigned int status = desc->status & ~IRQ_DISABLED;
 
+		if (desc->status & IRQ_SUSPENDED)
+			goto err_out;
 		/* Prevent probing on this irq: */
 		desc->status = status | IRQ_NOPROBE;
 		check_irq_resend(desc, irq);
@@ -253,7 +270,7 @@ void enable_irq(unsigned int irq)
 		return;
 
 	spin_lock_irqsave(&desc->lock, flags);
-	__enable_irq(desc, irq);
+	__enable_irq(desc, irq, false);
 	spin_unlock_irqrestore(&desc->lock, flags);
 }
 EXPORT_SYMBOL(enable_irq);
@@ -389,9 +406,9 @@ int __irq_set_trigger(struct irq_desc *desc, unsigned int irq,
  * allocate special interrupts that are part of the architecture.
  */
 static int
-__setup_irq(unsigned int irq, struct irq_desc * desc, struct irqaction *new)
+__setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new)
 {
-	struct irqaction *old, **p;
+	struct irqaction *old, **old_ptr;
 	const char *old_name = NULL;
 	unsigned long flags;
 	int shared = 0;
@@ -423,8 +440,8 @@ __setup_irq(unsigned int irq, struct irq_desc * desc, struct irqaction *new)
 	 * The following block of code has to be executed atomically
 	 */
 	spin_lock_irqsave(&desc->lock, flags);
-	p = &desc->action;
-	old = *p;
+	old_ptr = &desc->action;
+	old = *old_ptr;
 	if (old) {
 		/*
 		 * Can't share interrupts unless both agree to and are
@@ -447,8 +464,8 @@ __setup_irq(unsigned int irq, struct irq_desc * desc, struct irqaction *new)
 
 		/* add new interrupt at end of irq queue */
 		do {
-			p = &old->next;
-			old = *p;
+			old_ptr = &old->next;
+			old = *old_ptr;
 		} while (old);
 		shared = 1;
 	}
@@ -488,7 +505,7 @@ __setup_irq(unsigned int irq, struct irq_desc * desc, struct irqaction *new)
 			desc->status |= IRQ_NO_BALANCING;
 
 		/* Set default affinity mask once everything is setup */
-		do_irq_select_affinity(irq, desc);
+		setup_affinity(irq, desc);
 
 	} else if ((new->flags & IRQF_TRIGGER_MASK)
 			&& (new->flags & IRQF_TRIGGER_MASK)
@@ -499,7 +516,7 @@ __setup_irq(unsigned int irq, struct irq_desc * desc, struct irqaction *new)
 				(int)(new->flags & IRQF_TRIGGER_MASK));
 	}
 
-	*p = new;
+	*old_ptr = new;
 
 	/* Reset broken irq detection when installing new handler */
 	desc->irq_count = 0;
@@ -511,7 +528,7 @@ __setup_irq(unsigned int irq, struct irq_desc * desc, struct irqaction *new)
 	 */
 	if (shared && (desc->status & IRQ_SPURIOUS_DISABLED)) {
 		desc->status &= ~IRQ_SPURIOUS_DISABLED;
-		__enable_irq(desc, irq);
+		__enable_irq(desc, irq, false);
 	}
 
 	spin_unlock_irqrestore(&desc->lock, flags);
@@ -549,90 +566,117 @@ int setup_irq(unsigned int irq, struct irqaction *act)
 
 	return __setup_irq(irq, desc, act);
 }
+EXPORT_SYMBOL_GPL(setup_irq);
 
-/**
- *	free_irq - free an interrupt
- *	@irq: Interrupt line to free
- *	@dev_id: Device identity to free
- *
- *	Remove an interrupt handler. The handler is removed and if the
- *	interrupt line is no longer in use by any driver it is disabled.
- *	On a shared IRQ the caller must ensure the interrupt is disabled
- *	on the card it drives before calling this function. The function
- *	does not return until any executing interrupts for this IRQ
- *	have completed.
- *
- *	This function must not be called from interrupt context.
+ /*
+ * Internal function to unregister an irqaction - used to free
+ * regular and special interrupts that are part of the architecture.
  */
-void free_irq(unsigned int irq, void *dev_id)
+static struct irqaction *__free_irq(unsigned int irq, void *dev_id)
 {
 	struct irq_desc *desc = irq_to_desc(irq);
-	struct irqaction **p;
+	struct irqaction *action, **action_ptr;
 	unsigned long flags;
 
-	WARN_ON(in_interrupt());
+	WARN(in_interrupt(), "Trying to free IRQ %d from IRQ context!\n", irq);
 
 	if (!desc)
-		return;
+		return NULL;
 
 	spin_lock_irqsave(&desc->lock, flags);
-	p = &desc->action;
+
+	/*
+	 * There can be multiple actions per IRQ descriptor, find the right
+	 * one based on the dev_id:
+	 */
+	action_ptr = &desc->action;
 	for (;;) {
-		struct irqaction *action = *p;
+		action = *action_ptr;
 
-		if (action) {
-			struct irqaction **pp = p;
+		if (!action) {
+			WARN(1, "Trying to free already-free IRQ %d\n", irq);
+			spin_unlock_irqrestore(&desc->lock, flags);
 
-			p = &action->next;
-			if (action->dev_id != dev_id)
-				continue;
+			return NULL;
+		}
 
-			/* Found it - now remove it from the list of entries */
-			*pp = action->next;
+		if (action->dev_id == dev_id)
+			break;
+		action_ptr = &action->next;
+	}
 
-			/* Currently used only by UML, might disappear one day.*/
+	/* Found it - now remove it from the list of entries: */
+	*action_ptr = action->next;
+
+	/* Currently used only by UML, might disappear one day: */
 #ifdef CONFIG_IRQ_RELEASE_METHOD
-			if (desc->chip->release)
-				desc->chip->release(irq, dev_id);
+	if (desc->chip->release)
+		desc->chip->release(irq, dev_id);
 #endif
 
-			if (!desc->action) {
-				desc->status |= IRQ_DISABLED;
-				if (desc->chip->shutdown)
-					desc->chip->shutdown(irq);
-				else
-					desc->chip->disable(irq);
-			}
-			spin_unlock_irqrestore(&desc->lock, flags);
-			unregister_handler_proc(irq, action);
+	/* If this was the last handler, shut down the IRQ line: */
+	if (!desc->action) {
+		desc->status |= IRQ_DISABLED;
+		if (desc->chip->shutdown)
+			desc->chip->shutdown(irq);
+		else
+			desc->chip->disable(irq);
+	}
+	spin_unlock_irqrestore(&desc->lock, flags);
+
+	unregister_handler_proc(irq, action);
+
+	/* Make sure it's not being used on another CPU: */
+	synchronize_irq(irq);
 
-			/* Make sure it's not being used on another CPU */
-			synchronize_irq(irq);
-#ifdef CONFIG_DEBUG_SHIRQ
-			/*
-			 * It's a shared IRQ -- the driver ought to be
-			 * prepared for it to happen even now it's
-			 * being freed, so let's make sure....  We do
-			 * this after actually deregistering it, to
-			 * make sure that a 'real' IRQ doesn't run in
-			 * parallel with our fake
-			 */
-			if (action->flags & IRQF_SHARED) {
-				local_irq_save(flags);
-				action->handler(irq, dev_id);
-				local_irq_restore(flags);
-			}
-#endif
-			kfree(action);
-			return;
-		}
-		printk(KERN_ERR "Trying to free already-free IRQ %d\n", irq);
 #ifdef CONFIG_DEBUG_SHIRQ
-		dump_stack();
-#endif
-		spin_unlock_irqrestore(&desc->lock, flags);
-		return;
+	/*
+	 * It's a shared IRQ -- the driver ought to be prepared for an IRQ
+	 * event to happen even now it's being freed, so let's make sure that
+	 * is so by doing an extra call to the handler ....
+	 *
+	 * ( We do this after actually deregistering it, to make sure that a
+	 *   'real' IRQ doesn't run in * parallel with our fake. )
+	 */
+	if (action->flags & IRQF_SHARED) {
+		local_irq_save(flags);
+		action->handler(irq, dev_id);
+		local_irq_restore(flags);
 	}
+#endif
+	return action;
+}
+
+/**
+ *	remove_irq - free an interrupt
+ *	@irq: Interrupt line to free
+ *	@act: irqaction for the interrupt
+ *
+ * Used to remove interrupts statically setup by the early boot process.
+ */
+void remove_irq(unsigned int irq, struct irqaction *act)
+{
+	__free_irq(irq, act->dev_id);
+}
+EXPORT_SYMBOL_GPL(remove_irq);
+
+/**
+ *	free_irq - free an interrupt allocated with request_irq
+ *	@irq: Interrupt line to free
+ *	@dev_id: Device identity to free
+ *
+ *	Remove an interrupt handler. The handler is removed and if the
+ *	interrupt line is no longer in use by any driver it is disabled.
+ *	On a shared IRQ the caller must ensure the interrupt is disabled
+ *	on the card it drives before calling this function. The function
+ *	does not return until any executing interrupts for this IRQ
+ *	have completed.
+ *
+ *	This function must not be called from interrupt context.
+ */
+void free_irq(unsigned int irq, void *dev_id)
+{
+	kfree(__free_irq(irq, dev_id));
 }
 EXPORT_SYMBOL(free_irq);
 
@@ -679,11 +723,12 @@ int request_irq(unsigned int irq, irq_handler_t handler,
 	 * the behavior is classified as "will not fix" so we need to
 	 * start nudging drivers away from using that idiom.
 	 */
-	if ((irqflags & (IRQF_SHARED|IRQF_DISABLED))
-			== (IRQF_SHARED|IRQF_DISABLED))
-		pr_warning("IRQ %d/%s: IRQF_DISABLED is not "
-				"guaranteed on shared IRQs\n",
-				irq, devname);
+	if ((irqflags & (IRQF_SHARED|IRQF_DISABLED)) ==
+					(IRQF_SHARED|IRQF_DISABLED)) {
+		pr_warning(
+		  "IRQ %d/%s: IRQF_DISABLED is not guaranteed on shared IRQs\n",
+			irq, devname);
+	}
 
 #ifdef CONFIG_LOCKDEP
 	/*
@@ -709,15 +754,13 @@ int request_irq(unsigned int irq, irq_handler_t handler,
 	if (!handler)
 		return -EINVAL;
 
-	action = kmalloc(sizeof(struct irqaction), GFP_ATOMIC);
+	action = kzalloc(sizeof(struct irqaction), GFP_KERNEL);
 	if (!action)
 		return -ENOMEM;
 
 	action->handler = handler;
 	action->flags = irqflags;
-	cpus_clear(action->mask);
 	action->name = devname;
-	action->next = NULL;
 	action->dev_id = dev_id;
 
 	retval = __setup_irq(irq, desc, action);
diff --git a/kernel/irq/numa_migrate.c b/kernel/irq/numa_migrate.c
index 7f9b80434e3..243d6121e50 100644
--- a/kernel/irq/numa_migrate.c
+++ b/kernel/irq/numa_migrate.c
@@ -17,16 +17,11 @@ static void init_copy_kstat_irqs(struct irq_desc *old_desc,
 				 struct irq_desc *desc,
 				 int cpu, int nr)
 {
-	unsigned long bytes;
-
 	init_kstat_irqs(desc, cpu, nr);
 
-	if (desc->kstat_irqs != old_desc->kstat_irqs) {
-		/* Compute how many bytes we need per irq and allocate them */
-		bytes = nr * sizeof(unsigned int);
-
-		memcpy(desc->kstat_irqs, old_desc->kstat_irqs, bytes);
-	}
+	if (desc->kstat_irqs != old_desc->kstat_irqs)
+		memcpy(desc->kstat_irqs, old_desc->kstat_irqs,
+			 nr * sizeof(*desc->kstat_irqs));
 }
 
 static void free_kstat_irqs(struct irq_desc *old_desc, struct irq_desc *desc)
diff --git a/kernel/irq/pm.c b/kernel/irq/pm.c
new file mode 100644
index 00000000000..638d8bedec1
--- /dev/null
+++ b/kernel/irq/pm.c
@@ -0,0 +1,79 @@
+/*
+ * linux/kernel/irq/pm.c
+ *
+ * Copyright (C) 2009 Rafael J. Wysocki <rjw@sisk.pl>, Novell Inc.
+ *
+ * This file contains power management functions related to interrupts.
+ */
+
+#include <linux/irq.h>
+#include <linux/module.h>
+#include <linux/interrupt.h>
+
+#include "internals.h"
+
+/**
+ * suspend_device_irqs - disable all currently enabled interrupt lines
+ *
+ * During system-wide suspend or hibernation device interrupts need to be
+ * disabled at the chip level and this function is provided for this purpose.
+ * It disables all interrupt lines that are enabled at the moment and sets the
+ * IRQ_SUSPENDED flag for them.
+ */
+void suspend_device_irqs(void)
+{
+	struct irq_desc *desc;
+	int irq;
+
+	for_each_irq_desc(irq, desc) {
+		unsigned long flags;
+
+		spin_lock_irqsave(&desc->lock, flags);
+		__disable_irq(desc, irq, true);
+		spin_unlock_irqrestore(&desc->lock, flags);
+	}
+
+	for_each_irq_desc(irq, desc)
+		if (desc->status & IRQ_SUSPENDED)
+			synchronize_irq(irq);
+}
+EXPORT_SYMBOL_GPL(suspend_device_irqs);
+
+/**
+ * resume_device_irqs - enable interrupt lines disabled by suspend_device_irqs()
+ *
+ * Enable all interrupt lines previously disabled by suspend_device_irqs() that
+ * have the IRQ_SUSPENDED flag set.
+ */
+void resume_device_irqs(void)
+{
+	struct irq_desc *desc;
+	int irq;
+
+	for_each_irq_desc(irq, desc) {
+		unsigned long flags;
+
+		if (!(desc->status & IRQ_SUSPENDED))
+			continue;
+
+		spin_lock_irqsave(&desc->lock, flags);
+		__enable_irq(desc, irq, true);
+		spin_unlock_irqrestore(&desc->lock, flags);
+	}
+}
+EXPORT_SYMBOL_GPL(resume_device_irqs);
+
+/**
+ * check_wakeup_irqs - check if any wake-up interrupts are pending
+ */
+int check_wakeup_irqs(void)
+{
+	struct irq_desc *desc;
+	int irq;
+
+	for_each_irq_desc(irq, desc)
+		if ((desc->status & IRQ_WAKEUP) && (desc->status & IRQ_PENDING))
+			return -EBUSY;
+
+	return 0;
+}
diff --git a/kernel/irq/spurious.c b/kernel/irq/spurious.c
index dd364c11e56..4d568294de3 100644
--- a/kernel/irq/spurious.c
+++ b/kernel/irq/spurious.c
@@ -104,7 +104,7 @@ static int misrouted_irq(int irq)
 	return ok;
 }
 
-static void poll_spurious_irqs(unsigned long dummy)
+static void poll_all_shared_irqs(void)
 {
 	struct irq_desc *desc;
 	int i;
@@ -123,11 +123,23 @@ static void poll_spurious_irqs(unsigned long dummy)
 
 		try_one_irq(i, desc);
 	}
+}
+
+static void poll_spurious_irqs(unsigned long dummy)
+{
+	poll_all_shared_irqs();
 
 	mod_timer(&poll_spurious_irq_timer,
 		  jiffies + POLL_SPURIOUS_IRQ_INTERVAL);
 }
 
+#ifdef CONFIG_DEBUG_SHIRQ
+void debug_poll_all_shared_irqs(void)
+{
+	poll_all_shared_irqs();
+}
+#endif
+
 /*
  * If 99,900 of the previous 100,000 interrupts have not been handled
  * then assume that the IRQ is stuck in some manner. Drop a diagnostic
diff --git a/kernel/kallsyms.c b/kernel/kallsyms.c
index 7b8b0f21a5b..374faf9bfdc 100644
--- a/kernel/kallsyms.c
+++ b/kernel/kallsyms.c
@@ -161,6 +161,25 @@ unsigned long kallsyms_lookup_name(const char *name)
 	return module_kallsyms_lookup_name(name);
 }
 
+int kallsyms_on_each_symbol(int (*fn)(void *, const char *, struct module *,
+				      unsigned long),
+			    void *data)
+{
+	char namebuf[KSYM_NAME_LEN];
+	unsigned long i;
+	unsigned int off;
+	int ret;
+
+	for (i = 0, off = 0; i < kallsyms_num_syms; i++) {
+		off = kallsyms_expand_symbol(off, namebuf);
+		ret = fn(data, namebuf, NULL, kallsyms_addresses[i]);
+		if (ret != 0)
+			return ret;
+	}
+	return module_kallsyms_on_each_symbol(fn, data);
+}
+EXPORT_SYMBOL_GPL(kallsyms_on_each_symbol);
+
 static unsigned long get_symbol_pos(unsigned long addr,
 				    unsigned long *symbolsize,
 				    unsigned long *offset)
diff --git a/kernel/kexec.c b/kernel/kexec.c
index c7fd6692939..5a758c6e495 100644
--- a/kernel/kexec.c
+++ b/kernel/kexec.c
@@ -42,7 +42,7 @@
 note_buf_t* crash_notes;
 
 /* vmcoreinfo stuff */
-unsigned char vmcoreinfo_data[VMCOREINFO_BYTES];
+static unsigned char vmcoreinfo_data[VMCOREINFO_BYTES];
 u32 vmcoreinfo_note[VMCOREINFO_NOTE_SIZE/4];
 size_t vmcoreinfo_size;
 size_t vmcoreinfo_max_size = sizeof(vmcoreinfo_data);
@@ -1409,6 +1409,7 @@ static int __init crash_save_vmcoreinfo_init(void)
 	VMCOREINFO_OFFSET(list_head, prev);
 	VMCOREINFO_OFFSET(vm_struct, addr);
 	VMCOREINFO_LENGTH(zone.free_area, MAX_ORDER);
+	log_buf_kexec_setup();
 	VMCOREINFO_LENGTH(free_area.free_list, MIGRATE_TYPES);
 	VMCOREINFO_NUMBER(NR_FREE_PAGES);
 	VMCOREINFO_NUMBER(PG_lru);
@@ -1450,11 +1451,7 @@ int kernel_kexec(void)
 		error = device_suspend(PMSG_FREEZE);
 		if (error)
 			goto Resume_console;
-		error = disable_nonboot_cpus();
-		if (error)
-			goto Resume_devices;
 		device_pm_lock();
-		local_irq_disable();
 		/* At this point, device_suspend() has been called,
 		 * but *not* device_power_down(). We *must*
 		 * device_power_down() now.  Otherwise, drivers for
@@ -1464,12 +1461,15 @@ int kernel_kexec(void)
 		 */
 		error = device_power_down(PMSG_FREEZE);
 		if (error)
-			goto Enable_irqs;
-
+			goto Resume_devices;
+		error = disable_nonboot_cpus();
+		if (error)
+			goto Enable_cpus;
+		local_irq_disable();
 		/* Suspend system devices */
 		error = sysdev_suspend(PMSG_FREEZE);
 		if (error)
-			goto Power_up_devices;
+			goto Enable_irqs;
 	} else
 #endif
 	{
@@ -1483,13 +1483,13 @@ int kernel_kexec(void)
 #ifdef CONFIG_KEXEC_JUMP
 	if (kexec_image->preserve_context) {
 		sysdev_resume();
- Power_up_devices:
-		device_power_up(PMSG_RESTORE);
  Enable_irqs:
 		local_irq_enable();
-		device_pm_unlock();
+ Enable_cpus:
 		enable_nonboot_cpus();
+		device_power_up(PMSG_RESTORE);
  Resume_devices:
+		device_pm_unlock();
 		device_resume(PMSG_RESTORE);
  Resume_console:
 		resume_console();
diff --git a/kernel/kmod.c b/kernel/kmod.c
index a27a5f64443..b750675251e 100644
--- a/kernel/kmod.c
+++ b/kernel/kmod.c
@@ -50,7 +50,8 @@ static struct workqueue_struct *khelper_wq;
 char modprobe_path[KMOD_PATH_LEN] = "/sbin/modprobe";
 
 /**
- * request_module - try to load a kernel module
+ * __request_module - try to load a kernel module
+ * @wait: wait (or not) for the operation to complete
  * @fmt: printf style format string for the name of the module
  * @...: arguments as specified in the format string
  *
@@ -63,7 +64,7 @@ char modprobe_path[KMOD_PATH_LEN] = "/sbin/modprobe";
  * If module auto-loading support is disabled then this function
  * becomes a no-operation.
  */
-int request_module(const char *fmt, ...)
+int __request_module(bool wait, const char *fmt, ...)
 {
 	va_list args;
 	char module_name[MODULE_NAME_LEN];
@@ -108,11 +109,12 @@ int request_module(const char *fmt, ...)
 		return -ENOMEM;
 	}
 
-	ret = call_usermodehelper(modprobe_path, argv, envp, 1);
+	ret = call_usermodehelper(modprobe_path, argv, envp,
+			wait ? UMH_WAIT_PROC : UMH_WAIT_EXEC);
 	atomic_dec(&kmod_concurrent);
 	return ret;
 }
-EXPORT_SYMBOL(request_module);
+EXPORT_SYMBOL(__request_module);
 #endif /* CONFIG_MODULES */
 
 struct subprocess_info {
@@ -167,7 +169,7 @@ static int ____call_usermodehelper(void *data)
 	}
 
 	/* We can run anywhere, unlike our parent keventd(). */
-	set_cpus_allowed_ptr(current, CPU_MASK_ALL_PTR);
+	set_cpus_allowed_ptr(current, cpu_all_mask);
 
 	/*
 	 * Our parent is keventd, which runs with elevated scheduling priority.
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index 479d4d5672f..5016bfb682b 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -919,10 +919,8 @@ static int __kprobes pre_handler_kretprobe(struct kprobe *p,
 		ri->rp = rp;
 		ri->task = current;
 
-		if (rp->entry_handler && rp->entry_handler(ri, regs)) {
-			spin_unlock_irqrestore(&rp->lock, flags);
+		if (rp->entry_handler && rp->entry_handler(ri, regs))
 			return 0;
-		}
 
 		arch_prepare_kretprobe(ri, regs);
 
diff --git a/kernel/kthread.c b/kernel/kthread.c
index 4fbc456f393..84bbadd4d02 100644
--- a/kernel/kthread.c
+++ b/kernel/kthread.c
@@ -110,7 +110,7 @@ static void create_kthread(struct kthread_create_info *create)
 		 */
 		sched_setscheduler(create->result, SCHED_NORMAL, &param);
 		set_user_nice(create->result, KTHREAD_NICE_LEVEL);
-		set_cpus_allowed_ptr(create->result, CPU_MASK_ALL_PTR);
+		set_cpus_allowed_ptr(create->result, cpu_all_mask);
 	}
 	complete(&create->done);
 }
@@ -240,7 +240,7 @@ int kthreadd(void *unused)
 	set_task_comm(tsk, "kthreadd");
 	ignore_signals(tsk);
 	set_user_nice(tsk, KTHREAD_NICE_LEVEL);
-	set_cpus_allowed_ptr(tsk, CPU_MASK_ALL_PTR);
+	set_cpus_allowed_ptr(tsk, cpu_all_mask);
 
 	current->flags |= PF_NOFREEZE | PF_FREEZER_NOSIG;
 
diff --git a/kernel/latencytop.c b/kernel/latencytop.c
index 449db466bdb..ca07c5c0c91 100644
--- a/kernel/latencytop.c
+++ b/kernel/latencytop.c
@@ -9,6 +9,44 @@
  * as published by the Free Software Foundation; version 2
  * of the License.
  */
+
+/*
+ * CONFIG_LATENCYTOP enables a kernel latency tracking infrastructure that is
+ * used by the "latencytop" userspace tool. The latency that is tracked is not
+ * the 'traditional' interrupt latency (which is primarily caused by something
+ * else consuming CPU), but instead, it is the latency an application encounters
+ * because the kernel sleeps on its behalf for various reasons.
+ *
+ * This code tracks 2 levels of statistics:
+ * 1) System level latency
+ * 2) Per process latency
+ *
+ * The latency is stored in fixed sized data structures in an accumulated form;
+ * if the "same" latency cause is hit twice, this will be tracked as one entry
+ * in the data structure. Both the count, total accumulated latency and maximum
+ * latency are tracked in this data structure. When the fixed size structure is
+ * full, no new causes are tracked until the buffer is flushed by writing to
+ * the /proc file; the userspace tool does this on a regular basis.
+ *
+ * A latency cause is identified by a stringified backtrace at the point that
+ * the scheduler gets invoked. The userland tool will use this string to
+ * identify the cause of the latency in human readable form.
+ *
+ * The information is exported via /proc/latency_stats and /proc/<pid>/latency.
+ * These files look like this:
+ *
+ * Latency Top version : v0.1
+ * 70 59433 4897 i915_irq_wait drm_ioctl vfs_ioctl do_vfs_ioctl sys_ioctl
+ * |    |    |    |
+ * |    |    |    +----> the stringified backtrace
+ * |    |    +---------> The maximum latency for this entry in microseconds
+ * |    +--------------> The accumulated latency for this entry (microseconds)
+ * +-------------------> The number of times this entry is hit
+ *
+ * (note: the average latency is the accumulated latency divided by the number
+ * of times)
+ */
+
 #include <linux/latencytop.h>
 #include <linux/kallsyms.h>
 #include <linux/seq_file.h>
@@ -72,7 +110,7 @@ account_global_scheduler_latency(struct task_struct *tsk, struct latency_record
 				firstnonnull = i;
 			continue;
 		}
-		for (q = 0 ; q < LT_BACKTRACEDEPTH ; q++) {
+		for (q = 0; q < LT_BACKTRACEDEPTH; q++) {
 			unsigned long record = lat->backtrace[q];
 
 			if (latency_record[i].backtrace[q] != record) {
@@ -101,31 +139,52 @@ account_global_scheduler_latency(struct task_struct *tsk, struct latency_record
 	memcpy(&latency_record[i], lat, sizeof(struct latency_record));
 }
 
-static inline void store_stacktrace(struct task_struct *tsk, struct latency_record *lat)
+/*
+ * Iterator to store a backtrace into a latency record entry
+ */
+static inline void store_stacktrace(struct task_struct *tsk,
+					struct latency_record *lat)
 {
 	struct stack_trace trace;
 
 	memset(&trace, 0, sizeof(trace));
 	trace.max_entries = LT_BACKTRACEDEPTH;
 	trace.entries = &lat->backtrace[0];
-	trace.skip = 0;
 	save_stack_trace_tsk(tsk, &trace);
 }
 
+/**
+ * __account_scheduler_latency - record an occured latency
+ * @tsk - the task struct of the task hitting the latency
+ * @usecs - the duration of the latency in microseconds
+ * @inter - 1 if the sleep was interruptible, 0 if uninterruptible
+ *
+ * This function is the main entry point for recording latency entries
+ * as called by the scheduler.
+ *
+ * This function has a few special cases to deal with normal 'non-latency'
+ * sleeps: specifically, interruptible sleep longer than 5 msec is skipped
+ * since this usually is caused by waiting for events via select() and co.
+ *
+ * Negative latencies (caused by time going backwards) are also explicitly
+ * skipped.
+ */
 void __sched
-account_scheduler_latency(struct task_struct *tsk, int usecs, int inter)
+__account_scheduler_latency(struct task_struct *tsk, int usecs, int inter)
 {
 	unsigned long flags;
 	int i, q;
 	struct latency_record lat;
 
-	if (!latencytop_enabled)
-		return;
-
 	/* Long interruptible waits are generally user requested... */
 	if (inter && usecs > 5000)
 		return;
 
+	/* Negative sleeps are time going backwards */
+	/* Zero-time sleeps are non-interesting */
+	if (usecs <= 0)
+		return;
+
 	memset(&lat, 0, sizeof(lat));
 	lat.count = 1;
 	lat.time = usecs;
@@ -143,12 +202,12 @@ account_scheduler_latency(struct task_struct *tsk, int usecs, int inter)
 	if (tsk->latency_record_count >= LT_SAVECOUNT)
 		goto out_unlock;
 
-	for (i = 0; i < LT_SAVECOUNT ; i++) {
+	for (i = 0; i < LT_SAVECOUNT; i++) {
 		struct latency_record *mylat;
 		int same = 1;
 
 		mylat = &tsk->latency_record[i];
-		for (q = 0 ; q < LT_BACKTRACEDEPTH ; q++) {
+		for (q = 0; q < LT_BACKTRACEDEPTH; q++) {
 			unsigned long record = lat.backtrace[q];
 
 			if (mylat->backtrace[q] != record) {
@@ -186,7 +245,7 @@ static int lstats_show(struct seq_file *m, void *v)
 	for (i = 0; i < MAXLR; i++) {
 		if (latency_record[i].backtrace[0]) {
 			int q;
-			seq_printf(m, "%i %li %li ",
+			seq_printf(m, "%i %lu %lu ",
 				latency_record[i].count,
 				latency_record[i].time,
 				latency_record[i].max);
@@ -223,7 +282,7 @@ static int lstats_open(struct inode *inode, struct file *filp)
 	return single_open(filp, lstats_show, NULL);
 }
 
-static struct file_operations lstats_fops = {
+static const struct file_operations lstats_fops = {
 	.open		= lstats_open,
 	.read		= seq_read,
 	.write		= lstats_write,
@@ -236,4 +295,4 @@ static int __init init_lstats_procfs(void)
 	proc_create("latency_stats", 0644, NULL, &lstats_fops);
 	return 0;
 }
-__initcall(init_lstats_procfs);
+device_initcall(init_lstats_procfs);
diff --git a/kernel/lockdep.c b/kernel/lockdep.c
index 71b567f5281..b0f01186696 100644
--- a/kernel/lockdep.c
+++ b/kernel/lockdep.c
@@ -793,6 +793,7 @@ register_lock_class(struct lockdep_map *lock, unsigned int subclass, int force)
 
 		printk("BUG: MAX_LOCKDEP_KEYS too low!\n");
 		printk("turning off the locking correctness validator.\n");
+		dump_stack();
 		return NULL;
 	}
 	class = lock_classes + nr_lock_classes++;
@@ -856,6 +857,7 @@ static struct lock_list *alloc_list_entry(void)
 
 		printk("BUG: MAX_LOCKDEP_ENTRIES too low!\n");
 		printk("turning off the locking correctness validator.\n");
+		dump_stack();
 		return NULL;
 	}
 	return list_entries + nr_list_entries++;
@@ -1682,6 +1684,7 @@ cache_hit:
 
 		printk("BUG: MAX_LOCKDEP_CHAINS too low!\n");
 		printk("turning off the locking correctness validator.\n");
+		dump_stack();
 		return 0;
 	}
 	chain = lock_chains + nr_lock_chains++;
@@ -2255,7 +2258,7 @@ void trace_softirqs_off(unsigned long ip)
 		debug_atomic_inc(&redundant_softirqs_off);
 }
 
-void lockdep_trace_alloc(gfp_t gfp_mask)
+static void __lockdep_trace_alloc(gfp_t gfp_mask, unsigned long flags)
 {
 	struct task_struct *curr = current;
 
@@ -2274,12 +2277,29 @@ void lockdep_trace_alloc(gfp_t gfp_mask)
 	if (!(gfp_mask & __GFP_FS))
 		return;
 
-	if (DEBUG_LOCKS_WARN_ON(irqs_disabled()))
+	if (DEBUG_LOCKS_WARN_ON(irqs_disabled_flags(flags)))
 		return;
 
 	mark_held_locks(curr, RECLAIM_FS);
 }
 
+static void check_flags(unsigned long flags);
+
+void lockdep_trace_alloc(gfp_t gfp_mask)
+{
+	unsigned long flags;
+
+	if (unlikely(current->lockdep_recursion))
+		return;
+
+	raw_local_irq_save(flags);
+	check_flags(flags);
+	current->lockdep_recursion = 1;
+	__lockdep_trace_alloc(gfp_mask, flags);
+	current->lockdep_recursion = 0;
+	raw_local_irq_restore(flags);
+}
+
 static int mark_irqflags(struct task_struct *curr, struct held_lock *hlock)
 {
 	/*
@@ -2524,6 +2544,7 @@ static int __lock_acquire(struct lockdep_map *lock, unsigned int subclass,
 		debug_locks_off();
 		printk("BUG: MAX_LOCKDEP_SUBCLASSES too low!\n");
 		printk("turning off the locking correctness validator.\n");
+		dump_stack();
 		return 0;
 	}
 
@@ -2620,6 +2641,7 @@ static int __lock_acquire(struct lockdep_map *lock, unsigned int subclass,
 		debug_locks_off();
 		printk("BUG: MAX_LOCK_DEPTH too low!\n");
 		printk("turning off the locking correctness validator.\n");
+		dump_stack();
 		return 0;
 	}
 
diff --git a/kernel/module.c b/kernel/module.c
index 8b742f2b384..c268a771595 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -68,7 +68,8 @@
 
 /* List of modules, protected by module_mutex or preempt_disable
  * (delete uses stop_machine/add uses RCU list operations). */
-static DEFINE_MUTEX(module_mutex);
+DEFINE_MUTEX(module_mutex);
+EXPORT_SYMBOL_GPL(module_mutex);
 static LIST_HEAD(modules);
 
 /* Waiting for a module to finish initializing? */
@@ -76,7 +77,7 @@ static DECLARE_WAIT_QUEUE_HEAD(module_wq);
 
 static BLOCKING_NOTIFIER_HEAD(module_notify_list);
 
-/* Bounds of module allocation, for speeding __module_text_address */
+/* Bounds of module allocation, for speeding __module_address */
 static unsigned long module_addr_min = -1UL, module_addr_max = 0;
 
 int register_module_notifier(struct notifier_block * nb)
@@ -186,17 +187,6 @@ extern const unsigned long __start___kcrctab_unused_gpl[];
 #define symversion(base, idx) ((base != NULL) ? ((base) + (idx)) : NULL)
 #endif
 
-struct symsearch {
-	const struct kernel_symbol *start, *stop;
-	const unsigned long *crcs;
-	enum {
-		NOT_GPL_ONLY,
-		GPL_ONLY,
-		WILL_BE_GPL_ONLY,
-	} licence;
-	bool unused;
-};
-
 static bool each_symbol_in_section(const struct symsearch *arr,
 				   unsigned int arrsize,
 				   struct module *owner,
@@ -217,10 +207,8 @@ static bool each_symbol_in_section(const struct symsearch *arr,
 }
 
 /* Returns true as soon as fn returns true, otherwise false. */
-static bool each_symbol(bool (*fn)(const struct symsearch *arr,
-				   struct module *owner,
-				   unsigned int symnum, void *data),
-			void *data)
+bool each_symbol(bool (*fn)(const struct symsearch *arr, struct module *owner,
+			    unsigned int symnum, void *data), void *data)
 {
 	struct module *mod;
 	const struct symsearch arr[] = {
@@ -273,6 +261,7 @@ static bool each_symbol(bool (*fn)(const struct symsearch *arr,
 	}
 	return false;
 }
+EXPORT_SYMBOL_GPL(each_symbol);
 
 struct find_symbol_arg {
 	/* Input */
@@ -283,7 +272,7 @@ struct find_symbol_arg {
 	/* Output */
 	struct module *owner;
 	const unsigned long *crc;
-	unsigned long value;
+	const struct kernel_symbol *sym;
 };
 
 static bool find_symbol_in_section(const struct symsearch *syms,
@@ -324,17 +313,17 @@ static bool find_symbol_in_section(const struct symsearch *syms,
 
 	fsa->owner = owner;
 	fsa->crc = symversion(syms->crcs, symnum);
-	fsa->value = syms->start[symnum].value;
+	fsa->sym = &syms->start[symnum];
 	return true;
 }
 
-/* Find a symbol, return value, (optional) crc and (optional) module
- * which owns it */
-static unsigned long find_symbol(const char *name,
-				 struct module **owner,
-				 const unsigned long **crc,
-				 bool gplok,
-				 bool warn)
+/* Find a symbol and return it, along with, (optional) crc and
+ * (optional) module which owns it */
+const struct kernel_symbol *find_symbol(const char *name,
+					struct module **owner,
+					const unsigned long **crc,
+					bool gplok,
+					bool warn)
 {
 	struct find_symbol_arg fsa;
 
@@ -347,15 +336,16 @@ static unsigned long find_symbol(const char *name,
 			*owner = fsa.owner;
 		if (crc)
 			*crc = fsa.crc;
-		return fsa.value;
+		return fsa.sym;
 	}
 
 	DEBUGP("Failed to find symbol %s\n", name);
-	return -ENOENT;
+	return NULL;
 }
+EXPORT_SYMBOL_GPL(find_symbol);
 
 /* Search for module by name: must hold module_mutex. */
-static struct module *find_module(const char *name)
+struct module *find_module(const char *name)
 {
 	struct module *mod;
 
@@ -365,6 +355,7 @@ static struct module *find_module(const char *name)
 	}
 	return NULL;
 }
+EXPORT_SYMBOL_GPL(find_module);
 
 #ifdef CONFIG_SMP
 
@@ -641,7 +632,7 @@ static int already_uses(struct module *a, struct module *b)
 }
 
 /* Module a uses b */
-static int use_module(struct module *a, struct module *b)
+int use_module(struct module *a, struct module *b)
 {
 	struct module_use *use;
 	int no_warn, err;
@@ -674,6 +665,7 @@ static int use_module(struct module *a, struct module *b)
 	no_warn = sysfs_create_link(b->holders_dir, &a->mkobj.kobj, a->name);
 	return 1;
 }
+EXPORT_SYMBOL_GPL(use_module);
 
 /* Clear the unload stuff of the module. */
 static void module_unload_free(struct module *mod)
@@ -856,7 +848,7 @@ SYSCALL_DEFINE2(delete_module, const char __user *, name_user,
 	mutex_lock(&module_mutex);
 	/* Store the name of the last unloaded module for diagnostic purposes */
 	strlcpy(last_unloaded_module, mod->name, sizeof(last_unloaded_module));
-	unregister_dynamic_debug_module(mod->name);
+	ddebug_remove_module(mod->name);
 	free_module(mod);
 
  out:
@@ -894,7 +886,7 @@ void __symbol_put(const char *symbol)
 	struct module *owner;
 
 	preempt_disable();
-	if (IS_ERR_VALUE(find_symbol(symbol, &owner, NULL, true, false)))
+	if (!find_symbol(symbol, &owner, NULL, true, false))
 		BUG();
 	module_put(owner);
 	preempt_enable();
@@ -908,8 +900,10 @@ void symbol_put_addr(void *addr)
 	if (core_kernel_text((unsigned long)addr))
 		return;
 
-	if (!(modaddr = module_text_address((unsigned long)addr)))
-		BUG();
+	/* module_text_address is safe here: we're supposed to have reference
+	 * to module from symbol_get, so it can't go away. */
+	modaddr = __module_text_address((unsigned long)addr);
+	BUG_ON(!modaddr);
 	module_put(modaddr);
 }
 EXPORT_SYMBOL_GPL(symbol_put_addr);
@@ -949,10 +943,11 @@ static inline void module_unload_free(struct module *mod)
 {
 }
 
-static inline int use_module(struct module *a, struct module *b)
+int use_module(struct module *a, struct module *b)
 {
 	return strong_try_module_get(b) == 0;
 }
+EXPORT_SYMBOL_GPL(use_module);
 
 static inline void module_unload_init(struct module *mod)
 {
@@ -995,12 +990,12 @@ static struct module_attribute *modinfo_attrs[] = {
 
 static const char vermagic[] = VERMAGIC_STRING;
 
-static int try_to_force_load(struct module *mod, const char *symname)
+static int try_to_force_load(struct module *mod, const char *reason)
 {
 #ifdef CONFIG_MODULE_FORCE_LOAD
 	if (!test_taint(TAINT_FORCED_MODULE))
-		printk("%s: no version for \"%s\" found: kernel tainted.\n",
-		       mod->name, symname);
+		printk(KERN_WARNING "%s: %s: kernel tainted.\n",
+		       mod->name, reason);
 	add_taint_module(mod, TAINT_FORCED_MODULE);
 	return 0;
 #else
@@ -1057,9 +1052,9 @@ static inline int check_modstruct_version(Elf_Shdr *sechdrs,
 {
 	const unsigned long *crc;
 
-	if (IS_ERR_VALUE(find_symbol("struct_module", NULL, &crc, true, false)))
+	if (!find_symbol("module_layout", NULL, &crc, true, false))
 		BUG();
-	return check_version(sechdrs, versindex, "struct_module", mod, crc);
+	return check_version(sechdrs, versindex, "module_layout", mod, crc);
 }
 
 /* First part is kernel version, which we ignore if module has crcs. */
@@ -1098,25 +1093,25 @@ static inline int same_magic(const char *amagic, const char *bmagic,
 
 /* Resolve a symbol for this module.  I.e. if we find one, record usage.
    Must be holding module_mutex. */
-static unsigned long resolve_symbol(Elf_Shdr *sechdrs,
-				    unsigned int versindex,
-				    const char *name,
-				    struct module *mod)
+static const struct kernel_symbol *resolve_symbol(Elf_Shdr *sechdrs,
+						  unsigned int versindex,
+						  const char *name,
+						  struct module *mod)
 {
 	struct module *owner;
-	unsigned long ret;
+	const struct kernel_symbol *sym;
 	const unsigned long *crc;
 
-	ret = find_symbol(name, &owner, &crc,
+	sym = find_symbol(name, &owner, &crc,
 			  !(mod->taints & (1 << TAINT_PROPRIETARY_MODULE)), true);
-	if (!IS_ERR_VALUE(ret)) {
-		/* use_module can fail due to OOM,
-		   or module initialization or unloading */
+	/* use_module can fail due to OOM,
+	   or module initialization or unloading */
+	if (sym) {
 		if (!check_version(sechdrs, versindex, name, mod, crc) ||
 		    !use_module(mod, owner))
-			ret = -EINVAL;
+			sym = NULL;
 	}
-	return ret;
+	return sym;
 }
 
 /*
@@ -1491,6 +1486,9 @@ static void free_module(struct module *mod)
 	/* Module unload stuff */
 	module_unload_free(mod);
 
+	/* Free any allocated parameters. */
+	destroy_params(mod->kp, mod->num_kp);
+
 	/* release any pointers to mcount in this module */
 	ftrace_release(mod->module_core, mod->core_size);
 
@@ -1513,17 +1511,15 @@ static void free_module(struct module *mod)
 void *__symbol_get(const char *symbol)
 {
 	struct module *owner;
-	unsigned long value;
+	const struct kernel_symbol *sym;
 
 	preempt_disable();
-	value = find_symbol(symbol, &owner, NULL, true, true);
-	if (IS_ERR_VALUE(value))
-		value = 0;
-	else if (strong_try_module_get(owner))
-		value = 0;
+	sym = find_symbol(symbol, &owner, NULL, true, true);
+	if (sym && strong_try_module_get(owner))
+		sym = NULL;
 	preempt_enable();
 
-	return (void *)value;
+	return sym ? (void *)sym->value : NULL;
 }
 EXPORT_SYMBOL_GPL(__symbol_get);
 
@@ -1551,8 +1547,7 @@ static int verify_export_symbols(struct module *mod)
 
 	for (i = 0; i < ARRAY_SIZE(arr); i++) {
 		for (s = arr[i].sym; s < arr[i].sym + arr[i].num; s++) {
-			if (!IS_ERR_VALUE(find_symbol(s->name, &owner,
-						      NULL, true, false))) {
+			if (find_symbol(s->name, &owner, NULL, true, false)) {
 				printk(KERN_ERR
 				       "%s: exports duplicate symbol %s"
 				       " (owned by %s)\n",
@@ -1576,6 +1571,7 @@ static int simplify_symbols(Elf_Shdr *sechdrs,
 	unsigned long secbase;
 	unsigned int i, n = sechdrs[symindex].sh_size / sizeof(Elf_Sym);
 	int ret = 0;
+	const struct kernel_symbol *ksym;
 
 	for (i = 1; i < n; i++) {
 		switch (sym[i].st_shndx) {
@@ -1595,13 +1591,14 @@ static int simplify_symbols(Elf_Shdr *sechdrs,
 			break;
 
 		case SHN_UNDEF:
-			sym[i].st_value
-			  = resolve_symbol(sechdrs, versindex,
-					   strtab + sym[i].st_name, mod);
-
+			ksym = resolve_symbol(sechdrs, versindex,
+					      strtab + sym[i].st_name, mod);
 			/* Ok if resolved.  */
-			if (!IS_ERR_VALUE(sym[i].st_value))
+			if (ksym) {
+				sym[i].st_value = ksym->value;
 				break;
+			}
+
 			/* Ok if weak.  */
 			if (ELF_ST_BIND(sym[i].st_info) == STB_WEAK)
 				break;
@@ -1676,8 +1673,7 @@ static void layout_sections(struct module *mod,
 			if ((s->sh_flags & masks[m][0]) != masks[m][0]
 			    || (s->sh_flags & masks[m][1])
 			    || s->sh_entsize != ~0UL
-			    || strncmp(secstrings + s->sh_name,
-				       ".init", 5) == 0)
+			    || strstarts(secstrings + s->sh_name, ".init"))
 				continue;
 			s->sh_entsize = get_offset(mod, &mod->core_size, s, i);
 			DEBUGP("\t%s\n", secstrings + s->sh_name);
@@ -1694,8 +1690,7 @@ static void layout_sections(struct module *mod,
 			if ((s->sh_flags & masks[m][0]) != masks[m][0]
 			    || (s->sh_flags & masks[m][1])
 			    || s->sh_entsize != ~0UL
-			    || strncmp(secstrings + s->sh_name,
-				       ".init", 5) != 0)
+			    || !strstarts(secstrings + s->sh_name, ".init"))
 				continue;
 			s->sh_entsize = (get_offset(mod, &mod->init_size, s, i)
 					 | INIT_OFFSET_MASK);
@@ -1828,8 +1823,7 @@ static char elf_type(const Elf_Sym *sym,
 		else
 			return 'b';
 	}
-	if (strncmp(secstrings + sechdrs[sym->st_shndx].sh_name,
-		    ".debug", strlen(".debug")) == 0)
+	if (strstarts(secstrings + sechdrs[sym->st_shndx].sh_name, ".debug"))
 		return 'n';
 	return '?';
 }
@@ -1861,19 +1855,13 @@ static inline void add_kallsyms(struct module *mod,
 }
 #endif /* CONFIG_KALLSYMS */
 
-static void dynamic_printk_setup(struct mod_debug *debug, unsigned int num)
+static void dynamic_debug_setup(struct _ddebug *debug, unsigned int num)
 {
-#ifdef CONFIG_DYNAMIC_PRINTK_DEBUG
-	unsigned int i;
-
-	for (i = 0; i < num; i++) {
-		register_dynamic_debug_module(debug[i].modname,
-					      debug[i].type,
-					      debug[i].logical_modname,
-					      debug[i].flag_names,
-					      debug[i].hash, debug[i].hash2);
-	}
-#endif /* CONFIG_DYNAMIC_PRINTK_DEBUG */
+#ifdef CONFIG_DYNAMIC_DEBUG
+	if (ddebug_add_module(debug, num, debug->modname))
+		printk(KERN_ERR "dynamic debug error adding module: %s\n",
+					debug->modname);
+#endif
 }
 
 static void *module_alloc_update_bounds(unsigned long size)
@@ -1904,8 +1892,7 @@ static noinline struct module *load_module(void __user *umod,
 	unsigned int symindex = 0;
 	unsigned int strindex = 0;
 	unsigned int modindex, versindex, infoindex, pcpuindex;
-	unsigned int num_kp, num_mcount;
-	struct kernel_param *kp;
+	unsigned int num_mcount;
 	struct module *mod;
 	long err = 0;
 	void *percpu = NULL, *ptr = NULL; /* Stops spurious gcc warning */
@@ -1922,12 +1909,6 @@ static noinline struct module *load_module(void __user *umod,
 	if (len > 64 * 1024 * 1024 || (hdr = vmalloc(len)) == NULL)
 		return ERR_PTR(-ENOMEM);
 
-	/* Create stop_machine threads since the error path relies on
-	 * a non-failing stop_machine call. */
-	err = stop_machine_create();
-	if (err)
-		goto free_hdr;
-
 	if (copy_from_user(hdr, umod, len) != 0) {
 		err = -EFAULT;
 		goto free_hdr;
@@ -1968,9 +1949,12 @@ static noinline struct module *load_module(void __user *umod,
 		}
 #ifndef CONFIG_MODULE_UNLOAD
 		/* Don't load .exit sections */
-		if (strncmp(secstrings+sechdrs[i].sh_name, ".exit", 5) == 0)
+		if (strstarts(secstrings+sechdrs[i].sh_name, ".exit"))
 			sechdrs[i].sh_flags &= ~(unsigned long)SHF_ALLOC;
 #endif
+		/* Don't keep __versions around; it's just for loading. */
+		if (strcmp(secstrings + sechdrs[i].sh_name, "__versions") == 0)
+			sechdrs[i].sh_flags &= ~(unsigned long)SHF_ALLOC;
 	}
 
 	modindex = find_sec(hdr, sechdrs, secstrings,
@@ -2012,7 +1996,7 @@ static noinline struct module *load_module(void __user *umod,
 	modmagic = get_modinfo(sechdrs, infoindex, "vermagic");
 	/* This is allowed: modprobe --force will invalidate it. */
 	if (!modmagic) {
-		err = try_to_force_load(mod, "magic");
+		err = try_to_force_load(mod, "bad vermagic");
 		if (err)
 			goto free_hdr;
 	} else if (!same_magic(modmagic, vermagic, versindex)) {
@@ -2049,14 +2033,6 @@ static noinline struct module *load_module(void __user *umod,
 	if (err < 0)
 		goto free_mod;
 
-#if defined(CONFIG_MODULE_UNLOAD) && defined(CONFIG_SMP)
-	mod->refptr = percpu_modalloc(sizeof(local_t), __alignof__(local_t),
-				      mod->name);
-	if (!mod->refptr) {
-		err = -ENOMEM;
-		goto free_mod;
-	}
-#endif
 	if (pcpuindex) {
 		/* We have a special allocation for this section. */
 		percpu = percpu_modalloc(sechdrs[pcpuindex].sh_size,
@@ -2064,7 +2040,7 @@ static noinline struct module *load_module(void __user *umod,
 					 mod->name);
 		if (!percpu) {
 			err = -ENOMEM;
-			goto free_percpu;
+			goto free_mod;
 		}
 		sechdrs[pcpuindex].sh_flags &= ~(unsigned long)SHF_ALLOC;
 		mod->percpu = percpu;
@@ -2116,6 +2092,14 @@ static noinline struct module *load_module(void __user *umod,
 	/* Module has been moved. */
 	mod = (void *)sechdrs[modindex].sh_addr;
 
+#if defined(CONFIG_MODULE_UNLOAD) && defined(CONFIG_SMP)
+	mod->refptr = percpu_modalloc(sizeof(local_t), __alignof__(local_t),
+				      mod->name);
+	if (!mod->refptr) {
+		err = -ENOMEM;
+		goto free_init;
+	}
+#endif
 	/* Now we've moved module, initialize linked lists, etc. */
 	module_unload_init(mod);
 
@@ -2150,8 +2134,8 @@ static noinline struct module *load_module(void __user *umod,
 
 	/* Now we've got everything in the final locations, we can
 	 * find optional sections. */
-	kp = section_objs(hdr, sechdrs, secstrings, "__param", sizeof(*kp),
-			  &num_kp);
+	mod->kp = section_objs(hdr, sechdrs, secstrings, "__param",
+			       sizeof(*mod->kp), &mod->num_kp);
 	mod->syms = section_objs(hdr, sechdrs, secstrings, "__ksymtab",
 				 sizeof(*mod->syms), &mod->num_syms);
 	mod->crcs = section_addr(hdr, sechdrs, secstrings, "__kcrctab");
@@ -2201,8 +2185,8 @@ static noinline struct module *load_module(void __user *umod,
 	    || (mod->num_unused_gpl_syms && !mod->unused_gpl_crcs)
 #endif
 		) {
-		printk(KERN_WARNING "%s: No versions for exported symbols.\n", mod->name);
-		err = try_to_force_load(mod, "nocrc");
+		err = try_to_force_load(mod,
+					"no versions for exported symbols");
 		if (err)
 			goto cleanup;
 	}
@@ -2247,12 +2231,13 @@ static noinline struct module *load_module(void __user *umod,
 	add_kallsyms(mod, sechdrs, symindex, strindex, secstrings);
 
 	if (!mod->taints) {
-		struct mod_debug *debug;
+		struct _ddebug *debug;
 		unsigned int num_debug;
 
 		debug = section_objs(hdr, sechdrs, secstrings, "__verbose",
 				     sizeof(*debug), &num_debug);
-		dynamic_printk_setup(debug, num_debug);
+		if (debug)
+			dynamic_debug_setup(debug, num_debug);
 	}
 
 	/* sechdrs[0].sh_size is always zero */
@@ -2296,11 +2281,11 @@ static noinline struct module *load_module(void __user *umod,
 	 */
 	list_add_rcu(&mod->list, &modules);
 
-	err = parse_args(mod->name, mod->args, kp, num_kp, NULL);
+	err = parse_args(mod->name, mod->args, mod->kp, mod->num_kp, NULL);
 	if (err < 0)
 		goto unlink;
 
-	err = mod_sysfs_setup(mod, kp, num_kp);
+	err = mod_sysfs_setup(mod, mod->kp, mod->num_kp);
 	if (err < 0)
 		goto unlink;
 	add_sect_attrs(mod, hdr->e_shnum, secstrings, sechdrs);
@@ -2309,12 +2294,13 @@ static noinline struct module *load_module(void __user *umod,
 	/* Get rid of temporary copy */
 	vfree(hdr);
 
-	stop_machine_destroy();
 	/* Done! */
 	return mod;
 
  unlink:
-	stop_machine(__unlink_module, mod, NULL);
+	/* Unlink carefully: kallsyms could be walking list. */
+	list_del_rcu(&mod->list);
+	synchronize_sched();
 	module_arch_cleanup(mod);
  cleanup:
 	kobject_del(&mod->mkobj.kobj);
@@ -2322,20 +2308,21 @@ static noinline struct module *load_module(void __user *umod,
 	ftrace_release(mod->module_core, mod->core_size);
  free_unload:
 	module_unload_free(mod);
+#if defined(CONFIG_MODULE_UNLOAD) && defined(CONFIG_SMP)
+ free_init:
+	percpu_modfree(mod->refptr);
+#endif
 	module_free(mod, mod->module_init);
  free_core:
 	module_free(mod, mod->module_core);
+	/* mod will be freed with core. Don't access it beyond this line! */
  free_percpu:
 	if (percpu)
 		percpu_modfree(percpu);
-#if defined(CONFIG_MODULE_UNLOAD) && defined(CONFIG_SMP)
-	percpu_modfree(mod->refptr);
-#endif
  free_mod:
 	kfree(args);
  free_hdr:
 	vfree(hdr);
-	stop_machine_destroy();
 	return ERR_PTR(err);
 
  truncated:
@@ -2612,6 +2599,25 @@ unsigned long module_kallsyms_lookup_name(const char *name)
 	preempt_enable();
 	return ret;
 }
+
+int module_kallsyms_on_each_symbol(int (*fn)(void *, const char *,
+					     struct module *, unsigned long),
+				   void *data)
+{
+	struct module *mod;
+	unsigned int i;
+	int ret;
+
+	list_for_each_entry(mod, &modules, list) {
+		for (i = 0; i < mod->num_symtab; i++) {
+			ret = fn(data, mod->strtab + mod->symtab[i].st_name,
+				 mod, mod->symtab[i].st_value);
+			if (ret != 0)
+				return ret;
+		}
+	}
+	return 0;
+}
 #endif /* CONFIG_KALLSYMS */
 
 static char *module_flags(struct module *mod, char *buf)
@@ -2747,29 +2753,31 @@ const struct exception_table_entry *search_module_extables(unsigned long addr)
 }
 
 /*
- * Is this a valid module address?
+ * is_module_address - is this address inside a module?
+ * @addr: the address to check.
+ *
+ * See is_module_text_address() if you simply want to see if the address
+ * is code (not data).
  */
-int is_module_address(unsigned long addr)
+bool is_module_address(unsigned long addr)
 {
-	struct module *mod;
+	bool ret;
 
 	preempt_disable();
-
-	list_for_each_entry_rcu(mod, &modules, list) {
-		if (within_module_core(addr, mod)) {
-			preempt_enable();
-			return 1;
-		}
-	}
-
+	ret = __module_address(addr) != NULL;
 	preempt_enable();
 
-	return 0;
+	return ret;
 }
 
-
-/* Is this a valid kernel address? */
-struct module *__module_text_address(unsigned long addr)
+/*
+ * __module_address - get the module which contains an address.
+ * @addr: the address.
+ *
+ * Must be called with preempt disabled or module mutex held so that
+ * module doesn't get freed during this.
+ */
+struct module *__module_address(unsigned long addr)
 {
 	struct module *mod;
 
@@ -2777,22 +2785,51 @@ struct module *__module_text_address(unsigned long addr)
 		return NULL;
 
 	list_for_each_entry_rcu(mod, &modules, list)
-		if (within(addr, mod->module_init, mod->init_text_size)
-		    || within(addr, mod->module_core, mod->core_text_size))
+		if (within_module_core(addr, mod)
+		    || within_module_init(addr, mod))
 			return mod;
 	return NULL;
 }
+EXPORT_SYMBOL_GPL(__module_address);
 
-struct module *module_text_address(unsigned long addr)
+/*
+ * is_module_text_address - is this address inside module code?
+ * @addr: the address to check.
+ *
+ * See is_module_address() if you simply want to see if the address is
+ * anywhere in a module.  See kernel_text_address() for testing if an
+ * address corresponds to kernel or module code.
+ */
+bool is_module_text_address(unsigned long addr)
 {
-	struct module *mod;
+	bool ret;
 
 	preempt_disable();
-	mod = __module_text_address(addr);
+	ret = __module_text_address(addr) != NULL;
 	preempt_enable();
 
+	return ret;
+}
+
+/*
+ * __module_text_address - get the module whose code contains an address.
+ * @addr: the address.
+ *
+ * Must be called with preempt disabled or module mutex held so that
+ * module doesn't get freed during this.
+ */
+struct module *__module_text_address(unsigned long addr)
+{
+	struct module *mod = __module_address(addr);
+	if (mod) {
+		/* Make sure it's within the text section. */
+		if (!within(addr, mod->module_init, mod->init_text_size)
+		    && !within(addr, mod->module_core, mod->core_text_size))
+			mod = NULL;
+	}
 	return mod;
 }
+EXPORT_SYMBOL_GPL(__module_text_address);
 
 /* Don't grab lock, we're oopsing. */
 void print_modules(void)
@@ -2812,9 +2849,17 @@ void print_modules(void)
 }
 
 #ifdef CONFIG_MODVERSIONS
-/* Generate the signature for struct module here, too, for modversions. */
-void struct_module(struct module *mod) { return; }
-EXPORT_SYMBOL(struct_module);
+/* Generate the signature for all relevant module structures here.
+ * If these change, we don't want to try to parse the module. */
+void module_layout(struct module *mod,
+		   struct modversion_info *ver,
+		   struct kernel_param *kp,
+		   struct kernel_symbol *ks,
+		   struct marker *marker,
+		   struct tracepoint *tp)
+{
+}
+EXPORT_SYMBOL(module_layout);
 #endif
 
 #ifdef CONFIG_MARKERS
diff --git a/kernel/ns_cgroup.c b/kernel/ns_cgroup.c
index 78bc3fdac0d..5aa854f9e5a 100644
--- a/kernel/ns_cgroup.c
+++ b/kernel/ns_cgroup.c
@@ -34,7 +34,7 @@ int ns_cgroup_clone(struct task_struct *task, struct pid *pid)
 
 /*
  * Rules:
- *   1. you can only enter a cgroup which is a child of your current
+ *   1. you can only enter a cgroup which is a descendant of your current
  *     cgroup
  *   2. you can only place another process into a cgroup if
  *     a. you have CAP_SYS_ADMIN
@@ -45,21 +45,15 @@ int ns_cgroup_clone(struct task_struct *task, struct pid *pid)
 static int ns_can_attach(struct cgroup_subsys *ss,
 		struct cgroup *new_cgroup, struct task_struct *task)
 {
-	struct cgroup *orig;
-
 	if (current != task) {
 		if (!capable(CAP_SYS_ADMIN))
 			return -EPERM;
 
-		if (!cgroup_is_descendant(new_cgroup))
+		if (!cgroup_is_descendant(new_cgroup, current))
 			return -EPERM;
 	}
 
-	if (atomic_read(&new_cgroup->count) != 0)
-		return -EPERM;
-
-	orig = task_cgroup(task, ns_subsys_id);
-	if (orig && orig != new_cgroup->parent)
+	if (!cgroup_is_descendant(new_cgroup, task))
 		return -EPERM;
 
 	return 0;
@@ -77,7 +71,7 @@ static struct cgroup_subsys_state *ns_create(struct cgroup_subsys *ss,
 
 	if (!capable(CAP_SYS_ADMIN))
 		return ERR_PTR(-EPERM);
-	if (!cgroup_is_descendant(cgroup))
+	if (!cgroup_is_descendant(cgroup, current))
 		return ERR_PTR(-EPERM);
 
 	ns_cgroup = kzalloc(sizeof(*ns_cgroup), GFP_KERNEL);
diff --git a/kernel/panic.c b/kernel/panic.c
index 32fe4eff1b8..3fd8c5bf8b3 100644
--- a/kernel/panic.c
+++ b/kernel/panic.c
@@ -8,19 +8,19 @@
  * This function is used through-out the kernel (including mm and fs)
  * to indicate a major problem.
  */
+#include <linux/debug_locks.h>
+#include <linux/interrupt.h>
+#include <linux/kallsyms.h>
+#include <linux/notifier.h>
 #include <linux/module.h>
-#include <linux/sched.h>
-#include <linux/delay.h>
+#include <linux/random.h>
 #include <linux/reboot.h>
-#include <linux/notifier.h>
-#include <linux/init.h>
+#include <linux/delay.h>
+#include <linux/kexec.h>
+#include <linux/sched.h>
 #include <linux/sysrq.h>
-#include <linux/interrupt.h>
+#include <linux/init.h>
 #include <linux/nmi.h>
-#include <linux/kexec.h>
-#include <linux/debug_locks.h>
-#include <linux/random.h>
-#include <linux/kallsyms.h>
 #include <linux/dmi.h>
 
 int panic_on_oops;
@@ -52,19 +52,15 @@ EXPORT_SYMBOL(panic_blink);
  *
  *	This function never returns.
  */
-
 NORET_TYPE void panic(const char * fmt, ...)
 {
-	long i;
 	static char buf[1024];
 	va_list args;
-#if defined(CONFIG_S390)
-	unsigned long caller = (unsigned long) __builtin_return_address(0);
-#endif
+	long i;
 
 	/*
-	 * It's possible to come here directly from a panic-assertion and not
-	 * have preempt disabled. Some functions called from here want
+	 * It's possible to come here directly from a panic-assertion and
+	 * not have preempt disabled. Some functions called from here want
 	 * preempt to be disabled. No point enabling it later though...
 	 */
 	preempt_disable();
@@ -77,7 +73,6 @@ NORET_TYPE void panic(const char * fmt, ...)
 #ifdef CONFIG_DEBUG_BUGVERBOSE
 	dump_stack();
 #endif
-	bust_spinlocks(0);
 
 	/*
 	 * If we have crashed and we have a crash kernel loaded let it handle
@@ -86,14 +81,12 @@ NORET_TYPE void panic(const char * fmt, ...)
 	 */
 	crash_kexec(NULL);
 
-#ifdef CONFIG_SMP
 	/*
 	 * Note smp_send_stop is the usual smp shutdown function, which
 	 * unfortunately means it may not be hardened to work in a panic
 	 * situation.
 	 */
 	smp_send_stop();
-#endif
 
 	atomic_notifier_call_chain(&panic_notifier_list, 0, buf);
 
@@ -102,19 +95,21 @@ NORET_TYPE void panic(const char * fmt, ...)
 
 	if (panic_timeout > 0) {
 		/*
-	 	 * Delay timeout seconds before rebooting the machine. 
-		 * We can't use the "normal" timers since we just panicked..
-	 	 */
-		printk(KERN_EMERG "Rebooting in %d seconds..",panic_timeout);
+		 * Delay timeout seconds before rebooting the machine.
+		 * We can't use the "normal" timers since we just panicked.
+		 */
+		printk(KERN_EMERG "Rebooting in %d seconds..", panic_timeout);
+
 		for (i = 0; i < panic_timeout*1000; ) {
 			touch_nmi_watchdog();
 			i += panic_blink(i);
 			mdelay(1);
 			i++;
 		}
-		/*	This will not be a clean reboot, with everything
-		 *	shutting down.  But if there is a chance of
-		 *	rebooting the system it will be rebooted.
+		/*
+		 * This will not be a clean reboot, with everything
+		 * shutting down.  But if there is a chance of
+		 * rebooting the system it will be rebooted.
 		 */
 		emergency_restart();
 	}
@@ -127,38 +122,44 @@ NORET_TYPE void panic(const char * fmt, ...)
 	}
 #endif
 #if defined(CONFIG_S390)
-	disabled_wait(caller);
+	{
+		unsigned long caller;
+
+		caller = (unsigned long)__builtin_return_address(0);
+		disabled_wait(caller);
+	}
 #endif
 	local_irq_enable();
-	for (i = 0;;) {
+	for (i = 0; ; ) {
 		touch_softlockup_watchdog();
 		i += panic_blink(i);
 		mdelay(1);
 		i++;
 	}
+	bust_spinlocks(0);
 }
 
 EXPORT_SYMBOL(panic);
 
 
 struct tnt {
-	u8 bit;
-	char true;
-	char false;
+	u8	bit;
+	char	true;
+	char	false;
 };
 
 static const struct tnt tnts[] = {
-	{ TAINT_PROPRIETARY_MODULE, 'P', 'G' },
-	{ TAINT_FORCED_MODULE, 'F', ' ' },
-	{ TAINT_UNSAFE_SMP, 'S', ' ' },
-	{ TAINT_FORCED_RMMOD, 'R', ' ' },
-	{ TAINT_MACHINE_CHECK, 'M', ' ' },
-	{ TAINT_BAD_PAGE, 'B', ' ' },
-	{ TAINT_USER, 'U', ' ' },
-	{ TAINT_DIE, 'D', ' ' },
-	{ TAINT_OVERRIDDEN_ACPI_TABLE, 'A', ' ' },
-	{ TAINT_WARN, 'W', ' ' },
-	{ TAINT_CRAP, 'C', ' ' },
+	{ TAINT_PROPRIETARY_MODULE,	'P', 'G' },
+	{ TAINT_FORCED_MODULE,		'F', ' ' },
+	{ TAINT_UNSAFE_SMP,		'S', ' ' },
+	{ TAINT_FORCED_RMMOD,		'R', ' ' },
+	{ TAINT_MACHINE_CHECK,		'M', ' ' },
+	{ TAINT_BAD_PAGE,		'B', ' ' },
+	{ TAINT_USER,			'U', ' ' },
+	{ TAINT_DIE,			'D', ' ' },
+	{ TAINT_OVERRIDDEN_ACPI_TABLE,	'A', ' ' },
+	{ TAINT_WARN,			'W', ' ' },
+	{ TAINT_CRAP,			'C', ' ' },
 };
 
 /**
@@ -195,7 +196,8 @@ const char *print_tainted(void)
 		*s = 0;
 	} else
 		snprintf(buf, sizeof(buf), "Not tainted");
-	return(buf);
+
+	return buf;
 }
 
 int test_taint(unsigned flag)
@@ -211,7 +213,8 @@ unsigned long get_taint(void)
 
 void add_taint(unsigned flag)
 {
-	debug_locks = 0; /* can't trust the integrity of the kernel anymore */
+	/* can't trust the integrity of the kernel anymore: */
+	debug_locks = 0;
 	set_bit(flag, &tainted_mask);
 }
 EXPORT_SYMBOL(add_taint);
@@ -266,8 +269,8 @@ static void do_oops_enter_exit(void)
 }
 
 /*
- * Return true if the calling CPU is allowed to print oops-related info.  This
- * is a bit racy..
+ * Return true if the calling CPU is allowed to print oops-related info.
+ * This is a bit racy..
  */
 int oops_may_print(void)
 {
@@ -276,20 +279,22 @@ int oops_may_print(void)
 
 /*
  * Called when the architecture enters its oops handler, before it prints
- * anything.  If this is the first CPU to oops, and it's oopsing the first time
- * then let it proceed.
+ * anything.  If this is the first CPU to oops, and it's oopsing the first
+ * time then let it proceed.
  *
- * This is all enabled by the pause_on_oops kernel boot option.  We do all this
- * to ensure that oopses don't scroll off the screen.  It has the side-effect
- * of preventing later-oopsing CPUs from mucking up the display, too.
+ * This is all enabled by the pause_on_oops kernel boot option.  We do all
+ * this to ensure that oopses don't scroll off the screen.  It has the
+ * side-effect of preventing later-oopsing CPUs from mucking up the display,
+ * too.
  *
- * It turns out that the CPU which is allowed to print ends up pausing for the
- * right duration, whereas all the other CPUs pause for twice as long: once in
- * oops_enter(), once in oops_exit().
+ * It turns out that the CPU which is allowed to print ends up pausing for
+ * the right duration, whereas all the other CPUs pause for twice as long:
+ * once in oops_enter(), once in oops_exit().
  */
 void oops_enter(void)
 {
-	debug_locks_off(); /* can't trust the integrity of the kernel anymore */
+	/* can't trust the integrity of the kernel anymore: */
+	debug_locks_off();
 	do_oops_enter_exit();
 }
 
diff --git a/kernel/params.c b/kernel/params.c
index a1e3025b19a..de273ec85bd 100644
--- a/kernel/params.c
+++ b/kernel/params.c
@@ -24,6 +24,9 @@
 #include <linux/err.h>
 #include <linux/slab.h>
 
+/* We abuse the high bits of "perm" to record whether we kmalloc'ed. */
+#define KPARAM_KMALLOCED	0x80000000
+
 #if 0
 #define DEBUGP printk
 #else
@@ -217,7 +220,19 @@ int param_set_charp(const char *val, struct kernel_param *kp)
 		return -ENOSPC;
 	}
 
-	*(char **)kp->arg = (char *)val;
+	if (kp->perm & KPARAM_KMALLOCED)
+		kfree(*(char **)kp->arg);
+
+	/* This is a hack.  We can't need to strdup in early boot, and we
+	 * don't need to; this mangled commandline is preserved. */
+	if (slab_is_available()) {
+		kp->perm |= KPARAM_KMALLOCED;
+		*(char **)kp->arg = kstrdup(val, GFP_KERNEL);
+		if (!kp->arg)
+			return -ENOMEM;
+	} else
+		*(const char **)kp->arg = val;
+
 	return 0;
 }
 
@@ -571,6 +586,15 @@ void module_param_sysfs_remove(struct module *mod)
 }
 #endif
 
+void destroy_params(const struct kernel_param *params, unsigned num)
+{
+	unsigned int i;
+
+	for (i = 0; i < num; i++)
+		if (params[i].perm & KPARAM_KMALLOCED)
+			kfree(*(char **)params[i].arg);
+}
+
 static void __init kernel_add_sysfs_param(const char *name,
 					  struct kernel_param *kparam,
 					  unsigned int name_skip)
diff --git a/kernel/pid.c b/kernel/pid.c
index 1b3586fe753..b2e5f78fd28 100644
--- a/kernel/pid.c
+++ b/kernel/pid.c
@@ -403,6 +403,8 @@ struct pid *get_task_pid(struct task_struct *task, enum pid_type type)
 {
 	struct pid *pid;
 	rcu_read_lock();
+	if (type != PIDTYPE_PID)
+		task = task->group_leader;
 	pid = get_pid(task->pids[type].pid);
 	rcu_read_unlock();
 	return pid;
@@ -450,11 +452,24 @@ pid_t pid_vnr(struct pid *pid)
 }
 EXPORT_SYMBOL_GPL(pid_vnr);
 
-pid_t task_pid_nr_ns(struct task_struct *tsk, struct pid_namespace *ns)
+pid_t __task_pid_nr_ns(struct task_struct *task, enum pid_type type,
+			struct pid_namespace *ns)
 {
-	return pid_nr_ns(task_pid(tsk), ns);
+	pid_t nr = 0;
+
+	rcu_read_lock();
+	if (!ns)
+		ns = current->nsproxy->pid_ns;
+	if (likely(pid_alive(task))) {
+		if (type != PIDTYPE_PID)
+			task = task->group_leader;
+		nr = pid_nr_ns(task->pids[type].pid, ns);
+	}
+	rcu_read_unlock();
+
+	return nr;
 }
-EXPORT_SYMBOL(task_pid_nr_ns);
+EXPORT_SYMBOL(__task_pid_nr_ns);
 
 pid_t task_tgid_nr_ns(struct task_struct *tsk, struct pid_namespace *ns)
 {
@@ -462,18 +477,6 @@ pid_t task_tgid_nr_ns(struct task_struct *tsk, struct pid_namespace *ns)
 }
 EXPORT_SYMBOL(task_tgid_nr_ns);
 
-pid_t task_pgrp_nr_ns(struct task_struct *tsk, struct pid_namespace *ns)
-{
-	return pid_nr_ns(task_pgrp(tsk), ns);
-}
-EXPORT_SYMBOL(task_pgrp_nr_ns);
-
-pid_t task_session_nr_ns(struct task_struct *tsk, struct pid_namespace *ns)
-{
-	return pid_nr_ns(task_session(tsk), ns);
-}
-EXPORT_SYMBOL(task_session_nr_ns);
-
 struct pid_namespace *task_active_pid_ns(struct task_struct *tsk)
 {
 	return ns_of_pid(task_pid(tsk));
diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c
index fab8ea86fac..2d1001b4858 100644
--- a/kernel/pid_namespace.c
+++ b/kernel/pid_namespace.c
@@ -152,6 +152,7 @@ void zap_pid_ns_processes(struct pid_namespace *pid_ns)
 {
 	int nr;
 	int rc;
+	struct task_struct *task;
 
 	/*
 	 * The last thread in the cgroup-init thread group is terminating.
@@ -169,7 +170,19 @@ void zap_pid_ns_processes(struct pid_namespace *pid_ns)
 	read_lock(&tasklist_lock);
 	nr = next_pidmap(pid_ns, 1);
 	while (nr > 0) {
-		kill_proc_info(SIGKILL, SEND_SIG_PRIV, nr);
+		rcu_read_lock();
+
+		/*
+		 * Use force_sig() since it clears SIGNAL_UNKILLABLE ensuring
+		 * any nested-container's init processes don't ignore the
+		 * signal
+		 */
+		task = pid_task(find_vpid(nr), PIDTYPE_PID);
+		if (task)
+			force_sig(SIGKILL, task);
+
+		rcu_read_unlock();
+
 		nr = next_pidmap(pid_ns, nr);
 	}
 	read_unlock(&tasklist_lock);
diff --git a/kernel/posix-cpu-timers.c b/kernel/posix-cpu-timers.c
index e976e505648..8e5d9a68b02 100644
--- a/kernel/posix-cpu-timers.c
+++ b/kernel/posix-cpu-timers.c
@@ -1370,7 +1370,8 @@ static inline int fastpath_timer_check(struct task_struct *tsk)
 		if (task_cputime_expired(&group_sample, &sig->cputime_expires))
 			return 1;
 	}
-	return 0;
+
+	return sig->rlim[RLIMIT_CPU].rlim_cur != RLIM_INFINITY;
 }
 
 /*
diff --git a/kernel/power/disk.c b/kernel/power/disk.c
index 4a4a206b197..5f21ab2bbcd 100644
--- a/kernel/power/disk.c
+++ b/kernel/power/disk.c
@@ -22,6 +22,7 @@
 #include <linux/console.h>
 #include <linux/cpu.h>
 #include <linux/freezer.h>
+#include <asm/suspend.h>
 
 #include "power.h"
 
@@ -214,7 +215,7 @@ static int create_image(int platform_mode)
 		return error;
 
 	device_pm_lock();
-	local_irq_disable();
+
 	/* At this point, device_suspend() has been called, but *not*
 	 * device_power_down(). We *must* call device_power_down() now.
 	 * Otherwise, drivers for some devices (e.g. interrupt controllers)
@@ -225,13 +226,25 @@ static int create_image(int platform_mode)
 	if (error) {
 		printk(KERN_ERR "PM: Some devices failed to power down, "
 			"aborting hibernation\n");
-		goto Enable_irqs;
+		goto Unlock;
 	}
+
+	error = platform_pre_snapshot(platform_mode);
+	if (error || hibernation_test(TEST_PLATFORM))
+		goto Platform_finish;
+
+	error = disable_nonboot_cpus();
+	if (error || hibernation_test(TEST_CPUS)
+	    || hibernation_testmode(HIBERNATION_TEST))
+		goto Enable_cpus;
+
+	local_irq_disable();
+
 	sysdev_suspend(PMSG_FREEZE);
 	if (error) {
 		printk(KERN_ERR "PM: Some devices failed to power down, "
 			"aborting hibernation\n");
-		goto Power_up_devices;
+		goto Enable_irqs;
 	}
 
 	if (hibernation_test(TEST_CORE))
@@ -247,17 +260,28 @@ static int create_image(int platform_mode)
 	restore_processor_state();
 	if (!in_suspend)
 		platform_leave(platform_mode);
+
  Power_up:
 	sysdev_resume();
 	/* NOTE:  device_power_up() is just a resume() for devices
 	 * that suspended with irqs off ... no overall powerup.
 	 */
- Power_up_devices:
-	device_power_up(in_suspend ?
-		(error ? PMSG_RECOVER : PMSG_THAW) : PMSG_RESTORE);
+
  Enable_irqs:
 	local_irq_enable();
+
+ Enable_cpus:
+	enable_nonboot_cpus();
+
+ Platform_finish:
+	platform_finish(platform_mode);
+
+	device_power_up(in_suspend ?
+		(error ? PMSG_RECOVER : PMSG_THAW) : PMSG_RESTORE);
+
+ Unlock:
 	device_pm_unlock();
+
 	return error;
 }
 
@@ -265,7 +289,7 @@ static int create_image(int platform_mode)
  *	hibernation_snapshot - quiesce devices and create the hibernation
  *	snapshot image.
  *	@platform_mode - if set, use the platform driver, if available, to
- *			 prepare the platform frimware for the power transition.
+ *			 prepare the platform firmware for the power transition.
  *
  *	Must be called with pm_mutex held
  */
@@ -291,25 +315,9 @@ int hibernation_snapshot(int platform_mode)
 	if (hibernation_test(TEST_DEVICES))
 		goto Recover_platform;
 
-	error = platform_pre_snapshot(platform_mode);
-	if (error || hibernation_test(TEST_PLATFORM))
-		goto Finish;
-
-	error = disable_nonboot_cpus();
-	if (!error) {
-		if (hibernation_test(TEST_CPUS))
-			goto Enable_cpus;
-
-		if (hibernation_testmode(HIBERNATION_TEST))
-			goto Enable_cpus;
+	error = create_image(platform_mode);
+	/* Control returns here after successful restore */
 
-		error = create_image(platform_mode);
-		/* Control returns here after successful restore */
-	}
- Enable_cpus:
-	enable_nonboot_cpus();
- Finish:
-	platform_finish(platform_mode);
  Resume_devices:
 	device_resume(in_suspend ?
 		(error ? PMSG_RECOVER : PMSG_THAW) : PMSG_RESTORE);
@@ -331,19 +339,33 @@ int hibernation_snapshot(int platform_mode)
  *	kernel.
  */
 
-static int resume_target_kernel(void)
+static int resume_target_kernel(bool platform_mode)
 {
 	int error;
 
 	device_pm_lock();
-	local_irq_disable();
+
 	error = device_power_down(PMSG_QUIESCE);
 	if (error) {
 		printk(KERN_ERR "PM: Some devices failed to power down, "
 			"aborting resume\n");
-		goto Enable_irqs;
+		goto Unlock;
 	}
-	sysdev_suspend(PMSG_QUIESCE);
+
+	error = platform_pre_restore(platform_mode);
+	if (error)
+		goto Cleanup;
+
+	error = disable_nonboot_cpus();
+	if (error)
+		goto Enable_cpus;
+
+	local_irq_disable();
+
+	error = sysdev_suspend(PMSG_QUIESCE);
+	if (error)
+		goto Enable_irqs;
+
 	/* We'll ignore saved state, but this gets preempt count (etc) right */
 	save_processor_state();
 	error = restore_highmem();
@@ -366,11 +388,23 @@ static int resume_target_kernel(void)
 	swsusp_free();
 	restore_processor_state();
 	touch_softlockup_watchdog();
+
 	sysdev_resume();
-	device_power_up(PMSG_RECOVER);
+
  Enable_irqs:
 	local_irq_enable();
+
+ Enable_cpus:
+	enable_nonboot_cpus();
+
+ Cleanup:
+	platform_restore_cleanup(platform_mode);
+
+	device_power_up(PMSG_RECOVER);
+
+ Unlock:
 	device_pm_unlock();
+
 	return error;
 }
 
@@ -378,7 +412,7 @@ static int resume_target_kernel(void)
  *	hibernation_restore - quiesce devices and restore the hibernation
  *	snapshot image.  If successful, control returns in hibernation_snaphot()
  *	@platform_mode - if set, use the platform driver, if available, to
- *			 prepare the platform frimware for the transition.
+ *			 prepare the platform firmware for the transition.
  *
  *	Must be called with pm_mutex held
  */
@@ -390,19 +424,10 @@ int hibernation_restore(int platform_mode)
 	pm_prepare_console();
 	suspend_console();
 	error = device_suspend(PMSG_QUIESCE);
-	if (error)
-		goto Finish;
-
-	error = platform_pre_restore(platform_mode);
 	if (!error) {
-		error = disable_nonboot_cpus();
-		if (!error)
-			error = resume_target_kernel();
-		enable_nonboot_cpus();
+		error = resume_target_kernel(platform_mode);
+		device_resume(PMSG_RECOVER);
 	}
-	platform_restore_cleanup(platform_mode);
-	device_resume(PMSG_RECOVER);
- Finish:
 	resume_console();
 	pm_restore_console();
 	return error;
@@ -438,38 +463,46 @@ int hibernation_platform_enter(void)
 		goto Resume_devices;
 	}
 
+	device_pm_lock();
+
+	error = device_power_down(PMSG_HIBERNATE);
+	if (error)
+		goto Unlock;
+
 	error = hibernation_ops->prepare();
 	if (error)
-		goto Resume_devices;
+		goto Platofrm_finish;
 
 	error = disable_nonboot_cpus();
 	if (error)
-		goto Finish;
+		goto Platofrm_finish;
 
-	device_pm_lock();
 	local_irq_disable();
-	error = device_power_down(PMSG_HIBERNATE);
-	if (!error) {
-		sysdev_suspend(PMSG_HIBERNATE);
-		hibernation_ops->enter();
-		/* We should never get here */
-		while (1);
-	}
-	local_irq_enable();
-	device_pm_unlock();
+	sysdev_suspend(PMSG_HIBERNATE);
+	hibernation_ops->enter();
+	/* We should never get here */
+	while (1);
 
 	/*
 	 * We don't need to reenable the nonboot CPUs or resume consoles, since
 	 * the system is going to be halted anyway.
 	 */
- Finish:
+ Platofrm_finish:
 	hibernation_ops->finish();
+
+	device_power_up(PMSG_RESTORE);
+
+ Unlock:
+	device_pm_unlock();
+
  Resume_devices:
 	entering_platform_hibernation = false;
 	device_resume(PMSG_RESTORE);
 	resume_console();
+
  Close:
 	hibernation_ops->end();
+
 	return error;
 }
 
diff --git a/kernel/power/main.c b/kernel/power/main.c
index c9632f841f6..f172f41858b 100644
--- a/kernel/power/main.c
+++ b/kernel/power/main.c
@@ -287,17 +287,32 @@ void __attribute__ ((weak)) arch_suspend_enable_irqs(void)
  */
 static int suspend_enter(suspend_state_t state)
 {
-	int error = 0;
+	int error;
 
 	device_pm_lock();
-	arch_suspend_disable_irqs();
-	BUG_ON(!irqs_disabled());
 
-	if ((error = device_power_down(PMSG_SUSPEND))) {
+	error = device_power_down(PMSG_SUSPEND);
+	if (error) {
 		printk(KERN_ERR "PM: Some devices failed to power down\n");
 		goto Done;
 	}
 
+	if (suspend_ops->prepare) {
+		error = suspend_ops->prepare();
+		if (error)
+			goto Power_up_devices;
+	}
+
+	if (suspend_test(TEST_PLATFORM))
+		goto Platfrom_finish;
+
+	error = disable_nonboot_cpus();
+	if (error || suspend_test(TEST_CPUS))
+		goto Enable_cpus;
+
+	arch_suspend_disable_irqs();
+	BUG_ON(!irqs_disabled());
+
 	error = sysdev_suspend(PMSG_SUSPEND);
 	if (!error) {
 		if (!suspend_test(TEST_CORE))
@@ -305,11 +320,22 @@ static int suspend_enter(suspend_state_t state)
 		sysdev_resume();
 	}
 
-	device_power_up(PMSG_RESUME);
- Done:
 	arch_suspend_enable_irqs();
 	BUG_ON(irqs_disabled());
+
+ Enable_cpus:
+	enable_nonboot_cpus();
+
+ Platfrom_finish:
+	if (suspend_ops->finish)
+		suspend_ops->finish();
+
+ Power_up_devices:
+	device_power_up(PMSG_RESUME);
+
+ Done:
 	device_pm_unlock();
+
 	return error;
 }
 
@@ -341,23 +367,8 @@ int suspend_devices_and_enter(suspend_state_t state)
 	if (suspend_test(TEST_DEVICES))
 		goto Recover_platform;
 
-	if (suspend_ops->prepare) {
-		error = suspend_ops->prepare();
-		if (error)
-			goto Resume_devices;
-	}
-
-	if (suspend_test(TEST_PLATFORM))
-		goto Finish;
-
-	error = disable_nonboot_cpus();
-	if (!error && !suspend_test(TEST_CPUS))
-		suspend_enter(state);
+	suspend_enter(state);
 
-	enable_nonboot_cpus();
- Finish:
-	if (suspend_ops->finish)
-		suspend_ops->finish();
  Resume_devices:
 	suspend_test_start();
 	device_resume(PMSG_RESUME);
diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c
index f5fc2d7680f..33e2e4a819f 100644
--- a/kernel/power/snapshot.c
+++ b/kernel/power/snapshot.c
@@ -321,13 +321,10 @@ static int create_mem_extents(struct list_head *list, gfp_t gfp_mask)
 
 	INIT_LIST_HEAD(list);
 
-	for_each_zone(zone) {
+	for_each_populated_zone(zone) {
 		unsigned long zone_start, zone_end;
 		struct mem_extent *ext, *cur, *aux;
 
-		if (!populated_zone(zone))
-			continue;
-
 		zone_start = zone->zone_start_pfn;
 		zone_end = zone->zone_start_pfn + zone->spanned_pages;
 
@@ -804,8 +801,8 @@ static unsigned int count_free_highmem_pages(void)
 	struct zone *zone;
 	unsigned int cnt = 0;
 
-	for_each_zone(zone)
-		if (populated_zone(zone) && is_highmem(zone))
+	for_each_populated_zone(zone)
+		if (is_highmem(zone))
 			cnt += zone_page_state(zone, NR_FREE_PAGES);
 
 	return cnt;
diff --git a/kernel/power/swsusp.c b/kernel/power/swsusp.c
index a92c9145155..78c35047586 100644
--- a/kernel/power/swsusp.c
+++ b/kernel/power/swsusp.c
@@ -51,6 +51,7 @@
 #include <linux/highmem.h>
 #include <linux/time.h>
 #include <linux/rbtree.h>
+#include <linux/io.h>
 
 #include "power.h"
 
@@ -229,17 +230,16 @@ int swsusp_shrink_memory(void)
 		size = count_data_pages() + PAGES_FOR_IO + SPARE_PAGES;
 		tmp = size;
 		size += highmem_size;
-		for_each_zone (zone)
-			if (populated_zone(zone)) {
-				tmp += snapshot_additional_pages(zone);
-				if (is_highmem(zone)) {
-					highmem_size -=
+		for_each_populated_zone(zone) {
+			tmp += snapshot_additional_pages(zone);
+			if (is_highmem(zone)) {
+				highmem_size -=
 					zone_page_state(zone, NR_FREE_PAGES);
-				} else {
-					tmp -= zone_page_state(zone, NR_FREE_PAGES);
-					tmp += zone->lowmem_reserve[ZONE_NORMAL];
-				}
+			} else {
+				tmp -= zone_page_state(zone, NR_FREE_PAGES);
+				tmp += zone->lowmem_reserve[ZONE_NORMAL];
 			}
+		}
 
 		if (highmem_size < 0)
 			highmem_size = 0;
diff --git a/kernel/printk.c b/kernel/printk.c
index e3602d0755b..5052b5497c6 100644
--- a/kernel/printk.c
+++ b/kernel/printk.c
@@ -32,6 +32,7 @@
 #include <linux/security.h>
 #include <linux/bootmem.h>
 #include <linux/syscalls.h>
+#include <linux/kexec.h>
 
 #include <asm/uaccess.h>
 
@@ -135,6 +136,24 @@ static char *log_buf = __log_buf;
 static int log_buf_len = __LOG_BUF_LEN;
 static unsigned logged_chars; /* Number of chars produced since last read+clear operation */
 
+#ifdef CONFIG_KEXEC
+/*
+ * This appends the listed symbols to /proc/vmcoreinfo
+ *
+ * /proc/vmcoreinfo is used by various utiilties, like crash and makedumpfile to
+ * obtain access to symbols that are otherwise very difficult to locate.  These
+ * symbols are specifically used so that utilities can access and extract the
+ * dmesg log from a vmcore file after a crash.
+ */
+void log_buf_kexec_setup(void)
+{
+	VMCOREINFO_SYMBOL(log_buf);
+	VMCOREINFO_SYMBOL(log_end);
+	VMCOREINFO_SYMBOL(log_buf_len);
+	VMCOREINFO_SYMBOL(logged_chars);
+}
+#endif
+
 static int __init log_buf_len_setup(char *str)
 {
 	unsigned size = memparse(str, &str);
@@ -1292,8 +1311,11 @@ EXPORT_SYMBOL(printk_ratelimit);
 bool printk_timed_ratelimit(unsigned long *caller_jiffies,
 			unsigned int interval_msecs)
 {
-	if (*caller_jiffies == 0 || time_after(jiffies, *caller_jiffies)) {
-		*caller_jiffies = jiffies + msecs_to_jiffies(interval_msecs);
+	if (*caller_jiffies == 0
+			|| !time_in_range(jiffies, *caller_jiffies,
+					*caller_jiffies
+					+ msecs_to_jiffies(interval_msecs))) {
+		*caller_jiffies = jiffies;
 		return true;
 	}
 	return false;
diff --git a/kernel/ptrace.c b/kernel/ptrace.c
index c9cf48b21f0..aaad0ec3419 100644
--- a/kernel/ptrace.c
+++ b/kernel/ptrace.c
@@ -60,11 +60,15 @@ static void ptrace_untrace(struct task_struct *child)
 {
 	spin_lock(&child->sighand->siglock);
 	if (task_is_traced(child)) {
-		if (child->signal->flags & SIGNAL_STOP_STOPPED) {
+		/*
+		 * If the group stop is completed or in progress,
+		 * this thread was already counted as stopped.
+		 */
+		if (child->signal->flags & SIGNAL_STOP_STOPPED ||
+		    child->signal->group_stop_count)
 			__set_task_state(child, TASK_STOPPED);
-		} else {
+		else
 			signal_wake_up(child, 1);
-		}
 	}
 	spin_unlock(&child->sighand->siglock);
 }
@@ -235,18 +239,58 @@ out:
 	return retval;
 }
 
-static inline void __ptrace_detach(struct task_struct *child, unsigned int data)
+/*
+ * Called with irqs disabled, returns true if childs should reap themselves.
+ */
+static int ignoring_children(struct sighand_struct *sigh)
 {
-	child->exit_code = data;
-	/* .. re-parent .. */
-	__ptrace_unlink(child);
-	/* .. and wake it up. */
-	if (child->exit_state != EXIT_ZOMBIE)
-		wake_up_process(child);
+	int ret;
+	spin_lock(&sigh->siglock);
+	ret = (sigh->action[SIGCHLD-1].sa.sa_handler == SIG_IGN) ||
+	      (sigh->action[SIGCHLD-1].sa.sa_flags & SA_NOCLDWAIT);
+	spin_unlock(&sigh->siglock);
+	return ret;
+}
+
+/*
+ * Called with tasklist_lock held for writing.
+ * Unlink a traced task, and clean it up if it was a traced zombie.
+ * Return true if it needs to be reaped with release_task().
+ * (We can't call release_task() here because we already hold tasklist_lock.)
+ *
+ * If it's a zombie, our attachedness prevented normal parent notification
+ * or self-reaping.  Do notification now if it would have happened earlier.
+ * If it should reap itself, return true.
+ *
+ * If it's our own child, there is no notification to do.
+ * But if our normal children self-reap, then this child
+ * was prevented by ptrace and we must reap it now.
+ */
+static bool __ptrace_detach(struct task_struct *tracer, struct task_struct *p)
+{
+	__ptrace_unlink(p);
+
+	if (p->exit_state == EXIT_ZOMBIE) {
+		if (!task_detached(p) && thread_group_empty(p)) {
+			if (!same_thread_group(p->real_parent, tracer))
+				do_notify_parent(p, p->exit_signal);
+			else if (ignoring_children(tracer->sighand))
+				p->exit_signal = -1;
+		}
+		if (task_detached(p)) {
+			/* Mark it as in the process of being reaped. */
+			p->exit_state = EXIT_DEAD;
+			return true;
+		}
+	}
+
+	return false;
 }
 
 int ptrace_detach(struct task_struct *child, unsigned int data)
 {
+	bool dead = false;
+
 	if (!valid_signal(data))
 		return -EIO;
 
@@ -255,14 +299,45 @@ int ptrace_detach(struct task_struct *child, unsigned int data)
 	clear_tsk_thread_flag(child, TIF_SYSCALL_TRACE);
 
 	write_lock_irq(&tasklist_lock);
-	/* protect against de_thread()->release_task() */
-	if (child->ptrace)
-		__ptrace_detach(child, data);
+	/*
+	 * This child can be already killed. Make sure de_thread() or
+	 * our sub-thread doing do_wait() didn't do release_task() yet.
+	 */
+	if (child->ptrace) {
+		child->exit_code = data;
+		dead = __ptrace_detach(current, child);
+	}
 	write_unlock_irq(&tasklist_lock);
 
+	if (unlikely(dead))
+		release_task(child);
+
 	return 0;
 }
 
+/*
+ * Detach all tasks we were using ptrace on.
+ */
+void exit_ptrace(struct task_struct *tracer)
+{
+	struct task_struct *p, *n;
+	LIST_HEAD(ptrace_dead);
+
+	write_lock_irq(&tasklist_lock);
+	list_for_each_entry_safe(p, n, &tracer->ptraced, ptrace_entry) {
+		if (__ptrace_detach(tracer, p))
+			list_add(&p->ptrace_entry, &ptrace_dead);
+	}
+	write_unlock_irq(&tasklist_lock);
+
+	BUG_ON(!list_empty(&tracer->ptraced));
+
+	list_for_each_entry_safe(p, n, &ptrace_dead, ptrace_entry) {
+		list_del_init(&p->ptrace_entry);
+		release_task(p);
+	}
+}
+
 int ptrace_readdata(struct task_struct *tsk, unsigned long src, char __user *dst, int len)
 {
 	int copied = 0;
@@ -612,8 +687,6 @@ SYSCALL_DEFINE4(ptrace, long, request, long, pid, long, addr, long, data)
 		goto out_put_task_struct;
 
 	ret = arch_ptrace(child, request, addr, data);
-	if (ret < 0)
-		goto out_put_task_struct;
 
  out_put_task_struct:
 	put_task_struct(child);
diff --git a/kernel/rcuclassic.c b/kernel/rcuclassic.c
index 654c640a6b9..0f2b0b31130 100644
--- a/kernel/rcuclassic.c
+++ b/kernel/rcuclassic.c
@@ -65,6 +65,7 @@ static struct rcu_ctrlblk rcu_ctrlblk = {
 	.lock = __SPIN_LOCK_UNLOCKED(&rcu_ctrlblk.lock),
 	.cpumask = CPU_BITS_NONE,
 };
+
 static struct rcu_ctrlblk rcu_bh_ctrlblk = {
 	.cur = -300,
 	.completed = -300,
@@ -73,8 +74,26 @@ static struct rcu_ctrlblk rcu_bh_ctrlblk = {
 	.cpumask = CPU_BITS_NONE,
 };
 
-DEFINE_PER_CPU(struct rcu_data, rcu_data) = { 0L };
-DEFINE_PER_CPU(struct rcu_data, rcu_bh_data) = { 0L };
+static DEFINE_PER_CPU(struct rcu_data, rcu_data);
+static DEFINE_PER_CPU(struct rcu_data, rcu_bh_data);
+
+/*
+ * Increment the quiescent state counter.
+ * The counter is a bit degenerated: We do not need to know
+ * how many quiescent states passed, just if there was at least
+ * one since the start of the grace period. Thus just a flag.
+ */
+void rcu_qsctr_inc(int cpu)
+{
+	struct rcu_data *rdp = &per_cpu(rcu_data, cpu);
+	rdp->passed_quiesc = 1;
+}
+
+void rcu_bh_qsctr_inc(int cpu)
+{
+	struct rcu_data *rdp = &per_cpu(rcu_bh_data, cpu);
+	rdp->passed_quiesc = 1;
+}
 
 static int blimit = 10;
 static int qhimark = 10000;
diff --git a/kernel/rcupdate.c b/kernel/rcupdate.c
index cae8a059cf4..2c7b8457d0d 100644
--- a/kernel/rcupdate.c
+++ b/kernel/rcupdate.c
@@ -122,6 +122,8 @@ static void rcu_barrier_func(void *type)
 	}
 }
 
+static inline void wait_migrated_callbacks(void);
+
 /*
  * Orchestrate the specified type of RCU barrier, waiting for all
  * RCU callbacks of the specified type to complete.
@@ -147,6 +149,7 @@ static void _rcu_barrier(enum rcu_barrier type)
 		complete(&rcu_barrier_completion);
 	wait_for_completion(&rcu_barrier_completion);
 	mutex_unlock(&rcu_barrier_mutex);
+	wait_migrated_callbacks();
 }
 
 /**
@@ -176,9 +179,50 @@ void rcu_barrier_sched(void)
 }
 EXPORT_SYMBOL_GPL(rcu_barrier_sched);
 
+static atomic_t rcu_migrate_type_count = ATOMIC_INIT(0);
+static struct rcu_head rcu_migrate_head[3];
+static DECLARE_WAIT_QUEUE_HEAD(rcu_migrate_wq);
+
+static void rcu_migrate_callback(struct rcu_head *notused)
+{
+	if (atomic_dec_and_test(&rcu_migrate_type_count))
+		wake_up(&rcu_migrate_wq);
+}
+
+static inline void wait_migrated_callbacks(void)
+{
+	wait_event(rcu_migrate_wq, !atomic_read(&rcu_migrate_type_count));
+}
+
+static int __cpuinit rcu_barrier_cpu_hotplug(struct notifier_block *self,
+		unsigned long action, void *hcpu)
+{
+	if (action == CPU_DYING) {
+		/*
+		 * preempt_disable() in on_each_cpu() prevents stop_machine(),
+		 * so when "on_each_cpu(rcu_barrier_func, (void *)type, 1);"
+		 * returns, all online cpus have queued rcu_barrier_func(),
+		 * and the dead cpu(if it exist) queues rcu_migrate_callback()s.
+		 *
+		 * These callbacks ensure _rcu_barrier() waits for all
+		 * RCU callbacks of the specified type to complete.
+		 */
+		atomic_set(&rcu_migrate_type_count, 3);
+		call_rcu_bh(rcu_migrate_head, rcu_migrate_callback);
+		call_rcu_sched(rcu_migrate_head + 1, rcu_migrate_callback);
+		call_rcu(rcu_migrate_head + 2, rcu_migrate_callback);
+	} else if (action == CPU_POST_DEAD) {
+		/* rcu_migrate_head is protected by cpu_add_remove_lock */
+		wait_migrated_callbacks();
+	}
+
+	return NOTIFY_OK;
+}
+
 void __init rcu_init(void)
 {
 	__rcu_init();
+	hotcpu_notifier(rcu_barrier_cpu_hotplug, 0);
 }
 
 void rcu_scheduler_starting(void)
diff --git a/kernel/rcupreempt.c b/kernel/rcupreempt.c
index 5d59e850fb7..ce97a4df64d 100644
--- a/kernel/rcupreempt.c
+++ b/kernel/rcupreempt.c
@@ -147,7 +147,51 @@ struct rcu_ctrlblk {
 	wait_queue_head_t sched_wq;	/* Place for rcu_sched to sleep. */
 };
 
+struct rcu_dyntick_sched {
+	int dynticks;
+	int dynticks_snap;
+	int sched_qs;
+	int sched_qs_snap;
+	int sched_dynticks_snap;
+};
+
+static DEFINE_PER_CPU_SHARED_ALIGNED(struct rcu_dyntick_sched, rcu_dyntick_sched) = {
+	.dynticks = 1,
+};
+
+void rcu_qsctr_inc(int cpu)
+{
+	struct rcu_dyntick_sched *rdssp = &per_cpu(rcu_dyntick_sched, cpu);
+
+	rdssp->sched_qs++;
+}
+
+#ifdef CONFIG_NO_HZ
+
+void rcu_enter_nohz(void)
+{
+	static DEFINE_RATELIMIT_STATE(rs, 10 * HZ, 1);
+
+	smp_mb(); /* CPUs seeing ++ must see prior RCU read-side crit sects */
+	__get_cpu_var(rcu_dyntick_sched).dynticks++;
+	WARN_ON_RATELIMIT(__get_cpu_var(rcu_dyntick_sched).dynticks & 0x1, &rs);
+}
+
+void rcu_exit_nohz(void)
+{
+	static DEFINE_RATELIMIT_STATE(rs, 10 * HZ, 1);
+
+	__get_cpu_var(rcu_dyntick_sched).dynticks++;
+	smp_mb(); /* CPUs seeing ++ must see later RCU read-side crit sects */
+	WARN_ON_RATELIMIT(!(__get_cpu_var(rcu_dyntick_sched).dynticks & 0x1),
+				&rs);
+}
+
+#endif /* CONFIG_NO_HZ */
+
+
 static DEFINE_PER_CPU(struct rcu_data, rcu_data);
+
 static struct rcu_ctrlblk rcu_ctrlblk = {
 	.fliplock = __SPIN_LOCK_UNLOCKED(rcu_ctrlblk.fliplock),
 	.completed = 0,
@@ -427,10 +471,6 @@ static void __rcu_advance_callbacks(struct rcu_data *rdp)
 	}
 }
 
-DEFINE_PER_CPU_SHARED_ALIGNED(struct rcu_dyntick_sched, rcu_dyntick_sched) = {
-	.dynticks = 1,
-};
-
 #ifdef CONFIG_NO_HZ
 static DEFINE_PER_CPU(int, rcu_update_flag);
 
diff --git a/kernel/rcutorture.c b/kernel/rcutorture.c
index 7c4142a79f0..9b4a975a4b4 100644
--- a/kernel/rcutorture.c
+++ b/kernel/rcutorture.c
@@ -126,6 +126,7 @@ static atomic_t n_rcu_torture_mberror;
 static atomic_t n_rcu_torture_error;
 static long n_rcu_torture_timers = 0;
 static struct list_head rcu_torture_removed;
+static cpumask_var_t shuffle_tmp_mask;
 
 static int stutter_pause_test = 0;
 
@@ -889,10 +890,9 @@ static int rcu_idle_cpu;	/* Force all torture tasks off this CPU */
  */
 static void rcu_torture_shuffle_tasks(void)
 {
-	cpumask_t tmp_mask;
 	int i;
 
-	cpus_setall(tmp_mask);
+	cpumask_setall(shuffle_tmp_mask);
 	get_online_cpus();
 
 	/* No point in shuffling if there is only one online CPU (ex: UP) */
@@ -902,29 +902,29 @@ static void rcu_torture_shuffle_tasks(void)
 	}
 
 	if (rcu_idle_cpu != -1)
-		cpu_clear(rcu_idle_cpu, tmp_mask);
+		cpumask_clear_cpu(rcu_idle_cpu, shuffle_tmp_mask);
 
-	set_cpus_allowed_ptr(current, &tmp_mask);
+	set_cpus_allowed_ptr(current, shuffle_tmp_mask);
 
 	if (reader_tasks) {
 		for (i = 0; i < nrealreaders; i++)
 			if (reader_tasks[i])
 				set_cpus_allowed_ptr(reader_tasks[i],
-						     &tmp_mask);
+						     shuffle_tmp_mask);
 	}
 
 	if (fakewriter_tasks) {
 		for (i = 0; i < nfakewriters; i++)
 			if (fakewriter_tasks[i])
 				set_cpus_allowed_ptr(fakewriter_tasks[i],
-						     &tmp_mask);
+						     shuffle_tmp_mask);
 	}
 
 	if (writer_task)
-		set_cpus_allowed_ptr(writer_task, &tmp_mask);
+		set_cpus_allowed_ptr(writer_task, shuffle_tmp_mask);
 
 	if (stats_task)
-		set_cpus_allowed_ptr(stats_task, &tmp_mask);
+		set_cpus_allowed_ptr(stats_task, shuffle_tmp_mask);
 
 	if (rcu_idle_cpu == -1)
 		rcu_idle_cpu = num_online_cpus() - 1;
@@ -1012,6 +1012,7 @@ rcu_torture_cleanup(void)
 	if (shuffler_task) {
 		VERBOSE_PRINTK_STRING("Stopping rcu_torture_shuffle task");
 		kthread_stop(shuffler_task);
+		free_cpumask_var(shuffle_tmp_mask);
 	}
 	shuffler_task = NULL;
 
@@ -1190,10 +1191,18 @@ rcu_torture_init(void)
 	}
 	if (test_no_idle_hz) {
 		rcu_idle_cpu = num_online_cpus() - 1;
+
+		if (!alloc_cpumask_var(&shuffle_tmp_mask, GFP_KERNEL)) {
+			firsterr = -ENOMEM;
+			VERBOSE_PRINTK_ERRSTRING("Failed to alloc mask");
+			goto unwind;
+		}
+
 		/* Create the shuffler thread */
 		shuffler_task = kthread_run(rcu_torture_shuffle, NULL,
 					  "rcu_torture_shuffle");
 		if (IS_ERR(shuffler_task)) {
+			free_cpumask_var(shuffle_tmp_mask);
 			firsterr = PTR_ERR(shuffler_task);
 			VERBOSE_PRINTK_ERRSTRING("Failed to create shuffler");
 			shuffler_task = NULL;
diff --git a/kernel/rcutree.c b/kernel/rcutree.c
index 97ce31579ec..7f326692257 100644
--- a/kernel/rcutree.c
+++ b/kernel/rcutree.c
@@ -78,6 +78,26 @@ DEFINE_PER_CPU(struct rcu_data, rcu_data);
 struct rcu_state rcu_bh_state = RCU_STATE_INITIALIZER(rcu_bh_state);
 DEFINE_PER_CPU(struct rcu_data, rcu_bh_data);
 
+/*
+ * Increment the quiescent state counter.
+ * The counter is a bit degenerated: We do not need to know
+ * how many quiescent states passed, just if there was at least
+ * one since the start of the grace period. Thus just a flag.
+ */
+void rcu_qsctr_inc(int cpu)
+{
+	struct rcu_data *rdp = &per_cpu(rcu_data, cpu);
+	rdp->passed_quiesc = 1;
+	rdp->passed_quiesc_completed = rdp->completed;
+}
+
+void rcu_bh_qsctr_inc(int cpu)
+{
+	struct rcu_data *rdp = &per_cpu(rcu_bh_data, cpu);
+	rdp->passed_quiesc = 1;
+	rdp->passed_quiesc_completed = rdp->completed;
+}
+
 #ifdef CONFIG_NO_HZ
 DEFINE_PER_CPU(struct rcu_dynticks, rcu_dynticks) = {
 	.dynticks_nesting = 1,
diff --git a/kernel/rcutree.h b/kernel/rcutree.h
new file mode 100644
index 00000000000..5e872bbf07f
--- /dev/null
+++ b/kernel/rcutree.h
@@ -0,0 +1,10 @@
+
+/*
+ * RCU implementation internal declarations:
+ */
+extern struct rcu_state rcu_state;
+DECLARE_PER_CPU(struct rcu_data, rcu_data);
+
+extern struct rcu_state rcu_bh_state;
+DECLARE_PER_CPU(struct rcu_data, rcu_bh_data);
+
diff --git a/kernel/rcutree_trace.c b/kernel/rcutree_trace.c
index d6db3e83782..4ee954f6a8d 100644
--- a/kernel/rcutree_trace.c
+++ b/kernel/rcutree_trace.c
@@ -43,6 +43,8 @@
 #include <linux/debugfs.h>
 #include <linux/seq_file.h>
 
+#include "rcutree.h"
+
 static void print_one_rcu_data(struct seq_file *m, struct rcu_data *rdp)
 {
 	if (!rdp->beenonline)
diff --git a/kernel/relay.c b/kernel/relay.c
index edc0ba6d816..bc188549788 100644
--- a/kernel/relay.c
+++ b/kernel/relay.c
@@ -748,7 +748,7 @@ size_t relay_switch_subbuf(struct rchan_buf *buf, size_t length)
 			 * from the scheduler (trying to re-grab
 			 * rq->lock), so defer it.
 			 */
-			__mod_timer(&buf->timer, jiffies + 1);
+			mod_timer(&buf->timer, jiffies + 1);
 	}
 
 	old = buf->data;
@@ -795,13 +795,15 @@ void relay_subbufs_consumed(struct rchan *chan,
 	if (!chan)
 		return;
 
-	if (cpu >= NR_CPUS || !chan->buf[cpu])
+	if (cpu >= NR_CPUS || !chan->buf[cpu] ||
+					subbufs_consumed > chan->n_subbufs)
 		return;
 
 	buf = chan->buf[cpu];
-	buf->subbufs_consumed += subbufs_consumed;
-	if (buf->subbufs_consumed > buf->subbufs_produced)
+	if (subbufs_consumed > buf->subbufs_produced - buf->subbufs_consumed)
 		buf->subbufs_consumed = buf->subbufs_produced;
+	else
+		buf->subbufs_consumed += subbufs_consumed;
 }
 EXPORT_SYMBOL_GPL(relay_subbufs_consumed);
 
diff --git a/kernel/sched.c b/kernel/sched.c
index 7299083e69e..6cc1fd5d507 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -231,13 +231,20 @@ static void start_rt_bandwidth(struct rt_bandwidth *rt_b)
 
 	spin_lock(&rt_b->rt_runtime_lock);
 	for (;;) {
+		unsigned long delta;
+		ktime_t soft, hard;
+
 		if (hrtimer_active(&rt_b->rt_period_timer))
 			break;
 
 		now = hrtimer_cb_get_time(&rt_b->rt_period_timer);
 		hrtimer_forward(&rt_b->rt_period_timer, now, rt_b->rt_period);
-		hrtimer_start_expires(&rt_b->rt_period_timer,
-				HRTIMER_MODE_ABS);
+
+		soft = hrtimer_get_softexpires(&rt_b->rt_period_timer);
+		hard = hrtimer_get_expires(&rt_b->rt_period_timer);
+		delta = ktime_to_ns(ktime_sub(hard, soft));
+		__hrtimer_start_range_ns(&rt_b->rt_period_timer, soft, delta,
+				HRTIMER_MODE_ABS, 0);
 	}
 	spin_unlock(&rt_b->rt_runtime_lock);
 }
@@ -331,6 +338,13 @@ static DEFINE_PER_CPU(struct rt_rq, init_rt_rq) ____cacheline_aligned_in_smp;
  */
 static DEFINE_SPINLOCK(task_group_lock);
 
+#ifdef CONFIG_SMP
+static int root_task_group_empty(void)
+{
+	return list_empty(&root_task_group.children);
+}
+#endif
+
 #ifdef CONFIG_FAIR_GROUP_SCHED
 #ifdef CONFIG_USER_SCHED
 # define INIT_TASK_GROUP_LOAD	(2*NICE_0_LOAD)
@@ -391,6 +405,13 @@ static inline void set_task_rq(struct task_struct *p, unsigned int cpu)
 
 #else
 
+#ifdef CONFIG_SMP
+static int root_task_group_empty(void)
+{
+	return 1;
+}
+#endif
+
 static inline void set_task_rq(struct task_struct *p, unsigned int cpu) { }
 static inline struct task_group *task_group(struct task_struct *p)
 {
@@ -467,11 +488,17 @@ struct rt_rq {
 	struct rt_prio_array active;
 	unsigned long rt_nr_running;
 #if defined CONFIG_SMP || defined CONFIG_RT_GROUP_SCHED
-	int highest_prio; /* highest queued rt task prio */
+	struct {
+		int curr; /* highest queued rt task prio */
+#ifdef CONFIG_SMP
+		int next; /* next highest */
+#endif
+	} highest_prio;
 #endif
 #ifdef CONFIG_SMP
 	unsigned long rt_nr_migratory;
 	int overloaded;
+	struct plist_head pushable_tasks;
 #endif
 	int rt_throttled;
 	u64 rt_time;
@@ -549,7 +576,6 @@ struct rq {
 	unsigned long nr_running;
 	#define CPU_LOAD_IDX_MAX 5
 	unsigned long cpu_load[CPU_LOAD_IDX_MAX];
-	unsigned char idle_at_tick;
 #ifdef CONFIG_NO_HZ
 	unsigned long last_tick_seen;
 	unsigned char in_nohz_recently;
@@ -590,6 +616,7 @@ struct rq {
 	struct root_domain *rd;
 	struct sched_domain *sd;
 
+	unsigned char idle_at_tick;
 	/* For active balancing */
 	int active_balance;
 	int push_cpu;
@@ -618,9 +645,6 @@ struct rq {
 	/* could above be rq->cfs_rq.exec_clock + rq->rt_rq.rt_runtime ? */
 
 	/* sys_sched_yield() stats */
-	unsigned int yld_exp_empty;
-	unsigned int yld_act_empty;
-	unsigned int yld_both_empty;
 	unsigned int yld_count;
 
 	/* schedule() stats */
@@ -1093,7 +1117,7 @@ static void hrtick_start(struct rq *rq, u64 delay)
 	if (rq == this_rq()) {
 		hrtimer_restart(timer);
 	} else if (!rq->hrtick_csd_pending) {
-		__smp_call_function_single(cpu_of(rq), &rq->hrtick_csd);
+		__smp_call_function_single(cpu_of(rq), &rq->hrtick_csd, 0);
 		rq->hrtick_csd_pending = 1;
 	}
 }
@@ -1129,7 +1153,8 @@ static __init void init_hrtick(void)
  */
 static void hrtick_start(struct rq *rq, u64 delay)
 {
-	hrtimer_start(&rq->hrtick_timer, ns_to_ktime(delay), HRTIMER_MODE_REL);
+	__hrtimer_start_range_ns(&rq->hrtick_timer, ns_to_ktime(delay), 0,
+			HRTIMER_MODE_REL, 0);
 }
 
 static inline void init_hrtick(void)
@@ -1183,10 +1208,10 @@ static void resched_task(struct task_struct *p)
 
 	assert_spin_locked(&task_rq(p)->lock);
 
-	if (unlikely(test_tsk_thread_flag(p, TIF_NEED_RESCHED)))
+	if (test_tsk_need_resched(p))
 		return;
 
-	set_tsk_thread_flag(p, TIF_NEED_RESCHED);
+	set_tsk_need_resched(p);
 
 	cpu = task_cpu(p);
 	if (cpu == smp_processor_id())
@@ -1242,7 +1267,7 @@ void wake_up_idle_cpu(int cpu)
 	 * lockless. The worst case is that the other CPU runs the
 	 * idle task through an additional NOOP schedule()
 	 */
-	set_tsk_thread_flag(rq->idle, TIF_NEED_RESCHED);
+	set_tsk_need_resched(rq->idle);
 
 	/* NEED_RESCHED must be visible before we test polling */
 	smp_mb();
@@ -1610,21 +1635,42 @@ static inline void update_shares_locked(struct rq *rq, struct sched_domain *sd)
 
 #endif
 
+#ifdef CONFIG_PREEMPT
+
 /*
- * double_lock_balance - lock the busiest runqueue, this_rq is locked already.
+ * fair double_lock_balance: Safely acquires both rq->locks in a fair
+ * way at the expense of forcing extra atomic operations in all
+ * invocations.  This assures that the double_lock is acquired using the
+ * same underlying policy as the spinlock_t on this architecture, which
+ * reduces latency compared to the unfair variant below.  However, it
+ * also adds more overhead and therefore may reduce throughput.
  */
-static int double_lock_balance(struct rq *this_rq, struct rq *busiest)
+static inline int _double_lock_balance(struct rq *this_rq, struct rq *busiest)
+	__releases(this_rq->lock)
+	__acquires(busiest->lock)
+	__acquires(this_rq->lock)
+{
+	spin_unlock(&this_rq->lock);
+	double_rq_lock(this_rq, busiest);
+
+	return 1;
+}
+
+#else
+/*
+ * Unfair double_lock_balance: Optimizes throughput at the expense of
+ * latency by eliminating extra atomic operations when the locks are
+ * already in proper order on entry.  This favors lower cpu-ids and will
+ * grant the double lock to lower cpus over higher ids under contention,
+ * regardless of entry order into the function.
+ */
+static int _double_lock_balance(struct rq *this_rq, struct rq *busiest)
 	__releases(this_rq->lock)
 	__acquires(busiest->lock)
 	__acquires(this_rq->lock)
 {
 	int ret = 0;
 
-	if (unlikely(!irqs_disabled())) {
-		/* printk() doesn't work good under rq->lock */
-		spin_unlock(&this_rq->lock);
-		BUG_ON(1);
-	}
 	if (unlikely(!spin_trylock(&busiest->lock))) {
 		if (busiest < this_rq) {
 			spin_unlock(&this_rq->lock);
@@ -1637,6 +1683,22 @@ static int double_lock_balance(struct rq *this_rq, struct rq *busiest)
 	return ret;
 }
 
+#endif /* CONFIG_PREEMPT */
+
+/*
+ * double_lock_balance - lock the busiest runqueue, this_rq is locked already.
+ */
+static int double_lock_balance(struct rq *this_rq, struct rq *busiest)
+{
+	if (unlikely(!irqs_disabled())) {
+		/* printk() doesn't work good under rq->lock */
+		spin_unlock(&this_rq->lock);
+		BUG_ON(1);
+	}
+
+	return _double_lock_balance(this_rq, busiest);
+}
+
 static inline void double_unlock_balance(struct rq *this_rq, struct rq *busiest)
 	__releases(busiest->lock)
 {
@@ -1705,6 +1767,9 @@ static void update_avg(u64 *avg, u64 sample)
 
 static void enqueue_task(struct rq *rq, struct task_struct *p, int wakeup)
 {
+	if (wakeup)
+		p->se.start_runtime = p->se.sum_exec_runtime;
+
 	sched_info_queued(p);
 	p->sched_class->enqueue_task(rq, p, wakeup);
 	p->se.on_rq = 1;
@@ -1712,10 +1777,15 @@ static void enqueue_task(struct rq *rq, struct task_struct *p, int wakeup)
 
 static void dequeue_task(struct rq *rq, struct task_struct *p, int sleep)
 {
-	if (sleep && p->se.last_wakeup) {
-		update_avg(&p->se.avg_overlap,
-			   p->se.sum_exec_runtime - p->se.last_wakeup);
-		p->se.last_wakeup = 0;
+	if (sleep) {
+		if (p->se.last_wakeup) {
+			update_avg(&p->se.avg_overlap,
+				p->se.sum_exec_runtime - p->se.last_wakeup);
+			p->se.last_wakeup = 0;
+		} else {
+			update_avg(&p->se.avg_wakeup,
+				sysctl_sched_wakeup_granularity);
+		}
 	}
 
 	sched_info_dequeued(p);
@@ -2017,7 +2087,7 @@ unsigned long wait_task_inactive(struct task_struct *p, long match_state)
 		 * it must be off the runqueue _entirely_, and not
 		 * preempted!
 		 *
-		 * So if it wa still runnable (but just not actively
+		 * So if it was still runnable (but just not actively
 		 * running right now), it's preempted, and we should
 		 * yield - it could be a while.
 		 */
@@ -2267,7 +2337,7 @@ static int try_to_wake_up(struct task_struct *p, unsigned int state, int sync)
 		sync = 0;
 
 #ifdef CONFIG_SMP
-	if (sched_feat(LB_WAKEUP_UPDATE)) {
+	if (sched_feat(LB_WAKEUP_UPDATE) && !root_task_group_empty()) {
 		struct sched_domain *sd;
 
 		this_cpu = raw_smp_processor_id();
@@ -2345,6 +2415,22 @@ out_activate:
 	activate_task(rq, p, 1);
 	success = 1;
 
+	/*
+	 * Only attribute actual wakeups done by this task.
+	 */
+	if (!in_interrupt()) {
+		struct sched_entity *se = &current->se;
+		u64 sample = se->sum_exec_runtime;
+
+		if (se->last_wakeup)
+			sample -= se->last_wakeup;
+		else
+			sample -= se->start_runtime;
+		update_avg(&se->avg_wakeup, sample);
+
+		se->last_wakeup = se->sum_exec_runtime;
+	}
+
 out_running:
 	trace_sched_wakeup(rq, p, success);
 	check_preempt_curr(rq, p, sync);
@@ -2355,8 +2441,6 @@ out_running:
 		p->sched_class->task_wake_up(rq, p);
 #endif
 out:
-	current->se.last_wakeup = current->se.sum_exec_runtime;
-
 	task_rq_unlock(rq, &flags);
 
 	return success;
@@ -2386,6 +2470,8 @@ static void __sched_fork(struct task_struct *p)
 	p->se.prev_sum_exec_runtime	= 0;
 	p->se.last_wakeup		= 0;
 	p->se.avg_overlap		= 0;
+	p->se.start_runtime		= 0;
+	p->se.avg_wakeup		= sysctl_sched_wakeup_granularity;
 
 #ifdef CONFIG_SCHEDSTATS
 	p->se.wait_start		= 0;
@@ -2448,6 +2534,8 @@ void sched_fork(struct task_struct *p, int clone_flags)
 	/* Want to start with kernel preemption disabled. */
 	task_thread_info(p)->preempt_count = 1;
 #endif
+	plist_node_init(&p->pushable_tasks, MAX_PRIO);
+
 	put_cpu();
 }
 
@@ -2491,7 +2579,7 @@ void wake_up_new_task(struct task_struct *p, unsigned long clone_flags)
 #ifdef CONFIG_PREEMPT_NOTIFIERS
 
 /**
- * preempt_notifier_register - tell me when current is being being preempted & rescheduled
+ * preempt_notifier_register - tell me when current is being preempted & rescheduled
  * @notifier: notifier struct to register
  */
 void preempt_notifier_register(struct preempt_notifier *notifier)
@@ -2588,6 +2676,12 @@ static void finish_task_switch(struct rq *rq, struct task_struct *prev)
 {
 	struct mm_struct *mm = rq->prev_mm;
 	long prev_state;
+#ifdef CONFIG_SMP
+	int post_schedule = 0;
+
+	if (current->sched_class->needs_post_schedule)
+		post_schedule = current->sched_class->needs_post_schedule(rq);
+#endif
 
 	rq->prev_mm = NULL;
 
@@ -2606,7 +2700,7 @@ static void finish_task_switch(struct rq *rq, struct task_struct *prev)
 	finish_arch_switch(prev);
 	finish_lock_switch(rq, prev);
 #ifdef CONFIG_SMP
-	if (current->sched_class->post_schedule)
+	if (post_schedule)
 		current->sched_class->post_schedule(rq);
 #endif
 
@@ -2913,6 +3007,7 @@ int can_migrate_task(struct task_struct *p, struct rq *rq, int this_cpu,
 		     struct sched_domain *sd, enum cpu_idle_type idle,
 		     int *all_pinned)
 {
+	int tsk_cache_hot = 0;
 	/*
 	 * We do not migrate tasks that are:
 	 * 1) running (obviously), or
@@ -2936,10 +3031,11 @@ int can_migrate_task(struct task_struct *p, struct rq *rq, int this_cpu,
 	 * 2) too many balance attempts have failed.
 	 */
 
-	if (!task_hot(p, rq->clock, sd) ||
-			sd->nr_balance_failed > sd->cache_nice_tries) {
+	tsk_cache_hot = task_hot(p, rq->clock, sd);
+	if (!tsk_cache_hot ||
+		sd->nr_balance_failed > sd->cache_nice_tries) {
 #ifdef CONFIG_SCHEDSTATS
-		if (task_hot(p, rq->clock, sd)) {
+		if (tsk_cache_hot) {
 			schedstat_inc(sd, lb_hot_gained[idle]);
 			schedstat_inc(p, se.nr_forced_migrations);
 		}
@@ -2947,7 +3043,7 @@ int can_migrate_task(struct task_struct *p, struct rq *rq, int this_cpu,
 		return 1;
 	}
 
-	if (task_hot(p, rq->clock, sd)) {
+	if (tsk_cache_hot) {
 		schedstat_inc(p, se.nr_failed_migrations_hot);
 		return 0;
 	}
@@ -2987,6 +3083,16 @@ next:
 	pulled++;
 	rem_load_move -= p->se.load.weight;
 
+#ifdef CONFIG_PREEMPT
+	/*
+	 * NEWIDLE balancing is a source of latency, so preemptible kernels
+	 * will stop after the first task is pulled to minimize the critical
+	 * section.
+	 */
+	if (idle == CPU_NEWLY_IDLE)
+		goto out;
+#endif
+
 	/*
 	 * We only want to steal up to the prescribed amount of weighted load.
 	 */
@@ -3033,9 +3139,15 @@ static int move_tasks(struct rq *this_rq, int this_cpu, struct rq *busiest,
 				sd, idle, all_pinned, &this_best_prio);
 		class = class->next;
 
+#ifdef CONFIG_PREEMPT
+		/*
+		 * NEWIDLE balancing is a source of latency, so preemptible
+		 * kernels will stop after the first task is pulled to minimize
+		 * the critical section.
+		 */
 		if (idle == CPU_NEWLY_IDLE && this_rq->nr_running)
 			break;
-
+#endif
 	} while (class && max_load_move > total_load_moved);
 
 	return total_load_moved > 0;
@@ -3085,246 +3197,480 @@ static int move_one_task(struct rq *this_rq, int this_cpu, struct rq *busiest,
 
 	return 0;
 }
-
+/********** Helpers for find_busiest_group ************************/
 /*
- * find_busiest_group finds and returns the busiest CPU group within the
- * domain. It calculates and returns the amount of weighted load which
- * should be moved to restore balance via the imbalance parameter.
+ * sd_lb_stats - Structure to store the statistics of a sched_domain
+ * 		during load balancing.
  */
-static struct sched_group *
-find_busiest_group(struct sched_domain *sd, int this_cpu,
-		   unsigned long *imbalance, enum cpu_idle_type idle,
-		   int *sd_idle, const struct cpumask *cpus, int *balance)
-{
-	struct sched_group *busiest = NULL, *this = NULL, *group = sd->groups;
-	unsigned long max_load, avg_load, total_load, this_load, total_pwr;
-	unsigned long max_pull;
-	unsigned long busiest_load_per_task, busiest_nr_running;
-	unsigned long this_load_per_task, this_nr_running;
-	int load_idx, group_imb = 0;
+struct sd_lb_stats {
+	struct sched_group *busiest; /* Busiest group in this sd */
+	struct sched_group *this;  /* Local group in this sd */
+	unsigned long total_load;  /* Total load of all groups in sd */
+	unsigned long total_pwr;   /*	Total power of all groups in sd */
+	unsigned long avg_load;	   /* Average load across all groups in sd */
+
+	/** Statistics of this group */
+	unsigned long this_load;
+	unsigned long this_load_per_task;
+	unsigned long this_nr_running;
+
+	/* Statistics of the busiest group */
+	unsigned long max_load;
+	unsigned long busiest_load_per_task;
+	unsigned long busiest_nr_running;
+
+	int group_imb; /* Is there imbalance in this sd */
 #if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT)
-	int power_savings_balance = 1;
-	unsigned long leader_nr_running = 0, min_load_per_task = 0;
-	unsigned long min_nr_running = ULONG_MAX;
-	struct sched_group *group_min = NULL, *group_leader = NULL;
+	int power_savings_balance; /* Is powersave balance needed for this sd */
+	struct sched_group *group_min; /* Least loaded group in sd */
+	struct sched_group *group_leader; /* Group which relieves group_min */
+	unsigned long min_load_per_task; /* load_per_task in group_min */
+	unsigned long leader_nr_running; /* Nr running of group_leader */
+	unsigned long min_nr_running; /* Nr running of group_min */
 #endif
+};
+
+/*
+ * sg_lb_stats - stats of a sched_group required for load_balancing
+ */
+struct sg_lb_stats {
+	unsigned long avg_load; /*Avg load across the CPUs of the group */
+	unsigned long group_load; /* Total load over the CPUs of the group */
+	unsigned long sum_nr_running; /* Nr tasks running in the group */
+	unsigned long sum_weighted_load; /* Weighted load of group's tasks */
+	unsigned long group_capacity;
+	int group_imb; /* Is there an imbalance in the group ? */
+};
+
+/**
+ * group_first_cpu - Returns the first cpu in the cpumask of a sched_group.
+ * @group: The group whose first cpu is to be returned.
+ */
+static inline unsigned int group_first_cpu(struct sched_group *group)
+{
+	return cpumask_first(sched_group_cpus(group));
+}
 
-	max_load = this_load = total_load = total_pwr = 0;
-	busiest_load_per_task = busiest_nr_running = 0;
-	this_load_per_task = this_nr_running = 0;
+/**
+ * get_sd_load_idx - Obtain the load index for a given sched domain.
+ * @sd: The sched_domain whose load_idx is to be obtained.
+ * @idle: The Idle status of the CPU for whose sd load_icx is obtained.
+ */
+static inline int get_sd_load_idx(struct sched_domain *sd,
+					enum cpu_idle_type idle)
+{
+	int load_idx;
 
-	if (idle == CPU_NOT_IDLE)
+	switch (idle) {
+	case CPU_NOT_IDLE:
 		load_idx = sd->busy_idx;
-	else if (idle == CPU_NEWLY_IDLE)
+		break;
+
+	case CPU_NEWLY_IDLE:
 		load_idx = sd->newidle_idx;
-	else
+		break;
+	default:
 		load_idx = sd->idle_idx;
+		break;
+	}
 
-	do {
-		unsigned long load, group_capacity, max_cpu_load, min_cpu_load;
-		int local_group;
-		int i;
-		int __group_imb = 0;
-		unsigned int balance_cpu = -1, first_idle_cpu = 0;
-		unsigned long sum_nr_running, sum_weighted_load;
-		unsigned long sum_avg_load_per_task;
-		unsigned long avg_load_per_task;
+	return load_idx;
+}
 
-		local_group = cpumask_test_cpu(this_cpu,
-					       sched_group_cpus(group));
 
-		if (local_group)
-			balance_cpu = cpumask_first(sched_group_cpus(group));
+#if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT)
+/**
+ * init_sd_power_savings_stats - Initialize power savings statistics for
+ * the given sched_domain, during load balancing.
+ *
+ * @sd: Sched domain whose power-savings statistics are to be initialized.
+ * @sds: Variable containing the statistics for sd.
+ * @idle: Idle status of the CPU at which we're performing load-balancing.
+ */
+static inline void init_sd_power_savings_stats(struct sched_domain *sd,
+	struct sd_lb_stats *sds, enum cpu_idle_type idle)
+{
+	/*
+	 * Busy processors will not participate in power savings
+	 * balance.
+	 */
+	if (idle == CPU_NOT_IDLE || !(sd->flags & SD_POWERSAVINGS_BALANCE))
+		sds->power_savings_balance = 0;
+	else {
+		sds->power_savings_balance = 1;
+		sds->min_nr_running = ULONG_MAX;
+		sds->leader_nr_running = 0;
+	}
+}
+
+/**
+ * update_sd_power_savings_stats - Update the power saving stats for a
+ * sched_domain while performing load balancing.
+ *
+ * @group: sched_group belonging to the sched_domain under consideration.
+ * @sds: Variable containing the statistics of the sched_domain
+ * @local_group: Does group contain the CPU for which we're performing
+ * 		load balancing ?
+ * @sgs: Variable containing the statistics of the group.
+ */
+static inline void update_sd_power_savings_stats(struct sched_group *group,
+	struct sd_lb_stats *sds, int local_group, struct sg_lb_stats *sgs)
+{
 
-		/* Tally up the load of all CPUs in the group */
-		sum_weighted_load = sum_nr_running = avg_load = 0;
-		sum_avg_load_per_task = avg_load_per_task = 0;
+	if (!sds->power_savings_balance)
+		return;
 
-		max_cpu_load = 0;
-		min_cpu_load = ~0UL;
+	/*
+	 * If the local group is idle or completely loaded
+	 * no need to do power savings balance at this domain
+	 */
+	if (local_group && (sds->this_nr_running >= sgs->group_capacity ||
+				!sds->this_nr_running))
+		sds->power_savings_balance = 0;
 
-		for_each_cpu_and(i, sched_group_cpus(group), cpus) {
-			struct rq *rq = cpu_rq(i);
+	/*
+	 * If a group is already running at full capacity or idle,
+	 * don't include that group in power savings calculations
+	 */
+	if (!sds->power_savings_balance ||
+		sgs->sum_nr_running >= sgs->group_capacity ||
+		!sgs->sum_nr_running)
+		return;
 
-			if (*sd_idle && rq->nr_running)
-				*sd_idle = 0;
+	/*
+	 * Calculate the group which has the least non-idle load.
+	 * This is the group from where we need to pick up the load
+	 * for saving power
+	 */
+	if ((sgs->sum_nr_running < sds->min_nr_running) ||
+	    (sgs->sum_nr_running == sds->min_nr_running &&
+	     group_first_cpu(group) > group_first_cpu(sds->group_min))) {
+		sds->group_min = group;
+		sds->min_nr_running = sgs->sum_nr_running;
+		sds->min_load_per_task = sgs->sum_weighted_load /
+						sgs->sum_nr_running;
+	}
 
-			/* Bias balancing toward cpus of our domain */
-			if (local_group) {
-				if (idle_cpu(i) && !first_idle_cpu) {
-					first_idle_cpu = 1;
-					balance_cpu = i;
-				}
+	/*
+	 * Calculate the group which is almost near its
+	 * capacity but still has some space to pick up some load
+	 * from other group and save more power
+	 */
+	if (sgs->sum_nr_running > sgs->group_capacity - 1)
+		return;
 
-				load = target_load(i, load_idx);
-			} else {
-				load = source_load(i, load_idx);
-				if (load > max_cpu_load)
-					max_cpu_load = load;
-				if (min_cpu_load > load)
-					min_cpu_load = load;
-			}
+	if (sgs->sum_nr_running > sds->leader_nr_running ||
+	    (sgs->sum_nr_running == sds->leader_nr_running &&
+	     group_first_cpu(group) < group_first_cpu(sds->group_leader))) {
+		sds->group_leader = group;
+		sds->leader_nr_running = sgs->sum_nr_running;
+	}
+}
 
-			avg_load += load;
-			sum_nr_running += rq->nr_running;
-			sum_weighted_load += weighted_cpuload(i);
+/**
+ * check_power_save_busiest_group - see if there is potential for some power-savings balance
+ * @sds: Variable containing the statistics of the sched_domain
+ *	under consideration.
+ * @this_cpu: Cpu at which we're currently performing load-balancing.
+ * @imbalance: Variable to store the imbalance.
+ *
+ * Description:
+ * Check if we have potential to perform some power-savings balance.
+ * If yes, set the busiest group to be the least loaded group in the
+ * sched_domain, so that it's CPUs can be put to idle.
+ *
+ * Returns 1 if there is potential to perform power-savings balance.
+ * Else returns 0.
+ */
+static inline int check_power_save_busiest_group(struct sd_lb_stats *sds,
+					int this_cpu, unsigned long *imbalance)
+{
+	if (!sds->power_savings_balance)
+		return 0;
 
-			sum_avg_load_per_task += cpu_avg_load_per_task(i);
-		}
+	if (sds->this != sds->group_leader ||
+			sds->group_leader == sds->group_min)
+		return 0;
 
-		/*
-		 * First idle cpu or the first cpu(busiest) in this sched group
-		 * is eligible for doing load balancing at this and above
-		 * domains. In the newly idle case, we will allow all the cpu's
-		 * to do the newly idle load balance.
-		 */
-		if (idle != CPU_NEWLY_IDLE && local_group &&
-		    balance_cpu != this_cpu && balance) {
-			*balance = 0;
-			goto ret;
-		}
+	*imbalance = sds->min_load_per_task;
+	sds->busiest = sds->group_min;
 
-		total_load += avg_load;
-		total_pwr += group->__cpu_power;
+	if (sched_mc_power_savings >= POWERSAVINGS_BALANCE_WAKEUP) {
+		cpu_rq(this_cpu)->rd->sched_mc_preferred_wakeup_cpu =
+			group_first_cpu(sds->group_leader);
+	}
 
-		/* Adjust by relative CPU power of the group */
-		avg_load = sg_div_cpu_power(group,
-				avg_load * SCHED_LOAD_SCALE);
+	return 1;
 
+}
+#else /* CONFIG_SCHED_MC || CONFIG_SCHED_SMT */
+static inline void init_sd_power_savings_stats(struct sched_domain *sd,
+	struct sd_lb_stats *sds, enum cpu_idle_type idle)
+{
+	return;
+}
 
-		/*
-		 * Consider the group unbalanced when the imbalance is larger
-		 * than the average weight of two tasks.
-		 *
-		 * APZ: with cgroup the avg task weight can vary wildly and
-		 *      might not be a suitable number - should we keep a
-		 *      normalized nr_running number somewhere that negates
-		 *      the hierarchy?
-		 */
-		avg_load_per_task = sg_div_cpu_power(group,
-				sum_avg_load_per_task * SCHED_LOAD_SCALE);
+static inline void update_sd_power_savings_stats(struct sched_group *group,
+	struct sd_lb_stats *sds, int local_group, struct sg_lb_stats *sgs)
+{
+	return;
+}
+
+static inline int check_power_save_busiest_group(struct sd_lb_stats *sds,
+					int this_cpu, unsigned long *imbalance)
+{
+	return 0;
+}
+#endif /* CONFIG_SCHED_MC || CONFIG_SCHED_SMT */
+
+
+/**
+ * update_sg_lb_stats - Update sched_group's statistics for load balancing.
+ * @group: sched_group whose statistics are to be updated.
+ * @this_cpu: Cpu for which load balance is currently performed.
+ * @idle: Idle status of this_cpu
+ * @load_idx: Load index of sched_domain of this_cpu for load calc.
+ * @sd_idle: Idle status of the sched_domain containing group.
+ * @local_group: Does group contain this_cpu.
+ * @cpus: Set of cpus considered for load balancing.
+ * @balance: Should we balance.
+ * @sgs: variable to hold the statistics for this group.
+ */
+static inline void update_sg_lb_stats(struct sched_group *group, int this_cpu,
+			enum cpu_idle_type idle, int load_idx, int *sd_idle,
+			int local_group, const struct cpumask *cpus,
+			int *balance, struct sg_lb_stats *sgs)
+{
+	unsigned long load, max_cpu_load, min_cpu_load;
+	int i;
+	unsigned int balance_cpu = -1, first_idle_cpu = 0;
+	unsigned long sum_avg_load_per_task;
+	unsigned long avg_load_per_task;
+
+	if (local_group)
+		balance_cpu = group_first_cpu(group);
+
+	/* Tally up the load of all CPUs in the group */
+	sum_avg_load_per_task = avg_load_per_task = 0;
+	max_cpu_load = 0;
+	min_cpu_load = ~0UL;
 
-		if ((max_cpu_load - min_cpu_load) > 2*avg_load_per_task)
-			__group_imb = 1;
+	for_each_cpu_and(i, sched_group_cpus(group), cpus) {
+		struct rq *rq = cpu_rq(i);
 
-		group_capacity = group->__cpu_power / SCHED_LOAD_SCALE;
+		if (*sd_idle && rq->nr_running)
+			*sd_idle = 0;
 
+		/* Bias balancing toward cpus of our domain */
 		if (local_group) {
-			this_load = avg_load;
-			this = group;
-			this_nr_running = sum_nr_running;
-			this_load_per_task = sum_weighted_load;
-		} else if (avg_load > max_load &&
-			   (sum_nr_running > group_capacity || __group_imb)) {
-			max_load = avg_load;
-			busiest = group;
-			busiest_nr_running = sum_nr_running;
-			busiest_load_per_task = sum_weighted_load;
-			group_imb = __group_imb;
+			if (idle_cpu(i) && !first_idle_cpu) {
+				first_idle_cpu = 1;
+				balance_cpu = i;
+			}
+
+			load = target_load(i, load_idx);
+		} else {
+			load = source_load(i, load_idx);
+			if (load > max_cpu_load)
+				max_cpu_load = load;
+			if (min_cpu_load > load)
+				min_cpu_load = load;
 		}
 
-#if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT)
-		/*
-		 * Busy processors will not participate in power savings
-		 * balance.
-		 */
-		if (idle == CPU_NOT_IDLE ||
-				!(sd->flags & SD_POWERSAVINGS_BALANCE))
-			goto group_next;
+		sgs->group_load += load;
+		sgs->sum_nr_running += rq->nr_running;
+		sgs->sum_weighted_load += weighted_cpuload(i);
 
-		/*
-		 * If the local group is idle or completely loaded
-		 * no need to do power savings balance at this domain
-		 */
-		if (local_group && (this_nr_running >= group_capacity ||
-				    !this_nr_running))
-			power_savings_balance = 0;
+		sum_avg_load_per_task += cpu_avg_load_per_task(i);
+	}
 
-		/*
-		 * If a group is already running at full capacity or idle,
-		 * don't include that group in power savings calculations
-		 */
-		if (!power_savings_balance || sum_nr_running >= group_capacity
-		    || !sum_nr_running)
-			goto group_next;
+	/*
+	 * First idle cpu or the first cpu(busiest) in this sched group
+	 * is eligible for doing load balancing at this and above
+	 * domains. In the newly idle case, we will allow all the cpu's
+	 * to do the newly idle load balance.
+	 */
+	if (idle != CPU_NEWLY_IDLE && local_group &&
+	    balance_cpu != this_cpu && balance) {
+		*balance = 0;
+		return;
+	}
 
-		/*
-		 * Calculate the group which has the least non-idle load.
-		 * This is the group from where we need to pick up the load
-		 * for saving power
-		 */
-		if ((sum_nr_running < min_nr_running) ||
-		    (sum_nr_running == min_nr_running &&
-		     cpumask_first(sched_group_cpus(group)) >
-		     cpumask_first(sched_group_cpus(group_min)))) {
-			group_min = group;
-			min_nr_running = sum_nr_running;
-			min_load_per_task = sum_weighted_load /
-						sum_nr_running;
-		}
+	/* Adjust by relative CPU power of the group */
+	sgs->avg_load = sg_div_cpu_power(group,
+			sgs->group_load * SCHED_LOAD_SCALE);
 
-		/*
-		 * Calculate the group which is almost near its
-		 * capacity but still has some space to pick up some load
-		 * from other group and save more power
-		 */
-		if (sum_nr_running <= group_capacity - 1) {
-			if (sum_nr_running > leader_nr_running ||
-			    (sum_nr_running == leader_nr_running &&
-			     cpumask_first(sched_group_cpus(group)) <
-			     cpumask_first(sched_group_cpus(group_leader)))) {
-				group_leader = group;
-				leader_nr_running = sum_nr_running;
-			}
+
+	/*
+	 * Consider the group unbalanced when the imbalance is larger
+	 * than the average weight of two tasks.
+	 *
+	 * APZ: with cgroup the avg task weight can vary wildly and
+	 *      might not be a suitable number - should we keep a
+	 *      normalized nr_running number somewhere that negates
+	 *      the hierarchy?
+	 */
+	avg_load_per_task = sg_div_cpu_power(group,
+			sum_avg_load_per_task * SCHED_LOAD_SCALE);
+
+	if ((max_cpu_load - min_cpu_load) > 2*avg_load_per_task)
+		sgs->group_imb = 1;
+
+	sgs->group_capacity = group->__cpu_power / SCHED_LOAD_SCALE;
+
+}
+
+/**
+ * update_sd_lb_stats - Update sched_group's statistics for load balancing.
+ * @sd: sched_domain whose statistics are to be updated.
+ * @this_cpu: Cpu for which load balance is currently performed.
+ * @idle: Idle status of this_cpu
+ * @sd_idle: Idle status of the sched_domain containing group.
+ * @cpus: Set of cpus considered for load balancing.
+ * @balance: Should we balance.
+ * @sds: variable to hold the statistics for this sched_domain.
+ */
+static inline void update_sd_lb_stats(struct sched_domain *sd, int this_cpu,
+			enum cpu_idle_type idle, int *sd_idle,
+			const struct cpumask *cpus, int *balance,
+			struct sd_lb_stats *sds)
+{
+	struct sched_group *group = sd->groups;
+	struct sg_lb_stats sgs;
+	int load_idx;
+
+	init_sd_power_savings_stats(sd, sds, idle);
+	load_idx = get_sd_load_idx(sd, idle);
+
+	do {
+		int local_group;
+
+		local_group = cpumask_test_cpu(this_cpu,
+					       sched_group_cpus(group));
+		memset(&sgs, 0, sizeof(sgs));
+		update_sg_lb_stats(group, this_cpu, idle, load_idx, sd_idle,
+				local_group, cpus, balance, &sgs);
+
+		if (local_group && balance && !(*balance))
+			return;
+
+		sds->total_load += sgs.group_load;
+		sds->total_pwr += group->__cpu_power;
+
+		if (local_group) {
+			sds->this_load = sgs.avg_load;
+			sds->this = group;
+			sds->this_nr_running = sgs.sum_nr_running;
+			sds->this_load_per_task = sgs.sum_weighted_load;
+		} else if (sgs.avg_load > sds->max_load &&
+			   (sgs.sum_nr_running > sgs.group_capacity ||
+				sgs.group_imb)) {
+			sds->max_load = sgs.avg_load;
+			sds->busiest = group;
+			sds->busiest_nr_running = sgs.sum_nr_running;
+			sds->busiest_load_per_task = sgs.sum_weighted_load;
+			sds->group_imb = sgs.group_imb;
 		}
-group_next:
-#endif
+
+		update_sd_power_savings_stats(group, sds, local_group, &sgs);
 		group = group->next;
 	} while (group != sd->groups);
 
-	if (!busiest || this_load >= max_load || busiest_nr_running == 0)
-		goto out_balanced;
-
-	avg_load = (SCHED_LOAD_SCALE * total_load) / total_pwr;
+}
 
-	if (this_load >= avg_load ||
-			100*max_load <= sd->imbalance_pct*this_load)
-		goto out_balanced;
+/**
+ * fix_small_imbalance - Calculate the minor imbalance that exists
+ *			amongst the groups of a sched_domain, during
+ *			load balancing.
+ * @sds: Statistics of the sched_domain whose imbalance is to be calculated.
+ * @this_cpu: The cpu at whose sched_domain we're performing load-balance.
+ * @imbalance: Variable to store the imbalance.
+ */
+static inline void fix_small_imbalance(struct sd_lb_stats *sds,
+				int this_cpu, unsigned long *imbalance)
+{
+	unsigned long tmp, pwr_now = 0, pwr_move = 0;
+	unsigned int imbn = 2;
+
+	if (sds->this_nr_running) {
+		sds->this_load_per_task /= sds->this_nr_running;
+		if (sds->busiest_load_per_task >
+				sds->this_load_per_task)
+			imbn = 1;
+	} else
+		sds->this_load_per_task =
+			cpu_avg_load_per_task(this_cpu);
 
-	busiest_load_per_task /= busiest_nr_running;
-	if (group_imb)
-		busiest_load_per_task = min(busiest_load_per_task, avg_load);
+	if (sds->max_load - sds->this_load + sds->busiest_load_per_task >=
+			sds->busiest_load_per_task * imbn) {
+		*imbalance = sds->busiest_load_per_task;
+		return;
+	}
 
 	/*
-	 * We're trying to get all the cpus to the average_load, so we don't
-	 * want to push ourselves above the average load, nor do we wish to
-	 * reduce the max loaded cpu below the average load, as either of these
-	 * actions would just result in more rebalancing later, and ping-pong
-	 * tasks around. Thus we look for the minimum possible imbalance.
-	 * Negative imbalances (*we* are more loaded than anyone else) will
-	 * be counted as no imbalance for these purposes -- we can't fix that
-	 * by pulling tasks to us. Be careful of negative numbers as they'll
-	 * appear as very large values with unsigned longs.
+	 * OK, we don't have enough imbalance to justify moving tasks,
+	 * however we may be able to increase total CPU power used by
+	 * moving them.
 	 */
-	if (max_load <= busiest_load_per_task)
-		goto out_balanced;
 
+	pwr_now += sds->busiest->__cpu_power *
+			min(sds->busiest_load_per_task, sds->max_load);
+	pwr_now += sds->this->__cpu_power *
+			min(sds->this_load_per_task, sds->this_load);
+	pwr_now /= SCHED_LOAD_SCALE;
+
+	/* Amount of load we'd subtract */
+	tmp = sg_div_cpu_power(sds->busiest,
+			sds->busiest_load_per_task * SCHED_LOAD_SCALE);
+	if (sds->max_load > tmp)
+		pwr_move += sds->busiest->__cpu_power *
+			min(sds->busiest_load_per_task, sds->max_load - tmp);
+
+	/* Amount of load we'd add */
+	if (sds->max_load * sds->busiest->__cpu_power <
+		sds->busiest_load_per_task * SCHED_LOAD_SCALE)
+		tmp = sg_div_cpu_power(sds->this,
+			sds->max_load * sds->busiest->__cpu_power);
+	else
+		tmp = sg_div_cpu_power(sds->this,
+			sds->busiest_load_per_task * SCHED_LOAD_SCALE);
+	pwr_move += sds->this->__cpu_power *
+			min(sds->this_load_per_task, sds->this_load + tmp);
+	pwr_move /= SCHED_LOAD_SCALE;
+
+	/* Move if we gain throughput */
+	if (pwr_move > pwr_now)
+		*imbalance = sds->busiest_load_per_task;
+}
+
+/**
+ * calculate_imbalance - Calculate the amount of imbalance present within the
+ *			 groups of a given sched_domain during load balance.
+ * @sds: statistics of the sched_domain whose imbalance is to be calculated.
+ * @this_cpu: Cpu for which currently load balance is being performed.
+ * @imbalance: The variable to store the imbalance.
+ */
+static inline void calculate_imbalance(struct sd_lb_stats *sds, int this_cpu,
+		unsigned long *imbalance)
+{
+	unsigned long max_pull;
 	/*
 	 * In the presence of smp nice balancing, certain scenarios can have
 	 * max load less than avg load(as we skip the groups at or below
 	 * its cpu_power, while calculating max_load..)
 	 */
-	if (max_load < avg_load) {
+	if (sds->max_load < sds->avg_load) {
 		*imbalance = 0;
-		goto small_imbalance;
+		return fix_small_imbalance(sds, this_cpu, imbalance);
 	}
 
 	/* Don't want to pull so many tasks that a group would go idle */
-	max_pull = min(max_load - avg_load, max_load - busiest_load_per_task);
+	max_pull = min(sds->max_load - sds->avg_load,
+			sds->max_load - sds->busiest_load_per_task);
 
 	/* How much load to actually move to equalise the imbalance */
-	*imbalance = min(max_pull * busiest->__cpu_power,
-				(avg_load - this_load) * this->__cpu_power)
+	*imbalance = min(max_pull * sds->busiest->__cpu_power,
+		(sds->avg_load - sds->this_load) * sds->this->__cpu_power)
 			/ SCHED_LOAD_SCALE;
 
 	/*
@@ -3333,78 +3679,110 @@ group_next:
 	 * a think about bumping its value to force at least one task to be
 	 * moved
 	 */
-	if (*imbalance < busiest_load_per_task) {
-		unsigned long tmp, pwr_now, pwr_move;
-		unsigned int imbn;
-
-small_imbalance:
-		pwr_move = pwr_now = 0;
-		imbn = 2;
-		if (this_nr_running) {
-			this_load_per_task /= this_nr_running;
-			if (busiest_load_per_task > this_load_per_task)
-				imbn = 1;
-		} else
-			this_load_per_task = cpu_avg_load_per_task(this_cpu);
+	if (*imbalance < sds->busiest_load_per_task)
+		return fix_small_imbalance(sds, this_cpu, imbalance);
 
-		if (max_load - this_load + busiest_load_per_task >=
-					busiest_load_per_task * imbn) {
-			*imbalance = busiest_load_per_task;
-			return busiest;
-		}
+}
+/******* find_busiest_group() helpers end here *********************/
 
-		/*
-		 * OK, we don't have enough imbalance to justify moving tasks,
-		 * however we may be able to increase total CPU power used by
-		 * moving them.
-		 */
+/**
+ * find_busiest_group - Returns the busiest group within the sched_domain
+ * if there is an imbalance. If there isn't an imbalance, and
+ * the user has opted for power-savings, it returns a group whose
+ * CPUs can be put to idle by rebalancing those tasks elsewhere, if
+ * such a group exists.
+ *
+ * Also calculates the amount of weighted load which should be moved
+ * to restore balance.
+ *
+ * @sd: The sched_domain whose busiest group is to be returned.
+ * @this_cpu: The cpu for which load balancing is currently being performed.
+ * @imbalance: Variable which stores amount of weighted load which should
+ *		be moved to restore balance/put a group to idle.
+ * @idle: The idle status of this_cpu.
+ * @sd_idle: The idleness of sd
+ * @cpus: The set of CPUs under consideration for load-balancing.
+ * @balance: Pointer to a variable indicating if this_cpu
+ *	is the appropriate cpu to perform load balancing at this_level.
+ *
+ * Returns:	- the busiest group if imbalance exists.
+ *		- If no imbalance and user has opted for power-savings balance,
+ *		   return the least loaded group whose CPUs can be
+ *		   put to idle by rebalancing its tasks onto our group.
+ */
+static struct sched_group *
+find_busiest_group(struct sched_domain *sd, int this_cpu,
+		   unsigned long *imbalance, enum cpu_idle_type idle,
+		   int *sd_idle, const struct cpumask *cpus, int *balance)
+{
+	struct sd_lb_stats sds;
 
-		pwr_now += busiest->__cpu_power *
-				min(busiest_load_per_task, max_load);
-		pwr_now += this->__cpu_power *
-				min(this_load_per_task, this_load);
-		pwr_now /= SCHED_LOAD_SCALE;
-
-		/* Amount of load we'd subtract */
-		tmp = sg_div_cpu_power(busiest,
-				busiest_load_per_task * SCHED_LOAD_SCALE);
-		if (max_load > tmp)
-			pwr_move += busiest->__cpu_power *
-				min(busiest_load_per_task, max_load - tmp);
-
-		/* Amount of load we'd add */
-		if (max_load * busiest->__cpu_power <
-				busiest_load_per_task * SCHED_LOAD_SCALE)
-			tmp = sg_div_cpu_power(this,
-					max_load * busiest->__cpu_power);
-		else
-			tmp = sg_div_cpu_power(this,
-				busiest_load_per_task * SCHED_LOAD_SCALE);
-		pwr_move += this->__cpu_power *
-				min(this_load_per_task, this_load + tmp);
-		pwr_move /= SCHED_LOAD_SCALE;
+	memset(&sds, 0, sizeof(sds));
 
-		/* Move if we gain throughput */
-		if (pwr_move > pwr_now)
-			*imbalance = busiest_load_per_task;
-	}
+	/*
+	 * Compute the various statistics relavent for load balancing at
+	 * this level.
+	 */
+	update_sd_lb_stats(sd, this_cpu, idle, sd_idle, cpus,
+					balance, &sds);
+
+	/* Cases where imbalance does not exist from POV of this_cpu */
+	/* 1) this_cpu is not the appropriate cpu to perform load balancing
+	 *    at this level.
+	 * 2) There is no busy sibling group to pull from.
+	 * 3) This group is the busiest group.
+	 * 4) This group is more busy than the avg busieness at this
+	 *    sched_domain.
+	 * 5) The imbalance is within the specified limit.
+	 * 6) Any rebalance would lead to ping-pong
+	 */
+	if (balance && !(*balance))
+		goto ret;
 
-	return busiest;
+	if (!sds.busiest || sds.busiest_nr_running == 0)
+		goto out_balanced;
 
-out_balanced:
-#if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT)
-	if (idle == CPU_NOT_IDLE || !(sd->flags & SD_POWERSAVINGS_BALANCE))
-		goto ret;
+	if (sds.this_load >= sds.max_load)
+		goto out_balanced;
 
-	if (this == group_leader && group_leader != group_min) {
-		*imbalance = min_load_per_task;
-		if (sched_mc_power_savings >= POWERSAVINGS_BALANCE_WAKEUP) {
-			cpu_rq(this_cpu)->rd->sched_mc_preferred_wakeup_cpu =
-				cpumask_first(sched_group_cpus(group_leader));
-		}
-		return group_min;
-	}
-#endif
+	sds.avg_load = (SCHED_LOAD_SCALE * sds.total_load) / sds.total_pwr;
+
+	if (sds.this_load >= sds.avg_load)
+		goto out_balanced;
+
+	if (100 * sds.max_load <= sd->imbalance_pct * sds.this_load)
+		goto out_balanced;
+
+	sds.busiest_load_per_task /= sds.busiest_nr_running;
+	if (sds.group_imb)
+		sds.busiest_load_per_task =
+			min(sds.busiest_load_per_task, sds.avg_load);
+
+	/*
+	 * We're trying to get all the cpus to the average_load, so we don't
+	 * want to push ourselves above the average load, nor do we wish to
+	 * reduce the max loaded cpu below the average load, as either of these
+	 * actions would just result in more rebalancing later, and ping-pong
+	 * tasks around. Thus we look for the minimum possible imbalance.
+	 * Negative imbalances (*we* are more loaded than anyone else) will
+	 * be counted as no imbalance for these purposes -- we can't fix that
+	 * by pulling tasks to us. Be careful of negative numbers as they'll
+	 * appear as very large values with unsigned longs.
+	 */
+	if (sds.max_load <= sds.busiest_load_per_task)
+		goto out_balanced;
+
+	/* Looks like there is an imbalance. Compute it */
+	calculate_imbalance(&sds, this_cpu, imbalance);
+	return sds.busiest;
+
+out_balanced:
+	/*
+	 * There is no obvious imbalance. But check if we can do some balancing
+	 * to save power.
+	 */
+	if (check_power_save_busiest_group(&sds, this_cpu, imbalance))
+		return sds.busiest;
 ret:
 	*imbalance = 0;
 	return NULL;
@@ -3448,19 +3826,23 @@ find_busiest_queue(struct sched_group *group, enum cpu_idle_type idle,
  */
 #define MAX_PINNED_INTERVAL	512
 
+/* Working cpumask for load_balance and load_balance_newidle. */
+static DEFINE_PER_CPU(cpumask_var_t, load_balance_tmpmask);
+
 /*
  * Check this_cpu to ensure it is balanced within domain. Attempt to move
  * tasks if there is an imbalance.
  */
 static int load_balance(int this_cpu, struct rq *this_rq,
 			struct sched_domain *sd, enum cpu_idle_type idle,
-			int *balance, struct cpumask *cpus)
+			int *balance)
 {
 	int ld_moved, all_pinned = 0, active_balance = 0, sd_idle = 0;
 	struct sched_group *group;
 	unsigned long imbalance;
 	struct rq *busiest;
 	unsigned long flags;
+	struct cpumask *cpus = __get_cpu_var(load_balance_tmpmask);
 
 	cpumask_setall(cpus);
 
@@ -3615,8 +3997,7 @@ out:
  * this_rq is locked.
  */
 static int
-load_balance_newidle(int this_cpu, struct rq *this_rq, struct sched_domain *sd,
-			struct cpumask *cpus)
+load_balance_newidle(int this_cpu, struct rq *this_rq, struct sched_domain *sd)
 {
 	struct sched_group *group;
 	struct rq *busiest = NULL;
@@ -3624,6 +4005,7 @@ load_balance_newidle(int this_cpu, struct rq *this_rq, struct sched_domain *sd,
 	int ld_moved = 0;
 	int sd_idle = 0;
 	int all_pinned = 0;
+	struct cpumask *cpus = __get_cpu_var(load_balance_tmpmask);
 
 	cpumask_setall(cpus);
 
@@ -3764,10 +4146,6 @@ static void idle_balance(int this_cpu, struct rq *this_rq)
 	struct sched_domain *sd;
 	int pulled_task = 0;
 	unsigned long next_balance = jiffies + HZ;
-	cpumask_var_t tmpmask;
-
-	if (!alloc_cpumask_var(&tmpmask, GFP_ATOMIC))
-		return;
 
 	for_each_domain(this_cpu, sd) {
 		unsigned long interval;
@@ -3778,7 +4156,7 @@ static void idle_balance(int this_cpu, struct rq *this_rq)
 		if (sd->flags & SD_BALANCE_NEWIDLE)
 			/* If we've pulled tasks over stop searching: */
 			pulled_task = load_balance_newidle(this_cpu, this_rq,
-							   sd, tmpmask);
+							   sd);
 
 		interval = msecs_to_jiffies(sd->balance_interval);
 		if (time_after(next_balance, sd->last_balance + interval))
@@ -3793,7 +4171,6 @@ static void idle_balance(int this_cpu, struct rq *this_rq)
 		 */
 		this_rq->next_balance = next_balance;
 	}
-	free_cpumask_var(tmpmask);
 }
 
 /*
@@ -3943,11 +4320,6 @@ static void rebalance_domains(int cpu, enum cpu_idle_type idle)
 	unsigned long next_balance = jiffies + 60*HZ;
 	int update_next_balance = 0;
 	int need_serialize;
-	cpumask_var_t tmp;
-
-	/* Fails alloc?  Rebalancing probably not a priority right now. */
-	if (!alloc_cpumask_var(&tmp, GFP_ATOMIC))
-		return;
 
 	for_each_domain(cpu, sd) {
 		if (!(sd->flags & SD_LOAD_BALANCE))
@@ -3972,7 +4344,7 @@ static void rebalance_domains(int cpu, enum cpu_idle_type idle)
 		}
 
 		if (time_after_eq(jiffies, sd->last_balance + interval)) {
-			if (load_balance(cpu, rq, sd, idle, &balance, tmp)) {
+			if (load_balance(cpu, rq, sd, idle, &balance)) {
 				/*
 				 * We've pulled tasks over so either we're no
 				 * longer idle, or one of our SMT siblings is
@@ -4006,8 +4378,6 @@ out:
 	 */
 	if (likely(update_next_balance))
 		rq->next_balance = next_balance;
-
-	free_cpumask_var(tmp);
 }
 
 /*
@@ -4057,6 +4427,11 @@ static void run_rebalance_domains(struct softirq_action *h)
 #endif
 }
 
+static inline int on_null_domain(int cpu)
+{
+	return !rcu_dereference(cpu_rq(cpu)->sd);
+}
+
 /*
  * Trigger the SCHED_SOFTIRQ if it is time to do periodic load balancing.
  *
@@ -4114,7 +4489,9 @@ static inline void trigger_load_balance(struct rq *rq, int cpu)
 	    cpumask_test_cpu(cpu, nohz.cpu_mask))
 		return;
 #endif
-	if (time_after_eq(jiffies, rq->next_balance))
+	/* Don't need to rebalance while attached to NULL domain */
+	if (time_after_eq(jiffies, rq->next_balance) &&
+	    likely(!on_null_domain(cpu)))
 		raise_softirq(SCHED_SOFTIRQ);
 }
 
@@ -4508,11 +4885,33 @@ static inline void schedule_debug(struct task_struct *prev)
 #endif
 }
 
+static void put_prev_task(struct rq *rq, struct task_struct *prev)
+{
+	if (prev->state == TASK_RUNNING) {
+		u64 runtime = prev->se.sum_exec_runtime;
+
+		runtime -= prev->se.prev_sum_exec_runtime;
+		runtime = min_t(u64, runtime, 2*sysctl_sched_migration_cost);
+
+		/*
+		 * In order to avoid avg_overlap growing stale when we are
+		 * indeed overlapping and hence not getting put to sleep, grow
+		 * the avg_overlap on preemption.
+		 *
+		 * We use the average preemption runtime because that
+		 * correlates to the amount of cache footprint a task can
+		 * build up.
+		 */
+		update_avg(&prev->se.avg_overlap, runtime);
+	}
+	prev->sched_class->put_prev_task(rq, prev);
+}
+
 /*
  * Pick up the highest-prio task:
  */
 static inline struct task_struct *
-pick_next_task(struct rq *rq, struct task_struct *prev)
+pick_next_task(struct rq *rq)
 {
 	const struct sched_class *class;
 	struct task_struct *p;
@@ -4584,8 +4983,8 @@ need_resched_nonpreemptible:
 	if (unlikely(!rq->nr_running))
 		idle_balance(cpu, rq);
 
-	prev->sched_class->put_prev_task(rq, prev);
-	next = pick_next_task(rq, prev);
+	put_prev_task(rq, prev);
+	next = pick_next_task(rq);
 
 	if (likely(prev != next)) {
 		sched_info_switch(prev, next);
@@ -4707,7 +5106,7 @@ asmlinkage void __sched preempt_schedule(void)
 		 * between schedule and now.
 		 */
 		barrier();
-	} while (unlikely(test_thread_flag(TIF_NEED_RESCHED)));
+	} while (need_resched());
 }
 EXPORT_SYMBOL(preempt_schedule);
 
@@ -4736,7 +5135,7 @@ asmlinkage void __sched preempt_schedule_irq(void)
 		 * between schedule and now.
 		 */
 		barrier();
-	} while (unlikely(test_thread_flag(TIF_NEED_RESCHED)));
+	} while (need_resched());
 }
 
 #endif /* CONFIG_PREEMPT */
@@ -4797,11 +5196,17 @@ void __wake_up_locked(wait_queue_head_t *q, unsigned int mode)
 	__wake_up_common(q, mode, 1, 0, NULL);
 }
 
+void __wake_up_locked_key(wait_queue_head_t *q, unsigned int mode, void *key)
+{
+	__wake_up_common(q, mode, 1, 0, key);
+}
+
 /**
- * __wake_up_sync - wake up threads blocked on a waitqueue.
+ * __wake_up_sync_key - wake up threads blocked on a waitqueue.
  * @q: the waitqueue
  * @mode: which threads
  * @nr_exclusive: how many wake-one or wake-many threads to wake up
+ * @key: opaque value to be passed to wakeup targets
  *
  * The sync wakeup differs that the waker knows that it will schedule
  * away soon, so while the target thread will be woken up, it will not
@@ -4810,8 +5215,8 @@ void __wake_up_locked(wait_queue_head_t *q, unsigned int mode)
  *
  * On UP it can prevent extra preemption.
  */
-void
-__wake_up_sync(wait_queue_head_t *q, unsigned int mode, int nr_exclusive)
+void __wake_up_sync_key(wait_queue_head_t *q, unsigned int mode,
+			int nr_exclusive, void *key)
 {
 	unsigned long flags;
 	int sync = 1;
@@ -4823,9 +5228,18 @@ __wake_up_sync(wait_queue_head_t *q, unsigned int mode, int nr_exclusive)
 		sync = 0;
 
 	spin_lock_irqsave(&q->lock, flags);
-	__wake_up_common(q, mode, nr_exclusive, sync, NULL);
+	__wake_up_common(q, mode, nr_exclusive, sync, key);
 	spin_unlock_irqrestore(&q->lock, flags);
 }
+EXPORT_SYMBOL_GPL(__wake_up_sync_key);
+
+/*
+ * __wake_up_sync - see __wake_up_sync_key()
+ */
+void __wake_up_sync(wait_queue_head_t *q, unsigned int mode, int nr_exclusive)
+{
+	__wake_up_sync_key(q, mode, nr_exclusive, NULL);
+}
 EXPORT_SYMBOL_GPL(__wake_up_sync);	/* For internal use only */
 
 /**
@@ -5210,7 +5624,7 @@ SYSCALL_DEFINE1(nice, int, increment)
 	if (increment > 40)
 		increment = 40;
 
-	nice = PRIO_TO_NICE(current->static_prio) + increment;
+	nice = TASK_NICE(current) + increment;
 	if (nice < -20)
 		nice = -20;
 	if (nice > 19)
@@ -6483,7 +6897,7 @@ static void migrate_dead_tasks(unsigned int dead_cpu)
 		if (!rq->nr_running)
 			break;
 		update_rq_clock(rq);
-		next = pick_next_task(rq, rq->curr);
+		next = pick_next_task(rq);
 		if (!next)
 			break;
 		next->sched_class->put_prev_task(rq, next);
@@ -7314,7 +7728,7 @@ cpu_to_core_group(int cpu, const struct cpumask *cpu_map,
 {
 	int group;
 
-	cpumask_and(mask, &per_cpu(cpu_sibling_map, cpu), cpu_map);
+	cpumask_and(mask, topology_thread_cpumask(cpu), cpu_map);
 	group = cpumask_first(mask);
 	if (sg)
 		*sg = &per_cpu(sched_group_core, group).sg;
@@ -7343,7 +7757,7 @@ cpu_to_phys_group(int cpu, const struct cpumask *cpu_map,
 	cpumask_and(mask, cpu_coregroup_mask(cpu), cpu_map);
 	group = cpumask_first(mask);
 #elif defined(CONFIG_SCHED_SMT)
-	cpumask_and(mask, &per_cpu(cpu_sibling_map, cpu), cpu_map);
+	cpumask_and(mask, topology_thread_cpumask(cpu), cpu_map);
 	group = cpumask_first(mask);
 #else
 	group = cpu;
@@ -7686,7 +8100,7 @@ static int __build_sched_domains(const struct cpumask *cpu_map,
 		SD_INIT(sd, SIBLING);
 		set_domain_attribute(sd, attr);
 		cpumask_and(sched_domain_span(sd),
-			    &per_cpu(cpu_sibling_map, i), cpu_map);
+			    topology_thread_cpumask(i), cpu_map);
 		sd->parent = p;
 		p->child = sd;
 		cpu_to_cpu_group(i, cpu_map, &sd->groups, tmpmask);
@@ -7697,7 +8111,7 @@ static int __build_sched_domains(const struct cpumask *cpu_map,
 	/* Set up CPU (sibling) groups */
 	for_each_cpu(i, cpu_map) {
 		cpumask_and(this_sibling_map,
-			    &per_cpu(cpu_sibling_map, i), cpu_map);
+			    topology_thread_cpumask(i), cpu_map);
 		if (i != cpumask_first(this_sibling_map))
 			continue;
 
@@ -8278,11 +8692,15 @@ static void init_rt_rq(struct rt_rq *rt_rq, struct rq *rq)
 	__set_bit(MAX_RT_PRIO, array->bitmap);
 
 #if defined CONFIG_SMP || defined CONFIG_RT_GROUP_SCHED
-	rt_rq->highest_prio = MAX_RT_PRIO;
+	rt_rq->highest_prio.curr = MAX_RT_PRIO;
+#ifdef CONFIG_SMP
+	rt_rq->highest_prio.next = MAX_RT_PRIO;
+#endif
 #endif
 #ifdef CONFIG_SMP
 	rt_rq->rt_nr_migratory = 0;
 	rt_rq->overloaded = 0;
+	plist_head_init(&rq->rt.pushable_tasks, &rq->lock);
 #endif
 
 	rt_rq->rt_time = 0;
@@ -8369,6 +8787,9 @@ void __init sched_init(void)
 #ifdef CONFIG_USER_SCHED
 	alloc_size *= 2;
 #endif
+#ifdef CONFIG_CPUMASK_OFFSTACK
+	alloc_size += num_possible_cpus() * cpumask_size();
+#endif
 	/*
 	 * As sched_init() is called before page_alloc is setup,
 	 * we use alloc_bootmem().
@@ -8406,6 +8827,12 @@ void __init sched_init(void)
 		ptr += nr_cpu_ids * sizeof(void **);
 #endif /* CONFIG_USER_SCHED */
 #endif /* CONFIG_RT_GROUP_SCHED */
+#ifdef CONFIG_CPUMASK_OFFSTACK
+		for_each_possible_cpu(i) {
+			per_cpu(load_balance_tmpmask, i) = (void *)ptr;
+			ptr += cpumask_size();
+		}
+#endif /* CONFIG_CPUMASK_OFFSTACK */
 	}
 
 #ifdef CONFIG_SMP
@@ -9658,7 +10085,7 @@ static void cpuacct_charge(struct task_struct *tsk, u64 cputime)
 	struct cpuacct *ca;
 	int cpu;
 
-	if (!cpuacct_subsys.active)
+	if (unlikely(!cpuacct_subsys.active))
 		return;
 
 	cpu = task_cpu(tsk);
diff --git a/kernel/sched_clock.c b/kernel/sched_clock.c
index 7ec82c1c61c..819f17ac796 100644
--- a/kernel/sched_clock.c
+++ b/kernel/sched_clock.c
@@ -45,9 +45,6 @@ static __read_mostly int sched_clock_running;
 
 #ifdef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK
 __read_mostly int sched_clock_stable;
-#else
-static const int sched_clock_stable = 1;
-#endif
 
 struct sched_clock_data {
 	/*
@@ -116,14 +113,9 @@ static u64 __update_sched_clock(struct sched_clock_data *scd, u64 now)
 	s64 delta = now - scd->tick_raw;
 	u64 clock, min_clock, max_clock;
 
-	WARN_ON_ONCE(!irqs_disabled());
-
 	if (unlikely(delta < 0))
 		delta = 0;
 
-	if (unlikely(!sched_clock_running))
-		return 0ull;
-
 	/*
 	 * scd->clock = clamp(scd->tick_gtod + delta,
 	 *		      max(scd->tick_gtod, scd->clock),
@@ -213,18 +205,20 @@ u64 sched_clock_cpu(int cpu)
 	return clock;
 }
 
-#ifdef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK
-
 void sched_clock_tick(void)
 {
-	struct sched_clock_data *scd = this_scd();
+	struct sched_clock_data *scd;
 	u64 now, now_gtod;
 
+	if (sched_clock_stable)
+		return;
+
 	if (unlikely(!sched_clock_running))
 		return;
 
 	WARN_ON_ONCE(!irqs_disabled());
 
+	scd = this_scd();
 	now_gtod = ktime_to_ns(ktime_get());
 	now = sched_clock();
 
@@ -257,6 +251,21 @@ void sched_clock_idle_wakeup_event(u64 delta_ns)
 }
 EXPORT_SYMBOL_GPL(sched_clock_idle_wakeup_event);
 
+#else /* CONFIG_HAVE_UNSTABLE_SCHED_CLOCK */
+
+void sched_clock_init(void)
+{
+	sched_clock_running = 1;
+}
+
+u64 sched_clock_cpu(int cpu)
+{
+	if (unlikely(!sched_clock_running))
+		return 0;
+
+	return sched_clock();
+}
+
 #endif /* CONFIG_HAVE_UNSTABLE_SCHED_CLOCK */
 
 unsigned long long cpu_clock(int cpu)
diff --git a/kernel/sched_cpupri.h b/kernel/sched_cpupri.h
index 642a94ef8a0..9a7e859b8fb 100644
--- a/kernel/sched_cpupri.h
+++ b/kernel/sched_cpupri.h
@@ -25,7 +25,7 @@ struct cpupri {
 
 #ifdef CONFIG_SMP
 int  cpupri_find(struct cpupri *cp,
-		 struct task_struct *p, cpumask_t *lowest_mask);
+		 struct task_struct *p, struct cpumask *lowest_mask);
 void cpupri_set(struct cpupri *cp, int cpu, int pri);
 int cpupri_init(struct cpupri *cp, bool bootmem);
 void cpupri_cleanup(struct cpupri *cp);
diff --git a/kernel/sched_debug.c b/kernel/sched_debug.c
index 16eeba4e416..467ca72f165 100644
--- a/kernel/sched_debug.c
+++ b/kernel/sched_debug.c
@@ -272,7 +272,6 @@ static void print_cpu(struct seq_file *m, int cpu)
 	P(nr_switches);
 	P(nr_load_updates);
 	P(nr_uninterruptible);
-	SEQ_printf(m, "  .%-30s: %lu\n", "jiffies", jiffies);
 	PN(next_balance);
 	P(curr->pid);
 	PN(clock);
@@ -287,9 +286,6 @@ static void print_cpu(struct seq_file *m, int cpu)
 #ifdef CONFIG_SCHEDSTATS
 #define P(n) SEQ_printf(m, "  .%-30s: %d\n", #n, rq->n);
 
-	P(yld_exp_empty);
-	P(yld_act_empty);
-	P(yld_both_empty);
 	P(yld_count);
 
 	P(sched_switch);
@@ -314,7 +310,7 @@ static int sched_debug_show(struct seq_file *m, void *v)
 	u64 now = ktime_to_ns(ktime_get());
 	int cpu;
 
-	SEQ_printf(m, "Sched Debug Version: v0.08, %s %.*s\n",
+	SEQ_printf(m, "Sched Debug Version: v0.09, %s %.*s\n",
 		init_utsname()->release,
 		(int)strcspn(init_utsname()->version, " "),
 		init_utsname()->version);
@@ -325,6 +321,7 @@ static int sched_debug_show(struct seq_file *m, void *v)
 	SEQ_printf(m, "  .%-40s: %Ld\n", #x, (long long)(x))
 #define PN(x) \
 	SEQ_printf(m, "  .%-40s: %Ld.%06ld\n", #x, SPLIT_NS(x))
+	P(jiffies);
 	PN(sysctl_sched_latency);
 	PN(sysctl_sched_min_granularity);
 	PN(sysctl_sched_wakeup_granularity);
@@ -397,6 +394,7 @@ void proc_sched_show_task(struct task_struct *p, struct seq_file *m)
 	PN(se.vruntime);
 	PN(se.sum_exec_runtime);
 	PN(se.avg_overlap);
+	PN(se.avg_wakeup);
 
 	nr_switches = p->nvcsw + p->nivcsw;
 
diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index 0566f2a03c4..3816f217f11 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -1314,16 +1314,63 @@ out:
 }
 #endif /* CONFIG_SMP */
 
-static unsigned long wakeup_gran(struct sched_entity *se)
+/*
+ * Adaptive granularity
+ *
+ * se->avg_wakeup gives the average time a task runs until it does a wakeup,
+ * with the limit of wakeup_gran -- when it never does a wakeup.
+ *
+ * So the smaller avg_wakeup is the faster we want this task to preempt,
+ * but we don't want to treat the preemptee unfairly and therefore allow it
+ * to run for at least the amount of time we'd like to run.
+ *
+ * NOTE: we use 2*avg_wakeup to increase the probability of actually doing one
+ *
+ * NOTE: we use *nr_running to scale with load, this nicely matches the
+ *       degrading latency on load.
+ */
+static unsigned long
+adaptive_gran(struct sched_entity *curr, struct sched_entity *se)
+{
+	u64 this_run = curr->sum_exec_runtime - curr->prev_sum_exec_runtime;
+	u64 expected_wakeup = 2*se->avg_wakeup * cfs_rq_of(se)->nr_running;
+	u64 gran = 0;
+
+	if (this_run < expected_wakeup)
+		gran = expected_wakeup - this_run;
+
+	return min_t(s64, gran, sysctl_sched_wakeup_granularity);
+}
+
+static unsigned long
+wakeup_gran(struct sched_entity *curr, struct sched_entity *se)
 {
 	unsigned long gran = sysctl_sched_wakeup_granularity;
 
+	if (cfs_rq_of(curr)->curr && sched_feat(ADAPTIVE_GRAN))
+		gran = adaptive_gran(curr, se);
+
 	/*
-	 * More easily preempt - nice tasks, while not making it harder for
-	 * + nice tasks.
+	 * Since its curr running now, convert the gran from real-time
+	 * to virtual-time in his units.
 	 */
-	if (!sched_feat(ASYM_GRAN) || se->load.weight > NICE_0_LOAD)
-		gran = calc_delta_fair(sysctl_sched_wakeup_granularity, se);
+	if (sched_feat(ASYM_GRAN)) {
+		/*
+		 * By using 'se' instead of 'curr' we penalize light tasks, so
+		 * they get preempted easier. That is, if 'se' < 'curr' then
+		 * the resulting gran will be larger, therefore penalizing the
+		 * lighter, if otoh 'se' > 'curr' then the resulting gran will
+		 * be smaller, again penalizing the lighter task.
+		 *
+		 * This is especially important for buddies when the leftmost
+		 * task is higher priority than the buddy.
+		 */
+		if (unlikely(se->load.weight != NICE_0_LOAD))
+			gran = calc_delta_fair(gran, se);
+	} else {
+		if (unlikely(curr->load.weight != NICE_0_LOAD))
+			gran = calc_delta_fair(gran, curr);
+	}
 
 	return gran;
 }
@@ -1350,7 +1397,7 @@ wakeup_preempt_entity(struct sched_entity *curr, struct sched_entity *se)
 	if (vdiff <= 0)
 		return -1;
 
-	gran = wakeup_gran(curr);
+	gran = wakeup_gran(curr, se);
 	if (vdiff > gran)
 		return 1;
 
diff --git a/kernel/sched_features.h b/kernel/sched_features.h
index 07bc02e99ab..4569bfa7df9 100644
--- a/kernel/sched_features.h
+++ b/kernel/sched_features.h
@@ -1,5 +1,6 @@
 SCHED_FEAT(NEW_FAIR_SLEEPERS, 1)
-SCHED_FEAT(NORMALIZED_SLEEPER, 1)
+SCHED_FEAT(NORMALIZED_SLEEPER, 0)
+SCHED_FEAT(ADAPTIVE_GRAN, 1)
 SCHED_FEAT(WAKEUP_PREEMPT, 1)
 SCHED_FEAT(START_DEBIT, 1)
 SCHED_FEAT(AFFINE_WAKEUPS, 1)
diff --git a/kernel/sched_rt.c b/kernel/sched_rt.c
index da932f4c852..299d012b439 100644
--- a/kernel/sched_rt.c
+++ b/kernel/sched_rt.c
@@ -3,6 +3,40 @@
  * policies)
  */
 
+static inline struct task_struct *rt_task_of(struct sched_rt_entity *rt_se)
+{
+	return container_of(rt_se, struct task_struct, rt);
+}
+
+#ifdef CONFIG_RT_GROUP_SCHED
+
+static inline struct rq *rq_of_rt_rq(struct rt_rq *rt_rq)
+{
+	return rt_rq->rq;
+}
+
+static inline struct rt_rq *rt_rq_of_se(struct sched_rt_entity *rt_se)
+{
+	return rt_se->rt_rq;
+}
+
+#else /* CONFIG_RT_GROUP_SCHED */
+
+static inline struct rq *rq_of_rt_rq(struct rt_rq *rt_rq)
+{
+	return container_of(rt_rq, struct rq, rt);
+}
+
+static inline struct rt_rq *rt_rq_of_se(struct sched_rt_entity *rt_se)
+{
+	struct task_struct *p = rt_task_of(rt_se);
+	struct rq *rq = task_rq(p);
+
+	return &rq->rt;
+}
+
+#endif /* CONFIG_RT_GROUP_SCHED */
+
 #ifdef CONFIG_SMP
 
 static inline int rt_overloaded(struct rq *rq)
@@ -37,25 +71,69 @@ static inline void rt_clear_overload(struct rq *rq)
 	cpumask_clear_cpu(rq->cpu, rq->rd->rto_mask);
 }
 
-static void update_rt_migration(struct rq *rq)
+static void update_rt_migration(struct rt_rq *rt_rq)
 {
-	if (rq->rt.rt_nr_migratory && (rq->rt.rt_nr_running > 1)) {
-		if (!rq->rt.overloaded) {
-			rt_set_overload(rq);
-			rq->rt.overloaded = 1;
+	if (rt_rq->rt_nr_migratory && (rt_rq->rt_nr_running > 1)) {
+		if (!rt_rq->overloaded) {
+			rt_set_overload(rq_of_rt_rq(rt_rq));
+			rt_rq->overloaded = 1;
 		}
-	} else if (rq->rt.overloaded) {
-		rt_clear_overload(rq);
-		rq->rt.overloaded = 0;
+	} else if (rt_rq->overloaded) {
+		rt_clear_overload(rq_of_rt_rq(rt_rq));
+		rt_rq->overloaded = 0;
 	}
 }
-#endif /* CONFIG_SMP */
 
-static inline struct task_struct *rt_task_of(struct sched_rt_entity *rt_se)
+static void inc_rt_migration(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq)
+{
+	if (rt_se->nr_cpus_allowed > 1)
+		rt_rq->rt_nr_migratory++;
+
+	update_rt_migration(rt_rq);
+}
+
+static void dec_rt_migration(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq)
+{
+	if (rt_se->nr_cpus_allowed > 1)
+		rt_rq->rt_nr_migratory--;
+
+	update_rt_migration(rt_rq);
+}
+
+static void enqueue_pushable_task(struct rq *rq, struct task_struct *p)
+{
+	plist_del(&p->pushable_tasks, &rq->rt.pushable_tasks);
+	plist_node_init(&p->pushable_tasks, p->prio);
+	plist_add(&p->pushable_tasks, &rq->rt.pushable_tasks);
+}
+
+static void dequeue_pushable_task(struct rq *rq, struct task_struct *p)
+{
+	plist_del(&p->pushable_tasks, &rq->rt.pushable_tasks);
+}
+
+#else
+
+static inline void enqueue_pushable_task(struct rq *rq, struct task_struct *p)
 {
-	return container_of(rt_se, struct task_struct, rt);
 }
 
+static inline void dequeue_pushable_task(struct rq *rq, struct task_struct *p)
+{
+}
+
+static inline
+void inc_rt_migration(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq)
+{
+}
+
+static inline
+void dec_rt_migration(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq)
+{
+}
+
+#endif /* CONFIG_SMP */
+
 static inline int on_rt_rq(struct sched_rt_entity *rt_se)
 {
 	return !list_empty(&rt_se->run_list);
@@ -79,16 +157,6 @@ static inline u64 sched_rt_period(struct rt_rq *rt_rq)
 #define for_each_leaf_rt_rq(rt_rq, rq) \
 	list_for_each_entry_rcu(rt_rq, &rq->leaf_rt_rq_list, leaf_rt_rq_list)
 
-static inline struct rq *rq_of_rt_rq(struct rt_rq *rt_rq)
-{
-	return rt_rq->rq;
-}
-
-static inline struct rt_rq *rt_rq_of_se(struct sched_rt_entity *rt_se)
-{
-	return rt_se->rt_rq;
-}
-
 #define for_each_sched_rt_entity(rt_se) \
 	for (; rt_se; rt_se = rt_se->parent)
 
@@ -108,7 +176,7 @@ static void sched_rt_rq_enqueue(struct rt_rq *rt_rq)
 	if (rt_rq->rt_nr_running) {
 		if (rt_se && !on_rt_rq(rt_se))
 			enqueue_rt_entity(rt_se);
-		if (rt_rq->highest_prio < curr->prio)
+		if (rt_rq->highest_prio.curr < curr->prio)
 			resched_task(curr);
 	}
 }
@@ -176,19 +244,6 @@ static inline u64 sched_rt_period(struct rt_rq *rt_rq)
 #define for_each_leaf_rt_rq(rt_rq, rq) \
 	for (rt_rq = &rq->rt; rt_rq; rt_rq = NULL)
 
-static inline struct rq *rq_of_rt_rq(struct rt_rq *rt_rq)
-{
-	return container_of(rt_rq, struct rq, rt);
-}
-
-static inline struct rt_rq *rt_rq_of_se(struct sched_rt_entity *rt_se)
-{
-	struct task_struct *p = rt_task_of(rt_se);
-	struct rq *rq = task_rq(p);
-
-	return &rq->rt;
-}
-
 #define for_each_sched_rt_entity(rt_se) \
 	for (; rt_se; rt_se = NULL)
 
@@ -473,7 +528,7 @@ static inline int rt_se_prio(struct sched_rt_entity *rt_se)
 	struct rt_rq *rt_rq = group_rt_rq(rt_se);
 
 	if (rt_rq)
-		return rt_rq->highest_prio;
+		return rt_rq->highest_prio.curr;
 #endif
 
 	return rt_task_of(rt_se)->prio;
@@ -547,91 +602,174 @@ static void update_curr_rt(struct rq *rq)
 	}
 }
 
-static inline
-void inc_rt_tasks(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq)
+#if defined CONFIG_SMP
+
+static struct task_struct *pick_next_highest_task_rt(struct rq *rq, int cpu);
+
+static inline int next_prio(struct rq *rq)
 {
-	WARN_ON(!rt_prio(rt_se_prio(rt_se)));
-	rt_rq->rt_nr_running++;
-#if defined CONFIG_SMP || defined CONFIG_RT_GROUP_SCHED
-	if (rt_se_prio(rt_se) < rt_rq->highest_prio) {
-#ifdef CONFIG_SMP
-		struct rq *rq = rq_of_rt_rq(rt_rq);
-#endif
+	struct task_struct *next = pick_next_highest_task_rt(rq, rq->cpu);
+
+	if (next && rt_prio(next->prio))
+		return next->prio;
+	else
+		return MAX_RT_PRIO;
+}
+
+static void
+inc_rt_prio_smp(struct rt_rq *rt_rq, int prio, int prev_prio)
+{
+	struct rq *rq = rq_of_rt_rq(rt_rq);
+
+	if (prio < prev_prio) {
+
+		/*
+		 * If the new task is higher in priority than anything on the
+		 * run-queue, we know that the previous high becomes our
+		 * next-highest.
+		 */
+		rt_rq->highest_prio.next = prev_prio;
 
-		rt_rq->highest_prio = rt_se_prio(rt_se);
-#ifdef CONFIG_SMP
 		if (rq->online)
-			cpupri_set(&rq->rd->cpupri, rq->cpu,
-				   rt_se_prio(rt_se));
-#endif
-	}
-#endif
-#ifdef CONFIG_SMP
-	if (rt_se->nr_cpus_allowed > 1) {
-		struct rq *rq = rq_of_rt_rq(rt_rq);
+			cpupri_set(&rq->rd->cpupri, rq->cpu, prio);
 
-		rq->rt.rt_nr_migratory++;
-	}
+	} else if (prio == rt_rq->highest_prio.curr)
+		/*
+		 * If the next task is equal in priority to the highest on
+		 * the run-queue, then we implicitly know that the next highest
+		 * task cannot be any lower than current
+		 */
+		rt_rq->highest_prio.next = prio;
+	else if (prio < rt_rq->highest_prio.next)
+		/*
+		 * Otherwise, we need to recompute next-highest
+		 */
+		rt_rq->highest_prio.next = next_prio(rq);
+}
 
-	update_rt_migration(rq_of_rt_rq(rt_rq));
-#endif
-#ifdef CONFIG_RT_GROUP_SCHED
-	if (rt_se_boosted(rt_se))
-		rt_rq->rt_nr_boosted++;
+static void
+dec_rt_prio_smp(struct rt_rq *rt_rq, int prio, int prev_prio)
+{
+	struct rq *rq = rq_of_rt_rq(rt_rq);
 
-	if (rt_rq->tg)
-		start_rt_bandwidth(&rt_rq->tg->rt_bandwidth);
-#else
-	start_rt_bandwidth(&def_rt_bandwidth);
-#endif
+	if (rt_rq->rt_nr_running && (prio <= rt_rq->highest_prio.next))
+		rt_rq->highest_prio.next = next_prio(rq);
+
+	if (rq->online && rt_rq->highest_prio.curr != prev_prio)
+		cpupri_set(&rq->rd->cpupri, rq->cpu, rt_rq->highest_prio.curr);
 }
 
+#else /* CONFIG_SMP */
+
 static inline
-void dec_rt_tasks(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq)
-{
-#ifdef CONFIG_SMP
-	int highest_prio = rt_rq->highest_prio;
-#endif
+void inc_rt_prio_smp(struct rt_rq *rt_rq, int prio, int prev_prio) {}
+static inline
+void dec_rt_prio_smp(struct rt_rq *rt_rq, int prio, int prev_prio) {}
+
+#endif /* CONFIG_SMP */
 
-	WARN_ON(!rt_prio(rt_se_prio(rt_se)));
-	WARN_ON(!rt_rq->rt_nr_running);
-	rt_rq->rt_nr_running--;
 #if defined CONFIG_SMP || defined CONFIG_RT_GROUP_SCHED
+static void
+inc_rt_prio(struct rt_rq *rt_rq, int prio)
+{
+	int prev_prio = rt_rq->highest_prio.curr;
+
+	if (prio < prev_prio)
+		rt_rq->highest_prio.curr = prio;
+
+	inc_rt_prio_smp(rt_rq, prio, prev_prio);
+}
+
+static void
+dec_rt_prio(struct rt_rq *rt_rq, int prio)
+{
+	int prev_prio = rt_rq->highest_prio.curr;
+
 	if (rt_rq->rt_nr_running) {
-		struct rt_prio_array *array;
 
-		WARN_ON(rt_se_prio(rt_se) < rt_rq->highest_prio);
-		if (rt_se_prio(rt_se) == rt_rq->highest_prio) {
-			/* recalculate */
-			array = &rt_rq->active;
-			rt_rq->highest_prio =
+		WARN_ON(prio < prev_prio);
+
+		/*
+		 * This may have been our highest task, and therefore
+		 * we may have some recomputation to do
+		 */
+		if (prio == prev_prio) {
+			struct rt_prio_array *array = &rt_rq->active;
+
+			rt_rq->highest_prio.curr =
 				sched_find_first_bit(array->bitmap);
-		} /* otherwise leave rq->highest prio alone */
+		}
+
 	} else
-		rt_rq->highest_prio = MAX_RT_PRIO;
-#endif
-#ifdef CONFIG_SMP
-	if (rt_se->nr_cpus_allowed > 1) {
-		struct rq *rq = rq_of_rt_rq(rt_rq);
-		rq->rt.rt_nr_migratory--;
-	}
+		rt_rq->highest_prio.curr = MAX_RT_PRIO;
 
-	if (rt_rq->highest_prio != highest_prio) {
-		struct rq *rq = rq_of_rt_rq(rt_rq);
+	dec_rt_prio_smp(rt_rq, prio, prev_prio);
+}
 
-		if (rq->online)
-			cpupri_set(&rq->rd->cpupri, rq->cpu,
-				   rt_rq->highest_prio);
-	}
+#else
+
+static inline void inc_rt_prio(struct rt_rq *rt_rq, int prio) {}
+static inline void dec_rt_prio(struct rt_rq *rt_rq, int prio) {}
+
+#endif /* CONFIG_SMP || CONFIG_RT_GROUP_SCHED */
 
-	update_rt_migration(rq_of_rt_rq(rt_rq));
-#endif /* CONFIG_SMP */
 #ifdef CONFIG_RT_GROUP_SCHED
+
+static void
+inc_rt_group(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq)
+{
+	if (rt_se_boosted(rt_se))
+		rt_rq->rt_nr_boosted++;
+
+	if (rt_rq->tg)
+		start_rt_bandwidth(&rt_rq->tg->rt_bandwidth);
+}
+
+static void
+dec_rt_group(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq)
+{
 	if (rt_se_boosted(rt_se))
 		rt_rq->rt_nr_boosted--;
 
 	WARN_ON(!rt_rq->rt_nr_running && rt_rq->rt_nr_boosted);
-#endif
+}
+
+#else /* CONFIG_RT_GROUP_SCHED */
+
+static void
+inc_rt_group(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq)
+{
+	start_rt_bandwidth(&def_rt_bandwidth);
+}
+
+static inline
+void dec_rt_group(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq) {}
+
+#endif /* CONFIG_RT_GROUP_SCHED */
+
+static inline
+void inc_rt_tasks(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq)
+{
+	int prio = rt_se_prio(rt_se);
+
+	WARN_ON(!rt_prio(prio));
+	rt_rq->rt_nr_running++;
+
+	inc_rt_prio(rt_rq, prio);
+	inc_rt_migration(rt_se, rt_rq);
+	inc_rt_group(rt_se, rt_rq);
+}
+
+static inline
+void dec_rt_tasks(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq)
+{
+	WARN_ON(!rt_prio(rt_se_prio(rt_se)));
+	WARN_ON(!rt_rq->rt_nr_running);
+	rt_rq->rt_nr_running--;
+
+	dec_rt_prio(rt_rq, rt_se_prio(rt_se));
+	dec_rt_migration(rt_se, rt_rq);
+	dec_rt_group(rt_se, rt_rq);
 }
 
 static void __enqueue_rt_entity(struct sched_rt_entity *rt_se)
@@ -718,6 +856,9 @@ static void enqueue_task_rt(struct rq *rq, struct task_struct *p, int wakeup)
 
 	enqueue_rt_entity(rt_se);
 
+	if (!task_current(rq, p) && p->rt.nr_cpus_allowed > 1)
+		enqueue_pushable_task(rq, p);
+
 	inc_cpu_load(rq, p->se.load.weight);
 }
 
@@ -728,6 +869,8 @@ static void dequeue_task_rt(struct rq *rq, struct task_struct *p, int sleep)
 	update_curr_rt(rq);
 	dequeue_rt_entity(rt_se);
 
+	dequeue_pushable_task(rq, p);
+
 	dec_cpu_load(rq, p->se.load.weight);
 }
 
@@ -878,7 +1021,7 @@ static struct sched_rt_entity *pick_next_rt_entity(struct rq *rq,
 	return next;
 }
 
-static struct task_struct *pick_next_task_rt(struct rq *rq)
+static struct task_struct *_pick_next_task_rt(struct rq *rq)
 {
 	struct sched_rt_entity *rt_se;
 	struct task_struct *p;
@@ -900,6 +1043,18 @@ static struct task_struct *pick_next_task_rt(struct rq *rq)
 
 	p = rt_task_of(rt_se);
 	p->se.exec_start = rq->clock;
+
+	return p;
+}
+
+static struct task_struct *pick_next_task_rt(struct rq *rq)
+{
+	struct task_struct *p = _pick_next_task_rt(rq);
+
+	/* The running task is never eligible for pushing */
+	if (p)
+		dequeue_pushable_task(rq, p);
+
 	return p;
 }
 
@@ -907,6 +1062,13 @@ static void put_prev_task_rt(struct rq *rq, struct task_struct *p)
 {
 	update_curr_rt(rq);
 	p->se.exec_start = 0;
+
+	/*
+	 * The previous task needs to be made eligible for pushing
+	 * if it is still active
+	 */
+	if (p->se.on_rq && p->rt.nr_cpus_allowed > 1)
+		enqueue_pushable_task(rq, p);
 }
 
 #ifdef CONFIG_SMP
@@ -1080,7 +1242,7 @@ static struct rq *find_lock_lowest_rq(struct task_struct *task, struct rq *rq)
 		}
 
 		/* If this rq is still suitable use it. */
-		if (lowest_rq->rt.highest_prio > task->prio)
+		if (lowest_rq->rt.highest_prio.curr > task->prio)
 			break;
 
 		/* try again */
@@ -1091,6 +1253,31 @@ static struct rq *find_lock_lowest_rq(struct task_struct *task, struct rq *rq)
 	return lowest_rq;
 }
 
+static inline int has_pushable_tasks(struct rq *rq)
+{
+	return !plist_head_empty(&rq->rt.pushable_tasks);
+}
+
+static struct task_struct *pick_next_pushable_task(struct rq *rq)
+{
+	struct task_struct *p;
+
+	if (!has_pushable_tasks(rq))
+		return NULL;
+
+	p = plist_first_entry(&rq->rt.pushable_tasks,
+			      struct task_struct, pushable_tasks);
+
+	BUG_ON(rq->cpu != task_cpu(p));
+	BUG_ON(task_current(rq, p));
+	BUG_ON(p->rt.nr_cpus_allowed <= 1);
+
+	BUG_ON(!p->se.on_rq);
+	BUG_ON(!rt_task(p));
+
+	return p;
+}
+
 /*
  * If the current CPU has more than one RT task, see if the non
  * running task can migrate over to a CPU that is running a task
@@ -1100,13 +1287,11 @@ static int push_rt_task(struct rq *rq)
 {
 	struct task_struct *next_task;
 	struct rq *lowest_rq;
-	int ret = 0;
-	int paranoid = RT_MAX_TRIES;
 
 	if (!rq->rt.overloaded)
 		return 0;
 
-	next_task = pick_next_highest_task_rt(rq, -1);
+	next_task = pick_next_pushable_task(rq);
 	if (!next_task)
 		return 0;
 
@@ -1135,16 +1320,34 @@ static int push_rt_task(struct rq *rq)
 		struct task_struct *task;
 		/*
 		 * find lock_lowest_rq releases rq->lock
-		 * so it is possible that next_task has changed.
-		 * If it has, then try again.
+		 * so it is possible that next_task has migrated.
+		 *
+		 * We need to make sure that the task is still on the same
+		 * run-queue and is also still the next task eligible for
+		 * pushing.
 		 */
-		task = pick_next_highest_task_rt(rq, -1);
-		if (unlikely(task != next_task) && task && paranoid--) {
-			put_task_struct(next_task);
-			next_task = task;
-			goto retry;
+		task = pick_next_pushable_task(rq);
+		if (task_cpu(next_task) == rq->cpu && task == next_task) {
+			/*
+			 * If we get here, the task hasnt moved at all, but
+			 * it has failed to push.  We will not try again,
+			 * since the other cpus will pull from us when they
+			 * are ready.
+			 */
+			dequeue_pushable_task(rq, next_task);
+			goto out;
 		}
-		goto out;
+
+		if (!task)
+			/* No more tasks, just exit */
+			goto out;
+
+		/*
+		 * Something has shifted, try again.
+		 */
+		put_task_struct(next_task);
+		next_task = task;
+		goto retry;
 	}
 
 	deactivate_task(rq, next_task, 0);
@@ -1155,23 +1358,12 @@ static int push_rt_task(struct rq *rq)
 
 	double_unlock_balance(rq, lowest_rq);
 
-	ret = 1;
 out:
 	put_task_struct(next_task);
 
-	return ret;
+	return 1;
 }
 
-/*
- * TODO: Currently we just use the second highest prio task on
- *       the queue, and stop when it can't migrate (or there's
- *       no more RT tasks).  There may be a case where a lower
- *       priority RT task has a different affinity than the
- *       higher RT task. In this case the lower RT task could
- *       possibly be able to migrate where as the higher priority
- *       RT task could not.  We currently ignore this issue.
- *       Enhancements are welcome!
- */
 static void push_rt_tasks(struct rq *rq)
 {
 	/* push_rt_task will return true if it moved an RT */
@@ -1182,33 +1374,35 @@ static void push_rt_tasks(struct rq *rq)
 static int pull_rt_task(struct rq *this_rq)
 {
 	int this_cpu = this_rq->cpu, ret = 0, cpu;
-	struct task_struct *p, *next;
+	struct task_struct *p;
 	struct rq *src_rq;
 
 	if (likely(!rt_overloaded(this_rq)))
 		return 0;
 
-	next = pick_next_task_rt(this_rq);
-
 	for_each_cpu(cpu, this_rq->rd->rto_mask) {
 		if (this_cpu == cpu)
 			continue;
 
 		src_rq = cpu_rq(cpu);
+
+		/*
+		 * Don't bother taking the src_rq->lock if the next highest
+		 * task is known to be lower-priority than our current task.
+		 * This may look racy, but if this value is about to go
+		 * logically higher, the src_rq will push this task away.
+		 * And if its going logically lower, we do not care
+		 */
+		if (src_rq->rt.highest_prio.next >=
+		    this_rq->rt.highest_prio.curr)
+			continue;
+
 		/*
 		 * We can potentially drop this_rq's lock in
 		 * double_lock_balance, and another CPU could
-		 * steal our next task - hence we must cause
-		 * the caller to recalculate the next task
-		 * in that case:
+		 * alter this_rq
 		 */
-		if (double_lock_balance(this_rq, src_rq)) {
-			struct task_struct *old_next = next;
-
-			next = pick_next_task_rt(this_rq);
-			if (next != old_next)
-				ret = 1;
-		}
+		double_lock_balance(this_rq, src_rq);
 
 		/*
 		 * Are there still pullable RT tasks?
@@ -1222,7 +1416,7 @@ static int pull_rt_task(struct rq *this_rq)
 		 * Do we have an RT task that preempts
 		 * the to-be-scheduled task?
 		 */
-		if (p && (!next || (p->prio < next->prio))) {
+		if (p && (p->prio < this_rq->rt.highest_prio.curr)) {
 			WARN_ON(p == src_rq->curr);
 			WARN_ON(!p->se.on_rq);
 
@@ -1232,12 +1426,9 @@ static int pull_rt_task(struct rq *this_rq)
 			 * This is just that p is wakeing up and hasn't
 			 * had a chance to schedule. We only pull
 			 * p if it is lower in priority than the
-			 * current task on the run queue or
-			 * this_rq next task is lower in prio than
-			 * the current task on that rq.
+			 * current task on the run queue
 			 */
-			if (p->prio < src_rq->curr->prio ||
-			    (next && next->prio < src_rq->curr->prio))
+			if (p->prio < src_rq->curr->prio)
 				goto skip;
 
 			ret = 1;
@@ -1250,13 +1441,7 @@ static int pull_rt_task(struct rq *this_rq)
 			 * case there's an even higher prio task
 			 * in another runqueue. (low likelyhood
 			 * but possible)
-			 *
-			 * Update next so that we won't pick a task
-			 * on another cpu with a priority lower (or equal)
-			 * than the one we just picked.
 			 */
-			next = p;
-
 		}
  skip:
 		double_unlock_balance(this_rq, src_rq);
@@ -1268,24 +1453,27 @@ static int pull_rt_task(struct rq *this_rq)
 static void pre_schedule_rt(struct rq *rq, struct task_struct *prev)
 {
 	/* Try to pull RT tasks here if we lower this rq's prio */
-	if (unlikely(rt_task(prev)) && rq->rt.highest_prio > prev->prio)
+	if (unlikely(rt_task(prev)) && rq->rt.highest_prio.curr > prev->prio)
 		pull_rt_task(rq);
 }
 
+/*
+ * assumes rq->lock is held
+ */
+static int needs_post_schedule_rt(struct rq *rq)
+{
+	return has_pushable_tasks(rq);
+}
+
 static void post_schedule_rt(struct rq *rq)
 {
 	/*
-	 * If we have more than one rt_task queued, then
-	 * see if we can push the other rt_tasks off to other CPUS.
-	 * Note we may release the rq lock, and since
-	 * the lock was owned by prev, we need to release it
-	 * first via finish_lock_switch and then reaquire it here.
+	 * This is only called if needs_post_schedule_rt() indicates that
+	 * we need to push tasks away
 	 */
-	if (unlikely(rq->rt.overloaded)) {
-		spin_lock_irq(&rq->lock);
-		push_rt_tasks(rq);
-		spin_unlock_irq(&rq->lock);
-	}
+	spin_lock_irq(&rq->lock);
+	push_rt_tasks(rq);
+	spin_unlock_irq(&rq->lock);
 }
 
 /*
@@ -1296,7 +1484,8 @@ static void task_wake_up_rt(struct rq *rq, struct task_struct *p)
 {
 	if (!task_running(rq, p) &&
 	    !test_tsk_need_resched(rq->curr) &&
-	    rq->rt.overloaded)
+	    has_pushable_tasks(rq) &&
+	    p->rt.nr_cpus_allowed > 1)
 		push_rt_tasks(rq);
 }
 
@@ -1332,6 +1521,24 @@ static void set_cpus_allowed_rt(struct task_struct *p,
 	if (p->se.on_rq && (weight != p->rt.nr_cpus_allowed)) {
 		struct rq *rq = task_rq(p);
 
+		if (!task_current(rq, p)) {
+			/*
+			 * Make sure we dequeue this task from the pushable list
+			 * before going further.  It will either remain off of
+			 * the list because we are no longer pushable, or it
+			 * will be requeued.
+			 */
+			if (p->rt.nr_cpus_allowed > 1)
+				dequeue_pushable_task(rq, p);
+
+			/*
+			 * Requeue if our weight is changing and still > 1
+			 */
+			if (weight > 1)
+				enqueue_pushable_task(rq, p);
+
+		}
+
 		if ((p->rt.nr_cpus_allowed <= 1) && (weight > 1)) {
 			rq->rt.rt_nr_migratory++;
 		} else if ((p->rt.nr_cpus_allowed > 1) && (weight <= 1)) {
@@ -1339,7 +1546,7 @@ static void set_cpus_allowed_rt(struct task_struct *p,
 			rq->rt.rt_nr_migratory--;
 		}
 
-		update_rt_migration(rq);
+		update_rt_migration(&rq->rt);
 	}
 
 	cpumask_copy(&p->cpus_allowed, new_mask);
@@ -1354,7 +1561,7 @@ static void rq_online_rt(struct rq *rq)
 
 	__enable_runtime(rq);
 
-	cpupri_set(&rq->rd->cpupri, rq->cpu, rq->rt.highest_prio);
+	cpupri_set(&rq->rd->cpupri, rq->cpu, rq->rt.highest_prio.curr);
 }
 
 /* Assumes rq->lock is held */
@@ -1446,7 +1653,7 @@ static void prio_changed_rt(struct rq *rq, struct task_struct *p,
 		 * can release the rq lock and p could migrate.
 		 * Only reschedule if p is still on the same runqueue.
 		 */
-		if (p->prio > rq->rt.highest_prio && rq->curr == p)
+		if (p->prio > rq->rt.highest_prio.curr && rq->curr == p)
 			resched_task(p);
 #else
 		/* For UP simply resched on drop of prio */
@@ -1517,6 +1724,9 @@ static void set_curr_task_rt(struct rq *rq)
 	struct task_struct *p = rq->curr;
 
 	p->se.exec_start = rq->clock;
+
+	/* The running task is never eligible for pushing */
+	dequeue_pushable_task(rq, p);
 }
 
 static const struct sched_class rt_sched_class = {
@@ -1539,6 +1749,7 @@ static const struct sched_class rt_sched_class = {
 	.rq_online              = rq_online_rt,
 	.rq_offline             = rq_offline_rt,
 	.pre_schedule		= pre_schedule_rt,
+	.needs_post_schedule	= needs_post_schedule_rt,
 	.post_schedule		= post_schedule_rt,
 	.task_wake_up		= task_wake_up_rt,
 	.switched_from		= switched_from_rt,
diff --git a/kernel/sched_stats.h b/kernel/sched_stats.h
index a8f93dd374e..32d2bd4061b 100644
--- a/kernel/sched_stats.h
+++ b/kernel/sched_stats.h
@@ -4,7 +4,7 @@
  * bump this up when changing the output format or the meaning of an existing
  * format, so that tools can adapt (or abort)
  */
-#define SCHEDSTAT_VERSION 14
+#define SCHEDSTAT_VERSION 15
 
 static int show_schedstat(struct seq_file *seq, void *v)
 {
@@ -26,9 +26,8 @@ static int show_schedstat(struct seq_file *seq, void *v)
 
 		/* runqueue-specific stats */
 		seq_printf(seq,
-		    "cpu%d %u %u %u %u %u %u %u %u %u %llu %llu %lu",
-		    cpu, rq->yld_both_empty,
-		    rq->yld_act_empty, rq->yld_exp_empty, rq->yld_count,
+		    "cpu%d %u %u %u %u %u %u %llu %llu %lu",
+		    cpu, rq->yld_count,
 		    rq->sched_switch, rq->sched_count, rq->sched_goidle,
 		    rq->ttwu_count, rq->ttwu_local,
 		    rq->rq_cpu_time,
diff --git a/kernel/signal.c b/kernel/signal.c
index 2a74fe87c0d..d8034737db4 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -55,10 +55,22 @@ static int sig_handler_ignored(void __user *handler, int sig)
 		(handler == SIG_DFL && sig_kernel_ignore(sig));
 }
 
-static int sig_ignored(struct task_struct *t, int sig)
+static int sig_task_ignored(struct task_struct *t, int sig,
+		int from_ancestor_ns)
 {
 	void __user *handler;
 
+	handler = sig_handler(t, sig);
+
+	if (unlikely(t->signal->flags & SIGNAL_UNKILLABLE) &&
+			handler == SIG_DFL && !from_ancestor_ns)
+		return 1;
+
+	return sig_handler_ignored(handler, sig);
+}
+
+static int sig_ignored(struct task_struct *t, int sig, int from_ancestor_ns)
+{
 	/*
 	 * Blocked signals are never ignored, since the
 	 * signal handler may change by the time it is
@@ -67,14 +79,13 @@ static int sig_ignored(struct task_struct *t, int sig)
 	if (sigismember(&t->blocked, sig) || sigismember(&t->real_blocked, sig))
 		return 0;
 
-	handler = sig_handler(t, sig);
-	if (!sig_handler_ignored(handler, sig))
+	if (!sig_task_ignored(t, sig, from_ancestor_ns))
 		return 0;
 
 	/*
 	 * Tracers may want to know about even ignored signals.
 	 */
-	return !tracehook_consider_ignored_signal(t, sig, handler);
+	return !tracehook_consider_ignored_signal(t, sig);
 }
 
 /*
@@ -318,7 +329,7 @@ int unhandled_signal(struct task_struct *tsk, int sig)
 		return 1;
 	if (handler != SIG_IGN && handler != SIG_DFL)
 		return 0;
-	return !tracehook_consider_fatal_signal(tsk, sig, handler);
+	return !tracehook_consider_fatal_signal(tsk, sig);
 }
 
 
@@ -624,7 +635,7 @@ static int check_kill_permission(int sig, struct siginfo *info,
  * Returns true if the signal should be actually delivered, otherwise
  * it should be dropped.
  */
-static int prepare_signal(int sig, struct task_struct *p)
+static int prepare_signal(int sig, struct task_struct *p, int from_ancestor_ns)
 {
 	struct signal_struct *signal = p->signal;
 	struct task_struct *t;
@@ -708,7 +719,7 @@ static int prepare_signal(int sig, struct task_struct *p)
 		}
 	}
 
-	return !sig_ignored(p, sig);
+	return !sig_ignored(p, sig, from_ancestor_ns);
 }
 
 /*
@@ -777,7 +788,7 @@ static void complete_signal(int sig, struct task_struct *p, int group)
 	    !(signal->flags & (SIGNAL_UNKILLABLE | SIGNAL_GROUP_EXIT)) &&
 	    !sigismember(&t->real_blocked, sig) &&
 	    (sig == SIGKILL ||
-	     !tracehook_consider_fatal_signal(t, sig, SIG_DFL))) {
+	     !tracehook_consider_fatal_signal(t, sig))) {
 		/*
 		 * This signal will be fatal to the whole group.
 		 */
@@ -813,8 +824,8 @@ static inline int legacy_queue(struct sigpending *signals, int sig)
 	return (sig < SIGRTMIN) && sigismember(&signals->signal, sig);
 }
 
-static int send_signal(int sig, struct siginfo *info, struct task_struct *t,
-			int group)
+static int __send_signal(int sig, struct siginfo *info, struct task_struct *t,
+			int group, int from_ancestor_ns)
 {
 	struct sigpending *pending;
 	struct sigqueue *q;
@@ -822,7 +833,8 @@ static int send_signal(int sig, struct siginfo *info, struct task_struct *t,
 	trace_sched_signal_send(sig, t);
 
 	assert_spin_locked(&t->sighand->siglock);
-	if (!prepare_signal(sig, t))
+
+	if (!prepare_signal(sig, t, from_ancestor_ns))
 		return 0;
 
 	pending = group ? &t->signal->shared_pending : &t->pending;
@@ -871,6 +883,8 @@ static int send_signal(int sig, struct siginfo *info, struct task_struct *t,
 			break;
 		default:
 			copy_siginfo(&q->info, info);
+			if (from_ancestor_ns)
+				q->info.si_pid = 0;
 			break;
 		}
 	} else if (!is_si_special(info)) {
@@ -889,6 +903,20 @@ out_set:
 	return 0;
 }
 
+static int send_signal(int sig, struct siginfo *info, struct task_struct *t,
+			int group)
+{
+	int from_ancestor_ns = 0;
+
+#ifdef CONFIG_PID_NS
+	if (!is_si_special(info) && SI_FROMUSER(info) &&
+			task_pid_nr_ns(current, task_active_pid_ns(t)) <= 0)
+		from_ancestor_ns = 1;
+#endif
+
+	return __send_signal(sig, info, t, group, from_ancestor_ns);
+}
+
 int print_fatal_signals;
 
 static void print_fatal_signal(struct pt_regs *regs, int signr)
@@ -1133,7 +1161,7 @@ int kill_pid_info_as_uid(int sig, struct siginfo *info, struct pid *pid,
 	if (sig && p->sighand) {
 		unsigned long flags;
 		spin_lock_irqsave(&p->sighand->siglock, flags);
-		ret = __group_send_sig_info(sig, info, p);
+		ret = __send_signal(sig, info, p, 1, 0);
 		spin_unlock_irqrestore(&p->sighand->siglock, flags);
 	}
 out_unlock:
@@ -1320,7 +1348,7 @@ int send_sigqueue(struct sigqueue *q, struct task_struct *t, int group)
 		goto ret;
 
 	ret = 1; /* the signal is ignored */
-	if (!prepare_signal(sig, t))
+	if (!prepare_signal(sig, t, 0))
 		goto out;
 
 	ret = 0;
@@ -1575,7 +1603,15 @@ static void ptrace_stop(int exit_code, int clear_code, siginfo_t *info)
 	read_lock(&tasklist_lock);
 	if (may_ptrace_stop()) {
 		do_notify_parent_cldstop(current, CLD_TRAPPED);
+		/*
+		 * Don't want to allow preemption here, because
+		 * sys_ptrace() needs this task to be inactive.
+		 *
+		 * XXX: implement read_unlock_no_resched().
+		 */
+		preempt_disable();
 		read_unlock(&tasklist_lock);
+		preempt_enable_no_resched();
 		schedule();
 	} else {
 		/*
@@ -1836,9 +1872,16 @@ relock:
 
 		/*
 		 * Global init gets no signals it doesn't want.
+		 * Container-init gets no signals it doesn't want from same
+		 * container.
+		 *
+		 * Note that if global/container-init sees a sig_kernel_only()
+		 * signal here, the signal must have been generated internally
+		 * or must have come from an ancestor namespace. In either
+		 * case, the signal cannot be dropped.
 		 */
 		if (unlikely(signal->flags & SIGNAL_UNKILLABLE) &&
-		    !signal_group_exit(signal))
+				!sig_kernel_only(signr))
 			continue;
 
 		if (sig_kernel_stop(signr)) {
diff --git a/kernel/slow-work.c b/kernel/slow-work.c
new file mode 100644
index 00000000000..cf2bc01186e
--- /dev/null
+++ b/kernel/slow-work.c
@@ -0,0 +1,640 @@
+/* Worker thread pool for slow items, such as filesystem lookups or mkdirs
+ *
+ * Copyright (C) 2008 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public Licence
+ * as published by the Free Software Foundation; either version
+ * 2 of the Licence, or (at your option) any later version.
+ *
+ * See Documentation/slow-work.txt
+ */
+
+#include <linux/module.h>
+#include <linux/slow-work.h>
+#include <linux/kthread.h>
+#include <linux/freezer.h>
+#include <linux/wait.h>
+
+#define SLOW_WORK_CULL_TIMEOUT (5 * HZ)	/* cull threads 5s after running out of
+					 * things to do */
+#define SLOW_WORK_OOM_TIMEOUT (5 * HZ)	/* can't start new threads for 5s after
+					 * OOM */
+
+static void slow_work_cull_timeout(unsigned long);
+static void slow_work_oom_timeout(unsigned long);
+
+#ifdef CONFIG_SYSCTL
+static int slow_work_min_threads_sysctl(struct ctl_table *, int, struct file *,
+					void __user *, size_t *, loff_t *);
+
+static int slow_work_max_threads_sysctl(struct ctl_table *, int , struct file *,
+					void __user *, size_t *, loff_t *);
+#endif
+
+/*
+ * The pool of threads has at least min threads in it as long as someone is
+ * using the facility, and may have as many as max.
+ *
+ * A portion of the pool may be processing very slow operations.
+ */
+static unsigned slow_work_min_threads = 2;
+static unsigned slow_work_max_threads = 4;
+static unsigned vslow_work_proportion = 50; /* % of threads that may process
+					     * very slow work */
+
+#ifdef CONFIG_SYSCTL
+static const int slow_work_min_min_threads = 2;
+static int slow_work_max_max_threads = 255;
+static const int slow_work_min_vslow = 1;
+static const int slow_work_max_vslow = 99;
+
+ctl_table slow_work_sysctls[] = {
+	{
+		.ctl_name	= CTL_UNNUMBERED,
+		.procname	= "min-threads",
+		.data		= &slow_work_min_threads,
+		.maxlen		= sizeof(unsigned),
+		.mode		= 0644,
+		.proc_handler	= slow_work_min_threads_sysctl,
+		.extra1		= (void *) &slow_work_min_min_threads,
+		.extra2		= &slow_work_max_threads,
+	},
+	{
+		.ctl_name	= CTL_UNNUMBERED,
+		.procname	= "max-threads",
+		.data		= &slow_work_max_threads,
+		.maxlen		= sizeof(unsigned),
+		.mode		= 0644,
+		.proc_handler	= slow_work_max_threads_sysctl,
+		.extra1		= &slow_work_min_threads,
+		.extra2		= (void *) &slow_work_max_max_threads,
+	},
+	{
+		.ctl_name	= CTL_UNNUMBERED,
+		.procname	= "vslow-percentage",
+		.data		= &vslow_work_proportion,
+		.maxlen		= sizeof(unsigned),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec_minmax,
+		.extra1		= (void *) &slow_work_min_vslow,
+		.extra2		= (void *) &slow_work_max_vslow,
+	},
+	{ .ctl_name = 0 }
+};
+#endif
+
+/*
+ * The active state of the thread pool
+ */
+static atomic_t slow_work_thread_count;
+static atomic_t vslow_work_executing_count;
+
+static bool slow_work_may_not_start_new_thread;
+static bool slow_work_cull; /* cull a thread due to lack of activity */
+static DEFINE_TIMER(slow_work_cull_timer, slow_work_cull_timeout, 0, 0);
+static DEFINE_TIMER(slow_work_oom_timer, slow_work_oom_timeout, 0, 0);
+static struct slow_work slow_work_new_thread; /* new thread starter */
+
+/*
+ * The queues of work items and the lock governing access to them.  These are
+ * shared between all the CPUs.  It doesn't make sense to have per-CPU queues
+ * as the number of threads bears no relation to the number of CPUs.
+ *
+ * There are two queues of work items: one for slow work items, and one for
+ * very slow work items.
+ */
+static LIST_HEAD(slow_work_queue);
+static LIST_HEAD(vslow_work_queue);
+static DEFINE_SPINLOCK(slow_work_queue_lock);
+
+/*
+ * The thread controls.  A variable used to signal to the threads that they
+ * should exit when the queue is empty, a waitqueue used by the threads to wait
+ * for signals, and a completion set by the last thread to exit.
+ */
+static bool slow_work_threads_should_exit;
+static DECLARE_WAIT_QUEUE_HEAD(slow_work_thread_wq);
+static DECLARE_COMPLETION(slow_work_last_thread_exited);
+
+/*
+ * The number of users of the thread pool and its lock.  Whilst this is zero we
+ * have no threads hanging around, and when this reaches zero, we wait for all
+ * active or queued work items to complete and kill all the threads we do have.
+ */
+static int slow_work_user_count;
+static DEFINE_MUTEX(slow_work_user_lock);
+
+/*
+ * Calculate the maximum number of active threads in the pool that are
+ * permitted to process very slow work items.
+ *
+ * The answer is rounded up to at least 1, but may not equal or exceed the
+ * maximum number of the threads in the pool.  This means we always have at
+ * least one thread that can process slow work items, and we always have at
+ * least one thread that won't get tied up doing so.
+ */
+static unsigned slow_work_calc_vsmax(void)
+{
+	unsigned vsmax;
+
+	vsmax = atomic_read(&slow_work_thread_count) * vslow_work_proportion;
+	vsmax /= 100;
+	vsmax = max(vsmax, 1U);
+	return min(vsmax, slow_work_max_threads - 1);
+}
+
+/*
+ * Attempt to execute stuff queued on a slow thread.  Return true if we managed
+ * it, false if there was nothing to do.
+ */
+static bool slow_work_execute(void)
+{
+	struct slow_work *work = NULL;
+	unsigned vsmax;
+	bool very_slow;
+
+	vsmax = slow_work_calc_vsmax();
+
+	/* see if we can schedule a new thread to be started if we're not
+	 * keeping up with the work */
+	if (!waitqueue_active(&slow_work_thread_wq) &&
+	    (!list_empty(&slow_work_queue) || !list_empty(&vslow_work_queue)) &&
+	    atomic_read(&slow_work_thread_count) < slow_work_max_threads &&
+	    !slow_work_may_not_start_new_thread)
+		slow_work_enqueue(&slow_work_new_thread);
+
+	/* find something to execute */
+	spin_lock_irq(&slow_work_queue_lock);
+	if (!list_empty(&vslow_work_queue) &&
+	    atomic_read(&vslow_work_executing_count) < vsmax) {
+		work = list_entry(vslow_work_queue.next,
+				  struct slow_work, link);
+		if (test_and_set_bit_lock(SLOW_WORK_EXECUTING, &work->flags))
+			BUG();
+		list_del_init(&work->link);
+		atomic_inc(&vslow_work_executing_count);
+		very_slow = true;
+	} else if (!list_empty(&slow_work_queue)) {
+		work = list_entry(slow_work_queue.next,
+				  struct slow_work, link);
+		if (test_and_set_bit_lock(SLOW_WORK_EXECUTING, &work->flags))
+			BUG();
+		list_del_init(&work->link);
+		very_slow = false;
+	} else {
+		very_slow = false; /* avoid the compiler warning */
+	}
+	spin_unlock_irq(&slow_work_queue_lock);
+
+	if (!work)
+		return false;
+
+	if (!test_and_clear_bit(SLOW_WORK_PENDING, &work->flags))
+		BUG();
+
+	work->ops->execute(work);
+
+	if (very_slow)
+		atomic_dec(&vslow_work_executing_count);
+	clear_bit_unlock(SLOW_WORK_EXECUTING, &work->flags);
+
+	/* if someone tried to enqueue the item whilst we were executing it,
+	 * then it'll be left unenqueued to avoid multiple threads trying to
+	 * execute it simultaneously
+	 *
+	 * there is, however, a race between us testing the pending flag and
+	 * getting the spinlock, and between the enqueuer setting the pending
+	 * flag and getting the spinlock, so we use a deferral bit to tell us
+	 * if the enqueuer got there first
+	 */
+	if (test_bit(SLOW_WORK_PENDING, &work->flags)) {
+		spin_lock_irq(&slow_work_queue_lock);
+
+		if (!test_bit(SLOW_WORK_EXECUTING, &work->flags) &&
+		    test_and_clear_bit(SLOW_WORK_ENQ_DEFERRED, &work->flags))
+			goto auto_requeue;
+
+		spin_unlock_irq(&slow_work_queue_lock);
+	}
+
+	work->ops->put_ref(work);
+	return true;
+
+auto_requeue:
+	/* we must complete the enqueue operation
+	 * - we transfer our ref on the item back to the appropriate queue
+	 * - don't wake another thread up as we're awake already
+	 */
+	if (test_bit(SLOW_WORK_VERY_SLOW, &work->flags))
+		list_add_tail(&work->link, &vslow_work_queue);
+	else
+		list_add_tail(&work->link, &slow_work_queue);
+	spin_unlock_irq(&slow_work_queue_lock);
+	return true;
+}
+
+/**
+ * slow_work_enqueue - Schedule a slow work item for processing
+ * @work: The work item to queue
+ *
+ * Schedule a slow work item for processing.  If the item is already undergoing
+ * execution, this guarantees not to re-enter the execution routine until the
+ * first execution finishes.
+ *
+ * The item is pinned by this function as it retains a reference to it, managed
+ * through the item operations.  The item is unpinned once it has been
+ * executed.
+ *
+ * An item may hog the thread that is running it for a relatively large amount
+ * of time, sufficient, for example, to perform several lookup, mkdir, create
+ * and setxattr operations.  It may sleep on I/O and may sleep to obtain locks.
+ *
+ * Conversely, if a number of items are awaiting processing, it may take some
+ * time before any given item is given attention.  The number of threads in the
+ * pool may be increased to deal with demand, but only up to a limit.
+ *
+ * If SLOW_WORK_VERY_SLOW is set on the work item, then it will be placed in
+ * the very slow queue, from which only a portion of the threads will be
+ * allowed to pick items to execute.  This ensures that very slow items won't
+ * overly block ones that are just ordinarily slow.
+ *
+ * Returns 0 if successful, -EAGAIN if not.
+ */
+int slow_work_enqueue(struct slow_work *work)
+{
+	unsigned long flags;
+
+	BUG_ON(slow_work_user_count <= 0);
+	BUG_ON(!work);
+	BUG_ON(!work->ops);
+	BUG_ON(!work->ops->get_ref);
+
+	/* when honouring an enqueue request, we only promise that we will run
+	 * the work function in the future; we do not promise to run it once
+	 * per enqueue request
+	 *
+	 * we use the PENDING bit to merge together repeat requests without
+	 * having to disable IRQs and take the spinlock, whilst still
+	 * maintaining our promise
+	 */
+	if (!test_and_set_bit_lock(SLOW_WORK_PENDING, &work->flags)) {
+		spin_lock_irqsave(&slow_work_queue_lock, flags);
+
+		/* we promise that we will not attempt to execute the work
+		 * function in more than one thread simultaneously
+		 *
+		 * this, however, leaves us with a problem if we're asked to
+		 * enqueue the work whilst someone is executing the work
+		 * function as simply queueing the work immediately means that
+		 * another thread may try executing it whilst it is already
+		 * under execution
+		 *
+		 * to deal with this, we set the ENQ_DEFERRED bit instead of
+		 * enqueueing, and the thread currently executing the work
+		 * function will enqueue the work item when the work function
+		 * returns and it has cleared the EXECUTING bit
+		 */
+		if (test_bit(SLOW_WORK_EXECUTING, &work->flags)) {
+			set_bit(SLOW_WORK_ENQ_DEFERRED, &work->flags);
+		} else {
+			if (work->ops->get_ref(work) < 0)
+				goto cant_get_ref;
+			if (test_bit(SLOW_WORK_VERY_SLOW, &work->flags))
+				list_add_tail(&work->link, &vslow_work_queue);
+			else
+				list_add_tail(&work->link, &slow_work_queue);
+			wake_up(&slow_work_thread_wq);
+		}
+
+		spin_unlock_irqrestore(&slow_work_queue_lock, flags);
+	}
+	return 0;
+
+cant_get_ref:
+	spin_unlock_irqrestore(&slow_work_queue_lock, flags);
+	return -EAGAIN;
+}
+EXPORT_SYMBOL(slow_work_enqueue);
+
+/*
+ * Worker thread culling algorithm
+ */
+static bool slow_work_cull_thread(void)
+{
+	unsigned long flags;
+	bool do_cull = false;
+
+	spin_lock_irqsave(&slow_work_queue_lock, flags);
+
+	if (slow_work_cull) {
+		slow_work_cull = false;
+
+		if (list_empty(&slow_work_queue) &&
+		    list_empty(&vslow_work_queue) &&
+		    atomic_read(&slow_work_thread_count) >
+		    slow_work_min_threads) {
+			mod_timer(&slow_work_cull_timer,
+				  jiffies + SLOW_WORK_CULL_TIMEOUT);
+			do_cull = true;
+		}
+	}
+
+	spin_unlock_irqrestore(&slow_work_queue_lock, flags);
+	return do_cull;
+}
+
+/*
+ * Determine if there is slow work available for dispatch
+ */
+static inline bool slow_work_available(int vsmax)
+{
+	return !list_empty(&slow_work_queue) ||
+		(!list_empty(&vslow_work_queue) &&
+		 atomic_read(&vslow_work_executing_count) < vsmax);
+}
+
+/*
+ * Worker thread dispatcher
+ */
+static int slow_work_thread(void *_data)
+{
+	int vsmax;
+
+	DEFINE_WAIT(wait);
+
+	set_freezable();
+	set_user_nice(current, -5);
+
+	for (;;) {
+		vsmax = vslow_work_proportion;
+		vsmax *= atomic_read(&slow_work_thread_count);
+		vsmax /= 100;
+
+		prepare_to_wait(&slow_work_thread_wq, &wait,
+				TASK_INTERRUPTIBLE);
+		if (!freezing(current) &&
+		    !slow_work_threads_should_exit &&
+		    !slow_work_available(vsmax) &&
+		    !slow_work_cull)
+			schedule();
+		finish_wait(&slow_work_thread_wq, &wait);
+
+		try_to_freeze();
+
+		vsmax = vslow_work_proportion;
+		vsmax *= atomic_read(&slow_work_thread_count);
+		vsmax /= 100;
+
+		if (slow_work_available(vsmax) && slow_work_execute()) {
+			cond_resched();
+			if (list_empty(&slow_work_queue) &&
+			    list_empty(&vslow_work_queue) &&
+			    atomic_read(&slow_work_thread_count) >
+			    slow_work_min_threads)
+				mod_timer(&slow_work_cull_timer,
+					  jiffies + SLOW_WORK_CULL_TIMEOUT);
+			continue;
+		}
+
+		if (slow_work_threads_should_exit)
+			break;
+
+		if (slow_work_cull && slow_work_cull_thread())
+			break;
+	}
+
+	if (atomic_dec_and_test(&slow_work_thread_count))
+		complete_and_exit(&slow_work_last_thread_exited, 0);
+	return 0;
+}
+
+/*
+ * Handle thread cull timer expiration
+ */
+static void slow_work_cull_timeout(unsigned long data)
+{
+	slow_work_cull = true;
+	wake_up(&slow_work_thread_wq);
+}
+
+/*
+ * Get a reference on slow work thread starter
+ */
+static int slow_work_new_thread_get_ref(struct slow_work *work)
+{
+	return 0;
+}
+
+/*
+ * Drop a reference on slow work thread starter
+ */
+static void slow_work_new_thread_put_ref(struct slow_work *work)
+{
+}
+
+/*
+ * Start a new slow work thread
+ */
+static void slow_work_new_thread_execute(struct slow_work *work)
+{
+	struct task_struct *p;
+
+	if (slow_work_threads_should_exit)
+		return;
+
+	if (atomic_read(&slow_work_thread_count) >= slow_work_max_threads)
+		return;
+
+	if (!mutex_trylock(&slow_work_user_lock))
+		return;
+
+	slow_work_may_not_start_new_thread = true;
+	atomic_inc(&slow_work_thread_count);
+	p = kthread_run(slow_work_thread, NULL, "kslowd");
+	if (IS_ERR(p)) {
+		printk(KERN_DEBUG "Slow work thread pool: OOM\n");
+		if (atomic_dec_and_test(&slow_work_thread_count))
+			BUG(); /* we're running on a slow work thread... */
+		mod_timer(&slow_work_oom_timer,
+			  jiffies + SLOW_WORK_OOM_TIMEOUT);
+	} else {
+		/* ratelimit the starting of new threads */
+		mod_timer(&slow_work_oom_timer, jiffies + 1);
+	}
+
+	mutex_unlock(&slow_work_user_lock);
+}
+
+static const struct slow_work_ops slow_work_new_thread_ops = {
+	.get_ref	= slow_work_new_thread_get_ref,
+	.put_ref	= slow_work_new_thread_put_ref,
+	.execute	= slow_work_new_thread_execute,
+};
+
+/*
+ * post-OOM new thread start suppression expiration
+ */
+static void slow_work_oom_timeout(unsigned long data)
+{
+	slow_work_may_not_start_new_thread = false;
+}
+
+#ifdef CONFIG_SYSCTL
+/*
+ * Handle adjustment of the minimum number of threads
+ */
+static int slow_work_min_threads_sysctl(struct ctl_table *table, int write,
+					struct file *filp, void __user *buffer,
+					size_t *lenp, loff_t *ppos)
+{
+	int ret = proc_dointvec_minmax(table, write, filp, buffer, lenp, ppos);
+	int n;
+
+	if (ret == 0) {
+		mutex_lock(&slow_work_user_lock);
+		if (slow_work_user_count > 0) {
+			/* see if we need to start or stop threads */
+			n = atomic_read(&slow_work_thread_count) -
+				slow_work_min_threads;
+
+			if (n < 0 && !slow_work_may_not_start_new_thread)
+				slow_work_enqueue(&slow_work_new_thread);
+			else if (n > 0)
+				mod_timer(&slow_work_cull_timer,
+					  jiffies + SLOW_WORK_CULL_TIMEOUT);
+		}
+		mutex_unlock(&slow_work_user_lock);
+	}
+
+	return ret;
+}
+
+/*
+ * Handle adjustment of the maximum number of threads
+ */
+static int slow_work_max_threads_sysctl(struct ctl_table *table, int write,
+					struct file *filp, void __user *buffer,
+					size_t *lenp, loff_t *ppos)
+{
+	int ret = proc_dointvec_minmax(table, write, filp, buffer, lenp, ppos);
+	int n;
+
+	if (ret == 0) {
+		mutex_lock(&slow_work_user_lock);
+		if (slow_work_user_count > 0) {
+			/* see if we need to stop threads */
+			n = slow_work_max_threads -
+				atomic_read(&slow_work_thread_count);
+
+			if (n < 0)
+				mod_timer(&slow_work_cull_timer,
+					  jiffies + SLOW_WORK_CULL_TIMEOUT);
+		}
+		mutex_unlock(&slow_work_user_lock);
+	}
+
+	return ret;
+}
+#endif /* CONFIG_SYSCTL */
+
+/**
+ * slow_work_register_user - Register a user of the facility
+ *
+ * Register a user of the facility, starting up the initial threads if there
+ * aren't any other users at this point.  This will return 0 if successful, or
+ * an error if not.
+ */
+int slow_work_register_user(void)
+{
+	struct task_struct *p;
+	int loop;
+
+	mutex_lock(&slow_work_user_lock);
+
+	if (slow_work_user_count == 0) {
+		printk(KERN_NOTICE "Slow work thread pool: Starting up\n");
+		init_completion(&slow_work_last_thread_exited);
+
+		slow_work_threads_should_exit = false;
+		slow_work_init(&slow_work_new_thread,
+			       &slow_work_new_thread_ops);
+		slow_work_may_not_start_new_thread = false;
+		slow_work_cull = false;
+
+		/* start the minimum number of threads */
+		for (loop = 0; loop < slow_work_min_threads; loop++) {
+			atomic_inc(&slow_work_thread_count);
+			p = kthread_run(slow_work_thread, NULL, "kslowd");
+			if (IS_ERR(p))
+				goto error;
+		}
+		printk(KERN_NOTICE "Slow work thread pool: Ready\n");
+	}
+
+	slow_work_user_count++;
+	mutex_unlock(&slow_work_user_lock);
+	return 0;
+
+error:
+	if (atomic_dec_and_test(&slow_work_thread_count))
+		complete(&slow_work_last_thread_exited);
+	if (loop > 0) {
+		printk(KERN_ERR "Slow work thread pool:"
+		       " Aborting startup on ENOMEM\n");
+		slow_work_threads_should_exit = true;
+		wake_up_all(&slow_work_thread_wq);
+		wait_for_completion(&slow_work_last_thread_exited);
+		printk(KERN_ERR "Slow work thread pool: Aborted\n");
+	}
+	mutex_unlock(&slow_work_user_lock);
+	return PTR_ERR(p);
+}
+EXPORT_SYMBOL(slow_work_register_user);
+
+/**
+ * slow_work_unregister_user - Unregister a user of the facility
+ *
+ * Unregister a user of the facility, killing all the threads if this was the
+ * last one.
+ */
+void slow_work_unregister_user(void)
+{
+	mutex_lock(&slow_work_user_lock);
+
+	BUG_ON(slow_work_user_count <= 0);
+
+	slow_work_user_count--;
+	if (slow_work_user_count == 0) {
+		printk(KERN_NOTICE "Slow work thread pool: Shutting down\n");
+		slow_work_threads_should_exit = true;
+		wake_up_all(&slow_work_thread_wq);
+		wait_for_completion(&slow_work_last_thread_exited);
+		printk(KERN_NOTICE "Slow work thread pool:"
+		       " Shut down complete\n");
+	}
+
+	del_timer_sync(&slow_work_cull_timer);
+
+	mutex_unlock(&slow_work_user_lock);
+}
+EXPORT_SYMBOL(slow_work_unregister_user);
+
+/*
+ * Initialise the slow work facility
+ */
+static int __init init_slow_work(void)
+{
+	unsigned nr_cpus = num_possible_cpus();
+
+	if (slow_work_max_threads < nr_cpus)
+		slow_work_max_threads = nr_cpus;
+#ifdef CONFIG_SYSCTL
+	if (slow_work_max_max_threads < nr_cpus * 2)
+		slow_work_max_max_threads = nr_cpus * 2;
+#endif
+	return 0;
+}
+
+subsys_initcall(init_slow_work);
diff --git a/kernel/smp.c b/kernel/smp.c
index bbedbb7efe3..858baac568e 100644
--- a/kernel/smp.c
+++ b/kernel/smp.c
@@ -2,40 +2,82 @@
  * Generic helpers for smp ipi calls
  *
  * (C) Jens Axboe <jens.axboe@oracle.com> 2008
- *
  */
-#include <linux/init.h>
-#include <linux/module.h>
-#include <linux/percpu.h>
 #include <linux/rcupdate.h>
 #include <linux/rculist.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/percpu.h>
+#include <linux/init.h>
 #include <linux/smp.h>
+#include <linux/cpu.h>
 
 static DEFINE_PER_CPU(struct call_single_queue, call_single_queue);
-static LIST_HEAD(call_function_queue);
-__cacheline_aligned_in_smp DEFINE_SPINLOCK(call_function_lock);
+
+static struct {
+	struct list_head	queue;
+	spinlock_t		lock;
+} call_function __cacheline_aligned_in_smp =
+	{
+		.queue		= LIST_HEAD_INIT(call_function.queue),
+		.lock		= __SPIN_LOCK_UNLOCKED(call_function.lock),
+	};
 
 enum {
-	CSD_FLAG_WAIT		= 0x01,
-	CSD_FLAG_ALLOC		= 0x02,
-	CSD_FLAG_LOCK		= 0x04,
+	CSD_FLAG_LOCK		= 0x01,
 };
 
 struct call_function_data {
-	struct call_single_data csd;
-	spinlock_t lock;
-	unsigned int refs;
-	struct rcu_head rcu_head;
-	unsigned long cpumask_bits[];
+	struct call_single_data	csd;
+	spinlock_t		lock;
+	unsigned int		refs;
+	cpumask_var_t		cpumask;
 };
 
 struct call_single_queue {
-	struct list_head list;
-	spinlock_t lock;
+	struct list_head	list;
+	spinlock_t		lock;
+};
+
+static DEFINE_PER_CPU(struct call_function_data, cfd_data) = {
+	.lock			= __SPIN_LOCK_UNLOCKED(cfd_data.lock),
+};
+
+static int
+hotplug_cfd(struct notifier_block *nfb, unsigned long action, void *hcpu)
+{
+	long cpu = (long)hcpu;
+	struct call_function_data *cfd = &per_cpu(cfd_data, cpu);
+
+	switch (action) {
+	case CPU_UP_PREPARE:
+	case CPU_UP_PREPARE_FROZEN:
+		if (!alloc_cpumask_var_node(&cfd->cpumask, GFP_KERNEL,
+				cpu_to_node(cpu)))
+			return NOTIFY_BAD;
+		break;
+
+#ifdef CONFIG_CPU_HOTPLUG
+	case CPU_UP_CANCELED:
+	case CPU_UP_CANCELED_FROZEN:
+
+	case CPU_DEAD:
+	case CPU_DEAD_FROZEN:
+		free_cpumask_var(cfd->cpumask);
+		break;
+#endif
+	};
+
+	return NOTIFY_OK;
+}
+
+static struct notifier_block __cpuinitdata hotplug_cfd_notifier = {
+	.notifier_call		= hotplug_cfd,
 };
 
 static int __cpuinit init_call_single_data(void)
 {
+	void *cpu = (void *)(long)smp_processor_id();
 	int i;
 
 	for_each_possible_cpu(i) {
@@ -44,29 +86,63 @@ static int __cpuinit init_call_single_data(void)
 		spin_lock_init(&q->lock);
 		INIT_LIST_HEAD(&q->list);
 	}
+
+	hotplug_cfd(&hotplug_cfd_notifier, CPU_UP_PREPARE, cpu);
+	register_cpu_notifier(&hotplug_cfd_notifier);
+
 	return 0;
 }
 early_initcall(init_call_single_data);
 
-static void csd_flag_wait(struct call_single_data *data)
+/*
+ * csd_lock/csd_unlock used to serialize access to per-cpu csd resources
+ *
+ * For non-synchronous ipi calls the csd can still be in use by the
+ * previous function call. For multi-cpu calls its even more interesting
+ * as we'll have to ensure no other cpu is observing our csd.
+ */
+static void csd_lock_wait(struct call_single_data *data)
 {
-	/* Wait for response */
-	do {
-		if (!(data->flags & CSD_FLAG_WAIT))
-			break;
+	while (data->flags & CSD_FLAG_LOCK)
 		cpu_relax();
-	} while (1);
+}
+
+static void csd_lock(struct call_single_data *data)
+{
+	csd_lock_wait(data);
+	data->flags = CSD_FLAG_LOCK;
+
+	/*
+	 * prevent CPU from reordering the above assignment
+	 * to ->flags with any subsequent assignments to other
+	 * fields of the specified call_single_data structure:
+	 */
+	smp_mb();
+}
+
+static void csd_unlock(struct call_single_data *data)
+{
+	WARN_ON(!(data->flags & CSD_FLAG_LOCK));
+
+	/*
+	 * ensure we're all done before releasing data:
+	 */
+	smp_mb();
+
+	data->flags &= ~CSD_FLAG_LOCK;
 }
 
 /*
- * Insert a previously allocated call_single_data element for execution
- * on the given CPU. data must already have ->func, ->info, and ->flags set.
+ * Insert a previously allocated call_single_data element
+ * for execution on the given CPU. data must already have
+ * ->func, ->info, and ->flags set.
  */
-static void generic_exec_single(int cpu, struct call_single_data *data)
+static
+void generic_exec_single(int cpu, struct call_single_data *data, int wait)
 {
 	struct call_single_queue *dst = &per_cpu(call_single_queue, cpu);
-	int wait = data->flags & CSD_FLAG_WAIT, ipi;
 	unsigned long flags;
+	int ipi;
 
 	spin_lock_irqsave(&dst->lock, flags);
 	ipi = list_empty(&dst->list);
@@ -74,24 +150,21 @@ static void generic_exec_single(int cpu, struct call_single_data *data)
 	spin_unlock_irqrestore(&dst->lock, flags);
 
 	/*
-	 * Make the list addition visible before sending the ipi.
+	 * The list addition should be visible before sending the IPI
+	 * handler locks the list to pull the entry off it because of
+	 * normal cache coherency rules implied by spinlocks.
+	 *
+	 * If IPIs can go out of order to the cache coherency protocol
+	 * in an architecture, sufficient synchronisation should be added
+	 * to arch code to make it appear to obey cache coherency WRT
+	 * locking and barrier primitives. Generic code isn't really
+	 * equipped to do the right thing...
 	 */
-	smp_mb();
-
 	if (ipi)
 		arch_send_call_function_single_ipi(cpu);
 
 	if (wait)
-		csd_flag_wait(data);
-}
-
-static void rcu_free_call_data(struct rcu_head *head)
-{
-	struct call_function_data *data;
-
-	data = container_of(head, struct call_function_data, rcu_head);
-
-	kfree(data);
+		csd_lock_wait(data);
 }
 
 /*
@@ -104,99 +177,83 @@ void generic_smp_call_function_interrupt(void)
 	int cpu = get_cpu();
 
 	/*
-	 * It's ok to use list_for_each_rcu() here even though we may delete
-	 * 'pos', since list_del_rcu() doesn't clear ->next
+	 * Ensure entry is visible on call_function_queue after we have
+	 * entered the IPI. See comment in smp_call_function_many.
+	 * If we don't have this, then we may miss an entry on the list
+	 * and never get another IPI to process it.
+	 */
+	smp_mb();
+
+	/*
+	 * It's ok to use list_for_each_rcu() here even though we may
+	 * delete 'pos', since list_del_rcu() doesn't clear ->next
 	 */
-	rcu_read_lock();
-	list_for_each_entry_rcu(data, &call_function_queue, csd.list) {
+	list_for_each_entry_rcu(data, &call_function.queue, csd.list) {
 		int refs;
 
-		if (!cpumask_test_cpu(cpu, to_cpumask(data->cpumask_bits)))
+		spin_lock(&data->lock);
+		if (!cpumask_test_cpu(cpu, data->cpumask)) {
+			spin_unlock(&data->lock);
 			continue;
+		}
+		cpumask_clear_cpu(cpu, data->cpumask);
+		spin_unlock(&data->lock);
 
 		data->csd.func(data->csd.info);
 
 		spin_lock(&data->lock);
-		cpumask_clear_cpu(cpu, to_cpumask(data->cpumask_bits));
 		WARN_ON(data->refs == 0);
-		data->refs--;
-		refs = data->refs;
+		refs = --data->refs;
+		if (!refs) {
+			spin_lock(&call_function.lock);
+			list_del_rcu(&data->csd.list);
+			spin_unlock(&call_function.lock);
+		}
 		spin_unlock(&data->lock);
 
 		if (refs)
 			continue;
 
-		spin_lock(&call_function_lock);
-		list_del_rcu(&data->csd.list);
-		spin_unlock(&call_function_lock);
-
-		if (data->csd.flags & CSD_FLAG_WAIT) {
-			/*
-			 * serialize stores to data with the flag clear
-			 * and wakeup
-			 */
-			smp_wmb();
-			data->csd.flags &= ~CSD_FLAG_WAIT;
-		}
-		if (data->csd.flags & CSD_FLAG_ALLOC)
-			call_rcu(&data->rcu_head, rcu_free_call_data);
+		csd_unlock(&data->csd);
 	}
-	rcu_read_unlock();
 
 	put_cpu();
 }
 
 /*
- * Invoked by arch to handle an IPI for call function single. Must be called
- * from the arch with interrupts disabled.
+ * Invoked by arch to handle an IPI for call function single. Must be
+ * called from the arch with interrupts disabled.
  */
 void generic_smp_call_function_single_interrupt(void)
 {
 	struct call_single_queue *q = &__get_cpu_var(call_single_queue);
+	unsigned int data_flags;
 	LIST_HEAD(list);
 
-	/*
-	 * Need to see other stores to list head for checking whether
-	 * list is empty without holding q->lock
-	 */
-	smp_read_barrier_depends();
-	while (!list_empty(&q->list)) {
-		unsigned int data_flags;
-
-		spin_lock(&q->lock);
-		list_replace_init(&q->list, &list);
-		spin_unlock(&q->lock);
-
-		while (!list_empty(&list)) {
-			struct call_single_data *data;
-
-			data = list_entry(list.next, struct call_single_data,
-						list);
-			list_del(&data->list);
-
-			/*
-			 * 'data' can be invalid after this call if
-			 * flags == 0 (when called through
-			 * generic_exec_single(), so save them away before
-			 * making the call.
-			 */
-			data_flags = data->flags;
-
-			data->func(data->info);
-
-			if (data_flags & CSD_FLAG_WAIT) {
-				smp_wmb();
-				data->flags &= ~CSD_FLAG_WAIT;
-			} else if (data_flags & CSD_FLAG_LOCK) {
-				smp_wmb();
-				data->flags &= ~CSD_FLAG_LOCK;
-			} else if (data_flags & CSD_FLAG_ALLOC)
-				kfree(data);
-		}
+	spin_lock(&q->lock);
+	list_replace_init(&q->list, &list);
+	spin_unlock(&q->lock);
+
+	while (!list_empty(&list)) {
+		struct call_single_data *data;
+
+		data = list_entry(list.next, struct call_single_data, list);
+		list_del(&data->list);
+
+		/*
+		 * 'data' can be invalid after this call if flags == 0
+		 * (when called through generic_exec_single()),
+		 * so save them away before making the call:
+		 */
+		data_flags = data->flags;
+
+		data->func(data->info);
+
 		/*
-		 * See comment on outer loop
+		 * Unlocked CSDs are valid through generic_exec_single():
 		 */
-		smp_read_barrier_depends();
+		if (data_flags & CSD_FLAG_LOCK)
+			csd_unlock(data);
 	}
 }
 
@@ -215,65 +272,45 @@ static DEFINE_PER_CPU(struct call_single_data, csd_data);
 int smp_call_function_single(int cpu, void (*func) (void *info), void *info,
 			     int wait)
 {
-	struct call_single_data d;
+	struct call_single_data d = {
+		.flags = 0,
+	};
 	unsigned long flags;
-	/* prevent preemption and reschedule on another processor,
-	   as well as CPU removal */
-	int me = get_cpu();
+	int this_cpu;
 	int err = 0;
 
+	/*
+	 * prevent preemption and reschedule on another processor,
+	 * as well as CPU removal
+	 */
+	this_cpu = get_cpu();
+
 	/* Can deadlock when called with interrupts disabled */
-	WARN_ON(irqs_disabled());
+	WARN_ON_ONCE(irqs_disabled() && !oops_in_progress);
 
-	if (cpu == me) {
+	if (cpu == this_cpu) {
 		local_irq_save(flags);
 		func(info);
 		local_irq_restore(flags);
-	} else if ((unsigned)cpu < nr_cpu_ids && cpu_online(cpu)) {
-		struct call_single_data *data;
+	} else {
+		if ((unsigned)cpu < nr_cpu_ids && cpu_online(cpu)) {
+			struct call_single_data *data = &d;
+
+			if (!wait)
+				data = &__get_cpu_var(csd_data);
 
-		if (!wait) {
-			/*
-			 * We are calling a function on a single CPU
-			 * and we are not going to wait for it to finish.
-			 * We first try to allocate the data, but if we
-			 * fail, we fall back to use a per cpu data to pass
-			 * the information to that CPU. Since all callers
-			 * of this code will use the same data, we must
-			 * synchronize the callers to prevent a new caller
-			 * from corrupting the data before the callee
-			 * can access it.
-			 *
-			 * The CSD_FLAG_LOCK is used to let us know when
-			 * the IPI handler is done with the data.
-			 * The first caller will set it, and the callee
-			 * will clear it. The next caller must wait for
-			 * it to clear before we set it again. This
-			 * will make sure the callee is done with the
-			 * data before a new caller will use it.
-			 */
-			data = kmalloc(sizeof(*data), GFP_ATOMIC);
-			if (data)
-				data->flags = CSD_FLAG_ALLOC;
-			else {
-				data = &per_cpu(csd_data, me);
-				while (data->flags & CSD_FLAG_LOCK)
-					cpu_relax();
-				data->flags = CSD_FLAG_LOCK;
-			}
+			csd_lock(data);
+
+			data->func = func;
+			data->info = info;
+			generic_exec_single(cpu, data, wait);
 		} else {
-			data = &d;
-			data->flags = CSD_FLAG_WAIT;
+			err = -ENXIO;	/* CPU not online */
 		}
-
-		data->func = func;
-		data->info = info;
-		generic_exec_single(cpu, data);
-	} else {
-		err = -ENXIO;	/* CPU not online */
 	}
 
 	put_cpu();
+
 	return err;
 }
 EXPORT_SYMBOL(smp_call_function_single);
@@ -283,23 +320,26 @@ EXPORT_SYMBOL(smp_call_function_single);
  * @cpu: The CPU to run on.
  * @data: Pre-allocated and setup data structure
  *
- * Like smp_call_function_single(), but allow caller to pass in a pre-allocated
- * data structure. Useful for embedding @data inside other structures, for
- * instance.
- *
+ * Like smp_call_function_single(), but allow caller to pass in a
+ * pre-allocated data structure. Useful for embedding @data inside
+ * other structures, for instance.
  */
-void __smp_call_function_single(int cpu, struct call_single_data *data)
+void __smp_call_function_single(int cpu, struct call_single_data *data,
+				int wait)
 {
+	csd_lock(data);
+
 	/* Can deadlock when called with interrupts disabled */
-	WARN_ON((data->flags & CSD_FLAG_WAIT) && irqs_disabled());
+	WARN_ON_ONCE(wait && irqs_disabled() && !oops_in_progress);
 
-	generic_exec_single(cpu, data);
+	generic_exec_single(cpu, data, wait);
 }
 
-/* FIXME: Shim for archs using old arch_send_call_function_ipi API. */
+/* Deprecated: shim for archs using old arch_send_call_function_ipi API. */
+
 #ifndef arch_send_call_function_ipi_mask
-#define arch_send_call_function_ipi_mask(maskp) \
-	arch_send_call_function_ipi(*(maskp))
+# define arch_send_call_function_ipi_mask(maskp) \
+	 arch_send_call_function_ipi(*(maskp))
 #endif
 
 /**
@@ -307,7 +347,8 @@ void __smp_call_function_single(int cpu, struct call_single_data *data)
  * @mask: The set of cpus to run on (only runs on online subset).
  * @func: The function to run. This must be fast and non-blocking.
  * @info: An arbitrary pointer to pass to the function.
- * @wait: If true, wait (atomically) until function has completed on other CPUs.
+ * @wait: If true, wait (atomically) until function has completed
+ *        on other CPUs.
  *
  * If @wait is true, then returns once @func has returned. Note that @wait
  * will be implicitly turned on in case of allocation failures, since
@@ -318,27 +359,27 @@ void __smp_call_function_single(int cpu, struct call_single_data *data)
  * must be disabled when calling this function.
  */
 void smp_call_function_many(const struct cpumask *mask,
-			    void (*func)(void *), void *info,
-			    bool wait)
+			    void (*func)(void *), void *info, bool wait)
 {
 	struct call_function_data *data;
 	unsigned long flags;
-	int cpu, next_cpu;
+	int cpu, next_cpu, this_cpu = smp_processor_id();
 
 	/* Can deadlock when called with interrupts disabled */
-	WARN_ON(irqs_disabled());
+	WARN_ON_ONCE(irqs_disabled() && !oops_in_progress);
 
-	/* So, what's a CPU they want?  Ignoring this one. */
+	/* So, what's a CPU they want? Ignoring this one. */
 	cpu = cpumask_first_and(mask, cpu_online_mask);
-	if (cpu == smp_processor_id())
+	if (cpu == this_cpu)
 		cpu = cpumask_next_and(cpu, mask, cpu_online_mask);
+
 	/* No online cpus?  We're done. */
 	if (cpu >= nr_cpu_ids)
 		return;
 
 	/* Do we have another CPU which isn't us? */
 	next_cpu = cpumask_next_and(cpu, mask, cpu_online_mask);
-	if (next_cpu == smp_processor_id())
+	if (next_cpu == this_cpu)
 		next_cpu = cpumask_next_and(next_cpu, mask, cpu_online_mask);
 
 	/* Fastpath: do that cpu by itself. */
@@ -347,43 +388,40 @@ void smp_call_function_many(const struct cpumask *mask,
 		return;
 	}
 
-	data = kmalloc(sizeof(*data) + cpumask_size(), GFP_ATOMIC);
-	if (unlikely(!data)) {
-		/* Slow path. */
-		for_each_online_cpu(cpu) {
-			if (cpu == smp_processor_id())
-				continue;
-			if (cpumask_test_cpu(cpu, mask))
-				smp_call_function_single(cpu, func, info, wait);
-		}
-		return;
-	}
+	data = &__get_cpu_var(cfd_data);
+	csd_lock(&data->csd);
 
-	spin_lock_init(&data->lock);
-	data->csd.flags = CSD_FLAG_ALLOC;
-	if (wait)
-		data->csd.flags |= CSD_FLAG_WAIT;
+	spin_lock_irqsave(&data->lock, flags);
 	data->csd.func = func;
 	data->csd.info = info;
-	cpumask_and(to_cpumask(data->cpumask_bits), mask, cpu_online_mask);
-	cpumask_clear_cpu(smp_processor_id(), to_cpumask(data->cpumask_bits));
-	data->refs = cpumask_weight(to_cpumask(data->cpumask_bits));
+	cpumask_and(data->cpumask, mask, cpu_online_mask);
+	cpumask_clear_cpu(this_cpu, data->cpumask);
+	data->refs = cpumask_weight(data->cpumask);
 
-	spin_lock_irqsave(&call_function_lock, flags);
-	list_add_tail_rcu(&data->csd.list, &call_function_queue);
-	spin_unlock_irqrestore(&call_function_lock, flags);
+	spin_lock(&call_function.lock);
+	/*
+	 * Place entry at the _HEAD_ of the list, so that any cpu still
+	 * observing the entry in generic_smp_call_function_interrupt()
+	 * will not miss any other list entries:
+	 */
+	list_add_rcu(&data->csd.list, &call_function.queue);
+	spin_unlock(&call_function.lock);
+
+	spin_unlock_irqrestore(&data->lock, flags);
 
 	/*
 	 * Make the list addition visible before sending the ipi.
+	 * (IPIs must obey or appear to obey normal Linux cache
+	 * coherency rules -- see comment in generic_exec_single).
 	 */
 	smp_mb();
 
 	/* Send a message to all CPUs in the map */
-	arch_send_call_function_ipi_mask(to_cpumask(data->cpumask_bits));
+	arch_send_call_function_ipi_mask(data->cpumask);
 
-	/* optionally wait for the CPUs to complete */
+	/* Optionally wait for the CPUs to complete */
 	if (wait)
-		csd_flag_wait(&data->csd);
+		csd_lock_wait(&data->csd);
 }
 EXPORT_SYMBOL(smp_call_function_many);
 
@@ -391,7 +429,8 @@ EXPORT_SYMBOL(smp_call_function_many);
  * smp_call_function(): Run a function on all other CPUs.
  * @func: The function to run. This must be fast and non-blocking.
  * @info: An arbitrary pointer to pass to the function.
- * @wait: If true, wait (atomically) until function has completed on other CPUs.
+ * @wait: If true, wait (atomically) until function has completed
+ *        on other CPUs.
  *
  * Returns 0.
  *
@@ -407,26 +446,27 @@ int smp_call_function(void (*func)(void *), void *info, int wait)
 	preempt_disable();
 	smp_call_function_many(cpu_online_mask, func, info, wait);
 	preempt_enable();
+
 	return 0;
 }
 EXPORT_SYMBOL(smp_call_function);
 
 void ipi_call_lock(void)
 {
-	spin_lock(&call_function_lock);
+	spin_lock(&call_function.lock);
 }
 
 void ipi_call_unlock(void)
 {
-	spin_unlock(&call_function_lock);
+	spin_unlock(&call_function.lock);
 }
 
 void ipi_call_lock_irq(void)
 {
-	spin_lock_irq(&call_function_lock);
+	spin_lock_irq(&call_function.lock);
 }
 
 void ipi_call_unlock_irq(void)
 {
-	spin_unlock_irq(&call_function_lock);
+	spin_unlock_irq(&call_function.lock);
 }
diff --git a/kernel/softirq.c b/kernel/softirq.c
index 65ff3e3961b..2fecefacdc5 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -65,7 +65,7 @@ char *softirq_to_name[NR_SOFTIRQS] = {
  * to the pending events, so lets the scheduler to balance
  * the softirq load for us.
  */
-static inline void wakeup_softirqd(void)
+void wakeup_softirqd(void)
 {
 	/* Interrupts are disabled: no need to stop preemption */
 	struct task_struct *tsk = __get_cpu_var(ksoftirqd);
@@ -518,7 +518,7 @@ static int __try_remote_softirq(struct call_single_data *cp, int cpu, int softir
 		cp->flags = 0;
 		cp->priv = softirq;
 
-		__smp_call_function_single(cpu, cp);
+		__smp_call_function_single(cpu, cp, 0);
 		return 0;
 	}
 	return 1;
diff --git a/kernel/spinlock.c b/kernel/spinlock.c
index 29ab20749dd..7932653c4eb 100644
--- a/kernel/spinlock.c
+++ b/kernel/spinlock.c
@@ -121,7 +121,8 @@ unsigned long __lockfunc _read_lock_irqsave(rwlock_t *lock)
 	local_irq_save(flags);
 	preempt_disable();
 	rwlock_acquire_read(&lock->dep_map, 0, 0, _RET_IP_);
-	LOCK_CONTENDED(lock, _raw_read_trylock, _raw_read_lock);
+	LOCK_CONTENDED_FLAGS(lock, _raw_read_trylock, _raw_read_lock,
+			     _raw_read_lock_flags, &flags);
 	return flags;
 }
 EXPORT_SYMBOL(_read_lock_irqsave);
@@ -151,7 +152,8 @@ unsigned long __lockfunc _write_lock_irqsave(rwlock_t *lock)
 	local_irq_save(flags);
 	preempt_disable();
 	rwlock_acquire(&lock->dep_map, 0, 0, _RET_IP_);
-	LOCK_CONTENDED(lock, _raw_write_trylock, _raw_write_lock);
+	LOCK_CONTENDED_FLAGS(lock, _raw_write_trylock, _raw_write_lock,
+			     _raw_write_lock_flags, &flags);
 	return flags;
 }
 EXPORT_SYMBOL(_write_lock_irqsave);
@@ -299,16 +301,8 @@ unsigned long __lockfunc _spin_lock_irqsave_nested(spinlock_t *lock, int subclas
 	local_irq_save(flags);
 	preempt_disable();
 	spin_acquire(&lock->dep_map, subclass, 0, _RET_IP_);
-	/*
-	 * On lockdep we dont want the hand-coded irq-enable of
-	 * _raw_spin_lock_flags() code, because lockdep assumes
-	 * that interrupts are not re-enabled during lock-acquire:
-	 */
-#ifdef CONFIG_LOCKDEP
-	LOCK_CONTENDED(lock, _raw_spin_trylock, _raw_spin_lock);
-#else
-	_raw_spin_lock_flags(lock, &flags);
-#endif
+	LOCK_CONTENDED_FLAGS(lock, _raw_spin_trylock, _raw_spin_lock,
+				_raw_spin_lock_flags, &flags);
 	return flags;
 }
 EXPORT_SYMBOL(_spin_lock_irqsave_nested);
diff --git a/kernel/stop_machine.c b/kernel/stop_machine.c
index 74541ca4953..912823e2a11 100644
--- a/kernel/stop_machine.c
+++ b/kernel/stop_machine.c
@@ -44,7 +44,7 @@ static DEFINE_MUTEX(setup_lock);
 static int refcount;
 static struct workqueue_struct *stop_machine_wq;
 static struct stop_machine_data active, idle;
-static const cpumask_t *active_cpus;
+static const struct cpumask *active_cpus;
 static void *stop_machine_work;
 
 static void set_state(enum stopmachine_state newstate)
diff --git a/kernel/sys.c b/kernel/sys.c
index 37f458e6882..51dbb55604e 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -34,6 +34,7 @@
 #include <linux/seccomp.h>
 #include <linux/cpu.h>
 #include <linux/ptrace.h>
+#include <linux/fs_struct.h>
 
 #include <linux/compat.h>
 #include <linux/syscalls.h>
@@ -1013,10 +1014,8 @@ SYSCALL_DEFINE2(setpgid, pid_t, pid, pid_t, pgid)
 	if (err)
 		goto out;
 
-	if (task_pgrp(p) != pgrp) {
+	if (task_pgrp(p) != pgrp)
 		change_pid(p, PIDTYPE_PGID, pgrp);
-		set_task_pgrp(p, pid_nr(pgrp));
-	}
 
 	err = 0;
 out:
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index c5ef44ff850..b125e338756 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -48,6 +48,7 @@
 #include <linux/acpi.h>
 #include <linux/reboot.h>
 #include <linux/ftrace.h>
+#include <linux/slow-work.h>
 
 #include <asm/uaccess.h>
 #include <asm/processor.h>
@@ -95,12 +96,9 @@ static int sixty = 60;
 static int neg_one = -1;
 #endif
 
-#if defined(CONFIG_MMU) && defined(CONFIG_FILE_LOCKING)
-static int two = 2;
-#endif
-
 static int zero;
-static int one = 1;
+static int __maybe_unused one = 1;
+static int __maybe_unused two = 2;
 static unsigned long one_ul = 1;
 static int one_hundred = 100;
 
@@ -900,6 +898,14 @@ static struct ctl_table kern_table[] = {
 		.proc_handler	= &scan_unevictable_handler,
 	},
 #endif
+#ifdef CONFIG_SLOW_WORK
+	{
+		.ctl_name	= CTL_UNNUMBERED,
+		.procname	= "slow-work",
+		.mode		= 0555,
+		.child		= slow_work_sysctls,
+	},
+#endif
 /*
  * NOTE: do not add new entries to this table unless you have read
  * Documentation/sysctl/ctl_unnumbered.txt
@@ -1010,7 +1016,7 @@ static struct ctl_table vm_table[] = {
 		.data		= &dirty_expire_interval,
 		.maxlen		= sizeof(dirty_expire_interval),
 		.mode		= 0644,
-		.proc_handler	= &proc_dointvec_userhz_jiffies,
+		.proc_handler	= &proc_dointvec,
 	},
 	{
 		.ctl_name	= VM_NR_PDFLUSH_THREADS,
@@ -1373,10 +1379,7 @@ static struct ctl_table fs_table[] = {
 		.data		= &lease_break_time,
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
-		.proc_handler	= &proc_dointvec_minmax,
-		.strategy	= &sysctl_intvec,
-		.extra1		= &zero,
-		.extra2		= &two,
+		.proc_handler	= &proc_dointvec,
 	},
 #endif
 #ifdef CONFIG_AIO
@@ -1417,7 +1420,10 @@ static struct ctl_table fs_table[] = {
 		.data		= &suid_dumpable,
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
-		.proc_handler	= &proc_dointvec,
+		.proc_handler	= &proc_dointvec_minmax,
+		.strategy	= &sysctl_intvec,
+		.extra1		= &zero,
+		.extra2		= &two,
 	},
 #if defined(CONFIG_BINFMT_MISC) || defined(CONFIG_BINFMT_MISC_MODULE)
 	{
diff --git a/kernel/sysctl_check.c b/kernel/sysctl_check.c
index fafeb48f27c..b38423ca711 100644
--- a/kernel/sysctl_check.c
+++ b/kernel/sysctl_check.c
@@ -219,6 +219,7 @@ static const struct trans_ctl_table trans_net_ipv4_conf_vars_table[] = {
 	{ NET_IPV4_CONF_ARP_IGNORE,		"arp_ignore" },
 	{ NET_IPV4_CONF_PROMOTE_SECONDARIES,	"promote_secondaries" },
 	{ NET_IPV4_CONF_ARP_ACCEPT,		"arp_accept" },
+	{ NET_IPV4_CONF_ARP_NOTIFY,		"arp_notify" },
 	{}
 };
 
diff --git a/kernel/time/Makefile b/kernel/time/Makefile
index 905b0b50792..0b0a6366c9d 100644
--- a/kernel/time/Makefile
+++ b/kernel/time/Makefile
@@ -1,4 +1,4 @@
-obj-y += timekeeping.o ntp.o clocksource.o jiffies.o timer_list.o
+obj-y += timekeeping.o ntp.o clocksource.o jiffies.o timer_list.o timecompare.o
 
 obj-$(CONFIG_GENERIC_CLOCKEVENTS_BUILD)		+= clockevents.o
 obj-$(CONFIG_GENERIC_CLOCKEVENTS)		+= tick-common.o
diff --git a/kernel/time/clockevents.c b/kernel/time/clockevents.c
index ea2f48af83c..d13be216a79 100644
--- a/kernel/time/clockevents.c
+++ b/kernel/time/clockevents.c
@@ -68,6 +68,17 @@ void clockevents_set_mode(struct clock_event_device *dev,
 	if (dev->mode != mode) {
 		dev->set_mode(mode, dev);
 		dev->mode = mode;
+
+		/*
+		 * A nsec2cyc multiplicator of 0 is invalid and we'd crash
+		 * on it, so fix it up and emit a warning:
+		 */
+		if (mode == CLOCK_EVT_MODE_ONESHOT) {
+			if (unlikely(!dev->mult)) {
+				dev->mult = 1;
+				WARN_ON(1);
+			}
+		}
 	}
 }
 
@@ -168,15 +179,6 @@ void clockevents_register_device(struct clock_event_device *dev)
 	BUG_ON(dev->mode != CLOCK_EVT_MODE_UNUSED);
 	BUG_ON(!dev->cpumask);
 
-	/*
-	 * A nsec2cyc multiplicator of 0 is invalid and we'd crash
-	 * on it, so fix it up and emit a warning:
-	 */
-	if (unlikely(!dev->mult)) {
-		dev->mult = 1;
-		WARN_ON(1);
-	}
-
 	spin_lock(&clockevents_lock);
 
 	list_add(&dev->list, &clockevent_devices);
diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c
index ca89e1593f0..c46c931a7fe 100644
--- a/kernel/time/clocksource.c
+++ b/kernel/time/clocksource.c
@@ -31,6 +31,82 @@
 #include <linux/sched.h> /* for spin_unlock_irq() using preempt_count() m68k */
 #include <linux/tick.h>
 
+void timecounter_init(struct timecounter *tc,
+		      const struct cyclecounter *cc,
+		      u64 start_tstamp)
+{
+	tc->cc = cc;
+	tc->cycle_last = cc->read(cc);
+	tc->nsec = start_tstamp;
+}
+EXPORT_SYMBOL(timecounter_init);
+
+/**
+ * timecounter_read_delta - get nanoseconds since last call of this function
+ * @tc:         Pointer to time counter
+ *
+ * When the underlying cycle counter runs over, this will be handled
+ * correctly as long as it does not run over more than once between
+ * calls.
+ *
+ * The first call to this function for a new time counter initializes
+ * the time tracking and returns an undefined result.
+ */
+static u64 timecounter_read_delta(struct timecounter *tc)
+{
+	cycle_t cycle_now, cycle_delta;
+	u64 ns_offset;
+
+	/* read cycle counter: */
+	cycle_now = tc->cc->read(tc->cc);
+
+	/* calculate the delta since the last timecounter_read_delta(): */
+	cycle_delta = (cycle_now - tc->cycle_last) & tc->cc->mask;
+
+	/* convert to nanoseconds: */
+	ns_offset = cyclecounter_cyc2ns(tc->cc, cycle_delta);
+
+	/* update time stamp of timecounter_read_delta() call: */
+	tc->cycle_last = cycle_now;
+
+	return ns_offset;
+}
+
+u64 timecounter_read(struct timecounter *tc)
+{
+	u64 nsec;
+
+	/* increment time by nanoseconds since last call */
+	nsec = timecounter_read_delta(tc);
+	nsec += tc->nsec;
+	tc->nsec = nsec;
+
+	return nsec;
+}
+EXPORT_SYMBOL(timecounter_read);
+
+u64 timecounter_cyc2time(struct timecounter *tc,
+			 cycle_t cycle_tstamp)
+{
+	u64 cycle_delta = (cycle_tstamp - tc->cycle_last) & tc->cc->mask;
+	u64 nsec;
+
+	/*
+	 * Instead of always treating cycle_tstamp as more recent
+	 * than tc->cycle_last, detect when it is too far in the
+	 * future and treat it as old time stamp instead.
+	 */
+	if (cycle_delta > tc->cc->mask / 2) {
+		cycle_delta = (tc->cycle_last - cycle_tstamp) & tc->cc->mask;
+		nsec = tc->nsec - cyclecounter_cyc2ns(tc->cc, cycle_delta);
+	} else {
+		nsec = cyclecounter_cyc2ns(tc->cc, cycle_delta) + tc->nsec;
+	}
+
+	return nsec;
+}
+EXPORT_SYMBOL(timecounter_cyc2time);
+
 /* XXX - Would like a better way for initializing curr_clocksource */
 extern struct clocksource clocksource_jiffies;
 
diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c
index f5f793d9241..7fc64375ff4 100644
--- a/kernel/time/ntp.c
+++ b/kernel/time/ntp.c
@@ -1,71 +1,129 @@
 /*
- * linux/kernel/time/ntp.c
- *
  * NTP state machine interfaces and logic.
  *
  * This code was mainly moved from kernel/timer.c and kernel/time.c
  * Please see those files for relevant copyright info and historical
  * changelogs.
  */
-
-#include <linux/mm.h>
-#include <linux/time.h>
-#include <linux/timex.h>
-#include <linux/jiffies.h>
-#include <linux/hrtimer.h>
 #include <linux/capability.h>
-#include <linux/math64.h>
 #include <linux/clocksource.h>
 #include <linux/workqueue.h>
-#include <asm/timex.h>
+#include <linux/hrtimer.h>
+#include <linux/jiffies.h>
+#include <linux/math64.h>
+#include <linux/timex.h>
+#include <linux/time.h>
+#include <linux/mm.h>
 
 /*
- * Timekeeping variables
+ * NTP timekeeping variables:
  */
-unsigned long tick_usec = TICK_USEC; 		/* USER_HZ period (usec) */
-unsigned long tick_nsec;			/* ACTHZ period (nsec) */
-u64 tick_length;
-static u64 tick_length_base;
 
-static struct hrtimer leap_timer;
+/* USER_HZ period (usecs): */
+unsigned long			tick_usec = TICK_USEC;
 
-#define MAX_TICKADJ		500		/* microsecs */
-#define MAX_TICKADJ_SCALED	(((u64)(MAX_TICKADJ * NSEC_PER_USEC) << \
-				  NTP_SCALE_SHIFT) / NTP_INTERVAL_FREQ)
+/* ACTHZ period (nsecs): */
+unsigned long			tick_nsec;
+
+u64				tick_length;
+static u64			tick_length_base;
+
+static struct hrtimer		leap_timer;
+
+#define MAX_TICKADJ		500LL		/* usecs */
+#define MAX_TICKADJ_SCALED \
+	(((MAX_TICKADJ * NSEC_PER_USEC) << NTP_SCALE_SHIFT) / NTP_INTERVAL_FREQ)
 
 /*
  * phase-lock loop variables
  */
-/* TIME_ERROR prevents overwriting the CMOS clock */
-static int time_state = TIME_OK;	/* clock synchronization status	*/
-int time_status = STA_UNSYNC;		/* clock status bits		*/
-static long time_tai;			/* TAI offset (s)		*/
-static s64 time_offset;			/* time adjustment (ns)		*/
-static long time_constant = 2;		/* pll time constant		*/
-long time_maxerror = NTP_PHASE_LIMIT;	/* maximum error (us)		*/
-long time_esterror = NTP_PHASE_LIMIT;	/* estimated error (us)		*/
-static s64 time_freq;			/* frequency offset (scaled ns/s)*/
-static long time_reftime;		/* time at last adjustment (s)	*/
-long time_adjust;
-static long ntp_tick_adj;
 
+/*
+ * clock synchronization status
+ *
+ * (TIME_ERROR prevents overwriting the CMOS clock)
+ */
+static int			time_state = TIME_OK;
+
+/* clock status bits:							*/
+int				time_status = STA_UNSYNC;
+
+/* TAI offset (secs):							*/
+static long			time_tai;
+
+/* time adjustment (nsecs):						*/
+static s64			time_offset;
+
+/* pll time constant:							*/
+static long			time_constant = 2;
+
+/* maximum error (usecs):						*/
+long				time_maxerror = NTP_PHASE_LIMIT;
+
+/* estimated error (usecs):						*/
+long				time_esterror = NTP_PHASE_LIMIT;
+
+/* frequency offset (scaled nsecs/secs):				*/
+static s64			time_freq;
+
+/* time at last adjustment (secs):					*/
+static long			time_reftime;
+
+long				time_adjust;
+
+/* constant (boot-param configurable) NTP tick adjustment (upscaled)	*/
+static s64			ntp_tick_adj;
+
+/*
+ * NTP methods:
+ */
+
+/*
+ * Update (tick_length, tick_length_base, tick_nsec), based
+ * on (tick_usec, ntp_tick_adj, time_freq):
+ */
 static void ntp_update_frequency(void)
 {
-	u64 second_length = (u64)(tick_usec * NSEC_PER_USEC * USER_HZ)
-				<< NTP_SCALE_SHIFT;
-	second_length += (s64)ntp_tick_adj << NTP_SCALE_SHIFT;
-	second_length += time_freq;
+	u64 second_length;
+	u64 new_base;
+
+	second_length		 = (u64)(tick_usec * NSEC_PER_USEC * USER_HZ)
+						<< NTP_SCALE_SHIFT;
+
+	second_length		+= ntp_tick_adj;
+	second_length		+= time_freq;
 
-	tick_length_base = second_length;
+	tick_nsec		 = div_u64(second_length, HZ) >> NTP_SCALE_SHIFT;
+	new_base		 = div_u64(second_length, NTP_INTERVAL_FREQ);
 
-	tick_nsec = div_u64(second_length, HZ) >> NTP_SCALE_SHIFT;
-	tick_length_base = div_u64(tick_length_base, NTP_INTERVAL_FREQ);
+	/*
+	 * Don't wait for the next second_overflow, apply
+	 * the change to the tick length immediately:
+	 */
+	tick_length		+= new_base - tick_length_base;
+	tick_length_base	 = new_base;
+}
+
+static inline s64 ntp_update_offset_fll(s64 offset64, long secs)
+{
+	time_status &= ~STA_MODE;
+
+	if (secs < MINSEC)
+		return 0;
+
+	if (!(time_status & STA_FLL) && (secs <= MAXSEC))
+		return 0;
+
+	time_status |= STA_MODE;
+
+	return div_s64(offset64 << (NTP_SCALE_SHIFT - SHIFT_FLL), secs);
 }
 
 static void ntp_update_offset(long offset)
 {
-	long mtemp;
 	s64 freq_adj;
+	s64 offset64;
+	long secs;
 
 	if (!(time_status & STA_PLL))
 		return;
@@ -84,24 +142,23 @@ static void ntp_update_offset(long offset)
 	 * Select how the frequency is to be controlled
 	 * and in which mode (PLL or FLL).
 	 */
-	if (time_status & STA_FREQHOLD || time_reftime == 0)
-		time_reftime = xtime.tv_sec;
-	mtemp = xtime.tv_sec - time_reftime;
+	secs = xtime.tv_sec - time_reftime;
+	if (unlikely(time_status & STA_FREQHOLD))
+		secs = 0;
+
 	time_reftime = xtime.tv_sec;
 
-	freq_adj = (s64)offset * mtemp;
-	freq_adj <<= NTP_SCALE_SHIFT - 2 * (SHIFT_PLL + 2 + time_constant);
-	time_status &= ~STA_MODE;
-	if (mtemp >= MINSEC && (time_status & STA_FLL || mtemp > MAXSEC)) {
-		freq_adj += div_s64((s64)offset << (NTP_SCALE_SHIFT - SHIFT_FLL),
-				    mtemp);
-		time_status |= STA_MODE;
-	}
-	freq_adj += time_freq;
-	freq_adj = min(freq_adj, MAXFREQ_SCALED);
-	time_freq = max(freq_adj, -MAXFREQ_SCALED);
+	offset64    = offset;
+	freq_adj    = (offset64 * secs) <<
+			(NTP_SCALE_SHIFT - 2 * (SHIFT_PLL + 2 + time_constant));
 
-	time_offset = div_s64((s64)offset << NTP_SCALE_SHIFT, NTP_INTERVAL_FREQ);
+	freq_adj    += ntp_update_offset_fll(offset64, secs);
+
+	freq_adj    = min(freq_adj + time_freq, MAXFREQ_SCALED);
+
+	time_freq   = max(freq_adj, -MAXFREQ_SCALED);
+
+	time_offset = div_s64(offset64 << NTP_SCALE_SHIFT, NTP_INTERVAL_FREQ);
 }
 
 /**
@@ -111,15 +168,15 @@ static void ntp_update_offset(long offset)
  */
 void ntp_clear(void)
 {
-	time_adjust = 0;		/* stop active adjtime() */
-	time_status |= STA_UNSYNC;
-	time_maxerror = NTP_PHASE_LIMIT;
-	time_esterror = NTP_PHASE_LIMIT;
+	time_adjust	= 0;		/* stop active adjtime() */
+	time_status	|= STA_UNSYNC;
+	time_maxerror	= NTP_PHASE_LIMIT;
+	time_esterror	= NTP_PHASE_LIMIT;
 
 	ntp_update_frequency();
 
-	tick_length = tick_length_base;
-	time_offset = 0;
+	tick_length	= tick_length_base;
+	time_offset	= 0;
 }
 
 /*
@@ -140,8 +197,8 @@ static enum hrtimer_restart ntp_leap_second(struct hrtimer *timer)
 		xtime.tv_sec--;
 		wall_to_monotonic.tv_sec++;
 		time_state = TIME_OOP;
-		printk(KERN_NOTICE "Clock: "
-		       "inserting leap second 23:59:60 UTC\n");
+		printk(KERN_NOTICE
+			"Clock: inserting leap second 23:59:60 UTC\n");
 		hrtimer_add_expires_ns(&leap_timer, NSEC_PER_SEC);
 		res = HRTIMER_RESTART;
 		break;
@@ -150,8 +207,8 @@ static enum hrtimer_restart ntp_leap_second(struct hrtimer *timer)
 		time_tai--;
 		wall_to_monotonic.tv_sec--;
 		time_state = TIME_WAIT;
-		printk(KERN_NOTICE "Clock: "
-		       "deleting leap second 23:59:59 UTC\n");
+		printk(KERN_NOTICE
+			"Clock: deleting leap second 23:59:59 UTC\n");
 		break;
 	case TIME_OOP:
 		time_tai++;
@@ -179,7 +236,7 @@ static enum hrtimer_restart ntp_leap_second(struct hrtimer *timer)
  */
 void second_overflow(void)
 {
-	s64 time_adj;
+	s64 delta;
 
 	/* Bump the maxerror field */
 	time_maxerror += MAXFREQ / NSEC_PER_USEC;
@@ -192,24 +249,30 @@ void second_overflow(void)
 	 * Compute the phase adjustment for the next second. The offset is
 	 * reduced by a fixed factor times the time constant.
 	 */
-	tick_length = tick_length_base;
-	time_adj = shift_right(time_offset, SHIFT_PLL + time_constant);
-	time_offset -= time_adj;
-	tick_length += time_adj;
-
-	if (unlikely(time_adjust)) {
-		if (time_adjust > MAX_TICKADJ) {
-			time_adjust -= MAX_TICKADJ;
-			tick_length += MAX_TICKADJ_SCALED;
-		} else if (time_adjust < -MAX_TICKADJ) {
-			time_adjust += MAX_TICKADJ;
-			tick_length -= MAX_TICKADJ_SCALED;
-		} else {
-			tick_length += (s64)(time_adjust * NSEC_PER_USEC /
-					NTP_INTERVAL_FREQ) << NTP_SCALE_SHIFT;
-			time_adjust = 0;
-		}
+	tick_length	 = tick_length_base;
+
+	delta		 = shift_right(time_offset, SHIFT_PLL + time_constant);
+	time_offset	-= delta;
+	tick_length	+= delta;
+
+	if (!time_adjust)
+		return;
+
+	if (time_adjust > MAX_TICKADJ) {
+		time_adjust -= MAX_TICKADJ;
+		tick_length += MAX_TICKADJ_SCALED;
+		return;
 	}
+
+	if (time_adjust < -MAX_TICKADJ) {
+		time_adjust += MAX_TICKADJ;
+		tick_length -= MAX_TICKADJ_SCALED;
+		return;
+	}
+
+	tick_length += (s64)(time_adjust * NSEC_PER_USEC / NTP_INTERVAL_FREQ)
+							 << NTP_SCALE_SHIFT;
+	time_adjust = 0;
 }
 
 #ifdef CONFIG_GENERIC_CMOS_UPDATE
@@ -233,12 +296,13 @@ static void sync_cmos_clock(struct work_struct *work)
 	 * This code is run on a timer.  If the clock is set, that timer
 	 * may not expire at the correct time.  Thus, we adjust...
 	 */
-	if (!ntp_synced())
+	if (!ntp_synced()) {
 		/*
 		 * Not synced, exit, do not restart a timer (if one is
 		 * running, let it run out).
 		 */
 		return;
+	}
 
 	getnstimeofday(&now);
 	if (abs(now.tv_nsec - (NSEC_PER_SEC / 2)) <= tick_nsec / 2)
@@ -270,7 +334,116 @@ static void notify_cmos_timer(void)
 static inline void notify_cmos_timer(void) { }
 #endif
 
-/* adjtimex mainly allows reading (and writing, if superuser) of
+/*
+ * Start the leap seconds timer:
+ */
+static inline void ntp_start_leap_timer(struct timespec *ts)
+{
+	long now = ts->tv_sec;
+
+	if (time_status & STA_INS) {
+		time_state = TIME_INS;
+		now += 86400 - now % 86400;
+		hrtimer_start(&leap_timer, ktime_set(now, 0), HRTIMER_MODE_ABS);
+
+		return;
+	}
+
+	if (time_status & STA_DEL) {
+		time_state = TIME_DEL;
+		now += 86400 - (now + 1) % 86400;
+		hrtimer_start(&leap_timer, ktime_set(now, 0), HRTIMER_MODE_ABS);
+	}
+}
+
+/*
+ * Propagate a new txc->status value into the NTP state:
+ */
+static inline void process_adj_status(struct timex *txc, struct timespec *ts)
+{
+	if ((time_status & STA_PLL) && !(txc->status & STA_PLL)) {
+		time_state = TIME_OK;
+		time_status = STA_UNSYNC;
+	}
+
+	/*
+	 * If we turn on PLL adjustments then reset the
+	 * reference time to current time.
+	 */
+	if (!(time_status & STA_PLL) && (txc->status & STA_PLL))
+		time_reftime = xtime.tv_sec;
+
+	/* only set allowed bits */
+	time_status &= STA_RONLY;
+	time_status |= txc->status & ~STA_RONLY;
+
+	switch (time_state) {
+	case TIME_OK:
+		ntp_start_leap_timer(ts);
+		break;
+	case TIME_INS:
+	case TIME_DEL:
+		time_state = TIME_OK;
+		ntp_start_leap_timer(ts);
+	case TIME_WAIT:
+		if (!(time_status & (STA_INS | STA_DEL)))
+			time_state = TIME_OK;
+		break;
+	case TIME_OOP:
+		hrtimer_restart(&leap_timer);
+		break;
+	}
+}
+/*
+ * Called with the xtime lock held, so we can access and modify
+ * all the global NTP state:
+ */
+static inline void process_adjtimex_modes(struct timex *txc, struct timespec *ts)
+{
+	if (txc->modes & ADJ_STATUS)
+		process_adj_status(txc, ts);
+
+	if (txc->modes & ADJ_NANO)
+		time_status |= STA_NANO;
+
+	if (txc->modes & ADJ_MICRO)
+		time_status &= ~STA_NANO;
+
+	if (txc->modes & ADJ_FREQUENCY) {
+		time_freq = txc->freq * PPM_SCALE;
+		time_freq = min(time_freq, MAXFREQ_SCALED);
+		time_freq = max(time_freq, -MAXFREQ_SCALED);
+	}
+
+	if (txc->modes & ADJ_MAXERROR)
+		time_maxerror = txc->maxerror;
+
+	if (txc->modes & ADJ_ESTERROR)
+		time_esterror = txc->esterror;
+
+	if (txc->modes & ADJ_TIMECONST) {
+		time_constant = txc->constant;
+		if (!(time_status & STA_NANO))
+			time_constant += 4;
+		time_constant = min(time_constant, (long)MAXTC);
+		time_constant = max(time_constant, 0l);
+	}
+
+	if (txc->modes & ADJ_TAI && txc->constant > 0)
+		time_tai = txc->constant;
+
+	if (txc->modes & ADJ_OFFSET)
+		ntp_update_offset(txc->offset);
+
+	if (txc->modes & ADJ_TICK)
+		tick_usec = txc->tick;
+
+	if (txc->modes & (ADJ_TICK|ADJ_FREQUENCY|ADJ_OFFSET))
+		ntp_update_frequency();
+}
+
+/*
+ * adjtimex mainly allows reading (and writing, if superuser) of
  * kernel time-keeping variables. used by xntpd.
  */
 int do_adjtimex(struct timex *txc)
@@ -291,11 +464,14 @@ int do_adjtimex(struct timex *txc)
 		 if (txc->modes && !capable(CAP_SYS_TIME))
 			return -EPERM;
 
-		/* if the quartz is off by more than 10% something is VERY wrong! */
+		/*
+		 * if the quartz is off by more than 10% then
+		 * something is VERY wrong!
+		 */
 		if (txc->modes & ADJ_TICK &&
 		    (txc->tick <  900000/USER_HZ ||
 		     txc->tick > 1100000/USER_HZ))
-				return -EINVAL;
+			return -EINVAL;
 
 		if (txc->modes & ADJ_STATUS && time_state != TIME_OK)
 			hrtimer_cancel(&leap_timer);
@@ -305,7 +481,6 @@ int do_adjtimex(struct timex *txc)
 
 	write_seqlock_irq(&xtime_lock);
 
-	/* If there are input parameters, then process them */
 	if (txc->modes & ADJ_ADJTIME) {
 		long save_adjust = time_adjust;
 
@@ -315,98 +490,24 @@ int do_adjtimex(struct timex *txc)
 			ntp_update_frequency();
 		}
 		txc->offset = save_adjust;
-		goto adj_done;
-	}
-	if (txc->modes) {
-		long sec;
-
-		if (txc->modes & ADJ_STATUS) {
-			if ((time_status & STA_PLL) &&
-			    !(txc->status & STA_PLL)) {
-				time_state = TIME_OK;
-				time_status = STA_UNSYNC;
-			}
-			/* only set allowed bits */
-			time_status &= STA_RONLY;
-			time_status |= txc->status & ~STA_RONLY;
-
-			switch (time_state) {
-			case TIME_OK:
-			start_timer:
-				sec = ts.tv_sec;
-				if (time_status & STA_INS) {
-					time_state = TIME_INS;
-					sec += 86400 - sec % 86400;
-					hrtimer_start(&leap_timer, ktime_set(sec, 0), HRTIMER_MODE_ABS);
-				} else if (time_status & STA_DEL) {
-					time_state = TIME_DEL;
-					sec += 86400 - (sec + 1) % 86400;
-					hrtimer_start(&leap_timer, ktime_set(sec, 0), HRTIMER_MODE_ABS);
-				}
-				break;
-			case TIME_INS:
-			case TIME_DEL:
-				time_state = TIME_OK;
-				goto start_timer;
-				break;
-			case TIME_WAIT:
-				if (!(time_status & (STA_INS | STA_DEL)))
-					time_state = TIME_OK;
-				break;
-			case TIME_OOP:
-				hrtimer_restart(&leap_timer);
-				break;
-			}
-		}
-
-		if (txc->modes & ADJ_NANO)
-			time_status |= STA_NANO;
-		if (txc->modes & ADJ_MICRO)
-			time_status &= ~STA_NANO;
-
-		if (txc->modes & ADJ_FREQUENCY) {
-			time_freq = (s64)txc->freq * PPM_SCALE;
-			time_freq = min(time_freq, MAXFREQ_SCALED);
-			time_freq = max(time_freq, -MAXFREQ_SCALED);
-		}
-
-		if (txc->modes & ADJ_MAXERROR)
-			time_maxerror = txc->maxerror;
-		if (txc->modes & ADJ_ESTERROR)
-			time_esterror = txc->esterror;
-
-		if (txc->modes & ADJ_TIMECONST) {
-			time_constant = txc->constant;
-			if (!(time_status & STA_NANO))
-				time_constant += 4;
-			time_constant = min(time_constant, (long)MAXTC);
-			time_constant = max(time_constant, 0l);
-		}
-
-		if (txc->modes & ADJ_TAI && txc->constant > 0)
-			time_tai = txc->constant;
-
-		if (txc->modes & ADJ_OFFSET)
-			ntp_update_offset(txc->offset);
-		if (txc->modes & ADJ_TICK)
-			tick_usec = txc->tick;
+	} else {
 
-		if (txc->modes & (ADJ_TICK|ADJ_FREQUENCY|ADJ_OFFSET))
-			ntp_update_frequency();
-	}
+		/* If there are input parameters, then process them: */
+		if (txc->modes)
+			process_adjtimex_modes(txc, &ts);
 
-	txc->offset = shift_right(time_offset * NTP_INTERVAL_FREQ,
+		txc->offset = shift_right(time_offset * NTP_INTERVAL_FREQ,
 				  NTP_SCALE_SHIFT);
-	if (!(time_status & STA_NANO))
-		txc->offset /= NSEC_PER_USEC;
+		if (!(time_status & STA_NANO))
+			txc->offset /= NSEC_PER_USEC;
+	}
 
-adj_done:
 	result = time_state;	/* mostly `TIME_OK' */
 	if (time_status & (STA_UNSYNC|STA_CLOCKERR))
 		result = TIME_ERROR;
 
 	txc->freq	   = shift_right((time_freq >> PPM_SCALE_INV_SHIFT) *
-					 (s64)PPM_SCALE_INV, NTP_SCALE_SHIFT);
+					 PPM_SCALE_INV, NTP_SCALE_SHIFT);
 	txc->maxerror	   = time_maxerror;
 	txc->esterror	   = time_esterror;
 	txc->status	   = time_status;
@@ -425,6 +526,7 @@ adj_done:
 	txc->calcnt	   = 0;
 	txc->errcnt	   = 0;
 	txc->stbcnt	   = 0;
+
 	write_sequnlock_irq(&xtime_lock);
 
 	txc->time.tv_sec = ts.tv_sec;
@@ -440,6 +542,8 @@ adj_done:
 static int __init ntp_tick_adj_setup(char *str)
 {
 	ntp_tick_adj = simple_strtol(str, NULL, 0);
+	ntp_tick_adj <<= NTP_SCALE_SHIFT;
+
 	return 1;
 }
 
diff --git a/kernel/time/timecompare.c b/kernel/time/timecompare.c
new file mode 100644
index 00000000000..71e7f1a1915
--- /dev/null
+++ b/kernel/time/timecompare.c
@@ -0,0 +1,191 @@
+/*
+ * Copyright (C) 2009 Intel Corporation.
+ * Author: Patrick Ohly <patrick.ohly@intel.com>
+ *
+ * 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.
+ *
+ * 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., 675 Mass Ave, Cambridge, MA 02139, USA.
+ */
+
+#include <linux/timecompare.h>
+#include <linux/module.h>
+#include <linux/math64.h>
+
+/*
+ * fixed point arithmetic scale factor for skew
+ *
+ * Usually one would measure skew in ppb (parts per billion, 1e9), but
+ * using a factor of 2 simplifies the math.
+ */
+#define TIMECOMPARE_SKEW_RESOLUTION (((s64)1)<<30)
+
+ktime_t timecompare_transform(struct timecompare *sync,
+			      u64 source_tstamp)
+{
+	u64 nsec;
+
+	nsec = source_tstamp + sync->offset;
+	nsec += (s64)(source_tstamp - sync->last_update) * sync->skew /
+		TIMECOMPARE_SKEW_RESOLUTION;
+
+	return ns_to_ktime(nsec);
+}
+EXPORT_SYMBOL(timecompare_transform);
+
+int timecompare_offset(struct timecompare *sync,
+		       s64 *offset,
+		       u64 *source_tstamp)
+{
+	u64 start_source = 0, end_source = 0;
+	struct {
+		s64 offset;
+		s64 duration_target;
+	} buffer[10], sample, *samples;
+	int counter = 0, i;
+	int used;
+	int index;
+	int num_samples = sync->num_samples;
+
+	if (num_samples > sizeof(buffer)/sizeof(buffer[0])) {
+		samples = kmalloc(sizeof(*samples) * num_samples, GFP_ATOMIC);
+		if (!samples) {
+			samples = buffer;
+			num_samples = sizeof(buffer)/sizeof(buffer[0]);
+		}
+	} else {
+		samples = buffer;
+	}
+
+	/* run until we have enough valid samples, but do not try forever */
+	i = 0;
+	counter = 0;
+	while (1) {
+		u64 ts;
+		ktime_t start, end;
+
+		start = sync->target();
+		ts = timecounter_read(sync->source);
+		end = sync->target();
+
+		if (!i)
+			start_source = ts;
+
+		/* ignore negative durations */
+		sample.duration_target = ktime_to_ns(ktime_sub(end, start));
+		if (sample.duration_target >= 0) {
+			/*
+			 * assume symetric delay to and from source:
+			 * average target time corresponds to measured
+			 * source time
+			 */
+			sample.offset =
+				ktime_to_ns(ktime_add(end, start)) / 2 -
+				ts;
+
+			/* simple insertion sort based on duration */
+			index = counter - 1;
+			while (index >= 0) {
+				if (samples[index].duration_target <
+				    sample.duration_target)
+					break;
+				samples[index + 1] = samples[index];
+				index--;
+			}
+			samples[index + 1] = sample;
+			counter++;
+		}
+
+		i++;
+		if (counter >= num_samples || i >= 100000) {
+			end_source = ts;
+			break;
+		}
+	}
+
+	*source_tstamp = (end_source + start_source) / 2;
+
+	/* remove outliers by only using 75% of the samples */
+	used = counter * 3 / 4;
+	if (!used)
+		used = counter;
+	if (used) {
+		/* calculate average */
+		s64 off = 0;
+		for (index = 0; index < used; index++)
+			off += samples[index].offset;
+		*offset = div_s64(off, used);
+	}
+
+	if (samples && samples != buffer)
+		kfree(samples);
+
+	return used;
+}
+EXPORT_SYMBOL(timecompare_offset);
+
+void __timecompare_update(struct timecompare *sync,
+			  u64 source_tstamp)
+{
+	s64 offset;
+	u64 average_time;
+
+	if (!timecompare_offset(sync, &offset, &average_time))
+		return;
+
+	if (!sync->last_update) {
+		sync->last_update = average_time;
+		sync->offset = offset;
+		sync->skew = 0;
+	} else {
+		s64 delta_nsec = average_time - sync->last_update;
+
+		/* avoid division by negative or small deltas */
+		if (delta_nsec >= 10000) {
+			s64 delta_offset_nsec = offset - sync->offset;
+			s64 skew; /* delta_offset_nsec *
+				     TIMECOMPARE_SKEW_RESOLUTION /
+				     delta_nsec */
+			u64 divisor;
+
+			/* div_s64() is limited to 32 bit divisor */
+			skew = delta_offset_nsec * TIMECOMPARE_SKEW_RESOLUTION;
+			divisor = delta_nsec;
+			while (unlikely(divisor >= ((s64)1) << 32)) {
+				/* divide both by 2; beware, right shift
+				   of negative value has undefined
+				   behavior and can only be used for
+				   the positive divisor */
+				skew = div_s64(skew, 2);
+				divisor >>= 1;
+			}
+			skew = div_s64(skew, divisor);
+
+			/*
+			 * Calculate new overall skew as 4/16 the
+			 * old value and 12/16 the new one. This is
+			 * a rather arbitrary tradeoff between
+			 * only using the latest measurement (0/16 and
+			 * 16/16) and even more weight on past measurements.
+			 */
+#define TIMECOMPARE_NEW_SKEW_PER_16 12
+			sync->skew =
+				div_s64((16 - TIMECOMPARE_NEW_SKEW_PER_16) *
+					sync->skew +
+					TIMECOMPARE_NEW_SKEW_PER_16 * skew,
+					16);
+			sync->last_update = average_time;
+			sync->offset = offset;
+		}
+	}
+}
+EXPORT_SYMBOL(__timecompare_update);
diff --git a/kernel/timer.c b/kernel/timer.c
index ef1c385bc57..b4555568b4e 100644
--- a/kernel/timer.c
+++ b/kernel/timer.c
@@ -600,11 +600,14 @@ static struct tvec_base *lock_timer_base(struct timer_list *timer,
 	}
 }
 
-int __mod_timer(struct timer_list *timer, unsigned long expires)
+static inline int
+__mod_timer(struct timer_list *timer, unsigned long expires, bool pending_only)
 {
 	struct tvec_base *base, *new_base;
 	unsigned long flags;
-	int ret = 0;
+	int ret;
+
+	ret = 0;
 
 	timer_stats_timer_set_start_info(timer);
 	BUG_ON(!timer->function);
@@ -614,6 +617,9 @@ int __mod_timer(struct timer_list *timer, unsigned long expires)
 	if (timer_pending(timer)) {
 		detach_timer(timer, 0);
 		ret = 1;
+	} else {
+		if (pending_only)
+			goto out_unlock;
 	}
 
 	debug_timer_activate(timer);
@@ -640,42 +646,28 @@ int __mod_timer(struct timer_list *timer, unsigned long expires)
 
 	timer->expires = expires;
 	internal_add_timer(base, timer);
+
+out_unlock:
 	spin_unlock_irqrestore(&base->lock, flags);
 
 	return ret;
 }
 
-EXPORT_SYMBOL(__mod_timer);
-
 /**
- * add_timer_on - start a timer on a particular CPU
- * @timer: the timer to be added
- * @cpu: the CPU to start it on
+ * mod_timer_pending - modify a pending timer's timeout
+ * @timer: the pending timer to be modified
+ * @expires: new timeout in jiffies
  *
- * This is not very scalable on SMP. Double adds are not possible.
+ * mod_timer_pending() is the same for pending timers as mod_timer(),
+ * but will not re-activate and modify already deleted timers.
+ *
+ * It is useful for unserialized use of timers.
  */
-void add_timer_on(struct timer_list *timer, int cpu)
+int mod_timer_pending(struct timer_list *timer, unsigned long expires)
 {
-	struct tvec_base *base = per_cpu(tvec_bases, cpu);
-	unsigned long flags;
-
-	timer_stats_timer_set_start_info(timer);
-	BUG_ON(timer_pending(timer) || !timer->function);
-	spin_lock_irqsave(&base->lock, flags);
-	timer_set_base(timer, base);
-	debug_timer_activate(timer);
-	internal_add_timer(base, timer);
-	/*
-	 * Check whether the other CPU is idle and needs to be
-	 * triggered to reevaluate the timer wheel when nohz is
-	 * active. We are protected against the other CPU fiddling
-	 * with the timer by holding the timer base lock. This also
-	 * makes sure that a CPU on the way to idle can not evaluate
-	 * the timer wheel.
-	 */
-	wake_up_idle_cpu(cpu);
-	spin_unlock_irqrestore(&base->lock, flags);
+	return __mod_timer(timer, expires, true);
 }
+EXPORT_SYMBOL(mod_timer_pending);
 
 /**
  * mod_timer - modify a timer's timeout
@@ -699,9 +691,6 @@ void add_timer_on(struct timer_list *timer, int cpu)
  */
 int mod_timer(struct timer_list *timer, unsigned long expires)
 {
-	BUG_ON(!timer->function);
-
-	timer_stats_timer_set_start_info(timer);
 	/*
 	 * This is a common optimization triggered by the
 	 * networking code - if the timer is re-modified
@@ -710,12 +699,62 @@ int mod_timer(struct timer_list *timer, unsigned long expires)
 	if (timer->expires == expires && timer_pending(timer))
 		return 1;
 
-	return __mod_timer(timer, expires);
+	return __mod_timer(timer, expires, false);
 }
-
 EXPORT_SYMBOL(mod_timer);
 
 /**
+ * add_timer - start a timer
+ * @timer: the timer to be added
+ *
+ * The kernel will do a ->function(->data) callback from the
+ * timer interrupt at the ->expires point in the future. The
+ * current time is 'jiffies'.
+ *
+ * The timer's ->expires, ->function (and if the handler uses it, ->data)
+ * fields must be set prior calling this function.
+ *
+ * Timers with an ->expires field in the past will be executed in the next
+ * timer tick.
+ */
+void add_timer(struct timer_list *timer)
+{
+	BUG_ON(timer_pending(timer));
+	mod_timer(timer, timer->expires);
+}
+EXPORT_SYMBOL(add_timer);
+
+/**
+ * add_timer_on - start a timer on a particular CPU
+ * @timer: the timer to be added
+ * @cpu: the CPU to start it on
+ *
+ * This is not very scalable on SMP. Double adds are not possible.
+ */
+void add_timer_on(struct timer_list *timer, int cpu)
+{
+	struct tvec_base *base = per_cpu(tvec_bases, cpu);
+	unsigned long flags;
+
+	timer_stats_timer_set_start_info(timer);
+	BUG_ON(timer_pending(timer) || !timer->function);
+	spin_lock_irqsave(&base->lock, flags);
+	timer_set_base(timer, base);
+	debug_timer_activate(timer);
+	internal_add_timer(base, timer);
+	/*
+	 * Check whether the other CPU is idle and needs to be
+	 * triggered to reevaluate the timer wheel when nohz is
+	 * active. We are protected against the other CPU fiddling
+	 * with the timer by holding the timer base lock. This also
+	 * makes sure that a CPU on the way to idle can not evaluate
+	 * the timer wheel.
+	 */
+	wake_up_idle_cpu(cpu);
+	spin_unlock_irqrestore(&base->lock, flags);
+}
+
+/**
  * del_timer - deactive a timer.
  * @timer: the timer to be deactivated
  *
@@ -744,7 +783,6 @@ int del_timer(struct timer_list *timer)
 
 	return ret;
 }
-
 EXPORT_SYMBOL(del_timer);
 
 #ifdef CONFIG_SMP
@@ -778,7 +816,6 @@ out:
 
 	return ret;
 }
-
 EXPORT_SYMBOL(try_to_del_timer_sync);
 
 /**
@@ -816,7 +853,6 @@ int del_timer_sync(struct timer_list *timer)
 		cpu_relax();
 	}
 }
-
 EXPORT_SYMBOL(del_timer_sync);
 #endif
 
@@ -1314,7 +1350,7 @@ signed long __sched schedule_timeout(signed long timeout)
 	expire = timeout + jiffies;
 
 	setup_timer_on_stack(&timer, process_timeout, (unsigned long)current);
-	__mod_timer(&timer, expire);
+	__mod_timer(&timer, expire, false);
 	schedule();
 	del_singleshot_timer_sync(&timer);
 
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index 95a0ad191f1..2246141bda4 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -63,7 +63,11 @@ config TRACING
 #
 config TRACING_SUPPORT
 	bool
-	depends on TRACE_IRQFLAGS_SUPPORT
+	# PPC32 has no irqflags tracing support, but it can use most of the
+	# tracers anyway, they were tested to build and work. Note that new
+	# exceptions to this list aren't welcomed, better implement the
+	# irqflags tracing for your architecture.
+	depends on TRACE_IRQFLAGS_SUPPORT || PPC32
 	depends on STACKTRACE_SUPPORT
 	default y
 
@@ -95,11 +99,10 @@ config FUNCTION_GRAPH_TRACER
 	help
 	  Enable the kernel to trace a function at both its return
 	  and its entry.
-	  It's first purpose is to trace the duration of functions and
-	  draw a call graph for each thread with some informations like
-	  the return value.
-	  This is done by setting the current return address on the current
-	  task structure into a stack of calls.
+	  Its first purpose is to trace the duration of functions and
+	  draw a call graph for each thread with some information like
+	  the return value. This is done by setting the current return 
+	  address on the current task structure into a stack of calls.
 
 config IRQSOFF_TRACER
 	bool "Interrupts-off Latency Tracer"
@@ -182,6 +185,7 @@ config FTRACE_SYSCALLS
 	bool "Trace syscalls"
 	depends on HAVE_FTRACE_SYSCALLS
 	select TRACING
+	select KALLSYMS
 	help
 	  Basic tracer to catch the syscall entry and exit events.
 
diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile
index c3feea01c3e..2630f5121ec 100644
--- a/kernel/trace/Makefile
+++ b/kernel/trace/Makefile
@@ -44,5 +44,7 @@ obj-$(CONFIG_EVENT_TRACER) += trace_events.o
 obj-$(CONFIG_EVENT_TRACER) += events.o
 obj-$(CONFIG_EVENT_TRACER) += trace_export.o
 obj-$(CONFIG_FTRACE_SYSCALLS) += trace_syscalls.o
+obj-$(CONFIG_EVENT_PROFILE) += trace_event_profile.o
+obj-$(CONFIG_EVENT_TRACER) += trace_events_filter.o
 
 libftrace-y := ftrace.o
diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c
index 1f32e4edf49..947c5b3f90c 100644
--- a/kernel/trace/blktrace.c
+++ b/kernel/trace/blktrace.c
@@ -30,7 +30,7 @@
 static unsigned int blktrace_seq __read_mostly = 1;
 
 static struct trace_array *blk_tr;
-static int __read_mostly  blk_tracer_enabled;
+static bool blk_tracer_enabled __read_mostly;
 
 /* Select an alternative, minimalistic output than the original one */
 #define TRACE_BLK_OPT_CLASSIC	0x1
@@ -47,10 +47,9 @@ static struct tracer_flags blk_tracer_flags = {
 };
 
 /* Global reference count of probes */
-static DEFINE_MUTEX(blk_probe_mutex);
 static atomic_t blk_probes_ref = ATOMIC_INIT(0);
 
-static int blk_register_tracepoints(void);
+static void blk_register_tracepoints(void);
 static void blk_unregister_tracepoints(void);
 
 /*
@@ -60,22 +59,39 @@ static void trace_note(struct blk_trace *bt, pid_t pid, int action,
 		       const void *data, size_t len)
 {
 	struct blk_io_trace *t;
+	struct ring_buffer_event *event = NULL;
+	int pc = 0;
+	int cpu = smp_processor_id();
+	bool blk_tracer = blk_tracer_enabled;
+
+	if (blk_tracer) {
+		pc = preempt_count();
+		event = trace_buffer_lock_reserve(blk_tr, TRACE_BLK,
+						  sizeof(*t) + len,
+						  0, pc);
+		if (!event)
+			return;
+		t = ring_buffer_event_data(event);
+		goto record_it;
+	}
 
 	if (!bt->rchan)
 		return;
 
 	t = relay_reserve(bt->rchan, sizeof(*t) + len);
 	if (t) {
-		const int cpu = smp_processor_id();
-
 		t->magic = BLK_IO_TRACE_MAGIC | BLK_IO_TRACE_VERSION;
 		t->time = ktime_to_ns(ktime_get());
+record_it:
 		t->device = bt->dev;
 		t->action = action;
 		t->pid = pid;
 		t->cpu = cpu;
 		t->pdu_len = len;
 		memcpy((void *) t + sizeof(*t), data, len);
+
+		if (blk_tracer)
+			trace_buffer_unlock_commit(blk_tr, event, 0, pc);
 	}
 }
 
@@ -111,14 +127,8 @@ void __trace_note_message(struct blk_trace *bt, const char *fmt, ...)
 	unsigned long flags;
 	char *buf;
 
-	if (blk_tr) {
-		va_start(args, fmt);
-		ftrace_vprintk(fmt, args);
-		va_end(args);
-		return;
-	}
-
-	if (!bt->msg_data)
+	if (unlikely(bt->trace_state != Blktrace_running &&
+		     !blk_tracer_enabled))
 		return;
 
 	local_irq_save(flags);
@@ -148,8 +158,8 @@ static int act_log_check(struct blk_trace *bt, u32 what, sector_t sector,
 /*
  * Data direction bit lookup
  */
-static u32 ddir_act[2] __read_mostly = { BLK_TC_ACT(BLK_TC_READ),
-					 BLK_TC_ACT(BLK_TC_WRITE) };
+static const u32 ddir_act[2] = { BLK_TC_ACT(BLK_TC_READ),
+				 BLK_TC_ACT(BLK_TC_WRITE) };
 
 /* The ilog2() calls fall out because they're constant */
 #define MASK_TC_BIT(rw, __name) ((rw & (1 << BIO_RW_ ## __name)) << \
@@ -169,9 +179,9 @@ static void __blk_add_trace(struct blk_trace *bt, sector_t sector, int bytes,
 	unsigned long *sequence;
 	pid_t pid;
 	int cpu, pc = 0;
+	bool blk_tracer = blk_tracer_enabled;
 
-	if (unlikely(bt->trace_state != Blktrace_running ||
-		     !blk_tracer_enabled))
+	if (unlikely(bt->trace_state != Blktrace_running && !blk_tracer))
 		return;
 
 	what |= ddir_act[rw & WRITE];
@@ -186,7 +196,7 @@ static void __blk_add_trace(struct blk_trace *bt, sector_t sector, int bytes,
 		return;
 	cpu = raw_smp_processor_id();
 
-	if (blk_tr) {
+	if (blk_tracer) {
 		tracing_record_cmdline(current);
 
 		pc = preempt_count();
@@ -236,7 +246,7 @@ record_it:
 		if (pdu_len)
 			memcpy((void *) t + sizeof(*t), pdu_data, pdu_len);
 
-		if (blk_tr) {
+		if (blk_tracer) {
 			trace_buffer_unlock_commit(blk_tr, event, 0, pc);
 			return;
 		}
@@ -248,7 +258,7 @@ record_it:
 static struct dentry *blk_tree_root;
 static DEFINE_MUTEX(blk_tree_mutex);
 
-static void blk_trace_cleanup(struct blk_trace *bt)
+static void blk_trace_free(struct blk_trace *bt)
 {
 	debugfs_remove(bt->msg_file);
 	debugfs_remove(bt->dropped_file);
@@ -256,10 +266,13 @@ static void blk_trace_cleanup(struct blk_trace *bt)
 	free_percpu(bt->sequence);
 	free_percpu(bt->msg_data);
 	kfree(bt);
-	mutex_lock(&blk_probe_mutex);
+}
+
+static void blk_trace_cleanup(struct blk_trace *bt)
+{
+	blk_trace_free(bt);
 	if (atomic_dec_and_test(&blk_probes_ref))
 		blk_unregister_tracepoints();
-	mutex_unlock(&blk_probe_mutex);
 }
 
 int blk_trace_remove(struct request_queue *q)
@@ -270,8 +283,7 @@ int blk_trace_remove(struct request_queue *q)
 	if (!bt)
 		return -EINVAL;
 
-	if (bt->trace_state == Blktrace_setup ||
-	    bt->trace_state == Blktrace_stopped)
+	if (bt->trace_state != Blktrace_running)
 		blk_trace_cleanup(bt);
 
 	return 0;
@@ -414,11 +426,11 @@ int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
 		if (buts->name[i] == '/')
 			buts->name[i] = '_';
 
-	ret = -ENOMEM;
 	bt = kzalloc(sizeof(*bt), GFP_KERNEL);
 	if (!bt)
-		goto err;
+		return -ENOMEM;
 
+	ret = -ENOMEM;
 	bt->sequence = alloc_percpu(unsigned long);
 	if (!bt->sequence)
 		goto err;
@@ -429,11 +441,15 @@ int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
 
 	ret = -ENOENT;
 
+	mutex_lock(&blk_tree_mutex);
 	if (!blk_tree_root) {
 		blk_tree_root = debugfs_create_dir("block", NULL);
-		if (!blk_tree_root)
-			return -ENOMEM;
+		if (!blk_tree_root) {
+			mutex_unlock(&blk_tree_mutex);
+			goto err;
+		}
 	}
+	mutex_unlock(&blk_tree_mutex);
 
 	dir = debugfs_create_dir(buts->name, blk_tree_root);
 
@@ -471,14 +487,6 @@ int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
 	bt->pid = buts->pid;
 	bt->trace_state = Blktrace_setup;
 
-	mutex_lock(&blk_probe_mutex);
-	if (atomic_add_return(1, &blk_probes_ref) == 1) {
-		ret = blk_register_tracepoints();
-		if (ret)
-			goto probe_err;
-	}
-	mutex_unlock(&blk_probe_mutex);
-
 	ret = -EBUSY;
 	old_bt = xchg(&q->blk_trace, bt);
 	if (old_bt) {
@@ -486,22 +494,12 @@ int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
 		goto err;
 	}
 
+	if (atomic_inc_return(&blk_probes_ref) == 1)
+		blk_register_tracepoints();
+
 	return 0;
-probe_err:
-	atomic_dec(&blk_probes_ref);
-	mutex_unlock(&blk_probe_mutex);
 err:
-	if (bt) {
-		if (bt->msg_file)
-			debugfs_remove(bt->msg_file);
-		if (bt->dropped_file)
-			debugfs_remove(bt->dropped_file);
-		free_percpu(bt->sequence);
-		free_percpu(bt->msg_data);
-		if (bt->rchan)
-			relay_close(bt->rchan);
-		kfree(bt);
-	}
+	blk_trace_free(bt);
 	return ret;
 }
 
@@ -863,7 +861,7 @@ void blk_add_driver_data(struct request_queue *q,
 }
 EXPORT_SYMBOL_GPL(blk_add_driver_data);
 
-static int blk_register_tracepoints(void)
+static void blk_register_tracepoints(void)
 {
 	int ret;
 
@@ -901,7 +899,6 @@ static int blk_register_tracepoints(void)
 	WARN_ON(ret);
 	ret = register_trace_block_remap(blk_add_trace_remap);
 	WARN_ON(ret);
-	return 0;
 }
 
 static void blk_unregister_tracepoints(void)
@@ -934,25 +931,31 @@ static void blk_unregister_tracepoints(void)
 static void fill_rwbs(char *rwbs, const struct blk_io_trace *t)
 {
 	int i = 0;
+	int tc = t->action >> BLK_TC_SHIFT;
+
+	if (t->action == BLK_TN_MESSAGE) {
+		rwbs[i++] = 'N';
+		goto out;
+	}
 
-	if (t->action & BLK_TC_DISCARD)
+	if (tc & BLK_TC_DISCARD)
 		rwbs[i++] = 'D';
-	else if (t->action & BLK_TC_WRITE)
+	else if (tc & BLK_TC_WRITE)
 		rwbs[i++] = 'W';
 	else if (t->bytes)
 		rwbs[i++] = 'R';
 	else
 		rwbs[i++] = 'N';
 
-	if (t->action & BLK_TC_AHEAD)
+	if (tc & BLK_TC_AHEAD)
 		rwbs[i++] = 'A';
-	if (t->action & BLK_TC_BARRIER)
+	if (tc & BLK_TC_BARRIER)
 		rwbs[i++] = 'B';
-	if (t->action & BLK_TC_SYNC)
+	if (tc & BLK_TC_SYNC)
 		rwbs[i++] = 'S';
-	if (t->action & BLK_TC_META)
+	if (tc & BLK_TC_META)
 		rwbs[i++] = 'M';
-
+out:
 	rwbs[i] = '\0';
 }
 
@@ -979,7 +982,7 @@ static inline unsigned long long t_sector(const struct trace_entry *ent)
 
 static inline __u16 t_error(const struct trace_entry *ent)
 {
-	return te_blk_io_trace(ent)->sector;
+	return te_blk_io_trace(ent)->error;
 }
 
 static __u64 get_pdu_int(const struct trace_entry *ent)
@@ -999,35 +1002,39 @@ static void get_pdu_remap(const struct trace_entry *ent,
 	r->sector = be64_to_cpu(sector);
 }
 
-static int blk_log_action_iter(struct trace_iterator *iter, const char *act)
+typedef int (blk_log_action_t) (struct trace_iterator *iter, const char *act);
+
+static int blk_log_action_classic(struct trace_iterator *iter, const char *act)
 {
 	char rwbs[6];
-	unsigned long long ts  = ns2usecs(iter->ts);
-	unsigned long usec_rem = do_div(ts, USEC_PER_SEC);
+	unsigned long long ts  = iter->ts;
+	unsigned long nsec_rem = do_div(ts, NSEC_PER_SEC);
 	unsigned secs	       = (unsigned long)ts;
-	const struct trace_entry *ent = iter->ent;
-	const struct blk_io_trace *t = (const struct blk_io_trace *)ent;
+	const struct blk_io_trace *t = te_blk_io_trace(iter->ent);
 
 	fill_rwbs(rwbs, t);
 
 	return trace_seq_printf(&iter->seq,
-				"%3d,%-3d %2d %5d.%06lu %5u %2s %3s ",
+				"%3d,%-3d %2d %5d.%09lu %5u %2s %3s ",
 				MAJOR(t->device), MINOR(t->device), iter->cpu,
-				secs, usec_rem, ent->pid, act, rwbs);
+				secs, nsec_rem, iter->ent->pid, act, rwbs);
 }
 
-static int blk_log_action_seq(struct trace_seq *s, const struct blk_io_trace *t,
-			      const char *act)
+static int blk_log_action(struct trace_iterator *iter, const char *act)
 {
 	char rwbs[6];
+	const struct blk_io_trace *t = te_blk_io_trace(iter->ent);
+
 	fill_rwbs(rwbs, t);
-	return trace_seq_printf(s, "%3d,%-3d %2s %3s ",
+	return trace_seq_printf(&iter->seq, "%3d,%-3d %2s %3s ",
 				MAJOR(t->device), MINOR(t->device), act, rwbs);
 }
 
 static int blk_log_generic(struct trace_seq *s, const struct trace_entry *ent)
 {
-	const char *cmd = trace_find_cmdline(ent->pid);
+	char cmd[TASK_COMM_LEN];
+
+	trace_find_cmdline(ent->pid, cmd);
 
 	if (t_sec(ent))
 		return trace_seq_printf(s, "%llu + %u [%s]\n",
@@ -1057,19 +1064,41 @@ static int blk_log_remap(struct trace_seq *s, const struct trace_entry *ent)
 
 static int blk_log_plug(struct trace_seq *s, const struct trace_entry *ent)
 {
-	return trace_seq_printf(s, "[%s]\n", trace_find_cmdline(ent->pid));
+	char cmd[TASK_COMM_LEN];
+
+	trace_find_cmdline(ent->pid, cmd);
+
+	return trace_seq_printf(s, "[%s]\n", cmd);
 }
 
 static int blk_log_unplug(struct trace_seq *s, const struct trace_entry *ent)
 {
-	return trace_seq_printf(s, "[%s] %llu\n", trace_find_cmdline(ent->pid),
-				get_pdu_int(ent));
+	char cmd[TASK_COMM_LEN];
+
+	trace_find_cmdline(ent->pid, cmd);
+
+	return trace_seq_printf(s, "[%s] %llu\n", cmd, get_pdu_int(ent));
 }
 
 static int blk_log_split(struct trace_seq *s, const struct trace_entry *ent)
 {
+	char cmd[TASK_COMM_LEN];
+
+	trace_find_cmdline(ent->pid, cmd);
+
 	return trace_seq_printf(s, "%llu / %llu [%s]\n", t_sector(ent),
-				get_pdu_int(ent), trace_find_cmdline(ent->pid));
+				get_pdu_int(ent), cmd);
+}
+
+static int blk_log_msg(struct trace_seq *s, const struct trace_entry *ent)
+{
+	int ret;
+	const struct blk_io_trace *t = te_blk_io_trace(ent);
+
+	ret = trace_seq_putmem(s, t + 1, t->pdu_len);
+	if (ret)
+		return trace_seq_putc(s, '\n');
+	return ret;
 }
 
 /*
@@ -1086,11 +1115,7 @@ static void blk_tracer_print_header(struct seq_file *m)
 
 static void blk_tracer_start(struct trace_array *tr)
 {
-	mutex_lock(&blk_probe_mutex);
-	if (atomic_add_return(1, &blk_probes_ref) == 1)
-		if (blk_register_tracepoints())
-			atomic_dec(&blk_probes_ref);
-	mutex_unlock(&blk_probe_mutex);
+	blk_tracer_enabled = true;
 	trace_flags &= ~TRACE_ITER_CONTEXT_INFO;
 }
 
@@ -1098,38 +1123,24 @@ static int blk_tracer_init(struct trace_array *tr)
 {
 	blk_tr = tr;
 	blk_tracer_start(tr);
-	mutex_lock(&blk_probe_mutex);
-	blk_tracer_enabled++;
-	mutex_unlock(&blk_probe_mutex);
 	return 0;
 }
 
 static void blk_tracer_stop(struct trace_array *tr)
 {
+	blk_tracer_enabled = false;
 	trace_flags |= TRACE_ITER_CONTEXT_INFO;
-	mutex_lock(&blk_probe_mutex);
-	if (atomic_dec_and_test(&blk_probes_ref))
-		blk_unregister_tracepoints();
-	mutex_unlock(&blk_probe_mutex);
 }
 
 static void blk_tracer_reset(struct trace_array *tr)
 {
-	if (!atomic_read(&blk_probes_ref))
-		return;
-
-	mutex_lock(&blk_probe_mutex);
-	blk_tracer_enabled--;
-	WARN_ON(blk_tracer_enabled < 0);
-	mutex_unlock(&blk_probe_mutex);
-
 	blk_tracer_stop(tr);
 }
 
-static struct {
+static const struct {
 	const char *act[2];
 	int	   (*print)(struct trace_seq *s, const struct trace_entry *ent);
-} what2act[] __read_mostly = {
+} what2act[] = {
 	[__BLK_TA_QUEUE]	= {{  "Q", "queue" },	   blk_log_generic },
 	[__BLK_TA_BACKMERGE]	= {{  "M", "backmerge" },  blk_log_generic },
 	[__BLK_TA_FRONTMERGE]	= {{  "F", "frontmerge" }, blk_log_generic },
@@ -1147,29 +1158,48 @@ static struct {
 	[__BLK_TA_REMAP]	= {{  "A", "remap" },	   blk_log_remap },
 };
 
-static enum print_line_t blk_trace_event_print(struct trace_iterator *iter,
-					       int flags)
+static enum print_line_t print_one_line(struct trace_iterator *iter,
+					bool classic)
 {
 	struct trace_seq *s = &iter->seq;
-	const struct blk_io_trace *t = (struct blk_io_trace *)iter->ent;
-	const u16 what = t->action & ((1 << BLK_TC_SHIFT) - 1);
+	const struct blk_io_trace *t;
+	u16 what;
 	int ret;
+	bool long_act;
+	blk_log_action_t *log_action;
 
-	if (!trace_print_context(iter))
-		return TRACE_TYPE_PARTIAL_LINE;
+	t	   = te_blk_io_trace(iter->ent);
+	what	   = t->action & ((1 << BLK_TC_SHIFT) - 1);
+	long_act   = !!(trace_flags & TRACE_ITER_VERBOSE);
+	log_action = classic ? &blk_log_action_classic : &blk_log_action;
 
-	if (unlikely(what == 0 || what > ARRAY_SIZE(what2act)))
+	if (t->action == BLK_TN_MESSAGE) {
+		ret = log_action(iter, long_act ? "message" : "m");
+		if (ret)
+			ret = blk_log_msg(s, iter->ent);
+		goto out;
+	}
+
+	if (unlikely(what == 0 || what >= ARRAY_SIZE(what2act)))
 		ret = trace_seq_printf(s, "Bad pc action %x\n", what);
 	else {
-		const bool long_act = !!(trace_flags & TRACE_ITER_VERBOSE);
-		ret = blk_log_action_seq(s, t, what2act[what].act[long_act]);
+		ret = log_action(iter, what2act[what].act[long_act]);
 		if (ret)
 			ret = what2act[what].print(s, iter->ent);
 	}
-
+out:
 	return ret ? TRACE_TYPE_HANDLED : TRACE_TYPE_PARTIAL_LINE;
 }
 
+static enum print_line_t blk_trace_event_print(struct trace_iterator *iter,
+					       int flags)
+{
+	if (!trace_print_context(iter))
+		return TRACE_TYPE_PARTIAL_LINE;
+
+	return print_one_line(iter, false);
+}
+
 static int blk_trace_synthesize_old_trace(struct trace_iterator *iter)
 {
 	struct trace_seq *s = &iter->seq;
@@ -1177,7 +1207,7 @@ static int blk_trace_synthesize_old_trace(struct trace_iterator *iter)
 	const int offset = offsetof(struct blk_io_trace, sector);
 	struct blk_io_trace old = {
 		.magic	  = BLK_IO_TRACE_MAGIC | BLK_IO_TRACE_VERSION,
-		.time     = ns2usecs(iter->ts),
+		.time     = iter->ts,
 	};
 
 	if (!trace_seq_putmem(s, &old, offset))
@@ -1195,26 +1225,10 @@ blk_trace_event_print_binary(struct trace_iterator *iter, int flags)
 
 static enum print_line_t blk_tracer_print_line(struct trace_iterator *iter)
 {
-	const struct blk_io_trace *t;
-	u16 what;
-	int ret;
-
 	if (!(blk_tracer_flags.val & TRACE_BLK_OPT_CLASSIC))
 		return TRACE_TYPE_UNHANDLED;
 
-	t = (const struct blk_io_trace *)iter->ent;
-	what = t->action & ((1 << BLK_TC_SHIFT) - 1);
-
-	if (unlikely(what == 0 || what > ARRAY_SIZE(what2act)))
-		ret = trace_seq_printf(&iter->seq, "Bad pc action %x\n", what);
-	else {
-		const bool long_act = !!(trace_flags & TRACE_ITER_VERBOSE);
-		ret = blk_log_action_iter(iter, what2act[what].act[long_act]);
-		if (ret)
-			ret = what2act[what].print(&iter->seq, iter->ent);
-	}
-
-	return ret ? TRACE_TYPE_HANDLED : TRACE_TYPE_PARTIAL_LINE;
+	return print_one_line(iter, true);
 }
 
 static struct tracer blk_tracer __read_mostly = {
@@ -1260,7 +1274,10 @@ static int blk_trace_remove_queue(struct request_queue *q)
 	if (bt == NULL)
 		return -EINVAL;
 
-	kfree(bt);
+	if (atomic_dec_and_test(&blk_probes_ref))
+		blk_unregister_tracepoints();
+
+	blk_trace_free(bt);
 	return 0;
 }
 
@@ -1270,26 +1287,33 @@ static int blk_trace_remove_queue(struct request_queue *q)
 static int blk_trace_setup_queue(struct request_queue *q, dev_t dev)
 {
 	struct blk_trace *old_bt, *bt = NULL;
-	int ret;
+	int ret = -ENOMEM;
 
-	ret = -ENOMEM;
 	bt = kzalloc(sizeof(*bt), GFP_KERNEL);
 	if (!bt)
-		goto err;
+		return -ENOMEM;
+
+	bt->msg_data = __alloc_percpu(BLK_TN_MAX_MSG, __alignof__(char));
+	if (!bt->msg_data)
+		goto free_bt;
 
 	bt->dev = dev;
 	bt->act_mask = (u16)-1;
 	bt->end_lba = -1ULL;
-	bt->trace_state = Blktrace_running;
 
 	old_bt = xchg(&q->blk_trace, bt);
 	if (old_bt != NULL) {
 		(void)xchg(&q->blk_trace, old_bt);
-		kfree(bt);
 		ret = -EBUSY;
+		goto free_bt;
 	}
+
+	if (atomic_inc_return(&blk_probes_ref) == 1)
+		blk_register_tracepoints();
 	return 0;
-err:
+
+free_bt:
+	blk_trace_free(bt);
 	return ret;
 }
 
@@ -1297,72 +1321,6 @@ err:
  * sysfs interface to enable and configure tracing
  */
 
-static ssize_t sysfs_blk_trace_enable_show(struct device *dev,
-					   struct device_attribute *attr,
-					   char *buf)
-{
-	struct hd_struct *p = dev_to_part(dev);
-	struct block_device *bdev;
-	ssize_t ret = -ENXIO;
-
-	lock_kernel();
-	bdev = bdget(part_devt(p));
-	if (bdev != NULL) {
-		struct request_queue *q = bdev_get_queue(bdev);
-
-		if (q != NULL) {
-			mutex_lock(&bdev->bd_mutex);
-			ret = sprintf(buf, "%u\n", !!q->blk_trace);
-			mutex_unlock(&bdev->bd_mutex);
-		}
-
-		bdput(bdev);
-	}
-
-	unlock_kernel();
-	return ret;
-}
-
-static ssize_t sysfs_blk_trace_enable_store(struct device *dev,
-					    struct device_attribute *attr,
-					    const char *buf, size_t count)
-{
-	struct block_device *bdev;
-	struct request_queue *q;
-	struct hd_struct *p;
-	int value;
-	ssize_t ret = -ENXIO;
-
-	if (count == 0 || sscanf(buf, "%d", &value) != 1)
-		goto out;
-
-	lock_kernel();
-	p = dev_to_part(dev);
-	bdev = bdget(part_devt(p));
-	if (bdev == NULL)
-		goto out_unlock_kernel;
-
-	q = bdev_get_queue(bdev);
-	if (q == NULL)
-		goto out_bdput;
-
-	mutex_lock(&bdev->bd_mutex);
-	if (value)
-		ret = blk_trace_setup_queue(q, bdev->bd_dev);
-	else
-		ret = blk_trace_remove_queue(q);
-	mutex_unlock(&bdev->bd_mutex);
-
-	if (ret == 0)
-		ret = count;
-out_bdput:
-	bdput(bdev);
-out_unlock_kernel:
-	unlock_kernel();
-out:
-	return ret;
-}
-
 static ssize_t sysfs_blk_trace_attr_show(struct device *dev,
 					 struct device_attribute *attr,
 					 char *buf);
@@ -1374,8 +1332,7 @@ static ssize_t sysfs_blk_trace_attr_store(struct device *dev,
 		    sysfs_blk_trace_attr_show, \
 		    sysfs_blk_trace_attr_store)
 
-static DEVICE_ATTR(enable, S_IRUGO | S_IWUSR,
-		   sysfs_blk_trace_enable_show, sysfs_blk_trace_enable_store);
+static BLK_TRACE_DEVICE_ATTR(enable);
 static BLK_TRACE_DEVICE_ATTR(act_mask);
 static BLK_TRACE_DEVICE_ATTR(pid);
 static BLK_TRACE_DEVICE_ATTR(start_lba);
@@ -1395,53 +1352,85 @@ struct attribute_group blk_trace_attr_group = {
 	.attrs = blk_trace_attrs,
 };
 
-static int blk_str2act_mask(const char *str)
+static const struct {
+	int mask;
+	const char *str;
+} mask_maps[] = {
+	{ BLK_TC_READ,		"read"		},
+	{ BLK_TC_WRITE,		"write"		},
+	{ BLK_TC_BARRIER,	"barrier"	},
+	{ BLK_TC_SYNC,		"sync"		},
+	{ BLK_TC_QUEUE,		"queue"		},
+	{ BLK_TC_REQUEUE,	"requeue"	},
+	{ BLK_TC_ISSUE,		"issue"		},
+	{ BLK_TC_COMPLETE,	"complete"	},
+	{ BLK_TC_FS,		"fs"		},
+	{ BLK_TC_PC,		"pc"		},
+	{ BLK_TC_AHEAD,		"ahead"		},
+	{ BLK_TC_META,		"meta"		},
+	{ BLK_TC_DISCARD,	"discard"	},
+	{ BLK_TC_DRV_DATA,	"drv_data"	},
+};
+
+static int blk_trace_str2mask(const char *str)
 {
+	int i;
 	int mask = 0;
-	char *copy = kstrdup(str, GFP_KERNEL), *s;
+	char *s, *token;
 
-	if (copy == NULL)
+	s = kstrdup(str, GFP_KERNEL);
+	if (s == NULL)
 		return -ENOMEM;
-
-	s = strstrip(copy);
+	s = strstrip(s);
 
 	while (1) {
-		char *sep = strchr(s, ',');
-
-		if (sep != NULL)
-			*sep = '\0';
-
-		if (strcasecmp(s, "barrier") == 0)
-			mask |= BLK_TC_BARRIER;
-		else if (strcasecmp(s, "complete") == 0)
-			mask |= BLK_TC_COMPLETE;
-		else if (strcasecmp(s, "fs") == 0)
-			mask |= BLK_TC_FS;
-		else if (strcasecmp(s, "issue") == 0)
-			mask |= BLK_TC_ISSUE;
-		else if (strcasecmp(s, "pc") == 0)
-			mask |= BLK_TC_PC;
-		else if (strcasecmp(s, "queue") == 0)
-			mask |= BLK_TC_QUEUE;
-		else if (strcasecmp(s, "read") == 0)
-			mask |= BLK_TC_READ;
-		else if (strcasecmp(s, "requeue") == 0)
-			mask |= BLK_TC_REQUEUE;
-		else if (strcasecmp(s, "sync") == 0)
-			mask |= BLK_TC_SYNC;
-		else if (strcasecmp(s, "write") == 0)
-			mask |= BLK_TC_WRITE;
-
-		if (sep == NULL)
+		token = strsep(&s, ",");
+		if (token == NULL)
 			break;
 
-		s = sep + 1;
+		if (*token == '\0')
+			continue;
+
+		for (i = 0; i < ARRAY_SIZE(mask_maps); i++) {
+			if (strcasecmp(token, mask_maps[i].str) == 0) {
+				mask |= mask_maps[i].mask;
+				break;
+			}
+		}
+		if (i == ARRAY_SIZE(mask_maps)) {
+			mask = -EINVAL;
+			break;
+		}
 	}
-	kfree(copy);
+	kfree(s);
 
 	return mask;
 }
 
+static ssize_t blk_trace_mask2str(char *buf, int mask)
+{
+	int i;
+	char *p = buf;
+
+	for (i = 0; i < ARRAY_SIZE(mask_maps); i++) {
+		if (mask & mask_maps[i].mask) {
+			p += sprintf(p, "%s%s",
+				    (p == buf) ? "" : ",", mask_maps[i].str);
+		}
+	}
+	*p++ = '\n';
+
+	return p - buf;
+}
+
+static struct request_queue *blk_trace_get_queue(struct block_device *bdev)
+{
+	if (bdev->bd_disk == NULL)
+		return NULL;
+
+	return bdev_get_queue(bdev);
+}
+
 static ssize_t sysfs_blk_trace_attr_show(struct device *dev,
 					 struct device_attribute *attr,
 					 char *buf)
@@ -1456,20 +1445,29 @@ static ssize_t sysfs_blk_trace_attr_show(struct device *dev,
 	if (bdev == NULL)
 		goto out_unlock_kernel;
 
-	q = bdev_get_queue(bdev);
+	q = blk_trace_get_queue(bdev);
 	if (q == NULL)
 		goto out_bdput;
+
 	mutex_lock(&bdev->bd_mutex);
+
+	if (attr == &dev_attr_enable) {
+		ret = sprintf(buf, "%u\n", !!q->blk_trace);
+		goto out_unlock_bdev;
+	}
+
 	if (q->blk_trace == NULL)
 		ret = sprintf(buf, "disabled\n");
 	else if (attr == &dev_attr_act_mask)
-		ret = sprintf(buf, "%#x\n", q->blk_trace->act_mask);
+		ret = blk_trace_mask2str(buf, q->blk_trace->act_mask);
 	else if (attr == &dev_attr_pid)
 		ret = sprintf(buf, "%u\n", q->blk_trace->pid);
 	else if (attr == &dev_attr_start_lba)
 		ret = sprintf(buf, "%llu\n", q->blk_trace->start_lba);
 	else if (attr == &dev_attr_end_lba)
 		ret = sprintf(buf, "%llu\n", q->blk_trace->end_lba);
+
+out_unlock_bdev:
 	mutex_unlock(&bdev->bd_mutex);
 out_bdput:
 	bdput(bdev);
@@ -1486,7 +1484,7 @@ static ssize_t sysfs_blk_trace_attr_store(struct device *dev,
 	struct request_queue *q;
 	struct hd_struct *p;
 	u64 value;
-	ssize_t ret = -ENXIO;
+	ssize_t ret = -EINVAL;
 
 	if (count == 0)
 		goto out;
@@ -1494,24 +1492,36 @@ static ssize_t sysfs_blk_trace_attr_store(struct device *dev,
 	if (attr == &dev_attr_act_mask) {
 		if (sscanf(buf, "%llx", &value) != 1) {
 			/* Assume it is a list of trace category names */
-			value = blk_str2act_mask(buf);
-			if (value < 0)
+			ret = blk_trace_str2mask(buf);
+			if (ret < 0)
 				goto out;
+			value = ret;
 		}
 	} else if (sscanf(buf, "%llu", &value) != 1)
 		goto out;
 
+	ret = -ENXIO;
+
 	lock_kernel();
 	p = dev_to_part(dev);
 	bdev = bdget(part_devt(p));
 	if (bdev == NULL)
 		goto out_unlock_kernel;
 
-	q = bdev_get_queue(bdev);
+	q = blk_trace_get_queue(bdev);
 	if (q == NULL)
 		goto out_bdput;
 
 	mutex_lock(&bdev->bd_mutex);
+
+	if (attr == &dev_attr_enable) {
+		if (value)
+			ret = blk_trace_setup_queue(q, bdev->bd_dev);
+		else
+			ret = blk_trace_remove_queue(q);
+		goto out_unlock_bdev;
+	}
+
 	ret = 0;
 	if (q->blk_trace == NULL)
 		ret = blk_trace_setup_queue(q, bdev->bd_dev);
@@ -1525,13 +1535,15 @@ static ssize_t sysfs_blk_trace_attr_store(struct device *dev,
 			q->blk_trace->start_lba = value;
 		else if (attr == &dev_attr_end_lba)
 			q->blk_trace->end_lba = value;
-		ret = count;
 	}
+
+out_unlock_bdev:
 	mutex_unlock(&bdev->bd_mutex);
 out_bdput:
 	bdput(bdev);
 out_unlock_kernel:
 	unlock_kernel();
 out:
-	return ret;
+	return ret ? ret : count;
 }
+
diff --git a/kernel/trace/events.c b/kernel/trace/events.c
index 9fc918da404..246f2aa6dc4 100644
--- a/kernel/trace/events.c
+++ b/kernel/trace/events.c
@@ -12,4 +12,3 @@
 #include "trace_events_stage_2.h"
 #include "trace_events_stage_3.h"
 
-#include <trace/trace_event_types.h>
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index d33d306bdcf..f1ed080406c 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -29,6 +29,8 @@
 #include <linux/list.h>
 #include <linux/hash.h>
 
+#include <trace/sched.h>
+
 #include <asm/ftrace.h>
 
 #include "trace.h"
@@ -272,7 +274,7 @@ enum {
 
 static int ftrace_filtered;
 
-static LIST_HEAD(ftrace_new_addrs);
+static struct dyn_ftrace *ftrace_new_addrs;
 
 static DEFINE_MUTEX(ftrace_regex_lock);
 
@@ -339,7 +341,7 @@ static inline int record_frozen(struct dyn_ftrace *rec)
 
 static void ftrace_free_rec(struct dyn_ftrace *rec)
 {
-	rec->ip = (unsigned long)ftrace_free_records;
+	rec->freelist = ftrace_free_records;
 	ftrace_free_records = rec;
 	rec->flags |= FTRACE_FL_FREE;
 }
@@ -356,8 +358,14 @@ void ftrace_release(void *start, unsigned long size)
 
 	mutex_lock(&ftrace_lock);
 	do_for_each_ftrace_rec(pg, rec) {
-		if ((rec->ip >= s) && (rec->ip < e))
+		if ((rec->ip >= s) && (rec->ip < e)) {
+			/*
+			 * rec->ip is changed in ftrace_free_rec()
+			 * It should not between s and e if record was freed.
+			 */
+			FTRACE_WARN_ON(rec->flags & FTRACE_FL_FREE);
 			ftrace_free_rec(rec);
+		}
 	} while_for_each_ftrace_rec();
 	mutex_unlock(&ftrace_lock);
 }
@@ -376,7 +384,7 @@ static struct dyn_ftrace *ftrace_alloc_dyn_node(unsigned long ip)
 			return NULL;
 		}
 
-		ftrace_free_records = (void *)rec->ip;
+		ftrace_free_records = rec->freelist;
 		memset(rec, 0, sizeof(*rec));
 		return rec;
 	}
@@ -408,8 +416,8 @@ ftrace_record_ip(unsigned long ip)
 		return NULL;
 
 	rec->ip = ip;
-
-	list_add(&rec->list, &ftrace_new_addrs);
+	rec->newlist = ftrace_new_addrs;
+	ftrace_new_addrs = rec;
 
 	return rec;
 }
@@ -531,11 +539,12 @@ static void ftrace_replace_code(int enable)
 
 	do_for_each_ftrace_rec(pg, rec) {
 		/*
-		 * Skip over free records and records that have
-		 * failed.
+		 * Skip over free records, records that have
+		 * failed and not converted.
 		 */
 		if (rec->flags & FTRACE_FL_FREE ||
-		    rec->flags & FTRACE_FL_FAILED)
+		    rec->flags & FTRACE_FL_FAILED ||
+		    !(rec->flags & FTRACE_FL_CONVERTED))
 			continue;
 
 		/* ignore updates to this record's mcount site */
@@ -547,7 +556,7 @@ static void ftrace_replace_code(int enable)
 		}
 
 		failed = __ftrace_replace_code(rec, enable);
-		if (failed && (rec->flags & FTRACE_FL_CONVERTED)) {
+		if (failed) {
 			rec->flags |= FTRACE_FL_FAILED;
 			if ((system_state == SYSTEM_BOOTING) ||
 			    !core_kernel_text(rec->ip)) {
@@ -714,19 +723,21 @@ unsigned long		ftrace_update_tot_cnt;
 
 static int ftrace_update_code(struct module *mod)
 {
-	struct dyn_ftrace *p, *t;
+	struct dyn_ftrace *p;
 	cycle_t start, stop;
 
 	start = ftrace_now(raw_smp_processor_id());
 	ftrace_update_cnt = 0;
 
-	list_for_each_entry_safe(p, t, &ftrace_new_addrs, list) {
+	while (ftrace_new_addrs) {
 
 		/* If something went wrong, bail without enabling anything */
 		if (unlikely(ftrace_disabled))
 			return -1;
 
-		list_del_init(&p->list);
+		p = ftrace_new_addrs;
+		ftrace_new_addrs = p->newlist;
+		p->flags = 0L;
 
 		/* convert record (i.e, patch mcount-call with NOP) */
 		if (ftrace_code_disable(mod, p)) {
@@ -1118,16 +1129,6 @@ ftrace_notrace_open(struct inode *inode, struct file *file)
 	return ftrace_regex_open(inode, file, 0);
 }
 
-static ssize_t
-ftrace_regex_read(struct file *file, char __user *ubuf,
-		       size_t cnt, loff_t *ppos)
-{
-	if (file->f_mode & FMODE_READ)
-		return seq_read(file, ubuf, cnt, ppos);
-	else
-		return -EPERM;
-}
-
 static loff_t
 ftrace_regex_lseek(struct file *file, loff_t offset, int origin)
 {
@@ -1880,7 +1881,7 @@ static const struct file_operations ftrace_failures_fops = {
 
 static const struct file_operations ftrace_filter_fops = {
 	.open = ftrace_filter_open,
-	.read = ftrace_regex_read,
+	.read = seq_read,
 	.write = ftrace_filter_write,
 	.llseek = ftrace_regex_lseek,
 	.release = ftrace_filter_release,
@@ -1888,7 +1889,7 @@ static const struct file_operations ftrace_filter_fops = {
 
 static const struct file_operations ftrace_notrace_fops = {
 	.open = ftrace_notrace_open,
-	.read = ftrace_regex_read,
+	.read = seq_read,
 	.write = ftrace_notrace_write,
 	.llseek = ftrace_regex_lseek,
 	.release = ftrace_notrace_release,
@@ -1990,16 +1991,6 @@ ftrace_graph_open(struct inode *inode, struct file *file)
 	return ret;
 }
 
-static ssize_t
-ftrace_graph_read(struct file *file, char __user *ubuf,
-		       size_t cnt, loff_t *ppos)
-{
-	if (file->f_mode & FMODE_READ)
-		return seq_read(file, ubuf, cnt, ppos);
-	else
-		return -EPERM;
-}
-
 static int
 ftrace_set_func(unsigned long *array, int *idx, char *buffer)
 {
@@ -2130,7 +2121,7 @@ ftrace_graph_write(struct file *file, const char __user *ubuf,
 
 static const struct file_operations ftrace_graph_fops = {
 	.open = ftrace_graph_open,
-	.read = ftrace_graph_read,
+	.read = seq_read,
 	.write = ftrace_graph_write,
 };
 #endif /* CONFIG_FUNCTION_GRAPH_TRACER */
@@ -2278,7 +2269,7 @@ ftrace_pid_read(struct file *file, char __user *ubuf,
 	if (ftrace_pid_trace == ftrace_swapper_pid)
 		r = sprintf(buf, "swapper tasks\n");
 	else if (ftrace_pid_trace)
-		r = sprintf(buf, "%u\n", pid_nr(ftrace_pid_trace));
+		r = sprintf(buf, "%u\n", pid_vnr(ftrace_pid_trace));
 	else
 		r = sprintf(buf, "no pid\n");
 
@@ -2606,6 +2597,38 @@ free:
 	return ret;
 }
 
+static void
+ftrace_graph_probe_sched_switch(struct rq *__rq, struct task_struct *prev,
+				struct task_struct *next)
+{
+	unsigned long long timestamp;
+	int index;
+
+	/*
+	 * Does the user want to count the time a function was asleep.
+	 * If so, do not update the time stamps.
+	 */
+	if (trace_flags & TRACE_ITER_SLEEP_TIME)
+		return;
+
+	timestamp = trace_clock_local();
+
+	prev->ftrace_timestamp = timestamp;
+
+	/* only process tasks that we timestamped */
+	if (!next->ftrace_timestamp)
+		return;
+
+	/*
+	 * Update all the counters in next to make up for the
+	 * time next was sleeping.
+	 */
+	timestamp -= next->ftrace_timestamp;
+
+	for (index = next->curr_ret_stack; index >= 0; index--)
+		next->ret_stack[index].calltime += timestamp;
+}
+
 /* Allocate a return stack for each task */
 static int start_graph_tracing(void)
 {
@@ -2627,6 +2650,13 @@ static int start_graph_tracing(void)
 		ret = alloc_retstack_tasklist(ret_stack_list);
 	} while (ret == -EAGAIN);
 
+	if (!ret) {
+		ret = register_trace_sched_switch(ftrace_graph_probe_sched_switch);
+		if (ret)
+			pr_info("ftrace_graph: Couldn't activate tracepoint"
+				" probe to kernel_sched_switch\n");
+	}
+
 	kfree(ret_stack_list);
 	return ret;
 }
@@ -2659,6 +2689,12 @@ int register_ftrace_graph(trace_func_graph_ret_t retfunc,
 
 	mutex_lock(&ftrace_lock);
 
+	/* we currently allow only one tracer registered at a time */
+	if (atomic_read(&ftrace_graph_active)) {
+		ret = -EBUSY;
+		goto out;
+	}
+
 	ftrace_suspend_notifier.notifier_call = ftrace_suspend_notifier_call;
 	register_pm_notifier(&ftrace_suspend_notifier);
 
@@ -2683,12 +2719,17 @@ void unregister_ftrace_graph(void)
 {
 	mutex_lock(&ftrace_lock);
 
+	if (!unlikely(atomic_read(&ftrace_graph_active)))
+		goto out;
+
 	atomic_dec(&ftrace_graph_active);
+	unregister_trace_sched_switch(ftrace_graph_probe_sched_switch);
 	ftrace_graph_return = (trace_func_graph_ret_t)ftrace_stub;
 	ftrace_graph_entry = ftrace_graph_entry_stub;
 	ftrace_shutdown(FTRACE_STOP_FUNC_RET);
 	unregister_pm_notifier(&ftrace_suspend_notifier);
 
+ out:
 	mutex_unlock(&ftrace_lock);
 }
 
@@ -2704,6 +2745,7 @@ void ftrace_graph_init_task(struct task_struct *t)
 		t->curr_ret_stack = -1;
 		atomic_set(&t->tracing_graph_pause, 0);
 		atomic_set(&t->trace_overrun, 0);
+		t->ftrace_timestamp = 0;
 	} else
 		t->ret_stack = NULL;
 }
diff --git a/kernel/trace/kmemtrace.c b/kernel/trace/kmemtrace.c
index ae201b3eda8..5011f4d91e3 100644
--- a/kernel/trace/kmemtrace.c
+++ b/kernel/trace/kmemtrace.c
@@ -6,14 +6,16 @@
  * Copyright (C) 2008 Frederic Weisbecker <fweisbec@gmail.com>
  */
 
-#include <linux/dcache.h>
+#include <linux/tracepoint.h>
+#include <linux/seq_file.h>
 #include <linux/debugfs.h>
+#include <linux/dcache.h>
 #include <linux/fs.h>
-#include <linux/seq_file.h>
+
 #include <trace/kmemtrace.h>
 
-#include "trace.h"
 #include "trace_output.h"
+#include "trace.h"
 
 /* Select an alternative, minimalistic output than the original one */
 #define TRACE_KMEM_OPT_MINIMAL	0x1
@@ -25,14 +27,156 @@ static struct tracer_opt kmem_opts[] = {
 };
 
 static struct tracer_flags kmem_tracer_flags = {
-	.val = 0,
-	.opts = kmem_opts
+	.val			= 0,
+	.opts			= kmem_opts
 };
 
-
-static bool kmem_tracing_enabled __read_mostly;
 static struct trace_array *kmemtrace_array;
 
+/* Trace allocations */
+static inline void kmemtrace_alloc(enum kmemtrace_type_id type_id,
+				   unsigned long call_site,
+				   const void *ptr,
+				   size_t bytes_req,
+				   size_t bytes_alloc,
+				   gfp_t gfp_flags,
+				   int node)
+{
+	struct trace_array *tr = kmemtrace_array;
+	struct kmemtrace_alloc_entry *entry;
+	struct ring_buffer_event *event;
+
+	event = ring_buffer_lock_reserve(tr->buffer, sizeof(*entry));
+	if (!event)
+		return;
+
+	entry = ring_buffer_event_data(event);
+	tracing_generic_entry_update(&entry->ent, 0, 0);
+
+	entry->ent.type		= TRACE_KMEM_ALLOC;
+	entry->type_id		= type_id;
+	entry->call_site	= call_site;
+	entry->ptr		= ptr;
+	entry->bytes_req	= bytes_req;
+	entry->bytes_alloc	= bytes_alloc;
+	entry->gfp_flags	= gfp_flags;
+	entry->node		= node;
+
+	ring_buffer_unlock_commit(tr->buffer, event);
+
+	trace_wake_up();
+}
+
+static inline void kmemtrace_free(enum kmemtrace_type_id type_id,
+				  unsigned long call_site,
+				  const void *ptr)
+{
+	struct trace_array *tr = kmemtrace_array;
+	struct kmemtrace_free_entry *entry;
+	struct ring_buffer_event *event;
+
+	event = ring_buffer_lock_reserve(tr->buffer, sizeof(*entry));
+	if (!event)
+		return;
+	entry	= ring_buffer_event_data(event);
+	tracing_generic_entry_update(&entry->ent, 0, 0);
+
+	entry->ent.type		= TRACE_KMEM_FREE;
+	entry->type_id		= type_id;
+	entry->call_site	= call_site;
+	entry->ptr		= ptr;
+
+	ring_buffer_unlock_commit(tr->buffer, event);
+
+	trace_wake_up();
+}
+
+static void kmemtrace_kmalloc(unsigned long call_site,
+			      const void *ptr,
+			      size_t bytes_req,
+			      size_t bytes_alloc,
+			      gfp_t gfp_flags)
+{
+	kmemtrace_alloc(KMEMTRACE_TYPE_KMALLOC, call_site, ptr,
+			bytes_req, bytes_alloc, gfp_flags, -1);
+}
+
+static void kmemtrace_kmem_cache_alloc(unsigned long call_site,
+				       const void *ptr,
+				       size_t bytes_req,
+				       size_t bytes_alloc,
+				       gfp_t gfp_flags)
+{
+	kmemtrace_alloc(KMEMTRACE_TYPE_CACHE, call_site, ptr,
+			bytes_req, bytes_alloc, gfp_flags, -1);
+}
+
+static void kmemtrace_kmalloc_node(unsigned long call_site,
+				   const void *ptr,
+				   size_t bytes_req,
+				   size_t bytes_alloc,
+				   gfp_t gfp_flags,
+				   int node)
+{
+	kmemtrace_alloc(KMEMTRACE_TYPE_KMALLOC, call_site, ptr,
+			bytes_req, bytes_alloc, gfp_flags, node);
+}
+
+static void kmemtrace_kmem_cache_alloc_node(unsigned long call_site,
+					    const void *ptr,
+					    size_t bytes_req,
+					    size_t bytes_alloc,
+					    gfp_t gfp_flags,
+					    int node)
+{
+	kmemtrace_alloc(KMEMTRACE_TYPE_CACHE, call_site, ptr,
+			bytes_req, bytes_alloc, gfp_flags, node);
+}
+
+static void kmemtrace_kfree(unsigned long call_site, const void *ptr)
+{
+	kmemtrace_free(KMEMTRACE_TYPE_KMALLOC, call_site, ptr);
+}
+
+static void kmemtrace_kmem_cache_free(unsigned long call_site, const void *ptr)
+{
+	kmemtrace_free(KMEMTRACE_TYPE_CACHE, call_site, ptr);
+}
+
+static int kmemtrace_start_probes(void)
+{
+	int err;
+
+	err = register_trace_kmalloc(kmemtrace_kmalloc);
+	if (err)
+		return err;
+	err = register_trace_kmem_cache_alloc(kmemtrace_kmem_cache_alloc);
+	if (err)
+		return err;
+	err = register_trace_kmalloc_node(kmemtrace_kmalloc_node);
+	if (err)
+		return err;
+	err = register_trace_kmem_cache_alloc_node(kmemtrace_kmem_cache_alloc_node);
+	if (err)
+		return err;
+	err = register_trace_kfree(kmemtrace_kfree);
+	if (err)
+		return err;
+	err = register_trace_kmem_cache_free(kmemtrace_kmem_cache_free);
+
+	return err;
+}
+
+static void kmemtrace_stop_probes(void)
+{
+	unregister_trace_kmalloc(kmemtrace_kmalloc);
+	unregister_trace_kmem_cache_alloc(kmemtrace_kmem_cache_alloc);
+	unregister_trace_kmalloc_node(kmemtrace_kmalloc_node);
+	unregister_trace_kmem_cache_alloc_node(kmemtrace_kmem_cache_alloc_node);
+	unregister_trace_kfree(kmemtrace_kfree);
+	unregister_trace_kmem_cache_free(kmemtrace_kmem_cache_free);
+}
+
 static int kmem_trace_init(struct trace_array *tr)
 {
 	int cpu;
@@ -41,14 +185,14 @@ static int kmem_trace_init(struct trace_array *tr)
 	for_each_cpu_mask(cpu, cpu_possible_map)
 		tracing_reset(tr, cpu);
 
-	kmem_tracing_enabled = true;
+	kmemtrace_start_probes();
 
 	return 0;
 }
 
 static void kmem_trace_reset(struct trace_array *tr)
 {
-	kmem_tracing_enabled = false;
+	kmemtrace_stop_probes();
 }
 
 static void kmemtrace_headers(struct seq_file *s)
@@ -66,47 +210,84 @@ static void kmemtrace_headers(struct seq_file *s)
 }
 
 /*
- * The two following functions give the original output from kmemtrace,
- * or something close to....perhaps they need some missing things
+ * The following functions give the original output from kmemtrace,
+ * plus the origin CPU, since reordering occurs in-kernel now.
  */
+
+#define KMEMTRACE_USER_ALLOC	0
+#define KMEMTRACE_USER_FREE	1
+
+struct kmemtrace_user_event {
+	u8			event_id;
+	u8			type_id;
+	u16			event_size;
+	u32			cpu;
+	u64			timestamp;
+	unsigned long		call_site;
+	unsigned long		ptr;
+};
+
+struct kmemtrace_user_event_alloc {
+	size_t			bytes_req;
+	size_t			bytes_alloc;
+	unsigned		gfp_flags;
+	int			node;
+};
+
 static enum print_line_t
-kmemtrace_print_alloc_original(struct trace_iterator *iter,
-				struct kmemtrace_alloc_entry *entry)
+kmemtrace_print_alloc_user(struct trace_iterator *iter,
+			   struct kmemtrace_alloc_entry *entry)
 {
+	struct kmemtrace_user_event_alloc *ev_alloc;
 	struct trace_seq *s = &iter->seq;
-	int ret;
+	struct kmemtrace_user_event *ev;
+
+	ev = trace_seq_reserve(s, sizeof(*ev));
+	if (!ev)
+		return TRACE_TYPE_PARTIAL_LINE;
 
-	/* Taken from the old linux/kmemtrace.h */
-	ret = trace_seq_printf(s, "type_id %d call_site %lu ptr %lu "
-	  "bytes_req %lu bytes_alloc %lu gfp_flags %lu node %d\n",
-	   entry->type_id, entry->call_site, (unsigned long) entry->ptr,
-	   (unsigned long) entry->bytes_req, (unsigned long) entry->bytes_alloc,
-	   (unsigned long) entry->gfp_flags, entry->node);
+	ev->event_id		= KMEMTRACE_USER_ALLOC;
+	ev->type_id		= entry->type_id;
+	ev->event_size		= sizeof(*ev) + sizeof(*ev_alloc);
+	ev->cpu			= iter->cpu;
+	ev->timestamp		= iter->ts;
+	ev->call_site		= entry->call_site;
+	ev->ptr			= (unsigned long)entry->ptr;
 
-	if (!ret)
+	ev_alloc = trace_seq_reserve(s, sizeof(*ev_alloc));
+	if (!ev_alloc)
 		return TRACE_TYPE_PARTIAL_LINE;
 
+	ev_alloc->bytes_req	= entry->bytes_req;
+	ev_alloc->bytes_alloc	= entry->bytes_alloc;
+	ev_alloc->gfp_flags	= entry->gfp_flags;
+	ev_alloc->node		= entry->node;
+
 	return TRACE_TYPE_HANDLED;
 }
 
 static enum print_line_t
-kmemtrace_print_free_original(struct trace_iterator *iter,
-				struct kmemtrace_free_entry *entry)
+kmemtrace_print_free_user(struct trace_iterator *iter,
+			  struct kmemtrace_free_entry *entry)
 {
 	struct trace_seq *s = &iter->seq;
-	int ret;
+	struct kmemtrace_user_event *ev;
 
-	/* Taken from the old linux/kmemtrace.h */
-	ret = trace_seq_printf(s, "type_id %d call_site %lu ptr %lu\n",
-	   entry->type_id, entry->call_site, (unsigned long) entry->ptr);
-
-	if (!ret)
+	ev = trace_seq_reserve(s, sizeof(*ev));
+	if (!ev)
 		return TRACE_TYPE_PARTIAL_LINE;
 
+	ev->event_id		= KMEMTRACE_USER_FREE;
+	ev->type_id		= entry->type_id;
+	ev->event_size		= sizeof(*ev);
+	ev->cpu			= iter->cpu;
+	ev->timestamp		= iter->ts;
+	ev->call_site		= entry->call_site;
+	ev->ptr			= (unsigned long)entry->ptr;
+
 	return TRACE_TYPE_HANDLED;
 }
 
-
 /* The two other following provide a more minimalistic output */
 static enum print_line_t
 kmemtrace_print_alloc_compress(struct trace_iterator *iter,
@@ -178,7 +359,7 @@ kmemtrace_print_alloc_compress(struct trace_iterator *iter,
 
 static enum print_line_t
 kmemtrace_print_free_compress(struct trace_iterator *iter,
-				struct kmemtrace_free_entry *entry)
+			      struct kmemtrace_free_entry *entry)
 {
 	struct trace_seq *s = &iter->seq;
 	int ret;
@@ -239,20 +420,22 @@ static enum print_line_t kmemtrace_print_line(struct trace_iterator *iter)
 	switch (entry->type) {
 	case TRACE_KMEM_ALLOC: {
 		struct kmemtrace_alloc_entry *field;
+
 		trace_assign_type(field, entry);
 		if (kmem_tracer_flags.val & TRACE_KMEM_OPT_MINIMAL)
 			return kmemtrace_print_alloc_compress(iter, field);
 		else
-			return kmemtrace_print_alloc_original(iter, field);
+			return kmemtrace_print_alloc_user(iter, field);
 	}
 
 	case TRACE_KMEM_FREE: {
 		struct kmemtrace_free_entry *field;
+
 		trace_assign_type(field, entry);
 		if (kmem_tracer_flags.val & TRACE_KMEM_OPT_MINIMAL)
 			return kmemtrace_print_free_compress(iter, field);
 		else
-			return kmemtrace_print_free_original(iter, field);
+			return kmemtrace_print_free_user(iter, field);
 	}
 
 	default:
@@ -260,70 +443,13 @@ static enum print_line_t kmemtrace_print_line(struct trace_iterator *iter)
 	}
 }
 
-/* Trace allocations */
-void kmemtrace_mark_alloc_node(enum kmemtrace_type_id type_id,
-			     unsigned long call_site,
-			     const void *ptr,
-			     size_t bytes_req,
-			     size_t bytes_alloc,
-			     gfp_t gfp_flags,
-			     int node)
-{
-	struct ring_buffer_event *event;
-	struct kmemtrace_alloc_entry *entry;
-	struct trace_array *tr = kmemtrace_array;
-
-	if (!kmem_tracing_enabled)
-		return;
-
-	event = trace_buffer_lock_reserve(tr, TRACE_KMEM_ALLOC,
-					  sizeof(*entry), 0, 0);
-	if (!event)
-		return;
-	entry	= ring_buffer_event_data(event);
-
-	entry->call_site = call_site;
-	entry->ptr = ptr;
-	entry->bytes_req = bytes_req;
-	entry->bytes_alloc = bytes_alloc;
-	entry->gfp_flags = gfp_flags;
-	entry->node	=	node;
-
-	trace_buffer_unlock_commit(tr, event, 0, 0);
-}
-EXPORT_SYMBOL(kmemtrace_mark_alloc_node);
-
-void kmemtrace_mark_free(enum kmemtrace_type_id type_id,
-		       unsigned long call_site,
-		       const void *ptr)
-{
-	struct ring_buffer_event *event;
-	struct kmemtrace_free_entry *entry;
-	struct trace_array *tr = kmemtrace_array;
-
-	if (!kmem_tracing_enabled)
-		return;
-
-	event = trace_buffer_lock_reserve(tr, TRACE_KMEM_FREE,
-					  sizeof(*entry), 0, 0);
-	if (!event)
-		return;
-	entry	= ring_buffer_event_data(event);
-	entry->type_id	= type_id;
-	entry->call_site = call_site;
-	entry->ptr = ptr;
-
-	trace_buffer_unlock_commit(tr, event, 0, 0);
-}
-EXPORT_SYMBOL(kmemtrace_mark_free);
-
 static struct tracer kmem_tracer __read_mostly = {
-	.name		= "kmemtrace",
-	.init		= kmem_trace_init,
-	.reset		= kmem_trace_reset,
-	.print_line	= kmemtrace_print_line,
-	.print_header = kmemtrace_headers,
-	.flags		= &kmem_tracer_flags
+	.name			= "kmemtrace",
+	.init			= kmem_trace_init,
+	.reset			= kmem_trace_reset,
+	.print_line		= kmemtrace_print_line,
+	.print_header		= kmemtrace_headers,
+	.flags			= &kmem_tracer_flags
 };
 
 void kmemtrace_init(void)
@@ -335,5 +461,4 @@ static int __init init_kmem_tracer(void)
 {
 	return register_tracer(&kmem_tracer);
 }
-
 device_initcall(init_kmem_tracer);
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 58128ad2fde..960cbf44c84 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -180,48 +180,74 @@ EXPORT_SYMBOL_GPL(tracing_is_on);
 
 #include "trace.h"
 
-/* Up this if you want to test the TIME_EXTENTS and normalization */
-#define DEBUG_SHIFT 0
+#define RB_EVNT_HDR_SIZE (offsetof(struct ring_buffer_event, array))
+#define RB_ALIGNMENT		4U
+#define RB_MAX_SMALL_DATA	28
 
-u64 ring_buffer_time_stamp(int cpu)
+enum {
+	RB_LEN_TIME_EXTEND = 8,
+	RB_LEN_TIME_STAMP = 16,
+};
+
+static inline int rb_null_event(struct ring_buffer_event *event)
 {
-	u64 time;
+	return event->type == RINGBUF_TYPE_PADDING && event->time_delta == 0;
+}
 
-	preempt_disable_notrace();
-	/* shift to debug/test normalization and TIME_EXTENTS */
-	time = trace_clock_local() << DEBUG_SHIFT;
-	preempt_enable_no_resched_notrace();
+static inline int rb_discarded_event(struct ring_buffer_event *event)
+{
+	return event->type == RINGBUF_TYPE_PADDING && event->time_delta;
+}
 
-	return time;
+static void rb_event_set_padding(struct ring_buffer_event *event)
+{
+	event->type = RINGBUF_TYPE_PADDING;
+	event->time_delta = 0;
 }
-EXPORT_SYMBOL_GPL(ring_buffer_time_stamp);
 
-void ring_buffer_normalize_time_stamp(int cpu, u64 *ts)
+/**
+ * ring_buffer_event_discard - discard an event in the ring buffer
+ * @buffer: the ring buffer
+ * @event: the event to discard
+ *
+ * Sometimes a event that is in the ring buffer needs to be ignored.
+ * This function lets the user discard an event in the ring buffer
+ * and then that event will not be read later.
+ *
+ * Note, it is up to the user to be careful with this, and protect
+ * against races. If the user discards an event that has been consumed
+ * it is possible that it could corrupt the ring buffer.
+ */
+void ring_buffer_event_discard(struct ring_buffer_event *event)
 {
-	/* Just stupid testing the normalize function and deltas */
-	*ts >>= DEBUG_SHIFT;
+	event->type = RINGBUF_TYPE_PADDING;
+	/* time delta must be non zero */
+	if (!event->time_delta)
+		event->time_delta = 1;
 }
-EXPORT_SYMBOL_GPL(ring_buffer_normalize_time_stamp);
 
-#define RB_EVNT_HDR_SIZE (offsetof(struct ring_buffer_event, array))
-#define RB_ALIGNMENT		4U
-#define RB_MAX_SMALL_DATA	28
+static unsigned
+rb_event_data_length(struct ring_buffer_event *event)
+{
+	unsigned length;
 
-enum {
-	RB_LEN_TIME_EXTEND = 8,
-	RB_LEN_TIME_STAMP = 16,
-};
+	if (event->len)
+		length = event->len * RB_ALIGNMENT;
+	else
+		length = event->array[0];
+	return length + RB_EVNT_HDR_SIZE;
+}
 
 /* inline for ring buffer fast paths */
 static unsigned
 rb_event_length(struct ring_buffer_event *event)
 {
-	unsigned length;
-
 	switch (event->type) {
 	case RINGBUF_TYPE_PADDING:
-		/* undefined */
-		return -1;
+		if (rb_null_event(event))
+			/* undefined */
+			return -1;
+		return rb_event_data_length(event);
 
 	case RINGBUF_TYPE_TIME_EXTEND:
 		return RB_LEN_TIME_EXTEND;
@@ -230,11 +256,7 @@ rb_event_length(struct ring_buffer_event *event)
 		return RB_LEN_TIME_STAMP;
 
 	case RINGBUF_TYPE_DATA:
-		if (event->len)
-			length = event->len * RB_ALIGNMENT;
-		else
-			length = event->array[0];
-		return length + RB_EVNT_HDR_SIZE;
+		return rb_event_data_length(event);
 	default:
 		BUG();
 	}
@@ -374,6 +396,7 @@ struct ring_buffer {
 #ifdef CONFIG_HOTPLUG_CPU
 	struct notifier_block		cpu_notify;
 #endif
+	u64				(*clock)(void);
 };
 
 struct ring_buffer_iter {
@@ -394,6 +417,30 @@ struct ring_buffer_iter {
 		_____ret;					\
 	})
 
+/* Up this if you want to test the TIME_EXTENTS and normalization */
+#define DEBUG_SHIFT 0
+
+u64 ring_buffer_time_stamp(struct ring_buffer *buffer, int cpu)
+{
+	u64 time;
+
+	preempt_disable_notrace();
+	/* shift to debug/test normalization and TIME_EXTENTS */
+	time = buffer->clock() << DEBUG_SHIFT;
+	preempt_enable_no_resched_notrace();
+
+	return time;
+}
+EXPORT_SYMBOL_GPL(ring_buffer_time_stamp);
+
+void ring_buffer_normalize_time_stamp(struct ring_buffer *buffer,
+				      int cpu, u64 *ts)
+{
+	/* Just stupid testing the normalize function and deltas */
+	*ts >>= DEBUG_SHIFT;
+}
+EXPORT_SYMBOL_GPL(ring_buffer_normalize_time_stamp);
+
 /**
  * check_pages - integrity check of buffer pages
  * @cpu_buffer: CPU buffer with pages to test
@@ -516,7 +563,6 @@ static void rb_free_cpu_buffer(struct ring_buffer_per_cpu *cpu_buffer)
 	struct list_head *head = &cpu_buffer->pages;
 	struct buffer_page *bpage, *tmp;
 
-	list_del_init(&cpu_buffer->reader_page->list);
 	free_buffer_page(cpu_buffer->reader_page);
 
 	list_for_each_entry_safe(bpage, tmp, head, list) {
@@ -533,8 +579,8 @@ static void rb_free_cpu_buffer(struct ring_buffer_per_cpu *cpu_buffer)
 extern int ring_buffer_page_too_big(void);
 
 #ifdef CONFIG_HOTPLUG_CPU
-static int __cpuinit rb_cpu_notify(struct notifier_block *self,
-				   unsigned long action, void *hcpu);
+static int rb_cpu_notify(struct notifier_block *self,
+			 unsigned long action, void *hcpu);
 #endif
 
 /**
@@ -569,13 +615,23 @@ struct ring_buffer *ring_buffer_alloc(unsigned long size, unsigned flags)
 
 	buffer->pages = DIV_ROUND_UP(size, BUF_PAGE_SIZE);
 	buffer->flags = flags;
+	buffer->clock = trace_clock_local;
 
 	/* need at least two pages */
 	if (buffer->pages == 1)
 		buffer->pages++;
 
+	/*
+	 * In case of non-hotplug cpu, if the ring-buffer is allocated
+	 * in early initcall, it will not be notified of secondary cpus.
+	 * In that off case, we need to allocate for all possible cpus.
+	 */
+#ifdef CONFIG_HOTPLUG_CPU
 	get_online_cpus();
 	cpumask_copy(buffer->cpumask, cpu_online_mask);
+#else
+	cpumask_copy(buffer->cpumask, cpu_possible_mask);
+#endif
 	buffer->cpus = nr_cpu_ids;
 
 	bsize = sizeof(void *) * nr_cpu_ids;
@@ -645,6 +701,12 @@ ring_buffer_free(struct ring_buffer *buffer)
 }
 EXPORT_SYMBOL_GPL(ring_buffer_free);
 
+void ring_buffer_set_clock(struct ring_buffer *buffer,
+			   u64 (*clock)(void))
+{
+	buffer->clock = clock;
+}
+
 static void rb_reset_cpu(struct ring_buffer_per_cpu *cpu_buffer);
 
 static void
@@ -827,11 +889,6 @@ int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size)
 }
 EXPORT_SYMBOL_GPL(ring_buffer_resize);
 
-static inline int rb_null_event(struct ring_buffer_event *event)
-{
-	return event->type == RINGBUF_TYPE_PADDING;
-}
-
 static inline void *
 __rb_data_page_index(struct buffer_data_page *bpage, unsigned index)
 {
@@ -1191,7 +1248,7 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer,
 			cpu_buffer->tail_page = next_page;
 
 			/* reread the time stamp */
-			*ts = ring_buffer_time_stamp(cpu_buffer->cpu);
+			*ts = ring_buffer_time_stamp(buffer, cpu_buffer->cpu);
 			cpu_buffer->tail_page->page->time_stamp = *ts;
 		}
 
@@ -1201,7 +1258,7 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer,
 		if (tail < BUF_PAGE_SIZE) {
 			/* Mark the rest of the page with padding */
 			event = __rb_page_index(tail_page, tail);
-			event->type = RINGBUF_TYPE_PADDING;
+			rb_event_set_padding(event);
 		}
 
 		if (tail <= BUF_PAGE_SIZE)
@@ -1334,7 +1391,7 @@ rb_reserve_next_event(struct ring_buffer_per_cpu *cpu_buffer,
 	if (RB_WARN_ON(cpu_buffer, ++nr_loops > 1000))
 		return NULL;
 
-	ts = ring_buffer_time_stamp(cpu_buffer->cpu);
+	ts = ring_buffer_time_stamp(cpu_buffer->buffer, cpu_buffer->cpu);
 
 	/*
 	 * Only the first commit can update the timestamp.
@@ -1951,7 +2008,7 @@ static void rb_advance_reader(struct ring_buffer_per_cpu *cpu_buffer)
 
 	event = rb_reader_event(cpu_buffer);
 
-	if (event->type == RINGBUF_TYPE_DATA)
+	if (event->type == RINGBUF_TYPE_DATA || rb_discarded_event(event))
 		cpu_buffer->entries--;
 
 	rb_update_read_stamp(cpu_buffer, event);
@@ -2034,9 +2091,18 @@ rb_buffer_peek(struct ring_buffer *buffer, int cpu, u64 *ts)
 
 	switch (event->type) {
 	case RINGBUF_TYPE_PADDING:
-		RB_WARN_ON(cpu_buffer, 1);
+		if (rb_null_event(event))
+			RB_WARN_ON(cpu_buffer, 1);
+		/*
+		 * Because the writer could be discarding every
+		 * event it creates (which would probably be bad)
+		 * if we were to go back to "again" then we may never
+		 * catch up, and will trigger the warn on, or lock
+		 * the box. Return the padding, and we will release
+		 * the current locks, and try again.
+		 */
 		rb_advance_reader(cpu_buffer);
-		return NULL;
+		return event;
 
 	case RINGBUF_TYPE_TIME_EXTEND:
 		/* Internal data, OK to advance */
@@ -2051,7 +2117,8 @@ rb_buffer_peek(struct ring_buffer *buffer, int cpu, u64 *ts)
 	case RINGBUF_TYPE_DATA:
 		if (ts) {
 			*ts = cpu_buffer->read_stamp + event->time_delta;
-			ring_buffer_normalize_time_stamp(cpu_buffer->cpu, ts);
+			ring_buffer_normalize_time_stamp(buffer,
+							 cpu_buffer->cpu, ts);
 		}
 		return event;
 
@@ -2096,8 +2163,12 @@ rb_iter_peek(struct ring_buffer_iter *iter, u64 *ts)
 
 	switch (event->type) {
 	case RINGBUF_TYPE_PADDING:
-		rb_inc_iter(iter);
-		goto again;
+		if (rb_null_event(event)) {
+			rb_inc_iter(iter);
+			goto again;
+		}
+		rb_advance_iter(iter);
+		return event;
 
 	case RINGBUF_TYPE_TIME_EXTEND:
 		/* Internal data, OK to advance */
@@ -2112,7 +2183,8 @@ rb_iter_peek(struct ring_buffer_iter *iter, u64 *ts)
 	case RINGBUF_TYPE_DATA:
 		if (ts) {
 			*ts = iter->read_stamp + event->time_delta;
-			ring_buffer_normalize_time_stamp(cpu_buffer->cpu, ts);
+			ring_buffer_normalize_time_stamp(buffer,
+							 cpu_buffer->cpu, ts);
 		}
 		return event;
 
@@ -2143,10 +2215,16 @@ ring_buffer_peek(struct ring_buffer *buffer, int cpu, u64 *ts)
 	if (!cpumask_test_cpu(cpu, buffer->cpumask))
 		return NULL;
 
+ again:
 	spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
 	event = rb_buffer_peek(buffer, cpu, ts);
 	spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
 
+	if (event && event->type == RINGBUF_TYPE_PADDING) {
+		cpu_relax();
+		goto again;
+	}
+
 	return event;
 }
 
@@ -2165,10 +2243,16 @@ ring_buffer_iter_peek(struct ring_buffer_iter *iter, u64 *ts)
 	struct ring_buffer_event *event;
 	unsigned long flags;
 
+ again:
 	spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
 	event = rb_iter_peek(iter, ts);
 	spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
 
+	if (event && event->type == RINGBUF_TYPE_PADDING) {
+		cpu_relax();
+		goto again;
+	}
+
 	return event;
 }
 
@@ -2187,6 +2271,7 @@ ring_buffer_consume(struct ring_buffer *buffer, int cpu, u64 *ts)
 	struct ring_buffer_event *event = NULL;
 	unsigned long flags;
 
+ again:
 	/* might be called in atomic */
 	preempt_disable();
 
@@ -2208,6 +2293,11 @@ ring_buffer_consume(struct ring_buffer *buffer, int cpu, u64 *ts)
  out:
 	preempt_enable();
 
+	if (event && event->type == RINGBUF_TYPE_PADDING) {
+		cpu_relax();
+		goto again;
+	}
+
 	return event;
 }
 EXPORT_SYMBOL_GPL(ring_buffer_consume);
@@ -2286,6 +2376,7 @@ ring_buffer_read(struct ring_buffer_iter *iter, u64 *ts)
 	struct ring_buffer_per_cpu *cpu_buffer = iter->cpu_buffer;
 	unsigned long flags;
 
+ again:
 	spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
 	event = rb_iter_peek(iter, ts);
 	if (!event)
@@ -2295,6 +2386,11 @@ ring_buffer_read(struct ring_buffer_iter *iter, u64 *ts)
  out:
 	spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
 
+	if (event && event->type == RINGBUF_TYPE_PADDING) {
+		cpu_relax();
+		goto again;
+	}
+
 	return event;
 }
 EXPORT_SYMBOL_GPL(ring_buffer_read);
@@ -2764,8 +2860,8 @@ static __init int rb_init_debugfs(void)
 fs_initcall(rb_init_debugfs);
 
 #ifdef CONFIG_HOTPLUG_CPU
-static int __cpuinit rb_cpu_notify(struct notifier_block *self,
-				   unsigned long action, void *hcpu)
+static int rb_cpu_notify(struct notifier_block *self,
+			 unsigned long action, void *hcpu)
 {
 	struct ring_buffer *buffer =
 		container_of(self, struct ring_buffer, cpu_notify);
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index efe3202c020..a0174a40c56 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -155,13 +155,6 @@ ns2usecs(cycle_t nsec)
 	return nsec;
 }
 
-cycle_t ftrace_now(int cpu)
-{
-	u64 ts = ring_buffer_time_stamp(cpu);
-	ring_buffer_normalize_time_stamp(cpu, &ts);
-	return ts;
-}
-
 /*
  * The global_trace is the descriptor that holds the tracing
  * buffers for the live tracing. For each CPU, it contains
@@ -178,6 +171,20 @@ static struct trace_array	global_trace;
 
 static DEFINE_PER_CPU(struct trace_array_cpu, global_trace_cpu);
 
+cycle_t ftrace_now(int cpu)
+{
+	u64 ts;
+
+	/* Early boot up does not have a buffer yet */
+	if (!global_trace.buffer)
+		return trace_clock_local();
+
+	ts = ring_buffer_time_stamp(global_trace.buffer, cpu);
+	ring_buffer_normalize_time_stamp(global_trace.buffer, cpu, &ts);
+
+	return ts;
+}
+
 /*
  * The max_tr is used to snapshot the global_trace when a maximum
  * latency is reached. Some tracers will use this to store a maximum
@@ -248,7 +255,7 @@ static DECLARE_WAIT_QUEUE_HEAD(trace_wait);
 
 /* trace_flags holds trace_options default values */
 unsigned long trace_flags = TRACE_ITER_PRINT_PARENT | TRACE_ITER_PRINTK |
-	TRACE_ITER_ANNOTATE | TRACE_ITER_CONTEXT_INFO;
+	TRACE_ITER_ANNOTATE | TRACE_ITER_CONTEXT_INFO | TRACE_ITER_SLEEP_TIME;
 
 /**
  * trace_wake_up - wake up tasks waiting for trace input
@@ -308,6 +315,8 @@ static const char *trace_options[] = {
 	"printk-msg-only",
 	"context-info",
 	"latency-format",
+	"global-clock",
+	"sleep-time",
 	NULL
 };
 
@@ -374,7 +383,7 @@ ssize_t trace_seq_to_user(struct trace_seq *s, char __user *ubuf, size_t cnt)
 	return cnt;
 }
 
-ssize_t trace_seq_to_buffer(struct trace_seq *s, void *buf, size_t cnt)
+static ssize_t trace_seq_to_buffer(struct trace_seq *s, void *buf, size_t cnt)
 {
 	int len;
 	void *ret;
@@ -633,6 +642,7 @@ void tracing_reset_online_cpus(struct trace_array *tr)
 }
 
 #define SAVED_CMDLINES 128
+#define NO_CMDLINE_MAP UINT_MAX
 static unsigned map_pid_to_cmdline[PID_MAX_DEFAULT+1];
 static unsigned map_cmdline_to_pid[SAVED_CMDLINES];
 static char saved_cmdlines[SAVED_CMDLINES][TASK_COMM_LEN];
@@ -644,8 +654,8 @@ static atomic_t trace_record_cmdline_disabled __read_mostly;
 
 static void trace_init_cmdlines(void)
 {
-	memset(&map_pid_to_cmdline, -1, sizeof(map_pid_to_cmdline));
-	memset(&map_cmdline_to_pid, -1, sizeof(map_cmdline_to_pid));
+	memset(&map_pid_to_cmdline, NO_CMDLINE_MAP, sizeof(map_pid_to_cmdline));
+	memset(&map_cmdline_to_pid, NO_CMDLINE_MAP, sizeof(map_cmdline_to_pid));
 	cmdline_idx = 0;
 }
 
@@ -737,8 +747,7 @@ void trace_stop_cmdline_recording(void);
 
 static void trace_save_cmdline(struct task_struct *tsk)
 {
-	unsigned map;
-	unsigned idx;
+	unsigned pid, idx;
 
 	if (!tsk->pid || unlikely(tsk->pid > PID_MAX_DEFAULT))
 		return;
@@ -753,13 +762,20 @@ static void trace_save_cmdline(struct task_struct *tsk)
 		return;
 
 	idx = map_pid_to_cmdline[tsk->pid];
-	if (idx >= SAVED_CMDLINES) {
+	if (idx == NO_CMDLINE_MAP) {
 		idx = (cmdline_idx + 1) % SAVED_CMDLINES;
 
-		map = map_cmdline_to_pid[idx];
-		if (map <= PID_MAX_DEFAULT)
-			map_pid_to_cmdline[map] = (unsigned)-1;
+		/*
+		 * Check whether the cmdline buffer at idx has a pid
+		 * mapped. We are going to overwrite that entry so we
+		 * need to clear the map_pid_to_cmdline. Otherwise we
+		 * would read the new comm for the old pid.
+		 */
+		pid = map_cmdline_to_pid[idx];
+		if (pid != NO_CMDLINE_MAP)
+			map_pid_to_cmdline[pid] = NO_CMDLINE_MAP;
 
+		map_cmdline_to_pid[idx] = tsk->pid;
 		map_pid_to_cmdline[tsk->pid] = idx;
 
 		cmdline_idx = idx;
@@ -770,30 +786,34 @@ static void trace_save_cmdline(struct task_struct *tsk)
 	__raw_spin_unlock(&trace_cmdline_lock);
 }
 
-char *trace_find_cmdline(int pid)
+void trace_find_cmdline(int pid, char comm[])
 {
-	char *cmdline = "<...>";
 	unsigned map;
 
-	if (!pid)
-		return "<idle>";
+	if (!pid) {
+		strcpy(comm, "<idle>");
+		return;
+	}
 
-	if (pid > PID_MAX_DEFAULT)
-		goto out;
+	if (pid > PID_MAX_DEFAULT) {
+		strcpy(comm, "<...>");
+		return;
+	}
 
+	__raw_spin_lock(&trace_cmdline_lock);
 	map = map_pid_to_cmdline[pid];
-	if (map >= SAVED_CMDLINES)
-		goto out;
-
-	cmdline = saved_cmdlines[map];
+	if (map != NO_CMDLINE_MAP)
+		strcpy(comm, saved_cmdlines[map]);
+	else
+		strcpy(comm, "<...>");
 
- out:
-	return cmdline;
+	__raw_spin_unlock(&trace_cmdline_lock);
 }
 
 void tracing_record_cmdline(struct task_struct *tsk)
 {
-	if (atomic_read(&trace_record_cmdline_disabled))
+	if (atomic_read(&trace_record_cmdline_disabled) || !tracer_enabled ||
+	    !tracing_is_on())
 		return;
 
 	trace_save_cmdline(tsk);
@@ -841,15 +861,25 @@ static void ftrace_trace_stack(struct trace_array *tr,
 static void ftrace_trace_userstack(struct trace_array *tr,
 				   unsigned long flags, int pc);
 
-void trace_buffer_unlock_commit(struct trace_array *tr,
-				struct ring_buffer_event *event,
-				unsigned long flags, int pc)
+static inline void __trace_buffer_unlock_commit(struct trace_array *tr,
+					struct ring_buffer_event *event,
+					unsigned long flags, int pc,
+					int wake)
 {
 	ring_buffer_unlock_commit(tr->buffer, event);
 
 	ftrace_trace_stack(tr, flags, 6, pc);
 	ftrace_trace_userstack(tr, flags, pc);
-	trace_wake_up();
+
+	if (wake)
+		trace_wake_up();
+}
+
+void trace_buffer_unlock_commit(struct trace_array *tr,
+					struct ring_buffer_event *event,
+					unsigned long flags, int pc)
+{
+	__trace_buffer_unlock_commit(tr, event, flags, pc, 1);
 }
 
 struct ring_buffer_event *
@@ -863,7 +893,13 @@ trace_current_buffer_lock_reserve(unsigned char type, unsigned long len,
 void trace_current_buffer_unlock_commit(struct ring_buffer_event *event,
 					unsigned long flags, int pc)
 {
-	return trace_buffer_unlock_commit(&global_trace, event, flags, pc);
+	return __trace_buffer_unlock_commit(&global_trace, event, flags, pc, 1);
+}
+
+void trace_nowake_buffer_unlock_commit(struct ring_buffer_event *event,
+					unsigned long flags, int pc)
+{
+	return __trace_buffer_unlock_commit(&global_trace, event, flags, pc, 0);
 }
 
 void
@@ -889,7 +925,7 @@ trace_function(struct trace_array *tr,
 }
 
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
-static void __trace_graph_entry(struct trace_array *tr,
+static int __trace_graph_entry(struct trace_array *tr,
 				struct ftrace_graph_ent *trace,
 				unsigned long flags,
 				int pc)
@@ -898,15 +934,17 @@ static void __trace_graph_entry(struct trace_array *tr,
 	struct ftrace_graph_ent_entry *entry;
 
 	if (unlikely(local_read(&__get_cpu_var(ftrace_cpu_disabled))))
-		return;
+		return 0;
 
 	event = trace_buffer_lock_reserve(&global_trace, TRACE_GRAPH_ENT,
 					  sizeof(*entry), flags, pc);
 	if (!event)
-		return;
+		return 0;
 	entry	= ring_buffer_event_data(event);
 	entry->graph_ent			= *trace;
 	ring_buffer_unlock_commit(global_trace.buffer, event);
+
+	return 1;
 }
 
 static void __trace_graph_return(struct trace_array *tr,
@@ -1127,6 +1165,7 @@ int trace_graph_entry(struct ftrace_graph_ent *trace)
 	struct trace_array_cpu *data;
 	unsigned long flags;
 	long disabled;
+	int ret;
 	int cpu;
 	int pc;
 
@@ -1142,15 +1181,18 @@ int trace_graph_entry(struct ftrace_graph_ent *trace)
 	disabled = atomic_inc_return(&data->disabled);
 	if (likely(disabled == 1)) {
 		pc = preempt_count();
-		__trace_graph_entry(tr, trace, flags, pc);
+		ret = __trace_graph_entry(tr, trace, flags, pc);
+	} else {
+		ret = 0;
 	}
 	/* Only do the atomic if it is not already set */
 	if (!test_tsk_trace_graph(current))
 		set_tsk_trace_graph(current);
+
 	atomic_dec(&data->disabled);
 	local_irq_restore(flags);
 
-	return 1;
+	return ret;
 }
 
 void trace_graph_return(struct ftrace_graph_ret *trace)
@@ -1182,7 +1224,7 @@ void trace_graph_return(struct ftrace_graph_ret *trace)
  * trace_vbprintk - write binary msg to tracing buffer
  *
  */
-int trace_vbprintk(unsigned long ip, int depth, const char *fmt, va_list args)
+int trace_vbprintk(unsigned long ip, const char *fmt, va_list args)
 {
 	static raw_spinlock_t trace_buf_lock =
 		(raw_spinlock_t)__RAW_SPIN_LOCK_UNLOCKED;
@@ -1224,7 +1266,6 @@ int trace_vbprintk(unsigned long ip, int depth, const char *fmt, va_list args)
 		goto out_unlock;
 	entry = ring_buffer_event_data(event);
 	entry->ip			= ip;
-	entry->depth			= depth;
 	entry->fmt			= fmt;
 
 	memcpy(entry->buf, trace_buf, sizeof(u32) * len);
@@ -1242,7 +1283,7 @@ out:
 }
 EXPORT_SYMBOL_GPL(trace_vbprintk);
 
-int trace_vprintk(unsigned long ip, int depth, const char *fmt, va_list args)
+int trace_vprintk(unsigned long ip, const char *fmt, va_list args)
 {
 	static raw_spinlock_t trace_buf_lock = __RAW_SPIN_LOCK_UNLOCKED;
 	static char trace_buf[TRACE_BUF_SIZE];
@@ -1279,7 +1320,6 @@ int trace_vprintk(unsigned long ip, int depth, const char *fmt, va_list args)
 		goto out_unlock;
 	entry = ring_buffer_event_data(event);
 	entry->ip			= ip;
-	entry->depth			= depth;
 
 	memcpy(&entry->buf, trace_buf, len);
 	entry->buf[len] = 0;
@@ -1682,38 +1722,6 @@ static enum print_line_t print_hex_fmt(struct trace_iterator *iter)
 	return TRACE_TYPE_HANDLED;
 }
 
-static enum print_line_t print_bprintk_msg_only(struct trace_iterator *iter)
-{
-	struct trace_seq *s = &iter->seq;
-	struct trace_entry *entry = iter->ent;
-	struct bprint_entry *field;
-	int ret;
-
-	trace_assign_type(field, entry);
-
-	ret = trace_seq_bprintf(s, field->fmt, field->buf);
-	if (!ret)
-		return TRACE_TYPE_PARTIAL_LINE;
-
-	return TRACE_TYPE_HANDLED;
-}
-
-static enum print_line_t print_printk_msg_only(struct trace_iterator *iter)
-{
-	struct trace_seq *s = &iter->seq;
-	struct trace_entry *entry = iter->ent;
-	struct print_entry *field;
-	int ret;
-
-	trace_assign_type(field, entry);
-
-	ret = trace_seq_printf(s, "%s", field->buf);
-	if (!ret)
-		return TRACE_TYPE_PARTIAL_LINE;
-
-	return TRACE_TYPE_HANDLED;
-}
-
 static enum print_line_t print_bin_fmt(struct trace_iterator *iter)
 {
 	struct trace_seq *s = &iter->seq;
@@ -1775,12 +1783,12 @@ static enum print_line_t print_trace_line(struct trace_iterator *iter)
 	if (iter->ent->type == TRACE_BPRINT &&
 			trace_flags & TRACE_ITER_PRINTK &&
 			trace_flags & TRACE_ITER_PRINTK_MSGONLY)
-		return print_bprintk_msg_only(iter);
+		return trace_print_bprintk_msg_only(iter);
 
 	if (iter->ent->type == TRACE_PRINT &&
 			trace_flags & TRACE_ITER_PRINTK &&
 			trace_flags & TRACE_ITER_PRINTK_MSGONLY)
-		return print_printk_msg_only(iter);
+		return trace_print_printk_msg_only(iter);
 
 	if (trace_flags & TRACE_ITER_BIN)
 		return print_bin_fmt(iter);
@@ -1929,9 +1937,14 @@ int tracing_open_generic(struct inode *inode, struct file *filp)
 static int tracing_release(struct inode *inode, struct file *file)
 {
 	struct seq_file *m = (struct seq_file *)file->private_data;
-	struct trace_iterator *iter = m->private;
+	struct trace_iterator *iter;
 	int cpu;
 
+	if (!(file->f_mode & FMODE_READ))
+		return 0;
+
+	iter = m->private;
+
 	mutex_lock(&trace_types_lock);
 	for_each_tracing_cpu(cpu) {
 		if (iter->buffer_iter[cpu])
@@ -1957,12 +1970,24 @@ static int tracing_open(struct inode *inode, struct file *file)
 	struct trace_iterator *iter;
 	int ret = 0;
 
-	iter = __tracing_open(inode, file);
-	if (IS_ERR(iter))
-		ret = PTR_ERR(iter);
-	else if (trace_flags & TRACE_ITER_LATENCY_FMT)
-		iter->iter_flags |= TRACE_FILE_LAT_FMT;
+	/* If this file was open for write, then erase contents */
+	if ((file->f_mode & FMODE_WRITE) &&
+	    !(file->f_flags & O_APPEND)) {
+		long cpu = (long) inode->i_private;
 
+		if (cpu == TRACE_PIPE_ALL_CPU)
+			tracing_reset_online_cpus(&global_trace);
+		else
+			tracing_reset(&global_trace, cpu);
+	}
+
+	if (file->f_mode & FMODE_READ) {
+		iter = __tracing_open(inode, file);
+		if (IS_ERR(iter))
+			ret = PTR_ERR(iter);
+		else if (trace_flags & TRACE_ITER_LATENCY_FMT)
+			iter->iter_flags |= TRACE_FILE_LAT_FMT;
+	}
 	return ret;
 }
 
@@ -2037,9 +2062,17 @@ static int show_traces_open(struct inode *inode, struct file *file)
 	return ret;
 }
 
+static ssize_t
+tracing_write_stub(struct file *filp, const char __user *ubuf,
+		   size_t count, loff_t *ppos)
+{
+	return count;
+}
+
 static const struct file_operations tracing_fops = {
 	.open		= tracing_open,
 	.read		= seq_read,
+	.write		= tracing_write_stub,
 	.llseek		= seq_lseek,
 	.release	= tracing_release,
 };
@@ -2240,6 +2273,34 @@ static int set_tracer_option(struct tracer *trace, char *cmp, int neg)
 	return 0;
 }
 
+static void set_tracer_flags(unsigned int mask, int enabled)
+{
+	/* do nothing if flag is already set */
+	if (!!(trace_flags & mask) == !!enabled)
+		return;
+
+	if (enabled)
+		trace_flags |= mask;
+	else
+		trace_flags &= ~mask;
+
+	if (mask == TRACE_ITER_GLOBAL_CLK) {
+		u64 (*func)(void);
+
+		if (enabled)
+			func = trace_clock_global;
+		else
+			func = trace_clock_local;
+
+		mutex_lock(&trace_types_lock);
+		ring_buffer_set_clock(global_trace.buffer, func);
+
+		if (max_tr.buffer)
+			ring_buffer_set_clock(max_tr.buffer, func);
+		mutex_unlock(&trace_types_lock);
+	}
+}
+
 static ssize_t
 tracing_trace_options_write(struct file *filp, const char __user *ubuf,
 			size_t cnt, loff_t *ppos)
@@ -2267,10 +2328,7 @@ tracing_trace_options_write(struct file *filp, const char __user *ubuf,
 		int len = strlen(trace_options[i]);
 
 		if (strncmp(cmp, trace_options[i], len) == 0) {
-			if (neg)
-				trace_flags &= ~(1 << i);
-			else
-				trace_flags |= (1 << i);
+			set_tracer_flags(1 << i, !neg);
 			break;
 		}
 	}
@@ -2494,7 +2552,7 @@ static int tracing_set_tracer(const char *buf)
 	if (!ring_buffer_expanded) {
 		ret = tracing_resize_ring_buffer(trace_buf_size);
 		if (ret < 0)
-			return ret;
+			goto out;
 		ret = 0;
 	}
 
@@ -3110,7 +3168,7 @@ static int mark_printk(const char *fmt, ...)
 	int ret;
 	va_list args;
 	va_start(args, fmt);
-	ret = trace_vprintk(0, -1, fmt, args);
+	ret = trace_vprintk(0, fmt, args);
 	va_end(args);
 	return ret;
 }
@@ -3478,6 +3536,9 @@ struct dentry *tracing_init_dentry(void)
 	if (d_tracer)
 		return d_tracer;
 
+	if (!debugfs_initialized())
+		return NULL;
+
 	d_tracer = debugfs_create_dir("tracing", NULL);
 
 	if (!d_tracer && !once) {
@@ -3539,7 +3600,7 @@ static void tracing_init_debugfs_percpu(long cpu)
 		pr_warning("Could not create debugfs 'trace_pipe' entry\n");
 
 	/* per cpu trace */
-	entry = debugfs_create_file("trace", 0444, d_cpu,
+	entry = debugfs_create_file("trace", 0644, d_cpu,
 				(void *) cpu, &tracing_fops);
 	if (!entry)
 		pr_warning("Could not create debugfs 'trace' entry\n");
@@ -3853,7 +3914,7 @@ static __init int tracer_init_debugfs(void)
 	if (!entry)
 		pr_warning("Could not create debugfs 'tracing_cpumask' entry\n");
 
-	entry = debugfs_create_file("trace", 0444, d_tracer,
+	entry = debugfs_create_file("trace", 0644, d_tracer,
 				 (void *) TRACE_PIPE_ALL_CPU, &tracing_fops);
 	if (!entry)
 		pr_warning("Could not create debugfs 'trace' entry\n");
@@ -3983,11 +4044,12 @@ trace_printk_seq(struct trace_seq *s)
 	trace_seq_init(s);
 }
 
-void ftrace_dump(void)
+static void __ftrace_dump(bool disable_tracing)
 {
 	static DEFINE_SPINLOCK(ftrace_dump_lock);
 	/* use static because iter can be a bit big for the stack */
 	static struct trace_iterator iter;
+	unsigned int old_userobj;
 	static int dump_ran;
 	unsigned long flags;
 	int cnt = 0, cpu;
@@ -3999,14 +4061,17 @@ void ftrace_dump(void)
 
 	dump_ran = 1;
 
-	/* No turning back! */
 	tracing_off();
-	ftrace_kill();
+
+	if (disable_tracing)
+		ftrace_kill();
 
 	for_each_tracing_cpu(cpu) {
 		atomic_inc(&global_trace.data[cpu]->disabled);
 	}
 
+	old_userobj = trace_flags & TRACE_ITER_SYM_USEROBJ;
+
 	/* don't look at user memory in panic mode */
 	trace_flags &= ~TRACE_ITER_SYM_USEROBJ;
 
@@ -4051,10 +4116,26 @@ void ftrace_dump(void)
 	else
 		printk(KERN_TRACE "---------------------------------\n");
 
+	/* Re-enable tracing if requested */
+	if (!disable_tracing) {
+		trace_flags |= old_userobj;
+
+		for_each_tracing_cpu(cpu) {
+			atomic_dec(&global_trace.data[cpu]->disabled);
+		}
+		tracing_on();
+	}
+
  out:
 	spin_unlock_irqrestore(&ftrace_dump_lock, flags);
 }
 
+/* By default: disable tracing after the dump */
+void ftrace_dump(void)
+{
+	__ftrace_dump(true);
+}
+
 __init static int tracer_alloc_buffers(void)
 {
 	struct trace_array_cpu *data;
@@ -4125,7 +4206,8 @@ __init static int tracer_alloc_buffers(void)
 				       &trace_panic_notifier);
 
 	register_die_notifier(&trace_die_notifier);
-	ret = 0;
+
+	return 0;
 
 out_free_cpumask:
 	free_cpumask_var(tracing_reader_cpumask);
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index e7fbc826f1e..9e15802cca9 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -123,7 +123,6 @@ struct userstack_entry {
 struct bprint_entry {
 	struct trace_entry	ent;
 	unsigned long		ip;
-	int			depth;
 	const char		*fmt;
 	u32			buf[];
 };
@@ -131,7 +130,6 @@ struct bprint_entry {
 struct print_entry {
 	struct trace_entry	ent;
 	unsigned long		ip;
-	int			depth;
 	char			buf[];
 };
 
@@ -184,6 +182,12 @@ struct trace_power {
 	struct power_trace	state_data;
 };
 
+enum kmemtrace_type_id {
+	KMEMTRACE_TYPE_KMALLOC = 0,	/* kmalloc() or kfree(). */
+	KMEMTRACE_TYPE_CACHE,		/* kmem_cache_*(). */
+	KMEMTRACE_TYPE_PAGES,		/* __get_free_pages() and friends. */
+};
+
 struct kmemtrace_alloc_entry {
 	struct trace_entry	ent;
 	enum kmemtrace_type_id type_id;
@@ -202,6 +206,19 @@ struct kmemtrace_free_entry {
 	const void *ptr;
 };
 
+struct syscall_trace_enter {
+	struct trace_entry	ent;
+	int			nr;
+	unsigned long		args[];
+};
+
+struct syscall_trace_exit {
+	struct trace_entry	ent;
+	int			nr;
+	unsigned long		ret;
+};
+
+
 /*
  * trace_flag_type is an enumeration that holds different
  * states when a trace occurs. These are:
@@ -315,6 +332,10 @@ extern void __ftrace_bad_type(void);
 			  TRACE_KMEM_ALLOC);	\
 		IF_ASSIGN(var, ent, struct kmemtrace_free_entry,	\
 			  TRACE_KMEM_FREE);	\
+		IF_ASSIGN(var, ent, struct syscall_trace_enter,		\
+			  TRACE_SYSCALL_ENTER);				\
+		IF_ASSIGN(var, ent, struct syscall_trace_exit,		\
+			  TRACE_SYSCALL_EXIT);				\
 		__ftrace_bad_type();					\
 	} while (0)
 
@@ -468,6 +489,8 @@ trace_current_buffer_lock_reserve(unsigned char type, unsigned long len,
 				  unsigned long flags, int pc);
 void trace_current_buffer_unlock_commit(struct ring_buffer_event *event,
 					unsigned long flags, int pc);
+void trace_nowake_buffer_unlock_commit(struct ring_buffer_event *event,
+					unsigned long flags, int pc);
 
 struct trace_entry *tracing_get_trace_entry(struct trace_array *tr,
 						struct trace_array_cpu *data);
@@ -547,7 +570,7 @@ struct tracer_switch_ops {
 };
 #endif /* CONFIG_CONTEXT_SWITCH_TRACER */
 
-extern char *trace_find_cmdline(int pid);
+extern void trace_find_cmdline(int pid, char comm[]);
 
 #ifdef CONFIG_DYNAMIC_FTRACE
 extern unsigned long ftrace_update_tot_cnt;
@@ -583,9 +606,9 @@ extern int trace_selftest_startup_hw_branches(struct tracer *trace,
 extern void *head_page(struct trace_array_cpu *data);
 extern long ns2usecs(cycle_t nsec);
 extern int
-trace_vbprintk(unsigned long ip, int depth, const char *fmt, va_list args);
+trace_vbprintk(unsigned long ip, const char *fmt, va_list args);
 extern int
-trace_vprintk(unsigned long ip, int depth, const char *fmt, va_list args);
+trace_vprintk(unsigned long ip, const char *fmt, va_list args);
 
 extern unsigned long trace_flags;
 
@@ -669,6 +692,8 @@ enum trace_iterator_flags {
 	TRACE_ITER_PRINTK_MSGONLY	= 0x10000,
 	TRACE_ITER_CONTEXT_INFO		= 0x20000, /* Print pid/cpu/time */
 	TRACE_ITER_LATENCY_FMT		= 0x40000,
+	TRACE_ITER_GLOBAL_CLK		= 0x80000,
+	TRACE_ITER_SLEEP_TIME		= 0x100000,
 };
 
 /*
@@ -761,22 +786,89 @@ enum {
 	TRACE_EVENT_TYPE_RAW		= 2,
 };
 
+struct ftrace_event_field {
+	struct list_head	link;
+	char			*name;
+	char			*type;
+	int			offset;
+	int			size;
+};
+
 struct ftrace_event_call {
-	char		*name;
-	char		*system;
-	struct dentry	*dir;
-	int		enabled;
-	int		(*regfunc)(void);
-	void		(*unregfunc)(void);
-	int		id;
-	int		(*raw_init)(void);
-	int		(*show_format)(struct trace_seq *s);
+	char			*name;
+	char			*system;
+	struct dentry		*dir;
+	int			enabled;
+	int			(*regfunc)(void);
+	void			(*unregfunc)(void);
+	int			id;
+	int			(*raw_init)(void);
+	int			(*show_format)(struct trace_seq *s);
+	int			(*define_fields)(void);
+	struct list_head	fields;
+	struct filter_pred	**preds;
+
+#ifdef CONFIG_EVENT_PROFILE
+	atomic_t	profile_count;
+	int		(*profile_enable)(struct ftrace_event_call *);
+	void		(*profile_disable)(struct ftrace_event_call *);
+#endif
 };
 
+struct event_subsystem {
+	struct list_head	list;
+	const char		*name;
+	struct dentry		*entry;
+	struct filter_pred	**preds;
+};
+
+#define events_for_each(event)						\
+	for (event = __start_ftrace_events;				\
+	     (unsigned long)event < (unsigned long)__stop_ftrace_events; \
+	     event++)
+
+#define MAX_FILTER_PRED 8
+
+struct filter_pred;
+
+typedef int (*filter_pred_fn_t) (struct filter_pred *pred, void *event);
+
+struct filter_pred {
+	filter_pred_fn_t fn;
+	u64 val;
+	char *str_val;
+	int str_len;
+	char *field_name;
+	int offset;
+	int not;
+	int or;
+	int compound;
+	int clear;
+};
+
+int trace_define_field(struct ftrace_event_call *call, char *type,
+		       char *name, int offset, int size);
+extern void filter_free_pred(struct filter_pred *pred);
+extern void filter_print_preds(struct filter_pred **preds,
+			       struct trace_seq *s);
+extern int filter_parse(char **pbuf, struct filter_pred *pred);
+extern int filter_add_pred(struct ftrace_event_call *call,
+			   struct filter_pred *pred);
+extern void filter_free_preds(struct ftrace_event_call *call);
+extern int filter_match_preds(struct ftrace_event_call *call, void *rec);
+extern void filter_free_subsystem_preds(struct event_subsystem *system);
+extern int filter_add_subsystem_pred(struct event_subsystem *system,
+				     struct filter_pred *pred);
+
 void event_trace_printk(unsigned long ip, const char *fmt, ...);
 extern struct ftrace_event_call __start_ftrace_events[];
 extern struct ftrace_event_call __stop_ftrace_events[];
 
+#define for_each_event(event)						\
+	for (event = __start_ftrace_events;				\
+	     (unsigned long)event < (unsigned long)__stop_ftrace_events; \
+	     event++)
+
 extern const char *__start___trace_bprintk_fmt[];
 extern const char *__stop___trace_bprintk_fmt[];
 
diff --git a/kernel/trace/trace_clock.c b/kernel/trace/trace_clock.c
index 05b176abfd3..b588fd81f7f 100644
--- a/kernel/trace/trace_clock.c
+++ b/kernel/trace/trace_clock.c
@@ -18,6 +18,7 @@
 #include <linux/percpu.h>
 #include <linux/sched.h>
 #include <linux/ktime.h>
+#include <linux/trace_clock.h>
 
 /*
  * trace_clock_local(): the simplest and least coherent tracing clock.
diff --git a/kernel/trace/trace_event_profile.c b/kernel/trace/trace_event_profile.c
new file mode 100644
index 00000000000..22cba997077
--- /dev/null
+++ b/kernel/trace/trace_event_profile.c
@@ -0,0 +1,31 @@
+/*
+ * trace event based perf counter profiling
+ *
+ * Copyright (C) 2009 Red Hat Inc, Peter Zijlstra <pzijlstr@redhat.com>
+ *
+ */
+
+#include "trace.h"
+
+int ftrace_profile_enable(int event_id)
+{
+	struct ftrace_event_call *event;
+
+	for_each_event(event) {
+		if (event->id == event_id)
+			return event->profile_enable(event);
+	}
+
+	return -EINVAL;
+}
+
+void ftrace_profile_disable(int event_id)
+{
+	struct ftrace_event_call *event;
+
+	for_each_event(event) {
+		if (event->id == event_id)
+			return event->profile_disable(event);
+	}
+}
+
diff --git a/kernel/trace/trace_event_types.h b/kernel/trace/trace_event_types.h
index 019915063fe..fd78bee71dd 100644
--- a/kernel/trace/trace_event_types.h
+++ b/kernel/trace/trace_event_types.h
@@ -105,7 +105,6 @@ TRACE_EVENT_FORMAT(user_stack, TRACE_USER_STACK, userstack_entry, ignore,
 TRACE_EVENT_FORMAT(bprint, TRACE_BPRINT, bprint_entry, ignore,
 	TRACE_STRUCT(
 		TRACE_FIELD(unsigned long, ip, ip)
-		TRACE_FIELD(unsigned int, depth, depth)
 		TRACE_FIELD(char *, fmt, fmt)
 		TRACE_FIELD_ZERO_CHAR(buf)
 	),
@@ -115,7 +114,6 @@ TRACE_EVENT_FORMAT(bprint, TRACE_BPRINT, bprint_entry, ignore,
 TRACE_EVENT_FORMAT(print, TRACE_PRINT, print_entry, ignore,
 	TRACE_STRUCT(
 		TRACE_FIELD(unsigned long, ip, ip)
-		TRACE_FIELD(unsigned int, depth, depth)
 		TRACE_FIELD_ZERO_CHAR(buf)
 	),
 	TP_RAW_FMT("%08lx (%d) fmt:%p %s")
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 238ea95a411..64ec4d278ff 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -19,10 +19,38 @@
 
 static DEFINE_MUTEX(event_mutex);
 
-#define events_for_each(event)						\
-	for (event = __start_ftrace_events;				\
-	     (unsigned long)event < (unsigned long)__stop_ftrace_events; \
-	     event++)
+int trace_define_field(struct ftrace_event_call *call, char *type,
+		       char *name, int offset, int size)
+{
+	struct ftrace_event_field *field;
+
+	field = kzalloc(sizeof(*field), GFP_KERNEL);
+	if (!field)
+		goto err;
+
+	field->name = kstrdup(name, GFP_KERNEL);
+	if (!field->name)
+		goto err;
+
+	field->type = kstrdup(type, GFP_KERNEL);
+	if (!field->type)
+		goto err;
+
+	field->offset = offset;
+	field->size = size;
+	list_add(&field->link, &call->fields);
+
+	return 0;
+
+err:
+	if (field) {
+		kfree(field->name);
+		kfree(field->type);
+	}
+	kfree(field);
+
+	return -ENOMEM;
+}
 
 static void ftrace_clear_events(void)
 {
@@ -90,7 +118,7 @@ static int ftrace_set_clr_event(char *buf, int set)
 	}
 
 	mutex_lock(&event_mutex);
-	events_for_each(call) {
+	for_each_event(call) {
 
 		if (!call->name || !call->regfunc)
 			continue;
@@ -348,7 +376,8 @@ event_enable_write(struct file *filp, const char __user *ubuf, size_t cnt,
 
 #undef FIELD
 #define FIELD(type, name)						\
-	#type, #name, offsetof(typeof(field), name), sizeof(field.name)
+	#type, "common_" #name, offsetof(typeof(field), name),		\
+		sizeof(field.name)
 
 static int trace_write_header(struct trace_seq *s)
 {
@@ -378,15 +407,15 @@ event_format_read(struct file *filp, char __user *ubuf, size_t cnt,
 	char *buf;
 	int r;
 
+	if (*ppos)
+		return 0;
+
 	s = kmalloc(sizeof(*s), GFP_KERNEL);
 	if (!s)
 		return -ENOMEM;
 
 	trace_seq_init(s);
 
-	if (*ppos)
-		return 0;
-
 	/* If any of the first writes fail, so will the show_format. */
 
 	trace_seq_printf(s, "name: %s\n", call->name);
@@ -412,6 +441,162 @@ event_format_read(struct file *filp, char __user *ubuf, size_t cnt,
 	return r;
 }
 
+static ssize_t
+event_id_read(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos)
+{
+	struct ftrace_event_call *call = filp->private_data;
+	struct trace_seq *s;
+	int r;
+
+	if (*ppos)
+		return 0;
+
+	s = kmalloc(sizeof(*s), GFP_KERNEL);
+	if (!s)
+		return -ENOMEM;
+
+	trace_seq_init(s);
+	trace_seq_printf(s, "%d\n", call->id);
+
+	r = simple_read_from_buffer(ubuf, cnt, ppos,
+				    s->buffer, s->len);
+	kfree(s);
+	return r;
+}
+
+static ssize_t
+event_filter_read(struct file *filp, char __user *ubuf, size_t cnt,
+		  loff_t *ppos)
+{
+	struct ftrace_event_call *call = filp->private_data;
+	struct trace_seq *s;
+	int r;
+
+	if (*ppos)
+		return 0;
+
+	s = kmalloc(sizeof(*s), GFP_KERNEL);
+	if (!s)
+		return -ENOMEM;
+
+	trace_seq_init(s);
+
+	filter_print_preds(call->preds, s);
+	r = simple_read_from_buffer(ubuf, cnt, ppos, s->buffer, s->len);
+
+	kfree(s);
+
+	return r;
+}
+
+static ssize_t
+event_filter_write(struct file *filp, const char __user *ubuf, size_t cnt,
+		   loff_t *ppos)
+{
+	struct ftrace_event_call *call = filp->private_data;
+	char buf[64], *pbuf = buf;
+	struct filter_pred *pred;
+	int err;
+
+	if (cnt >= sizeof(buf))
+		return -EINVAL;
+
+	if (copy_from_user(&buf, ubuf, cnt))
+		return -EFAULT;
+
+	pred = kzalloc(sizeof(*pred), GFP_KERNEL);
+	if (!pred)
+		return -ENOMEM;
+
+	err = filter_parse(&pbuf, pred);
+	if (err < 0) {
+		filter_free_pred(pred);
+		return err;
+	}
+
+	if (pred->clear) {
+		filter_free_preds(call);
+		filter_free_pred(pred);
+		return cnt;
+	}
+
+	if (filter_add_pred(call, pred)) {
+		filter_free_pred(pred);
+		return -EINVAL;
+	}
+
+	*ppos += cnt;
+
+	return cnt;
+}
+
+static ssize_t
+subsystem_filter_read(struct file *filp, char __user *ubuf, size_t cnt,
+		      loff_t *ppos)
+{
+	struct event_subsystem *system = filp->private_data;
+	struct trace_seq *s;
+	int r;
+
+	if (*ppos)
+		return 0;
+
+	s = kmalloc(sizeof(*s), GFP_KERNEL);
+	if (!s)
+		return -ENOMEM;
+
+	trace_seq_init(s);
+
+	filter_print_preds(system->preds, s);
+	r = simple_read_from_buffer(ubuf, cnt, ppos, s->buffer, s->len);
+
+	kfree(s);
+
+	return r;
+}
+
+static ssize_t
+subsystem_filter_write(struct file *filp, const char __user *ubuf, size_t cnt,
+		       loff_t *ppos)
+{
+	struct event_subsystem *system = filp->private_data;
+	char buf[64], *pbuf = buf;
+	struct filter_pred *pred;
+	int err;
+
+	if (cnt >= sizeof(buf))
+		return -EINVAL;
+
+	if (copy_from_user(&buf, ubuf, cnt))
+		return -EFAULT;
+
+	pred = kzalloc(sizeof(*pred), GFP_KERNEL);
+	if (!pred)
+		return -ENOMEM;
+
+	err = filter_parse(&pbuf, pred);
+	if (err < 0) {
+		filter_free_pred(pred);
+		return err;
+	}
+
+	if (pred->clear) {
+		filter_free_subsystem_preds(system);
+		filter_free_pred(pred);
+		return cnt;
+	}
+
+	if (filter_add_subsystem_pred(system, pred)) {
+		filter_free_subsystem_preds(system);
+		filter_free_pred(pred);
+		return -EINVAL;
+	}
+
+	*ppos += cnt;
+
+	return cnt;
+}
+
 static const struct seq_operations show_event_seq_ops = {
 	.start = t_start,
 	.next = t_next,
@@ -452,6 +637,23 @@ static const struct file_operations ftrace_event_format_fops = {
 	.read = event_format_read,
 };
 
+static const struct file_operations ftrace_event_id_fops = {
+	.open = tracing_open_generic,
+	.read = event_id_read,
+};
+
+static const struct file_operations ftrace_event_filter_fops = {
+	.open = tracing_open_generic,
+	.read = event_filter_read,
+	.write = event_filter_write,
+};
+
+static const struct file_operations ftrace_subsystem_filter_fops = {
+	.open = tracing_open_generic,
+	.read = subsystem_filter_read,
+	.write = subsystem_filter_write,
+};
+
 static struct dentry *event_trace_events_dir(void)
 {
 	static struct dentry *d_tracer;
@@ -472,12 +674,6 @@ static struct dentry *event_trace_events_dir(void)
 	return d_events;
 }
 
-struct event_subsystem {
-	struct list_head	list;
-	const char		*name;
-	struct dentry		*entry;
-};
-
 static LIST_HEAD(event_subsystems);
 
 static struct dentry *
@@ -510,6 +706,8 @@ event_subsystem_dir(const char *name, struct dentry *d_events)
 	system->name = name;
 	list_add(&system->list, &event_subsystems);
 
+	system->preds = NULL;
+
 	return system->entry;
 }
 
@@ -550,6 +748,28 @@ event_create_dir(struct ftrace_event_call *call, struct dentry *d_events)
 				   "'%s/enable' entry\n", call->name);
 	}
 
+	if (call->id) {
+		entry = debugfs_create_file("id", 0444, call->dir, call,
+				&ftrace_event_id_fops);
+		if (!entry)
+			pr_warning("Could not create debugfs '%s/id' entry\n",
+					call->name);
+	}
+
+	if (call->define_fields) {
+		ret = call->define_fields();
+		if (ret < 0) {
+			pr_warning("Could not initialize trace point"
+				   " events/%s\n", call->name);
+			return ret;
+		}
+		entry = debugfs_create_file("filter", 0644, call->dir, call,
+					    &ftrace_event_filter_fops);
+		if (!entry)
+			pr_warning("Could not create debugfs "
+				   "'%s/filter' entry\n", call->name);
+	}
+
 	/* A trace may not want to export its format */
 	if (!call->show_format)
 		return 0;
@@ -592,7 +812,7 @@ static __init int event_trace_init(void)
 	if (!d_events)
 		return 0;
 
-	events_for_each(call) {
+	for_each_event(call) {
 		/* The linker may leave blanks */
 		if (!call->name)
 			continue;
diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c
new file mode 100644
index 00000000000..026be412f35
--- /dev/null
+++ b/kernel/trace/trace_events_filter.c
@@ -0,0 +1,427 @@
+/*
+ * trace_events_filter - generic event filtering
+ *
+ * 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.
+ *
+ * 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.
+ *
+ * Copyright (C) 2009 Tom Zanussi <tzanussi@gmail.com>
+ */
+
+#include <linux/debugfs.h>
+#include <linux/uaccess.h>
+#include <linux/module.h>
+#include <linux/ctype.h>
+
+#include "trace.h"
+#include "trace_output.h"
+
+static int filter_pred_64(struct filter_pred *pred, void *event)
+{
+	u64 *addr = (u64 *)(event + pred->offset);
+	u64 val = (u64)pred->val;
+	int match;
+
+	match = (val == *addr) ^ pred->not;
+
+	return match;
+}
+
+static int filter_pred_32(struct filter_pred *pred, void *event)
+{
+	u32 *addr = (u32 *)(event + pred->offset);
+	u32 val = (u32)pred->val;
+	int match;
+
+	match = (val == *addr) ^ pred->not;
+
+	return match;
+}
+
+static int filter_pred_16(struct filter_pred *pred, void *event)
+{
+	u16 *addr = (u16 *)(event + pred->offset);
+	u16 val = (u16)pred->val;
+	int match;
+
+	match = (val == *addr) ^ pred->not;
+
+	return match;
+}
+
+static int filter_pred_8(struct filter_pred *pred, void *event)
+{
+	u8 *addr = (u8 *)(event + pred->offset);
+	u8 val = (u8)pred->val;
+	int match;
+
+	match = (val == *addr) ^ pred->not;
+
+	return match;
+}
+
+static int filter_pred_string(struct filter_pred *pred, void *event)
+{
+	char *addr = (char *)(event + pred->offset);
+	int cmp, match;
+
+	cmp = strncmp(addr, pred->str_val, pred->str_len);
+
+	match = (!cmp) ^ pred->not;
+
+	return match;
+}
+
+/* return 1 if event matches, 0 otherwise (discard) */
+int filter_match_preds(struct ftrace_event_call *call, void *rec)
+{
+	int i, matched, and_failed = 0;
+	struct filter_pred *pred;
+
+	for (i = 0; i < MAX_FILTER_PRED; i++) {
+		if (call->preds[i]) {
+			pred = call->preds[i];
+			if (and_failed && !pred->or)
+				continue;
+			matched = pred->fn(pred, rec);
+			if (!matched && !pred->or) {
+				and_failed = 1;
+				continue;
+			} else if (matched && pred->or)
+				return 1;
+		} else
+			break;
+	}
+
+	if (and_failed)
+		return 0;
+
+	return 1;
+}
+
+void filter_print_preds(struct filter_pred **preds, struct trace_seq *s)
+{
+	char *field_name;
+	struct filter_pred *pred;
+	int i;
+
+	if (!preds) {
+		trace_seq_printf(s, "none\n");
+		return;
+	}
+
+	for (i = 0; i < MAX_FILTER_PRED; i++) {
+		if (preds[i]) {
+			pred = preds[i];
+			field_name = pred->field_name;
+			if (i)
+				trace_seq_printf(s, pred->or ? "|| " : "&& ");
+			trace_seq_printf(s, "%s ", field_name);
+			trace_seq_printf(s, pred->not ? "!= " : "== ");
+			if (pred->str_val)
+				trace_seq_printf(s, "%s\n", pred->str_val);
+			else
+				trace_seq_printf(s, "%llu\n", pred->val);
+		} else
+			break;
+	}
+}
+
+static struct ftrace_event_field *
+find_event_field(struct ftrace_event_call *call, char *name)
+{
+	struct ftrace_event_field *field;
+
+	list_for_each_entry(field, &call->fields, link) {
+		if (!strcmp(field->name, name))
+			return field;
+	}
+
+	return NULL;
+}
+
+void filter_free_pred(struct filter_pred *pred)
+{
+	if (!pred)
+		return;
+
+	kfree(pred->field_name);
+	kfree(pred->str_val);
+	kfree(pred);
+}
+
+void filter_free_preds(struct ftrace_event_call *call)
+{
+	int i;
+
+	if (call->preds) {
+		for (i = 0; i < MAX_FILTER_PRED; i++)
+			filter_free_pred(call->preds[i]);
+		kfree(call->preds);
+		call->preds = NULL;
+	}
+}
+
+void filter_free_subsystem_preds(struct event_subsystem *system)
+{
+	struct ftrace_event_call *call = __start_ftrace_events;
+	int i;
+
+	if (system->preds) {
+		for (i = 0; i < MAX_FILTER_PRED; i++)
+			filter_free_pred(system->preds[i]);
+		kfree(system->preds);
+		system->preds = NULL;
+	}
+
+	events_for_each(call) {
+		if (!call->name || !call->regfunc)
+			continue;
+
+		if (!strcmp(call->system, system->name))
+			filter_free_preds(call);
+	}
+}
+
+static int __filter_add_pred(struct ftrace_event_call *call,
+			     struct filter_pred *pred)
+{
+	int i;
+
+	if (call->preds && !pred->compound)
+		filter_free_preds(call);
+
+	if (!call->preds) {
+		call->preds = kzalloc(MAX_FILTER_PRED * sizeof(pred),
+				      GFP_KERNEL);
+		if (!call->preds)
+			return -ENOMEM;
+	}
+
+	for (i = 0; i < MAX_FILTER_PRED; i++) {
+		if (!call->preds[i]) {
+			call->preds[i] = pred;
+			return 0;
+		}
+	}
+
+	return -ENOMEM;
+}
+
+static int is_string_field(const char *type)
+{
+	if (strchr(type, '[') && strstr(type, "char"))
+		return 1;
+
+	return 0;
+}
+
+int filter_add_pred(struct ftrace_event_call *call, struct filter_pred *pred)
+{
+	struct ftrace_event_field *field;
+
+	field = find_event_field(call, pred->field_name);
+	if (!field)
+		return -EINVAL;
+
+	pred->offset = field->offset;
+
+	if (is_string_field(field->type)) {
+		if (!pred->str_val)
+			return -EINVAL;
+		pred->fn = filter_pred_string;
+		pred->str_len = field->size;
+		return __filter_add_pred(call, pred);
+	} else {
+		if (pred->str_val)
+			return -EINVAL;
+	}
+
+	switch (field->size) {
+	case 8:
+		pred->fn = filter_pred_64;
+		break;
+	case 4:
+		pred->fn = filter_pred_32;
+		break;
+	case 2:
+		pred->fn = filter_pred_16;
+		break;
+	case 1:
+		pred->fn = filter_pred_8;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return __filter_add_pred(call, pred);
+}
+
+static struct filter_pred *copy_pred(struct filter_pred *pred)
+{
+	struct filter_pred *new_pred = kmalloc(sizeof(*pred), GFP_KERNEL);
+	if (!new_pred)
+		return NULL;
+
+	memcpy(new_pred, pred, sizeof(*pred));
+
+	if (pred->field_name) {
+		new_pred->field_name = kstrdup(pred->field_name, GFP_KERNEL);
+		if (!new_pred->field_name) {
+			kfree(new_pred);
+			return NULL;
+		}
+	}
+
+	if (pred->str_val) {
+		new_pred->str_val = kstrdup(pred->str_val, GFP_KERNEL);
+		if (!new_pred->str_val) {
+			filter_free_pred(new_pred);
+			return NULL;
+		}
+	}
+
+	return new_pred;
+}
+
+int filter_add_subsystem_pred(struct event_subsystem *system,
+			      struct filter_pred *pred)
+{
+	struct ftrace_event_call *call = __start_ftrace_events;
+	struct filter_pred *event_pred;
+	int i;
+
+	if (system->preds && !pred->compound)
+		filter_free_subsystem_preds(system);
+
+	if (!system->preds) {
+		system->preds = kzalloc(MAX_FILTER_PRED * sizeof(pred),
+					GFP_KERNEL);
+		if (!system->preds)
+			return -ENOMEM;
+	}
+
+	for (i = 0; i < MAX_FILTER_PRED; i++) {
+		if (!system->preds[i]) {
+			system->preds[i] = pred;
+			break;
+		}
+	}
+
+	if (i == MAX_FILTER_PRED)
+		return -EINVAL;
+
+	events_for_each(call) {
+		int err;
+
+		if (!call->name || !call->regfunc)
+			continue;
+
+		if (strcmp(call->system, system->name))
+			continue;
+
+		if (!find_event_field(call, pred->field_name))
+			continue;
+
+		event_pred = copy_pred(pred);
+		if (!event_pred)
+			goto oom;
+
+		err = filter_add_pred(call, event_pred);
+		if (err)
+			filter_free_pred(event_pred);
+		if (err == -ENOMEM)
+			goto oom;
+	}
+
+	return 0;
+
+oom:
+	system->preds[i] = NULL;
+	return -ENOMEM;
+}
+
+int filter_parse(char **pbuf, struct filter_pred *pred)
+{
+	char *tmp, *tok, *val_str = NULL;
+	int tok_n = 0;
+
+	/* field ==/!= number, or/and field ==/!= number, number */
+	while ((tok = strsep(pbuf, " \n"))) {
+		if (tok_n == 0) {
+			if (!strcmp(tok, "0")) {
+				pred->clear = 1;
+				return 0;
+			} else if (!strcmp(tok, "&&")) {
+				pred->or = 0;
+				pred->compound = 1;
+			} else if (!strcmp(tok, "||")) {
+				pred->or = 1;
+				pred->compound = 1;
+			} else
+				pred->field_name = tok;
+			tok_n = 1;
+			continue;
+		}
+		if (tok_n == 1) {
+			if (!pred->field_name)
+				pred->field_name = tok;
+			else if (!strcmp(tok, "!="))
+				pred->not = 1;
+			else if (!strcmp(tok, "=="))
+				pred->not = 0;
+			else {
+				pred->field_name = NULL;
+				return -EINVAL;
+			}
+			tok_n = 2;
+			continue;
+		}
+		if (tok_n == 2) {
+			if (pred->compound) {
+				if (!strcmp(tok, "!="))
+					pred->not = 1;
+				else if (!strcmp(tok, "=="))
+					pred->not = 0;
+				else {
+					pred->field_name = NULL;
+					return -EINVAL;
+				}
+			} else {
+				val_str = tok;
+				break; /* done */
+			}
+			tok_n = 3;
+			continue;
+		}
+		if (tok_n == 3) {
+			val_str = tok;
+			break; /* done */
+		}
+	}
+
+	pred->field_name = kstrdup(pred->field_name, GFP_KERNEL);
+	if (!pred->field_name)
+		return -ENOMEM;
+
+	pred->val = simple_strtoull(val_str, &tmp, 10);
+	if (tmp == val_str) {
+		pred->str_val = kstrdup(val_str, GFP_KERNEL);
+		if (!pred->str_val)
+			return -ENOMEM;
+	}
+
+	return 0;
+}
+
+
diff --git a/kernel/trace/trace_events_stage_2.h b/kernel/trace/trace_events_stage_2.h
index 5117c43f5c6..30743f7d411 100644
--- a/kernel/trace/trace_events_stage_2.h
+++ b/kernel/trace/trace_events_stage_2.h
@@ -129,3 +129,48 @@ ftrace_format_##call(struct trace_seq *s)				\
 }
 
 #include <trace/trace_event_types.h>
+
+#undef __field
+#define __field(type, item)						\
+	ret = trace_define_field(event_call, #type, #item,		\
+				 offsetof(typeof(field), item),		\
+				 sizeof(field.item));			\
+	if (ret)							\
+		return ret;
+
+#undef __array
+#define __array(type, item, len)					\
+	ret = trace_define_field(event_call, #type "[" #len "]", #item,	\
+				 offsetof(typeof(field), item),		\
+				 sizeof(field.item));			\
+	if (ret)							\
+		return ret;
+
+#define __common_field(type, item)					\
+	ret = trace_define_field(event_call, #type, "common_" #item,	\
+				 offsetof(typeof(field.ent), item),	\
+				 sizeof(field.ent.item));		\
+	if (ret)							\
+		return ret;
+
+#undef TRACE_EVENT
+#define TRACE_EVENT(call, proto, args, tstruct, func, print)		\
+int									\
+ftrace_define_fields_##call(void)					\
+{									\
+	struct ftrace_raw_##call field;					\
+	struct ftrace_event_call *event_call = &event_##call;		\
+	int ret;							\
+									\
+	__common_field(unsigned char, type);				\
+	__common_field(unsigned char, flags);				\
+	__common_field(unsigned char, preempt_count);			\
+	__common_field(int, pid);					\
+	__common_field(int, tgid);					\
+									\
+	tstruct;							\
+									\
+	return ret;							\
+}
+
+#include <trace/trace_event_types.h>
diff --git a/kernel/trace/trace_events_stage_3.h b/kernel/trace/trace_events_stage_3.h
index ae2e323df0c..9d2fa78cecc 100644
--- a/kernel/trace/trace_events_stage_3.h
+++ b/kernel/trace/trace_events_stage_3.h
@@ -109,6 +109,40 @@
 #undef TP_FMT
 #define TP_FMT(fmt, args...)	fmt "\n", ##args
 
+#ifdef CONFIG_EVENT_PROFILE
+#define _TRACE_PROFILE(call, proto, args)				\
+static void ftrace_profile_##call(proto)				\
+{									\
+	extern void perf_tpcounter_event(int);				\
+	perf_tpcounter_event(event_##call.id);				\
+}									\
+									\
+static int ftrace_profile_enable_##call(struct ftrace_event_call *call) \
+{									\
+	int ret = 0;							\
+									\
+	if (!atomic_inc_return(&call->profile_count))			\
+		ret = register_trace_##call(ftrace_profile_##call);	\
+									\
+	return ret;							\
+}									\
+									\
+static void ftrace_profile_disable_##call(struct ftrace_event_call *call) \
+{									\
+	if (atomic_add_negative(-1, &call->profile_count))		\
+		unregister_trace_##call(ftrace_profile_##call);		\
+}
+
+#define _TRACE_PROFILE_INIT(call)					\
+	.profile_count = ATOMIC_INIT(-1),				\
+	.profile_enable = ftrace_profile_enable_##call,			\
+	.profile_disable = ftrace_profile_disable_##call,
+
+#else
+#define _TRACE_PROFILE(call, proto, args)
+#define _TRACE_PROFILE_INIT(call)
+#endif
+
 #define _TRACE_FORMAT(call, proto, args, fmt)				\
 static void ftrace_event_##call(proto)					\
 {									\
@@ -130,18 +164,33 @@ static void ftrace_unreg_event_##call(void)				\
 {									\
 	unregister_trace_##call(ftrace_event_##call);			\
 }									\
-
+									\
+static struct ftrace_event_call event_##call;				\
+									\
+static int ftrace_init_event_##call(void)				\
+{									\
+	int id;								\
+									\
+	id = register_ftrace_event(NULL);				\
+	if (!id)							\
+		return -ENODEV;						\
+	event_##call.id = id;						\
+	return 0;							\
+}
 
 #undef TRACE_FORMAT
 #define TRACE_FORMAT(call, proto, args, fmt)				\
 _TRACE_FORMAT(call, PARAMS(proto), PARAMS(args), PARAMS(fmt))		\
+_TRACE_PROFILE(call, PARAMS(proto), PARAMS(args))			\
 static struct ftrace_event_call __used					\
 __attribute__((__aligned__(4)))						\
 __attribute__((section("_ftrace_events"))) event_##call = {		\
 	.name			= #call,				\
 	.system			= __stringify(TRACE_SYSTEM),		\
+	.raw_init		= ftrace_init_event_##call,		\
 	.regfunc		= ftrace_reg_event_##call,		\
 	.unregfunc		= ftrace_unreg_event_##call,		\
+	_TRACE_PROFILE_INIT(call)					\
 }
 
 #undef __entry
@@ -149,11 +198,13 @@ __attribute__((section("_ftrace_events"))) event_##call = {		\
 
 #undef TRACE_EVENT
 #define TRACE_EVENT(call, proto, args, tstruct, assign, print)		\
+_TRACE_PROFILE(call, PARAMS(proto), PARAMS(args))			\
 									\
 static struct ftrace_event_call event_##call;				\
 									\
 static void ftrace_raw_event_##call(proto)				\
 {									\
+	struct ftrace_event_call *call = &event_##call;			\
 	struct ring_buffer_event *event;				\
 	struct ftrace_raw_##call *entry;				\
 	unsigned long irq_flags;					\
@@ -171,7 +222,11 @@ static void ftrace_raw_event_##call(proto)				\
 									\
 	assign;								\
 									\
-	trace_current_buffer_unlock_commit(event, irq_flags, pc);	\
+	if (call->preds && !filter_match_preds(call, entry))		\
+		ring_buffer_event_discard(event);			\
+									\
+	trace_nowake_buffer_unlock_commit(event, irq_flags, pc);	\
+									\
 }									\
 									\
 static int ftrace_raw_reg_event_##call(void)				\
@@ -202,6 +257,7 @@ static int ftrace_raw_init_event_##call(void)				\
 	if (!id)							\
 		return -ENODEV;						\
 	event_##call.id = id;						\
+	INIT_LIST_HEAD(&event_##call.fields);				\
 	return 0;							\
 }									\
 									\
@@ -214,4 +270,12 @@ __attribute__((section("_ftrace_events"))) event_##call = {		\
 	.regfunc		= ftrace_raw_reg_event_##call,		\
 	.unregfunc		= ftrace_raw_unreg_event_##call,	\
 	.show_format		= ftrace_format_##call,			\
+	.define_fields		= ftrace_define_fields_##call,		\
+	_TRACE_PROFILE_INIT(call)					\
 }
+
+#include <trace/trace_event_types.h>
+
+#undef _TRACE_PROFILE
+#undef _TRACE_PROFILE_INIT
+
diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c
index 4c388607ed6..d28687e7b3a 100644
--- a/kernel/trace/trace_functions_graph.c
+++ b/kernel/trace/trace_functions_graph.c
@@ -14,6 +14,11 @@
 #include "trace.h"
 #include "trace_output.h"
 
+struct fgraph_data {
+	pid_t		last_pid;
+	int		depth;
+};
+
 #define TRACE_GRAPH_INDENT	2
 
 /* Flag options */
@@ -52,9 +57,9 @@ static struct tracer_flags tracer_flags = {
 
 /* Add a function return address to the trace stack on thread info.*/
 int
-ftrace_push_return_trace(unsigned long ret, unsigned long long time,
-			 unsigned long func, int *depth)
+ftrace_push_return_trace(unsigned long ret, unsigned long func, int *depth)
 {
+	unsigned long long calltime;
 	int index;
 
 	if (!current->ret_stack)
@@ -66,11 +71,13 @@ ftrace_push_return_trace(unsigned long ret, unsigned long long time,
 		return -EBUSY;
 	}
 
+	calltime = trace_clock_local();
+
 	index = ++current->curr_ret_stack;
 	barrier();
 	current->ret_stack[index].ret = ret;
 	current->ret_stack[index].func = func;
-	current->ret_stack[index].calltime = time;
+	current->ret_stack[index].calltime = calltime;
 	*depth = index;
 
 	return 0;
@@ -190,15 +197,15 @@ print_graph_cpu(struct trace_seq *s, int cpu)
 static enum print_line_t
 print_graph_proc(struct trace_seq *s, pid_t pid)
 {
-	int i;
-	int ret;
-	int len;
-	char comm[8];
-	int spaces = 0;
+	char comm[TASK_COMM_LEN];
 	/* sign + log10(MAX_INT) + '\0' */
 	char pid_str[11];
+	int spaces = 0;
+	int ret;
+	int len;
+	int i;
 
-	strncpy(comm, trace_find_cmdline(pid), 7);
+	trace_find_cmdline(pid, comm);
 	comm[7] = '\0';
 	sprintf(pid_str, "%d", pid);
 
@@ -231,16 +238,16 @@ print_graph_proc(struct trace_seq *s, pid_t pid)
 
 /* If the pid changed since the last trace, output this event */
 static enum print_line_t
-verif_pid(struct trace_seq *s, pid_t pid, int cpu, pid_t *last_pids_cpu)
+verif_pid(struct trace_seq *s, pid_t pid, int cpu, struct fgraph_data *data)
 {
 	pid_t prev_pid;
 	pid_t *last_pid;
 	int ret;
 
-	if (!last_pids_cpu)
+	if (!data)
 		return TRACE_TYPE_HANDLED;
 
-	last_pid = per_cpu_ptr(last_pids_cpu, cpu);
+	last_pid = &(per_cpu_ptr(data, cpu)->last_pid);
 
 	if (*last_pid == pid)
 		return TRACE_TYPE_HANDLED;
@@ -471,6 +478,7 @@ print_graph_entry_leaf(struct trace_iterator *iter,
 		struct ftrace_graph_ent_entry *entry,
 		struct ftrace_graph_ret_entry *ret_entry, struct trace_seq *s)
 {
+	struct fgraph_data *data = iter->private;
 	struct ftrace_graph_ret *graph_ret;
 	struct ftrace_graph_ent *call;
 	unsigned long long duration;
@@ -481,6 +489,18 @@ print_graph_entry_leaf(struct trace_iterator *iter,
 	call = &entry->graph_ent;
 	duration = graph_ret->rettime - graph_ret->calltime;
 
+	if (data) {
+		int cpu = iter->cpu;
+		int *depth = &(per_cpu_ptr(data, cpu)->depth);
+
+		/*
+		 * Comments display at + 1 to depth. Since
+		 * this is a leaf function, keep the comments
+		 * equal to this depth.
+		 */
+		*depth = call->depth - 1;
+	}
+
 	/* Overhead */
 	ret = print_graph_overhead(duration, s);
 	if (!ret)
@@ -512,12 +532,21 @@ print_graph_entry_leaf(struct trace_iterator *iter,
 }
 
 static enum print_line_t
-print_graph_entry_nested(struct ftrace_graph_ent_entry *entry,
-			struct trace_seq *s, pid_t pid, int cpu)
+print_graph_entry_nested(struct trace_iterator *iter,
+			 struct ftrace_graph_ent_entry *entry,
+			 struct trace_seq *s, int cpu)
 {
-	int i;
-	int ret;
 	struct ftrace_graph_ent *call = &entry->graph_ent;
+	struct fgraph_data *data = iter->private;
+	int ret;
+	int i;
+
+	if (data) {
+		int cpu = iter->cpu;
+		int *depth = &(per_cpu_ptr(data, cpu)->depth);
+
+		*depth = call->depth;
+	}
 
 	/* No overhead */
 	ret = print_graph_overhead(-1, s);
@@ -554,24 +583,24 @@ print_graph_entry_nested(struct ftrace_graph_ent_entry *entry,
 }
 
 static enum print_line_t
-print_graph_entry(struct ftrace_graph_ent_entry *field, struct trace_seq *s,
-			struct trace_iterator *iter)
+print_graph_prologue(struct trace_iterator *iter, struct trace_seq *s,
+		     int type, unsigned long addr)
 {
-	int ret;
-	int cpu = iter->cpu;
-	pid_t *last_entry = iter->private;
+	struct fgraph_data *data = iter->private;
 	struct trace_entry *ent = iter->ent;
-	struct ftrace_graph_ent *call = &field->graph_ent;
-	struct ftrace_graph_ret_entry *leaf_ret;
+	int cpu = iter->cpu;
+	int ret;
 
 	/* Pid */
-	if (verif_pid(s, ent->pid, cpu, last_entry) == TRACE_TYPE_PARTIAL_LINE)
+	if (verif_pid(s, ent->pid, cpu, data) == TRACE_TYPE_PARTIAL_LINE)
 		return TRACE_TYPE_PARTIAL_LINE;
 
-	/* Interrupt */
-	ret = print_graph_irq(iter, call->func, TRACE_GRAPH_ENT, cpu, ent->pid);
-	if (ret == TRACE_TYPE_PARTIAL_LINE)
-		return TRACE_TYPE_PARTIAL_LINE;
+	if (type) {
+		/* Interrupt */
+		ret = print_graph_irq(iter, addr, type, cpu, ent->pid);
+		if (ret == TRACE_TYPE_PARTIAL_LINE)
+			return TRACE_TYPE_PARTIAL_LINE;
+	}
 
 	/* Absolute time */
 	if (tracer_flags.val & TRACE_GRAPH_PRINT_ABS_TIME) {
@@ -598,11 +627,25 @@ print_graph_entry(struct ftrace_graph_ent_entry *field, struct trace_seq *s,
 			return TRACE_TYPE_PARTIAL_LINE;
 	}
 
+	return 0;
+}
+
+static enum print_line_t
+print_graph_entry(struct ftrace_graph_ent_entry *field, struct trace_seq *s,
+			struct trace_iterator *iter)
+{
+	int cpu = iter->cpu;
+	struct ftrace_graph_ent *call = &field->graph_ent;
+	struct ftrace_graph_ret_entry *leaf_ret;
+
+	if (print_graph_prologue(iter, s, TRACE_GRAPH_ENT, call->func))
+		return TRACE_TYPE_PARTIAL_LINE;
+
 	leaf_ret = get_return_for_leaf(iter, field);
 	if (leaf_ret)
 		return print_graph_entry_leaf(iter, field, leaf_ret, s);
 	else
-		return print_graph_entry_nested(field, s, iter->ent->pid, cpu);
+		return print_graph_entry_nested(iter, field, s, cpu);
 
 }
 
@@ -610,40 +653,27 @@ static enum print_line_t
 print_graph_return(struct ftrace_graph_ret *trace, struct trace_seq *s,
 		   struct trace_entry *ent, struct trace_iterator *iter)
 {
-	int i;
-	int ret;
-	int cpu = iter->cpu;
-	pid_t *last_pid = iter->private, pid = ent->pid;
 	unsigned long long duration = trace->rettime - trace->calltime;
+	struct fgraph_data *data = iter->private;
+	pid_t pid = ent->pid;
+	int cpu = iter->cpu;
+	int ret;
+	int i;
 
-	/* Pid */
-	if (verif_pid(s, pid, cpu, last_pid) == TRACE_TYPE_PARTIAL_LINE)
-		return TRACE_TYPE_PARTIAL_LINE;
+	if (data) {
+		int cpu = iter->cpu;
+		int *depth = &(per_cpu_ptr(data, cpu)->depth);
 
-	/* Absolute time */
-	if (tracer_flags.val & TRACE_GRAPH_PRINT_ABS_TIME) {
-		ret = print_graph_abs_time(iter->ts, s);
-		if (!ret)
-			return TRACE_TYPE_PARTIAL_LINE;
+		/*
+		 * Comments display at + 1 to depth. This is the
+		 * return from a function, we now want the comments
+		 * to display at the same level of the bracket.
+		 */
+		*depth = trace->depth - 1;
 	}
 
-	/* Cpu */
-	if (tracer_flags.val & TRACE_GRAPH_PRINT_CPU) {
-		ret = print_graph_cpu(s, cpu);
-		if (ret == TRACE_TYPE_PARTIAL_LINE)
-			return TRACE_TYPE_PARTIAL_LINE;
-	}
-
-	/* Proc */
-	if (tracer_flags.val & TRACE_GRAPH_PRINT_PROC) {
-		ret = print_graph_proc(s, ent->pid);
-		if (ret == TRACE_TYPE_PARTIAL_LINE)
-			return TRACE_TYPE_PARTIAL_LINE;
-
-		ret = trace_seq_printf(s, " | ");
-		if (!ret)
-			return TRACE_TYPE_PARTIAL_LINE;
-	}
+	if (print_graph_prologue(iter, s, 0, 0))
+		return TRACE_TYPE_PARTIAL_LINE;
 
 	/* Overhead */
 	ret = print_graph_overhead(duration, s);
@@ -684,42 +714,21 @@ print_graph_return(struct ftrace_graph_ret *trace, struct trace_seq *s,
 }
 
 static enum print_line_t
-print_graph_comment(struct bprint_entry *trace, struct trace_seq *s,
-		   struct trace_entry *ent, struct trace_iterator *iter)
+print_graph_comment(struct trace_seq *s,  struct trace_entry *ent,
+		    struct trace_iterator *iter)
 {
-	int i;
+	unsigned long sym_flags = (trace_flags & TRACE_ITER_SYM_MASK);
+	struct fgraph_data *data = iter->private;
+	struct trace_event *event;
+	int depth = 0;
 	int ret;
-	int cpu = iter->cpu;
-	pid_t *last_pid = iter->private;
-
-	/* Pid */
-	if (verif_pid(s, ent->pid, cpu, last_pid) == TRACE_TYPE_PARTIAL_LINE)
-		return TRACE_TYPE_PARTIAL_LINE;
-
-	/* Absolute time */
-	if (tracer_flags.val & TRACE_GRAPH_PRINT_ABS_TIME) {
-		ret = print_graph_abs_time(iter->ts, s);
-		if (!ret)
-			return TRACE_TYPE_PARTIAL_LINE;
-	}
+	int i;
 
-	/* Cpu */
-	if (tracer_flags.val & TRACE_GRAPH_PRINT_CPU) {
-		ret = print_graph_cpu(s, cpu);
-		if (ret == TRACE_TYPE_PARTIAL_LINE)
-			return TRACE_TYPE_PARTIAL_LINE;
-	}
+	if (data)
+		depth = per_cpu_ptr(data, iter->cpu)->depth;
 
-	/* Proc */
-	if (tracer_flags.val & TRACE_GRAPH_PRINT_PROC) {
-		ret = print_graph_proc(s, ent->pid);
-		if (ret == TRACE_TYPE_PARTIAL_LINE)
-			return TRACE_TYPE_PARTIAL_LINE;
-
-		ret = trace_seq_printf(s, " | ");
-		if (!ret)
-			return TRACE_TYPE_PARTIAL_LINE;
-	}
+	if (print_graph_prologue(iter, s, 0, 0))
+		return TRACE_TYPE_PARTIAL_LINE;
 
 	/* No overhead */
 	ret = print_graph_overhead(-1, s);
@@ -734,8 +743,8 @@ print_graph_comment(struct bprint_entry *trace, struct trace_seq *s,
 	}
 
 	/* Indentation */
-	if (trace->depth > 0)
-		for (i = 0; i < (trace->depth + 1) * TRACE_GRAPH_INDENT; i++) {
+	if (depth > 0)
+		for (i = 0; i < (depth + 1) * TRACE_GRAPH_INDENT; i++) {
 			ret = trace_seq_printf(s, " ");
 			if (!ret)
 				return TRACE_TYPE_PARTIAL_LINE;
@@ -746,9 +755,26 @@ print_graph_comment(struct bprint_entry *trace, struct trace_seq *s,
 	if (!ret)
 		return TRACE_TYPE_PARTIAL_LINE;
 
-	ret = trace_seq_bprintf(s, trace->fmt, trace->buf);
-	if (!ret)
-		return TRACE_TYPE_PARTIAL_LINE;
+	switch (iter->ent->type) {
+	case TRACE_BPRINT:
+		ret = trace_print_bprintk_msg_only(iter);
+		if (ret != TRACE_TYPE_HANDLED)
+			return ret;
+		break;
+	case TRACE_PRINT:
+		ret = trace_print_printk_msg_only(iter);
+		if (ret != TRACE_TYPE_HANDLED)
+			return ret;
+		break;
+	default:
+		event = ftrace_find_event(ent->type);
+		if (!event)
+			return TRACE_TYPE_UNHANDLED;
+
+		ret = event->trace(iter, sym_flags);
+		if (ret != TRACE_TYPE_HANDLED)
+			return ret;
+	}
 
 	/* Strip ending newline */
 	if (s->buffer[s->len - 1] == '\n') {
@@ -767,8 +793,8 @@ print_graph_comment(struct bprint_entry *trace, struct trace_seq *s,
 enum print_line_t
 print_graph_function(struct trace_iterator *iter)
 {
-	struct trace_seq *s = &iter->seq;
 	struct trace_entry *entry = iter->ent;
+	struct trace_seq *s = &iter->seq;
 
 	switch (entry->type) {
 	case TRACE_GRAPH_ENT: {
@@ -781,14 +807,11 @@ print_graph_function(struct trace_iterator *iter)
 		trace_assign_type(field, entry);
 		return print_graph_return(&field->ret, s, entry, iter);
 	}
-	case TRACE_BPRINT: {
-		struct bprint_entry *field;
-		trace_assign_type(field, entry);
-		return print_graph_comment(field, s, entry, iter);
-	}
 	default:
-		return TRACE_TYPE_UNHANDLED;
+		return print_graph_comment(s, entry, iter);
 	}
+
+	return TRACE_TYPE_HANDLED;
 }
 
 static void print_graph_headers(struct seq_file *s)
@@ -820,19 +843,21 @@ static void print_graph_headers(struct seq_file *s)
 
 static void graph_trace_open(struct trace_iterator *iter)
 {
-	/* pid on the last trace processed */
-	pid_t *last_pid = alloc_percpu(pid_t);
+	/* pid and depth on the last trace processed */
+	struct fgraph_data *data = alloc_percpu(struct fgraph_data);
 	int cpu;
 
-	if (!last_pid)
+	if (!data)
 		pr_warning("function graph tracer: not enough memory\n");
 	else
 		for_each_possible_cpu(cpu) {
-			pid_t *pid = per_cpu_ptr(last_pid, cpu);
+			pid_t *pid = &(per_cpu_ptr(data, cpu)->last_pid);
+			int *depth = &(per_cpu_ptr(data, cpu)->depth);
 			*pid = -1;
+			*depth = 0;
 		}
 
-	iter->private = last_pid;
+	iter->private = data;
 }
 
 static void graph_trace_close(struct trace_iterator *iter)
diff --git a/kernel/trace/trace_mmiotrace.c b/kernel/trace/trace_mmiotrace.c
index f095916e477..8e37fcddd8b 100644
--- a/kernel/trace/trace_mmiotrace.c
+++ b/kernel/trace/trace_mmiotrace.c
@@ -359,5 +359,5 @@ void mmio_trace_mapping(struct mmiotrace_map *map)
 
 int mmio_trace_printk(const char *fmt, va_list args)
 {
-	return trace_vprintk(0, -1, fmt, args);
+	return trace_vprintk(0, fmt, args);
 }
diff --git a/kernel/trace/trace_nop.c b/kernel/trace/trace_nop.c
index 9aa84bde23c..394f94417e2 100644
--- a/kernel/trace/trace_nop.c
+++ b/kernel/trace/trace_nop.c
@@ -91,6 +91,7 @@ struct tracer nop_trace __read_mostly =
 	.name		= "nop",
 	.init		= nop_trace_init,
 	.reset		= nop_trace_reset,
+	.wait_pipe	= poll_wait_pipe,
 #ifdef CONFIG_FTRACE_SELFTEST
 	.selftest	= trace_selftest_startup_nop,
 #endif
diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c
index ea9d3b410c7..d72b9a63b24 100644
--- a/kernel/trace/trace_output.c
+++ b/kernel/trace/trace_output.c
@@ -19,6 +19,38 @@ static struct hlist_head event_hash[EVENT_HASHSIZE] __read_mostly;
 
 static int next_event_type = __TRACE_LAST_TYPE + 1;
 
+enum print_line_t trace_print_bprintk_msg_only(struct trace_iterator *iter)
+{
+	struct trace_seq *s = &iter->seq;
+	struct trace_entry *entry = iter->ent;
+	struct bprint_entry *field;
+	int ret;
+
+	trace_assign_type(field, entry);
+
+	ret = trace_seq_bprintf(s, field->fmt, field->buf);
+	if (!ret)
+		return TRACE_TYPE_PARTIAL_LINE;
+
+	return TRACE_TYPE_HANDLED;
+}
+
+enum print_line_t trace_print_printk_msg_only(struct trace_iterator *iter)
+{
+	struct trace_seq *s = &iter->seq;
+	struct trace_entry *entry = iter->ent;
+	struct print_entry *field;
+	int ret;
+
+	trace_assign_type(field, entry);
+
+	ret = trace_seq_printf(s, "%s", field->buf);
+	if (!ret)
+		return TRACE_TYPE_PARTIAL_LINE;
+
+	return TRACE_TYPE_HANDLED;
+}
+
 /**
  * trace_seq_printf - sequence printing of trace information
  * @s: trace sequence descriptor
@@ -105,7 +137,7 @@ int trace_seq_putc(struct trace_seq *s, unsigned char c)
 	return 1;
 }
 
-int trace_seq_putmem(struct trace_seq *s, void *mem, size_t len)
+int trace_seq_putmem(struct trace_seq *s, const void *mem, size_t len)
 {
 	if (len > ((PAGE_SIZE - 1) - s->len))
 		return 0;
@@ -116,10 +148,10 @@ int trace_seq_putmem(struct trace_seq *s, void *mem, size_t len)
 	return len;
 }
 
-int trace_seq_putmem_hex(struct trace_seq *s, void *mem, size_t len)
+int trace_seq_putmem_hex(struct trace_seq *s, const void *mem, size_t len)
 {
 	unsigned char hex[HEX_CHARS];
-	unsigned char *data = mem;
+	const unsigned char *data = mem;
 	int i, j;
 
 #ifdef __BIG_ENDIAN
@@ -135,6 +167,19 @@ int trace_seq_putmem_hex(struct trace_seq *s, void *mem, size_t len)
 	return trace_seq_putmem(s, hex, j);
 }
 
+void *trace_seq_reserve(struct trace_seq *s, size_t len)
+{
+	void *ret;
+
+	if (len > ((PAGE_SIZE - 1) - s->len))
+		return NULL;
+
+	ret = s->buffer + s->len;
+	s->len += len;
+
+	return ret;
+}
+
 int trace_seq_path(struct trace_seq *s, struct path *path)
 {
 	unsigned char *p;
@@ -309,9 +354,9 @@ static int
 lat_print_generic(struct trace_seq *s, struct trace_entry *entry, int cpu)
 {
 	int hardirq, softirq;
-	char *comm;
+	char comm[TASK_COMM_LEN];
 
-	comm = trace_find_cmdline(entry->pid);
+	trace_find_cmdline(entry->pid, comm);
 	hardirq = entry->flags & TRACE_FLAG_HARDIRQ;
 	softirq = entry->flags & TRACE_FLAG_SOFTIRQ;
 
@@ -346,10 +391,12 @@ int trace_print_context(struct trace_iterator *iter)
 {
 	struct trace_seq *s = &iter->seq;
 	struct trace_entry *entry = iter->ent;
-	char *comm = trace_find_cmdline(entry->pid);
 	unsigned long long t = ns2usecs(iter->ts);
 	unsigned long usec_rem = do_div(t, USEC_PER_SEC);
 	unsigned long secs = (unsigned long)t;
+	char comm[TASK_COMM_LEN];
+
+	trace_find_cmdline(entry->pid, comm);
 
 	return trace_seq_printf(s, "%16s-%-5d [%03d] %5lu.%06lu: ",
 				comm, entry->pid, iter->cpu, secs, usec_rem);
@@ -372,7 +419,10 @@ int trace_print_lat_context(struct trace_iterator *iter)
 	rel_usecs = ns2usecs(next_ts - iter->ts);
 
 	if (verbose) {
-		char *comm = trace_find_cmdline(entry->pid);
+		char comm[TASK_COMM_LEN];
+
+		trace_find_cmdline(entry->pid, comm);
+
 		ret = trace_seq_printf(s, "%16s %5d %3d %d %08x %08lx [%08lx]"
 				       " %ld.%03ldms (+%ld.%03ldms): ", comm,
 				       entry->pid, iter->cpu, entry->flags,
@@ -444,6 +494,11 @@ int register_ftrace_event(struct trace_event *event)
 
 	mutex_lock(&trace_event_mutex);
 
+	if (!event) {
+		ret = next_event_type++;
+		goto out;
+	}
+
 	if (!event->type)
 		event->type = next_event_type++;
 	else if (event->type > __TRACE_LAST_TYPE) {
@@ -577,14 +632,15 @@ static enum print_line_t trace_ctxwake_print(struct trace_iterator *iter,
 					     char *delim)
 {
 	struct ctx_switch_entry *field;
-	char *comm;
+	char comm[TASK_COMM_LEN];
 	int S, T;
 
+
 	trace_assign_type(field, iter->ent);
 
 	T = task_state_char(field->next_state);
 	S = task_state_char(field->prev_state);
-	comm = trace_find_cmdline(field->next_pid);
+	trace_find_cmdline(field->next_pid, comm);
 	if (!trace_seq_printf(&iter->seq,
 			      " %5d:%3d:%c %s [%03d] %5d:%3d:%c %s\n",
 			      field->prev_pid,
diff --git a/kernel/trace/trace_output.h b/kernel/trace/trace_output.h
index 3b90e6ade1a..e0bde39c2dd 100644
--- a/kernel/trace/trace_output.h
+++ b/kernel/trace/trace_output.h
@@ -15,6 +15,11 @@ struct trace_event {
 	trace_print_func	binary;
 };
 
+extern enum print_line_t
+trace_print_bprintk_msg_only(struct trace_iterator *iter);
+extern enum print_line_t
+trace_print_printk_msg_only(struct trace_iterator *iter);
+
 extern int trace_seq_printf(struct trace_seq *s, const char *fmt, ...)
 	__attribute__ ((format (printf, 2, 3)));
 extern int
@@ -24,24 +29,27 @@ seq_print_ip_sym(struct trace_seq *s, unsigned long ip,
 		unsigned long sym_flags);
 extern ssize_t trace_seq_to_user(struct trace_seq *s, char __user *ubuf,
 				 size_t cnt);
-int trace_seq_puts(struct trace_seq *s, const char *str);
-int trace_seq_putc(struct trace_seq *s, unsigned char c);
-int trace_seq_putmem(struct trace_seq *s, void *mem, size_t len);
-int trace_seq_putmem_hex(struct trace_seq *s, void *mem, size_t len);
-int trace_seq_path(struct trace_seq *s, struct path *path);
-int seq_print_userip_objs(const struct userstack_entry *entry,
-			  struct trace_seq *s, unsigned long sym_flags);
-int seq_print_user_ip(struct trace_seq *s, struct mm_struct *mm,
-		      unsigned long ip, unsigned long sym_flags);
-
-int trace_print_context(struct trace_iterator *iter);
-int trace_print_lat_context(struct trace_iterator *iter);
-
-struct trace_event *ftrace_find_event(int type);
-int register_ftrace_event(struct trace_event *event);
-int unregister_ftrace_event(struct trace_event *event);
-
-enum print_line_t trace_nop_print(struct trace_iterator *iter, int flags);
+extern int trace_seq_puts(struct trace_seq *s, const char *str);
+extern int trace_seq_putc(struct trace_seq *s, unsigned char c);
+extern int trace_seq_putmem(struct trace_seq *s, const void *mem, size_t len);
+extern int trace_seq_putmem_hex(struct trace_seq *s, const void *mem,
+				size_t len);
+extern void *trace_seq_reserve(struct trace_seq *s, size_t len);
+extern int trace_seq_path(struct trace_seq *s, struct path *path);
+extern int seq_print_userip_objs(const struct userstack_entry *entry,
+				 struct trace_seq *s, unsigned long sym_flags);
+extern int seq_print_user_ip(struct trace_seq *s, struct mm_struct *mm,
+			     unsigned long ip, unsigned long sym_flags);
+
+extern int trace_print_context(struct trace_iterator *iter);
+extern int trace_print_lat_context(struct trace_iterator *iter);
+
+extern struct trace_event *ftrace_find_event(int type);
+extern int register_ftrace_event(struct trace_event *event);
+extern int unregister_ftrace_event(struct trace_event *event);
+
+extern enum print_line_t trace_nop_print(struct trace_iterator *iter,
+					 int flags);
 
 #define MAX_MEMHEX_BYTES	8
 #define HEX_CHARS		(MAX_MEMHEX_BYTES*2 + 1)
diff --git a/kernel/trace/trace_power.c b/kernel/trace/trace_power.c
index 91ce672fb03..bae791ebcc5 100644
--- a/kernel/trace/trace_power.c
+++ b/kernel/trace/trace_power.c
@@ -122,12 +122,16 @@ fail_start:
 static void start_power_trace(struct trace_array *tr)
 {
 	trace_power_enabled = 1;
-	tracing_power_register();
 }
 
 static void stop_power_trace(struct trace_array *tr)
 {
 	trace_power_enabled = 0;
+}
+
+static void power_trace_reset(struct trace_array *tr)
+{
+	trace_power_enabled = 0;
 	unregister_trace_power_start(probe_power_start);
 	unregister_trace_power_end(probe_power_end);
 	unregister_trace_power_mark(probe_power_mark);
@@ -188,7 +192,7 @@ static struct tracer power_tracer __read_mostly =
 	.init		= power_trace_init,
 	.start		= start_power_trace,
 	.stop		= stop_power_trace,
-	.reset		= stop_power_trace,
+	.reset		= power_trace_reset,
 	.print_line	= power_print_line,
 };
 
diff --git a/kernel/trace/trace_printk.c b/kernel/trace/trace_printk.c
index 486785214e3..eb81556107f 100644
--- a/kernel/trace/trace_printk.c
+++ b/kernel/trace/trace_printk.c
@@ -112,7 +112,7 @@ int __trace_bprintk(unsigned long ip, const char *fmt, ...)
 		return 0;
 
 	va_start(ap, fmt);
-	ret = trace_vbprintk(ip, task_curr_ret_stack(current), fmt, ap);
+	ret = trace_vbprintk(ip, fmt, ap);
 	va_end(ap);
 	return ret;
 }
@@ -126,7 +126,7 @@ int __ftrace_vbprintk(unsigned long ip, const char *fmt, va_list ap)
 	if (!(trace_flags & TRACE_ITER_PRINTK))
 		return 0;
 
-	return trace_vbprintk(ip, task_curr_ret_stack(current), fmt, ap);
+	return trace_vbprintk(ip, fmt, ap);
 }
 EXPORT_SYMBOL_GPL(__ftrace_vbprintk);
 
@@ -139,7 +139,7 @@ int __trace_printk(unsigned long ip, const char *fmt, ...)
 		return 0;
 
 	va_start(ap, fmt);
-	ret = trace_vprintk(ip, task_curr_ret_stack(current), fmt, ap);
+	ret = trace_vprintk(ip, fmt, ap);
 	va_end(ap);
 	return ret;
 }
@@ -150,7 +150,7 @@ int __ftrace_vprintk(unsigned long ip, const char *fmt, va_list ap)
 	if (!(trace_flags & TRACE_ITER_PRINTK))
 		return 0;
 
-	return trace_vprintk(ip, task_curr_ret_stack(current), fmt, ap);
+	return trace_vprintk(ip, fmt, ap);
 }
 EXPORT_SYMBOL_GPL(__ftrace_vprintk);
 
diff --git a/kernel/trace/trace_sched_switch.c b/kernel/trace/trace_sched_switch.c
index 77132c2cf3d..de35f200abd 100644
--- a/kernel/trace/trace_sched_switch.c
+++ b/kernel/trace/trace_sched_switch.c
@@ -18,6 +18,7 @@ static struct trace_array	*ctx_trace;
 static int __read_mostly	tracer_enabled;
 static int			sched_ref;
 static DEFINE_MUTEX(sched_register_mutex);
+static int			sched_stopped;
 
 static void
 probe_sched_switch(struct rq *__rq, struct task_struct *prev,
@@ -28,7 +29,7 @@ probe_sched_switch(struct rq *__rq, struct task_struct *prev,
 	int cpu;
 	int pc;
 
-	if (!sched_ref)
+	if (!sched_ref || sched_stopped)
 		return;
 
 	tracing_record_cmdline(prev);
@@ -193,6 +194,7 @@ static void stop_sched_trace(struct trace_array *tr)
 static int sched_switch_trace_init(struct trace_array *tr)
 {
 	ctx_trace = tr;
+	tracing_reset_online_cpus(tr);
 	tracing_start_sched_switch_record();
 	return 0;
 }
@@ -205,13 +207,12 @@ static void sched_switch_trace_reset(struct trace_array *tr)
 
 static void sched_switch_trace_start(struct trace_array *tr)
 {
-	tracing_reset_online_cpus(tr);
-	tracing_start_sched_switch();
+	sched_stopped = 0;
 }
 
 static void sched_switch_trace_stop(struct trace_array *tr)
 {
-	tracing_stop_sched_switch();
+	sched_stopped = 1;
 }
 
 static struct tracer sched_switch_trace __read_mostly =
diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c
index b9109126706..499d01c44cd 100644
--- a/kernel/trace/trace_selftest.c
+++ b/kernel/trace/trace_selftest.c
@@ -250,6 +250,28 @@ trace_selftest_startup_function(struct tracer *trace, struct trace_array *tr)
 
 
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
+
+/* Maximum number of functions to trace before diagnosing a hang */
+#define GRAPH_MAX_FUNC_TEST	100000000
+
+static void __ftrace_dump(bool disable_tracing);
+static unsigned int graph_hang_thresh;
+
+/* Wrap the real function entry probe to avoid possible hanging */
+static int trace_graph_entry_watchdog(struct ftrace_graph_ent *trace)
+{
+	/* This is harmlessly racy, we want to approximately detect a hang */
+	if (unlikely(++graph_hang_thresh > GRAPH_MAX_FUNC_TEST)) {
+		ftrace_graph_stop();
+		printk(KERN_WARNING "BUG: Function graph tracer hang!\n");
+		if (ftrace_dump_on_oops)
+			__ftrace_dump(false);
+		return 0;
+	}
+
+	return trace_graph_entry(trace);
+}
+
 /*
  * Pretty much the same than for the function tracer from which the selftest
  * has been borrowed.
@@ -261,15 +283,29 @@ trace_selftest_startup_function_graph(struct tracer *trace,
 	int ret;
 	unsigned long count;
 
-	ret = tracer_init(trace, tr);
+	/*
+	 * Simulate the init() callback but we attach a watchdog callback
+	 * to detect and recover from possible hangs
+	 */
+	tracing_reset_online_cpus(tr);
+	ret = register_ftrace_graph(&trace_graph_return,
+				    &trace_graph_entry_watchdog);
 	if (ret) {
 		warn_failed_init_tracer(trace, ret);
 		goto out;
 	}
+	tracing_start_cmdline_record();
 
 	/* Sleep for a 1/10 of a second */
 	msleep(100);
 
+	/* Have we just recovered from a hang? */
+	if (graph_hang_thresh > GRAPH_MAX_FUNC_TEST) {
+		tracing_selftest_disabled = true;
+		ret = -1;
+		goto out;
+	}
+
 	tracing_stop();
 
 	/* check the trace buffer */
@@ -317,6 +353,14 @@ trace_selftest_startup_irqsoff(struct tracer *trace, struct trace_array *tr)
 	local_irq_disable();
 	udelay(100);
 	local_irq_enable();
+
+	/*
+	 * Stop the tracer to avoid a warning subsequent
+	 * to buffer flipping failure because tracing_stop()
+	 * disables the tr and max buffers, making flipping impossible
+	 * in case of parallels max irqs off latencies.
+	 */
+	trace->stop(tr);
 	/* stop the tracing. */
 	tracing_stop();
 	/* check both trace buffers */
@@ -371,6 +415,14 @@ trace_selftest_startup_preemptoff(struct tracer *trace, struct trace_array *tr)
 	preempt_disable();
 	udelay(100);
 	preempt_enable();
+
+	/*
+	 * Stop the tracer to avoid a warning subsequent
+	 * to buffer flipping failure because tracing_stop()
+	 * disables the tr and max buffers, making flipping impossible
+	 * in case of parallels max preempt off latencies.
+	 */
+	trace->stop(tr);
 	/* stop the tracing. */
 	tracing_stop();
 	/* check both trace buffers */
@@ -416,7 +468,7 @@ trace_selftest_startup_preemptirqsoff(struct tracer *trace, struct trace_array *
 	ret = tracer_init(trace, tr);
 	if (ret) {
 		warn_failed_init_tracer(trace, ret);
-		goto out;
+		goto out_no_start;
 	}
 
 	/* reset the max latency */
@@ -430,31 +482,35 @@ trace_selftest_startup_preemptirqsoff(struct tracer *trace, struct trace_array *
 	/* reverse the order of preempt vs irqs */
 	local_irq_enable();
 
+	/*
+	 * Stop the tracer to avoid a warning subsequent
+	 * to buffer flipping failure because tracing_stop()
+	 * disables the tr and max buffers, making flipping impossible
+	 * in case of parallels max irqs/preempt off latencies.
+	 */
+	trace->stop(tr);
 	/* stop the tracing. */
 	tracing_stop();
 	/* check both trace buffers */
 	ret = trace_test_buffer(tr, NULL);
-	if (ret) {
-		tracing_start();
+	if (ret)
 		goto out;
-	}
 
 	ret = trace_test_buffer(&max_tr, &count);
-	if (ret) {
-		tracing_start();
+	if (ret)
 		goto out;
-	}
 
 	if (!ret && !count) {
 		printk(KERN_CONT ".. no entries found ..");
 		ret = -1;
-		tracing_start();
 		goto out;
 	}
 
 	/* do the test by disabling interrupts first this time */
 	tracing_max_latency = 0;
 	tracing_start();
+	trace->start(tr);
+
 	preempt_disable();
 	local_irq_disable();
 	udelay(100);
@@ -462,6 +518,7 @@ trace_selftest_startup_preemptirqsoff(struct tracer *trace, struct trace_array *
 	/* reverse the order of preempt vs irqs */
 	local_irq_enable();
 
+	trace->stop(tr);
 	/* stop the tracing. */
 	tracing_stop();
 	/* check both trace buffers */
@@ -477,9 +534,10 @@ trace_selftest_startup_preemptirqsoff(struct tracer *trace, struct trace_array *
 		goto out;
 	}
 
- out:
-	trace->reset(tr);
+out:
 	tracing_start();
+out_no_start:
+	trace->reset(tr);
 	tracing_max_latency = save_max;
 
 	return ret;
diff --git a/kernel/trace/trace_stat.c b/kernel/trace/trace_stat.c
index 39310e3434e..acdebd771a9 100644
--- a/kernel/trace/trace_stat.c
+++ b/kernel/trace/trace_stat.c
@@ -75,7 +75,7 @@ static int stat_seq_init(struct tracer_stat_session *session)
 {
 	struct trace_stat_list *iter_entry, *new_entry;
 	struct tracer_stat *ts = session->ts;
-	void *prev_stat;
+	void *stat;
 	int ret = 0;
 	int i;
 
@@ -85,6 +85,10 @@ static int stat_seq_init(struct tracer_stat_session *session)
 	if (!ts->stat_cmp)
 		ts->stat_cmp = dummy_cmp;
 
+	stat = ts->stat_start();
+	if (!stat)
+		goto exit;
+
 	/*
 	 * The first entry. Actually this is the second, but the first
 	 * one (the stat_list head) is pointless.
@@ -99,14 +103,19 @@ static int stat_seq_init(struct tracer_stat_session *session)
 
 	list_add(&new_entry->list, &session->stat_list);
 
-	new_entry->stat = ts->stat_start();
-	prev_stat = new_entry->stat;
+	new_entry->stat = stat;
 
 	/*
 	 * Iterate over the tracer stat entries and store them in a sorted
 	 * list.
 	 */
 	for (i = 1; ; i++) {
+		stat = ts->stat_next(stat, i);
+
+		/* End of insertion */
+		if (!stat)
+			break;
+
 		new_entry = kmalloc(sizeof(struct trace_stat_list), GFP_KERNEL);
 		if (!new_entry) {
 			ret = -ENOMEM;
@@ -114,31 +123,23 @@ static int stat_seq_init(struct tracer_stat_session *session)
 		}
 
 		INIT_LIST_HEAD(&new_entry->list);
-		new_entry->stat = ts->stat_next(prev_stat, i);
+		new_entry->stat = stat;
 
-		/* End of insertion */
-		if (!new_entry->stat)
-			break;
-
-		list_for_each_entry(iter_entry, &session->stat_list, list) {
+		list_for_each_entry_reverse(iter_entry, &session->stat_list,
+				list) {
 
 			/* Insertion with a descendent sorting */
-			if (ts->stat_cmp(new_entry->stat,
-						iter_entry->stat) > 0) {
-
-				list_add_tail(&new_entry->list,
-						&iter_entry->list);
-				break;
+			if (ts->stat_cmp(iter_entry->stat,
+					new_entry->stat) >= 0) {
 
-			/* The current smaller value */
-			} else if (list_is_last(&iter_entry->list,
-						&session->stat_list)) {
 				list_add(&new_entry->list, &iter_entry->list);
 				break;
 			}
 		}
 
-		prev_stat = new_entry->stat;
+		/* The current larger value */
+		if (list_empty(&new_entry->list))
+			list_add(&new_entry->list, &session->stat_list);
 	}
 exit:
 	mutex_unlock(&session->stat_mutex);
@@ -160,7 +161,7 @@ static void *stat_seq_start(struct seq_file *s, loff_t *pos)
 
 	/* If we are in the beginning of the file, print the headers */
 	if (!*pos && session->ts->stat_headers)
-		session->ts->stat_headers(s);
+		return SEQ_START_TOKEN;
 
 	return seq_list_start(&session->stat_list, *pos);
 }
@@ -169,6 +170,9 @@ static void *stat_seq_next(struct seq_file *s, void *p, loff_t *pos)
 {
 	struct tracer_stat_session *session = s->private;
 
+	if (p == SEQ_START_TOKEN)
+		return seq_list_start(&session->stat_list, *pos);
+
 	return seq_list_next(p, &session->stat_list, pos);
 }
 
@@ -183,6 +187,9 @@ static int stat_seq_show(struct seq_file *s, void *v)
 	struct tracer_stat_session *session = s->private;
 	struct trace_stat_list *l = list_entry(v, struct trace_stat_list, list);
 
+	if (v == SEQ_START_TOKEN)
+		return session->ts->stat_headers(s);
+
 	return session->ts->stat_show(s, l->stat);
 }
 
diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c
index 66cf97449af..a2a3af29c94 100644
--- a/kernel/trace/trace_syscalls.c
+++ b/kernel/trace/trace_syscalls.c
@@ -1,21 +1,112 @@
-#include <linux/ftrace.h>
 #include <linux/kernel.h>
-
+#include <linux/ftrace.h>
 #include <asm/syscall.h>
 
 #include "trace_output.h"
 #include "trace.h"
 
-static atomic_t refcount;
+/* Keep a counter of the syscall tracing users */
+static int refcount;
+
+/* Prevent from races on thread flags toggling */
+static DEFINE_MUTEX(syscall_trace_lock);
+
+/* Option to display the parameters types */
+enum {
+	TRACE_SYSCALLS_OPT_TYPES = 0x1,
+};
+
+static struct tracer_opt syscalls_opts[] = {
+	{ TRACER_OPT(syscall_arg_type, TRACE_SYSCALLS_OPT_TYPES) },
+	{ }
+};
+
+static struct tracer_flags syscalls_flags = {
+	.val = 0, /* By default: no parameters types */
+	.opts = syscalls_opts
+};
+
+enum print_line_t
+print_syscall_enter(struct trace_iterator *iter, int flags)
+{
+	struct trace_seq *s = &iter->seq;
+	struct trace_entry *ent = iter->ent;
+	struct syscall_trace_enter *trace;
+	struct syscall_metadata *entry;
+	int i, ret, syscall;
+
+	trace_assign_type(trace, ent);
+
+	syscall = trace->nr;
+
+	entry = syscall_nr_to_meta(syscall);
+	if (!entry)
+		goto end;
+
+	ret = trace_seq_printf(s, "%s(", entry->name);
+	if (!ret)
+		return TRACE_TYPE_PARTIAL_LINE;
+
+	for (i = 0; i < entry->nb_args; i++) {
+		/* parameter types */
+		if (syscalls_flags.val & TRACE_SYSCALLS_OPT_TYPES) {
+			ret = trace_seq_printf(s, "%s ", entry->types[i]);
+			if (!ret)
+				return TRACE_TYPE_PARTIAL_LINE;
+		}
+		/* parameter values */
+		ret = trace_seq_printf(s, "%s: %lx%s ", entry->args[i],
+				       trace->args[i],
+				       i == entry->nb_args - 1 ? ")" : ",");
+		if (!ret)
+			return TRACE_TYPE_PARTIAL_LINE;
+	}
+
+end:
+	trace_seq_printf(s, "\n");
+	return TRACE_TYPE_HANDLED;
+}
+
+enum print_line_t
+print_syscall_exit(struct trace_iterator *iter, int flags)
+{
+	struct trace_seq *s = &iter->seq;
+	struct trace_entry *ent = iter->ent;
+	struct syscall_trace_exit *trace;
+	int syscall;
+	struct syscall_metadata *entry;
+	int ret;
+
+	trace_assign_type(trace, ent);
+
+	syscall = trace->nr;
+
+	entry = syscall_nr_to_meta(syscall);
+	if (!entry) {
+		trace_seq_printf(s, "\n");
+		return TRACE_TYPE_HANDLED;
+	}
+
+	ret = trace_seq_printf(s, "%s -> 0x%lx\n", entry->name,
+				trace->ret);
+	if (!ret)
+		return TRACE_TYPE_PARTIAL_LINE;
+
+	return TRACE_TYPE_HANDLED;
+}
 
 void start_ftrace_syscalls(void)
 {
 	unsigned long flags;
 	struct task_struct *g, *t;
 
-	if (atomic_inc_return(&refcount) != 1)
-		goto out;
+	mutex_lock(&syscall_trace_lock);
 
+	/* Don't enable the flag on the tasks twice */
+	if (++refcount != 1)
+		goto unlock;
+
+	arch_init_ftrace_syscalls();
 	read_lock_irqsave(&tasklist_lock, flags);
 
 	do_each_thread(g, t) {
@@ -23,8 +114,9 @@ void start_ftrace_syscalls(void)
 	} while_each_thread(g, t);
 
 	read_unlock_irqrestore(&tasklist_lock, flags);
-out:
-	atomic_dec(&refcount);
+
+unlock:
+	mutex_unlock(&syscall_trace_lock);
 }
 
 void stop_ftrace_syscalls(void)
@@ -32,8 +124,11 @@ void stop_ftrace_syscalls(void)
 	unsigned long flags;
 	struct task_struct *g, *t;
 
-	if (atomic_dec_return(&refcount))
-		goto out;
+	mutex_lock(&syscall_trace_lock);
+
+	/* There are perhaps still some users */
+	if (--refcount)
+		goto unlock;
 
 	read_lock_irqsave(&tasklist_lock, flags);
 
@@ -42,26 +137,64 @@ void stop_ftrace_syscalls(void)
 	} while_each_thread(g, t);
 
 	read_unlock_irqrestore(&tasklist_lock, flags);
-out:
-	atomic_inc(&refcount);
+
+unlock:
+	mutex_unlock(&syscall_trace_lock);
 }
 
 void ftrace_syscall_enter(struct pt_regs *regs)
 {
+	struct syscall_trace_enter *entry;
+	struct syscall_metadata *sys_data;
+	struct ring_buffer_event *event;
+	int size;
 	int syscall_nr;
 
 	syscall_nr = syscall_get_nr(current, regs);
 
-	trace_printk("syscall %d enter\n", syscall_nr);
+	sys_data = syscall_nr_to_meta(syscall_nr);
+	if (!sys_data)
+		return;
+
+	size = sizeof(*entry) + sizeof(unsigned long) * sys_data->nb_args;
+
+	event = trace_current_buffer_lock_reserve(TRACE_SYSCALL_ENTER, size,
+							0, 0);
+	if (!event)
+		return;
+
+	entry = ring_buffer_event_data(event);
+	entry->nr = syscall_nr;
+	syscall_get_arguments(current, regs, 0, sys_data->nb_args, entry->args);
+
+	trace_current_buffer_unlock_commit(event, 0, 0);
+	trace_wake_up();
 }
 
 void ftrace_syscall_exit(struct pt_regs *regs)
 {
+	struct syscall_trace_exit *entry;
+	struct syscall_metadata *sys_data;
+	struct ring_buffer_event *event;
 	int syscall_nr;
 
 	syscall_nr = syscall_get_nr(current, regs);
 
-	trace_printk("syscall %d exit\n", syscall_nr);
+	sys_data = syscall_nr_to_meta(syscall_nr);
+	if (!sys_data)
+		return;
+
+	event = trace_current_buffer_lock_reserve(TRACE_SYSCALL_EXIT,
+				sizeof(*entry), 0, 0);
+	if (!event)
+		return;
+
+	entry = ring_buffer_event_data(event);
+	entry->nr = syscall_nr;
+	entry->ret = syscall_get_return_value(current, regs);
+
+	trace_current_buffer_unlock_commit(event, 0, 0);
+	trace_wake_up();
 }
 
 static int init_syscall_tracer(struct trace_array *tr)
@@ -74,20 +207,24 @@ static int init_syscall_tracer(struct trace_array *tr)
 static void reset_syscall_tracer(struct trace_array *tr)
 {
 	stop_ftrace_syscalls();
+	tracing_reset_online_cpus(tr);
 }
 
 static struct trace_event syscall_enter_event = {
-	.type		= TRACE_SYSCALL_ENTER,
+	.type	 	= TRACE_SYSCALL_ENTER,
+	.trace		= print_syscall_enter,
 };
 
 static struct trace_event syscall_exit_event = {
-	.type		= TRACE_SYSCALL_EXIT,
+	.type	 	= TRACE_SYSCALL_EXIT,
+	.trace		= print_syscall_exit,
 };
 
 static struct tracer syscall_tracer __read_mostly = {
-	.name		= "syscall",
+	.name	     	= "syscall",
 	.init		= init_syscall_tracer,
-	.reset		= reset_syscall_tracer
+	.reset		= reset_syscall_tracer,
+	.flags		= &syscalls_flags,
 };
 
 __init int register_ftrace_syscalls(void)
diff --git a/kernel/trace/trace_workqueue.c b/kernel/trace/trace_workqueue.c
index 9ab035b58cf..797201e4a13 100644
--- a/kernel/trace/trace_workqueue.c
+++ b/kernel/trace/trace_workqueue.c
@@ -196,6 +196,11 @@ static int workqueue_stat_show(struct seq_file *s, void *p)
 	struct pid *pid;
 	struct task_struct *tsk;
 
+	spin_lock_irqsave(&workqueue_cpu_stat(cpu)->lock, flags);
+	if (&cws->list == workqueue_cpu_stat(cpu)->list.next)
+		seq_printf(s, "\n");
+	spin_unlock_irqrestore(&workqueue_cpu_stat(cpu)->lock, flags);
+
 	pid = find_get_pid(cws->pid);
 	if (pid) {
 		tsk = get_pid_task(pid, PIDTYPE_PID);
@@ -208,18 +213,13 @@ static int workqueue_stat_show(struct seq_file *s, void *p)
 		put_pid(pid);
 	}
 
-	spin_lock_irqsave(&workqueue_cpu_stat(cpu)->lock, flags);
-	if (&cws->list == workqueue_cpu_stat(cpu)->list.next)
-		seq_printf(s, "\n");
-	spin_unlock_irqrestore(&workqueue_cpu_stat(cpu)->lock, flags);
-
 	return 0;
 }
 
 static int workqueue_stat_headers(struct seq_file *s)
 {
 	seq_printf(s, "# CPU  INSERTED  EXECUTED   NAME\n");
-	seq_printf(s, "# |      |         |          |\n\n");
+	seq_printf(s, "# |      |         |          |\n");
 	return 0;
 }
 
diff --git a/kernel/tracepoint.c b/kernel/tracepoint.c
index 79602740bbb..1ef5d3a601c 100644
--- a/kernel/tracepoint.c
+++ b/kernel/tracepoint.c
@@ -272,12 +272,15 @@ static void disable_tracepoint(struct tracepoint *elem)
  *
  * Updates the probe callback corresponding to a range of tracepoints.
  */
-void tracepoint_update_probe_range(struct tracepoint *begin,
-	struct tracepoint *end)
+void
+tracepoint_update_probe_range(struct tracepoint *begin, struct tracepoint *end)
 {
 	struct tracepoint *iter;
 	struct tracepoint_entry *mark_entry;
 
+	if (!begin)
+		return;
+
 	mutex_lock(&tracepoints_mutex);
 	for (iter = begin; iter < end; iter++) {
 		mark_entry = get_tracepoint(iter->name);
diff --git a/kernel/user.c b/kernel/user.c
index fbb300e6191..850e0ba41c1 100644
--- a/kernel/user.c
+++ b/kernel/user.c
@@ -20,7 +20,7 @@
 
 struct user_namespace init_user_ns = {
 	.kref = {
-		.refcount	= ATOMIC_INIT(1),
+		.refcount	= ATOMIC_INIT(2),
 	},
 	.creator = &root_user,
 };
diff --git a/kernel/utsname_sysctl.c b/kernel/utsname_sysctl.c
index 3b34b354593..92359cc747a 100644
--- a/kernel/utsname_sysctl.c
+++ b/kernel/utsname_sysctl.c
@@ -37,7 +37,7 @@ static void put_uts(ctl_table *table, int write, void *which)
 		up_write(&uts_sem);
 }
 
-#ifdef CONFIG_PROC_FS
+#ifdef CONFIG_PROC_SYSCTL
 /*
  *	Special case of dostring for the UTS structure. This has locks
  *	to observe. Should this be in kernel/sys.c ????
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index e53ee18ef43..b6b966ce145 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -49,8 +49,6 @@ struct cpu_workqueue_struct {
 
 	struct workqueue_struct *wq;
 	struct task_struct *thread;
-
-	int run_depth;		/* Detect run_workqueue() recursion depth */
 } ____cacheline_aligned;
 
 /*
@@ -269,13 +267,6 @@ DEFINE_TRACE(workqueue_execution);
 static void run_workqueue(struct cpu_workqueue_struct *cwq)
 {
 	spin_lock_irq(&cwq->lock);
-	cwq->run_depth++;
-	if (cwq->run_depth > 3) {
-		/* morton gets to eat his hat */
-		printk("%s: recursion depth exceeded: %d\n",
-			__func__, cwq->run_depth);
-		dump_stack();
-	}
 	while (!list_empty(&cwq->worklist)) {
 		struct work_struct *work = list_entry(cwq->worklist.next,
 						struct work_struct, entry);
@@ -318,7 +309,6 @@ static void run_workqueue(struct cpu_workqueue_struct *cwq)
 		spin_lock_irq(&cwq->lock);
 		cwq->current_work = NULL;
 	}
-	cwq->run_depth--;
 	spin_unlock_irq(&cwq->lock);
 }
 
@@ -375,29 +365,20 @@ static void insert_wq_barrier(struct cpu_workqueue_struct *cwq,
 
 static int flush_cpu_workqueue(struct cpu_workqueue_struct *cwq)
 {
-	int active;
+	int active = 0;
+	struct wq_barrier barr;
 
-	if (cwq->thread == current) {
-		/*
-		 * Probably keventd trying to flush its own queue. So simply run
-		 * it by hand rather than deadlocking.
-		 */
-		run_workqueue(cwq);
-		active = 1;
-	} else {
-		struct wq_barrier barr;
+	WARN_ON(cwq->thread == current);
 
-		active = 0;
-		spin_lock_irq(&cwq->lock);
-		if (!list_empty(&cwq->worklist) || cwq->current_work != NULL) {
-			insert_wq_barrier(cwq, &barr, &cwq->worklist);
-			active = 1;
-		}
-		spin_unlock_irq(&cwq->lock);
-
-		if (active)
-			wait_for_completion(&barr.done);
+	spin_lock_irq(&cwq->lock);
+	if (!list_empty(&cwq->worklist) || cwq->current_work != NULL) {
+		insert_wq_barrier(cwq, &barr, &cwq->worklist);
+		active = 1;
 	}
+	spin_unlock_irq(&cwq->lock);
+
+	if (active)
+		wait_for_completion(&barr.done);
 
 	return active;
 }
@@ -423,7 +404,7 @@ void flush_workqueue(struct workqueue_struct *wq)
 	might_sleep();
 	lock_map_acquire(&wq->lockdep_map);
 	lock_map_release(&wq->lockdep_map);
-	for_each_cpu_mask_nr(cpu, *cpu_map)
+	for_each_cpu(cpu, cpu_map)
 		flush_cpu_workqueue(per_cpu_ptr(wq->cpu_wq, cpu));
 }
 EXPORT_SYMBOL_GPL(flush_workqueue);
@@ -554,7 +535,7 @@ static void wait_on_work(struct work_struct *work)
 	wq = cwq->wq;
 	cpu_map = wq_cpu_map(wq);
 
-	for_each_cpu_mask_nr(cpu, *cpu_map)
+	for_each_cpu(cpu, cpu_map)
 		wait_on_cpu_work(per_cpu_ptr(wq->cpu_wq, cpu), work);
 }
 
@@ -925,7 +906,7 @@ void destroy_workqueue(struct workqueue_struct *wq)
 	list_del(&wq->list);
 	spin_unlock(&workqueue_lock);
 
-	for_each_cpu_mask_nr(cpu, *cpu_map)
+	for_each_cpu(cpu, cpu_map)
 		cleanup_workqueue_thread(per_cpu_ptr(wq->cpu_wq, cpu));
  	cpu_maps_update_done();