Merge commit 'v2.6.32' into reiserfs/kill-bkl

Merge-reason: The tree was based 2.6.31. It's better to be up to date
with 2.6.32. Although no conflicting changes were made in between,
it gives benchmarking results closer to the lastest kernel behaviour.

143 files changed, 17683 insertions, 14867 deletions

diff --git a/kernel/Makefile b/kernel/Makefile
index 2093a691f1c2..d7c13d249b2d 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -58,7 +58,6 @@ obj-$(CONFIG_KEXEC) += kexec.o
 obj-$(CONFIG_BACKTRACE_SELF_TEST) += backtracetest.o
 obj-$(CONFIG_COMPAT) += compat.o
 obj-$(CONFIG_CGROUPS) += cgroup.o
-obj-$(CONFIG_CGROUP_DEBUG) += cgroup_debug.o
 obj-$(CONFIG_CGROUP_FREEZER) += cgroup_freezer.o
 obj-$(CONFIG_CPUSETS) += cpuset.o
 obj-$(CONFIG_CGROUP_NS) += ns_cgroup.o
@@ -80,26 +79,23 @@ obj-$(CONFIG_DETECT_HUNG_TASK) += hung_task.o
 obj-$(CONFIG_GENERIC_HARDIRQS) += irq/
 obj-$(CONFIG_SECCOMP) += seccomp.o
 obj-$(CONFIG_RCU_TORTURE_TEST) += rcutorture.o
-obj-$(CONFIG_CLASSIC_RCU) += rcuclassic.o
 obj-$(CONFIG_TREE_RCU) += rcutree.o
-obj-$(CONFIG_PREEMPT_RCU) += rcupreempt.o
+obj-$(CONFIG_TREE_PREEMPT_RCU) += rcutree.o
 obj-$(CONFIG_TREE_RCU_TRACE) += rcutree_trace.o
-obj-$(CONFIG_PREEMPT_RCU_TRACE) += rcupreempt_trace.o
 obj-$(CONFIG_RELAY) += relay.o
 obj-$(CONFIG_SYSCTL) += utsname_sysctl.o
 obj-$(CONFIG_TASK_DELAY_ACCT) += delayacct.o
 obj-$(CONFIG_TASKSTATS) += taskstats.o tsacct.o
-obj-$(CONFIG_MARKERS) += marker.o
 obj-$(CONFIG_TRACEPOINTS) += tracepoint.o
 obj-$(CONFIG_LATENCYTOP) += latencytop.o
-obj-$(CONFIG_HAVE_GENERIC_DMA_COHERENT) += dma-coherent.o
 obj-$(CONFIG_FUNCTION_TRACER) += trace/
 obj-$(CONFIG_TRACING) += trace/
 obj-$(CONFIG_X86_DS) += trace/
 obj-$(CONFIG_RING_BUFFER) += trace/
 obj-$(CONFIG_SMP) += sched_cpupri.o
 obj-$(CONFIG_SLOW_WORK) += slow-work.o
-obj-$(CONFIG_PERF_COUNTERS) += perf_counter.o
+obj-$(CONFIG_SLOW_WORK_DEBUG) += slow-work-debugfs.o
+obj-$(CONFIG_PERF_EVENTS) += perf_event.o
 
 ifneq ($(CONFIG_SCHED_OMIT_FRAME_POINTER),y)
 # According to Alan Modra <alan@linuxcare.com.au>, the -fno-omit-frame-pointer is
@@ -119,7 +115,7 @@ $(obj)/config_data.gz: .config FORCE
 	$(call if_changed,gzip)
 
 quiet_cmd_ikconfiggz = IKCFG   $@
-      cmd_ikconfiggz = (echo "static const char kernel_config_data[] = MAGIC_START"; cat $< | scripts/bin2c; echo "MAGIC_END;") > $@
+      cmd_ikconfiggz = (echo "static const char kernel_config_data[] __used = MAGIC_START"; cat $< | scripts/bin2c; echo "MAGIC_END;") > $@
 targets += config_data.h
 $(obj)/config_data.h: $(obj)/config_data.gz FORCE
 	$(call if_changed,ikconfiggz)
diff --git a/kernel/acct.c b/kernel/acct.c
index 9f3391090b3e..9a4715a2f6bf 100644
--- a/kernel/acct.c
+++ b/kernel/acct.c
@@ -491,13 +491,17 @@ static void do_acct_process(struct bsd_acct_struct *acct,
 	u64 run_time;
 	struct timespec uptime;
 	struct tty_struct *tty;
+	const struct cred *orig_cred;
+
+	/* Perform file operations on behalf of whoever enabled accounting */
+	orig_cred = override_creds(file->f_cred);
 
 	/*
 	 * First check to see if there is enough free_space to continue
 	 * the process accounting system.
 	 */
 	if (!check_free_space(acct, file))
-		return;
+		goto out;
 
 	/*
 	 * Fill the accounting struct with the needed info as recorded
@@ -578,6 +582,8 @@ static void do_acct_process(struct bsd_acct_struct *acct,
 			       sizeof(acct_t), &file->f_pos);
 	current->signal->rlim[RLIMIT_FSIZE].rlim_cur = flim;
 	set_fs(fs);
+out:
+	revert_creds(orig_cred);
 }
 
 /**
diff --git a/kernel/audit.c b/kernel/audit.c
index defc2e6f1e3b..5feed232be9d 100644
--- a/kernel/audit.c
+++ b/kernel/audit.c
@@ -855,18 +855,24 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
 		break;
 	}
 	case AUDIT_SIGNAL_INFO:
-		err = security_secid_to_secctx(audit_sig_sid, &ctx, &len);
-		if (err)
-			return err;
+		len = 0;
+		if (audit_sig_sid) {
+			err = security_secid_to_secctx(audit_sig_sid, &ctx, &len);
+			if (err)
+				return err;
+		}
 		sig_data = kmalloc(sizeof(*sig_data) + len, GFP_KERNEL);
 		if (!sig_data) {
-			security_release_secctx(ctx, len);
+			if (audit_sig_sid)
+				security_release_secctx(ctx, len);
 			return -ENOMEM;
 		}
 		sig_data->uid = audit_sig_uid;
 		sig_data->pid = audit_sig_pid;
-		memcpy(sig_data->ctx, ctx, len);
-		security_release_secctx(ctx, len);
+		if (audit_sig_sid) {
+			memcpy(sig_data->ctx, ctx, len);
+			security_release_secctx(ctx, len);
+		}
 		audit_send_reply(NETLINK_CB(skb).pid, seq, AUDIT_SIGNAL_INFO,
 				0, 0, sig_data, sizeof(*sig_data) + len);
 		kfree(sig_data);
diff --git a/kernel/audit_watch.c b/kernel/audit_watch.c
index 0e96dbc60ea9..cc7e87936cbc 100644
--- a/kernel/audit_watch.c
+++ b/kernel/audit_watch.c
@@ -45,8 +45,8 @@
 
 struct audit_watch {
 	atomic_t		count;	/* reference count */
-	char			*path;	/* insertion path */
 	dev_t			dev;	/* associated superblock device */
+	char			*path;	/* insertion path */
 	unsigned long		ino;	/* associated inode number */
 	struct audit_parent	*parent; /* associated parent */
 	struct list_head	wlist;	/* entry in parent->watches list */
diff --git a/kernel/auditsc.c b/kernel/auditsc.c
index 68d3c6a0ecd6..267e484f0198 100644
--- a/kernel/auditsc.c
+++ b/kernel/auditsc.c
@@ -168,12 +168,12 @@ struct audit_context {
 	int		    in_syscall;	/* 1 if task is in a syscall */
 	enum audit_state    state, current_state;
 	unsigned int	    serial;     /* serial number for record */
-	struct timespec	    ctime;      /* time of syscall entry */
 	int		    major;      /* syscall number */
+	struct timespec	    ctime;      /* time of syscall entry */
 	unsigned long	    argv[4];    /* syscall arguments */
-	int		    return_valid; /* return code is valid */
 	long		    return_code;/* syscall return code */
 	u64		    prio;
+	int		    return_valid; /* return code is valid */
 	int		    name_count;
 	struct audit_names  names[AUDIT_NAMES];
 	char *		    filterkey;	/* key for rule that triggered record */
@@ -198,8 +198,8 @@ struct audit_context {
 	char		    target_comm[TASK_COMM_LEN];
 
 	struct audit_tree_refs *trees, *first_trees;
-	int tree_count;
 	struct list_head killed_trees;
+	int tree_count;
 
 	int type;
 	union {
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index b6eadfe30e7b..0249f4be9b5c 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -23,6 +23,7 @@
  */
 
 #include <linux/cgroup.h>
+#include <linux/ctype.h>
 #include <linux/errno.h>
 #include <linux/fs.h>
 #include <linux/kernel.h>
@@ -48,6 +49,8 @@
 #include <linux/namei.h>
 #include <linux/smp_lock.h>
 #include <linux/pid_namespace.h>
+#include <linux/idr.h>
+#include <linux/vmalloc.h> /* TODO: replace with more sophisticated array */
 
 #include <asm/atomic.h>
 
@@ -60,6 +63,8 @@ static struct cgroup_subsys *subsys[] = {
 #include <linux/cgroup_subsys.h>
 };
 
+#define MAX_CGROUP_ROOT_NAMELEN 64
+
 /*
  * A cgroupfs_root represents the root of a cgroup hierarchy,
  * and may be associated with a superblock to form an active
@@ -74,6 +79,9 @@ struct cgroupfs_root {
 	 */
 	unsigned long subsys_bits;
 
+	/* Unique id for this hierarchy. */
+	int hierarchy_id;
+
 	/* The bitmask of subsystems currently attached to this hierarchy */
 	unsigned long actual_subsys_bits;
 
@@ -94,6 +102,9 @@ struct cgroupfs_root {
 
 	/* The path to use for release notifications. */
 	char release_agent_path[PATH_MAX];
+
+	/* The name for this hierarchy - may be empty */
+	char name[MAX_CGROUP_ROOT_NAMELEN];
 };
 
 /*
@@ -141,6 +152,10 @@ struct css_id {
 static LIST_HEAD(roots);
 static int root_count;
 
+static DEFINE_IDA(hierarchy_ida);
+static int next_hierarchy_id;
+static DEFINE_SPINLOCK(hierarchy_id_lock);
+
 /* dummytop is a shorthand for the dummy hierarchy's top cgroup */
 #define dummytop (&rootnode.top_cgroup)
 
@@ -201,6 +216,7 @@ struct cg_cgroup_link {
 	 * cgroup, anchored on cgroup->css_sets
 	 */
 	struct list_head cgrp_link_list;
+	struct cgroup *cgrp;
 	/*
 	 * List running through cg_cgroup_links pointing at a
 	 * single css_set object, anchored on css_set->cg_links
@@ -227,8 +243,11 @@ static int cgroup_subsys_init_idr(struct cgroup_subsys *ss);
 static DEFINE_RWLOCK(css_set_lock);
 static int css_set_count;
 
-/* hash table for cgroup groups. This improves the performance to
- * find an existing css_set */
+/*
+ * hash table for cgroup groups. This improves the performance to find
+ * an existing css_set. This hash doesn't (currently) take into
+ * account cgroups in empty hierarchies.
+ */
 #define CSS_SET_HASH_BITS	7
 #define CSS_SET_TABLE_SIZE	(1 << CSS_SET_HASH_BITS)
 static struct hlist_head css_set_table[CSS_SET_TABLE_SIZE];
@@ -248,48 +267,22 @@ static struct hlist_head *css_set_hash(struct cgroup_subsys_state *css[])
 	return &css_set_table[index];
 }
 
+static void free_css_set_rcu(struct rcu_head *obj)
+{
+	struct css_set *cg = container_of(obj, struct css_set, rcu_head);
+	kfree(cg);
+}
+
 /* We don't maintain the lists running through each css_set to its
  * task until after the first call to cgroup_iter_start(). This
  * reduces the fork()/exit() overhead for people who have cgroups
  * compiled into their kernel but not actually in use */
 static int use_task_css_set_links __read_mostly;
 
-/* When we create or destroy a css_set, the operation simply
- * takes/releases a reference count on all the cgroups referenced
- * by subsystems in this css_set. This can end up multiple-counting
- * some cgroups, but that's OK - the ref-count is just a
- * busy/not-busy indicator; ensuring that we only count each cgroup
- * once would require taking a global lock to ensure that no
- * subsystems moved between hierarchies while we were doing so.
- *
- * Possible TODO: decide at boot time based on the number of
- * registered subsystems and the number of CPUs or NUMA nodes whether
- * it's better for performance to ref-count every subsystem, or to
- * take a global lock and only add one ref count to each hierarchy.
- */
-
-/*
- * unlink a css_set from the list and free it
- */
-static void unlink_css_set(struct css_set *cg)
+static void __put_css_set(struct css_set *cg, int taskexit)
 {
 	struct cg_cgroup_link *link;
 	struct cg_cgroup_link *saved_link;
-
-	hlist_del(&cg->hlist);
-	css_set_count--;
-
-	list_for_each_entry_safe(link, saved_link, &cg->cg_links,
-				 cg_link_list) {
-		list_del(&link->cg_link_list);
-		list_del(&link->cgrp_link_list);
-		kfree(link);
-	}
-}
-
-static void __put_css_set(struct css_set *cg, int taskexit)
-{
-	int i;
 	/*
 	 * Ensure that the refcount doesn't hit zero while any readers
 	 * can see it. Similar to atomic_dec_and_lock(), but for an
@@ -302,21 +295,28 @@ static void __put_css_set(struct css_set *cg, int taskexit)
 		write_unlock(&css_set_lock);
 		return;
 	}
-	unlink_css_set(cg);
-	write_unlock(&css_set_lock);
 
-	rcu_read_lock();
-	for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
-		struct cgroup *cgrp = rcu_dereference(cg->subsys[i]->cgroup);
+	/* This css_set is dead. unlink it and release cgroup refcounts */
+	hlist_del(&cg->hlist);
+	css_set_count--;
+
+	list_for_each_entry_safe(link, saved_link, &cg->cg_links,
+				 cg_link_list) {
+		struct cgroup *cgrp = link->cgrp;
+		list_del(&link->cg_link_list);
+		list_del(&link->cgrp_link_list);
 		if (atomic_dec_and_test(&cgrp->count) &&
 		    notify_on_release(cgrp)) {
 			if (taskexit)
 				set_bit(CGRP_RELEASABLE, &cgrp->flags);
 			check_for_release(cgrp);
 		}
+
+		kfree(link);
 	}
-	rcu_read_unlock();
-	kfree(cg);
+
+	write_unlock(&css_set_lock);
+	call_rcu(&cg->rcu_head, free_css_set_rcu);
 }
 
 /*
@@ -338,6 +338,78 @@ static inline void put_css_set_taskexit(struct css_set *cg)
 }
 
 /*
+ * compare_css_sets - helper function for find_existing_css_set().
+ * @cg: candidate css_set being tested
+ * @old_cg: existing css_set for a task
+ * @new_cgrp: cgroup that's being entered by the task
+ * @template: desired set of css pointers in css_set (pre-calculated)
+ *
+ * Returns true if "cg" matches "old_cg" except for the hierarchy
+ * which "new_cgrp" belongs to, for which it should match "new_cgrp".
+ */
+static bool compare_css_sets(struct css_set *cg,
+			     struct css_set *old_cg,
+			     struct cgroup *new_cgrp,
+			     struct cgroup_subsys_state *template[])
+{
+	struct list_head *l1, *l2;
+
+	if (memcmp(template, cg->subsys, sizeof(cg->subsys))) {
+		/* Not all subsystems matched */
+		return false;
+	}
+
+	/*
+	 * Compare cgroup pointers in order to distinguish between
+	 * different cgroups in heirarchies with no subsystems. We
+	 * could get by with just this check alone (and skip the
+	 * memcmp above) but on most setups the memcmp check will
+	 * avoid the need for this more expensive check on almost all
+	 * candidates.
+	 */
+
+	l1 = &cg->cg_links;
+	l2 = &old_cg->cg_links;
+	while (1) {
+		struct cg_cgroup_link *cgl1, *cgl2;
+		struct cgroup *cg1, *cg2;
+
+		l1 = l1->next;
+		l2 = l2->next;
+		/* See if we reached the end - both lists are equal length. */
+		if (l1 == &cg->cg_links) {
+			BUG_ON(l2 != &old_cg->cg_links);
+			break;
+		} else {
+			BUG_ON(l2 == &old_cg->cg_links);
+		}
+		/* Locate the cgroups associated with these links. */
+		cgl1 = list_entry(l1, struct cg_cgroup_link, cg_link_list);
+		cgl2 = list_entry(l2, struct cg_cgroup_link, cg_link_list);
+		cg1 = cgl1->cgrp;
+		cg2 = cgl2->cgrp;
+		/* Hierarchies should be linked in the same order. */
+		BUG_ON(cg1->root != cg2->root);
+
+		/*
+		 * If this hierarchy is the hierarchy of the cgroup
+		 * that's changing, then we need to check that this
+		 * css_set points to the new cgroup; if it's any other
+		 * hierarchy, then this css_set should point to the
+		 * same cgroup as the old css_set.
+		 */
+		if (cg1->root == new_cgrp->root) {
+			if (cg1 != new_cgrp)
+				return false;
+		} else {
+			if (cg1 != cg2)
+				return false;
+		}
+	}
+	return true;
+}
+
+/*
  * find_existing_css_set() is a helper for
  * find_css_set(), and checks to see whether an existing
  * css_set is suitable.
@@ -378,10 +450,11 @@ static struct css_set *find_existing_css_set(
 
 	hhead = css_set_hash(template);
 	hlist_for_each_entry(cg, node, hhead, hlist) {
-		if (!memcmp(template, cg->subsys, sizeof(cg->subsys))) {
-			/* All subsystems matched */
-			return cg;
-		}
+		if (!compare_css_sets(cg, oldcg, cgrp, template))
+			continue;
+
+		/* This css_set matches what we need */
+		return cg;
 	}
 
 	/* No existing cgroup group matched */
@@ -435,8 +508,14 @@ static void link_css_set(struct list_head *tmp_cg_links,
 	link = list_first_entry(tmp_cg_links, struct cg_cgroup_link,
 				cgrp_link_list);
 	link->cg = cg;
+	link->cgrp = cgrp;
+	atomic_inc(&cgrp->count);
 	list_move(&link->cgrp_link_list, &cgrp->css_sets);
-	list_add(&link->cg_link_list, &cg->cg_links);
+	/*
+	 * Always add links to the tail of the list so that the list
+	 * is sorted by order of hierarchy creation
+	 */
+	list_add_tail(&link->cg_link_list, &cg->cg_links);
 }
 
 /*
@@ -451,11 +530,11 @@ static struct css_set *find_css_set(
 {
 	struct css_set *res;
 	struct cgroup_subsys_state *template[CGROUP_SUBSYS_COUNT];
-	int i;
 
 	struct list_head tmp_cg_links;
 
 	struct hlist_head *hhead;
+	struct cg_cgroup_link *link;
 
 	/* First see if we already have a cgroup group that matches
 	 * the desired set */
@@ -489,20 +568,12 @@ static struct css_set *find_css_set(
 
 	write_lock(&css_set_lock);
 	/* Add reference counts and links from the new css_set. */
-	for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
-		struct cgroup *cgrp = res->subsys[i]->cgroup;
-		struct cgroup_subsys *ss = subsys[i];
-		atomic_inc(&cgrp->count);
-		/*
-		 * We want to add a link once per cgroup, so we
-		 * only do it for the first subsystem in each
-		 * hierarchy
-		 */
-		if (ss->root->subsys_list.next == &ss->sibling)
-			link_css_set(&tmp_cg_links, res, cgrp);
+	list_for_each_entry(link, &oldcg->cg_links, cg_link_list) {
+		struct cgroup *c = link->cgrp;
+		if (c->root == cgrp->root)
+			c = cgrp;
+		link_css_set(&tmp_cg_links, res, c);
 	}
-	if (list_empty(&rootnode.subsys_list))
-		link_css_set(&tmp_cg_links, res, dummytop);
 
 	BUG_ON(!list_empty(&tmp_cg_links));
 
@@ -518,6 +589,41 @@ static struct css_set *find_css_set(
 }
 
 /*
+ * Return the cgroup for "task" from the given hierarchy. Must be
+ * called with cgroup_mutex held.
+ */
+static struct cgroup *task_cgroup_from_root(struct task_struct *task,
+					    struct cgroupfs_root *root)
+{
+	struct css_set *css;
+	struct cgroup *res = NULL;
+
+	BUG_ON(!mutex_is_locked(&cgroup_mutex));
+	read_lock(&css_set_lock);
+	/*
+	 * No need to lock the task - since we hold cgroup_mutex the
+	 * task can't change groups, so the only thing that can happen
+	 * is that it exits and its css is set back to init_css_set.
+	 */
+	css = task->cgroups;
+	if (css == &init_css_set) {
+		res = &root->top_cgroup;
+	} else {
+		struct cg_cgroup_link *link;
+		list_for_each_entry(link, &css->cg_links, cg_link_list) {
+			struct cgroup *c = link->cgrp;
+			if (c->root == root) {
+				res = c;
+				break;
+			}
+		}
+	}
+	read_unlock(&css_set_lock);
+	BUG_ON(!res);
+	return res;
+}
+
+/*
  * There is one global cgroup mutex. We also require taking
  * task_lock() when dereferencing a task's cgroup subsys pointers.
  * See "The task_lock() exception", at the end of this comment.
@@ -596,10 +702,11 @@ void cgroup_unlock(void)
 static int cgroup_mkdir(struct inode *dir, struct dentry *dentry, int mode);
 static int cgroup_rmdir(struct inode *unused_dir, struct dentry *dentry);
 static int cgroup_populate_dir(struct cgroup *cgrp);
-static struct inode_operations cgroup_dir_inode_operations;
-static struct file_operations proc_cgroupstats_operations;
+static const struct inode_operations cgroup_dir_inode_operations;
+static const struct file_operations proc_cgroupstats_operations;
 
 static struct backing_dev_info cgroup_backing_dev_info = {
+	.name		= "cgroup",
 	.capabilities	= BDI_CAP_NO_ACCT_AND_WRITEBACK,
 };
 
@@ -676,6 +783,12 @@ static void cgroup_diput(struct dentry *dentry, struct inode *inode)
 		 */
 		deactivate_super(cgrp->root->sb);
 
+		/*
+		 * if we're getting rid of the cgroup, refcount should ensure
+		 * that there are no pidlists left.
+		 */
+		BUG_ON(!list_empty(&cgrp->pidlists));
+
 		call_rcu(&cgrp->rcu_head, free_cgroup_rcu);
 	}
 	iput(inode);
@@ -840,6 +953,8 @@ static int cgroup_show_options(struct seq_file *seq, struct vfsmount *vfs)
 		seq_puts(seq, ",noprefix");
 	if (strlen(root->release_agent_path))
 		seq_printf(seq, ",release_agent=%s", root->release_agent_path);
+	if (strlen(root->name))
+		seq_printf(seq, ",name=%s", root->name);
 	mutex_unlock(&cgroup_mutex);
 	return 0;
 }
@@ -848,6 +963,12 @@ struct cgroup_sb_opts {
 	unsigned long subsys_bits;
 	unsigned long flags;
 	char *release_agent;
+	char *name;
+	/* User explicitly requested empty subsystem */
+	bool none;
+
+	struct cgroupfs_root *new_root;
+
 };
 
 /* Convert a hierarchy specifier into a bitmask of subsystems and
@@ -862,9 +983,7 @@ static int parse_cgroupfs_options(char *data,
 	mask = ~(1UL << cpuset_subsys_id);
 #endif
 
-	opts->subsys_bits = 0;
-	opts->flags = 0;
-	opts->release_agent = NULL;
+	memset(opts, 0, sizeof(*opts));
 
 	while ((token = strsep(&o, ",")) != NULL) {
 		if (!*token)
@@ -878,17 +997,42 @@ static int parse_cgroupfs_options(char *data,
 				if (!ss->disabled)
 					opts->subsys_bits |= 1ul << i;
 			}
+		} else if (!strcmp(token, "none")) {
+			/* Explicitly have no subsystems */
+			opts->none = true;
 		} else if (!strcmp(token, "noprefix")) {
 			set_bit(ROOT_NOPREFIX, &opts->flags);
 		} else if (!strncmp(token, "release_agent=", 14)) {
 			/* Specifying two release agents is forbidden */
 			if (opts->release_agent)
 				return -EINVAL;
-			opts->release_agent = kzalloc(PATH_MAX, GFP_KERNEL);
+			opts->release_agent =
+				kstrndup(token + 14, PATH_MAX, GFP_KERNEL);
 			if (!opts->release_agent)
 				return -ENOMEM;
-			strncpy(opts->release_agent, token + 14, PATH_MAX - 1);
-			opts->release_agent[PATH_MAX - 1] = 0;
+		} else if (!strncmp(token, "name=", 5)) {
+			int i;
+			const char *name = token + 5;
+			/* Can't specify an empty name */
+			if (!strlen(name))
+				return -EINVAL;
+			/* Must match [\w.-]+ */
+			for (i = 0; i < strlen(name); i++) {
+				char c = name[i];
+				if (isalnum(c))
+					continue;
+				if ((c == '.') || (c == '-') || (c == '_'))
+					continue;
+				return -EINVAL;
+			}
+			/* Specifying two names is forbidden */
+			if (opts->name)
+				return -EINVAL;
+			opts->name = kstrndup(name,
+					      MAX_CGROUP_ROOT_NAMELEN,
+					      GFP_KERNEL);
+			if (!opts->name)
+				return -ENOMEM;
 		} else {
 			struct cgroup_subsys *ss;
 			int i;
@@ -905,6 +1049,8 @@ static int parse_cgroupfs_options(char *data,
 		}
 	}
 
+	/* Consistency checks */
+
 	/*
 	 * Option noprefix was introduced just for backward compatibility
 	 * with the old cpuset, so we allow noprefix only if mounting just
@@ -914,8 +1060,16 @@ static int parse_cgroupfs_options(char *data,
 	    (opts->subsys_bits & mask))
 		return -EINVAL;
 
-	/* We can't have an empty hierarchy */
-	if (!opts->subsys_bits)
+
+	/* Can't specify "none" and some subsystems */
+	if (opts->subsys_bits && opts->none)
+		return -EINVAL;
+
+	/*
+	 * We either have to specify by name or by subsystems. (So all
+	 * empty hierarchies must have a name).
+	 */
+	if (!opts->subsys_bits && !opts->name)
 		return -EINVAL;
 
 	return 0;
@@ -943,6 +1097,12 @@ static int cgroup_remount(struct super_block *sb, int *flags, char *data)
 		goto out_unlock;
 	}
 
+	/* Don't allow name to change at remount */
+	if (opts.name && strcmp(opts.name, root->name)) {
+		ret = -EINVAL;
+		goto out_unlock;
+	}
+
 	ret = rebind_subsystems(root, opts.subsys_bits);
 	if (ret)
 		goto out_unlock;
@@ -954,13 +1114,14 @@ static int cgroup_remount(struct super_block *sb, int *flags, char *data)
 		strcpy(root->release_agent_path, opts.release_agent);
  out_unlock:
 	kfree(opts.release_agent);
+	kfree(opts.name);
 	mutex_unlock(&cgroup_mutex);
 	mutex_unlock(&cgrp->dentry->d_inode->i_mutex);
 	unlock_kernel();
 	return ret;
 }
 
-static struct super_operations cgroup_ops = {
+static const struct super_operations cgroup_ops = {
 	.statfs = simple_statfs,
 	.drop_inode = generic_delete_inode,
 	.show_options = cgroup_show_options,
@@ -973,9 +1134,10 @@ static void init_cgroup_housekeeping(struct cgroup *cgrp)
 	INIT_LIST_HEAD(&cgrp->children);
 	INIT_LIST_HEAD(&cgrp->css_sets);
 	INIT_LIST_HEAD(&cgrp->release_list);
-	INIT_LIST_HEAD(&cgrp->pids_list);
-	init_rwsem(&cgrp->pids_mutex);
+	INIT_LIST_HEAD(&cgrp->pidlists);
+	mutex_init(&cgrp->pidlist_mutex);
 }
+
 static void init_cgroup_root(struct cgroupfs_root *root)
 {
 	struct cgroup *cgrp = &root->top_cgroup;
@@ -987,33 +1149,106 @@ static void init_cgroup_root(struct cgroupfs_root *root)
 	init_cgroup_housekeeping(cgrp);
 }
 
+static bool init_root_id(struct cgroupfs_root *root)
+{
+	int ret = 0;
+
+	do {
+		if (!ida_pre_get(&hierarchy_ida, GFP_KERNEL))
+			return false;
+		spin_lock(&hierarchy_id_lock);
+		/* Try to allocate the next unused ID */
+		ret = ida_get_new_above(&hierarchy_ida, next_hierarchy_id,
+					&root->hierarchy_id);
+		if (ret == -ENOSPC)
+			/* Try again starting from 0 */
+			ret = ida_get_new(&hierarchy_ida, &root->hierarchy_id);
+		if (!ret) {
+			next_hierarchy_id = root->hierarchy_id + 1;
+		} else if (ret != -EAGAIN) {
+			/* Can only get here if the 31-bit IDR is full ... */
+			BUG_ON(ret);
+		}
+		spin_unlock(&hierarchy_id_lock);
+	} while (ret);
+	return true;
+}
+
 static int cgroup_test_super(struct super_block *sb, void *data)
 {
-	struct cgroupfs_root *new = data;
+	struct cgroup_sb_opts *opts = data;
 	struct cgroupfs_root *root = sb->s_fs_info;
 
-	/* First check subsystems */
-	if (new->subsys_bits != root->subsys_bits)
-	    return 0;
+	/* If we asked for a name then it must match */
+	if (opts->name && strcmp(opts->name, root->name))
+		return 0;
 
-	/* Next check flags */
-	if (new->flags != root->flags)
+	/*
+	 * If we asked for subsystems (or explicitly for no
+	 * subsystems) then they must match
+	 */
+	if ((opts->subsys_bits || opts->none)
+	    && (opts->subsys_bits != root->subsys_bits))
 		return 0;
 
 	return 1;
 }
 
+static struct cgroupfs_root *cgroup_root_from_opts(struct cgroup_sb_opts *opts)
+{
+	struct cgroupfs_root *root;
+
+	if (!opts->subsys_bits && !opts->none)
+		return NULL;
+
+	root = kzalloc(sizeof(*root), GFP_KERNEL);
+	if (!root)
+		return ERR_PTR(-ENOMEM);
+
+	if (!init_root_id(root)) {
+		kfree(root);
+		return ERR_PTR(-ENOMEM);
+	}
+	init_cgroup_root(root);
+
+	root->subsys_bits = opts->subsys_bits;
+	root->flags = opts->flags;
+	if (opts->release_agent)
+		strcpy(root->release_agent_path, opts->release_agent);
+	if (opts->name)
+		strcpy(root->name, opts->name);
+	return root;
+}
+
+static void cgroup_drop_root(struct cgroupfs_root *root)
+{
+	if (!root)
+		return;
+
+	BUG_ON(!root->hierarchy_id);
+	spin_lock(&hierarchy_id_lock);
+	ida_remove(&hierarchy_ida, root->hierarchy_id);
+	spin_unlock(&hierarchy_id_lock);
+	kfree(root);
+}
+
 static int cgroup_set_super(struct super_block *sb, void *data)
 {
 	int ret;
-	struct cgroupfs_root *root = data;
+	struct cgroup_sb_opts *opts = data;
+
+	/* If we don't have a new root, we can't set up a new sb */
+	if (!opts->new_root)
+		return -EINVAL;
+
+	BUG_ON(!opts->subsys_bits && !opts->none);
 
 	ret = set_anon_super(sb, NULL);
 	if (ret)
 		return ret;
 
-	sb->s_fs_info = root;
-	root->sb = sb;
+	sb->s_fs_info = opts->new_root;
+	opts->new_root->sb = sb;
 
 	sb->s_blocksize = PAGE_CACHE_SIZE;
 	sb->s_blocksize_bits = PAGE_CACHE_SHIFT;
@@ -1050,48 +1285,43 @@ static int cgroup_get_sb(struct file_system_type *fs_type,
 			 void *data, struct vfsmount *mnt)
 {
 	struct cgroup_sb_opts opts;
+	struct cgroupfs_root *root;
 	int ret = 0;
 	struct super_block *sb;
-	struct cgroupfs_root *root;
-	struct list_head tmp_cg_links;
+	struct cgroupfs_root *new_root;
 
 	/* First find the desired set of subsystems */
 	ret = parse_cgroupfs_options(data, &opts);
-	if (ret) {
-		kfree(opts.release_agent);
-		return ret;
-	}
-
-	root = kzalloc(sizeof(*root), GFP_KERNEL);
-	if (!root) {
-		kfree(opts.release_agent);
-		return -ENOMEM;
-	}
+	if (ret)
+		goto out_err;
 
-	init_cgroup_root(root);
-	root->subsys_bits = opts.subsys_bits;
-	root->flags = opts.flags;
-	if (opts.release_agent) {
-		strcpy(root->release_agent_path, opts.release_agent);
-		kfree(opts.release_agent);
+	/*
+	 * Allocate a new cgroup root. We may not need it if we're
+	 * reusing an existing hierarchy.
+	 */
+	new_root = cgroup_root_from_opts(&opts);
+	if (IS_ERR(new_root)) {
+		ret = PTR_ERR(new_root);
+		goto out_err;
 	}
+	opts.new_root = new_root;
 
-	sb = sget(fs_type, cgroup_test_super, cgroup_set_super, root);
-
+	/* Locate an existing or new sb for this hierarchy */
+	sb = sget(fs_type, cgroup_test_super, cgroup_set_super, &opts);
 	if (IS_ERR(sb)) {
-		kfree(root);
-		return PTR_ERR(sb);
+		ret = PTR_ERR(sb);
+		cgroup_drop_root(opts.new_root);
+		goto out_err;
 	}
 
-	if (sb->s_fs_info != root) {
-		/* Reusing an existing superblock */
-		BUG_ON(sb->s_root == NULL);
-		kfree(root);
-		root = NULL;
-	} else {
-		/* New superblock */
+	root = sb->s_fs_info;
+	BUG_ON(!root);
+	if (root == opts.new_root) {
+		/* We used the new root structure, so this is a new hierarchy */
+		struct list_head tmp_cg_links;
 		struct cgroup *root_cgrp = &root->top_cgroup;
 		struct inode *inode;
+		struct cgroupfs_root *existing_root;
 		int i;
 
 		BUG_ON(sb->s_root != NULL);
@@ -1104,6 +1334,18 @@ static int cgroup_get_sb(struct file_system_type *fs_type,
 		mutex_lock(&inode->i_mutex);
 		mutex_lock(&cgroup_mutex);
 
+		if (strlen(root->name)) {
+			/* Check for name clashes with existing mounts */
+			for_each_active_root(existing_root) {
+				if (!strcmp(existing_root->name, root->name)) {
+					ret = -EBUSY;
+					mutex_unlock(&cgroup_mutex);
+					mutex_unlock(&inode->i_mutex);
+					goto drop_new_super;
+				}
+			}
+		}
+
 		/*
 		 * We're accessing css_set_count without locking
 		 * css_set_lock here, but that's OK - it can only be
@@ -1122,7 +1364,8 @@ static int cgroup_get_sb(struct file_system_type *fs_type,
 		if (ret == -EBUSY) {
 			mutex_unlock(&cgroup_mutex);
 			mutex_unlock(&inode->i_mutex);
-			goto free_cg_links;
+			free_cg_links(&tmp_cg_links);
+			goto drop_new_super;
 		}
 
 		/* EBUSY should be the only error here */
@@ -1154,17 +1397,27 @@ static int cgroup_get_sb(struct file_system_type *fs_type,
 		BUG_ON(root->number_of_cgroups != 1);
 
 		cgroup_populate_dir(root_cgrp);
-		mutex_unlock(&inode->i_mutex);
 		mutex_unlock(&cgroup_mutex);
+		mutex_unlock(&inode->i_mutex);
+	} else {
+		/*
+		 * We re-used an existing hierarchy - the new root (if
+		 * any) is not needed
+		 */
+		cgroup_drop_root(opts.new_root);
 	}
 
 	simple_set_mnt(mnt, sb);
+	kfree(opts.release_agent);
+	kfree(opts.name);
 	return 0;
 
- free_cg_links:
-	free_cg_links(&tmp_cg_links);
  drop_new_super:
 	deactivate_locked_super(sb);
+ out_err:
+	kfree(opts.release_agent);
+	kfree(opts.name);
+
 	return ret;
 }
 
@@ -1210,7 +1463,7 @@ static void cgroup_kill_sb(struct super_block *sb) {
 	mutex_unlock(&cgroup_mutex);
 
 	kill_litter_super(sb);
-	kfree(root);
+	cgroup_drop_root(root);
 }
 
 static struct file_system_type cgroup_fs_type = {
@@ -1275,27 +1528,6 @@ int cgroup_path(const struct cgroup *cgrp, char *buf, int buflen)
 	return 0;
 }
 
-/*
- * Return the first subsystem attached to a cgroup's hierarchy, and
- * its subsystem id.
- */
-
-static void get_first_subsys(const struct cgroup *cgrp,
-			struct cgroup_subsys_state **css, int *subsys_id)
-{
-	const struct cgroupfs_root *root = cgrp->root;
-	const struct cgroup_subsys *test_ss;
-	BUG_ON(list_empty(&root->subsys_list));
-	test_ss = list_entry(root->subsys_list.next,
-			     struct cgroup_subsys, sibling);
-	if (css) {
-		*css = cgrp->subsys[test_ss->subsys_id];
-		BUG_ON(!*css);
-	}
-	if (subsys_id)
-		*subsys_id = test_ss->subsys_id;
-}
-
 /**
  * cgroup_attach_task - attach task 'tsk' to cgroup 'cgrp'
  * @cgrp: the cgroup the task is attaching to
@@ -1312,18 +1544,15 @@ int cgroup_attach_task(struct cgroup *cgrp, struct task_struct *tsk)
 	struct css_set *cg;
 	struct css_set *newcg;
 	struct cgroupfs_root *root = cgrp->root;
-	int subsys_id;
-
-	get_first_subsys(cgrp, NULL, &subsys_id);
 
 	/* Nothing to do if the task is already in that cgroup */
-	oldcgrp = task_cgroup(tsk, subsys_id);
+	oldcgrp = task_cgroup_from_root(tsk, root);
 	if (cgrp == oldcgrp)
 		return 0;
 
 	for_each_subsys(root, ss) {
 		if (ss->can_attach) {
-			retval = ss->can_attach(ss, cgrp, tsk);
+			retval = ss->can_attach(ss, cgrp, tsk, false);
 			if (retval)
 				return retval;
 		}
@@ -1361,7 +1590,7 @@ int cgroup_attach_task(struct cgroup *cgrp, struct task_struct *tsk)
 
 	for_each_subsys(root, ss) {
 		if (ss->attach)
-			ss->attach(ss, cgrp, oldcgrp, tsk);
+			ss->attach(ss, cgrp, oldcgrp, tsk, false);
 	}
 	set_bit(CGRP_RELEASABLE, &oldcgrp->flags);
 	synchronize_rcu();
@@ -1422,15 +1651,6 @@ static int cgroup_tasks_write(struct cgroup *cgrp, struct cftype *cft, u64 pid)
 	return ret;
 }
 
-/* The various types of files and directories in a cgroup file system */
-enum cgroup_filetype {
-	FILE_ROOT,
-	FILE_DIR,
-	FILE_TASKLIST,
-	FILE_NOTIFY_ON_RELEASE,
-	FILE_RELEASE_AGENT,
-};
-
 /**
  * cgroup_lock_live_group - take cgroup_mutex and check that cgrp is alive.
  * @cgrp: the cgroup to be checked for liveness
@@ -1490,14 +1710,13 @@ static ssize_t cgroup_write_X64(struct cgroup *cgrp, struct cftype *cft,
 		return -EFAULT;
 
 	buffer[nbytes] = 0;     /* nul-terminate */
-	strstrip(buffer);
 	if (cft->write_u64) {
-		u64 val = simple_strtoull(buffer, &end, 0);
+		u64 val = simple_strtoull(strstrip(buffer), &end, 0);
 		if (*end)
 			return -EINVAL;
 		retval = cft->write_u64(cgrp, cft, val);
 	} else {
-		s64 val = simple_strtoll(buffer, &end, 0);
+		s64 val = simple_strtoll(strstrip(buffer), &end, 0);
 		if (*end)
 			return -EINVAL;
 		retval = cft->write_s64(cgrp, cft, val);
@@ -1533,8 +1752,7 @@ static ssize_t cgroup_write_string(struct cgroup *cgrp, struct cftype *cft,
 	}
 
 	buffer[nbytes] = 0;     /* nul-terminate */
-	strstrip(buffer);
-	retval = cft->write_string(cgrp, cft, buffer);
+	retval = cft->write_string(cgrp, cft, strstrip(buffer));
 	if (!retval)
 		retval = nbytes;
 out:
@@ -1643,7 +1861,7 @@ static int cgroup_seqfile_release(struct inode *inode, struct file *file)
 	return single_release(inode, file);
 }
 
-static struct file_operations cgroup_seqfile_operations = {
+static const struct file_operations cgroup_seqfile_operations = {
 	.read = seq_read,
 	.write = cgroup_file_write,
 	.llseek = seq_lseek,
@@ -1702,7 +1920,7 @@ static int cgroup_rename(struct inode *old_dir, struct dentry *old_dentry,
 	return simple_rename(old_dir, old_dentry, new_dir, new_dentry);
 }
 
-static struct file_operations cgroup_file_operations = {
+static const struct file_operations cgroup_file_operations = {
 	.read = cgroup_file_read,
 	.write = cgroup_file_write,
 	.llseek = generic_file_llseek,
@@ -1710,7 +1928,7 @@ static struct file_operations cgroup_file_operations = {
 	.release = cgroup_file_release,
 };
 
-static struct inode_operations cgroup_dir_inode_operations = {
+static const struct inode_operations cgroup_dir_inode_operations = {
 	.lookup = simple_lookup,
 	.mkdir = cgroup_mkdir,
 	.rmdir = cgroup_rmdir,
@@ -1875,7 +2093,7 @@ int cgroup_task_count(const struct cgroup *cgrp)
  * the start of a css_set
  */
 static void cgroup_advance_iter(struct cgroup *cgrp,
-					  struct cgroup_iter *it)
+				struct cgroup_iter *it)
 {
 	struct list_head *l = it->cg_link;
 	struct cg_cgroup_link *link;
@@ -2128,7 +2346,7 @@ int cgroup_scan_tasks(struct cgroup_scanner *scan)
 }
 
 /*
- * Stuff for reading the 'tasks' file.
+ * Stuff for reading the 'tasks'/'procs' files.
  *
  * Reading this file can return large amounts of data if a cgroup has
  * *lots* of attached tasks. So it may need several calls to read(),
@@ -2138,27 +2356,196 @@ int cgroup_scan_tasks(struct cgroup_scanner *scan)
  */
 
 /*
- * Load into 'pidarray' up to 'npids' of the tasks using cgroup
- * 'cgrp'.  Return actual number of pids loaded.  No need to
- * task_lock(p) when reading out p->cgroup, since we're in an RCU
- * read section, so the css_set can't go away, and is
- * immutable after creation.
+ * The following two functions "fix" the issue where there are more pids
+ * than kmalloc will give memory for; in such cases, we use vmalloc/vfree.
+ * TODO: replace with a kernel-wide solution to this problem
+ */
+#define PIDLIST_TOO_LARGE(c) ((c) * sizeof(pid_t) > (PAGE_SIZE * 2))
+static void *pidlist_allocate(int count)
+{
+	if (PIDLIST_TOO_LARGE(count))
+		return vmalloc(count * sizeof(pid_t));
+	else
+		return kmalloc(count * sizeof(pid_t), GFP_KERNEL);
+}
+static void pidlist_free(void *p)
+{
+	if (is_vmalloc_addr(p))
+		vfree(p);
+	else
+		kfree(p);
+}
+static void *pidlist_resize(void *p, int newcount)
+{
+	void *newlist;
+	/* note: if new alloc fails, old p will still be valid either way */
+	if (is_vmalloc_addr(p)) {
+		newlist = vmalloc(newcount * sizeof(pid_t));
+		if (!newlist)
+			return NULL;
+		memcpy(newlist, p, newcount * sizeof(pid_t));
+		vfree(p);
+	} else {
+		newlist = krealloc(p, newcount * sizeof(pid_t), GFP_KERNEL);
+	}
+	return newlist;
+}
+
+/*
+ * pidlist_uniq - given a kmalloc()ed list, strip out all duplicate entries
+ * If the new stripped list is sufficiently smaller and there's enough memory
+ * to allocate a new buffer, will let go of the unneeded memory. Returns the
+ * number of unique elements.
+ */
+/* is the size difference enough that we should re-allocate the array? */
+#define PIDLIST_REALLOC_DIFFERENCE(old, new) ((old) - PAGE_SIZE >= (new))
+static int pidlist_uniq(pid_t **p, int length)
+{
+	int src, dest = 1;
+	pid_t *list = *p;
+	pid_t *newlist;
+
+	/*
+	 * we presume the 0th element is unique, so i starts at 1. trivial
+	 * edge cases first; no work needs to be done for either
+	 */
+	if (length == 0 || length == 1)
+		return length;
+	/* src and dest walk down the list; dest counts unique elements */
+	for (src = 1; src < length; src++) {
+		/* find next unique element */
+		while (list[src] == list[src-1]) {
+			src++;
+			if (src == length)
+				goto after;
+		}
+		/* dest always points to where the next unique element goes */
+		list[dest] = list[src];
+		dest++;
+	}
+after:
+	/*
+	 * if the length difference is large enough, we want to allocate a
+	 * smaller buffer to save memory. if this fails due to out of memory,
+	 * we'll just stay with what we've got.
+	 */
+	if (PIDLIST_REALLOC_DIFFERENCE(length, dest)) {
+		newlist = pidlist_resize(list, dest);
+		if (newlist)
+			*p = newlist;
+	}
+	return dest;
+}
+
+static int cmppid(const void *a, const void *b)
+{
+	return *(pid_t *)a - *(pid_t *)b;
+}
+
+/*
+ * find the appropriate pidlist for our purpose (given procs vs tasks)
+ * returns with the lock on that pidlist already held, and takes care
+ * of the use count, or returns NULL with no locks held if we're out of
+ * memory.
  */
-static int pid_array_load(pid_t *pidarray, int npids, struct cgroup *cgrp)
+static struct cgroup_pidlist *cgroup_pidlist_find(struct cgroup *cgrp,
+						  enum cgroup_filetype type)
 {
-	int n = 0, pid;
+	struct cgroup_pidlist *l;
+	/* don't need task_nsproxy() if we're looking at ourself */
+	struct pid_namespace *ns = get_pid_ns(current->nsproxy->pid_ns);
+	/*
+	 * We can't drop the pidlist_mutex before taking the l->mutex in case
+	 * the last ref-holder is trying to remove l from the list at the same
+	 * time. Holding the pidlist_mutex precludes somebody taking whichever
+	 * list we find out from under us - compare release_pid_array().
+	 */
+	mutex_lock(&cgrp->pidlist_mutex);
+	list_for_each_entry(l, &cgrp->pidlists, links) {
+		if (l->key.type == type && l->key.ns == ns) {
+			/* found a matching list - drop the extra refcount */
+			put_pid_ns(ns);
+			/* make sure l doesn't vanish out from under us */
+			down_write(&l->mutex);
+			mutex_unlock(&cgrp->pidlist_mutex);
+			l->use_count++;
+			return l;
+		}
+	}
+	/* entry not found; create a new one */
+	l = kmalloc(sizeof(struct cgroup_pidlist), GFP_KERNEL);
+	if (!l) {
+		mutex_unlock(&cgrp->pidlist_mutex);
+		put_pid_ns(ns);
+		return l;
+	}
+	init_rwsem(&l->mutex);
+	down_write(&l->mutex);
+	l->key.type = type;
+	l->key.ns = ns;
+	l->use_count = 0; /* don't increment here */
+	l->list = NULL;
+	l->owner = cgrp;
+	list_add(&l->links, &cgrp->pidlists);
+	mutex_unlock(&cgrp->pidlist_mutex);
+	return l;
+}
+
+/*
+ * Load a cgroup's pidarray with either procs' tgids or tasks' pids
+ */
+static int pidlist_array_load(struct cgroup *cgrp, enum cgroup_filetype type,
+			      struct cgroup_pidlist **lp)
+{
+	pid_t *array;
+	int length;
+	int pid, n = 0; /* used for populating the array */
 	struct cgroup_iter it;
 	struct task_struct *tsk;
+	struct cgroup_pidlist *l;
+
+	/*
+	 * If cgroup gets more users after we read count, we won't have
+	 * enough space - tough.  This race is indistinguishable to the
+	 * caller from the case that the additional cgroup users didn't
+	 * show up until sometime later on.
+	 */
+	length = cgroup_task_count(cgrp);
+	array = pidlist_allocate(length);
+	if (!array)
+		return -ENOMEM;
+	/* now, populate the array */
 	cgroup_iter_start(cgrp, &it);
 	while ((tsk = cgroup_iter_next(cgrp, &it))) {
-		if (unlikely(n == npids))
+		if (unlikely(n == length))
 			break;
-		pid = task_pid_vnr(tsk);
-		if (pid > 0)
-			pidarray[n++] = pid;
+		/* get tgid or pid for procs or tasks file respectively */
+		if (type == CGROUP_FILE_PROCS)
+			pid = task_tgid_vnr(tsk);
+		else
+			pid = task_pid_vnr(tsk);
+		if (pid > 0) /* make sure to only use valid results */
+			array[n++] = pid;
 	}
 	cgroup_iter_end(cgrp, &it);
-	return n;
+	length = n;
+	/* now sort & (if procs) strip out duplicates */
+	sort(array, length, sizeof(pid_t), cmppid, NULL);
+	if (type == CGROUP_FILE_PROCS)
+		length = pidlist_uniq(&array, length);
+	l = cgroup_pidlist_find(cgrp, type);
+	if (!l) {
+		pidlist_free(array);
+		return -ENOMEM;
+	}
+	/* store array, freeing old if necessary - lock already held */
+	pidlist_free(l->list);
+	l->list = array;
+	l->length = length;
+	l->use_count++;
+	up_write(&l->mutex);
+	*lp = l;
+	return 0;
 }
 
 /**
@@ -2215,37 +2602,14 @@ err:
 	return ret;
 }
 
-/*
- * Cache pids for all threads in the same pid namespace that are
- * opening the same "tasks" file.
- */
-struct cgroup_pids {
-	/* The node in cgrp->pids_list */
-	struct list_head list;
-	/* The cgroup those pids belong to */
-	struct cgroup *cgrp;
-	/* The namepsace those pids belong to */
-	struct pid_namespace *ns;
-	/* Array of process ids in the cgroup */
-	pid_t *tasks_pids;
-	/* How many files are using the this tasks_pids array */
-	int use_count;
-	/* Length of the current tasks_pids array */
-	int length;
-};
-
-static int cmppid(const void *a, const void *b)
-{
-	return *(pid_t *)a - *(pid_t *)b;
-}
 
 /*
- * seq_file methods for the "tasks" file. The seq_file position is the
+ * seq_file methods for the tasks/procs files. The seq_file position is the
  * next pid to display; the seq_file iterator is a pointer to the pid
- * in the cgroup->tasks_pids array.
+ * in the cgroup->l->list array.
  */
 
-static void *cgroup_tasks_start(struct seq_file *s, loff_t *pos)
+static void *cgroup_pidlist_start(struct seq_file *s, loff_t *pos)
 {
 	/*
 	 * Initially we receive a position value that corresponds to
@@ -2253,48 +2617,45 @@ static void *cgroup_tasks_start(struct seq_file *s, loff_t *pos)
 	 * after a seek to the start). Use a binary-search to find the
 	 * next pid to display, if any
 	 */
-	struct cgroup_pids *cp = s->private;
-	struct cgroup *cgrp = cp->cgrp;
+	struct cgroup_pidlist *l = s->private;
 	int index = 0, pid = *pos;
 	int *iter;
 
-	down_read(&cgrp->pids_mutex);
+	down_read(&l->mutex);
 	if (pid) {
-		int end = cp->length;
+		int end = l->length;
 
 		while (index < end) {
 			int mid = (index + end) / 2;
-			if (cp->tasks_pids[mid] == pid) {
+			if (l->list[mid] == pid) {
 				index = mid;
 				break;
-			} else if (cp->tasks_pids[mid] <= pid)
+			} else if (l->list[mid] <= pid)
 				index = mid + 1;
 			else
 				end = mid;
 		}
 	}
 	/* If we're off the end of the array, we're done */
-	if (index >= cp->length)
+	if (index >= l->length)
 		return NULL;
 	/* Update the abstract position to be the actual pid that we found */
-	iter = cp->tasks_pids + index;
+	iter = l->list + index;
 	*pos = *iter;
 	return iter;
 }
 
-static void cgroup_tasks_stop(struct seq_file *s, void *v)
+static void cgroup_pidlist_stop(struct seq_file *s, void *v)
 {
-	struct cgroup_pids *cp = s->private;
-	struct cgroup *cgrp = cp->cgrp;
-	up_read(&cgrp->pids_mutex);
+	struct cgroup_pidlist *l = s->private;
+	up_read(&l->mutex);
 }
 
-static void *cgroup_tasks_next(struct seq_file *s, void *v, loff_t *pos)
+static void *cgroup_pidlist_next(struct seq_file *s, void *v, loff_t *pos)
 {
-	struct cgroup_pids *cp = s->private;
-	int *p = v;
-	int *end = cp->tasks_pids + cp->length;
-
+	struct cgroup_pidlist *l = s->private;
+	pid_t *p = v;
+	pid_t *end = l->list + l->length;
 	/*
 	 * Advance to the next pid in the array. If this goes off the
 	 * end, we're done
@@ -2308,124 +2669,107 @@ static void *cgroup_tasks_next(struct seq_file *s, void *v, loff_t *pos)
 	}
 }
 
-static int cgroup_tasks_show(struct seq_file *s, void *v)
+static int cgroup_pidlist_show(struct seq_file *s, void *v)
 {
 	return seq_printf(s, "%d\n", *(int *)v);
 }
 
-static struct seq_operations cgroup_tasks_seq_operations = {
-	.start = cgroup_tasks_start,
-	.stop = cgroup_tasks_stop,
-	.next = cgroup_tasks_next,
-	.show = cgroup_tasks_show,
+/*
+ * seq_operations functions for iterating on pidlists through seq_file -
+ * independent of whether it's tasks or procs
+ */
+static const struct seq_operations cgroup_pidlist_seq_operations = {
+	.start = cgroup_pidlist_start,
+	.stop = cgroup_pidlist_stop,
+	.next = cgroup_pidlist_next,
+	.show = cgroup_pidlist_show,
 };
 
-static void release_cgroup_pid_array(struct cgroup_pids *cp)
+static void cgroup_release_pid_array(struct cgroup_pidlist *l)
 {
-	struct cgroup *cgrp = cp->cgrp;
-
-	down_write(&cgrp->pids_mutex);
-	BUG_ON(!cp->use_count);
-	if (!--cp->use_count) {
-		list_del(&cp->list);
-		put_pid_ns(cp->ns);
-		kfree(cp->tasks_pids);
-		kfree(cp);
+	/*
+	 * the case where we're the last user of this particular pidlist will
+	 * have us remove it from the cgroup's list, which entails taking the
+	 * mutex. since in pidlist_find the pidlist->lock depends on cgroup->
+	 * pidlist_mutex, we have to take pidlist_mutex first.
+	 */
+	mutex_lock(&l->owner->pidlist_mutex);
+	down_write(&l->mutex);
+	BUG_ON(!l->use_count);
+	if (!--l->use_count) {
+		/* we're the last user if refcount is 0; remove and free */
+		list_del(&l->links);
+		mutex_unlock(&l->owner->pidlist_mutex);
+		pidlist_free(l->list);
+		put_pid_ns(l->key.ns);
+		up_write(&l->mutex);
+		kfree(l);
+		return;
 	}
-	up_write(&cgrp->pids_mutex);
+	mutex_unlock(&l->owner->pidlist_mutex);
+	up_write(&l->mutex);
 }
 
-static int cgroup_tasks_release(struct inode *inode, struct file *file)
+static int cgroup_pidlist_release(struct inode *inode, struct file *file)
 {
-	struct seq_file *seq;
-	struct cgroup_pids *cp;
-
+	struct cgroup_pidlist *l;
 	if (!(file->f_mode & FMODE_READ))
 		return 0;
-
-	seq = file->private_data;
-	cp = seq->private;
-
-	release_cgroup_pid_array(cp);
+	/*
+	 * the seq_file will only be initialized if the file was opened for
+	 * reading; hence we check if it's not null only in that case.
+	 */
+	l = ((struct seq_file *)file->private_data)->private;
+	cgroup_release_pid_array(l);
 	return seq_release(inode, file);
 }
 
-static struct file_operations cgroup_tasks_operations = {
+static const struct file_operations cgroup_pidlist_operations = {
 	.read = seq_read,
 	.llseek = seq_lseek,
 	.write = cgroup_file_write,
-	.release = cgroup_tasks_release,
+	.release = cgroup_pidlist_release,
 };
 
 /*
- * Handle an open on 'tasks' file.  Prepare an array containing the
- * process id's of tasks currently attached to the cgroup being opened.
+ * The following functions handle opens on a file that displays a pidlist
+ * (tasks or procs). Prepare an array of the process/thread IDs of whoever's
+ * in the cgroup.
  */
-
-static int cgroup_tasks_open(struct inode *unused, struct file *file)
+/* helper function for the two below it */
+static int cgroup_pidlist_open(struct file *file, enum cgroup_filetype type)
 {
 	struct cgroup *cgrp = __d_cgrp(file->f_dentry->d_parent);
-	struct pid_namespace *ns = current->nsproxy->pid_ns;
-	struct cgroup_pids *cp;
-	pid_t *pidarray;
-	int npids;
+	struct cgroup_pidlist *l;
 	int retval;
 
 	/* Nothing to do for write-only files */
 	if (!(file->f_mode & FMODE_READ))
 		return 0;
 
-	/*
-	 * If cgroup gets more users after we read count, we won't have
-	 * enough space - tough.  This race is indistinguishable to the
-	 * caller from the case that the additional cgroup users didn't
-	 * show up until sometime later on.
-	 */
-	npids = cgroup_task_count(cgrp);
-	pidarray = kmalloc(npids * sizeof(pid_t), GFP_KERNEL);
-	if (!pidarray)
-		return -ENOMEM;
-	npids = pid_array_load(pidarray, npids, cgrp);
-	sort(pidarray, npids, sizeof(pid_t), cmppid, NULL);
-
-	/*
-	 * Store the array in the cgroup, freeing the old
-	 * array if necessary
-	 */
-	down_write(&cgrp->pids_mutex);
-
-	list_for_each_entry(cp, &cgrp->pids_list, list) {
-		if (ns == cp->ns)
-			goto found;
-	}
-
-	cp = kzalloc(sizeof(*cp), GFP_KERNEL);
-	if (!cp) {
-		up_write(&cgrp->pids_mutex);
-		kfree(pidarray);
-		return -ENOMEM;
-	}
-	cp->cgrp = cgrp;
-	cp->ns = ns;
-	get_pid_ns(ns);
-	list_add(&cp->list, &cgrp->pids_list);
-found:
-	kfree(cp->tasks_pids);
-	cp->tasks_pids = pidarray;
-	cp->length = npids;
-	cp->use_count++;
-	up_write(&cgrp->pids_mutex);
-
-	file->f_op = &cgroup_tasks_operations;
+	/* have the array populated */
+	retval = pidlist_array_load(cgrp, type, &l);
+	if (retval)
+		return retval;
+	/* configure file information */
+	file->f_op = &cgroup_pidlist_operations;
 
-	retval = seq_open(file, &cgroup_tasks_seq_operations);
+	retval = seq_open(file, &cgroup_pidlist_seq_operations);
 	if (retval) {
-		release_cgroup_pid_array(cp);
+		cgroup_release_pid_array(l);
 		return retval;
 	}
-	((struct seq_file *)file->private_data)->private = cp;
+	((struct seq_file *)file->private_data)->private = l;
 	return 0;
 }
+static int cgroup_tasks_open(struct inode *unused, struct file *file)
+{
+	return cgroup_pidlist_open(file, CGROUP_FILE_TASKS);
+}
+static int cgroup_procs_open(struct inode *unused, struct file *file)
+{
+	return cgroup_pidlist_open(file, CGROUP_FILE_PROCS);
+}
 
 static u64 cgroup_read_notify_on_release(struct cgroup *cgrp,
 					    struct cftype *cft)
@@ -2448,21 +2792,27 @@ static int cgroup_write_notify_on_release(struct cgroup *cgrp,
 /*
  * for the common functions, 'private' gives the type of file
  */
+/* for hysterical raisins, we can't put this on the older files */
+#define CGROUP_FILE_GENERIC_PREFIX "cgroup."
 static struct cftype files[] = {
 	{
 		.name = "tasks",
 		.open = cgroup_tasks_open,
 		.write_u64 = cgroup_tasks_write,
-		.release = cgroup_tasks_release,
-		.private = FILE_TASKLIST,
+		.release = cgroup_pidlist_release,
 		.mode = S_IRUGO | S_IWUSR,
 	},
-
+	{
+		.name = CGROUP_FILE_GENERIC_PREFIX "procs",
+		.open = cgroup_procs_open,
+		/* .write_u64 = cgroup_procs_write, TODO */
+		.release = cgroup_pidlist_release,
+		.mode = S_IRUGO,
+	},
 	{
 		.name = "notify_on_release",
 		.read_u64 = cgroup_read_notify_on_release,
 		.write_u64 = cgroup_write_notify_on_release,
-		.private = FILE_NOTIFY_ON_RELEASE,
 	},
 };
 
@@ -2471,7 +2821,6 @@ static struct cftype cft_release_agent = {
 	.read_seq_string = cgroup_release_agent_show,
 	.write_string = cgroup_release_agent_write,
 	.max_write_len = PATH_MAX,
-	.private = FILE_RELEASE_AGENT,
 };
 
 static int cgroup_populate_dir(struct cgroup *cgrp)
@@ -2878,6 +3227,7 @@ int __init cgroup_init_early(void)
 	init_task.cgroups = &init_css_set;
 
 	init_css_set_link.cg = &init_css_set;
+	init_css_set_link.cgrp = dummytop;
 	list_add(&init_css_set_link.cgrp_link_list,
 		 &rootnode.top_cgroup.css_sets);
 	list_add(&init_css_set_link.cg_link_list,
@@ -2932,7 +3282,7 @@ int __init cgroup_init(void)
 	/* Add init_css_set to the hash table */
 	hhead = css_set_hash(init_css_set.subsys);
 	hlist_add_head(&init_css_set.hlist, hhead);
-
+	BUG_ON(!init_root_id(&rootnode));
 	err = register_filesystem(&cgroup_fs_type);
 	if (err < 0)
 		goto out;
@@ -2985,15 +3335,16 @@ static int proc_cgroup_show(struct seq_file *m, void *v)
 	for_each_active_root(root) {
 		struct cgroup_subsys *ss;
 		struct cgroup *cgrp;
-		int subsys_id;
 		int count = 0;
 
-		seq_printf(m, "%lu:", root->subsys_bits);
+		seq_printf(m, "%d:", root->hierarchy_id);
 		for_each_subsys(root, ss)
 			seq_printf(m, "%s%s", count++ ? "," : "", ss->name);
+		if (strlen(root->name))
+			seq_printf(m, "%sname=%s", count ? "," : "",
+				   root->name);
 		seq_putc(m, ':');
-		get_first_subsys(&root->top_cgroup, NULL, &subsys_id);
-		cgrp = task_cgroup(tsk, subsys_id);
+		cgrp = task_cgroup_from_root(tsk, root);
 		retval = cgroup_path(cgrp, buf, PAGE_SIZE);
 		if (retval < 0)
 			goto out_unlock;
@@ -3016,7 +3367,7 @@ static int cgroup_open(struct inode *inode, struct file *file)
 	return single_open(file, proc_cgroup_show, pid);
 }
 
-struct file_operations proc_cgroup_operations = {
+const struct file_operations proc_cgroup_operations = {
 	.open		= cgroup_open,
 	.read		= seq_read,
 	.llseek		= seq_lseek,
@@ -3032,8 +3383,8 @@ static int proc_cgroupstats_show(struct seq_file *m, void *v)
 	mutex_lock(&cgroup_mutex);
 	for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
 		struct cgroup_subsys *ss = subsys[i];
-		seq_printf(m, "%s\t%lu\t%d\t%d\n",
-			   ss->name, ss->root->subsys_bits,
+		seq_printf(m, "%s\t%d\t%d\t%d\n",
+			   ss->name, ss->root->hierarchy_id,
 			   ss->root->number_of_cgroups, !ss->disabled);
 	}
 	mutex_unlock(&cgroup_mutex);
@@ -3045,7 +3396,7 @@ static int cgroupstats_open(struct inode *inode, struct file *file)
 	return single_open(file, proc_cgroupstats_show, NULL);
 }
 
-static struct file_operations proc_cgroupstats_operations = {
+static const struct file_operations proc_cgroupstats_operations = {
 	.open = cgroupstats_open,
 	.read = seq_read,
 	.llseek = seq_lseek,
@@ -3319,13 +3670,11 @@ int cgroup_is_descendant(const struct cgroup *cgrp, struct task_struct *task)
 {
 	int ret;
 	struct cgroup *target;
-	int subsys_id;
 
 	if (cgrp == dummytop)
 		return 1;
 
-	get_first_subsys(cgrp, NULL, &subsys_id);
-	target = task_cgroup(task, subsys_id);
+	target = task_cgroup_from_root(task, cgrp->root);
 	while (cgrp != target && cgrp!= cgrp->top_cgroup)
 		cgrp = cgrp->parent;
 	ret = (cgrp == target);
@@ -3357,8 +3706,10 @@ static void check_for_release(struct cgroup *cgrp)
 void __css_put(struct cgroup_subsys_state *css)
 {
 	struct cgroup *cgrp = css->cgroup;
+	int val;
 	rcu_read_lock();
-	if (atomic_dec_return(&css->refcnt) == 1) {
+	val = atomic_dec_return(&css->refcnt);
+	if (val == 1) {
 		if (notify_on_release(cgrp)) {
 			set_bit(CGRP_RELEASABLE, &cgrp->flags);
 			check_for_release(cgrp);
@@ -3366,6 +3717,7 @@ void __css_put(struct cgroup_subsys_state *css)
 		cgroup_wakeup_rmdir_waiter(cgrp);
 	}
 	rcu_read_unlock();
+	WARN_ON_ONCE(val < 1);
 }
 
 /*
@@ -3692,3 +4044,154 @@ css_get_next(struct cgroup_subsys *ss, int id,
 	return ret;
 }
 
+#ifdef CONFIG_CGROUP_DEBUG
+static struct cgroup_subsys_state *debug_create(struct cgroup_subsys *ss,
+						   struct cgroup *cont)
+{
+	struct cgroup_subsys_state *css = kzalloc(sizeof(*css), GFP_KERNEL);
+
+	if (!css)
+		return ERR_PTR(-ENOMEM);
+
+	return css;
+}
+
+static void debug_destroy(struct cgroup_subsys *ss, struct cgroup *cont)
+{
+	kfree(cont->subsys[debug_subsys_id]);
+}
+
+static u64 cgroup_refcount_read(struct cgroup *cont, struct cftype *cft)
+{
+	return atomic_read(&cont->count);
+}
+
+static u64 debug_taskcount_read(struct cgroup *cont, struct cftype *cft)
+{
+	return cgroup_task_count(cont);
+}
+
+static u64 current_css_set_read(struct cgroup *cont, struct cftype *cft)
+{
+	return (u64)(unsigned long)current->cgroups;
+}
+
+static u64 current_css_set_refcount_read(struct cgroup *cont,
+					   struct cftype *cft)
+{
+	u64 count;
+
+	rcu_read_lock();
+	count = atomic_read(&current->cgroups->refcount);
+	rcu_read_unlock();
+	return count;
+}
+
+static int current_css_set_cg_links_read(struct cgroup *cont,
+					 struct cftype *cft,
+					 struct seq_file *seq)
+{
+	struct cg_cgroup_link *link;
+	struct css_set *cg;
+
+	read_lock(&css_set_lock);
+	rcu_read_lock();
+	cg = rcu_dereference(current->cgroups);
+	list_for_each_entry(link, &cg->cg_links, cg_link_list) {
+		struct cgroup *c = link->cgrp;
+		const char *name;
+
+		if (c->dentry)
+			name = c->dentry->d_name.name;
+		else
+			name = "?";
+		seq_printf(seq, "Root %d group %s\n",
+			   c->root->hierarchy_id, name);
+	}
+	rcu_read_unlock();
+	read_unlock(&css_set_lock);
+	return 0;
+}
+
+#define MAX_TASKS_SHOWN_PER_CSS 25
+static int cgroup_css_links_read(struct cgroup *cont,
+				 struct cftype *cft,
+				 struct seq_file *seq)
+{
+	struct cg_cgroup_link *link;
+
+	read_lock(&css_set_lock);
+	list_for_each_entry(link, &cont->css_sets, cgrp_link_list) {
+		struct css_set *cg = link->cg;
+		struct task_struct *task;
+		int count = 0;
+		seq_printf(seq, "css_set %p\n", cg);
+		list_for_each_entry(task, &cg->tasks, cg_list) {
+			if (count++ > MAX_TASKS_SHOWN_PER_CSS) {
+				seq_puts(seq, "  ...\n");
+				break;
+			} else {
+				seq_printf(seq, "  task %d\n",
+					   task_pid_vnr(task));
+			}
+		}
+	}
+	read_unlock(&css_set_lock);
+	return 0;
+}
+
+static u64 releasable_read(struct cgroup *cgrp, struct cftype *cft)
+{
+	return test_bit(CGRP_RELEASABLE, &cgrp->flags);
+}
+
+static struct cftype debug_files[] =  {
+	{
+		.name = "cgroup_refcount",
+		.read_u64 = cgroup_refcount_read,
+	},
+	{
+		.name = "taskcount",
+		.read_u64 = debug_taskcount_read,
+	},
+
+	{
+		.name = "current_css_set",
+		.read_u64 = current_css_set_read,
+	},
+
+	{
+		.name = "current_css_set_refcount",
+		.read_u64 = current_css_set_refcount_read,
+	},
+
+	{
+		.name = "current_css_set_cg_links",
+		.read_seq_string = current_css_set_cg_links_read,
+	},
+
+	{
+		.name = "cgroup_css_links",
+		.read_seq_string = cgroup_css_links_read,
+	},
+
+	{
+		.name = "releasable",
+		.read_u64 = releasable_read,
+	},
+};
+
+static int debug_populate(struct cgroup_subsys *ss, struct cgroup *cont)
+{
+	return cgroup_add_files(cont, ss, debug_files,
+				ARRAY_SIZE(debug_files));
+}
+
+struct cgroup_subsys debug_subsys = {
+	.name = "debug",
+	.create = debug_create,
+	.destroy = debug_destroy,
+	.populate = debug_populate,
+	.subsys_id = debug_subsys_id,
+};
+#endif /* CONFIG_CGROUP_DEBUG */
diff --git a/kernel/cgroup_debug.c b/kernel/cgroup_debug.c
deleted file mode 100644
index 0c92d797baa6..000000000000
--- a/kernel/cgroup_debug.c
+++ /dev/null
@@ -1,105 +0,0 @@
-/*
- * kernel/cgroup_debug.c - Example cgroup subsystem that
- * exposes debug info
- *
- * Copyright (C) Google Inc, 2007
- *
- * Developed by Paul Menage (menage@google.com)
- *
- */
-
-#include <linux/cgroup.h>
-#include <linux/fs.h>
-#include <linux/slab.h>
-#include <linux/rcupdate.h>
-
-#include <asm/atomic.h>
-
-static struct cgroup_subsys_state *debug_create(struct cgroup_subsys *ss,
-						   struct cgroup *cont)
-{
-	struct cgroup_subsys_state *css = kzalloc(sizeof(*css), GFP_KERNEL);
-
-	if (!css)
-		return ERR_PTR(-ENOMEM);
-
-	return css;
-}
-
-static void debug_destroy(struct cgroup_subsys *ss, struct cgroup *cont)
-{
-	kfree(cont->subsys[debug_subsys_id]);
-}
-
-static u64 cgroup_refcount_read(struct cgroup *cont, struct cftype *cft)
-{
-	return atomic_read(&cont->count);
-}
-
-static u64 taskcount_read(struct cgroup *cont, struct cftype *cft)
-{
-	u64 count;
-
-	count = cgroup_task_count(cont);
-	return count;
-}
-
-static u64 current_css_set_read(struct cgroup *cont, struct cftype *cft)
-{
-	return (u64)(long)current->cgroups;
-}
-
-static u64 current_css_set_refcount_read(struct cgroup *cont,
-					   struct cftype *cft)
-{
-	u64 count;
-
-	rcu_read_lock();
-	count = atomic_read(&current->cgroups->refcount);
-	rcu_read_unlock();
-	return count;
-}
-
-static u64 releasable_read(struct cgroup *cgrp, struct cftype *cft)
-{
-	return test_bit(CGRP_RELEASABLE, &cgrp->flags);
-}
-
-static struct cftype files[] =  {
-	{
-		.name = "cgroup_refcount",
-		.read_u64 = cgroup_refcount_read,
-	},
-	{
-		.name = "taskcount",
-		.read_u64 = taskcount_read,
-	},
-
-	{
-		.name = "current_css_set",
-		.read_u64 = current_css_set_read,
-	},
-
-	{
-		.name = "current_css_set_refcount",
-		.read_u64 = current_css_set_refcount_read,
-	},
-
-	{
-		.name = "releasable",
-		.read_u64 = releasable_read,
-	},
-};
-
-static int debug_populate(struct cgroup_subsys *ss, struct cgroup *cont)
-{
-	return cgroup_add_files(cont, ss, files, ARRAY_SIZE(files));
-}
-
-struct cgroup_subsys debug_subsys = {
-	.name = "debug",
-	.create = debug_create,
-	.destroy = debug_destroy,
-	.populate = debug_populate,
-	.subsys_id = debug_subsys_id,
-};
diff --git a/kernel/cgroup_freezer.c b/kernel/cgroup_freezer.c
index fb249e2bcada..59e9ef6aab40 100644
--- a/kernel/cgroup_freezer.c
+++ b/kernel/cgroup_freezer.c
@@ -159,7 +159,7 @@ static bool is_task_frozen_enough(struct task_struct *task)
  */
 static int freezer_can_attach(struct cgroup_subsys *ss,
 			      struct cgroup *new_cgroup,
-			      struct task_struct *task)
+			      struct task_struct *task, bool threadgroup)
 {
 	struct freezer *freezer;
 
@@ -177,6 +177,19 @@ static int freezer_can_attach(struct cgroup_subsys *ss,
 	if (freezer->state == CGROUP_FROZEN)
 		return -EBUSY;
 
+	if (threadgroup) {
+		struct task_struct *c;
+
+		rcu_read_lock();
+		list_for_each_entry_rcu(c, &task->thread_group, thread_group) {
+			if (is_task_frozen_enough(c)) {
+				rcu_read_unlock();
+				return -EBUSY;
+			}
+		}
+		rcu_read_unlock();
+	}
+
 	return 0;
 }
 
diff --git a/kernel/cpu.c b/kernel/cpu.c
index 8ce10043e4ac..6ba0f1ecb212 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -401,6 +401,7 @@ int disable_nonboot_cpus(void)
 			break;
 		}
 	}
+
 	if (!error) {
 		BUG_ON(num_online_cpus() > 1);
 		/* Make sure the CPUs won't be enabled by someone else */
@@ -413,6 +414,14 @@ int disable_nonboot_cpus(void)
 	return error;
 }
 
+void __weak arch_enable_nonboot_cpus_begin(void)
+{
+}
+
+void __weak arch_enable_nonboot_cpus_end(void)
+{
+}
+
 void __ref enable_nonboot_cpus(void)
 {
 	int cpu, error;
@@ -424,6 +433,9 @@ void __ref enable_nonboot_cpus(void)
 		goto out;
 
 	printk("Enabling non-boot CPUs ...\n");
+
+	arch_enable_nonboot_cpus_begin();
+
 	for_each_cpu(cpu, frozen_cpus) {
 		error = _cpu_up(cpu, 1);
 		if (!error) {
@@ -432,6 +444,9 @@ void __ref enable_nonboot_cpus(void)
 		}
 		printk(KERN_WARNING "Error taking CPU%d up: %d\n", cpu, error);
 	}
+
+	arch_enable_nonboot_cpus_end();
+
 	cpumask_clear(frozen_cpus);
 out:
 	cpu_maps_update_done();
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index 7e75a41bd508..b5cb469d2545 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -1324,9 +1324,10 @@ static int fmeter_getrate(struct fmeter *fmp)
 static cpumask_var_t cpus_attach;
 
 /* Called by cgroups to determine if a cpuset is usable; cgroup_mutex held */
-static int cpuset_can_attach(struct cgroup_subsys *ss,
-			     struct cgroup *cont, struct task_struct *tsk)
+static int cpuset_can_attach(struct cgroup_subsys *ss, struct cgroup *cont,
+			     struct task_struct *tsk, bool threadgroup)
 {
+	int ret;
 	struct cpuset *cs = cgroup_cs(cont);
 
 	if (cpumask_empty(cs->cpus_allowed) || nodes_empty(cs->mems_allowed))
@@ -1343,18 +1344,51 @@ static int cpuset_can_attach(struct cgroup_subsys *ss,
 	if (tsk->flags & PF_THREAD_BOUND)
 		return -EINVAL;
 
-	return security_task_setscheduler(tsk, 0, NULL);
+	ret = security_task_setscheduler(tsk, 0, NULL);
+	if (ret)
+		return ret;
+	if (threadgroup) {
+		struct task_struct *c;
+
+		rcu_read_lock();
+		list_for_each_entry_rcu(c, &tsk->thread_group, thread_group) {
+			ret = security_task_setscheduler(c, 0, NULL);
+			if (ret) {
+				rcu_read_unlock();
+				return ret;
+			}
+		}
+		rcu_read_unlock();
+	}
+	return 0;
+}
+
+static void cpuset_attach_task(struct task_struct *tsk, nodemask_t *to,
+			       struct cpuset *cs)
+{
+	int err;
+	/*
+	 * can_attach beforehand should guarantee that this doesn't fail.
+	 * TODO: have a better way to handle failure here
+	 */
+	err = set_cpus_allowed_ptr(tsk, cpus_attach);
+	WARN_ON_ONCE(err);
+
+	task_lock(tsk);
+	cpuset_change_task_nodemask(tsk, to);
+	task_unlock(tsk);
+	cpuset_update_task_spread_flag(cs, tsk);
+
 }
 
-static void cpuset_attach(struct cgroup_subsys *ss,
-			  struct cgroup *cont, struct cgroup *oldcont,
-			  struct task_struct *tsk)
+static void cpuset_attach(struct cgroup_subsys *ss, struct cgroup *cont,
+			  struct cgroup *oldcont, struct task_struct *tsk,
+			  bool threadgroup)
 {
 	nodemask_t from, to;
 	struct mm_struct *mm;
 	struct cpuset *cs = cgroup_cs(cont);
 	struct cpuset *oldcs = cgroup_cs(oldcont);
-	int err;
 
 	if (cs == &top_cpuset) {
 		cpumask_copy(cpus_attach, cpu_possible_mask);
@@ -1363,15 +1397,19 @@ static void cpuset_attach(struct cgroup_subsys *ss,
 		guarantee_online_cpus(cs, cpus_attach);
 		guarantee_online_mems(cs, &to);
 	}
-	err = set_cpus_allowed_ptr(tsk, cpus_attach);
-	if (err)
-		return;
 
-	task_lock(tsk);
-	cpuset_change_task_nodemask(tsk, &to);
-	task_unlock(tsk);
-	cpuset_update_task_spread_flag(cs, tsk);
+	/* do per-task migration stuff possibly for each in the threadgroup */
+	cpuset_attach_task(tsk, &to, cs);
+	if (threadgroup) {
+		struct task_struct *c;
+		rcu_read_lock();
+		list_for_each_entry_rcu(c, &tsk->thread_group, thread_group) {
+			cpuset_attach_task(c, &to, cs);
+		}
+		rcu_read_unlock();
+	}
 
+	/* change mm; only needs to be done once even if threadgroup */
 	from = oldcs->mems_allowed;
 	to = cs->mems_allowed;
 	mm = get_task_mm(tsk);
diff --git a/kernel/cred.c b/kernel/cred.c
index 1bb4d7e5d616..dd76cfe5f5b0 100644
--- a/kernel/cred.c
+++ b/kernel/cred.c
@@ -18,6 +18,18 @@
 #include <linux/cn_proc.h>
 #include "cred-internals.h"
 
+#if 0
+#define kdebug(FMT, ...) \
+	printk("[%-5.5s%5u] "FMT"\n", current->comm, current->pid ,##__VA_ARGS__)
+#else
+static inline __attribute__((format(printf, 1, 2)))
+void no_printk(const char *fmt, ...)
+{
+}
+#define kdebug(FMT, ...) \
+	no_printk("[%-5.5s%5u] "FMT"\n", current->comm, current->pid ,##__VA_ARGS__)
+#endif
+
 static struct kmem_cache *cred_jar;
 
 /*
@@ -36,6 +48,10 @@ static struct thread_group_cred init_tgcred = {
  */
 struct cred init_cred = {
 	.usage			= ATOMIC_INIT(4),
+#ifdef CONFIG_DEBUG_CREDENTIALS
+	.subscribers		= ATOMIC_INIT(2),
+	.magic			= CRED_MAGIC,
+#endif
 	.securebits		= SECUREBITS_DEFAULT,
 	.cap_inheritable	= CAP_INIT_INH_SET,
 	.cap_permitted		= CAP_FULL_SET,
@@ -48,6 +64,31 @@ struct cred init_cred = {
 #endif
 };
 
+static inline void set_cred_subscribers(struct cred *cred, int n)
+{
+#ifdef CONFIG_DEBUG_CREDENTIALS
+	atomic_set(&cred->subscribers, n);
+#endif
+}
+
+static inline int read_cred_subscribers(const struct cred *cred)
+{
+#ifdef CONFIG_DEBUG_CREDENTIALS
+	return atomic_read(&cred->subscribers);
+#else
+	return 0;
+#endif
+}
+
+static inline void alter_cred_subscribers(const struct cred *_cred, int n)
+{
+#ifdef CONFIG_DEBUG_CREDENTIALS
+	struct cred *cred = (struct cred *) _cred;
+
+	atomic_add(n, &cred->subscribers);
+#endif
+}
+
 /*
  * Dispose of the shared task group credentials
  */
@@ -85,15 +126,29 @@ static void put_cred_rcu(struct rcu_head *rcu)
 {
 	struct cred *cred = container_of(rcu, struct cred, rcu);
 
+	kdebug("put_cred_rcu(%p)", cred);
+
+#ifdef CONFIG_DEBUG_CREDENTIALS
+	if (cred->magic != CRED_MAGIC_DEAD ||
+	    atomic_read(&cred->usage) != 0 ||
+	    read_cred_subscribers(cred) != 0)
+		panic("CRED: put_cred_rcu() sees %p with"
+		      " mag %x, put %p, usage %d, subscr %d\n",
+		      cred, cred->magic, cred->put_addr,
+		      atomic_read(&cred->usage),
+		      read_cred_subscribers(cred));
+#else
 	if (atomic_read(&cred->usage) != 0)
 		panic("CRED: put_cred_rcu() sees %p with usage %d\n",
 		      cred, atomic_read(&cred->usage));
+#endif
 
 	security_cred_free(cred);
 	key_put(cred->thread_keyring);
 	key_put(cred->request_key_auth);
 	release_tgcred(cred);
-	put_group_info(cred->group_info);
+	if (cred->group_info)
+		put_group_info(cred->group_info);
 	free_uid(cred->user);
 	kmem_cache_free(cred_jar, cred);
 }
@@ -106,12 +161,90 @@ static void put_cred_rcu(struct rcu_head *rcu)
  */
 void __put_cred(struct cred *cred)
 {
+	kdebug("__put_cred(%p{%d,%d})", cred,
+	       atomic_read(&cred->usage),
+	       read_cred_subscribers(cred));
+
 	BUG_ON(atomic_read(&cred->usage) != 0);
+#ifdef CONFIG_DEBUG_CREDENTIALS
+	BUG_ON(read_cred_subscribers(cred) != 0);
+	cred->magic = CRED_MAGIC_DEAD;
+	cred->put_addr = __builtin_return_address(0);
+#endif
+	BUG_ON(cred == current->cred);
+	BUG_ON(cred == current->real_cred);
 
 	call_rcu(&cred->rcu, put_cred_rcu);
 }
 EXPORT_SYMBOL(__put_cred);
 
+/*
+ * Clean up a task's credentials when it exits
+ */
+void exit_creds(struct task_struct *tsk)
+{
+	struct cred *cred;
+
+	kdebug("exit_creds(%u,%p,%p,{%d,%d})", tsk->pid, tsk->real_cred, tsk->cred,
+	       atomic_read(&tsk->cred->usage),
+	       read_cred_subscribers(tsk->cred));
+
+	cred = (struct cred *) tsk->real_cred;
+	tsk->real_cred = NULL;
+	validate_creds(cred);
+	alter_cred_subscribers(cred, -1);
+	put_cred(cred);
+
+	cred = (struct cred *) tsk->cred;
+	tsk->cred = NULL;
+	validate_creds(cred);
+	alter_cred_subscribers(cred, -1);
+	put_cred(cred);
+
+	cred = (struct cred *) tsk->replacement_session_keyring;
+	if (cred) {
+		tsk->replacement_session_keyring = NULL;
+		validate_creds(cred);
+		put_cred(cred);
+	}
+}
+
+/*
+ * Allocate blank credentials, such that the credentials can be filled in at a
+ * later date without risk of ENOMEM.
+ */
+struct cred *cred_alloc_blank(void)
+{
+	struct cred *new;
+
+	new = kmem_cache_zalloc(cred_jar, GFP_KERNEL);
+	if (!new)
+		return NULL;
+
+#ifdef CONFIG_KEYS
+	new->tgcred = kzalloc(sizeof(*new->tgcred), GFP_KERNEL);
+	if (!new->tgcred) {
+		kfree(new);
+		return NULL;
+	}
+	atomic_set(&new->tgcred->usage, 1);
+#endif
+
+	atomic_set(&new->usage, 1);
+
+	if (security_cred_alloc_blank(new, GFP_KERNEL) < 0)
+		goto error;
+
+#ifdef CONFIG_DEBUG_CREDENTIALS
+	new->magic = CRED_MAGIC;
+#endif
+	return new;
+
+error:
+	abort_creds(new);
+	return NULL;
+}
+
 /**
  * prepare_creds - Prepare a new set of credentials for modification
  *
@@ -132,16 +265,19 @@ struct cred *prepare_creds(void)
 	const struct cred *old;
 	struct cred *new;
 
-	BUG_ON(atomic_read(&task->real_cred->usage) < 1);
+	validate_process_creds();
 
 	new = kmem_cache_alloc(cred_jar, GFP_KERNEL);
 	if (!new)
 		return NULL;
 
+	kdebug("prepare_creds() alloc %p", new);
+
 	old = task->cred;
 	memcpy(new, old, sizeof(struct cred));
 
 	atomic_set(&new->usage, 1);
+	set_cred_subscribers(new, 0);
 	get_group_info(new->group_info);
 	get_uid(new->user);
 
@@ -157,6 +293,7 @@ struct cred *prepare_creds(void)
 
 	if (security_prepare_creds(new, old, GFP_KERNEL) < 0)
 		goto error;
+	validate_creds(new);
 	return new;
 
 error:
@@ -229,9 +366,12 @@ struct cred *prepare_usermodehelper_creds(void)
 	if (!new)
 		return NULL;
 
+	kdebug("prepare_usermodehelper_creds() alloc %p", new);
+
 	memcpy(new, &init_cred, sizeof(struct cred));
 
 	atomic_set(&new->usage, 1);
+	set_cred_subscribers(new, 0);
 	get_group_info(new->group_info);
 	get_uid(new->user);
 
@@ -250,6 +390,7 @@ struct cred *prepare_usermodehelper_creds(void)
 #endif
 	if (security_prepare_creds(new, &init_cred, GFP_ATOMIC) < 0)
 		goto error;
+	validate_creds(new);
 
 	BUG_ON(atomic_read(&new->usage) != 1);
 	return new;
@@ -286,6 +427,10 @@ int copy_creds(struct task_struct *p, unsigned long clone_flags)
 	    ) {
 		p->real_cred = get_cred(p->cred);
 		get_cred(p->cred);
+		alter_cred_subscribers(p->cred, 2);
+		kdebug("share_creds(%p{%d,%d})",
+		       p->cred, atomic_read(&p->cred->usage),
+		       read_cred_subscribers(p->cred));
 		atomic_inc(&p->cred->user->processes);
 		return 0;
 	}
@@ -331,6 +476,8 @@ int copy_creds(struct task_struct *p, unsigned long clone_flags)
 
 	atomic_inc(&new->user->processes);
 	p->cred = p->real_cred = get_cred(new);
+	alter_cred_subscribers(new, 2);
+	validate_creds(new);
 	return 0;
 
 error_put:
@@ -355,13 +502,20 @@ error_put:
 int commit_creds(struct cred *new)
 {
 	struct task_struct *task = current;
-	const struct cred *old;
+	const struct cred *old = task->real_cred;
+
+	kdebug("commit_creds(%p{%d,%d})", new,
+	       atomic_read(&new->usage),
+	       read_cred_subscribers(new));
 
-	BUG_ON(task->cred != task->real_cred);
-	BUG_ON(atomic_read(&task->real_cred->usage) < 2);
+	BUG_ON(task->cred != old);
+#ifdef CONFIG_DEBUG_CREDENTIALS
+	BUG_ON(read_cred_subscribers(old) < 2);
+	validate_creds(old);
+	validate_creds(new);
+#endif
 	BUG_ON(atomic_read(&new->usage) < 1);
 
-	old = task->real_cred;
 	security_commit_creds(new, old);
 
 	get_cred(new); /* we will require a ref for the subj creds too */
@@ -390,12 +544,14 @@ int commit_creds(struct cred *new)
 	 *   cheaply with the new uid cache, so if it matters
 	 *   we should be checking for it.  -DaveM
 	 */
+	alter_cred_subscribers(new, 2);
 	if (new->user != old->user)
 		atomic_inc(&new->user->processes);
 	rcu_assign_pointer(task->real_cred, new);
 	rcu_assign_pointer(task->cred, new);
 	if (new->user != old->user)
 		atomic_dec(&old->user->processes);
+	alter_cred_subscribers(old, -2);
 
 	sched_switch_user(task);
 
@@ -428,6 +584,13 @@ EXPORT_SYMBOL(commit_creds);
  */
 void abort_creds(struct cred *new)
 {
+	kdebug("abort_creds(%p{%d,%d})", new,
+	       atomic_read(&new->usage),
+	       read_cred_subscribers(new));
+
+#ifdef CONFIG_DEBUG_CREDENTIALS
+	BUG_ON(read_cred_subscribers(new) != 0);
+#endif
 	BUG_ON(atomic_read(&new->usage) < 1);
 	put_cred(new);
 }
@@ -444,7 +607,20 @@ const struct cred *override_creds(const struct cred *new)
 {
 	const struct cred *old = current->cred;
 
-	rcu_assign_pointer(current->cred, get_cred(new));
+	kdebug("override_creds(%p{%d,%d})", new,
+	       atomic_read(&new->usage),
+	       read_cred_subscribers(new));
+
+	validate_creds(old);
+	validate_creds(new);
+	get_cred(new);
+	alter_cred_subscribers(new, 1);
+	rcu_assign_pointer(current->cred, new);
+	alter_cred_subscribers(old, -1);
+
+	kdebug("override_creds() = %p{%d,%d}", old,
+	       atomic_read(&old->usage),
+	       read_cred_subscribers(old));
 	return old;
 }
 EXPORT_SYMBOL(override_creds);
@@ -460,7 +636,15 @@ void revert_creds(const struct cred *old)
 {
 	const struct cred *override = current->cred;
 
+	kdebug("revert_creds(%p{%d,%d})", old,
+	       atomic_read(&old->usage),
+	       read_cred_subscribers(old));
+
+	validate_creds(old);
+	validate_creds(override);
+	alter_cred_subscribers(old, 1);
 	rcu_assign_pointer(current->cred, old);
+	alter_cred_subscribers(override, -1);
 	put_cred(override);
 }
 EXPORT_SYMBOL(revert_creds);
@@ -502,11 +686,15 @@ struct cred *prepare_kernel_cred(struct task_struct *daemon)
 	if (!new)
 		return NULL;
 
+	kdebug("prepare_kernel_cred() alloc %p", new);
+
 	if (daemon)
 		old = get_task_cred(daemon);
 	else
 		old = get_cred(&init_cred);
 
+	validate_creds(old);
+
 	*new = *old;
 	get_uid(new->user);
 	get_group_info(new->group_info);
@@ -526,7 +714,9 @@ struct cred *prepare_kernel_cred(struct task_struct *daemon)
 		goto error;
 
 	atomic_set(&new->usage, 1);
+	set_cred_subscribers(new, 0);
 	put_cred(old);
+	validate_creds(new);
 	return new;
 
 error:
@@ -589,3 +779,114 @@ int set_create_files_as(struct cred *new, struct inode *inode)
 	return security_kernel_create_files_as(new, inode);
 }
 EXPORT_SYMBOL(set_create_files_as);
+
+#ifdef CONFIG_DEBUG_CREDENTIALS
+
+bool creds_are_invalid(const struct cred *cred)
+{
+	if (cred->magic != CRED_MAGIC)
+		return true;
+	if (atomic_read(&cred->usage) < atomic_read(&cred->subscribers))
+		return true;
+#ifdef CONFIG_SECURITY_SELINUX
+	if (selinux_is_enabled()) {
+		if ((unsigned long) cred->security < PAGE_SIZE)
+			return true;
+		if ((*(u32 *)cred->security & 0xffffff00) ==
+		    (POISON_FREE << 24 | POISON_FREE << 16 | POISON_FREE << 8))
+			return true;
+	}
+#endif
+	return false;
+}
+EXPORT_SYMBOL(creds_are_invalid);
+
+/*
+ * dump invalid credentials
+ */
+static void dump_invalid_creds(const struct cred *cred, const char *label,
+			       const struct task_struct *tsk)
+{
+	printk(KERN_ERR "CRED: %s credentials: %p %s%s%s\n",
+	       label, cred,
+	       cred == &init_cred ? "[init]" : "",
+	       cred == tsk->real_cred ? "[real]" : "",
+	       cred == tsk->cred ? "[eff]" : "");
+	printk(KERN_ERR "CRED: ->magic=%x, put_addr=%p\n",
+	       cred->magic, cred->put_addr);
+	printk(KERN_ERR "CRED: ->usage=%d, subscr=%d\n",
+	       atomic_read(&cred->usage),
+	       read_cred_subscribers(cred));
+	printk(KERN_ERR "CRED: ->*uid = { %d,%d,%d,%d }\n",
+	       cred->uid, cred->euid, cred->suid, cred->fsuid);
+	printk(KERN_ERR "CRED: ->*gid = { %d,%d,%d,%d }\n",
+	       cred->gid, cred->egid, cred->sgid, cred->fsgid);
+#ifdef CONFIG_SECURITY
+	printk(KERN_ERR "CRED: ->security is %p\n", cred->security);
+	if ((unsigned long) cred->security >= PAGE_SIZE &&
+	    (((unsigned long) cred->security & 0xffffff00) !=
+	     (POISON_FREE << 24 | POISON_FREE << 16 | POISON_FREE << 8)))
+		printk(KERN_ERR "CRED: ->security {%x, %x}\n",
+		       ((u32*)cred->security)[0],
+		       ((u32*)cred->security)[1]);
+#endif
+}
+
+/*
+ * report use of invalid credentials
+ */
+void __invalid_creds(const struct cred *cred, const char *file, unsigned line)
+{
+	printk(KERN_ERR "CRED: Invalid credentials\n");
+	printk(KERN_ERR "CRED: At %s:%u\n", file, line);
+	dump_invalid_creds(cred, "Specified", current);
+	BUG();
+}
+EXPORT_SYMBOL(__invalid_creds);
+
+/*
+ * check the credentials on a process
+ */
+void __validate_process_creds(struct task_struct *tsk,
+			      const char *file, unsigned line)
+{
+	if (tsk->cred == tsk->real_cred) {
+		if (unlikely(read_cred_subscribers(tsk->cred) < 2 ||
+			     creds_are_invalid(tsk->cred)))
+			goto invalid_creds;
+	} else {
+		if (unlikely(read_cred_subscribers(tsk->real_cred) < 1 ||
+			     read_cred_subscribers(tsk->cred) < 1 ||
+			     creds_are_invalid(tsk->real_cred) ||
+			     creds_are_invalid(tsk->cred)))
+			goto invalid_creds;
+	}
+	return;
+
+invalid_creds:
+	printk(KERN_ERR "CRED: Invalid process credentials\n");
+	printk(KERN_ERR "CRED: At %s:%u\n", file, line);
+
+	dump_invalid_creds(tsk->real_cred, "Real", tsk);
+	if (tsk->cred != tsk->real_cred)
+		dump_invalid_creds(tsk->cred, "Effective", tsk);
+	else
+		printk(KERN_ERR "CRED: Effective creds == Real creds\n");
+	BUG();
+}
+EXPORT_SYMBOL(__validate_process_creds);
+
+/*
+ * check creds for do_exit()
+ */
+void validate_creds_for_do_exit(struct task_struct *tsk)
+{
+	kdebug("validate_creds_for_do_exit(%p,%p{%d,%d})",
+	       tsk->real_cred, tsk->cred,
+	       atomic_read(&tsk->cred->usage),
+	       read_cred_subscribers(tsk->cred));
+
+	__validate_process_creds(tsk, __FILE__, __LINE__);
+}
+
+#endif /* CONFIG_DEBUG_CREDENTIALS */
diff --git a/kernel/delayacct.c b/kernel/delayacct.c
index abb6e17505e2..ead9b610aa71 100644
--- a/kernel/delayacct.c
+++ b/kernel/delayacct.c
@@ -15,6 +15,7 @@
 
 #include <linux/sched.h>
 #include <linux/slab.h>
+#include <linux/taskstats.h>
 #include <linux/time.h>
 #include <linux/sysctl.h>
 #include <linux/delayacct.h>
diff --git a/kernel/dma-coherent.c b/kernel/dma-coherent.c
deleted file mode 100644
index 962a3b574f21..000000000000
--- a/kernel/dma-coherent.c
+++ /dev/null
@@ -1,176 +0,0 @@
-/*
- * Coherent per-device memory handling.
- * Borrowed from i386
- */
-#include <linux/kernel.h>
-#include <linux/dma-mapping.h>
-
-struct dma_coherent_mem {
-	void		*virt_base;
-	u32		device_base;
-	int		size;
-	int		flags;
-	unsigned long	*bitmap;
-};
-
-int dma_declare_coherent_memory(struct device *dev, dma_addr_t bus_addr,
-				dma_addr_t device_addr, size_t size, int flags)
-{
-	void __iomem *mem_base = NULL;
-	int pages = size >> PAGE_SHIFT;
-	int bitmap_size = BITS_TO_LONGS(pages) * sizeof(long);
-
-	if ((flags & (DMA_MEMORY_MAP | DMA_MEMORY_IO)) == 0)
-		goto out;
-	if (!size)
-		goto out;
-	if (dev->dma_mem)
-		goto out;
-
-	/* FIXME: this routine just ignores DMA_MEMORY_INCLUDES_CHILDREN */
-
-	mem_base = ioremap(bus_addr, size);
-	if (!mem_base)
-		goto out;
-
-	dev->dma_mem = kzalloc(sizeof(struct dma_coherent_mem), GFP_KERNEL);
-	if (!dev->dma_mem)
-		goto out;
-	dev->dma_mem->bitmap = kzalloc(bitmap_size, GFP_KERNEL);
-	if (!dev->dma_mem->bitmap)
-		goto free1_out;
-
-	dev->dma_mem->virt_base = mem_base;
-	dev->dma_mem->device_base = device_addr;
-	dev->dma_mem->size = pages;
-	dev->dma_mem->flags = flags;
-
-	if (flags & DMA_MEMORY_MAP)
-		return DMA_MEMORY_MAP;
-
-	return DMA_MEMORY_IO;
-
- free1_out:
-	kfree(dev->dma_mem);
- out:
-	if (mem_base)
-		iounmap(mem_base);
-	return 0;
-}
-EXPORT_SYMBOL(dma_declare_coherent_memory);
-
-void dma_release_declared_memory(struct device *dev)
-{
-	struct dma_coherent_mem *mem = dev->dma_mem;
-
-	if (!mem)
-		return;
-	dev->dma_mem = NULL;
-	iounmap(mem->virt_base);
-	kfree(mem->bitmap);
-	kfree(mem);
-}
-EXPORT_SYMBOL(dma_release_declared_memory);
-
-void *dma_mark_declared_memory_occupied(struct device *dev,
-					dma_addr_t device_addr, size_t size)
-{
-	struct dma_coherent_mem *mem = dev->dma_mem;
-	int pos, err;
-
-	size += device_addr & ~PAGE_MASK;
-
-	if (!mem)
-		return ERR_PTR(-EINVAL);
-
-	pos = (device_addr - mem->device_base) >> PAGE_SHIFT;
-	err = bitmap_allocate_region(mem->bitmap, pos, get_order(size));
-	if (err != 0)
-		return ERR_PTR(err);
-	return mem->virt_base + (pos << PAGE_SHIFT);
-}
-EXPORT_SYMBOL(dma_mark_declared_memory_occupied);
-
-/**
- * dma_alloc_from_coherent() - try to allocate memory from the per-device coherent area
- *
- * @dev:	device from which we allocate memory
- * @size:	size of requested memory area
- * @dma_handle:	This will be filled with the correct dma handle
- * @ret:	This pointer will be filled with the virtual address
- *		to allocated area.
- *
- * This function should be only called from per-arch dma_alloc_coherent()
- * to support allocation from per-device coherent memory pools.
- *
- * Returns 0 if dma_alloc_coherent should continue with allocating from
- * generic memory areas, or !0 if dma_alloc_coherent should return @ret.
- */
-int dma_alloc_from_coherent(struct device *dev, ssize_t size,
-				       dma_addr_t *dma_handle, void **ret)
-{
-	struct dma_coherent_mem *mem;
-	int order = get_order(size);
-	int pageno;
-
-	if (!dev)
-		return 0;
-	mem = dev->dma_mem;
-	if (!mem)
-		return 0;
-
-	*ret = NULL;
-
-	if (unlikely(size > (mem->size << PAGE_SHIFT)))
-		goto err;
-
-	pageno = bitmap_find_free_region(mem->bitmap, mem->size, order);
-	if (unlikely(pageno < 0))
-		goto err;
-
-	/*
-	 * Memory was found in the per-device area.
-	 */
-	*dma_handle = mem->device_base + (pageno << PAGE_SHIFT);
-	*ret = mem->virt_base + (pageno << PAGE_SHIFT);
-	memset(*ret, 0, size);
-
-	return 1;
-
-err:
-	/*
-	 * In the case where the allocation can not be satisfied from the
-	 * per-device area, try to fall back to generic memory if the
-	 * constraints allow it.
-	 */
-	return mem->flags & DMA_MEMORY_EXCLUSIVE;
-}
-EXPORT_SYMBOL(dma_alloc_from_coherent);
-
-/**
- * dma_release_from_coherent() - try to free the memory allocated from per-device coherent memory pool
- * @dev:	device from which the memory was allocated
- * @order:	the order of pages allocated
- * @vaddr:	virtual address of allocated pages
- *
- * This checks whether the memory was allocated from the per-device
- * coherent memory pool and if so, releases that memory.
- *
- * Returns 1 if we correctly released the memory, or 0 if
- * dma_release_coherent() should proceed with releasing memory from
- * generic pools.
- */
-int dma_release_from_coherent(struct device *dev, int order, void *vaddr)
-{
-	struct dma_coherent_mem *mem = dev ? dev->dma_mem : NULL;
-
-	if (mem && vaddr >= mem->virt_base && vaddr <
-		   (mem->virt_base + (mem->size << PAGE_SHIFT))) {
-		int page = (vaddr - mem->virt_base) >> PAGE_SHIFT;
-
-		bitmap_release_region(mem->bitmap, page, order);
-		return 1;
-	}
-	return 0;
-}
-EXPORT_SYMBOL(dma_release_from_coherent);
diff --git a/kernel/exit.c b/kernel/exit.c
index 869dc221733e..f7864ac2ecc1 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -47,7 +47,7 @@
 #include <linux/tracehook.h>
 #include <linux/fs_struct.h>
 #include <linux/init_task.h>
-#include <linux/perf_counter.h>
+#include <linux/perf_event.h>
 #include <trace/events/sched.h>
 
 #include <asm/uaccess.h>
@@ -154,8 +154,8 @@ static void delayed_put_task_struct(struct rcu_head *rhp)
 {
 	struct task_struct *tsk = container_of(rhp, struct task_struct, rcu);
 
-#ifdef CONFIG_PERF_COUNTERS
-	WARN_ON_ONCE(tsk->perf_counter_ctxp);
+#ifdef CONFIG_PERF_EVENTS
+	WARN_ON_ONCE(tsk->perf_event_ctxp);
 #endif
 	trace_sched_process_free(tsk);
 	put_task_struct(tsk);
@@ -901,6 +901,8 @@ NORET_TYPE void do_exit(long code)
 
 	tracehook_report_exit(&code);
 
+	validate_creds_for_do_exit(tsk);
+
 	/*
 	 * We're taking recursive faults here in do_exit. Safest is to just
 	 * leave this task alone and wait for reboot.
@@ -943,6 +945,8 @@ NORET_TYPE void do_exit(long code)
 	if (group_dead) {
 		hrtimer_cancel(&tsk->signal->real_timer);
 		exit_itimers(tsk->signal);
+		if (tsk->mm)
+			setmax_mm_hiwater_rss(&tsk->signal->maxrss, tsk->mm);
 	}
 	acct_collect(code, group_dead);
 	if (group_dead)
@@ -970,8 +974,6 @@ NORET_TYPE void do_exit(long code)
 		disassociate_ctty(1);
 
 	module_put(task_thread_info(tsk)->exec_domain->module);
-	if (tsk->binfmt)
-		module_put(tsk->binfmt->module);
 
 	proc_exit_connector(tsk);
 
@@ -979,7 +981,7 @@ NORET_TYPE void do_exit(long code)
 	 * Flush inherited counters to the parent - before the parent
 	 * gets woken up by child-exit notifications.
 	 */
-	perf_counter_exit_task(tsk);
+	perf_event_exit_task(tsk);
 
 	exit_notify(tsk, group_dead);
 #ifdef CONFIG_NUMA
@@ -987,8 +989,6 @@ NORET_TYPE void do_exit(long code)
 	tsk->mempolicy = NULL;
 #endif
 #ifdef CONFIG_FUTEX
-	if (unlikely(!list_empty(&tsk->pi_state_list)))
-		exit_pi_state_list(tsk);
 	if (unlikely(current->pi_state_cache))
 		kfree(current->pi_state_cache);
 #endif
@@ -1009,7 +1009,10 @@ NORET_TYPE void do_exit(long code)
 	if (tsk->splice_pipe)
 		__free_pipe_info(tsk->splice_pipe);
 
+	validate_creds_for_do_exit(tsk);
+
 	preempt_disable();
+	exit_rcu();
 	/* causes final put_task_struct in finish_task_switch(). */
 	tsk->state = TASK_DEAD;
 	schedule();
@@ -1088,28 +1091,28 @@ struct wait_opts {
 	int __user		*wo_stat;
 	struct rusage __user	*wo_rusage;
 
+	wait_queue_t		child_wait;
 	int			notask_error;
 };
 
-static struct pid *task_pid_type(struct task_struct *task, enum pid_type type)
+static inline
+struct pid *task_pid_type(struct task_struct *task, enum pid_type type)
 {
-	struct pid *pid = NULL;
-	if (type == PIDTYPE_PID)
-		pid = task->pids[type].pid;
-	else if (type < PIDTYPE_MAX)
-		pid = task->group_leader->pids[type].pid;
-	return pid;
+	if (type != PIDTYPE_PID)
+		task = task->group_leader;
+	return task->pids[type].pid;
 }
 
-static int eligible_child(struct wait_opts *wo, struct task_struct *p)
+static int eligible_pid(struct wait_opts *wo, struct task_struct *p)
 {
-	int err;
-
-	if (wo->wo_type < PIDTYPE_MAX) {
-		if (task_pid_type(p, wo->wo_type) != wo->wo_pid)
-			return 0;
-	}
+	return	wo->wo_type == PIDTYPE_MAX ||
+		task_pid_type(p, wo->wo_type) == wo->wo_pid;
+}
 
+static int eligible_child(struct wait_opts *wo, struct task_struct *p)
+{
+	if (!eligible_pid(wo, p))
+		return 0;
 	/* Wait for all children (clone and not) if __WALL is set;
 	 * otherwise, wait for clone children *only* if __WCLONE is
 	 * set; otherwise, wait for non-clone children *only*.  (Note:
@@ -1119,10 +1122,6 @@ static int eligible_child(struct wait_opts *wo, struct task_struct *p)
 	    && !(wo->wo_flags & __WALL))
 		return 0;
 
-	err = security_task_wait(p);
-	if (err)
-		return err;
-
 	return 1;
 }
 
@@ -1135,18 +1134,20 @@ static int wait_noreap_copyout(struct wait_opts *wo, struct task_struct *p,
 
 	put_task_struct(p);
 	infop = wo->wo_info;
-	if (!retval)
-		retval = put_user(SIGCHLD, &infop->si_signo);
-	if (!retval)
-		retval = put_user(0, &infop->si_errno);
-	if (!retval)
-		retval = put_user((short)why, &infop->si_code);
-	if (!retval)
-		retval = put_user(pid, &infop->si_pid);
-	if (!retval)
-		retval = put_user(uid, &infop->si_uid);
-	if (!retval)
-		retval = put_user(status, &infop->si_status);
+	if (infop) {
+		if (!retval)
+			retval = put_user(SIGCHLD, &infop->si_signo);
+		if (!retval)
+			retval = put_user(0, &infop->si_errno);
+		if (!retval)
+			retval = put_user((short)why, &infop->si_code);
+		if (!retval)
+			retval = put_user(pid, &infop->si_pid);
+		if (!retval)
+			retval = put_user(uid, &infop->si_uid);
+		if (!retval)
+			retval = put_user(status, &infop->si_status);
+	}
 	if (!retval)
 		retval = pid;
 	return retval;
@@ -1203,6 +1204,7 @@ static int wait_task_zombie(struct wait_opts *wo, struct task_struct *p)
 	if (likely(!traced) && likely(!task_detached(p))) {
 		struct signal_struct *psig;
 		struct signal_struct *sig;
+		unsigned long maxrss;
 
 		/*
 		 * The resource counters for the group leader are in its
@@ -1251,6 +1253,9 @@ static int wait_task_zombie(struct wait_opts *wo, struct task_struct *p)
 		psig->coublock +=
 			task_io_get_oublock(p) +
 			sig->oublock + sig->coublock;
+		maxrss = max(sig->maxrss, sig->cmaxrss);
+		if (psig->cmaxrss < maxrss)
+			psig->cmaxrss = maxrss;
 		task_io_accounting_add(&psig->ioac, &p->ioac);
 		task_io_accounting_add(&psig->ioac, &sig->ioac);
 		spin_unlock_irq(&p->real_parent->sighand->siglock);
@@ -1472,13 +1477,14 @@ static int wait_task_continued(struct wait_opts *wo, struct task_struct *p)
  * then ->notask_error is 0 if @p is an eligible child,
  * or another error from security_task_wait(), or still -ECHILD.
  */
-static int wait_consider_task(struct wait_opts *wo, struct task_struct *parent,
-				int ptrace, struct task_struct *p)
+static int wait_consider_task(struct wait_opts *wo, int ptrace,
+				struct task_struct *p)
 {
 	int ret = eligible_child(wo, p);
 	if (!ret)
 		return ret;
 
+	ret = security_task_wait(p);
 	if (unlikely(ret < 0)) {
 		/*
 		 * If we have not yet seen any eligible child,
@@ -1540,7 +1546,7 @@ static int do_wait_thread(struct wait_opts *wo, struct task_struct *tsk)
 		 * Do not consider detached threads.
 		 */
 		if (!task_detached(p)) {
-			int ret = wait_consider_task(wo, tsk, 0, p);
+			int ret = wait_consider_task(wo, 0, p);
 			if (ret)
 				return ret;
 		}
@@ -1554,7 +1560,7 @@ static int ptrace_do_wait(struct wait_opts *wo, struct task_struct *tsk)
 	struct task_struct *p;
 
 	list_for_each_entry(p, &tsk->ptraced, ptrace_entry) {
-		int ret = wait_consider_task(wo, tsk, 1, p);
+		int ret = wait_consider_task(wo, 1, p);
 		if (ret)
 			return ret;
 	}
@@ -1562,15 +1568,38 @@ static int ptrace_do_wait(struct wait_opts *wo, struct task_struct *tsk)
 	return 0;
 }
 
+static int child_wait_callback(wait_queue_t *wait, unsigned mode,
+				int sync, void *key)
+{
+	struct wait_opts *wo = container_of(wait, struct wait_opts,
+						child_wait);
+	struct task_struct *p = key;
+
+	if (!eligible_pid(wo, p))
+		return 0;
+
+	if ((wo->wo_flags & __WNOTHREAD) && wait->private != p->parent)
+		return 0;
+
+	return default_wake_function(wait, mode, sync, key);
+}
+
+void __wake_up_parent(struct task_struct *p, struct task_struct *parent)
+{
+	__wake_up_sync_key(&parent->signal->wait_chldexit,
+				TASK_INTERRUPTIBLE, 1, p);
+}
+
 static long do_wait(struct wait_opts *wo)
 {
-	DECLARE_WAITQUEUE(wait, current);
 	struct task_struct *tsk;
 	int retval;
 
 	trace_sched_process_wait(wo->wo_pid);
 
-	add_wait_queue(&current->signal->wait_chldexit,&wait);
+	init_waitqueue_func_entry(&wo->child_wait, child_wait_callback);
+	wo->child_wait.private = current;
+	add_wait_queue(&current->signal->wait_chldexit, &wo->child_wait);
 repeat:
 	/*
 	 * If there is nothing that can match our critiera just get out.
@@ -1611,32 +1640,7 @@ notask:
 	}
 end:
 	__set_current_state(TASK_RUNNING);
-	remove_wait_queue(&current->signal->wait_chldexit,&wait);
-	if (wo->wo_info) {
-		struct siginfo __user *infop = wo->wo_info;
-
-		if (retval > 0)
-			retval = 0;
-		else {
-			/*
-			 * For a WNOHANG return, clear out all the fields
-			 * we would set so the user can easily tell the
-			 * difference.
-			 */
-			if (!retval)
-				retval = put_user(0, &infop->si_signo);
-			if (!retval)
-				retval = put_user(0, &infop->si_errno);
-			if (!retval)
-				retval = put_user(0, &infop->si_code);
-			if (!retval)
-				retval = put_user(0, &infop->si_pid);
-			if (!retval)
-				retval = put_user(0, &infop->si_uid);
-			if (!retval)
-				retval = put_user(0, &infop->si_status);
-		}
-	}
+	remove_wait_queue(&current->signal->wait_chldexit, &wo->child_wait);
 	return retval;
 }
 
@@ -1681,6 +1685,29 @@ SYSCALL_DEFINE5(waitid, int, which, pid_t, upid, struct siginfo __user *,
 	wo.wo_stat	= NULL;
 	wo.wo_rusage	= ru;
 	ret = do_wait(&wo);
+
+	if (ret > 0) {
+		ret = 0;
+	} else if (infop) {
+		/*
+		 * For a WNOHANG return, clear out all the fields
+		 * we would set so the user can easily tell the
+		 * difference.
+		 */
+		if (!ret)
+			ret = put_user(0, &infop->si_signo);
+		if (!ret)
+			ret = put_user(0, &infop->si_errno);
+		if (!ret)
+			ret = put_user(0, &infop->si_code);
+		if (!ret)
+			ret = put_user(0, &infop->si_pid);
+		if (!ret)
+			ret = put_user(0, &infop->si_uid);
+		if (!ret)
+			ret = put_user(0, &infop->si_status);
+	}
+
 	put_pid(pid);
 
 	/* avoid REGPARM breakage on x86: */
diff --git a/kernel/fork.c b/kernel/fork.c
index e6c04d462ab2..166b8c49257c 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -49,6 +49,7 @@
 #include <linux/ftrace.h>
 #include <linux/profile.h>
 #include <linux/rmap.h>
+#include <linux/ksm.h>
 #include <linux/acct.h>
 #include <linux/tsacct_kern.h>
 #include <linux/cn_proc.h>
@@ -61,7 +62,8 @@
 #include <linux/blkdev.h>
 #include <linux/fs_struct.h>
 #include <linux/magic.h>
-#include <linux/perf_counter.h>
+#include <linux/perf_event.h>
+#include <linux/posix-timers.h>
 
 #include <asm/pgtable.h>
 #include <asm/pgalloc.h>
@@ -89,7 +91,7 @@ int nr_processes(void)
 	int cpu;
 	int total = 0;
 
-	for_each_online_cpu(cpu)
+	for_each_possible_cpu(cpu)
 		total += per_cpu(process_counts, cpu);
 
 	return total;
@@ -136,9 +138,17 @@ struct kmem_cache *vm_area_cachep;
 /* SLAB cache for mm_struct structures (tsk->mm) */
 static struct kmem_cache *mm_cachep;
 
+static void account_kernel_stack(struct thread_info *ti, int account)
+{
+	struct zone *zone = page_zone(virt_to_page(ti));
+
+	mod_zone_page_state(zone, NR_KERNEL_STACK, account);
+}
+
 void free_task(struct task_struct *tsk)
 {
 	prop_local_destroy_single(&tsk->dirties);
+	account_kernel_stack(tsk->stack, -1);
 	free_thread_info(tsk->stack);
 	rt_mutex_debug_task_free(tsk);
 	ftrace_graph_exit_task(tsk);
@@ -152,8 +162,7 @@ void __put_task_struct(struct task_struct *tsk)
 	WARN_ON(atomic_read(&tsk->usage));
 	WARN_ON(tsk == current);
 
-	put_cred(tsk->real_cred);
-	put_cred(tsk->cred);
+	exit_creds(tsk);
 	delayacct_tsk_free(tsk);
 
 	if (!profile_handoff_task(tsk))
@@ -254,6 +263,9 @@ static struct task_struct *dup_task_struct(struct task_struct *orig)
 	tsk->btrace_seq = 0;
 #endif
 	tsk->splice_pipe = NULL;
+
+	account_kernel_stack(ti, 1);
+
 	return tsk;
 
 out:
@@ -289,6 +301,9 @@ static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm)
 	rb_link = &mm->mm_rb.rb_node;
 	rb_parent = NULL;
 	pprev = &mm->mmap;
+	retval = ksm_fork(mm, oldmm);
+	if (retval)
+		goto out;
 
 	for (mpnt = oldmm->mmap; mpnt; mpnt = mpnt->vm_next) {
 		struct file *file;
@@ -419,22 +434,30 @@ __setup("coredump_filter=", coredump_filter_setup);
 
 #include <linux/init_task.h>
 
+static void mm_init_aio(struct mm_struct *mm)
+{
+#ifdef CONFIG_AIO
+	spin_lock_init(&mm->ioctx_lock);
+	INIT_HLIST_HEAD(&mm->ioctx_list);
+#endif
+}
+
 static struct mm_struct * mm_init(struct mm_struct * mm, struct task_struct *p)
 {
 	atomic_set(&mm->mm_users, 1);
 	atomic_set(&mm->mm_count, 1);
 	init_rwsem(&mm->mmap_sem);
 	INIT_LIST_HEAD(&mm->mmlist);
-	mm->flags = (current->mm) ? current->mm->flags : default_dump_filter;
+	mm->flags = (current->mm) ?
+		(current->mm->flags & MMF_INIT_MASK) : default_dump_filter;
 	mm->core_state = NULL;
 	mm->nr_ptes = 0;
 	set_mm_counter(mm, file_rss, 0);
 	set_mm_counter(mm, anon_rss, 0);
 	spin_lock_init(&mm->page_table_lock);
-	spin_lock_init(&mm->ioctx_lock);
-	INIT_HLIST_HEAD(&mm->ioctx_list);
 	mm->free_area_cache = TASK_UNMAPPED_BASE;
 	mm->cached_hole_size = ~0UL;
+	mm_init_aio(mm);
 	mm_init_owner(mm, p);
 
 	if (likely(!mm_alloc_pgd(mm))) {
@@ -486,6 +509,7 @@ void mmput(struct mm_struct *mm)
 
 	if (atomic_dec_and_test(&mm->mm_users)) {
 		exit_aio(mm);
+		ksm_exit(mm);
 		exit_mmap(mm);
 		set_mm_exe_file(mm, NULL);
 		if (!list_empty(&mm->mmlist)) {
@@ -494,6 +518,8 @@ void mmput(struct mm_struct *mm)
 			spin_unlock(&mmlist_lock);
 		}
 		put_swap_token(mm);
+		if (mm->binfmt)
+			module_put(mm->binfmt->module);
 		mmdrop(mm);
 	}
 }
@@ -544,12 +570,18 @@ void mm_release(struct task_struct *tsk, struct mm_struct *mm)
 
 	/* Get rid of any futexes when releasing the mm */
 #ifdef CONFIG_FUTEX
-	if (unlikely(tsk->robust_list))
+	if (unlikely(tsk->robust_list)) {
 		exit_robust_list(tsk);
+		tsk->robust_list = NULL;
+	}
 #ifdef CONFIG_COMPAT
-	if (unlikely(tsk->compat_robust_list))
+	if (unlikely(tsk->compat_robust_list)) {
 		compat_exit_robust_list(tsk);
+		tsk->compat_robust_list = NULL;
+	}
 #endif
+	if (unlikely(!list_empty(&tsk->pi_state_list)))
+		exit_pi_state_list(tsk);
 #endif
 
 	/* Get rid of any cached register state */
@@ -619,9 +651,14 @@ struct mm_struct *dup_mm(struct task_struct *tsk)
 	mm->hiwater_rss = get_mm_rss(mm);
 	mm->hiwater_vm = mm->total_vm;
 
+	if (mm->binfmt && !try_module_get(mm->binfmt->module))
+		goto free_pt;
+
 	return mm;
 
 free_pt:
+	/* don't put binfmt in mmput, we haven't got module yet */
+	mm->binfmt = NULL;
 	mmput(mm);
 
 fail_nomem:
@@ -789,10 +826,10 @@ static void posix_cpu_timers_init_group(struct signal_struct *sig)
 	thread_group_cputime_init(sig);
 
 	/* Expiration times and increments. */
-	sig->it_virt_expires = cputime_zero;
-	sig->it_virt_incr = cputime_zero;
-	sig->it_prof_expires = cputime_zero;
-	sig->it_prof_incr = cputime_zero;
+	sig->it[CPUCLOCK_PROF].expires = cputime_zero;
+	sig->it[CPUCLOCK_PROF].incr = cputime_zero;
+	sig->it[CPUCLOCK_VIRT].expires = cputime_zero;
+	sig->it[CPUCLOCK_VIRT].incr = cputime_zero;
 
 	/* Cached expiration times. */
 	sig->cputime_expires.prof_exp = cputime_zero;
@@ -850,6 +887,7 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk)
 	sig->nvcsw = sig->nivcsw = sig->cnvcsw = sig->cnivcsw = 0;
 	sig->min_flt = sig->maj_flt = sig->cmin_flt = sig->cmaj_flt = 0;
 	sig->inblock = sig->oublock = sig->cinblock = sig->coublock = 0;
+	sig->maxrss = sig->cmaxrss = 0;
 	task_io_accounting_init(&sig->ioac);
 	sig->sum_sched_runtime = 0;
 	taskstats_tgid_init(sig);
@@ -864,6 +902,8 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk)
 
 	tty_audit_fork(sig);
 
+	sig->oom_adj = current->signal->oom_adj;
+
 	return 0;
 }
 
@@ -959,6 +999,16 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 	if ((clone_flags & CLONE_SIGHAND) && !(clone_flags & CLONE_VM))
 		return ERR_PTR(-EINVAL);
 
+	/*
+	 * Siblings of global init remain as zombies on exit since they are
+	 * not reaped by their parent (swapper). To solve this and to avoid
+	 * multi-rooted process trees, prevent global and container-inits
+	 * from creating siblings.
+	 */
+	if ((clone_flags & CLONE_PARENT) &&
+				current->signal->flags & SIGNAL_UNKILLABLE)
+		return ERR_PTR(-EINVAL);
+
 	retval = security_task_create(clone_flags);
 	if (retval)
 		goto fork_out;
@@ -1000,18 +1050,12 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 	if (!try_module_get(task_thread_info(p)->exec_domain->module))
 		goto bad_fork_cleanup_count;
 
-	if (p->binfmt && !try_module_get(p->binfmt->module))
-		goto bad_fork_cleanup_put_domain;
-
 	p->did_exec = 0;
 	delayacct_tsk_init(p);	/* Must remain after dup_task_struct() */
 	copy_flags(clone_flags, p);
 	INIT_LIST_HEAD(&p->children);
 	INIT_LIST_HEAD(&p->sibling);
-#ifdef CONFIG_PREEMPT_RCU
-	p->rcu_read_lock_nesting = 0;
-	p->rcu_flipctr_idx = 0;
-#endif /* #ifdef CONFIG_PREEMPT_RCU */
+	rcu_copy_process(p);
 	p->vfork_done = NULL;
 	spin_lock_init(&p->alloc_lock);
 
@@ -1079,10 +1123,12 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 
 	p->bts = NULL;
 
+	p->stack_start = stack_start;
+
 	/* Perform scheduler related setup. Assign this task to a CPU. */
 	sched_fork(p, clone_flags);
 
-	retval = perf_counter_init_task(p);
+	retval = perf_event_init_task(p);
 	if (retval)
 		goto bad_fork_cleanup_policy;
 
@@ -1257,7 +1303,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 	write_unlock_irq(&tasklist_lock);
 	proc_fork_connector(p);
 	cgroup_post_fork(p);
-	perf_counter_fork(p);
+	perf_event_fork(p);
 	return p;
 
 bad_fork_free_pid:
@@ -1284,21 +1330,17 @@ bad_fork_cleanup_semundo:
 bad_fork_cleanup_audit:
 	audit_free(p);
 bad_fork_cleanup_policy:
-	perf_counter_free_task(p);
+	perf_event_free_task(p);
 #ifdef CONFIG_NUMA
 	mpol_put(p->mempolicy);
 bad_fork_cleanup_cgroup:
 #endif
 	cgroup_exit(p, cgroup_callbacks_done);
 	delayacct_tsk_free(p);
-	if (p->binfmt)
-		module_put(p->binfmt->module);
-bad_fork_cleanup_put_domain:
 	module_put(task_thread_info(p)->exec_domain->module);
 bad_fork_cleanup_count:
 	atomic_dec(&p->cred->user->processes);
-	put_cred(p->real_cred);
-	put_cred(p->cred);
+	exit_creds(p);
 bad_fork_free:
 	free_task(p);
 fork_out:
diff --git a/kernel/futex.c b/kernel/futex.c
index e18cfbdc7190..fb65e822fc41 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -89,33 +89,36 @@ struct futex_pi_state {
 	union futex_key key;
 };
 
-/*
- * We use this hashed waitqueue instead of a normal wait_queue_t, so
+/**
+ * struct futex_q - The hashed futex queue entry, one per waiting task
+ * @task:		the task waiting on the futex
+ * @lock_ptr:		the hash bucket lock
+ * @key:		the key the futex is hashed on
+ * @pi_state:		optional priority inheritance state
+ * @rt_waiter:		rt_waiter storage for use with requeue_pi
+ * @requeue_pi_key:	the requeue_pi target futex key
+ * @bitset:		bitset for the optional bitmasked wakeup
+ *
+ * We use this hashed waitqueue, instead of a normal wait_queue_t, so
  * we can wake only the relevant ones (hashed queues may be shared).
  *
  * A futex_q has a woken state, just like tasks have TASK_RUNNING.
  * It is considered woken when plist_node_empty(&q->list) || q->lock_ptr == 0.
  * The order of wakup is always to make the first condition true, then
- * wake up q->waiter, then make the second condition true.
+ * the second.
+ *
+ * PI futexes are typically woken before they are removed from the hash list via
+ * the rt_mutex code. See unqueue_me_pi().
  */
 struct futex_q {
 	struct plist_node list;
-	/* Waiter reference */
-	struct task_struct *task;
 
-	/* Which hash list lock to use: */
+	struct task_struct *task;
 	spinlock_t *lock_ptr;
-
-	/* Key which the futex is hashed on: */
 	union futex_key key;
-
-	/* Optional priority inheritance state: */
 	struct futex_pi_state *pi_state;
-
-	/* rt_waiter storage for requeue_pi: */
 	struct rt_mutex_waiter *rt_waiter;
-
-	/* Bitset for the optional bitmasked wakeup */
+	union futex_key *requeue_pi_key;
 	u32 bitset;
 };
 
@@ -147,7 +150,8 @@ static struct futex_hash_bucket *hash_futex(union futex_key *key)
  */
 static inline int match_futex(union futex_key *key1, union futex_key *key2)
 {
-	return (key1->both.word == key2->both.word
+	return (key1 && key2
+		&& key1->both.word == key2->both.word
 		&& key1->both.ptr == key2->both.ptr
 		&& key1->both.offset == key2->both.offset);
 }
@@ -195,11 +199,12 @@ 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
- * @fshared: 0 for a PROCESS_PRIVATE futex, 1 for PROCESS_SHARED
- * @key: address where result is stored.
- * @rw: mapping needs to be read/write (values: VERIFY_READ, VERIFY_WRITE)
+ * get_futex_key() - Get parameters which are the keys for a futex
+ * @uaddr:	virtual address of the futex
+ * @fshared:	0 for a PROCESS_PRIVATE futex, 1 for PROCESS_SHARED
+ * @key:	address where result is stored.
+ * @rw:		mapping needs to be read/write (values: VERIFY_READ,
+ * 		VERIFY_WRITE)
  *
  * Returns a negative error code or 0
  * The key words are stored in *key on success.
@@ -285,8 +290,8 @@ void put_futex_key(int fshared, union futex_key *key)
 	drop_futex_key_refs(key);
 }
 
-/*
- * fault_in_user_writeable - fault in user address and verify RW access
+/**
+ * fault_in_user_writeable() - Fault in user address and verify RW access
  * @uaddr:	pointer to faulting user space address
  *
  * Slow path to fixup the fault we just took in the atomic write
@@ -306,8 +311,8 @@ static int fault_in_user_writeable(u32 __user *uaddr)
 
 /**
  * futex_top_waiter() - Return the highest priority waiter on a futex
- * @hb:     the hash bucket the futex_q's reside in
- * @key:    the futex key (to distinguish it from other futex futex_q's)
+ * @hb:		the hash bucket the futex_q's reside in
+ * @key:	the futex key (to distinguish it from other futex futex_q's)
  *
  * Must be called with the hb lock held.
  */
@@ -585,7 +590,7 @@ lookup_pi_state(u32 uval, struct futex_hash_bucket *hb,
 }
 
 /**
- * futex_lock_pi_atomic() - atomic work required to acquire a pi aware futex
+ * futex_lock_pi_atomic() - Atomic work required to acquire a pi aware futex
  * @uaddr:		the pi futex user address
  * @hb:			the pi futex hash bucket
  * @key:		the futex key associated with uaddr and hb
@@ -912,8 +917,8 @@ retry:
 	hb1 = hash_futex(&key1);
 	hb2 = hash_futex(&key2);
 
-	double_lock_hb(hb1, hb2);
 retry_private:
+	double_lock_hb(hb1, hb2);
 	op_ret = futex_atomic_op_inuser(op, uaddr2);
 	if (unlikely(op_ret < 0)) {
 
@@ -1008,9 +1013,9 @@ void requeue_futex(struct futex_q *q, struct futex_hash_bucket *hb1,
 
 /**
  * requeue_pi_wake_futex() - Wake a task that acquired the lock during requeue
- * q:	the futex_q
- * key:	the key of the requeue target futex
- * hb:  the hash_bucket of the requeue target futex
+ * @q:		the futex_q
+ * @key:	the key of the requeue target futex
+ * @hb:		the hash_bucket of the requeue target futex
  *
  * During futex_requeue, with requeue_pi=1, it is possible to acquire the
  * target futex if it is uncontended or via a lock steal.  Set the futex_q key
@@ -1024,7 +1029,6 @@ static inline
 void requeue_pi_wake_futex(struct futex_q *q, union futex_key *key,
 			   struct futex_hash_bucket *hb)
 {
-	drop_futex_key_refs(&q->key);
 	get_futex_key_refs(key);
 	q->key = *key;
 
@@ -1089,6 +1093,10 @@ static int futex_proxy_trylock_atomic(u32 __user *pifutex,
 	if (!top_waiter)
 		return 0;
 
+	/* Ensure we requeue to the expected futex. */
+	if (!match_futex(top_waiter->requeue_pi_key, key2))
+		return -EINVAL;
+
 	/*
 	 * Try to take the lock for top_waiter.  Set the FUTEX_WAITERS bit in
 	 * the contended case or if set_waiters is 1.  The pi_state is returned
@@ -1218,6 +1226,7 @@ retry_private:
 		 */
 		if (ret == 1) {
 			WARN_ON(pi_state);
+			drop_count++;
 			task_count++;
 			ret = get_futex_value_locked(&curval2, uaddr2);
 			if (!ret)
@@ -1276,6 +1285,12 @@ retry_private:
 			continue;
 		}
 
+		/* Ensure we requeue to the expected futex for requeue_pi. */
+		if (requeue_pi && !match_futex(this->requeue_pi_key, &key2)) {
+			ret = -EINVAL;
+			break;
+		}
+
 		/*
 		 * Requeue nr_requeue waiters and possibly one more in the case
 		 * of requeue_pi if we couldn't acquire the lock atomically.
@@ -1290,6 +1305,7 @@ retry_private:
 			if (ret == 1) {
 				/* We got the lock. */
 				requeue_pi_wake_futex(this, &key2, hb2);
+				drop_count++;
 				continue;
 			} else if (ret) {
 				/* -EDEADLK */
@@ -1337,6 +1353,25 @@ static inline struct futex_hash_bucket *queue_lock(struct futex_q *q)
 	return hb;
 }
 
+static inline void
+queue_unlock(struct futex_q *q, struct futex_hash_bucket *hb)
+{
+	spin_unlock(&hb->lock);
+	drop_futex_key_refs(&q->key);
+}
+
+/**
+ * queue_me() - Enqueue the futex_q on the futex_hash_bucket
+ * @q:	The futex_q to enqueue
+ * @hb:	The destination hash bucket
+ *
+ * The hb->lock must be held by the caller, and is released here. A call to
+ * queue_me() is typically paired with exactly one call to unqueue_me().  The
+ * exceptions involve the PI related operations, which may use unqueue_me_pi()
+ * or nothing if the unqueue is done as part of the wake process and the unqueue
+ * state is implicit in the state of woken task (see futex_wait_requeue_pi() for
+ * an example).
+ */
 static inline void queue_me(struct futex_q *q, struct futex_hash_bucket *hb)
 {
 	int prio;
@@ -1360,19 +1395,17 @@ static inline void queue_me(struct futex_q *q, struct futex_hash_bucket *hb)
 	spin_unlock(&hb->lock);
 }
 
-static inline void
-queue_unlock(struct futex_q *q, struct futex_hash_bucket *hb)
-{
-	spin_unlock(&hb->lock);
-	drop_futex_key_refs(&q->key);
-}
-
-/*
- * queue_me and unqueue_me must be called as a pair, each
- * exactly once.  They are called with the hashed spinlock held.
+/**
+ * unqueue_me() - Remove the futex_q from its futex_hash_bucket
+ * @q:	The futex_q to unqueue
+ *
+ * The q->lock_ptr must not be held by the caller. A call to unqueue_me() must
+ * be paired with exactly one earlier call to queue_me().
+ *
+ * Returns:
+ *   1 - if the futex_q was still queued (and we removed unqueued it)
+ *   0 - if the futex_q was already removed by the waking thread
  */
-
-/* Return 1 if we were still queued (ie. 0 means we were woken) */
 static int unqueue_me(struct futex_q *q)
 {
 	spinlock_t *lock_ptr;
@@ -1625,17 +1658,14 @@ out:
 static void futex_wait_queue_me(struct futex_hash_bucket *hb, struct futex_q *q,
 				struct hrtimer_sleeper *timeout)
 {
-	queue_me(q, hb);
-
 	/*
-	 * There might have been scheduling since the queue_me(), as we
-	 * cannot hold a spinlock across the get_user() in case it
-	 * faults, and we cannot just set TASK_INTERRUPTIBLE state when
-	 * queueing ourselves into the futex hash. This code thus has to
-	 * rely on the futex_wake() code removing us from hash when it
-	 * wakes us up.
+	 * The task state is guaranteed to be set before another task can
+	 * wake it. set_current_state() is implemented using set_mb() and
+	 * queue_me() calls spin_unlock() upon completion, both serializing
+	 * access to the hash list and forcing another memory barrier.
 	 */
 	set_current_state(TASK_INTERRUPTIBLE);
+	queue_me(q, hb);
 
 	/* Arm the timer */
 	if (timeout) {
@@ -1645,8 +1675,8 @@ static void futex_wait_queue_me(struct futex_hash_bucket *hb, struct futex_q *q,
 	}
 
 	/*
-	 * !plist_node_empty() is safe here without any lock.
-	 * q.lock_ptr != 0 is not safe, because of ordering against wakeup.
+	 * If we have been removed from the hash list, then another task
+	 * has tried to wake us, and we can skip the call to schedule().
 	 */
 	if (likely(!plist_node_empty(&q->list))) {
 		/*
@@ -1751,6 +1781,7 @@ static int futex_wait(u32 __user *uaddr, int fshared,
 	q.pi_state = NULL;
 	q.bitset = bitset;
 	q.rt_waiter = NULL;
+	q.requeue_pi_key = NULL;
 
 	if (abs_time) {
 		to = &timeout;
@@ -1762,6 +1793,7 @@ static int futex_wait(u32 __user *uaddr, int fshared,
 					     current->timer_slack_ns);
 	}
 
+retry:
 	/* Prepare to wait on uaddr. */
 	ret = futex_wait_setup(uaddr, val, fshared, &q, &hb);
 	if (ret)
@@ -1779,9 +1811,14 @@ static int futex_wait(u32 __user *uaddr, int fshared,
 		goto out_put_key;
 
 	/*
-	 * We expect signal_pending(current), but another thread may
-	 * have handled it for us already.
+	 * We expect signal_pending(current), but we might be the
+	 * victim of a spurious wakeup as well.
 	 */
+	if (!signal_pending(current)) {
+		put_futex_key(fshared, &q.key);
+		goto retry;
+	}
+
 	ret = -ERESTARTSYS;
 	if (!abs_time)
 		goto out_put_key;
@@ -1858,6 +1895,7 @@ static int futex_lock_pi(u32 __user *uaddr, int fshared,
 
 	q.pi_state = NULL;
 	q.rt_waiter = NULL;
+	q.requeue_pi_key = NULL;
 retry:
 	q.key = FUTEX_KEY_INIT;
 	ret = get_futex_key(uaddr, fshared, &q.key, VERIFY_WRITE);
@@ -2087,11 +2125,12 @@ int handle_early_requeue_pi_wakeup(struct futex_hash_bucket *hb,
 		 * Unqueue the futex_q and determine which it was.
 		 */
 		plist_del(&q->list, &q->list.plist);
-		drop_futex_key_refs(&q->key);
 
+		/* Handle spurious wakeups gracefully */
+		ret = -EWOULDBLOCK;
 		if (timeout && !timeout->task)
 			ret = -ETIMEDOUT;
-		else
+		else if (signal_pending(current))
 			ret = -ERESTARTNOINTR;
 	}
 	return ret;
@@ -2099,12 +2138,12 @@ int handle_early_requeue_pi_wakeup(struct futex_hash_bucket *hb,
 
 /**
  * futex_wait_requeue_pi() - Wait on uaddr and take uaddr2
- * @uaddr:	the futex we initialyl wait on (non-pi)
+ * @uaddr:	the futex we initially wait on (non-pi)
  * @fshared:	whether the futexes are shared (1) or not (0).  They must be
  * 		the same type, no requeueing from private to shared, etc.
  * @val:	the expected value of uaddr
  * @abs_time:	absolute timeout
- * @bitset:	32 bit wakeup bitset set by userspace, defaults to all.
+ * @bitset:	32 bit wakeup bitset set by userspace, defaults to all
  * @clockrt:	whether to use CLOCK_REALTIME (1) or CLOCK_MONOTONIC (0)
  * @uaddr2:	the pi futex we will take prior to returning to user-space
  *
@@ -2118,11 +2157,11 @@ int handle_early_requeue_pi_wakeup(struct futex_hash_bucket *hb,
  * We call schedule in futex_wait_queue_me() when we enqueue and return there
  * via the following:
  * 1) wakeup on uaddr2 after an atomic lock acquisition by futex_requeue()
- * 2) wakeup on uaddr2 after a requeue and subsequent unlock
- * 3) signal (before or after requeue)
- * 4) timeout (before or after requeue)
+ * 2) wakeup on uaddr2 after a requeue
+ * 3) signal
+ * 4) timeout
  *
- * If 3, we setup a restart_block with futex_wait_requeue_pi() as the function.
+ * If 3, cleanup and return -ERESTARTNOINTR.
  *
  * If 2, we may then block on trying to take the rt_mutex and return via:
  * 5) successful lock
@@ -2130,7 +2169,7 @@ int handle_early_requeue_pi_wakeup(struct futex_hash_bucket *hb,
  * 7) timeout
  * 8) other lock acquisition failure
  *
- * If 6, we setup a restart_block with futex_lock_pi() as the function.
+ * If 6, return -EWOULDBLOCK (restarting the syscall would do the same).
  *
  * If 4 or 7, we cleanup and return with -ETIMEDOUT.
  *
@@ -2169,15 +2208,16 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, int fshared,
 	debug_rt_mutex_init_waiter(&rt_waiter);
 	rt_waiter.task = NULL;
 
-	q.pi_state = NULL;
-	q.bitset = bitset;
-	q.rt_waiter = &rt_waiter;
-
 	key2 = FUTEX_KEY_INIT;
 	ret = get_futex_key(uaddr2, fshared, &key2, VERIFY_WRITE);
 	if (unlikely(ret != 0))
 		goto out;
 
+	q.pi_state = NULL;
+	q.bitset = bitset;
+	q.rt_waiter = &rt_waiter;
+	q.requeue_pi_key = &key2;
+
 	/* Prepare to wait on uaddr. */
 	ret = futex_wait_setup(uaddr, val, fshared, &q, &hb);
 	if (ret)
@@ -2230,7 +2270,7 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, int fshared,
 		res = fixup_owner(uaddr2, fshared, &q, !ret);
 		/*
 		 * If fixup_owner() returned an error, proprogate that.  If it
-		 * acquired the lock, clear our -ETIMEDOUT or -EINTR.
+		 * acquired the lock, clear -ETIMEDOUT or -EINTR.
 		 */
 		if (res)
 			ret = (res < 0) ? res : 0;
@@ -2248,14 +2288,11 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, int fshared,
 			rt_mutex_unlock(pi_mutex);
 	} else if (ret == -EINTR) {
 		/*
-		 * We've already been requeued, but we have no way to
-		 * restart by calling futex_lock_pi() directly. We
-		 * could restart the syscall, but that will look at
-		 * the user space value and return right away. So we
-		 * drop back with EWOULDBLOCK to tell user space that
-		 * "val" has been changed. That's the same what the
-		 * restart of the syscall would do in
-		 * futex_wait_setup().
+		 * We've already been requeued, but cannot restart by calling
+		 * futex_lock_pi() directly. We could restart this syscall, but
+		 * it would detect that the user space "val" changed and return
+		 * -EWOULDBLOCK.  Save the overhead of the restart and return
+		 * -EWOULDBLOCK directly.
 		 */
 		ret = -EWOULDBLOCK;
 	}
@@ -2289,9 +2326,9 @@ out:
  */
 
 /**
- * sys_set_robust_list - set the robust-futex list head of a task
- * @head: pointer to the list-head
- * @len: length of the list-head, as userspace expects
+ * sys_set_robust_list() - Set the robust-futex list head of a task
+ * @head:	pointer to the list-head
+ * @len:	length of the list-head, as userspace expects
  */
 SYSCALL_DEFINE2(set_robust_list, struct robust_list_head __user *, head,
 		size_t, len)
@@ -2310,10 +2347,10 @@ SYSCALL_DEFINE2(set_robust_list, struct robust_list_head __user *, head,
 }
 
 /**
- * sys_get_robust_list - get the robust-futex list head of a task
- * @pid: pid of the process [zero for current task]
- * @head_ptr: pointer to a list-head pointer, the kernel fills it in
- * @len_ptr: pointer to a length field, the kernel fills in the header size
+ * sys_get_robust_list() - Get the robust-futex list head of a task
+ * @pid:	pid of the process [zero for current task]
+ * @head_ptr:	pointer to a list-head pointer, the kernel fills it in
+ * @len_ptr:	pointer to a length field, the kernel fills in the header size
  */
 SYSCALL_DEFINE3(get_robust_list, int, pid,
 		struct robust_list_head __user * __user *, head_ptr,
diff --git a/kernel/gcov/Kconfig b/kernel/gcov/Kconfig
index 22e9dcfaa3d3..70a298d6da71 100644
--- a/kernel/gcov/Kconfig
+++ b/kernel/gcov/Kconfig
@@ -34,7 +34,7 @@ config GCOV_KERNEL
 config GCOV_PROFILE_ALL
 	bool "Profile entire Kernel"
 	depends on GCOV_KERNEL
-	depends on S390 || X86
+	depends on S390 || X86 || (PPC && EXPERIMENTAL) || MICROBLAZE
 	default n
 	---help---
 	This options activates profiling for the entire kernel.
diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c
index 49da79ab8486..3e1c36e7998f 100644
--- a/kernel/hrtimer.c
+++ b/kernel/hrtimer.c
@@ -48,36 +48,7 @@
 
 #include <asm/uaccess.h>
 
-/**
- * ktime_get - get the monotonic time in ktime_t format
- *
- * returns the time in ktime_t format
- */
-ktime_t ktime_get(void)
-{
-	struct timespec now;
-
-	ktime_get_ts(&now);
-
-	return timespec_to_ktime(now);
-}
-EXPORT_SYMBOL_GPL(ktime_get);
-
-/**
- * ktime_get_real - get the real (wall-) time in ktime_t format
- *
- * returns the time in ktime_t format
- */
-ktime_t ktime_get_real(void)
-{
-	struct timespec now;
-
-	getnstimeofday(&now);
-
-	return timespec_to_ktime(now);
-}
-
-EXPORT_SYMBOL_GPL(ktime_get_real);
+#include <trace/events/timer.h>
 
 /*
  * The timer bases:
@@ -106,31 +77,6 @@ DEFINE_PER_CPU(struct hrtimer_cpu_base, hrtimer_bases) =
 	}
 };
 
-/**
- * ktime_get_ts - get the monotonic clock in timespec format
- * @ts:		pointer to timespec variable
- *
- * The function calculates the monotonic clock from the realtime
- * clock and the wall_to_monotonic offset and stores the result
- * in normalized timespec format in the variable pointed to by @ts.
- */
-void ktime_get_ts(struct timespec *ts)
-{
-	struct timespec tomono;
-	unsigned long seq;
-
-	do {
-		seq = read_seqbegin(&xtime_lock);
-		getnstimeofday(ts);
-		tomono = wall_to_monotonic;
-
-	} while (read_seqretry(&xtime_lock, seq));
-
-	set_normalized_timespec(ts, ts->tv_sec + tomono.tv_sec,
-				ts->tv_nsec + tomono.tv_nsec);
-}
-EXPORT_SYMBOL_GPL(ktime_get_ts);
-
 /*
  * Get the coarse grained time at the softirq based on xtime and
  * wall_to_monotonic.
@@ -485,6 +431,7 @@ void hrtimer_init_on_stack(struct hrtimer *timer, clockid_t clock_id,
 	debug_object_init_on_stack(timer, &hrtimer_debug_descr);
 	__hrtimer_init(timer, clock_id, mode);
 }
+EXPORT_SYMBOL_GPL(hrtimer_init_on_stack);
 
 void destroy_hrtimer_on_stack(struct hrtimer *timer)
 {
@@ -497,6 +444,26 @@ static inline void debug_hrtimer_activate(struct hrtimer *timer) { }
 static inline void debug_hrtimer_deactivate(struct hrtimer *timer) { }
 #endif
 
+static inline void
+debug_init(struct hrtimer *timer, clockid_t clockid,
+	   enum hrtimer_mode mode)
+{
+	debug_hrtimer_init(timer);
+	trace_hrtimer_init(timer, clockid, mode);
+}
+
+static inline void debug_activate(struct hrtimer *timer)
+{
+	debug_hrtimer_activate(timer);
+	trace_hrtimer_start(timer);
+}
+
+static inline void debug_deactivate(struct hrtimer *timer)
+{
+	debug_hrtimer_deactivate(timer);
+	trace_hrtimer_cancel(timer);
+}
+
 /* High resolution timer related functions */
 #ifdef CONFIG_HIGH_RES_TIMERS
 
@@ -542,13 +509,14 @@ static inline int hrtimer_hres_active(void)
  * next event
  * Called with interrupts disabled and base->lock held
  */
-static void hrtimer_force_reprogram(struct hrtimer_cpu_base *cpu_base)
+static void
+hrtimer_force_reprogram(struct hrtimer_cpu_base *cpu_base, int skip_equal)
 {
 	int i;
 	struct hrtimer_clock_base *base = cpu_base->clock_base;
-	ktime_t expires;
+	ktime_t expires, expires_next;
 
-	cpu_base->expires_next.tv64 = KTIME_MAX;
+	expires_next.tv64 = KTIME_MAX;
 
 	for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++, base++) {
 		struct hrtimer *timer;
@@ -564,10 +532,15 @@ static void hrtimer_force_reprogram(struct hrtimer_cpu_base *cpu_base)
 		 */
 		if (expires.tv64 < 0)
 			expires.tv64 = 0;
-		if (expires.tv64 < cpu_base->expires_next.tv64)
-			cpu_base->expires_next = expires;
+		if (expires.tv64 < expires_next.tv64)
+			expires_next = expires;
 	}
 
+	if (skip_equal && expires_next.tv64 == cpu_base->expires_next.tv64)
+		return;
+
+	cpu_base->expires_next.tv64 = expires_next.tv64;
+
 	if (cpu_base->expires_next.tv64 != KTIME_MAX)
 		tick_program_event(cpu_base->expires_next, 1);
 }
@@ -650,7 +623,7 @@ static void retrigger_next_event(void *arg)
 	base->clock_base[CLOCK_REALTIME].offset =
 		timespec_to_ktime(realtime_offset);
 
-	hrtimer_force_reprogram(base);
+	hrtimer_force_reprogram(base, 0);
 	spin_unlock(&base->lock);
 }
 
@@ -753,8 +726,6 @@ static int hrtimer_switch_to_hres(void)
 	/* "Retrigger" the interrupt to get things going */
 	retrigger_next_event(NULL);
 	local_irq_restore(flags);
-	printk(KERN_DEBUG "Switched to high resolution mode on CPU %d\n",
-	       smp_processor_id());
 	return 1;
 }
 
@@ -763,7 +734,8 @@ static int hrtimer_switch_to_hres(void)
 static inline int hrtimer_hres_active(void) { return 0; }
 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 void
+hrtimer_force_reprogram(struct hrtimer_cpu_base *base, int skip_equal) { }
 static inline int hrtimer_enqueue_reprogram(struct hrtimer *timer,
 					    struct hrtimer_clock_base *base,
 					    int wakeup)
@@ -853,7 +825,7 @@ static int enqueue_hrtimer(struct hrtimer *timer,
 	struct hrtimer *entry;
 	int leftmost = 1;
 
-	debug_hrtimer_activate(timer);
+	debug_activate(timer);
 
 	/*
 	 * Find the right place in the rbtree:
@@ -906,19 +878,29 @@ static void __remove_hrtimer(struct hrtimer *timer,
 			     struct hrtimer_clock_base *base,
 			     unsigned long newstate, int reprogram)
 {
-	if (timer->state & HRTIMER_STATE_ENQUEUED) {
-		/*
-		 * Remove the timer from the rbtree and replace the
-		 * first entry pointer if necessary.
-		 */
-		if (base->first == &timer->node) {
-			base->first = rb_next(&timer->node);
-			/* Reprogram the clock event device. if enabled */
-			if (reprogram && hrtimer_hres_active())
-				hrtimer_force_reprogram(base->cpu_base);
+	if (!(timer->state & HRTIMER_STATE_ENQUEUED))
+		goto out;
+
+	/*
+	 * Remove the timer from the rbtree and replace the first
+	 * entry pointer if necessary.
+	 */
+	if (base->first == &timer->node) {
+		base->first = rb_next(&timer->node);
+#ifdef CONFIG_HIGH_RES_TIMERS
+		/* Reprogram the clock event device. if enabled */
+		if (reprogram && hrtimer_hres_active()) {
+			ktime_t expires;
+
+			expires = ktime_sub(hrtimer_get_expires(timer),
+					    base->offset);
+			if (base->cpu_base->expires_next.tv64 == expires.tv64)
+				hrtimer_force_reprogram(base->cpu_base, 1);
 		}
-		rb_erase(&timer->node, &base->active);
+#endif
 	}
+	rb_erase(&timer->node, &base->active);
+out:
 	timer->state = newstate;
 }
 
@@ -939,7 +921,7 @@ remove_hrtimer(struct hrtimer *timer, struct hrtimer_clock_base *base)
 		 * reprogramming happens in the interrupt handler. This is a
 		 * rare case and less expensive than a smp call.
 		 */
-		debug_hrtimer_deactivate(timer);
+		debug_deactivate(timer);
 		timer_stats_hrtimer_clear_start_info(timer);
 		reprogram = base->cpu_base == &__get_cpu_var(hrtimer_bases);
 		__remove_hrtimer(timer, base, HRTIMER_STATE_INACTIVE,
@@ -1154,7 +1136,6 @@ static void __hrtimer_init(struct hrtimer *timer, clockid_t clock_id,
 		clock_id = CLOCK_MONOTONIC;
 
 	timer->base = &cpu_base->clock_base[clock_id];
-	INIT_LIST_HEAD(&timer->cb_entry);
 	hrtimer_init_timer_hres(timer);
 
 #ifdef CONFIG_TIMER_STATS
@@ -1173,7 +1154,7 @@ static void __hrtimer_init(struct hrtimer *timer, clockid_t clock_id,
 void hrtimer_init(struct hrtimer *timer, clockid_t clock_id,
 		  enum hrtimer_mode mode)
 {
-	debug_hrtimer_init(timer);
+	debug_init(timer, clock_id, mode);
 	__hrtimer_init(timer, clock_id, mode);
 }
 EXPORT_SYMBOL_GPL(hrtimer_init);
@@ -1197,7 +1178,7 @@ int hrtimer_get_res(const clockid_t which_clock, struct timespec *tp)
 }
 EXPORT_SYMBOL_GPL(hrtimer_get_res);
 
-static void __run_hrtimer(struct hrtimer *timer)
+static void __run_hrtimer(struct hrtimer *timer, ktime_t *now)
 {
 	struct hrtimer_clock_base *base = timer->base;
 	struct hrtimer_cpu_base *cpu_base = base->cpu_base;
@@ -1206,7 +1187,7 @@ static void __run_hrtimer(struct hrtimer *timer)
 
 	WARN_ON(!irqs_disabled());
 
-	debug_hrtimer_deactivate(timer);
+	debug_deactivate(timer);
 	__remove_hrtimer(timer, base, HRTIMER_STATE_CALLBACK, 0);
 	timer_stats_account_hrtimer(timer);
 	fn = timer->function;
@@ -1217,7 +1198,9 @@ static void __run_hrtimer(struct hrtimer *timer)
 	 * the timer base.
 	 */
 	spin_unlock(&cpu_base->lock);
+	trace_hrtimer_expire_entry(timer, now);
 	restart = fn(timer);
+	trace_hrtimer_expire_exit(timer);
 	spin_lock(&cpu_base->lock);
 
 	/*
@@ -1328,7 +1311,7 @@ void hrtimer_interrupt(struct clock_event_device *dev)
 				break;
 			}
 
-			__run_hrtimer(timer);
+			__run_hrtimer(timer, &basenow);
 		}
 		base++;
 	}
@@ -1450,7 +1433,7 @@ void hrtimer_run_queues(void)
 					hrtimer_get_expires_tv64(timer))
 				break;
 
-			__run_hrtimer(timer);
+			__run_hrtimer(timer, &base->softirq_time);
 		}
 		spin_unlock(&cpu_base->lock);
 	}
@@ -1477,6 +1460,7 @@ void hrtimer_init_sleeper(struct hrtimer_sleeper *sl, struct task_struct *task)
 	sl->timer.function = hrtimer_wakeup;
 	sl->task = task;
 }
+EXPORT_SYMBOL_GPL(hrtimer_init_sleeper);
 
 static int __sched do_nanosleep(struct hrtimer_sleeper *t, enum hrtimer_mode mode)
 {
@@ -1626,7 +1610,7 @@ static void migrate_hrtimer_list(struct hrtimer_clock_base *old_base,
 	while ((node = rb_first(&old_base->active))) {
 		timer = rb_entry(node, struct hrtimer, node);
 		BUG_ON(hrtimer_callback_running(timer));
-		debug_hrtimer_deactivate(timer);
+		debug_deactivate(timer);
 
 		/*
 		 * Mark it as STATE_MIGRATE not INACTIVE otherwise the
diff --git a/kernel/hung_task.c b/kernel/hung_task.c
index 022a4927b785..d4e841747400 100644
--- a/kernel/hung_task.c
+++ b/kernel/hung_task.c
@@ -171,12 +171,12 @@ static unsigned long timeout_jiffies(unsigned long timeout)
  * Process updating of timeout sysctl
  */
 int proc_dohung_task_timeout_secs(struct ctl_table *table, int write,
-				  struct file *filp, void __user *buffer,
+				  void __user *buffer,
 				  size_t *lenp, loff_t *ppos)
 {
 	int ret;
 
-	ret = proc_doulongvec_minmax(table, write, filp, buffer, lenp, ppos);
+	ret = proc_doulongvec_minmax(table, write, buffer, lenp, ppos);
 
 	if (ret || !write)
 		goto out;
diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c
index 13c68e71b726..c1660194d115 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -222,6 +222,34 @@ int set_irq_chip_data(unsigned int irq, void *data)
 }
 EXPORT_SYMBOL(set_irq_chip_data);
 
+/**
+ *	set_irq_nested_thread - Set/Reset the IRQ_NESTED_THREAD flag of an irq
+ *
+ *	@irq:	Interrupt number
+ *	@nest:	0 to clear / 1 to set the IRQ_NESTED_THREAD flag
+ *
+ *	The IRQ_NESTED_THREAD flag indicates that on
+ *	request_threaded_irq() no separate interrupt thread should be
+ *	created for the irq as the handler are called nested in the
+ *	context of a demultiplexing interrupt handler thread.
+ */
+void set_irq_nested_thread(unsigned int irq, int nest)
+{
+	struct irq_desc *desc = irq_to_desc(irq);
+	unsigned long flags;
+
+	if (!desc)
+		return;
+
+	spin_lock_irqsave(&desc->lock, flags);
+	if (nest)
+		desc->status |= IRQ_NESTED_THREAD;
+	else
+		desc->status &= ~IRQ_NESTED_THREAD;
+	spin_unlock_irqrestore(&desc->lock, flags);
+}
+EXPORT_SYMBOL_GPL(set_irq_nested_thread);
+
 /*
  * default enable function
  */
@@ -299,6 +327,45 @@ static inline void mask_ack_irq(struct irq_desc *desc, int irq)
 	}
 }
 
+/*
+ *	handle_nested_irq - Handle a nested irq from a irq thread
+ *	@irq:	the interrupt number
+ *
+ *	Handle interrupts which are nested into a threaded interrupt
+ *	handler. The handler function is called inside the calling
+ *	threads context.
+ */
+void handle_nested_irq(unsigned int irq)
+{
+	struct irq_desc *desc = irq_to_desc(irq);
+	struct irqaction *action;
+	irqreturn_t action_ret;
+
+	might_sleep();
+
+	spin_lock_irq(&desc->lock);
+
+	kstat_incr_irqs_this_cpu(irq, desc);
+
+	action = desc->action;
+	if (unlikely(!action || (desc->status & IRQ_DISABLED)))
+		goto out_unlock;
+
+	desc->status |= IRQ_INPROGRESS;
+	spin_unlock_irq(&desc->lock);
+
+	action_ret = action->thread_fn(action->irq, action->dev_id);
+	if (!noirqdebug)
+		note_interrupt(irq, desc, action_ret);
+
+	spin_lock_irq(&desc->lock);
+	desc->status &= ~IRQ_INPROGRESS;
+
+out_unlock:
+	spin_unlock_irq(&desc->lock);
+}
+EXPORT_SYMBOL_GPL(handle_nested_irq);
+
 /**
  *	handle_simple_irq - Simple and software-decoded IRQs.
  *	@irq:	the interrupt number
@@ -382,7 +449,10 @@ handle_level_irq(unsigned int irq, struct irq_desc *desc)
 
 	spin_lock(&desc->lock);
 	desc->status &= ~IRQ_INPROGRESS;
-	if (!(desc->status & IRQ_DISABLED) && desc->chip->unmask)
+
+	if (unlikely(desc->status & IRQ_ONESHOT))
+		desc->status |= IRQ_MASKED;
+	else if (!(desc->status & IRQ_DISABLED) && desc->chip->unmask)
 		desc->chip->unmask(irq);
 out_unlock:
 	spin_unlock(&desc->lock);
@@ -572,6 +642,7 @@ __set_irq_handler(unsigned int irq, irq_flow_handler_t handle, int is_chained,
 		desc->chip = &dummy_irq_chip;
 	}
 
+	chip_bus_lock(irq, desc);
 	spin_lock_irqsave(&desc->lock, flags);
 
 	/* Uninstall? */
@@ -591,6 +662,7 @@ __set_irq_handler(unsigned int irq, irq_flow_handler_t handle, int is_chained,
 		desc->chip->startup(irq);
 	}
 	spin_unlock_irqrestore(&desc->lock, flags);
+	chip_bus_sync_unlock(irq, desc);
 }
 EXPORT_SYMBOL_GPL(__set_irq_handler);
 
diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c
index 065205bdd920..17c71bb565c6 100644
--- a/kernel/irq/handle.c
+++ b/kernel/irq/handle.c
@@ -11,6 +11,7 @@
  */
 
 #include <linux/irq.h>
+#include <linux/sched.h>
 #include <linux/slab.h>
 #include <linux/module.h>
 #include <linux/random.h>
@@ -161,7 +162,7 @@ int __init early_irq_init(void)
 
 	desc = irq_desc_legacy;
 	legacy_count = ARRAY_SIZE(irq_desc_legacy);
- 	node = first_online_node;
+	node = first_online_node;
 
 	/* allocate irq_desc_ptrs array based on nr_irqs */
 	irq_desc_ptrs = kcalloc(nr_irqs, sizeof(void *), GFP_NOWAIT);
@@ -172,6 +173,9 @@ int __init early_irq_init(void)
 
 	for (i = 0; i < legacy_count; i++) {
 		desc[i].irq = i;
+#ifdef CONFIG_SMP
+		desc[i].node = node;
+#endif
 		desc[i].kstat_irqs = kstat_irqs_legacy + i * nr_cpu_ids;
 		lockdep_set_class(&desc[i].lock, &irq_desc_lock_class);
 		alloc_desc_masks(&desc[i], node, true);
diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h
index e70ed5592eb9..1b5d742c6a77 100644
--- a/kernel/irq/internals.h
+++ b/kernel/irq/internals.h
@@ -44,6 +44,19 @@ extern int irq_select_affinity_usr(unsigned int irq);
 
 extern void irq_set_thread_affinity(struct irq_desc *desc);
 
+/* Inline functions for support of irq chips on slow busses */
+static inline void chip_bus_lock(unsigned int irq, struct irq_desc *desc)
+{
+	if (unlikely(desc->chip->bus_lock))
+		desc->chip->bus_lock(irq);
+}
+
+static inline void chip_bus_sync_unlock(unsigned int irq, struct irq_desc *desc)
+{
+	if (unlikely(desc->chip->bus_sync_unlock))
+		desc->chip->bus_sync_unlock(irq);
+}
+
 /*
  * Debugging printout:
  */
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index 0ec9ed831737..bde4c667d24d 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -230,9 +230,11 @@ void disable_irq_nosync(unsigned int irq)
 	if (!desc)
 		return;
 
+	chip_bus_lock(irq, desc);
 	spin_lock_irqsave(&desc->lock, flags);
 	__disable_irq(desc, irq, false);
 	spin_unlock_irqrestore(&desc->lock, flags);
+	chip_bus_sync_unlock(irq, desc);
 }
 EXPORT_SYMBOL(disable_irq_nosync);
 
@@ -294,7 +296,8 @@ void __enable_irq(struct irq_desc *desc, unsigned int irq, bool resume)
  *	matches the last disable, processing of interrupts on this
  *	IRQ line is re-enabled.
  *
- *	This function may be called from IRQ context.
+ *	This function may be called from IRQ context only when
+ *	desc->chip->bus_lock and desc->chip->bus_sync_unlock are NULL !
  */
 void enable_irq(unsigned int irq)
 {
@@ -304,9 +307,11 @@ void enable_irq(unsigned int irq)
 	if (!desc)
 		return;
 
+	chip_bus_lock(irq, desc);
 	spin_lock_irqsave(&desc->lock, flags);
 	__enable_irq(desc, irq, false);
 	spin_unlock_irqrestore(&desc->lock, flags);
+	chip_bus_sync_unlock(irq, desc);
 }
 EXPORT_SYMBOL(enable_irq);
 
@@ -436,6 +441,26 @@ int __irq_set_trigger(struct irq_desc *desc, unsigned int irq,
 	return ret;
 }
 
+/*
+ * Default primary interrupt handler for threaded interrupts. Is
+ * assigned as primary handler when request_threaded_irq is called
+ * with handler == NULL. Useful for oneshot interrupts.
+ */
+static irqreturn_t irq_default_primary_handler(int irq, void *dev_id)
+{
+	return IRQ_WAKE_THREAD;
+}
+
+/*
+ * Primary handler for nested threaded interrupts. Should never be
+ * called.
+ */
+static irqreturn_t irq_nested_primary_handler(int irq, void *dev_id)
+{
+	WARN(1, "Primary handler called for nested irq %d\n", irq);
+	return IRQ_NONE;
+}
+
 static int irq_wait_for_interrupt(struct irqaction *action)
 {
 	while (!kthread_should_stop()) {
@@ -451,6 +476,23 @@ static int irq_wait_for_interrupt(struct irqaction *action)
 	return -1;
 }
 
+/*
+ * Oneshot interrupts keep the irq line masked until the threaded
+ * handler finished. unmask if the interrupt has not been disabled and
+ * is marked MASKED.
+ */
+static void irq_finalize_oneshot(unsigned int irq, struct irq_desc *desc)
+{
+	chip_bus_lock(irq, desc);
+	spin_lock_irq(&desc->lock);
+	if (!(desc->status & IRQ_DISABLED) && (desc->status & IRQ_MASKED)) {
+		desc->status &= ~IRQ_MASKED;
+		desc->chip->unmask(irq);
+	}
+	spin_unlock_irq(&desc->lock);
+	chip_bus_sync_unlock(irq, desc);
+}
+
 #ifdef CONFIG_SMP
 /*
  * Check whether we need to change the affinity of the interrupt thread.
@@ -492,7 +534,7 @@ static int irq_thread(void *data)
 	struct sched_param param = { .sched_priority = MAX_USER_RT_PRIO/2, };
 	struct irqaction *action = data;
 	struct irq_desc *desc = irq_to_desc(action->irq);
-	int wake;
+	int wake, oneshot = desc->status & IRQ_ONESHOT;
 
 	sched_setscheduler(current, SCHED_FIFO, &param);
 	current->irqaction = action;
@@ -518,6 +560,9 @@ static int irq_thread(void *data)
 			spin_unlock_irq(&desc->lock);
 
 			action->thread_fn(action->irq, action->dev_id);
+
+			if (oneshot)
+				irq_finalize_oneshot(action->irq, desc);
 		}
 
 		wake = atomic_dec_and_test(&desc->threads_active);
@@ -565,7 +610,7 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new)
 	struct irqaction *old, **old_ptr;
 	const char *old_name = NULL;
 	unsigned long flags;
-	int shared = 0;
+	int nested, shared = 0;
 	int ret;
 
 	if (!desc)
@@ -590,10 +635,32 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new)
 		rand_initialize_irq(irq);
 	}
 
+	/* Oneshot interrupts are not allowed with shared */
+	if ((new->flags & IRQF_ONESHOT) && (new->flags & IRQF_SHARED))
+		return -EINVAL;
+
+	/*
+	 * Check whether the interrupt nests into another interrupt
+	 * thread.
+	 */
+	nested = desc->status & IRQ_NESTED_THREAD;
+	if (nested) {
+		if (!new->thread_fn)
+			return -EINVAL;
+		/*
+		 * Replace the primary handler which was provided from
+		 * the driver for non nested interrupt handling by the
+		 * dummy function which warns when called.
+		 */
+		new->handler = irq_nested_primary_handler;
+	}
+
 	/*
-	 * Threaded handler ?
+	 * Create a handler thread when a thread function is supplied
+	 * and the interrupt does not nest into another interrupt
+	 * thread.
 	 */
-	if (new->thread_fn) {
+	if (new->thread_fn && !nested) {
 		struct task_struct *t;
 
 		t = kthread_create(irq_thread, new, "irq/%d-%s", irq,
@@ -662,9 +729,12 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new)
 			desc->status |= IRQ_PER_CPU;
 #endif
 
-		desc->status &= ~(IRQ_AUTODETECT | IRQ_WAITING |
+		desc->status &= ~(IRQ_AUTODETECT | IRQ_WAITING | IRQ_ONESHOT |
 				  IRQ_INPROGRESS | IRQ_SPURIOUS_DISABLED);
 
+		if (new->flags & IRQF_ONESHOT)
+			desc->status |= IRQ_ONESHOT;
+
 		if (!(desc->status & IRQ_NOAUTOEN)) {
 			desc->depth = 0;
 			desc->status &= ~IRQ_DISABLED;
@@ -875,7 +945,14 @@ EXPORT_SYMBOL_GPL(remove_irq);
  */
 void free_irq(unsigned int irq, void *dev_id)
 {
+	struct irq_desc *desc = irq_to_desc(irq);
+
+	if (!desc)
+		return;
+
+	chip_bus_lock(irq, desc);
 	kfree(__free_irq(irq, dev_id));
+	chip_bus_sync_unlock(irq, desc);
 }
 EXPORT_SYMBOL(free_irq);
 
@@ -884,6 +961,8 @@ EXPORT_SYMBOL(free_irq);
  *	@irq: Interrupt line to allocate
  *	@handler: Function to be called when the IRQ occurs.
  *		  Primary handler for threaded interrupts
+ *		  If NULL and thread_fn != NULL the default
+ *		  primary handler is installed
  *	@thread_fn: Function called from the irq handler thread
  *		    If NULL, no irq thread is created
  *	@irqflags: Interrupt type flags
@@ -963,8 +1042,12 @@ int request_threaded_irq(unsigned int irq, irq_handler_t handler,
 
 	if (desc->status & IRQ_NOREQUEST)
 		return -EINVAL;
-	if (!handler)
-		return -EINVAL;
+
+	if (!handler) {
+		if (!thread_fn)
+			return -EINVAL;
+		handler = irq_default_primary_handler;
+	}
 
 	action = kzalloc(sizeof(struct irqaction), GFP_KERNEL);
 	if (!action)
@@ -976,7 +1059,10 @@ int request_threaded_irq(unsigned int irq, irq_handler_t handler,
 	action->name = devname;
 	action->dev_id = dev_id;
 
+	chip_bus_lock(irq, desc);
 	retval = __setup_irq(irq, desc, action);
+	chip_bus_sync_unlock(irq, desc);
+
 	if (retval)
 		kfree(action);
 
diff --git a/kernel/irq/pm.c b/kernel/irq/pm.c
index 638d8bedec14..a0bb09e79867 100644
--- a/kernel/irq/pm.c
+++ b/kernel/irq/pm.c
@@ -15,10 +15,10 @@
 /**
  * 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.
+ * During system-wide suspend or hibernation device drivers need to be prevented
+ * from receiving interrupts and this function is provided for this purpose.
+ * It marks all interrupt lines in use, except for the timer ones, as disabled
+ * and sets the IRQ_SUSPENDED flag for each of them.
  */
 void suspend_device_irqs(void)
 {
diff --git a/kernel/irq/resend.c b/kernel/irq/resend.c
index 89c7117acf2b..090c3763f3a2 100644
--- a/kernel/irq/resend.c
+++ b/kernel/irq/resend.c
@@ -70,8 +70,7 @@ void check_irq_resend(struct irq_desc *desc, unsigned int irq)
 	if ((status & (IRQ_LEVEL | IRQ_PENDING | IRQ_REPLAY)) == IRQ_PENDING) {
 		desc->status = (status & ~IRQ_PENDING) | IRQ_REPLAY;
 
-		if (!desc->chip || !desc->chip->retrigger ||
-					!desc->chip->retrigger(irq)) {
+		if (!desc->chip->retrigger || !desc->chip->retrigger(irq)) {
 #ifdef CONFIG_HARDIRQS_SW_RESEND
 			/* Set it pending and activate the softirq: */
 			set_bit(irq, irqs_resend);
diff --git a/kernel/irq/spurious.c b/kernel/irq/spurious.c
index 4d568294de3e..bd7273e6282e 100644
--- a/kernel/irq/spurious.c
+++ b/kernel/irq/spurious.c
@@ -121,7 +121,9 @@ static void poll_all_shared_irqs(void)
 		if (!(status & IRQ_SPURIOUS_DISABLED))
 			continue;
 
+		local_irq_disable();
 		try_one_irq(i, desc);
+		local_irq_enable();
 	}
 }
 
@@ -297,7 +299,6 @@ static int __init irqfixup_setup(char *str)
 
 __setup("irqfixup", irqfixup_setup);
 module_param(irqfixup, int, 0644);
-MODULE_PARM_DESC("irqfixup", "0: No fixup, 1: irqfixup mode, 2: irqpoll mode");
 
 static int __init irqpoll_setup(char *str)
 {
diff --git a/kernel/itimer.c b/kernel/itimer.c
index 58762f7077ec..b03451ede528 100644
--- a/kernel/itimer.c
+++ b/kernel/itimer.c
@@ -12,6 +12,7 @@
 #include <linux/time.h>
 #include <linux/posix-timers.h>
 #include <linux/hrtimer.h>
+#include <trace/events/timer.h>
 
 #include <asm/uaccess.h>
 
@@ -41,10 +42,43 @@ static struct timeval itimer_get_remtime(struct hrtimer *timer)
 	return ktime_to_timeval(rem);
 }
 
+static void get_cpu_itimer(struct task_struct *tsk, unsigned int clock_id,
+			   struct itimerval *const value)
+{
+	cputime_t cval, cinterval;
+	struct cpu_itimer *it = &tsk->signal->it[clock_id];
+
+	spin_lock_irq(&tsk->sighand->siglock);
+
+	cval = it->expires;
+	cinterval = it->incr;
+	if (!cputime_eq(cval, cputime_zero)) {
+		struct task_cputime cputime;
+		cputime_t t;
+
+		thread_group_cputimer(tsk, &cputime);
+		if (clock_id == CPUCLOCK_PROF)
+			t = cputime_add(cputime.utime, cputime.stime);
+		else
+			/* CPUCLOCK_VIRT */
+			t = cputime.utime;
+
+		if (cputime_le(cval, t))
+			/* about to fire */
+			cval = cputime_one_jiffy;
+		else
+			cval = cputime_sub(cval, t);
+	}
+
+	spin_unlock_irq(&tsk->sighand->siglock);
+
+	cputime_to_timeval(cval, &value->it_value);
+	cputime_to_timeval(cinterval, &value->it_interval);
+}
+
 int do_getitimer(int which, struct itimerval *value)
 {
 	struct task_struct *tsk = current;
-	cputime_t cinterval, cval;
 
 	switch (which) {
 	case ITIMER_REAL:
@@ -55,44 +89,10 @@ int do_getitimer(int which, struct itimerval *value)
 		spin_unlock_irq(&tsk->sighand->siglock);
 		break;
 	case ITIMER_VIRTUAL:
-		spin_lock_irq(&tsk->sighand->siglock);
-		cval = tsk->signal->it_virt_expires;
-		cinterval = tsk->signal->it_virt_incr;
-		if (!cputime_eq(cval, cputime_zero)) {
-			struct task_cputime cputime;
-			cputime_t utime;
-
-			thread_group_cputimer(tsk, &cputime);
-			utime = cputime.utime;
-			if (cputime_le(cval, utime)) { /* about to fire */
-				cval = jiffies_to_cputime(1);
-			} else {
-				cval = cputime_sub(cval, utime);
-			}
-		}
-		spin_unlock_irq(&tsk->sighand->siglock);
-		cputime_to_timeval(cval, &value->it_value);
-		cputime_to_timeval(cinterval, &value->it_interval);
+		get_cpu_itimer(tsk, CPUCLOCK_VIRT, value);
 		break;
 	case ITIMER_PROF:
-		spin_lock_irq(&tsk->sighand->siglock);
-		cval = tsk->signal->it_prof_expires;
-		cinterval = tsk->signal->it_prof_incr;
-		if (!cputime_eq(cval, cputime_zero)) {
-			struct task_cputime times;
-			cputime_t ptime;
-
-			thread_group_cputimer(tsk, &times);
-			ptime = cputime_add(times.utime, times.stime);
-			if (cputime_le(cval, ptime)) { /* about to fire */
-				cval = jiffies_to_cputime(1);
-			} else {
-				cval = cputime_sub(cval, ptime);
-			}
-		}
-		spin_unlock_irq(&tsk->sighand->siglock);
-		cputime_to_timeval(cval, &value->it_value);
-		cputime_to_timeval(cinterval, &value->it_interval);
+		get_cpu_itimer(tsk, CPUCLOCK_PROF, value);
 		break;
 	default:
 		return(-EINVAL);
@@ -123,11 +123,62 @@ enum hrtimer_restart it_real_fn(struct hrtimer *timer)
 	struct signal_struct *sig =
 		container_of(timer, struct signal_struct, real_timer);
 
+	trace_itimer_expire(ITIMER_REAL, sig->leader_pid, 0);
 	kill_pid_info(SIGALRM, SEND_SIG_PRIV, sig->leader_pid);
 
 	return HRTIMER_NORESTART;
 }
 
+static inline u32 cputime_sub_ns(cputime_t ct, s64 real_ns)
+{
+	struct timespec ts;
+	s64 cpu_ns;
+
+	cputime_to_timespec(ct, &ts);
+	cpu_ns = timespec_to_ns(&ts);
+
+	return (cpu_ns <= real_ns) ? 0 : cpu_ns - real_ns;
+}
+
+static void set_cpu_itimer(struct task_struct *tsk, unsigned int clock_id,
+			   const struct itimerval *const value,
+			   struct itimerval *const ovalue)
+{
+	cputime_t cval, nval, cinterval, ninterval;
+	s64 ns_ninterval, ns_nval;
+	struct cpu_itimer *it = &tsk->signal->it[clock_id];
+
+	nval = timeval_to_cputime(&value->it_value);
+	ns_nval = timeval_to_ns(&value->it_value);
+	ninterval = timeval_to_cputime(&value->it_interval);
+	ns_ninterval = timeval_to_ns(&value->it_interval);
+
+	it->incr_error = cputime_sub_ns(ninterval, ns_ninterval);
+	it->error = cputime_sub_ns(nval, ns_nval);
+
+	spin_lock_irq(&tsk->sighand->siglock);
+
+	cval = it->expires;
+	cinterval = it->incr;
+	if (!cputime_eq(cval, cputime_zero) ||
+	    !cputime_eq(nval, cputime_zero)) {
+		if (cputime_gt(nval, cputime_zero))
+			nval = cputime_add(nval, cputime_one_jiffy);
+		set_process_cpu_timer(tsk, clock_id, &nval, &cval);
+	}
+	it->expires = nval;
+	it->incr = ninterval;
+	trace_itimer_state(clock_id == CPUCLOCK_VIRT ?
+			   ITIMER_VIRTUAL : ITIMER_PROF, value, nval);
+
+	spin_unlock_irq(&tsk->sighand->siglock);
+
+	if (ovalue) {
+		cputime_to_timeval(cval, &ovalue->it_value);
+		cputime_to_timeval(cinterval, &ovalue->it_interval);
+	}
+}
+
 /*
  * Returns true if the timeval is in canonical form
  */
@@ -139,7 +190,6 @@ int do_setitimer(int which, struct itimerval *value, struct itimerval *ovalue)
 	struct task_struct *tsk = current;
 	struct hrtimer *timer;
 	ktime_t expires;
-	cputime_t cval, cinterval, nval, ninterval;
 
 	/*
 	 * Validate the timevals in value.
@@ -171,51 +221,14 @@ again:
 		} else
 			tsk->signal->it_real_incr.tv64 = 0;
 
+		trace_itimer_state(ITIMER_REAL, value, 0);
 		spin_unlock_irq(&tsk->sighand->siglock);
 		break;
 	case ITIMER_VIRTUAL:
-		nval = timeval_to_cputime(&value->it_value);
-		ninterval = timeval_to_cputime(&value->it_interval);
-		spin_lock_irq(&tsk->sighand->siglock);
-		cval = tsk->signal->it_virt_expires;
-		cinterval = tsk->signal->it_virt_incr;
-		if (!cputime_eq(cval, cputime_zero) ||
-		    !cputime_eq(nval, cputime_zero)) {
-			if (cputime_gt(nval, cputime_zero))
-				nval = cputime_add(nval,
-						   jiffies_to_cputime(1));
-			set_process_cpu_timer(tsk, CPUCLOCK_VIRT,
-					      &nval, &cval);
-		}
-		tsk->signal->it_virt_expires = nval;
-		tsk->signal->it_virt_incr = ninterval;
-		spin_unlock_irq(&tsk->sighand->siglock);
-		if (ovalue) {
-			cputime_to_timeval(cval, &ovalue->it_value);
-			cputime_to_timeval(cinterval, &ovalue->it_interval);
-		}
+		set_cpu_itimer(tsk, CPUCLOCK_VIRT, value, ovalue);
 		break;
 	case ITIMER_PROF:
-		nval = timeval_to_cputime(&value->it_value);
-		ninterval = timeval_to_cputime(&value->it_interval);
-		spin_lock_irq(&tsk->sighand->siglock);
-		cval = tsk->signal->it_prof_expires;
-		cinterval = tsk->signal->it_prof_incr;
-		if (!cputime_eq(cval, cputime_zero) ||
-		    !cputime_eq(nval, cputime_zero)) {
-			if (cputime_gt(nval, cputime_zero))
-				nval = cputime_add(nval,
-						   jiffies_to_cputime(1));
-			set_process_cpu_timer(tsk, CPUCLOCK_PROF,
-					      &nval, &cval);
-		}
-		tsk->signal->it_prof_expires = nval;
-		tsk->signal->it_prof_incr = ninterval;
-		spin_unlock_irq(&tsk->sighand->siglock);
-		if (ovalue) {
-			cputime_to_timeval(cval, &ovalue->it_value);
-			cputime_to_timeval(cinterval, &ovalue->it_interval);
-		}
+		set_cpu_itimer(tsk, CPUCLOCK_PROF, value, ovalue);
 		break;
 	default:
 		return -EINVAL;
diff --git a/kernel/kallsyms.c b/kernel/kallsyms.c
index 3a29dbe7898e..8b6b8b697c68 100644
--- a/kernel/kallsyms.c
+++ b/kernel/kallsyms.c
@@ -59,7 +59,8 @@ static inline int is_kernel_inittext(unsigned long addr)
 
 static inline int is_kernel_text(unsigned long addr)
 {
-	if (addr >= (unsigned long)_stext && addr <= (unsigned long)_etext)
+	if ((addr >= (unsigned long)_stext && addr <= (unsigned long)_etext) ||
+	    arch_is_kernel_text(addr))
 		return 1;
 	return in_gate_area_no_task(addr);
 }
diff --git a/kernel/kfifo.c b/kernel/kfifo.c
index 26539e3228e5..3765ff3c1bbe 100644
--- a/kernel/kfifo.c
+++ b/kernel/kfifo.c
@@ -117,7 +117,7 @@ EXPORT_SYMBOL(kfifo_free);
  * writer, you don't need extra locking to use these functions.
  */
 unsigned int __kfifo_put(struct kfifo *fifo,
-			 unsigned char *buffer, unsigned int len)
+			const unsigned char *buffer, unsigned int len)
 {
 	unsigned int l;
 
diff --git a/kernel/kmod.c b/kernel/kmod.c
index 385c31a1bdbf..9fcb53a11f87 100644
--- a/kernel/kmod.c
+++ b/kernel/kmod.c
@@ -37,6 +37,8 @@
 #include <linux/suspend.h>
 #include <asm/uaccess.h>
 
+#include <trace/events/module.h>
+
 extern int max_threads;
 
 static struct workqueue_struct *khelper_wq;
@@ -78,6 +80,10 @@ int __request_module(bool wait, const char *fmt, ...)
 #define MAX_KMOD_CONCURRENT 50	/* Completely arbitrary value - KAO */
 	static int kmod_loop_msg;
 
+	ret = security_kernel_module_request();
+	if (ret)
+		return ret;
+
 	va_start(args, fmt);
 	ret = vsnprintf(module_name, MODULE_NAME_LEN, fmt, args);
 	va_end(args);
@@ -108,6 +114,8 @@ int __request_module(bool wait, const char *fmt, ...)
 		return -ENOMEM;
 	}
 
+	trace_module_request(module_name, wait, _RET_IP_);
+
 	ret = call_usermodehelper(modprobe_path, argv, envp,
 			wait ? UMH_WAIT_PROC : UMH_WAIT_EXEC);
 	atomic_dec(&kmod_concurrent);
@@ -462,6 +470,7 @@ int call_usermodehelper_exec(struct subprocess_info *sub_info,
 	int retval = 0;
 
 	BUG_ON(atomic_read(&sub_info->cred->usage) != 1);
+	validate_creds(sub_info->cred);
 
 	helper_lock();
 	if (sub_info->path[0] == '\0')
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index 0540948e29ab..5240d75f4c60 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -103,7 +103,7 @@ static struct kprobe_blackpoint kprobe_blacklist[] = {
 #define INSNS_PER_PAGE	(PAGE_SIZE/(MAX_INSN_SIZE * sizeof(kprobe_opcode_t)))
 
 struct kprobe_insn_page {
-	struct hlist_node hlist;
+	struct list_head list;
 	kprobe_opcode_t *insns;		/* Page of instruction slots */
 	char slot_used[INSNS_PER_PAGE];
 	int nused;
@@ -117,7 +117,7 @@ enum kprobe_slot_state {
 };
 
 static DEFINE_MUTEX(kprobe_insn_mutex);	/* Protects kprobe_insn_pages */
-static struct hlist_head kprobe_insn_pages;
+static LIST_HEAD(kprobe_insn_pages);
 static int kprobe_garbage_slots;
 static int collect_garbage_slots(void);
 
@@ -152,10 +152,9 @@ loop_end:
 static kprobe_opcode_t __kprobes *__get_insn_slot(void)
 {
 	struct kprobe_insn_page *kip;
-	struct hlist_node *pos;
 
  retry:
-	hlist_for_each_entry(kip, pos, &kprobe_insn_pages, hlist) {
+	list_for_each_entry(kip, &kprobe_insn_pages, list) {
 		if (kip->nused < INSNS_PER_PAGE) {
 			int i;
 			for (i = 0; i < INSNS_PER_PAGE; i++) {
@@ -189,8 +188,8 @@ static kprobe_opcode_t __kprobes *__get_insn_slot(void)
 		kfree(kip);
 		return NULL;
 	}
-	INIT_HLIST_NODE(&kip->hlist);
-	hlist_add_head(&kip->hlist, &kprobe_insn_pages);
+	INIT_LIST_HEAD(&kip->list);
+	list_add(&kip->list, &kprobe_insn_pages);
 	memset(kip->slot_used, SLOT_CLEAN, INSNS_PER_PAGE);
 	kip->slot_used[0] = SLOT_USED;
 	kip->nused = 1;
@@ -219,12 +218,8 @@ static int __kprobes collect_one_slot(struct kprobe_insn_page *kip, int idx)
 		 * so as not to have to set it up again the
 		 * next time somebody inserts a probe.
 		 */
-		hlist_del(&kip->hlist);
-		if (hlist_empty(&kprobe_insn_pages)) {
-			INIT_HLIST_NODE(&kip->hlist);
-			hlist_add_head(&kip->hlist,
-				       &kprobe_insn_pages);
-		} else {
+		if (!list_is_singular(&kprobe_insn_pages)) {
+			list_del(&kip->list);
 			module_free(NULL, kip->insns);
 			kfree(kip);
 		}
@@ -235,14 +230,13 @@ static int __kprobes collect_one_slot(struct kprobe_insn_page *kip, int idx)
 
 static int __kprobes collect_garbage_slots(void)
 {
-	struct kprobe_insn_page *kip;
-	struct hlist_node *pos, *next;
+	struct kprobe_insn_page *kip, *next;
 
 	/* Ensure no-one is preepmted on the garbages */
 	if (check_safety())
 		return -EAGAIN;
 
-	hlist_for_each_entry_safe(kip, pos, next, &kprobe_insn_pages, hlist) {
+	list_for_each_entry_safe(kip, next, &kprobe_insn_pages, list) {
 		int i;
 		if (kip->ngarbage == 0)
 			continue;
@@ -260,19 +254,17 @@ static int __kprobes collect_garbage_slots(void)
 void __kprobes free_insn_slot(kprobe_opcode_t * slot, int dirty)
 {
 	struct kprobe_insn_page *kip;
-	struct hlist_node *pos;
 
 	mutex_lock(&kprobe_insn_mutex);
-	hlist_for_each_entry(kip, pos, &kprobe_insn_pages, hlist) {
+	list_for_each_entry(kip, &kprobe_insn_pages, list) {
 		if (kip->insns <= slot &&
 		    slot < kip->insns + (INSNS_PER_PAGE * MAX_INSN_SIZE)) {
 			int i = (slot - kip->insns) / MAX_INSN_SIZE;
 			if (dirty) {
 				kip->slot_used[i] = SLOT_DIRTY;
 				kip->ngarbage++;
-			} else {
+			} else
 				collect_one_slot(kip, i);
-			}
 			break;
 		}
 	}
@@ -1329,7 +1321,7 @@ static int __kprobes show_kprobe_addr(struct seq_file *pi, void *v)
 	return 0;
 }
 
-static struct seq_operations kprobes_seq_ops = {
+static const struct seq_operations kprobes_seq_ops = {
 	.start = kprobe_seq_start,
 	.next  = kprobe_seq_next,
 	.stop  = kprobe_seq_stop,
@@ -1341,7 +1333,7 @@ static int __kprobes kprobes_open(struct inode *inode, struct file *filp)
 	return seq_open(filp, &kprobes_seq_ops);
 }
 
-static struct file_operations debugfs_kprobes_operations = {
+static const struct file_operations debugfs_kprobes_operations = {
 	.open           = kprobes_open,
 	.read           = seq_read,
 	.llseek         = seq_lseek,
@@ -1523,7 +1515,7 @@ static ssize_t write_enabled_file_bool(struct file *file,
 	return count;
 }
 
-static struct file_operations fops_kp = {
+static const struct file_operations fops_kp = {
 	.read =         read_enabled_file_bool,
 	.write =        write_enabled_file_bool,
 };
diff --git a/kernel/kthread.c b/kernel/kthread.c
index eb8751aa0418..ab7ae57773e1 100644
--- a/kernel/kthread.c
+++ b/kernel/kthread.c
@@ -16,8 +16,6 @@
 #include <linux/mutex.h>
 #include <trace/events/sched.h>
 
-#define KTHREAD_NICE_LEVEL (-5)
-
 static DEFINE_SPINLOCK(kthread_create_lock);
 static LIST_HEAD(kthread_create_list);
 struct task_struct *kthreadd_task;
@@ -145,7 +143,6 @@ struct task_struct *kthread_create(int (*threadfn)(void *data),
 		 * The kernel thread should not inherit these properties.
 		 */
 		sched_setscheduler_nocheck(create.result, SCHED_NORMAL, &param);
-		set_user_nice(create.result, KTHREAD_NICE_LEVEL);
 		set_cpus_allowed_ptr(create.result, cpu_all_mask);
 	}
 	return create.result;
@@ -153,29 +150,6 @@ struct task_struct *kthread_create(int (*threadfn)(void *data),
 EXPORT_SYMBOL(kthread_create);
 
 /**
- * kthread_bind - bind a just-created kthread to a cpu.
- * @k: thread created by kthread_create().
- * @cpu: cpu (might not be online, must be possible) for @k to run on.
- *
- * Description: This function is equivalent to set_cpus_allowed(),
- * except that @cpu doesn't need to be online, and the thread must be
- * stopped (i.e., just returned from kthread_create()).
- */
-void kthread_bind(struct task_struct *k, unsigned int cpu)
-{
-	/* Must have done schedule() in kthread() before we set_task_cpu */
-	if (!wait_task_inactive(k, TASK_UNINTERRUPTIBLE)) {
-		WARN_ON(1);
-		return;
-	}
-	set_task_cpu(k, cpu);
-	k->cpus_allowed = cpumask_of_cpu(cpu);
-	k->rt.nr_cpus_allowed = 1;
-	k->flags |= PF_THREAD_BOUND;
-}
-EXPORT_SYMBOL(kthread_bind);
-
-/**
  * kthread_stop - stop a thread created by kthread_create().
  * @k: thread created by kthread_create().
  *
@@ -221,7 +195,6 @@ int kthreadd(void *unused)
 	/* Setup a clean context for our children to inherit. */
 	set_task_comm(tsk, "kthreadd");
 	ignore_signals(tsk);
-	set_user_nice(tsk, KTHREAD_NICE_LEVEL);
 	set_cpus_allowed_ptr(tsk, cpu_all_mask);
 	set_mems_allowed(node_possible_map);
 
diff --git a/kernel/lockdep.c b/kernel/lockdep.c
index 8bbeef996c76..9af56723c096 100644
--- a/kernel/lockdep.c
+++ b/kernel/lockdep.c
@@ -42,6 +42,7 @@
 #include <linux/hash.h>
 #include <linux/ftrace.h>
 #include <linux/stringify.h>
+#include <linux/bitops.h>
 
 #include <asm/sections.h>
 
@@ -141,6 +142,11 @@ static inline struct lock_class *hlock_class(struct held_lock *hlock)
 #ifdef CONFIG_LOCK_STAT
 static DEFINE_PER_CPU(struct lock_class_stats[MAX_LOCKDEP_KEYS], lock_stats);
 
+static inline u64 lockstat_clock(void)
+{
+	return cpu_clock(smp_processor_id());
+}
+
 static int lock_point(unsigned long points[], unsigned long ip)
 {
 	int i;
@@ -157,7 +163,7 @@ static int lock_point(unsigned long points[], unsigned long ip)
 	return i;
 }
 
-static void lock_time_inc(struct lock_time *lt, s64 time)
+static void lock_time_inc(struct lock_time *lt, u64 time)
 {
 	if (time > lt->max)
 		lt->max = time;
@@ -233,12 +239,12 @@ static void put_lock_stats(struct lock_class_stats *stats)
 static void lock_release_holdtime(struct held_lock *hlock)
 {
 	struct lock_class_stats *stats;
-	s64 holdtime;
+	u64 holdtime;
 
 	if (!lock_stat)
 		return;
 
-	holdtime = sched_clock() - hlock->holdtime_stamp;
+	holdtime = lockstat_clock() - hlock->holdtime_stamp;
 
 	stats = get_lock_stats(hlock_class(hlock));
 	if (hlock->read)
@@ -366,11 +372,21 @@ static int save_trace(struct stack_trace *trace)
 
 	save_stack_trace(trace);
 
+	/*
+	 * Some daft arches put -1 at the end to indicate its a full trace.
+	 *
+	 * <rant> this is buggy anyway, since it takes a whole extra entry so a
+	 * complete trace that maxes out the entries provided will be reported
+	 * as incomplete, friggin useless </rant>
+	 */
+	if (trace->entries[trace->nr_entries-1] == ULONG_MAX)
+		trace->nr_entries--;
+
 	trace->max_entries = trace->nr_entries;
 
 	nr_stack_trace_entries += trace->nr_entries;
 
-	if (nr_stack_trace_entries == MAX_STACK_TRACE_ENTRIES) {
+	if (nr_stack_trace_entries >= MAX_STACK_TRACE_ENTRIES-1) {
 		if (!debug_locks_off_graph_unlock())
 			return 0;
 
@@ -388,20 +404,6 @@ unsigned int nr_hardirq_chains;
 unsigned int nr_softirq_chains;
 unsigned int nr_process_chains;
 unsigned int max_lockdep_depth;
-unsigned int max_recursion_depth;
-
-static unsigned int lockdep_dependency_gen_id;
-
-static bool lockdep_dependency_visit(struct lock_class *source,
-				     unsigned int depth)
-{
-	if (!depth)
-		lockdep_dependency_gen_id++;
-	if (source->dep_gen_id == lockdep_dependency_gen_id)
-		return true;
-	source->dep_gen_id = lockdep_dependency_gen_id;
-	return false;
-}
 
 #ifdef CONFIG_DEBUG_LOCKDEP
 /*
@@ -431,11 +433,8 @@ atomic_t redundant_softirqs_on;
 atomic_t redundant_softirqs_off;
 atomic_t nr_unused_locks;
 atomic_t nr_cyclic_checks;
-atomic_t nr_cyclic_check_recursions;
 atomic_t nr_find_usage_forwards_checks;
-atomic_t nr_find_usage_forwards_recursions;
 atomic_t nr_find_usage_backwards_checks;
-atomic_t nr_find_usage_backwards_recursions;
 #endif
 
 /*
@@ -551,58 +550,6 @@ static void lockdep_print_held_locks(struct task_struct *curr)
 	}
 }
 
-static void print_lock_class_header(struct lock_class *class, int depth)
-{
-	int bit;
-
-	printk("%*s->", depth, "");
-	print_lock_name(class);
-	printk(" ops: %lu", class->ops);
-	printk(" {\n");
-
-	for (bit = 0; bit < LOCK_USAGE_STATES; bit++) {
-		if (class->usage_mask & (1 << bit)) {
-			int len = depth;
-
-			len += printk("%*s   %s", depth, "", usage_str[bit]);
-			len += printk(" at:\n");
-			print_stack_trace(class->usage_traces + bit, len);
-		}
-	}
-	printk("%*s }\n", depth, "");
-
-	printk("%*s ... key      at: ",depth,"");
-	print_ip_sym((unsigned long)class->key);
-}
-
-/*
- * printk all lock dependencies starting at <entry>:
- */
-static void __used
-print_lock_dependencies(struct lock_class *class, int depth)
-{
-	struct lock_list *entry;
-
-	if (lockdep_dependency_visit(class, depth))
-		return;
-
-	if (DEBUG_LOCKS_WARN_ON(depth >= 20))
-		return;
-
-	print_lock_class_header(class, depth);
-
-	list_for_each_entry(entry, &class->locks_after, entry) {
-		if (DEBUG_LOCKS_WARN_ON(!entry->class))
-			return;
-
-		print_lock_dependencies(entry->class, depth + 1);
-
-		printk("%*s ... acquired at:\n",depth,"");
-		print_stack_trace(&entry->trace, 2);
-		printk("\n");
-	}
-}
-
 static void print_kernel_version(void)
 {
 	printk("%s %.*s\n", init_utsname()->release,
@@ -636,6 +583,9 @@ static int static_obj(void *obj)
 	if ((addr >= start) && (addr < end))
 		return 1;
 
+	if (arch_is_kernel_data(addr))
+		return 1;
+
 #ifdef CONFIG_SMP
 	/*
 	 * percpu var?
@@ -898,22 +848,203 @@ static int add_lock_to_list(struct lock_class *class, struct lock_class *this,
 }
 
 /*
+ * For good efficiency of modular, we use power of 2
+ */
+#define MAX_CIRCULAR_QUEUE_SIZE		4096UL
+#define CQ_MASK				(MAX_CIRCULAR_QUEUE_SIZE-1)
+
+/*
+ * The circular_queue and helpers is used to implement the
+ * breadth-first search(BFS)algorithem, by which we can build
+ * the shortest path from the next lock to be acquired to the
+ * previous held lock if there is a circular between them.
+ */
+struct circular_queue {
+	unsigned long element[MAX_CIRCULAR_QUEUE_SIZE];
+	unsigned int  front, rear;
+};
+
+static struct circular_queue lock_cq;
+
+unsigned int max_bfs_queue_depth;
+
+static unsigned int lockdep_dependency_gen_id;
+
+static inline void __cq_init(struct circular_queue *cq)
+{
+	cq->front = cq->rear = 0;
+	lockdep_dependency_gen_id++;
+}
+
+static inline int __cq_empty(struct circular_queue *cq)
+{
+	return (cq->front == cq->rear);
+}
+
+static inline int __cq_full(struct circular_queue *cq)
+{
+	return ((cq->rear + 1) & CQ_MASK) == cq->front;
+}
+
+static inline int __cq_enqueue(struct circular_queue *cq, unsigned long elem)
+{
+	if (__cq_full(cq))
+		return -1;
+
+	cq->element[cq->rear] = elem;
+	cq->rear = (cq->rear + 1) & CQ_MASK;
+	return 0;
+}
+
+static inline int __cq_dequeue(struct circular_queue *cq, unsigned long *elem)
+{
+	if (__cq_empty(cq))
+		return -1;
+
+	*elem = cq->element[cq->front];
+	cq->front = (cq->front + 1) & CQ_MASK;
+	return 0;
+}
+
+static inline unsigned int  __cq_get_elem_count(struct circular_queue *cq)
+{
+	return (cq->rear - cq->front) & CQ_MASK;
+}
+
+static inline void mark_lock_accessed(struct lock_list *lock,
+					struct lock_list *parent)
+{
+	unsigned long nr;
+
+	nr = lock - list_entries;
+	WARN_ON(nr >= nr_list_entries);
+	lock->parent = parent;
+	lock->class->dep_gen_id = lockdep_dependency_gen_id;
+}
+
+static inline unsigned long lock_accessed(struct lock_list *lock)
+{
+	unsigned long nr;
+
+	nr = lock - list_entries;
+	WARN_ON(nr >= nr_list_entries);
+	return lock->class->dep_gen_id == lockdep_dependency_gen_id;
+}
+
+static inline struct lock_list *get_lock_parent(struct lock_list *child)
+{
+	return child->parent;
+}
+
+static inline int get_lock_depth(struct lock_list *child)
+{
+	int depth = 0;
+	struct lock_list *parent;
+
+	while ((parent = get_lock_parent(child))) {
+		child = parent;
+		depth++;
+	}
+	return depth;
+}
+
+static int __bfs(struct lock_list *source_entry,
+		 void *data,
+		 int (*match)(struct lock_list *entry, void *data),
+		 struct lock_list **target_entry,
+		 int forward)
+{
+	struct lock_list *entry;
+	struct list_head *head;
+	struct circular_queue *cq = &lock_cq;
+	int ret = 1;
+
+	if (match(source_entry, data)) {
+		*target_entry = source_entry;
+		ret = 0;
+		goto exit;
+	}
+
+	if (forward)
+		head = &source_entry->class->locks_after;
+	else
+		head = &source_entry->class->locks_before;
+
+	if (list_empty(head))
+		goto exit;
+
+	__cq_init(cq);
+	__cq_enqueue(cq, (unsigned long)source_entry);
+
+	while (!__cq_empty(cq)) {
+		struct lock_list *lock;
+
+		__cq_dequeue(cq, (unsigned long *)&lock);
+
+		if (!lock->class) {
+			ret = -2;
+			goto exit;
+		}
+
+		if (forward)
+			head = &lock->class->locks_after;
+		else
+			head = &lock->class->locks_before;
+
+		list_for_each_entry(entry, head, entry) {
+			if (!lock_accessed(entry)) {
+				unsigned int cq_depth;
+				mark_lock_accessed(entry, lock);
+				if (match(entry, data)) {
+					*target_entry = entry;
+					ret = 0;
+					goto exit;
+				}
+
+				if (__cq_enqueue(cq, (unsigned long)entry)) {
+					ret = -1;
+					goto exit;
+				}
+				cq_depth = __cq_get_elem_count(cq);
+				if (max_bfs_queue_depth < cq_depth)
+					max_bfs_queue_depth = cq_depth;
+			}
+		}
+	}
+exit:
+	return ret;
+}
+
+static inline int __bfs_forwards(struct lock_list *src_entry,
+			void *data,
+			int (*match)(struct lock_list *entry, void *data),
+			struct lock_list **target_entry)
+{
+	return __bfs(src_entry, data, match, target_entry, 1);
+
+}
+
+static inline int __bfs_backwards(struct lock_list *src_entry,
+			void *data,
+			int (*match)(struct lock_list *entry, void *data),
+			struct lock_list **target_entry)
+{
+	return __bfs(src_entry, data, match, target_entry, 0);
+
+}
+
+/*
  * Recursive, forwards-direction lock-dependency checking, used for
  * both noncyclic checking and for hardirq-unsafe/softirq-unsafe
  * checking.
- *
- * (to keep the stackframe of the recursive functions small we
- *  use these global variables, and we also mark various helper
- *  functions as noinline.)
  */
-static struct held_lock *check_source, *check_target;
 
 /*
  * Print a dependency chain entry (this is only done when a deadlock
  * has been detected):
  */
 static noinline int
-print_circular_bug_entry(struct lock_list *target, unsigned int depth)
+print_circular_bug_entry(struct lock_list *target, int depth)
 {
 	if (debug_locks_silent)
 		return 0;
@@ -930,11 +1061,13 @@ print_circular_bug_entry(struct lock_list *target, unsigned int depth)
  * header first:
  */
 static noinline int
-print_circular_bug_header(struct lock_list *entry, unsigned int depth)
+print_circular_bug_header(struct lock_list *entry, unsigned int depth,
+			struct held_lock *check_src,
+			struct held_lock *check_tgt)
 {
 	struct task_struct *curr = current;
 
-	if (!debug_locks_off_graph_unlock() || debug_locks_silent)
+	if (debug_locks_silent)
 		return 0;
 
 	printk("\n=======================================================\n");
@@ -943,9 +1076,9 @@ print_circular_bug_header(struct lock_list *entry, unsigned int depth)
 	printk(  "-------------------------------------------------------\n");
 	printk("%s/%d is trying to acquire lock:\n",
 		curr->comm, task_pid_nr(curr));
-	print_lock(check_source);
+	print_lock(check_src);
 	printk("\nbut task is already holding lock:\n");
-	print_lock(check_target);
+	print_lock(check_tgt);
 	printk("\nwhich lock already depends on the new lock.\n\n");
 	printk("\nthe existing dependency chain (in reverse order) is:\n");
 
@@ -954,19 +1087,36 @@ print_circular_bug_header(struct lock_list *entry, unsigned int depth)
 	return 0;
 }
 
-static noinline int print_circular_bug_tail(void)
+static inline int class_equal(struct lock_list *entry, void *data)
+{
+	return entry->class == data;
+}
+
+static noinline int print_circular_bug(struct lock_list *this,
+				struct lock_list *target,
+				struct held_lock *check_src,
+				struct held_lock *check_tgt)
 {
 	struct task_struct *curr = current;
-	struct lock_list this;
+	struct lock_list *parent;
+	int depth;
 
-	if (debug_locks_silent)
+	if (!debug_locks_off_graph_unlock() || debug_locks_silent)
 		return 0;
 
-	this.class = hlock_class(check_source);
-	if (!save_trace(&this.trace))
+	if (!save_trace(&this->trace))
 		return 0;
 
-	print_circular_bug_entry(&this, 0);
+	depth = get_lock_depth(target);
+
+	print_circular_bug_header(target, depth, check_src, check_tgt);
+
+	parent = get_lock_parent(target);
+
+	while (parent) {
+		print_circular_bug_entry(parent, --depth);
+		parent = get_lock_parent(parent);
+	}
 
 	printk("\nother info that might help us debug this:\n\n");
 	lockdep_print_held_locks(curr);
@@ -977,73 +1127,69 @@ static noinline int print_circular_bug_tail(void)
 	return 0;
 }
 
-#define RECURSION_LIMIT 40
-
-static int noinline print_infinite_recursion_bug(void)
+static noinline int print_bfs_bug(int ret)
 {
 	if (!debug_locks_off_graph_unlock())
 		return 0;
 
-	WARN_ON(1);
+	WARN(1, "lockdep bfs error:%d\n", ret);
 
 	return 0;
 }
 
-unsigned long __lockdep_count_forward_deps(struct lock_class *class,
-					   unsigned int depth)
+static int noop_count(struct lock_list *entry, void *data)
 {
-	struct lock_list *entry;
-	unsigned long ret = 1;
+	(*(unsigned long *)data)++;
+	return 0;
+}
 
-	if (lockdep_dependency_visit(class, depth))
-		return 0;
+unsigned long __lockdep_count_forward_deps(struct lock_list *this)
+{
+	unsigned long  count = 0;
+	struct lock_list *uninitialized_var(target_entry);
 
-	/*
-	 * Recurse this class's dependency list:
-	 */
-	list_for_each_entry(entry, &class->locks_after, entry)
-		ret += __lockdep_count_forward_deps(entry->class, depth + 1);
+	__bfs_forwards(this, (void *)&count, noop_count, &target_entry);
 
-	return ret;
+	return count;
 }
-
 unsigned long lockdep_count_forward_deps(struct lock_class *class)
 {
 	unsigned long ret, flags;
+	struct lock_list this;
+
+	this.parent = NULL;
+	this.class = class;
 
 	local_irq_save(flags);
 	__raw_spin_lock(&lockdep_lock);
-	ret = __lockdep_count_forward_deps(class, 0);
+	ret = __lockdep_count_forward_deps(&this);
 	__raw_spin_unlock(&lockdep_lock);
 	local_irq_restore(flags);
 
 	return ret;
 }
 
-unsigned long __lockdep_count_backward_deps(struct lock_class *class,
-					    unsigned int depth)
+unsigned long __lockdep_count_backward_deps(struct lock_list *this)
 {
-	struct lock_list *entry;
-	unsigned long ret = 1;
+	unsigned long  count = 0;
+	struct lock_list *uninitialized_var(target_entry);
 
-	if (lockdep_dependency_visit(class, depth))
-		return 0;
-	/*
-	 * Recurse this class's dependency list:
-	 */
-	list_for_each_entry(entry, &class->locks_before, entry)
-		ret += __lockdep_count_backward_deps(entry->class, depth + 1);
+	__bfs_backwards(this, (void *)&count, noop_count, &target_entry);
 
-	return ret;
+	return count;
 }
 
 unsigned long lockdep_count_backward_deps(struct lock_class *class)
 {
 	unsigned long ret, flags;
+	struct lock_list this;
+
+	this.parent = NULL;
+	this.class = class;
 
 	local_irq_save(flags);
 	__raw_spin_lock(&lockdep_lock);
-	ret = __lockdep_count_backward_deps(class, 0);
+	ret = __lockdep_count_backward_deps(&this);
 	__raw_spin_unlock(&lockdep_lock);
 	local_irq_restore(flags);
 
@@ -1055,29 +1201,16 @@ unsigned long lockdep_count_backward_deps(struct lock_class *class)
  * lead to <target>. Print an error and return 0 if it does.
  */
 static noinline int
-check_noncircular(struct lock_class *source, unsigned int depth)
+check_noncircular(struct lock_list *root, struct lock_class *target,
+		struct lock_list **target_entry)
 {
-	struct lock_list *entry;
+	int result;
 
-	if (lockdep_dependency_visit(source, depth))
-		return 1;
+	debug_atomic_inc(&nr_cyclic_checks);
 
-	debug_atomic_inc(&nr_cyclic_check_recursions);
-	if (depth > max_recursion_depth)
-		max_recursion_depth = depth;
-	if (depth >= RECURSION_LIMIT)
-		return print_infinite_recursion_bug();
-	/*
-	 * Check this lock's dependency list:
-	 */
-	list_for_each_entry(entry, &source->locks_after, entry) {
-		if (entry->class == hlock_class(check_target))
-			return print_circular_bug_header(entry, depth+1);
-		debug_atomic_inc(&nr_cyclic_checks);
-		if (!check_noncircular(entry->class, depth+1))
-			return print_circular_bug_entry(entry, depth+1);
-	}
-	return 1;
+	result = __bfs_forwards(root, target, class_equal, target_entry);
+
+	return result;
 }
 
 #if defined(CONFIG_TRACE_IRQFLAGS) && defined(CONFIG_PROVE_LOCKING)
@@ -1086,103 +1219,121 @@ check_noncircular(struct lock_class *source, unsigned int depth)
  * proving that two subgraphs can be connected by a new dependency
  * without creating any illegal irq-safe -> irq-unsafe lock dependency.
  */
-static enum lock_usage_bit find_usage_bit;
-static struct lock_class *forwards_match, *backwards_match;
+
+static inline int usage_match(struct lock_list *entry, void *bit)
+{
+	return entry->class->usage_mask & (1 << (enum lock_usage_bit)bit);
+}
+
+
 
 /*
  * Find a node in the forwards-direction dependency sub-graph starting
- * at <source> that matches <find_usage_bit>.
+ * at @root->class that matches @bit.
  *
- * Return 2 if such a node exists in the subgraph, and put that node
- * into <forwards_match>.
+ * Return 0 if such a node exists in the subgraph, and put that node
+ * into *@target_entry.
  *
- * Return 1 otherwise and keep <forwards_match> unchanged.
- * Return 0 on error.
+ * Return 1 otherwise and keep *@target_entry unchanged.
+ * Return <0 on error.
  */
-static noinline int
-find_usage_forwards(struct lock_class *source, unsigned int depth)
+static int
+find_usage_forwards(struct lock_list *root, enum lock_usage_bit bit,
+			struct lock_list **target_entry)
 {
-	struct lock_list *entry;
-	int ret;
-
-	if (lockdep_dependency_visit(source, depth))
-		return 1;
-
-	if (depth > max_recursion_depth)
-		max_recursion_depth = depth;
-	if (depth >= RECURSION_LIMIT)
-		return print_infinite_recursion_bug();
+	int result;
 
 	debug_atomic_inc(&nr_find_usage_forwards_checks);
-	if (source->usage_mask & (1 << find_usage_bit)) {
-		forwards_match = source;
-		return 2;
-	}
 
-	/*
-	 * Check this lock's dependency list:
-	 */
-	list_for_each_entry(entry, &source->locks_after, entry) {
-		debug_atomic_inc(&nr_find_usage_forwards_recursions);
-		ret = find_usage_forwards(entry->class, depth+1);
-		if (ret == 2 || ret == 0)
-			return ret;
-	}
-	return 1;
+	result = __bfs_forwards(root, (void *)bit, usage_match, target_entry);
+
+	return result;
 }
 
 /*
  * Find a node in the backwards-direction dependency sub-graph starting
- * at <source> that matches <find_usage_bit>.
+ * at @root->class that matches @bit.
  *
- * Return 2 if such a node exists in the subgraph, and put that node
- * into <backwards_match>.
+ * Return 0 if such a node exists in the subgraph, and put that node
+ * into *@target_entry.
  *
- * Return 1 otherwise and keep <backwards_match> unchanged.
- * Return 0 on error.
+ * Return 1 otherwise and keep *@target_entry unchanged.
+ * Return <0 on error.
  */
-static noinline int
-find_usage_backwards(struct lock_class *source, unsigned int depth)
+static int
+find_usage_backwards(struct lock_list *root, enum lock_usage_bit bit,
+			struct lock_list **target_entry)
 {
-	struct lock_list *entry;
-	int ret;
+	int result;
 
-	if (lockdep_dependency_visit(source, depth))
-		return 1;
+	debug_atomic_inc(&nr_find_usage_backwards_checks);
 
-	if (!__raw_spin_is_locked(&lockdep_lock))
-		return DEBUG_LOCKS_WARN_ON(1);
+	result = __bfs_backwards(root, (void *)bit, usage_match, target_entry);
 
-	if (depth > max_recursion_depth)
-		max_recursion_depth = depth;
-	if (depth >= RECURSION_LIMIT)
-		return print_infinite_recursion_bug();
+	return result;
+}
 
-	debug_atomic_inc(&nr_find_usage_backwards_checks);
-	if (source->usage_mask & (1 << find_usage_bit)) {
-		backwards_match = source;
-		return 2;
-	}
+static void print_lock_class_header(struct lock_class *class, int depth)
+{
+	int bit;
 
-	if (!source && debug_locks_off_graph_unlock()) {
-		WARN_ON(1);
-		return 0;
-	}
+	printk("%*s->", depth, "");
+	print_lock_name(class);
+	printk(" ops: %lu", class->ops);
+	printk(" {\n");
 
-	/*
-	 * Check this lock's dependency list:
-	 */
-	list_for_each_entry(entry, &source->locks_before, entry) {
-		debug_atomic_inc(&nr_find_usage_backwards_recursions);
-		ret = find_usage_backwards(entry->class, depth+1);
-		if (ret == 2 || ret == 0)
-			return ret;
+	for (bit = 0; bit < LOCK_USAGE_STATES; bit++) {
+		if (class->usage_mask & (1 << bit)) {
+			int len = depth;
+
+			len += printk("%*s   %s", depth, "", usage_str[bit]);
+			len += printk(" at:\n");
+			print_stack_trace(class->usage_traces + bit, len);
+		}
 	}
-	return 1;
+	printk("%*s }\n", depth, "");
+
+	printk("%*s ... key      at: ",depth,"");
+	print_ip_sym((unsigned long)class->key);
+}
+
+/*
+ * printk the shortest lock dependencies from @start to @end in reverse order:
+ */
+static void __used
+print_shortest_lock_dependencies(struct lock_list *leaf,
+				struct lock_list *root)
+{
+	struct lock_list *entry = leaf;
+	int depth;
+
+	/*compute depth from generated tree by BFS*/
+	depth = get_lock_depth(leaf);
+
+	do {
+		print_lock_class_header(entry->class, depth);
+		printk("%*s ... acquired at:\n", depth, "");
+		print_stack_trace(&entry->trace, 2);
+		printk("\n");
+
+		if (depth == 0 && (entry != root)) {
+			printk("lockdep:%s bad BFS generated tree\n", __func__);
+			break;
+		}
+
+		entry = get_lock_parent(entry);
+		depth--;
+	} while (entry && (depth >= 0));
+
+	return;
 }
 
 static int
 print_bad_irq_dependency(struct task_struct *curr,
+			 struct lock_list *prev_root,
+			 struct lock_list *next_root,
+			 struct lock_list *backwards_entry,
+			 struct lock_list *forwards_entry,
 			 struct held_lock *prev,
 			 struct held_lock *next,
 			 enum lock_usage_bit bit1,
@@ -1215,26 +1366,32 @@ print_bad_irq_dependency(struct task_struct *curr,
 
 	printk("\nbut this new dependency connects a %s-irq-safe lock:\n",
 		irqclass);
-	print_lock_name(backwards_match);
+	print_lock_name(backwards_entry->class);
 	printk("\n... which became %s-irq-safe at:\n", irqclass);
 
-	print_stack_trace(backwards_match->usage_traces + bit1, 1);
+	print_stack_trace(backwards_entry->class->usage_traces + bit1, 1);
 
 	printk("\nto a %s-irq-unsafe lock:\n", irqclass);
-	print_lock_name(forwards_match);
+	print_lock_name(forwards_entry->class);
 	printk("\n... which became %s-irq-unsafe at:\n", irqclass);
 	printk("...");
 
-	print_stack_trace(forwards_match->usage_traces + bit2, 1);
+	print_stack_trace(forwards_entry->class->usage_traces + bit2, 1);
 
 	printk("\nother info that might help us debug this:\n\n");
 	lockdep_print_held_locks(curr);
 
-	printk("\nthe %s-irq-safe lock's dependencies:\n", irqclass);
-	print_lock_dependencies(backwards_match, 0);
+	printk("\nthe dependencies between %s-irq-safe lock", irqclass);
+	printk(" and the holding lock:\n");
+	if (!save_trace(&prev_root->trace))
+		return 0;
+	print_shortest_lock_dependencies(backwards_entry, prev_root);
 
-	printk("\nthe %s-irq-unsafe lock's dependencies:\n", irqclass);
-	print_lock_dependencies(forwards_match, 0);
+	printk("\nthe dependencies between the lock to be acquired");
+	printk(" and %s-irq-unsafe lock:\n", irqclass);
+	if (!save_trace(&next_root->trace))
+		return 0;
+	print_shortest_lock_dependencies(forwards_entry, next_root);
 
 	printk("\nstack backtrace:\n");
 	dump_stack();
@@ -1248,19 +1405,30 @@ check_usage(struct task_struct *curr, struct held_lock *prev,
 	    enum lock_usage_bit bit_forwards, const char *irqclass)
 {
 	int ret;
+	struct lock_list this, that;
+	struct lock_list *uninitialized_var(target_entry);
+	struct lock_list *uninitialized_var(target_entry1);
+
+	this.parent = NULL;
 
-	find_usage_bit = bit_backwards;
-	/* fills in <backwards_match> */
-	ret = find_usage_backwards(hlock_class(prev), 0);
-	if (!ret || ret == 1)
+	this.class = hlock_class(prev);
+	ret = find_usage_backwards(&this, bit_backwards, &target_entry);
+	if (ret < 0)
+		return print_bfs_bug(ret);
+	if (ret == 1)
 		return ret;
 
-	find_usage_bit = bit_forwards;
-	ret = find_usage_forwards(hlock_class(next), 0);
-	if (!ret || ret == 1)
+	that.parent = NULL;
+	that.class = hlock_class(next);
+	ret = find_usage_forwards(&that, bit_forwards, &target_entry1);
+	if (ret < 0)
+		return print_bfs_bug(ret);
+	if (ret == 1)
 		return ret;
-	/* ret == 2 */
-	return print_bad_irq_dependency(curr, prev, next,
+
+	return print_bad_irq_dependency(curr, &this, &that,
+			target_entry, target_entry1,
+			prev, next,
 			bit_backwards, bit_forwards, irqclass);
 }
 
@@ -1472,6 +1640,8 @@ check_prev_add(struct task_struct *curr, struct held_lock *prev,
 {
 	struct lock_list *entry;
 	int ret;
+	struct lock_list this;
+	struct lock_list *uninitialized_var(target_entry);
 
 	/*
 	 * Prove that the new <prev> -> <next> dependency would not
@@ -1482,10 +1652,13 @@ check_prev_add(struct task_struct *curr, struct held_lock *prev,
 	 * We are using global variables to control the recursion, to
 	 * keep the stackframe size of the recursive functions low:
 	 */
-	check_source = next;
-	check_target = prev;
-	if (!(check_noncircular(hlock_class(next), 0)))
-		return print_circular_bug_tail();
+	this.class = hlock_class(next);
+	this.parent = NULL;
+	ret = check_noncircular(&this, hlock_class(prev), &target_entry);
+	if (unlikely(!ret))
+		return print_circular_bug(&this, target_entry, next, prev);
+	else if (unlikely(ret < 0))
+		return print_bfs_bug(ret);
 
 	if (!check_prev_add_irq(curr, prev, next))
 		return 0;
@@ -1884,7 +2057,8 @@ static int mark_lock(struct task_struct *curr, struct held_lock *this,
  * print irq inversion bug:
  */
 static int
-print_irq_inversion_bug(struct task_struct *curr, struct lock_class *other,
+print_irq_inversion_bug(struct task_struct *curr,
+			struct lock_list *root, struct lock_list *other,
 			struct held_lock *this, int forwards,
 			const char *irqclass)
 {
@@ -1902,17 +2076,16 @@ print_irq_inversion_bug(struct task_struct *curr, struct lock_class *other,
 		printk("but this lock took another, %s-unsafe lock in the past:\n", irqclass);
 	else
 		printk("but this lock was taken by another, %s-safe lock in the past:\n", irqclass);
-	print_lock_name(other);
+	print_lock_name(other->class);
 	printk("\n\nand interrupts could create inverse lock ordering between them.\n\n");
 
 	printk("\nother info that might help us debug this:\n");
 	lockdep_print_held_locks(curr);
 
-	printk("\nthe first lock's dependencies:\n");
-	print_lock_dependencies(hlock_class(this), 0);
-
-	printk("\nthe second lock's dependencies:\n");
-	print_lock_dependencies(other, 0);
+	printk("\nthe shortest dependencies between 2nd lock and 1st lock:\n");
+	if (!save_trace(&root->trace))
+		return 0;
+	print_shortest_lock_dependencies(other, root);
 
 	printk("\nstack backtrace:\n");
 	dump_stack();
@@ -1929,14 +2102,19 @@ check_usage_forwards(struct task_struct *curr, struct held_lock *this,
 		     enum lock_usage_bit bit, const char *irqclass)
 {
 	int ret;
-
-	find_usage_bit = bit;
-	/* fills in <forwards_match> */
-	ret = find_usage_forwards(hlock_class(this), 0);
-	if (!ret || ret == 1)
+	struct lock_list root;
+	struct lock_list *uninitialized_var(target_entry);
+
+	root.parent = NULL;
+	root.class = hlock_class(this);
+	ret = find_usage_forwards(&root, bit, &target_entry);
+	if (ret < 0)
+		return print_bfs_bug(ret);
+	if (ret == 1)
 		return ret;
 
-	return print_irq_inversion_bug(curr, forwards_match, this, 1, irqclass);
+	return print_irq_inversion_bug(curr, &root, target_entry,
+					this, 1, irqclass);
 }
 
 /*
@@ -1948,14 +2126,19 @@ check_usage_backwards(struct task_struct *curr, struct held_lock *this,
 		      enum lock_usage_bit bit, const char *irqclass)
 {
 	int ret;
-
-	find_usage_bit = bit;
-	/* fills in <backwards_match> */
-	ret = find_usage_backwards(hlock_class(this), 0);
-	if (!ret || ret == 1)
+	struct lock_list root;
+	struct lock_list *uninitialized_var(target_entry);
+
+	root.parent = NULL;
+	root.class = hlock_class(this);
+	ret = find_usage_backwards(&root, bit, &target_entry);
+	if (ret < 0)
+		return print_bfs_bug(ret);
+	if (ret == 1)
 		return ret;
 
-	return print_irq_inversion_bug(curr, backwards_match, this, 0, irqclass);
+	return print_irq_inversion_bug(curr, &root, target_entry,
+					this, 1, irqclass);
 }
 
 void print_irqtrace_events(struct task_struct *curr)
@@ -2530,13 +2713,15 @@ EXPORT_SYMBOL_GPL(lockdep_init_map);
  */
 static int __lock_acquire(struct lockdep_map *lock, unsigned int subclass,
 			  int trylock, int read, int check, int hardirqs_off,
-			  struct lockdep_map *nest_lock, unsigned long ip)
+			  struct lockdep_map *nest_lock, unsigned long ip,
+			  int references)
 {
 	struct task_struct *curr = current;
 	struct lock_class *class = NULL;
 	struct held_lock *hlock;
 	unsigned int depth, id;
 	int chain_head = 0;
+	int class_idx;
 	u64 chain_key;
 
 	if (!prove_locking)
@@ -2584,10 +2769,24 @@ static int __lock_acquire(struct lockdep_map *lock, unsigned int subclass,
 	if (DEBUG_LOCKS_WARN_ON(depth >= MAX_LOCK_DEPTH))
 		return 0;
 
+	class_idx = class - lock_classes + 1;
+
+	if (depth) {
+		hlock = curr->held_locks + depth - 1;
+		if (hlock->class_idx == class_idx && nest_lock) {
+			if (hlock->references)
+				hlock->references++;
+			else
+				hlock->references = 2;
+
+			return 1;
+		}
+	}
+
 	hlock = curr->held_locks + depth;
 	if (DEBUG_LOCKS_WARN_ON(!class))
 		return 0;
-	hlock->class_idx = class - lock_classes + 1;
+	hlock->class_idx = class_idx;
 	hlock->acquire_ip = ip;
 	hlock->instance = lock;
 	hlock->nest_lock = nest_lock;
@@ -2595,9 +2794,10 @@ static int __lock_acquire(struct lockdep_map *lock, unsigned int subclass,
 	hlock->read = read;
 	hlock->check = check;
 	hlock->hardirqs_off = !!hardirqs_off;
+	hlock->references = references;
 #ifdef CONFIG_LOCK_STAT
 	hlock->waittime_stamp = 0;
-	hlock->holdtime_stamp = sched_clock();
+	hlock->holdtime_stamp = lockstat_clock();
 #endif
 
 	if (check == 2 && !mark_irqflags(curr, hlock))
@@ -2703,6 +2903,30 @@ static int check_unlock(struct task_struct *curr, struct lockdep_map *lock,
 	return 1;
 }
 
+static int match_held_lock(struct held_lock *hlock, struct lockdep_map *lock)
+{
+	if (hlock->instance == lock)
+		return 1;
+
+	if (hlock->references) {
+		struct lock_class *class = lock->class_cache;
+
+		if (!class)
+			class = look_up_lock_class(lock, 0);
+
+		if (DEBUG_LOCKS_WARN_ON(!class))
+			return 0;
+
+		if (DEBUG_LOCKS_WARN_ON(!hlock->nest_lock))
+			return 0;
+
+		if (hlock->class_idx == class - lock_classes + 1)
+			return 1;
+	}
+
+	return 0;
+}
+
 static int
 __lock_set_class(struct lockdep_map *lock, const char *name,
 		 struct lock_class_key *key, unsigned int subclass,
@@ -2726,7 +2950,7 @@ __lock_set_class(struct lockdep_map *lock, const char *name,
 		 */
 		if (prev_hlock && prev_hlock->irq_context != hlock->irq_context)
 			break;
-		if (hlock->instance == lock)
+		if (match_held_lock(hlock, lock))
 			goto found_it;
 		prev_hlock = hlock;
 	}
@@ -2745,7 +2969,8 @@ found_it:
 		if (!__lock_acquire(hlock->instance,
 			hlock_class(hlock)->subclass, hlock->trylock,
 				hlock->read, hlock->check, hlock->hardirqs_off,
-				hlock->nest_lock, hlock->acquire_ip))
+				hlock->nest_lock, hlock->acquire_ip,
+				hlock->references))
 			return 0;
 	}
 
@@ -2784,20 +3009,34 @@ lock_release_non_nested(struct task_struct *curr,
 		 */
 		if (prev_hlock && prev_hlock->irq_context != hlock->irq_context)
 			break;
-		if (hlock->instance == lock)
+		if (match_held_lock(hlock, lock))
 			goto found_it;
 		prev_hlock = hlock;
 	}
 	return print_unlock_inbalance_bug(curr, lock, ip);
 
 found_it:
-	lock_release_holdtime(hlock);
+	if (hlock->instance == lock)
+		lock_release_holdtime(hlock);
+
+	if (hlock->references) {
+		hlock->references--;
+		if (hlock->references) {
+			/*
+			 * We had, and after removing one, still have
+			 * references, the current lock stack is still
+			 * valid. We're done!
+			 */
+			return 1;
+		}
+	}
 
 	/*
 	 * We have the right lock to unlock, 'hlock' points to it.
 	 * Now we remove it from the stack, and add back the other
 	 * entries (if any), recalculating the hash along the way:
 	 */
+
 	curr->lockdep_depth = i;
 	curr->curr_chain_key = hlock->prev_chain_key;
 
@@ -2806,7 +3045,8 @@ found_it:
 		if (!__lock_acquire(hlock->instance,
 			hlock_class(hlock)->subclass, hlock->trylock,
 				hlock->read, hlock->check, hlock->hardirqs_off,
-				hlock->nest_lock, hlock->acquire_ip))
+				hlock->nest_lock, hlock->acquire_ip,
+				hlock->references))
 			return 0;
 	}
 
@@ -2836,7 +3076,7 @@ static int lock_release_nested(struct task_struct *curr,
 	/*
 	 * Is the unlock non-nested:
 	 */
-	if (hlock->instance != lock)
+	if (hlock->instance != lock || hlock->references)
 		return lock_release_non_nested(curr, lock, ip);
 	curr->lockdep_depth--;
 
@@ -2881,6 +3121,21 @@ __lock_release(struct lockdep_map *lock, int nested, unsigned long ip)
 	check_chain_key(curr);
 }
 
+static int __lock_is_held(struct lockdep_map *lock)
+{
+	struct task_struct *curr = current;
+	int i;
+
+	for (i = 0; i < curr->lockdep_depth; i++) {
+		struct held_lock *hlock = curr->held_locks + i;
+
+		if (match_held_lock(hlock, lock))
+			return 1;
+	}
+
+	return 0;
+}
+
 /*
  * Check whether we follow the irq-flags state precisely:
  */
@@ -2957,7 +3212,7 @@ void lock_acquire(struct lockdep_map *lock, unsigned int subclass,
 
 	current->lockdep_recursion = 1;
 	__lock_acquire(lock, subclass, trylock, read, check,
-		       irqs_disabled_flags(flags), nest_lock, ip);
+		       irqs_disabled_flags(flags), nest_lock, ip, 0);
 	current->lockdep_recursion = 0;
 	raw_local_irq_restore(flags);
 }
@@ -2982,6 +3237,26 @@ void lock_release(struct lockdep_map *lock, int nested,
 }
 EXPORT_SYMBOL_GPL(lock_release);
 
+int lock_is_held(struct lockdep_map *lock)
+{
+	unsigned long flags;
+	int ret = 0;
+
+	if (unlikely(current->lockdep_recursion))
+		return ret;
+
+	raw_local_irq_save(flags);
+	check_flags(flags);
+
+	current->lockdep_recursion = 1;
+	ret = __lock_is_held(lock);
+	current->lockdep_recursion = 0;
+	raw_local_irq_restore(flags);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(lock_is_held);
+
 void lockdep_set_current_reclaim_state(gfp_t gfp_mask)
 {
 	current->lockdep_reclaim_gfp = gfp_mask;
@@ -3041,7 +3316,7 @@ __lock_contended(struct lockdep_map *lock, unsigned long ip)
 		 */
 		if (prev_hlock && prev_hlock->irq_context != hlock->irq_context)
 			break;
-		if (hlock->instance == lock)
+		if (match_held_lock(hlock, lock))
 			goto found_it;
 		prev_hlock = hlock;
 	}
@@ -3049,7 +3324,10 @@ __lock_contended(struct lockdep_map *lock, unsigned long ip)
 	return;
 
 found_it:
-	hlock->waittime_stamp = sched_clock();
+	if (hlock->instance != lock)
+		return;
+
+	hlock->waittime_stamp = lockstat_clock();
 
 	contention_point = lock_point(hlock_class(hlock)->contention_point, ip);
 	contending_point = lock_point(hlock_class(hlock)->contending_point,
@@ -3072,8 +3350,7 @@ __lock_acquired(struct lockdep_map *lock, unsigned long ip)
 	struct held_lock *hlock, *prev_hlock;
 	struct lock_class_stats *stats;
 	unsigned int depth;
-	u64 now;
-	s64 waittime = 0;
+	u64 now, waittime = 0;
 	int i, cpu;
 
 	depth = curr->lockdep_depth;
@@ -3088,7 +3365,7 @@ __lock_acquired(struct lockdep_map *lock, unsigned long ip)
 		 */
 		if (prev_hlock && prev_hlock->irq_context != hlock->irq_context)
 			break;
-		if (hlock->instance == lock)
+		if (match_held_lock(hlock, lock))
 			goto found_it;
 		prev_hlock = hlock;
 	}
@@ -3096,9 +3373,12 @@ __lock_acquired(struct lockdep_map *lock, unsigned long ip)
 	return;
 
 found_it:
+	if (hlock->instance != lock)
+		return;
+
 	cpu = smp_processor_id();
 	if (hlock->waittime_stamp) {
-		now = sched_clock();
+		now = lockstat_clock();
 		waittime = now - hlock->waittime_stamp;
 		hlock->holdtime_stamp = now;
 	}
@@ -3326,7 +3606,12 @@ void __init lockdep_info(void)
 		sizeof(struct list_head) * CLASSHASH_SIZE +
 		sizeof(struct lock_list) * MAX_LOCKDEP_ENTRIES +
 		sizeof(struct lock_chain) * MAX_LOCKDEP_CHAINS +
-		sizeof(struct list_head) * CHAINHASH_SIZE) / 1024);
+		sizeof(struct list_head) * CHAINHASH_SIZE
+#ifdef CONFIG_PROVE_LOCKING
+		+ sizeof(struct circular_queue)
+#endif
+		) / 1024
+		);
 
 	printk(" per task-struct memory footprint: %lu bytes\n",
 		sizeof(struct held_lock) * MAX_LOCK_DEPTH);
diff --git a/kernel/lockdep_internals.h b/kernel/lockdep_internals.h
index 699a2ac3a0d7..a2ee95ad1313 100644
--- a/kernel/lockdep_internals.h
+++ b/kernel/lockdep_internals.h
@@ -91,6 +91,8 @@ extern unsigned int nr_process_chains;
 extern unsigned int max_lockdep_depth;
 extern unsigned int max_recursion_depth;
 
+extern unsigned int max_bfs_queue_depth;
+
 #ifdef CONFIG_PROVE_LOCKING
 extern unsigned long lockdep_count_forward_deps(struct lock_class *);
 extern unsigned long lockdep_count_backward_deps(struct lock_class *);
diff --git a/kernel/lockdep_proc.c b/kernel/lockdep_proc.c
index e94caa666dba..d4aba4f3584c 100644
--- a/kernel/lockdep_proc.c
+++ b/kernel/lockdep_proc.c
@@ -25,38 +25,12 @@
 
 static void *l_next(struct seq_file *m, void *v, loff_t *pos)
 {
-	struct lock_class *class;
-
-	(*pos)++;
-
-	if (v == SEQ_START_TOKEN)
-		class = m->private;
-	else {
-		class = v;
-
-		if (class->lock_entry.next != &all_lock_classes)
-			class = list_entry(class->lock_entry.next,
-					   struct lock_class, lock_entry);
-		else
-			class = NULL;
-	}
-
-	return class;
+	return seq_list_next(v, &all_lock_classes, pos);
 }
 
 static void *l_start(struct seq_file *m, loff_t *pos)
 {
-	struct lock_class *class;
-	loff_t i = 0;
-
-	if (*pos == 0)
-		return SEQ_START_TOKEN;
-
-	list_for_each_entry(class, &all_lock_classes, lock_entry) {
-		if (++i == *pos)
-		return class;
-	}
-	return NULL;
+	return seq_list_start_head(&all_lock_classes, *pos);
 }
 
 static void l_stop(struct seq_file *m, void *v)
@@ -82,11 +56,11 @@ static void print_name(struct seq_file *m, struct lock_class *class)
 
 static int l_show(struct seq_file *m, void *v)
 {
-	struct lock_class *class = v;
+	struct lock_class *class = list_entry(v, struct lock_class, lock_entry);
 	struct lock_list *entry;
 	char usage[LOCK_USAGE_CHARS];
 
-	if (v == SEQ_START_TOKEN) {
+	if (v == &all_lock_classes) {
 		seq_printf(m, "all lock classes:\n");
 		return 0;
 	}
@@ -128,17 +102,7 @@ static const struct seq_operations lockdep_ops = {
 
 static int lockdep_open(struct inode *inode, struct file *file)
 {
-	int res = seq_open(file, &lockdep_ops);
-	if (!res) {
-		struct seq_file *m = file->private_data;
-
-		if (!list_empty(&all_lock_classes))
-			m->private = list_entry(all_lock_classes.next,
-					struct lock_class, lock_entry);
-		else
-			m->private = NULL;
-	}
-	return res;
+	return seq_open(file, &lockdep_ops);
 }
 
 static const struct file_operations proc_lockdep_operations = {
@@ -149,37 +113,23 @@ static const struct file_operations proc_lockdep_operations = {
 };
 
 #ifdef CONFIG_PROVE_LOCKING
-static void *lc_next(struct seq_file *m, void *v, loff_t *pos)
-{
-	struct lock_chain *chain;
-
-	(*pos)++;
-
-	if (v == SEQ_START_TOKEN)
-		chain = m->private;
-	else {
-		chain = v;
-
-		if (*pos < nr_lock_chains)
-			chain = lock_chains + *pos;
-		else
-			chain = NULL;
-	}
-
-	return chain;
-}
-
 static void *lc_start(struct seq_file *m, loff_t *pos)
 {
 	if (*pos == 0)
 		return SEQ_START_TOKEN;
 
-	if (*pos < nr_lock_chains)
-		return lock_chains + *pos;
+	if (*pos - 1 < nr_lock_chains)
+		return lock_chains + (*pos - 1);
 
 	return NULL;
 }
 
+static void *lc_next(struct seq_file *m, void *v, loff_t *pos)
+{
+	(*pos)++;
+	return lc_start(m, pos);
+}
+
 static void lc_stop(struct seq_file *m, void *v)
 {
 }
@@ -220,16 +170,7 @@ static const struct seq_operations lockdep_chains_ops = {
 
 static int lockdep_chains_open(struct inode *inode, struct file *file)
 {
-	int res = seq_open(file, &lockdep_chains_ops);
-	if (!res) {
-		struct seq_file *m = file->private_data;
-
-		if (nr_lock_chains)
-			m->private = lock_chains;
-		else
-			m->private = NULL;
-	}
-	return res;
+	return seq_open(file, &lockdep_chains_ops);
 }
 
 static const struct file_operations proc_lockdep_chains_operations = {
@@ -258,16 +199,10 @@ static void lockdep_stats_debug_show(struct seq_file *m)
 		debug_atomic_read(&chain_lookup_hits));
 	seq_printf(m, " cyclic checks:                 %11u\n",
 		debug_atomic_read(&nr_cyclic_checks));
-	seq_printf(m, " cyclic-check recursions:       %11u\n",
-		debug_atomic_read(&nr_cyclic_check_recursions));
 	seq_printf(m, " find-mask forwards checks:     %11u\n",
 		debug_atomic_read(&nr_find_usage_forwards_checks));
-	seq_printf(m, " find-mask forwards recursions: %11u\n",
-		debug_atomic_read(&nr_find_usage_forwards_recursions));
 	seq_printf(m, " find-mask backwards checks:    %11u\n",
 		debug_atomic_read(&nr_find_usage_backwards_checks));
-	seq_printf(m, " find-mask backwards recursions:%11u\n",
-		debug_atomic_read(&nr_find_usage_backwards_recursions));
 
 	seq_printf(m, " hardirq on events:             %11u\n", hi1);
 	seq_printf(m, " hardirq off events:            %11u\n", hi2);
@@ -409,8 +344,10 @@ static int lockdep_stats_show(struct seq_file *m, void *v)
 			nr_unused);
 	seq_printf(m, " max locking depth:             %11u\n",
 			max_lockdep_depth);
-	seq_printf(m, " max recursion depth:           %11u\n",
-			max_recursion_depth);
+#ifdef CONFIG_PROVE_LOCKING
+	seq_printf(m, " max bfs queue depth:           %11u\n",
+			max_bfs_queue_depth);
+#endif
 	lockdep_stats_debug_show(m);
 	seq_printf(m, " debug_locks:                   %11u\n",
 			debug_locks);
@@ -438,7 +375,6 @@ struct lock_stat_data {
 };
 
 struct lock_stat_seq {
-	struct lock_stat_data *iter;
 	struct lock_stat_data *iter_end;
 	struct lock_stat_data stats[MAX_LOCKDEP_KEYS];
 };
@@ -626,34 +562,22 @@ static void seq_header(struct seq_file *m)
 static void *ls_start(struct seq_file *m, loff_t *pos)
 {
 	struct lock_stat_seq *data = m->private;
+	struct lock_stat_data *iter;
 
 	if (*pos == 0)
 		return SEQ_START_TOKEN;
 
-	data->iter = data->stats + *pos;
-	if (data->iter >= data->iter_end)
-		data->iter = NULL;
+	iter = data->stats + (*pos - 1);
+	if (iter >= data->iter_end)
+		iter = NULL;
 
-	return data->iter;
+	return iter;
 }
 
 static void *ls_next(struct seq_file *m, void *v, loff_t *pos)
 {
-	struct lock_stat_seq *data = m->private;
-
 	(*pos)++;
-
-	if (v == SEQ_START_TOKEN)
-		data->iter = data->stats;
-	else {
-		data->iter = v;
-		data->iter++;
-	}
-
-	if (data->iter == data->iter_end)
-		data->iter = NULL;
-
-	return data->iter;
+	return ls_start(m, pos);
 }
 
 static void ls_stop(struct seq_file *m, void *v)
@@ -670,7 +594,7 @@ static int ls_show(struct seq_file *m, void *v)
 	return 0;
 }
 
-static struct seq_operations lockstat_ops = {
+static const struct seq_operations lockstat_ops = {
 	.start	= ls_start,
 	.next	= ls_next,
 	.stop	= ls_stop,
@@ -691,7 +615,6 @@ static int lock_stat_open(struct inode *inode, struct file *file)
 		struct lock_stat_data *iter = data->stats;
 		struct seq_file *m = file->private_data;
 
-		data->iter = iter;
 		list_for_each_entry(class, &all_lock_classes, lock_entry) {
 			iter->class = class;
 			iter->stats = lock_stats(class);
@@ -699,7 +622,7 @@ static int lock_stat_open(struct inode *inode, struct file *file)
 		}
 		data->iter_end = iter;
 
-		sort(data->stats, data->iter_end - data->iter,
+		sort(data->stats, data->iter_end - data->stats,
 				sizeof(struct lock_stat_data),
 				lock_stat_cmp, NULL);
 
@@ -734,7 +657,6 @@ static int lock_stat_release(struct inode *inode, struct file *file)
 	struct seq_file *seq = file->private_data;
 
 	vfree(seq->private);
-	seq->private = NULL;
 	return seq_release(inode, file);
 }
 
diff --git a/kernel/marker.c b/kernel/marker.c
deleted file mode 100644
index ea54f2647868..000000000000
--- a/kernel/marker.c
+++ /dev/null
@@ -1,930 +0,0 @@
-/*
- * Copyright (C) 2007 Mathieu Desnoyers
- *
- * 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.
- */
-#include <linux/module.h>
-#include <linux/mutex.h>
-#include <linux/types.h>
-#include <linux/jhash.h>
-#include <linux/list.h>
-#include <linux/rcupdate.h>
-#include <linux/marker.h>
-#include <linux/err.h>
-#include <linux/slab.h>
-
-extern struct marker __start___markers[];
-extern struct marker __stop___markers[];
-
-/* Set to 1 to enable marker debug output */
-static const int marker_debug;
-
-/*
- * markers_mutex nests inside module_mutex. Markers mutex protects the builtin
- * and module markers and the hash table.
- */
-static DEFINE_MUTEX(markers_mutex);
-
-/*
- * Marker hash table, containing the active markers.
- * Protected by module_mutex.
- */
-#define MARKER_HASH_BITS 6
-#define MARKER_TABLE_SIZE (1 << MARKER_HASH_BITS)
-static struct hlist_head marker_table[MARKER_TABLE_SIZE];
-
-/*
- * Note about RCU :
- * It is used to make sure every handler has finished using its private data
- * between two consecutive operation (add or remove) on a given marker.  It is
- * also used to delay the free of multiple probes array until a quiescent state
- * is reached.
- * marker entries modifications are protected by the markers_mutex.
- */
-struct marker_entry {
-	struct hlist_node hlist;
-	char *format;
-			/* Probe wrapper */
-	void (*call)(const struct marker *mdata, void *call_private, ...);
-	struct marker_probe_closure single;
-	struct marker_probe_closure *multi;
-	int refcount;	/* Number of times armed. 0 if disarmed. */
-	struct rcu_head rcu;
-	void *oldptr;
-	int rcu_pending;
-	unsigned char ptype:1;
-	unsigned char format_allocated:1;
-	char name[0];	/* Contains name'\0'format'\0' */
-};
-
-/**
- * __mark_empty_function - Empty probe callback
- * @probe_private: probe private data
- * @call_private: call site private data
- * @fmt: format string
- * @...: variable argument list
- *
- * Empty callback provided as a probe to the markers. By providing this to a
- * disabled marker, we make sure the  execution flow is always valid even
- * though the function pointer change and the marker enabling are two distinct
- * operations that modifies the execution flow of preemptible code.
- */
-notrace void __mark_empty_function(void *probe_private, void *call_private,
-	const char *fmt, va_list *args)
-{
-}
-EXPORT_SYMBOL_GPL(__mark_empty_function);
-
-/*
- * marker_probe_cb Callback that prepares the variable argument list for probes.
- * @mdata: pointer of type struct marker
- * @call_private: caller site private data
- * @...:  Variable argument list.
- *
- * Since we do not use "typical" pointer based RCU in the 1 argument case, we
- * need to put a full smp_rmb() in this branch. This is why we do not use
- * rcu_dereference() for the pointer read.
- */
-notrace void marker_probe_cb(const struct marker *mdata,
-		void *call_private, ...)
-{
-	va_list args;
-	char ptype;
-
-	/*
-	 * rcu_read_lock_sched does two things : disabling preemption to make
-	 * sure the teardown of the callbacks can be done correctly when they
-	 * are in modules and they insure RCU read coherency.
-	 */
-	rcu_read_lock_sched_notrace();
-	ptype = mdata->ptype;
-	if (likely(!ptype)) {
-		marker_probe_func *func;
-		/* Must read the ptype before ptr. They are not data dependant,
-		 * so we put an explicit smp_rmb() here. */
-		smp_rmb();
-		func = mdata->single.func;
-		/* Must read the ptr before private data. They are not data
-		 * dependant, so we put an explicit smp_rmb() here. */
-		smp_rmb();
-		va_start(args, call_private);
-		func(mdata->single.probe_private, call_private, mdata->format,
-			&args);
-		va_end(args);
-	} else {
-		struct marker_probe_closure *multi;
-		int i;
-		/*
-		 * Read mdata->ptype before mdata->multi.
-		 */
-		smp_rmb();
-		multi = mdata->multi;
-		/*
-		 * multi points to an array, therefore accessing the array
-		 * depends on reading multi. However, even in this case,
-		 * we must insure that the pointer is read _before_ the array
-		 * data. Same as rcu_dereference, but we need a full smp_rmb()
-		 * in the fast path, so put the explicit barrier here.
-		 */
-		smp_read_barrier_depends();
-		for (i = 0; multi[i].func; i++) {
-			va_start(args, call_private);
-			multi[i].func(multi[i].probe_private, call_private,
-				mdata->format, &args);
-			va_end(args);
-		}
-	}
-	rcu_read_unlock_sched_notrace();
-}
-EXPORT_SYMBOL_GPL(marker_probe_cb);
-
-/*
- * marker_probe_cb Callback that does not prepare the variable argument list.
- * @mdata: pointer of type struct marker
- * @call_private: caller site private data
- * @...:  Variable argument list.
- *
- * Should be connected to markers "MARK_NOARGS".
- */
-static notrace void marker_probe_cb_noarg(const struct marker *mdata,
-		void *call_private, ...)
-{
-	va_list args;	/* not initialized */
-	char ptype;
-
-	rcu_read_lock_sched_notrace();
-	ptype = mdata->ptype;
-	if (likely(!ptype)) {
-		marker_probe_func *func;
-		/* Must read the ptype before ptr. They are not data dependant,
-		 * so we put an explicit smp_rmb() here. */
-		smp_rmb();
-		func = mdata->single.func;
-		/* Must read the ptr before private data. They are not data
-		 * dependant, so we put an explicit smp_rmb() here. */
-		smp_rmb();
-		func(mdata->single.probe_private, call_private, mdata->format,
-			&args);
-	} else {
-		struct marker_probe_closure *multi;
-		int i;
-		/*
-		 * Read mdata->ptype before mdata->multi.
-		 */
-		smp_rmb();
-		multi = mdata->multi;
-		/*
-		 * multi points to an array, therefore accessing the array
-		 * depends on reading multi. However, even in this case,
-		 * we must insure that the pointer is read _before_ the array
-		 * data. Same as rcu_dereference, but we need a full smp_rmb()
-		 * in the fast path, so put the explicit barrier here.
-		 */
-		smp_read_barrier_depends();
-		for (i = 0; multi[i].func; i++)
-			multi[i].func(multi[i].probe_private, call_private,
-				mdata->format, &args);
-	}
-	rcu_read_unlock_sched_notrace();
-}
-
-static void free_old_closure(struct rcu_head *head)
-{
-	struct marker_entry *entry = container_of(head,
-		struct marker_entry, rcu);
-	kfree(entry->oldptr);
-	/* Make sure we free the data before setting the pending flag to 0 */
-	smp_wmb();
-	entry->rcu_pending = 0;
-}
-
-static void debug_print_probes(struct marker_entry *entry)
-{
-	int i;
-
-	if (!marker_debug)
-		return;
-
-	if (!entry->ptype) {
-		printk(KERN_DEBUG "Single probe : %p %p\n",
-			entry->single.func,
-			entry->single.probe_private);
-	} else {
-		for (i = 0; entry->multi[i].func; i++)
-			printk(KERN_DEBUG "Multi probe %d : %p %p\n", i,
-				entry->multi[i].func,
-				entry->multi[i].probe_private);
-	}
-}
-
-static struct marker_probe_closure *
-marker_entry_add_probe(struct marker_entry *entry,
-		marker_probe_func *probe, void *probe_private)
-{
-	int nr_probes = 0;
-	struct marker_probe_closure *old, *new;
-
-	WARN_ON(!probe);
-
-	debug_print_probes(entry);
-	old = entry->multi;
-	if (!entry->ptype) {
-		if (entry->single.func == probe &&
-				entry->single.probe_private == probe_private)
-			return ERR_PTR(-EBUSY);
-		if (entry->single.func == __mark_empty_function) {
-			/* 0 -> 1 probes */
-			entry->single.func = probe;
-			entry->single.probe_private = probe_private;
-			entry->refcount = 1;
-			entry->ptype = 0;
-			debug_print_probes(entry);
-			return NULL;
-		} else {
-			/* 1 -> 2 probes */
-			nr_probes = 1;
-			old = NULL;
-		}
-	} else {
-		/* (N -> N+1), (N != 0, 1) probes */
-		for (nr_probes = 0; old[nr_probes].func; nr_probes++)
-			if (old[nr_probes].func == probe
-					&& old[nr_probes].probe_private
-						== probe_private)
-				return ERR_PTR(-EBUSY);
-	}
-	/* + 2 : one for new probe, one for NULL func */
-	new = kzalloc((nr_probes + 2) * sizeof(struct marker_probe_closure),
-			GFP_KERNEL);
-	if (new == NULL)
-		return ERR_PTR(-ENOMEM);
-	if (!old)
-		new[0] = entry->single;
-	else
-		memcpy(new, old,
-			nr_probes * sizeof(struct marker_probe_closure));
-	new[nr_probes].func = probe;
-	new[nr_probes].probe_private = probe_private;
-	entry->refcount = nr_probes + 1;
-	entry->multi = new;
-	entry->ptype = 1;
-	debug_print_probes(entry);
-	return old;
-}
-
-static struct marker_probe_closure *
-marker_entry_remove_probe(struct marker_entry *entry,
-		marker_probe_func *probe, void *probe_private)
-{
-	int nr_probes = 0, nr_del = 0, i;
-	struct marker_probe_closure *old, *new;
-
-	old = entry->multi;
-
-	debug_print_probes(entry);
-	if (!entry->ptype) {
-		/* 0 -> N is an error */
-		WARN_ON(entry->single.func == __mark_empty_function);
-		/* 1 -> 0 probes */
-		WARN_ON(probe && entry->single.func != probe);
-		WARN_ON(entry->single.probe_private != probe_private);
-		entry->single.func = __mark_empty_function;
-		entry->refcount = 0;
-		entry->ptype = 0;
-		debug_print_probes(entry);
-		return NULL;
-	} else {
-		/* (N -> M), (N > 1, M >= 0) probes */
-		for (nr_probes = 0; old[nr_probes].func; nr_probes++) {
-			if ((!probe || old[nr_probes].func == probe)
-					&& old[nr_probes].probe_private
-						== probe_private)
-				nr_del++;
-		}
-	}
-
-	if (nr_probes - nr_del == 0) {
-		/* N -> 0, (N > 1) */
-		entry->single.func = __mark_empty_function;
-		entry->refcount = 0;
-		entry->ptype = 0;
-	} else if (nr_probes - nr_del == 1) {
-		/* N -> 1, (N > 1) */
-		for (i = 0; old[i].func; i++)
-			if ((probe && old[i].func != probe) ||
-					old[i].probe_private != probe_private)
-				entry->single = old[i];
-		entry->refcount = 1;
-		entry->ptype = 0;
-	} else {
-		int j = 0;
-		/* N -> M, (N > 1, M > 1) */
-		/* + 1 for NULL */
-		new = kzalloc((nr_probes - nr_del + 1)
-			* sizeof(struct marker_probe_closure), GFP_KERNEL);
-		if (new == NULL)
-			return ERR_PTR(-ENOMEM);
-		for (i = 0; old[i].func; i++)
-			if ((probe && old[i].func != probe) ||
-					old[i].probe_private != probe_private)
-				new[j++] = old[i];
-		entry->refcount = nr_probes - nr_del;
-		entry->ptype = 1;
-		entry->multi = new;
-	}
-	debug_print_probes(entry);
-	return old;
-}
-
-/*
- * Get marker if the marker is present in the marker hash table.
- * Must be called with markers_mutex held.
- * Returns NULL if not present.
- */
-static struct marker_entry *get_marker(const char *name)
-{
-	struct hlist_head *head;
-	struct hlist_node *node;
-	struct marker_entry *e;
-	u32 hash = jhash(name, strlen(name), 0);
-
-	head = &marker_table[hash & ((1 << MARKER_HASH_BITS)-1)];
-	hlist_for_each_entry(e, node, head, hlist) {
-		if (!strcmp(name, e->name))
-			return e;
-	}
-	return NULL;
-}
-
-/*
- * Add the marker to the marker hash table. Must be called with markers_mutex
- * held.
- */
-static struct marker_entry *add_marker(const char *name, const char *format)
-{
-	struct hlist_head *head;
-	struct hlist_node *node;
-	struct marker_entry *e;
-	size_t name_len = strlen(name) + 1;
-	size_t format_len = 0;
-	u32 hash = jhash(name, name_len-1, 0);
-
-	if (format)
-		format_len = strlen(format) + 1;
-	head = &marker_table[hash & ((1 << MARKER_HASH_BITS)-1)];
-	hlist_for_each_entry(e, node, head, hlist) {
-		if (!strcmp(name, e->name)) {
-			printk(KERN_NOTICE
-				"Marker %s busy\n", name);
-			return ERR_PTR(-EBUSY);	/* Already there */
-		}
-	}
-	/*
-	 * Using kmalloc here to allocate a variable length element. Could
-	 * cause some memory fragmentation if overused.
-	 */
-	e = kmalloc(sizeof(struct marker_entry) + name_len + format_len,
-			GFP_KERNEL);
-	if (!e)
-		return ERR_PTR(-ENOMEM);
-	memcpy(&e->name[0], name, name_len);
-	if (format) {
-		e->format = &e->name[name_len];
-		memcpy(e->format, format, format_len);
-		if (strcmp(e->format, MARK_NOARGS) == 0)
-			e->call = marker_probe_cb_noarg;
-		else
-			e->call = marker_probe_cb;
-		trace_mark(core_marker_format, "name %s format %s",
-				e->name, e->format);
-	} else {
-		e->format = NULL;
-		e->call = marker_probe_cb;
-	}
-	e->single.func = __mark_empty_function;
-	e->single.probe_private = NULL;
-	e->multi = NULL;
-	e->ptype = 0;
-	e->format_allocated = 0;
-	e->refcount = 0;
-	e->rcu_pending = 0;
-	hlist_add_head(&e->hlist, head);
-	return e;
-}
-
-/*
- * Remove the marker from the marker hash table. Must be called with mutex_lock
- * held.
- */
-static int remove_marker(const char *name)
-{
-	struct hlist_head *head;
-	struct hlist_node *node;
-	struct marker_entry *e;
-	int found = 0;
-	size_t len = strlen(name) + 1;
-	u32 hash = jhash(name, len-1, 0);
-
-	head = &marker_table[hash & ((1 << MARKER_HASH_BITS)-1)];
-	hlist_for_each_entry(e, node, head, hlist) {
-		if (!strcmp(name, e->name)) {
-			found = 1;
-			break;
-		}
-	}
-	if (!found)
-		return -ENOENT;
-	if (e->single.func != __mark_empty_function)
-		return -EBUSY;
-	hlist_del(&e->hlist);
-	if (e->format_allocated)
-		kfree(e->format);
-	/* Make sure the call_rcu has been executed */
-	if (e->rcu_pending)
-		rcu_barrier_sched();
-	kfree(e);
-	return 0;
-}
-
-/*
- * Set the mark_entry format to the format found in the element.
- */
-static int marker_set_format(struct marker_entry *entry, const char *format)
-{
-	entry->format = kstrdup(format, GFP_KERNEL);
-	if (!entry->format)
-		return -ENOMEM;
-	entry->format_allocated = 1;
-
-	trace_mark(core_marker_format, "name %s format %s",
-			entry->name, entry->format);
-	return 0;
-}
-
-/*
- * Sets the probe callback corresponding to one marker.
- */
-static int set_marker(struct marker_entry *entry, struct marker *elem,
-		int active)
-{
-	int ret = 0;
-	WARN_ON(strcmp(entry->name, elem->name) != 0);
-
-	if (entry->format) {
-		if (strcmp(entry->format, elem->format) != 0) {
-			printk(KERN_NOTICE
-				"Format mismatch for probe %s "
-				"(%s), marker (%s)\n",
-				entry->name,
-				entry->format,
-				elem->format);
-			return -EPERM;
-		}
-	} else {
-		ret = marker_set_format(entry, elem->format);
-		if (ret)
-			return ret;
-	}
-
-	/*
-	 * probe_cb setup (statically known) is done here. It is
-	 * asynchronous with the rest of execution, therefore we only
-	 * pass from a "safe" callback (with argument) to an "unsafe"
-	 * callback (does not set arguments).
-	 */
-	elem->call = entry->call;
-	/*
-	 * Sanity check :
-	 * We only update the single probe private data when the ptr is
-	 * set to a _non_ single probe! (0 -> 1 and N -> 1, N != 1)
-	 */
-	WARN_ON(elem->single.func != __mark_empty_function
-		&& elem->single.probe_private != entry->single.probe_private
-		&& !elem->ptype);
-	elem->single.probe_private = entry->single.probe_private;
-	/*
-	 * Make sure the private data is valid when we update the
-	 * single probe ptr.
-	 */
-	smp_wmb();
-	elem->single.func = entry->single.func;
-	/*
-	 * We also make sure that the new probe callbacks array is consistent
-	 * before setting a pointer to it.
-	 */
-	rcu_assign_pointer(elem->multi, entry->multi);
-	/*
-	 * Update the function or multi probe array pointer before setting the
-	 * ptype.
-	 */
-	smp_wmb();
-	elem->ptype = entry->ptype;
-
-	if (elem->tp_name && (active ^ elem->state)) {
-		WARN_ON(!elem->tp_cb);
-		/*
-		 * It is ok to directly call the probe registration because type
-		 * checking has been done in the __trace_mark_tp() macro.
-		 */
-
-		if (active) {
-			/*
-			 * try_module_get should always succeed because we hold
-			 * lock_module() to get the tp_cb address.
-			 */
-			ret = try_module_get(__module_text_address(
-				(unsigned long)elem->tp_cb));
-			BUG_ON(!ret);
-			ret = tracepoint_probe_register_noupdate(
-				elem->tp_name,
-				elem->tp_cb);
-		} else {
-			ret = tracepoint_probe_unregister_noupdate(
-				elem->tp_name,
-				elem->tp_cb);
-			/*
-			 * tracepoint_probe_update_all() must be called
-			 * before the module containing tp_cb is unloaded.
-			 */
-			module_put(__module_text_address(
-				(unsigned long)elem->tp_cb));
-		}
-	}
-	elem->state = active;
-
-	return ret;
-}
-
-/*
- * Disable a marker and its probe callback.
- * Note: only waiting an RCU period after setting elem->call to the empty
- * function insures that the original callback is not used anymore. This insured
- * by rcu_read_lock_sched around the call site.
- */
-static void disable_marker(struct marker *elem)
-{
-	int ret;
-
-	/* leave "call" as is. It is known statically. */
-	if (elem->tp_name && elem->state) {
-		WARN_ON(!elem->tp_cb);
-		/*
-		 * It is ok to directly call the probe registration because type
-		 * checking has been done in the __trace_mark_tp() macro.
-		 */
-		ret = tracepoint_probe_unregister_noupdate(elem->tp_name,
-			elem->tp_cb);
-		WARN_ON(ret);
-		/*
-		 * tracepoint_probe_update_all() must be called
-		 * before the module containing tp_cb is unloaded.
-		 */
-		module_put(__module_text_address((unsigned long)elem->tp_cb));
-	}
-	elem->state = 0;
-	elem->single.func = __mark_empty_function;
-	/* Update the function before setting the ptype */
-	smp_wmb();
-	elem->ptype = 0;	/* single probe */
-	/*
-	 * Leave the private data and id there, because removal is racy and
-	 * should be done only after an RCU period. These are never used until
-	 * the next initialization anyway.
-	 */
-}
-
-/**
- * marker_update_probe_range - Update a probe range
- * @begin: beginning of the range
- * @end: end of the range
- *
- * Updates the probe callback corresponding to a range of markers.
- */
-void marker_update_probe_range(struct marker *begin,
-	struct marker *end)
-{
-	struct marker *iter;
-	struct marker_entry *mark_entry;
-
-	mutex_lock(&markers_mutex);
-	for (iter = begin; iter < end; iter++) {
-		mark_entry = get_marker(iter->name);
-		if (mark_entry) {
-			set_marker(mark_entry, iter, !!mark_entry->refcount);
-			/*
-			 * ignore error, continue
-			 */
-		} else {
-			disable_marker(iter);
-		}
-	}
-	mutex_unlock(&markers_mutex);
-}
-
-/*
- * Update probes, removing the faulty probes.
- *
- * Internal callback only changed before the first probe is connected to it.
- * Single probe private data can only be changed on 0 -> 1 and 2 -> 1
- * transitions.  All other transitions will leave the old private data valid.
- * This makes the non-atomicity of the callback/private data updates valid.
- *
- * "special case" updates :
- * 0 -> 1 callback
- * 1 -> 0 callback
- * 1 -> 2 callbacks
- * 2 -> 1 callbacks
- * Other updates all behave the same, just like the 2 -> 3 or 3 -> 2 updates.
- * Site effect : marker_set_format may delete the marker entry (creating a
- * replacement).
- */
-static void marker_update_probes(void)
-{
-	/* Core kernel markers */
-	marker_update_probe_range(__start___markers, __stop___markers);
-	/* Markers in modules. */
-	module_update_markers();
-	tracepoint_probe_update_all();
-}
-
-/**
- * marker_probe_register -  Connect a probe to a marker
- * @name: marker name
- * @format: format string
- * @probe: probe handler
- * @probe_private: probe private data
- *
- * private data must be a valid allocated memory address, or NULL.
- * Returns 0 if ok, error value on error.
- * The probe address must at least be aligned on the architecture pointer size.
- */
-int marker_probe_register(const char *name, const char *format,
-			marker_probe_func *probe, void *probe_private)
-{
-	struct marker_entry *entry;
-	int ret = 0;
-	struct marker_probe_closure *old;
-
-	mutex_lock(&markers_mutex);
-	entry = get_marker(name);
-	if (!entry) {
-		entry = add_marker(name, format);
-		if (IS_ERR(entry))
-			ret = PTR_ERR(entry);
-	} else if (format) {
-		if (!entry->format)
-			ret = marker_set_format(entry, format);
-		else if (strcmp(entry->format, format))
-			ret = -EPERM;
-	}
-	if (ret)
-		goto end;
-
-	/*
-	 * If we detect that a call_rcu is pending for this marker,
-	 * make sure it's executed now.
-	 */
-	if (entry->rcu_pending)
-		rcu_barrier_sched();
-	old = marker_entry_add_probe(entry, probe, probe_private);
-	if (IS_ERR(old)) {
-		ret = PTR_ERR(old);
-		goto end;
-	}
-	mutex_unlock(&markers_mutex);
-	marker_update_probes();
-	mutex_lock(&markers_mutex);
-	entry = get_marker(name);
-	if (!entry)
-		goto end;
-	if (entry->rcu_pending)
-		rcu_barrier_sched();
-	entry->oldptr = old;
-	entry->rcu_pending = 1;
-	/* write rcu_pending before calling the RCU callback */
-	smp_wmb();
-	call_rcu_sched(&entry->rcu, free_old_closure);
-end:
-	mutex_unlock(&markers_mutex);
-	return ret;
-}
-EXPORT_SYMBOL_GPL(marker_probe_register);
-
-/**
- * marker_probe_unregister -  Disconnect a probe from a marker
- * @name: marker name
- * @probe: probe function pointer
- * @probe_private: probe private data
- *
- * Returns the private data given to marker_probe_register, or an ERR_PTR().
- * We do not need to call a synchronize_sched to make sure the probes have
- * finished running before doing a module unload, because the module unload
- * itself uses stop_machine(), which insures that every preempt disabled section
- * have finished.
- */
-int marker_probe_unregister(const char *name,
-	marker_probe_func *probe, void *probe_private)
-{
-	struct marker_entry *entry;
-	struct marker_probe_closure *old;
-	int ret = -ENOENT;
-
-	mutex_lock(&markers_mutex);
-	entry = get_marker(name);
-	if (!entry)
-		goto end;
-	if (entry->rcu_pending)
-		rcu_barrier_sched();
-	old = marker_entry_remove_probe(entry, probe, probe_private);
-	mutex_unlock(&markers_mutex);
-	marker_update_probes();
-	mutex_lock(&markers_mutex);
-	entry = get_marker(name);
-	if (!entry)
-		goto end;
-	if (entry->rcu_pending)
-		rcu_barrier_sched();
-	entry->oldptr = old;
-	entry->rcu_pending = 1;
-	/* write rcu_pending before calling the RCU callback */
-	smp_wmb();
-	call_rcu_sched(&entry->rcu, free_old_closure);
-	remove_marker(name);	/* Ignore busy error message */
-	ret = 0;
-end:
-	mutex_unlock(&markers_mutex);
-	return ret;
-}
-EXPORT_SYMBOL_GPL(marker_probe_unregister);
-
-static struct marker_entry *
-get_marker_from_private_data(marker_probe_func *probe, void *probe_private)
-{
-	struct marker_entry *entry;
-	unsigned int i;
-	struct hlist_head *head;
-	struct hlist_node *node;
-
-	for (i = 0; i < MARKER_TABLE_SIZE; i++) {
-		head = &marker_table[i];
-		hlist_for_each_entry(entry, node, head, hlist) {
-			if (!entry->ptype) {
-				if (entry->single.func == probe
-						&& entry->single.probe_private
-						== probe_private)
-					return entry;
-			} else {
-				struct marker_probe_closure *closure;
-				closure = entry->multi;
-				for (i = 0; closure[i].func; i++) {
-					if (closure[i].func == probe &&
-							closure[i].probe_private
-							== probe_private)
-						return entry;
-				}
-			}
-		}
-	}
-	return NULL;
-}
-
-/**
- * marker_probe_unregister_private_data -  Disconnect a probe from a marker
- * @probe: probe function
- * @probe_private: probe private data
- *
- * Unregister a probe by providing the registered private data.
- * Only removes the first marker found in hash table.
- * Return 0 on success or error value.
- * We do not need to call a synchronize_sched to make sure the probes have
- * finished running before doing a module unload, because the module unload
- * itself uses stop_machine(), which insures that every preempt disabled section
- * have finished.
- */
-int marker_probe_unregister_private_data(marker_probe_func *probe,
-		void *probe_private)
-{
-	struct marker_entry *entry;
-	int ret = 0;
-	struct marker_probe_closure *old;
-
-	mutex_lock(&markers_mutex);
-	entry = get_marker_from_private_data(probe, probe_private);
-	if (!entry) {
-		ret = -ENOENT;
-		goto end;
-	}
-	if (entry->rcu_pending)
-		rcu_barrier_sched();
-	old = marker_entry_remove_probe(entry, NULL, probe_private);
-	mutex_unlock(&markers_mutex);
-	marker_update_probes();
-	mutex_lock(&markers_mutex);
-	entry = get_marker_from_private_data(probe, probe_private);
-	if (!entry)
-		goto end;
-	if (entry->rcu_pending)
-		rcu_barrier_sched();
-	entry->oldptr = old;
-	entry->rcu_pending = 1;
-	/* write rcu_pending before calling the RCU callback */
-	smp_wmb();
-	call_rcu_sched(&entry->rcu, free_old_closure);
-	remove_marker(entry->name);	/* Ignore busy error message */
-end:
-	mutex_unlock(&markers_mutex);
-	return ret;
-}
-EXPORT_SYMBOL_GPL(marker_probe_unregister_private_data);
-
-/**
- * marker_get_private_data - Get a marker's probe private data
- * @name: marker name
- * @probe: probe to match
- * @num: get the nth matching probe's private data
- *
- * Returns the nth private data pointer (starting from 0) matching, or an
- * ERR_PTR.
- * Returns the private data pointer, or an ERR_PTR.
- * The private data pointer should _only_ be dereferenced if the caller is the
- * owner of the data, or its content could vanish. This is mostly used to
- * confirm that a caller is the owner of a registered probe.
- */
-void *marker_get_private_data(const char *name, marker_probe_func *probe,
-		int num)
-{
-	struct hlist_head *head;
-	struct hlist_node *node;
-	struct marker_entry *e;
-	size_t name_len = strlen(name) + 1;
-	u32 hash = jhash(name, name_len-1, 0);
-	int i;
-
-	head = &marker_table[hash & ((1 << MARKER_HASH_BITS)-1)];
-	hlist_for_each_entry(e, node, head, hlist) {
-		if (!strcmp(name, e->name)) {
-			if (!e->ptype) {
-				if (num == 0 && e->single.func == probe)
-					return e->single.probe_private;
-			} else {
-				struct marker_probe_closure *closure;
-				int match = 0;
-				closure = e->multi;
-				for (i = 0; closure[i].func; i++) {
-					if (closure[i].func != probe)
-						continue;
-					if (match++ == num)
-						return closure[i].probe_private;
-				}
-			}
-			break;
-		}
-	}
-	return ERR_PTR(-ENOENT);
-}
-EXPORT_SYMBOL_GPL(marker_get_private_data);
-
-#ifdef CONFIG_MODULES
-
-int marker_module_notify(struct notifier_block *self,
-			 unsigned long val, void *data)
-{
-	struct module *mod = data;
-
-	switch (val) {
-	case MODULE_STATE_COMING:
-		marker_update_probe_range(mod->markers,
-			mod->markers + mod->num_markers);
-		break;
-	case MODULE_STATE_GOING:
-		marker_update_probe_range(mod->markers,
-			mod->markers + mod->num_markers);
-		break;
-	}
-	return 0;
-}
-
-struct notifier_block marker_module_nb = {
-	.notifier_call = marker_module_notify,
-	.priority = 0,
-};
-
-static int init_markers(void)
-{
-	return register_module_notifier(&marker_module_nb);
-}
-__initcall(init_markers);
-
-#endif /* CONFIG_MODULES */
diff --git a/kernel/module.c b/kernel/module.c
index 2d537186191f..5842a71cf052 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -47,6 +47,7 @@
 #include <linux/rculist.h>
 #include <asm/uaccess.h>
 #include <asm/cacheflush.h>
+#include <asm/mmu_context.h>
 #include <linux/license.h>
 #include <asm/sections.h>
 #include <linux/tracepoint.h>
@@ -55,6 +56,11 @@
 #include <linux/percpu.h>
 #include <linux/kmemleak.h>
 
+#define CREATE_TRACE_POINTS
+#include <trace/events/module.h>
+
+EXPORT_TRACEPOINT_SYMBOL(module_get);
+
 #if 0
 #define DEBUGP printk
 #else
@@ -364,7 +370,7 @@ EXPORT_SYMBOL_GPL(find_module);
 
 #ifdef CONFIG_SMP
 
-#ifdef CONFIG_HAVE_DYNAMIC_PER_CPU_AREA
+#ifndef CONFIG_HAVE_LEGACY_PER_CPU_AREA
 
 static void *percpu_modalloc(unsigned long size, unsigned long align,
 			     const char *name)
@@ -389,7 +395,7 @@ static void percpu_modfree(void *freeme)
 	free_percpu(freeme);
 }
 
-#else /* ... !CONFIG_HAVE_DYNAMIC_PER_CPU_AREA */
+#else /* ... CONFIG_HAVE_LEGACY_PER_CPU_AREA */
 
 /* Number of blocks used and allocated. */
 static unsigned int pcpu_num_used, pcpu_num_allocated;
@@ -535,7 +541,7 @@ static int percpu_modinit(void)
 }
 __initcall(percpu_modinit);
 
-#endif /* CONFIG_HAVE_DYNAMIC_PER_CPU_AREA */
+#endif /* CONFIG_HAVE_LEGACY_PER_CPU_AREA */
 
 static unsigned int find_pcpusec(Elf_Ehdr *hdr,
 				 Elf_Shdr *sechdrs,
@@ -942,6 +948,8 @@ void module_put(struct module *module)
 	if (module) {
 		unsigned int cpu = get_cpu();
 		local_dec(__module_ref_addr(module, cpu));
+		trace_module_put(module, _RET_IP_,
+				 local_read(__module_ref_addr(module, cpu)));
 		/* Maybe they're waiting for us to drop reference? */
 		if (unlikely(!module_is_live(module)))
 			wake_up_process(module->waiter);
@@ -1179,7 +1187,8 @@ static void add_sect_attrs(struct module *mod, unsigned int nsect,
 
 	/* Count loaded sections and allocate structures */
 	for (i = 0; i < nsect; i++)
-		if (sechdrs[i].sh_flags & SHF_ALLOC)
+		if (sechdrs[i].sh_flags & SHF_ALLOC
+		    && sechdrs[i].sh_size)
 			nloaded++;
 	size[0] = ALIGN(sizeof(*sect_attrs)
 			+ nloaded * sizeof(sect_attrs->attrs[0]),
@@ -1199,6 +1208,8 @@ static void add_sect_attrs(struct module *mod, unsigned int nsect,
 	for (i = 0; i < nsect; i++) {
 		if (! (sechdrs[i].sh_flags & SHF_ALLOC))
 			continue;
+		if (!sechdrs[i].sh_size)
+			continue;
 		sattr->address = sechdrs[i].sh_addr;
 		sattr->name = kstrdup(secstrings + sechdrs[i].sh_name,
 					GFP_KERNEL);
@@ -1497,6 +1508,8 @@ static int __unlink_module(void *_mod)
 /* Free a module, remove from lists, etc (must hold module_mutex). */
 static void free_module(struct module *mod)
 {
+	trace_module_free(mod);
+
 	/* Delete from various lists */
 	stop_machine(__unlink_module, mod, NULL);
 	remove_notes_attrs(mod);
@@ -1526,6 +1539,10 @@ static void free_module(struct module *mod)
 
 	/* Finally, free the core (containing the module structure) */
 	module_free(mod, mod->module_core);
+
+#ifdef CONFIG_MPU
+	update_protections(current->mm);
+#endif
 }
 
 void *__symbol_get(const char *symbol)
@@ -1783,6 +1800,17 @@ static void setup_modinfo(struct module *mod, Elf_Shdr *sechdrs,
 	}
 }
 
+static void free_modinfo(struct module *mod)
+{
+	struct module_attribute *attr;
+	int i;
+
+	for (i = 0; (attr = modinfo_attrs[i]); i++) {
+		if (attr->free)
+			attr->free(mod);
+	}
+}
+
 #ifdef CONFIG_KALLSYMS
 
 /* lookup symbol in given range of kernel_symbols */
@@ -1848,13 +1876,93 @@ static char elf_type(const Elf_Sym *sym,
 	return '?';
 }
 
+static bool is_core_symbol(const Elf_Sym *src, const Elf_Shdr *sechdrs,
+                           unsigned int shnum)
+{
+	const Elf_Shdr *sec;
+
+	if (src->st_shndx == SHN_UNDEF
+	    || src->st_shndx >= shnum
+	    || !src->st_name)
+		return false;
+
+	sec = sechdrs + src->st_shndx;
+	if (!(sec->sh_flags & SHF_ALLOC)
+#ifndef CONFIG_KALLSYMS_ALL
+	    || !(sec->sh_flags & SHF_EXECINSTR)
+#endif
+	    || (sec->sh_entsize & INIT_OFFSET_MASK))
+		return false;
+
+	return true;
+}
+
+static unsigned long layout_symtab(struct module *mod,
+				   Elf_Shdr *sechdrs,
+				   unsigned int symindex,
+				   unsigned int strindex,
+				   const Elf_Ehdr *hdr,
+				   const char *secstrings,
+				   unsigned long *pstroffs,
+				   unsigned long *strmap)
+{
+	unsigned long symoffs;
+	Elf_Shdr *symsect = sechdrs + symindex;
+	Elf_Shdr *strsect = sechdrs + strindex;
+	const Elf_Sym *src;
+	const char *strtab;
+	unsigned int i, nsrc, ndst;
+
+	/* Put symbol section at end of init part of module. */
+	symsect->sh_flags |= SHF_ALLOC;
+	symsect->sh_entsize = get_offset(mod, &mod->init_size, symsect,
+					 symindex) | INIT_OFFSET_MASK;
+	DEBUGP("\t%s\n", secstrings + symsect->sh_name);
+
+	src = (void *)hdr + symsect->sh_offset;
+	nsrc = symsect->sh_size / sizeof(*src);
+	strtab = (void *)hdr + strsect->sh_offset;
+	for (ndst = i = 1; i < nsrc; ++i, ++src)
+		if (is_core_symbol(src, sechdrs, hdr->e_shnum)) {
+			unsigned int j = src->st_name;
+
+			while(!__test_and_set_bit(j, strmap) && strtab[j])
+				++j;
+			++ndst;
+		}
+
+	/* Append room for core symbols at end of core part. */
+	symoffs = ALIGN(mod->core_size, symsect->sh_addralign ?: 1);
+	mod->core_size = symoffs + ndst * sizeof(Elf_Sym);
+
+	/* Put string table section at end of init part of module. */
+	strsect->sh_flags |= SHF_ALLOC;
+	strsect->sh_entsize = get_offset(mod, &mod->init_size, strsect,
+					 strindex) | INIT_OFFSET_MASK;
+	DEBUGP("\t%s\n", secstrings + strsect->sh_name);
+
+	/* Append room for core symbols' strings at end of core part. */
+	*pstroffs = mod->core_size;
+	__set_bit(0, strmap);
+	mod->core_size += bitmap_weight(strmap, strsect->sh_size);
+
+	return symoffs;
+}
+
 static void add_kallsyms(struct module *mod,
 			 Elf_Shdr *sechdrs,
+			 unsigned int shnum,
 			 unsigned int symindex,
 			 unsigned int strindex,
-			 const char *secstrings)
+			 unsigned long symoffs,
+			 unsigned long stroffs,
+			 const char *secstrings,
+			 unsigned long *strmap)
 {
-	unsigned int i;
+	unsigned int i, ndst;
+	const Elf_Sym *src;
+	Elf_Sym *dst;
+	char *s;
 
 	mod->symtab = (void *)sechdrs[symindex].sh_addr;
 	mod->num_symtab = sechdrs[symindex].sh_size / sizeof(Elf_Sym);
@@ -1864,13 +1972,46 @@ static void add_kallsyms(struct module *mod,
 	for (i = 0; i < mod->num_symtab; i++)
 		mod->symtab[i].st_info
 			= elf_type(&mod->symtab[i], sechdrs, secstrings, mod);
+
+	mod->core_symtab = dst = mod->module_core + symoffs;
+	src = mod->symtab;
+	*dst = *src;
+	for (ndst = i = 1; i < mod->num_symtab; ++i, ++src) {
+		if (!is_core_symbol(src, sechdrs, shnum))
+			continue;
+		dst[ndst] = *src;
+		dst[ndst].st_name = bitmap_weight(strmap, dst[ndst].st_name);
+		++ndst;
+	}
+	mod->core_num_syms = ndst;
+
+	mod->core_strtab = s = mod->module_core + stroffs;
+	for (*s = 0, i = 1; i < sechdrs[strindex].sh_size; ++i)
+		if (test_bit(i, strmap))
+			*++s = mod->strtab[i];
 }
 #else
+static inline unsigned long layout_symtab(struct module *mod,
+					  Elf_Shdr *sechdrs,
+					  unsigned int symindex,
+					  unsigned int strindex,
+					  const Elf_Ehdr *hdr,
+					  const char *secstrings,
+					  unsigned long *pstroffs,
+					  unsigned long *strmap)
+{
+	return 0;
+}
+
 static inline void add_kallsyms(struct module *mod,
 				Elf_Shdr *sechdrs,
+				unsigned int shnum,
 				unsigned int symindex,
 				unsigned int strindex,
-				const char *secstrings)
+				unsigned long symoffs,
+				unsigned long stroffs,
+				const char *secstrings,
+				const unsigned long *strmap)
 {
 }
 #endif /* CONFIG_KALLSYMS */
@@ -1945,6 +2086,8 @@ static noinline struct module *load_module(void __user *umod,
 	struct module *mod;
 	long err = 0;
 	void *percpu = NULL, *ptr = NULL; /* Stops spurious gcc warning */
+	unsigned long symoffs, stroffs, *strmap;
+
 	mm_segment_t old_fs;
 
 	DEBUGP("load_module: umod=%p, len=%lu, uargs=%p\n",
@@ -2026,11 +2169,6 @@ static noinline struct module *load_module(void __user *umod,
 	/* Don't keep modinfo and version sections. */
 	sechdrs[infoindex].sh_flags &= ~(unsigned long)SHF_ALLOC;
 	sechdrs[versindex].sh_flags &= ~(unsigned long)SHF_ALLOC;
-#ifdef CONFIG_KALLSYMS
-	/* Keep symbol and string tables for decoding later. */
-	sechdrs[symindex].sh_flags |= SHF_ALLOC;
-	sechdrs[strindex].sh_flags |= SHF_ALLOC;
-#endif
 
 	/* Check module struct version now, before we try to use module. */
 	if (!check_modstruct_version(sechdrs, versindex, mod)) {
@@ -2066,6 +2204,13 @@ static noinline struct module *load_module(void __user *umod,
 		goto free_hdr;
 	}
 
+	strmap = kzalloc(BITS_TO_LONGS(sechdrs[strindex].sh_size)
+			 * sizeof(long), GFP_KERNEL);
+	if (!strmap) {
+		err = -ENOMEM;
+		goto free_mod;
+	}
+
 	if (find_module(mod->name)) {
 		err = -EEXIST;
 		goto free_mod;
@@ -2095,6 +2240,8 @@ static noinline struct module *load_module(void __user *umod,
 	   this is done generically; there doesn't appear to be any
 	   special cases for the architectures. */
 	layout_sections(mod, hdr, sechdrs, secstrings);
+	symoffs = layout_symtab(mod, sechdrs, symindex, strindex, hdr,
+				secstrings, &stroffs, strmap);
 
 	/* Do the allocs. */
 	ptr = module_alloc_update_bounds(mod->core_size);
@@ -2228,10 +2375,6 @@ static noinline struct module *load_module(void __user *umod,
 				  sizeof(*mod->ctors), &mod->num_ctors);
 #endif
 
-#ifdef CONFIG_MARKERS
-	mod->markers = section_objs(hdr, sechdrs, secstrings, "__markers",
-				    sizeof(*mod->markers), &mod->num_markers);
-#endif
 #ifdef CONFIG_TRACEPOINTS
 	mod->tracepoints = section_objs(hdr, sechdrs, secstrings,
 					"__tracepoints",
@@ -2303,7 +2446,10 @@ static noinline struct module *load_module(void __user *umod,
 	percpu_modcopy(mod->percpu, (void *)sechdrs[pcpuindex].sh_addr,
 		       sechdrs[pcpuindex].sh_size);
 
-	add_kallsyms(mod, sechdrs, symindex, strindex, secstrings);
+	add_kallsyms(mod, sechdrs, hdr->e_shnum, symindex, strindex,
+		     symoffs, stroffs, secstrings, strmap);
+	kfree(strmap);
+	strmap = NULL;
 
 	if (!mod->taints) {
 		struct _ddebug *debug;
@@ -2364,6 +2510,8 @@ static noinline struct module *load_module(void __user *umod,
 	/* Get rid of temporary copy */
 	vfree(hdr);
 
+	trace_module_load(mod);
+
 	/* Done! */
 	return mod;
 
@@ -2373,13 +2521,14 @@ static noinline struct module *load_module(void __user *umod,
 	synchronize_sched();
 	module_arch_cleanup(mod);
  cleanup:
+	free_modinfo(mod);
 	kobject_del(&mod->mkobj.kobj);
 	kobject_put(&mod->mkobj.kobj);
  free_unload:
 	module_unload_free(mod);
 #if defined(CONFIG_MODULE_UNLOAD) && defined(CONFIG_SMP)
- free_init:
 	percpu_modfree(mod->refptr);
+ free_init:
 #endif
 	module_free(mod, mod->module_init);
  free_core:
@@ -2390,6 +2539,7 @@ static noinline struct module *load_module(void __user *umod,
 		percpu_modfree(percpu);
  free_mod:
 	kfree(args);
+	kfree(strmap);
  free_hdr:
 	vfree(hdr);
 	return ERR_PTR(err);
@@ -2479,6 +2629,11 @@ SYSCALL_DEFINE3(init_module, void __user *, umod,
 	/* Drop initial reference. */
 	module_put(mod);
 	trim_init_extable(mod);
+#ifdef CONFIG_KALLSYMS
+	mod->num_symtab = mod->core_num_syms;
+	mod->symtab = mod->core_symtab;
+	mod->strtab = mod->core_strtab;
+#endif
 	module_free(mod, mod->module_init);
 	mod->module_init = NULL;
 	mod->init_size = 0;
@@ -2940,27 +3095,12 @@ 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
-void module_update_markers(void)
-{
-	struct module *mod;
-
-	mutex_lock(&module_mutex);
-	list_for_each_entry(mod, &modules, list)
-		if (!mod->taints)
-			marker_update_probe_range(mod->markers,
-				mod->markers + mod->num_markers);
-	mutex_unlock(&module_mutex);
-}
-#endif
-
 #ifdef CONFIG_TRACEPOINTS
 void module_update_tracepoints(void)
 {
diff --git a/kernel/mutex-debug.c b/kernel/mutex-debug.c
index 50d022e5a560..ec815a960b5d 100644
--- a/kernel/mutex-debug.c
+++ b/kernel/mutex-debug.c
@@ -16,6 +16,7 @@
 #include <linux/delay.h>
 #include <linux/module.h>
 #include <linux/poison.h>
+#include <linux/sched.h>
 #include <linux/spinlock.h>
 #include <linux/kallsyms.h>
 #include <linux/interrupt.h>
diff --git a/kernel/ns_cgroup.c b/kernel/ns_cgroup.c
index 5aa854f9e5ae..2a5dfec8efe0 100644
--- a/kernel/ns_cgroup.c
+++ b/kernel/ns_cgroup.c
@@ -42,8 +42,8 @@ int ns_cgroup_clone(struct task_struct *task, struct pid *pid)
  *       (hence either you are in the same cgroup as task, or in an
  *        ancestor cgroup thereof)
  */
-static int ns_can_attach(struct cgroup_subsys *ss,
-		struct cgroup *new_cgroup, struct task_struct *task)
+static int ns_can_attach(struct cgroup_subsys *ss, struct cgroup *new_cgroup,
+			 struct task_struct *task, bool threadgroup)
 {
 	if (current != task) {
 		if (!capable(CAP_SYS_ADMIN))
@@ -56,6 +56,18 @@ static int ns_can_attach(struct cgroup_subsys *ss,
 	if (!cgroup_is_descendant(new_cgroup, task))
 		return -EPERM;
 
+	if (threadgroup) {
+		struct task_struct *c;
+		rcu_read_lock();
+		list_for_each_entry_rcu(c, &task->thread_group, thread_group) {
+			if (!cgroup_is_descendant(new_cgroup, c)) {
+				rcu_read_unlock();
+				return -EPERM;
+			}
+		}
+		rcu_read_unlock();
+	}
+
 	return 0;
 }
 
diff --git a/kernel/panic.c b/kernel/panic.c
index 512ab73b0ca3..96b45d0b4ba5 100644
--- a/kernel/panic.c
+++ b/kernel/panic.c
@@ -90,6 +90,8 @@ NORET_TYPE void panic(const char * fmt, ...)
 
 	atomic_notifier_call_chain(&panic_notifier_list, 0, buf);
 
+	bust_spinlocks(0);
+
 	if (!panic_blink)
 		panic_blink = no_blink;
 
@@ -136,7 +138,6 @@ NORET_TYPE void panic(const char * fmt, ...)
 		mdelay(1);
 		i++;
 	}
-	bust_spinlocks(0);
 }
 
 EXPORT_SYMBOL(panic);
@@ -177,7 +178,7 @@ static const struct tnt tnts[] = {
  *  'W' - Taint on warning.
  *  'C' - modules from drivers/staging are loaded.
  *
- *	The string is overwritten by the next call to print_taint().
+ *	The string is overwritten by the next call to print_tainted().
  */
 const char *print_tainted(void)
 {
diff --git a/kernel/params.c b/kernel/params.c
index 7f6912ced2ba..d656c276508d 100644
--- a/kernel/params.c
+++ b/kernel/params.c
@@ -23,6 +23,7 @@
 #include <linux/device.h>
 #include <linux/err.h>
 #include <linux/slab.h>
+#include <linux/ctype.h>
 
 #if 0
 #define DEBUGP printk
@@ -87,7 +88,7 @@ static char *next_arg(char *args, char **param, char **val)
 	}
 
 	for (i = 0; args[i]; i++) {
-		if (args[i] == ' ' && !in_quote)
+		if (isspace(args[i]) && !in_quote)
 			break;
 		if (equals == 0) {
 			if (args[i] == '=')
@@ -121,7 +122,7 @@ static char *next_arg(char *args, char **param, char **val)
 		next = args + i;
 
 	/* Chew up trailing spaces. */
-	while (*next == ' ')
+	while (isspace(*next))
 		next++;
 	return next;
 }
@@ -138,7 +139,7 @@ int parse_args(const char *name,
 	DEBUGP("Parsing ARGS: %s\n", args);
 
 	/* Chew leading spaces */
-	while (*args == ' ')
+	while (isspace(*args))
 		args++;
 
 	while (*args) {
@@ -217,15 +218,11 @@ int param_set_charp(const char *val, struct kernel_param *kp)
 		return -ENOSPC;
 	}
 
-	if (kp->flags & 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->flags |= KPARAM_KMALLOCED;
 		*(char **)kp->arg = kstrdup(val, GFP_KERNEL);
-		if (!kp->arg)
+		if (!*(char **)kp->arg)
 			return -ENOMEM;
 	} else
 		*(const char **)kp->arg = val;
@@ -303,6 +300,7 @@ static int param_array(const char *name,
 		       unsigned int min, unsigned int max,
 		       void *elem, int elemsize,
 		       int (*set)(const char *, struct kernel_param *kp),
+		       u16 flags,
 		       unsigned int *num)
 {
 	int ret;
@@ -312,6 +310,7 @@ static int param_array(const char *name,
 	/* Get the name right for errors. */
 	kp.name = name;
 	kp.arg = elem;
+	kp.flags = flags;
 
 	/* No equals sign? */
 	if (!val) {
@@ -357,7 +356,8 @@ int param_array_set(const char *val, struct kernel_param *kp)
 	unsigned int temp_num;
 
 	return param_array(kp->name, val, 1, arr->max, arr->elem,
-			   arr->elemsize, arr->set, arr->num ?: &temp_num);
+			   arr->elemsize, arr->set, kp->flags,
+			   arr->num ?: &temp_num);
 }
 
 int param_array_get(char *buffer, struct kernel_param *kp)
@@ -604,11 +604,7 @@ void module_param_sysfs_remove(struct module *mod)
 
 void destroy_params(const struct kernel_param *params, unsigned num)
 {
-	unsigned int i;
-
-	for (i = 0; i < num; i++)
-		if (params[i].flags & KPARAM_KMALLOCED)
-			kfree(*(char **)params[i].arg);
+	/* FIXME: This should free kmalloced charp parameters.  It doesn't. */
 }
 
 static void __init kernel_add_sysfs_param(const char *name,
diff --git a/kernel/perf_counter.c b/kernel/perf_counter.c
deleted file mode 100644
index d7cbc579fc80..000000000000
--- a/kernel/perf_counter.c
+++ /dev/null
@@ -1,4861 +0,0 @@
-/*
- * Performance counter core code
- *
- *  Copyright (C) 2008 Thomas Gleixner <tglx@linutronix.de>
- *  Copyright (C) 2008-2009 Red Hat, Inc., Ingo Molnar
- *  Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
- *  Copyright  ©  2009 Paul Mackerras, IBM Corp. <paulus@au1.ibm.com>
- *
- *  For licensing details see kernel-base/COPYING
- */
-
-#include <linux/fs.h>
-#include <linux/mm.h>
-#include <linux/cpu.h>
-#include <linux/smp.h>
-#include <linux/file.h>
-#include <linux/poll.h>
-#include <linux/sysfs.h>
-#include <linux/dcache.h>
-#include <linux/percpu.h>
-#include <linux/ptrace.h>
-#include <linux/vmstat.h>
-#include <linux/hardirq.h>
-#include <linux/rculist.h>
-#include <linux/uaccess.h>
-#include <linux/syscalls.h>
-#include <linux/anon_inodes.h>
-#include <linux/kernel_stat.h>
-#include <linux/perf_counter.h>
-
-#include <asm/irq_regs.h>
-
-/*
- * Each CPU has a list of per CPU counters:
- */
-DEFINE_PER_CPU(struct perf_cpu_context, perf_cpu_context);
-
-int perf_max_counters __read_mostly = 1;
-static int perf_reserved_percpu __read_mostly;
-static int perf_overcommit __read_mostly = 1;
-
-static atomic_t nr_counters __read_mostly;
-static atomic_t nr_mmap_counters __read_mostly;
-static atomic_t nr_comm_counters __read_mostly;
-static atomic_t nr_task_counters __read_mostly;
-
-/*
- * perf counter paranoia level:
- *  0 - not paranoid
- *  1 - disallow cpu counters to unpriv
- *  2 - disallow kernel profiling to unpriv
- */
-int sysctl_perf_counter_paranoid __read_mostly = 1;
-
-static inline bool perf_paranoid_cpu(void)
-{
-	return sysctl_perf_counter_paranoid > 0;
-}
-
-static inline bool perf_paranoid_kernel(void)
-{
-	return sysctl_perf_counter_paranoid > 1;
-}
-
-int sysctl_perf_counter_mlock __read_mostly = 512; /* 'free' kb per user */
-
-/*
- * max perf counter sample rate
- */
-int sysctl_perf_counter_sample_rate __read_mostly = 100000;
-
-static atomic64_t perf_counter_id;
-
-/*
- * Lock for (sysadmin-configurable) counter reservations:
- */
-static DEFINE_SPINLOCK(perf_resource_lock);
-
-/*
- * Architecture provided APIs - weak aliases:
- */
-extern __weak const struct pmu *hw_perf_counter_init(struct perf_counter *counter)
-{
-	return NULL;
-}
-
-void __weak hw_perf_disable(void)		{ barrier(); }
-void __weak hw_perf_enable(void)		{ barrier(); }
-
-void __weak hw_perf_counter_setup(int cpu)	{ barrier(); }
-void __weak hw_perf_counter_setup_online(int cpu)	{ barrier(); }
-
-int __weak
-hw_perf_group_sched_in(struct perf_counter *group_leader,
-	       struct perf_cpu_context *cpuctx,
-	       struct perf_counter_context *ctx, int cpu)
-{
-	return 0;
-}
-
-void __weak perf_counter_print_debug(void)	{ }
-
-static DEFINE_PER_CPU(int, disable_count);
-
-void __perf_disable(void)
-{
-	__get_cpu_var(disable_count)++;
-}
-
-bool __perf_enable(void)
-{
-	return !--__get_cpu_var(disable_count);
-}
-
-void perf_disable(void)
-{
-	__perf_disable();
-	hw_perf_disable();
-}
-
-void perf_enable(void)
-{
-	if (__perf_enable())
-		hw_perf_enable();
-}
-
-static void get_ctx(struct perf_counter_context *ctx)
-{
-	WARN_ON(!atomic_inc_not_zero(&ctx->refcount));
-}
-
-static void free_ctx(struct rcu_head *head)
-{
-	struct perf_counter_context *ctx;
-
-	ctx = container_of(head, struct perf_counter_context, rcu_head);
-	kfree(ctx);
-}
-
-static void put_ctx(struct perf_counter_context *ctx)
-{
-	if (atomic_dec_and_test(&ctx->refcount)) {
-		if (ctx->parent_ctx)
-			put_ctx(ctx->parent_ctx);
-		if (ctx->task)
-			put_task_struct(ctx->task);
-		call_rcu(&ctx->rcu_head, free_ctx);
-	}
-}
-
-static void unclone_ctx(struct perf_counter_context *ctx)
-{
-	if (ctx->parent_ctx) {
-		put_ctx(ctx->parent_ctx);
-		ctx->parent_ctx = NULL;
-	}
-}
-
-/*
- * If we inherit counters we want to return the parent counter id
- * to userspace.
- */
-static u64 primary_counter_id(struct perf_counter *counter)
-{
-	u64 id = counter->id;
-
-	if (counter->parent)
-		id = counter->parent->id;
-
-	return id;
-}
-
-/*
- * Get the perf_counter_context for a task and lock it.
- * This has to cope with with the fact that until it is locked,
- * the context could get moved to another task.
- */
-static struct perf_counter_context *
-perf_lock_task_context(struct task_struct *task, unsigned long *flags)
-{
-	struct perf_counter_context *ctx;
-
-	rcu_read_lock();
- retry:
-	ctx = rcu_dereference(task->perf_counter_ctxp);
-	if (ctx) {
-		/*
-		 * If this context is a clone of another, it might
-		 * get swapped for another underneath us by
-		 * perf_counter_task_sched_out, though the
-		 * rcu_read_lock() protects us from any context
-		 * getting freed.  Lock the context and check if it
-		 * got swapped before we could get the lock, and retry
-		 * if so.  If we locked the right context, then it
-		 * can't get swapped on us any more.
-		 */
-		spin_lock_irqsave(&ctx->lock, *flags);
-		if (ctx != rcu_dereference(task->perf_counter_ctxp)) {
-			spin_unlock_irqrestore(&ctx->lock, *flags);
-			goto retry;
-		}
-
-		if (!atomic_inc_not_zero(&ctx->refcount)) {
-			spin_unlock_irqrestore(&ctx->lock, *flags);
-			ctx = NULL;
-		}
-	}
-	rcu_read_unlock();
-	return ctx;
-}
-
-/*
- * Get the context for a task and increment its pin_count so it
- * can't get swapped to another task.  This also increments its
- * reference count so that the context can't get freed.
- */
-static struct perf_counter_context *perf_pin_task_context(struct task_struct *task)
-{
-	struct perf_counter_context *ctx;
-	unsigned long flags;
-
-	ctx = perf_lock_task_context(task, &flags);
-	if (ctx) {
-		++ctx->pin_count;
-		spin_unlock_irqrestore(&ctx->lock, flags);
-	}
-	return ctx;
-}
-
-static void perf_unpin_context(struct perf_counter_context *ctx)
-{
-	unsigned long flags;
-
-	spin_lock_irqsave(&ctx->lock, flags);
-	--ctx->pin_count;
-	spin_unlock_irqrestore(&ctx->lock, flags);
-	put_ctx(ctx);
-}
-
-/*
- * Add a counter from the lists for its context.
- * Must be called with ctx->mutex and ctx->lock held.
- */
-static void
-list_add_counter(struct perf_counter *counter, struct perf_counter_context *ctx)
-{
-	struct perf_counter *group_leader = counter->group_leader;
-
-	/*
-	 * Depending on whether it is a standalone or sibling counter,
-	 * add it straight to the context's counter list, or to the group
-	 * leader's sibling list:
-	 */
-	if (group_leader == counter)
-		list_add_tail(&counter->list_entry, &ctx->counter_list);
-	else {
-		list_add_tail(&counter->list_entry, &group_leader->sibling_list);
-		group_leader->nr_siblings++;
-	}
-
-	list_add_rcu(&counter->event_entry, &ctx->event_list);
-	ctx->nr_counters++;
-	if (counter->attr.inherit_stat)
-		ctx->nr_stat++;
-}
-
-/*
- * Remove a counter from the lists for its context.
- * Must be called with ctx->mutex and ctx->lock held.
- */
-static void
-list_del_counter(struct perf_counter *counter, struct perf_counter_context *ctx)
-{
-	struct perf_counter *sibling, *tmp;
-
-	if (list_empty(&counter->list_entry))
-		return;
-	ctx->nr_counters--;
-	if (counter->attr.inherit_stat)
-		ctx->nr_stat--;
-
-	list_del_init(&counter->list_entry);
-	list_del_rcu(&counter->event_entry);
-
-	if (counter->group_leader != counter)
-		counter->group_leader->nr_siblings--;
-
-	/*
-	 * If this was a group counter with sibling counters then
-	 * upgrade the siblings to singleton counters by adding them
-	 * to the context list directly:
-	 */
-	list_for_each_entry_safe(sibling, tmp,
-				 &counter->sibling_list, list_entry) {
-
-		list_move_tail(&sibling->list_entry, &ctx->counter_list);
-		sibling->group_leader = sibling;
-	}
-}
-
-static void
-counter_sched_out(struct perf_counter *counter,
-		  struct perf_cpu_context *cpuctx,
-		  struct perf_counter_context *ctx)
-{
-	if (counter->state != PERF_COUNTER_STATE_ACTIVE)
-		return;
-
-	counter->state = PERF_COUNTER_STATE_INACTIVE;
-	if (counter->pending_disable) {
-		counter->pending_disable = 0;
-		counter->state = PERF_COUNTER_STATE_OFF;
-	}
-	counter->tstamp_stopped = ctx->time;
-	counter->pmu->disable(counter);
-	counter->oncpu = -1;
-
-	if (!is_software_counter(counter))
-		cpuctx->active_oncpu--;
-	ctx->nr_active--;
-	if (counter->attr.exclusive || !cpuctx->active_oncpu)
-		cpuctx->exclusive = 0;
-}
-
-static void
-group_sched_out(struct perf_counter *group_counter,
-		struct perf_cpu_context *cpuctx,
-		struct perf_counter_context *ctx)
-{
-	struct perf_counter *counter;
-
-	if (group_counter->state != PERF_COUNTER_STATE_ACTIVE)
-		return;
-
-	counter_sched_out(group_counter, cpuctx, ctx);
-
-	/*
-	 * Schedule out siblings (if any):
-	 */
-	list_for_each_entry(counter, &group_counter->sibling_list, list_entry)
-		counter_sched_out(counter, cpuctx, ctx);
-
-	if (group_counter->attr.exclusive)
-		cpuctx->exclusive = 0;
-}
-
-/*
- * Cross CPU call to remove a performance counter
- *
- * We disable the counter on the hardware level first. After that we
- * remove it from the context list.
- */
-static void __perf_counter_remove_from_context(void *info)
-{
-	struct perf_cpu_context *cpuctx = &__get_cpu_var(perf_cpu_context);
-	struct perf_counter *counter = info;
-	struct perf_counter_context *ctx = counter->ctx;
-
-	/*
-	 * If this is a task context, we need to check whether it is
-	 * the current task context of this cpu. If not it has been
-	 * scheduled out before the smp call arrived.
-	 */
-	if (ctx->task && cpuctx->task_ctx != ctx)
-		return;
-
-	spin_lock(&ctx->lock);
-	/*
-	 * Protect the list operation against NMI by disabling the
-	 * counters on a global level.
-	 */
-	perf_disable();
-
-	counter_sched_out(counter, cpuctx, ctx);
-
-	list_del_counter(counter, ctx);
-
-	if (!ctx->task) {
-		/*
-		 * Allow more per task counters with respect to the
-		 * reservation:
-		 */
-		cpuctx->max_pertask =
-			min(perf_max_counters - ctx->nr_counters,
-			    perf_max_counters - perf_reserved_percpu);
-	}
-
-	perf_enable();
-	spin_unlock(&ctx->lock);
-}
-
-
-/*
- * Remove the counter from a task's (or a CPU's) list of counters.
- *
- * Must be called with ctx->mutex held.
- *
- * CPU counters are removed with a smp call. For task counters we only
- * call when the task is on a CPU.
- *
- * If counter->ctx is a cloned context, callers must make sure that
- * every task struct that counter->ctx->task could possibly point to
- * remains valid.  This is OK when called from perf_release since
- * that only calls us on the top-level context, which can't be a clone.
- * When called from perf_counter_exit_task, it's OK because the
- * context has been detached from its task.
- */
-static void perf_counter_remove_from_context(struct perf_counter *counter)
-{
-	struct perf_counter_context *ctx = counter->ctx;
-	struct task_struct *task = ctx->task;
-
-	if (!task) {
-		/*
-		 * Per cpu counters are removed via an smp call and
-		 * the removal is always sucessful.
-		 */
-		smp_call_function_single(counter->cpu,
-					 __perf_counter_remove_from_context,
-					 counter, 1);
-		return;
-	}
-
-retry:
-	task_oncpu_function_call(task, __perf_counter_remove_from_context,
-				 counter);
-
-	spin_lock_irq(&ctx->lock);
-	/*
-	 * If the context is active we need to retry the smp call.
-	 */
-	if (ctx->nr_active && !list_empty(&counter->list_entry)) {
-		spin_unlock_irq(&ctx->lock);
-		goto retry;
-	}
-
-	/*
-	 * The lock prevents that this context is scheduled in so we
-	 * can remove the counter safely, if the call above did not
-	 * succeed.
-	 */
-	if (!list_empty(&counter->list_entry)) {
-		list_del_counter(counter, ctx);
-	}
-	spin_unlock_irq(&ctx->lock);
-}
-
-static inline u64 perf_clock(void)
-{
-	return cpu_clock(smp_processor_id());
-}
-
-/*
- * Update the record of the current time in a context.
- */
-static void update_context_time(struct perf_counter_context *ctx)
-{
-	u64 now = perf_clock();
-
-	ctx->time += now - ctx->timestamp;
-	ctx->timestamp = now;
-}
-
-/*
- * Update the total_time_enabled and total_time_running fields for a counter.
- */
-static void update_counter_times(struct perf_counter *counter)
-{
-	struct perf_counter_context *ctx = counter->ctx;
-	u64 run_end;
-
-	if (counter->state < PERF_COUNTER_STATE_INACTIVE)
-		return;
-
-	counter->total_time_enabled = ctx->time - counter->tstamp_enabled;
-
-	if (counter->state == PERF_COUNTER_STATE_INACTIVE)
-		run_end = counter->tstamp_stopped;
-	else
-		run_end = ctx->time;
-
-	counter->total_time_running = run_end - counter->tstamp_running;
-}
-
-/*
- * Update total_time_enabled and total_time_running for all counters in a group.
- */
-static void update_group_times(struct perf_counter *leader)
-{
-	struct perf_counter *counter;
-
-	update_counter_times(leader);
-	list_for_each_entry(counter, &leader->sibling_list, list_entry)
-		update_counter_times(counter);
-}
-
-/*
- * Cross CPU call to disable a performance counter
- */
-static void __perf_counter_disable(void *info)
-{
-	struct perf_counter *counter = info;
-	struct perf_cpu_context *cpuctx = &__get_cpu_var(perf_cpu_context);
-	struct perf_counter_context *ctx = counter->ctx;
-
-	/*
-	 * If this is a per-task counter, need to check whether this
-	 * counter's task is the current task on this cpu.
-	 */
-	if (ctx->task && cpuctx->task_ctx != ctx)
-		return;
-
-	spin_lock(&ctx->lock);
-
-	/*
-	 * If the counter is on, turn it off.
-	 * If it is in error state, leave it in error state.
-	 */
-	if (counter->state >= PERF_COUNTER_STATE_INACTIVE) {
-		update_context_time(ctx);
-		update_counter_times(counter);
-		if (counter == counter->group_leader)
-			group_sched_out(counter, cpuctx, ctx);
-		else
-			counter_sched_out(counter, cpuctx, ctx);
-		counter->state = PERF_COUNTER_STATE_OFF;
-	}
-
-	spin_unlock(&ctx->lock);
-}
-
-/*
- * Disable a counter.
- *
- * If counter->ctx is a cloned context, callers must make sure that
- * every task struct that counter->ctx->task could possibly point to
- * remains valid.  This condition is satisifed when called through
- * perf_counter_for_each_child or perf_counter_for_each because they
- * hold the top-level counter's child_mutex, so any descendant that
- * goes to exit will block in sync_child_counter.
- * When called from perf_pending_counter it's OK because counter->ctx
- * is the current context on this CPU and preemption is disabled,
- * hence we can't get into perf_counter_task_sched_out for this context.
- */
-static void perf_counter_disable(struct perf_counter *counter)
-{
-	struct perf_counter_context *ctx = counter->ctx;
-	struct task_struct *task = ctx->task;
-
-	if (!task) {
-		/*
-		 * Disable the counter on the cpu that it's on
-		 */
-		smp_call_function_single(counter->cpu, __perf_counter_disable,
-					 counter, 1);
-		return;
-	}
-
- retry:
-	task_oncpu_function_call(task, __perf_counter_disable, counter);
-
-	spin_lock_irq(&ctx->lock);
-	/*
-	 * If the counter is still active, we need to retry the cross-call.
-	 */
-	if (counter->state == PERF_COUNTER_STATE_ACTIVE) {
-		spin_unlock_irq(&ctx->lock);
-		goto retry;
-	}
-
-	/*
-	 * Since we have the lock this context can't be scheduled
-	 * in, so we can change the state safely.
-	 */
-	if (counter->state == PERF_COUNTER_STATE_INACTIVE) {
-		update_counter_times(counter);
-		counter->state = PERF_COUNTER_STATE_OFF;
-	}
-
-	spin_unlock_irq(&ctx->lock);
-}
-
-static int
-counter_sched_in(struct perf_counter *counter,
-		 struct perf_cpu_context *cpuctx,
-		 struct perf_counter_context *ctx,
-		 int cpu)
-{
-	if (counter->state <= PERF_COUNTER_STATE_OFF)
-		return 0;
-
-	counter->state = PERF_COUNTER_STATE_ACTIVE;
-	counter->oncpu = cpu;	/* TODO: put 'cpu' into cpuctx->cpu */
-	/*
-	 * The new state must be visible before we turn it on in the hardware:
-	 */
-	smp_wmb();
-
-	if (counter->pmu->enable(counter)) {
-		counter->state = PERF_COUNTER_STATE_INACTIVE;
-		counter->oncpu = -1;
-		return -EAGAIN;
-	}
-
-	counter->tstamp_running += ctx->time - counter->tstamp_stopped;
-
-	if (!is_software_counter(counter))
-		cpuctx->active_oncpu++;
-	ctx->nr_active++;
-
-	if (counter->attr.exclusive)
-		cpuctx->exclusive = 1;
-
-	return 0;
-}
-
-static int
-group_sched_in(struct perf_counter *group_counter,
-	       struct perf_cpu_context *cpuctx,
-	       struct perf_counter_context *ctx,
-	       int cpu)
-{
-	struct perf_counter *counter, *partial_group;
-	int ret;
-
-	if (group_counter->state == PERF_COUNTER_STATE_OFF)
-		return 0;
-
-	ret = hw_perf_group_sched_in(group_counter, cpuctx, ctx, cpu);
-	if (ret)
-		return ret < 0 ? ret : 0;
-
-	if (counter_sched_in(group_counter, cpuctx, ctx, cpu))
-		return -EAGAIN;
-
-	/*
-	 * Schedule in siblings as one group (if any):
-	 */
-	list_for_each_entry(counter, &group_counter->sibling_list, list_entry) {
-		if (counter_sched_in(counter, cpuctx, ctx, cpu)) {
-			partial_group = counter;
-			goto group_error;
-		}
-	}
-
-	return 0;
-
-group_error:
-	/*
-	 * Groups can be scheduled in as one unit only, so undo any
-	 * partial group before returning:
-	 */
-	list_for_each_entry(counter, &group_counter->sibling_list, list_entry) {
-		if (counter == partial_group)
-			break;
-		counter_sched_out(counter, cpuctx, ctx);
-	}
-	counter_sched_out(group_counter, cpuctx, ctx);
-
-	return -EAGAIN;
-}
-
-/*
- * Return 1 for a group consisting entirely of software counters,
- * 0 if the group contains any hardware counters.
- */
-static int is_software_only_group(struct perf_counter *leader)
-{
-	struct perf_counter *counter;
-
-	if (!is_software_counter(leader))
-		return 0;
-
-	list_for_each_entry(counter, &leader->sibling_list, list_entry)
-		if (!is_software_counter(counter))
-			return 0;
-
-	return 1;
-}
-
-/*
- * Work out whether we can put this counter group on the CPU now.
- */
-static int group_can_go_on(struct perf_counter *counter,
-			   struct perf_cpu_context *cpuctx,
-			   int can_add_hw)
-{
-	/*
-	 * Groups consisting entirely of software counters can always go on.
-	 */
-	if (is_software_only_group(counter))
-		return 1;
-	/*
-	 * If an exclusive group is already on, no other hardware
-	 * counters can go on.
-	 */
-	if (cpuctx->exclusive)
-		return 0;
-	/*
-	 * If this group is exclusive and there are already
-	 * counters on the CPU, it can't go on.
-	 */
-	if (counter->attr.exclusive && cpuctx->active_oncpu)
-		return 0;
-	/*
-	 * Otherwise, try to add it if all previous groups were able
-	 * to go on.
-	 */
-	return can_add_hw;
-}
-
-static void add_counter_to_ctx(struct perf_counter *counter,
-			       struct perf_counter_context *ctx)
-{
-	list_add_counter(counter, ctx);
-	counter->tstamp_enabled = ctx->time;
-	counter->tstamp_running = ctx->time;
-	counter->tstamp_stopped = ctx->time;
-}
-
-/*
- * Cross CPU call to install and enable a performance counter
- *
- * Must be called with ctx->mutex held
- */
-static void __perf_install_in_context(void *info)
-{
-	struct perf_cpu_context *cpuctx = &__get_cpu_var(perf_cpu_context);
-	struct perf_counter *counter = info;
-	struct perf_counter_context *ctx = counter->ctx;
-	struct perf_counter *leader = counter->group_leader;
-	int cpu = smp_processor_id();
-	int err;
-
-	/*
-	 * If this is a task context, we need to check whether it is
-	 * the current task context of this cpu. If not it has been
-	 * scheduled out before the smp call arrived.
-	 * Or possibly this is the right context but it isn't
-	 * on this cpu because it had no counters.
-	 */
-	if (ctx->task && cpuctx->task_ctx != ctx) {
-		if (cpuctx->task_ctx || ctx->task != current)
-			return;
-		cpuctx->task_ctx = ctx;
-	}
-
-	spin_lock(&ctx->lock);
-	ctx->is_active = 1;
-	update_context_time(ctx);
-
-	/*
-	 * Protect the list operation against NMI by disabling the
-	 * counters on a global level. NOP for non NMI based counters.
-	 */
-	perf_disable();
-
-	add_counter_to_ctx(counter, ctx);
-
-	/*
-	 * Don't put the counter on if it is disabled or if
-	 * it is in a group and the group isn't on.
-	 */
-	if (counter->state != PERF_COUNTER_STATE_INACTIVE ||
-	    (leader != counter && leader->state != PERF_COUNTER_STATE_ACTIVE))
-		goto unlock;
-
-	/*
-	 * An exclusive counter can't go on if there are already active
-	 * hardware counters, and no hardware counter can go on if there
-	 * is already an exclusive counter on.
-	 */
-	if (!group_can_go_on(counter, cpuctx, 1))
-		err = -EEXIST;
-	else
-		err = counter_sched_in(counter, cpuctx, ctx, cpu);
-
-	if (err) {
-		/*
-		 * This counter couldn't go on.  If it is in a group
-		 * then we have to pull the whole group off.
-		 * If the counter group is pinned then put it in error state.
-		 */
-		if (leader != counter)
-			group_sched_out(leader, cpuctx, ctx);
-		if (leader->attr.pinned) {
-			update_group_times(leader);
-			leader->state = PERF_COUNTER_STATE_ERROR;
-		}
-	}
-
-	if (!err && !ctx->task && cpuctx->max_pertask)
-		cpuctx->max_pertask--;
-
- unlock:
-	perf_enable();
-
-	spin_unlock(&ctx->lock);
-}
-
-/*
- * Attach a performance counter to a context
- *
- * First we add the counter to the list with the hardware enable bit
- * in counter->hw_config cleared.
- *
- * If the counter is attached to a task which is on a CPU we use a smp
- * call to enable it in the task context. The task might have been
- * scheduled away, but we check this in the smp call again.
- *
- * Must be called with ctx->mutex held.
- */
-static void
-perf_install_in_context(struct perf_counter_context *ctx,
-			struct perf_counter *counter,
-			int cpu)
-{
-	struct task_struct *task = ctx->task;
-
-	if (!task) {
-		/*
-		 * Per cpu counters are installed via an smp call and
-		 * the install is always sucessful.
-		 */
-		smp_call_function_single(cpu, __perf_install_in_context,
-					 counter, 1);
-		return;
-	}
-
-retry:
-	task_oncpu_function_call(task, __perf_install_in_context,
-				 counter);
-
-	spin_lock_irq(&ctx->lock);
-	/*
-	 * we need to retry the smp call.
-	 */
-	if (ctx->is_active && list_empty(&counter->list_entry)) {
-		spin_unlock_irq(&ctx->lock);
-		goto retry;
-	}
-
-	/*
-	 * The lock prevents that this context is scheduled in so we
-	 * can add the counter safely, if it the call above did not
-	 * succeed.
-	 */
-	if (list_empty(&counter->list_entry))
-		add_counter_to_ctx(counter, ctx);
-	spin_unlock_irq(&ctx->lock);
-}
-
-/*
- * Cross CPU call to enable a performance counter
- */
-static void __perf_counter_enable(void *info)
-{
-	struct perf_counter *counter = info;
-	struct perf_cpu_context *cpuctx = &__get_cpu_var(perf_cpu_context);
-	struct perf_counter_context *ctx = counter->ctx;
-	struct perf_counter *leader = counter->group_leader;
-	int err;
-
-	/*
-	 * If this is a per-task counter, need to check whether this
-	 * counter's task is the current task on this cpu.
-	 */
-	if (ctx->task && cpuctx->task_ctx != ctx) {
-		if (cpuctx->task_ctx || ctx->task != current)
-			return;
-		cpuctx->task_ctx = ctx;
-	}
-
-	spin_lock(&ctx->lock);
-	ctx->is_active = 1;
-	update_context_time(ctx);
-
-	if (counter->state >= PERF_COUNTER_STATE_INACTIVE)
-		goto unlock;
-	counter->state = PERF_COUNTER_STATE_INACTIVE;
-	counter->tstamp_enabled = ctx->time - counter->total_time_enabled;
-
-	/*
-	 * If the counter is in a group and isn't the group leader,
-	 * then don't put it on unless the group is on.
-	 */
-	if (leader != counter && leader->state != PERF_COUNTER_STATE_ACTIVE)
-		goto unlock;
-
-	if (!group_can_go_on(counter, cpuctx, 1)) {
-		err = -EEXIST;
-	} else {
-		perf_disable();
-		if (counter == leader)
-			err = group_sched_in(counter, cpuctx, ctx,
-					     smp_processor_id());
-		else
-			err = counter_sched_in(counter, cpuctx, ctx,
-					       smp_processor_id());
-		perf_enable();
-	}
-
-	if (err) {
-		/*
-		 * If this counter can't go on and it's part of a
-		 * group, then the whole group has to come off.
-		 */
-		if (leader != counter)
-			group_sched_out(leader, cpuctx, ctx);
-		if (leader->attr.pinned) {
-			update_group_times(leader);
-			leader->state = PERF_COUNTER_STATE_ERROR;
-		}
-	}
-
- unlock:
-	spin_unlock(&ctx->lock);
-}
-
-/*
- * Enable a counter.
- *
- * If counter->ctx is a cloned context, callers must make sure that
- * every task struct that counter->ctx->task could possibly point to
- * remains valid.  This condition is satisfied when called through
- * perf_counter_for_each_child or perf_counter_for_each as described
- * for perf_counter_disable.
- */
-static void perf_counter_enable(struct perf_counter *counter)
-{
-	struct perf_counter_context *ctx = counter->ctx;
-	struct task_struct *task = ctx->task;
-
-	if (!task) {
-		/*
-		 * Enable the counter on the cpu that it's on
-		 */
-		smp_call_function_single(counter->cpu, __perf_counter_enable,
-					 counter, 1);
-		return;
-	}
-
-	spin_lock_irq(&ctx->lock);
-	if (counter->state >= PERF_COUNTER_STATE_INACTIVE)
-		goto out;
-
-	/*
-	 * If the counter is in error state, clear that first.
-	 * That way, if we see the counter in error state below, we
-	 * know that it has gone back into error state, as distinct
-	 * from the task having been scheduled away before the
-	 * cross-call arrived.
-	 */
-	if (counter->state == PERF_COUNTER_STATE_ERROR)
-		counter->state = PERF_COUNTER_STATE_OFF;
-
- retry:
-	spin_unlock_irq(&ctx->lock);
-	task_oncpu_function_call(task, __perf_counter_enable, counter);
-
-	spin_lock_irq(&ctx->lock);
-
-	/*
-	 * If the context is active and the counter is still off,
-	 * we need to retry the cross-call.
-	 */
-	if (ctx->is_active && counter->state == PERF_COUNTER_STATE_OFF)
-		goto retry;
-
-	/*
-	 * Since we have the lock this context can't be scheduled
-	 * in, so we can change the state safely.
-	 */
-	if (counter->state == PERF_COUNTER_STATE_OFF) {
-		counter->state = PERF_COUNTER_STATE_INACTIVE;
-		counter->tstamp_enabled =
-			ctx->time - counter->total_time_enabled;
-	}
- out:
-	spin_unlock_irq(&ctx->lock);
-}
-
-static int perf_counter_refresh(struct perf_counter *counter, int refresh)
-{
-	/*
-	 * not supported on inherited counters
-	 */
-	if (counter->attr.inherit)
-		return -EINVAL;
-
-	atomic_add(refresh, &counter->event_limit);
-	perf_counter_enable(counter);
-
-	return 0;
-}
-
-void __perf_counter_sched_out(struct perf_counter_context *ctx,
-			      struct perf_cpu_context *cpuctx)
-{
-	struct perf_counter *counter;
-
-	spin_lock(&ctx->lock);
-	ctx->is_active = 0;
-	if (likely(!ctx->nr_counters))
-		goto out;
-	update_context_time(ctx);
-
-	perf_disable();
-	if (ctx->nr_active) {
-		list_for_each_entry(counter, &ctx->counter_list, list_entry) {
-			if (counter != counter->group_leader)
-				counter_sched_out(counter, cpuctx, ctx);
-			else
-				group_sched_out(counter, cpuctx, ctx);
-		}
-	}
-	perf_enable();
- out:
-	spin_unlock(&ctx->lock);
-}
-
-/*
- * Test whether two contexts are equivalent, i.e. whether they
- * have both been cloned from the same version of the same context
- * and they both have the same number of enabled counters.
- * If the number of enabled counters is the same, then the set
- * of enabled counters should be the same, because these are both
- * inherited contexts, therefore we can't access individual counters
- * in them directly with an fd; we can only enable/disable all
- * counters via prctl, or enable/disable all counters in a family
- * via ioctl, which will have the same effect on both contexts.
- */
-static int context_equiv(struct perf_counter_context *ctx1,
-			 struct perf_counter_context *ctx2)
-{
-	return ctx1->parent_ctx && ctx1->parent_ctx == ctx2->parent_ctx
-		&& ctx1->parent_gen == ctx2->parent_gen
-		&& !ctx1->pin_count && !ctx2->pin_count;
-}
-
-static void __perf_counter_read(void *counter);
-
-static void __perf_counter_sync_stat(struct perf_counter *counter,
-				     struct perf_counter *next_counter)
-{
-	u64 value;
-
-	if (!counter->attr.inherit_stat)
-		return;
-
-	/*
-	 * Update the counter value, we cannot use perf_counter_read()
-	 * because we're in the middle of a context switch and have IRQs
-	 * disabled, which upsets smp_call_function_single(), however
-	 * we know the counter must be on the current CPU, therefore we
-	 * don't need to use it.
-	 */
-	switch (counter->state) {
-	case PERF_COUNTER_STATE_ACTIVE:
-		__perf_counter_read(counter);
-		break;
-
-	case PERF_COUNTER_STATE_INACTIVE:
-		update_counter_times(counter);
-		break;
-
-	default:
-		break;
-	}
-
-	/*
-	 * In order to keep per-task stats reliable we need to flip the counter
-	 * values when we flip the contexts.
-	 */
-	value = atomic64_read(&next_counter->count);
-	value = atomic64_xchg(&counter->count, value);
-	atomic64_set(&next_counter->count, value);
-
-	swap(counter->total_time_enabled, next_counter->total_time_enabled);
-	swap(counter->total_time_running, next_counter->total_time_running);
-
-	/*
-	 * Since we swizzled the values, update the user visible data too.
-	 */
-	perf_counter_update_userpage(counter);
-	perf_counter_update_userpage(next_counter);
-}
-
-#define list_next_entry(pos, member) \
-	list_entry(pos->member.next, typeof(*pos), member)
-
-static void perf_counter_sync_stat(struct perf_counter_context *ctx,
-				   struct perf_counter_context *next_ctx)
-{
-	struct perf_counter *counter, *next_counter;
-
-	if (!ctx->nr_stat)
-		return;
-
-	counter = list_first_entry(&ctx->event_list,
-				   struct perf_counter, event_entry);
-
-	next_counter = list_first_entry(&next_ctx->event_list,
-					struct perf_counter, event_entry);
-
-	while (&counter->event_entry != &ctx->event_list &&
-	       &next_counter->event_entry != &next_ctx->event_list) {
-
-		__perf_counter_sync_stat(counter, next_counter);
-
-		counter = list_next_entry(counter, event_entry);
-		next_counter = list_next_entry(next_counter, event_entry);
-	}
-}
-
-/*
- * Called from scheduler to remove the counters of the current task,
- * with interrupts disabled.
- *
- * We stop each counter and update the counter value in counter->count.
- *
- * This does not protect us against NMI, but disable()
- * sets the disabled bit in the control field of counter _before_
- * accessing the counter control register. If a NMI hits, then it will
- * not restart the counter.
- */
-void perf_counter_task_sched_out(struct task_struct *task,
-				 struct task_struct *next, int cpu)
-{
-	struct perf_cpu_context *cpuctx = &per_cpu(perf_cpu_context, cpu);
-	struct perf_counter_context *ctx = task->perf_counter_ctxp;
-	struct perf_counter_context *next_ctx;
-	struct perf_counter_context *parent;
-	struct pt_regs *regs;
-	int do_switch = 1;
-
-	regs = task_pt_regs(task);
-	perf_swcounter_event(PERF_COUNT_SW_CONTEXT_SWITCHES, 1, 1, regs, 0);
-
-	if (likely(!ctx || !cpuctx->task_ctx))
-		return;
-
-	update_context_time(ctx);
-
-	rcu_read_lock();
-	parent = rcu_dereference(ctx->parent_ctx);
-	next_ctx = next->perf_counter_ctxp;
-	if (parent && next_ctx &&
-	    rcu_dereference(next_ctx->parent_ctx) == parent) {
-		/*
-		 * Looks like the two contexts are clones, so we might be
-		 * able to optimize the context switch.  We lock both
-		 * contexts and check that they are clones under the
-		 * lock (including re-checking that neither has been
-		 * uncloned in the meantime).  It doesn't matter which
-		 * order we take the locks because no other cpu could
-		 * be trying to lock both of these tasks.
-		 */
-		spin_lock(&ctx->lock);
-		spin_lock_nested(&next_ctx->lock, SINGLE_DEPTH_NESTING);
-		if (context_equiv(ctx, next_ctx)) {
-			/*
-			 * XXX do we need a memory barrier of sorts
-			 * wrt to rcu_dereference() of perf_counter_ctxp
-			 */
-			task->perf_counter_ctxp = next_ctx;
-			next->perf_counter_ctxp = ctx;
-			ctx->task = next;
-			next_ctx->task = task;
-			do_switch = 0;
-
-			perf_counter_sync_stat(ctx, next_ctx);
-		}
-		spin_unlock(&next_ctx->lock);
-		spin_unlock(&ctx->lock);
-	}
-	rcu_read_unlock();
-
-	if (do_switch) {
-		__perf_counter_sched_out(ctx, cpuctx);
-		cpuctx->task_ctx = NULL;
-	}
-}
-
-/*
- * Called with IRQs disabled
- */
-static void __perf_counter_task_sched_out(struct perf_counter_context *ctx)
-{
-	struct perf_cpu_context *cpuctx = &__get_cpu_var(perf_cpu_context);
-
-	if (!cpuctx->task_ctx)
-		return;
-
-	if (WARN_ON_ONCE(ctx != cpuctx->task_ctx))
-		return;
-
-	__perf_counter_sched_out(ctx, cpuctx);
-	cpuctx->task_ctx = NULL;
-}
-
-/*
- * Called with IRQs disabled
- */
-static void perf_counter_cpu_sched_out(struct perf_cpu_context *cpuctx)
-{
-	__perf_counter_sched_out(&cpuctx->ctx, cpuctx);
-}
-
-static void
-__perf_counter_sched_in(struct perf_counter_context *ctx,
-			struct perf_cpu_context *cpuctx, int cpu)
-{
-	struct perf_counter *counter;
-	int can_add_hw = 1;
-
-	spin_lock(&ctx->lock);
-	ctx->is_active = 1;
-	if (likely(!ctx->nr_counters))
-		goto out;
-
-	ctx->timestamp = perf_clock();
-
-	perf_disable();
-
-	/*
-	 * First go through the list and put on any pinned groups
-	 * in order to give them the best chance of going on.
-	 */
-	list_for_each_entry(counter, &ctx->counter_list, list_entry) {
-		if (counter->state <= PERF_COUNTER_STATE_OFF ||
-		    !counter->attr.pinned)
-			continue;
-		if (counter->cpu != -1 && counter->cpu != cpu)
-			continue;
-
-		if (counter != counter->group_leader)
-			counter_sched_in(counter, cpuctx, ctx, cpu);
-		else {
-			if (group_can_go_on(counter, cpuctx, 1))
-				group_sched_in(counter, cpuctx, ctx, cpu);
-		}
-
-		/*
-		 * If this pinned group hasn't been scheduled,
-		 * put it in error state.
-		 */
-		if (counter->state == PERF_COUNTER_STATE_INACTIVE) {
-			update_group_times(counter);
-			counter->state = PERF_COUNTER_STATE_ERROR;
-		}
-	}
-
-	list_for_each_entry(counter, &ctx->counter_list, list_entry) {
-		/*
-		 * Ignore counters in OFF or ERROR state, and
-		 * ignore pinned counters since we did them already.
-		 */
-		if (counter->state <= PERF_COUNTER_STATE_OFF ||
-		    counter->attr.pinned)
-			continue;
-
-		/*
-		 * Listen to the 'cpu' scheduling filter constraint
-		 * of counters:
-		 */
-		if (counter->cpu != -1 && counter->cpu != cpu)
-			continue;
-
-		if (counter != counter->group_leader) {
-			if (counter_sched_in(counter, cpuctx, ctx, cpu))
-				can_add_hw = 0;
-		} else {
-			if (group_can_go_on(counter, cpuctx, can_add_hw)) {
-				if (group_sched_in(counter, cpuctx, ctx, cpu))
-					can_add_hw = 0;
-			}
-		}
-	}
-	perf_enable();
- out:
-	spin_unlock(&ctx->lock);
-}
-
-/*
- * Called from scheduler to add the counters of the current task
- * with interrupts disabled.
- *
- * We restore the counter value and then enable it.
- *
- * This does not protect us against NMI, but enable()
- * sets the enabled bit in the control field of counter _before_
- * accessing the counter control register. If a NMI hits, then it will
- * keep the counter running.
- */
-void perf_counter_task_sched_in(struct task_struct *task, int cpu)
-{
-	struct perf_cpu_context *cpuctx = &per_cpu(perf_cpu_context, cpu);
-	struct perf_counter_context *ctx = task->perf_counter_ctxp;
-
-	if (likely(!ctx))
-		return;
-	if (cpuctx->task_ctx == ctx)
-		return;
-	__perf_counter_sched_in(ctx, cpuctx, cpu);
-	cpuctx->task_ctx = ctx;
-}
-
-static void perf_counter_cpu_sched_in(struct perf_cpu_context *cpuctx, int cpu)
-{
-	struct perf_counter_context *ctx = &cpuctx->ctx;
-
-	__perf_counter_sched_in(ctx, cpuctx, cpu);
-}
-
-#define MAX_INTERRUPTS (~0ULL)
-
-static void perf_log_throttle(struct perf_counter *counter, int enable);
-
-static void perf_adjust_period(struct perf_counter *counter, u64 events)
-{
-	struct hw_perf_counter *hwc = &counter->hw;
-	u64 period, sample_period;
-	s64 delta;
-
-	events *= hwc->sample_period;
-	period = div64_u64(events, counter->attr.sample_freq);
-
-	delta = (s64)(period - hwc->sample_period);
-	delta = (delta + 7) / 8; /* low pass filter */
-
-	sample_period = hwc->sample_period + delta;
-
-	if (!sample_period)
-		sample_period = 1;
-
-	hwc->sample_period = sample_period;
-}
-
-static void perf_ctx_adjust_freq(struct perf_counter_context *ctx)
-{
-	struct perf_counter *counter;
-	struct hw_perf_counter *hwc;
-	u64 interrupts, freq;
-
-	spin_lock(&ctx->lock);
-	list_for_each_entry(counter, &ctx->counter_list, list_entry) {
-		if (counter->state != PERF_COUNTER_STATE_ACTIVE)
-			continue;
-
-		hwc = &counter->hw;
-
-		interrupts = hwc->interrupts;
-		hwc->interrupts = 0;
-
-		/*
-		 * unthrottle counters on the tick
-		 */
-		if (interrupts == MAX_INTERRUPTS) {
-			perf_log_throttle(counter, 1);
-			counter->pmu->unthrottle(counter);
-			interrupts = 2*sysctl_perf_counter_sample_rate/HZ;
-		}
-
-		if (!counter->attr.freq || !counter->attr.sample_freq)
-			continue;
-
-		/*
-		 * if the specified freq < HZ then we need to skip ticks
-		 */
-		if (counter->attr.sample_freq < HZ) {
-			freq = counter->attr.sample_freq;
-
-			hwc->freq_count += freq;
-			hwc->freq_interrupts += interrupts;
-
-			if (hwc->freq_count < HZ)
-				continue;
-
-			interrupts = hwc->freq_interrupts;
-			hwc->freq_interrupts = 0;
-			hwc->freq_count -= HZ;
-		} else
-			freq = HZ;
-
-		perf_adjust_period(counter, freq * interrupts);
-
-		/*
-		 * In order to avoid being stalled by an (accidental) huge
-		 * sample period, force reset the sample period if we didn't
-		 * get any events in this freq period.
-		 */
-		if (!interrupts) {
-			perf_disable();
-			counter->pmu->disable(counter);
-			atomic64_set(&hwc->period_left, 0);
-			counter->pmu->enable(counter);
-			perf_enable();
-		}
-	}
-	spin_unlock(&ctx->lock);
-}
-
-/*
- * Round-robin a context's counters:
- */
-static void rotate_ctx(struct perf_counter_context *ctx)
-{
-	struct perf_counter *counter;
-
-	if (!ctx->nr_counters)
-		return;
-
-	spin_lock(&ctx->lock);
-	/*
-	 * Rotate the first entry last (works just fine for group counters too):
-	 */
-	perf_disable();
-	list_for_each_entry(counter, &ctx->counter_list, list_entry) {
-		list_move_tail(&counter->list_entry, &ctx->counter_list);
-		break;
-	}
-	perf_enable();
-
-	spin_unlock(&ctx->lock);
-}
-
-void perf_counter_task_tick(struct task_struct *curr, int cpu)
-{
-	struct perf_cpu_context *cpuctx;
-	struct perf_counter_context *ctx;
-
-	if (!atomic_read(&nr_counters))
-		return;
-
-	cpuctx = &per_cpu(perf_cpu_context, cpu);
-	ctx = curr->perf_counter_ctxp;
-
-	perf_ctx_adjust_freq(&cpuctx->ctx);
-	if (ctx)
-		perf_ctx_adjust_freq(ctx);
-
-	perf_counter_cpu_sched_out(cpuctx);
-	if (ctx)
-		__perf_counter_task_sched_out(ctx);
-
-	rotate_ctx(&cpuctx->ctx);
-	if (ctx)
-		rotate_ctx(ctx);
-
-	perf_counter_cpu_sched_in(cpuctx, cpu);
-	if (ctx)
-		perf_counter_task_sched_in(curr, cpu);
-}
-
-/*
- * Enable all of a task's counters that have been marked enable-on-exec.
- * This expects task == current.
- */
-static void perf_counter_enable_on_exec(struct task_struct *task)
-{
-	struct perf_counter_context *ctx;
-	struct perf_counter *counter;
-	unsigned long flags;
-	int enabled = 0;
-
-	local_irq_save(flags);
-	ctx = task->perf_counter_ctxp;
-	if (!ctx || !ctx->nr_counters)
-		goto out;
-
-	__perf_counter_task_sched_out(ctx);
-
-	spin_lock(&ctx->lock);
-
-	list_for_each_entry(counter, &ctx->counter_list, list_entry) {
-		if (!counter->attr.enable_on_exec)
-			continue;
-		counter->attr.enable_on_exec = 0;
-		if (counter->state >= PERF_COUNTER_STATE_INACTIVE)
-			continue;
-		counter->state = PERF_COUNTER_STATE_INACTIVE;
-		counter->tstamp_enabled =
-			ctx->time - counter->total_time_enabled;
-		enabled = 1;
-	}
-
-	/*
-	 * Unclone this context if we enabled any counter.
-	 */
-	if (enabled)
-		unclone_ctx(ctx);
-
-	spin_unlock(&ctx->lock);
-
-	perf_counter_task_sched_in(task, smp_processor_id());
- out:
-	local_irq_restore(flags);
-}
-
-/*
- * Cross CPU call to read the hardware counter
- */
-static void __perf_counter_read(void *info)
-{
-	struct perf_cpu_context *cpuctx = &__get_cpu_var(perf_cpu_context);
-	struct perf_counter *counter = info;
-	struct perf_counter_context *ctx = counter->ctx;
-	unsigned long flags;
-
-	/*
-	 * If this is a task context, we need to check whether it is
-	 * the current task context of this cpu.  If not it has been
-	 * scheduled out before the smp call arrived.  In that case
-	 * counter->count would have been updated to a recent sample
-	 * when the counter was scheduled out.
-	 */
-	if (ctx->task && cpuctx->task_ctx != ctx)
-		return;
-
-	local_irq_save(flags);
-	if (ctx->is_active)
-		update_context_time(ctx);
-	counter->pmu->read(counter);
-	update_counter_times(counter);
-	local_irq_restore(flags);
-}
-
-static u64 perf_counter_read(struct perf_counter *counter)
-{
-	/*
-	 * If counter is enabled and currently active on a CPU, update the
-	 * value in the counter structure:
-	 */
-	if (counter->state == PERF_COUNTER_STATE_ACTIVE) {
-		smp_call_function_single(counter->oncpu,
-					 __perf_counter_read, counter, 1);
-	} else if (counter->state == PERF_COUNTER_STATE_INACTIVE) {
-		update_counter_times(counter);
-	}
-
-	return atomic64_read(&counter->count);
-}
-
-/*
- * Initialize the perf_counter context in a task_struct:
- */
-static void
-__perf_counter_init_context(struct perf_counter_context *ctx,
-			    struct task_struct *task)
-{
-	memset(ctx, 0, sizeof(*ctx));
-	spin_lock_init(&ctx->lock);
-	mutex_init(&ctx->mutex);
-	INIT_LIST_HEAD(&ctx->counter_list);
-	INIT_LIST_HEAD(&ctx->event_list);
-	atomic_set(&ctx->refcount, 1);
-	ctx->task = task;
-}
-
-static struct perf_counter_context *find_get_context(pid_t pid, int cpu)
-{
-	struct perf_counter_context *ctx;
-	struct perf_cpu_context *cpuctx;
-	struct task_struct *task;
-	unsigned long flags;
-	int err;
-
-	/*
-	 * If cpu is not a wildcard then this is a percpu counter:
-	 */
-	if (cpu != -1) {
-		/* Must be root to operate on a CPU counter: */
-		if (perf_paranoid_cpu() && !capable(CAP_SYS_ADMIN))
-			return ERR_PTR(-EACCES);
-
-		if (cpu < 0 || cpu > num_possible_cpus())
-			return ERR_PTR(-EINVAL);
-
-		/*
-		 * We could be clever and allow to attach a counter to an
-		 * offline CPU and activate it when the CPU comes up, but
-		 * that's for later.
-		 */
-		if (!cpu_isset(cpu, cpu_online_map))
-			return ERR_PTR(-ENODEV);
-
-		cpuctx = &per_cpu(perf_cpu_context, cpu);
-		ctx = &cpuctx->ctx;
-		get_ctx(ctx);
-
-		return ctx;
-	}
-
-	rcu_read_lock();
-	if (!pid)
-		task = current;
-	else
-		task = find_task_by_vpid(pid);
-	if (task)
-		get_task_struct(task);
-	rcu_read_unlock();
-
-	if (!task)
-		return ERR_PTR(-ESRCH);
-
-	/*
-	 * Can't attach counters to a dying task.
-	 */
-	err = -ESRCH;
-	if (task->flags & PF_EXITING)
-		goto errout;
-
-	/* Reuse ptrace permission checks for now. */
-	err = -EACCES;
-	if (!ptrace_may_access(task, PTRACE_MODE_READ))
-		goto errout;
-
- retry:
-	ctx = perf_lock_task_context(task, &flags);
-	if (ctx) {
-		unclone_ctx(ctx);
-		spin_unlock_irqrestore(&ctx->lock, flags);
-	}
-
-	if (!ctx) {
-		ctx = kmalloc(sizeof(struct perf_counter_context), GFP_KERNEL);
-		err = -ENOMEM;
-		if (!ctx)
-			goto errout;
-		__perf_counter_init_context(ctx, task);
-		get_ctx(ctx);
-		if (cmpxchg(&task->perf_counter_ctxp, NULL, ctx)) {
-			/*
-			 * We raced with some other task; use
-			 * the context they set.
-			 */
-			kfree(ctx);
-			goto retry;
-		}
-		get_task_struct(task);
-	}
-
-	put_task_struct(task);
-	return ctx;
-
- errout:
-	put_task_struct(task);
-	return ERR_PTR(err);
-}
-
-static void free_counter_rcu(struct rcu_head *head)
-{
-	struct perf_counter *counter;
-
-	counter = container_of(head, struct perf_counter, rcu_head);
-	if (counter->ns)
-		put_pid_ns(counter->ns);
-	kfree(counter);
-}
-
-static void perf_pending_sync(struct perf_counter *counter);
-
-static void free_counter(struct perf_counter *counter)
-{
-	perf_pending_sync(counter);
-
-	if (!counter->parent) {
-		atomic_dec(&nr_counters);
-		if (counter->attr.mmap)
-			atomic_dec(&nr_mmap_counters);
-		if (counter->attr.comm)
-			atomic_dec(&nr_comm_counters);
-		if (counter->attr.task)
-			atomic_dec(&nr_task_counters);
-	}
-
-	if (counter->destroy)
-		counter->destroy(counter);
-
-	put_ctx(counter->ctx);
-	call_rcu(&counter->rcu_head, free_counter_rcu);
-}
-
-/*
- * Called when the last reference to the file is gone.
- */
-static int perf_release(struct inode *inode, struct file *file)
-{
-	struct perf_counter *counter = file->private_data;
-	struct perf_counter_context *ctx = counter->ctx;
-
-	file->private_data = NULL;
-
-	WARN_ON_ONCE(ctx->parent_ctx);
-	mutex_lock(&ctx->mutex);
-	perf_counter_remove_from_context(counter);
-	mutex_unlock(&ctx->mutex);
-
-	mutex_lock(&counter->owner->perf_counter_mutex);
-	list_del_init(&counter->owner_entry);
-	mutex_unlock(&counter->owner->perf_counter_mutex);
-	put_task_struct(counter->owner);
-
-	free_counter(counter);
-
-	return 0;
-}
-
-static int perf_counter_read_size(struct perf_counter *counter)
-{
-	int entry = sizeof(u64); /* value */
-	int size = 0;
-	int nr = 1;
-
-	if (counter->attr.read_format & PERF_FORMAT_TOTAL_TIME_ENABLED)
-		size += sizeof(u64);
-
-	if (counter->attr.read_format & PERF_FORMAT_TOTAL_TIME_RUNNING)
-		size += sizeof(u64);
-
-	if (counter->attr.read_format & PERF_FORMAT_ID)
-		entry += sizeof(u64);
-
-	if (counter->attr.read_format & PERF_FORMAT_GROUP) {
-		nr += counter->group_leader->nr_siblings;
-		size += sizeof(u64);
-	}
-
-	size += entry * nr;
-
-	return size;
-}
-
-static u64 perf_counter_read_value(struct perf_counter *counter)
-{
-	struct perf_counter *child;
-	u64 total = 0;
-
-	total += perf_counter_read(counter);
-	list_for_each_entry(child, &counter->child_list, child_list)
-		total += perf_counter_read(child);
-
-	return total;
-}
-
-static int perf_counter_read_entry(struct perf_counter *counter,
-				   u64 read_format, char __user *buf)
-{
-	int n = 0, count = 0;
-	u64 values[2];
-
-	values[n++] = perf_counter_read_value(counter);
-	if (read_format & PERF_FORMAT_ID)
-		values[n++] = primary_counter_id(counter);
-
-	count = n * sizeof(u64);
-
-	if (copy_to_user(buf, values, count))
-		return -EFAULT;
-
-	return count;
-}
-
-static int perf_counter_read_group(struct perf_counter *counter,
-				   u64 read_format, char __user *buf)
-{
-	struct perf_counter *leader = counter->group_leader, *sub;
-	int n = 0, size = 0, err = -EFAULT;
-	u64 values[3];
-
-	values[n++] = 1 + leader->nr_siblings;
-	if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) {
-		values[n++] = leader->total_time_enabled +
-			atomic64_read(&leader->child_total_time_enabled);
-	}
-	if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING) {
-		values[n++] = leader->total_time_running +
-			atomic64_read(&leader->child_total_time_running);
-	}
-
-	size = n * sizeof(u64);
-
-	if (copy_to_user(buf, values, size))
-		return -EFAULT;
-
-	err = perf_counter_read_entry(leader, read_format, buf + size);
-	if (err < 0)
-		return err;
-
-	size += err;
-
-	list_for_each_entry(sub, &leader->sibling_list, list_entry) {
-		err = perf_counter_read_entry(sub, read_format,
-				buf + size);
-		if (err < 0)
-			return err;
-
-		size += err;
-	}
-
-	return size;
-}
-
-static int perf_counter_read_one(struct perf_counter *counter,
-				 u64 read_format, char __user *buf)
-{
-	u64 values[4];
-	int n = 0;
-
-	values[n++] = perf_counter_read_value(counter);
-	if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) {
-		values[n++] = counter->total_time_enabled +
-			atomic64_read(&counter->child_total_time_enabled);
-	}
-	if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING) {
-		values[n++] = counter->total_time_running +
-			atomic64_read(&counter->child_total_time_running);
-	}
-	if (read_format & PERF_FORMAT_ID)
-		values[n++] = primary_counter_id(counter);
-
-	if (copy_to_user(buf, values, n * sizeof(u64)))
-		return -EFAULT;
-
-	return n * sizeof(u64);
-}
-
-/*
- * Read the performance counter - simple non blocking version for now
- */
-static ssize_t
-perf_read_hw(struct perf_counter *counter, char __user *buf, size_t count)
-{
-	u64 read_format = counter->attr.read_format;
-	int ret;
-
-	/*
-	 * Return end-of-file for a read on a counter that is in
-	 * error state (i.e. because it was pinned but it couldn't be
-	 * scheduled on to the CPU at some point).
-	 */
-	if (counter->state == PERF_COUNTER_STATE_ERROR)
-		return 0;
-
-	if (count < perf_counter_read_size(counter))
-		return -ENOSPC;
-
-	WARN_ON_ONCE(counter->ctx->parent_ctx);
-	mutex_lock(&counter->child_mutex);
-	if (read_format & PERF_FORMAT_GROUP)
-		ret = perf_counter_read_group(counter, read_format, buf);
-	else
-		ret = perf_counter_read_one(counter, read_format, buf);
-	mutex_unlock(&counter->child_mutex);
-
-	return ret;
-}
-
-static ssize_t
-perf_read(struct file *file, char __user *buf, size_t count, loff_t *ppos)
-{
-	struct perf_counter *counter = file->private_data;
-
-	return perf_read_hw(counter, buf, count);
-}
-
-static unsigned int perf_poll(struct file *file, poll_table *wait)
-{
-	struct perf_counter *counter = file->private_data;
-	struct perf_mmap_data *data;
-	unsigned int events = POLL_HUP;
-
-	rcu_read_lock();
-	data = rcu_dereference(counter->data);
-	if (data)
-		events = atomic_xchg(&data->poll, 0);
-	rcu_read_unlock();
-
-	poll_wait(file, &counter->waitq, wait);
-
-	return events;
-}
-
-static void perf_counter_reset(struct perf_counter *counter)
-{
-	(void)perf_counter_read(counter);
-	atomic64_set(&counter->count, 0);
-	perf_counter_update_userpage(counter);
-}
-
-/*
- * Holding the top-level counter's child_mutex means that any
- * descendant process that has inherited this counter will block
- * in sync_child_counter if it goes to exit, thus satisfying the
- * task existence requirements of perf_counter_enable/disable.
- */
-static void perf_counter_for_each_child(struct perf_counter *counter,
-					void (*func)(struct perf_counter *))
-{
-	struct perf_counter *child;
-
-	WARN_ON_ONCE(counter->ctx->parent_ctx);
-	mutex_lock(&counter->child_mutex);
-	func(counter);
-	list_for_each_entry(child, &counter->child_list, child_list)
-		func(child);
-	mutex_unlock(&counter->child_mutex);
-}
-
-static void perf_counter_for_each(struct perf_counter *counter,
-				  void (*func)(struct perf_counter *))
-{
-	struct perf_counter_context *ctx = counter->ctx;
-	struct perf_counter *sibling;
-
-	WARN_ON_ONCE(ctx->parent_ctx);
-	mutex_lock(&ctx->mutex);
-	counter = counter->group_leader;
-
-	perf_counter_for_each_child(counter, func);
-	func(counter);
-	list_for_each_entry(sibling, &counter->sibling_list, list_entry)
-		perf_counter_for_each_child(counter, func);
-	mutex_unlock(&ctx->mutex);
-}
-
-static int perf_counter_period(struct perf_counter *counter, u64 __user *arg)
-{
-	struct perf_counter_context *ctx = counter->ctx;
-	unsigned long size;
-	int ret = 0;
-	u64 value;
-
-	if (!counter->attr.sample_period)
-		return -EINVAL;
-
-	size = copy_from_user(&value, arg, sizeof(value));
-	if (size != sizeof(value))
-		return -EFAULT;
-
-	if (!value)
-		return -EINVAL;
-
-	spin_lock_irq(&ctx->lock);
-	if (counter->attr.freq) {
-		if (value > sysctl_perf_counter_sample_rate) {
-			ret = -EINVAL;
-			goto unlock;
-		}
-
-		counter->attr.sample_freq = value;
-	} else {
-		counter->attr.sample_period = value;
-		counter->hw.sample_period = value;
-	}
-unlock:
-	spin_unlock_irq(&ctx->lock);
-
-	return ret;
-}
-
-static long perf_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
-{
-	struct perf_counter *counter = file->private_data;
-	void (*func)(struct perf_counter *);
-	u32 flags = arg;
-
-	switch (cmd) {
-	case PERF_COUNTER_IOC_ENABLE:
-		func = perf_counter_enable;
-		break;
-	case PERF_COUNTER_IOC_DISABLE:
-		func = perf_counter_disable;
-		break;
-	case PERF_COUNTER_IOC_RESET:
-		func = perf_counter_reset;
-		break;
-
-	case PERF_COUNTER_IOC_REFRESH:
-		return perf_counter_refresh(counter, arg);
-
-	case PERF_COUNTER_IOC_PERIOD:
-		return perf_counter_period(counter, (u64 __user *)arg);
-
-	default:
-		return -ENOTTY;
-	}
-
-	if (flags & PERF_IOC_FLAG_GROUP)
-		perf_counter_for_each(counter, func);
-	else
-		perf_counter_for_each_child(counter, func);
-
-	return 0;
-}
-
-int perf_counter_task_enable(void)
-{
-	struct perf_counter *counter;
-
-	mutex_lock(&current->perf_counter_mutex);
-	list_for_each_entry(counter, &current->perf_counter_list, owner_entry)
-		perf_counter_for_each_child(counter, perf_counter_enable);
-	mutex_unlock(&current->perf_counter_mutex);
-
-	return 0;
-}
-
-int perf_counter_task_disable(void)
-{
-	struct perf_counter *counter;
-
-	mutex_lock(&current->perf_counter_mutex);
-	list_for_each_entry(counter, &current->perf_counter_list, owner_entry)
-		perf_counter_for_each_child(counter, perf_counter_disable);
-	mutex_unlock(&current->perf_counter_mutex);
-
-	return 0;
-}
-
-#ifndef PERF_COUNTER_INDEX_OFFSET
-# define PERF_COUNTER_INDEX_OFFSET 0
-#endif
-
-static int perf_counter_index(struct perf_counter *counter)
-{
-	if (counter->state != PERF_COUNTER_STATE_ACTIVE)
-		return 0;
-
-	return counter->hw.idx + 1 - PERF_COUNTER_INDEX_OFFSET;
-}
-
-/*
- * Callers need to ensure there can be no nesting of this function, otherwise
- * the seqlock logic goes bad. We can not serialize this because the arch
- * code calls this from NMI context.
- */
-void perf_counter_update_userpage(struct perf_counter *counter)
-{
-	struct perf_counter_mmap_page *userpg;
-	struct perf_mmap_data *data;
-
-	rcu_read_lock();
-	data = rcu_dereference(counter->data);
-	if (!data)
-		goto unlock;
-
-	userpg = data->user_page;
-
-	/*
-	 * Disable preemption so as to not let the corresponding user-space
-	 * spin too long if we get preempted.
-	 */
-	preempt_disable();
-	++userpg->lock;
-	barrier();
-	userpg->index = perf_counter_index(counter);
-	userpg->offset = atomic64_read(&counter->count);
-	if (counter->state == PERF_COUNTER_STATE_ACTIVE)
-		userpg->offset -= atomic64_read(&counter->hw.prev_count);
-
-	userpg->time_enabled = counter->total_time_enabled +
-			atomic64_read(&counter->child_total_time_enabled);
-
-	userpg->time_running = counter->total_time_running +
-			atomic64_read(&counter->child_total_time_running);
-
-	barrier();
-	++userpg->lock;
-	preempt_enable();
-unlock:
-	rcu_read_unlock();
-}
-
-static int perf_mmap_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
-{
-	struct perf_counter *counter = vma->vm_file->private_data;
-	struct perf_mmap_data *data;
-	int ret = VM_FAULT_SIGBUS;
-
-	if (vmf->flags & FAULT_FLAG_MKWRITE) {
-		if (vmf->pgoff == 0)
-			ret = 0;
-		return ret;
-	}
-
-	rcu_read_lock();
-	data = rcu_dereference(counter->data);
-	if (!data)
-		goto unlock;
-
-	if (vmf->pgoff == 0) {
-		vmf->page = virt_to_page(data->user_page);
-	} else {
-		int nr = vmf->pgoff - 1;
-
-		if ((unsigned)nr > data->nr_pages)
-			goto unlock;
-
-		if (vmf->flags & FAULT_FLAG_WRITE)
-			goto unlock;
-
-		vmf->page = virt_to_page(data->data_pages[nr]);
-	}
-
-	get_page(vmf->page);
-	vmf->page->mapping = vma->vm_file->f_mapping;
-	vmf->page->index   = vmf->pgoff;
-
-	ret = 0;
-unlock:
-	rcu_read_unlock();
-
-	return ret;
-}
-
-static int perf_mmap_data_alloc(struct perf_counter *counter, int nr_pages)
-{
-	struct perf_mmap_data *data;
-	unsigned long size;
-	int i;
-
-	WARN_ON(atomic_read(&counter->mmap_count));
-
-	size = sizeof(struct perf_mmap_data);
-	size += nr_pages * sizeof(void *);
-
-	data = kzalloc(size, GFP_KERNEL);
-	if (!data)
-		goto fail;
-
-	data->user_page = (void *)get_zeroed_page(GFP_KERNEL);
-	if (!data->user_page)
-		goto fail_user_page;
-
-	for (i = 0; i < nr_pages; i++) {
-		data->data_pages[i] = (void *)get_zeroed_page(GFP_KERNEL);
-		if (!data->data_pages[i])
-			goto fail_data_pages;
-	}
-
-	data->nr_pages = nr_pages;
-	atomic_set(&data->lock, -1);
-
-	rcu_assign_pointer(counter->data, data);
-
-	return 0;
-
-fail_data_pages:
-	for (i--; i >= 0; i--)
-		free_page((unsigned long)data->data_pages[i]);
-
-	free_page((unsigned long)data->user_page);
-
-fail_user_page:
-	kfree(data);
-
-fail:
-	return -ENOMEM;
-}
-
-static void perf_mmap_free_page(unsigned long addr)
-{
-	struct page *page = virt_to_page((void *)addr);
-
-	page->mapping = NULL;
-	__free_page(page);
-}
-
-static void __perf_mmap_data_free(struct rcu_head *rcu_head)
-{
-	struct perf_mmap_data *data;
-	int i;
-
-	data = container_of(rcu_head, struct perf_mmap_data, rcu_head);
-
-	perf_mmap_free_page((unsigned long)data->user_page);
-	for (i = 0; i < data->nr_pages; i++)
-		perf_mmap_free_page((unsigned long)data->data_pages[i]);
-
-	kfree(data);
-}
-
-static void perf_mmap_data_free(struct perf_counter *counter)
-{
-	struct perf_mmap_data *data = counter->data;
-
-	WARN_ON(atomic_read(&counter->mmap_count));
-
-	rcu_assign_pointer(counter->data, NULL);
-	call_rcu(&data->rcu_head, __perf_mmap_data_free);
-}
-
-static void perf_mmap_open(struct vm_area_struct *vma)
-{
-	struct perf_counter *counter = vma->vm_file->private_data;
-
-	atomic_inc(&counter->mmap_count);
-}
-
-static void perf_mmap_close(struct vm_area_struct *vma)
-{
-	struct perf_counter *counter = vma->vm_file->private_data;
-
-	WARN_ON_ONCE(counter->ctx->parent_ctx);
-	if (atomic_dec_and_mutex_lock(&counter->mmap_count, &counter->mmap_mutex)) {
-		struct user_struct *user = current_user();
-
-		atomic_long_sub(counter->data->nr_pages + 1, &user->locked_vm);
-		vma->vm_mm->locked_vm -= counter->data->nr_locked;
-		perf_mmap_data_free(counter);
-		mutex_unlock(&counter->mmap_mutex);
-	}
-}
-
-static struct vm_operations_struct perf_mmap_vmops = {
-	.open		= perf_mmap_open,
-	.close		= perf_mmap_close,
-	.fault		= perf_mmap_fault,
-	.page_mkwrite	= perf_mmap_fault,
-};
-
-static int perf_mmap(struct file *file, struct vm_area_struct *vma)
-{
-	struct perf_counter *counter = file->private_data;
-	unsigned long user_locked, user_lock_limit;
-	struct user_struct *user = current_user();
-	unsigned long locked, lock_limit;
-	unsigned long vma_size;
-	unsigned long nr_pages;
-	long user_extra, extra;
-	int ret = 0;
-
-	if (!(vma->vm_flags & VM_SHARED))
-		return -EINVAL;
-
-	vma_size = vma->vm_end - vma->vm_start;
-	nr_pages = (vma_size / PAGE_SIZE) - 1;
-
-	/*
-	 * If we have data pages ensure they're a power-of-two number, so we
-	 * can do bitmasks instead of modulo.
-	 */
-	if (nr_pages != 0 && !is_power_of_2(nr_pages))
-		return -EINVAL;
-
-	if (vma_size != PAGE_SIZE * (1 + nr_pages))
-		return -EINVAL;
-
-	if (vma->vm_pgoff != 0)
-		return -EINVAL;
-
-	WARN_ON_ONCE(counter->ctx->parent_ctx);
-	mutex_lock(&counter->mmap_mutex);
-	if (atomic_inc_not_zero(&counter->mmap_count)) {
-		if (nr_pages != counter->data->nr_pages)
-			ret = -EINVAL;
-		goto unlock;
-	}
-
-	user_extra = nr_pages + 1;
-	user_lock_limit = sysctl_perf_counter_mlock >> (PAGE_SHIFT - 10);
-
-	/*
-	 * Increase the limit linearly with more CPUs:
-	 */
-	user_lock_limit *= num_online_cpus();
-
-	user_locked = atomic_long_read(&user->locked_vm) + user_extra;
-
-	extra = 0;
-	if (user_locked > user_lock_limit)
-		extra = user_locked - user_lock_limit;
-
-	lock_limit = current->signal->rlim[RLIMIT_MEMLOCK].rlim_cur;
-	lock_limit >>= PAGE_SHIFT;
-	locked = vma->vm_mm->locked_vm + extra;
-
-	if ((locked > lock_limit) && !capable(CAP_IPC_LOCK)) {
-		ret = -EPERM;
-		goto unlock;
-	}
-
-	WARN_ON(counter->data);
-	ret = perf_mmap_data_alloc(counter, nr_pages);
-	if (ret)
-		goto unlock;
-
-	atomic_set(&counter->mmap_count, 1);
-	atomic_long_add(user_extra, &user->locked_vm);
-	vma->vm_mm->locked_vm += extra;
-	counter->data->nr_locked = extra;
-	if (vma->vm_flags & VM_WRITE)
-		counter->data->writable = 1;
-
-unlock:
-	mutex_unlock(&counter->mmap_mutex);
-
-	vma->vm_flags |= VM_RESERVED;
-	vma->vm_ops = &perf_mmap_vmops;
-
-	return ret;
-}
-
-static int perf_fasync(int fd, struct file *filp, int on)
-{
-	struct inode *inode = filp->f_path.dentry->d_inode;
-	struct perf_counter *counter = filp->private_data;
-	int retval;
-
-	mutex_lock(&inode->i_mutex);
-	retval = fasync_helper(fd, filp, on, &counter->fasync);
-	mutex_unlock(&inode->i_mutex);
-
-	if (retval < 0)
-		return retval;
-
-	return 0;
-}
-
-static const struct file_operations perf_fops = {
-	.release		= perf_release,
-	.read			= perf_read,
-	.poll			= perf_poll,
-	.unlocked_ioctl		= perf_ioctl,
-	.compat_ioctl		= perf_ioctl,
-	.mmap			= perf_mmap,
-	.fasync			= perf_fasync,
-};
-
-/*
- * Perf counter wakeup
- *
- * If there's data, ensure we set the poll() state and publish everything
- * to user-space before waking everybody up.
- */
-
-void perf_counter_wakeup(struct perf_counter *counter)
-{
-	wake_up_all(&counter->waitq);
-
-	if (counter->pending_kill) {
-		kill_fasync(&counter->fasync, SIGIO, counter->pending_kill);
-		counter->pending_kill = 0;
-	}
-}
-
-/*
- * Pending wakeups
- *
- * Handle the case where we need to wakeup up from NMI (or rq->lock) context.
- *
- * The NMI bit means we cannot possibly take locks. Therefore, maintain a
- * single linked list and use cmpxchg() to add entries lockless.
- */
-
-static void perf_pending_counter(struct perf_pending_entry *entry)
-{
-	struct perf_counter *counter = container_of(entry,
-			struct perf_counter, pending);
-
-	if (counter->pending_disable) {
-		counter->pending_disable = 0;
-		__perf_counter_disable(counter);
-	}
-
-	if (counter->pending_wakeup) {
-		counter->pending_wakeup = 0;
-		perf_counter_wakeup(counter);
-	}
-}
-
-#define PENDING_TAIL ((struct perf_pending_entry *)-1UL)
-
-static DEFINE_PER_CPU(struct perf_pending_entry *, perf_pending_head) = {
-	PENDING_TAIL,
-};
-
-static void perf_pending_queue(struct perf_pending_entry *entry,
-			       void (*func)(struct perf_pending_entry *))
-{
-	struct perf_pending_entry **head;
-
-	if (cmpxchg(&entry->next, NULL, PENDING_TAIL) != NULL)
-		return;
-
-	entry->func = func;
-
-	head = &get_cpu_var(perf_pending_head);
-
-	do {
-		entry->next = *head;
-	} while (cmpxchg(head, entry->next, entry) != entry->next);
-
-	set_perf_counter_pending();
-
-	put_cpu_var(perf_pending_head);
-}
-
-static int __perf_pending_run(void)
-{
-	struct perf_pending_entry *list;
-	int nr = 0;
-
-	list = xchg(&__get_cpu_var(perf_pending_head), PENDING_TAIL);
-	while (list != PENDING_TAIL) {
-		void (*func)(struct perf_pending_entry *);
-		struct perf_pending_entry *entry = list;
-
-		list = list->next;
-
-		func = entry->func;
-		entry->next = NULL;
-		/*
-		 * Ensure we observe the unqueue before we issue the wakeup,
-		 * so that we won't be waiting forever.
-		 * -- see perf_not_pending().
-		 */
-		smp_wmb();
-
-		func(entry);
-		nr++;
-	}
-
-	return nr;
-}
-
-static inline int perf_not_pending(struct perf_counter *counter)
-{
-	/*
-	 * If we flush on whatever cpu we run, there is a chance we don't
-	 * need to wait.
-	 */
-	get_cpu();
-	__perf_pending_run();
-	put_cpu();
-
-	/*
-	 * Ensure we see the proper queue state before going to sleep
-	 * so that we do not miss the wakeup. -- see perf_pending_handle()
-	 */
-	smp_rmb();
-	return counter->pending.next == NULL;
-}
-
-static void perf_pending_sync(struct perf_counter *counter)
-{
-	wait_event(counter->waitq, perf_not_pending(counter));
-}
-
-void perf_counter_do_pending(void)
-{
-	__perf_pending_run();
-}
-
-/*
- * Callchain support -- arch specific
- */
-
-__weak struct perf_callchain_entry *perf_callchain(struct pt_regs *regs)
-{
-	return NULL;
-}
-
-/*
- * Output
- */
-
-struct perf_output_handle {
-	struct perf_counter	*counter;
-	struct perf_mmap_data	*data;
-	unsigned long		head;
-	unsigned long		offset;
-	int			nmi;
-	int			sample;
-	int			locked;
-	unsigned long		flags;
-};
-
-static bool perf_output_space(struct perf_mmap_data *data,
-			      unsigned int offset, unsigned int head)
-{
-	unsigned long tail;
-	unsigned long mask;
-
-	if (!data->writable)
-		return true;
-
-	mask = (data->nr_pages << PAGE_SHIFT) - 1;
-	/*
-	 * Userspace could choose to issue a mb() before updating the tail
-	 * pointer. So that all reads will be completed before the write is
-	 * issued.
-	 */
-	tail = ACCESS_ONCE(data->user_page->data_tail);
-	smp_rmb();
-
-	offset = (offset - tail) & mask;
-	head   = (head   - tail) & mask;
-
-	if ((int)(head - offset) < 0)
-		return false;
-
-	return true;
-}
-
-static void perf_output_wakeup(struct perf_output_handle *handle)
-{
-	atomic_set(&handle->data->poll, POLL_IN);
-
-	if (handle->nmi) {
-		handle->counter->pending_wakeup = 1;
-		perf_pending_queue(&handle->counter->pending,
-				   perf_pending_counter);
-	} else
-		perf_counter_wakeup(handle->counter);
-}
-
-/*
- * Curious locking construct.
- *
- * We need to ensure a later event doesn't publish a head when a former
- * event isn't done writing. However since we need to deal with NMIs we
- * cannot fully serialize things.
- *
- * What we do is serialize between CPUs so we only have to deal with NMI
- * nesting on a single CPU.
- *
- * We only publish the head (and generate a wakeup) when the outer-most
- * event completes.
- */
-static void perf_output_lock(struct perf_output_handle *handle)
-{
-	struct perf_mmap_data *data = handle->data;
-	int cpu;
-
-	handle->locked = 0;
-
-	local_irq_save(handle->flags);
-	cpu = smp_processor_id();
-
-	if (in_nmi() && atomic_read(&data->lock) == cpu)
-		return;
-
-	while (atomic_cmpxchg(&data->lock, -1, cpu) != -1)
-		cpu_relax();
-
-	handle->locked = 1;
-}
-
-static void perf_output_unlock(struct perf_output_handle *handle)
-{
-	struct perf_mmap_data *data = handle->data;
-	unsigned long head;
-	int cpu;
-
-	data->done_head = data->head;
-
-	if (!handle->locked)
-		goto out;
-
-again:
-	/*
-	 * The xchg implies a full barrier that ensures all writes are done
-	 * before we publish the new head, matched by a rmb() in userspace when
-	 * reading this position.
-	 */
-	while ((head = atomic_long_xchg(&data->done_head, 0)))
-		data->user_page->data_head = head;
-
-	/*
-	 * NMI can happen here, which means we can miss a done_head update.
-	 */
-
-	cpu = atomic_xchg(&data->lock, -1);
-	WARN_ON_ONCE(cpu != smp_processor_id());
-
-	/*
-	 * Therefore we have to validate we did not indeed do so.
-	 */
-	if (unlikely(atomic_long_read(&data->done_head))) {
-		/*
-		 * Since we had it locked, we can lock it again.
-		 */
-		while (atomic_cmpxchg(&data->lock, -1, cpu) != -1)
-			cpu_relax();
-
-		goto again;
-	}
-
-	if (atomic_xchg(&data->wakeup, 0))
-		perf_output_wakeup(handle);
-out:
-	local_irq_restore(handle->flags);
-}
-
-static void perf_output_copy(struct perf_output_handle *handle,
-			     const void *buf, unsigned int len)
-{
-	unsigned int pages_mask;
-	unsigned int offset;
-	unsigned int size;
-	void **pages;
-
-	offset		= handle->offset;
-	pages_mask	= handle->data->nr_pages - 1;
-	pages		= handle->data->data_pages;
-
-	do {
-		unsigned int page_offset;
-		int nr;
-
-		nr	    = (offset >> PAGE_SHIFT) & pages_mask;
-		page_offset = offset & (PAGE_SIZE - 1);
-		size	    = min_t(unsigned int, PAGE_SIZE - page_offset, len);
-
-		memcpy(pages[nr] + page_offset, buf, size);
-
-		len	    -= size;
-		buf	    += size;
-		offset	    += size;
-	} while (len);
-
-	handle->offset = offset;
-
-	/*
-	 * Check we didn't copy past our reservation window, taking the
-	 * possible unsigned int wrap into account.
-	 */
-	WARN_ON_ONCE(((long)(handle->head - handle->offset)) < 0);
-}
-
-#define perf_output_put(handle, x) \
-	perf_output_copy((handle), &(x), sizeof(x))
-
-static int perf_output_begin(struct perf_output_handle *handle,
-			     struct perf_counter *counter, unsigned int size,
-			     int nmi, int sample)
-{
-	struct perf_mmap_data *data;
-	unsigned int offset, head;
-	int have_lost;
-	struct {
-		struct perf_event_header header;
-		u64			 id;
-		u64			 lost;
-	} lost_event;
-
-	/*
-	 * For inherited counters we send all the output towards the parent.
-	 */
-	if (counter->parent)
-		counter = counter->parent;
-
-	rcu_read_lock();
-	data = rcu_dereference(counter->data);
-	if (!data)
-		goto out;
-
-	handle->data	= data;
-	handle->counter	= counter;
-	handle->nmi	= nmi;
-	handle->sample	= sample;
-
-	if (!data->nr_pages)
-		goto fail;
-
-	have_lost = atomic_read(&data->lost);
-	if (have_lost)
-		size += sizeof(lost_event);
-
-	perf_output_lock(handle);
-
-	do {
-		offset = head = atomic_long_read(&data->head);
-		head += size;
-		if (unlikely(!perf_output_space(data, offset, head)))
-			goto fail;
-	} while (atomic_long_cmpxchg(&data->head, offset, head) != offset);
-
-	handle->offset	= offset;
-	handle->head	= head;
-
-	if ((offset >> PAGE_SHIFT) != (head >> PAGE_SHIFT))
-		atomic_set(&data->wakeup, 1);
-
-	if (have_lost) {
-		lost_event.header.type = PERF_EVENT_LOST;
-		lost_event.header.misc = 0;
-		lost_event.header.size = sizeof(lost_event);
-		lost_event.id          = counter->id;
-		lost_event.lost        = atomic_xchg(&data->lost, 0);
-
-		perf_output_put(handle, lost_event);
-	}
-
-	return 0;
-
-fail:
-	atomic_inc(&data->lost);
-	perf_output_unlock(handle);
-out:
-	rcu_read_unlock();
-
-	return -ENOSPC;
-}
-
-static void perf_output_end(struct perf_output_handle *handle)
-{
-	struct perf_counter *counter = handle->counter;
-	struct perf_mmap_data *data = handle->data;
-
-	int wakeup_events = counter->attr.wakeup_events;
-
-	if (handle->sample && wakeup_events) {
-		int events = atomic_inc_return(&data->events);
-		if (events >= wakeup_events) {
-			atomic_sub(wakeup_events, &data->events);
-			atomic_set(&data->wakeup, 1);
-		}
-	}
-
-	perf_output_unlock(handle);
-	rcu_read_unlock();
-}
-
-static u32 perf_counter_pid(struct perf_counter *counter, struct task_struct *p)
-{
-	/*
-	 * only top level counters have the pid namespace they were created in
-	 */
-	if (counter->parent)
-		counter = counter->parent;
-
-	return task_tgid_nr_ns(p, counter->ns);
-}
-
-static u32 perf_counter_tid(struct perf_counter *counter, struct task_struct *p)
-{
-	/*
-	 * only top level counters have the pid namespace they were created in
-	 */
-	if (counter->parent)
-		counter = counter->parent;
-
-	return task_pid_nr_ns(p, counter->ns);
-}
-
-static void perf_output_read_one(struct perf_output_handle *handle,
-				 struct perf_counter *counter)
-{
-	u64 read_format = counter->attr.read_format;
-	u64 values[4];
-	int n = 0;
-
-	values[n++] = atomic64_read(&counter->count);
-	if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) {
-		values[n++] = counter->total_time_enabled +
-			atomic64_read(&counter->child_total_time_enabled);
-	}
-	if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING) {
-		values[n++] = counter->total_time_running +
-			atomic64_read(&counter->child_total_time_running);
-	}
-	if (read_format & PERF_FORMAT_ID)
-		values[n++] = primary_counter_id(counter);
-
-	perf_output_copy(handle, values, n * sizeof(u64));
-}
-
-/*
- * XXX PERF_FORMAT_GROUP vs inherited counters seems difficult.
- */
-static void perf_output_read_group(struct perf_output_handle *handle,
-			    struct perf_counter *counter)
-{
-	struct perf_counter *leader = counter->group_leader, *sub;
-	u64 read_format = counter->attr.read_format;
-	u64 values[5];
-	int n = 0;
-
-	values[n++] = 1 + leader->nr_siblings;
-
-	if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED)
-		values[n++] = leader->total_time_enabled;
-
-	if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING)
-		values[n++] = leader->total_time_running;
-
-	if (leader != counter)
-		leader->pmu->read(leader);
-
-	values[n++] = atomic64_read(&leader->count);
-	if (read_format & PERF_FORMAT_ID)
-		values[n++] = primary_counter_id(leader);
-
-	perf_output_copy(handle, values, n * sizeof(u64));
-
-	list_for_each_entry(sub, &leader->sibling_list, list_entry) {
-		n = 0;
-
-		if (sub != counter)
-			sub->pmu->read(sub);
-
-		values[n++] = atomic64_read(&sub->count);
-		if (read_format & PERF_FORMAT_ID)
-			values[n++] = primary_counter_id(sub);
-
-		perf_output_copy(handle, values, n * sizeof(u64));
-	}
-}
-
-static void perf_output_read(struct perf_output_handle *handle,
-			     struct perf_counter *counter)
-{
-	if (counter->attr.read_format & PERF_FORMAT_GROUP)
-		perf_output_read_group(handle, counter);
-	else
-		perf_output_read_one(handle, counter);
-}
-
-void perf_counter_output(struct perf_counter *counter, int nmi,
-				struct perf_sample_data *data)
-{
-	int ret;
-	u64 sample_type = counter->attr.sample_type;
-	struct perf_output_handle handle;
-	struct perf_event_header header;
-	u64 ip;
-	struct {
-		u32 pid, tid;
-	} tid_entry;
-	struct perf_callchain_entry *callchain = NULL;
-	int callchain_size = 0;
-	u64 time;
-	struct {
-		u32 cpu, reserved;
-	} cpu_entry;
-
-	header.type = PERF_EVENT_SAMPLE;
-	header.size = sizeof(header);
-
-	header.misc = 0;
-	header.misc |= perf_misc_flags(data->regs);
-
-	if (sample_type & PERF_SAMPLE_IP) {
-		ip = perf_instruction_pointer(data->regs);
-		header.size += sizeof(ip);
-	}
-
-	if (sample_type & PERF_SAMPLE_TID) {
-		/* namespace issues */
-		tid_entry.pid = perf_counter_pid(counter, current);
-		tid_entry.tid = perf_counter_tid(counter, current);
-
-		header.size += sizeof(tid_entry);
-	}
-
-	if (sample_type & PERF_SAMPLE_TIME) {
-		/*
-		 * Maybe do better on x86 and provide cpu_clock_nmi()
-		 */
-		time = sched_clock();
-
-		header.size += sizeof(u64);
-	}
-
-	if (sample_type & PERF_SAMPLE_ADDR)
-		header.size += sizeof(u64);
-
-	if (sample_type & PERF_SAMPLE_ID)
-		header.size += sizeof(u64);
-
-	if (sample_type & PERF_SAMPLE_STREAM_ID)
-		header.size += sizeof(u64);
-
-	if (sample_type & PERF_SAMPLE_CPU) {
-		header.size += sizeof(cpu_entry);
-
-		cpu_entry.cpu = raw_smp_processor_id();
-		cpu_entry.reserved = 0;
-	}
-
-	if (sample_type & PERF_SAMPLE_PERIOD)
-		header.size += sizeof(u64);
-
-	if (sample_type & PERF_SAMPLE_READ)
-		header.size += perf_counter_read_size(counter);
-
-	if (sample_type & PERF_SAMPLE_CALLCHAIN) {
-		callchain = perf_callchain(data->regs);
-
-		if (callchain) {
-			callchain_size = (1 + callchain->nr) * sizeof(u64);
-			header.size += callchain_size;
-		} else
-			header.size += sizeof(u64);
-	}
-
-	if (sample_type & PERF_SAMPLE_RAW) {
-		int size = sizeof(u32);
-
-		if (data->raw)
-			size += data->raw->size;
-		else
-			size += sizeof(u32);
-
-		WARN_ON_ONCE(size & (sizeof(u64)-1));
-		header.size += size;
-	}
-
-	ret = perf_output_begin(&handle, counter, header.size, nmi, 1);
-	if (ret)
-		return;
-
-	perf_output_put(&handle, header);
-
-	if (sample_type & PERF_SAMPLE_IP)
-		perf_output_put(&handle, ip);
-
-	if (sample_type & PERF_SAMPLE_TID)
-		perf_output_put(&handle, tid_entry);
-
-	if (sample_type & PERF_SAMPLE_TIME)
-		perf_output_put(&handle, time);
-
-	if (sample_type & PERF_SAMPLE_ADDR)
-		perf_output_put(&handle, data->addr);
-
-	if (sample_type & PERF_SAMPLE_ID) {
-		u64 id = primary_counter_id(counter);
-
-		perf_output_put(&handle, id);
-	}
-
-	if (sample_type & PERF_SAMPLE_STREAM_ID)
-		perf_output_put(&handle, counter->id);
-
-	if (sample_type & PERF_SAMPLE_CPU)
-		perf_output_put(&handle, cpu_entry);
-
-	if (sample_type & PERF_SAMPLE_PERIOD)
-		perf_output_put(&handle, data->period);
-
-	if (sample_type & PERF_SAMPLE_READ)
-		perf_output_read(&handle, counter);
-
-	if (sample_type & PERF_SAMPLE_CALLCHAIN) {
-		if (callchain)
-			perf_output_copy(&handle, callchain, callchain_size);
-		else {
-			u64 nr = 0;
-			perf_output_put(&handle, nr);
-		}
-	}
-
-	if (sample_type & PERF_SAMPLE_RAW) {
-		if (data->raw) {
-			perf_output_put(&handle, data->raw->size);
-			perf_output_copy(&handle, data->raw->data, data->raw->size);
-		} else {
-			struct {
-				u32	size;
-				u32	data;
-			} raw = {
-				.size = sizeof(u32),
-				.data = 0,
-			};
-			perf_output_put(&handle, raw);
-		}
-	}
-
-	perf_output_end(&handle);
-}
-
-/*
- * read event
- */
-
-struct perf_read_event {
-	struct perf_event_header	header;
-
-	u32				pid;
-	u32				tid;
-};
-
-static void
-perf_counter_read_event(struct perf_counter *counter,
-			struct task_struct *task)
-{
-	struct perf_output_handle handle;
-	struct perf_read_event event = {
-		.header = {
-			.type = PERF_EVENT_READ,
-			.misc = 0,
-			.size = sizeof(event) + perf_counter_read_size(counter),
-		},
-		.pid = perf_counter_pid(counter, task),
-		.tid = perf_counter_tid(counter, task),
-	};
-	int ret;
-
-	ret = perf_output_begin(&handle, counter, event.header.size, 0, 0);
-	if (ret)
-		return;
-
-	perf_output_put(&handle, event);
-	perf_output_read(&handle, counter);
-
-	perf_output_end(&handle);
-}
-
-/*
- * task tracking -- fork/exit
- *
- * enabled by: attr.comm | attr.mmap | attr.task
- */
-
-struct perf_task_event {
-	struct task_struct		*task;
-	struct perf_counter_context	*task_ctx;
-
-	struct {
-		struct perf_event_header	header;
-
-		u32				pid;
-		u32				ppid;
-		u32				tid;
-		u32				ptid;
-	} event;
-};
-
-static void perf_counter_task_output(struct perf_counter *counter,
-				     struct perf_task_event *task_event)
-{
-	struct perf_output_handle handle;
-	int size = task_event->event.header.size;
-	struct task_struct *task = task_event->task;
-	int ret = perf_output_begin(&handle, counter, size, 0, 0);
-
-	if (ret)
-		return;
-
-	task_event->event.pid = perf_counter_pid(counter, task);
-	task_event->event.ppid = perf_counter_pid(counter, current);
-
-	task_event->event.tid = perf_counter_tid(counter, task);
-	task_event->event.ptid = perf_counter_tid(counter, current);
-
-	perf_output_put(&handle, task_event->event);
-	perf_output_end(&handle);
-}
-
-static int perf_counter_task_match(struct perf_counter *counter)
-{
-	if (counter->attr.comm || counter->attr.mmap || counter->attr.task)
-		return 1;
-
-	return 0;
-}
-
-static void perf_counter_task_ctx(struct perf_counter_context *ctx,
-				  struct perf_task_event *task_event)
-{
-	struct perf_counter *counter;
-
-	if (system_state != SYSTEM_RUNNING || list_empty(&ctx->event_list))
-		return;
-
-	rcu_read_lock();
-	list_for_each_entry_rcu(counter, &ctx->event_list, event_entry) {
-		if (perf_counter_task_match(counter))
-			perf_counter_task_output(counter, task_event);
-	}
-	rcu_read_unlock();
-}
-
-static void perf_counter_task_event(struct perf_task_event *task_event)
-{
-	struct perf_cpu_context *cpuctx;
-	struct perf_counter_context *ctx = task_event->task_ctx;
-
-	cpuctx = &get_cpu_var(perf_cpu_context);
-	perf_counter_task_ctx(&cpuctx->ctx, task_event);
-	put_cpu_var(perf_cpu_context);
-
-	rcu_read_lock();
-	if (!ctx)
-		ctx = rcu_dereference(task_event->task->perf_counter_ctxp);
-	if (ctx)
-		perf_counter_task_ctx(ctx, task_event);
-	rcu_read_unlock();
-}
-
-static void perf_counter_task(struct task_struct *task,
-			      struct perf_counter_context *task_ctx,
-			      int new)
-{
-	struct perf_task_event task_event;
-
-	if (!atomic_read(&nr_comm_counters) &&
-	    !atomic_read(&nr_mmap_counters) &&
-	    !atomic_read(&nr_task_counters))
-		return;
-
-	task_event = (struct perf_task_event){
-		.task	  = task,
-		.task_ctx = task_ctx,
-		.event    = {
-			.header = {
-				.type = new ? PERF_EVENT_FORK : PERF_EVENT_EXIT,
-				.misc = 0,
-				.size = sizeof(task_event.event),
-			},
-			/* .pid  */
-			/* .ppid */
-			/* .tid  */
-			/* .ptid */
-		},
-	};
-
-	perf_counter_task_event(&task_event);
-}
-
-void perf_counter_fork(struct task_struct *task)
-{
-	perf_counter_task(task, NULL, 1);
-}
-
-/*
- * comm tracking
- */
-
-struct perf_comm_event {
-	struct task_struct	*task;
-	char			*comm;
-	int			comm_size;
-
-	struct {
-		struct perf_event_header	header;
-
-		u32				pid;
-		u32				tid;
-	} event;
-};
-
-static void perf_counter_comm_output(struct perf_counter *counter,
-				     struct perf_comm_event *comm_event)
-{
-	struct perf_output_handle handle;
-	int size = comm_event->event.header.size;
-	int ret = perf_output_begin(&handle, counter, size, 0, 0);
-
-	if (ret)
-		return;
-
-	comm_event->event.pid = perf_counter_pid(counter, comm_event->task);
-	comm_event->event.tid = perf_counter_tid(counter, comm_event->task);
-
-	perf_output_put(&handle, comm_event->event);
-	perf_output_copy(&handle, comm_event->comm,
-				   comm_event->comm_size);
-	perf_output_end(&handle);
-}
-
-static int perf_counter_comm_match(struct perf_counter *counter)
-{
-	if (counter->attr.comm)
-		return 1;
-
-	return 0;
-}
-
-static void perf_counter_comm_ctx(struct perf_counter_context *ctx,
-				  struct perf_comm_event *comm_event)
-{
-	struct perf_counter *counter;
-
-	if (system_state != SYSTEM_RUNNING || list_empty(&ctx->event_list))
-		return;
-
-	rcu_read_lock();
-	list_for_each_entry_rcu(counter, &ctx->event_list, event_entry) {
-		if (perf_counter_comm_match(counter))
-			perf_counter_comm_output(counter, comm_event);
-	}
-	rcu_read_unlock();
-}
-
-static void perf_counter_comm_event(struct perf_comm_event *comm_event)
-{
-	struct perf_cpu_context *cpuctx;
-	struct perf_counter_context *ctx;
-	unsigned int size;
-	char comm[TASK_COMM_LEN];
-
-	memset(comm, 0, sizeof(comm));
-	strncpy(comm, comm_event->task->comm, sizeof(comm));
-	size = ALIGN(strlen(comm)+1, sizeof(u64));
-
-	comm_event->comm = comm;
-	comm_event->comm_size = size;
-
-	comm_event->event.header.size = sizeof(comm_event->event) + size;
-
-	cpuctx = &get_cpu_var(perf_cpu_context);
-	perf_counter_comm_ctx(&cpuctx->ctx, comm_event);
-	put_cpu_var(perf_cpu_context);
-
-	rcu_read_lock();
-	/*
-	 * doesn't really matter which of the child contexts the
-	 * events ends up in.
-	 */
-	ctx = rcu_dereference(current->perf_counter_ctxp);
-	if (ctx)
-		perf_counter_comm_ctx(ctx, comm_event);
-	rcu_read_unlock();
-}
-
-void perf_counter_comm(struct task_struct *task)
-{
-	struct perf_comm_event comm_event;
-
-	if (task->perf_counter_ctxp)
-		perf_counter_enable_on_exec(task);
-
-	if (!atomic_read(&nr_comm_counters))
-		return;
-
-	comm_event = (struct perf_comm_event){
-		.task	= task,
-		/* .comm      */
-		/* .comm_size */
-		.event  = {
-			.header = {
-				.type = PERF_EVENT_COMM,
-				.misc = 0,
-				/* .size */
-			},
-			/* .pid */
-			/* .tid */
-		},
-	};
-
-	perf_counter_comm_event(&comm_event);
-}
-
-/*
- * mmap tracking
- */
-
-struct perf_mmap_event {
-	struct vm_area_struct	*vma;
-
-	const char		*file_name;
-	int			file_size;
-
-	struct {
-		struct perf_event_header	header;
-
-		u32				pid;
-		u32				tid;
-		u64				start;
-		u64				len;
-		u64				pgoff;
-	} event;
-};
-
-static void perf_counter_mmap_output(struct perf_counter *counter,
-				     struct perf_mmap_event *mmap_event)
-{
-	struct perf_output_handle handle;
-	int size = mmap_event->event.header.size;
-	int ret = perf_output_begin(&handle, counter, size, 0, 0);
-
-	if (ret)
-		return;
-
-	mmap_event->event.pid = perf_counter_pid(counter, current);
-	mmap_event->event.tid = perf_counter_tid(counter, current);
-
-	perf_output_put(&handle, mmap_event->event);
-	perf_output_copy(&handle, mmap_event->file_name,
-				   mmap_event->file_size);
-	perf_output_end(&handle);
-}
-
-static int perf_counter_mmap_match(struct perf_counter *counter,
-				   struct perf_mmap_event *mmap_event)
-{
-	if (counter->attr.mmap)
-		return 1;
-
-	return 0;
-}
-
-static void perf_counter_mmap_ctx(struct perf_counter_context *ctx,
-				  struct perf_mmap_event *mmap_event)
-{
-	struct perf_counter *counter;
-
-	if (system_state != SYSTEM_RUNNING || list_empty(&ctx->event_list))
-		return;
-
-	rcu_read_lock();
-	list_for_each_entry_rcu(counter, &ctx->event_list, event_entry) {
-		if (perf_counter_mmap_match(counter, mmap_event))
-			perf_counter_mmap_output(counter, mmap_event);
-	}
-	rcu_read_unlock();
-}
-
-static void perf_counter_mmap_event(struct perf_mmap_event *mmap_event)
-{
-	struct perf_cpu_context *cpuctx;
-	struct perf_counter_context *ctx;
-	struct vm_area_struct *vma = mmap_event->vma;
-	struct file *file = vma->vm_file;
-	unsigned int size;
-	char tmp[16];
-	char *buf = NULL;
-	const char *name;
-
-	memset(tmp, 0, sizeof(tmp));
-
-	if (file) {
-		/*
-		 * d_path works from the end of the buffer backwards, so we
-		 * need to add enough zero bytes after the string to handle
-		 * the 64bit alignment we do later.
-		 */
-		buf = kzalloc(PATH_MAX + sizeof(u64), GFP_KERNEL);
-		if (!buf) {
-			name = strncpy(tmp, "//enomem", sizeof(tmp));
-			goto got_name;
-		}
-		name = d_path(&file->f_path, buf, PATH_MAX);
-		if (IS_ERR(name)) {
-			name = strncpy(tmp, "//toolong", sizeof(tmp));
-			goto got_name;
-		}
-	} else {
-		if (arch_vma_name(mmap_event->vma)) {
-			name = strncpy(tmp, arch_vma_name(mmap_event->vma),
-				       sizeof(tmp));
-			goto got_name;
-		}
-
-		if (!vma->vm_mm) {
-			name = strncpy(tmp, "[vdso]", sizeof(tmp));
-			goto got_name;
-		}
-
-		name = strncpy(tmp, "//anon", sizeof(tmp));
-		goto got_name;
-	}
-
-got_name:
-	size = ALIGN(strlen(name)+1, sizeof(u64));
-
-	mmap_event->file_name = name;
-	mmap_event->file_size = size;
-
-	mmap_event->event.header.size = sizeof(mmap_event->event) + size;
-
-	cpuctx = &get_cpu_var(perf_cpu_context);
-	perf_counter_mmap_ctx(&cpuctx->ctx, mmap_event);
-	put_cpu_var(perf_cpu_context);
-
-	rcu_read_lock();
-	/*
-	 * doesn't really matter which of the child contexts the
-	 * events ends up in.
-	 */
-	ctx = rcu_dereference(current->perf_counter_ctxp);
-	if (ctx)
-		perf_counter_mmap_ctx(ctx, mmap_event);
-	rcu_read_unlock();
-
-	kfree(buf);
-}
-
-void __perf_counter_mmap(struct vm_area_struct *vma)
-{
-	struct perf_mmap_event mmap_event;
-
-	if (!atomic_read(&nr_mmap_counters))
-		return;
-
-	mmap_event = (struct perf_mmap_event){
-		.vma	= vma,
-		/* .file_name */
-		/* .file_size */
-		.event  = {
-			.header = {
-				.type = PERF_EVENT_MMAP,
-				.misc = 0,
-				/* .size */
-			},
-			/* .pid */
-			/* .tid */
-			.start  = vma->vm_start,
-			.len    = vma->vm_end - vma->vm_start,
-			.pgoff  = vma->vm_pgoff,
-		},
-	};
-
-	perf_counter_mmap_event(&mmap_event);
-}
-
-/*
- * IRQ throttle logging
- */
-
-static void perf_log_throttle(struct perf_counter *counter, int enable)
-{
-	struct perf_output_handle handle;
-	int ret;
-
-	struct {
-		struct perf_event_header	header;
-		u64				time;
-		u64				id;
-		u64				stream_id;
-	} throttle_event = {
-		.header = {
-			.type = PERF_EVENT_THROTTLE,
-			.misc = 0,
-			.size = sizeof(throttle_event),
-		},
-		.time		= sched_clock(),
-		.id		= primary_counter_id(counter),
-		.stream_id	= counter->id,
-	};
-
-	if (enable)
-		throttle_event.header.type = PERF_EVENT_UNTHROTTLE;
-
-	ret = perf_output_begin(&handle, counter, sizeof(throttle_event), 1, 0);
-	if (ret)
-		return;
-
-	perf_output_put(&handle, throttle_event);
-	perf_output_end(&handle);
-}
-
-/*
- * Generic counter overflow handling, sampling.
- */
-
-int perf_counter_overflow(struct perf_counter *counter, int nmi,
-			  struct perf_sample_data *data)
-{
-	int events = atomic_read(&counter->event_limit);
-	int throttle = counter->pmu->unthrottle != NULL;
-	struct hw_perf_counter *hwc = &counter->hw;
-	int ret = 0;
-
-	if (!throttle) {
-		hwc->interrupts++;
-	} else {
-		if (hwc->interrupts != MAX_INTERRUPTS) {
-			hwc->interrupts++;
-			if (HZ * hwc->interrupts >
-					(u64)sysctl_perf_counter_sample_rate) {
-				hwc->interrupts = MAX_INTERRUPTS;
-				perf_log_throttle(counter, 0);
-				ret = 1;
-			}
-		} else {
-			/*
-			 * Keep re-disabling counters even though on the previous
-			 * pass we disabled it - just in case we raced with a
-			 * sched-in and the counter got enabled again:
-			 */
-			ret = 1;
-		}
-	}
-
-	if (counter->attr.freq) {
-		u64 now = sched_clock();
-		s64 delta = now - hwc->freq_stamp;
-
-		hwc->freq_stamp = now;
-
-		if (delta > 0 && delta < TICK_NSEC)
-			perf_adjust_period(counter, NSEC_PER_SEC / (int)delta);
-	}
-
-	/*
-	 * XXX event_limit might not quite work as expected on inherited
-	 * counters
-	 */
-
-	counter->pending_kill = POLL_IN;
-	if (events && atomic_dec_and_test(&counter->event_limit)) {
-		ret = 1;
-		counter->pending_kill = POLL_HUP;
-		if (nmi) {
-			counter->pending_disable = 1;
-			perf_pending_queue(&counter->pending,
-					   perf_pending_counter);
-		} else
-			perf_counter_disable(counter);
-	}
-
-	perf_counter_output(counter, nmi, data);
-	return ret;
-}
-
-/*
- * Generic software counter infrastructure
- */
-
-/*
- * We directly increment counter->count and keep a second value in
- * counter->hw.period_left to count intervals. This period counter
- * is kept in the range [-sample_period, 0] so that we can use the
- * sign as trigger.
- */
-
-static u64 perf_swcounter_set_period(struct perf_counter *counter)
-{
-	struct hw_perf_counter *hwc = &counter->hw;
-	u64 period = hwc->last_period;
-	u64 nr, offset;
-	s64 old, val;
-
-	hwc->last_period = hwc->sample_period;
-
-again:
-	old = val = atomic64_read(&hwc->period_left);
-	if (val < 0)
-		return 0;
-
-	nr = div64_u64(period + val, period);
-	offset = nr * period;
-	val -= offset;
-	if (atomic64_cmpxchg(&hwc->period_left, old, val) != old)
-		goto again;
-
-	return nr;
-}
-
-static void perf_swcounter_overflow(struct perf_counter *counter,
-				    int nmi, struct perf_sample_data *data)
-{
-	struct hw_perf_counter *hwc = &counter->hw;
-	u64 overflow;
-
-	data->period = counter->hw.last_period;
-	overflow = perf_swcounter_set_period(counter);
-
-	if (hwc->interrupts == MAX_INTERRUPTS)
-		return;
-
-	for (; overflow; overflow--) {
-		if (perf_counter_overflow(counter, nmi, data)) {
-			/*
-			 * We inhibit the overflow from happening when
-			 * hwc->interrupts == MAX_INTERRUPTS.
-			 */
-			break;
-		}
-	}
-}
-
-static void perf_swcounter_unthrottle(struct perf_counter *counter)
-{
-	/*
-	 * Nothing to do, we already reset hwc->interrupts.
-	 */
-}
-
-static void perf_swcounter_add(struct perf_counter *counter, u64 nr,
-			       int nmi, struct perf_sample_data *data)
-{
-	struct hw_perf_counter *hwc = &counter->hw;
-
-	atomic64_add(nr, &counter->count);
-
-	if (!hwc->sample_period)
-		return;
-
-	if (!data->regs)
-		return;
-
-	if (!atomic64_add_negative(nr, &hwc->period_left))
-		perf_swcounter_overflow(counter, nmi, data);
-}
-
-static int perf_swcounter_is_counting(struct perf_counter *counter)
-{
-	/*
-	 * The counter is active, we're good!
-	 */
-	if (counter->state == PERF_COUNTER_STATE_ACTIVE)
-		return 1;
-
-	/*
-	 * The counter is off/error, not counting.
-	 */
-	if (counter->state != PERF_COUNTER_STATE_INACTIVE)
-		return 0;
-
-	/*
-	 * The counter is inactive, if the context is active
-	 * we're part of a group that didn't make it on the 'pmu',
-	 * not counting.
-	 */
-	if (counter->ctx->is_active)
-		return 0;
-
-	/*
-	 * We're inactive and the context is too, this means the
-	 * task is scheduled out, we're counting events that happen
-	 * to us, like migration events.
-	 */
-	return 1;
-}
-
-static int perf_swcounter_match(struct perf_counter *counter,
-				enum perf_type_id type,
-				u32 event, struct pt_regs *regs)
-{
-	if (!perf_swcounter_is_counting(counter))
-		return 0;
-
-	if (counter->attr.type != type)
-		return 0;
-	if (counter->attr.config != event)
-		return 0;
-
-	if (regs) {
-		if (counter->attr.exclude_user && user_mode(regs))
-			return 0;
-
-		if (counter->attr.exclude_kernel && !user_mode(regs))
-			return 0;
-	}
-
-	return 1;
-}
-
-static void perf_swcounter_ctx_event(struct perf_counter_context *ctx,
-				     enum perf_type_id type,
-				     u32 event, u64 nr, int nmi,
-				     struct perf_sample_data *data)
-{
-	struct perf_counter *counter;
-
-	if (system_state != SYSTEM_RUNNING || list_empty(&ctx->event_list))
-		return;
-
-	rcu_read_lock();
-	list_for_each_entry_rcu(counter, &ctx->event_list, event_entry) {
-		if (perf_swcounter_match(counter, type, event, data->regs))
-			perf_swcounter_add(counter, nr, nmi, data);
-	}
-	rcu_read_unlock();
-}
-
-static int *perf_swcounter_recursion_context(struct perf_cpu_context *cpuctx)
-{
-	if (in_nmi())
-		return &cpuctx->recursion[3];
-
-	if (in_irq())
-		return &cpuctx->recursion[2];
-
-	if (in_softirq())
-		return &cpuctx->recursion[1];
-
-	return &cpuctx->recursion[0];
-}
-
-static void do_perf_swcounter_event(enum perf_type_id type, u32 event,
-				    u64 nr, int nmi,
-				    struct perf_sample_data *data)
-{
-	struct perf_cpu_context *cpuctx = &get_cpu_var(perf_cpu_context);
-	int *recursion = perf_swcounter_recursion_context(cpuctx);
-	struct perf_counter_context *ctx;
-
-	if (*recursion)
-		goto out;
-
-	(*recursion)++;
-	barrier();
-
-	perf_swcounter_ctx_event(&cpuctx->ctx, type, event,
-				 nr, nmi, data);
-	rcu_read_lock();
-	/*
-	 * doesn't really matter which of the child contexts the
-	 * events ends up in.
-	 */
-	ctx = rcu_dereference(current->perf_counter_ctxp);
-	if (ctx)
-		perf_swcounter_ctx_event(ctx, type, event, nr, nmi, data);
-	rcu_read_unlock();
-
-	barrier();
-	(*recursion)--;
-
-out:
-	put_cpu_var(perf_cpu_context);
-}
-
-void __perf_swcounter_event(u32 event, u64 nr, int nmi,
-			    struct pt_regs *regs, u64 addr)
-{
-	struct perf_sample_data data = {
-		.regs = regs,
-		.addr = addr,
-	};
-
-	do_perf_swcounter_event(PERF_TYPE_SOFTWARE, event, nr, nmi, &data);
-}
-
-static void perf_swcounter_read(struct perf_counter *counter)
-{
-}
-
-static int perf_swcounter_enable(struct perf_counter *counter)
-{
-	struct hw_perf_counter *hwc = &counter->hw;
-
-	if (hwc->sample_period) {
-		hwc->last_period = hwc->sample_period;
-		perf_swcounter_set_period(counter);
-	}
-	return 0;
-}
-
-static void perf_swcounter_disable(struct perf_counter *counter)
-{
-}
-
-static const struct pmu perf_ops_generic = {
-	.enable		= perf_swcounter_enable,
-	.disable	= perf_swcounter_disable,
-	.read		= perf_swcounter_read,
-	.unthrottle	= perf_swcounter_unthrottle,
-};
-
-/*
- * hrtimer based swcounter callback
- */
-
-static enum hrtimer_restart perf_swcounter_hrtimer(struct hrtimer *hrtimer)
-{
-	enum hrtimer_restart ret = HRTIMER_RESTART;
-	struct perf_sample_data data;
-	struct perf_counter *counter;
-	u64 period;
-
-	counter	= container_of(hrtimer, struct perf_counter, hw.hrtimer);
-	counter->pmu->read(counter);
-
-	data.addr = 0;
-	data.regs = get_irq_regs();
-	/*
-	 * In case we exclude kernel IPs or are somehow not in interrupt
-	 * context, provide the next best thing, the user IP.
-	 */
-	if ((counter->attr.exclude_kernel || !data.regs) &&
-			!counter->attr.exclude_user)
-		data.regs = task_pt_regs(current);
-
-	if (data.regs) {
-		if (perf_counter_overflow(counter, 0, &data))
-			ret = HRTIMER_NORESTART;
-	}
-
-	period = max_t(u64, 10000, counter->hw.sample_period);
-	hrtimer_forward_now(hrtimer, ns_to_ktime(period));
-
-	return ret;
-}
-
-/*
- * Software counter: cpu wall time clock
- */
-
-static void cpu_clock_perf_counter_update(struct perf_counter *counter)
-{
-	int cpu = raw_smp_processor_id();
-	s64 prev;
-	u64 now;
-
-	now = cpu_clock(cpu);
-	prev = atomic64_read(&counter->hw.prev_count);
-	atomic64_set(&counter->hw.prev_count, now);
-	atomic64_add(now - prev, &counter->count);
-}
-
-static int cpu_clock_perf_counter_enable(struct perf_counter *counter)
-{
-	struct hw_perf_counter *hwc = &counter->hw;
-	int cpu = raw_smp_processor_id();
-
-	atomic64_set(&hwc->prev_count, cpu_clock(cpu));
-	hrtimer_init(&hwc->hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
-	hwc->hrtimer.function = perf_swcounter_hrtimer;
-	if (hwc->sample_period) {
-		u64 period = max_t(u64, 10000, hwc->sample_period);
-		__hrtimer_start_range_ns(&hwc->hrtimer,
-				ns_to_ktime(period), 0,
-				HRTIMER_MODE_REL, 0);
-	}
-
-	return 0;
-}
-
-static void cpu_clock_perf_counter_disable(struct perf_counter *counter)
-{
-	if (counter->hw.sample_period)
-		hrtimer_cancel(&counter->hw.hrtimer);
-	cpu_clock_perf_counter_update(counter);
-}
-
-static void cpu_clock_perf_counter_read(struct perf_counter *counter)
-{
-	cpu_clock_perf_counter_update(counter);
-}
-
-static const struct pmu perf_ops_cpu_clock = {
-	.enable		= cpu_clock_perf_counter_enable,
-	.disable	= cpu_clock_perf_counter_disable,
-	.read		= cpu_clock_perf_counter_read,
-};
-
-/*
- * Software counter: task time clock
- */
-
-static void task_clock_perf_counter_update(struct perf_counter *counter, u64 now)
-{
-	u64 prev;
-	s64 delta;
-
-	prev = atomic64_xchg(&counter->hw.prev_count, now);
-	delta = now - prev;
-	atomic64_add(delta, &counter->count);
-}
-
-static int task_clock_perf_counter_enable(struct perf_counter *counter)
-{
-	struct hw_perf_counter *hwc = &counter->hw;
-	u64 now;
-
-	now = counter->ctx->time;
-
-	atomic64_set(&hwc->prev_count, now);
-	hrtimer_init(&hwc->hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
-	hwc->hrtimer.function = perf_swcounter_hrtimer;
-	if (hwc->sample_period) {
-		u64 period = max_t(u64, 10000, hwc->sample_period);
-		__hrtimer_start_range_ns(&hwc->hrtimer,
-				ns_to_ktime(period), 0,
-				HRTIMER_MODE_REL, 0);
-	}
-
-	return 0;
-}
-
-static void task_clock_perf_counter_disable(struct perf_counter *counter)
-{
-	if (counter->hw.sample_period)
-		hrtimer_cancel(&counter->hw.hrtimer);
-	task_clock_perf_counter_update(counter, counter->ctx->time);
-
-}
-
-static void task_clock_perf_counter_read(struct perf_counter *counter)
-{
-	u64 time;
-
-	if (!in_nmi()) {
-		update_context_time(counter->ctx);
-		time = counter->ctx->time;
-	} else {
-		u64 now = perf_clock();
-		u64 delta = now - counter->ctx->timestamp;
-		time = counter->ctx->time + delta;
-	}
-
-	task_clock_perf_counter_update(counter, time);
-}
-
-static const struct pmu perf_ops_task_clock = {
-	.enable		= task_clock_perf_counter_enable,
-	.disable	= task_clock_perf_counter_disable,
-	.read		= task_clock_perf_counter_read,
-};
-
-#ifdef CONFIG_EVENT_PROFILE
-void perf_tpcounter_event(int event_id, u64 addr, u64 count, void *record,
-			  int entry_size)
-{
-	struct perf_raw_record raw = {
-		.size = entry_size,
-		.data = record,
-	};
-
-	struct perf_sample_data data = {
-		.regs = get_irq_regs(),
-		.addr = addr,
-		.raw = &raw,
-	};
-
-	if (!data.regs)
-		data.regs = task_pt_regs(current);
-
-	do_perf_swcounter_event(PERF_TYPE_TRACEPOINT, event_id, count, 1, &data);
-}
-EXPORT_SYMBOL_GPL(perf_tpcounter_event);
-
-extern int ftrace_profile_enable(int);
-extern void ftrace_profile_disable(int);
-
-static void tp_perf_counter_destroy(struct perf_counter *counter)
-{
-	ftrace_profile_disable(counter->attr.config);
-}
-
-static const struct pmu *tp_perf_counter_init(struct perf_counter *counter)
-{
-	/*
-	 * Raw tracepoint data is a severe data leak, only allow root to
-	 * have these.
-	 */
-	if ((counter->attr.sample_type & PERF_SAMPLE_RAW) &&
-			!capable(CAP_SYS_ADMIN))
-		return ERR_PTR(-EPERM);
-
-	if (ftrace_profile_enable(counter->attr.config))
-		return NULL;
-
-	counter->destroy = tp_perf_counter_destroy;
-
-	return &perf_ops_generic;
-}
-#else
-static const struct pmu *tp_perf_counter_init(struct perf_counter *counter)
-{
-	return NULL;
-}
-#endif
-
-atomic_t perf_swcounter_enabled[PERF_COUNT_SW_MAX];
-
-static void sw_perf_counter_destroy(struct perf_counter *counter)
-{
-	u64 event = counter->attr.config;
-
-	WARN_ON(counter->parent);
-
-	atomic_dec(&perf_swcounter_enabled[event]);
-}
-
-static const struct pmu *sw_perf_counter_init(struct perf_counter *counter)
-{
-	const struct pmu *pmu = NULL;
-	u64 event = counter->attr.config;
-
-	/*
-	 * Software counters (currently) can't in general distinguish
-	 * between user, kernel and hypervisor events.
-	 * However, context switches and cpu migrations are considered
-	 * to be kernel events, and page faults are never hypervisor
-	 * events.
-	 */
-	switch (event) {
-	case PERF_COUNT_SW_CPU_CLOCK:
-		pmu = &perf_ops_cpu_clock;
-
-		break;
-	case PERF_COUNT_SW_TASK_CLOCK:
-		/*
-		 * If the user instantiates this as a per-cpu counter,
-		 * use the cpu_clock counter instead.
-		 */
-		if (counter->ctx->task)
-			pmu = &perf_ops_task_clock;
-		else
-			pmu = &perf_ops_cpu_clock;
-
-		break;
-	case PERF_COUNT_SW_PAGE_FAULTS:
-	case PERF_COUNT_SW_PAGE_FAULTS_MIN:
-	case PERF_COUNT_SW_PAGE_FAULTS_MAJ:
-	case PERF_COUNT_SW_CONTEXT_SWITCHES:
-	case PERF_COUNT_SW_CPU_MIGRATIONS:
-		if (!counter->parent) {
-			atomic_inc(&perf_swcounter_enabled[event]);
-			counter->destroy = sw_perf_counter_destroy;
-		}
-		pmu = &perf_ops_generic;
-		break;
-	}
-
-	return pmu;
-}
-
-/*
- * Allocate and initialize a counter structure
- */
-static struct perf_counter *
-perf_counter_alloc(struct perf_counter_attr *attr,
-		   int cpu,
-		   struct perf_counter_context *ctx,
-		   struct perf_counter *group_leader,
-		   struct perf_counter *parent_counter,
-		   gfp_t gfpflags)
-{
-	const struct pmu *pmu;
-	struct perf_counter *counter;
-	struct hw_perf_counter *hwc;
-	long err;
-
-	counter = kzalloc(sizeof(*counter), gfpflags);
-	if (!counter)
-		return ERR_PTR(-ENOMEM);
-
-	/*
-	 * Single counters are their own group leaders, with an
-	 * empty sibling list:
-	 */
-	if (!group_leader)
-		group_leader = counter;
-
-	mutex_init(&counter->child_mutex);
-	INIT_LIST_HEAD(&counter->child_list);
-
-	INIT_LIST_HEAD(&counter->list_entry);
-	INIT_LIST_HEAD(&counter->event_entry);
-	INIT_LIST_HEAD(&counter->sibling_list);
-	init_waitqueue_head(&counter->waitq);
-
-	mutex_init(&counter->mmap_mutex);
-
-	counter->cpu		= cpu;
-	counter->attr		= *attr;
-	counter->group_leader	= group_leader;
-	counter->pmu		= NULL;
-	counter->ctx		= ctx;
-	counter->oncpu		= -1;
-
-	counter->parent		= parent_counter;
-
-	counter->ns		= get_pid_ns(current->nsproxy->pid_ns);
-	counter->id		= atomic64_inc_return(&perf_counter_id);
-
-	counter->state		= PERF_COUNTER_STATE_INACTIVE;
-
-	if (attr->disabled)
-		counter->state = PERF_COUNTER_STATE_OFF;
-
-	pmu = NULL;
-
-	hwc = &counter->hw;
-	hwc->sample_period = attr->sample_period;
-	if (attr->freq && attr->sample_freq)
-		hwc->sample_period = 1;
-	hwc->last_period = hwc->sample_period;
-
-	atomic64_set(&hwc->period_left, hwc->sample_period);
-
-	/*
-	 * we currently do not support PERF_FORMAT_GROUP on inherited counters
-	 */
-	if (attr->inherit && (attr->read_format & PERF_FORMAT_GROUP))
-		goto done;
-
-	switch (attr->type) {
-	case PERF_TYPE_RAW:
-	case PERF_TYPE_HARDWARE:
-	case PERF_TYPE_HW_CACHE:
-		pmu = hw_perf_counter_init(counter);
-		break;
-
-	case PERF_TYPE_SOFTWARE:
-		pmu = sw_perf_counter_init(counter);
-		break;
-
-	case PERF_TYPE_TRACEPOINT:
-		pmu = tp_perf_counter_init(counter);
-		break;
-
-	default:
-		break;
-	}
-done:
-	err = 0;
-	if (!pmu)
-		err = -EINVAL;
-	else if (IS_ERR(pmu))
-		err = PTR_ERR(pmu);
-
-	if (err) {
-		if (counter->ns)
-			put_pid_ns(counter->ns);
-		kfree(counter);
-		return ERR_PTR(err);
-	}
-
-	counter->pmu = pmu;
-
-	if (!counter->parent) {
-		atomic_inc(&nr_counters);
-		if (counter->attr.mmap)
-			atomic_inc(&nr_mmap_counters);
-		if (counter->attr.comm)
-			atomic_inc(&nr_comm_counters);
-		if (counter->attr.task)
-			atomic_inc(&nr_task_counters);
-	}
-
-	return counter;
-}
-
-static int perf_copy_attr(struct perf_counter_attr __user *uattr,
-			  struct perf_counter_attr *attr)
-{
-	int ret;
-	u32 size;
-
-	if (!access_ok(VERIFY_WRITE, uattr, PERF_ATTR_SIZE_VER0))
-		return -EFAULT;
-
-	/*
-	 * zero the full structure, so that a short copy will be nice.
-	 */
-	memset(attr, 0, sizeof(*attr));
-
-	ret = get_user(size, &uattr->size);
-	if (ret)
-		return ret;
-
-	if (size > PAGE_SIZE)	/* silly large */
-		goto err_size;
-
-	if (!size)		/* abi compat */
-		size = PERF_ATTR_SIZE_VER0;
-
-	if (size < PERF_ATTR_SIZE_VER0)
-		goto err_size;
-
-	/*
-	 * If we're handed a bigger struct than we know of,
-	 * ensure all the unknown bits are 0.
-	 */
-	if (size > sizeof(*attr)) {
-		unsigned long val;
-		unsigned long __user *addr;
-		unsigned long __user *end;
-
-		addr = PTR_ALIGN((void __user *)uattr + sizeof(*attr),
-				sizeof(unsigned long));
-		end  = PTR_ALIGN((void __user *)uattr + size,
-				sizeof(unsigned long));
-
-		for (; addr < end; addr += sizeof(unsigned long)) {
-			ret = get_user(val, addr);
-			if (ret)
-				return ret;
-			if (val)
-				goto err_size;
-		}
-	}
-
-	ret = copy_from_user(attr, uattr, size);
-	if (ret)
-		return -EFAULT;
-
-	/*
-	 * If the type exists, the corresponding creation will verify
-	 * the attr->config.
-	 */
-	if (attr->type >= PERF_TYPE_MAX)
-		return -EINVAL;
-
-	if (attr->__reserved_1 || attr->__reserved_2 || attr->__reserved_3)
-		return -EINVAL;
-
-	if (attr->sample_type & ~(PERF_SAMPLE_MAX-1))
-		return -EINVAL;
-
-	if (attr->read_format & ~(PERF_FORMAT_MAX-1))
-		return -EINVAL;
-
-out:
-	return ret;
-
-err_size:
-	put_user(sizeof(*attr), &uattr->size);
-	ret = -E2BIG;
-	goto out;
-}
-
-/**
- * sys_perf_counter_open - open a performance counter, associate it to a task/cpu
- *
- * @attr_uptr:	event type attributes for monitoring/sampling
- * @pid:		target pid
- * @cpu:		target cpu
- * @group_fd:		group leader counter fd
- */
-SYSCALL_DEFINE5(perf_counter_open,
-		struct perf_counter_attr __user *, attr_uptr,
-		pid_t, pid, int, cpu, int, group_fd, unsigned long, flags)
-{
-	struct perf_counter *counter, *group_leader;
-	struct perf_counter_attr attr;
-	struct perf_counter_context *ctx;
-	struct file *counter_file = NULL;
-	struct file *group_file = NULL;
-	int fput_needed = 0;
-	int fput_needed2 = 0;
-	int ret;
-
-	/* for future expandability... */
-	if (flags)
-		return -EINVAL;
-
-	ret = perf_copy_attr(attr_uptr, &attr);
-	if (ret)
-		return ret;
-
-	if (!attr.exclude_kernel) {
-		if (perf_paranoid_kernel() && !capable(CAP_SYS_ADMIN))
-			return -EACCES;
-	}
-
-	if (attr.freq) {
-		if (attr.sample_freq > sysctl_perf_counter_sample_rate)
-			return -EINVAL;
-	}
-
-	/*
-	 * Get the target context (task or percpu):
-	 */
-	ctx = find_get_context(pid, cpu);
-	if (IS_ERR(ctx))
-		return PTR_ERR(ctx);
-
-	/*
-	 * Look up the group leader (we will attach this counter to it):
-	 */
-	group_leader = NULL;
-	if (group_fd != -1) {
-		ret = -EINVAL;
-		group_file = fget_light(group_fd, &fput_needed);
-		if (!group_file)
-			goto err_put_context;
-		if (group_file->f_op != &perf_fops)
-			goto err_put_context;
-
-		group_leader = group_file->private_data;
-		/*
-		 * Do not allow a recursive hierarchy (this new sibling
-		 * becoming part of another group-sibling):
-		 */
-		if (group_leader->group_leader != group_leader)
-			goto err_put_context;
-		/*
-		 * Do not allow to attach to a group in a different
-		 * task or CPU context:
-		 */
-		if (group_leader->ctx != ctx)
-			goto err_put_context;
-		/*
-		 * Only a group leader can be exclusive or pinned
-		 */
-		if (attr.exclusive || attr.pinned)
-			goto err_put_context;
-	}
-
-	counter = perf_counter_alloc(&attr, cpu, ctx, group_leader,
-				     NULL, GFP_KERNEL);
-	ret = PTR_ERR(counter);
-	if (IS_ERR(counter))
-		goto err_put_context;
-
-	ret = anon_inode_getfd("[perf_counter]", &perf_fops, counter, 0);
-	if (ret < 0)
-		goto err_free_put_context;
-
-	counter_file = fget_light(ret, &fput_needed2);
-	if (!counter_file)
-		goto err_free_put_context;
-
-	counter->filp = counter_file;
-	WARN_ON_ONCE(ctx->parent_ctx);
-	mutex_lock(&ctx->mutex);
-	perf_install_in_context(ctx, counter, cpu);
-	++ctx->generation;
-	mutex_unlock(&ctx->mutex);
-
-	counter->owner = current;
-	get_task_struct(current);
-	mutex_lock(&current->perf_counter_mutex);
-	list_add_tail(&counter->owner_entry, &current->perf_counter_list);
-	mutex_unlock(&current->perf_counter_mutex);
-
-	fput_light(counter_file, fput_needed2);
-
-out_fput:
-	fput_light(group_file, fput_needed);
-
-	return ret;
-
-err_free_put_context:
-	kfree(counter);
-
-err_put_context:
-	put_ctx(ctx);
-
-	goto out_fput;
-}
-
-/*
- * inherit a counter from parent task to child task:
- */
-static struct perf_counter *
-inherit_counter(struct perf_counter *parent_counter,
-	      struct task_struct *parent,
-	      struct perf_counter_context *parent_ctx,
-	      struct task_struct *child,
-	      struct perf_counter *group_leader,
-	      struct perf_counter_context *child_ctx)
-{
-	struct perf_counter *child_counter;
-
-	/*
-	 * Instead of creating recursive hierarchies of counters,
-	 * we link inherited counters back to the original parent,
-	 * which has a filp for sure, which we use as the reference
-	 * count:
-	 */
-	if (parent_counter->parent)
-		parent_counter = parent_counter->parent;
-
-	child_counter = perf_counter_alloc(&parent_counter->attr,
-					   parent_counter->cpu, child_ctx,
-					   group_leader, parent_counter,
-					   GFP_KERNEL);
-	if (IS_ERR(child_counter))
-		return child_counter;
-	get_ctx(child_ctx);
-
-	/*
-	 * Make the child state follow the state of the parent counter,
-	 * not its attr.disabled bit.  We hold the parent's mutex,
-	 * so we won't race with perf_counter_{en, dis}able_family.
-	 */
-	if (parent_counter->state >= PERF_COUNTER_STATE_INACTIVE)
-		child_counter->state = PERF_COUNTER_STATE_INACTIVE;
-	else
-		child_counter->state = PERF_COUNTER_STATE_OFF;
-
-	if (parent_counter->attr.freq)
-		child_counter->hw.sample_period = parent_counter->hw.sample_period;
-
-	/*
-	 * Link it up in the child's context:
-	 */
-	add_counter_to_ctx(child_counter, child_ctx);
-
-	/*
-	 * Get a reference to the parent filp - we will fput it
-	 * when the child counter exits. This is safe to do because
-	 * we are in the parent and we know that the filp still
-	 * exists and has a nonzero count:
-	 */
-	atomic_long_inc(&parent_counter->filp->f_count);
-
-	/*
-	 * Link this into the parent counter's child list
-	 */
-	WARN_ON_ONCE(parent_counter->ctx->parent_ctx);
-	mutex_lock(&parent_counter->child_mutex);
-	list_add_tail(&child_counter->child_list, &parent_counter->child_list);
-	mutex_unlock(&parent_counter->child_mutex);
-
-	return child_counter;
-}
-
-static int inherit_group(struct perf_counter *parent_counter,
-	      struct task_struct *parent,
-	      struct perf_counter_context *parent_ctx,
-	      struct task_struct *child,
-	      struct perf_counter_context *child_ctx)
-{
-	struct perf_counter *leader;
-	struct perf_counter *sub;
-	struct perf_counter *child_ctr;
-
-	leader = inherit_counter(parent_counter, parent, parent_ctx,
-				 child, NULL, child_ctx);
-	if (IS_ERR(leader))
-		return PTR_ERR(leader);
-	list_for_each_entry(sub, &parent_counter->sibling_list, list_entry) {
-		child_ctr = inherit_counter(sub, parent, parent_ctx,
-					    child, leader, child_ctx);
-		if (IS_ERR(child_ctr))
-			return PTR_ERR(child_ctr);
-	}
-	return 0;
-}
-
-static void sync_child_counter(struct perf_counter *child_counter,
-			       struct task_struct *child)
-{
-	struct perf_counter *parent_counter = child_counter->parent;
-	u64 child_val;
-
-	if (child_counter->attr.inherit_stat)
-		perf_counter_read_event(child_counter, child);
-
-	child_val = atomic64_read(&child_counter->count);
-
-	/*
-	 * Add back the child's count to the parent's count:
-	 */
-	atomic64_add(child_val, &parent_counter->count);
-	atomic64_add(child_counter->total_time_enabled,
-		     &parent_counter->child_total_time_enabled);
-	atomic64_add(child_counter->total_time_running,
-		     &parent_counter->child_total_time_running);
-
-	/*
-	 * Remove this counter from the parent's list
-	 */
-	WARN_ON_ONCE(parent_counter->ctx->parent_ctx);
-	mutex_lock(&parent_counter->child_mutex);
-	list_del_init(&child_counter->child_list);
-	mutex_unlock(&parent_counter->child_mutex);
-
-	/*
-	 * Release the parent counter, if this was the last
-	 * reference to it.
-	 */
-	fput(parent_counter->filp);
-}
-
-static void
-__perf_counter_exit_task(struct perf_counter *child_counter,
-			 struct perf_counter_context *child_ctx,
-			 struct task_struct *child)
-{
-	struct perf_counter *parent_counter;
-
-	update_counter_times(child_counter);
-	perf_counter_remove_from_context(child_counter);
-
-	parent_counter = child_counter->parent;
-	/*
-	 * It can happen that parent exits first, and has counters
-	 * that are still around due to the child reference. These
-	 * counters need to be zapped - but otherwise linger.
-	 */
-	if (parent_counter) {
-		sync_child_counter(child_counter, child);
-		free_counter(child_counter);
-	}
-}
-
-/*
- * When a child task exits, feed back counter values to parent counters.
- */
-void perf_counter_exit_task(struct task_struct *child)
-{
-	struct perf_counter *child_counter, *tmp;
-	struct perf_counter_context *child_ctx;
-	unsigned long flags;
-
-	if (likely(!child->perf_counter_ctxp)) {
-		perf_counter_task(child, NULL, 0);
-		return;
-	}
-
-	local_irq_save(flags);
-	/*
-	 * We can't reschedule here because interrupts are disabled,
-	 * and either child is current or it is a task that can't be
-	 * scheduled, so we are now safe from rescheduling changing
-	 * our context.
-	 */
-	child_ctx = child->perf_counter_ctxp;
-	__perf_counter_task_sched_out(child_ctx);
-
-	/*
-	 * Take the context lock here so that if find_get_context is
-	 * reading child->perf_counter_ctxp, we wait until it has
-	 * incremented the context's refcount before we do put_ctx below.
-	 */
-	spin_lock(&child_ctx->lock);
-	child->perf_counter_ctxp = NULL;
-	/*
-	 * If this context is a clone; unclone it so it can't get
-	 * swapped to another process while we're removing all
-	 * the counters from it.
-	 */
-	unclone_ctx(child_ctx);
-	spin_unlock_irqrestore(&child_ctx->lock, flags);
-
-	/*
-	 * Report the task dead after unscheduling the counters so that we
-	 * won't get any samples after PERF_EVENT_EXIT. We can however still
-	 * get a few PERF_EVENT_READ events.
-	 */
-	perf_counter_task(child, child_ctx, 0);
-
-	/*
-	 * We can recurse on the same lock type through:
-	 *
-	 *   __perf_counter_exit_task()
-	 *     sync_child_counter()
-	 *       fput(parent_counter->filp)
-	 *         perf_release()
-	 *           mutex_lock(&ctx->mutex)
-	 *
-	 * But since its the parent context it won't be the same instance.
-	 */
-	mutex_lock_nested(&child_ctx->mutex, SINGLE_DEPTH_NESTING);
-
-again:
-	list_for_each_entry_safe(child_counter, tmp, &child_ctx->counter_list,
-				 list_entry)
-		__perf_counter_exit_task(child_counter, child_ctx, child);
-
-	/*
-	 * If the last counter was a group counter, it will have appended all
-	 * its siblings to the list, but we obtained 'tmp' before that which
-	 * will still point to the list head terminating the iteration.
-	 */
-	if (!list_empty(&child_ctx->counter_list))
-		goto again;
-
-	mutex_unlock(&child_ctx->mutex);
-
-	put_ctx(child_ctx);
-}
-
-/*
- * free an unexposed, unused context as created by inheritance by
- * init_task below, used by fork() in case of fail.
- */
-void perf_counter_free_task(struct task_struct *task)
-{
-	struct perf_counter_context *ctx = task->perf_counter_ctxp;
-	struct perf_counter *counter, *tmp;
-
-	if (!ctx)
-		return;
-
-	mutex_lock(&ctx->mutex);
-again:
-	list_for_each_entry_safe(counter, tmp, &ctx->counter_list, list_entry) {
-		struct perf_counter *parent = counter->parent;
-
-		if (WARN_ON_ONCE(!parent))
-			continue;
-
-		mutex_lock(&parent->child_mutex);
-		list_del_init(&counter->child_list);
-		mutex_unlock(&parent->child_mutex);
-
-		fput(parent->filp);
-
-		list_del_counter(counter, ctx);
-		free_counter(counter);
-	}
-
-	if (!list_empty(&ctx->counter_list))
-		goto again;
-
-	mutex_unlock(&ctx->mutex);
-
-	put_ctx(ctx);
-}
-
-/*
- * Initialize the perf_counter context in task_struct
- */
-int perf_counter_init_task(struct task_struct *child)
-{
-	struct perf_counter_context *child_ctx, *parent_ctx;
-	struct perf_counter_context *cloned_ctx;
-	struct perf_counter *counter;
-	struct task_struct *parent = current;
-	int inherited_all = 1;
-	int ret = 0;
-
-	child->perf_counter_ctxp = NULL;
-
-	mutex_init(&child->perf_counter_mutex);
-	INIT_LIST_HEAD(&child->perf_counter_list);
-
-	if (likely(!parent->perf_counter_ctxp))
-		return 0;
-
-	/*
-	 * This is executed from the parent task context, so inherit
-	 * counters that have been marked for cloning.
-	 * First allocate and initialize a context for the child.
-	 */
-
-	child_ctx = kmalloc(sizeof(struct perf_counter_context), GFP_KERNEL);
-	if (!child_ctx)
-		return -ENOMEM;
-
-	__perf_counter_init_context(child_ctx, child);
-	child->perf_counter_ctxp = child_ctx;
-	get_task_struct(child);
-
-	/*
-	 * If the parent's context is a clone, pin it so it won't get
-	 * swapped under us.
-	 */
-	parent_ctx = perf_pin_task_context(parent);
-
-	/*
-	 * No need to check if parent_ctx != NULL here; since we saw
-	 * it non-NULL earlier, the only reason for it to become NULL
-	 * is if we exit, and since we're currently in the middle of
-	 * a fork we can't be exiting at the same time.
-	 */
-
-	/*
-	 * Lock the parent list. No need to lock the child - not PID
-	 * hashed yet and not running, so nobody can access it.
-	 */
-	mutex_lock(&parent_ctx->mutex);
-
-	/*
-	 * We dont have to disable NMIs - we are only looking at
-	 * the list, not manipulating it:
-	 */
-	list_for_each_entry_rcu(counter, &parent_ctx->event_list, event_entry) {
-		if (counter != counter->group_leader)
-			continue;
-
-		if (!counter->attr.inherit) {
-			inherited_all = 0;
-			continue;
-		}
-
-		ret = inherit_group(counter, parent, parent_ctx,
-					     child, child_ctx);
-		if (ret) {
-			inherited_all = 0;
-			break;
-		}
-	}
-
-	if (inherited_all) {
-		/*
-		 * Mark the child context as a clone of the parent
-		 * context, or of whatever the parent is a clone of.
-		 * Note that if the parent is a clone, it could get
-		 * uncloned at any point, but that doesn't matter
-		 * because the list of counters and the generation
-		 * count can't have changed since we took the mutex.
-		 */
-		cloned_ctx = rcu_dereference(parent_ctx->parent_ctx);
-		if (cloned_ctx) {
-			child_ctx->parent_ctx = cloned_ctx;
-			child_ctx->parent_gen = parent_ctx->parent_gen;
-		} else {
-			child_ctx->parent_ctx = parent_ctx;
-			child_ctx->parent_gen = parent_ctx->generation;
-		}
-		get_ctx(child_ctx->parent_ctx);
-	}
-
-	mutex_unlock(&parent_ctx->mutex);
-
-	perf_unpin_context(parent_ctx);
-
-	return ret;
-}
-
-static void __cpuinit perf_counter_init_cpu(int cpu)
-{
-	struct perf_cpu_context *cpuctx;
-
-	cpuctx = &per_cpu(perf_cpu_context, cpu);
-	__perf_counter_init_context(&cpuctx->ctx, NULL);
-
-	spin_lock(&perf_resource_lock);
-	cpuctx->max_pertask = perf_max_counters - perf_reserved_percpu;
-	spin_unlock(&perf_resource_lock);
-
-	hw_perf_counter_setup(cpu);
-}
-
-#ifdef CONFIG_HOTPLUG_CPU
-static void __perf_counter_exit_cpu(void *info)
-{
-	struct perf_cpu_context *cpuctx = &__get_cpu_var(perf_cpu_context);
-	struct perf_counter_context *ctx = &cpuctx->ctx;
-	struct perf_counter *counter, *tmp;
-
-	list_for_each_entry_safe(counter, tmp, &ctx->counter_list, list_entry)
-		__perf_counter_remove_from_context(counter);
-}
-static void perf_counter_exit_cpu(int cpu)
-{
-	struct perf_cpu_context *cpuctx = &per_cpu(perf_cpu_context, cpu);
-	struct perf_counter_context *ctx = &cpuctx->ctx;
-
-	mutex_lock(&ctx->mutex);
-	smp_call_function_single(cpu, __perf_counter_exit_cpu, NULL, 1);
-	mutex_unlock(&ctx->mutex);
-}
-#else
-static inline void perf_counter_exit_cpu(int cpu) { }
-#endif
-
-static int __cpuinit
-perf_cpu_notify(struct notifier_block *self, unsigned long action, void *hcpu)
-{
-	unsigned int cpu = (long)hcpu;
-
-	switch (action) {
-
-	case CPU_UP_PREPARE:
-	case CPU_UP_PREPARE_FROZEN:
-		perf_counter_init_cpu(cpu);
-		break;
-
-	case CPU_ONLINE:
-	case CPU_ONLINE_FROZEN:
-		hw_perf_counter_setup_online(cpu);
-		break;
-
-	case CPU_DOWN_PREPARE:
-	case CPU_DOWN_PREPARE_FROZEN:
-		perf_counter_exit_cpu(cpu);
-		break;
-
-	default:
-		break;
-	}
-
-	return NOTIFY_OK;
-}
-
-/*
- * This has to have a higher priority than migration_notifier in sched.c.
- */
-static struct notifier_block __cpuinitdata perf_cpu_nb = {
-	.notifier_call		= perf_cpu_notify,
-	.priority		= 20,
-};
-
-void __init perf_counter_init(void)
-{
-	perf_cpu_notify(&perf_cpu_nb, (unsigned long)CPU_UP_PREPARE,
-			(void *)(long)smp_processor_id());
-	perf_cpu_notify(&perf_cpu_nb, (unsigned long)CPU_ONLINE,
-			(void *)(long)smp_processor_id());
-	register_cpu_notifier(&perf_cpu_nb);
-}
-
-static ssize_t perf_show_reserve_percpu(struct sysdev_class *class, char *buf)
-{
-	return sprintf(buf, "%d\n", perf_reserved_percpu);
-}
-
-static ssize_t
-perf_set_reserve_percpu(struct sysdev_class *class,
-			const char *buf,
-			size_t count)
-{
-	struct perf_cpu_context *cpuctx;
-	unsigned long val;
-	int err, cpu, mpt;
-
-	err = strict_strtoul(buf, 10, &val);
-	if (err)
-		return err;
-	if (val > perf_max_counters)
-		return -EINVAL;
-
-	spin_lock(&perf_resource_lock);
-	perf_reserved_percpu = val;
-	for_each_online_cpu(cpu) {
-		cpuctx = &per_cpu(perf_cpu_context, cpu);
-		spin_lock_irq(&cpuctx->ctx.lock);
-		mpt = min(perf_max_counters - cpuctx->ctx.nr_counters,
-			  perf_max_counters - perf_reserved_percpu);
-		cpuctx->max_pertask = mpt;
-		spin_unlock_irq(&cpuctx->ctx.lock);
-	}
-	spin_unlock(&perf_resource_lock);
-
-	return count;
-}
-
-static ssize_t perf_show_overcommit(struct sysdev_class *class, char *buf)
-{
-	return sprintf(buf, "%d\n", perf_overcommit);
-}
-
-static ssize_t
-perf_set_overcommit(struct sysdev_class *class, const char *buf, size_t count)
-{
-	unsigned long val;
-	int err;
-
-	err = strict_strtoul(buf, 10, &val);
-	if (err)
-		return err;
-	if (val > 1)
-		return -EINVAL;
-
-	spin_lock(&perf_resource_lock);
-	perf_overcommit = val;
-	spin_unlock(&perf_resource_lock);
-
-	return count;
-}
-
-static SYSDEV_CLASS_ATTR(
-				reserve_percpu,
-				0644,
-				perf_show_reserve_percpu,
-				perf_set_reserve_percpu
-			);
-
-static SYSDEV_CLASS_ATTR(
-				overcommit,
-				0644,
-				perf_show_overcommit,
-				perf_set_overcommit
-			);
-
-static struct attribute *perfclass_attrs[] = {
-	&attr_reserve_percpu.attr,
-	&attr_overcommit.attr,
-	NULL
-};
-
-static struct attribute_group perfclass_attr_group = {
-	.attrs			= perfclass_attrs,
-	.name			= "perf_counters",
-};
-
-static int __init perf_counter_sysfs_init(void)
-{
-	return sysfs_create_group(&cpu_sysdev_class.kset.kobj,
-				  &perfclass_attr_group);
-}
-device_initcall(perf_counter_sysfs_init);
diff --git a/kernel/perf_event.c b/kernel/perf_event.c
new file mode 100644
index 000000000000..7f29643c8985
--- /dev/null
+++ b/kernel/perf_event.c
@@ -0,0 +1,5130 @@
+/*
+ * Performance events core code:
+ *
+ *  Copyright (C) 2008 Thomas Gleixner <tglx@linutronix.de>
+ *  Copyright (C) 2008-2009 Red Hat, Inc., Ingo Molnar
+ *  Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
+ *  Copyright  ©  2009 Paul Mackerras, IBM Corp. <paulus@au1.ibm.com>
+ *
+ * For licensing details see kernel-base/COPYING
+ */
+
+#include <linux/fs.h>
+#include <linux/mm.h>
+#include <linux/cpu.h>
+#include <linux/smp.h>
+#include <linux/file.h>
+#include <linux/poll.h>
+#include <linux/sysfs.h>
+#include <linux/dcache.h>
+#include <linux/percpu.h>
+#include <linux/ptrace.h>
+#include <linux/vmstat.h>
+#include <linux/vmalloc.h>
+#include <linux/hardirq.h>
+#include <linux/rculist.h>
+#include <linux/uaccess.h>
+#include <linux/syscalls.h>
+#include <linux/anon_inodes.h>
+#include <linux/kernel_stat.h>
+#include <linux/perf_event.h>
+
+#include <asm/irq_regs.h>
+
+/*
+ * Each CPU has a list of per CPU events:
+ */
+DEFINE_PER_CPU(struct perf_cpu_context, perf_cpu_context);
+
+int perf_max_events __read_mostly = 1;
+static int perf_reserved_percpu __read_mostly;
+static int perf_overcommit __read_mostly = 1;
+
+static atomic_t nr_events __read_mostly;
+static atomic_t nr_mmap_events __read_mostly;
+static atomic_t nr_comm_events __read_mostly;
+static atomic_t nr_task_events __read_mostly;
+
+/*
+ * perf event paranoia level:
+ *  -1 - not paranoid at all
+ *   0 - disallow raw tracepoint access for unpriv
+ *   1 - disallow cpu events for unpriv
+ *   2 - disallow kernel profiling for unpriv
+ */
+int sysctl_perf_event_paranoid __read_mostly = 1;
+
+static inline bool perf_paranoid_tracepoint_raw(void)
+{
+	return sysctl_perf_event_paranoid > -1;
+}
+
+static inline bool perf_paranoid_cpu(void)
+{
+	return sysctl_perf_event_paranoid > 0;
+}
+
+static inline bool perf_paranoid_kernel(void)
+{
+	return sysctl_perf_event_paranoid > 1;
+}
+
+int sysctl_perf_event_mlock __read_mostly = 512; /* 'free' kb per user */
+
+/*
+ * max perf event sample rate
+ */
+int sysctl_perf_event_sample_rate __read_mostly = 100000;
+
+static atomic64_t perf_event_id;
+
+/*
+ * Lock for (sysadmin-configurable) event reservations:
+ */
+static DEFINE_SPINLOCK(perf_resource_lock);
+
+/*
+ * Architecture provided APIs - weak aliases:
+ */
+extern __weak const struct pmu *hw_perf_event_init(struct perf_event *event)
+{
+	return NULL;
+}
+
+void __weak hw_perf_disable(void)		{ barrier(); }
+void __weak hw_perf_enable(void)		{ barrier(); }
+
+void __weak hw_perf_event_setup(int cpu)	{ barrier(); }
+void __weak hw_perf_event_setup_online(int cpu)	{ barrier(); }
+
+int __weak
+hw_perf_group_sched_in(struct perf_event *group_leader,
+	       struct perf_cpu_context *cpuctx,
+	       struct perf_event_context *ctx, int cpu)
+{
+	return 0;
+}
+
+void __weak perf_event_print_debug(void)	{ }
+
+static DEFINE_PER_CPU(int, perf_disable_count);
+
+void __perf_disable(void)
+{
+	__get_cpu_var(perf_disable_count)++;
+}
+
+bool __perf_enable(void)
+{
+	return !--__get_cpu_var(perf_disable_count);
+}
+
+void perf_disable(void)
+{
+	__perf_disable();
+	hw_perf_disable();
+}
+
+void perf_enable(void)
+{
+	if (__perf_enable())
+		hw_perf_enable();
+}
+
+static void get_ctx(struct perf_event_context *ctx)
+{
+	WARN_ON(!atomic_inc_not_zero(&ctx->refcount));
+}
+
+static void free_ctx(struct rcu_head *head)
+{
+	struct perf_event_context *ctx;
+
+	ctx = container_of(head, struct perf_event_context, rcu_head);
+	kfree(ctx);
+}
+
+static void put_ctx(struct perf_event_context *ctx)
+{
+	if (atomic_dec_and_test(&ctx->refcount)) {
+		if (ctx->parent_ctx)
+			put_ctx(ctx->parent_ctx);
+		if (ctx->task)
+			put_task_struct(ctx->task);
+		call_rcu(&ctx->rcu_head, free_ctx);
+	}
+}
+
+static void unclone_ctx(struct perf_event_context *ctx)
+{
+	if (ctx->parent_ctx) {
+		put_ctx(ctx->parent_ctx);
+		ctx->parent_ctx = NULL;
+	}
+}
+
+/*
+ * If we inherit events we want to return the parent event id
+ * to userspace.
+ */
+static u64 primary_event_id(struct perf_event *event)
+{
+	u64 id = event->id;
+
+	if (event->parent)
+		id = event->parent->id;
+
+	return id;
+}
+
+/*
+ * Get the perf_event_context for a task and lock it.
+ * This has to cope with with the fact that until it is locked,
+ * the context could get moved to another task.
+ */
+static struct perf_event_context *
+perf_lock_task_context(struct task_struct *task, unsigned long *flags)
+{
+	struct perf_event_context *ctx;
+
+	rcu_read_lock();
+ retry:
+	ctx = rcu_dereference(task->perf_event_ctxp);
+	if (ctx) {
+		/*
+		 * If this context is a clone of another, it might
+		 * get swapped for another underneath us by
+		 * perf_event_task_sched_out, though the
+		 * rcu_read_lock() protects us from any context
+		 * getting freed.  Lock the context and check if it
+		 * got swapped before we could get the lock, and retry
+		 * if so.  If we locked the right context, then it
+		 * can't get swapped on us any more.
+		 */
+		spin_lock_irqsave(&ctx->lock, *flags);
+		if (ctx != rcu_dereference(task->perf_event_ctxp)) {
+			spin_unlock_irqrestore(&ctx->lock, *flags);
+			goto retry;
+		}
+
+		if (!atomic_inc_not_zero(&ctx->refcount)) {
+			spin_unlock_irqrestore(&ctx->lock, *flags);
+			ctx = NULL;
+		}
+	}
+	rcu_read_unlock();
+	return ctx;
+}
+
+/*
+ * Get the context for a task and increment its pin_count so it
+ * can't get swapped to another task.  This also increments its
+ * reference count so that the context can't get freed.
+ */
+static struct perf_event_context *perf_pin_task_context(struct task_struct *task)
+{
+	struct perf_event_context *ctx;
+	unsigned long flags;
+
+	ctx = perf_lock_task_context(task, &flags);
+	if (ctx) {
+		++ctx->pin_count;
+		spin_unlock_irqrestore(&ctx->lock, flags);
+	}
+	return ctx;
+}
+
+static void perf_unpin_context(struct perf_event_context *ctx)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&ctx->lock, flags);
+	--ctx->pin_count;
+	spin_unlock_irqrestore(&ctx->lock, flags);
+	put_ctx(ctx);
+}
+
+/*
+ * Add a event from the lists for its context.
+ * Must be called with ctx->mutex and ctx->lock held.
+ */
+static void
+list_add_event(struct perf_event *event, struct perf_event_context *ctx)
+{
+	struct perf_event *group_leader = event->group_leader;
+
+	/*
+	 * Depending on whether it is a standalone or sibling event,
+	 * add it straight to the context's event list, or to the group
+	 * leader's sibling list:
+	 */
+	if (group_leader == event)
+		list_add_tail(&event->group_entry, &ctx->group_list);
+	else {
+		list_add_tail(&event->group_entry, &group_leader->sibling_list);
+		group_leader->nr_siblings++;
+	}
+
+	list_add_rcu(&event->event_entry, &ctx->event_list);
+	ctx->nr_events++;
+	if (event->attr.inherit_stat)
+		ctx->nr_stat++;
+}
+
+/*
+ * Remove a event from the lists for its context.
+ * Must be called with ctx->mutex and ctx->lock held.
+ */
+static void
+list_del_event(struct perf_event *event, struct perf_event_context *ctx)
+{
+	struct perf_event *sibling, *tmp;
+
+	if (list_empty(&event->group_entry))
+		return;
+	ctx->nr_events--;
+	if (event->attr.inherit_stat)
+		ctx->nr_stat--;
+
+	list_del_init(&event->group_entry);
+	list_del_rcu(&event->event_entry);
+
+	if (event->group_leader != event)
+		event->group_leader->nr_siblings--;
+
+	/*
+	 * If this was a group event with sibling events then
+	 * upgrade the siblings to singleton events by adding them
+	 * to the context list directly:
+	 */
+	list_for_each_entry_safe(sibling, tmp, &event->sibling_list, group_entry) {
+
+		list_move_tail(&sibling->group_entry, &ctx->group_list);
+		sibling->group_leader = sibling;
+	}
+}
+
+static void
+event_sched_out(struct perf_event *event,
+		  struct perf_cpu_context *cpuctx,
+		  struct perf_event_context *ctx)
+{
+	if (event->state != PERF_EVENT_STATE_ACTIVE)
+		return;
+
+	event->state = PERF_EVENT_STATE_INACTIVE;
+	if (event->pending_disable) {
+		event->pending_disable = 0;
+		event->state = PERF_EVENT_STATE_OFF;
+	}
+	event->tstamp_stopped = ctx->time;
+	event->pmu->disable(event);
+	event->oncpu = -1;
+
+	if (!is_software_event(event))
+		cpuctx->active_oncpu--;
+	ctx->nr_active--;
+	if (event->attr.exclusive || !cpuctx->active_oncpu)
+		cpuctx->exclusive = 0;
+}
+
+static void
+group_sched_out(struct perf_event *group_event,
+		struct perf_cpu_context *cpuctx,
+		struct perf_event_context *ctx)
+{
+	struct perf_event *event;
+
+	if (group_event->state != PERF_EVENT_STATE_ACTIVE)
+		return;
+
+	event_sched_out(group_event, cpuctx, ctx);
+
+	/*
+	 * Schedule out siblings (if any):
+	 */
+	list_for_each_entry(event, &group_event->sibling_list, group_entry)
+		event_sched_out(event, cpuctx, ctx);
+
+	if (group_event->attr.exclusive)
+		cpuctx->exclusive = 0;
+}
+
+/*
+ * Cross CPU call to remove a performance event
+ *
+ * We disable the event on the hardware level first. After that we
+ * remove it from the context list.
+ */
+static void __perf_event_remove_from_context(void *info)
+{
+	struct perf_cpu_context *cpuctx = &__get_cpu_var(perf_cpu_context);
+	struct perf_event *event = info;
+	struct perf_event_context *ctx = event->ctx;
+
+	/*
+	 * If this is a task context, we need to check whether it is
+	 * the current task context of this cpu. If not it has been
+	 * scheduled out before the smp call arrived.
+	 */
+	if (ctx->task && cpuctx->task_ctx != ctx)
+		return;
+
+	spin_lock(&ctx->lock);
+	/*
+	 * Protect the list operation against NMI by disabling the
+	 * events on a global level.
+	 */
+	perf_disable();
+
+	event_sched_out(event, cpuctx, ctx);
+
+	list_del_event(event, ctx);
+
+	if (!ctx->task) {
+		/*
+		 * Allow more per task events with respect to the
+		 * reservation:
+		 */
+		cpuctx->max_pertask =
+			min(perf_max_events - ctx->nr_events,
+			    perf_max_events - perf_reserved_percpu);
+	}
+
+	perf_enable();
+	spin_unlock(&ctx->lock);
+}
+
+
+/*
+ * Remove the event from a task's (or a CPU's) list of events.
+ *
+ * Must be called with ctx->mutex held.
+ *
+ * CPU events are removed with a smp call. For task events we only
+ * call when the task is on a CPU.
+ *
+ * If event->ctx is a cloned context, callers must make sure that
+ * every task struct that event->ctx->task could possibly point to
+ * remains valid.  This is OK when called from perf_release since
+ * that only calls us on the top-level context, which can't be a clone.
+ * When called from perf_event_exit_task, it's OK because the
+ * context has been detached from its task.
+ */
+static void perf_event_remove_from_context(struct perf_event *event)
+{
+	struct perf_event_context *ctx = event->ctx;
+	struct task_struct *task = ctx->task;
+
+	if (!task) {
+		/*
+		 * Per cpu events are removed via an smp call and
+		 * the removal is always sucessful.
+		 */
+		smp_call_function_single(event->cpu,
+					 __perf_event_remove_from_context,
+					 event, 1);
+		return;
+	}
+
+retry:
+	task_oncpu_function_call(task, __perf_event_remove_from_context,
+				 event);
+
+	spin_lock_irq(&ctx->lock);
+	/*
+	 * If the context is active we need to retry the smp call.
+	 */
+	if (ctx->nr_active && !list_empty(&event->group_entry)) {
+		spin_unlock_irq(&ctx->lock);
+		goto retry;
+	}
+
+	/*
+	 * The lock prevents that this context is scheduled in so we
+	 * can remove the event safely, if the call above did not
+	 * succeed.
+	 */
+	if (!list_empty(&event->group_entry)) {
+		list_del_event(event, ctx);
+	}
+	spin_unlock_irq(&ctx->lock);
+}
+
+static inline u64 perf_clock(void)
+{
+	return cpu_clock(smp_processor_id());
+}
+
+/*
+ * Update the record of the current time in a context.
+ */
+static void update_context_time(struct perf_event_context *ctx)
+{
+	u64 now = perf_clock();
+
+	ctx->time += now - ctx->timestamp;
+	ctx->timestamp = now;
+}
+
+/*
+ * Update the total_time_enabled and total_time_running fields for a event.
+ */
+static void update_event_times(struct perf_event *event)
+{
+	struct perf_event_context *ctx = event->ctx;
+	u64 run_end;
+
+	if (event->state < PERF_EVENT_STATE_INACTIVE ||
+	    event->group_leader->state < PERF_EVENT_STATE_INACTIVE)
+		return;
+
+	event->total_time_enabled = ctx->time - event->tstamp_enabled;
+
+	if (event->state == PERF_EVENT_STATE_INACTIVE)
+		run_end = event->tstamp_stopped;
+	else
+		run_end = ctx->time;
+
+	event->total_time_running = run_end - event->tstamp_running;
+}
+
+/*
+ * Update total_time_enabled and total_time_running for all events in a group.
+ */
+static void update_group_times(struct perf_event *leader)
+{
+	struct perf_event *event;
+
+	update_event_times(leader);
+	list_for_each_entry(event, &leader->sibling_list, group_entry)
+		update_event_times(event);
+}
+
+/*
+ * Cross CPU call to disable a performance event
+ */
+static void __perf_event_disable(void *info)
+{
+	struct perf_event *event = info;
+	struct perf_cpu_context *cpuctx = &__get_cpu_var(perf_cpu_context);
+	struct perf_event_context *ctx = event->ctx;
+
+	/*
+	 * If this is a per-task event, need to check whether this
+	 * event's task is the current task on this cpu.
+	 */
+	if (ctx->task && cpuctx->task_ctx != ctx)
+		return;
+
+	spin_lock(&ctx->lock);
+
+	/*
+	 * If the event is on, turn it off.
+	 * If it is in error state, leave it in error state.
+	 */
+	if (event->state >= PERF_EVENT_STATE_INACTIVE) {
+		update_context_time(ctx);
+		update_group_times(event);
+		if (event == event->group_leader)
+			group_sched_out(event, cpuctx, ctx);
+		else
+			event_sched_out(event, cpuctx, ctx);
+		event->state = PERF_EVENT_STATE_OFF;
+	}
+
+	spin_unlock(&ctx->lock);
+}
+
+/*
+ * Disable a event.
+ *
+ * If event->ctx is a cloned context, callers must make sure that
+ * every task struct that event->ctx->task could possibly point to
+ * remains valid.  This condition is satisifed when called through
+ * perf_event_for_each_child or perf_event_for_each because they
+ * hold the top-level event's child_mutex, so any descendant that
+ * goes to exit will block in sync_child_event.
+ * When called from perf_pending_event it's OK because event->ctx
+ * is the current context on this CPU and preemption is disabled,
+ * hence we can't get into perf_event_task_sched_out for this context.
+ */
+static void perf_event_disable(struct perf_event *event)
+{
+	struct perf_event_context *ctx = event->ctx;
+	struct task_struct *task = ctx->task;
+
+	if (!task) {
+		/*
+		 * Disable the event on the cpu that it's on
+		 */
+		smp_call_function_single(event->cpu, __perf_event_disable,
+					 event, 1);
+		return;
+	}
+
+ retry:
+	task_oncpu_function_call(task, __perf_event_disable, event);
+
+	spin_lock_irq(&ctx->lock);
+	/*
+	 * If the event is still active, we need to retry the cross-call.
+	 */
+	if (event->state == PERF_EVENT_STATE_ACTIVE) {
+		spin_unlock_irq(&ctx->lock);
+		goto retry;
+	}
+
+	/*
+	 * Since we have the lock this context can't be scheduled
+	 * in, so we can change the state safely.
+	 */
+	if (event->state == PERF_EVENT_STATE_INACTIVE) {
+		update_group_times(event);
+		event->state = PERF_EVENT_STATE_OFF;
+	}
+
+	spin_unlock_irq(&ctx->lock);
+}
+
+static int
+event_sched_in(struct perf_event *event,
+		 struct perf_cpu_context *cpuctx,
+		 struct perf_event_context *ctx,
+		 int cpu)
+{
+	if (event->state <= PERF_EVENT_STATE_OFF)
+		return 0;
+
+	event->state = PERF_EVENT_STATE_ACTIVE;
+	event->oncpu = cpu;	/* TODO: put 'cpu' into cpuctx->cpu */
+	/*
+	 * The new state must be visible before we turn it on in the hardware:
+	 */
+	smp_wmb();
+
+	if (event->pmu->enable(event)) {
+		event->state = PERF_EVENT_STATE_INACTIVE;
+		event->oncpu = -1;
+		return -EAGAIN;
+	}
+
+	event->tstamp_running += ctx->time - event->tstamp_stopped;
+
+	if (!is_software_event(event))
+		cpuctx->active_oncpu++;
+	ctx->nr_active++;
+
+	if (event->attr.exclusive)
+		cpuctx->exclusive = 1;
+
+	return 0;
+}
+
+static int
+group_sched_in(struct perf_event *group_event,
+	       struct perf_cpu_context *cpuctx,
+	       struct perf_event_context *ctx,
+	       int cpu)
+{
+	struct perf_event *event, *partial_group;
+	int ret;
+
+	if (group_event->state == PERF_EVENT_STATE_OFF)
+		return 0;
+
+	ret = hw_perf_group_sched_in(group_event, cpuctx, ctx, cpu);
+	if (ret)
+		return ret < 0 ? ret : 0;
+
+	if (event_sched_in(group_event, cpuctx, ctx, cpu))
+		return -EAGAIN;
+
+	/*
+	 * Schedule in siblings as one group (if any):
+	 */
+	list_for_each_entry(event, &group_event->sibling_list, group_entry) {
+		if (event_sched_in(event, cpuctx, ctx, cpu)) {
+			partial_group = event;
+			goto group_error;
+		}
+	}
+
+	return 0;
+
+group_error:
+	/*
+	 * Groups can be scheduled in as one unit only, so undo any
+	 * partial group before returning:
+	 */
+	list_for_each_entry(event, &group_event->sibling_list, group_entry) {
+		if (event == partial_group)
+			break;
+		event_sched_out(event, cpuctx, ctx);
+	}
+	event_sched_out(group_event, cpuctx, ctx);
+
+	return -EAGAIN;
+}
+
+/*
+ * Return 1 for a group consisting entirely of software events,
+ * 0 if the group contains any hardware events.
+ */
+static int is_software_only_group(struct perf_event *leader)
+{
+	struct perf_event *event;
+
+	if (!is_software_event(leader))
+		return 0;
+
+	list_for_each_entry(event, &leader->sibling_list, group_entry)
+		if (!is_software_event(event))
+			return 0;
+
+	return 1;
+}
+
+/*
+ * Work out whether we can put this event group on the CPU now.
+ */
+static int group_can_go_on(struct perf_event *event,
+			   struct perf_cpu_context *cpuctx,
+			   int can_add_hw)
+{
+	/*
+	 * Groups consisting entirely of software events can always go on.
+	 */
+	if (is_software_only_group(event))
+		return 1;
+	/*
+	 * If an exclusive group is already on, no other hardware
+	 * events can go on.
+	 */
+	if (cpuctx->exclusive)
+		return 0;
+	/*
+	 * If this group is exclusive and there are already
+	 * events on the CPU, it can't go on.
+	 */
+	if (event->attr.exclusive && cpuctx->active_oncpu)
+		return 0;
+	/*
+	 * Otherwise, try to add it if all previous groups were able
+	 * to go on.
+	 */
+	return can_add_hw;
+}
+
+static void add_event_to_ctx(struct perf_event *event,
+			       struct perf_event_context *ctx)
+{
+	list_add_event(event, ctx);
+	event->tstamp_enabled = ctx->time;
+	event->tstamp_running = ctx->time;
+	event->tstamp_stopped = ctx->time;
+}
+
+/*
+ * Cross CPU call to install and enable a performance event
+ *
+ * Must be called with ctx->mutex held
+ */
+static void __perf_install_in_context(void *info)
+{
+	struct perf_cpu_context *cpuctx = &__get_cpu_var(perf_cpu_context);
+	struct perf_event *event = info;
+	struct perf_event_context *ctx = event->ctx;
+	struct perf_event *leader = event->group_leader;
+	int cpu = smp_processor_id();
+	int err;
+
+	/*
+	 * If this is a task context, we need to check whether it is
+	 * the current task context of this cpu. If not it has been
+	 * scheduled out before the smp call arrived.
+	 * Or possibly this is the right context but it isn't
+	 * on this cpu because it had no events.
+	 */
+	if (ctx->task && cpuctx->task_ctx != ctx) {
+		if (cpuctx->task_ctx || ctx->task != current)
+			return;
+		cpuctx->task_ctx = ctx;
+	}
+
+	spin_lock(&ctx->lock);
+	ctx->is_active = 1;
+	update_context_time(ctx);
+
+	/*
+	 * Protect the list operation against NMI by disabling the
+	 * events on a global level. NOP for non NMI based events.
+	 */
+	perf_disable();
+
+	add_event_to_ctx(event, ctx);
+
+	/*
+	 * Don't put the event on if it is disabled or if
+	 * it is in a group and the group isn't on.
+	 */
+	if (event->state != PERF_EVENT_STATE_INACTIVE ||
+	    (leader != event && leader->state != PERF_EVENT_STATE_ACTIVE))
+		goto unlock;
+
+	/*
+	 * An exclusive event can't go on if there are already active
+	 * hardware events, and no hardware event can go on if there
+	 * is already an exclusive event on.
+	 */
+	if (!group_can_go_on(event, cpuctx, 1))
+		err = -EEXIST;
+	else
+		err = event_sched_in(event, cpuctx, ctx, cpu);
+
+	if (err) {
+		/*
+		 * This event couldn't go on.  If it is in a group
+		 * then we have to pull the whole group off.
+		 * If the event group is pinned then put it in error state.
+		 */
+		if (leader != event)
+			group_sched_out(leader, cpuctx, ctx);
+		if (leader->attr.pinned) {
+			update_group_times(leader);
+			leader->state = PERF_EVENT_STATE_ERROR;
+		}
+	}
+
+	if (!err && !ctx->task && cpuctx->max_pertask)
+		cpuctx->max_pertask--;
+
+ unlock:
+	perf_enable();
+
+	spin_unlock(&ctx->lock);
+}
+
+/*
+ * Attach a performance event to a context
+ *
+ * First we add the event to the list with the hardware enable bit
+ * in event->hw_config cleared.
+ *
+ * If the event is attached to a task which is on a CPU we use a smp
+ * call to enable it in the task context. The task might have been
+ * scheduled away, but we check this in the smp call again.
+ *
+ * Must be called with ctx->mutex held.
+ */
+static void
+perf_install_in_context(struct perf_event_context *ctx,
+			struct perf_event *event,
+			int cpu)
+{
+	struct task_struct *task = ctx->task;
+
+	if (!task) {
+		/*
+		 * Per cpu events are installed via an smp call and
+		 * the install is always sucessful.
+		 */
+		smp_call_function_single(cpu, __perf_install_in_context,
+					 event, 1);
+		return;
+	}
+
+retry:
+	task_oncpu_function_call(task, __perf_install_in_context,
+				 event);
+
+	spin_lock_irq(&ctx->lock);
+	/*
+	 * we need to retry the smp call.
+	 */
+	if (ctx->is_active && list_empty(&event->group_entry)) {
+		spin_unlock_irq(&ctx->lock);
+		goto retry;
+	}
+
+	/*
+	 * The lock prevents that this context is scheduled in so we
+	 * can add the event safely, if it the call above did not
+	 * succeed.
+	 */
+	if (list_empty(&event->group_entry))
+		add_event_to_ctx(event, ctx);
+	spin_unlock_irq(&ctx->lock);
+}
+
+/*
+ * Put a event into inactive state and update time fields.
+ * Enabling the leader of a group effectively enables all
+ * the group members that aren't explicitly disabled, so we
+ * have to update their ->tstamp_enabled also.
+ * Note: this works for group members as well as group leaders
+ * since the non-leader members' sibling_lists will be empty.
+ */
+static void __perf_event_mark_enabled(struct perf_event *event,
+					struct perf_event_context *ctx)
+{
+	struct perf_event *sub;
+
+	event->state = PERF_EVENT_STATE_INACTIVE;
+	event->tstamp_enabled = ctx->time - event->total_time_enabled;
+	list_for_each_entry(sub, &event->sibling_list, group_entry)
+		if (sub->state >= PERF_EVENT_STATE_INACTIVE)
+			sub->tstamp_enabled =
+				ctx->time - sub->total_time_enabled;
+}
+
+/*
+ * Cross CPU call to enable a performance event
+ */
+static void __perf_event_enable(void *info)
+{
+	struct perf_event *event = info;
+	struct perf_cpu_context *cpuctx = &__get_cpu_var(perf_cpu_context);
+	struct perf_event_context *ctx = event->ctx;
+	struct perf_event *leader = event->group_leader;
+	int err;
+
+	/*
+	 * If this is a per-task event, need to check whether this
+	 * event's task is the current task on this cpu.
+	 */
+	if (ctx->task && cpuctx->task_ctx != ctx) {
+		if (cpuctx->task_ctx || ctx->task != current)
+			return;
+		cpuctx->task_ctx = ctx;
+	}
+
+	spin_lock(&ctx->lock);
+	ctx->is_active = 1;
+	update_context_time(ctx);
+
+	if (event->state >= PERF_EVENT_STATE_INACTIVE)
+		goto unlock;
+	__perf_event_mark_enabled(event, ctx);
+
+	/*
+	 * If the event is in a group and isn't the group leader,
+	 * then don't put it on unless the group is on.
+	 */
+	if (leader != event && leader->state != PERF_EVENT_STATE_ACTIVE)
+		goto unlock;
+
+	if (!group_can_go_on(event, cpuctx, 1)) {
+		err = -EEXIST;
+	} else {
+		perf_disable();
+		if (event == leader)
+			err = group_sched_in(event, cpuctx, ctx,
+					     smp_processor_id());
+		else
+			err = event_sched_in(event, cpuctx, ctx,
+					       smp_processor_id());
+		perf_enable();
+	}
+
+	if (err) {
+		/*
+		 * If this event can't go on and it's part of a
+		 * group, then the whole group has to come off.
+		 */
+		if (leader != event)
+			group_sched_out(leader, cpuctx, ctx);
+		if (leader->attr.pinned) {
+			update_group_times(leader);
+			leader->state = PERF_EVENT_STATE_ERROR;
+		}
+	}
+
+ unlock:
+	spin_unlock(&ctx->lock);
+}
+
+/*
+ * Enable a event.
+ *
+ * If event->ctx is a cloned context, callers must make sure that
+ * every task struct that event->ctx->task could possibly point to
+ * remains valid.  This condition is satisfied when called through
+ * perf_event_for_each_child or perf_event_for_each as described
+ * for perf_event_disable.
+ */
+static void perf_event_enable(struct perf_event *event)
+{
+	struct perf_event_context *ctx = event->ctx;
+	struct task_struct *task = ctx->task;
+
+	if (!task) {
+		/*
+		 * Enable the event on the cpu that it's on
+		 */
+		smp_call_function_single(event->cpu, __perf_event_enable,
+					 event, 1);
+		return;
+	}
+
+	spin_lock_irq(&ctx->lock);
+	if (event->state >= PERF_EVENT_STATE_INACTIVE)
+		goto out;
+
+	/*
+	 * If the event is in error state, clear that first.
+	 * That way, if we see the event in error state below, we
+	 * know that it has gone back into error state, as distinct
+	 * from the task having been scheduled away before the
+	 * cross-call arrived.
+	 */
+	if (event->state == PERF_EVENT_STATE_ERROR)
+		event->state = PERF_EVENT_STATE_OFF;
+
+ retry:
+	spin_unlock_irq(&ctx->lock);
+	task_oncpu_function_call(task, __perf_event_enable, event);
+
+	spin_lock_irq(&ctx->lock);
+
+	/*
+	 * If the context is active and the event is still off,
+	 * we need to retry the cross-call.
+	 */
+	if (ctx->is_active && event->state == PERF_EVENT_STATE_OFF)
+		goto retry;
+
+	/*
+	 * Since we have the lock this context can't be scheduled
+	 * in, so we can change the state safely.
+	 */
+	if (event->state == PERF_EVENT_STATE_OFF)
+		__perf_event_mark_enabled(event, ctx);
+
+ out:
+	spin_unlock_irq(&ctx->lock);
+}
+
+static int perf_event_refresh(struct perf_event *event, int refresh)
+{
+	/*
+	 * not supported on inherited events
+	 */
+	if (event->attr.inherit)
+		return -EINVAL;
+
+	atomic_add(refresh, &event->event_limit);
+	perf_event_enable(event);
+
+	return 0;
+}
+
+void __perf_event_sched_out(struct perf_event_context *ctx,
+			      struct perf_cpu_context *cpuctx)
+{
+	struct perf_event *event;
+
+	spin_lock(&ctx->lock);
+	ctx->is_active = 0;
+	if (likely(!ctx->nr_events))
+		goto out;
+	update_context_time(ctx);
+
+	perf_disable();
+	if (ctx->nr_active)
+		list_for_each_entry(event, &ctx->group_list, group_entry)
+			group_sched_out(event, cpuctx, ctx);
+
+	perf_enable();
+ out:
+	spin_unlock(&ctx->lock);
+}
+
+/*
+ * Test whether two contexts are equivalent, i.e. whether they
+ * have both been cloned from the same version of the same context
+ * and they both have the same number of enabled events.
+ * If the number of enabled events is the same, then the set
+ * of enabled events should be the same, because these are both
+ * inherited contexts, therefore we can't access individual events
+ * in them directly with an fd; we can only enable/disable all
+ * events via prctl, or enable/disable all events in a family
+ * via ioctl, which will have the same effect on both contexts.
+ */
+static int context_equiv(struct perf_event_context *ctx1,
+			 struct perf_event_context *ctx2)
+{
+	return ctx1->parent_ctx && ctx1->parent_ctx == ctx2->parent_ctx
+		&& ctx1->parent_gen == ctx2->parent_gen
+		&& !ctx1->pin_count && !ctx2->pin_count;
+}
+
+static void __perf_event_read(void *event);
+
+static void __perf_event_sync_stat(struct perf_event *event,
+				     struct perf_event *next_event)
+{
+	u64 value;
+
+	if (!event->attr.inherit_stat)
+		return;
+
+	/*
+	 * Update the event value, we cannot use perf_event_read()
+	 * because we're in the middle of a context switch and have IRQs
+	 * disabled, which upsets smp_call_function_single(), however
+	 * we know the event must be on the current CPU, therefore we
+	 * don't need to use it.
+	 */
+	switch (event->state) {
+	case PERF_EVENT_STATE_ACTIVE:
+		__perf_event_read(event);
+		break;
+
+	case PERF_EVENT_STATE_INACTIVE:
+		update_event_times(event);
+		break;
+
+	default:
+		break;
+	}
+
+	/*
+	 * In order to keep per-task stats reliable we need to flip the event
+	 * values when we flip the contexts.
+	 */
+	value = atomic64_read(&next_event->count);
+	value = atomic64_xchg(&event->count, value);
+	atomic64_set(&next_event->count, value);
+
+	swap(event->total_time_enabled, next_event->total_time_enabled);
+	swap(event->total_time_running, next_event->total_time_running);
+
+	/*
+	 * Since we swizzled the values, update the user visible data too.
+	 */
+	perf_event_update_userpage(event);
+	perf_event_update_userpage(next_event);
+}
+
+#define list_next_entry(pos, member) \
+	list_entry(pos->member.next, typeof(*pos), member)
+
+static void perf_event_sync_stat(struct perf_event_context *ctx,
+				   struct perf_event_context *next_ctx)
+{
+	struct perf_event *event, *next_event;
+
+	if (!ctx->nr_stat)
+		return;
+
+	event = list_first_entry(&ctx->event_list,
+				   struct perf_event, event_entry);
+
+	next_event = list_first_entry(&next_ctx->event_list,
+					struct perf_event, event_entry);
+
+	while (&event->event_entry != &ctx->event_list &&
+	       &next_event->event_entry != &next_ctx->event_list) {
+
+		__perf_event_sync_stat(event, next_event);
+
+		event = list_next_entry(event, event_entry);
+		next_event = list_next_entry(next_event, event_entry);
+	}
+}
+
+/*
+ * Called from scheduler to remove the events of the current task,
+ * with interrupts disabled.
+ *
+ * We stop each event and update the event value in event->count.
+ *
+ * This does not protect us against NMI, but disable()
+ * sets the disabled bit in the control field of event _before_
+ * accessing the event control register. If a NMI hits, then it will
+ * not restart the event.
+ */
+void perf_event_task_sched_out(struct task_struct *task,
+				 struct task_struct *next, int cpu)
+{
+	struct perf_cpu_context *cpuctx = &per_cpu(perf_cpu_context, cpu);
+	struct perf_event_context *ctx = task->perf_event_ctxp;
+	struct perf_event_context *next_ctx;
+	struct perf_event_context *parent;
+	struct pt_regs *regs;
+	int do_switch = 1;
+
+	regs = task_pt_regs(task);
+	perf_sw_event(PERF_COUNT_SW_CONTEXT_SWITCHES, 1, 1, regs, 0);
+
+	if (likely(!ctx || !cpuctx->task_ctx))
+		return;
+
+	update_context_time(ctx);
+
+	rcu_read_lock();
+	parent = rcu_dereference(ctx->parent_ctx);
+	next_ctx = next->perf_event_ctxp;
+	if (parent && next_ctx &&
+	    rcu_dereference(next_ctx->parent_ctx) == parent) {
+		/*
+		 * Looks like the two contexts are clones, so we might be
+		 * able to optimize the context switch.  We lock both
+		 * contexts and check that they are clones under the
+		 * lock (including re-checking that neither has been
+		 * uncloned in the meantime).  It doesn't matter which
+		 * order we take the locks because no other cpu could
+		 * be trying to lock both of these tasks.
+		 */
+		spin_lock(&ctx->lock);
+		spin_lock_nested(&next_ctx->lock, SINGLE_DEPTH_NESTING);
+		if (context_equiv(ctx, next_ctx)) {
+			/*
+			 * XXX do we need a memory barrier of sorts
+			 * wrt to rcu_dereference() of perf_event_ctxp
+			 */
+			task->perf_event_ctxp = next_ctx;
+			next->perf_event_ctxp = ctx;
+			ctx->task = next;
+			next_ctx->task = task;
+			do_switch = 0;
+
+			perf_event_sync_stat(ctx, next_ctx);
+		}
+		spin_unlock(&next_ctx->lock);
+		spin_unlock(&ctx->lock);
+	}
+	rcu_read_unlock();
+
+	if (do_switch) {
+		__perf_event_sched_out(ctx, cpuctx);
+		cpuctx->task_ctx = NULL;
+	}
+}
+
+/*
+ * Called with IRQs disabled
+ */
+static void __perf_event_task_sched_out(struct perf_event_context *ctx)
+{
+	struct perf_cpu_context *cpuctx = &__get_cpu_var(perf_cpu_context);
+
+	if (!cpuctx->task_ctx)
+		return;
+
+	if (WARN_ON_ONCE(ctx != cpuctx->task_ctx))
+		return;
+
+	__perf_event_sched_out(ctx, cpuctx);
+	cpuctx->task_ctx = NULL;
+}
+
+/*
+ * Called with IRQs disabled
+ */
+static void perf_event_cpu_sched_out(struct perf_cpu_context *cpuctx)
+{
+	__perf_event_sched_out(&cpuctx->ctx, cpuctx);
+}
+
+static void
+__perf_event_sched_in(struct perf_event_context *ctx,
+			struct perf_cpu_context *cpuctx, int cpu)
+{
+	struct perf_event *event;
+	int can_add_hw = 1;
+
+	spin_lock(&ctx->lock);
+	ctx->is_active = 1;
+	if (likely(!ctx->nr_events))
+		goto out;
+
+	ctx->timestamp = perf_clock();
+
+	perf_disable();
+
+	/*
+	 * First go through the list and put on any pinned groups
+	 * in order to give them the best chance of going on.
+	 */
+	list_for_each_entry(event, &ctx->group_list, group_entry) {
+		if (event->state <= PERF_EVENT_STATE_OFF ||
+		    !event->attr.pinned)
+			continue;
+		if (event->cpu != -1 && event->cpu != cpu)
+			continue;
+
+		if (group_can_go_on(event, cpuctx, 1))
+			group_sched_in(event, cpuctx, ctx, cpu);
+
+		/*
+		 * If this pinned group hasn't been scheduled,
+		 * put it in error state.
+		 */
+		if (event->state == PERF_EVENT_STATE_INACTIVE) {
+			update_group_times(event);
+			event->state = PERF_EVENT_STATE_ERROR;
+		}
+	}
+
+	list_for_each_entry(event, &ctx->group_list, group_entry) {
+		/*
+		 * Ignore events in OFF or ERROR state, and
+		 * ignore pinned events since we did them already.
+		 */
+		if (event->state <= PERF_EVENT_STATE_OFF ||
+		    event->attr.pinned)
+			continue;
+
+		/*
+		 * Listen to the 'cpu' scheduling filter constraint
+		 * of events:
+		 */
+		if (event->cpu != -1 && event->cpu != cpu)
+			continue;
+
+		if (group_can_go_on(event, cpuctx, can_add_hw))
+			if (group_sched_in(event, cpuctx, ctx, cpu))
+				can_add_hw = 0;
+	}
+	perf_enable();
+ out:
+	spin_unlock(&ctx->lock);
+}
+
+/*
+ * Called from scheduler to add the events of the current task
+ * with interrupts disabled.
+ *
+ * We restore the event value and then enable it.
+ *
+ * This does not protect us against NMI, but enable()
+ * sets the enabled bit in the control field of event _before_
+ * accessing the event control register. If a NMI hits, then it will
+ * keep the event running.
+ */
+void perf_event_task_sched_in(struct task_struct *task, int cpu)
+{
+	struct perf_cpu_context *cpuctx = &per_cpu(perf_cpu_context, cpu);
+	struct perf_event_context *ctx = task->perf_event_ctxp;
+
+	if (likely(!ctx))
+		return;
+	if (cpuctx->task_ctx == ctx)
+		return;
+	__perf_event_sched_in(ctx, cpuctx, cpu);
+	cpuctx->task_ctx = ctx;
+}
+
+static void perf_event_cpu_sched_in(struct perf_cpu_context *cpuctx, int cpu)
+{
+	struct perf_event_context *ctx = &cpuctx->ctx;
+
+	__perf_event_sched_in(ctx, cpuctx, cpu);
+}
+
+#define MAX_INTERRUPTS (~0ULL)
+
+static void perf_log_throttle(struct perf_event *event, int enable);
+
+static void perf_adjust_period(struct perf_event *event, u64 events)
+{
+	struct hw_perf_event *hwc = &event->hw;
+	u64 period, sample_period;
+	s64 delta;
+
+	events *= hwc->sample_period;
+	period = div64_u64(events, event->attr.sample_freq);
+
+	delta = (s64)(period - hwc->sample_period);
+	delta = (delta + 7) / 8; /* low pass filter */
+
+	sample_period = hwc->sample_period + delta;
+
+	if (!sample_period)
+		sample_period = 1;
+
+	hwc->sample_period = sample_period;
+}
+
+static void perf_ctx_adjust_freq(struct perf_event_context *ctx)
+{
+	struct perf_event *event;
+	struct hw_perf_event *hwc;
+	u64 interrupts, freq;
+
+	spin_lock(&ctx->lock);
+	list_for_each_entry_rcu(event, &ctx->event_list, event_entry) {
+		if (event->state != PERF_EVENT_STATE_ACTIVE)
+			continue;
+
+		hwc = &event->hw;
+
+		interrupts = hwc->interrupts;
+		hwc->interrupts = 0;
+
+		/*
+		 * unthrottle events on the tick
+		 */
+		if (interrupts == MAX_INTERRUPTS) {
+			perf_log_throttle(event, 1);
+			event->pmu->unthrottle(event);
+			interrupts = 2*sysctl_perf_event_sample_rate/HZ;
+		}
+
+		if (!event->attr.freq || !event->attr.sample_freq)
+			continue;
+
+		/*
+		 * if the specified freq < HZ then we need to skip ticks
+		 */
+		if (event->attr.sample_freq < HZ) {
+			freq = event->attr.sample_freq;
+
+			hwc->freq_count += freq;
+			hwc->freq_interrupts += interrupts;
+
+			if (hwc->freq_count < HZ)
+				continue;
+
+			interrupts = hwc->freq_interrupts;
+			hwc->freq_interrupts = 0;
+			hwc->freq_count -= HZ;
+		} else
+			freq = HZ;
+
+		perf_adjust_period(event, freq * interrupts);
+
+		/*
+		 * In order to avoid being stalled by an (accidental) huge
+		 * sample period, force reset the sample period if we didn't
+		 * get any events in this freq period.
+		 */
+		if (!interrupts) {
+			perf_disable();
+			event->pmu->disable(event);
+			atomic64_set(&hwc->period_left, 0);
+			event->pmu->enable(event);
+			perf_enable();
+		}
+	}
+	spin_unlock(&ctx->lock);
+}
+
+/*
+ * Round-robin a context's events:
+ */
+static void rotate_ctx(struct perf_event_context *ctx)
+{
+	struct perf_event *event;
+
+	if (!ctx->nr_events)
+		return;
+
+	spin_lock(&ctx->lock);
+	/*
+	 * Rotate the first entry last (works just fine for group events too):
+	 */
+	perf_disable();
+	list_for_each_entry(event, &ctx->group_list, group_entry) {
+		list_move_tail(&event->group_entry, &ctx->group_list);
+		break;
+	}
+	perf_enable();
+
+	spin_unlock(&ctx->lock);
+}
+
+void perf_event_task_tick(struct task_struct *curr, int cpu)
+{
+	struct perf_cpu_context *cpuctx;
+	struct perf_event_context *ctx;
+
+	if (!atomic_read(&nr_events))
+		return;
+
+	cpuctx = &per_cpu(perf_cpu_context, cpu);
+	ctx = curr->perf_event_ctxp;
+
+	perf_ctx_adjust_freq(&cpuctx->ctx);
+	if (ctx)
+		perf_ctx_adjust_freq(ctx);
+
+	perf_event_cpu_sched_out(cpuctx);
+	if (ctx)
+		__perf_event_task_sched_out(ctx);
+
+	rotate_ctx(&cpuctx->ctx);
+	if (ctx)
+		rotate_ctx(ctx);
+
+	perf_event_cpu_sched_in(cpuctx, cpu);
+	if (ctx)
+		perf_event_task_sched_in(curr, cpu);
+}
+
+/*
+ * Enable all of a task's events that have been marked enable-on-exec.
+ * This expects task == current.
+ */
+static void perf_event_enable_on_exec(struct task_struct *task)
+{
+	struct perf_event_context *ctx;
+	struct perf_event *event;
+	unsigned long flags;
+	int enabled = 0;
+
+	local_irq_save(flags);
+	ctx = task->perf_event_ctxp;
+	if (!ctx || !ctx->nr_events)
+		goto out;
+
+	__perf_event_task_sched_out(ctx);
+
+	spin_lock(&ctx->lock);
+
+	list_for_each_entry(event, &ctx->group_list, group_entry) {
+		if (!event->attr.enable_on_exec)
+			continue;
+		event->attr.enable_on_exec = 0;
+		if (event->state >= PERF_EVENT_STATE_INACTIVE)
+			continue;
+		__perf_event_mark_enabled(event, ctx);
+		enabled = 1;
+	}
+
+	/*
+	 * Unclone this context if we enabled any event.
+	 */
+	if (enabled)
+		unclone_ctx(ctx);
+
+	spin_unlock(&ctx->lock);
+
+	perf_event_task_sched_in(task, smp_processor_id());
+ out:
+	local_irq_restore(flags);
+}
+
+/*
+ * Cross CPU call to read the hardware event
+ */
+static void __perf_event_read(void *info)
+{
+	struct perf_cpu_context *cpuctx = &__get_cpu_var(perf_cpu_context);
+	struct perf_event *event = info;
+	struct perf_event_context *ctx = event->ctx;
+	unsigned long flags;
+
+	/*
+	 * If this is a task context, we need to check whether it is
+	 * the current task context of this cpu.  If not it has been
+	 * scheduled out before the smp call arrived.  In that case
+	 * event->count would have been updated to a recent sample
+	 * when the event was scheduled out.
+	 */
+	if (ctx->task && cpuctx->task_ctx != ctx)
+		return;
+
+	local_irq_save(flags);
+	if (ctx->is_active)
+		update_context_time(ctx);
+	event->pmu->read(event);
+	update_event_times(event);
+	local_irq_restore(flags);
+}
+
+static u64 perf_event_read(struct perf_event *event)
+{
+	/*
+	 * If event is enabled and currently active on a CPU, update the
+	 * value in the event structure:
+	 */
+	if (event->state == PERF_EVENT_STATE_ACTIVE) {
+		smp_call_function_single(event->oncpu,
+					 __perf_event_read, event, 1);
+	} else if (event->state == PERF_EVENT_STATE_INACTIVE) {
+		update_event_times(event);
+	}
+
+	return atomic64_read(&event->count);
+}
+
+/*
+ * Initialize the perf_event context in a task_struct:
+ */
+static void
+__perf_event_init_context(struct perf_event_context *ctx,
+			    struct task_struct *task)
+{
+	memset(ctx, 0, sizeof(*ctx));
+	spin_lock_init(&ctx->lock);
+	mutex_init(&ctx->mutex);
+	INIT_LIST_HEAD(&ctx->group_list);
+	INIT_LIST_HEAD(&ctx->event_list);
+	atomic_set(&ctx->refcount, 1);
+	ctx->task = task;
+}
+
+static struct perf_event_context *find_get_context(pid_t pid, int cpu)
+{
+	struct perf_event_context *ctx;
+	struct perf_cpu_context *cpuctx;
+	struct task_struct *task;
+	unsigned long flags;
+	int err;
+
+	/*
+	 * If cpu is not a wildcard then this is a percpu event:
+	 */
+	if (cpu != -1) {
+		/* Must be root to operate on a CPU event: */
+		if (perf_paranoid_cpu() && !capable(CAP_SYS_ADMIN))
+			return ERR_PTR(-EACCES);
+
+		if (cpu < 0 || cpu > num_possible_cpus())
+			return ERR_PTR(-EINVAL);
+
+		/*
+		 * We could be clever and allow to attach a event to an
+		 * offline CPU and activate it when the CPU comes up, but
+		 * that's for later.
+		 */
+		if (!cpu_isset(cpu, cpu_online_map))
+			return ERR_PTR(-ENODEV);
+
+		cpuctx = &per_cpu(perf_cpu_context, cpu);
+		ctx = &cpuctx->ctx;
+		get_ctx(ctx);
+
+		return ctx;
+	}
+
+	rcu_read_lock();
+	if (!pid)
+		task = current;
+	else
+		task = find_task_by_vpid(pid);
+	if (task)
+		get_task_struct(task);
+	rcu_read_unlock();
+
+	if (!task)
+		return ERR_PTR(-ESRCH);
+
+	/*
+	 * Can't attach events to a dying task.
+	 */
+	err = -ESRCH;
+	if (task->flags & PF_EXITING)
+		goto errout;
+
+	/* Reuse ptrace permission checks for now. */
+	err = -EACCES;
+	if (!ptrace_may_access(task, PTRACE_MODE_READ))
+		goto errout;
+
+ retry:
+	ctx = perf_lock_task_context(task, &flags);
+	if (ctx) {
+		unclone_ctx(ctx);
+		spin_unlock_irqrestore(&ctx->lock, flags);
+	}
+
+	if (!ctx) {
+		ctx = kmalloc(sizeof(struct perf_event_context), GFP_KERNEL);
+		err = -ENOMEM;
+		if (!ctx)
+			goto errout;
+		__perf_event_init_context(ctx, task);
+		get_ctx(ctx);
+		if (cmpxchg(&task->perf_event_ctxp, NULL, ctx)) {
+			/*
+			 * We raced with some other task; use
+			 * the context they set.
+			 */
+			kfree(ctx);
+			goto retry;
+		}
+		get_task_struct(task);
+	}
+
+	put_task_struct(task);
+	return ctx;
+
+ errout:
+	put_task_struct(task);
+	return ERR_PTR(err);
+}
+
+static void free_event_rcu(struct rcu_head *head)
+{
+	struct perf_event *event;
+
+	event = container_of(head, struct perf_event, rcu_head);
+	if (event->ns)
+		put_pid_ns(event->ns);
+	kfree(event);
+}
+
+static void perf_pending_sync(struct perf_event *event);
+
+static void free_event(struct perf_event *event)
+{
+	perf_pending_sync(event);
+
+	if (!event->parent) {
+		atomic_dec(&nr_events);
+		if (event->attr.mmap)
+			atomic_dec(&nr_mmap_events);
+		if (event->attr.comm)
+			atomic_dec(&nr_comm_events);
+		if (event->attr.task)
+			atomic_dec(&nr_task_events);
+	}
+
+	if (event->output) {
+		fput(event->output->filp);
+		event->output = NULL;
+	}
+
+	if (event->destroy)
+		event->destroy(event);
+
+	put_ctx(event->ctx);
+	call_rcu(&event->rcu_head, free_event_rcu);
+}
+
+/*
+ * Called when the last reference to the file is gone.
+ */
+static int perf_release(struct inode *inode, struct file *file)
+{
+	struct perf_event *event = file->private_data;
+	struct perf_event_context *ctx = event->ctx;
+
+	file->private_data = NULL;
+
+	WARN_ON_ONCE(ctx->parent_ctx);
+	mutex_lock(&ctx->mutex);
+	perf_event_remove_from_context(event);
+	mutex_unlock(&ctx->mutex);
+
+	mutex_lock(&event->owner->perf_event_mutex);
+	list_del_init(&event->owner_entry);
+	mutex_unlock(&event->owner->perf_event_mutex);
+	put_task_struct(event->owner);
+
+	free_event(event);
+
+	return 0;
+}
+
+static int perf_event_read_size(struct perf_event *event)
+{
+	int entry = sizeof(u64); /* value */
+	int size = 0;
+	int nr = 1;
+
+	if (event->attr.read_format & PERF_FORMAT_TOTAL_TIME_ENABLED)
+		size += sizeof(u64);
+
+	if (event->attr.read_format & PERF_FORMAT_TOTAL_TIME_RUNNING)
+		size += sizeof(u64);
+
+	if (event->attr.read_format & PERF_FORMAT_ID)
+		entry += sizeof(u64);
+
+	if (event->attr.read_format & PERF_FORMAT_GROUP) {
+		nr += event->group_leader->nr_siblings;
+		size += sizeof(u64);
+	}
+
+	size += entry * nr;
+
+	return size;
+}
+
+static u64 perf_event_read_value(struct perf_event *event)
+{
+	struct perf_event *child;
+	u64 total = 0;
+
+	total += perf_event_read(event);
+	list_for_each_entry(child, &event->child_list, child_list)
+		total += perf_event_read(child);
+
+	return total;
+}
+
+static int perf_event_read_entry(struct perf_event *event,
+				   u64 read_format, char __user *buf)
+{
+	int n = 0, count = 0;
+	u64 values[2];
+
+	values[n++] = perf_event_read_value(event);
+	if (read_format & PERF_FORMAT_ID)
+		values[n++] = primary_event_id(event);
+
+	count = n * sizeof(u64);
+
+	if (copy_to_user(buf, values, count))
+		return -EFAULT;
+
+	return count;
+}
+
+static int perf_event_read_group(struct perf_event *event,
+				   u64 read_format, char __user *buf)
+{
+	struct perf_event *leader = event->group_leader, *sub;
+	int n = 0, size = 0, err = -EFAULT;
+	u64 values[3];
+
+	values[n++] = 1 + leader->nr_siblings;
+	if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) {
+		values[n++] = leader->total_time_enabled +
+			atomic64_read(&leader->child_total_time_enabled);
+	}
+	if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING) {
+		values[n++] = leader->total_time_running +
+			atomic64_read(&leader->child_total_time_running);
+	}
+
+	size = n * sizeof(u64);
+
+	if (copy_to_user(buf, values, size))
+		return -EFAULT;
+
+	err = perf_event_read_entry(leader, read_format, buf + size);
+	if (err < 0)
+		return err;
+
+	size += err;
+
+	list_for_each_entry(sub, &leader->sibling_list, group_entry) {
+		err = perf_event_read_entry(sub, read_format,
+				buf + size);
+		if (err < 0)
+			return err;
+
+		size += err;
+	}
+
+	return size;
+}
+
+static int perf_event_read_one(struct perf_event *event,
+				 u64 read_format, char __user *buf)
+{
+	u64 values[4];
+	int n = 0;
+
+	values[n++] = perf_event_read_value(event);
+	if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) {
+		values[n++] = event->total_time_enabled +
+			atomic64_read(&event->child_total_time_enabled);
+	}
+	if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING) {
+		values[n++] = event->total_time_running +
+			atomic64_read(&event->child_total_time_running);
+	}
+	if (read_format & PERF_FORMAT_ID)
+		values[n++] = primary_event_id(event);
+
+	if (copy_to_user(buf, values, n * sizeof(u64)))
+		return -EFAULT;
+
+	return n * sizeof(u64);
+}
+
+/*
+ * Read the performance event - simple non blocking version for now
+ */
+static ssize_t
+perf_read_hw(struct perf_event *event, char __user *buf, size_t count)
+{
+	u64 read_format = event->attr.read_format;
+	int ret;
+
+	/*
+	 * Return end-of-file for a read on a event that is in
+	 * error state (i.e. because it was pinned but it couldn't be
+	 * scheduled on to the CPU at some point).
+	 */
+	if (event->state == PERF_EVENT_STATE_ERROR)
+		return 0;
+
+	if (count < perf_event_read_size(event))
+		return -ENOSPC;
+
+	WARN_ON_ONCE(event->ctx->parent_ctx);
+	mutex_lock(&event->child_mutex);
+	if (read_format & PERF_FORMAT_GROUP)
+		ret = perf_event_read_group(event, read_format, buf);
+	else
+		ret = perf_event_read_one(event, read_format, buf);
+	mutex_unlock(&event->child_mutex);
+
+	return ret;
+}
+
+static ssize_t
+perf_read(struct file *file, char __user *buf, size_t count, loff_t *ppos)
+{
+	struct perf_event *event = file->private_data;
+
+	return perf_read_hw(event, buf, count);
+}
+
+static unsigned int perf_poll(struct file *file, poll_table *wait)
+{
+	struct perf_event *event = file->private_data;
+	struct perf_mmap_data *data;
+	unsigned int events = POLL_HUP;
+
+	rcu_read_lock();
+	data = rcu_dereference(event->data);
+	if (data)
+		events = atomic_xchg(&data->poll, 0);
+	rcu_read_unlock();
+
+	poll_wait(file, &event->waitq, wait);
+
+	return events;
+}
+
+static void perf_event_reset(struct perf_event *event)
+{
+	(void)perf_event_read(event);
+	atomic64_set(&event->count, 0);
+	perf_event_update_userpage(event);
+}
+
+/*
+ * Holding the top-level event's child_mutex means that any
+ * descendant process that has inherited this event will block
+ * in sync_child_event if it goes to exit, thus satisfying the
+ * task existence requirements of perf_event_enable/disable.
+ */
+static void perf_event_for_each_child(struct perf_event *event,
+					void (*func)(struct perf_event *))
+{
+	struct perf_event *child;
+
+	WARN_ON_ONCE(event->ctx->parent_ctx);
+	mutex_lock(&event->child_mutex);
+	func(event);
+	list_for_each_entry(child, &event->child_list, child_list)
+		func(child);
+	mutex_unlock(&event->child_mutex);
+}
+
+static void perf_event_for_each(struct perf_event *event,
+				  void (*func)(struct perf_event *))
+{
+	struct perf_event_context *ctx = event->ctx;
+	struct perf_event *sibling;
+
+	WARN_ON_ONCE(ctx->parent_ctx);
+	mutex_lock(&ctx->mutex);
+	event = event->group_leader;
+
+	perf_event_for_each_child(event, func);
+	func(event);
+	list_for_each_entry(sibling, &event->sibling_list, group_entry)
+		perf_event_for_each_child(event, func);
+	mutex_unlock(&ctx->mutex);
+}
+
+static int perf_event_period(struct perf_event *event, u64 __user *arg)
+{
+	struct perf_event_context *ctx = event->ctx;
+	unsigned long size;
+	int ret = 0;
+	u64 value;
+
+	if (!event->attr.sample_period)
+		return -EINVAL;
+
+	size = copy_from_user(&value, arg, sizeof(value));
+	if (size != sizeof(value))
+		return -EFAULT;
+
+	if (!value)
+		return -EINVAL;
+
+	spin_lock_irq(&ctx->lock);
+	if (event->attr.freq) {
+		if (value > sysctl_perf_event_sample_rate) {
+			ret = -EINVAL;
+			goto unlock;
+		}
+
+		event->attr.sample_freq = value;
+	} else {
+		event->attr.sample_period = value;
+		event->hw.sample_period = value;
+	}
+unlock:
+	spin_unlock_irq(&ctx->lock);
+
+	return ret;
+}
+
+int perf_event_set_output(struct perf_event *event, int output_fd);
+
+static long perf_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
+{
+	struct perf_event *event = file->private_data;
+	void (*func)(struct perf_event *);
+	u32 flags = arg;
+
+	switch (cmd) {
+	case PERF_EVENT_IOC_ENABLE:
+		func = perf_event_enable;
+		break;
+	case PERF_EVENT_IOC_DISABLE:
+		func = perf_event_disable;
+		break;
+	case PERF_EVENT_IOC_RESET:
+		func = perf_event_reset;
+		break;
+
+	case PERF_EVENT_IOC_REFRESH:
+		return perf_event_refresh(event, arg);
+
+	case PERF_EVENT_IOC_PERIOD:
+		return perf_event_period(event, (u64 __user *)arg);
+
+	case PERF_EVENT_IOC_SET_OUTPUT:
+		return perf_event_set_output(event, arg);
+
+	default:
+		return -ENOTTY;
+	}
+
+	if (flags & PERF_IOC_FLAG_GROUP)
+		perf_event_for_each(event, func);
+	else
+		perf_event_for_each_child(event, func);
+
+	return 0;
+}
+
+int perf_event_task_enable(void)
+{
+	struct perf_event *event;
+
+	mutex_lock(&current->perf_event_mutex);
+	list_for_each_entry(event, &current->perf_event_list, owner_entry)
+		perf_event_for_each_child(event, perf_event_enable);
+	mutex_unlock(&current->perf_event_mutex);
+
+	return 0;
+}
+
+int perf_event_task_disable(void)
+{
+	struct perf_event *event;
+
+	mutex_lock(&current->perf_event_mutex);
+	list_for_each_entry(event, &current->perf_event_list, owner_entry)
+		perf_event_for_each_child(event, perf_event_disable);
+	mutex_unlock(&current->perf_event_mutex);
+
+	return 0;
+}
+
+#ifndef PERF_EVENT_INDEX_OFFSET
+# define PERF_EVENT_INDEX_OFFSET 0
+#endif
+
+static int perf_event_index(struct perf_event *event)
+{
+	if (event->state != PERF_EVENT_STATE_ACTIVE)
+		return 0;
+
+	return event->hw.idx + 1 - PERF_EVENT_INDEX_OFFSET;
+}
+
+/*
+ * Callers need to ensure there can be no nesting of this function, otherwise
+ * the seqlock logic goes bad. We can not serialize this because the arch
+ * code calls this from NMI context.
+ */
+void perf_event_update_userpage(struct perf_event *event)
+{
+	struct perf_event_mmap_page *userpg;
+	struct perf_mmap_data *data;
+
+	rcu_read_lock();
+	data = rcu_dereference(event->data);
+	if (!data)
+		goto unlock;
+
+	userpg = data->user_page;
+
+	/*
+	 * Disable preemption so as to not let the corresponding user-space
+	 * spin too long if we get preempted.
+	 */
+	preempt_disable();
+	++userpg->lock;
+	barrier();
+	userpg->index = perf_event_index(event);
+	userpg->offset = atomic64_read(&event->count);
+	if (event->state == PERF_EVENT_STATE_ACTIVE)
+		userpg->offset -= atomic64_read(&event->hw.prev_count);
+
+	userpg->time_enabled = event->total_time_enabled +
+			atomic64_read(&event->child_total_time_enabled);
+
+	userpg->time_running = event->total_time_running +
+			atomic64_read(&event->child_total_time_running);
+
+	barrier();
+	++userpg->lock;
+	preempt_enable();
+unlock:
+	rcu_read_unlock();
+}
+
+static unsigned long perf_data_size(struct perf_mmap_data *data)
+{
+	return data->nr_pages << (PAGE_SHIFT + data->data_order);
+}
+
+#ifndef CONFIG_PERF_USE_VMALLOC
+
+/*
+ * Back perf_mmap() with regular GFP_KERNEL-0 pages.
+ */
+
+static struct page *
+perf_mmap_to_page(struct perf_mmap_data *data, unsigned long pgoff)
+{
+	if (pgoff > data->nr_pages)
+		return NULL;
+
+	if (pgoff == 0)
+		return virt_to_page(data->user_page);
+
+	return virt_to_page(data->data_pages[pgoff - 1]);
+}
+
+static struct perf_mmap_data *
+perf_mmap_data_alloc(struct perf_event *event, int nr_pages)
+{
+	struct perf_mmap_data *data;
+	unsigned long size;
+	int i;
+
+	WARN_ON(atomic_read(&event->mmap_count));
+
+	size = sizeof(struct perf_mmap_data);
+	size += nr_pages * sizeof(void *);
+
+	data = kzalloc(size, GFP_KERNEL);
+	if (!data)
+		goto fail;
+
+	data->user_page = (void *)get_zeroed_page(GFP_KERNEL);
+	if (!data->user_page)
+		goto fail_user_page;
+
+	for (i = 0; i < nr_pages; i++) {
+		data->data_pages[i] = (void *)get_zeroed_page(GFP_KERNEL);
+		if (!data->data_pages[i])
+			goto fail_data_pages;
+	}
+
+	data->data_order = 0;
+	data->nr_pages = nr_pages;
+
+	return data;
+
+fail_data_pages:
+	for (i--; i >= 0; i--)
+		free_page((unsigned long)data->data_pages[i]);
+
+	free_page((unsigned long)data->user_page);
+
+fail_user_page:
+	kfree(data);
+
+fail:
+	return NULL;
+}
+
+static void perf_mmap_free_page(unsigned long addr)
+{
+	struct page *page = virt_to_page((void *)addr);
+
+	page->mapping = NULL;
+	__free_page(page);
+}
+
+static void perf_mmap_data_free(struct perf_mmap_data *data)
+{
+	int i;
+
+	perf_mmap_free_page((unsigned long)data->user_page);
+	for (i = 0; i < data->nr_pages; i++)
+		perf_mmap_free_page((unsigned long)data->data_pages[i]);
+}
+
+#else
+
+/*
+ * Back perf_mmap() with vmalloc memory.
+ *
+ * Required for architectures that have d-cache aliasing issues.
+ */
+
+static struct page *
+perf_mmap_to_page(struct perf_mmap_data *data, unsigned long pgoff)
+{
+	if (pgoff > (1UL << data->data_order))
+		return NULL;
+
+	return vmalloc_to_page((void *)data->user_page + pgoff * PAGE_SIZE);
+}
+
+static void perf_mmap_unmark_page(void *addr)
+{
+	struct page *page = vmalloc_to_page(addr);
+
+	page->mapping = NULL;
+}
+
+static void perf_mmap_data_free_work(struct work_struct *work)
+{
+	struct perf_mmap_data *data;
+	void *base;
+	int i, nr;
+
+	data = container_of(work, struct perf_mmap_data, work);
+	nr = 1 << data->data_order;
+
+	base = data->user_page;
+	for (i = 0; i < nr + 1; i++)
+		perf_mmap_unmark_page(base + (i * PAGE_SIZE));
+
+	vfree(base);
+}
+
+static void perf_mmap_data_free(struct perf_mmap_data *data)
+{
+	schedule_work(&data->work);
+}
+
+static struct perf_mmap_data *
+perf_mmap_data_alloc(struct perf_event *event, int nr_pages)
+{
+	struct perf_mmap_data *data;
+	unsigned long size;
+	void *all_buf;
+
+	WARN_ON(atomic_read(&event->mmap_count));
+
+	size = sizeof(struct perf_mmap_data);
+	size += sizeof(void *);
+
+	data = kzalloc(size, GFP_KERNEL);
+	if (!data)
+		goto fail;
+
+	INIT_WORK(&data->work, perf_mmap_data_free_work);
+
+	all_buf = vmalloc_user((nr_pages + 1) * PAGE_SIZE);
+	if (!all_buf)
+		goto fail_all_buf;
+
+	data->user_page = all_buf;
+	data->data_pages[0] = all_buf + PAGE_SIZE;
+	data->data_order = ilog2(nr_pages);
+	data->nr_pages = 1;
+
+	return data;
+
+fail_all_buf:
+	kfree(data);
+
+fail:
+	return NULL;
+}
+
+#endif
+
+static int perf_mmap_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
+{
+	struct perf_event *event = vma->vm_file->private_data;
+	struct perf_mmap_data *data;
+	int ret = VM_FAULT_SIGBUS;
+
+	if (vmf->flags & FAULT_FLAG_MKWRITE) {
+		if (vmf->pgoff == 0)
+			ret = 0;
+		return ret;
+	}
+
+	rcu_read_lock();
+	data = rcu_dereference(event->data);
+	if (!data)
+		goto unlock;
+
+	if (vmf->pgoff && (vmf->flags & FAULT_FLAG_WRITE))
+		goto unlock;
+
+	vmf->page = perf_mmap_to_page(data, vmf->pgoff);
+	if (!vmf->page)
+		goto unlock;
+
+	get_page(vmf->page);
+	vmf->page->mapping = vma->vm_file->f_mapping;
+	vmf->page->index   = vmf->pgoff;
+
+	ret = 0;
+unlock:
+	rcu_read_unlock();
+
+	return ret;
+}
+
+static void
+perf_mmap_data_init(struct perf_event *event, struct perf_mmap_data *data)
+{
+	long max_size = perf_data_size(data);
+
+	atomic_set(&data->lock, -1);
+
+	if (event->attr.watermark) {
+		data->watermark = min_t(long, max_size,
+					event->attr.wakeup_watermark);
+	}
+
+	if (!data->watermark)
+		data->watermark = max_t(long, PAGE_SIZE, max_size / 2);
+
+
+	rcu_assign_pointer(event->data, data);
+}
+
+static void perf_mmap_data_free_rcu(struct rcu_head *rcu_head)
+{
+	struct perf_mmap_data *data;
+
+	data = container_of(rcu_head, struct perf_mmap_data, rcu_head);
+	perf_mmap_data_free(data);
+	kfree(data);
+}
+
+static void perf_mmap_data_release(struct perf_event *event)
+{
+	struct perf_mmap_data *data = event->data;
+
+	WARN_ON(atomic_read(&event->mmap_count));
+
+	rcu_assign_pointer(event->data, NULL);
+	call_rcu(&data->rcu_head, perf_mmap_data_free_rcu);
+}
+
+static void perf_mmap_open(struct vm_area_struct *vma)
+{
+	struct perf_event *event = vma->vm_file->private_data;
+
+	atomic_inc(&event->mmap_count);
+}
+
+static void perf_mmap_close(struct vm_area_struct *vma)
+{
+	struct perf_event *event = vma->vm_file->private_data;
+
+	WARN_ON_ONCE(event->ctx->parent_ctx);
+	if (atomic_dec_and_mutex_lock(&event->mmap_count, &event->mmap_mutex)) {
+		unsigned long size = perf_data_size(event->data);
+		struct user_struct *user = current_user();
+
+		atomic_long_sub((size >> PAGE_SHIFT) + 1, &user->locked_vm);
+		vma->vm_mm->locked_vm -= event->data->nr_locked;
+		perf_mmap_data_release(event);
+		mutex_unlock(&event->mmap_mutex);
+	}
+}
+
+static const struct vm_operations_struct perf_mmap_vmops = {
+	.open		= perf_mmap_open,
+	.close		= perf_mmap_close,
+	.fault		= perf_mmap_fault,
+	.page_mkwrite	= perf_mmap_fault,
+};
+
+static int perf_mmap(struct file *file, struct vm_area_struct *vma)
+{
+	struct perf_event *event = file->private_data;
+	unsigned long user_locked, user_lock_limit;
+	struct user_struct *user = current_user();
+	unsigned long locked, lock_limit;
+	struct perf_mmap_data *data;
+	unsigned long vma_size;
+	unsigned long nr_pages;
+	long user_extra, extra;
+	int ret = 0;
+
+	if (!(vma->vm_flags & VM_SHARED))
+		return -EINVAL;
+
+	vma_size = vma->vm_end - vma->vm_start;
+	nr_pages = (vma_size / PAGE_SIZE) - 1;
+
+	/*
+	 * If we have data pages ensure they're a power-of-two number, so we
+	 * can do bitmasks instead of modulo.
+	 */
+	if (nr_pages != 0 && !is_power_of_2(nr_pages))
+		return -EINVAL;
+
+	if (vma_size != PAGE_SIZE * (1 + nr_pages))
+		return -EINVAL;
+
+	if (vma->vm_pgoff != 0)
+		return -EINVAL;
+
+	WARN_ON_ONCE(event->ctx->parent_ctx);
+	mutex_lock(&event->mmap_mutex);
+	if (event->output) {
+		ret = -EINVAL;
+		goto unlock;
+	}
+
+	if (atomic_inc_not_zero(&event->mmap_count)) {
+		if (nr_pages != event->data->nr_pages)
+			ret = -EINVAL;
+		goto unlock;
+	}
+
+	user_extra = nr_pages + 1;
+	user_lock_limit = sysctl_perf_event_mlock >> (PAGE_SHIFT - 10);
+
+	/*
+	 * Increase the limit linearly with more CPUs:
+	 */
+	user_lock_limit *= num_online_cpus();
+
+	user_locked = atomic_long_read(&user->locked_vm) + user_extra;
+
+	extra = 0;
+	if (user_locked > user_lock_limit)
+		extra = user_locked - user_lock_limit;
+
+	lock_limit = current->signal->rlim[RLIMIT_MEMLOCK].rlim_cur;
+	lock_limit >>= PAGE_SHIFT;
+	locked = vma->vm_mm->locked_vm + extra;
+
+	if ((locked > lock_limit) && perf_paranoid_tracepoint_raw() &&
+		!capable(CAP_IPC_LOCK)) {
+		ret = -EPERM;
+		goto unlock;
+	}
+
+	WARN_ON(event->data);
+
+	data = perf_mmap_data_alloc(event, nr_pages);
+	ret = -ENOMEM;
+	if (!data)
+		goto unlock;
+
+	ret = 0;
+	perf_mmap_data_init(event, data);
+
+	atomic_set(&event->mmap_count, 1);
+	atomic_long_add(user_extra, &user->locked_vm);
+	vma->vm_mm->locked_vm += extra;
+	event->data->nr_locked = extra;
+	if (vma->vm_flags & VM_WRITE)
+		event->data->writable = 1;
+
+unlock:
+	mutex_unlock(&event->mmap_mutex);
+
+	vma->vm_flags |= VM_RESERVED;
+	vma->vm_ops = &perf_mmap_vmops;
+
+	return ret;
+}
+
+static int perf_fasync(int fd, struct file *filp, int on)
+{
+	struct inode *inode = filp->f_path.dentry->d_inode;
+	struct perf_event *event = filp->private_data;
+	int retval;
+
+	mutex_lock(&inode->i_mutex);
+	retval = fasync_helper(fd, filp, on, &event->fasync);
+	mutex_unlock(&inode->i_mutex);
+
+	if (retval < 0)
+		return retval;
+
+	return 0;
+}
+
+static const struct file_operations perf_fops = {
+	.release		= perf_release,
+	.read			= perf_read,
+	.poll			= perf_poll,
+	.unlocked_ioctl		= perf_ioctl,
+	.compat_ioctl		= perf_ioctl,
+	.mmap			= perf_mmap,
+	.fasync			= perf_fasync,
+};
+
+/*
+ * Perf event wakeup
+ *
+ * If there's data, ensure we set the poll() state and publish everything
+ * to user-space before waking everybody up.
+ */
+
+void perf_event_wakeup(struct perf_event *event)
+{
+	wake_up_all(&event->waitq);
+
+	if (event->pending_kill) {
+		kill_fasync(&event->fasync, SIGIO, event->pending_kill);
+		event->pending_kill = 0;
+	}
+}
+
+/*
+ * Pending wakeups
+ *
+ * Handle the case where we need to wakeup up from NMI (or rq->lock) context.
+ *
+ * The NMI bit means we cannot possibly take locks. Therefore, maintain a
+ * single linked list and use cmpxchg() to add entries lockless.
+ */
+
+static void perf_pending_event(struct perf_pending_entry *entry)
+{
+	struct perf_event *event = container_of(entry,
+			struct perf_event, pending);
+
+	if (event->pending_disable) {
+		event->pending_disable = 0;
+		__perf_event_disable(event);
+	}
+
+	if (event->pending_wakeup) {
+		event->pending_wakeup = 0;
+		perf_event_wakeup(event);
+	}
+}
+
+#define PENDING_TAIL ((struct perf_pending_entry *)-1UL)
+
+static DEFINE_PER_CPU(struct perf_pending_entry *, perf_pending_head) = {
+	PENDING_TAIL,
+};
+
+static void perf_pending_queue(struct perf_pending_entry *entry,
+			       void (*func)(struct perf_pending_entry *))
+{
+	struct perf_pending_entry **head;
+
+	if (cmpxchg(&entry->next, NULL, PENDING_TAIL) != NULL)
+		return;
+
+	entry->func = func;
+
+	head = &get_cpu_var(perf_pending_head);
+
+	do {
+		entry->next = *head;
+	} while (cmpxchg(head, entry->next, entry) != entry->next);
+
+	set_perf_event_pending();
+
+	put_cpu_var(perf_pending_head);
+}
+
+static int __perf_pending_run(void)
+{
+	struct perf_pending_entry *list;
+	int nr = 0;
+
+	list = xchg(&__get_cpu_var(perf_pending_head), PENDING_TAIL);
+	while (list != PENDING_TAIL) {
+		void (*func)(struct perf_pending_entry *);
+		struct perf_pending_entry *entry = list;
+
+		list = list->next;
+
+		func = entry->func;
+		entry->next = NULL;
+		/*
+		 * Ensure we observe the unqueue before we issue the wakeup,
+		 * so that we won't be waiting forever.
+		 * -- see perf_not_pending().
+		 */
+		smp_wmb();
+
+		func(entry);
+		nr++;
+	}
+
+	return nr;
+}
+
+static inline int perf_not_pending(struct perf_event *event)
+{
+	/*
+	 * If we flush on whatever cpu we run, there is a chance we don't
+	 * need to wait.
+	 */
+	get_cpu();
+	__perf_pending_run();
+	put_cpu();
+
+	/*
+	 * Ensure we see the proper queue state before going to sleep
+	 * so that we do not miss the wakeup. -- see perf_pending_handle()
+	 */
+	smp_rmb();
+	return event->pending.next == NULL;
+}
+
+static void perf_pending_sync(struct perf_event *event)
+{
+	wait_event(event->waitq, perf_not_pending(event));
+}
+
+void perf_event_do_pending(void)
+{
+	__perf_pending_run();
+}
+
+/*
+ * Callchain support -- arch specific
+ */
+
+__weak struct perf_callchain_entry *perf_callchain(struct pt_regs *regs)
+{
+	return NULL;
+}
+
+/*
+ * Output
+ */
+static bool perf_output_space(struct perf_mmap_data *data, unsigned long tail,
+			      unsigned long offset, unsigned long head)
+{
+	unsigned long mask;
+
+	if (!data->writable)
+		return true;
+
+	mask = perf_data_size(data) - 1;
+
+	offset = (offset - tail) & mask;
+	head   = (head   - tail) & mask;
+
+	if ((int)(head - offset) < 0)
+		return false;
+
+	return true;
+}
+
+static void perf_output_wakeup(struct perf_output_handle *handle)
+{
+	atomic_set(&handle->data->poll, POLL_IN);
+
+	if (handle->nmi) {
+		handle->event->pending_wakeup = 1;
+		perf_pending_queue(&handle->event->pending,
+				   perf_pending_event);
+	} else
+		perf_event_wakeup(handle->event);
+}
+
+/*
+ * Curious locking construct.
+ *
+ * We need to ensure a later event_id doesn't publish a head when a former
+ * event_id isn't done writing. However since we need to deal with NMIs we
+ * cannot fully serialize things.
+ *
+ * What we do is serialize between CPUs so we only have to deal with NMI
+ * nesting on a single CPU.
+ *
+ * We only publish the head (and generate a wakeup) when the outer-most
+ * event_id completes.
+ */
+static void perf_output_lock(struct perf_output_handle *handle)
+{
+	struct perf_mmap_data *data = handle->data;
+	int cpu;
+
+	handle->locked = 0;
+
+	local_irq_save(handle->flags);
+	cpu = smp_processor_id();
+
+	if (in_nmi() && atomic_read(&data->lock) == cpu)
+		return;
+
+	while (atomic_cmpxchg(&data->lock, -1, cpu) != -1)
+		cpu_relax();
+
+	handle->locked = 1;
+}
+
+static void perf_output_unlock(struct perf_output_handle *handle)
+{
+	struct perf_mmap_data *data = handle->data;
+	unsigned long head;
+	int cpu;
+
+	data->done_head = data->head;
+
+	if (!handle->locked)
+		goto out;
+
+again:
+	/*
+	 * The xchg implies a full barrier that ensures all writes are done
+	 * before we publish the new head, matched by a rmb() in userspace when
+	 * reading this position.
+	 */
+	while ((head = atomic_long_xchg(&data->done_head, 0)))
+		data->user_page->data_head = head;
+
+	/*
+	 * NMI can happen here, which means we can miss a done_head update.
+	 */
+
+	cpu = atomic_xchg(&data->lock, -1);
+	WARN_ON_ONCE(cpu != smp_processor_id());
+
+	/*
+	 * Therefore we have to validate we did not indeed do so.
+	 */
+	if (unlikely(atomic_long_read(&data->done_head))) {
+		/*
+		 * Since we had it locked, we can lock it again.
+		 */
+		while (atomic_cmpxchg(&data->lock, -1, cpu) != -1)
+			cpu_relax();
+
+		goto again;
+	}
+
+	if (atomic_xchg(&data->wakeup, 0))
+		perf_output_wakeup(handle);
+out:
+	local_irq_restore(handle->flags);
+}
+
+void perf_output_copy(struct perf_output_handle *handle,
+		      const void *buf, unsigned int len)
+{
+	unsigned int pages_mask;
+	unsigned long offset;
+	unsigned int size;
+	void **pages;
+
+	offset		= handle->offset;
+	pages_mask	= handle->data->nr_pages - 1;
+	pages		= handle->data->data_pages;
+
+	do {
+		unsigned long page_offset;
+		unsigned long page_size;
+		int nr;
+
+		nr	    = (offset >> PAGE_SHIFT) & pages_mask;
+		page_size   = 1UL << (handle->data->data_order + PAGE_SHIFT);
+		page_offset = offset & (page_size - 1);
+		size	    = min_t(unsigned int, page_size - page_offset, len);
+
+		memcpy(pages[nr] + page_offset, buf, size);
+
+		len	    -= size;
+		buf	    += size;
+		offset	    += size;
+	} while (len);
+
+	handle->offset = offset;
+
+	/*
+	 * Check we didn't copy past our reservation window, taking the
+	 * possible unsigned int wrap into account.
+	 */
+	WARN_ON_ONCE(((long)(handle->head - handle->offset)) < 0);
+}
+
+int perf_output_begin(struct perf_output_handle *handle,
+		      struct perf_event *event, unsigned int size,
+		      int nmi, int sample)
+{
+	struct perf_event *output_event;
+	struct perf_mmap_data *data;
+	unsigned long tail, offset, head;
+	int have_lost;
+	struct {
+		struct perf_event_header header;
+		u64			 id;
+		u64			 lost;
+	} lost_event;
+
+	rcu_read_lock();
+	/*
+	 * For inherited events we send all the output towards the parent.
+	 */
+	if (event->parent)
+		event = event->parent;
+
+	output_event = rcu_dereference(event->output);
+	if (output_event)
+		event = output_event;
+
+	data = rcu_dereference(event->data);
+	if (!data)
+		goto out;
+
+	handle->data	= data;
+	handle->event	= event;
+	handle->nmi	= nmi;
+	handle->sample	= sample;
+
+	if (!data->nr_pages)
+		goto fail;
+
+	have_lost = atomic_read(&data->lost);
+	if (have_lost)
+		size += sizeof(lost_event);
+
+	perf_output_lock(handle);
+
+	do {
+		/*
+		 * Userspace could choose to issue a mb() before updating the
+		 * tail pointer. So that all reads will be completed before the
+		 * write is issued.
+		 */
+		tail = ACCESS_ONCE(data->user_page->data_tail);
+		smp_rmb();
+		offset = head = atomic_long_read(&data->head);
+		head += size;
+		if (unlikely(!perf_output_space(data, tail, offset, head)))
+			goto fail;
+	} while (atomic_long_cmpxchg(&data->head, offset, head) != offset);
+
+	handle->offset	= offset;
+	handle->head	= head;
+
+	if (head - tail > data->watermark)
+		atomic_set(&data->wakeup, 1);
+
+	if (have_lost) {
+		lost_event.header.type = PERF_RECORD_LOST;
+		lost_event.header.misc = 0;
+		lost_event.header.size = sizeof(lost_event);
+		lost_event.id          = event->id;
+		lost_event.lost        = atomic_xchg(&data->lost, 0);
+
+		perf_output_put(handle, lost_event);
+	}
+
+	return 0;
+
+fail:
+	atomic_inc(&data->lost);
+	perf_output_unlock(handle);
+out:
+	rcu_read_unlock();
+
+	return -ENOSPC;
+}
+
+void perf_output_end(struct perf_output_handle *handle)
+{
+	struct perf_event *event = handle->event;
+	struct perf_mmap_data *data = handle->data;
+
+	int wakeup_events = event->attr.wakeup_events;
+
+	if (handle->sample && wakeup_events) {
+		int events = atomic_inc_return(&data->events);
+		if (events >= wakeup_events) {
+			atomic_sub(wakeup_events, &data->events);
+			atomic_set(&data->wakeup, 1);
+		}
+	}
+
+	perf_output_unlock(handle);
+	rcu_read_unlock();
+}
+
+static u32 perf_event_pid(struct perf_event *event, struct task_struct *p)
+{
+	/*
+	 * only top level events have the pid namespace they were created in
+	 */
+	if (event->parent)
+		event = event->parent;
+
+	return task_tgid_nr_ns(p, event->ns);
+}
+
+static u32 perf_event_tid(struct perf_event *event, struct task_struct *p)
+{
+	/*
+	 * only top level events have the pid namespace they were created in
+	 */
+	if (event->parent)
+		event = event->parent;
+
+	return task_pid_nr_ns(p, event->ns);
+}
+
+static void perf_output_read_one(struct perf_output_handle *handle,
+				 struct perf_event *event)
+{
+	u64 read_format = event->attr.read_format;
+	u64 values[4];
+	int n = 0;
+
+	values[n++] = atomic64_read(&event->count);
+	if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) {
+		values[n++] = event->total_time_enabled +
+			atomic64_read(&event->child_total_time_enabled);
+	}
+	if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING) {
+		values[n++] = event->total_time_running +
+			atomic64_read(&event->child_total_time_running);
+	}
+	if (read_format & PERF_FORMAT_ID)
+		values[n++] = primary_event_id(event);
+
+	perf_output_copy(handle, values, n * sizeof(u64));
+}
+
+/*
+ * XXX PERF_FORMAT_GROUP vs inherited events seems difficult.
+ */
+static void perf_output_read_group(struct perf_output_handle *handle,
+			    struct perf_event *event)
+{
+	struct perf_event *leader = event->group_leader, *sub;
+	u64 read_format = event->attr.read_format;
+	u64 values[5];
+	int n = 0;
+
+	values[n++] = 1 + leader->nr_siblings;
+
+	if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED)
+		values[n++] = leader->total_time_enabled;
+
+	if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING)
+		values[n++] = leader->total_time_running;
+
+	if (leader != event)
+		leader->pmu->read(leader);
+
+	values[n++] = atomic64_read(&leader->count);
+	if (read_format & PERF_FORMAT_ID)
+		values[n++] = primary_event_id(leader);
+
+	perf_output_copy(handle, values, n * sizeof(u64));
+
+	list_for_each_entry(sub, &leader->sibling_list, group_entry) {
+		n = 0;
+
+		if (sub != event)
+			sub->pmu->read(sub);
+
+		values[n++] = atomic64_read(&sub->count);
+		if (read_format & PERF_FORMAT_ID)
+			values[n++] = primary_event_id(sub);
+
+		perf_output_copy(handle, values, n * sizeof(u64));
+	}
+}
+
+static void perf_output_read(struct perf_output_handle *handle,
+			     struct perf_event *event)
+{
+	if (event->attr.read_format & PERF_FORMAT_GROUP)
+		perf_output_read_group(handle, event);
+	else
+		perf_output_read_one(handle, event);
+}
+
+void perf_output_sample(struct perf_output_handle *handle,
+			struct perf_event_header *header,
+			struct perf_sample_data *data,
+			struct perf_event *event)
+{
+	u64 sample_type = data->type;
+
+	perf_output_put(handle, *header);
+
+	if (sample_type & PERF_SAMPLE_IP)
+		perf_output_put(handle, data->ip);
+
+	if (sample_type & PERF_SAMPLE_TID)
+		perf_output_put(handle, data->tid_entry);
+
+	if (sample_type & PERF_SAMPLE_TIME)
+		perf_output_put(handle, data->time);
+
+	if (sample_type & PERF_SAMPLE_ADDR)
+		perf_output_put(handle, data->addr);
+
+	if (sample_type & PERF_SAMPLE_ID)
+		perf_output_put(handle, data->id);
+
+	if (sample_type & PERF_SAMPLE_STREAM_ID)
+		perf_output_put(handle, data->stream_id);
+
+	if (sample_type & PERF_SAMPLE_CPU)
+		perf_output_put(handle, data->cpu_entry);
+
+	if (sample_type & PERF_SAMPLE_PERIOD)
+		perf_output_put(handle, data->period);
+
+	if (sample_type & PERF_SAMPLE_READ)
+		perf_output_read(handle, event);
+
+	if (sample_type & PERF_SAMPLE_CALLCHAIN) {
+		if (data->callchain) {
+			int size = 1;
+
+			if (data->callchain)
+				size += data->callchain->nr;
+
+			size *= sizeof(u64);
+
+			perf_output_copy(handle, data->callchain, size);
+		} else {
+			u64 nr = 0;
+			perf_output_put(handle, nr);
+		}
+	}
+
+	if (sample_type & PERF_SAMPLE_RAW) {
+		if (data->raw) {
+			perf_output_put(handle, data->raw->size);
+			perf_output_copy(handle, data->raw->data,
+					 data->raw->size);
+		} else {
+			struct {
+				u32	size;
+				u32	data;
+			} raw = {
+				.size = sizeof(u32),
+				.data = 0,
+			};
+			perf_output_put(handle, raw);
+		}
+	}
+}
+
+void perf_prepare_sample(struct perf_event_header *header,
+			 struct perf_sample_data *data,
+			 struct perf_event *event,
+			 struct pt_regs *regs)
+{
+	u64 sample_type = event->attr.sample_type;
+
+	data->type = sample_type;
+
+	header->type = PERF_RECORD_SAMPLE;
+	header->size = sizeof(*header);
+
+	header->misc = 0;
+	header->misc |= perf_misc_flags(regs);
+
+	if (sample_type & PERF_SAMPLE_IP) {
+		data->ip = perf_instruction_pointer(regs);
+
+		header->size += sizeof(data->ip);
+	}
+
+	if (sample_type & PERF_SAMPLE_TID) {
+		/* namespace issues */
+		data->tid_entry.pid = perf_event_pid(event, current);
+		data->tid_entry.tid = perf_event_tid(event, current);
+
+		header->size += sizeof(data->tid_entry);
+	}
+
+	if (sample_type & PERF_SAMPLE_TIME) {
+		data->time = perf_clock();
+
+		header->size += sizeof(data->time);
+	}
+
+	if (sample_type & PERF_SAMPLE_ADDR)
+		header->size += sizeof(data->addr);
+
+	if (sample_type & PERF_SAMPLE_ID) {
+		data->id = primary_event_id(event);
+
+		header->size += sizeof(data->id);
+	}
+
+	if (sample_type & PERF_SAMPLE_STREAM_ID) {
+		data->stream_id = event->id;
+
+		header->size += sizeof(data->stream_id);
+	}
+
+	if (sample_type & PERF_SAMPLE_CPU) {
+		data->cpu_entry.cpu		= raw_smp_processor_id();
+		data->cpu_entry.reserved	= 0;
+
+		header->size += sizeof(data->cpu_entry);
+	}
+
+	if (sample_type & PERF_SAMPLE_PERIOD)
+		header->size += sizeof(data->period);
+
+	if (sample_type & PERF_SAMPLE_READ)
+		header->size += perf_event_read_size(event);
+
+	if (sample_type & PERF_SAMPLE_CALLCHAIN) {
+		int size = 1;
+
+		data->callchain = perf_callchain(regs);
+
+		if (data->callchain)
+			size += data->callchain->nr;
+
+		header->size += size * sizeof(u64);
+	}
+
+	if (sample_type & PERF_SAMPLE_RAW) {
+		int size = sizeof(u32);
+
+		if (data->raw)
+			size += data->raw->size;
+		else
+			size += sizeof(u32);
+
+		WARN_ON_ONCE(size & (sizeof(u64)-1));
+		header->size += size;
+	}
+}
+
+static void perf_event_output(struct perf_event *event, int nmi,
+				struct perf_sample_data *data,
+				struct pt_regs *regs)
+{
+	struct perf_output_handle handle;
+	struct perf_event_header header;
+
+	perf_prepare_sample(&header, data, event, regs);
+
+	if (perf_output_begin(&handle, event, header.size, nmi, 1))
+		return;
+
+	perf_output_sample(&handle, &header, data, event);
+
+	perf_output_end(&handle);
+}
+
+/*
+ * read event_id
+ */
+
+struct perf_read_event {
+	struct perf_event_header	header;
+
+	u32				pid;
+	u32				tid;
+};
+
+static void
+perf_event_read_event(struct perf_event *event,
+			struct task_struct *task)
+{
+	struct perf_output_handle handle;
+	struct perf_read_event read_event = {
+		.header = {
+			.type = PERF_RECORD_READ,
+			.misc = 0,
+			.size = sizeof(read_event) + perf_event_read_size(event),
+		},
+		.pid = perf_event_pid(event, task),
+		.tid = perf_event_tid(event, task),
+	};
+	int ret;
+
+	ret = perf_output_begin(&handle, event, read_event.header.size, 0, 0);
+	if (ret)
+		return;
+
+	perf_output_put(&handle, read_event);
+	perf_output_read(&handle, event);
+
+	perf_output_end(&handle);
+}
+
+/*
+ * task tracking -- fork/exit
+ *
+ * enabled by: attr.comm | attr.mmap | attr.task
+ */
+
+struct perf_task_event {
+	struct task_struct		*task;
+	struct perf_event_context	*task_ctx;
+
+	struct {
+		struct perf_event_header	header;
+
+		u32				pid;
+		u32				ppid;
+		u32				tid;
+		u32				ptid;
+		u64				time;
+	} event_id;
+};
+
+static void perf_event_task_output(struct perf_event *event,
+				     struct perf_task_event *task_event)
+{
+	struct perf_output_handle handle;
+	int size;
+	struct task_struct *task = task_event->task;
+	int ret;
+
+	size  = task_event->event_id.header.size;
+	ret = perf_output_begin(&handle, event, size, 0, 0);
+
+	if (ret)
+		return;
+
+	task_event->event_id.pid = perf_event_pid(event, task);
+	task_event->event_id.ppid = perf_event_pid(event, current);
+
+	task_event->event_id.tid = perf_event_tid(event, task);
+	task_event->event_id.ptid = perf_event_tid(event, current);
+
+	task_event->event_id.time = perf_clock();
+
+	perf_output_put(&handle, task_event->event_id);
+
+	perf_output_end(&handle);
+}
+
+static int perf_event_task_match(struct perf_event *event)
+{
+	if (event->attr.comm || event->attr.mmap || event->attr.task)
+		return 1;
+
+	return 0;
+}
+
+static void perf_event_task_ctx(struct perf_event_context *ctx,
+				  struct perf_task_event *task_event)
+{
+	struct perf_event *event;
+
+	if (system_state != SYSTEM_RUNNING || list_empty(&ctx->event_list))
+		return;
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(event, &ctx->event_list, event_entry) {
+		if (perf_event_task_match(event))
+			perf_event_task_output(event, task_event);
+	}
+	rcu_read_unlock();
+}
+
+static void perf_event_task_event(struct perf_task_event *task_event)
+{
+	struct perf_cpu_context *cpuctx;
+	struct perf_event_context *ctx = task_event->task_ctx;
+
+	cpuctx = &get_cpu_var(perf_cpu_context);
+	perf_event_task_ctx(&cpuctx->ctx, task_event);
+	put_cpu_var(perf_cpu_context);
+
+	rcu_read_lock();
+	if (!ctx)
+		ctx = rcu_dereference(task_event->task->perf_event_ctxp);
+	if (ctx)
+		perf_event_task_ctx(ctx, task_event);
+	rcu_read_unlock();
+}
+
+static void perf_event_task(struct task_struct *task,
+			      struct perf_event_context *task_ctx,
+			      int new)
+{
+	struct perf_task_event task_event;
+
+	if (!atomic_read(&nr_comm_events) &&
+	    !atomic_read(&nr_mmap_events) &&
+	    !atomic_read(&nr_task_events))
+		return;
+
+	task_event = (struct perf_task_event){
+		.task	  = task,
+		.task_ctx = task_ctx,
+		.event_id    = {
+			.header = {
+				.type = new ? PERF_RECORD_FORK : PERF_RECORD_EXIT,
+				.misc = 0,
+				.size = sizeof(task_event.event_id),
+			},
+			/* .pid  */
+			/* .ppid */
+			/* .tid  */
+			/* .ptid */
+		},
+	};
+
+	perf_event_task_event(&task_event);
+}
+
+void perf_event_fork(struct task_struct *task)
+{
+	perf_event_task(task, NULL, 1);
+}
+
+/*
+ * comm tracking
+ */
+
+struct perf_comm_event {
+	struct task_struct	*task;
+	char			*comm;
+	int			comm_size;
+
+	struct {
+		struct perf_event_header	header;
+
+		u32				pid;
+		u32				tid;
+	} event_id;
+};
+
+static void perf_event_comm_output(struct perf_event *event,
+				     struct perf_comm_event *comm_event)
+{
+	struct perf_output_handle handle;
+	int size = comm_event->event_id.header.size;
+	int ret = perf_output_begin(&handle, event, size, 0, 0);
+
+	if (ret)
+		return;
+
+	comm_event->event_id.pid = perf_event_pid(event, comm_event->task);
+	comm_event->event_id.tid = perf_event_tid(event, comm_event->task);
+
+	perf_output_put(&handle, comm_event->event_id);
+	perf_output_copy(&handle, comm_event->comm,
+				   comm_event->comm_size);
+	perf_output_end(&handle);
+}
+
+static int perf_event_comm_match(struct perf_event *event)
+{
+	if (event->attr.comm)
+		return 1;
+
+	return 0;
+}
+
+static void perf_event_comm_ctx(struct perf_event_context *ctx,
+				  struct perf_comm_event *comm_event)
+{
+	struct perf_event *event;
+
+	if (system_state != SYSTEM_RUNNING || list_empty(&ctx->event_list))
+		return;
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(event, &ctx->event_list, event_entry) {
+		if (perf_event_comm_match(event))
+			perf_event_comm_output(event, comm_event);
+	}
+	rcu_read_unlock();
+}
+
+static void perf_event_comm_event(struct perf_comm_event *comm_event)
+{
+	struct perf_cpu_context *cpuctx;
+	struct perf_event_context *ctx;
+	unsigned int size;
+	char comm[TASK_COMM_LEN];
+
+	memset(comm, 0, sizeof(comm));
+	strncpy(comm, comm_event->task->comm, sizeof(comm));
+	size = ALIGN(strlen(comm)+1, sizeof(u64));
+
+	comm_event->comm = comm;
+	comm_event->comm_size = size;
+
+	comm_event->event_id.header.size = sizeof(comm_event->event_id) + size;
+
+	cpuctx = &get_cpu_var(perf_cpu_context);
+	perf_event_comm_ctx(&cpuctx->ctx, comm_event);
+	put_cpu_var(perf_cpu_context);
+
+	rcu_read_lock();
+	/*
+	 * doesn't really matter which of the child contexts the
+	 * events ends up in.
+	 */
+	ctx = rcu_dereference(current->perf_event_ctxp);
+	if (ctx)
+		perf_event_comm_ctx(ctx, comm_event);
+	rcu_read_unlock();
+}
+
+void perf_event_comm(struct task_struct *task)
+{
+	struct perf_comm_event comm_event;
+
+	if (task->perf_event_ctxp)
+		perf_event_enable_on_exec(task);
+
+	if (!atomic_read(&nr_comm_events))
+		return;
+
+	comm_event = (struct perf_comm_event){
+		.task	= task,
+		/* .comm      */
+		/* .comm_size */
+		.event_id  = {
+			.header = {
+				.type = PERF_RECORD_COMM,
+				.misc = 0,
+				/* .size */
+			},
+			/* .pid */
+			/* .tid */
+		},
+	};
+
+	perf_event_comm_event(&comm_event);
+}
+
+/*
+ * mmap tracking
+ */
+
+struct perf_mmap_event {
+	struct vm_area_struct	*vma;
+
+	const char		*file_name;
+	int			file_size;
+
+	struct {
+		struct perf_event_header	header;
+
+		u32				pid;
+		u32				tid;
+		u64				start;
+		u64				len;
+		u64				pgoff;
+	} event_id;
+};
+
+static void perf_event_mmap_output(struct perf_event *event,
+				     struct perf_mmap_event *mmap_event)
+{
+	struct perf_output_handle handle;
+	int size = mmap_event->event_id.header.size;
+	int ret = perf_output_begin(&handle, event, size, 0, 0);
+
+	if (ret)
+		return;
+
+	mmap_event->event_id.pid = perf_event_pid(event, current);
+	mmap_event->event_id.tid = perf_event_tid(event, current);
+
+	perf_output_put(&handle, mmap_event->event_id);
+	perf_output_copy(&handle, mmap_event->file_name,
+				   mmap_event->file_size);
+	perf_output_end(&handle);
+}
+
+static int perf_event_mmap_match(struct perf_event *event,
+				   struct perf_mmap_event *mmap_event)
+{
+	if (event->attr.mmap)
+		return 1;
+
+	return 0;
+}
+
+static void perf_event_mmap_ctx(struct perf_event_context *ctx,
+				  struct perf_mmap_event *mmap_event)
+{
+	struct perf_event *event;
+
+	if (system_state != SYSTEM_RUNNING || list_empty(&ctx->event_list))
+		return;
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(event, &ctx->event_list, event_entry) {
+		if (perf_event_mmap_match(event, mmap_event))
+			perf_event_mmap_output(event, mmap_event);
+	}
+	rcu_read_unlock();
+}
+
+static void perf_event_mmap_event(struct perf_mmap_event *mmap_event)
+{
+	struct perf_cpu_context *cpuctx;
+	struct perf_event_context *ctx;
+	struct vm_area_struct *vma = mmap_event->vma;
+	struct file *file = vma->vm_file;
+	unsigned int size;
+	char tmp[16];
+	char *buf = NULL;
+	const char *name;
+
+	memset(tmp, 0, sizeof(tmp));
+
+	if (file) {
+		/*
+		 * d_path works from the end of the buffer backwards, so we
+		 * need to add enough zero bytes after the string to handle
+		 * the 64bit alignment we do later.
+		 */
+		buf = kzalloc(PATH_MAX + sizeof(u64), GFP_KERNEL);
+		if (!buf) {
+			name = strncpy(tmp, "//enomem", sizeof(tmp));
+			goto got_name;
+		}
+		name = d_path(&file->f_path, buf, PATH_MAX);
+		if (IS_ERR(name)) {
+			name = strncpy(tmp, "//toolong", sizeof(tmp));
+			goto got_name;
+		}
+	} else {
+		if (arch_vma_name(mmap_event->vma)) {
+			name = strncpy(tmp, arch_vma_name(mmap_event->vma),
+				       sizeof(tmp));
+			goto got_name;
+		}
+
+		if (!vma->vm_mm) {
+			name = strncpy(tmp, "[vdso]", sizeof(tmp));
+			goto got_name;
+		}
+
+		name = strncpy(tmp, "//anon", sizeof(tmp));
+		goto got_name;
+	}
+
+got_name:
+	size = ALIGN(strlen(name)+1, sizeof(u64));
+
+	mmap_event->file_name = name;
+	mmap_event->file_size = size;
+
+	mmap_event->event_id.header.size = sizeof(mmap_event->event_id) + size;
+
+	cpuctx = &get_cpu_var(perf_cpu_context);
+	perf_event_mmap_ctx(&cpuctx->ctx, mmap_event);
+	put_cpu_var(perf_cpu_context);
+
+	rcu_read_lock();
+	/*
+	 * doesn't really matter which of the child contexts the
+	 * events ends up in.
+	 */
+	ctx = rcu_dereference(current->perf_event_ctxp);
+	if (ctx)
+		perf_event_mmap_ctx(ctx, mmap_event);
+	rcu_read_unlock();
+
+	kfree(buf);
+}
+
+void __perf_event_mmap(struct vm_area_struct *vma)
+{
+	struct perf_mmap_event mmap_event;
+
+	if (!atomic_read(&nr_mmap_events))
+		return;
+
+	mmap_event = (struct perf_mmap_event){
+		.vma	= vma,
+		/* .file_name */
+		/* .file_size */
+		.event_id  = {
+			.header = {
+				.type = PERF_RECORD_MMAP,
+				.misc = 0,
+				/* .size */
+			},
+			/* .pid */
+			/* .tid */
+			.start  = vma->vm_start,
+			.len    = vma->vm_end - vma->vm_start,
+			.pgoff  = vma->vm_pgoff,
+		},
+	};
+
+	perf_event_mmap_event(&mmap_event);
+}
+
+/*
+ * IRQ throttle logging
+ */
+
+static void perf_log_throttle(struct perf_event *event, int enable)
+{
+	struct perf_output_handle handle;
+	int ret;
+
+	struct {
+		struct perf_event_header	header;
+		u64				time;
+		u64				id;
+		u64				stream_id;
+	} throttle_event = {
+		.header = {
+			.type = PERF_RECORD_THROTTLE,
+			.misc = 0,
+			.size = sizeof(throttle_event),
+		},
+		.time		= perf_clock(),
+		.id		= primary_event_id(event),
+		.stream_id	= event->id,
+	};
+
+	if (enable)
+		throttle_event.header.type = PERF_RECORD_UNTHROTTLE;
+
+	ret = perf_output_begin(&handle, event, sizeof(throttle_event), 1, 0);
+	if (ret)
+		return;
+
+	perf_output_put(&handle, throttle_event);
+	perf_output_end(&handle);
+}
+
+/*
+ * Generic event overflow handling, sampling.
+ */
+
+static int __perf_event_overflow(struct perf_event *event, int nmi,
+				   int throttle, struct perf_sample_data *data,
+				   struct pt_regs *regs)
+{
+	int events = atomic_read(&event->event_limit);
+	struct hw_perf_event *hwc = &event->hw;
+	int ret = 0;
+
+	throttle = (throttle && event->pmu->unthrottle != NULL);
+
+	if (!throttle) {
+		hwc->interrupts++;
+	} else {
+		if (hwc->interrupts != MAX_INTERRUPTS) {
+			hwc->interrupts++;
+			if (HZ * hwc->interrupts >
+					(u64)sysctl_perf_event_sample_rate) {
+				hwc->interrupts = MAX_INTERRUPTS;
+				perf_log_throttle(event, 0);
+				ret = 1;
+			}
+		} else {
+			/*
+			 * Keep re-disabling events even though on the previous
+			 * pass we disabled it - just in case we raced with a
+			 * sched-in and the event got enabled again:
+			 */
+			ret = 1;
+		}
+	}
+
+	if (event->attr.freq) {
+		u64 now = perf_clock();
+		s64 delta = now - hwc->freq_stamp;
+
+		hwc->freq_stamp = now;
+
+		if (delta > 0 && delta < TICK_NSEC)
+			perf_adjust_period(event, NSEC_PER_SEC / (int)delta);
+	}
+
+	/*
+	 * XXX event_limit might not quite work as expected on inherited
+	 * events
+	 */
+
+	event->pending_kill = POLL_IN;
+	if (events && atomic_dec_and_test(&event->event_limit)) {
+		ret = 1;
+		event->pending_kill = POLL_HUP;
+		if (nmi) {
+			event->pending_disable = 1;
+			perf_pending_queue(&event->pending,
+					   perf_pending_event);
+		} else
+			perf_event_disable(event);
+	}
+
+	perf_event_output(event, nmi, data, regs);
+	return ret;
+}
+
+int perf_event_overflow(struct perf_event *event, int nmi,
+			  struct perf_sample_data *data,
+			  struct pt_regs *regs)
+{
+	return __perf_event_overflow(event, nmi, 1, data, regs);
+}
+
+/*
+ * Generic software event infrastructure
+ */
+
+/*
+ * We directly increment event->count and keep a second value in
+ * event->hw.period_left to count intervals. This period event
+ * is kept in the range [-sample_period, 0] so that we can use the
+ * sign as trigger.
+ */
+
+static u64 perf_swevent_set_period(struct perf_event *event)
+{
+	struct hw_perf_event *hwc = &event->hw;
+	u64 period = hwc->last_period;
+	u64 nr, offset;
+	s64 old, val;
+
+	hwc->last_period = hwc->sample_period;
+
+again:
+	old = val = atomic64_read(&hwc->period_left);
+	if (val < 0)
+		return 0;
+
+	nr = div64_u64(period + val, period);
+	offset = nr * period;
+	val -= offset;
+	if (atomic64_cmpxchg(&hwc->period_left, old, val) != old)
+		goto again;
+
+	return nr;
+}
+
+static void perf_swevent_overflow(struct perf_event *event,
+				    int nmi, struct perf_sample_data *data,
+				    struct pt_regs *regs)
+{
+	struct hw_perf_event *hwc = &event->hw;
+	int throttle = 0;
+	u64 overflow;
+
+	data->period = event->hw.last_period;
+	overflow = perf_swevent_set_period(event);
+
+	if (hwc->interrupts == MAX_INTERRUPTS)
+		return;
+
+	for (; overflow; overflow--) {
+		if (__perf_event_overflow(event, nmi, throttle,
+					    data, regs)) {
+			/*
+			 * We inhibit the overflow from happening when
+			 * hwc->interrupts == MAX_INTERRUPTS.
+			 */
+			break;
+		}
+		throttle = 1;
+	}
+}
+
+static void perf_swevent_unthrottle(struct perf_event *event)
+{
+	/*
+	 * Nothing to do, we already reset hwc->interrupts.
+	 */
+}
+
+static void perf_swevent_add(struct perf_event *event, u64 nr,
+			       int nmi, struct perf_sample_data *data,
+			       struct pt_regs *regs)
+{
+	struct hw_perf_event *hwc = &event->hw;
+
+	atomic64_add(nr, &event->count);
+
+	if (!hwc->sample_period)
+		return;
+
+	if (!regs)
+		return;
+
+	if (!atomic64_add_negative(nr, &hwc->period_left))
+		perf_swevent_overflow(event, nmi, data, regs);
+}
+
+static int perf_swevent_is_counting(struct perf_event *event)
+{
+	/*
+	 * The event is active, we're good!
+	 */
+	if (event->state == PERF_EVENT_STATE_ACTIVE)
+		return 1;
+
+	/*
+	 * The event is off/error, not counting.
+	 */
+	if (event->state != PERF_EVENT_STATE_INACTIVE)
+		return 0;
+
+	/*
+	 * The event is inactive, if the context is active
+	 * we're part of a group that didn't make it on the 'pmu',
+	 * not counting.
+	 */
+	if (event->ctx->is_active)
+		return 0;
+
+	/*
+	 * We're inactive and the context is too, this means the
+	 * task is scheduled out, we're counting events that happen
+	 * to us, like migration events.
+	 */
+	return 1;
+}
+
+static int perf_swevent_match(struct perf_event *event,
+				enum perf_type_id type,
+				u32 event_id, struct pt_regs *regs)
+{
+	if (!perf_swevent_is_counting(event))
+		return 0;
+
+	if (event->attr.type != type)
+		return 0;
+	if (event->attr.config != event_id)
+		return 0;
+
+	if (regs) {
+		if (event->attr.exclude_user && user_mode(regs))
+			return 0;
+
+		if (event->attr.exclude_kernel && !user_mode(regs))
+			return 0;
+	}
+
+	return 1;
+}
+
+static void perf_swevent_ctx_event(struct perf_event_context *ctx,
+				     enum perf_type_id type,
+				     u32 event_id, u64 nr, int nmi,
+				     struct perf_sample_data *data,
+				     struct pt_regs *regs)
+{
+	struct perf_event *event;
+
+	if (system_state != SYSTEM_RUNNING || list_empty(&ctx->event_list))
+		return;
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(event, &ctx->event_list, event_entry) {
+		if (perf_swevent_match(event, type, event_id, regs))
+			perf_swevent_add(event, nr, nmi, data, regs);
+	}
+	rcu_read_unlock();
+}
+
+static int *perf_swevent_recursion_context(struct perf_cpu_context *cpuctx)
+{
+	if (in_nmi())
+		return &cpuctx->recursion[3];
+
+	if (in_irq())
+		return &cpuctx->recursion[2];
+
+	if (in_softirq())
+		return &cpuctx->recursion[1];
+
+	return &cpuctx->recursion[0];
+}
+
+static void do_perf_sw_event(enum perf_type_id type, u32 event_id,
+				    u64 nr, int nmi,
+				    struct perf_sample_data *data,
+				    struct pt_regs *regs)
+{
+	struct perf_cpu_context *cpuctx = &get_cpu_var(perf_cpu_context);
+	int *recursion = perf_swevent_recursion_context(cpuctx);
+	struct perf_event_context *ctx;
+
+	if (*recursion)
+		goto out;
+
+	(*recursion)++;
+	barrier();
+
+	perf_swevent_ctx_event(&cpuctx->ctx, type, event_id,
+				 nr, nmi, data, regs);
+	rcu_read_lock();
+	/*
+	 * doesn't really matter which of the child contexts the
+	 * events ends up in.
+	 */
+	ctx = rcu_dereference(current->perf_event_ctxp);
+	if (ctx)
+		perf_swevent_ctx_event(ctx, type, event_id, nr, nmi, data, regs);
+	rcu_read_unlock();
+
+	barrier();
+	(*recursion)--;
+
+out:
+	put_cpu_var(perf_cpu_context);
+}
+
+void __perf_sw_event(u32 event_id, u64 nr, int nmi,
+			    struct pt_regs *regs, u64 addr)
+{
+	struct perf_sample_data data = {
+		.addr = addr,
+	};
+
+	do_perf_sw_event(PERF_TYPE_SOFTWARE, event_id, nr, nmi,
+				&data, regs);
+}
+
+static void perf_swevent_read(struct perf_event *event)
+{
+}
+
+static int perf_swevent_enable(struct perf_event *event)
+{
+	struct hw_perf_event *hwc = &event->hw;
+
+	if (hwc->sample_period) {
+		hwc->last_period = hwc->sample_period;
+		perf_swevent_set_period(event);
+	}
+	return 0;
+}
+
+static void perf_swevent_disable(struct perf_event *event)
+{
+}
+
+static const struct pmu perf_ops_generic = {
+	.enable		= perf_swevent_enable,
+	.disable	= perf_swevent_disable,
+	.read		= perf_swevent_read,
+	.unthrottle	= perf_swevent_unthrottle,
+};
+
+/*
+ * hrtimer based swevent callback
+ */
+
+static enum hrtimer_restart perf_swevent_hrtimer(struct hrtimer *hrtimer)
+{
+	enum hrtimer_restart ret = HRTIMER_RESTART;
+	struct perf_sample_data data;
+	struct pt_regs *regs;
+	struct perf_event *event;
+	u64 period;
+
+	event	= container_of(hrtimer, struct perf_event, hw.hrtimer);
+	event->pmu->read(event);
+
+	data.addr = 0;
+	regs = get_irq_regs();
+	/*
+	 * In case we exclude kernel IPs or are somehow not in interrupt
+	 * context, provide the next best thing, the user IP.
+	 */
+	if ((event->attr.exclude_kernel || !regs) &&
+			!event->attr.exclude_user)
+		regs = task_pt_regs(current);
+
+	if (regs) {
+		if (!(event->attr.exclude_idle && current->pid == 0))
+			if (perf_event_overflow(event, 0, &data, regs))
+				ret = HRTIMER_NORESTART;
+	}
+
+	period = max_t(u64, 10000, event->hw.sample_period);
+	hrtimer_forward_now(hrtimer, ns_to_ktime(period));
+
+	return ret;
+}
+
+static void perf_swevent_start_hrtimer(struct perf_event *event)
+{
+	struct hw_perf_event *hwc = &event->hw;
+
+	hrtimer_init(&hwc->hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+	hwc->hrtimer.function = perf_swevent_hrtimer;
+	if (hwc->sample_period) {
+		u64 period;
+
+		if (hwc->remaining) {
+			if (hwc->remaining < 0)
+				period = 10000;
+			else
+				period = hwc->remaining;
+			hwc->remaining = 0;
+		} else {
+			period = max_t(u64, 10000, hwc->sample_period);
+		}
+		__hrtimer_start_range_ns(&hwc->hrtimer,
+				ns_to_ktime(period), 0,
+				HRTIMER_MODE_REL, 0);
+	}
+}
+
+static void perf_swevent_cancel_hrtimer(struct perf_event *event)
+{
+	struct hw_perf_event *hwc = &event->hw;
+
+	if (hwc->sample_period) {
+		ktime_t remaining = hrtimer_get_remaining(&hwc->hrtimer);
+		hwc->remaining = ktime_to_ns(remaining);
+
+		hrtimer_cancel(&hwc->hrtimer);
+	}
+}
+
+/*
+ * Software event: cpu wall time clock
+ */
+
+static void cpu_clock_perf_event_update(struct perf_event *event)
+{
+	int cpu = raw_smp_processor_id();
+	s64 prev;
+	u64 now;
+
+	now = cpu_clock(cpu);
+	prev = atomic64_read(&event->hw.prev_count);
+	atomic64_set(&event->hw.prev_count, now);
+	atomic64_add(now - prev, &event->count);
+}
+
+static int cpu_clock_perf_event_enable(struct perf_event *event)
+{
+	struct hw_perf_event *hwc = &event->hw;
+	int cpu = raw_smp_processor_id();
+
+	atomic64_set(&hwc->prev_count, cpu_clock(cpu));
+	perf_swevent_start_hrtimer(event);
+
+	return 0;
+}
+
+static void cpu_clock_perf_event_disable(struct perf_event *event)
+{
+	perf_swevent_cancel_hrtimer(event);
+	cpu_clock_perf_event_update(event);
+}
+
+static void cpu_clock_perf_event_read(struct perf_event *event)
+{
+	cpu_clock_perf_event_update(event);
+}
+
+static const struct pmu perf_ops_cpu_clock = {
+	.enable		= cpu_clock_perf_event_enable,
+	.disable	= cpu_clock_perf_event_disable,
+	.read		= cpu_clock_perf_event_read,
+};
+
+/*
+ * Software event: task time clock
+ */
+
+static void task_clock_perf_event_update(struct perf_event *event, u64 now)
+{
+	u64 prev;
+	s64 delta;
+
+	prev = atomic64_xchg(&event->hw.prev_count, now);
+	delta = now - prev;
+	atomic64_add(delta, &event->count);
+}
+
+static int task_clock_perf_event_enable(struct perf_event *event)
+{
+	struct hw_perf_event *hwc = &event->hw;
+	u64 now;
+
+	now = event->ctx->time;
+
+	atomic64_set(&hwc->prev_count, now);
+
+	perf_swevent_start_hrtimer(event);
+
+	return 0;
+}
+
+static void task_clock_perf_event_disable(struct perf_event *event)
+{
+	perf_swevent_cancel_hrtimer(event);
+	task_clock_perf_event_update(event, event->ctx->time);
+
+}
+
+static void task_clock_perf_event_read(struct perf_event *event)
+{
+	u64 time;
+
+	if (!in_nmi()) {
+		update_context_time(event->ctx);
+		time = event->ctx->time;
+	} else {
+		u64 now = perf_clock();
+		u64 delta = now - event->ctx->timestamp;
+		time = event->ctx->time + delta;
+	}
+
+	task_clock_perf_event_update(event, time);
+}
+
+static const struct pmu perf_ops_task_clock = {
+	.enable		= task_clock_perf_event_enable,
+	.disable	= task_clock_perf_event_disable,
+	.read		= task_clock_perf_event_read,
+};
+
+#ifdef CONFIG_EVENT_PROFILE
+void perf_tp_event(int event_id, u64 addr, u64 count, void *record,
+			  int entry_size)
+{
+	struct perf_raw_record raw = {
+		.size = entry_size,
+		.data = record,
+	};
+
+	struct perf_sample_data data = {
+		.addr = addr,
+		.raw = &raw,
+	};
+
+	struct pt_regs *regs = get_irq_regs();
+
+	if (!regs)
+		regs = task_pt_regs(current);
+
+	do_perf_sw_event(PERF_TYPE_TRACEPOINT, event_id, count, 1,
+				&data, regs);
+}
+EXPORT_SYMBOL_GPL(perf_tp_event);
+
+extern int ftrace_profile_enable(int);
+extern void ftrace_profile_disable(int);
+
+static void tp_perf_event_destroy(struct perf_event *event)
+{
+	ftrace_profile_disable(event->attr.config);
+}
+
+static const struct pmu *tp_perf_event_init(struct perf_event *event)
+{
+	/*
+	 * Raw tracepoint data is a severe data leak, only allow root to
+	 * have these.
+	 */
+	if ((event->attr.sample_type & PERF_SAMPLE_RAW) &&
+			perf_paranoid_tracepoint_raw() &&
+			!capable(CAP_SYS_ADMIN))
+		return ERR_PTR(-EPERM);
+
+	if (ftrace_profile_enable(event->attr.config))
+		return NULL;
+
+	event->destroy = tp_perf_event_destroy;
+
+	return &perf_ops_generic;
+}
+#else
+static const struct pmu *tp_perf_event_init(struct perf_event *event)
+{
+	return NULL;
+}
+#endif
+
+atomic_t perf_swevent_enabled[PERF_COUNT_SW_MAX];
+
+static void sw_perf_event_destroy(struct perf_event *event)
+{
+	u64 event_id = event->attr.config;
+
+	WARN_ON(event->parent);
+
+	atomic_dec(&perf_swevent_enabled[event_id]);
+}
+
+static const struct pmu *sw_perf_event_init(struct perf_event *event)
+{
+	const struct pmu *pmu = NULL;
+	u64 event_id = event->attr.config;
+
+	/*
+	 * Software events (currently) can't in general distinguish
+	 * between user, kernel and hypervisor events.
+	 * However, context switches and cpu migrations are considered
+	 * to be kernel events, and page faults are never hypervisor
+	 * events.
+	 */
+	switch (event_id) {
+	case PERF_COUNT_SW_CPU_CLOCK:
+		pmu = &perf_ops_cpu_clock;
+
+		break;
+	case PERF_COUNT_SW_TASK_CLOCK:
+		/*
+		 * If the user instantiates this as a per-cpu event,
+		 * use the cpu_clock event instead.
+		 */
+		if (event->ctx->task)
+			pmu = &perf_ops_task_clock;
+		else
+			pmu = &perf_ops_cpu_clock;
+
+		break;
+	case PERF_COUNT_SW_PAGE_FAULTS:
+	case PERF_COUNT_SW_PAGE_FAULTS_MIN:
+	case PERF_COUNT_SW_PAGE_FAULTS_MAJ:
+	case PERF_COUNT_SW_CONTEXT_SWITCHES:
+	case PERF_COUNT_SW_CPU_MIGRATIONS:
+		if (!event->parent) {
+			atomic_inc(&perf_swevent_enabled[event_id]);
+			event->destroy = sw_perf_event_destroy;
+		}
+		pmu = &perf_ops_generic;
+		break;
+	}
+
+	return pmu;
+}
+
+/*
+ * Allocate and initialize a event structure
+ */
+static struct perf_event *
+perf_event_alloc(struct perf_event_attr *attr,
+		   int cpu,
+		   struct perf_event_context *ctx,
+		   struct perf_event *group_leader,
+		   struct perf_event *parent_event,
+		   gfp_t gfpflags)
+{
+	const struct pmu *pmu;
+	struct perf_event *event;
+	struct hw_perf_event *hwc;
+	long err;
+
+	event = kzalloc(sizeof(*event), gfpflags);
+	if (!event)
+		return ERR_PTR(-ENOMEM);
+
+	/*
+	 * Single events are their own group leaders, with an
+	 * empty sibling list:
+	 */
+	if (!group_leader)
+		group_leader = event;
+
+	mutex_init(&event->child_mutex);
+	INIT_LIST_HEAD(&event->child_list);
+
+	INIT_LIST_HEAD(&event->group_entry);
+	INIT_LIST_HEAD(&event->event_entry);
+	INIT_LIST_HEAD(&event->sibling_list);
+	init_waitqueue_head(&event->waitq);
+
+	mutex_init(&event->mmap_mutex);
+
+	event->cpu		= cpu;
+	event->attr		= *attr;
+	event->group_leader	= group_leader;
+	event->pmu		= NULL;
+	event->ctx		= ctx;
+	event->oncpu		= -1;
+
+	event->parent		= parent_event;
+
+	event->ns		= get_pid_ns(current->nsproxy->pid_ns);
+	event->id		= atomic64_inc_return(&perf_event_id);
+
+	event->state		= PERF_EVENT_STATE_INACTIVE;
+
+	if (attr->disabled)
+		event->state = PERF_EVENT_STATE_OFF;
+
+	pmu = NULL;
+
+	hwc = &event->hw;
+	hwc->sample_period = attr->sample_period;
+	if (attr->freq && attr->sample_freq)
+		hwc->sample_period = 1;
+	hwc->last_period = hwc->sample_period;
+
+	atomic64_set(&hwc->period_left, hwc->sample_period);
+
+	/*
+	 * we currently do not support PERF_FORMAT_GROUP on inherited events
+	 */
+	if (attr->inherit && (attr->read_format & PERF_FORMAT_GROUP))
+		goto done;
+
+	switch (attr->type) {
+	case PERF_TYPE_RAW:
+	case PERF_TYPE_HARDWARE:
+	case PERF_TYPE_HW_CACHE:
+		pmu = hw_perf_event_init(event);
+		break;
+
+	case PERF_TYPE_SOFTWARE:
+		pmu = sw_perf_event_init(event);
+		break;
+
+	case PERF_TYPE_TRACEPOINT:
+		pmu = tp_perf_event_init(event);
+		break;
+
+	default:
+		break;
+	}
+done:
+	err = 0;
+	if (!pmu)
+		err = -EINVAL;
+	else if (IS_ERR(pmu))
+		err = PTR_ERR(pmu);
+
+	if (err) {
+		if (event->ns)
+			put_pid_ns(event->ns);
+		kfree(event);
+		return ERR_PTR(err);
+	}
+
+	event->pmu = pmu;
+
+	if (!event->parent) {
+		atomic_inc(&nr_events);
+		if (event->attr.mmap)
+			atomic_inc(&nr_mmap_events);
+		if (event->attr.comm)
+			atomic_inc(&nr_comm_events);
+		if (event->attr.task)
+			atomic_inc(&nr_task_events);
+	}
+
+	return event;
+}
+
+static int perf_copy_attr(struct perf_event_attr __user *uattr,
+			  struct perf_event_attr *attr)
+{
+	u32 size;
+	int ret;
+
+	if (!access_ok(VERIFY_WRITE, uattr, PERF_ATTR_SIZE_VER0))
+		return -EFAULT;
+
+	/*
+	 * zero the full structure, so that a short copy will be nice.
+	 */
+	memset(attr, 0, sizeof(*attr));
+
+	ret = get_user(size, &uattr->size);
+	if (ret)
+		return ret;
+
+	if (size > PAGE_SIZE)	/* silly large */
+		goto err_size;
+
+	if (!size)		/* abi compat */
+		size = PERF_ATTR_SIZE_VER0;
+
+	if (size < PERF_ATTR_SIZE_VER0)
+		goto err_size;
+
+	/*
+	 * If we're handed a bigger struct than we know of,
+	 * ensure all the unknown bits are 0 - i.e. new
+	 * user-space does not rely on any kernel feature
+	 * extensions we dont know about yet.
+	 */
+	if (size > sizeof(*attr)) {
+		unsigned char __user *addr;
+		unsigned char __user *end;
+		unsigned char val;
+
+		addr = (void __user *)uattr + sizeof(*attr);
+		end  = (void __user *)uattr + size;
+
+		for (; addr < end; addr++) {
+			ret = get_user(val, addr);
+			if (ret)
+				return ret;
+			if (val)
+				goto err_size;
+		}
+		size = sizeof(*attr);
+	}
+
+	ret = copy_from_user(attr, uattr, size);
+	if (ret)
+		return -EFAULT;
+
+	/*
+	 * If the type exists, the corresponding creation will verify
+	 * the attr->config.
+	 */
+	if (attr->type >= PERF_TYPE_MAX)
+		return -EINVAL;
+
+	if (attr->__reserved_1 || attr->__reserved_2 || attr->__reserved_3)
+		return -EINVAL;
+
+	if (attr->sample_type & ~(PERF_SAMPLE_MAX-1))
+		return -EINVAL;
+
+	if (attr->read_format & ~(PERF_FORMAT_MAX-1))
+		return -EINVAL;
+
+out:
+	return ret;
+
+err_size:
+	put_user(sizeof(*attr), &uattr->size);
+	ret = -E2BIG;
+	goto out;
+}
+
+int perf_event_set_output(struct perf_event *event, int output_fd)
+{
+	struct perf_event *output_event = NULL;
+	struct file *output_file = NULL;
+	struct perf_event *old_output;
+	int fput_needed = 0;
+	int ret = -EINVAL;
+
+	if (!output_fd)
+		goto set;
+
+	output_file = fget_light(output_fd, &fput_needed);
+	if (!output_file)
+		return -EBADF;
+
+	if (output_file->f_op != &perf_fops)
+		goto out;
+
+	output_event = output_file->private_data;
+
+	/* Don't chain output fds */
+	if (output_event->output)
+		goto out;
+
+	/* Don't set an output fd when we already have an output channel */
+	if (event->data)
+		goto out;
+
+	atomic_long_inc(&output_file->f_count);
+
+set:
+	mutex_lock(&event->mmap_mutex);
+	old_output = event->output;
+	rcu_assign_pointer(event->output, output_event);
+	mutex_unlock(&event->mmap_mutex);
+
+	if (old_output) {
+		/*
+		 * we need to make sure no existing perf_output_*()
+		 * is still referencing this event.
+		 */
+		synchronize_rcu();
+		fput(old_output->filp);
+	}
+
+	ret = 0;
+out:
+	fput_light(output_file, fput_needed);
+	return ret;
+}
+
+/**
+ * sys_perf_event_open - open a performance event, associate it to a task/cpu
+ *
+ * @attr_uptr:	event_id type attributes for monitoring/sampling
+ * @pid:		target pid
+ * @cpu:		target cpu
+ * @group_fd:		group leader event fd
+ */
+SYSCALL_DEFINE5(perf_event_open,
+		struct perf_event_attr __user *, attr_uptr,
+		pid_t, pid, int, cpu, int, group_fd, unsigned long, flags)
+{
+	struct perf_event *event, *group_leader;
+	struct perf_event_attr attr;
+	struct perf_event_context *ctx;
+	struct file *event_file = NULL;
+	struct file *group_file = NULL;
+	int fput_needed = 0;
+	int fput_needed2 = 0;
+	int err;
+
+	/* for future expandability... */
+	if (flags & ~(PERF_FLAG_FD_NO_GROUP | PERF_FLAG_FD_OUTPUT))
+		return -EINVAL;
+
+	err = perf_copy_attr(attr_uptr, &attr);
+	if (err)
+		return err;
+
+	if (!attr.exclude_kernel) {
+		if (perf_paranoid_kernel() && !capable(CAP_SYS_ADMIN))
+			return -EACCES;
+	}
+
+	if (attr.freq) {
+		if (attr.sample_freq > sysctl_perf_event_sample_rate)
+			return -EINVAL;
+	}
+
+	/*
+	 * Get the target context (task or percpu):
+	 */
+	ctx = find_get_context(pid, cpu);
+	if (IS_ERR(ctx))
+		return PTR_ERR(ctx);
+
+	/*
+	 * Look up the group leader (we will attach this event to it):
+	 */
+	group_leader = NULL;
+	if (group_fd != -1 && !(flags & PERF_FLAG_FD_NO_GROUP)) {
+		err = -EINVAL;
+		group_file = fget_light(group_fd, &fput_needed);
+		if (!group_file)
+			goto err_put_context;
+		if (group_file->f_op != &perf_fops)
+			goto err_put_context;
+
+		group_leader = group_file->private_data;
+		/*
+		 * Do not allow a recursive hierarchy (this new sibling
+		 * becoming part of another group-sibling):
+		 */
+		if (group_leader->group_leader != group_leader)
+			goto err_put_context;
+		/*
+		 * Do not allow to attach to a group in a different
+		 * task or CPU context:
+		 */
+		if (group_leader->ctx != ctx)
+			goto err_put_context;
+		/*
+		 * Only a group leader can be exclusive or pinned
+		 */
+		if (attr.exclusive || attr.pinned)
+			goto err_put_context;
+	}
+
+	event = perf_event_alloc(&attr, cpu, ctx, group_leader,
+				     NULL, GFP_KERNEL);
+	err = PTR_ERR(event);
+	if (IS_ERR(event))
+		goto err_put_context;
+
+	err = anon_inode_getfd("[perf_event]", &perf_fops, event, 0);
+	if (err < 0)
+		goto err_free_put_context;
+
+	event_file = fget_light(err, &fput_needed2);
+	if (!event_file)
+		goto err_free_put_context;
+
+	if (flags & PERF_FLAG_FD_OUTPUT) {
+		err = perf_event_set_output(event, group_fd);
+		if (err)
+			goto err_fput_free_put_context;
+	}
+
+	event->filp = event_file;
+	WARN_ON_ONCE(ctx->parent_ctx);
+	mutex_lock(&ctx->mutex);
+	perf_install_in_context(ctx, event, cpu);
+	++ctx->generation;
+	mutex_unlock(&ctx->mutex);
+
+	event->owner = current;
+	get_task_struct(current);
+	mutex_lock(&current->perf_event_mutex);
+	list_add_tail(&event->owner_entry, &current->perf_event_list);
+	mutex_unlock(&current->perf_event_mutex);
+
+err_fput_free_put_context:
+	fput_light(event_file, fput_needed2);
+
+err_free_put_context:
+	if (err < 0)
+		kfree(event);
+
+err_put_context:
+	if (err < 0)
+		put_ctx(ctx);
+
+	fput_light(group_file, fput_needed);
+
+	return err;
+}
+
+/*
+ * inherit a event from parent task to child task:
+ */
+static struct perf_event *
+inherit_event(struct perf_event *parent_event,
+	      struct task_struct *parent,
+	      struct perf_event_context *parent_ctx,
+	      struct task_struct *child,
+	      struct perf_event *group_leader,
+	      struct perf_event_context *child_ctx)
+{
+	struct perf_event *child_event;
+
+	/*
+	 * Instead of creating recursive hierarchies of events,
+	 * we link inherited events back to the original parent,
+	 * which has a filp for sure, which we use as the reference
+	 * count:
+	 */
+	if (parent_event->parent)
+		parent_event = parent_event->parent;
+
+	child_event = perf_event_alloc(&parent_event->attr,
+					   parent_event->cpu, child_ctx,
+					   group_leader, parent_event,
+					   GFP_KERNEL);
+	if (IS_ERR(child_event))
+		return child_event;
+	get_ctx(child_ctx);
+
+	/*
+	 * Make the child state follow the state of the parent event,
+	 * not its attr.disabled bit.  We hold the parent's mutex,
+	 * so we won't race with perf_event_{en, dis}able_family.
+	 */
+	if (parent_event->state >= PERF_EVENT_STATE_INACTIVE)
+		child_event->state = PERF_EVENT_STATE_INACTIVE;
+	else
+		child_event->state = PERF_EVENT_STATE_OFF;
+
+	if (parent_event->attr.freq)
+		child_event->hw.sample_period = parent_event->hw.sample_period;
+
+	/*
+	 * Link it up in the child's context:
+	 */
+	add_event_to_ctx(child_event, child_ctx);
+
+	/*
+	 * Get a reference to the parent filp - we will fput it
+	 * when the child event exits. This is safe to do because
+	 * we are in the parent and we know that the filp still
+	 * exists and has a nonzero count:
+	 */
+	atomic_long_inc(&parent_event->filp->f_count);
+
+	/*
+	 * Link this into the parent event's child list
+	 */
+	WARN_ON_ONCE(parent_event->ctx->parent_ctx);
+	mutex_lock(&parent_event->child_mutex);
+	list_add_tail(&child_event->child_list, &parent_event->child_list);
+	mutex_unlock(&parent_event->child_mutex);
+
+	return child_event;
+}
+
+static int inherit_group(struct perf_event *parent_event,
+	      struct task_struct *parent,
+	      struct perf_event_context *parent_ctx,
+	      struct task_struct *child,
+	      struct perf_event_context *child_ctx)
+{
+	struct perf_event *leader;
+	struct perf_event *sub;
+	struct perf_event *child_ctr;
+
+	leader = inherit_event(parent_event, parent, parent_ctx,
+				 child, NULL, child_ctx);
+	if (IS_ERR(leader))
+		return PTR_ERR(leader);
+	list_for_each_entry(sub, &parent_event->sibling_list, group_entry) {
+		child_ctr = inherit_event(sub, parent, parent_ctx,
+					    child, leader, child_ctx);
+		if (IS_ERR(child_ctr))
+			return PTR_ERR(child_ctr);
+	}
+	return 0;
+}
+
+static void sync_child_event(struct perf_event *child_event,
+			       struct task_struct *child)
+{
+	struct perf_event *parent_event = child_event->parent;
+	u64 child_val;
+
+	if (child_event->attr.inherit_stat)
+		perf_event_read_event(child_event, child);
+
+	child_val = atomic64_read(&child_event->count);
+
+	/*
+	 * Add back the child's count to the parent's count:
+	 */
+	atomic64_add(child_val, &parent_event->count);
+	atomic64_add(child_event->total_time_enabled,
+		     &parent_event->child_total_time_enabled);
+	atomic64_add(child_event->total_time_running,
+		     &parent_event->child_total_time_running);
+
+	/*
+	 * Remove this event from the parent's list
+	 */
+	WARN_ON_ONCE(parent_event->ctx->parent_ctx);
+	mutex_lock(&parent_event->child_mutex);
+	list_del_init(&child_event->child_list);
+	mutex_unlock(&parent_event->child_mutex);
+
+	/*
+	 * Release the parent event, if this was the last
+	 * reference to it.
+	 */
+	fput(parent_event->filp);
+}
+
+static void
+__perf_event_exit_task(struct perf_event *child_event,
+			 struct perf_event_context *child_ctx,
+			 struct task_struct *child)
+{
+	struct perf_event *parent_event;
+
+	update_event_times(child_event);
+	perf_event_remove_from_context(child_event);
+
+	parent_event = child_event->parent;
+	/*
+	 * It can happen that parent exits first, and has events
+	 * that are still around due to the child reference. These
+	 * events need to be zapped - but otherwise linger.
+	 */
+	if (parent_event) {
+		sync_child_event(child_event, child);
+		free_event(child_event);
+	}
+}
+
+/*
+ * When a child task exits, feed back event values to parent events.
+ */
+void perf_event_exit_task(struct task_struct *child)
+{
+	struct perf_event *child_event, *tmp;
+	struct perf_event_context *child_ctx;
+	unsigned long flags;
+
+	if (likely(!child->perf_event_ctxp)) {
+		perf_event_task(child, NULL, 0);
+		return;
+	}
+
+	local_irq_save(flags);
+	/*
+	 * We can't reschedule here because interrupts are disabled,
+	 * and either child is current or it is a task that can't be
+	 * scheduled, so we are now safe from rescheduling changing
+	 * our context.
+	 */
+	child_ctx = child->perf_event_ctxp;
+	__perf_event_task_sched_out(child_ctx);
+
+	/*
+	 * Take the context lock here so that if find_get_context is
+	 * reading child->perf_event_ctxp, we wait until it has
+	 * incremented the context's refcount before we do put_ctx below.
+	 */
+	spin_lock(&child_ctx->lock);
+	child->perf_event_ctxp = NULL;
+	/*
+	 * If this context is a clone; unclone it so it can't get
+	 * swapped to another process while we're removing all
+	 * the events from it.
+	 */
+	unclone_ctx(child_ctx);
+	spin_unlock_irqrestore(&child_ctx->lock, flags);
+
+	/*
+	 * Report the task dead after unscheduling the events so that we
+	 * won't get any samples after PERF_RECORD_EXIT. We can however still
+	 * get a few PERF_RECORD_READ events.
+	 */
+	perf_event_task(child, child_ctx, 0);
+
+	/*
+	 * We can recurse on the same lock type through:
+	 *
+	 *   __perf_event_exit_task()
+	 *     sync_child_event()
+	 *       fput(parent_event->filp)
+	 *         perf_release()
+	 *           mutex_lock(&ctx->mutex)
+	 *
+	 * But since its the parent context it won't be the same instance.
+	 */
+	mutex_lock_nested(&child_ctx->mutex, SINGLE_DEPTH_NESTING);
+
+again:
+	list_for_each_entry_safe(child_event, tmp, &child_ctx->group_list,
+				 group_entry)
+		__perf_event_exit_task(child_event, child_ctx, child);
+
+	/*
+	 * If the last event was a group event, it will have appended all
+	 * its siblings to the list, but we obtained 'tmp' before that which
+	 * will still point to the list head terminating the iteration.
+	 */
+	if (!list_empty(&child_ctx->group_list))
+		goto again;
+
+	mutex_unlock(&child_ctx->mutex);
+
+	put_ctx(child_ctx);
+}
+
+/*
+ * free an unexposed, unused context as created by inheritance by
+ * init_task below, used by fork() in case of fail.
+ */
+void perf_event_free_task(struct task_struct *task)
+{
+	struct perf_event_context *ctx = task->perf_event_ctxp;
+	struct perf_event *event, *tmp;
+
+	if (!ctx)
+		return;
+
+	mutex_lock(&ctx->mutex);
+again:
+	list_for_each_entry_safe(event, tmp, &ctx->group_list, group_entry) {
+		struct perf_event *parent = event->parent;
+
+		if (WARN_ON_ONCE(!parent))
+			continue;
+
+		mutex_lock(&parent->child_mutex);
+		list_del_init(&event->child_list);
+		mutex_unlock(&parent->child_mutex);
+
+		fput(parent->filp);
+
+		list_del_event(event, ctx);
+		free_event(event);
+	}
+
+	if (!list_empty(&ctx->group_list))
+		goto again;
+
+	mutex_unlock(&ctx->mutex);
+
+	put_ctx(ctx);
+}
+
+/*
+ * Initialize the perf_event context in task_struct
+ */
+int perf_event_init_task(struct task_struct *child)
+{
+	struct perf_event_context *child_ctx, *parent_ctx;
+	struct perf_event_context *cloned_ctx;
+	struct perf_event *event;
+	struct task_struct *parent = current;
+	int inherited_all = 1;
+	int ret = 0;
+
+	child->perf_event_ctxp = NULL;
+
+	mutex_init(&child->perf_event_mutex);
+	INIT_LIST_HEAD(&child->perf_event_list);
+
+	if (likely(!parent->perf_event_ctxp))
+		return 0;
+
+	/*
+	 * This is executed from the parent task context, so inherit
+	 * events that have been marked for cloning.
+	 * First allocate and initialize a context for the child.
+	 */
+
+	child_ctx = kmalloc(sizeof(struct perf_event_context), GFP_KERNEL);
+	if (!child_ctx)
+		return -ENOMEM;
+
+	__perf_event_init_context(child_ctx, child);
+	child->perf_event_ctxp = child_ctx;
+	get_task_struct(child);
+
+	/*
+	 * If the parent's context is a clone, pin it so it won't get
+	 * swapped under us.
+	 */
+	parent_ctx = perf_pin_task_context(parent);
+
+	/*
+	 * No need to check if parent_ctx != NULL here; since we saw
+	 * it non-NULL earlier, the only reason for it to become NULL
+	 * is if we exit, and since we're currently in the middle of
+	 * a fork we can't be exiting at the same time.
+	 */
+
+	/*
+	 * Lock the parent list. No need to lock the child - not PID
+	 * hashed yet and not running, so nobody can access it.
+	 */
+	mutex_lock(&parent_ctx->mutex);
+
+	/*
+	 * We dont have to disable NMIs - we are only looking at
+	 * the list, not manipulating it:
+	 */
+	list_for_each_entry(event, &parent_ctx->group_list, group_entry) {
+
+		if (!event->attr.inherit) {
+			inherited_all = 0;
+			continue;
+		}
+
+		ret = inherit_group(event, parent, parent_ctx,
+					     child, child_ctx);
+		if (ret) {
+			inherited_all = 0;
+			break;
+		}
+	}
+
+	if (inherited_all) {
+		/*
+		 * Mark the child context as a clone of the parent
+		 * context, or of whatever the parent is a clone of.
+		 * Note that if the parent is a clone, it could get
+		 * uncloned at any point, but that doesn't matter
+		 * because the list of events and the generation
+		 * count can't have changed since we took the mutex.
+		 */
+		cloned_ctx = rcu_dereference(parent_ctx->parent_ctx);
+		if (cloned_ctx) {
+			child_ctx->parent_ctx = cloned_ctx;
+			child_ctx->parent_gen = parent_ctx->parent_gen;
+		} else {
+			child_ctx->parent_ctx = parent_ctx;
+			child_ctx->parent_gen = parent_ctx->generation;
+		}
+		get_ctx(child_ctx->parent_ctx);
+	}
+
+	mutex_unlock(&parent_ctx->mutex);
+
+	perf_unpin_context(parent_ctx);
+
+	return ret;
+}
+
+static void __cpuinit perf_event_init_cpu(int cpu)
+{
+	struct perf_cpu_context *cpuctx;
+
+	cpuctx = &per_cpu(perf_cpu_context, cpu);
+	__perf_event_init_context(&cpuctx->ctx, NULL);
+
+	spin_lock(&perf_resource_lock);
+	cpuctx->max_pertask = perf_max_events - perf_reserved_percpu;
+	spin_unlock(&perf_resource_lock);
+
+	hw_perf_event_setup(cpu);
+}
+
+#ifdef CONFIG_HOTPLUG_CPU
+static void __perf_event_exit_cpu(void *info)
+{
+	struct perf_cpu_context *cpuctx = &__get_cpu_var(perf_cpu_context);
+	struct perf_event_context *ctx = &cpuctx->ctx;
+	struct perf_event *event, *tmp;
+
+	list_for_each_entry_safe(event, tmp, &ctx->group_list, group_entry)
+		__perf_event_remove_from_context(event);
+}
+static void perf_event_exit_cpu(int cpu)
+{
+	struct perf_cpu_context *cpuctx = &per_cpu(perf_cpu_context, cpu);
+	struct perf_event_context *ctx = &cpuctx->ctx;
+
+	mutex_lock(&ctx->mutex);
+	smp_call_function_single(cpu, __perf_event_exit_cpu, NULL, 1);
+	mutex_unlock(&ctx->mutex);
+}
+#else
+static inline void perf_event_exit_cpu(int cpu) { }
+#endif
+
+static int __cpuinit
+perf_cpu_notify(struct notifier_block *self, unsigned long action, void *hcpu)
+{
+	unsigned int cpu = (long)hcpu;
+
+	switch (action) {
+
+	case CPU_UP_PREPARE:
+	case CPU_UP_PREPARE_FROZEN:
+		perf_event_init_cpu(cpu);
+		break;
+
+	case CPU_ONLINE:
+	case CPU_ONLINE_FROZEN:
+		hw_perf_event_setup_online(cpu);
+		break;
+
+	case CPU_DOWN_PREPARE:
+	case CPU_DOWN_PREPARE_FROZEN:
+		perf_event_exit_cpu(cpu);
+		break;
+
+	default:
+		break;
+	}
+
+	return NOTIFY_OK;
+}
+
+/*
+ * This has to have a higher priority than migration_notifier in sched.c.
+ */
+static struct notifier_block __cpuinitdata perf_cpu_nb = {
+	.notifier_call		= perf_cpu_notify,
+	.priority		= 20,
+};
+
+void __init perf_event_init(void)
+{
+	perf_cpu_notify(&perf_cpu_nb, (unsigned long)CPU_UP_PREPARE,
+			(void *)(long)smp_processor_id());
+	perf_cpu_notify(&perf_cpu_nb, (unsigned long)CPU_ONLINE,
+			(void *)(long)smp_processor_id());
+	register_cpu_notifier(&perf_cpu_nb);
+}
+
+static ssize_t perf_show_reserve_percpu(struct sysdev_class *class, char *buf)
+{
+	return sprintf(buf, "%d\n", perf_reserved_percpu);
+}
+
+static ssize_t
+perf_set_reserve_percpu(struct sysdev_class *class,
+			const char *buf,
+			size_t count)
+{
+	struct perf_cpu_context *cpuctx;
+	unsigned long val;
+	int err, cpu, mpt;
+
+	err = strict_strtoul(buf, 10, &val);
+	if (err)
+		return err;
+	if (val > perf_max_events)
+		return -EINVAL;
+
+	spin_lock(&perf_resource_lock);
+	perf_reserved_percpu = val;
+	for_each_online_cpu(cpu) {
+		cpuctx = &per_cpu(perf_cpu_context, cpu);
+		spin_lock_irq(&cpuctx->ctx.lock);
+		mpt = min(perf_max_events - cpuctx->ctx.nr_events,
+			  perf_max_events - perf_reserved_percpu);
+		cpuctx->max_pertask = mpt;
+		spin_unlock_irq(&cpuctx->ctx.lock);
+	}
+	spin_unlock(&perf_resource_lock);
+
+	return count;
+}
+
+static ssize_t perf_show_overcommit(struct sysdev_class *class, char *buf)
+{
+	return sprintf(buf, "%d\n", perf_overcommit);
+}
+
+static ssize_t
+perf_set_overcommit(struct sysdev_class *class, const char *buf, size_t count)
+{
+	unsigned long val;
+	int err;
+
+	err = strict_strtoul(buf, 10, &val);
+	if (err)
+		return err;
+	if (val > 1)
+		return -EINVAL;
+
+	spin_lock(&perf_resource_lock);
+	perf_overcommit = val;
+	spin_unlock(&perf_resource_lock);
+
+	return count;
+}
+
+static SYSDEV_CLASS_ATTR(
+				reserve_percpu,
+				0644,
+				perf_show_reserve_percpu,
+				perf_set_reserve_percpu
+			);
+
+static SYSDEV_CLASS_ATTR(
+				overcommit,
+				0644,
+				perf_show_overcommit,
+				perf_set_overcommit
+			);
+
+static struct attribute *perfclass_attrs[] = {
+	&attr_reserve_percpu.attr,
+	&attr_overcommit.attr,
+	NULL
+};
+
+static struct attribute_group perfclass_attr_group = {
+	.attrs			= perfclass_attrs,
+	.name			= "perf_events",
+};
+
+static int __init perf_event_sysfs_init(void)
+{
+	return sysfs_create_group(&cpu_sysdev_class.kset.kobj,
+				  &perfclass_attr_group);
+}
+device_initcall(perf_event_sysfs_init);
diff --git a/kernel/pid.c b/kernel/pid.c
index 31310b5d3f50..d3f722d20f9c 100644
--- a/kernel/pid.c
+++ b/kernel/pid.c
@@ -40,7 +40,7 @@
 #define pid_hashfn(nr, ns)	\
 	hash_long((unsigned long)nr + (unsigned long)ns, pidhash_shift)
 static struct hlist_head *pid_hash;
-static int pidhash_shift;
+static unsigned int pidhash_shift = 4;
 struct pid init_struct_pid = INIT_STRUCT_PID;
 
 int pid_max = PID_MAX_DEFAULT;
@@ -499,19 +499,12 @@ struct pid *find_ge_pid(int nr, struct pid_namespace *ns)
 void __init pidhash_init(void)
 {
 	int i, pidhash_size;
-	unsigned long megabytes = nr_kernel_pages >> (20 - PAGE_SHIFT);
 
-	pidhash_shift = max(4, fls(megabytes * 4));
-	pidhash_shift = min(12, pidhash_shift);
+	pid_hash = alloc_large_system_hash("PID", sizeof(*pid_hash), 0, 18,
+					   HASH_EARLY | HASH_SMALL,
+					   &pidhash_shift, NULL, 4096);
 	pidhash_size = 1 << pidhash_shift;
 
-	printk("PID hash table entries: %d (order: %d, %Zd bytes)\n",
-		pidhash_size, pidhash_shift,
-		pidhash_size * sizeof(struct hlist_head));
-
-	pid_hash = alloc_bootmem(pidhash_size *	sizeof(*(pid_hash)));
-	if (!pid_hash)
-		panic("Could not alloc pidhash!\n");
 	for (i = 0; i < pidhash_size; i++)
 		INIT_HLIST_HEAD(&pid_hash[i]);
 }
diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c
index 821722ae58a7..86b3796b0436 100644
--- a/kernel/pid_namespace.c
+++ b/kernel/pid_namespace.c
@@ -118,7 +118,7 @@ struct pid_namespace *copy_pid_ns(unsigned long flags, struct pid_namespace *old
 {
 	if (!(flags & CLONE_NEWPID))
 		return get_pid_ns(old_ns);
-	if (flags & CLONE_THREAD)
+	if (flags & (CLONE_THREAD|CLONE_PARENT))
 		return ERR_PTR(-EINVAL);
 	return create_pid_namespace(old_ns);
 }
diff --git a/kernel/posix-cpu-timers.c b/kernel/posix-cpu-timers.c
index e33a21cb9407..5c9dc228747b 100644
--- a/kernel/posix-cpu-timers.c
+++ b/kernel/posix-cpu-timers.c
@@ -8,17 +8,18 @@
 #include <linux/math64.h>
 #include <asm/uaccess.h>
 #include <linux/kernel_stat.h>
+#include <trace/events/timer.h>
 
 /*
  * Called after updating RLIMIT_CPU to set timer expiration if necessary.
  */
 void update_rlimit_cpu(unsigned long rlim_new)
 {
-	cputime_t cputime;
+	cputime_t cputime = secs_to_cputime(rlim_new);
+	struct signal_struct *const sig = current->signal;
 
-	cputime = secs_to_cputime(rlim_new);
-	if (cputime_eq(current->signal->it_prof_expires, cputime_zero) ||
-	    cputime_gt(current->signal->it_prof_expires, cputime)) {
+	if (cputime_eq(sig->it[CPUCLOCK_PROF].expires, cputime_zero) ||
+	    cputime_gt(sig->it[CPUCLOCK_PROF].expires, cputime)) {
 		spin_lock_irq(&current->sighand->siglock);
 		set_process_cpu_timer(current, CPUCLOCK_PROF, &cputime, NULL);
 		spin_unlock_irq(&current->sighand->siglock);
@@ -542,6 +543,17 @@ static void clear_dead_task(struct k_itimer *timer, union cpu_time_count now)
 					     now);
 }
 
+static inline int expires_gt(cputime_t expires, cputime_t new_exp)
+{
+	return cputime_eq(expires, cputime_zero) ||
+	       cputime_gt(expires, new_exp);
+}
+
+static inline int expires_le(cputime_t expires, cputime_t new_exp)
+{
+	return !cputime_eq(expires, cputime_zero) &&
+	       cputime_le(expires, new_exp);
+}
 /*
  * Insert the timer on the appropriate list before any timers that
  * expire later.  This must be called with the tasklist_lock held
@@ -586,34 +598,32 @@ static void arm_timer(struct k_itimer *timer, union cpu_time_count now)
 		 */
 
 		if (CPUCLOCK_PERTHREAD(timer->it_clock)) {
+			union cpu_time_count *exp = &nt->expires;
+
 			switch (CPUCLOCK_WHICH(timer->it_clock)) {
 			default:
 				BUG();
 			case CPUCLOCK_PROF:
-				if (cputime_eq(p->cputime_expires.prof_exp,
-					       cputime_zero) ||
-				    cputime_gt(p->cputime_expires.prof_exp,
-					       nt->expires.cpu))
-					p->cputime_expires.prof_exp =
-						nt->expires.cpu;
+				if (expires_gt(p->cputime_expires.prof_exp,
+					       exp->cpu))
+					p->cputime_expires.prof_exp = exp->cpu;
 				break;
 			case CPUCLOCK_VIRT:
-				if (cputime_eq(p->cputime_expires.virt_exp,
-					       cputime_zero) ||
-				    cputime_gt(p->cputime_expires.virt_exp,
-					       nt->expires.cpu))
-					p->cputime_expires.virt_exp =
-						nt->expires.cpu;
+				if (expires_gt(p->cputime_expires.virt_exp,
+					       exp->cpu))
+					p->cputime_expires.virt_exp = exp->cpu;
 				break;
 			case CPUCLOCK_SCHED:
 				if (p->cputime_expires.sched_exp == 0 ||
-				    p->cputime_expires.sched_exp >
-							nt->expires.sched)
+				    p->cputime_expires.sched_exp > exp->sched)
 					p->cputime_expires.sched_exp =
-						nt->expires.sched;
+								exp->sched;
 				break;
 			}
 		} else {
+			struct signal_struct *const sig = p->signal;
+			union cpu_time_count *exp = &timer->it.cpu.expires;
+
 			/*
 			 * For a process timer, set the cached expiration time.
 			 */
@@ -621,30 +631,23 @@ static void arm_timer(struct k_itimer *timer, union cpu_time_count now)
 			default:
 				BUG();
 			case CPUCLOCK_VIRT:
-				if (!cputime_eq(p->signal->it_virt_expires,
-						cputime_zero) &&
-				    cputime_lt(p->signal->it_virt_expires,
-					       timer->it.cpu.expires.cpu))
+				if (expires_le(sig->it[CPUCLOCK_VIRT].expires,
+					       exp->cpu))
 					break;
-				p->signal->cputime_expires.virt_exp =
-					timer->it.cpu.expires.cpu;
+				sig->cputime_expires.virt_exp = exp->cpu;
 				break;
 			case CPUCLOCK_PROF:
-				if (!cputime_eq(p->signal->it_prof_expires,
-						cputime_zero) &&
-				    cputime_lt(p->signal->it_prof_expires,
-					       timer->it.cpu.expires.cpu))
+				if (expires_le(sig->it[CPUCLOCK_PROF].expires,
+					       exp->cpu))
 					break;
-				i = p->signal->rlim[RLIMIT_CPU].rlim_cur;
+				i = sig->rlim[RLIMIT_CPU].rlim_cur;
 				if (i != RLIM_INFINITY &&
-				    i <= cputime_to_secs(timer->it.cpu.expires.cpu))
+				    i <= cputime_to_secs(exp->cpu))
 					break;
-				p->signal->cputime_expires.prof_exp =
-					timer->it.cpu.expires.cpu;
+				sig->cputime_expires.prof_exp = exp->cpu;
 				break;
 			case CPUCLOCK_SCHED:
-				p->signal->cputime_expires.sched_exp =
-					timer->it.cpu.expires.sched;
+				sig->cputime_expires.sched_exp = exp->sched;
 				break;
 			}
 		}
@@ -1071,6 +1074,40 @@ static void stop_process_timers(struct task_struct *tsk)
 	spin_unlock_irqrestore(&cputimer->lock, flags);
 }
 
+static u32 onecputick;
+
+static void check_cpu_itimer(struct task_struct *tsk, struct cpu_itimer *it,
+			     cputime_t *expires, cputime_t cur_time, int signo)
+{
+	if (cputime_eq(it->expires, cputime_zero))
+		return;
+
+	if (cputime_ge(cur_time, it->expires)) {
+		if (!cputime_eq(it->incr, cputime_zero)) {
+			it->expires = cputime_add(it->expires, it->incr);
+			it->error += it->incr_error;
+			if (it->error >= onecputick) {
+				it->expires = cputime_sub(it->expires,
+							  cputime_one_jiffy);
+				it->error -= onecputick;
+			}
+		} else {
+			it->expires = cputime_zero;
+		}
+
+		trace_itimer_expire(signo == SIGPROF ?
+				    ITIMER_PROF : ITIMER_VIRTUAL,
+				    tsk->signal->leader_pid, cur_time);
+		__group_send_sig_info(signo, SEND_SIG_PRIV, tsk);
+	}
+
+	if (!cputime_eq(it->expires, cputime_zero) &&
+	    (cputime_eq(*expires, cputime_zero) ||
+	     cputime_lt(it->expires, *expires))) {
+		*expires = it->expires;
+	}
+}
+
 /*
  * Check for any per-thread CPU timers that have fired and move them
  * off the tsk->*_timers list onto the firing list.  Per-thread timers
@@ -1090,10 +1127,10 @@ static void check_process_timers(struct task_struct *tsk,
 	 * Don't sample the current process CPU clocks if there are no timers.
 	 */
 	if (list_empty(&timers[CPUCLOCK_PROF]) &&
-	    cputime_eq(sig->it_prof_expires, cputime_zero) &&
+	    cputime_eq(sig->it[CPUCLOCK_PROF].expires, cputime_zero) &&
 	    sig->rlim[RLIMIT_CPU].rlim_cur == RLIM_INFINITY &&
 	    list_empty(&timers[CPUCLOCK_VIRT]) &&
-	    cputime_eq(sig->it_virt_expires, cputime_zero) &&
+	    cputime_eq(sig->it[CPUCLOCK_VIRT].expires, cputime_zero) &&
 	    list_empty(&timers[CPUCLOCK_SCHED])) {
 		stop_process_timers(tsk);
 		return;
@@ -1153,38 +1190,11 @@ static void check_process_timers(struct task_struct *tsk,
 	/*
 	 * Check for the special case process timers.
 	 */
-	if (!cputime_eq(sig->it_prof_expires, cputime_zero)) {
-		if (cputime_ge(ptime, sig->it_prof_expires)) {
-			/* ITIMER_PROF fires and reloads.  */
-			sig->it_prof_expires = sig->it_prof_incr;
-			if (!cputime_eq(sig->it_prof_expires, cputime_zero)) {
-				sig->it_prof_expires = cputime_add(
-					sig->it_prof_expires, ptime);
-			}
-			__group_send_sig_info(SIGPROF, SEND_SIG_PRIV, tsk);
-		}
-		if (!cputime_eq(sig->it_prof_expires, cputime_zero) &&
-		    (cputime_eq(prof_expires, cputime_zero) ||
-		     cputime_lt(sig->it_prof_expires, prof_expires))) {
-			prof_expires = sig->it_prof_expires;
-		}
-	}
-	if (!cputime_eq(sig->it_virt_expires, cputime_zero)) {
-		if (cputime_ge(utime, sig->it_virt_expires)) {
-			/* ITIMER_VIRTUAL fires and reloads.  */
-			sig->it_virt_expires = sig->it_virt_incr;
-			if (!cputime_eq(sig->it_virt_expires, cputime_zero)) {
-				sig->it_virt_expires = cputime_add(
-					sig->it_virt_expires, utime);
-			}
-			__group_send_sig_info(SIGVTALRM, SEND_SIG_PRIV, tsk);
-		}
-		if (!cputime_eq(sig->it_virt_expires, cputime_zero) &&
-		    (cputime_eq(virt_expires, cputime_zero) ||
-		     cputime_lt(sig->it_virt_expires, virt_expires))) {
-			virt_expires = sig->it_virt_expires;
-		}
-	}
+	check_cpu_itimer(tsk, &sig->it[CPUCLOCK_PROF], &prof_expires, ptime,
+			 SIGPROF);
+	check_cpu_itimer(tsk, &sig->it[CPUCLOCK_VIRT], &virt_expires, utime,
+			 SIGVTALRM);
+
 	if (sig->rlim[RLIMIT_CPU].rlim_cur != RLIM_INFINITY) {
 		unsigned long psecs = cputime_to_secs(ptime);
 		cputime_t x;
@@ -1457,7 +1467,7 @@ void set_process_cpu_timer(struct task_struct *tsk, unsigned int clock_idx,
 		if (!cputime_eq(*oldval, cputime_zero)) {
 			if (cputime_le(*oldval, now.cpu)) {
 				/* Just about to fire. */
-				*oldval = jiffies_to_cputime(1);
+				*oldval = cputime_one_jiffy;
 			} else {
 				*oldval = cputime_sub(*oldval, now.cpu);
 			}
@@ -1703,10 +1713,15 @@ static __init int init_posix_cpu_timers(void)
 		.nsleep = thread_cpu_nsleep,
 		.nsleep_restart = thread_cpu_nsleep_restart,
 	};
+	struct timespec ts;
 
 	register_posix_clock(CLOCK_PROCESS_CPUTIME_ID, &process);
 	register_posix_clock(CLOCK_THREAD_CPUTIME_ID, &thread);
 
+	cputime_to_timespec(cputime_one_jiffy, &ts);
+	onecputick = ts.tv_nsec;
+	WARN_ON(ts.tv_sec != 0);
+
 	return 0;
 }
 __initcall(init_posix_cpu_timers);
diff --git a/kernel/posix-timers.c b/kernel/posix-timers.c
index d089d052c4a9..495440779ce3 100644
--- a/kernel/posix-timers.c
+++ b/kernel/posix-timers.c
@@ -242,6 +242,25 @@ static int posix_get_monotonic_raw(clockid_t which_clock, struct timespec *tp)
 	return 0;
 }
 
+
+static int posix_get_realtime_coarse(clockid_t which_clock, struct timespec *tp)
+{
+	*tp = current_kernel_time();
+	return 0;
+}
+
+static int posix_get_monotonic_coarse(clockid_t which_clock,
+						struct timespec *tp)
+{
+	*tp = get_monotonic_coarse();
+	return 0;
+}
+
+int posix_get_coarse_res(const clockid_t which_clock, struct timespec *tp)
+{
+	*tp = ktime_to_timespec(KTIME_LOW_RES);
+	return 0;
+}
 /*
  * Initialize everything, well, just everything in Posix clocks/timers ;)
  */
@@ -262,10 +281,26 @@ static __init int init_posix_timers(void)
 		.timer_create = no_timer_create,
 		.nsleep = no_nsleep,
 	};
+	struct k_clock clock_realtime_coarse = {
+		.clock_getres = posix_get_coarse_res,
+		.clock_get = posix_get_realtime_coarse,
+		.clock_set = do_posix_clock_nosettime,
+		.timer_create = no_timer_create,
+		.nsleep = no_nsleep,
+	};
+	struct k_clock clock_monotonic_coarse = {
+		.clock_getres = posix_get_coarse_res,
+		.clock_get = posix_get_monotonic_coarse,
+		.clock_set = do_posix_clock_nosettime,
+		.timer_create = no_timer_create,
+		.nsleep = no_nsleep,
+	};
 
 	register_posix_clock(CLOCK_REALTIME, &clock_realtime);
 	register_posix_clock(CLOCK_MONOTONIC, &clock_monotonic);
 	register_posix_clock(CLOCK_MONOTONIC_RAW, &clock_monotonic_raw);
+	register_posix_clock(CLOCK_REALTIME_COARSE, &clock_realtime_coarse);
+	register_posix_clock(CLOCK_MONOTONIC_COARSE, &clock_monotonic_coarse);
 
 	posix_timers_cache = kmem_cache_create("posix_timers_cache",
 					sizeof (struct k_itimer), 0, SLAB_PANIC,
diff --git a/kernel/power/Kconfig b/kernel/power/Kconfig
index 72067cbdb37f..91e09d3b2eb2 100644
--- a/kernel/power/Kconfig
+++ b/kernel/power/Kconfig
@@ -208,3 +208,17 @@ config APM_EMULATION
 	  random kernel OOPSes or reboots that don't seem to be related to
 	  anything, try disabling/enabling this option (or disabling/enabling
 	  APM in your BIOS).
+
+config PM_RUNTIME
+	bool "Run-time PM core functionality"
+	depends on PM
+	---help---
+	  Enable functionality allowing I/O devices to be put into energy-saving
+	  (low power) states at run time (or autosuspended) after a specified
+	  period of inactivity and woken up in response to a hardware-generated
+	  wake-up event or a driver's request.
+
+	  Hardware support is generally required for this functionality to work
+	  and the bus type drivers of the buses the devices are on are
+	  responsible for the actual handling of the autosuspend requests and
+	  wake-up events.
diff --git a/kernel/power/console.c b/kernel/power/console.c
index a3961b205de7..5187136fe1de 100644
--- a/kernel/power/console.c
+++ b/kernel/power/console.c
@@ -14,56 +14,13 @@
 #define SUSPEND_CONSOLE	(MAX_NR_CONSOLES-1)
 
 static int orig_fgconsole, orig_kmsg;
-static int disable_vt_switch;
-
-/*
- * Normally during a suspend, we allocate a new console and switch to it.
- * When we resume, we switch back to the original console.  This switch
- * can be slow, so on systems where the framebuffer can handle restoration
- * of video registers anyways, there's little point in doing the console
- * switch.  This function allows you to disable it by passing it '0'.
- */
-void pm_set_vt_switch(int do_switch)
-{
-	acquire_console_sem();
-	disable_vt_switch = !do_switch;
-	release_console_sem();
-}
-EXPORT_SYMBOL(pm_set_vt_switch);
 
 int pm_prepare_console(void)
 {
-	acquire_console_sem();
-
-	if (disable_vt_switch) {
-		release_console_sem();
-		return 0;
-	}
-
-	orig_fgconsole = fg_console;
-
-	if (vc_allocate(SUSPEND_CONSOLE)) {
-	  /* we can't have a free VC for now. Too bad,
-	   * we don't want to mess the screen for now. */
-		release_console_sem();
+	orig_fgconsole = vt_move_to_console(SUSPEND_CONSOLE, 1);
+	if (orig_fgconsole < 0)
 		return 1;
-	}
 
-	if (set_console(SUSPEND_CONSOLE)) {
-		/*
-		 * We're unable to switch to the SUSPEND_CONSOLE.
-		 * Let the calling function know so it can decide
-		 * what to do.
-		 */
-		release_console_sem();
-		return 1;
-	}
-	release_console_sem();
-
-	if (vt_waitactive(SUSPEND_CONSOLE)) {
-		pr_debug("Suspend: Can't switch VCs.");
-		return 1;
-	}
 	orig_kmsg = kmsg_redirect;
 	kmsg_redirect = SUSPEND_CONSOLE;
 	return 0;
@@ -71,19 +28,9 @@ int pm_prepare_console(void)
 
 void pm_restore_console(void)
 {
-	acquire_console_sem();
-	if (disable_vt_switch) {
-		release_console_sem();
-		return;
-	}
-	set_console(orig_fgconsole);
-	release_console_sem();
-
-	if (vt_waitactive(orig_fgconsole)) {
-		pr_debug("Resume: Can't switch VCs.");
-		return;
+	if (orig_fgconsole >= 0) {
+		vt_move_to_console(orig_fgconsole, 0);
+		kmsg_redirect = orig_kmsg;
 	}
-
-	kmsg_redirect = orig_kmsg;
 }
 #endif
diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c
index 81d2e7464893..04a9e90d248f 100644
--- a/kernel/power/hibernate.c
+++ b/kernel/power/hibernate.c
@@ -298,8 +298,8 @@ int hibernation_snapshot(int platform_mode)
 	if (error)
 		return error;
 
-	/* Free memory before shutting down devices. */
-	error = swsusp_shrink_memory();
+	/* Preallocate image memory before shutting down devices. */
+	error = hibernate_preallocate_memory();
 	if (error)
 		goto Close;
 
@@ -315,6 +315,10 @@ int hibernation_snapshot(int platform_mode)
 	/* Control returns here after successful restore */
 
  Resume_devices:
+	/* We may need to release the preallocated image pages here. */
+	if (error || !in_suspend)
+		swsusp_free();
+
 	dpm_resume_end(in_suspend ?
 		(error ? PMSG_RECOVER : PMSG_THAW) : PMSG_RESTORE);
 	resume_console();
@@ -460,11 +464,11 @@ int hibernation_platform_enter(void)
 
 	error = hibernation_ops->prepare();
 	if (error)
-		goto Platofrm_finish;
+		goto Platform_finish;
 
 	error = disable_nonboot_cpus();
 	if (error)
-		goto Platofrm_finish;
+		goto Platform_finish;
 
 	local_irq_disable();
 	sysdev_suspend(PMSG_HIBERNATE);
@@ -476,7 +480,7 @@ int hibernation_platform_enter(void)
 	 * We don't need to reenable the nonboot CPUs or resume consoles, since
 	 * the system is going to be halted anyway.
 	 */
- Platofrm_finish:
+ Platform_finish:
 	hibernation_ops->finish();
 
 	dpm_suspend_noirq(PMSG_RESTORE);
@@ -578,7 +582,10 @@ int hibernate(void)
 		goto Thaw;
 
 	error = hibernation_snapshot(hibernation_mode == HIBERNATION_PLATFORM);
-	if (in_suspend && !error) {
+	if (error)
+		goto Thaw;
+
+	if (in_suspend) {
 		unsigned int flags = 0;
 
 		if (hibernation_mode == HIBERNATION_PLATFORM)
@@ -590,8 +597,8 @@ int hibernate(void)
 			power_down();
 	} else {
 		pr_debug("PM: Image restored successfully.\n");
-		swsusp_free();
 	}
+
  Thaw:
 	thaw_processes();
  Finish:
@@ -686,21 +693,22 @@ static int software_resume(void)
 	/* The snapshot device should not be opened while we're running */
 	if (!atomic_add_unless(&snapshot_device_available, -1, 0)) {
 		error = -EBUSY;
+		swsusp_close(FMODE_READ);
 		goto Unlock;
 	}
 
 	pm_prepare_console();
 	error = pm_notifier_call_chain(PM_RESTORE_PREPARE);
 	if (error)
-		goto Finish;
+		goto close_finish;
 
 	error = usermodehelper_disable();
 	if (error)
-		goto Finish;
+		goto close_finish;
 
 	error = create_basic_memory_bitmaps();
 	if (error)
-		goto Finish;
+		goto close_finish;
 
 	pr_debug("PM: Preparing processes for restore.\n");
 	error = prepare_processes();
@@ -712,6 +720,7 @@ static int software_resume(void)
 	pr_debug("PM: Reading hibernation image.\n");
 
 	error = swsusp_read(&flags);
+	swsusp_close(FMODE_READ);
 	if (!error)
 		hibernation_restore(flags & SF_PLATFORM_MODE);
 
@@ -730,6 +739,9 @@ static int software_resume(void)
 	mutex_unlock(&pm_mutex);
 	pr_debug("PM: Resume from disk failed.\n");
 	return error;
+close_finish:
+	swsusp_close(FMODE_READ);
+	goto Finish;
 }
 
 late_initcall(software_resume);
diff --git a/kernel/power/main.c b/kernel/power/main.c
index f710e36930cc..347d2cc88cd0 100644
--- a/kernel/power/main.c
+++ b/kernel/power/main.c
@@ -11,6 +11,7 @@
 #include <linux/kobject.h>
 #include <linux/string.h>
 #include <linux/resume-trace.h>
+#include <linux/workqueue.h>
 
 #include "power.h"
 
@@ -217,8 +218,24 @@ static struct attribute_group attr_group = {
 	.attrs = g,
 };
 
+#ifdef CONFIG_PM_RUNTIME
+struct workqueue_struct *pm_wq;
+
+static int __init pm_start_workqueue(void)
+{
+	pm_wq = create_freezeable_workqueue("pm");
+
+	return pm_wq ? 0 : -ENOMEM;
+}
+#else
+static inline int pm_start_workqueue(void) { return 0; }
+#endif
+
 static int __init pm_init(void)
 {
+	int error = pm_start_workqueue();
+	if (error)
+		return error;
 	power_kobj = kobject_create_and_add("power", NULL);
 	if (!power_kobj)
 		return -ENOMEM;
diff --git a/kernel/power/power.h b/kernel/power/power.h
index 26d5a26f82e3..46c5a26630a3 100644
--- a/kernel/power/power.h
+++ b/kernel/power/power.h
@@ -74,7 +74,7 @@ extern asmlinkage int swsusp_arch_resume(void);
 
 extern int create_basic_memory_bitmaps(void);
 extern void free_basic_memory_bitmaps(void);
-extern int swsusp_shrink_memory(void);
+extern int hibernate_preallocate_memory(void);
 
 /**
  *	Auxiliary structure used for reading the snapshot image data and
diff --git a/kernel/power/process.c b/kernel/power/process.c
index da2072d73811..cc2e55373b68 100644
--- a/kernel/power/process.c
+++ b/kernel/power/process.c
@@ -9,6 +9,7 @@
 #undef DEBUG
 
 #include <linux/interrupt.h>
+#include <linux/oom.h>
 #include <linux/suspend.h>
 #include <linux/module.h>
 #include <linux/syscalls.h>
diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c
index 523a451b45d3..36cb168e4330 100644
--- a/kernel/power/snapshot.c
+++ b/kernel/power/snapshot.c
@@ -233,7 +233,7 @@ static void *chain_alloc(struct chain_allocator *ca, unsigned int size)
 
 #define BM_END_OF_MAP	(~0UL)
 
-#define BM_BITS_PER_BLOCK	(PAGE_SIZE << 3)
+#define BM_BITS_PER_BLOCK	(PAGE_SIZE * BITS_PER_BYTE)
 
 struct bm_block {
 	struct list_head hook;	/* hook into a list of bitmap blocks */
@@ -275,7 +275,7 @@ static void memory_bm_free(struct memory_bitmap *bm, int clear_nosave_free);
 
 /**
  *	create_bm_block_list - create a list of block bitmap objects
- *	@nr_blocks - number of blocks to allocate
+ *	@pages - number of pages to track
  *	@list - list to put the allocated blocks into
  *	@ca - chain allocator to be used for allocating memory
  */
@@ -619,7 +619,7 @@ __register_nosave_region(unsigned long start_pfn, unsigned long end_pfn,
 		BUG_ON(!region);
 	} else
 		/* This allocation cannot fail */
-		region = alloc_bootmem_low(sizeof(struct nosave_region));
+		region = alloc_bootmem(sizeof(struct nosave_region));
 	region->start_pfn = start_pfn;
 	region->end_pfn = end_pfn;
 	list_add_tail(&region->list, &nosave_regions);
@@ -853,7 +853,7 @@ static unsigned int count_highmem_pages(void)
 	struct zone *zone;
 	unsigned int n = 0;
 
-	for_each_zone(zone) {
+	for_each_populated_zone(zone) {
 		unsigned long pfn, max_zone_pfn;
 
 		if (!is_highmem(zone))
@@ -916,7 +916,7 @@ static unsigned int count_data_pages(void)
 	unsigned long pfn, max_zone_pfn;
 	unsigned int n = 0;
 
-	for_each_zone(zone) {
+	for_each_populated_zone(zone) {
 		if (is_highmem(zone))
 			continue;
 
@@ -1010,7 +1010,7 @@ copy_data_pages(struct memory_bitmap *copy_bm, struct memory_bitmap *orig_bm)
 	struct zone *zone;
 	unsigned long pfn;
 
-	for_each_zone(zone) {
+	for_each_populated_zone(zone) {
 		unsigned long max_zone_pfn;
 
 		mark_free_pages(zone);
@@ -1033,6 +1033,25 @@ copy_data_pages(struct memory_bitmap *copy_bm, struct memory_bitmap *orig_bm)
 static unsigned int nr_copy_pages;
 /* Number of pages needed for saving the original pfns of the image pages */
 static unsigned int nr_meta_pages;
+/*
+ * Numbers of normal and highmem page frames allocated for hibernation image
+ * before suspending devices.
+ */
+unsigned int alloc_normal, alloc_highmem;
+/*
+ * Memory bitmap used for marking saveable pages (during hibernation) or
+ * hibernation image pages (during restore)
+ */
+static struct memory_bitmap orig_bm;
+/*
+ * Memory bitmap used during hibernation for marking allocated page frames that
+ * will contain copies of saveable pages.  During restore it is initially used
+ * for marking hibernation image pages, but then the set bits from it are
+ * duplicated in @orig_bm and it is released.  On highmem systems it is next
+ * used for marking "safe" highmem pages, but it has to be reinitialized for
+ * this purpose.
+ */
+static struct memory_bitmap copy_bm;
 
 /**
  *	swsusp_free - free pages allocated for the suspend.
@@ -1046,7 +1065,7 @@ void swsusp_free(void)
 	struct zone *zone;
 	unsigned long pfn, max_zone_pfn;
 
-	for_each_zone(zone) {
+	for_each_populated_zone(zone) {
 		max_zone_pfn = zone->zone_start_pfn + zone->spanned_pages;
 		for (pfn = zone->zone_start_pfn; pfn < max_zone_pfn; pfn++)
 			if (pfn_valid(pfn)) {
@@ -1064,74 +1083,286 @@ void swsusp_free(void)
 	nr_meta_pages = 0;
 	restore_pblist = NULL;
 	buffer = NULL;
+	alloc_normal = 0;
+	alloc_highmem = 0;
 }
 
+/* Helper functions used for the shrinking of memory. */
+
+#define GFP_IMAGE	(GFP_KERNEL | __GFP_NOWARN)
+
 /**
- *	swsusp_shrink_memory -  Try to free as much memory as needed
- *
- *	... but do not OOM-kill anyone
+ * preallocate_image_pages - Allocate a number of pages for hibernation image
+ * @nr_pages: Number of page frames to allocate.
+ * @mask: GFP flags to use for the allocation.
  *
- *	Notice: all userland should be stopped before it is called, or
- *	livelock is possible.
+ * Return value: Number of page frames actually allocated
+ */
+static unsigned long preallocate_image_pages(unsigned long nr_pages, gfp_t mask)
+{
+	unsigned long nr_alloc = 0;
+
+	while (nr_pages > 0) {
+		struct page *page;
+
+		page = alloc_image_page(mask);
+		if (!page)
+			break;
+		memory_bm_set_bit(&copy_bm, page_to_pfn(page));
+		if (PageHighMem(page))
+			alloc_highmem++;
+		else
+			alloc_normal++;
+		nr_pages--;
+		nr_alloc++;
+	}
+
+	return nr_alloc;
+}
+
+static unsigned long preallocate_image_memory(unsigned long nr_pages)
+{
+	return preallocate_image_pages(nr_pages, GFP_IMAGE);
+}
+
+#ifdef CONFIG_HIGHMEM
+static unsigned long preallocate_image_highmem(unsigned long nr_pages)
+{
+	return preallocate_image_pages(nr_pages, GFP_IMAGE | __GFP_HIGHMEM);
+}
+
+/**
+ *  __fraction - Compute (an approximation of) x * (multiplier / base)
  */
+static unsigned long __fraction(u64 x, u64 multiplier, u64 base)
+{
+	x *= multiplier;
+	do_div(x, base);
+	return (unsigned long)x;
+}
+
+static unsigned long preallocate_highmem_fraction(unsigned long nr_pages,
+						unsigned long highmem,
+						unsigned long total)
+{
+	unsigned long alloc = __fraction(nr_pages, highmem, total);
 
-#define SHRINK_BITE	10000
-static inline unsigned long __shrink_memory(long tmp)
+	return preallocate_image_pages(alloc, GFP_IMAGE | __GFP_HIGHMEM);
+}
+#else /* CONFIG_HIGHMEM */
+static inline unsigned long preallocate_image_highmem(unsigned long nr_pages)
 {
-	if (tmp > SHRINK_BITE)
-		tmp = SHRINK_BITE;
-	return shrink_all_memory(tmp);
+	return 0;
 }
 
-int swsusp_shrink_memory(void)
+static inline unsigned long preallocate_highmem_fraction(unsigned long nr_pages,
+						unsigned long highmem,
+						unsigned long total)
+{
+	return 0;
+}
+#endif /* CONFIG_HIGHMEM */
+
+/**
+ * free_unnecessary_pages - Release preallocated pages not needed for the image
+ */
+static void free_unnecessary_pages(void)
+{
+	unsigned long save_highmem, to_free_normal, to_free_highmem;
+
+	to_free_normal = alloc_normal - count_data_pages();
+	save_highmem = count_highmem_pages();
+	if (alloc_highmem > save_highmem) {
+		to_free_highmem = alloc_highmem - save_highmem;
+	} else {
+		to_free_highmem = 0;
+		to_free_normal -= save_highmem - alloc_highmem;
+	}
+
+	memory_bm_position_reset(&copy_bm);
+
+	while (to_free_normal > 0 && to_free_highmem > 0) {
+		unsigned long pfn = memory_bm_next_pfn(&copy_bm);
+		struct page *page = pfn_to_page(pfn);
+
+		if (PageHighMem(page)) {
+			if (!to_free_highmem)
+				continue;
+			to_free_highmem--;
+			alloc_highmem--;
+		} else {
+			if (!to_free_normal)
+				continue;
+			to_free_normal--;
+			alloc_normal--;
+		}
+		memory_bm_clear_bit(&copy_bm, pfn);
+		swsusp_unset_page_forbidden(page);
+		swsusp_unset_page_free(page);
+		__free_page(page);
+	}
+}
+
+/**
+ * minimum_image_size - Estimate the minimum acceptable size of an image
+ * @saveable: Number of saveable pages in the system.
+ *
+ * We want to avoid attempting to free too much memory too hard, so estimate the
+ * minimum acceptable size of a hibernation image to use as the lower limit for
+ * preallocating memory.
+ *
+ * We assume that the minimum image size should be proportional to
+ *
+ * [number of saveable pages] - [number of pages that can be freed in theory]
+ *
+ * where the second term is the sum of (1) reclaimable slab pages, (2) active
+ * and (3) inactive anonymouns pages, (4) active and (5) inactive file pages,
+ * minus mapped file pages.
+ */
+static unsigned long minimum_image_size(unsigned long saveable)
+{
+	unsigned long size;
+
+	size = global_page_state(NR_SLAB_RECLAIMABLE)
+		+ global_page_state(NR_ACTIVE_ANON)
+		+ global_page_state(NR_INACTIVE_ANON)
+		+ global_page_state(NR_ACTIVE_FILE)
+		+ global_page_state(NR_INACTIVE_FILE)
+		- global_page_state(NR_FILE_MAPPED);
+
+	return saveable <= size ? 0 : saveable - size;
+}
+
+/**
+ * hibernate_preallocate_memory - Preallocate memory for hibernation image
+ *
+ * To create a hibernation image it is necessary to make a copy of every page
+ * frame in use.  We also need a number of page frames to be free during
+ * hibernation for allocations made while saving the image and for device
+ * drivers, in case they need to allocate memory from their hibernation
+ * callbacks (these two numbers are given by PAGES_FOR_IO and SPARE_PAGES,
+ * respectively, both of which are rough estimates).  To make this happen, we
+ * compute the total number of available page frames and allocate at least
+ *
+ * ([page frames total] + PAGES_FOR_IO + [metadata pages]) / 2 + 2 * SPARE_PAGES
+ *
+ * of them, which corresponds to the maximum size of a hibernation image.
+ *
+ * If image_size is set below the number following from the above formula,
+ * the preallocation of memory is continued until the total number of saveable
+ * pages in the system is below the requested image size or the minimum
+ * acceptable image size returned by minimum_image_size(), whichever is greater.
+ */
+int hibernate_preallocate_memory(void)
 {
-	long tmp;
 	struct zone *zone;
-	unsigned long pages = 0;
-	unsigned int i = 0;
-	char *p = "-\\|/";
+	unsigned long saveable, size, max_size, count, highmem, pages = 0;
+	unsigned long alloc, save_highmem, pages_highmem;
 	struct timeval start, stop;
+	int error;
 
-	printk(KERN_INFO "PM: Shrinking memory...  ");
+	printk(KERN_INFO "PM: Preallocating image memory... ");
 	do_gettimeofday(&start);
-	do {
-		long size, highmem_size;
-
-		highmem_size = count_highmem_pages();
-		size = count_data_pages() + PAGES_FOR_IO + SPARE_PAGES;
-		tmp = size;
-		size += 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];
-			}
-		}
 
-		if (highmem_size < 0)
-			highmem_size = 0;
+	error = memory_bm_create(&orig_bm, GFP_IMAGE, PG_ANY);
+	if (error)
+		goto err_out;
 
-		tmp += highmem_size;
-		if (tmp > 0) {
-			tmp = __shrink_memory(tmp);
-			if (!tmp)
-				return -ENOMEM;
-			pages += tmp;
-		} else if (size > image_size / PAGE_SIZE) {
-			tmp = __shrink_memory(size - (image_size / PAGE_SIZE));
-			pages += tmp;
-		}
-		printk("\b%c", p[i++%4]);
-	} while (tmp > 0);
+	error = memory_bm_create(&copy_bm, GFP_IMAGE, PG_ANY);
+	if (error)
+		goto err_out;
+
+	alloc_normal = 0;
+	alloc_highmem = 0;
+
+	/* Count the number of saveable data pages. */
+	save_highmem = count_highmem_pages();
+	saveable = count_data_pages();
+
+	/*
+	 * Compute the total number of page frames we can use (count) and the
+	 * number of pages needed for image metadata (size).
+	 */
+	count = saveable;
+	saveable += save_highmem;
+	highmem = save_highmem;
+	size = 0;
+	for_each_populated_zone(zone) {
+		size += snapshot_additional_pages(zone);
+		if (is_highmem(zone))
+			highmem += zone_page_state(zone, NR_FREE_PAGES);
+		else
+			count += zone_page_state(zone, NR_FREE_PAGES);
+	}
+	count += highmem;
+	count -= totalreserve_pages;
+
+	/* Compute the maximum number of saveable pages to leave in memory. */
+	max_size = (count - (size + PAGES_FOR_IO)) / 2 - 2 * SPARE_PAGES;
+	size = DIV_ROUND_UP(image_size, PAGE_SIZE);
+	if (size > max_size)
+		size = max_size;
+	/*
+	 * If the maximum is not less than the current number of saveable pages
+	 * in memory, allocate page frames for the image and we're done.
+	 */
+	if (size >= saveable) {
+		pages = preallocate_image_highmem(save_highmem);
+		pages += preallocate_image_memory(saveable - pages);
+		goto out;
+	}
+
+	/* Estimate the minimum size of the image. */
+	pages = minimum_image_size(saveable);
+	if (size < pages)
+		size = min_t(unsigned long, pages, max_size);
+
+	/*
+	 * Let the memory management subsystem know that we're going to need a
+	 * large number of page frames to allocate and make it free some memory.
+	 * NOTE: If this is not done, performance will be hurt badly in some
+	 * test cases.
+	 */
+	shrink_all_memory(saveable - size);
+
+	/*
+	 * The number of saveable pages in memory was too high, so apply some
+	 * pressure to decrease it.  First, make room for the largest possible
+	 * image and fail if that doesn't work.  Next, try to decrease the size
+	 * of the image as much as indicated by 'size' using allocations from
+	 * highmem and non-highmem zones separately.
+	 */
+	pages_highmem = preallocate_image_highmem(highmem / 2);
+	alloc = (count - max_size) - pages_highmem;
+	pages = preallocate_image_memory(alloc);
+	if (pages < alloc)
+		goto err_out;
+	size = max_size - size;
+	alloc = size;
+	size = preallocate_highmem_fraction(size, highmem, count);
+	pages_highmem += size;
+	alloc -= size;
+	pages += preallocate_image_memory(alloc);
+	pages += pages_highmem;
+
+	/*
+	 * We only need as many page frames for the image as there are saveable
+	 * pages in memory, but we have allocated more.  Release the excessive
+	 * ones now.
+	 */
+	free_unnecessary_pages();
+
+ out:
 	do_gettimeofday(&stop);
-	printk("\bdone (%lu pages freed)\n", pages);
-	swsusp_show_speed(&start, &stop, pages, "Freed");
+	printk(KERN_CONT "done (allocated %lu pages)\n", pages);
+	swsusp_show_speed(&start, &stop, pages, "Allocated");
 
 	return 0;
+
+ err_out:
+	printk(KERN_CONT "\n");
+	swsusp_free();
+	return -ENOMEM;
 }
 
 #ifdef CONFIG_HIGHMEM
@@ -1142,7 +1373,7 @@ int swsusp_shrink_memory(void)
 
 static unsigned int count_pages_for_highmem(unsigned int nr_highmem)
 {
-	unsigned int free_highmem = count_free_highmem_pages();
+	unsigned int free_highmem = count_free_highmem_pages() + alloc_highmem;
 
 	if (free_highmem >= nr_highmem)
 		nr_highmem = 0;
@@ -1164,19 +1395,17 @@ count_pages_for_highmem(unsigned int nr_highmem) { return 0; }
 static int enough_free_mem(unsigned int nr_pages, unsigned int nr_highmem)
 {
 	struct zone *zone;
-	unsigned int free = 0, meta = 0;
+	unsigned int free = alloc_normal;
 
-	for_each_zone(zone) {
-		meta += snapshot_additional_pages(zone);
+	for_each_populated_zone(zone)
 		if (!is_highmem(zone))
 			free += zone_page_state(zone, NR_FREE_PAGES);
-	}
 
 	nr_pages += count_pages_for_highmem(nr_highmem);
-	pr_debug("PM: Normal pages needed: %u + %u + %u, available pages: %u\n",
-		nr_pages, PAGES_FOR_IO, meta, free);
+	pr_debug("PM: Normal pages needed: %u + %u, available pages: %u\n",
+		nr_pages, PAGES_FOR_IO, free);
 
-	return free > nr_pages + PAGES_FOR_IO + meta;
+	return free > nr_pages + PAGES_FOR_IO;
 }
 
 #ifdef CONFIG_HIGHMEM
@@ -1198,7 +1427,7 @@ static inline int get_highmem_buffer(int safe_needed)
  */
 
 static inline unsigned int
-alloc_highmem_image_pages(struct memory_bitmap *bm, unsigned int nr_highmem)
+alloc_highmem_pages(struct memory_bitmap *bm, unsigned int nr_highmem)
 {
 	unsigned int to_alloc = count_free_highmem_pages();
 
@@ -1218,7 +1447,7 @@ alloc_highmem_image_pages(struct memory_bitmap *bm, unsigned int nr_highmem)
 static inline int get_highmem_buffer(int safe_needed) { return 0; }
 
 static inline unsigned int
-alloc_highmem_image_pages(struct memory_bitmap *bm, unsigned int n) { return 0; }
+alloc_highmem_pages(struct memory_bitmap *bm, unsigned int n) { return 0; }
 #endif /* CONFIG_HIGHMEM */
 
 /**
@@ -1237,51 +1466,36 @@ static int
 swsusp_alloc(struct memory_bitmap *orig_bm, struct memory_bitmap *copy_bm,
 		unsigned int nr_pages, unsigned int nr_highmem)
 {
-	int error;
-
-	error = memory_bm_create(orig_bm, GFP_ATOMIC | __GFP_COLD, PG_ANY);
-	if (error)
-		goto Free;
-
-	error = memory_bm_create(copy_bm, GFP_ATOMIC | __GFP_COLD, PG_ANY);
-	if (error)
-		goto Free;
+	int error = 0;
 
 	if (nr_highmem > 0) {
 		error = get_highmem_buffer(PG_ANY);
 		if (error)
-			goto Free;
-
-		nr_pages += alloc_highmem_image_pages(copy_bm, nr_highmem);
+			goto err_out;
+		if (nr_highmem > alloc_highmem) {
+			nr_highmem -= alloc_highmem;
+			nr_pages += alloc_highmem_pages(copy_bm, nr_highmem);
+		}
 	}
-	while (nr_pages-- > 0) {
-		struct page *page = alloc_image_page(GFP_ATOMIC | __GFP_COLD);
-
-		if (!page)
-			goto Free;
+	if (nr_pages > alloc_normal) {
+		nr_pages -= alloc_normal;
+		while (nr_pages-- > 0) {
+			struct page *page;
 
-		memory_bm_set_bit(copy_bm, page_to_pfn(page));
+			page = alloc_image_page(GFP_ATOMIC | __GFP_COLD);
+			if (!page)
+				goto err_out;
+			memory_bm_set_bit(copy_bm, page_to_pfn(page));
+		}
 	}
+
 	return 0;
 
- Free:
+ err_out:
 	swsusp_free();
-	return -ENOMEM;
+	return error;
 }
 
-/* Memory bitmap used for marking saveable pages (during suspend) or the
- * suspend image pages (during resume)
- */
-static struct memory_bitmap orig_bm;
-/* Memory bitmap used on suspend for marking allocated pages that will contain
- * the copies of saveable pages.  During resume it is initially used for
- * marking the suspend image pages, but then its set bits are duplicated in
- * @orig_bm and it is released.  Next, on systems with high memory, it may be
- * used for marking "safe" highmem pages, but it has to be reinitialized for
- * this purpose.
- */
-static struct memory_bitmap copy_bm;
-
 asmlinkage int swsusp_save(void)
 {
 	unsigned int nr_pages, nr_highmem;
@@ -1474,7 +1688,7 @@ static int mark_unsafe_pages(struct memory_bitmap *bm)
 	unsigned long pfn, max_zone_pfn;
 
 	/* Clear page flags */
-	for_each_zone(zone) {
+	for_each_populated_zone(zone) {
 		max_zone_pfn = zone->zone_start_pfn + zone->spanned_pages;
 		for (pfn = zone->zone_start_pfn; pfn < max_zone_pfn; pfn++)
 			if (pfn_valid(pfn))
diff --git a/kernel/power/suspend_test.c b/kernel/power/suspend_test.c
index 17d8bb1acf9c..25596e450ac7 100644
--- a/kernel/power/suspend_test.c
+++ b/kernel/power/suspend_test.c
@@ -19,7 +19,7 @@
  * The time it takes is system-specific though, so when we test this
  * during system bootup we allow a LOT of time.
  */
-#define TEST_SUSPEND_SECONDS	5
+#define TEST_SUSPEND_SECONDS	10
 
 static unsigned long suspend_test_start_time;
 
@@ -49,7 +49,8 @@ void suspend_test_finish(const char *label)
 	 * has some performance issues.  The stack dump of a WARN_ON
 	 * is more likely to get the right attention than a printk...
 	 */
-	WARN(msec > (TEST_SUSPEND_SECONDS * 1000), "Component: %s\n", label);
+	WARN(msec > (TEST_SUSPEND_SECONDS * 1000),
+	     "Component: %s, time: %u\n", label, msec);
 }
 
 /*
diff --git a/kernel/power/swap.c b/kernel/power/swap.c
index 8ba052c86d48..890f6b11b1d3 100644
--- a/kernel/power/swap.c
+++ b/kernel/power/swap.c
@@ -13,7 +13,6 @@
 
 #include <linux/module.h>
 #include <linux/file.h>
-#include <linux/utsname.h>
 #include <linux/delay.h>
 #include <linux/bitops.h>
 #include <linux/genhd.h>
@@ -315,7 +314,6 @@ static int save_image(struct swap_map_handle *handle,
 {
 	unsigned int m;
 	int ret;
-	int error = 0;
 	int nr_pages;
 	int err2;
 	struct bio *bio;
@@ -330,26 +328,27 @@ static int save_image(struct swap_map_handle *handle,
 	nr_pages = 0;
 	bio = NULL;
 	do_gettimeofday(&start);
-	do {
+	while (1) {
 		ret = snapshot_read_next(snapshot, PAGE_SIZE);
-		if (ret > 0) {
-			error = swap_write_page(handle, data_of(*snapshot),
-						&bio);
-			if (error)
-				break;
-			if (!(nr_pages % m))
-				printk("\b\b\b\b%3d%%", nr_pages / m);
-			nr_pages++;
-		}
-	} while (ret > 0);
+		if (ret <= 0)
+			break;
+		ret = swap_write_page(handle, data_of(*snapshot), &bio);
+		if (ret)
+			break;
+		if (!(nr_pages % m))
+			printk("\b\b\b\b%3d%%", nr_pages / m);
+		nr_pages++;
+	}
 	err2 = wait_on_bio_chain(&bio);
 	do_gettimeofday(&stop);
-	if (!error)
-		error = err2;
-	if (!error)
+	if (!ret)
+		ret = err2;
+	if (!ret)
 		printk("\b\b\b\bdone\n");
+	else
+		printk("\n");
 	swsusp_show_speed(&start, &stop, nr_to_write, "Wrote");
-	return error;
+	return ret;
 }
 
 /**
@@ -537,7 +536,8 @@ static int load_image(struct swap_map_handle *handle,
 		snapshot_write_finalize(snapshot);
 		if (!snapshot_image_loaded(snapshot))
 			error = -ENODATA;
-	}
+	} else
+		printk("\n");
 	swsusp_show_speed(&start, &stop, nr_to_read, "Read");
 	return error;
 }
@@ -573,8 +573,6 @@ int swsusp_read(unsigned int *flags_p)
 		error = load_image(&handle, &snapshot, header->pages - 1);
 	release_swap_reader(&handle);
 
-	blkdev_put(resume_bdev, FMODE_READ);
-
 	if (!error)
 		pr_debug("PM: Image successfully loaded\n");
 	else
@@ -597,7 +595,7 @@ int swsusp_check(void)
 		error = bio_read_page(swsusp_resume_block,
 					swsusp_header, NULL);
 		if (error)
-			return error;
+			goto put;
 
 		if (!memcmp(SWSUSP_SIG, swsusp_header->sig, 10)) {
 			memcpy(swsusp_header->sig, swsusp_header->orig_sig, 10);
@@ -605,8 +603,10 @@ int swsusp_check(void)
 			error = bio_write_page(swsusp_resume_block,
 						swsusp_header, NULL);
 		} else {
-			return -EINVAL;
+			error = -EINVAL;
 		}
+
+put:
 		if (error)
 			blkdev_put(resume_bdev, FMODE_READ);
 		else
diff --git a/kernel/printk.c b/kernel/printk.c
index b4d97b54c1ec..f38b07f78a4e 100644
--- a/kernel/printk.c
+++ b/kernel/printk.c
@@ -37,6 +37,12 @@
 #include <asm/uaccess.h>
 
 /*
+ * for_each_console() allows you to iterate on each console
+ */
+#define for_each_console(con) \
+	for (con = console_drivers; con != NULL; con = con->next)
+
+/*
  * Architectures can override it:
  */
 void asmlinkage __attribute__((weak)) early_printk(const char *fmt, ...)
@@ -61,6 +67,8 @@ int console_printk[4] = {
 	DEFAULT_CONSOLE_LOGLEVEL,	/* default_console_loglevel */
 };
 
+static int saved_console_loglevel = -1;
+
 /*
  * Low level drivers may need that to know if they can schedule in
  * their unblank() callback or not. So let's export it.
@@ -198,12 +206,11 @@ __setup("log_buf_len=", log_buf_len_setup);
 #ifdef CONFIG_BOOT_PRINTK_DELAY
 
 static unsigned int boot_delay; /* msecs delay after each printk during bootup */
-static unsigned long long printk_delay_msec; /* per msec, based on boot_delay */
+static unsigned long long loops_per_msec;	/* based on boot_delay */
 
 static int __init boot_delay_setup(char *str)
 {
 	unsigned long lpj;
-	unsigned long long loops_per_msec;
 
 	lpj = preset_lpj ? preset_lpj : 1000000;	/* some guess */
 	loops_per_msec = (unsigned long long)lpj / 1000 * HZ;
@@ -212,10 +219,9 @@ static int __init boot_delay_setup(char *str)
 	if (boot_delay > 10 * 1000)
 		boot_delay = 0;
 
-	printk_delay_msec = loops_per_msec;
-	printk(KERN_DEBUG "boot_delay: %u, preset_lpj: %ld, lpj: %lu, "
-		"HZ: %d, printk_delay_msec: %llu\n",
-		boot_delay, preset_lpj, lpj, HZ, printk_delay_msec);
+	pr_debug("boot_delay: %u, preset_lpj: %ld, lpj: %lu, "
+		"HZ: %d, loops_per_msec: %llu\n",
+		boot_delay, preset_lpj, lpj, HZ, loops_per_msec);
 	return 1;
 }
 __setup("boot_delay=", boot_delay_setup);
@@ -228,7 +234,7 @@ static void boot_delay_msec(void)
 	if (boot_delay == 0 || system_state != SYSTEM_BOOTING)
 		return;
 
-	k = (unsigned long long)printk_delay_msec * boot_delay;
+	k = (unsigned long long)loops_per_msec * boot_delay;
 
 	timeout = jiffies + msecs_to_jiffies(boot_delay);
 	while (k) {
@@ -372,10 +378,15 @@ int do_syslog(int type, char __user *buf, int len)
 		logged_chars = 0;
 		break;
 	case 6:		/* Disable logging to console */
+		if (saved_console_loglevel == -1)
+			saved_console_loglevel = console_loglevel;
 		console_loglevel = minimum_console_loglevel;
 		break;
 	case 7:		/* Enable logging to console */
-		console_loglevel = default_console_loglevel;
+		if (saved_console_loglevel != -1) {
+			console_loglevel = saved_console_loglevel;
+			saved_console_loglevel = -1;
+		}
 		break;
 	case 8:		/* Set level of messages printed to console */
 		error = -EINVAL;
@@ -384,6 +395,8 @@ int do_syslog(int type, char __user *buf, int len)
 		if (len < minimum_console_loglevel)
 			len = minimum_console_loglevel;
 		console_loglevel = len;
+		/* Implicitly re-enable logging to console */
+		saved_console_loglevel = -1;
 		error = 0;
 		break;
 	case 9:		/* Number of chars in the log buffer */
@@ -412,7 +425,7 @@ static void __call_console_drivers(unsigned start, unsigned end)
 {
 	struct console *con;
 
-	for (con = console_drivers; con; con = con->next) {
+	for_each_console(con) {
 		if ((con->flags & CON_ENABLED) && con->write &&
 				(cpu_online(smp_processor_id()) ||
 				(con->flags & CON_ANYTIME)))
@@ -544,7 +557,7 @@ static int have_callable_console(void)
 {
 	struct console *con;
 
-	for (con = console_drivers; con; con = con->next)
+	for_each_console(con)
 		if (con->flags & CON_ANYTIME)
 			return 1;
 
@@ -640,6 +653,20 @@ static int recursion_bug;
 static int new_text_line = 1;
 static char printk_buf[1024];
 
+int printk_delay_msec __read_mostly;
+
+static inline void printk_delay(void)
+{
+	if (unlikely(printk_delay_msec)) {
+		int m = printk_delay_msec;
+
+		while (m--) {
+			mdelay(1);
+			touch_nmi_watchdog();
+		}
+	}
+}
+
 asmlinkage int vprintk(const char *fmt, va_list args)
 {
 	int printed_len = 0;
@@ -649,6 +676,7 @@ asmlinkage int vprintk(const char *fmt, va_list args)
 	char *p;
 
 	boot_delay_msec();
+	printk_delay();
 
 	preempt_disable();
 	/* This stops the holder of console_sem just where we want him */
@@ -1060,12 +1088,6 @@ void __sched console_conditional_schedule(void)
 }
 EXPORT_SYMBOL(console_conditional_schedule);
 
-void console_print(const char *s)
-{
-	printk(KERN_EMERG "%s", s);
-}
-EXPORT_SYMBOL(console_print);
-
 void console_unblank(void)
 {
 	struct console *c;
@@ -1082,7 +1104,7 @@ void console_unblank(void)
 
 	console_locked = 1;
 	console_may_schedule = 0;
-	for (c = console_drivers; c != NULL; c = c->next)
+	for_each_console(c)
 		if ((c->flags & CON_ENABLED) && c->unblank)
 			c->unblank();
 	release_console_sem();
@@ -1097,7 +1119,7 @@ struct tty_driver *console_device(int *index)
 	struct tty_driver *driver = NULL;
 
 	acquire_console_sem();
-	for (c = console_drivers; c != NULL; c = c->next) {
+	for_each_console(c) {
 		if (!c->device)
 			continue;
 		driver = c->device(c, index);
@@ -1134,25 +1156,49 @@ EXPORT_SYMBOL(console_start);
  * to register the console printing procedure with printk() and to
  * print any messages that were printed by the kernel before the
  * console driver was initialized.
+ *
+ * This can happen pretty early during the boot process (because of
+ * early_printk) - sometimes before setup_arch() completes - be careful
+ * of what kernel features are used - they may not be initialised yet.
+ *
+ * There are two types of consoles - bootconsoles (early_printk) and
+ * "real" consoles (everything which is not a bootconsole) which are
+ * handled differently.
+ *  - Any number of bootconsoles can be registered at any time.
+ *  - As soon as a "real" console is registered, all bootconsoles
+ *    will be unregistered automatically.
+ *  - Once a "real" console is registered, any attempt to register a
+ *    bootconsoles will be rejected
  */
-void register_console(struct console *console)
+void register_console(struct console *newcon)
 {
 	int i;
 	unsigned long flags;
-	struct console *bootconsole = NULL;
+	struct console *bcon = NULL;
 
-	if (console_drivers) {
-		if (console->flags & CON_BOOT)
-			return;
-		if (console_drivers->flags & CON_BOOT)
-			bootconsole = console_drivers;
+	/*
+	 * before we register a new CON_BOOT console, make sure we don't
+	 * already have a valid console
+	 */
+	if (console_drivers && newcon->flags & CON_BOOT) {
+		/* find the last or real console */
+		for_each_console(bcon) {
+			if (!(bcon->flags & CON_BOOT)) {
+				printk(KERN_INFO "Too late to register bootconsole %s%d\n",
+					newcon->name, newcon->index);
+				return;
+			}
+		}
 	}
 
-	if (preferred_console < 0 || bootconsole || !console_drivers)
+	if (console_drivers && console_drivers->flags & CON_BOOT)
+		bcon = console_drivers;
+
+	if (preferred_console < 0 || bcon || !console_drivers)
 		preferred_console = selected_console;
 
-	if (console->early_setup)
-		console->early_setup();
+	if (newcon->early_setup)
+		newcon->early_setup();
 
 	/*
 	 *	See if we want to use this console driver. If we
@@ -1160,13 +1206,13 @@ void register_console(struct console *console)
 	 *	that registers here.
 	 */
 	if (preferred_console < 0) {
-		if (console->index < 0)
-			console->index = 0;
-		if (console->setup == NULL ||
-		    console->setup(console, NULL) == 0) {
-			console->flags |= CON_ENABLED;
-			if (console->device) {
-				console->flags |= CON_CONSDEV;
+		if (newcon->index < 0)
+			newcon->index = 0;
+		if (newcon->setup == NULL ||
+		    newcon->setup(newcon, NULL) == 0) {
+			newcon->flags |= CON_ENABLED;
+			if (newcon->device) {
+				newcon->flags |= CON_CONSDEV;
 				preferred_console = 0;
 			}
 		}
@@ -1178,64 +1224,62 @@ void register_console(struct console *console)
 	 */
 	for (i = 0; i < MAX_CMDLINECONSOLES && console_cmdline[i].name[0];
 			i++) {
-		if (strcmp(console_cmdline[i].name, console->name) != 0)
+		if (strcmp(console_cmdline[i].name, newcon->name) != 0)
 			continue;
-		if (console->index >= 0 &&
-		    console->index != console_cmdline[i].index)
+		if (newcon->index >= 0 &&
+		    newcon->index != console_cmdline[i].index)
 			continue;
-		if (console->index < 0)
-			console->index = console_cmdline[i].index;
+		if (newcon->index < 0)
+			newcon->index = console_cmdline[i].index;
 #ifdef CONFIG_A11Y_BRAILLE_CONSOLE
 		if (console_cmdline[i].brl_options) {
-			console->flags |= CON_BRL;
-			braille_register_console(console,
+			newcon->flags |= CON_BRL;
+			braille_register_console(newcon,
 					console_cmdline[i].index,
 					console_cmdline[i].options,
 					console_cmdline[i].brl_options);
 			return;
 		}
 #endif
-		if (console->setup &&
-		    console->setup(console, console_cmdline[i].options) != 0)
+		if (newcon->setup &&
+		    newcon->setup(newcon, console_cmdline[i].options) != 0)
 			break;
-		console->flags |= CON_ENABLED;
-		console->index = console_cmdline[i].index;
+		newcon->flags |= CON_ENABLED;
+		newcon->index = console_cmdline[i].index;
 		if (i == selected_console) {
-			console->flags |= CON_CONSDEV;
+			newcon->flags |= CON_CONSDEV;
 			preferred_console = selected_console;
 		}
 		break;
 	}
 
-	if (!(console->flags & CON_ENABLED))
+	if (!(newcon->flags & CON_ENABLED))
 		return;
 
-	if (bootconsole && (console->flags & CON_CONSDEV)) {
-		printk(KERN_INFO "console handover: boot [%s%d] -> real [%s%d]\n",
-		       bootconsole->name, bootconsole->index,
-		       console->name, console->index);
-		unregister_console(bootconsole);
-		console->flags &= ~CON_PRINTBUFFER;
-	} else {
-		printk(KERN_INFO "console [%s%d] enabled\n",
-		       console->name, console->index);
-	}
+	/*
+	 * If we have a bootconsole, and are switching to a real console,
+	 * don't print everything out again, since when the boot console, and
+	 * the real console are the same physical device, it's annoying to
+	 * see the beginning boot messages twice
+	 */
+	if (bcon && ((newcon->flags & (CON_CONSDEV | CON_BOOT)) == CON_CONSDEV))
+		newcon->flags &= ~CON_PRINTBUFFER;
 
 	/*
 	 *	Put this console in the list - keep the
 	 *	preferred driver at the head of the list.
 	 */
 	acquire_console_sem();
-	if ((console->flags & CON_CONSDEV) || console_drivers == NULL) {
-		console->next = console_drivers;
-		console_drivers = console;
-		if (console->next)
-			console->next->flags &= ~CON_CONSDEV;
+	if ((newcon->flags & CON_CONSDEV) || console_drivers == NULL) {
+		newcon->next = console_drivers;
+		console_drivers = newcon;
+		if (newcon->next)
+			newcon->next->flags &= ~CON_CONSDEV;
 	} else {
-		console->next = console_drivers->next;
-		console_drivers->next = console;
+		newcon->next = console_drivers->next;
+		console_drivers->next = newcon;
 	}
-	if (console->flags & CON_PRINTBUFFER) {
+	if (newcon->flags & CON_PRINTBUFFER) {
 		/*
 		 * release_console_sem() will print out the buffered messages
 		 * for us.
@@ -1245,6 +1289,28 @@ void register_console(struct console *console)
 		spin_unlock_irqrestore(&logbuf_lock, flags);
 	}
 	release_console_sem();
+
+	/*
+	 * By unregistering the bootconsoles after we enable the real console
+	 * we get the "console xxx enabled" message on all the consoles -
+	 * boot consoles, real consoles, etc - this is to ensure that end
+	 * users know there might be something in the kernel's log buffer that
+	 * went to the bootconsole (that they do not see on the real console)
+	 */
+	if (bcon && ((newcon->flags & (CON_CONSDEV | CON_BOOT)) == CON_CONSDEV)) {
+		/* we need to iterate through twice, to make sure we print
+		 * everything out, before we unregister the console(s)
+		 */
+		printk(KERN_INFO "console [%s%d] enabled, bootconsole disabled\n",
+			newcon->name, newcon->index);
+		for_each_console(bcon)
+			if (bcon->flags & CON_BOOT)
+				unregister_console(bcon);
+	} else {
+		printk(KERN_INFO "%sconsole [%s%d] enabled\n",
+			(newcon->flags & CON_BOOT) ? "boot" : "" ,
+			newcon->name, newcon->index);
+	}
 }
 EXPORT_SYMBOL(register_console);
 
@@ -1287,11 +1353,13 @@ EXPORT_SYMBOL(unregister_console);
 
 static int __init disable_boot_consoles(void)
 {
-	if (console_drivers != NULL) {
-		if (console_drivers->flags & CON_BOOT) {
+	struct console *con;
+
+	for_each_console(con) {
+		if (con->flags & CON_BOOT) {
 			printk(KERN_INFO "turn off boot console %s%d\n",
-				console_drivers->name, console_drivers->index);
-			return unregister_console(console_drivers);
+				con->name, con->index);
+			unregister_console(con);
 		}
 	}
 	return 0;
diff --git a/kernel/profile.c b/kernel/profile.c
index 419250ebec4d..a55d3a367ae8 100644
--- a/kernel/profile.c
+++ b/kernel/profile.c
@@ -442,48 +442,51 @@ void profile_tick(int type)
 
 #ifdef CONFIG_PROC_FS
 #include <linux/proc_fs.h>
+#include <linux/seq_file.h>
 #include <asm/uaccess.h>
 
-static int prof_cpu_mask_read_proc(char *page, char **start, off_t off,
-			int count, int *eof, void *data)
+static int prof_cpu_mask_proc_show(struct seq_file *m, void *v)
 {
-	int len = cpumask_scnprintf(page, count, data);
-	if (count - len < 2)
-		return -EINVAL;
-	len += sprintf(page + len, "\n");
-	return len;
+	seq_cpumask(m, prof_cpu_mask);
+	seq_putc(m, '\n');
+	return 0;
 }
 
-static int prof_cpu_mask_write_proc(struct file *file,
-	const char __user *buffer,  unsigned long count, void *data)
+static int prof_cpu_mask_proc_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, prof_cpu_mask_proc_show, NULL);
+}
+
+static ssize_t prof_cpu_mask_proc_write(struct file *file,
+	const char __user *buffer, size_t count, loff_t *pos)
 {
-	struct cpumask *mask = data;
-	unsigned long full_count = count, err;
 	cpumask_var_t new_value;
+	int err;
 
 	if (!alloc_cpumask_var(&new_value, GFP_KERNEL))
 		return -ENOMEM;
 
 	err = cpumask_parse_user(buffer, count, new_value);
 	if (!err) {
-		cpumask_copy(mask, new_value);
-		err = full_count;
+		cpumask_copy(prof_cpu_mask, new_value);
+		err = count;
 	}
 	free_cpumask_var(new_value);
 	return err;
 }
 
+static const struct file_operations prof_cpu_mask_proc_fops = {
+	.open		= prof_cpu_mask_proc_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+	.write		= prof_cpu_mask_proc_write,
+};
+
 void create_prof_cpu_mask(struct proc_dir_entry *root_irq_dir)
 {
-	struct proc_dir_entry *entry;
-
 	/* create /proc/irq/prof_cpu_mask */
-	entry = create_proc_entry("prof_cpu_mask", 0600, root_irq_dir);
-	if (!entry)
-		return;
-	entry->data = prof_cpu_mask;
-	entry->read_proc = prof_cpu_mask_read_proc;
-	entry->write_proc = prof_cpu_mask_write_proc;
+	proc_create("prof_cpu_mask", 0600, root_irq_dir, &prof_cpu_mask_proc_fops);
 }
 
 /*
diff --git a/kernel/ptrace.c b/kernel/ptrace.c
index 082c320e4dbf..23bd09cd042e 100644
--- a/kernel/ptrace.c
+++ b/kernel/ptrace.c
@@ -152,7 +152,7 @@ int __ptrace_may_access(struct task_struct *task, unsigned int mode)
 	if (!dumpable && !capable(CAP_SYS_PTRACE))
 		return -EPERM;
 
-	return security_ptrace_may_access(task, mode);
+	return security_ptrace_access_check(task, mode);
 }
 
 bool ptrace_may_access(struct task_struct *task, unsigned int mode)
@@ -266,9 +266,10 @@ static int ignoring_children(struct sighand_struct *sigh)
  * 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.
+ * 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, in that case we must also wake up sub-threads sleeping in
+ * do_wait().
  */
 static bool __ptrace_detach(struct task_struct *tracer, struct task_struct *p)
 {
@@ -278,8 +279,10 @@ static bool __ptrace_detach(struct task_struct *tracer, struct task_struct *p)
 		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))
+			else if (ignoring_children(tracer->sighand)) {
+				__wake_up_parent(p, tracer);
 				p->exit_signal = -1;
+			}
 		}
 		if (task_detached(p)) {
 			/* Mark it as in the process of being reaped. */
diff --git a/kernel/rcuclassic.c b/kernel/rcuclassic.c
deleted file mode 100644
index 0f2b0b311304..000000000000
--- a/kernel/rcuclassic.c
+++ /dev/null
@@ -1,807 +0,0 @@
-/*
- * Read-Copy Update mechanism for mutual exclusion
- *
- * 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 IBM Corporation, 2001
- *
- * Authors: Dipankar Sarma <dipankar@in.ibm.com>
- *	    Manfred Spraul <manfred@colorfullife.com>
- *
- * Based on the original work by Paul McKenney <paulmck@us.ibm.com>
- * and inputs from Rusty Russell, Andrea Arcangeli and Andi Kleen.
- * Papers:
- * http://www.rdrop.com/users/paulmck/paper/rclockpdcsproof.pdf
- * http://lse.sourceforge.net/locking/rclock_OLS.2001.05.01c.sc.pdf (OLS2001)
- *
- * For detailed explanation of Read-Copy Update mechanism see -
- * 		Documentation/RCU
- *
- */
-#include <linux/types.h>
-#include <linux/kernel.h>
-#include <linux/init.h>
-#include <linux/spinlock.h>
-#include <linux/smp.h>
-#include <linux/rcupdate.h>
-#include <linux/interrupt.h>
-#include <linux/sched.h>
-#include <asm/atomic.h>
-#include <linux/bitops.h>
-#include <linux/module.h>
-#include <linux/completion.h>
-#include <linux/moduleparam.h>
-#include <linux/percpu.h>
-#include <linux/notifier.h>
-#include <linux/cpu.h>
-#include <linux/mutex.h>
-#include <linux/time.h>
-
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
-static struct lock_class_key rcu_lock_key;
-struct lockdep_map rcu_lock_map =
-	STATIC_LOCKDEP_MAP_INIT("rcu_read_lock", &rcu_lock_key);
-EXPORT_SYMBOL_GPL(rcu_lock_map);
-#endif
-
-
-/* Definition for rcupdate control block. */
-static struct rcu_ctrlblk rcu_ctrlblk = {
-	.cur = -300,
-	.completed = -300,
-	.pending = -300,
-	.lock = __SPIN_LOCK_UNLOCKED(&rcu_ctrlblk.lock),
-	.cpumask = CPU_BITS_NONE,
-};
-
-static struct rcu_ctrlblk rcu_bh_ctrlblk = {
-	.cur = -300,
-	.completed = -300,
-	.pending = -300,
-	.lock = __SPIN_LOCK_UNLOCKED(&rcu_bh_ctrlblk.lock),
-	.cpumask = CPU_BITS_NONE,
-};
-
-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;
-static int qlowmark = 100;
-
-#ifdef CONFIG_SMP
-static void force_quiescent_state(struct rcu_data *rdp,
-			struct rcu_ctrlblk *rcp)
-{
-	int cpu;
-	unsigned long flags;
-
-	set_need_resched();
-	spin_lock_irqsave(&rcp->lock, flags);
-	if (unlikely(!rcp->signaled)) {
-		rcp->signaled = 1;
-		/*
-		 * Don't send IPI to itself. With irqs disabled,
-		 * rdp->cpu is the current cpu.
-		 *
-		 * cpu_online_mask is updated by the _cpu_down()
-		 * using __stop_machine(). Since we're in irqs disabled
-		 * section, __stop_machine() is not exectuting, hence
-		 * the cpu_online_mask is stable.
-		 *
-		 * However,  a cpu might have been offlined _just_ before
-		 * we disabled irqs while entering here.
-		 * And rcu subsystem might not yet have handled the CPU_DEAD
-		 * notification, leading to the offlined cpu's bit
-		 * being set in the rcp->cpumask.
-		 *
-		 * Hence cpumask = (rcp->cpumask & cpu_online_mask) to prevent
-		 * sending smp_reschedule() to an offlined CPU.
-		 */
-		for_each_cpu_and(cpu,
-				  to_cpumask(rcp->cpumask), cpu_online_mask) {
-			if (cpu != rdp->cpu)
-				smp_send_reschedule(cpu);
-		}
-	}
-	spin_unlock_irqrestore(&rcp->lock, flags);
-}
-#else
-static inline void force_quiescent_state(struct rcu_data *rdp,
-			struct rcu_ctrlblk *rcp)
-{
-	set_need_resched();
-}
-#endif
-
-static void __call_rcu(struct rcu_head *head, struct rcu_ctrlblk *rcp,
-		struct rcu_data *rdp)
-{
-	long batch;
-
-	head->next = NULL;
-	smp_mb(); /* Read of rcu->cur must happen after any change by caller. */
-
-	/*
-	 * Determine the batch number of this callback.
-	 *
-	 * Using ACCESS_ONCE to avoid the following error when gcc eliminates
-	 * local variable "batch" and emits codes like this:
-	 *	1) rdp->batch = rcp->cur + 1 # gets old value
-	 *	......
-	 *	2)rcu_batch_after(rcp->cur + 1, rdp->batch) # gets new value
-	 * then [*nxttail[0], *nxttail[1]) may contain callbacks
-	 * that batch# = rdp->batch, see the comment of struct rcu_data.
-	 */
-	batch = ACCESS_ONCE(rcp->cur) + 1;
-
-	if (rdp->nxtlist && rcu_batch_after(batch, rdp->batch)) {
-		/* process callbacks */
-		rdp->nxttail[0] = rdp->nxttail[1];
-		rdp->nxttail[1] = rdp->nxttail[2];
-		if (rcu_batch_after(batch - 1, rdp->batch))
-			rdp->nxttail[0] = rdp->nxttail[2];
-	}
-
-	rdp->batch = batch;
-	*rdp->nxttail[2] = head;
-	rdp->nxttail[2] = &head->next;
-
-	if (unlikely(++rdp->qlen > qhimark)) {
-		rdp->blimit = INT_MAX;
-		force_quiescent_state(rdp, &rcu_ctrlblk);
-	}
-}
-
-#ifdef CONFIG_RCU_CPU_STALL_DETECTOR
-
-static void record_gp_stall_check_time(struct rcu_ctrlblk *rcp)
-{
-	rcp->gp_start = jiffies;
-	rcp->jiffies_stall = jiffies + RCU_SECONDS_TILL_STALL_CHECK;
-}
-
-static void print_other_cpu_stall(struct rcu_ctrlblk *rcp)
-{
-	int cpu;
-	long delta;
-	unsigned long flags;
-
-	/* Only let one CPU complain about others per time interval. */
-
-	spin_lock_irqsave(&rcp->lock, flags);
-	delta = jiffies - rcp->jiffies_stall;
-	if (delta < 2 || rcp->cur != rcp->completed) {
-		spin_unlock_irqrestore(&rcp->lock, flags);
-		return;
-	}
-	rcp->jiffies_stall = jiffies + RCU_SECONDS_TILL_STALL_RECHECK;
-	spin_unlock_irqrestore(&rcp->lock, flags);
-
-	/* OK, time to rat on our buddy... */
-
-	printk(KERN_ERR "INFO: RCU detected CPU stalls:");
-	for_each_possible_cpu(cpu) {
-		if (cpumask_test_cpu(cpu, to_cpumask(rcp->cpumask)))
-			printk(" %d", cpu);
-	}
-	printk(" (detected by %d, t=%ld jiffies)\n",
-	       smp_processor_id(), (long)(jiffies - rcp->gp_start));
-}
-
-static void print_cpu_stall(struct rcu_ctrlblk *rcp)
-{
-	unsigned long flags;
-
-	printk(KERN_ERR "INFO: RCU detected CPU %d stall (t=%lu/%lu jiffies)\n",
-			smp_processor_id(), jiffies,
-			jiffies - rcp->gp_start);
-	dump_stack();
-	spin_lock_irqsave(&rcp->lock, flags);
-	if ((long)(jiffies - rcp->jiffies_stall) >= 0)
-		rcp->jiffies_stall =
-			jiffies + RCU_SECONDS_TILL_STALL_RECHECK;
-	spin_unlock_irqrestore(&rcp->lock, flags);
-	set_need_resched();  /* kick ourselves to get things going. */
-}
-
-static void check_cpu_stall(struct rcu_ctrlblk *rcp)
-{
-	long delta;
-
-	delta = jiffies - rcp->jiffies_stall;
-	if (cpumask_test_cpu(smp_processor_id(), to_cpumask(rcp->cpumask)) &&
-		delta >= 0) {
-
-		/* We haven't checked in, so go dump stack. */
-		print_cpu_stall(rcp);
-
-	} else if (rcp->cur != rcp->completed && delta >= 2) {
-
-		/* They had two seconds to dump stack, so complain. */
-		print_other_cpu_stall(rcp);
-	}
-}
-
-#else /* #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */
-
-static void record_gp_stall_check_time(struct rcu_ctrlblk *rcp)
-{
-}
-
-static inline void check_cpu_stall(struct rcu_ctrlblk *rcp)
-{
-}
-
-#endif /* #else #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */
-
-/**
- * call_rcu - Queue an RCU callback for invocation after a grace period.
- * @head: structure to be used for queueing the RCU updates.
- * @func: actual update function to be invoked after the grace period
- *
- * The update function will be invoked some time after a full grace
- * period elapses, in other words after all currently executing RCU
- * read-side critical sections have completed.  RCU read-side critical
- * sections are delimited by rcu_read_lock() and rcu_read_unlock(),
- * and may be nested.
- */
-void call_rcu(struct rcu_head *head,
-				void (*func)(struct rcu_head *rcu))
-{
-	unsigned long flags;
-
-	head->func = func;
-	local_irq_save(flags);
-	__call_rcu(head, &rcu_ctrlblk, &__get_cpu_var(rcu_data));
-	local_irq_restore(flags);
-}
-EXPORT_SYMBOL_GPL(call_rcu);
-
-/**
- * call_rcu_bh - Queue an RCU for invocation after a quicker grace period.
- * @head: structure to be used for queueing the RCU updates.
- * @func: actual update function to be invoked after the grace period
- *
- * The update function will be invoked some time after a full grace
- * period elapses, in other words after all currently executing RCU
- * read-side critical sections have completed. call_rcu_bh() assumes
- * that the read-side critical sections end on completion of a softirq
- * handler. This means that read-side critical sections in process
- * context must not be interrupted by softirqs. This interface is to be
- * used when most of the read-side critical sections are in softirq context.
- * RCU read-side critical sections are delimited by rcu_read_lock() and
- * rcu_read_unlock(), * if in interrupt context or rcu_read_lock_bh()
- * and rcu_read_unlock_bh(), if in process context. These may be nested.
- */
-void call_rcu_bh(struct rcu_head *head,
-				void (*func)(struct rcu_head *rcu))
-{
-	unsigned long flags;
-
-	head->func = func;
-	local_irq_save(flags);
-	__call_rcu(head, &rcu_bh_ctrlblk, &__get_cpu_var(rcu_bh_data));
-	local_irq_restore(flags);
-}
-EXPORT_SYMBOL_GPL(call_rcu_bh);
-
-/*
- * Return the number of RCU batches processed thus far.  Useful
- * for debug and statistics.
- */
-long rcu_batches_completed(void)
-{
-	return rcu_ctrlblk.completed;
-}
-EXPORT_SYMBOL_GPL(rcu_batches_completed);
-
-/*
- * Return the number of RCU batches processed thus far.  Useful
- * for debug and statistics.
- */
-long rcu_batches_completed_bh(void)
-{
-	return rcu_bh_ctrlblk.completed;
-}
-EXPORT_SYMBOL_GPL(rcu_batches_completed_bh);
-
-/* Raises the softirq for processing rcu_callbacks. */
-static inline void raise_rcu_softirq(void)
-{
-	raise_softirq(RCU_SOFTIRQ);
-}
-
-/*
- * Invoke the completed RCU callbacks. They are expected to be in
- * a per-cpu list.
- */
-static void rcu_do_batch(struct rcu_data *rdp)
-{
-	unsigned long flags;
-	struct rcu_head *next, *list;
-	int count = 0;
-
-	list = rdp->donelist;
-	while (list) {
-		next = list->next;
-		prefetch(next);
-		list->func(list);
-		list = next;
-		if (++count >= rdp->blimit)
-			break;
-	}
-	rdp->donelist = list;
-
-	local_irq_save(flags);
-	rdp->qlen -= count;
-	local_irq_restore(flags);
-	if (rdp->blimit == INT_MAX && rdp->qlen <= qlowmark)
-		rdp->blimit = blimit;
-
-	if (!rdp->donelist)
-		rdp->donetail = &rdp->donelist;
-	else
-		raise_rcu_softirq();
-}
-
-/*
- * Grace period handling:
- * The grace period handling consists out of two steps:
- * - A new grace period is started.
- *   This is done by rcu_start_batch. The start is not broadcasted to
- *   all cpus, they must pick this up by comparing rcp->cur with
- *   rdp->quiescbatch. All cpus are recorded  in the
- *   rcu_ctrlblk.cpumask bitmap.
- * - All cpus must go through a quiescent state.
- *   Since the start of the grace period is not broadcasted, at least two
- *   calls to rcu_check_quiescent_state are required:
- *   The first call just notices that a new grace period is running. The
- *   following calls check if there was a quiescent state since the beginning
- *   of the grace period. If so, it updates rcu_ctrlblk.cpumask. If
- *   the bitmap is empty, then the grace period is completed.
- *   rcu_check_quiescent_state calls rcu_start_batch(0) to start the next grace
- *   period (if necessary).
- */
-
-/*
- * Register a new batch of callbacks, and start it up if there is currently no
- * active batch and the batch to be registered has not already occurred.
- * Caller must hold rcu_ctrlblk.lock.
- */
-static void rcu_start_batch(struct rcu_ctrlblk *rcp)
-{
-	if (rcp->cur != rcp->pending &&
-			rcp->completed == rcp->cur) {
-		rcp->cur++;
-		record_gp_stall_check_time(rcp);
-
-		/*
-		 * Accessing nohz_cpu_mask before incrementing rcp->cur needs a
-		 * Barrier  Otherwise it can cause tickless idle CPUs to be
-		 * included in rcp->cpumask, which will extend graceperiods
-		 * unnecessarily.
-		 */
-		smp_mb();
-		cpumask_andnot(to_cpumask(rcp->cpumask),
-			       cpu_online_mask, nohz_cpu_mask);
-
-		rcp->signaled = 0;
-	}
-}
-
-/*
- * cpu went through a quiescent state since the beginning of the grace period.
- * Clear it from the cpu mask and complete the grace period if it was the last
- * cpu. Start another grace period if someone has further entries pending
- */
-static void cpu_quiet(int cpu, struct rcu_ctrlblk *rcp)
-{
-	cpumask_clear_cpu(cpu, to_cpumask(rcp->cpumask));
-	if (cpumask_empty(to_cpumask(rcp->cpumask))) {
-		/* batch completed ! */
-		rcp->completed = rcp->cur;
-		rcu_start_batch(rcp);
-	}
-}
-
-/*
- * Check if the cpu has gone through a quiescent state (say context
- * switch). If so and if it already hasn't done so in this RCU
- * quiescent cycle, then indicate that it has done so.
- */
-static void rcu_check_quiescent_state(struct rcu_ctrlblk *rcp,
-					struct rcu_data *rdp)
-{
-	unsigned long flags;
-
-	if (rdp->quiescbatch != rcp->cur) {
-		/* start new grace period: */
-		rdp->qs_pending = 1;
-		rdp->passed_quiesc = 0;
-		rdp->quiescbatch = rcp->cur;
-		return;
-	}
-
-	/* Grace period already completed for this cpu?
-	 * qs_pending is checked instead of the actual bitmap to avoid
-	 * cacheline trashing.
-	 */
-	if (!rdp->qs_pending)
-		return;
-
-	/*
-	 * Was there a quiescent state since the beginning of the grace
-	 * period? If no, then exit and wait for the next call.
-	 */
-	if (!rdp->passed_quiesc)
-		return;
-	rdp->qs_pending = 0;
-
-	spin_lock_irqsave(&rcp->lock, flags);
-	/*
-	 * rdp->quiescbatch/rcp->cur and the cpu bitmap can come out of sync
-	 * during cpu startup. Ignore the quiescent state.
-	 */
-	if (likely(rdp->quiescbatch == rcp->cur))
-		cpu_quiet(rdp->cpu, rcp);
-
-	spin_unlock_irqrestore(&rcp->lock, flags);
-}
-
-
-#ifdef CONFIG_HOTPLUG_CPU
-
-/* warning! helper for rcu_offline_cpu. do not use elsewhere without reviewing
- * locking requirements, the list it's pulling from has to belong to a cpu
- * which is dead and hence not processing interrupts.
- */
-static void rcu_move_batch(struct rcu_data *this_rdp, struct rcu_head *list,
-				struct rcu_head **tail, long batch)
-{
-	unsigned long flags;
-
-	if (list) {
-		local_irq_save(flags);
-		this_rdp->batch = batch;
-		*this_rdp->nxttail[2] = list;
-		this_rdp->nxttail[2] = tail;
-		local_irq_restore(flags);
-	}
-}
-
-static void __rcu_offline_cpu(struct rcu_data *this_rdp,
-				struct rcu_ctrlblk *rcp, struct rcu_data *rdp)
-{
-	unsigned long flags;
-
-	/*
-	 * if the cpu going offline owns the grace period
-	 * we can block indefinitely waiting for it, so flush
-	 * it here
-	 */
-	spin_lock_irqsave(&rcp->lock, flags);
-	if (rcp->cur != rcp->completed)
-		cpu_quiet(rdp->cpu, rcp);
-	rcu_move_batch(this_rdp, rdp->donelist, rdp->donetail, rcp->cur + 1);
-	rcu_move_batch(this_rdp, rdp->nxtlist, rdp->nxttail[2], rcp->cur + 1);
-	spin_unlock(&rcp->lock);
-
-	this_rdp->qlen += rdp->qlen;
-	local_irq_restore(flags);
-}
-
-static void rcu_offline_cpu(int cpu)
-{
-	struct rcu_data *this_rdp = &get_cpu_var(rcu_data);
-	struct rcu_data *this_bh_rdp = &get_cpu_var(rcu_bh_data);
-
-	__rcu_offline_cpu(this_rdp, &rcu_ctrlblk,
-					&per_cpu(rcu_data, cpu));
-	__rcu_offline_cpu(this_bh_rdp, &rcu_bh_ctrlblk,
-					&per_cpu(rcu_bh_data, cpu));
-	put_cpu_var(rcu_data);
-	put_cpu_var(rcu_bh_data);
-}
-
-#else
-
-static void rcu_offline_cpu(int cpu)
-{
-}
-
-#endif
-
-/*
- * This does the RCU processing work from softirq context.
- */
-static void __rcu_process_callbacks(struct rcu_ctrlblk *rcp,
-					struct rcu_data *rdp)
-{
-	unsigned long flags;
-	long completed_snap;
-
-	if (rdp->nxtlist) {
-		local_irq_save(flags);
-		completed_snap = ACCESS_ONCE(rcp->completed);
-
-		/*
-		 * move the other grace-period-completed entries to
-		 * [rdp->nxtlist, *rdp->nxttail[0]) temporarily
-		 */
-		if (!rcu_batch_before(completed_snap, rdp->batch))
-			rdp->nxttail[0] = rdp->nxttail[1] = rdp->nxttail[2];
-		else if (!rcu_batch_before(completed_snap, rdp->batch - 1))
-			rdp->nxttail[0] = rdp->nxttail[1];
-
-		/*
-		 * the grace period for entries in
-		 * [rdp->nxtlist, *rdp->nxttail[0]) has completed and
-		 * move these entries to donelist
-		 */
-		if (rdp->nxttail[0] != &rdp->nxtlist) {
-			*rdp->donetail = rdp->nxtlist;
-			rdp->donetail = rdp->nxttail[0];
-			rdp->nxtlist = *rdp->nxttail[0];
-			*rdp->donetail = NULL;
-
-			if (rdp->nxttail[1] == rdp->nxttail[0])
-				rdp->nxttail[1] = &rdp->nxtlist;
-			if (rdp->nxttail[2] == rdp->nxttail[0])
-				rdp->nxttail[2] = &rdp->nxtlist;
-			rdp->nxttail[0] = &rdp->nxtlist;
-		}
-
-		local_irq_restore(flags);
-
-		if (rcu_batch_after(rdp->batch, rcp->pending)) {
-			unsigned long flags2;
-
-			/* and start it/schedule start if it's a new batch */
-			spin_lock_irqsave(&rcp->lock, flags2);
-			if (rcu_batch_after(rdp->batch, rcp->pending)) {
-				rcp->pending = rdp->batch;
-				rcu_start_batch(rcp);
-			}
-			spin_unlock_irqrestore(&rcp->lock, flags2);
-		}
-	}
-
-	rcu_check_quiescent_state(rcp, rdp);
-	if (rdp->donelist)
-		rcu_do_batch(rdp);
-}
-
-static void rcu_process_callbacks(struct softirq_action *unused)
-{
-	/*
-	 * Memory references from any prior RCU read-side critical sections
-	 * executed by the interrupted code must be see before any RCU
-	 * grace-period manupulations below.
-	 */
-
-	smp_mb(); /* See above block comment. */
-
-	__rcu_process_callbacks(&rcu_ctrlblk, &__get_cpu_var(rcu_data));
-	__rcu_process_callbacks(&rcu_bh_ctrlblk, &__get_cpu_var(rcu_bh_data));
-
-	/*
-	 * Memory references from any later RCU read-side critical sections
-	 * executed by the interrupted code must be see after any RCU
-	 * grace-period manupulations above.
-	 */
-
-	smp_mb(); /* See above block comment. */
-}
-
-static int __rcu_pending(struct rcu_ctrlblk *rcp, struct rcu_data *rdp)
-{
-	/* Check for CPU stalls, if enabled. */
-	check_cpu_stall(rcp);
-
-	if (rdp->nxtlist) {
-		long completed_snap = ACCESS_ONCE(rcp->completed);
-
-		/*
-		 * This cpu has pending rcu entries and the grace period
-		 * for them has completed.
-		 */
-		if (!rcu_batch_before(completed_snap, rdp->batch))
-			return 1;
-		if (!rcu_batch_before(completed_snap, rdp->batch - 1) &&
-				rdp->nxttail[0] != rdp->nxttail[1])
-			return 1;
-		if (rdp->nxttail[0] != &rdp->nxtlist)
-			return 1;
-
-		/*
-		 * This cpu has pending rcu entries and the new batch
-		 * for then hasn't been started nor scheduled start
-		 */
-		if (rcu_batch_after(rdp->batch, rcp->pending))
-			return 1;
-	}
-
-	/* This cpu has finished callbacks to invoke */
-	if (rdp->donelist)
-		return 1;
-
-	/* The rcu core waits for a quiescent state from the cpu */
-	if (rdp->quiescbatch != rcp->cur || rdp->qs_pending)
-		return 1;
-
-	/* nothing to do */
-	return 0;
-}
-
-/*
- * Check to see if there is any immediate RCU-related work to be done
- * by the current CPU, returning 1 if so.  This function is part of the
- * RCU implementation; it is -not- an exported member of the RCU API.
- */
-int rcu_pending(int cpu)
-{
-	return __rcu_pending(&rcu_ctrlblk, &per_cpu(rcu_data, cpu)) ||
-		__rcu_pending(&rcu_bh_ctrlblk, &per_cpu(rcu_bh_data, cpu));
-}
-
-/*
- * Check to see if any future RCU-related work will need to be done
- * by the current CPU, even if none need be done immediately, returning
- * 1 if so.  This function is part of the RCU implementation; it is -not-
- * an exported member of the RCU API.
- */
-int rcu_needs_cpu(int cpu)
-{
-	struct rcu_data *rdp = &per_cpu(rcu_data, cpu);
-	struct rcu_data *rdp_bh = &per_cpu(rcu_bh_data, cpu);
-
-	return !!rdp->nxtlist || !!rdp_bh->nxtlist || rcu_pending(cpu);
-}
-
-/*
- * Top-level function driving RCU grace-period detection, normally
- * invoked from the scheduler-clock interrupt.  This function simply
- * increments counters that are read only from softirq by this same
- * CPU, so there are no memory barriers required.
- */
-void rcu_check_callbacks(int cpu, int user)
-{
-	if (user ||
-	    (idle_cpu(cpu) && rcu_scheduler_active &&
-	     !in_softirq() && hardirq_count() <= (1 << HARDIRQ_SHIFT))) {
-
-		/*
-		 * Get here if this CPU took its interrupt from user
-		 * mode or from the idle loop, and if this is not a
-		 * nested interrupt.  In this case, the CPU is in
-		 * a quiescent state, so count it.
-		 *
-		 * Also do a memory barrier.  This is needed to handle
-		 * the case where writes from a preempt-disable section
-		 * of code get reordered into schedule() by this CPU's
-		 * write buffer.  The memory barrier makes sure that
-		 * the rcu_qsctr_inc() and rcu_bh_qsctr_inc() are see
-		 * by other CPUs to happen after any such write.
-		 */
-
-		smp_mb();  /* See above block comment. */
-		rcu_qsctr_inc(cpu);
-		rcu_bh_qsctr_inc(cpu);
-
-	} else if (!in_softirq()) {
-
-		/*
-		 * Get here if this CPU did not take its interrupt from
-		 * softirq, in other words, if it is not interrupting
-		 * a rcu_bh read-side critical section.  This is an _bh
-		 * critical section, so count it.  The memory barrier
-		 * is needed for the same reason as is the above one.
-		 */
-
-		smp_mb();  /* See above block comment. */
-		rcu_bh_qsctr_inc(cpu);
-	}
-	raise_rcu_softirq();
-}
-
-static void __cpuinit rcu_init_percpu_data(int cpu, struct rcu_ctrlblk *rcp,
-						struct rcu_data *rdp)
-{
-	unsigned long flags;
-
-	spin_lock_irqsave(&rcp->lock, flags);
-	memset(rdp, 0, sizeof(*rdp));
-	rdp->nxttail[0] = rdp->nxttail[1] = rdp->nxttail[2] = &rdp->nxtlist;
-	rdp->donetail = &rdp->donelist;
-	rdp->quiescbatch = rcp->completed;
-	rdp->qs_pending = 0;
-	rdp->cpu = cpu;
-	rdp->blimit = blimit;
-	spin_unlock_irqrestore(&rcp->lock, flags);
-}
-
-static void __cpuinit rcu_online_cpu(int cpu)
-{
-	struct rcu_data *rdp = &per_cpu(rcu_data, cpu);
-	struct rcu_data *bh_rdp = &per_cpu(rcu_bh_data, cpu);
-
-	rcu_init_percpu_data(cpu, &rcu_ctrlblk, rdp);
-	rcu_init_percpu_data(cpu, &rcu_bh_ctrlblk, bh_rdp);
-	open_softirq(RCU_SOFTIRQ, rcu_process_callbacks);
-}
-
-static int __cpuinit rcu_cpu_notify(struct notifier_block *self,
-				unsigned long action, void *hcpu)
-{
-	long cpu = (long)hcpu;
-
-	switch (action) {
-	case CPU_UP_PREPARE:
-	case CPU_UP_PREPARE_FROZEN:
-		rcu_online_cpu(cpu);
-		break;
-	case CPU_DEAD:
-	case CPU_DEAD_FROZEN:
-		rcu_offline_cpu(cpu);
-		break;
-	default:
-		break;
-	}
-	return NOTIFY_OK;
-}
-
-static struct notifier_block __cpuinitdata rcu_nb = {
-	.notifier_call	= rcu_cpu_notify,
-};
-
-/*
- * Initializes rcu mechanism.  Assumed to be called early.
- * That is before local timer(SMP) or jiffie timer (uniproc) is setup.
- * Note that rcu_qsctr and friends are implicitly
- * initialized due to the choice of ``0'' for RCU_CTR_INVALID.
- */
-void __init __rcu_init(void)
-{
-#ifdef CONFIG_RCU_CPU_STALL_DETECTOR
-	printk(KERN_INFO "RCU-based detection of stalled CPUs is enabled.\n");
-#endif /* #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */
-	rcu_cpu_notify(&rcu_nb, CPU_UP_PREPARE,
-			(void *)(long)smp_processor_id());
-	/* Register notifier for non-boot CPUs */
-	register_cpu_notifier(&rcu_nb);
-}
-
-module_param(blimit, int, 0);
-module_param(qhimark, int, 0);
-module_param(qlowmark, int, 0);
diff --git a/kernel/rcupdate.c b/kernel/rcupdate.c
index a967c9feb90a..400183346ad2 100644
--- a/kernel/rcupdate.c
+++ b/kernel/rcupdate.c
@@ -19,7 +19,7 @@
  *
  * Authors: Dipankar Sarma <dipankar@in.ibm.com>
  *	    Manfred Spraul <manfred@colorfullife.com>
- * 
+ *
  * Based on the original work by Paul McKenney <paulmck@us.ibm.com>
  * and inputs from Rusty Russell, Andrea Arcangeli and Andi Kleen.
  * Papers:
@@ -27,7 +27,7 @@
  * http://lse.sourceforge.net/locking/rclock_OLS.2001.05.01c.sc.pdf (OLS2001)
  *
  * For detailed explanation of Read-Copy Update mechanism see -
- * 		http://lse.sourceforge.net/locking/rcupdate.html
+ *		http://lse.sourceforge.net/locking/rcupdate.html
  *
  */
 #include <linux/types.h>
@@ -46,22 +46,15 @@
 #include <linux/module.h>
 #include <linux/kernel_stat.h>
 
-enum rcu_barrier {
-	RCU_BARRIER_STD,
-	RCU_BARRIER_BH,
-	RCU_BARRIER_SCHED,
-};
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+static struct lock_class_key rcu_lock_key;
+struct lockdep_map rcu_lock_map =
+	STATIC_LOCKDEP_MAP_INIT("rcu_read_lock", &rcu_lock_key);
+EXPORT_SYMBOL_GPL(rcu_lock_map);
+#endif
 
-static DEFINE_PER_CPU(struct rcu_head, rcu_barrier_head) = {NULL};
-static atomic_t rcu_barrier_cpu_count;
-static DEFINE_MUTEX(rcu_barrier_mutex);
-static struct completion rcu_barrier_completion;
 int rcu_scheduler_active __read_mostly;
 
-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);
-
 /*
  * Awaken the corresponding synchronize_rcu() instance now that a
  * grace period has elapsed.
@@ -74,6 +67,8 @@ void wakeme_after_rcu(struct rcu_head  *head)
 	complete(&rcu->completion);
 }
 
+#ifdef CONFIG_TREE_PREEMPT_RCU
+
 /**
  * synchronize_rcu - wait until a grace period has elapsed.
  *
@@ -87,7 +82,7 @@ void synchronize_rcu(void)
 {
 	struct rcu_synchronize rcu;
 
-	if (rcu_blocking_is_gp())
+	if (!rcu_scheduler_active)
 		return;
 
 	init_completion(&rcu.completion);
@@ -98,129 +93,90 @@ void synchronize_rcu(void)
 }
 EXPORT_SYMBOL_GPL(synchronize_rcu);
 
-static void rcu_barrier_callback(struct rcu_head *notused)
-{
-	if (atomic_dec_and_test(&rcu_barrier_cpu_count))
-		complete(&rcu_barrier_completion);
-}
+#endif /* #ifdef CONFIG_TREE_PREEMPT_RCU */
 
-/*
- * Called with preemption disabled, and from cross-cpu IRQ context.
+/**
+ * synchronize_sched - wait until an rcu-sched grace period has elapsed.
+ *
+ * Control will return to the caller some time after a full rcu-sched
+ * grace period has elapsed, in other words after all currently executing
+ * rcu-sched read-side critical sections have completed.   These read-side
+ * critical sections are delimited by rcu_read_lock_sched() and
+ * rcu_read_unlock_sched(), and may be nested.  Note that preempt_disable(),
+ * local_irq_disable(), and so on may be used in place of
+ * rcu_read_lock_sched().
+ *
+ * This means that all preempt_disable code sequences, including NMI and
+ * hardware-interrupt handlers, in progress on entry will have completed
+ * before this primitive returns.  However, this does not guarantee that
+ * softirq handlers will have completed, since in some kernels, these
+ * handlers can run in process context, and can block.
+ *
+ * This primitive provides the guarantees made by the (now removed)
+ * synchronize_kernel() API.  In contrast, synchronize_rcu() only
+ * guarantees that rcu_read_lock() sections will have completed.
+ * In "classic RCU", these two guarantees happen to be one and
+ * the same, but can differ in realtime RCU implementations.
  */
-static void rcu_barrier_func(void *type)
-{
-	int cpu = smp_processor_id();
-	struct rcu_head *head = &per_cpu(rcu_barrier_head, cpu);
-
-	atomic_inc(&rcu_barrier_cpu_count);
-	switch ((enum rcu_barrier)type) {
-	case RCU_BARRIER_STD:
-		call_rcu(head, rcu_barrier_callback);
-		break;
-	case RCU_BARRIER_BH:
-		call_rcu_bh(head, rcu_barrier_callback);
-		break;
-	case RCU_BARRIER_SCHED:
-		call_rcu_sched(head, rcu_barrier_callback);
-		break;
-	}
-}
-
-static inline void wait_migrated_callbacks(void)
+void synchronize_sched(void)
 {
-	wait_event(rcu_migrate_wq, !atomic_read(&rcu_migrate_type_count));
-}
+	struct rcu_synchronize rcu;
 
-/*
- * Orchestrate the specified type of RCU barrier, waiting for all
- * RCU callbacks of the specified type to complete.
- */
-static void _rcu_barrier(enum rcu_barrier type)
-{
-	BUG_ON(in_interrupt());
-	/* Take cpucontrol mutex to protect against CPU hotplug */
-	mutex_lock(&rcu_barrier_mutex);
-	init_completion(&rcu_barrier_completion);
-	/*
-	 * Initialize rcu_barrier_cpu_count to 1, then invoke
-	 * rcu_barrier_func() on each CPU, so that each CPU also has
-	 * incremented rcu_barrier_cpu_count.  Only then is it safe to
-	 * decrement rcu_barrier_cpu_count -- otherwise the first CPU
-	 * might complete its grace period before all of the other CPUs
-	 * did their increment, causing this function to return too
-	 * early.
-	 */
-	atomic_set(&rcu_barrier_cpu_count, 1);
-	on_each_cpu(rcu_barrier_func, (void *)type, 1);
-	if (atomic_dec_and_test(&rcu_barrier_cpu_count))
-		complete(&rcu_barrier_completion);
-	wait_for_completion(&rcu_barrier_completion);
-	mutex_unlock(&rcu_barrier_mutex);
-	wait_migrated_callbacks();
-}
+	if (rcu_blocking_is_gp())
+		return;
 
-/**
- * rcu_barrier - Wait until all in-flight call_rcu() callbacks complete.
- */
-void rcu_barrier(void)
-{
-	_rcu_barrier(RCU_BARRIER_STD);
+	init_completion(&rcu.completion);
+	/* Will wake me after RCU finished. */
+	call_rcu_sched(&rcu.head, wakeme_after_rcu);
+	/* Wait for it. */
+	wait_for_completion(&rcu.completion);
 }
-EXPORT_SYMBOL_GPL(rcu_barrier);
+EXPORT_SYMBOL_GPL(synchronize_sched);
 
 /**
- * rcu_barrier_bh - Wait until all in-flight call_rcu_bh() callbacks complete.
+ * synchronize_rcu_bh - wait until an rcu_bh grace period has elapsed.
+ *
+ * Control will return to the caller some time after a full rcu_bh grace
+ * period has elapsed, in other words after all currently executing rcu_bh
+ * read-side critical sections have completed.  RCU read-side critical
+ * sections are delimited by rcu_read_lock_bh() and rcu_read_unlock_bh(),
+ * and may be nested.
  */
-void rcu_barrier_bh(void)
+void synchronize_rcu_bh(void)
 {
-	_rcu_barrier(RCU_BARRIER_BH);
-}
-EXPORT_SYMBOL_GPL(rcu_barrier_bh);
+	struct rcu_synchronize rcu;
 
-/**
- * rcu_barrier_sched - Wait for in-flight call_rcu_sched() callbacks.
- */
-void rcu_barrier_sched(void)
-{
-	_rcu_barrier(RCU_BARRIER_SCHED);
-}
-EXPORT_SYMBOL_GPL(rcu_barrier_sched);
+	if (rcu_blocking_is_gp())
+		return;
 
-static void rcu_migrate_callback(struct rcu_head *notused)
-{
-	if (atomic_dec_and_test(&rcu_migrate_type_count))
-		wake_up(&rcu_migrate_wq);
+	init_completion(&rcu.completion);
+	/* Will wake me after RCU finished. */
+	call_rcu_bh(&rcu.head, wakeme_after_rcu);
+	/* Wait for it. */
+	wait_for_completion(&rcu.completion);
 }
+EXPORT_SYMBOL_GPL(synchronize_rcu_bh);
 
 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;
+	return rcu_cpu_notify(self, action, hcpu);
 }
 
 void __init rcu_init(void)
 {
+	int i;
+
 	__rcu_init();
-	hotcpu_notifier(rcu_barrier_cpu_hotplug, 0);
+	cpu_notifier(rcu_barrier_cpu_hotplug, 0);
+
+	/*
+	 * We don't need protection against CPU-hotplug here because
+	 * this is called early in boot, before either interrupts
+	 * or the scheduler are operational.
+	 */
+	for_each_online_cpu(i)
+		rcu_barrier_cpu_hotplug(NULL, CPU_UP_PREPARE, (void *)(long)i);
 }
 
 void rcu_scheduler_starting(void)
diff --git a/kernel/rcupreempt.c b/kernel/rcupreempt.c
deleted file mode 100644
index beb0e659adcc..000000000000
--- a/kernel/rcupreempt.c
+++ /dev/null
@@ -1,1539 +0,0 @@
-/*
- * Read-Copy Update mechanism for mutual exclusion, realtime implementation
- *
- * 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 IBM Corporation, 2006
- *
- * Authors: Paul E. McKenney <paulmck@us.ibm.com>
- *		With thanks to Esben Nielsen, Bill Huey, and Ingo Molnar
- *		for pushing me away from locks and towards counters, and
- *		to Suparna Bhattacharya for pushing me completely away
- *		from atomic instructions on the read side.
- *
- *  - Added handling of Dynamic Ticks
- *      Copyright 2007 - Paul E. Mckenney <paulmck@us.ibm.com>
- *                     - Steven Rostedt <srostedt@redhat.com>
- *
- * Papers:  http://www.rdrop.com/users/paulmck/RCU
- *
- * Design Document: http://lwn.net/Articles/253651/
- *
- * For detailed explanation of Read-Copy Update mechanism see -
- * 		Documentation/RCU/ *.txt
- *
- */
-#include <linux/types.h>
-#include <linux/kernel.h>
-#include <linux/init.h>
-#include <linux/spinlock.h>
-#include <linux/smp.h>
-#include <linux/rcupdate.h>
-#include <linux/interrupt.h>
-#include <linux/sched.h>
-#include <asm/atomic.h>
-#include <linux/bitops.h>
-#include <linux/module.h>
-#include <linux/kthread.h>
-#include <linux/completion.h>
-#include <linux/moduleparam.h>
-#include <linux/percpu.h>
-#include <linux/notifier.h>
-#include <linux/cpu.h>
-#include <linux/random.h>
-#include <linux/delay.h>
-#include <linux/cpumask.h>
-#include <linux/rcupreempt_trace.h>
-#include <asm/byteorder.h>
-
-/*
- * PREEMPT_RCU data structures.
- */
-
-/*
- * GP_STAGES specifies the number of times the state machine has
- * to go through the all the rcu_try_flip_states (see below)
- * in a single Grace Period.
- *
- * GP in GP_STAGES stands for Grace Period ;)
- */
-#define GP_STAGES    2
-struct rcu_data {
-	spinlock_t	lock;		/* Protect rcu_data fields. */
-	long		completed;	/* Number of last completed batch. */
-	int		waitlistcount;
-	struct rcu_head *nextlist;
-	struct rcu_head **nexttail;
-	struct rcu_head *waitlist[GP_STAGES];
-	struct rcu_head **waittail[GP_STAGES];
-	struct rcu_head *donelist;	/* from waitlist & waitschedlist */
-	struct rcu_head **donetail;
-	long rcu_flipctr[2];
-	struct rcu_head *nextschedlist;
-	struct rcu_head **nextschedtail;
-	struct rcu_head *waitschedlist;
-	struct rcu_head **waitschedtail;
-	int rcu_sched_sleeping;
-#ifdef CONFIG_RCU_TRACE
-	struct rcupreempt_trace trace;
-#endif /* #ifdef CONFIG_RCU_TRACE */
-};
-
-/*
- * States for rcu_try_flip() and friends.
- */
-
-enum rcu_try_flip_states {
-
-	/*
-	 * Stay here if nothing is happening. Flip the counter if somthing
-	 * starts happening. Denoted by "I"
-	 */
-	rcu_try_flip_idle_state,
-
-	/*
-	 * Wait here for all CPUs to notice that the counter has flipped. This
-	 * prevents the old set of counters from ever being incremented once
-	 * we leave this state, which in turn is necessary because we cannot
-	 * test any individual counter for zero -- we can only check the sum.
-	 * Denoted by "A".
-	 */
-	rcu_try_flip_waitack_state,
-
-	/*
-	 * Wait here for the sum of the old per-CPU counters to reach zero.
-	 * Denoted by "Z".
-	 */
-	rcu_try_flip_waitzero_state,
-
-	/*
-	 * Wait here for each of the other CPUs to execute a memory barrier.
-	 * This is necessary to ensure that these other CPUs really have
-	 * completed executing their RCU read-side critical sections, despite
-	 * their CPUs wildly reordering memory. Denoted by "M".
-	 */
-	rcu_try_flip_waitmb_state,
-};
-
-/*
- * States for rcu_ctrlblk.rcu_sched_sleep.
- */
-
-enum rcu_sched_sleep_states {
-	rcu_sched_not_sleeping,	/* Not sleeping, callbacks need GP.  */
-	rcu_sched_sleep_prep,	/* Thinking of sleeping, rechecking. */
-	rcu_sched_sleeping,	/* Sleeping, awaken if GP needed. */
-};
-
-struct rcu_ctrlblk {
-	spinlock_t	fliplock;	/* Protect state-machine transitions. */
-	long		completed;	/* Number of last completed batch. */
-	enum rcu_try_flip_states rcu_try_flip_state; /* The current state of
-							the rcu state machine */
-	spinlock_t	schedlock;	/* Protect rcu_sched sleep state. */
-	enum rcu_sched_sleep_states sched_sleep; /* rcu_sched state. */
-	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,
-	.rcu_try_flip_state = rcu_try_flip_idle_state,
-	.schedlock = __SPIN_LOCK_UNLOCKED(rcu_ctrlblk.schedlock),
-	.sched_sleep = rcu_sched_not_sleeping,
-	.sched_wq = __WAIT_QUEUE_HEAD_INITIALIZER(rcu_ctrlblk.sched_wq),
-};
-
-static struct task_struct *rcu_sched_grace_period_task;
-
-#ifdef CONFIG_RCU_TRACE
-static char *rcu_try_flip_state_names[] =
-	{ "idle", "waitack", "waitzero", "waitmb" };
-#endif /* #ifdef CONFIG_RCU_TRACE */
-
-static DECLARE_BITMAP(rcu_cpu_online_map, NR_CPUS) __read_mostly
-	= CPU_BITS_NONE;
-
-/*
- * Enum and per-CPU flag to determine when each CPU has seen
- * the most recent counter flip.
- */
-
-enum rcu_flip_flag_values {
-	rcu_flip_seen,		/* Steady/initial state, last flip seen. */
-				/* Only GP detector can update. */
-	rcu_flipped		/* Flip just completed, need confirmation. */
-				/* Only corresponding CPU can update. */
-};
-static DEFINE_PER_CPU_SHARED_ALIGNED(enum rcu_flip_flag_values, rcu_flip_flag)
-								= rcu_flip_seen;
-
-/*
- * Enum and per-CPU flag to determine when each CPU has executed the
- * needed memory barrier to fence in memory references from its last RCU
- * read-side critical section in the just-completed grace period.
- */
-
-enum rcu_mb_flag_values {
-	rcu_mb_done,		/* Steady/initial state, no mb()s required. */
-				/* Only GP detector can update. */
-	rcu_mb_needed		/* Flip just completed, need an mb(). */
-				/* Only corresponding CPU can update. */
-};
-static DEFINE_PER_CPU_SHARED_ALIGNED(enum rcu_mb_flag_values, rcu_mb_flag)
-								= rcu_mb_done;
-
-/*
- * RCU_DATA_ME: find the current CPU's rcu_data structure.
- * RCU_DATA_CPU: find the specified CPU's rcu_data structure.
- */
-#define RCU_DATA_ME()		(&__get_cpu_var(rcu_data))
-#define RCU_DATA_CPU(cpu)	(&per_cpu(rcu_data, cpu))
-
-/*
- * Helper macro for tracing when the appropriate rcu_data is not
- * cached in a local variable, but where the CPU number is so cached.
- */
-#define RCU_TRACE_CPU(f, cpu) RCU_TRACE(f, &(RCU_DATA_CPU(cpu)->trace));
-
-/*
- * Helper macro for tracing when the appropriate rcu_data is not
- * cached in a local variable.
- */
-#define RCU_TRACE_ME(f) RCU_TRACE(f, &(RCU_DATA_ME()->trace));
-
-/*
- * Helper macro for tracing when the appropriate rcu_data is pointed
- * to by a local variable.
- */
-#define RCU_TRACE_RDP(f, rdp) RCU_TRACE(f, &((rdp)->trace));
-
-#define RCU_SCHED_BATCH_TIME (HZ / 50)
-
-/*
- * Return the number of RCU batches processed thus far.  Useful
- * for debug and statistics.
- */
-long rcu_batches_completed(void)
-{
-	return rcu_ctrlblk.completed;
-}
-EXPORT_SYMBOL_GPL(rcu_batches_completed);
-
-void __rcu_read_lock(void)
-{
-	int idx;
-	struct task_struct *t = current;
-	int nesting;
-
-	nesting = ACCESS_ONCE(t->rcu_read_lock_nesting);
-	if (nesting != 0) {
-
-		/* An earlier rcu_read_lock() covers us, just count it. */
-
-		t->rcu_read_lock_nesting = nesting + 1;
-
-	} else {
-		unsigned long flags;
-
-		/*
-		 * We disable interrupts for the following reasons:
-		 * - If we get scheduling clock interrupt here, and we
-		 *   end up acking the counter flip, it's like a promise
-		 *   that we will never increment the old counter again.
-		 *   Thus we will break that promise if that
-		 *   scheduling clock interrupt happens between the time
-		 *   we pick the .completed field and the time that we
-		 *   increment our counter.
-		 *
-		 * - We don't want to be preempted out here.
-		 *
-		 * NMIs can still occur, of course, and might themselves
-		 * contain rcu_read_lock().
-		 */
-
-		local_irq_save(flags);
-
-		/*
-		 * Outermost nesting of rcu_read_lock(), so increment
-		 * the current counter for the current CPU.  Use volatile
-		 * casts to prevent the compiler from reordering.
-		 */
-
-		idx = ACCESS_ONCE(rcu_ctrlblk.completed) & 0x1;
-		ACCESS_ONCE(RCU_DATA_ME()->rcu_flipctr[idx])++;
-
-		/*
-		 * Now that the per-CPU counter has been incremented, we
-		 * are protected from races with rcu_read_lock() invoked
-		 * from NMI handlers on this CPU.  We can therefore safely
-		 * increment the nesting counter, relieving further NMIs
-		 * of the need to increment the per-CPU counter.
-		 */
-
-		ACCESS_ONCE(t->rcu_read_lock_nesting) = nesting + 1;
-
-		/*
-		 * Now that we have preventing any NMIs from storing
-		 * to the ->rcu_flipctr_idx, we can safely use it to
-		 * remember which counter to decrement in the matching
-		 * rcu_read_unlock().
-		 */
-
-		ACCESS_ONCE(t->rcu_flipctr_idx) = idx;
-		local_irq_restore(flags);
-	}
-}
-EXPORT_SYMBOL_GPL(__rcu_read_lock);
-
-void __rcu_read_unlock(void)
-{
-	int idx;
-	struct task_struct *t = current;
-	int nesting;
-
-	nesting = ACCESS_ONCE(t->rcu_read_lock_nesting);
-	if (nesting > 1) {
-
-		/*
-		 * We are still protected by the enclosing rcu_read_lock(),
-		 * so simply decrement the counter.
-		 */
-
-		t->rcu_read_lock_nesting = nesting - 1;
-
-	} else {
-		unsigned long flags;
-
-		/*
-		 * Disable local interrupts to prevent the grace-period
-		 * detection state machine from seeing us half-done.
-		 * NMIs can still occur, of course, and might themselves
-		 * contain rcu_read_lock() and rcu_read_unlock().
-		 */
-
-		local_irq_save(flags);
-
-		/*
-		 * Outermost nesting of rcu_read_unlock(), so we must
-		 * decrement the current counter for the current CPU.
-		 * This must be done carefully, because NMIs can
-		 * occur at any point in this code, and any rcu_read_lock()
-		 * and rcu_read_unlock() pairs in the NMI handlers
-		 * must interact non-destructively with this code.
-		 * Lots of volatile casts, and -very- careful ordering.
-		 *
-		 * Changes to this code, including this one, must be
-		 * inspected, validated, and tested extremely carefully!!!
-		 */
-
-		/*
-		 * First, pick up the index.
-		 */
-
-		idx = ACCESS_ONCE(t->rcu_flipctr_idx);
-
-		/*
-		 * Now that we have fetched the counter index, it is
-		 * safe to decrement the per-task RCU nesting counter.
-		 * After this, any interrupts or NMIs will increment and
-		 * decrement the per-CPU counters.
-		 */
-		ACCESS_ONCE(t->rcu_read_lock_nesting) = nesting - 1;
-
-		/*
-		 * It is now safe to decrement this task's nesting count.
-		 * NMIs that occur after this statement will route their
-		 * rcu_read_lock() calls through this "else" clause, and
-		 * will thus start incrementing the per-CPU counter on
-		 * their own.  They will also clobber ->rcu_flipctr_idx,
-		 * but that is OK, since we have already fetched it.
-		 */
-
-		ACCESS_ONCE(RCU_DATA_ME()->rcu_flipctr[idx])--;
-		local_irq_restore(flags);
-	}
-}
-EXPORT_SYMBOL_GPL(__rcu_read_unlock);
-
-/*
- * If a global counter flip has occurred since the last time that we
- * advanced callbacks, advance them.  Hardware interrupts must be
- * disabled when calling this function.
- */
-static void __rcu_advance_callbacks(struct rcu_data *rdp)
-{
-	int cpu;
-	int i;
-	int wlc = 0;
-
-	if (rdp->completed != rcu_ctrlblk.completed) {
-		if (rdp->waitlist[GP_STAGES - 1] != NULL) {
-			*rdp->donetail = rdp->waitlist[GP_STAGES - 1];
-			rdp->donetail = rdp->waittail[GP_STAGES - 1];
-			RCU_TRACE_RDP(rcupreempt_trace_move2done, rdp);
-		}
-		for (i = GP_STAGES - 2; i >= 0; i--) {
-			if (rdp->waitlist[i] != NULL) {
-				rdp->waitlist[i + 1] = rdp->waitlist[i];
-				rdp->waittail[i + 1] = rdp->waittail[i];
-				wlc++;
-			} else {
-				rdp->waitlist[i + 1] = NULL;
-				rdp->waittail[i + 1] =
-					&rdp->waitlist[i + 1];
-			}
-		}
-		if (rdp->nextlist != NULL) {
-			rdp->waitlist[0] = rdp->nextlist;
-			rdp->waittail[0] = rdp->nexttail;
-			wlc++;
-			rdp->nextlist = NULL;
-			rdp->nexttail = &rdp->nextlist;
-			RCU_TRACE_RDP(rcupreempt_trace_move2wait, rdp);
-		} else {
-			rdp->waitlist[0] = NULL;
-			rdp->waittail[0] = &rdp->waitlist[0];
-		}
-		rdp->waitlistcount = wlc;
-		rdp->completed = rcu_ctrlblk.completed;
-	}
-
-	/*
-	 * Check to see if this CPU needs to report that it has seen
-	 * the most recent counter flip, thereby declaring that all
-	 * subsequent rcu_read_lock() invocations will respect this flip.
-	 */
-
-	cpu = raw_smp_processor_id();
-	if (per_cpu(rcu_flip_flag, cpu) == rcu_flipped) {
-		smp_mb();  /* Subsequent counter accesses must see new value */
-		per_cpu(rcu_flip_flag, cpu) = rcu_flip_seen;
-		smp_mb();  /* Subsequent RCU read-side critical sections */
-			   /*  seen -after- acknowledgement. */
-	}
-}
-
-#ifdef CONFIG_NO_HZ
-static DEFINE_PER_CPU(int, rcu_update_flag);
-
-/**
- * rcu_irq_enter - Called from Hard irq handlers and NMI/SMI.
- *
- * If the CPU was idle with dynamic ticks active, this updates the
- * rcu_dyntick_sched.dynticks to let the RCU handling know that the
- * CPU is active.
- */
-void rcu_irq_enter(void)
-{
-	int cpu = smp_processor_id();
-	struct rcu_dyntick_sched *rdssp = &per_cpu(rcu_dyntick_sched, cpu);
-
-	if (per_cpu(rcu_update_flag, cpu))
-		per_cpu(rcu_update_flag, cpu)++;
-
-	/*
-	 * Only update if we are coming from a stopped ticks mode
-	 * (rcu_dyntick_sched.dynticks is even).
-	 */
-	if (!in_interrupt() &&
-	    (rdssp->dynticks & 0x1) == 0) {
-		/*
-		 * The following might seem like we could have a race
-		 * with NMI/SMIs. But this really isn't a problem.
-		 * Here we do a read/modify/write, and the race happens
-		 * when an NMI/SMI comes in after the read and before
-		 * the write. But NMI/SMIs will increment this counter
-		 * twice before returning, so the zero bit will not
-		 * be corrupted by the NMI/SMI which is the most important
-		 * part.
-		 *
-		 * The only thing is that we would bring back the counter
-		 * to a postion that it was in during the NMI/SMI.
-		 * But the zero bit would be set, so the rest of the
-		 * counter would again be ignored.
-		 *
-		 * On return from the IRQ, the counter may have the zero
-		 * bit be 0 and the counter the same as the return from
-		 * the NMI/SMI. If the state machine was so unlucky to
-		 * see that, it still doesn't matter, since all
-		 * RCU read-side critical sections on this CPU would
-		 * have already completed.
-		 */
-		rdssp->dynticks++;
-		/*
-		 * The following memory barrier ensures that any
-		 * rcu_read_lock() primitives in the irq handler
-		 * are seen by other CPUs to follow the above
-		 * increment to rcu_dyntick_sched.dynticks. This is
-		 * required in order for other CPUs to correctly
-		 * determine when it is safe to advance the RCU
-		 * grace-period state machine.
-		 */
-		smp_mb(); /* see above block comment. */
-		/*
-		 * Since we can't determine the dynamic tick mode from
-		 * the rcu_dyntick_sched.dynticks after this routine,
-		 * we use a second flag to acknowledge that we came
-		 * from an idle state with ticks stopped.
-		 */
-		per_cpu(rcu_update_flag, cpu)++;
-		/*
-		 * If we take an NMI/SMI now, they will also increment
-		 * the rcu_update_flag, and will not update the
-		 * rcu_dyntick_sched.dynticks on exit. That is for
-		 * this IRQ to do.
-		 */
-	}
-}
-
-/**
- * rcu_irq_exit - Called from exiting Hard irq context.
- *
- * If the CPU was idle with dynamic ticks active, update the
- * rcu_dyntick_sched.dynticks to put let the RCU handling be
- * aware that the CPU is going back to idle with no ticks.
- */
-void rcu_irq_exit(void)
-{
-	int cpu = smp_processor_id();
-	struct rcu_dyntick_sched *rdssp = &per_cpu(rcu_dyntick_sched, cpu);
-
-	/*
-	 * rcu_update_flag is set if we interrupted the CPU
-	 * when it was idle with ticks stopped.
-	 * Once this occurs, we keep track of interrupt nesting
-	 * because a NMI/SMI could also come in, and we still
-	 * only want the IRQ that started the increment of the
-	 * rcu_dyntick_sched.dynticks to be the one that modifies
-	 * it on exit.
-	 */
-	if (per_cpu(rcu_update_flag, cpu)) {
-		if (--per_cpu(rcu_update_flag, cpu))
-			return;
-
-		/* This must match the interrupt nesting */
-		WARN_ON(in_interrupt());
-
-		/*
-		 * If an NMI/SMI happens now we are still
-		 * protected by the rcu_dyntick_sched.dynticks being odd.
-		 */
-
-		/*
-		 * The following memory barrier ensures that any
-		 * rcu_read_unlock() primitives in the irq handler
-		 * are seen by other CPUs to preceed the following
-		 * increment to rcu_dyntick_sched.dynticks. This
-		 * is required in order for other CPUs to determine
-		 * when it is safe to advance the RCU grace-period
-		 * state machine.
-		 */
-		smp_mb(); /* see above block comment. */
-		rdssp->dynticks++;
-		WARN_ON(rdssp->dynticks & 0x1);
-	}
-}
-
-void rcu_nmi_enter(void)
-{
-	rcu_irq_enter();
-}
-
-void rcu_nmi_exit(void)
-{
-	rcu_irq_exit();
-}
-
-static void dyntick_save_progress_counter(int cpu)
-{
-	struct rcu_dyntick_sched *rdssp = &per_cpu(rcu_dyntick_sched, cpu);
-
-	rdssp->dynticks_snap = rdssp->dynticks;
-}
-
-static inline int
-rcu_try_flip_waitack_needed(int cpu)
-{
-	long curr;
-	long snap;
-	struct rcu_dyntick_sched *rdssp = &per_cpu(rcu_dyntick_sched, cpu);
-
-	curr = rdssp->dynticks;
-	snap = rdssp->dynticks_snap;
-	smp_mb(); /* force ordering with cpu entering/leaving dynticks. */
-
-	/*
-	 * If the CPU remained in dynticks mode for the entire time
-	 * and didn't take any interrupts, NMIs, SMIs, or whatever,
-	 * then it cannot be in the middle of an rcu_read_lock(), so
-	 * the next rcu_read_lock() it executes must use the new value
-	 * of the counter.  So we can safely pretend that this CPU
-	 * already acknowledged the counter.
-	 */
-
-	if ((curr == snap) && ((curr & 0x1) == 0))
-		return 0;
-
-	/*
-	 * If the CPU passed through or entered a dynticks idle phase with
-	 * no active irq handlers, then, as above, we can safely pretend
-	 * that this CPU already acknowledged the counter.
-	 */
-
-	if ((curr - snap) > 2 || (curr & 0x1) == 0)
-		return 0;
-
-	/* We need this CPU to explicitly acknowledge the counter flip. */
-
-	return 1;
-}
-
-static inline int
-rcu_try_flip_waitmb_needed(int cpu)
-{
-	long curr;
-	long snap;
-	struct rcu_dyntick_sched *rdssp = &per_cpu(rcu_dyntick_sched, cpu);
-
-	curr = rdssp->dynticks;
-	snap = rdssp->dynticks_snap;
-	smp_mb(); /* force ordering with cpu entering/leaving dynticks. */
-
-	/*
-	 * If the CPU remained in dynticks mode for the entire time
-	 * and didn't take any interrupts, NMIs, SMIs, or whatever,
-	 * then it cannot have executed an RCU read-side critical section
-	 * during that time, so there is no need for it to execute a
-	 * memory barrier.
-	 */
-
-	if ((curr == snap) && ((curr & 0x1) == 0))
-		return 0;
-
-	/*
-	 * If the CPU either entered or exited an outermost interrupt,
-	 * SMI, NMI, or whatever handler, then we know that it executed
-	 * a memory barrier when doing so.  So we don't need another one.
-	 */
-	if (curr != snap)
-		return 0;
-
-	/* We need the CPU to execute a memory barrier. */
-
-	return 1;
-}
-
-static void dyntick_save_progress_counter_sched(int cpu)
-{
-	struct rcu_dyntick_sched *rdssp = &per_cpu(rcu_dyntick_sched, cpu);
-
-	rdssp->sched_dynticks_snap = rdssp->dynticks;
-}
-
-static int rcu_qsctr_inc_needed_dyntick(int cpu)
-{
-	long curr;
-	long snap;
-	struct rcu_dyntick_sched *rdssp = &per_cpu(rcu_dyntick_sched, cpu);
-
-	curr = rdssp->dynticks;
-	snap = rdssp->sched_dynticks_snap;
-	smp_mb(); /* force ordering with cpu entering/leaving dynticks. */
-
-	/*
-	 * If the CPU remained in dynticks mode for the entire time
-	 * and didn't take any interrupts, NMIs, SMIs, or whatever,
-	 * then it cannot be in the middle of an rcu_read_lock(), so
-	 * the next rcu_read_lock() it executes must use the new value
-	 * of the counter.  Therefore, this CPU has been in a quiescent
-	 * state the entire time, and we don't need to wait for it.
-	 */
-
-	if ((curr == snap) && ((curr & 0x1) == 0))
-		return 0;
-
-	/*
-	 * If the CPU passed through or entered a dynticks idle phase with
-	 * no active irq handlers, then, as above, this CPU has already
-	 * passed through a quiescent state.
-	 */
-
-	if ((curr - snap) > 2 || (snap & 0x1) == 0)
-		return 0;
-
-	/* We need this CPU to go through a quiescent state. */
-
-	return 1;
-}
-
-#else /* !CONFIG_NO_HZ */
-
-# define dyntick_save_progress_counter(cpu)		do { } while (0)
-# define rcu_try_flip_waitack_needed(cpu)		(1)
-# define rcu_try_flip_waitmb_needed(cpu)		(1)
-
-# define dyntick_save_progress_counter_sched(cpu)	do { } while (0)
-# define rcu_qsctr_inc_needed_dyntick(cpu)		(1)
-
-#endif /* CONFIG_NO_HZ */
-
-static void save_qsctr_sched(int cpu)
-{
-	struct rcu_dyntick_sched *rdssp = &per_cpu(rcu_dyntick_sched, cpu);
-
-	rdssp->sched_qs_snap = rdssp->sched_qs;
-}
-
-static inline int rcu_qsctr_inc_needed(int cpu)
-{
-	struct rcu_dyntick_sched *rdssp = &per_cpu(rcu_dyntick_sched, cpu);
-
-	/*
-	 * If there has been a quiescent state, no more need to wait
-	 * on this CPU.
-	 */
-
-	if (rdssp->sched_qs != rdssp->sched_qs_snap) {
-		smp_mb(); /* force ordering with cpu entering schedule(). */
-		return 0;
-	}
-
-	/* We need this CPU to go through a quiescent state. */
-
-	return 1;
-}
-
-/*
- * Get here when RCU is idle.  Decide whether we need to
- * move out of idle state, and return non-zero if so.
- * "Straightforward" approach for the moment, might later
- * use callback-list lengths, grace-period duration, or
- * some such to determine when to exit idle state.
- * Might also need a pre-idle test that does not acquire
- * the lock, but let's get the simple case working first...
- */
-
-static int
-rcu_try_flip_idle(void)
-{
-	int cpu;
-
-	RCU_TRACE_ME(rcupreempt_trace_try_flip_i1);
-	if (!rcu_pending(smp_processor_id())) {
-		RCU_TRACE_ME(rcupreempt_trace_try_flip_ie1);
-		return 0;
-	}
-
-	/*
-	 * Do the flip.
-	 */
-
-	RCU_TRACE_ME(rcupreempt_trace_try_flip_g1);
-	rcu_ctrlblk.completed++;  /* stands in for rcu_try_flip_g2 */
-
-	/*
-	 * Need a memory barrier so that other CPUs see the new
-	 * counter value before they see the subsequent change of all
-	 * the rcu_flip_flag instances to rcu_flipped.
-	 */
-
-	smp_mb();	/* see above block comment. */
-
-	/* Now ask each CPU for acknowledgement of the flip. */
-
-	for_each_cpu(cpu, to_cpumask(rcu_cpu_online_map)) {
-		per_cpu(rcu_flip_flag, cpu) = rcu_flipped;
-		dyntick_save_progress_counter(cpu);
-	}
-
-	return 1;
-}
-
-/*
- * Wait for CPUs to acknowledge the flip.
- */
-
-static int
-rcu_try_flip_waitack(void)
-{
-	int cpu;
-
-	RCU_TRACE_ME(rcupreempt_trace_try_flip_a1);
-	for_each_cpu(cpu, to_cpumask(rcu_cpu_online_map))
-		if (rcu_try_flip_waitack_needed(cpu) &&
-		    per_cpu(rcu_flip_flag, cpu) != rcu_flip_seen) {
-			RCU_TRACE_ME(rcupreempt_trace_try_flip_ae1);
-			return 0;
-		}
-
-	/*
-	 * Make sure our checks above don't bleed into subsequent
-	 * waiting for the sum of the counters to reach zero.
-	 */
-
-	smp_mb();	/* see above block comment. */
-	RCU_TRACE_ME(rcupreempt_trace_try_flip_a2);
-	return 1;
-}
-
-/*
- * Wait for collective ``last'' counter to reach zero,
- * then tell all CPUs to do an end-of-grace-period memory barrier.
- */
-
-static int
-rcu_try_flip_waitzero(void)
-{
-	int cpu;
-	int lastidx = !(rcu_ctrlblk.completed & 0x1);
-	int sum = 0;
-
-	/* Check to see if the sum of the "last" counters is zero. */
-
-	RCU_TRACE_ME(rcupreempt_trace_try_flip_z1);
-	for_each_cpu(cpu, to_cpumask(rcu_cpu_online_map))
-		sum += RCU_DATA_CPU(cpu)->rcu_flipctr[lastidx];
-	if (sum != 0) {
-		RCU_TRACE_ME(rcupreempt_trace_try_flip_ze1);
-		return 0;
-	}
-
-	/*
-	 * This ensures that the other CPUs see the call for
-	 * memory barriers -after- the sum to zero has been
-	 * detected here
-	 */
-	smp_mb();  /*  ^^^^^^^^^^^^ */
-
-	/* Call for a memory barrier from each CPU. */
-	for_each_cpu(cpu, to_cpumask(rcu_cpu_online_map)) {
-		per_cpu(rcu_mb_flag, cpu) = rcu_mb_needed;
-		dyntick_save_progress_counter(cpu);
-	}
-
-	RCU_TRACE_ME(rcupreempt_trace_try_flip_z2);
-	return 1;
-}
-
-/*
- * Wait for all CPUs to do their end-of-grace-period memory barrier.
- * Return 0 once all CPUs have done so.
- */
-
-static int
-rcu_try_flip_waitmb(void)
-{
-	int cpu;
-
-	RCU_TRACE_ME(rcupreempt_trace_try_flip_m1);
-	for_each_cpu(cpu, to_cpumask(rcu_cpu_online_map))
-		if (rcu_try_flip_waitmb_needed(cpu) &&
-		    per_cpu(rcu_mb_flag, cpu) != rcu_mb_done) {
-			RCU_TRACE_ME(rcupreempt_trace_try_flip_me1);
-			return 0;
-		}
-
-	smp_mb(); /* Ensure that the above checks precede any following flip. */
-	RCU_TRACE_ME(rcupreempt_trace_try_flip_m2);
-	return 1;
-}
-
-/*
- * Attempt a single flip of the counters.  Remember, a single flip does
- * -not- constitute a grace period.  Instead, the interval between
- * at least GP_STAGES consecutive flips is a grace period.
- *
- * If anyone is nuts enough to run this CONFIG_PREEMPT_RCU implementation
- * on a large SMP, they might want to use a hierarchical organization of
- * the per-CPU-counter pairs.
- */
-static void rcu_try_flip(void)
-{
-	unsigned long flags;
-
-	RCU_TRACE_ME(rcupreempt_trace_try_flip_1);
-	if (unlikely(!spin_trylock_irqsave(&rcu_ctrlblk.fliplock, flags))) {
-		RCU_TRACE_ME(rcupreempt_trace_try_flip_e1);
-		return;
-	}
-
-	/*
-	 * Take the next transition(s) through the RCU grace-period
-	 * flip-counter state machine.
-	 */
-
-	switch (rcu_ctrlblk.rcu_try_flip_state) {
-	case rcu_try_flip_idle_state:
-		if (rcu_try_flip_idle())
-			rcu_ctrlblk.rcu_try_flip_state =
-				rcu_try_flip_waitack_state;
-		break;
-	case rcu_try_flip_waitack_state:
-		if (rcu_try_flip_waitack())
-			rcu_ctrlblk.rcu_try_flip_state =
-				rcu_try_flip_waitzero_state;
-		break;
-	case rcu_try_flip_waitzero_state:
-		if (rcu_try_flip_waitzero())
-			rcu_ctrlblk.rcu_try_flip_state =
-				rcu_try_flip_waitmb_state;
-		break;
-	case rcu_try_flip_waitmb_state:
-		if (rcu_try_flip_waitmb())
-			rcu_ctrlblk.rcu_try_flip_state =
-				rcu_try_flip_idle_state;
-	}
-	spin_unlock_irqrestore(&rcu_ctrlblk.fliplock, flags);
-}
-
-/*
- * Check to see if this CPU needs to do a memory barrier in order to
- * ensure that any prior RCU read-side critical sections have committed
- * their counter manipulations and critical-section memory references
- * before declaring the grace period to be completed.
- */
-static void rcu_check_mb(int cpu)
-{
-	if (per_cpu(rcu_mb_flag, cpu) == rcu_mb_needed) {
-		smp_mb();  /* Ensure RCU read-side accesses are visible. */
-		per_cpu(rcu_mb_flag, cpu) = rcu_mb_done;
-	}
-}
-
-void rcu_check_callbacks(int cpu, int user)
-{
-	unsigned long flags;
-	struct rcu_data *rdp = RCU_DATA_CPU(cpu);
-
-	/*
-	 * If this CPU took its interrupt from user mode or from the
-	 * idle loop, and this is not a nested interrupt, then
-	 * this CPU has to have exited all prior preept-disable
-	 * sections of code.  So increment the counter to note this.
-	 *
-	 * The memory barrier is needed to handle the case where
-	 * writes from a preempt-disable section of code get reordered
-	 * into schedule() by this CPU's write buffer.  So the memory
-	 * barrier makes sure that the rcu_qsctr_inc() is seen by other
-	 * CPUs to happen after any such write.
-	 */
-
-	if (user ||
-	    (idle_cpu(cpu) && !in_softirq() &&
-	     hardirq_count() <= (1 << HARDIRQ_SHIFT))) {
-		smp_mb();	/* Guard against aggressive schedule(). */
-	     	rcu_qsctr_inc(cpu);
-	}
-
-	rcu_check_mb(cpu);
-	if (rcu_ctrlblk.completed == rdp->completed)
-		rcu_try_flip();
-	spin_lock_irqsave(&rdp->lock, flags);
-	RCU_TRACE_RDP(rcupreempt_trace_check_callbacks, rdp);
-	__rcu_advance_callbacks(rdp);
-	if (rdp->donelist == NULL) {
-		spin_unlock_irqrestore(&rdp->lock, flags);
-	} else {
-		spin_unlock_irqrestore(&rdp->lock, flags);
-		raise_softirq(RCU_SOFTIRQ);
-	}
-}
-
-/*
- * Needed by dynticks, to make sure all RCU processing has finished
- * when we go idle:
- */
-void rcu_advance_callbacks(int cpu, int user)
-{
-	unsigned long flags;
-	struct rcu_data *rdp = RCU_DATA_CPU(cpu);
-
-	if (rcu_ctrlblk.completed == rdp->completed) {
-		rcu_try_flip();
-		if (rcu_ctrlblk.completed == rdp->completed)
-			return;
-	}
-	spin_lock_irqsave(&rdp->lock, flags);
-	RCU_TRACE_RDP(rcupreempt_trace_check_callbacks, rdp);
-	__rcu_advance_callbacks(rdp);
-	spin_unlock_irqrestore(&rdp->lock, flags);
-}
-
-#ifdef CONFIG_HOTPLUG_CPU
-#define rcu_offline_cpu_enqueue(srclist, srctail, dstlist, dsttail) do { \
-		*dsttail = srclist; \
-		if (srclist != NULL) { \
-			dsttail = srctail; \
-			srclist = NULL; \
-			srctail = &srclist;\
-		} \
-	} while (0)
-
-void rcu_offline_cpu(int cpu)
-{
-	int i;
-	struct rcu_head *list = NULL;
-	unsigned long flags;
-	struct rcu_data *rdp = RCU_DATA_CPU(cpu);
-	struct rcu_head *schedlist = NULL;
-	struct rcu_head **schedtail = &schedlist;
-	struct rcu_head **tail = &list;
-
-	/*
-	 * Remove all callbacks from the newly dead CPU, retaining order.
-	 * Otherwise rcu_barrier() will fail
-	 */
-
-	spin_lock_irqsave(&rdp->lock, flags);
-	rcu_offline_cpu_enqueue(rdp->donelist, rdp->donetail, list, tail);
-	for (i = GP_STAGES - 1; i >= 0; i--)
-		rcu_offline_cpu_enqueue(rdp->waitlist[i], rdp->waittail[i],
-						list, tail);
-	rcu_offline_cpu_enqueue(rdp->nextlist, rdp->nexttail, list, tail);
-	rcu_offline_cpu_enqueue(rdp->waitschedlist, rdp->waitschedtail,
-				schedlist, schedtail);
-	rcu_offline_cpu_enqueue(rdp->nextschedlist, rdp->nextschedtail,
-				schedlist, schedtail);
-	rdp->rcu_sched_sleeping = 0;
-	spin_unlock_irqrestore(&rdp->lock, flags);
-	rdp->waitlistcount = 0;
-
-	/* Disengage the newly dead CPU from the grace-period computation. */
-
-	spin_lock_irqsave(&rcu_ctrlblk.fliplock, flags);
-	rcu_check_mb(cpu);
-	if (per_cpu(rcu_flip_flag, cpu) == rcu_flipped) {
-		smp_mb();  /* Subsequent counter accesses must see new value */
-		per_cpu(rcu_flip_flag, cpu) = rcu_flip_seen;
-		smp_mb();  /* Subsequent RCU read-side critical sections */
-			   /*  seen -after- acknowledgement. */
-	}
-
-	RCU_DATA_ME()->rcu_flipctr[0] += RCU_DATA_CPU(cpu)->rcu_flipctr[0];
-	RCU_DATA_ME()->rcu_flipctr[1] += RCU_DATA_CPU(cpu)->rcu_flipctr[1];
-
-	RCU_DATA_CPU(cpu)->rcu_flipctr[0] = 0;
-	RCU_DATA_CPU(cpu)->rcu_flipctr[1] = 0;
-
-	cpumask_clear_cpu(cpu, to_cpumask(rcu_cpu_online_map));
-
-	spin_unlock_irqrestore(&rcu_ctrlblk.fliplock, flags);
-
-	/*
-	 * Place the removed callbacks on the current CPU's queue.
-	 * Make them all start a new grace period: simple approach,
-	 * in theory could starve a given set of callbacks, but
-	 * you would need to be doing some serious CPU hotplugging
-	 * to make this happen.  If this becomes a problem, adding
-	 * a synchronize_rcu() to the hotplug path would be a simple
-	 * fix.
-	 */
-
-	local_irq_save(flags);  /* disable preempt till we know what lock. */
-	rdp = RCU_DATA_ME();
-	spin_lock(&rdp->lock);
-	*rdp->nexttail = list;
-	if (list)
-		rdp->nexttail = tail;
-	*rdp->nextschedtail = schedlist;
-	if (schedlist)
-		rdp->nextschedtail = schedtail;
-	spin_unlock_irqrestore(&rdp->lock, flags);
-}
-
-#else /* #ifdef CONFIG_HOTPLUG_CPU */
-
-void rcu_offline_cpu(int cpu)
-{
-}
-
-#endif /* #else #ifdef CONFIG_HOTPLUG_CPU */
-
-void __cpuinit rcu_online_cpu(int cpu)
-{
-	unsigned long flags;
-	struct rcu_data *rdp;
-
-	spin_lock_irqsave(&rcu_ctrlblk.fliplock, flags);
-	cpumask_set_cpu(cpu, to_cpumask(rcu_cpu_online_map));
-	spin_unlock_irqrestore(&rcu_ctrlblk.fliplock, flags);
-
-	/*
-	 * The rcu_sched grace-period processing might have bypassed
-	 * this CPU, given that it was not in the rcu_cpu_online_map
-	 * when the grace-period scan started.  This means that the
-	 * grace-period task might sleep.  So make sure that if this
-	 * should happen, the first callback posted to this CPU will
-	 * wake up the grace-period task if need be.
-	 */
-
-	rdp = RCU_DATA_CPU(cpu);
-	spin_lock_irqsave(&rdp->lock, flags);
-	rdp->rcu_sched_sleeping = 1;
-	spin_unlock_irqrestore(&rdp->lock, flags);
-}
-
-static void rcu_process_callbacks(struct softirq_action *unused)
-{
-	unsigned long flags;
-	struct rcu_head *next, *list;
-	struct rcu_data *rdp;
-
-	local_irq_save(flags);
-	rdp = RCU_DATA_ME();
-	spin_lock(&rdp->lock);
-	list = rdp->donelist;
-	if (list == NULL) {
-		spin_unlock_irqrestore(&rdp->lock, flags);
-		return;
-	}
-	rdp->donelist = NULL;
-	rdp->donetail = &rdp->donelist;
-	RCU_TRACE_RDP(rcupreempt_trace_done_remove, rdp);
-	spin_unlock_irqrestore(&rdp->lock, flags);
-	while (list) {
-		next = list->next;
-		list->func(list);
-		list = next;
-		RCU_TRACE_ME(rcupreempt_trace_invoke);
-	}
-}
-
-void call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu))
-{
-	unsigned long flags;
-	struct rcu_data *rdp;
-
-	head->func = func;
-	head->next = NULL;
-	local_irq_save(flags);
-	rdp = RCU_DATA_ME();
-	spin_lock(&rdp->lock);
-	__rcu_advance_callbacks(rdp);
-	*rdp->nexttail = head;
-	rdp->nexttail = &head->next;
-	RCU_TRACE_RDP(rcupreempt_trace_next_add, rdp);
-	spin_unlock_irqrestore(&rdp->lock, flags);
-}
-EXPORT_SYMBOL_GPL(call_rcu);
-
-void call_rcu_sched(struct rcu_head *head, void (*func)(struct rcu_head *rcu))
-{
-	unsigned long flags;
-	struct rcu_data *rdp;
-	int wake_gp = 0;
-
-	head->func = func;
-	head->next = NULL;
-	local_irq_save(flags);
-	rdp = RCU_DATA_ME();
-	spin_lock(&rdp->lock);
-	*rdp->nextschedtail = head;
-	rdp->nextschedtail = &head->next;
-	if (rdp->rcu_sched_sleeping) {
-
-		/* Grace-period processing might be sleeping... */
-
-		rdp->rcu_sched_sleeping = 0;
-		wake_gp = 1;
-	}
-	spin_unlock_irqrestore(&rdp->lock, flags);
-	if (wake_gp) {
-
-		/* Wake up grace-period processing, unless someone beat us. */
-
-		spin_lock_irqsave(&rcu_ctrlblk.schedlock, flags);
-		if (rcu_ctrlblk.sched_sleep != rcu_sched_sleeping)
-			wake_gp = 0;
-		rcu_ctrlblk.sched_sleep = rcu_sched_not_sleeping;
-		spin_unlock_irqrestore(&rcu_ctrlblk.schedlock, flags);
-		if (wake_gp)
-			wake_up_interruptible(&rcu_ctrlblk.sched_wq);
-	}
-}
-EXPORT_SYMBOL_GPL(call_rcu_sched);
-
-/*
- * Wait until all currently running preempt_disable() code segments
- * (including hardware-irq-disable segments) complete.  Note that
- * in -rt this does -not- necessarily result in all currently executing
- * interrupt -handlers- having completed.
- */
-void __synchronize_sched(void)
-{
-	struct rcu_synchronize rcu;
-
-	if (num_online_cpus() == 1)
-		return;  /* blocking is gp if only one CPU! */
-
-	init_completion(&rcu.completion);
-	/* Will wake me after RCU finished. */
-	call_rcu_sched(&rcu.head, wakeme_after_rcu);
-	/* Wait for it. */
-	wait_for_completion(&rcu.completion);
-}
-EXPORT_SYMBOL_GPL(__synchronize_sched);
-
-/*
- * kthread function that manages call_rcu_sched grace periods.
- */
-static int rcu_sched_grace_period(void *arg)
-{
-	int couldsleep;		/* might sleep after current pass. */
-	int couldsleepnext = 0; /* might sleep after next pass. */
-	int cpu;
-	unsigned long flags;
-	struct rcu_data *rdp;
-	int ret;
-
-	/*
-	 * Each pass through the following loop handles one
-	 * rcu_sched grace period cycle.
-	 */
-	do {
-		/* Save each CPU's current state. */
-
-		for_each_online_cpu(cpu) {
-			dyntick_save_progress_counter_sched(cpu);
-			save_qsctr_sched(cpu);
-		}
-
-		/*
-		 * Sleep for about an RCU grace-period's worth to
-		 * allow better batching and to consume less CPU.
-		 */
-		schedule_timeout_interruptible(RCU_SCHED_BATCH_TIME);
-
-		/*
-		 * If there was nothing to do last time, prepare to
-		 * sleep at the end of the current grace period cycle.
-		 */
-		couldsleep = couldsleepnext;
-		couldsleepnext = 1;
-		if (couldsleep) {
-			spin_lock_irqsave(&rcu_ctrlblk.schedlock, flags);
-			rcu_ctrlblk.sched_sleep = rcu_sched_sleep_prep;
-			spin_unlock_irqrestore(&rcu_ctrlblk.schedlock, flags);
-		}
-
-		/*
-		 * Wait on each CPU in turn to have either visited
-		 * a quiescent state or been in dynticks-idle mode.
-		 */
-		for_each_online_cpu(cpu) {
-			while (rcu_qsctr_inc_needed(cpu) &&
-			       rcu_qsctr_inc_needed_dyntick(cpu)) {
-				/* resched_cpu(cpu); @@@ */
-				schedule_timeout_interruptible(1);
-			}
-		}
-
-		/* Advance callbacks for each CPU.  */
-
-		for_each_online_cpu(cpu) {
-
-			rdp = RCU_DATA_CPU(cpu);
-			spin_lock_irqsave(&rdp->lock, flags);
-
-			/*
-			 * We are running on this CPU irq-disabled, so no
-			 * CPU can go offline until we re-enable irqs.
-			 * The current CPU might have already gone
-			 * offline (between the for_each_offline_cpu and
-			 * the spin_lock_irqsave), but in that case all its
-			 * callback lists will be empty, so no harm done.
-			 *
-			 * Advance the callbacks!  We share normal RCU's
-			 * donelist, since callbacks are invoked the
-			 * same way in either case.
-			 */
-			if (rdp->waitschedlist != NULL) {
-				*rdp->donetail = rdp->waitschedlist;
-				rdp->donetail = rdp->waitschedtail;
-
-				/*
-				 * Next rcu_check_callbacks() will
-				 * do the required raise_softirq().
-				 */
-			}
-			if (rdp->nextschedlist != NULL) {
-				rdp->waitschedlist = rdp->nextschedlist;
-				rdp->waitschedtail = rdp->nextschedtail;
-				couldsleep = 0;
-				couldsleepnext = 0;
-			} else {
-				rdp->waitschedlist = NULL;
-				rdp->waitschedtail = &rdp->waitschedlist;
-			}
-			rdp->nextschedlist = NULL;
-			rdp->nextschedtail = &rdp->nextschedlist;
-
-			/* Mark sleep intention. */
-
-			rdp->rcu_sched_sleeping = couldsleep;
-
-			spin_unlock_irqrestore(&rdp->lock, flags);
-		}
-
-		/* If we saw callbacks on the last scan, go deal with them. */
-
-		if (!couldsleep)
-			continue;
-
-		/* Attempt to block... */
-
-		spin_lock_irqsave(&rcu_ctrlblk.schedlock, flags);
-		if (rcu_ctrlblk.sched_sleep != rcu_sched_sleep_prep) {
-
-			/*
-			 * Someone posted a callback after we scanned.
-			 * Go take care of it.
-			 */
-			spin_unlock_irqrestore(&rcu_ctrlblk.schedlock, flags);
-			couldsleepnext = 0;
-			continue;
-		}
-
-		/* Block until the next person posts a callback. */
-
-		rcu_ctrlblk.sched_sleep = rcu_sched_sleeping;
-		spin_unlock_irqrestore(&rcu_ctrlblk.schedlock, flags);
-		ret = 0; /* unused */
-		__wait_event_interruptible(rcu_ctrlblk.sched_wq,
-			rcu_ctrlblk.sched_sleep != rcu_sched_sleeping,
-			ret);
-
-		couldsleepnext = 0;
-
-	} while (!kthread_should_stop());
-
-	return (0);
-}
-
-/*
- * Check to see if any future RCU-related work will need to be done
- * by the current CPU, even if none need be done immediately, returning
- * 1 if so.  Assumes that notifiers would take care of handling any
- * outstanding requests from the RCU core.
- *
- * This function is part of the RCU implementation; it is -not-
- * an exported member of the RCU API.
- */
-int rcu_needs_cpu(int cpu)
-{
-	struct rcu_data *rdp = RCU_DATA_CPU(cpu);
-
-	return (rdp->donelist != NULL ||
-		!!rdp->waitlistcount ||
-		rdp->nextlist != NULL ||
-		rdp->nextschedlist != NULL ||
-		rdp->waitschedlist != NULL);
-}
-
-int rcu_pending(int cpu)
-{
-	struct rcu_data *rdp = RCU_DATA_CPU(cpu);
-
-	/* The CPU has at least one callback queued somewhere. */
-
-	if (rdp->donelist != NULL ||
-	    !!rdp->waitlistcount ||
-	    rdp->nextlist != NULL ||
-	    rdp->nextschedlist != NULL ||
-	    rdp->waitschedlist != NULL)
-		return 1;
-
-	/* The RCU core needs an acknowledgement from this CPU. */
-
-	if ((per_cpu(rcu_flip_flag, cpu) == rcu_flipped) ||
-	    (per_cpu(rcu_mb_flag, cpu) == rcu_mb_needed))
-		return 1;
-
-	/* This CPU has fallen behind the global grace-period number. */
-
-	if (rdp->completed != rcu_ctrlblk.completed)
-		return 1;
-
-	/* Nothing needed from this CPU. */
-
-	return 0;
-}
-
-static int __cpuinit rcu_cpu_notify(struct notifier_block *self,
-				unsigned long action, void *hcpu)
-{
-	long cpu = (long)hcpu;
-
-	switch (action) {
-	case CPU_UP_PREPARE:
-	case CPU_UP_PREPARE_FROZEN:
-		rcu_online_cpu(cpu);
-		break;
-	case CPU_UP_CANCELED:
-	case CPU_UP_CANCELED_FROZEN:
-	case CPU_DEAD:
-	case CPU_DEAD_FROZEN:
-		rcu_offline_cpu(cpu);
-		break;
-	default:
-		break;
-	}
-	return NOTIFY_OK;
-}
-
-static struct notifier_block __cpuinitdata rcu_nb = {
-	.notifier_call = rcu_cpu_notify,
-};
-
-void __init __rcu_init(void)
-{
-	int cpu;
-	int i;
-	struct rcu_data *rdp;
-
-	printk(KERN_NOTICE "Preemptible RCU implementation.\n");
-	for_each_possible_cpu(cpu) {
-		rdp = RCU_DATA_CPU(cpu);
-		spin_lock_init(&rdp->lock);
-		rdp->completed = 0;
-		rdp->waitlistcount = 0;
-		rdp->nextlist = NULL;
-		rdp->nexttail = &rdp->nextlist;
-		for (i = 0; i < GP_STAGES; i++) {
-			rdp->waitlist[i] = NULL;
-			rdp->waittail[i] = &rdp->waitlist[i];
-		}
-		rdp->donelist = NULL;
-		rdp->donetail = &rdp->donelist;
-		rdp->rcu_flipctr[0] = 0;
-		rdp->rcu_flipctr[1] = 0;
-		rdp->nextschedlist = NULL;
-		rdp->nextschedtail = &rdp->nextschedlist;
-		rdp->waitschedlist = NULL;
-		rdp->waitschedtail = &rdp->waitschedlist;
-		rdp->rcu_sched_sleeping = 0;
-	}
-	register_cpu_notifier(&rcu_nb);
-
-	/*
-	 * We don't need protection against CPU-Hotplug here
-	 * since
-	 * a) If a CPU comes online while we are iterating over the
-	 *    cpu_online_mask below, we would only end up making a
-	 *    duplicate call to rcu_online_cpu() which sets the corresponding
-	 *    CPU's mask in the rcu_cpu_online_map.
-	 *
-	 * b) A CPU cannot go offline at this point in time since the user
-	 *    does not have access to the sysfs interface, nor do we
-	 *    suspend the system.
-	 */
-	for_each_online_cpu(cpu)
-		rcu_cpu_notify(&rcu_nb, CPU_UP_PREPARE,	(void *)(long) cpu);
-
-	open_softirq(RCU_SOFTIRQ, rcu_process_callbacks);
-}
-
-/*
- * Late-boot-time RCU initialization that must wait until after scheduler
- * has been initialized.
- */
-void __init rcu_init_sched(void)
-{
-	rcu_sched_grace_period_task = kthread_run(rcu_sched_grace_period,
-						  NULL,
-						  "rcu_sched_grace_period");
-	WARN_ON(IS_ERR(rcu_sched_grace_period_task));
-}
-
-#ifdef CONFIG_RCU_TRACE
-long *rcupreempt_flipctr(int cpu)
-{
-	return &RCU_DATA_CPU(cpu)->rcu_flipctr[0];
-}
-EXPORT_SYMBOL_GPL(rcupreempt_flipctr);
-
-int rcupreempt_flip_flag(int cpu)
-{
-	return per_cpu(rcu_flip_flag, cpu);
-}
-EXPORT_SYMBOL_GPL(rcupreempt_flip_flag);
-
-int rcupreempt_mb_flag(int cpu)
-{
-	return per_cpu(rcu_mb_flag, cpu);
-}
-EXPORT_SYMBOL_GPL(rcupreempt_mb_flag);
-
-char *rcupreempt_try_flip_state_name(void)
-{
-	return rcu_try_flip_state_names[rcu_ctrlblk.rcu_try_flip_state];
-}
-EXPORT_SYMBOL_GPL(rcupreempt_try_flip_state_name);
-
-struct rcupreempt_trace *rcupreempt_trace_cpu(int cpu)
-{
-	struct rcu_data *rdp = RCU_DATA_CPU(cpu);
-
-	return &rdp->trace;
-}
-EXPORT_SYMBOL_GPL(rcupreempt_trace_cpu);
-
-#endif /* #ifdef RCU_TRACE */
diff --git a/kernel/rcupreempt_trace.c b/kernel/rcupreempt_trace.c
deleted file mode 100644
index 7c2665cac172..000000000000
--- a/kernel/rcupreempt_trace.c
+++ /dev/null
@@ -1,334 +0,0 @@
-/*
- * Read-Copy Update tracing for realtime implementation
- *
- * 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 IBM Corporation, 2006
- *
- * Papers:  http://www.rdrop.com/users/paulmck/RCU
- *
- * For detailed explanation of Read-Copy Update mechanism see -
- * 		Documentation/RCU/ *.txt
- *
- */
-#include <linux/types.h>
-#include <linux/kernel.h>
-#include <linux/init.h>
-#include <linux/spinlock.h>
-#include <linux/smp.h>
-#include <linux/rcupdate.h>
-#include <linux/interrupt.h>
-#include <linux/sched.h>
-#include <asm/atomic.h>
-#include <linux/bitops.h>
-#include <linux/module.h>
-#include <linux/completion.h>
-#include <linux/moduleparam.h>
-#include <linux/percpu.h>
-#include <linux/notifier.h>
-#include <linux/cpu.h>
-#include <linux/mutex.h>
-#include <linux/rcupreempt_trace.h>
-#include <linux/debugfs.h>
-
-static struct mutex rcupreempt_trace_mutex;
-static char *rcupreempt_trace_buf;
-#define RCUPREEMPT_TRACE_BUF_SIZE 4096
-
-void rcupreempt_trace_move2done(struct rcupreempt_trace *trace)
-{
-	trace->done_length += trace->wait_length;
-	trace->done_add += trace->wait_length;
-	trace->wait_length = 0;
-}
-void rcupreempt_trace_move2wait(struct rcupreempt_trace *trace)
-{
-	trace->wait_length += trace->next_length;
-	trace->wait_add += trace->next_length;
-	trace->next_length = 0;
-}
-void rcupreempt_trace_try_flip_1(struct rcupreempt_trace *trace)
-{
-	atomic_inc(&trace->rcu_try_flip_1);
-}
-void rcupreempt_trace_try_flip_e1(struct rcupreempt_trace *trace)
-{
-	atomic_inc(&trace->rcu_try_flip_e1);
-}
-void rcupreempt_trace_try_flip_i1(struct rcupreempt_trace *trace)
-{
-	trace->rcu_try_flip_i1++;
-}
-void rcupreempt_trace_try_flip_ie1(struct rcupreempt_trace *trace)
-{
-	trace->rcu_try_flip_ie1++;
-}
-void rcupreempt_trace_try_flip_g1(struct rcupreempt_trace *trace)
-{
-	trace->rcu_try_flip_g1++;
-}
-void rcupreempt_trace_try_flip_a1(struct rcupreempt_trace *trace)
-{
-	trace->rcu_try_flip_a1++;
-}
-void rcupreempt_trace_try_flip_ae1(struct rcupreempt_trace *trace)
-{
-	trace->rcu_try_flip_ae1++;
-}
-void rcupreempt_trace_try_flip_a2(struct rcupreempt_trace *trace)
-{
-	trace->rcu_try_flip_a2++;
-}
-void rcupreempt_trace_try_flip_z1(struct rcupreempt_trace *trace)
-{
-	trace->rcu_try_flip_z1++;
-}
-void rcupreempt_trace_try_flip_ze1(struct rcupreempt_trace *trace)
-{
-	trace->rcu_try_flip_ze1++;
-}
-void rcupreempt_trace_try_flip_z2(struct rcupreempt_trace *trace)
-{
-	trace->rcu_try_flip_z2++;
-}
-void rcupreempt_trace_try_flip_m1(struct rcupreempt_trace *trace)
-{
-	trace->rcu_try_flip_m1++;
-}
-void rcupreempt_trace_try_flip_me1(struct rcupreempt_trace *trace)
-{
-	trace->rcu_try_flip_me1++;
-}
-void rcupreempt_trace_try_flip_m2(struct rcupreempt_trace *trace)
-{
-	trace->rcu_try_flip_m2++;
-}
-void rcupreempt_trace_check_callbacks(struct rcupreempt_trace *trace)
-{
-	trace->rcu_check_callbacks++;
-}
-void rcupreempt_trace_done_remove(struct rcupreempt_trace *trace)
-{
-	trace->done_remove += trace->done_length;
-	trace->done_length = 0;
-}
-void rcupreempt_trace_invoke(struct rcupreempt_trace *trace)
-{
-	atomic_inc(&trace->done_invoked);
-}
-void rcupreempt_trace_next_add(struct rcupreempt_trace *trace)
-{
-	trace->next_add++;
-	trace->next_length++;
-}
-
-static void rcupreempt_trace_sum(struct rcupreempt_trace *sp)
-{
-	struct rcupreempt_trace *cp;
-	int cpu;
-
-	memset(sp, 0, sizeof(*sp));
-	for_each_possible_cpu(cpu) {
-		cp = rcupreempt_trace_cpu(cpu);
-		sp->next_length += cp->next_length;
-		sp->next_add += cp->next_add;
-		sp->wait_length += cp->wait_length;
-		sp->wait_add += cp->wait_add;
-		sp->done_length += cp->done_length;
-		sp->done_add += cp->done_add;
-		sp->done_remove += cp->done_remove;
-		atomic_add(atomic_read(&cp->done_invoked), &sp->done_invoked);
-		sp->rcu_check_callbacks += cp->rcu_check_callbacks;
-		atomic_add(atomic_read(&cp->rcu_try_flip_1),
-			   &sp->rcu_try_flip_1);
-		atomic_add(atomic_read(&cp->rcu_try_flip_e1),
-			   &sp->rcu_try_flip_e1);
-		sp->rcu_try_flip_i1 += cp->rcu_try_flip_i1;
-		sp->rcu_try_flip_ie1 += cp->rcu_try_flip_ie1;
-		sp->rcu_try_flip_g1 += cp->rcu_try_flip_g1;
-		sp->rcu_try_flip_a1 += cp->rcu_try_flip_a1;
-		sp->rcu_try_flip_ae1 += cp->rcu_try_flip_ae1;
-		sp->rcu_try_flip_a2 += cp->rcu_try_flip_a2;
-		sp->rcu_try_flip_z1 += cp->rcu_try_flip_z1;
-		sp->rcu_try_flip_ze1 += cp->rcu_try_flip_ze1;
-		sp->rcu_try_flip_z2 += cp->rcu_try_flip_z2;
-		sp->rcu_try_flip_m1 += cp->rcu_try_flip_m1;
-		sp->rcu_try_flip_me1 += cp->rcu_try_flip_me1;
-		sp->rcu_try_flip_m2 += cp->rcu_try_flip_m2;
-	}
-}
-
-static ssize_t rcustats_read(struct file *filp, char __user *buffer,
-				size_t count, loff_t *ppos)
-{
-	struct rcupreempt_trace trace;
-	ssize_t bcount;
-	int cnt = 0;
-
-	rcupreempt_trace_sum(&trace);
-	mutex_lock(&rcupreempt_trace_mutex);
-	snprintf(&rcupreempt_trace_buf[cnt], RCUPREEMPT_TRACE_BUF_SIZE - cnt,
-		 "ggp=%ld rcc=%ld\n",
-		 rcu_batches_completed(),
-		 trace.rcu_check_callbacks);
-	snprintf(&rcupreempt_trace_buf[cnt], RCUPREEMPT_TRACE_BUF_SIZE - cnt,
-		 "na=%ld nl=%ld wa=%ld wl=%ld da=%ld dl=%ld dr=%ld di=%d\n"
-		 "1=%d e1=%d i1=%ld ie1=%ld g1=%ld a1=%ld ae1=%ld a2=%ld\n"
-		 "z1=%ld ze1=%ld z2=%ld m1=%ld me1=%ld m2=%ld\n",
-
-		 trace.next_add, trace.next_length,
-		 trace.wait_add, trace.wait_length,
-		 trace.done_add, trace.done_length,
-		 trace.done_remove, atomic_read(&trace.done_invoked),
-		 atomic_read(&trace.rcu_try_flip_1),
-		 atomic_read(&trace.rcu_try_flip_e1),
-		 trace.rcu_try_flip_i1, trace.rcu_try_flip_ie1,
-		 trace.rcu_try_flip_g1,
-		 trace.rcu_try_flip_a1, trace.rcu_try_flip_ae1,
-			 trace.rcu_try_flip_a2,
-		 trace.rcu_try_flip_z1, trace.rcu_try_flip_ze1,
-			 trace.rcu_try_flip_z2,
-		 trace.rcu_try_flip_m1, trace.rcu_try_flip_me1,
-			trace.rcu_try_flip_m2);
-	bcount = simple_read_from_buffer(buffer, count, ppos,
-			rcupreempt_trace_buf, strlen(rcupreempt_trace_buf));
-	mutex_unlock(&rcupreempt_trace_mutex);
-	return bcount;
-}
-
-static ssize_t rcugp_read(struct file *filp, char __user *buffer,
-				size_t count, loff_t *ppos)
-{
-	long oldgp = rcu_batches_completed();
-	ssize_t bcount;
-
-	mutex_lock(&rcupreempt_trace_mutex);
-	synchronize_rcu();
-	snprintf(rcupreempt_trace_buf, RCUPREEMPT_TRACE_BUF_SIZE,
-		"oldggp=%ld  newggp=%ld\n", oldgp, rcu_batches_completed());
-	bcount = simple_read_from_buffer(buffer, count, ppos,
-			rcupreempt_trace_buf, strlen(rcupreempt_trace_buf));
-	mutex_unlock(&rcupreempt_trace_mutex);
-	return bcount;
-}
-
-static ssize_t rcuctrs_read(struct file *filp, char __user *buffer,
-				size_t count, loff_t *ppos)
-{
-	int cnt = 0;
-	int cpu;
-	int f = rcu_batches_completed() & 0x1;
-	ssize_t bcount;
-
-	mutex_lock(&rcupreempt_trace_mutex);
-
-	cnt += snprintf(&rcupreempt_trace_buf[cnt], RCUPREEMPT_TRACE_BUF_SIZE,
-				"CPU last cur F M\n");
-	for_each_online_cpu(cpu) {
-		long *flipctr = rcupreempt_flipctr(cpu);
-		cnt += snprintf(&rcupreempt_trace_buf[cnt],
-				RCUPREEMPT_TRACE_BUF_SIZE - cnt,
-					"%3d %4ld %3ld %d %d\n",
-			       cpu,
-			       flipctr[!f],
-			       flipctr[f],
-			       rcupreempt_flip_flag(cpu),
-			       rcupreempt_mb_flag(cpu));
-	}
-	cnt += snprintf(&rcupreempt_trace_buf[cnt],
-			RCUPREEMPT_TRACE_BUF_SIZE - cnt,
-			"ggp = %ld, state = %s\n",
-			rcu_batches_completed(),
-			rcupreempt_try_flip_state_name());
-	cnt += snprintf(&rcupreempt_trace_buf[cnt],
-			RCUPREEMPT_TRACE_BUF_SIZE - cnt,
-			"\n");
-	bcount = simple_read_from_buffer(buffer, count, ppos,
-			rcupreempt_trace_buf, strlen(rcupreempt_trace_buf));
-	mutex_unlock(&rcupreempt_trace_mutex);
-	return bcount;
-}
-
-static struct file_operations rcustats_fops = {
-	.owner = THIS_MODULE,
-	.read = rcustats_read,
-};
-
-static struct file_operations rcugp_fops = {
-	.owner = THIS_MODULE,
-	.read = rcugp_read,
-};
-
-static struct file_operations rcuctrs_fops = {
-	.owner = THIS_MODULE,
-	.read = rcuctrs_read,
-};
-
-static struct dentry *rcudir, *statdir, *ctrsdir, *gpdir;
-static int rcupreempt_debugfs_init(void)
-{
-	rcudir = debugfs_create_dir("rcu", NULL);
-	if (!rcudir)
-		goto out;
-	statdir = debugfs_create_file("rcustats", 0444, rcudir,
-						NULL, &rcustats_fops);
-	if (!statdir)
-		goto free_out;
-
-	gpdir = debugfs_create_file("rcugp", 0444, rcudir, NULL, &rcugp_fops);
-	if (!gpdir)
-		goto free_out;
-
-	ctrsdir = debugfs_create_file("rcuctrs", 0444, rcudir,
-						NULL, &rcuctrs_fops);
-	if (!ctrsdir)
-		goto free_out;
-	return 0;
-free_out:
-	if (statdir)
-		debugfs_remove(statdir);
-	if (gpdir)
-		debugfs_remove(gpdir);
-	debugfs_remove(rcudir);
-out:
-	return 1;
-}
-
-static int __init rcupreempt_trace_init(void)
-{
-	int ret;
-
-	mutex_init(&rcupreempt_trace_mutex);
-	rcupreempt_trace_buf = kmalloc(RCUPREEMPT_TRACE_BUF_SIZE, GFP_KERNEL);
-	if (!rcupreempt_trace_buf)
-		return 1;
-	ret = rcupreempt_debugfs_init();
-	if (ret)
-		kfree(rcupreempt_trace_buf);
-	return ret;
-}
-
-static void __exit rcupreempt_trace_cleanup(void)
-{
-	debugfs_remove(statdir);
-	debugfs_remove(gpdir);
-	debugfs_remove(ctrsdir);
-	debugfs_remove(rcudir);
-	kfree(rcupreempt_trace_buf);
-}
-
-
-module_init(rcupreempt_trace_init);
-module_exit(rcupreempt_trace_cleanup);
diff --git a/kernel/rcutorture.c b/kernel/rcutorture.c
index 9b4a975a4b4a..697c0a0229d4 100644
--- a/kernel/rcutorture.c
+++ b/kernel/rcutorture.c
@@ -18,7 +18,7 @@
  * Copyright (C) IBM Corporation, 2005, 2006
  *
  * Authors: Paul E. McKenney <paulmck@us.ibm.com>
- *          Josh Triplett <josh@freedesktop.org>
+ *	  Josh Triplett <josh@freedesktop.org>
  *
  * See also:  Documentation/RCU/torture.txt
  */
@@ -50,7 +50,7 @@
 
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Paul E. McKenney <paulmck@us.ibm.com> and "
-              "Josh Triplett <josh@freedesktop.org>");
+	      "Josh Triplett <josh@freedesktop.org>");
 
 static int nreaders = -1;	/* # reader threads, defaults to 2*ncpus */
 static int nfakewriters = 4;	/* # fake writer threads */
@@ -110,8 +110,8 @@ struct rcu_torture {
 };
 
 static LIST_HEAD(rcu_torture_freelist);
-static struct rcu_torture *rcu_torture_current = NULL;
-static long rcu_torture_current_version = 0;
+static struct rcu_torture *rcu_torture_current;
+static long rcu_torture_current_version;
 static struct rcu_torture rcu_tortures[10 * RCU_TORTURE_PIPE_LEN];
 static DEFINE_SPINLOCK(rcu_torture_lock);
 static DEFINE_PER_CPU(long [RCU_TORTURE_PIPE_LEN + 1], rcu_torture_count) =
@@ -124,11 +124,11 @@ static atomic_t n_rcu_torture_alloc_fail;
 static atomic_t n_rcu_torture_free;
 static atomic_t n_rcu_torture_mberror;
 static atomic_t n_rcu_torture_error;
-static long n_rcu_torture_timers = 0;
+static long n_rcu_torture_timers;
 static struct list_head rcu_torture_removed;
 static cpumask_var_t shuffle_tmp_mask;
 
-static int stutter_pause_test = 0;
+static int stutter_pause_test;
 
 #if defined(MODULE) || defined(CONFIG_RCU_TORTURE_TEST_RUNNABLE)
 #define RCUTORTURE_RUNNABLE_INIT 1
@@ -257,17 +257,18 @@ struct rcu_torture_ops {
 	void (*init)(void);
 	void (*cleanup)(void);
 	int (*readlock)(void);
-	void (*readdelay)(struct rcu_random_state *rrsp);
+	void (*read_delay)(struct rcu_random_state *rrsp);
 	void (*readunlock)(int idx);
 	int (*completed)(void);
-	void (*deferredfree)(struct rcu_torture *p);
+	void (*deferred_free)(struct rcu_torture *p);
 	void (*sync)(void);
 	void (*cb_barrier)(void);
 	int (*stats)(char *page);
-	int irqcapable;
+	int irq_capable;
 	char *name;
 };
-static struct rcu_torture_ops *cur_ops = NULL;
+
+static struct rcu_torture_ops *cur_ops;
 
 /*
  * Definitions for rcu torture testing.
@@ -281,14 +282,17 @@ static int rcu_torture_read_lock(void) __acquires(RCU)
 
 static void rcu_read_delay(struct rcu_random_state *rrsp)
 {
-	long delay;
-	const long longdelay = 200;
+	const unsigned long shortdelay_us = 200;
+	const unsigned long longdelay_ms = 50;
 
-	/* We want there to be long-running readers, but not all the time. */
+	/* We want a short delay sometimes to make a reader delay the grace
+	 * period, and we want a long delay occasionally to trigger
+	 * force_quiescent_state. */
 
-	delay = rcu_random(rrsp) % (nrealreaders * 2 * longdelay);
-	if (!delay)
-		udelay(longdelay);
+	if (!(rcu_random(rrsp) % (nrealreaders * 2000 * longdelay_ms)))
+		mdelay(longdelay_ms);
+	if (!(rcu_random(rrsp) % (nrealreaders * 2 * shortdelay_us)))
+		udelay(shortdelay_us);
 }
 
 static void rcu_torture_read_unlock(int idx) __releases(RCU)
@@ -320,7 +324,7 @@ rcu_torture_cb(struct rcu_head *p)
 		rp->rtort_mbtest = 0;
 		rcu_torture_free(rp);
 	} else
-		cur_ops->deferredfree(rp);
+		cur_ops->deferred_free(rp);
 }
 
 static void rcu_torture_deferred_free(struct rcu_torture *p)
@@ -329,18 +333,18 @@ static void rcu_torture_deferred_free(struct rcu_torture *p)
 }
 
 static struct rcu_torture_ops rcu_ops = {
-	.init = NULL,
-	.cleanup = NULL,
-	.readlock = rcu_torture_read_lock,
-	.readdelay = rcu_read_delay,
-	.readunlock = rcu_torture_read_unlock,
-	.completed = rcu_torture_completed,
-	.deferredfree = rcu_torture_deferred_free,
-	.sync = synchronize_rcu,
-	.cb_barrier = rcu_barrier,
-	.stats = NULL,
-	.irqcapable = 1,
-	.name = "rcu"
+	.init		= NULL,
+	.cleanup	= NULL,
+	.readlock	= rcu_torture_read_lock,
+	.read_delay	= rcu_read_delay,
+	.readunlock	= rcu_torture_read_unlock,
+	.completed	= rcu_torture_completed,
+	.deferred_free	= rcu_torture_deferred_free,
+	.sync		= synchronize_rcu,
+	.cb_barrier	= rcu_barrier,
+	.stats		= NULL,
+	.irq_capable	= 1,
+	.name		= "rcu"
 };
 
 static void rcu_sync_torture_deferred_free(struct rcu_torture *p)
@@ -370,18 +374,18 @@ static void rcu_sync_torture_init(void)
 }
 
 static struct rcu_torture_ops rcu_sync_ops = {
-	.init = rcu_sync_torture_init,
-	.cleanup = NULL,
-	.readlock = rcu_torture_read_lock,
-	.readdelay = rcu_read_delay,
-	.readunlock = rcu_torture_read_unlock,
-	.completed = rcu_torture_completed,
-	.deferredfree = rcu_sync_torture_deferred_free,
-	.sync = synchronize_rcu,
-	.cb_barrier = NULL,
-	.stats = NULL,
-	.irqcapable = 1,
-	.name = "rcu_sync"
+	.init		= rcu_sync_torture_init,
+	.cleanup	= NULL,
+	.readlock	= rcu_torture_read_lock,
+	.read_delay	= rcu_read_delay,
+	.readunlock	= rcu_torture_read_unlock,
+	.completed	= rcu_torture_completed,
+	.deferred_free	= rcu_sync_torture_deferred_free,
+	.sync		= synchronize_rcu,
+	.cb_barrier	= NULL,
+	.stats		= NULL,
+	.irq_capable	= 1,
+	.name		= "rcu_sync"
 };
 
 /*
@@ -432,33 +436,33 @@ static void rcu_bh_torture_synchronize(void)
 }
 
 static struct rcu_torture_ops rcu_bh_ops = {
-	.init = NULL,
-	.cleanup = NULL,
-	.readlock = rcu_bh_torture_read_lock,
-	.readdelay = rcu_read_delay,  /* just reuse rcu's version. */
-	.readunlock = rcu_bh_torture_read_unlock,
-	.completed = rcu_bh_torture_completed,
-	.deferredfree = rcu_bh_torture_deferred_free,
-	.sync = rcu_bh_torture_synchronize,
-	.cb_barrier = rcu_barrier_bh,
-	.stats = NULL,
-	.irqcapable = 1,
-	.name = "rcu_bh"
+	.init		= NULL,
+	.cleanup	= NULL,
+	.readlock	= rcu_bh_torture_read_lock,
+	.read_delay	= rcu_read_delay,  /* just reuse rcu's version. */
+	.readunlock	= rcu_bh_torture_read_unlock,
+	.completed	= rcu_bh_torture_completed,
+	.deferred_free	= rcu_bh_torture_deferred_free,
+	.sync		= rcu_bh_torture_synchronize,
+	.cb_barrier	= rcu_barrier_bh,
+	.stats		= NULL,
+	.irq_capable	= 1,
+	.name		= "rcu_bh"
 };
 
 static struct rcu_torture_ops rcu_bh_sync_ops = {
-	.init = rcu_sync_torture_init,
-	.cleanup = NULL,
-	.readlock = rcu_bh_torture_read_lock,
-	.readdelay = rcu_read_delay,  /* just reuse rcu's version. */
-	.readunlock = rcu_bh_torture_read_unlock,
-	.completed = rcu_bh_torture_completed,
-	.deferredfree = rcu_sync_torture_deferred_free,
-	.sync = rcu_bh_torture_synchronize,
-	.cb_barrier = NULL,
-	.stats = NULL,
-	.irqcapable = 1,
-	.name = "rcu_bh_sync"
+	.init		= rcu_sync_torture_init,
+	.cleanup	= NULL,
+	.readlock	= rcu_bh_torture_read_lock,
+	.read_delay	= rcu_read_delay,  /* just reuse rcu's version. */
+	.readunlock	= rcu_bh_torture_read_unlock,
+	.completed	= rcu_bh_torture_completed,
+	.deferred_free	= rcu_sync_torture_deferred_free,
+	.sync		= rcu_bh_torture_synchronize,
+	.cb_barrier	= NULL,
+	.stats		= NULL,
+	.irq_capable	= 1,
+	.name		= "rcu_bh_sync"
 };
 
 /*
@@ -530,17 +534,17 @@ static int srcu_torture_stats(char *page)
 }
 
 static struct rcu_torture_ops srcu_ops = {
-	.init = srcu_torture_init,
-	.cleanup = srcu_torture_cleanup,
-	.readlock = srcu_torture_read_lock,
-	.readdelay = srcu_read_delay,
-	.readunlock = srcu_torture_read_unlock,
-	.completed = srcu_torture_completed,
-	.deferredfree = rcu_sync_torture_deferred_free,
-	.sync = srcu_torture_synchronize,
-	.cb_barrier = NULL,
-	.stats = srcu_torture_stats,
-	.name = "srcu"
+	.init		= srcu_torture_init,
+	.cleanup	= srcu_torture_cleanup,
+	.readlock	= srcu_torture_read_lock,
+	.read_delay	= srcu_read_delay,
+	.readunlock	= srcu_torture_read_unlock,
+	.completed	= srcu_torture_completed,
+	.deferred_free	= rcu_sync_torture_deferred_free,
+	.sync		= srcu_torture_synchronize,
+	.cb_barrier	= NULL,
+	.stats		= srcu_torture_stats,
+	.name		= "srcu"
 };
 
 /*
@@ -574,32 +578,47 @@ static void sched_torture_synchronize(void)
 }
 
 static struct rcu_torture_ops sched_ops = {
-	.init = rcu_sync_torture_init,
-	.cleanup = NULL,
-	.readlock = sched_torture_read_lock,
-	.readdelay = rcu_read_delay,  /* just reuse rcu's version. */
-	.readunlock = sched_torture_read_unlock,
-	.completed = sched_torture_completed,
-	.deferredfree = rcu_sched_torture_deferred_free,
-	.sync = sched_torture_synchronize,
-	.cb_barrier = rcu_barrier_sched,
-	.stats = NULL,
-	.irqcapable = 1,
-	.name = "sched"
+	.init		= rcu_sync_torture_init,
+	.cleanup	= NULL,
+	.readlock	= sched_torture_read_lock,
+	.read_delay	= rcu_read_delay,  /* just reuse rcu's version. */
+	.readunlock	= sched_torture_read_unlock,
+	.completed	= sched_torture_completed,
+	.deferred_free	= rcu_sched_torture_deferred_free,
+	.sync		= sched_torture_synchronize,
+	.cb_barrier	= rcu_barrier_sched,
+	.stats		= NULL,
+	.irq_capable	= 1,
+	.name		= "sched"
 };
 
 static struct rcu_torture_ops sched_ops_sync = {
-	.init = rcu_sync_torture_init,
-	.cleanup = NULL,
-	.readlock = sched_torture_read_lock,
-	.readdelay = rcu_read_delay,  /* just reuse rcu's version. */
-	.readunlock = sched_torture_read_unlock,
-	.completed = sched_torture_completed,
-	.deferredfree = rcu_sync_torture_deferred_free,
-	.sync = sched_torture_synchronize,
-	.cb_barrier = NULL,
-	.stats = NULL,
-	.name = "sched_sync"
+	.init		= rcu_sync_torture_init,
+	.cleanup	= NULL,
+	.readlock	= sched_torture_read_lock,
+	.read_delay	= rcu_read_delay,  /* just reuse rcu's version. */
+	.readunlock	= sched_torture_read_unlock,
+	.completed	= sched_torture_completed,
+	.deferred_free	= rcu_sync_torture_deferred_free,
+	.sync		= sched_torture_synchronize,
+	.cb_barrier	= NULL,
+	.stats		= NULL,
+	.name		= "sched_sync"
+};
+
+static struct rcu_torture_ops sched_expedited_ops = {
+	.init		= rcu_sync_torture_init,
+	.cleanup	= NULL,
+	.readlock	= sched_torture_read_lock,
+	.read_delay	= rcu_read_delay,  /* just reuse rcu's version. */
+	.readunlock	= sched_torture_read_unlock,
+	.completed	= sched_torture_completed,
+	.deferred_free	= rcu_sync_torture_deferred_free,
+	.sync		= synchronize_sched_expedited,
+	.cb_barrier	= NULL,
+	.stats		= rcu_expedited_torture_stats,
+	.irq_capable	= 1,
+	.name		= "sched_expedited"
 };
 
 /*
@@ -621,21 +640,22 @@ rcu_torture_writer(void *arg)
 
 	do {
 		schedule_timeout_uninterruptible(1);
-		if ((rp = rcu_torture_alloc()) == NULL)
+		rp = rcu_torture_alloc();
+		if (rp == NULL)
 			continue;
 		rp->rtort_pipe_count = 0;
 		udelay(rcu_random(&rand) & 0x3ff);
 		old_rp = rcu_torture_current;
 		rp->rtort_mbtest = 1;
 		rcu_assign_pointer(rcu_torture_current, rp);
-		smp_wmb();
+		smp_wmb(); /* Mods to old_rp must follow rcu_assign_pointer() */
 		if (old_rp) {
 			i = old_rp->rtort_pipe_count;
 			if (i > RCU_TORTURE_PIPE_LEN)
 				i = RCU_TORTURE_PIPE_LEN;
 			atomic_inc(&rcu_torture_wcount[i]);
 			old_rp->rtort_pipe_count++;
-			cur_ops->deferredfree(old_rp);
+			cur_ops->deferred_free(old_rp);
 		}
 		rcu_torture_current_version++;
 		oldbatch = cur_ops->completed();
@@ -700,7 +720,7 @@ static void rcu_torture_timer(unsigned long unused)
 	if (p->rtort_mbtest == 0)
 		atomic_inc(&n_rcu_torture_mberror);
 	spin_lock(&rand_lock);
-	cur_ops->readdelay(&rand);
+	cur_ops->read_delay(&rand);
 	n_rcu_torture_timers++;
 	spin_unlock(&rand_lock);
 	preempt_disable();
@@ -738,11 +758,11 @@ rcu_torture_reader(void *arg)
 
 	VERBOSE_PRINTK_STRING("rcu_torture_reader task started");
 	set_user_nice(current, 19);
-	if (irqreader && cur_ops->irqcapable)
+	if (irqreader && cur_ops->irq_capable)
 		setup_timer_on_stack(&t, rcu_torture_timer, 0);
 
 	do {
-		if (irqreader && cur_ops->irqcapable) {
+		if (irqreader && cur_ops->irq_capable) {
 			if (!timer_pending(&t))
 				mod_timer(&t, 1);
 		}
@@ -757,7 +777,7 @@ rcu_torture_reader(void *arg)
 		}
 		if (p->rtort_mbtest == 0)
 			atomic_inc(&n_rcu_torture_mberror);
-		cur_ops->readdelay(&rand);
+		cur_ops->read_delay(&rand);
 		preempt_disable();
 		pipe_count = p->rtort_pipe_count;
 		if (pipe_count > RCU_TORTURE_PIPE_LEN) {
@@ -778,7 +798,7 @@ rcu_torture_reader(void *arg)
 	} while (!kthread_should_stop() && fullstop == FULLSTOP_DONTSTOP);
 	VERBOSE_PRINTK_STRING("rcu_torture_reader task stopping");
 	rcutorture_shutdown_absorb("rcu_torture_reader");
-	if (irqreader && cur_ops->irqcapable)
+	if (irqreader && cur_ops->irq_capable)
 		del_timer_sync(&t);
 	while (!kthread_should_stop())
 		schedule_timeout_uninterruptible(1);
@@ -1078,6 +1098,7 @@ rcu_torture_init(void)
 	int firsterr = 0;
 	static struct rcu_torture_ops *torture_ops[] =
 		{ &rcu_ops, &rcu_sync_ops, &rcu_bh_ops, &rcu_bh_sync_ops,
+		  &sched_expedited_ops,
 		  &srcu_ops, &sched_ops, &sched_ops_sync, };
 
 	mutex_lock(&fullstop_mutex);
@@ -1092,7 +1113,7 @@ rcu_torture_init(void)
 		printk(KERN_ALERT "rcutorture: invalid torture type: \"%s\"\n",
 		       torture_type);
 		mutex_unlock(&fullstop_mutex);
-		return (-EINVAL);
+		return -EINVAL;
 	}
 	if (cur_ops->init)
 		cur_ops->init(); /* no "goto unwind" prior to this point!!! */
@@ -1143,7 +1164,7 @@ rcu_torture_init(void)
 		goto unwind;
 	}
 	fakewriter_tasks = kzalloc(nfakewriters * sizeof(fakewriter_tasks[0]),
-	                           GFP_KERNEL);
+				   GFP_KERNEL);
 	if (fakewriter_tasks == NULL) {
 		VERBOSE_PRINTK_ERRSTRING("out of memory");
 		firsterr = -ENOMEM;
@@ -1152,7 +1173,7 @@ rcu_torture_init(void)
 	for (i = 0; i < nfakewriters; i++) {
 		VERBOSE_PRINTK_STRING("Creating rcu_torture_fakewriter task");
 		fakewriter_tasks[i] = kthread_run(rcu_torture_fakewriter, NULL,
-		                                  "rcu_torture_fakewriter");
+						  "rcu_torture_fakewriter");
 		if (IS_ERR(fakewriter_tasks[i])) {
 			firsterr = PTR_ERR(fakewriter_tasks[i]);
 			VERBOSE_PRINTK_ERRSTRING("Failed to create fakewriter");
diff --git a/kernel/rcutree.c b/kernel/rcutree.c
index 7717b95c2027..f3077c0ab181 100644
--- a/kernel/rcutree.c
+++ b/kernel/rcutree.c
@@ -25,7 +25,7 @@
  * and inputs from Rusty Russell, Andrea Arcangeli and Andi Kleen.
  *
  * For detailed explanation of Read-Copy Update mechanism see -
- * 	Documentation/RCU
+ *	Documentation/RCU
  */
 #include <linux/types.h>
 #include <linux/kernel.h>
@@ -35,6 +35,7 @@
 #include <linux/rcupdate.h>
 #include <linux/interrupt.h>
 #include <linux/sched.h>
+#include <linux/nmi.h>
 #include <asm/atomic.h>
 #include <linux/bitops.h>
 #include <linux/module.h>
@@ -46,12 +47,7 @@
 #include <linux/mutex.h>
 #include <linux/time.h>
 
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
-static struct lock_class_key rcu_lock_key;
-struct lockdep_map rcu_lock_map =
-	STATIC_LOCKDEP_MAP_INIT("rcu_read_lock", &rcu_lock_key);
-EXPORT_SYMBOL_GPL(rcu_lock_map);
-#endif
+#include "rcutree.h"
 
 /* Data structures. */
 
@@ -63,39 +59,59 @@ EXPORT_SYMBOL_GPL(rcu_lock_map);
 		NUM_RCU_LVL_2, \
 		NUM_RCU_LVL_3, /* == MAX_RCU_LVLS */ \
 	}, \
-	.signaled = RCU_SIGNAL_INIT, \
+	.signaled = RCU_GP_IDLE, \
 	.gpnum = -300, \
 	.completed = -300, \
 	.onofflock = __SPIN_LOCK_UNLOCKED(&name.onofflock), \
+	.orphan_cbs_list = NULL, \
+	.orphan_cbs_tail = &name.orphan_cbs_list, \
+	.orphan_qlen = 0, \
 	.fqslock = __SPIN_LOCK_UNLOCKED(&name.fqslock), \
 	.n_force_qs = 0, \
 	.n_force_qs_ngp = 0, \
 }
 
-struct rcu_state rcu_state = RCU_STATE_INITIALIZER(rcu_state);
-DEFINE_PER_CPU(struct rcu_data, rcu_data);
+struct rcu_state rcu_sched_state = RCU_STATE_INITIALIZER(rcu_sched_state);
+DEFINE_PER_CPU(struct rcu_data, rcu_sched_data);
 
 struct rcu_state rcu_bh_state = RCU_STATE_INITIALIZER(rcu_bh_state);
 DEFINE_PER_CPU(struct rcu_data, rcu_bh_data);
 
+
+/*
+ * Return true if an RCU grace period is in progress.  The ACCESS_ONCE()s
+ * permit this function to be invoked without holding the root rcu_node
+ * structure's ->lock, but of course results can be subject to change.
+ */
+static int rcu_gp_in_progress(struct rcu_state *rsp)
+{
+	return ACCESS_ONCE(rsp->completed) != ACCESS_ONCE(rsp->gpnum);
+}
+
 /*
- * Increment the quiescent state counter.
- * The counter is a bit degenerated: We do not need to know
+ * Note a quiescent state.  Because 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.
+ * one since the start of the grace period, this just sets a flag.
  */
-void rcu_qsctr_inc(int cpu)
+void rcu_sched_qs(int cpu)
 {
-	struct rcu_data *rdp = &per_cpu(rcu_data, cpu);
-	rdp->passed_quiesc = 1;
+	struct rcu_data *rdp;
+
+	rdp = &per_cpu(rcu_sched_data, cpu);
 	rdp->passed_quiesc_completed = rdp->completed;
+	barrier();
+	rdp->passed_quiesc = 1;
+	rcu_preempt_note_context_switch(cpu);
 }
 
-void rcu_bh_qsctr_inc(int cpu)
+void rcu_bh_qs(int cpu)
 {
-	struct rcu_data *rdp = &per_cpu(rcu_bh_data, cpu);
-	rdp->passed_quiesc = 1;
+	struct rcu_data *rdp;
+
+	rdp = &per_cpu(rcu_bh_data, cpu);
 	rdp->passed_quiesc_completed = rdp->completed;
+	barrier();
+	rdp->passed_quiesc = 1;
 }
 
 #ifdef CONFIG_NO_HZ
@@ -109,16 +125,21 @@ static int blimit = 10;		/* Maximum callbacks per softirq. */
 static int qhimark = 10000;	/* If this many pending, ignore blimit. */
 static int qlowmark = 100;	/* Once only this many pending, use blimit. */
 
+module_param(blimit, int, 0);
+module_param(qhimark, int, 0);
+module_param(qlowmark, int, 0);
+
 static void force_quiescent_state(struct rcu_state *rsp, int relaxed);
+static int rcu_pending(int cpu);
 
 /*
- * Return the number of RCU batches processed thus far for debug & stats.
+ * Return the number of RCU-sched batches processed thus far for debug & stats.
  */
-long rcu_batches_completed(void)
+long rcu_batches_completed_sched(void)
 {
-	return rcu_state.completed;
+	return rcu_sched_state.completed;
 }
-EXPORT_SYMBOL_GPL(rcu_batches_completed);
+EXPORT_SYMBOL_GPL(rcu_batches_completed_sched);
 
 /*
  * Return the number of RCU BH batches processed thus far for debug & stats.
@@ -144,9 +165,7 @@ cpu_has_callbacks_ready_to_invoke(struct rcu_data *rdp)
 static int
 cpu_needs_another_gp(struct rcu_state *rsp, struct rcu_data *rdp)
 {
-	/* ACCESS_ONCE() because we are accessing outside of lock. */
-	return *rdp->nxttail[RCU_DONE_TAIL] &&
-	       ACCESS_ONCE(rsp->completed) == ACCESS_ONCE(rsp->gpnum);
+	return *rdp->nxttail[RCU_DONE_TAIL] && !rcu_gp_in_progress(rsp);
 }
 
 /*
@@ -181,6 +200,10 @@ static int rcu_implicit_offline_qs(struct rcu_data *rdp)
 		return 1;
 	}
 
+	/* If preemptable RCU, no point in sending reschedule IPI. */
+	if (rdp->preemptable)
+		return 0;
+
 	/* The CPU is online, so send it a reschedule IPI. */
 	if (rdp->cpu != smp_processor_id())
 		smp_send_reschedule(rdp->cpu);
@@ -193,7 +216,6 @@ static int rcu_implicit_offline_qs(struct rcu_data *rdp)
 #endif /* #ifdef CONFIG_SMP */
 
 #ifdef CONFIG_NO_HZ
-static DEFINE_RATELIMIT_STATE(rcu_rs, 10 * HZ, 5);
 
 /**
  * rcu_enter_nohz - inform RCU that current CPU is entering nohz
@@ -213,7 +235,7 @@ void rcu_enter_nohz(void)
 	rdtp = &__get_cpu_var(rcu_dynticks);
 	rdtp->dynticks++;
 	rdtp->dynticks_nesting--;
-	WARN_ON_RATELIMIT(rdtp->dynticks & 0x1, &rcu_rs);
+	WARN_ON_ONCE(rdtp->dynticks & 0x1);
 	local_irq_restore(flags);
 }
 
@@ -232,7 +254,7 @@ void rcu_exit_nohz(void)
 	rdtp = &__get_cpu_var(rcu_dynticks);
 	rdtp->dynticks++;
 	rdtp->dynticks_nesting++;
-	WARN_ON_RATELIMIT(!(rdtp->dynticks & 0x1), &rcu_rs);
+	WARN_ON_ONCE(!(rdtp->dynticks & 0x1));
 	local_irq_restore(flags);
 	smp_mb(); /* CPUs seeing ++ must see later RCU read-side crit sects */
 }
@@ -251,7 +273,7 @@ void rcu_nmi_enter(void)
 	if (rdtp->dynticks & 0x1)
 		return;
 	rdtp->dynticks_nmi++;
-	WARN_ON_RATELIMIT(!(rdtp->dynticks_nmi & 0x1), &rcu_rs);
+	WARN_ON_ONCE(!(rdtp->dynticks_nmi & 0x1));
 	smp_mb(); /* CPUs seeing ++ must see later RCU read-side crit sects */
 }
 
@@ -270,7 +292,7 @@ void rcu_nmi_exit(void)
 		return;
 	smp_mb(); /* CPUs seeing ++ must see prior RCU read-side crit sects */
 	rdtp->dynticks_nmi++;
-	WARN_ON_RATELIMIT(rdtp->dynticks_nmi & 0x1, &rcu_rs);
+	WARN_ON_ONCE(rdtp->dynticks_nmi & 0x1);
 }
 
 /**
@@ -286,7 +308,7 @@ void rcu_irq_enter(void)
 	if (rdtp->dynticks_nesting++)
 		return;
 	rdtp->dynticks++;
-	WARN_ON_RATELIMIT(!(rdtp->dynticks & 0x1), &rcu_rs);
+	WARN_ON_ONCE(!(rdtp->dynticks & 0x1));
 	smp_mb(); /* CPUs seeing ++ must see later RCU read-side crit sects */
 }
 
@@ -305,10 +327,10 @@ void rcu_irq_exit(void)
 		return;
 	smp_mb(); /* CPUs seeing ++ must see prior RCU read-side crit sects */
 	rdtp->dynticks++;
-	WARN_ON_RATELIMIT(rdtp->dynticks & 0x1, &rcu_rs);
+	WARN_ON_ONCE(rdtp->dynticks & 0x1);
 
 	/* If the interrupt queued a callback, get out of dyntick mode. */
-	if (__get_cpu_var(rcu_data).nxtlist ||
+	if (__get_cpu_var(rcu_sched_data).nxtlist ||
 	    __get_cpu_var(rcu_bh_data).nxtlist)
 		set_need_resched();
 }
@@ -337,7 +359,7 @@ static long dyntick_recall_completed(struct rcu_state *rsp)
 /*
  * Snapshot the specified CPU's dynticks counter so that we can later
  * credit them with an implicit quiescent state.  Return 1 if this CPU
- * is already in a quiescent state courtesy of dynticks idle mode.
+ * is in dynticks idle mode, which is an extended quiescent state.
  */
 static int dyntick_save_progress_counter(struct rcu_data *rdp)
 {
@@ -443,32 +465,39 @@ static void print_other_cpu_stall(struct rcu_state *rsp)
 	long delta;
 	unsigned long flags;
 	struct rcu_node *rnp = rcu_get_root(rsp);
-	struct rcu_node *rnp_cur = rsp->level[NUM_RCU_LVLS - 1];
-	struct rcu_node *rnp_end = &rsp->node[NUM_RCU_NODES];
 
 	/* Only let one CPU complain about others per time interval. */
 
 	spin_lock_irqsave(&rnp->lock, flags);
 	delta = jiffies - rsp->jiffies_stall;
-	if (delta < RCU_STALL_RAT_DELAY || rsp->gpnum == rsp->completed) {
+	if (delta < RCU_STALL_RAT_DELAY || !rcu_gp_in_progress(rsp)) {
 		spin_unlock_irqrestore(&rnp->lock, flags);
 		return;
 	}
 	rsp->jiffies_stall = jiffies + RCU_SECONDS_TILL_STALL_RECHECK;
+
+	/*
+	 * Now rat on any tasks that got kicked up to the root rcu_node
+	 * due to CPU offlining.
+	 */
+	rcu_print_task_stall(rnp);
 	spin_unlock_irqrestore(&rnp->lock, flags);
 
 	/* OK, time to rat on our buddy... */
 
 	printk(KERN_ERR "INFO: RCU detected CPU stalls:");
-	for (; rnp_cur < rnp_end; rnp_cur++) {
-		if (rnp_cur->qsmask == 0)
+	rcu_for_each_leaf_node(rsp, rnp) {
+		rcu_print_task_stall(rnp);
+		if (rnp->qsmask == 0)
 			continue;
-		for (cpu = 0; cpu <= rnp_cur->grphi - rnp_cur->grplo; cpu++)
-			if (rnp_cur->qsmask & (1UL << cpu))
-				printk(" %d", rnp_cur->grplo + cpu);
+		for (cpu = 0; cpu <= rnp->grphi - rnp->grplo; cpu++)
+			if (rnp->qsmask & (1UL << cpu))
+				printk(" %d", rnp->grplo + cpu);
 	}
 	printk(" (detected by %d, t=%ld jiffies)\n",
 	       smp_processor_id(), (long)(jiffies - rsp->gp_start));
+	trigger_all_cpu_backtrace();
+
 	force_quiescent_state(rsp, 0);  /* Kick them all. */
 }
 
@@ -479,12 +508,14 @@ static void print_cpu_stall(struct rcu_state *rsp)
 
 	printk(KERN_ERR "INFO: RCU detected CPU %d stall (t=%lu jiffies)\n",
 			smp_processor_id(), jiffies - rsp->gp_start);
-	dump_stack();
+	trigger_all_cpu_backtrace();
+
 	spin_lock_irqsave(&rnp->lock, flags);
 	if ((long)(jiffies - rsp->jiffies_stall) >= 0)
 		rsp->jiffies_stall =
 			jiffies + RCU_SECONDS_TILL_STALL_RECHECK;
 	spin_unlock_irqrestore(&rnp->lock, flags);
+
 	set_need_resched();  /* kick ourselves to get things going. */
 }
 
@@ -500,8 +531,7 @@ static void check_cpu_stall(struct rcu_state *rsp, struct rcu_data *rdp)
 		/* We haven't checked in, so go dump stack. */
 		print_cpu_stall(rsp);
 
-	} else if (rsp->gpnum != rsp->completed &&
-		   delta >= RCU_STALL_RAT_DELAY) {
+	} else if (rcu_gp_in_progress(rsp) && delta >= RCU_STALL_RAT_DELAY) {
 
 		/* They had two time units to dump stack, so complain. */
 		print_other_cpu_stall(rsp);
@@ -564,8 +594,6 @@ rcu_start_gp(struct rcu_state *rsp, unsigned long flags)
 {
 	struct rcu_data *rdp = rsp->rda[smp_processor_id()];
 	struct rcu_node *rnp = rcu_get_root(rsp);
-	struct rcu_node *rnp_cur;
-	struct rcu_node *rnp_end;
 
 	if (!cpu_needs_another_gp(rsp, rdp)) {
 		spin_unlock_irqrestore(&rnp->lock, flags);
@@ -574,6 +602,7 @@ rcu_start_gp(struct rcu_state *rsp, unsigned long flags)
 
 	/* Advance to a new grace period and initialize state. */
 	rsp->gpnum++;
+	WARN_ON_ONCE(rsp->signaled == RCU_GP_INIT);
 	rsp->signaled = RCU_GP_INIT; /* Hold off force_quiescent_state. */
 	rsp->jiffies_force_qs = jiffies + RCU_JIFFIES_TILL_FORCE_QS;
 	record_gp_stall_check_time(rsp);
@@ -581,16 +610,24 @@ rcu_start_gp(struct rcu_state *rsp, unsigned long flags)
 	note_new_gpnum(rsp, rdp);
 
 	/*
-	 * Because we are first, we know that all our callbacks will
-	 * be covered by this upcoming grace period, even the ones
-	 * that were registered arbitrarily recently.
+	 * Because this CPU just now started the new grace period, we know
+	 * that all of its callbacks will be covered by this upcoming grace
+	 * period, even the ones that were registered arbitrarily recently.
+	 * Therefore, advance all outstanding callbacks to RCU_WAIT_TAIL.
+	 *
+	 * Other CPUs cannot be sure exactly when the grace period started.
+	 * Therefore, their recently registered callbacks must pass through
+	 * an additional RCU_NEXT_READY stage, so that they will be handled
+	 * by the next RCU grace period.
 	 */
 	rdp->nxttail[RCU_NEXT_READY_TAIL] = rdp->nxttail[RCU_NEXT_TAIL];
 	rdp->nxttail[RCU_WAIT_TAIL] = rdp->nxttail[RCU_NEXT_TAIL];
 
 	/* Special-case the common single-level case. */
 	if (NUM_RCU_NODES == 1) {
+		rcu_preempt_check_blocked_tasks(rnp);
 		rnp->qsmask = rnp->qsmaskinit;
+		rnp->gpnum = rsp->gpnum;
 		rsp->signaled = RCU_SIGNAL_INIT; /* force_quiescent_state OK. */
 		spin_unlock_irqrestore(&rnp->lock, flags);
 		return;
@@ -603,45 +640,34 @@ rcu_start_gp(struct rcu_state *rsp, unsigned long flags)
 	spin_lock(&rsp->onofflock);  /* irqs already disabled. */
 
 	/*
-	 * Set the quiescent-state-needed bits in all the non-leaf RCU
-	 * nodes for all currently online CPUs.  This operation relies
-	 * on the layout of the hierarchy within the rsp->node[] array.
-	 * Note that other CPUs will access only the leaves of the
-	 * hierarchy, which still indicate that no grace period is in
-	 * progress.  In addition, we have excluded CPU-hotplug operations.
-	 *
-	 * We therefore do not need to hold any locks.  Any required
-	 * memory barriers will be supplied by the locks guarding the
-	 * leaf rcu_nodes in the hierarchy.
-	 */
-
-	rnp_end = rsp->level[NUM_RCU_LVLS - 1];
-	for (rnp_cur = &rsp->node[0]; rnp_cur < rnp_end; rnp_cur++)
-		rnp_cur->qsmask = rnp_cur->qsmaskinit;
-
-	/*
-	 * Now set up the leaf nodes.  Here we must be careful.  First,
-	 * we need to hold the lock in order to exclude other CPUs, which
-	 * might be contending for the leaf nodes' locks.  Second, as
-	 * soon as we initialize a given leaf node, its CPUs might run
-	 * up the rest of the hierarchy.  We must therefore acquire locks
-	 * for each node that we touch during this stage.  (But we still
-	 * are excluding CPU-hotplug operations.)
+	 * Set the quiescent-state-needed bits in all the rcu_node
+	 * structures for all currently online CPUs in breadth-first
+	 * order, starting from the root rcu_node structure.  This
+	 * operation relies on the layout of the hierarchy within the
+	 * rsp->node[] array.  Note that other CPUs will access only
+	 * the leaves of the hierarchy, which still indicate that no
+	 * grace period is in progress, at least until the corresponding
+	 * leaf node has been initialized.  In addition, we have excluded
+	 * CPU-hotplug operations.
 	 *
 	 * Note that the grace period cannot complete until we finish
 	 * the initialization process, as there will be at least one
 	 * qsmask bit set in the root node until that time, namely the
-	 * one corresponding to this CPU.
+	 * one corresponding to this CPU, due to the fact that we have
+	 * irqs disabled.
 	 */
-	rnp_end = &rsp->node[NUM_RCU_NODES];
-	rnp_cur = rsp->level[NUM_RCU_LVLS - 1];
-	for (; rnp_cur < rnp_end; rnp_cur++) {
-		spin_lock(&rnp_cur->lock);	/* irqs already disabled. */
-		rnp_cur->qsmask = rnp_cur->qsmaskinit;
-		spin_unlock(&rnp_cur->lock);	/* irqs already disabled. */
+	rcu_for_each_node_breadth_first(rsp, rnp) {
+		spin_lock(&rnp->lock);		/* irqs already disabled. */
+		rcu_preempt_check_blocked_tasks(rnp);
+		rnp->qsmask = rnp->qsmaskinit;
+		rnp->gpnum = rsp->gpnum;
+		spin_unlock(&rnp->lock);	/* irqs remain disabled. */
 	}
 
+	rnp = rcu_get_root(rsp);
+	spin_lock(&rnp->lock);			/* irqs already disabled. */
 	rsp->signaled = RCU_SIGNAL_INIT; /* force_quiescent_state now OK. */
+	spin_unlock(&rnp->lock);		/* irqs remain disabled. */
 	spin_unlock_irqrestore(&rsp->onofflock, flags);
 }
 
@@ -674,6 +700,21 @@ rcu_process_gp_end(struct rcu_state *rsp, struct rcu_data *rdp)
 }
 
 /*
+ * Clean up after the prior grace period and let rcu_start_gp() start up
+ * the next grace period if one is needed.  Note that the caller must
+ * hold rnp->lock, as required by rcu_start_gp(), which will release it.
+ */
+static void cpu_quiet_msk_finish(struct rcu_state *rsp, unsigned long flags)
+	__releases(rcu_get_root(rsp)->lock)
+{
+	WARN_ON_ONCE(!rcu_gp_in_progress(rsp));
+	rsp->completed = rsp->gpnum;
+	rsp->signaled = RCU_GP_IDLE;
+	rcu_process_gp_end(rsp, rsp->rda[smp_processor_id()]);
+	rcu_start_gp(rsp, flags);  /* releases root node's rnp->lock. */
+}
+
+/*
  * Similar to cpu_quiet(), for which it is a helper function.  Allows
  * a group of CPUs to be quieted at one go, though all the CPUs in the
  * group must be represented by the same leaf rcu_node structure.
@@ -685,6 +726,8 @@ cpu_quiet_msk(unsigned long mask, struct rcu_state *rsp, struct rcu_node *rnp,
 	      unsigned long flags)
 	__releases(rnp->lock)
 {
+	struct rcu_node *rnp_c;
+
 	/* Walk up the rcu_node hierarchy. */
 	for (;;) {
 		if (!(rnp->qsmask & mask)) {
@@ -694,7 +737,7 @@ cpu_quiet_msk(unsigned long mask, struct rcu_state *rsp, struct rcu_node *rnp,
 			return;
 		}
 		rnp->qsmask &= ~mask;
-		if (rnp->qsmask != 0) {
+		if (rnp->qsmask != 0 || rcu_preempted_readers(rnp)) {
 
 			/* Other bits still set at this level, so done. */
 			spin_unlock_irqrestore(&rnp->lock, flags);
@@ -708,28 +751,26 @@ cpu_quiet_msk(unsigned long mask, struct rcu_state *rsp, struct rcu_node *rnp,
 			break;
 		}
 		spin_unlock_irqrestore(&rnp->lock, flags);
+		rnp_c = rnp;
 		rnp = rnp->parent;
 		spin_lock_irqsave(&rnp->lock, flags);
+		WARN_ON_ONCE(rnp_c->qsmask);
 	}
 
 	/*
 	 * Get here if we are the last CPU to pass through a quiescent
-	 * state for this grace period.  Clean up and let rcu_start_gp()
-	 * start up the next grace period if one is needed.  Note that
-	 * we still hold rnp->lock, as required by rcu_start_gp(), which
-	 * will release it.
+	 * state for this grace period.  Invoke cpu_quiet_msk_finish()
+	 * to clean up and start the next grace period if one is needed.
 	 */
-	rsp->completed = rsp->gpnum;
-	rcu_process_gp_end(rsp, rsp->rda[smp_processor_id()]);
-	rcu_start_gp(rsp, flags);  /* releases rnp->lock. */
+	cpu_quiet_msk_finish(rsp, flags); /* releases rnp->lock. */
 }
 
 /*
  * Record a quiescent state for the specified CPU, which must either be
- * the current CPU or an offline CPU.  The lastcomp argument is used to
- * make sure we are still in the grace period of interest.  We don't want
- * to end the current grace period based on quiescent states detected in
- * an earlier grace period!
+ * the current CPU.  The lastcomp argument is used to make sure we are
+ * still in the grace period of interest.  We don't want to end the current
+ * grace period based on quiescent states detected in an earlier grace
+ * period!
  */
 static void
 cpu_quiet(int cpu, struct rcu_state *rsp, struct rcu_data *rdp, long lastcomp)
@@ -764,7 +805,6 @@ cpu_quiet(int cpu, struct rcu_state *rsp, struct rcu_data *rdp, long lastcomp)
 		 * This GP can't end until cpu checks in, so all of our
 		 * callbacks can be processed during the next GP.
 		 */
-		rdp = rsp->rda[smp_processor_id()];
 		rdp->nxttail[RCU_NEXT_READY_TAIL] = rdp->nxttail[RCU_NEXT_TAIL];
 
 		cpu_quiet_msk(mask, rsp, rnp, flags); /* releases rnp->lock */
@@ -805,67 +845,101 @@ rcu_check_quiescent_state(struct rcu_state *rsp, struct rcu_data *rdp)
 #ifdef CONFIG_HOTPLUG_CPU
 
 /*
+ * Move a dying CPU's RCU callbacks to the ->orphan_cbs_list for the
+ * specified flavor of RCU.  The callbacks will be adopted by the next
+ * _rcu_barrier() invocation or by the CPU_DEAD notifier, whichever
+ * comes first.  Because this is invoked from the CPU_DYING notifier,
+ * irqs are already disabled.
+ */
+static void rcu_send_cbs_to_orphanage(struct rcu_state *rsp)
+{
+	int i;
+	struct rcu_data *rdp = rsp->rda[smp_processor_id()];
+
+	if (rdp->nxtlist == NULL)
+		return;  /* irqs disabled, so comparison is stable. */
+	spin_lock(&rsp->onofflock);  /* irqs already disabled. */
+	*rsp->orphan_cbs_tail = rdp->nxtlist;
+	rsp->orphan_cbs_tail = rdp->nxttail[RCU_NEXT_TAIL];
+	rdp->nxtlist = NULL;
+	for (i = 0; i < RCU_NEXT_SIZE; i++)
+		rdp->nxttail[i] = &rdp->nxtlist;
+	rsp->orphan_qlen += rdp->qlen;
+	rdp->qlen = 0;
+	spin_unlock(&rsp->onofflock);  /* irqs remain disabled. */
+}
+
+/*
+ * Adopt previously orphaned RCU callbacks.
+ */
+static void rcu_adopt_orphan_cbs(struct rcu_state *rsp)
+{
+	unsigned long flags;
+	struct rcu_data *rdp;
+
+	spin_lock_irqsave(&rsp->onofflock, flags);
+	rdp = rsp->rda[smp_processor_id()];
+	if (rsp->orphan_cbs_list == NULL) {
+		spin_unlock_irqrestore(&rsp->onofflock, flags);
+		return;
+	}
+	*rdp->nxttail[RCU_NEXT_TAIL] = rsp->orphan_cbs_list;
+	rdp->nxttail[RCU_NEXT_TAIL] = rsp->orphan_cbs_tail;
+	rdp->qlen += rsp->orphan_qlen;
+	rsp->orphan_cbs_list = NULL;
+	rsp->orphan_cbs_tail = &rsp->orphan_cbs_list;
+	rsp->orphan_qlen = 0;
+	spin_unlock_irqrestore(&rsp->onofflock, flags);
+}
+
+/*
  * Remove the outgoing CPU from the bitmasks in the rcu_node hierarchy
  * and move all callbacks from the outgoing CPU to the current one.
  */
 static void __rcu_offline_cpu(int cpu, struct rcu_state *rsp)
 {
-	int i;
 	unsigned long flags;
 	long lastcomp;
 	unsigned long mask;
 	struct rcu_data *rdp = rsp->rda[cpu];
-	struct rcu_data *rdp_me;
 	struct rcu_node *rnp;
 
 	/* Exclude any attempts to start a new grace period. */
 	spin_lock_irqsave(&rsp->onofflock, flags);
 
 	/* Remove the outgoing CPU from the masks in the rcu_node hierarchy. */
-	rnp = rdp->mynode;
+	rnp = rdp->mynode;	/* this is the outgoing CPU's rnp. */
 	mask = rdp->grpmask;	/* rnp->grplo is constant. */
 	do {
 		spin_lock(&rnp->lock);		/* irqs already disabled. */
 		rnp->qsmaskinit &= ~mask;
 		if (rnp->qsmaskinit != 0) {
-			spin_unlock(&rnp->lock); /* irqs already disabled. */
+			spin_unlock(&rnp->lock); /* irqs remain disabled. */
 			break;
 		}
+
+		/*
+		 * If there was a task blocking the current grace period,
+		 * and if all CPUs have checked in, we need to propagate
+		 * the quiescent state up the rcu_node hierarchy.  But that
+		 * is inconvenient at the moment due to deadlock issues if
+		 * this should end the current grace period.  So set the
+		 * offlined CPU's bit in ->qsmask in order to force the
+		 * next force_quiescent_state() invocation to clean up this
+		 * mess in a deadlock-free manner.
+		 */
+		if (rcu_preempt_offline_tasks(rsp, rnp, rdp) && !rnp->qsmask)
+			rnp->qsmask |= mask;
+
 		mask = rnp->grpmask;
-		spin_unlock(&rnp->lock);	/* irqs already disabled. */
+		spin_unlock(&rnp->lock);	/* irqs remain disabled. */
 		rnp = rnp->parent;
 	} while (rnp != NULL);
 	lastcomp = rsp->completed;
 
-	spin_unlock(&rsp->onofflock);		/* irqs remain disabled. */
-
-	/* Being offline is a quiescent state, so go record it. */
-	cpu_quiet(cpu, rsp, rdp, lastcomp);
+	spin_unlock_irqrestore(&rsp->onofflock, flags);
 
-	/*
-	 * Move callbacks from the outgoing CPU to the running CPU.
-	 * Note that the outgoing CPU is now quiscent, so it is now
-	 * (uncharacteristically) safe to access it rcu_data structure.
-	 * Note also that we must carefully retain the order of the
-	 * outgoing CPU's callbacks in order for rcu_barrier() to work
-	 * correctly.  Finally, note that we start all the callbacks
-	 * afresh, even those that have passed through a grace period
-	 * and are therefore ready to invoke.  The theory is that hotplug
-	 * events are rare, and that if they are frequent enough to
-	 * indefinitely delay callbacks, you have far worse things to
-	 * be worrying about.
-	 */
-	rdp_me = rsp->rda[smp_processor_id()];
-	if (rdp->nxtlist != NULL) {
-		*rdp_me->nxttail[RCU_NEXT_TAIL] = rdp->nxtlist;
-		rdp_me->nxttail[RCU_NEXT_TAIL] = rdp->nxttail[RCU_NEXT_TAIL];
-		rdp->nxtlist = NULL;
-		for (i = 0; i < RCU_NEXT_SIZE; i++)
-			rdp->nxttail[i] = &rdp->nxtlist;
-		rdp_me->qlen += rdp->qlen;
-		rdp->qlen = 0;
-	}
-	local_irq_restore(flags);
+	rcu_adopt_orphan_cbs(rsp);
 }
 
 /*
@@ -876,12 +950,21 @@ static void __rcu_offline_cpu(int cpu, struct rcu_state *rsp)
  */
 static void rcu_offline_cpu(int cpu)
 {
-	__rcu_offline_cpu(cpu, &rcu_state);
+	__rcu_offline_cpu(cpu, &rcu_sched_state);
 	__rcu_offline_cpu(cpu, &rcu_bh_state);
+	rcu_preempt_offline_cpu(cpu);
 }
 
 #else /* #ifdef CONFIG_HOTPLUG_CPU */
 
+static void rcu_send_cbs_to_orphanage(struct rcu_state *rsp)
+{
+}
+
+static void rcu_adopt_orphan_cbs(struct rcu_state *rsp)
+{
+}
+
 static void rcu_offline_cpu(int cpu)
 {
 }
@@ -892,7 +975,7 @@ static void rcu_offline_cpu(int cpu)
  * Invoke any RCU callbacks that have made it to the end of their grace
  * period.  Thottle as specified by rdp->blimit.
  */
-static void rcu_do_batch(struct rcu_data *rdp)
+static void rcu_do_batch(struct rcu_state *rsp, struct rcu_data *rdp)
 {
 	unsigned long flags;
 	struct rcu_head *next, *list, **tail;
@@ -945,6 +1028,13 @@ static void rcu_do_batch(struct rcu_data *rdp)
 	if (rdp->blimit == LONG_MAX && rdp->qlen <= qlowmark)
 		rdp->blimit = blimit;
 
+	/* Reset ->qlen_last_fqs_check trigger if enough CBs have drained. */
+	if (rdp->qlen == 0 && rdp->qlen_last_fqs_check != 0) {
+		rdp->qlen_last_fqs_check = 0;
+		rdp->n_force_qs_snap = rsp->n_force_qs;
+	} else if (rdp->qlen < rdp->qlen_last_fqs_check - qhimark)
+		rdp->qlen_last_fqs_check = rdp->qlen;
+
 	local_irq_restore(flags);
 
 	/* Re-raise the RCU softirq if there are callbacks remaining. */
@@ -963,6 +1053,8 @@ static void rcu_do_batch(struct rcu_data *rdp)
  */
 void rcu_check_callbacks(int cpu, int user)
 {
+	if (!rcu_pending(cpu))
+		return; /* if nothing for RCU to do. */
 	if (user ||
 	    (idle_cpu(cpu) && rcu_scheduler_active &&
 	     !in_softirq() && hardirq_count() <= (1 << HARDIRQ_SHIFT))) {
@@ -971,17 +1063,16 @@ void rcu_check_callbacks(int cpu, int user)
 		 * Get here if this CPU took its interrupt from user
 		 * mode or from the idle loop, and if this is not a
 		 * nested interrupt.  In this case, the CPU is in
-		 * a quiescent state, so count it.
+		 * a quiescent state, so note it.
 		 *
 		 * No memory barrier is required here because both
-		 * rcu_qsctr_inc() and rcu_bh_qsctr_inc() reference
-		 * only CPU-local variables that other CPUs neither
-		 * access nor modify, at least not while the corresponding
-		 * CPU is online.
+		 * rcu_sched_qs() and rcu_bh_qs() reference only CPU-local
+		 * variables that other CPUs neither access nor modify,
+		 * at least not while the corresponding CPU is online.
 		 */
 
-		rcu_qsctr_inc(cpu);
-		rcu_bh_qsctr_inc(cpu);
+		rcu_sched_qs(cpu);
+		rcu_bh_qs(cpu);
 
 	} else if (!in_softirq()) {
 
@@ -989,11 +1080,12 @@ void rcu_check_callbacks(int cpu, int user)
 		 * Get here if this CPU did not take its interrupt from
 		 * softirq, in other words, if it is not interrupting
 		 * a rcu_bh read-side critical section.  This is an _bh
-		 * critical section, so count it.
+		 * critical section, so note it.
 		 */
 
-		rcu_bh_qsctr_inc(cpu);
+		rcu_bh_qs(cpu);
 	}
+	rcu_preempt_check_callbacks(cpu);
 	raise_softirq(RCU_SOFTIRQ);
 }
 
@@ -1012,33 +1104,32 @@ static int rcu_process_dyntick(struct rcu_state *rsp, long lastcomp,
 	int cpu;
 	unsigned long flags;
 	unsigned long mask;
-	struct rcu_node *rnp_cur = rsp->level[NUM_RCU_LVLS - 1];
-	struct rcu_node *rnp_end = &rsp->node[NUM_RCU_NODES];
+	struct rcu_node *rnp;
 
-	for (; rnp_cur < rnp_end; rnp_cur++) {
+	rcu_for_each_leaf_node(rsp, rnp) {
 		mask = 0;
-		spin_lock_irqsave(&rnp_cur->lock, flags);
+		spin_lock_irqsave(&rnp->lock, flags);
 		if (rsp->completed != lastcomp) {
-			spin_unlock_irqrestore(&rnp_cur->lock, flags);
+			spin_unlock_irqrestore(&rnp->lock, flags);
 			return 1;
 		}
-		if (rnp_cur->qsmask == 0) {
-			spin_unlock_irqrestore(&rnp_cur->lock, flags);
+		if (rnp->qsmask == 0) {
+			spin_unlock_irqrestore(&rnp->lock, flags);
 			continue;
 		}
-		cpu = rnp_cur->grplo;
+		cpu = rnp->grplo;
 		bit = 1;
-		for (; cpu <= rnp_cur->grphi; cpu++, bit <<= 1) {
-			if ((rnp_cur->qsmask & bit) != 0 && f(rsp->rda[cpu]))
+		for (; cpu <= rnp->grphi; cpu++, bit <<= 1) {
+			if ((rnp->qsmask & bit) != 0 && f(rsp->rda[cpu]))
 				mask |= bit;
 		}
 		if (mask != 0 && rsp->completed == lastcomp) {
 
-			/* cpu_quiet_msk() releases rnp_cur->lock. */
-			cpu_quiet_msk(mask, rsp, rnp_cur, flags);
+			/* cpu_quiet_msk() releases rnp->lock. */
+			cpu_quiet_msk(mask, rsp, rnp, flags);
 			continue;
 		}
-		spin_unlock_irqrestore(&rnp_cur->lock, flags);
+		spin_unlock_irqrestore(&rnp->lock, flags);
 	}
 	return 0;
 }
@@ -1054,7 +1145,7 @@ static void force_quiescent_state(struct rcu_state *rsp, int relaxed)
 	struct rcu_node *rnp = rcu_get_root(rsp);
 	u8 signaled;
 
-	if (ACCESS_ONCE(rsp->completed) == ACCESS_ONCE(rsp->gpnum))
+	if (!rcu_gp_in_progress(rsp))
 		return;  /* No grace period in progress, nothing to force. */
 	if (!spin_trylock_irqsave(&rsp->fqslock, flags)) {
 		rsp->n_force_qs_lh++; /* Inexact, can lose counts.  Tough! */
@@ -1075,9 +1166,10 @@ static void force_quiescent_state(struct rcu_state *rsp, int relaxed)
 	}
 	spin_unlock(&rnp->lock);
 	switch (signaled) {
+	case RCU_GP_IDLE:
 	case RCU_GP_INIT:
 
-		break; /* grace period still initializing, ignore. */
+		break; /* grace period idle or initializing, ignore. */
 
 	case RCU_SAVE_DYNTICK:
 
@@ -1091,7 +1183,8 @@ static void force_quiescent_state(struct rcu_state *rsp, int relaxed)
 
 		/* Update state, record completion counter. */
 		spin_lock(&rnp->lock);
-		if (lastcomp == rsp->completed) {
+		if (lastcomp == rsp->completed &&
+		    rsp->signaled == RCU_SAVE_DYNTICK) {
 			rsp->signaled = RCU_FORCE_QS;
 			dyntick_record_completed(rsp, lastcomp);
 		}
@@ -1132,6 +1225,8 @@ __rcu_process_callbacks(struct rcu_state *rsp, struct rcu_data *rdp)
 {
 	unsigned long flags;
 
+	WARN_ON_ONCE(rdp->beenonline == 0);
+
 	/*
 	 * If an RCU GP has gone long enough, go check for dyntick
 	 * idle CPUs and, if needed, send resched IPIs.
@@ -1155,7 +1250,7 @@ __rcu_process_callbacks(struct rcu_state *rsp, struct rcu_data *rdp)
 	}
 
 	/* If there are callbacks ready, invoke them. */
-	rcu_do_batch(rdp);
+	rcu_do_batch(rsp, rdp);
 }
 
 /*
@@ -1170,8 +1265,10 @@ static void rcu_process_callbacks(struct softirq_action *unused)
 	 */
 	smp_mb(); /* See above block comment. */
 
-	__rcu_process_callbacks(&rcu_state, &__get_cpu_var(rcu_data));
+	__rcu_process_callbacks(&rcu_sched_state,
+				&__get_cpu_var(rcu_sched_data));
 	__rcu_process_callbacks(&rcu_bh_state, &__get_cpu_var(rcu_bh_data));
+	rcu_preempt_process_callbacks();
 
 	/*
 	 * Memory references from any later RCU read-side critical sections
@@ -1209,7 +1306,7 @@ __call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu),
 	rdp->nxttail[RCU_NEXT_TAIL] = &head->next;
 
 	/* Start a new grace period if one not already started. */
-	if (ACCESS_ONCE(rsp->completed) == ACCESS_ONCE(rsp->gpnum)) {
+	if (!rcu_gp_in_progress(rsp)) {
 		unsigned long nestflag;
 		struct rcu_node *rnp_root = rcu_get_root(rsp);
 
@@ -1217,23 +1314,33 @@ __call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu),
 		rcu_start_gp(rsp, nestflag);  /* releases rnp_root->lock. */
 	}
 
-	/* Force the grace period if too many callbacks or too long waiting. */
-	if (unlikely(++rdp->qlen > qhimark)) {
+	/*
+	 * Force the grace period if too many callbacks or too long waiting.
+	 * Enforce hysteresis, and don't invoke force_quiescent_state()
+	 * if some other CPU has recently done so.  Also, don't bother
+	 * invoking force_quiescent_state() if the newly enqueued callback
+	 * is the only one waiting for a grace period to complete.
+	 */
+	if (unlikely(++rdp->qlen > rdp->qlen_last_fqs_check + qhimark)) {
 		rdp->blimit = LONG_MAX;
-		force_quiescent_state(rsp, 0);
+		if (rsp->n_force_qs == rdp->n_force_qs_snap &&
+		    *rdp->nxttail[RCU_DONE_TAIL] != head)
+			force_quiescent_state(rsp, 0);
+		rdp->n_force_qs_snap = rsp->n_force_qs;
+		rdp->qlen_last_fqs_check = rdp->qlen;
 	} else if ((long)(ACCESS_ONCE(rsp->jiffies_force_qs) - jiffies) < 0)
 		force_quiescent_state(rsp, 1);
 	local_irq_restore(flags);
 }
 
 /*
- * Queue an RCU callback for invocation after a grace period.
+ * Queue an RCU-sched callback for invocation after a grace period.
  */
-void call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu))
+void call_rcu_sched(struct rcu_head *head, void (*func)(struct rcu_head *rcu))
 {
-	__call_rcu(head, func, &rcu_state);
+	__call_rcu(head, func, &rcu_sched_state);
 }
-EXPORT_SYMBOL_GPL(call_rcu);
+EXPORT_SYMBOL_GPL(call_rcu_sched);
 
 /*
  * Queue an RCU for invocation after a quicker grace period.
@@ -1289,7 +1396,7 @@ static int __rcu_pending(struct rcu_state *rsp, struct rcu_data *rdp)
 	}
 
 	/* Has an RCU GP gone long enough to send resched IPIs &c? */
-	if (ACCESS_ONCE(rsp->completed) != ACCESS_ONCE(rsp->gpnum) &&
+	if (rcu_gp_in_progress(rsp) &&
 	    ((long)(ACCESS_ONCE(rsp->jiffies_force_qs) - jiffies) < 0)) {
 		rdp->n_rp_need_fqs++;
 		return 1;
@@ -1305,10 +1412,11 @@ static int __rcu_pending(struct rcu_state *rsp, struct rcu_data *rdp)
  * by the current CPU, returning 1 if so.  This function is part of the
  * RCU implementation; it is -not- an exported member of the RCU API.
  */
-int rcu_pending(int cpu)
+static int rcu_pending(int cpu)
 {
-	return __rcu_pending(&rcu_state, &per_cpu(rcu_data, cpu)) ||
-	       __rcu_pending(&rcu_bh_state, &per_cpu(rcu_bh_data, cpu));
+	return __rcu_pending(&rcu_sched_state, &per_cpu(rcu_sched_data, cpu)) ||
+	       __rcu_pending(&rcu_bh_state, &per_cpu(rcu_bh_data, cpu)) ||
+	       rcu_preempt_pending(cpu);
 }
 
 /*
@@ -1320,27 +1428,122 @@ int rcu_pending(int cpu)
 int rcu_needs_cpu(int cpu)
 {
 	/* RCU callbacks either ready or pending? */
-	return per_cpu(rcu_data, cpu).nxtlist ||
-	       per_cpu(rcu_bh_data, cpu).nxtlist;
+	return per_cpu(rcu_sched_data, cpu).nxtlist ||
+	       per_cpu(rcu_bh_data, cpu).nxtlist ||
+	       rcu_preempt_needs_cpu(cpu);
+}
+
+static DEFINE_PER_CPU(struct rcu_head, rcu_barrier_head) = {NULL};
+static atomic_t rcu_barrier_cpu_count;
+static DEFINE_MUTEX(rcu_barrier_mutex);
+static struct completion rcu_barrier_completion;
+
+static void rcu_barrier_callback(struct rcu_head *notused)
+{
+	if (atomic_dec_and_test(&rcu_barrier_cpu_count))
+		complete(&rcu_barrier_completion);
 }
 
 /*
- * Initialize a CPU's per-CPU RCU data.  We take this "scorched earth"
- * approach so that we don't have to worry about how long the CPU has
- * been gone, or whether it ever was online previously.  We do trust the
- * ->mynode field, as it is constant for a given struct rcu_data and
- * initialized during early boot.
- *
- * Note that only one online or offline event can be happening at a given
- * time.  Note also that we can accept some slop in the rsp->completed
- * access due to the fact that this CPU cannot possibly have any RCU
- * callbacks in flight yet.
+ * Called with preemption disabled, and from cross-cpu IRQ context.
  */
-static void __cpuinit
-rcu_init_percpu_data(int cpu, struct rcu_state *rsp)
+static void rcu_barrier_func(void *type)
+{
+	int cpu = smp_processor_id();
+	struct rcu_head *head = &per_cpu(rcu_barrier_head, cpu);
+	void (*call_rcu_func)(struct rcu_head *head,
+			      void (*func)(struct rcu_head *head));
+
+	atomic_inc(&rcu_barrier_cpu_count);
+	call_rcu_func = type;
+	call_rcu_func(head, rcu_barrier_callback);
+}
+
+/*
+ * Orchestrate the specified type of RCU barrier, waiting for all
+ * RCU callbacks of the specified type to complete.
+ */
+static void _rcu_barrier(struct rcu_state *rsp,
+			 void (*call_rcu_func)(struct rcu_head *head,
+					       void (*func)(struct rcu_head *head)))
+{
+	BUG_ON(in_interrupt());
+	/* Take mutex to serialize concurrent rcu_barrier() requests. */
+	mutex_lock(&rcu_barrier_mutex);
+	init_completion(&rcu_barrier_completion);
+	/*
+	 * Initialize rcu_barrier_cpu_count to 1, then invoke
+	 * rcu_barrier_func() on each CPU, so that each CPU also has
+	 * incremented rcu_barrier_cpu_count.  Only then is it safe to
+	 * decrement rcu_barrier_cpu_count -- otherwise the first CPU
+	 * might complete its grace period before all of the other CPUs
+	 * did their increment, causing this function to return too
+	 * early.
+	 */
+	atomic_set(&rcu_barrier_cpu_count, 1);
+	preempt_disable(); /* stop CPU_DYING from filling orphan_cbs_list */
+	rcu_adopt_orphan_cbs(rsp);
+	on_each_cpu(rcu_barrier_func, (void *)call_rcu_func, 1);
+	preempt_enable(); /* CPU_DYING can again fill orphan_cbs_list */
+	if (atomic_dec_and_test(&rcu_barrier_cpu_count))
+		complete(&rcu_barrier_completion);
+	wait_for_completion(&rcu_barrier_completion);
+	mutex_unlock(&rcu_barrier_mutex);
+}
+
+/**
+ * rcu_barrier_bh - Wait until all in-flight call_rcu_bh() callbacks complete.
+ */
+void rcu_barrier_bh(void)
+{
+	_rcu_barrier(&rcu_bh_state, call_rcu_bh);
+}
+EXPORT_SYMBOL_GPL(rcu_barrier_bh);
+
+/**
+ * rcu_barrier_sched - Wait for in-flight call_rcu_sched() callbacks.
+ */
+void rcu_barrier_sched(void)
+{
+	_rcu_barrier(&rcu_sched_state, call_rcu_sched);
+}
+EXPORT_SYMBOL_GPL(rcu_barrier_sched);
+
+/*
+ * Do boot-time initialization of a CPU's per-CPU RCU data.
+ */
+static void __init
+rcu_boot_init_percpu_data(int cpu, struct rcu_state *rsp)
 {
 	unsigned long flags;
 	int i;
+	struct rcu_data *rdp = rsp->rda[cpu];
+	struct rcu_node *rnp = rcu_get_root(rsp);
+
+	/* Set up local state, ensuring consistent view of global state. */
+	spin_lock_irqsave(&rnp->lock, flags);
+	rdp->grpmask = 1UL << (cpu - rdp->mynode->grplo);
+	rdp->nxtlist = NULL;
+	for (i = 0; i < RCU_NEXT_SIZE; i++)
+		rdp->nxttail[i] = &rdp->nxtlist;
+	rdp->qlen = 0;
+#ifdef CONFIG_NO_HZ
+	rdp->dynticks = &per_cpu(rcu_dynticks, cpu);
+#endif /* #ifdef CONFIG_NO_HZ */
+	rdp->cpu = cpu;
+	spin_unlock_irqrestore(&rnp->lock, flags);
+}
+
+/*
+ * Initialize a CPU's per-CPU RCU data.  Note that only one online or
+ * offline event can be happening at a given time.  Note also that we
+ * can accept some slop in the rsp->completed access due to the fact
+ * that this CPU cannot possibly have any RCU callbacks in flight yet.
+ */
+static void __cpuinit
+rcu_init_percpu_data(int cpu, struct rcu_state *rsp, int preemptable)
+{
+	unsigned long flags;
 	long lastcomp;
 	unsigned long mask;
 	struct rcu_data *rdp = rsp->rda[cpu];
@@ -1354,17 +1557,11 @@ rcu_init_percpu_data(int cpu, struct rcu_state *rsp)
 	rdp->passed_quiesc = 0;  /* We could be racing with new GP, */
 	rdp->qs_pending = 1;	 /*  so set up to respond to current GP. */
 	rdp->beenonline = 1;	 /* We have now been online. */
+	rdp->preemptable = preemptable;
 	rdp->passed_quiesc_completed = lastcomp - 1;
-	rdp->grpmask = 1UL << (cpu - rdp->mynode->grplo);
-	rdp->nxtlist = NULL;
-	for (i = 0; i < RCU_NEXT_SIZE; i++)
-		rdp->nxttail[i] = &rdp->nxtlist;
-	rdp->qlen = 0;
+	rdp->qlen_last_fqs_check = 0;
+	rdp->n_force_qs_snap = rsp->n_force_qs;
 	rdp->blimit = blimit;
-#ifdef CONFIG_NO_HZ
-	rdp->dynticks = &per_cpu(rcu_dynticks, cpu);
-#endif /* #ifdef CONFIG_NO_HZ */
-	rdp->cpu = cpu;
 	spin_unlock(&rnp->lock);		/* irqs remain disabled. */
 
 	/*
@@ -1387,34 +1584,21 @@ rcu_init_percpu_data(int cpu, struct rcu_state *rsp)
 		rnp = rnp->parent;
 	} while (rnp != NULL && !(rnp->qsmaskinit & mask));
 
-	spin_unlock(&rsp->onofflock);		/* irqs remain disabled. */
-
-	/*
-	 * A new grace period might start here.  If so, we will be part of
-	 * it, and its gpnum will be greater than ours, so we will
-	 * participate.  It is also possible for the gpnum to have been
-	 * incremented before this function was called, and the bitmasks
-	 * to not be filled out until now, in which case we will also
-	 * participate due to our gpnum being behind.
-	 */
-
-	/* Since it is coming online, the CPU is in a quiescent state. */
-	cpu_quiet(cpu, rsp, rdp, lastcomp);
-	local_irq_restore(flags);
+	spin_unlock_irqrestore(&rsp->onofflock, flags);
 }
 
 static void __cpuinit rcu_online_cpu(int cpu)
 {
-	rcu_init_percpu_data(cpu, &rcu_state);
-	rcu_init_percpu_data(cpu, &rcu_bh_state);
-	open_softirq(RCU_SOFTIRQ, rcu_process_callbacks);
+	rcu_init_percpu_data(cpu, &rcu_sched_state, 0);
+	rcu_init_percpu_data(cpu, &rcu_bh_state, 0);
+	rcu_preempt_init_percpu_data(cpu);
 }
 
 /*
- * Handle CPU online/offline notifcation events.
+ * Handle CPU online/offline notification events.
  */
-static int __cpuinit rcu_cpu_notify(struct notifier_block *self,
-				unsigned long action, void *hcpu)
+int __cpuinit rcu_cpu_notify(struct notifier_block *self,
+			     unsigned long action, void *hcpu)
 {
 	long cpu = (long)hcpu;
 
@@ -1423,6 +1607,22 @@ static int __cpuinit rcu_cpu_notify(struct notifier_block *self,
 	case CPU_UP_PREPARE_FROZEN:
 		rcu_online_cpu(cpu);
 		break;
+	case CPU_DYING:
+	case CPU_DYING_FROZEN:
+		/*
+		 * preempt_disable() in _rcu_barrier() prevents stop_machine(),
+		 * so when "on_each_cpu(rcu_barrier_func, (void *)type, 1);"
+		 * returns, all online cpus have queued rcu_barrier_func().
+		 * The dying CPU clears its cpu_online_mask bit and
+		 * moves all of its RCU callbacks to ->orphan_cbs_list
+		 * in the context of stop_machine(), so subsequent calls
+		 * to _rcu_barrier() will adopt these callbacks and only
+		 * then queue rcu_barrier_func() on all remaining CPUs.
+		 */
+		rcu_send_cbs_to_orphanage(&rcu_bh_state);
+		rcu_send_cbs_to_orphanage(&rcu_sched_state);
+		rcu_preempt_send_cbs_to_orphanage();
+		break;
 	case CPU_DEAD:
 	case CPU_DEAD_FROZEN:
 	case CPU_UP_CANCELED:
@@ -1485,7 +1685,9 @@ static void __init rcu_init_one(struct rcu_state *rsp)
 		cpustride *= rsp->levelspread[i];
 		rnp = rsp->level[i];
 		for (j = 0; j < rsp->levelcnt[i]; j++, rnp++) {
-			spin_lock_init(&rnp->lock);
+			if (rnp != rcu_get_root(rsp))
+				spin_lock_init(&rnp->lock);
+			rnp->gpnum = 0;
 			rnp->qsmask = 0;
 			rnp->qsmaskinit = 0;
 			rnp->grplo = j * cpustride;
@@ -1503,16 +1705,25 @@ static void __init rcu_init_one(struct rcu_state *rsp)
 					      j / rsp->levelspread[i - 1];
 			}
 			rnp->level = i;
+			INIT_LIST_HEAD(&rnp->blocked_tasks[0]);
+			INIT_LIST_HEAD(&rnp->blocked_tasks[1]);
 		}
 	}
+	spin_lock_init(&rcu_get_root(rsp)->lock);
 }
 
 /*
- * Helper macro for __rcu_init().  To be used nowhere else!
- * Assigns leaf node pointers into each CPU's rcu_data structure.
+ * Helper macro for __rcu_init() and __rcu_init_preempt().  To be used
+ * nowhere else!  Assigns leaf node pointers into each CPU's rcu_data
+ * structure.
  */
-#define RCU_DATA_PTR_INIT(rsp, rcu_data) \
+#define RCU_INIT_FLAVOR(rsp, rcu_data) \
 do { \
+	int i; \
+	int j; \
+	struct rcu_node *rnp; \
+	\
+	rcu_init_one(rsp); \
 	rnp = (rsp)->level[NUM_RCU_LVLS - 1]; \
 	j = 0; \
 	for_each_possible_cpu(i) { \
@@ -1520,34 +1731,20 @@ do { \
 			j++; \
 		per_cpu(rcu_data, i).mynode = &rnp[j]; \
 		(rsp)->rda[i] = &per_cpu(rcu_data, i); \
+		rcu_boot_init_percpu_data(i, rsp); \
 	} \
 } while (0)
 
-static struct notifier_block __cpuinitdata rcu_nb = {
-	.notifier_call	= rcu_cpu_notify,
-};
-
 void __init __rcu_init(void)
 {
-	int i;			/* All used by RCU_DATA_PTR_INIT(). */
-	int j;
-	struct rcu_node *rnp;
-
-	printk(KERN_INFO "Hierarchical RCU implementation.\n");
+	rcu_bootup_announce();
 #ifdef CONFIG_RCU_CPU_STALL_DETECTOR
 	printk(KERN_INFO "RCU-based detection of stalled CPUs is enabled.\n");
 #endif /* #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */
-	rcu_init_one(&rcu_state);
-	RCU_DATA_PTR_INIT(&rcu_state, rcu_data);
-	rcu_init_one(&rcu_bh_state);
-	RCU_DATA_PTR_INIT(&rcu_bh_state, rcu_bh_data);
-
-	for_each_online_cpu(i)
-		rcu_cpu_notify(&rcu_nb, CPU_UP_PREPARE, (void *)(long)i);
-	/* Register notifier for non-boot CPUs */
-	register_cpu_notifier(&rcu_nb);
+	RCU_INIT_FLAVOR(&rcu_sched_state, rcu_sched_data);
+	RCU_INIT_FLAVOR(&rcu_bh_state, rcu_bh_data);
+	__rcu_init_preempt();
+	open_softirq(RCU_SOFTIRQ, rcu_process_callbacks);
 }
 
-module_param(blimit, int, 0);
-module_param(qhimark, int, 0);
-module_param(qlowmark, int, 0);
+#include "rcutree_plugin.h"
diff --git a/kernel/rcutree.h b/kernel/rcutree.h
index 5e872bbf07f5..1899023b0962 100644
--- a/kernel/rcutree.h
+++ b/kernel/rcutree.h
@@ -1,10 +1,324 @@
+/*
+ * Read-Copy Update mechanism for mutual exclusion (tree-based version)
+ * Internal non-public definitions.
+ *
+ * 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 IBM Corporation, 2008
+ *
+ * Author: Ingo Molnar <mingo@elte.hu>
+ *	   Paul E. McKenney <paulmck@linux.vnet.ibm.com>
+ */
+
+#include <linux/cache.h>
+#include <linux/spinlock.h>
+#include <linux/threads.h>
+#include <linux/cpumask.h>
+#include <linux/seqlock.h>
+
+/*
+ * Define shape of hierarchy based on NR_CPUS and CONFIG_RCU_FANOUT.
+ * In theory, it should be possible to add more levels straightforwardly.
+ * In practice, this has not been tested, so there is probably some
+ * bug somewhere.
+ */
+#define MAX_RCU_LVLS 3
+#define RCU_FANOUT	      (CONFIG_RCU_FANOUT)
+#define RCU_FANOUT_SQ	      (RCU_FANOUT * RCU_FANOUT)
+#define RCU_FANOUT_CUBE	      (RCU_FANOUT_SQ * RCU_FANOUT)
+
+#if NR_CPUS <= RCU_FANOUT
+#  define NUM_RCU_LVLS	      1
+#  define NUM_RCU_LVL_0	      1
+#  define NUM_RCU_LVL_1	      (NR_CPUS)
+#  define NUM_RCU_LVL_2	      0
+#  define NUM_RCU_LVL_3	      0
+#elif NR_CPUS <= RCU_FANOUT_SQ
+#  define NUM_RCU_LVLS	      2
+#  define NUM_RCU_LVL_0	      1
+#  define NUM_RCU_LVL_1	      DIV_ROUND_UP(NR_CPUS, RCU_FANOUT)
+#  define NUM_RCU_LVL_2	      (NR_CPUS)
+#  define NUM_RCU_LVL_3	      0
+#elif NR_CPUS <= RCU_FANOUT_CUBE
+#  define NUM_RCU_LVLS	      3
+#  define NUM_RCU_LVL_0	      1
+#  define NUM_RCU_LVL_1	      DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_SQ)
+#  define NUM_RCU_LVL_2	      DIV_ROUND_UP(NR_CPUS, RCU_FANOUT)
+#  define NUM_RCU_LVL_3	      NR_CPUS
+#else
+# error "CONFIG_RCU_FANOUT insufficient for NR_CPUS"
+#endif /* #if (NR_CPUS) <= RCU_FANOUT */
+
+#define RCU_SUM (NUM_RCU_LVL_0 + NUM_RCU_LVL_1 + NUM_RCU_LVL_2 + NUM_RCU_LVL_3)
+#define NUM_RCU_NODES (RCU_SUM - NR_CPUS)
+
+/*
+ * Dynticks per-CPU state.
+ */
+struct rcu_dynticks {
+	int dynticks_nesting;	/* Track nesting level, sort of. */
+	int dynticks;		/* Even value for dynticks-idle, else odd. */
+	int dynticks_nmi;	/* Even value for either dynticks-idle or */
+				/*  not in nmi handler, else odd.  So this */
+				/*  remains even for nmi from irq handler. */
+};
+
+/*
+ * Definition for node within the RCU grace-period-detection hierarchy.
+ */
+struct rcu_node {
+	spinlock_t lock;	/* Root rcu_node's lock protects some */
+				/*  rcu_state fields as well as following. */
+	long	gpnum;		/* Current grace period for this node. */
+				/*  This will either be equal to or one */
+				/*  behind the root rcu_node's gpnum. */
+	unsigned long qsmask;	/* CPUs or groups that need to switch in */
+				/*  order for current grace period to proceed.*/
+				/*  In leaf rcu_node, each bit corresponds to */
+				/*  an rcu_data structure, otherwise, each */
+				/*  bit corresponds to a child rcu_node */
+				/*  structure. */
+	unsigned long qsmaskinit;
+				/* Per-GP initialization for qsmask. */
+	unsigned long grpmask;	/* Mask to apply to parent qsmask. */
+				/*  Only one bit will be set in this mask. */
+	int	grplo;		/* lowest-numbered CPU or group here. */
+	int	grphi;		/* highest-numbered CPU or group here. */
+	u8	grpnum;		/* CPU/group number for next level up. */
+	u8	level;		/* root is at level 0. */
+	struct rcu_node *parent;
+	struct list_head blocked_tasks[2];
+				/* Tasks blocked in RCU read-side critsect. */
+				/*  Grace period number (->gpnum) x blocked */
+				/*  by tasks on the (x & 0x1) element of the */
+				/*  blocked_tasks[] array. */
+} ____cacheline_internodealigned_in_smp;
+
+/*
+ * Do a full breadth-first scan of the rcu_node structures for the
+ * specified rcu_state structure.
+ */
+#define rcu_for_each_node_breadth_first(rsp, rnp) \
+	for ((rnp) = &(rsp)->node[0]; \
+	     (rnp) < &(rsp)->node[NUM_RCU_NODES]; (rnp)++)
+
+#define rcu_for_each_leaf_node(rsp, rnp) \
+	for ((rnp) = (rsp)->level[NUM_RCU_LVLS - 1]; \
+	     (rnp) < &(rsp)->node[NUM_RCU_NODES]; (rnp)++)
+
+/* Index values for nxttail array in struct rcu_data. */
+#define RCU_DONE_TAIL		0	/* Also RCU_WAIT head. */
+#define RCU_WAIT_TAIL		1	/* Also RCU_NEXT_READY head. */
+#define RCU_NEXT_READY_TAIL	2	/* Also RCU_NEXT head. */
+#define RCU_NEXT_TAIL		3
+#define RCU_NEXT_SIZE		4
+
+/* Per-CPU data for read-copy update. */
+struct rcu_data {
+	/* 1) quiescent-state and grace-period handling : */
+	long		completed;	/* Track rsp->completed gp number */
+					/*  in order to detect GP end. */
+	long		gpnum;		/* Highest gp number that this CPU */
+					/*  is aware of having started. */
+	long		passed_quiesc_completed;
+					/* Value of completed at time of qs. */
+	bool		passed_quiesc;	/* User-mode/idle loop etc. */
+	bool		qs_pending;	/* Core waits for quiesc state. */
+	bool		beenonline;	/* CPU online at least once. */
+	bool		preemptable;	/* Preemptable RCU? */
+	struct rcu_node *mynode;	/* This CPU's leaf of hierarchy */
+	unsigned long grpmask;		/* Mask to apply to leaf qsmask. */
+
+	/* 2) batch handling */
+	/*
+	 * If nxtlist is not NULL, it is partitioned as follows.
+	 * Any of the partitions might be empty, in which case the
+	 * pointer to that partition will be equal to the pointer for
+	 * the following partition.  When the list is empty, all of
+	 * the nxttail elements point to the ->nxtlist pointer itself,
+	 * which in that case is NULL.
+	 *
+	 * [nxtlist, *nxttail[RCU_DONE_TAIL]):
+	 *	Entries that batch # <= ->completed
+	 *	The grace period for these entries has completed, and
+	 *	the other grace-period-completed entries may be moved
+	 *	here temporarily in rcu_process_callbacks().
+	 * [*nxttail[RCU_DONE_TAIL], *nxttail[RCU_WAIT_TAIL]):
+	 *	Entries that batch # <= ->completed - 1: waiting for current GP
+	 * [*nxttail[RCU_WAIT_TAIL], *nxttail[RCU_NEXT_READY_TAIL]):
+	 *	Entries known to have arrived before current GP ended
+	 * [*nxttail[RCU_NEXT_READY_TAIL], *nxttail[RCU_NEXT_TAIL]):
+	 *	Entries that might have arrived after current GP ended
+	 *	Note that the value of *nxttail[RCU_NEXT_TAIL] will
+	 *	always be NULL, as this is the end of the list.
+	 */
+	struct rcu_head *nxtlist;
+	struct rcu_head **nxttail[RCU_NEXT_SIZE];
+	long		qlen;		/* # of queued callbacks */
+	long		qlen_last_fqs_check;
+					/* qlen at last check for QS forcing */
+	unsigned long	n_force_qs_snap;
+					/* did other CPU force QS recently? */
+	long		blimit;		/* Upper limit on a processed batch */
+
+#ifdef CONFIG_NO_HZ
+	/* 3) dynticks interface. */
+	struct rcu_dynticks *dynticks;	/* Shared per-CPU dynticks state. */
+	int dynticks_snap;		/* Per-GP tracking for dynticks. */
+	int dynticks_nmi_snap;		/* Per-GP tracking for dynticks_nmi. */
+#endif /* #ifdef CONFIG_NO_HZ */
+
+	/* 4) reasons this CPU needed to be kicked by force_quiescent_state */
+#ifdef CONFIG_NO_HZ
+	unsigned long dynticks_fqs;	/* Kicked due to dynticks idle. */
+#endif /* #ifdef CONFIG_NO_HZ */
+	unsigned long offline_fqs;	/* Kicked due to being offline. */
+	unsigned long resched_ipi;	/* Sent a resched IPI. */
+
+	/* 5) __rcu_pending() statistics. */
+	long n_rcu_pending;		/* rcu_pending() calls since boot. */
+	long n_rp_qs_pending;
+	long n_rp_cb_ready;
+	long n_rp_cpu_needs_gp;
+	long n_rp_gp_completed;
+	long n_rp_gp_started;
+	long n_rp_need_fqs;
+	long n_rp_need_nothing;
+
+	int cpu;
+};
+
+/* Values for signaled field in struct rcu_state. */
+#define RCU_GP_IDLE		0	/* No grace period in progress. */
+#define RCU_GP_INIT		1	/* Grace period being initialized. */
+#define RCU_SAVE_DYNTICK	2	/* Need to scan dyntick state. */
+#define RCU_FORCE_QS		3	/* Need to force quiescent state. */
+#ifdef CONFIG_NO_HZ
+#define RCU_SIGNAL_INIT		RCU_SAVE_DYNTICK
+#else /* #ifdef CONFIG_NO_HZ */
+#define RCU_SIGNAL_INIT		RCU_FORCE_QS
+#endif /* #else #ifdef CONFIG_NO_HZ */
+
+#define RCU_JIFFIES_TILL_FORCE_QS	 3	/* for rsp->jiffies_force_qs */
+#ifdef CONFIG_RCU_CPU_STALL_DETECTOR
+#define RCU_SECONDS_TILL_STALL_CHECK   (10 * HZ)  /* for rsp->jiffies_stall */
+#define RCU_SECONDS_TILL_STALL_RECHECK (30 * HZ)  /* for rsp->jiffies_stall */
+#define RCU_STALL_RAT_DELAY		2	  /* Allow other CPUs time */
+						  /*  to take at least one */
+						  /*  scheduling clock irq */
+						  /*  before ratting on them. */
+
+#endif /* #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */
+
+/*
+ * RCU global state, including node hierarchy.  This hierarchy is
+ * represented in "heap" form in a dense array.  The root (first level)
+ * of the hierarchy is in ->node[0] (referenced by ->level[0]), the second
+ * level in ->node[1] through ->node[m] (->node[1] referenced by ->level[1]),
+ * and the third level in ->node[m+1] and following (->node[m+1] referenced
+ * by ->level[2]).  The number of levels is determined by the number of
+ * CPUs and by CONFIG_RCU_FANOUT.  Small systems will have a "hierarchy"
+ * consisting of a single rcu_node.
+ */
+struct rcu_state {
+	struct rcu_node node[NUM_RCU_NODES];	/* Hierarchy. */
+	struct rcu_node *level[NUM_RCU_LVLS];	/* Hierarchy levels. */
+	u32 levelcnt[MAX_RCU_LVLS + 1];		/* # nodes in each level. */
+	u8 levelspread[NUM_RCU_LVLS];		/* kids/node in each level. */
+	struct rcu_data *rda[NR_CPUS];		/* array of rdp pointers. */
+
+	/* The following fields are guarded by the root rcu_node's lock. */
+
+	u8	signaled ____cacheline_internodealigned_in_smp;
+						/* Force QS state. */
+	long	gpnum;				/* Current gp number. */
+	long	completed;			/* # of last completed gp. */
+
+	/* End  of fields guarded by root rcu_node's lock. */
+
+	spinlock_t onofflock;			/* exclude on/offline and */
+						/*  starting new GP.  Also */
+						/*  protects the following */
+						/*  orphan_cbs fields. */
+	struct rcu_head *orphan_cbs_list;	/* list of rcu_head structs */
+						/*  orphaned by all CPUs in */
+						/*  a given leaf rcu_node */
+						/*  going offline. */
+	struct rcu_head **orphan_cbs_tail;	/* And tail pointer. */
+	long orphan_qlen;			/* Number of orphaned cbs. */
+	spinlock_t fqslock;			/* Only one task forcing */
+						/*  quiescent states. */
+	unsigned long jiffies_force_qs;		/* Time at which to invoke */
+						/*  force_quiescent_state(). */
+	unsigned long n_force_qs;		/* Number of calls to */
+						/*  force_quiescent_state(). */
+	unsigned long n_force_qs_lh;		/* ~Number of calls leaving */
+						/*  due to lock unavailable. */
+	unsigned long n_force_qs_ngp;		/* Number of calls leaving */
+						/*  due to no GP active. */
+#ifdef CONFIG_RCU_CPU_STALL_DETECTOR
+	unsigned long gp_start;			/* Time at which GP started, */
+						/*  but in jiffies. */
+	unsigned long jiffies_stall;		/* Time at which to check */
+						/*  for CPU stalls. */
+#endif /* #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */
+#ifdef CONFIG_NO_HZ
+	long dynticks_completed;		/* Value of completed @ snap. */
+#endif /* #ifdef CONFIG_NO_HZ */
+};
+
+#ifdef RCU_TREE_NONCORE
 
 /*
  * RCU implementation internal declarations:
  */
-extern struct rcu_state rcu_state;
-DECLARE_PER_CPU(struct rcu_data, rcu_data);
+extern struct rcu_state rcu_sched_state;
+DECLARE_PER_CPU(struct rcu_data, rcu_sched_data);
 
 extern struct rcu_state rcu_bh_state;
 DECLARE_PER_CPU(struct rcu_data, rcu_bh_data);
 
+#ifdef CONFIG_TREE_PREEMPT_RCU
+extern struct rcu_state rcu_preempt_state;
+DECLARE_PER_CPU(struct rcu_data, rcu_preempt_data);
+#endif /* #ifdef CONFIG_TREE_PREEMPT_RCU */
+
+#else /* #ifdef RCU_TREE_NONCORE */
+
+/* Forward declarations for rcutree_plugin.h */
+static inline void rcu_bootup_announce(void);
+long rcu_batches_completed(void);
+static void rcu_preempt_note_context_switch(int cpu);
+static int rcu_preempted_readers(struct rcu_node *rnp);
+#ifdef CONFIG_RCU_CPU_STALL_DETECTOR
+static void rcu_print_task_stall(struct rcu_node *rnp);
+#endif /* #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */
+static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp);
+#ifdef CONFIG_HOTPLUG_CPU
+static int rcu_preempt_offline_tasks(struct rcu_state *rsp,
+				     struct rcu_node *rnp,
+				     struct rcu_data *rdp);
+static void rcu_preempt_offline_cpu(int cpu);
+#endif /* #ifdef CONFIG_HOTPLUG_CPU */
+static void rcu_preempt_check_callbacks(int cpu);
+static void rcu_preempt_process_callbacks(void);
+void call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu));
+static int rcu_preempt_pending(int cpu);
+static int rcu_preempt_needs_cpu(int cpu);
+static void __cpuinit rcu_preempt_init_percpu_data(int cpu);
+static void rcu_preempt_send_cbs_to_orphanage(void);
+static void __init __rcu_init_preempt(void);
+
+#endif /* #else #ifdef RCU_TREE_NONCORE */
diff --git a/kernel/rcutree_plugin.h b/kernel/rcutree_plugin.h
new file mode 100644
index 000000000000..ef2a58c2b9d5
--- /dev/null
+++ b/kernel/rcutree_plugin.h
@@ -0,0 +1,645 @@
+/*
+ * Read-Copy Update mechanism for mutual exclusion (tree-based version)
+ * Internal non-public definitions that provide either classic
+ * or preemptable semantics.
+ *
+ * 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 Red Hat, 2009
+ * Copyright IBM Corporation, 2009
+ *
+ * Author: Ingo Molnar <mingo@elte.hu>
+ *	   Paul E. McKenney <paulmck@linux.vnet.ibm.com>
+ */
+
+
+#ifdef CONFIG_TREE_PREEMPT_RCU
+
+struct rcu_state rcu_preempt_state = RCU_STATE_INITIALIZER(rcu_preempt_state);
+DEFINE_PER_CPU(struct rcu_data, rcu_preempt_data);
+
+/*
+ * Tell them what RCU they are running.
+ */
+static inline void rcu_bootup_announce(void)
+{
+	printk(KERN_INFO
+	       "Experimental preemptable hierarchical RCU implementation.\n");
+}
+
+/*
+ * Return the number of RCU-preempt batches processed thus far
+ * for debug and statistics.
+ */
+long rcu_batches_completed_preempt(void)
+{
+	return rcu_preempt_state.completed;
+}
+EXPORT_SYMBOL_GPL(rcu_batches_completed_preempt);
+
+/*
+ * Return the number of RCU batches processed thus far for debug & stats.
+ */
+long rcu_batches_completed(void)
+{
+	return rcu_batches_completed_preempt();
+}
+EXPORT_SYMBOL_GPL(rcu_batches_completed);
+
+/*
+ * Record a preemptable-RCU quiescent state for the specified CPU.  Note
+ * that this just means that the task currently running on the CPU is
+ * not in a quiescent state.  There might be any number of tasks blocked
+ * while in an RCU read-side critical section.
+ */
+static void rcu_preempt_qs(int cpu)
+{
+	struct rcu_data *rdp = &per_cpu(rcu_preempt_data, cpu);
+	rdp->passed_quiesc_completed = rdp->completed;
+	barrier();
+	rdp->passed_quiesc = 1;
+}
+
+/*
+ * We have entered the scheduler, and the current task might soon be
+ * context-switched away from.  If this task is in an RCU read-side
+ * critical section, we will no longer be able to rely on the CPU to
+ * record that fact, so we enqueue the task on the appropriate entry
+ * of the blocked_tasks[] array.  The task will dequeue itself when
+ * it exits the outermost enclosing RCU read-side critical section.
+ * Therefore, the current grace period cannot be permitted to complete
+ * until the blocked_tasks[] entry indexed by the low-order bit of
+ * rnp->gpnum empties.
+ *
+ * Caller must disable preemption.
+ */
+static void rcu_preempt_note_context_switch(int cpu)
+{
+	struct task_struct *t = current;
+	unsigned long flags;
+	int phase;
+	struct rcu_data *rdp;
+	struct rcu_node *rnp;
+
+	if (t->rcu_read_lock_nesting &&
+	    (t->rcu_read_unlock_special & RCU_READ_UNLOCK_BLOCKED) == 0) {
+
+		/* Possibly blocking in an RCU read-side critical section. */
+		rdp = rcu_preempt_state.rda[cpu];
+		rnp = rdp->mynode;
+		spin_lock_irqsave(&rnp->lock, flags);
+		t->rcu_read_unlock_special |= RCU_READ_UNLOCK_BLOCKED;
+		t->rcu_blocked_node = rnp;
+
+		/*
+		 * If this CPU has already checked in, then this task
+		 * will hold up the next grace period rather than the
+		 * current grace period.  Queue the task accordingly.
+		 * If the task is queued for the current grace period
+		 * (i.e., this CPU has not yet passed through a quiescent
+		 * state for the current grace period), then as long
+		 * as that task remains queued, the current grace period
+		 * cannot end.
+		 *
+		 * But first, note that the current CPU must still be
+		 * on line!
+		 */
+		WARN_ON_ONCE((rdp->grpmask & rnp->qsmaskinit) == 0);
+		WARN_ON_ONCE(!list_empty(&t->rcu_node_entry));
+		phase = (rnp->gpnum + !(rnp->qsmask & rdp->grpmask)) & 0x1;
+		list_add(&t->rcu_node_entry, &rnp->blocked_tasks[phase]);
+		spin_unlock_irqrestore(&rnp->lock, flags);
+	}
+
+	/*
+	 * Either we were not in an RCU read-side critical section to
+	 * begin with, or we have now recorded that critical section
+	 * globally.  Either way, we can now note a quiescent state
+	 * for this CPU.  Again, if we were in an RCU read-side critical
+	 * section, and if that critical section was blocking the current
+	 * grace period, then the fact that the task has been enqueued
+	 * means that we continue to block the current grace period.
+	 */
+	rcu_preempt_qs(cpu);
+	local_irq_save(flags);
+	t->rcu_read_unlock_special &= ~RCU_READ_UNLOCK_NEED_QS;
+	local_irq_restore(flags);
+}
+
+/*
+ * Tree-preemptable RCU implementation for rcu_read_lock().
+ * Just increment ->rcu_read_lock_nesting, shared state will be updated
+ * if we block.
+ */
+void __rcu_read_lock(void)
+{
+	ACCESS_ONCE(current->rcu_read_lock_nesting)++;
+	barrier();  /* needed if we ever invoke rcu_read_lock in rcutree.c */
+}
+EXPORT_SYMBOL_GPL(__rcu_read_lock);
+
+/*
+ * Check for preempted RCU readers blocking the current grace period
+ * for the specified rcu_node structure.  If the caller needs a reliable
+ * answer, it must hold the rcu_node's ->lock.
+ */
+static int rcu_preempted_readers(struct rcu_node *rnp)
+{
+	return !list_empty(&rnp->blocked_tasks[rnp->gpnum & 0x1]);
+}
+
+static void rcu_read_unlock_special(struct task_struct *t)
+{
+	int empty;
+	unsigned long flags;
+	unsigned long mask;
+	struct rcu_node *rnp;
+	int special;
+
+	/* NMI handlers cannot block and cannot safely manipulate state. */
+	if (in_nmi())
+		return;
+
+	local_irq_save(flags);
+
+	/*
+	 * If RCU core is waiting for this CPU to exit critical section,
+	 * let it know that we have done so.
+	 */
+	special = t->rcu_read_unlock_special;
+	if (special & RCU_READ_UNLOCK_NEED_QS) {
+		t->rcu_read_unlock_special &= ~RCU_READ_UNLOCK_NEED_QS;
+		rcu_preempt_qs(smp_processor_id());
+	}
+
+	/* Hardware IRQ handlers cannot block. */
+	if (in_irq()) {
+		local_irq_restore(flags);
+		return;
+	}
+
+	/* Clean up if blocked during RCU read-side critical section. */
+	if (special & RCU_READ_UNLOCK_BLOCKED) {
+		t->rcu_read_unlock_special &= ~RCU_READ_UNLOCK_BLOCKED;
+
+		/*
+		 * Remove this task from the list it blocked on.  The
+		 * task can migrate while we acquire the lock, but at
+		 * most one time.  So at most two passes through loop.
+		 */
+		for (;;) {
+			rnp = t->rcu_blocked_node;
+			spin_lock(&rnp->lock);  /* irqs already disabled. */
+			if (rnp == t->rcu_blocked_node)
+				break;
+			spin_unlock(&rnp->lock);  /* irqs remain disabled. */
+		}
+		empty = !rcu_preempted_readers(rnp);
+		list_del_init(&t->rcu_node_entry);
+		t->rcu_blocked_node = NULL;
+
+		/*
+		 * If this was the last task on the current list, and if
+		 * we aren't waiting on any CPUs, report the quiescent state.
+		 * Note that both cpu_quiet_msk_finish() and cpu_quiet_msk()
+		 * drop rnp->lock and restore irq.
+		 */
+		if (!empty && rnp->qsmask == 0 &&
+		    !rcu_preempted_readers(rnp)) {
+			struct rcu_node *rnp_p;
+
+			if (rnp->parent == NULL) {
+				/* Only one rcu_node in the tree. */
+				cpu_quiet_msk_finish(&rcu_preempt_state, flags);
+				return;
+			}
+			/* Report up the rest of the hierarchy. */
+			mask = rnp->grpmask;
+			spin_unlock_irqrestore(&rnp->lock, flags);
+			rnp_p = rnp->parent;
+			spin_lock_irqsave(&rnp_p->lock, flags);
+			WARN_ON_ONCE(rnp->qsmask);
+			cpu_quiet_msk(mask, &rcu_preempt_state, rnp_p, flags);
+			return;
+		}
+		spin_unlock(&rnp->lock);
+	}
+	local_irq_restore(flags);
+}
+
+/*
+ * Tree-preemptable RCU implementation for rcu_read_unlock().
+ * Decrement ->rcu_read_lock_nesting.  If the result is zero (outermost
+ * rcu_read_unlock()) and ->rcu_read_unlock_special is non-zero, then
+ * invoke rcu_read_unlock_special() to clean up after a context switch
+ * in an RCU read-side critical section and other special cases.
+ */
+void __rcu_read_unlock(void)
+{
+	struct task_struct *t = current;
+
+	barrier();  /* needed if we ever invoke rcu_read_unlock in rcutree.c */
+	if (--ACCESS_ONCE(t->rcu_read_lock_nesting) == 0 &&
+	    unlikely(ACCESS_ONCE(t->rcu_read_unlock_special)))
+		rcu_read_unlock_special(t);
+}
+EXPORT_SYMBOL_GPL(__rcu_read_unlock);
+
+#ifdef CONFIG_RCU_CPU_STALL_DETECTOR
+
+/*
+ * Scan the current list of tasks blocked within RCU read-side critical
+ * sections, printing out the tid of each.
+ */
+static void rcu_print_task_stall(struct rcu_node *rnp)
+{
+	unsigned long flags;
+	struct list_head *lp;
+	int phase;
+	struct task_struct *t;
+
+	if (rcu_preempted_readers(rnp)) {
+		spin_lock_irqsave(&rnp->lock, flags);
+		phase = rnp->gpnum & 0x1;
+		lp = &rnp->blocked_tasks[phase];
+		list_for_each_entry(t, lp, rcu_node_entry)
+			printk(" P%d", t->pid);
+		spin_unlock_irqrestore(&rnp->lock, flags);
+	}
+}
+
+#endif /* #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */
+
+/*
+ * Check that the list of blocked tasks for the newly completed grace
+ * period is in fact empty.  It is a serious bug to complete a grace
+ * period that still has RCU readers blocked!  This function must be
+ * invoked -before- updating this rnp's ->gpnum, and the rnp's ->lock
+ * must be held by the caller.
+ */
+static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp)
+{
+	WARN_ON_ONCE(rcu_preempted_readers(rnp));
+	WARN_ON_ONCE(rnp->qsmask);
+}
+
+#ifdef CONFIG_HOTPLUG_CPU
+
+/*
+ * Handle tasklist migration for case in which all CPUs covered by the
+ * specified rcu_node have gone offline.  Move them up to the root
+ * rcu_node.  The reason for not just moving them to the immediate
+ * parent is to remove the need for rcu_read_unlock_special() to
+ * make more than two attempts to acquire the target rcu_node's lock.
+ *
+ * Returns 1 if there was previously a task blocking the current grace
+ * period on the specified rcu_node structure.
+ *
+ * The caller must hold rnp->lock with irqs disabled.
+ */
+static int rcu_preempt_offline_tasks(struct rcu_state *rsp,
+				     struct rcu_node *rnp,
+				     struct rcu_data *rdp)
+{
+	int i;
+	struct list_head *lp;
+	struct list_head *lp_root;
+	int retval = rcu_preempted_readers(rnp);
+	struct rcu_node *rnp_root = rcu_get_root(rsp);
+	struct task_struct *tp;
+
+	if (rnp == rnp_root) {
+		WARN_ONCE(1, "Last CPU thought to be offlined?");
+		return 0;  /* Shouldn't happen: at least one CPU online. */
+	}
+	WARN_ON_ONCE(rnp != rdp->mynode &&
+		     (!list_empty(&rnp->blocked_tasks[0]) ||
+		      !list_empty(&rnp->blocked_tasks[1])));
+
+	/*
+	 * Move tasks up to root rcu_node.  Rely on the fact that the
+	 * root rcu_node can be at most one ahead of the rest of the
+	 * rcu_nodes in terms of gp_num value.  This fact allows us to
+	 * move the blocked_tasks[] array directly, element by element.
+	 */
+	for (i = 0; i < 2; i++) {
+		lp = &rnp->blocked_tasks[i];
+		lp_root = &rnp_root->blocked_tasks[i];
+		while (!list_empty(lp)) {
+			tp = list_entry(lp->next, typeof(*tp), rcu_node_entry);
+			spin_lock(&rnp_root->lock); /* irqs already disabled */
+			list_del(&tp->rcu_node_entry);
+			tp->rcu_blocked_node = rnp_root;
+			list_add(&tp->rcu_node_entry, lp_root);
+			spin_unlock(&rnp_root->lock); /* irqs remain disabled */
+		}
+	}
+
+	return retval;
+}
+
+/*
+ * Do CPU-offline processing for preemptable RCU.
+ */
+static void rcu_preempt_offline_cpu(int cpu)
+{
+	__rcu_offline_cpu(cpu, &rcu_preempt_state);
+}
+
+#endif /* #ifdef CONFIG_HOTPLUG_CPU */
+
+/*
+ * Check for a quiescent state from the current CPU.  When a task blocks,
+ * the task is recorded in the corresponding CPU's rcu_node structure,
+ * which is checked elsewhere.
+ *
+ * Caller must disable hard irqs.
+ */
+static void rcu_preempt_check_callbacks(int cpu)
+{
+	struct task_struct *t = current;
+
+	if (t->rcu_read_lock_nesting == 0) {
+		t->rcu_read_unlock_special &= ~RCU_READ_UNLOCK_NEED_QS;
+		rcu_preempt_qs(cpu);
+		return;
+	}
+	if (per_cpu(rcu_preempt_data, cpu).qs_pending)
+		t->rcu_read_unlock_special |= RCU_READ_UNLOCK_NEED_QS;
+}
+
+/*
+ * Process callbacks for preemptable RCU.
+ */
+static void rcu_preempt_process_callbacks(void)
+{
+	__rcu_process_callbacks(&rcu_preempt_state,
+				&__get_cpu_var(rcu_preempt_data));
+}
+
+/*
+ * Queue a preemptable-RCU callback for invocation after a grace period.
+ */
+void call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu))
+{
+	__call_rcu(head, func, &rcu_preempt_state);
+}
+EXPORT_SYMBOL_GPL(call_rcu);
+
+/*
+ * Wait for an rcu-preempt grace period.  We are supposed to expedite the
+ * grace period, but this is the crude slow compatability hack, so just
+ * invoke synchronize_rcu().
+ */
+void synchronize_rcu_expedited(void)
+{
+	synchronize_rcu();
+}
+EXPORT_SYMBOL_GPL(synchronize_rcu_expedited);
+
+/*
+ * Check to see if there is any immediate preemptable-RCU-related work
+ * to be done.
+ */
+static int rcu_preempt_pending(int cpu)
+{
+	return __rcu_pending(&rcu_preempt_state,
+			     &per_cpu(rcu_preempt_data, cpu));
+}
+
+/*
+ * Does preemptable RCU need the CPU to stay out of dynticks mode?
+ */
+static int rcu_preempt_needs_cpu(int cpu)
+{
+	return !!per_cpu(rcu_preempt_data, cpu).nxtlist;
+}
+
+/**
+ * rcu_barrier - Wait until all in-flight call_rcu() callbacks complete.
+ */
+void rcu_barrier(void)
+{
+	_rcu_barrier(&rcu_preempt_state, call_rcu);
+}
+EXPORT_SYMBOL_GPL(rcu_barrier);
+
+/*
+ * Initialize preemptable RCU's per-CPU data.
+ */
+static void __cpuinit rcu_preempt_init_percpu_data(int cpu)
+{
+	rcu_init_percpu_data(cpu, &rcu_preempt_state, 1);
+}
+
+/*
+ * Move preemptable RCU's callbacks to ->orphan_cbs_list.
+ */
+static void rcu_preempt_send_cbs_to_orphanage(void)
+{
+	rcu_send_cbs_to_orphanage(&rcu_preempt_state);
+}
+
+/*
+ * Initialize preemptable RCU's state structures.
+ */
+static void __init __rcu_init_preempt(void)
+{
+	RCU_INIT_FLAVOR(&rcu_preempt_state, rcu_preempt_data);
+}
+
+/*
+ * Check for a task exiting while in a preemptable-RCU read-side
+ * critical section, clean up if so.  No need to issue warnings,
+ * as debug_check_no_locks_held() already does this if lockdep
+ * is enabled.
+ */
+void exit_rcu(void)
+{
+	struct task_struct *t = current;
+
+	if (t->rcu_read_lock_nesting == 0)
+		return;
+	t->rcu_read_lock_nesting = 1;
+	rcu_read_unlock();
+}
+
+#else /* #ifdef CONFIG_TREE_PREEMPT_RCU */
+
+/*
+ * Tell them what RCU they are running.
+ */
+static inline void rcu_bootup_announce(void)
+{
+	printk(KERN_INFO "Hierarchical RCU implementation.\n");
+}
+
+/*
+ * Return the number of RCU batches processed thus far for debug & stats.
+ */
+long rcu_batches_completed(void)
+{
+	return rcu_batches_completed_sched();
+}
+EXPORT_SYMBOL_GPL(rcu_batches_completed);
+
+/*
+ * Because preemptable RCU does not exist, we never have to check for
+ * CPUs being in quiescent states.
+ */
+static void rcu_preempt_note_context_switch(int cpu)
+{
+}
+
+/*
+ * Because preemptable RCU does not exist, there are never any preempted
+ * RCU readers.
+ */
+static int rcu_preempted_readers(struct rcu_node *rnp)
+{
+	return 0;
+}
+
+#ifdef CONFIG_RCU_CPU_STALL_DETECTOR
+
+/*
+ * Because preemptable RCU does not exist, we never have to check for
+ * tasks blocked within RCU read-side critical sections.
+ */
+static void rcu_print_task_stall(struct rcu_node *rnp)
+{
+}
+
+#endif /* #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */
+
+/*
+ * Because there is no preemptable RCU, there can be no readers blocked,
+ * so there is no need to check for blocked tasks.  So check only for
+ * bogus qsmask values.
+ */
+static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp)
+{
+	WARN_ON_ONCE(rnp->qsmask);
+}
+
+#ifdef CONFIG_HOTPLUG_CPU
+
+/*
+ * Because preemptable RCU does not exist, it never needs to migrate
+ * tasks that were blocked within RCU read-side critical sections, and
+ * such non-existent tasks cannot possibly have been blocking the current
+ * grace period.
+ */
+static int rcu_preempt_offline_tasks(struct rcu_state *rsp,
+				     struct rcu_node *rnp,
+				     struct rcu_data *rdp)
+{
+	return 0;
+}
+
+/*
+ * Because preemptable RCU does not exist, it never needs CPU-offline
+ * processing.
+ */
+static void rcu_preempt_offline_cpu(int cpu)
+{
+}
+
+#endif /* #ifdef CONFIG_HOTPLUG_CPU */
+
+/*
+ * Because preemptable RCU does not exist, it never has any callbacks
+ * to check.
+ */
+static void rcu_preempt_check_callbacks(int cpu)
+{
+}
+
+/*
+ * Because preemptable RCU does not exist, it never has any callbacks
+ * to process.
+ */
+static void rcu_preempt_process_callbacks(void)
+{
+}
+
+/*
+ * In classic RCU, call_rcu() is just call_rcu_sched().
+ */
+void call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu))
+{
+	call_rcu_sched(head, func);
+}
+EXPORT_SYMBOL_GPL(call_rcu);
+
+/*
+ * Wait for an rcu-preempt grace period, but make it happen quickly.
+ * But because preemptable RCU does not exist, map to rcu-sched.
+ */
+void synchronize_rcu_expedited(void)
+{
+	synchronize_sched_expedited();
+}
+EXPORT_SYMBOL_GPL(synchronize_rcu_expedited);
+
+/*
+ * Because preemptable RCU does not exist, it never has any work to do.
+ */
+static int rcu_preempt_pending(int cpu)
+{
+	return 0;
+}
+
+/*
+ * Because preemptable RCU does not exist, it never needs any CPU.
+ */
+static int rcu_preempt_needs_cpu(int cpu)
+{
+	return 0;
+}
+
+/*
+ * Because preemptable RCU does not exist, rcu_barrier() is just
+ * another name for rcu_barrier_sched().
+ */
+void rcu_barrier(void)
+{
+	rcu_barrier_sched();
+}
+EXPORT_SYMBOL_GPL(rcu_barrier);
+
+/*
+ * Because preemptable RCU does not exist, there is no per-CPU
+ * data to initialize.
+ */
+static void __cpuinit rcu_preempt_init_percpu_data(int cpu)
+{
+}
+
+/*
+ * Because there is no preemptable RCU, there are no callbacks to move.
+ */
+static void rcu_preempt_send_cbs_to_orphanage(void)
+{
+}
+
+/*
+ * Because preemptable RCU does not exist, it need not be initialized.
+ */
+static void __init __rcu_init_preempt(void)
+{
+}
+
+#endif /* #else #ifdef CONFIG_TREE_PREEMPT_RCU */
diff --git a/kernel/rcutree_trace.c b/kernel/rcutree_trace.c
index fe1dcdbf1ca3..4b31c779e62e 100644
--- a/kernel/rcutree_trace.c
+++ b/kernel/rcutree_trace.c
@@ -20,7 +20,7 @@
  * Papers:  http://www.rdrop.com/users/paulmck/RCU
  *
  * For detailed explanation of Read-Copy Update mechanism see -
- * 		Documentation/RCU
+ *		Documentation/RCU
  *
  */
 #include <linux/types.h>
@@ -43,6 +43,7 @@
 #include <linux/debugfs.h>
 #include <linux/seq_file.h>
 
+#define RCU_TREE_NONCORE
 #include "rcutree.h"
 
 static void print_one_rcu_data(struct seq_file *m, struct rcu_data *rdp)
@@ -76,8 +77,12 @@ static void print_one_rcu_data(struct seq_file *m, struct rcu_data *rdp)
 
 static int show_rcudata(struct seq_file *m, void *unused)
 {
-	seq_puts(m, "rcu:\n");
-	PRINT_RCU_DATA(rcu_data, print_one_rcu_data, m);
+#ifdef CONFIG_TREE_PREEMPT_RCU
+	seq_puts(m, "rcu_preempt:\n");
+	PRINT_RCU_DATA(rcu_preempt_data, print_one_rcu_data, m);
+#endif /* #ifdef CONFIG_TREE_PREEMPT_RCU */
+	seq_puts(m, "rcu_sched:\n");
+	PRINT_RCU_DATA(rcu_sched_data, print_one_rcu_data, m);
 	seq_puts(m, "rcu_bh:\n");
 	PRINT_RCU_DATA(rcu_bh_data, print_one_rcu_data, m);
 	return 0;
@@ -88,7 +93,7 @@ static int rcudata_open(struct inode *inode, struct file *file)
 	return single_open(file, show_rcudata, NULL);
 }
 
-static struct file_operations rcudata_fops = {
+static const struct file_operations rcudata_fops = {
 	.owner = THIS_MODULE,
 	.open = rcudata_open,
 	.read = seq_read,
@@ -102,7 +107,7 @@ static void print_one_rcu_data_csv(struct seq_file *m, struct rcu_data *rdp)
 		return;
 	seq_printf(m, "%d,%s,%ld,%ld,%d,%ld,%d",
 		   rdp->cpu,
-		   cpu_is_offline(rdp->cpu) ? "\"Y\"" : "\"N\"",
+		   cpu_is_offline(rdp->cpu) ? "\"N\"" : "\"Y\"",
 		   rdp->completed, rdp->gpnum,
 		   rdp->passed_quiesc, rdp->passed_quiesc_completed,
 		   rdp->qs_pending);
@@ -124,8 +129,12 @@ static int show_rcudata_csv(struct seq_file *m, void *unused)
 	seq_puts(m, "\"dt\",\"dt nesting\",\"dn\",\"df\",");
 #endif /* #ifdef CONFIG_NO_HZ */
 	seq_puts(m, "\"of\",\"ri\",\"ql\",\"b\"\n");
-	seq_puts(m, "\"rcu:\"\n");
-	PRINT_RCU_DATA(rcu_data, print_one_rcu_data_csv, m);
+#ifdef CONFIG_TREE_PREEMPT_RCU
+	seq_puts(m, "\"rcu_preempt:\"\n");
+	PRINT_RCU_DATA(rcu_preempt_data, print_one_rcu_data_csv, m);
+#endif /* #ifdef CONFIG_TREE_PREEMPT_RCU */
+	seq_puts(m, "\"rcu_sched:\"\n");
+	PRINT_RCU_DATA(rcu_sched_data, print_one_rcu_data_csv, m);
 	seq_puts(m, "\"rcu_bh:\"\n");
 	PRINT_RCU_DATA(rcu_bh_data, print_one_rcu_data_csv, m);
 	return 0;
@@ -136,7 +145,7 @@ static int rcudata_csv_open(struct inode *inode, struct file *file)
 	return single_open(file, show_rcudata_csv, NULL);
 }
 
-static struct file_operations rcudata_csv_fops = {
+static const struct file_operations rcudata_csv_fops = {
 	.owner = THIS_MODULE,
 	.open = rcudata_csv_open,
 	.read = seq_read,
@@ -150,13 +159,13 @@ static void print_one_rcu_state(struct seq_file *m, struct rcu_state *rsp)
 	struct rcu_node *rnp;
 
 	seq_printf(m, "c=%ld g=%ld s=%d jfq=%ld j=%x "
-	              "nfqs=%lu/nfqsng=%lu(%lu) fqlh=%lu\n",
+		      "nfqs=%lu/nfqsng=%lu(%lu) fqlh=%lu oqlen=%ld\n",
 		   rsp->completed, rsp->gpnum, rsp->signaled,
 		   (long)(rsp->jiffies_force_qs - jiffies),
 		   (int)(jiffies & 0xffff),
 		   rsp->n_force_qs, rsp->n_force_qs_ngp,
 		   rsp->n_force_qs - rsp->n_force_qs_ngp,
-		   rsp->n_force_qs_lh);
+		   rsp->n_force_qs_lh, rsp->orphan_qlen);
 	for (rnp = &rsp->node[0]; rnp - &rsp->node[0] < NUM_RCU_NODES; rnp++) {
 		if (rnp->level != level) {
 			seq_puts(m, "\n");
@@ -171,8 +180,12 @@ static void print_one_rcu_state(struct seq_file *m, struct rcu_state *rsp)
 
 static int show_rcuhier(struct seq_file *m, void *unused)
 {
-	seq_puts(m, "rcu:\n");
-	print_one_rcu_state(m, &rcu_state);
+#ifdef CONFIG_TREE_PREEMPT_RCU
+	seq_puts(m, "rcu_preempt:\n");
+	print_one_rcu_state(m, &rcu_preempt_state);
+#endif /* #ifdef CONFIG_TREE_PREEMPT_RCU */
+	seq_puts(m, "rcu_sched:\n");
+	print_one_rcu_state(m, &rcu_sched_state);
 	seq_puts(m, "rcu_bh:\n");
 	print_one_rcu_state(m, &rcu_bh_state);
 	return 0;
@@ -183,7 +196,7 @@ static int rcuhier_open(struct inode *inode, struct file *file)
 	return single_open(file, show_rcuhier, NULL);
 }
 
-static struct file_operations rcuhier_fops = {
+static const struct file_operations rcuhier_fops = {
 	.owner = THIS_MODULE,
 	.open = rcuhier_open,
 	.read = seq_read,
@@ -193,8 +206,12 @@ static struct file_operations rcuhier_fops = {
 
 static int show_rcugp(struct seq_file *m, void *unused)
 {
-	seq_printf(m, "rcu: completed=%ld  gpnum=%ld\n",
-		   rcu_state.completed, rcu_state.gpnum);
+#ifdef CONFIG_TREE_PREEMPT_RCU
+	seq_printf(m, "rcu_preempt: completed=%ld  gpnum=%ld\n",
+		   rcu_preempt_state.completed, rcu_preempt_state.gpnum);
+#endif /* #ifdef CONFIG_TREE_PREEMPT_RCU */
+	seq_printf(m, "rcu_sched: completed=%ld  gpnum=%ld\n",
+		   rcu_sched_state.completed, rcu_sched_state.gpnum);
 	seq_printf(m, "rcu_bh: completed=%ld  gpnum=%ld\n",
 		   rcu_bh_state.completed, rcu_bh_state.gpnum);
 	return 0;
@@ -205,7 +222,7 @@ static int rcugp_open(struct inode *inode, struct file *file)
 	return single_open(file, show_rcugp, NULL);
 }
 
-static struct file_operations rcugp_fops = {
+static const struct file_operations rcugp_fops = {
 	.owner = THIS_MODULE,
 	.open = rcugp_open,
 	.read = seq_read,
@@ -243,8 +260,12 @@ static void print_rcu_pendings(struct seq_file *m, struct rcu_state *rsp)
 
 static int show_rcu_pending(struct seq_file *m, void *unused)
 {
-	seq_puts(m, "rcu:\n");
-	print_rcu_pendings(m, &rcu_state);
+#ifdef CONFIG_TREE_PREEMPT_RCU
+	seq_puts(m, "rcu_preempt:\n");
+	print_rcu_pendings(m, &rcu_preempt_state);
+#endif /* #ifdef CONFIG_TREE_PREEMPT_RCU */
+	seq_puts(m, "rcu_sched:\n");
+	print_rcu_pendings(m, &rcu_sched_state);
 	seq_puts(m, "rcu_bh:\n");
 	print_rcu_pendings(m, &rcu_bh_state);
 	return 0;
@@ -255,7 +276,7 @@ static int rcu_pending_open(struct inode *inode, struct file *file)
 	return single_open(file, show_rcu_pending, NULL);
 }
 
-static struct file_operations rcu_pending_fops = {
+static const struct file_operations rcu_pending_fops = {
 	.owner = THIS_MODULE,
 	.open = rcu_pending_open,
 	.read = seq_read,
@@ -264,62 +285,47 @@ static struct file_operations rcu_pending_fops = {
 };
 
 static struct dentry *rcudir;
-static struct dentry *datadir;
-static struct dentry *datadir_csv;
-static struct dentry *gpdir;
-static struct dentry *hierdir;
-static struct dentry *rcu_pendingdir;
 
 static int __init rcuclassic_trace_init(void)
 {
+	struct dentry *retval;
+
 	rcudir = debugfs_create_dir("rcu", NULL);
 	if (!rcudir)
-		goto out;
+		goto free_out;
 
-	datadir = debugfs_create_file("rcudata", 0444, rcudir,
+	retval = debugfs_create_file("rcudata", 0444, rcudir,
 						NULL, &rcudata_fops);
-	if (!datadir)
+	if (!retval)
 		goto free_out;
 
-	datadir_csv = debugfs_create_file("rcudata.csv", 0444, rcudir,
+	retval = debugfs_create_file("rcudata.csv", 0444, rcudir,
 						NULL, &rcudata_csv_fops);
-	if (!datadir_csv)
+	if (!retval)
 		goto free_out;
 
-	gpdir = debugfs_create_file("rcugp", 0444, rcudir, NULL, &rcugp_fops);
-	if (!gpdir)
+	retval = debugfs_create_file("rcugp", 0444, rcudir, NULL, &rcugp_fops);
+	if (!retval)
 		goto free_out;
 
-	hierdir = debugfs_create_file("rcuhier", 0444, rcudir,
+	retval = debugfs_create_file("rcuhier", 0444, rcudir,
 						NULL, &rcuhier_fops);
-	if (!hierdir)
+	if (!retval)
 		goto free_out;
 
-	rcu_pendingdir = debugfs_create_file("rcu_pending", 0444, rcudir,
+	retval = debugfs_create_file("rcu_pending", 0444, rcudir,
 						NULL, &rcu_pending_fops);
-	if (!rcu_pendingdir)
+	if (!retval)
 		goto free_out;
 	return 0;
 free_out:
-	if (datadir)
-		debugfs_remove(datadir);
-	if (datadir_csv)
-		debugfs_remove(datadir_csv);
-	if (gpdir)
-		debugfs_remove(gpdir);
-	debugfs_remove(rcudir);
-out:
+	debugfs_remove_recursive(rcudir);
 	return 1;
 }
 
 static void __exit rcuclassic_trace_cleanup(void)
 {
-	debugfs_remove(datadir);
-	debugfs_remove(datadir_csv);
-	debugfs_remove(gpdir);
-	debugfs_remove(hierdir);
-	debugfs_remove(rcu_pendingdir);
-	debugfs_remove(rcudir);
+	debugfs_remove_recursive(rcudir);
 }
 
 
diff --git a/kernel/relay.c b/kernel/relay.c
index bc188549788f..760c26209a3c 100644
--- a/kernel/relay.c
+++ b/kernel/relay.c
@@ -60,7 +60,7 @@ static int relay_buf_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 /*
  * vm_ops for relay file mappings.
  */
-static struct vm_operations_struct relay_file_mmap_ops = {
+static const struct vm_operations_struct relay_file_mmap_ops = {
 	.fault = relay_buf_fault,
 	.close = relay_file_mmap_close,
 };
diff --git a/kernel/res_counter.c b/kernel/res_counter.c
index e1338f074314..bcdabf37c40b 100644
--- a/kernel/res_counter.c
+++ b/kernel/res_counter.c
@@ -19,6 +19,7 @@ void res_counter_init(struct res_counter *counter, struct res_counter *parent)
 {
 	spin_lock_init(&counter->lock);
 	counter->limit = RESOURCE_MAX;
+	counter->soft_limit = RESOURCE_MAX;
 	counter->parent = parent;
 }
 
@@ -101,6 +102,8 @@ res_counter_member(struct res_counter *counter, int member)
 		return &counter->limit;
 	case RES_FAILCNT:
 		return &counter->failcnt;
+	case RES_SOFT_LIMIT:
+		return &counter->soft_limit;
 	};
 
 	BUG();
diff --git a/kernel/resource.c b/kernel/resource.c
index 78b087221c15..fb11a58b9594 100644
--- a/kernel/resource.c
+++ b/kernel/resource.c
@@ -223,13 +223,13 @@ int release_resource(struct resource *old)
 
 EXPORT_SYMBOL(release_resource);
 
-#if defined(CONFIG_MEMORY_HOTPLUG) && !defined(CONFIG_ARCH_HAS_WALK_MEMORY)
+#if !defined(CONFIG_ARCH_HAS_WALK_MEMORY)
 /*
  * Finds the lowest memory reosurce exists within [res->start.res->end)
- * the caller must specify res->start, res->end, res->flags.
+ * the caller must specify res->start, res->end, res->flags and "name".
  * If found, returns 0, res is overwritten, if not found, returns -1.
  */
-static int find_next_system_ram(struct resource *res)
+static int find_next_system_ram(struct resource *res, char *name)
 {
 	resource_size_t start, end;
 	struct resource *p;
@@ -245,6 +245,8 @@ static int find_next_system_ram(struct resource *res)
 		/* system ram is just marked as IORESOURCE_MEM */
 		if (p->flags != res->flags)
 			continue;
+		if (name && strcmp(p->name, name))
+			continue;
 		if (p->start > end) {
 			p = NULL;
 			break;
@@ -262,19 +264,26 @@ static int find_next_system_ram(struct resource *res)
 		res->end = p->end;
 	return 0;
 }
-int
-walk_memory_resource(unsigned long start_pfn, unsigned long nr_pages, void *arg,
-			int (*func)(unsigned long, unsigned long, void *))
+
+/*
+ * This function calls callback against all memory range of "System RAM"
+ * which are marked as IORESOURCE_MEM and IORESOUCE_BUSY.
+ * Now, this function is only for "System RAM".
+ */
+int walk_system_ram_range(unsigned long start_pfn, unsigned long nr_pages,
+		void *arg, int (*func)(unsigned long, unsigned long, void *))
 {
 	struct resource res;
 	unsigned long pfn, len;
 	u64 orig_end;
 	int ret = -1;
+
 	res.start = (u64) start_pfn << PAGE_SHIFT;
 	res.end = ((u64)(start_pfn + nr_pages) << PAGE_SHIFT) - 1;
 	res.flags = IORESOURCE_MEM | IORESOURCE_BUSY;
 	orig_end = res.end;
-	while ((res.start < res.end) && (find_next_system_ram(&res) >= 0)) {
+	while ((res.start < res.end) &&
+		(find_next_system_ram(&res, "System RAM") >= 0)) {
 		pfn = (unsigned long)(res.start >> PAGE_SHIFT);
 		len = (unsigned long)((res.end + 1 - res.start) >> PAGE_SHIFT);
 		ret = (*func)(pfn, len, arg);
diff --git a/kernel/sched.c b/kernel/sched.c
index 1b59e265273b..3c11ae0a948d 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -39,7 +39,7 @@
 #include <linux/completion.h>
 #include <linux/kernel_stat.h>
 #include <linux/debug_locks.h>
-#include <linux/perf_counter.h>
+#include <linux/perf_event.h>
 #include <linux/security.h>
 #include <linux/notifier.h>
 #include <linux/profile.h>
@@ -64,7 +64,6 @@
 #include <linux/tsacct_kern.h>
 #include <linux/kprobes.h>
 #include <linux/delayacct.h>
-#include <linux/reciprocal_div.h>
 #include <linux/unistd.h>
 #include <linux/pagemap.h>
 #include <linux/hrtimer.h>
@@ -120,30 +119,6 @@
  */
 #define RUNTIME_INF	((u64)~0ULL)
 
-#ifdef CONFIG_SMP
-
-static void double_rq_lock(struct rq *rq1, struct rq *rq2);
-
-/*
- * Divide a load by a sched group cpu_power : (load / sg->__cpu_power)
- * Since cpu_power is a 'constant', we can use a reciprocal divide.
- */
-static inline u32 sg_div_cpu_power(const struct sched_group *sg, u32 load)
-{
-	return reciprocal_divide(load, sg->reciprocal_cpu_power);
-}
-
-/*
- * Each time a sched group cpu_power is changed,
- * we must compute its reciprocal value
- */
-static inline void sg_inc_cpu_power(struct sched_group *sg, u32 val)
-{
-	sg->__cpu_power += val;
-	sg->reciprocal_cpu_power = reciprocal_value(sg->__cpu_power);
-}
-#endif
-
 static inline int rt_policy(int policy)
 {
 	if (unlikely(policy == SCHED_FIFO || policy == SCHED_RR))
@@ -309,8 +284,8 @@ void set_tg_uid(struct user_struct *user)
 
 /*
  * Root task group.
- * 	Every UID task group (including init_task_group aka UID-0) will
- * 	be a child to this group.
+ *	Every UID task group (including init_task_group aka UID-0) will
+ *	be a child to this group.
  */
 struct task_group root_task_group;
 
@@ -318,12 +293,12 @@ struct task_group root_task_group;
 /* Default task group's sched entity on each cpu */
 static DEFINE_PER_CPU(struct sched_entity, init_sched_entity);
 /* Default task group's cfs_rq on each cpu */
-static DEFINE_PER_CPU(struct cfs_rq, init_cfs_rq) ____cacheline_aligned_in_smp;
+static DEFINE_PER_CPU_SHARED_ALIGNED(struct cfs_rq, init_tg_cfs_rq);
 #endif /* CONFIG_FAIR_GROUP_SCHED */
 
 #ifdef CONFIG_RT_GROUP_SCHED
 static DEFINE_PER_CPU(struct sched_rt_entity, init_sched_rt_entity);
-static DEFINE_PER_CPU(struct rt_rq, init_rt_rq) ____cacheline_aligned_in_smp;
+static DEFINE_PER_CPU_SHARED_ALIGNED(struct rt_rq, init_rt_rq);
 #endif /* CONFIG_RT_GROUP_SCHED */
 #else /* !CONFIG_USER_SCHED */
 #define root_task_group init_task_group
@@ -334,6 +309,8 @@ static DEFINE_PER_CPU(struct rt_rq, init_rt_rq) ____cacheline_aligned_in_smp;
  */
 static DEFINE_SPINLOCK(task_group_lock);
 
+#ifdef CONFIG_FAIR_GROUP_SCHED
+
 #ifdef CONFIG_SMP
 static int root_task_group_empty(void)
 {
@@ -341,7 +318,6 @@ static int root_task_group_empty(void)
 }
 #endif
 
-#ifdef CONFIG_FAIR_GROUP_SCHED
 #ifdef CONFIG_USER_SCHED
 # define INIT_TASK_GROUP_LOAD	(2*NICE_0_LOAD)
 #else /* !CONFIG_USER_SCHED */
@@ -401,13 +377,6 @@ 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)
 {
@@ -537,14 +506,6 @@ struct root_domain {
 #ifdef CONFIG_SMP
 	struct cpupri cpupri;
 #endif
-#if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT)
-	/*
-	 * Preferred wake up cpu nominated by sched_mc balance that will be
-	 * used when most cpus are idle in the system indicating overall very
-	 * low system utilisation. Triggered at POWERSAVINGS_BALANCE_WAKEUP(2)
-	 */
-	unsigned int sched_mc_preferred_wakeup_cpu;
-#endif
 };
 
 /*
@@ -616,6 +577,7 @@ struct rq {
 
 	unsigned char idle_at_tick;
 	/* For active balancing */
+	int post_schedule;
 	int active_balance;
 	int push_cpu;
 	/* cpu of this runqueue: */
@@ -626,6 +588,9 @@ struct rq {
 
 	struct task_struct *migration_thread;
 	struct list_head migration_queue;
+
+	u64 rt_avg;
+	u64 age_stamp;
 #endif
 
 	/* calc_load related fields */
@@ -665,9 +630,10 @@ struct rq {
 
 static DEFINE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues);
 
-static inline void check_preempt_curr(struct rq *rq, struct task_struct *p, int sync)
+static inline
+void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags)
 {
-	rq->curr->sched_class->check_preempt_curr(rq, p, sync);
+	rq->curr->sched_class->check_preempt_curr(rq, p, flags);
 }
 
 static inline int cpu_of(struct rq *rq)
@@ -693,6 +659,7 @@ static inline int cpu_of(struct rq *rq)
 #define this_rq()		(&__get_cpu_var(runqueues))
 #define task_rq(p)		cpu_rq(task_cpu(p))
 #define cpu_curr(cpu)		(cpu_rq(cpu)->curr)
+#define raw_rq()		(&__raw_get_cpu_var(runqueues))
 
 inline void update_rq_clock(struct rq *rq)
 {
@@ -710,20 +677,15 @@ inline void update_rq_clock(struct rq *rq)
 
 /**
  * runqueue_is_locked
+ * @cpu: the processor in question.
  *
  * Returns true if the current cpu runqueue is locked.
  * This interface allows printk to be called with the runqueue lock
  * held and know whether or not it is OK to wake up the klogd.
  */
-int runqueue_is_locked(void)
+int runqueue_is_locked(int cpu)
 {
-	int cpu = get_cpu();
-	struct rq *rq = cpu_rq(cpu);
-	int ret;
-
-	ret = spin_is_locked(&rq->lock);
-	put_cpu();
-	return ret;
+	return spin_is_locked(&cpu_rq(cpu)->lock);
 }
 
 /*
@@ -820,7 +782,7 @@ static int sched_feat_open(struct inode *inode, struct file *filp)
 	return single_open(filp, sched_feat_show, NULL);
 }
 
-static struct file_operations sched_feat_fops = {
+static const struct file_operations sched_feat_fops = {
 	.open		= sched_feat_open,
 	.write		= sched_feat_write,
 	.read		= seq_read,
@@ -861,6 +823,14 @@ unsigned int sysctl_sched_shares_ratelimit = 250000;
 unsigned int sysctl_sched_shares_thresh = 4;
 
 /*
+ * period over which we average the RT time consumption, measured
+ * in ms.
+ *
+ * default: 1s
+ */
+const_debug unsigned int sysctl_sched_time_avg = MSEC_PER_SEC;
+
+/*
  * period over which we measure -rt task cpu usage in us.
  * default: 1s
  */
@@ -1278,12 +1248,37 @@ void wake_up_idle_cpu(int cpu)
 }
 #endif /* CONFIG_NO_HZ */
 
+static u64 sched_avg_period(void)
+{
+	return (u64)sysctl_sched_time_avg * NSEC_PER_MSEC / 2;
+}
+
+static void sched_avg_update(struct rq *rq)
+{
+	s64 period = sched_avg_period();
+
+	while ((s64)(rq->clock - rq->age_stamp) > period) {
+		rq->age_stamp += period;
+		rq->rt_avg /= 2;
+	}
+}
+
+static void sched_rt_avg_update(struct rq *rq, u64 rt_delta)
+{
+	rq->rt_avg += rt_delta;
+	sched_avg_update(rq);
+}
+
 #else /* !CONFIG_SMP */
 static void resched_task(struct task_struct *p)
 {
 	assert_spin_locked(&task_rq(p)->lock);
 	set_tsk_need_resched(p);
 }
+
+static void sched_rt_avg_update(struct rq *rq, u64 rt_delta)
+{
+}
 #endif /* CONFIG_SMP */
 
 #if BITS_PER_LONG == 32
@@ -1494,8 +1489,65 @@ static int tg_nop(struct task_group *tg, void *data)
 #endif
 
 #ifdef CONFIG_SMP
-static unsigned long source_load(int cpu, int type);
-static unsigned long target_load(int cpu, int type);
+/* Used instead of source_load when we know the type == 0 */
+static unsigned long weighted_cpuload(const int cpu)
+{
+	return cpu_rq(cpu)->load.weight;
+}
+
+/*
+ * Return a low guess at the load of a migration-source cpu weighted
+ * according to the scheduling class and "nice" value.
+ *
+ * We want to under-estimate the load of migration sources, to
+ * balance conservatively.
+ */
+static unsigned long source_load(int cpu, int type)
+{
+	struct rq *rq = cpu_rq(cpu);
+	unsigned long total = weighted_cpuload(cpu);
+
+	if (type == 0 || !sched_feat(LB_BIAS))
+		return total;
+
+	return min(rq->cpu_load[type-1], total);
+}
+
+/*
+ * Return a high guess at the load of a migration-target cpu weighted
+ * according to the scheduling class and "nice" value.
+ */
+static unsigned long target_load(int cpu, int type)
+{
+	struct rq *rq = cpu_rq(cpu);
+	unsigned long total = weighted_cpuload(cpu);
+
+	if (type == 0 || !sched_feat(LB_BIAS))
+		return total;
+
+	return max(rq->cpu_load[type-1], total);
+}
+
+static struct sched_group *group_of(int cpu)
+{
+	struct sched_domain *sd = rcu_dereference(cpu_rq(cpu)->sd);
+
+	if (!sd)
+		return NULL;
+
+	return sd->groups;
+}
+
+static unsigned long power_of(int cpu)
+{
+	struct sched_group *group = group_of(cpu);
+
+	if (!group)
+		return SCHED_LOAD_SCALE;
+
+	return group->cpu_power;
+}
+
 static int task_hot(struct task_struct *p, u64 now, struct sched_domain *sd);
 
 static unsigned long cpu_avg_load_per_task(int cpu)
@@ -1513,28 +1565,31 @@ static unsigned long cpu_avg_load_per_task(int cpu)
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
 
+static __read_mostly unsigned long *update_shares_data;
+
 static void __set_se_shares(struct sched_entity *se, unsigned long shares);
 
 /*
  * Calculate and set the cpu's group shares.
  */
-static void
-update_group_shares_cpu(struct task_group *tg, int cpu,
-			unsigned long sd_shares, unsigned long sd_rq_weight)
+static void update_group_shares_cpu(struct task_group *tg, int cpu,
+				    unsigned long sd_shares,
+				    unsigned long sd_rq_weight,
+				    unsigned long *usd_rq_weight)
 {
-	unsigned long shares;
-	unsigned long rq_weight;
-
-	if (!tg->se[cpu])
-		return;
+	unsigned long shares, rq_weight;
+	int boost = 0;
 
-	rq_weight = tg->cfs_rq[cpu]->rq_weight;
+	rq_weight = usd_rq_weight[cpu];
+	if (!rq_weight) {
+		boost = 1;
+		rq_weight = NICE_0_LOAD;
+	}
 
 	/*
-	 *           \Sum shares * rq_weight
-	 * shares =  -----------------------
-	 *               \Sum rq_weight
-	 *
+	 *             \Sum_j shares_j * rq_weight_i
+	 * shares_i =  -----------------------------
+	 *                  \Sum_j rq_weight_j
 	 */
 	shares = (sd_shares * rq_weight) / sd_rq_weight;
 	shares = clamp_t(unsigned long, shares, MIN_SHARES, MAX_SHARES);
@@ -1545,8 +1600,8 @@ update_group_shares_cpu(struct task_group *tg, int cpu,
 		unsigned long flags;
 
 		spin_lock_irqsave(&rq->lock, flags);
-		tg->cfs_rq[cpu]->shares = shares;
-
+		tg->cfs_rq[cpu]->rq_weight = boost ? 0 : rq_weight;
+		tg->cfs_rq[cpu]->shares = boost ? 0 : shares;
 		__set_se_shares(tg->se[cpu], shares);
 		spin_unlock_irqrestore(&rq->lock, flags);
 	}
@@ -1559,22 +1614,30 @@ update_group_shares_cpu(struct task_group *tg, int cpu,
  */
 static int tg_shares_up(struct task_group *tg, void *data)
 {
-	unsigned long weight, rq_weight = 0;
-	unsigned long shares = 0;
+	unsigned long weight, rq_weight = 0, shares = 0;
+	unsigned long *usd_rq_weight;
 	struct sched_domain *sd = data;
+	unsigned long flags;
 	int i;
 
+	if (!tg->se[0])
+		return 0;
+
+	local_irq_save(flags);
+	usd_rq_weight = per_cpu_ptr(update_shares_data, smp_processor_id());
+
 	for_each_cpu(i, sched_domain_span(sd)) {
+		weight = tg->cfs_rq[i]->load.weight;
+		usd_rq_weight[i] = weight;
+
 		/*
 		 * If there are currently no tasks on the cpu pretend there
 		 * is one of average load so that when a new task gets to
 		 * run here it will not get delayed by group starvation.
 		 */
-		weight = tg->cfs_rq[i]->load.weight;
 		if (!weight)
 			weight = NICE_0_LOAD;
 
-		tg->cfs_rq[i]->rq_weight = weight;
 		rq_weight += weight;
 		shares += tg->cfs_rq[i]->shares;
 	}
@@ -1586,7 +1649,9 @@ static int tg_shares_up(struct task_group *tg, void *data)
 		shares = tg->shares;
 
 	for_each_cpu(i, sched_domain_span(sd))
-		update_group_shares_cpu(tg, i, shares, rq_weight);
+		update_group_shares_cpu(tg, i, shares, rq_weight, usd_rq_weight);
+
+	local_irq_restore(flags);
 
 	return 0;
 }
@@ -1616,8 +1681,14 @@ static int tg_load_down(struct task_group *tg, void *data)
 
 static void update_shares(struct sched_domain *sd)
 {
-	u64 now = cpu_clock(raw_smp_processor_id());
-	s64 elapsed = now - sd->last_update;
+	s64 elapsed;
+	u64 now;
+
+	if (root_task_group_empty())
+		return;
+
+	now = cpu_clock(raw_smp_processor_id());
+	elapsed = now - sd->last_update;
 
 	if (elapsed >= (s64)(u64)sysctl_sched_shares_ratelimit) {
 		sd->last_update = now;
@@ -1627,6 +1698,9 @@ static void update_shares(struct sched_domain *sd)
 
 static void update_shares_locked(struct rq *rq, struct sched_domain *sd)
 {
+	if (root_task_group_empty())
+		return;
+
 	spin_unlock(&rq->lock);
 	update_shares(sd);
 	spin_lock(&rq->lock);
@@ -1634,6 +1708,9 @@ static void update_shares_locked(struct rq *rq, struct sched_domain *sd)
 
 static void update_h_load(long cpu)
 {
+	if (root_task_group_empty())
+		return;
+
 	walk_tg_tree(tg_load_down, tg_nop, (void *)cpu);
 }
 
@@ -1651,6 +1728,8 @@ static inline void update_shares_locked(struct rq *rq, struct sched_domain *sd)
 
 #ifdef CONFIG_PREEMPT
 
+static void double_rq_lock(struct rq *rq1, struct rq *rq2);
+
 /*
  * fair double_lock_balance: Safely acquires both rq->locks in a fair
  * way at the expense of forcing extra atomic operations in all
@@ -1914,14 +1993,39 @@ static inline void check_class_changed(struct rq *rq, struct task_struct *p,
 		p->sched_class->prio_changed(rq, p, oldprio, running);
 }
 
-#ifdef CONFIG_SMP
-
-/* Used instead of source_load when we know the type == 0 */
-static unsigned long weighted_cpuload(const int cpu)
+/**
+ * kthread_bind - bind a just-created kthread to a cpu.
+ * @p: thread created by kthread_create().
+ * @cpu: cpu (might not be online, must be possible) for @k to run on.
+ *
+ * Description: This function is equivalent to set_cpus_allowed(),
+ * except that @cpu doesn't need to be online, and the thread must be
+ * stopped (i.e., just returned from kthread_create()).
+ *
+ * Function lives here instead of kthread.c because it messes with
+ * scheduler internals which require locking.
+ */
+void kthread_bind(struct task_struct *p, unsigned int cpu)
 {
-	return cpu_rq(cpu)->load.weight;
+	struct rq *rq = cpu_rq(cpu);
+	unsigned long flags;
+
+	/* Must have done schedule() in kthread() before we set_task_cpu */
+	if (!wait_task_inactive(p, TASK_UNINTERRUPTIBLE)) {
+		WARN_ON(1);
+		return;
+	}
+
+	spin_lock_irqsave(&rq->lock, flags);
+	set_task_cpu(p, cpu);
+	p->cpus_allowed = cpumask_of_cpu(cpu);
+	p->rt.nr_cpus_allowed = 1;
+	p->flags |= PF_THREAD_BOUND;
+	spin_unlock_irqrestore(&rq->lock, flags);
 }
+EXPORT_SYMBOL(kthread_bind);
 
+#ifdef CONFIG_SMP
 /*
  * Is this task likely cache-hot:
  */
@@ -1933,7 +2037,7 @@ task_hot(struct task_struct *p, u64 now, struct sched_domain *sd)
 	/*
 	 * Buddy candidates are cache hot:
 	 */
-	if (sched_feat(CACHE_HOT_BUDDY) &&
+	if (sched_feat(CACHE_HOT_BUDDY) && this_rq()->nr_running &&
 			(&p->se == cfs_rq_of(&p->se)->next ||
 			 &p->se == cfs_rq_of(&p->se)->last))
 		return 1;
@@ -1979,7 +2083,7 @@ void set_task_cpu(struct task_struct *p, unsigned int new_cpu)
 		if (task_hot(p, old_rq->clock, NULL))
 			schedstat_inc(p, se.nr_forced2_migrations);
 #endif
-		perf_swcounter_event(PERF_COUNT_SW_CPU_MIGRATIONS,
+		perf_sw_event(PERF_COUNT_SW_CPU_MIGRATIONS,
 				     1, 1, NULL, 0);
 	}
 	p->se.vruntime -= old_cfsrq->min_vruntime -
@@ -2195,186 +2299,6 @@ void kick_process(struct task_struct *p)
 	preempt_enable();
 }
 EXPORT_SYMBOL_GPL(kick_process);
-
-/*
- * Return a low guess at the load of a migration-source cpu weighted
- * according to the scheduling class and "nice" value.
- *
- * We want to under-estimate the load of migration sources, to
- * balance conservatively.
- */
-static unsigned long source_load(int cpu, int type)
-{
-	struct rq *rq = cpu_rq(cpu);
-	unsigned long total = weighted_cpuload(cpu);
-
-	if (type == 0 || !sched_feat(LB_BIAS))
-		return total;
-
-	return min(rq->cpu_load[type-1], total);
-}
-
-/*
- * Return a high guess at the load of a migration-target cpu weighted
- * according to the scheduling class and "nice" value.
- */
-static unsigned long target_load(int cpu, int type)
-{
-	struct rq *rq = cpu_rq(cpu);
-	unsigned long total = weighted_cpuload(cpu);
-
-	if (type == 0 || !sched_feat(LB_BIAS))
-		return total;
-
-	return max(rq->cpu_load[type-1], total);
-}
-
-/*
- * find_idlest_group finds and returns the least busy CPU group within the
- * domain.
- */
-static struct sched_group *
-find_idlest_group(struct sched_domain *sd, struct task_struct *p, int this_cpu)
-{
-	struct sched_group *idlest = NULL, *this = NULL, *group = sd->groups;
-	unsigned long min_load = ULONG_MAX, this_load = 0;
-	int load_idx = sd->forkexec_idx;
-	int imbalance = 100 + (sd->imbalance_pct-100)/2;
-
-	do {
-		unsigned long load, avg_load;
-		int local_group;
-		int i;
-
-		/* Skip over this group if it has no CPUs allowed */
-		if (!cpumask_intersects(sched_group_cpus(group),
-					&p->cpus_allowed))
-			continue;
-
-		local_group = cpumask_test_cpu(this_cpu,
-					       sched_group_cpus(group));
-
-		/* Tally up the load of all CPUs in the group */
-		avg_load = 0;
-
-		for_each_cpu(i, sched_group_cpus(group)) {
-			/* Bias balancing toward cpus of our domain */
-			if (local_group)
-				load = source_load(i, load_idx);
-			else
-				load = target_load(i, load_idx);
-
-			avg_load += load;
-		}
-
-		/* Adjust by relative CPU power of the group */
-		avg_load = sg_div_cpu_power(group,
-				avg_load * SCHED_LOAD_SCALE);
-
-		if (local_group) {
-			this_load = avg_load;
-			this = group;
-		} else if (avg_load < min_load) {
-			min_load = avg_load;
-			idlest = group;
-		}
-	} while (group = group->next, group != sd->groups);
-
-	if (!idlest || 100*this_load < imbalance*min_load)
-		return NULL;
-	return idlest;
-}
-
-/*
- * find_idlest_cpu - find the idlest cpu among the cpus in group.
- */
-static int
-find_idlest_cpu(struct sched_group *group, struct task_struct *p, int this_cpu)
-{
-	unsigned long load, min_load = ULONG_MAX;
-	int idlest = -1;
-	int i;
-
-	/* Traverse only the allowed CPUs */
-	for_each_cpu_and(i, sched_group_cpus(group), &p->cpus_allowed) {
-		load = weighted_cpuload(i);
-
-		if (load < min_load || (load == min_load && i == this_cpu)) {
-			min_load = load;
-			idlest = i;
-		}
-	}
-
-	return idlest;
-}
-
-/*
- * sched_balance_self: balance the current task (running on cpu) in domains
- * that have the 'flag' flag set. In practice, this is SD_BALANCE_FORK and
- * SD_BALANCE_EXEC.
- *
- * Balance, ie. select the least loaded group.
- *
- * Returns the target CPU number, or the same CPU if no balancing is needed.
- *
- * preempt must be disabled.
- */
-static int sched_balance_self(int cpu, int flag)
-{
-	struct task_struct *t = current;
-	struct sched_domain *tmp, *sd = NULL;
-
-	for_each_domain(cpu, tmp) {
-		/*
-		 * If power savings logic is enabled for a domain, stop there.
-		 */
-		if (tmp->flags & SD_POWERSAVINGS_BALANCE)
-			break;
-		if (tmp->flags & flag)
-			sd = tmp;
-	}
-
-	if (sd)
-		update_shares(sd);
-
-	while (sd) {
-		struct sched_group *group;
-		int new_cpu, weight;
-
-		if (!(sd->flags & flag)) {
-			sd = sd->child;
-			continue;
-		}
-
-		group = find_idlest_group(sd, t, cpu);
-		if (!group) {
-			sd = sd->child;
-			continue;
-		}
-
-		new_cpu = find_idlest_cpu(group, t, cpu);
-		if (new_cpu == -1 || new_cpu == cpu) {
-			/* Now try balancing at a lower domain level of cpu */
-			sd = sd->child;
-			continue;
-		}
-
-		/* Now try balancing at a lower domain level of new_cpu */
-		cpu = new_cpu;
-		weight = cpumask_weight(sched_domain_span(sd));
-		sd = NULL;
-		for_each_domain(cpu, tmp) {
-			if (weight <= cpumask_weight(sched_domain_span(tmp)))
-				break;
-			if (tmp->flags & flag)
-				sd = tmp;
-		}
-		/* while loop will break here if sd == NULL */
-	}
-
-	return cpu;
-}
-
 #endif /* CONFIG_SMP */
 
 /**
@@ -2412,37 +2336,22 @@ void task_oncpu_function_call(struct task_struct *p,
  *
  * returns failure only if the task is already active.
  */
-static int try_to_wake_up(struct task_struct *p, unsigned int state, int sync)
+static int try_to_wake_up(struct task_struct *p, unsigned int state,
+			  int wake_flags)
 {
 	int cpu, orig_cpu, this_cpu, success = 0;
 	unsigned long flags;
-	long old_state;
-	struct rq *rq;
+	struct rq *rq, *orig_rq;
 
 	if (!sched_feat(SYNC_WAKEUPS))
-		sync = 0;
-
-#ifdef CONFIG_SMP
-	if (sched_feat(LB_WAKEUP_UPDATE) && !root_task_group_empty()) {
-		struct sched_domain *sd;
-
-		this_cpu = raw_smp_processor_id();
-		cpu = task_cpu(p);
+		wake_flags &= ~WF_SYNC;
 
-		for_each_domain(this_cpu, sd) {
-			if (cpumask_test_cpu(cpu, sched_domain_span(sd))) {
-				update_shares(sd);
-				break;
-			}
-		}
-	}
-#endif
+	this_cpu = get_cpu();
 
 	smp_wmb();
-	rq = task_rq_lock(p, &flags);
+	rq = orig_rq = task_rq_lock(p, &flags);
 	update_rq_clock(rq);
-	old_state = p->state;
-	if (!(old_state & state))
+	if (!(p->state & state))
 		goto out;
 
 	if (p->se.on_rq)
@@ -2450,27 +2359,33 @@ static int try_to_wake_up(struct task_struct *p, unsigned int state, int sync)
 
 	cpu = task_cpu(p);
 	orig_cpu = cpu;
-	this_cpu = smp_processor_id();
 
 #ifdef CONFIG_SMP
 	if (unlikely(task_running(rq, p)))
 		goto out_activate;
 
-	cpu = p->sched_class->select_task_rq(p, sync);
-	if (cpu != orig_cpu) {
+	/*
+	 * In order to handle concurrent wakeups and release the rq->lock
+	 * we put the task in TASK_WAKING state.
+	 *
+	 * First fix up the nr_uninterruptible count:
+	 */
+	if (task_contributes_to_load(p))
+		rq->nr_uninterruptible--;
+	p->state = TASK_WAKING;
+	task_rq_unlock(rq, &flags);
+
+	cpu = p->sched_class->select_task_rq(p, SD_BALANCE_WAKE, wake_flags);
+	if (cpu != orig_cpu)
 		set_task_cpu(p, cpu);
-		task_rq_unlock(rq, &flags);
-		/* might preempt at this point */
-		rq = task_rq_lock(p, &flags);
-		old_state = p->state;
-		if (!(old_state & state))
-			goto out;
-		if (p->se.on_rq)
-			goto out_running;
 
-		this_cpu = smp_processor_id();
-		cpu = task_cpu(p);
-	}
+	rq = task_rq_lock(p, &flags);
+
+	if (rq != orig_rq)
+		update_rq_clock(rq);
+
+	WARN_ON(p->state != TASK_WAKING);
+	cpu = task_cpu(p);
 
 #ifdef CONFIG_SCHEDSTATS
 	schedstat_inc(rq, ttwu_count);
@@ -2490,7 +2405,7 @@ static int try_to_wake_up(struct task_struct *p, unsigned int state, int sync)
 out_activate:
 #endif /* CONFIG_SMP */
 	schedstat_inc(p, se.nr_wakeups);
-	if (sync)
+	if (wake_flags & WF_SYNC)
 		schedstat_inc(p, se.nr_wakeups_sync);
 	if (orig_cpu != cpu)
 		schedstat_inc(p, se.nr_wakeups_migrate);
@@ -2519,7 +2434,7 @@ out_activate:
 
 out_running:
 	trace_sched_wakeup(rq, p, success);
-	check_preempt_curr(rq, p, sync);
+	check_preempt_curr(rq, p, wake_flags);
 
 	p->state = TASK_RUNNING;
 #ifdef CONFIG_SMP
@@ -2528,6 +2443,7 @@ out_running:
 #endif
 out:
 	task_rq_unlock(rq, &flags);
+	put_cpu();
 
 	return success;
 }
@@ -2570,6 +2486,7 @@ static void __sched_fork(struct task_struct *p)
 	p->se.avg_overlap		= 0;
 	p->se.start_runtime		= 0;
 	p->se.avg_wakeup		= sysctl_sched_wakeup_granularity;
+	p->se.avg_running		= 0;
 
 #ifdef CONFIG_SCHEDSTATS
 	p->se.wait_start			= 0;
@@ -2631,18 +2548,41 @@ void sched_fork(struct task_struct *p, int clone_flags)
 
 	__sched_fork(p);
 
-#ifdef CONFIG_SMP
-	cpu = sched_balance_self(cpu, SD_BALANCE_FORK);
-#endif
-	set_task_cpu(p, cpu);
+	/*
+	 * Revert to default priority/policy on fork if requested.
+	 */
+	if (unlikely(p->sched_reset_on_fork)) {
+		if (p->policy == SCHED_FIFO || p->policy == SCHED_RR) {
+			p->policy = SCHED_NORMAL;
+			p->normal_prio = p->static_prio;
+		}
+
+		if (PRIO_TO_NICE(p->static_prio) < 0) {
+			p->static_prio = NICE_TO_PRIO(0);
+			p->normal_prio = p->static_prio;
+			set_load_weight(p);
+		}
+
+		/*
+		 * We don't need the reset flag anymore after the fork. It has
+		 * fulfilled its duty:
+		 */
+		p->sched_reset_on_fork = 0;
+	}
 
 	/*
-	 * Make sure we do not leak PI boosting priority to the child:
+	 * Make sure we do not leak PI boosting priority to the child.
 	 */
 	p->prio = current->normal_prio;
+
 	if (!rt_prio(p->prio))
 		p->sched_class = &fair_sched_class;
 
+#ifdef CONFIG_SMP
+	cpu = p->sched_class->select_task_rq(p, SD_BALANCE_FORK, 0);
+#endif
+	set_task_cpu(p, cpu);
+
 #if defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT)
 	if (likely(sched_info_on()))
 		memset(&p->sched_info, 0, sizeof(p->sched_info));
@@ -2675,8 +2615,6 @@ void wake_up_new_task(struct task_struct *p, unsigned long clone_flags)
 	BUG_ON(p->state != TASK_RUNNING);
 	update_rq_clock(rq);
 
-	p->prio = effective_prio(p);
-
 	if (!p->sched_class->task_new || !current->se.on_rq) {
 		activate_task(rq, p, 0);
 	} else {
@@ -2688,7 +2626,7 @@ void wake_up_new_task(struct task_struct *p, unsigned long clone_flags)
 		inc_nr_running(rq);
 	}
 	trace_sched_wakeup_new(rq, p, 1);
-	check_preempt_curr(rq, p, 0);
+	check_preempt_curr(rq, p, WF_FORK);
 #ifdef CONFIG_SMP
 	if (p->sched_class->task_wake_up)
 		p->sched_class->task_wake_up(rq, p);
@@ -2796,12 +2734,6 @@ 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;
 
@@ -2818,12 +2750,8 @@ static void finish_task_switch(struct rq *rq, struct task_struct *prev)
 	 */
 	prev_state = prev->state;
 	finish_arch_switch(prev);
-	perf_counter_task_sched_in(current, cpu_of(rq));
+	perf_event_task_sched_in(current, cpu_of(rq));
 	finish_lock_switch(rq, prev);
-#ifdef CONFIG_SMP
-	if (post_schedule)
-		current->sched_class->post_schedule(rq);
-#endif
 
 	fire_sched_in_preempt_notifiers(current);
 	if (mm)
@@ -2838,6 +2766,42 @@ static void finish_task_switch(struct rq *rq, struct task_struct *prev)
 	}
 }
 
+#ifdef CONFIG_SMP
+
+/* assumes rq->lock is held */
+static inline void pre_schedule(struct rq *rq, struct task_struct *prev)
+{
+	if (prev->sched_class->pre_schedule)
+		prev->sched_class->pre_schedule(rq, prev);
+}
+
+/* rq->lock is NOT held, but preemption is disabled */
+static inline void post_schedule(struct rq *rq)
+{
+	if (rq->post_schedule) {
+		unsigned long flags;
+
+		spin_lock_irqsave(&rq->lock, flags);
+		if (rq->curr->sched_class->post_schedule)
+			rq->curr->sched_class->post_schedule(rq);
+		spin_unlock_irqrestore(&rq->lock, flags);
+
+		rq->post_schedule = 0;
+	}
+}
+
+#else
+
+static inline void pre_schedule(struct rq *rq, struct task_struct *p)
+{
+}
+
+static inline void post_schedule(struct rq *rq)
+{
+}
+
+#endif
+
 /**
  * schedule_tail - first thing a freshly forked thread must call.
  * @prev: the thread we just switched away from.
@@ -2848,6 +2812,13 @@ asmlinkage void schedule_tail(struct task_struct *prev)
 	struct rq *rq = this_rq();
 
 	finish_task_switch(rq, prev);
+
+	/*
+	 * FIXME: do we need to worry about rq being invalidated by the
+	 * task_switch?
+	 */
+	post_schedule(rq);
+
 #ifdef __ARCH_WANT_UNLOCKED_CTXSW
 	/* In this case, finish_task_switch does not reenable preemption */
 	preempt_enable();
@@ -2965,6 +2936,19 @@ unsigned long nr_iowait(void)
 	return sum;
 }
 
+unsigned long nr_iowait_cpu(void)
+{
+	struct rq *this = this_rq();
+	return atomic_read(&this->nr_iowait);
+}
+
+unsigned long this_cpu_load(void)
+{
+	struct rq *this = this_rq();
+	return this->cpu_load[0];
+}
+
+
 /* Variables and functions for calc_load */
 static atomic_long_t calc_load_tasks;
 static unsigned long calc_load_update;
@@ -3164,7 +3148,7 @@ out:
 void sched_exec(void)
 {
 	int new_cpu, this_cpu = get_cpu();
-	new_cpu = sched_balance_self(this_cpu, SD_BALANCE_EXEC);
+	new_cpu = current->sched_class->select_task_rq(current, SD_BALANCE_EXEC, 0);
 	put_cpu();
 	if (new_cpu != this_cpu)
 		sched_migrate_task(current, new_cpu);
@@ -3379,9 +3363,10 @@ static int move_one_task(struct rq *this_rq, int this_cpu, struct rq *busiest,
 {
 	const struct sched_class *class;
 
-	for (class = sched_class_highest; class; class = class->next)
+	for_each_class(class) {
 		if (class->move_one_task(this_rq, this_cpu, busiest, sd, idle))
 			return 1;
+	}
 
 	return 0;
 }
@@ -3544,7 +3529,7 @@ static inline void update_sd_power_savings_stats(struct sched_group *group,
 	 * 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)
+	if (sgs->sum_nr_running + 1 > sgs->group_capacity)
 		return;
 
 	if (sgs->sum_nr_running > sds->leader_nr_running ||
@@ -3583,11 +3568,6 @@ static inline int check_power_save_busiest_group(struct sd_lb_stats *sds,
 	*imbalance = sds->min_load_per_task;
 	sds->busiest = sds->group_min;
 
-	if (sched_mc_power_savings >= POWERSAVINGS_BALANCE_WAKEUP) {
-		cpu_rq(this_cpu)->rd->sched_mc_preferred_wakeup_cpu =
-			group_first_cpu(sds->group_leader);
-	}
-
 	return 1;
 
 }
@@ -3612,8 +3592,105 @@ static inline int check_power_save_busiest_group(struct sd_lb_stats *sds,
 #endif /* CONFIG_SCHED_MC || CONFIG_SCHED_SMT */
 
 
+unsigned long default_scale_freq_power(struct sched_domain *sd, int cpu)
+{
+	return SCHED_LOAD_SCALE;
+}
+
+unsigned long __weak arch_scale_freq_power(struct sched_domain *sd, int cpu)
+{
+	return default_scale_freq_power(sd, cpu);
+}
+
+unsigned long default_scale_smt_power(struct sched_domain *sd, int cpu)
+{
+	unsigned long weight = cpumask_weight(sched_domain_span(sd));
+	unsigned long smt_gain = sd->smt_gain;
+
+	smt_gain /= weight;
+
+	return smt_gain;
+}
+
+unsigned long __weak arch_scale_smt_power(struct sched_domain *sd, int cpu)
+{
+	return default_scale_smt_power(sd, cpu);
+}
+
+unsigned long scale_rt_power(int cpu)
+{
+	struct rq *rq = cpu_rq(cpu);
+	u64 total, available;
+
+	sched_avg_update(rq);
+
+	total = sched_avg_period() + (rq->clock - rq->age_stamp);
+	available = total - rq->rt_avg;
+
+	if (unlikely((s64)total < SCHED_LOAD_SCALE))
+		total = SCHED_LOAD_SCALE;
+
+	total >>= SCHED_LOAD_SHIFT;
+
+	return div_u64(available, total);
+}
+
+static void update_cpu_power(struct sched_domain *sd, int cpu)
+{
+	unsigned long weight = cpumask_weight(sched_domain_span(sd));
+	unsigned long power = SCHED_LOAD_SCALE;
+	struct sched_group *sdg = sd->groups;
+
+	if (sched_feat(ARCH_POWER))
+		power *= arch_scale_freq_power(sd, cpu);
+	else
+		power *= default_scale_freq_power(sd, cpu);
+
+	power >>= SCHED_LOAD_SHIFT;
+
+	if ((sd->flags & SD_SHARE_CPUPOWER) && weight > 1) {
+		if (sched_feat(ARCH_POWER))
+			power *= arch_scale_smt_power(sd, cpu);
+		else
+			power *= default_scale_smt_power(sd, cpu);
+
+		power >>= SCHED_LOAD_SHIFT;
+	}
+
+	power *= scale_rt_power(cpu);
+	power >>= SCHED_LOAD_SHIFT;
+
+	if (!power)
+		power = 1;
+
+	sdg->cpu_power = power;
+}
+
+static void update_group_power(struct sched_domain *sd, int cpu)
+{
+	struct sched_domain *child = sd->child;
+	struct sched_group *group, *sdg = sd->groups;
+	unsigned long power;
+
+	if (!child) {
+		update_cpu_power(sd, cpu);
+		return;
+	}
+
+	power = 0;
+
+	group = child->groups;
+	do {
+		power += group->cpu_power;
+		group = group->next;
+	} while (group != child->groups);
+
+	sdg->cpu_power = power;
+}
+
 /**
  * update_sg_lb_stats - Update sched_group's statistics for load balancing.
+ * @sd: The sched_domain whose statistics are to be updated.
  * @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
@@ -3624,7 +3701,8 @@ static inline int check_power_save_busiest_group(struct sd_lb_stats *sds,
  * @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,
+static inline void update_sg_lb_stats(struct sched_domain *sd,
+			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)
@@ -3635,8 +3713,11 @@ static inline void update_sg_lb_stats(struct sched_group *group, int this_cpu,
 	unsigned long sum_avg_load_per_task;
 	unsigned long avg_load_per_task;
 
-	if (local_group)
+	if (local_group) {
 		balance_cpu = group_first_cpu(group);
+		if (balance_cpu == this_cpu)
+			update_group_power(sd, this_cpu);
+	}
 
 	/* Tally up the load of all CPUs in the group */
 	sum_avg_load_per_task = avg_load_per_task = 0;
@@ -3685,8 +3766,7 @@ static inline void update_sg_lb_stats(struct sched_group *group, int this_cpu,
 	}
 
 	/* Adjust by relative CPU power of the group */
-	sgs->avg_load = sg_div_cpu_power(group,
-			sgs->group_load * SCHED_LOAD_SCALE);
+	sgs->avg_load = (sgs->group_load * SCHED_LOAD_SCALE) / group->cpu_power;
 
 
 	/*
@@ -3698,14 +3778,14 @@ static inline void update_sg_lb_stats(struct sched_group *group, int this_cpu,
 	 *      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);
+	avg_load_per_task = (sum_avg_load_per_task * SCHED_LOAD_SCALE) /
+		group->cpu_power;
 
 	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;
-
+	sgs->group_capacity =
+		DIV_ROUND_CLOSEST(group->cpu_power, SCHED_LOAD_SCALE);
 }
 
 /**
@@ -3723,9 +3803,13 @@ static inline void update_sd_lb_stats(struct sched_domain *sd, int this_cpu,
 			const struct cpumask *cpus, int *balance,
 			struct sd_lb_stats *sds)
 {
+	struct sched_domain *child = sd->child;
 	struct sched_group *group = sd->groups;
 	struct sg_lb_stats sgs;
-	int load_idx;
+	int load_idx, prefer_sibling = 0;
+
+	if (child && child->flags & SD_PREFER_SIBLING)
+		prefer_sibling = 1;
 
 	init_sd_power_savings_stats(sd, sds, idle);
 	load_idx = get_sd_load_idx(sd, idle);
@@ -3736,14 +3820,22 @@ static inline void update_sd_lb_stats(struct sched_domain *sd, int this_cpu,
 		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,
+		update_sg_lb_stats(sd, 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;
+		sds->total_pwr += group->cpu_power;
+
+		/*
+		 * In case the child domain prefers tasks go to siblings
+		 * first, lower the group capacity to one so that we'll try
+		 * and move all the excess tasks away.
+		 */
+		if (prefer_sibling)
+			sgs.group_capacity = min(sgs.group_capacity, 1UL);
 
 		if (local_group) {
 			sds->this_load = sgs.avg_load;
@@ -3763,7 +3855,6 @@ static inline void update_sd_lb_stats(struct sched_domain *sd, int this_cpu,
 		update_sd_power_savings_stats(group, sds, local_group, &sgs);
 		group = group->next;
 	} while (group != sd->groups);
-
 }
 
 /**
@@ -3801,28 +3892,28 @@ static inline void fix_small_imbalance(struct sd_lb_stats *sds,
 	 * moving them.
 	 */
 
-	pwr_now += sds->busiest->__cpu_power *
+	pwr_now += sds->busiest->cpu_power *
 			min(sds->busiest_load_per_task, sds->max_load);
-	pwr_now += sds->this->__cpu_power *
+	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);
+	tmp = (sds->busiest_load_per_task * SCHED_LOAD_SCALE) /
+		sds->busiest->cpu_power;
 	if (sds->max_load > tmp)
-		pwr_move += sds->busiest->__cpu_power *
+		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 <
+	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);
+		tmp = (sds->max_load * sds->busiest->cpu_power) /
+			sds->this->cpu_power;
 	else
-		tmp = sg_div_cpu_power(sds->this,
-			sds->busiest_load_per_task * SCHED_LOAD_SCALE);
-	pwr_move += sds->this->__cpu_power *
+		tmp = (sds->busiest_load_per_task * SCHED_LOAD_SCALE) /
+			sds->this->cpu_power;
+	pwr_move += sds->this->cpu_power *
 			min(sds->this_load_per_task, sds->this_load + tmp);
 	pwr_move /= SCHED_LOAD_SCALE;
 
@@ -3857,8 +3948,8 @@ static inline void calculate_imbalance(struct sd_lb_stats *sds, int this_cpu,
 			sds->max_load - sds->busiest_load_per_task);
 
 	/* How much load to actually move to equalise the imbalance */
-	*imbalance = min(max_pull * sds->busiest->__cpu_power,
-		(sds->avg_load - sds->this_load) * sds->this->__cpu_power)
+	*imbalance = min(max_pull * sds->busiest->cpu_power,
+		(sds->avg_load - sds->this_load) * sds->this->cpu_power)
 			/ SCHED_LOAD_SCALE;
 
 	/*
@@ -3988,15 +4079,18 @@ find_busiest_queue(struct sched_group *group, enum cpu_idle_type idle,
 	int i;
 
 	for_each_cpu(i, sched_group_cpus(group)) {
+		unsigned long power = power_of(i);
+		unsigned long capacity = DIV_ROUND_CLOSEST(power, SCHED_LOAD_SCALE);
 		unsigned long wl;
 
 		if (!cpumask_test_cpu(i, cpus))
 			continue;
 
 		rq = cpu_rq(i);
-		wl = weighted_cpuload(i);
+		wl = weighted_cpuload(i) * SCHED_LOAD_SCALE;
+		wl /= power;
 
-		if (rq->nr_running == 1 && wl > imbalance)
+		if (capacity && rq->nr_running == 1 && wl > imbalance)
 			continue;
 
 		if (wl > max_load) {
@@ -5031,17 +5125,16 @@ void account_idle_time(cputime_t cputime)
  */
 void account_process_tick(struct task_struct *p, int user_tick)
 {
-	cputime_t one_jiffy = jiffies_to_cputime(1);
-	cputime_t one_jiffy_scaled = cputime_to_scaled(one_jiffy);
+	cputime_t one_jiffy_scaled = cputime_to_scaled(cputime_one_jiffy);
 	struct rq *rq = this_rq();
 
 	if (user_tick)
-		account_user_time(p, one_jiffy, one_jiffy_scaled);
+		account_user_time(p, cputime_one_jiffy, one_jiffy_scaled);
 	else if ((p != rq->idle) || (irq_count() != HARDIRQ_OFFSET))
-		account_system_time(p, HARDIRQ_OFFSET, one_jiffy,
+		account_system_time(p, HARDIRQ_OFFSET, cputime_one_jiffy,
 				    one_jiffy_scaled);
 	else
-		account_idle_time(one_jiffy);
+		account_idle_time(cputime_one_jiffy);
 }
 
 /*
@@ -5145,7 +5238,7 @@ void scheduler_tick(void)
 	curr->sched_class->task_tick(rq, curr, 0);
 	spin_unlock(&rq->lock);
 
-	perf_counter_task_tick(curr, cpu);
+	perf_event_task_tick(curr, cpu);
 
 #ifdef CONFIG_SMP
 	rq->idle_at_tick = idle_cpu(cpu);
@@ -5257,14 +5350,13 @@ static inline void schedule_debug(struct task_struct *prev)
 #endif
 }
 
-static void put_prev_task(struct rq *rq, struct task_struct *prev)
+static void put_prev_task(struct rq *rq, struct task_struct *p)
 {
-	if (prev->state == TASK_RUNNING) {
-		u64 runtime = prev->se.sum_exec_runtime;
+	u64 runtime = p->se.sum_exec_runtime - p->se.prev_sum_exec_runtime;
 
-		runtime -= prev->se.prev_sum_exec_runtime;
-		runtime = min_t(u64, runtime, 2*sysctl_sched_migration_cost);
+	update_avg(&p->se.avg_running, runtime);
 
+	if (p->state == TASK_RUNNING) {
 		/*
 		 * In order to avoid avg_overlap growing stale when we are
 		 * indeed overlapping and hence not getting put to sleep, grow
@@ -5274,9 +5366,12 @@ static void put_prev_task(struct rq *rq, struct task_struct *prev)
 		 * correlates to the amount of cache footprint a task can
 		 * build up.
 		 */
-		update_avg(&prev->se.avg_overlap, runtime);
+		runtime = min_t(u64, runtime, 2*sysctl_sched_migration_cost);
+		update_avg(&p->se.avg_overlap, runtime);
+	} else {
+		update_avg(&p->se.avg_running, 0);
 	}
-	prev->sched_class->put_prev_task(rq, prev);
+	p->sched_class->put_prev_task(rq, p);
 }
 
 /*
@@ -5325,7 +5420,7 @@ need_resched:
 	preempt_disable();
 	cpu = smp_processor_id();
 	rq = cpu_rq(cpu);
-	rcu_qsctr_inc(cpu);
+	rcu_sched_qs(cpu);
 	prev = rq->curr;
 	switch_count = &prev->nivcsw;
 
@@ -5349,10 +5444,7 @@ need_resched_nonpreemptible:
 		switch_count = &prev->nvcsw;
 	}
 
-#ifdef CONFIG_SMP
-	if (prev->sched_class->pre_schedule)
-		prev->sched_class->pre_schedule(rq, prev);
-#endif
+	pre_schedule(rq, prev);
 
 	if (unlikely(!rq->nr_running))
 		idle_balance(cpu, rq);
@@ -5362,7 +5454,7 @@ need_resched_nonpreemptible:
 
 	if (likely(prev != next)) {
 		sched_info_switch(prev, next);
-		perf_counter_task_sched_out(prev, next, cpu);
+		perf_event_task_sched_out(prev, next, cpu);
 
 		rq->nr_switches++;
 		rq->curr = next;
@@ -5378,6 +5470,8 @@ need_resched_nonpreemptible:
 	} else
 		spin_unlock_irq(&rq->lock);
 
+	post_schedule(rq);
+
 	if (unlikely(reacquire_kernel_lock(current) < 0))
 		goto need_resched_nonpreemptible;
 
@@ -5509,10 +5603,10 @@ asmlinkage void __sched preempt_schedule_irq(void)
 
 #endif /* CONFIG_PREEMPT */
 
-int default_wake_function(wait_queue_t *curr, unsigned mode, int sync,
+int default_wake_function(wait_queue_t *curr, unsigned mode, int wake_flags,
 			  void *key)
 {
-	return try_to_wake_up(curr->private, mode, sync);
+	return try_to_wake_up(curr->private, mode, wake_flags);
 }
 EXPORT_SYMBOL(default_wake_function);
 
@@ -5526,14 +5620,14 @@ EXPORT_SYMBOL(default_wake_function);
  * zero in this (rare) case, and we handle it by continuing to scan the queue.
  */
 static void __wake_up_common(wait_queue_head_t *q, unsigned int mode,
-			int nr_exclusive, int sync, void *key)
+			int nr_exclusive, int wake_flags, void *key)
 {
 	wait_queue_t *curr, *next;
 
 	list_for_each_entry_safe(curr, next, &q->task_list, task_list) {
 		unsigned flags = curr->flags;
 
-		if (curr->func(curr, mode, sync, key) &&
+		if (curr->func(curr, mode, wake_flags, key) &&
 				(flags & WQ_FLAG_EXCLUSIVE) && !--nr_exclusive)
 			break;
 	}
@@ -5594,16 +5688,16 @@ void __wake_up_sync_key(wait_queue_head_t *q, unsigned int mode,
 			int nr_exclusive, void *key)
 {
 	unsigned long flags;
-	int sync = 1;
+	int wake_flags = WF_SYNC;
 
 	if (unlikely(!q))
 		return;
 
 	if (unlikely(!nr_exclusive))
-		sync = 0;
+		wake_flags = 0;
 
 	spin_lock_irqsave(&q->lock, flags);
-	__wake_up_common(q, mode, nr_exclusive, sync, key);
+	__wake_up_common(q, mode, nr_exclusive, wake_flags, key);
 	spin_unlock_irqrestore(&q->lock, flags);
 }
 EXPORT_SYMBOL_GPL(__wake_up_sync_key);
@@ -6123,17 +6217,25 @@ static int __sched_setscheduler(struct task_struct *p, int policy,
 	unsigned long flags;
 	const struct sched_class *prev_class = p->sched_class;
 	struct rq *rq;
+	int reset_on_fork;
 
 	/* may grab non-irq protected spin_locks */
 	BUG_ON(in_interrupt());
 recheck:
 	/* double check policy once rq lock held */
-	if (policy < 0)
+	if (policy < 0) {
+		reset_on_fork = p->sched_reset_on_fork;
 		policy = oldpolicy = p->policy;
-	else if (policy != SCHED_FIFO && policy != SCHED_RR &&
-			policy != SCHED_NORMAL && policy != SCHED_BATCH &&
-			policy != SCHED_IDLE)
-		return -EINVAL;
+	} else {
+		reset_on_fork = !!(policy & SCHED_RESET_ON_FORK);
+		policy &= ~SCHED_RESET_ON_FORK;
+
+		if (policy != SCHED_FIFO && policy != SCHED_RR &&
+				policy != SCHED_NORMAL && policy != SCHED_BATCH &&
+				policy != SCHED_IDLE)
+			return -EINVAL;
+	}
+
 	/*
 	 * Valid priorities for SCHED_FIFO and SCHED_RR are
 	 * 1..MAX_USER_RT_PRIO-1, valid priority for SCHED_NORMAL,
@@ -6177,6 +6279,10 @@ recheck:
 		/* can't change other user's priorities */
 		if (!check_same_owner(p))
 			return -EPERM;
+
+		/* Normal users shall not reset the sched_reset_on_fork flag */
+		if (p->sched_reset_on_fork && !reset_on_fork)
+			return -EPERM;
 	}
 
 	if (user) {
@@ -6220,6 +6326,8 @@ recheck:
 	if (running)
 		p->sched_class->put_prev_task(rq, p);
 
+	p->sched_reset_on_fork = reset_on_fork;
+
 	oldprio = p->prio;
 	__setscheduler(rq, p, policy, param->sched_priority);
 
@@ -6336,14 +6444,15 @@ SYSCALL_DEFINE1(sched_getscheduler, pid_t, pid)
 	if (p) {
 		retval = security_task_getscheduler(p);
 		if (!retval)
-			retval = p->policy;
+			retval = p->policy
+				| (p->sched_reset_on_fork ? SCHED_RESET_ON_FORK : 0);
 	}
 	read_unlock(&tasklist_lock);
 	return retval;
 }
 
 /**
- * sys_sched_getscheduler - get the RT priority of a thread
+ * sys_sched_getparam - get the RT priority of a thread
  * @pid: the pid in question.
  * @param: structure containing the RT priority.
  */
@@ -6571,19 +6680,9 @@ static inline int should_resched(void)
 
 static void __cond_resched(void)
 {
-#ifdef CONFIG_DEBUG_SPINLOCK_SLEEP
-	__might_sleep(__FILE__, __LINE__);
-#endif
-	/*
-	 * The BKS might be reacquired before we have dropped
-	 * PREEMPT_ACTIVE, which could trigger a second
-	 * cond_resched() call.
-	 */
-	do {
-		add_preempt_count(PREEMPT_ACTIVE);
-		schedule();
-		sub_preempt_count(PREEMPT_ACTIVE);
-	} while (need_resched());
+	add_preempt_count(PREEMPT_ACTIVE);
+	schedule();
+	sub_preempt_count(PREEMPT_ACTIVE);
 }
 
 int __sched _cond_resched(void)
@@ -6597,18 +6696,20 @@ int __sched _cond_resched(void)
 EXPORT_SYMBOL(_cond_resched);
 
 /*
- * cond_resched_lock() - if a reschedule is pending, drop the given lock,
+ * __cond_resched_lock() - if a reschedule is pending, drop the given lock,
  * call schedule, and on return reacquire the lock.
  *
  * This works OK both with and without CONFIG_PREEMPT. We do strange low-level
  * operations here to prevent schedule() from being called twice (once via
  * spin_unlock(), once by hand).
  */
-int cond_resched_lock(spinlock_t *lock)
+int __cond_resched_lock(spinlock_t *lock)
 {
 	int resched = should_resched();
 	int ret = 0;
 
+	lockdep_assert_held(lock);
+
 	if (spin_needbreak(lock) || resched) {
 		spin_unlock(lock);
 		if (resched)
@@ -6620,9 +6721,9 @@ int cond_resched_lock(spinlock_t *lock)
 	}
 	return ret;
 }
-EXPORT_SYMBOL(cond_resched_lock);
+EXPORT_SYMBOL(__cond_resched_lock);
 
-int __sched cond_resched_softirq(void)
+int __sched __cond_resched_softirq(void)
 {
 	BUG_ON(!in_softirq());
 
@@ -6634,7 +6735,7 @@ int __sched cond_resched_softirq(void)
 	}
 	return 0;
 }
-EXPORT_SYMBOL(cond_resched_softirq);
+EXPORT_SYMBOL(__cond_resched_softirq);
 
 /**
  * yield - yield the current processor to other threads.
@@ -6652,17 +6753,16 @@ EXPORT_SYMBOL(yield);
 /*
  * This task is about to go to sleep on IO. Increment rq->nr_iowait so
  * that process accounting knows that this is a task in IO wait state.
- *
- * But don't do that if it is a deliberate, throttling IO wait (this task
- * has set its backing_dev_info: the queue against which it should throttle)
  */
 void __sched io_schedule(void)
 {
-	struct rq *rq = &__raw_get_cpu_var(runqueues);
+	struct rq *rq = raw_rq();
 
 	delayacct_blkio_start();
 	atomic_inc(&rq->nr_iowait);
+	current->in_iowait = 1;
 	schedule();
+	current->in_iowait = 0;
 	atomic_dec(&rq->nr_iowait);
 	delayacct_blkio_end();
 }
@@ -6670,12 +6770,14 @@ EXPORT_SYMBOL(io_schedule);
 
 long __sched io_schedule_timeout(long timeout)
 {
-	struct rq *rq = &__raw_get_cpu_var(runqueues);
+	struct rq *rq = raw_rq();
 	long ret;
 
 	delayacct_blkio_start();
 	atomic_inc(&rq->nr_iowait);
+	current->in_iowait = 1;
 	ret = schedule_timeout(timeout);
+	current->in_iowait = 0;
 	atomic_dec(&rq->nr_iowait);
 	delayacct_blkio_end();
 	return ret;
@@ -6759,23 +6861,8 @@ SYSCALL_DEFINE2(sched_rr_get_interval, pid_t, pid,
 	if (retval)
 		goto out_unlock;
 
-	/*
-	 * Time slice is 0 for SCHED_FIFO tasks and for SCHED_OTHER
-	 * tasks that are on an otherwise idle runqueue:
-	 */
-	time_slice = 0;
-	if (p->policy == SCHED_RR) {
-		time_slice = DEF_TIMESLICE;
-	} else if (p->policy != SCHED_FIFO) {
-		struct sched_entity *se = &p->se;
-		unsigned long flags;
-		struct rq *rq;
+	time_slice = p->sched_class->get_rr_interval(p);
 
-		rq = task_rq_lock(p, &flags);
-		if (rq->cfs.load.weight)
-			time_slice = NS_TO_JIFFIES(sched_slice(&rq->cfs, se));
-		task_rq_unlock(rq, &flags);
-	}
 	read_unlock(&tasklist_lock);
 	jiffies_to_timespec(time_slice, &t);
 	retval = copy_to_user(interval, &t, sizeof(t)) ? -EFAULT : 0;
@@ -6992,8 +7079,12 @@ int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask)
 
 	if (migrate_task(p, cpumask_any_and(cpu_online_mask, new_mask), &req)) {
 		/* Need help from migration thread: drop lock and wait. */
+		struct task_struct *mt = rq->migration_thread;
+
+		get_task_struct(mt);
 		task_rq_unlock(rq, &flags);
 		wake_up_process(rq->migration_thread);
+		put_task_struct(mt);
 		wait_for_completion(&req.done);
 		tlb_migrate_finish(p->mm);
 		return 0;
@@ -7051,6 +7142,11 @@ fail:
 	return ret;
 }
 
+#define RCU_MIGRATION_IDLE	0
+#define RCU_MIGRATION_NEED_QS	1
+#define RCU_MIGRATION_GOT_QS	2
+#define RCU_MIGRATION_MUST_SYNC	3
+
 /*
  * migration_thread - this is a highprio system thread that performs
  * thread migration by bumping thread off CPU then 'pushing' onto
@@ -7058,6 +7154,7 @@ fail:
  */
 static int migration_thread(void *data)
 {
+	int badcpu;
 	int cpu = (long)data;
 	struct rq *rq;
 
@@ -7092,8 +7189,17 @@ static int migration_thread(void *data)
 		req = list_entry(head->next, struct migration_req, list);
 		list_del_init(head->next);
 
-		spin_unlock(&rq->lock);
-		__migrate_task(req->task, cpu, req->dest_cpu);
+		if (req->task != NULL) {
+			spin_unlock(&rq->lock);
+			__migrate_task(req->task, cpu, req->dest_cpu);
+		} else if (likely(cpu == (badcpu = smp_processor_id()))) {
+			req->dest_cpu = RCU_MIGRATION_GOT_QS;
+			spin_unlock(&rq->lock);
+		} else {
+			req->dest_cpu = RCU_MIGRATION_MUST_SYNC;
+			spin_unlock(&rq->lock);
+			WARN_ONCE(1, "migration_thread() on CPU %d, expected %d\n", badcpu, cpu);
+		}
 		local_irq_enable();
 
 		complete(&req->done);
@@ -7607,7 +7713,7 @@ migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu)
 /*
  * Register at high priority so that task migration (migrate_all_tasks)
  * happens before everything else.  This has to be lower priority than
- * the notifier in the perf_counter subsystem, though.
+ * the notifier in the perf_event subsystem, though.
  */
 static struct notifier_block __cpuinitdata migration_notifier = {
 	.notifier_call = migration_call,
@@ -7625,7 +7731,7 @@ static int __init migration_init(void)
 	migration_call(&migration_notifier, CPU_ONLINE, cpu);
 	register_cpu_notifier(&migration_notifier);
 
-	return err;
+	return 0;
 }
 early_initcall(migration_init);
 #endif
@@ -7672,7 +7778,7 @@ static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level,
 			break;
 		}
 
-		if (!group->__cpu_power) {
+		if (!group->cpu_power) {
 			printk(KERN_CONT "\n");
 			printk(KERN_ERR "ERROR: domain->cpu_power not "
 					"set\n");
@@ -7696,9 +7802,9 @@ static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level,
 		cpulist_scnprintf(str, sizeof(str), sched_group_cpus(group));
 
 		printk(KERN_CONT " %s", str);
-		if (group->__cpu_power != SCHED_LOAD_SCALE) {
-			printk(KERN_CONT " (__cpu_power = %d)",
-				group->__cpu_power);
+		if (group->cpu_power != SCHED_LOAD_SCALE) {
+			printk(KERN_CONT " (cpu_power = %d)",
+				group->cpu_power);
 		}
 
 		group = group->next;
@@ -7763,9 +7869,7 @@ static int sd_degenerate(struct sched_domain *sd)
 	}
 
 	/* Following flags don't use groups */
-	if (sd->flags & (SD_WAKE_IDLE |
-			 SD_WAKE_AFFINE |
-			 SD_WAKE_BALANCE))
+	if (sd->flags & (SD_WAKE_AFFINE))
 		return 0;
 
 	return 1;
@@ -7782,10 +7886,6 @@ sd_parent_degenerate(struct sched_domain *sd, struct sched_domain *parent)
 	if (!cpumask_equal(sched_domain_span(sd), sched_domain_span(parent)))
 		return 0;
 
-	/* Does parent contain flags not in child? */
-	/* WAKE_BALANCE is a subset of WAKE_AFFINE */
-	if (cflags & SD_WAKE_AFFINE)
-		pflags &= ~SD_WAKE_BALANCE;
 	/* Flags needing groups don't count if only 1 group in parent */
 	if (parent->groups == parent->groups->next) {
 		pflags &= ~(SD_LOAD_BALANCE |
@@ -7841,7 +7941,7 @@ static void rq_attach_root(struct rq *rq, struct root_domain *rd)
 	rq->rd = rd;
 
 	cpumask_set_cpu(rq->cpu, rd->span);
-	if (cpumask_test_cpu(rq->cpu, cpu_online_mask))
+	if (cpumask_test_cpu(rq->cpu, cpu_active_mask))
 		set_rq_online(rq);
 
 	spin_unlock_irqrestore(&rq->lock, flags);
@@ -7983,7 +8083,7 @@ init_sched_build_groups(const struct cpumask *span,
 			continue;
 
 		cpumask_clear(sched_group_cpus(sg));
-		sg->__cpu_power = 0;
+		sg->cpu_power = 0;
 
 		for_each_cpu(j, span) {
 			if (group_fn(j, cpu_map, NULL, tmpmask) != group)
@@ -8091,6 +8191,39 @@ struct static_sched_domain {
 	DECLARE_BITMAP(span, CONFIG_NR_CPUS);
 };
 
+struct s_data {
+#ifdef CONFIG_NUMA
+	int			sd_allnodes;
+	cpumask_var_t		domainspan;
+	cpumask_var_t		covered;
+	cpumask_var_t		notcovered;
+#endif
+	cpumask_var_t		nodemask;
+	cpumask_var_t		this_sibling_map;
+	cpumask_var_t		this_core_map;
+	cpumask_var_t		send_covered;
+	cpumask_var_t		tmpmask;
+	struct sched_group	**sched_group_nodes;
+	struct root_domain	*rd;
+};
+
+enum s_alloc {
+	sa_sched_groups = 0,
+	sa_rootdomain,
+	sa_tmpmask,
+	sa_send_covered,
+	sa_this_core_map,
+	sa_this_sibling_map,
+	sa_nodemask,
+	sa_sched_group_nodes,
+#ifdef CONFIG_NUMA
+	sa_notcovered,
+	sa_covered,
+	sa_domainspan,
+#endif
+	sa_none,
+};
+
 /*
  * SMT sched-domains:
  */
@@ -8208,11 +8341,76 @@ static void init_numa_sched_groups_power(struct sched_group *group_head)
 				continue;
 			}
 
-			sg_inc_cpu_power(sg, sd->groups->__cpu_power);
+			sg->cpu_power += sd->groups->cpu_power;
 		}
 		sg = sg->next;
 	} while (sg != group_head);
 }
+
+static int build_numa_sched_groups(struct s_data *d,
+				   const struct cpumask *cpu_map, int num)
+{
+	struct sched_domain *sd;
+	struct sched_group *sg, *prev;
+	int n, j;
+
+	cpumask_clear(d->covered);
+	cpumask_and(d->nodemask, cpumask_of_node(num), cpu_map);
+	if (cpumask_empty(d->nodemask)) {
+		d->sched_group_nodes[num] = NULL;
+		goto out;
+	}
+
+	sched_domain_node_span(num, d->domainspan);
+	cpumask_and(d->domainspan, d->domainspan, cpu_map);
+
+	sg = kmalloc_node(sizeof(struct sched_group) + cpumask_size(),
+			  GFP_KERNEL, num);
+	if (!sg) {
+		printk(KERN_WARNING "Can not alloc domain group for node %d\n",
+		       num);
+		return -ENOMEM;
+	}
+	d->sched_group_nodes[num] = sg;
+
+	for_each_cpu(j, d->nodemask) {
+		sd = &per_cpu(node_domains, j).sd;
+		sd->groups = sg;
+	}
+
+	sg->cpu_power = 0;
+	cpumask_copy(sched_group_cpus(sg), d->nodemask);
+	sg->next = sg;
+	cpumask_or(d->covered, d->covered, d->nodemask);
+
+	prev = sg;
+	for (j = 0; j < nr_node_ids; j++) {
+		n = (num + j) % nr_node_ids;
+		cpumask_complement(d->notcovered, d->covered);
+		cpumask_and(d->tmpmask, d->notcovered, cpu_map);
+		cpumask_and(d->tmpmask, d->tmpmask, d->domainspan);
+		if (cpumask_empty(d->tmpmask))
+			break;
+		cpumask_and(d->tmpmask, d->tmpmask, cpumask_of_node(n));
+		if (cpumask_empty(d->tmpmask))
+			continue;
+		sg = kmalloc_node(sizeof(struct sched_group) + cpumask_size(),
+				  GFP_KERNEL, num);
+		if (!sg) {
+			printk(KERN_WARNING
+			       "Can not alloc domain group for node %d\n", j);
+			return -ENOMEM;
+		}
+		sg->cpu_power = 0;
+		cpumask_copy(sched_group_cpus(sg), d->tmpmask);
+		sg->next = prev->next;
+		cpumask_or(d->covered, d->covered, d->tmpmask);
+		prev->next = sg;
+		prev = sg;
+	}
+out:
+	return 0;
+}
 #endif /* CONFIG_NUMA */
 
 #ifdef CONFIG_NUMA
@@ -8266,15 +8464,13 @@ static void free_sched_groups(const struct cpumask *cpu_map,
  * there are asymmetries in the topology. If there are asymmetries, group
  * having more cpu_power will pickup more load compared to the group having
  * less cpu_power.
- *
- * cpu_power will be a multiple of SCHED_LOAD_SCALE. This multiple represents
- * the maximum number of tasks a group can handle in the presence of other idle
- * or lightly loaded groups in the same sched domain.
  */
 static void init_sched_groups_power(int cpu, struct sched_domain *sd)
 {
 	struct sched_domain *child;
 	struct sched_group *group;
+	long power;
+	int weight;
 
 	WARN_ON(!sd || !sd->groups);
 
@@ -8283,28 +8479,32 @@ static void init_sched_groups_power(int cpu, struct sched_domain *sd)
 
 	child = sd->child;
 
-	sd->groups->__cpu_power = 0;
+	sd->groups->cpu_power = 0;
 
-	/*
-	 * For perf policy, if the groups in child domain share resources
-	 * (for example cores sharing some portions of the cache hierarchy
-	 * or SMT), then set this domain groups cpu_power such that each group
-	 * can handle only one task, when there are other idle groups in the
-	 * same sched domain.
-	 */
-	if (!child || (!(sd->flags & SD_POWERSAVINGS_BALANCE) &&
-		       (child->flags &
-			(SD_SHARE_CPUPOWER | SD_SHARE_PKG_RESOURCES)))) {
-		sg_inc_cpu_power(sd->groups, SCHED_LOAD_SCALE);
+	if (!child) {
+		power = SCHED_LOAD_SCALE;
+		weight = cpumask_weight(sched_domain_span(sd));
+		/*
+		 * SMT siblings share the power of a single core.
+		 * Usually multiple threads get a better yield out of
+		 * that one core than a single thread would have,
+		 * reflect that in sd->smt_gain.
+		 */
+		if ((sd->flags & SD_SHARE_CPUPOWER) && weight > 1) {
+			power *= sd->smt_gain;
+			power /= weight;
+			power >>= SCHED_LOAD_SHIFT;
+		}
+		sd->groups->cpu_power += power;
 		return;
 	}
 
 	/*
-	 * add cpu_power of each child group to this groups cpu_power
+	 * Add cpu_power of each child group to this groups cpu_power.
 	 */
 	group = child->groups;
 	do {
-		sg_inc_cpu_power(sd->groups, group->__cpu_power);
+		sd->groups->cpu_power += group->cpu_power;
 		group = group->next;
 	} while (group != child->groups);
 }
@@ -8371,287 +8571,292 @@ static void set_domain_attribute(struct sched_domain *sd,
 		request = attr->relax_domain_level;
 	if (request < sd->level) {
 		/* turn off idle balance on this domain */
-		sd->flags &= ~(SD_WAKE_IDLE|SD_BALANCE_NEWIDLE);
+		sd->flags &= ~(SD_BALANCE_WAKE|SD_BALANCE_NEWIDLE);
 	} else {
 		/* turn on idle balance on this domain */
-		sd->flags |= (SD_WAKE_IDLE_FAR|SD_BALANCE_NEWIDLE);
+		sd->flags |= (SD_BALANCE_WAKE|SD_BALANCE_NEWIDLE);
+	}
+}
+
+static void __free_domain_allocs(struct s_data *d, enum s_alloc what,
+				 const struct cpumask *cpu_map)
+{
+	switch (what) {
+	case sa_sched_groups:
+		free_sched_groups(cpu_map, d->tmpmask); /* fall through */
+		d->sched_group_nodes = NULL;
+	case sa_rootdomain:
+		free_rootdomain(d->rd); /* fall through */
+	case sa_tmpmask:
+		free_cpumask_var(d->tmpmask); /* fall through */
+	case sa_send_covered:
+		free_cpumask_var(d->send_covered); /* fall through */
+	case sa_this_core_map:
+		free_cpumask_var(d->this_core_map); /* fall through */
+	case sa_this_sibling_map:
+		free_cpumask_var(d->this_sibling_map); /* fall through */
+	case sa_nodemask:
+		free_cpumask_var(d->nodemask); /* fall through */
+	case sa_sched_group_nodes:
+#ifdef CONFIG_NUMA
+		kfree(d->sched_group_nodes); /* fall through */
+	case sa_notcovered:
+		free_cpumask_var(d->notcovered); /* fall through */
+	case sa_covered:
+		free_cpumask_var(d->covered); /* fall through */
+	case sa_domainspan:
+		free_cpumask_var(d->domainspan); /* fall through */
+#endif
+	case sa_none:
+		break;
 	}
 }
 
-/*
- * Build sched domains for a given set of cpus and attach the sched domains
- * to the individual cpus
- */
-static int __build_sched_domains(const struct cpumask *cpu_map,
-				 struct sched_domain_attr *attr)
+static enum s_alloc __visit_domain_allocation_hell(struct s_data *d,
+						   const struct cpumask *cpu_map)
 {
-	int i, err = -ENOMEM;
-	struct root_domain *rd;
-	cpumask_var_t nodemask, this_sibling_map, this_core_map, send_covered,
-		tmpmask;
-#ifdef CONFIG_NUMA
-	cpumask_var_t domainspan, covered, notcovered;
-	struct sched_group **sched_group_nodes = NULL;
-	int sd_allnodes = 0;
-
-	if (!alloc_cpumask_var(&domainspan, GFP_KERNEL))
-		goto out;
-	if (!alloc_cpumask_var(&covered, GFP_KERNEL))
-		goto free_domainspan;
-	if (!alloc_cpumask_var(&notcovered, GFP_KERNEL))
-		goto free_covered;
-#endif
-
-	if (!alloc_cpumask_var(&nodemask, GFP_KERNEL))
-		goto free_notcovered;
-	if (!alloc_cpumask_var(&this_sibling_map, GFP_KERNEL))
-		goto free_nodemask;
-	if (!alloc_cpumask_var(&this_core_map, GFP_KERNEL))
-		goto free_this_sibling_map;
-	if (!alloc_cpumask_var(&send_covered, GFP_KERNEL))
-		goto free_this_core_map;
-	if (!alloc_cpumask_var(&tmpmask, GFP_KERNEL))
-		goto free_send_covered;
-
 #ifdef CONFIG_NUMA
-	/*
-	 * Allocate the per-node list of sched groups
-	 */
-	sched_group_nodes = kcalloc(nr_node_ids, sizeof(struct sched_group *),
-				    GFP_KERNEL);
-	if (!sched_group_nodes) {
+	if (!alloc_cpumask_var(&d->domainspan, GFP_KERNEL))
+		return sa_none;
+	if (!alloc_cpumask_var(&d->covered, GFP_KERNEL))
+		return sa_domainspan;
+	if (!alloc_cpumask_var(&d->notcovered, GFP_KERNEL))
+		return sa_covered;
+	/* Allocate the per-node list of sched groups */
+	d->sched_group_nodes = kcalloc(nr_node_ids,
+				      sizeof(struct sched_group *), GFP_KERNEL);
+	if (!d->sched_group_nodes) {
 		printk(KERN_WARNING "Can not alloc sched group node list\n");
-		goto free_tmpmask;
-	}
-#endif
-
-	rd = alloc_rootdomain();
-	if (!rd) {
+		return sa_notcovered;
+	}
+	sched_group_nodes_bycpu[cpumask_first(cpu_map)] = d->sched_group_nodes;
+#endif
+	if (!alloc_cpumask_var(&d->nodemask, GFP_KERNEL))
+		return sa_sched_group_nodes;
+	if (!alloc_cpumask_var(&d->this_sibling_map, GFP_KERNEL))
+		return sa_nodemask;
+	if (!alloc_cpumask_var(&d->this_core_map, GFP_KERNEL))
+		return sa_this_sibling_map;
+	if (!alloc_cpumask_var(&d->send_covered, GFP_KERNEL))
+		return sa_this_core_map;
+	if (!alloc_cpumask_var(&d->tmpmask, GFP_KERNEL))
+		return sa_send_covered;
+	d->rd = alloc_rootdomain();
+	if (!d->rd) {
 		printk(KERN_WARNING "Cannot alloc root domain\n");
-		goto free_sched_groups;
+		return sa_tmpmask;
 	}
+	return sa_rootdomain;
+}
 
+static struct sched_domain *__build_numa_sched_domains(struct s_data *d,
+	const struct cpumask *cpu_map, struct sched_domain_attr *attr, int i)
+{
+	struct sched_domain *sd = NULL;
 #ifdef CONFIG_NUMA
-	sched_group_nodes_bycpu[cpumask_first(cpu_map)] = sched_group_nodes;
-#endif
-
-	/*
-	 * Set up domains for cpus specified by the cpu_map.
-	 */
-	for_each_cpu(i, cpu_map) {
-		struct sched_domain *sd = NULL, *p;
-
-		cpumask_and(nodemask, cpumask_of_node(cpu_to_node(i)), cpu_map);
-
-#ifdef CONFIG_NUMA
-		if (cpumask_weight(cpu_map) >
-				SD_NODES_PER_DOMAIN*cpumask_weight(nodemask)) {
-			sd = &per_cpu(allnodes_domains, i).sd;
-			SD_INIT(sd, ALLNODES);
-			set_domain_attribute(sd, attr);
-			cpumask_copy(sched_domain_span(sd), cpu_map);
-			cpu_to_allnodes_group(i, cpu_map, &sd->groups, tmpmask);
-			p = sd;
-			sd_allnodes = 1;
-		} else
-			p = NULL;
+	struct sched_domain *parent;
 
-		sd = &per_cpu(node_domains, i).sd;
-		SD_INIT(sd, NODE);
+	d->sd_allnodes = 0;
+	if (cpumask_weight(cpu_map) >
+	    SD_NODES_PER_DOMAIN * cpumask_weight(d->nodemask)) {
+		sd = &per_cpu(allnodes_domains, i).sd;
+		SD_INIT(sd, ALLNODES);
 		set_domain_attribute(sd, attr);
-		sched_domain_node_span(cpu_to_node(i), sched_domain_span(sd));
-		sd->parent = p;
-		if (p)
-			p->child = sd;
-		cpumask_and(sched_domain_span(sd),
-			    sched_domain_span(sd), cpu_map);
+		cpumask_copy(sched_domain_span(sd), cpu_map);
+		cpu_to_allnodes_group(i, cpu_map, &sd->groups, d->tmpmask);
+		d->sd_allnodes = 1;
+	}
+	parent = sd;
+
+	sd = &per_cpu(node_domains, i).sd;
+	SD_INIT(sd, NODE);
+	set_domain_attribute(sd, attr);
+	sched_domain_node_span(cpu_to_node(i), sched_domain_span(sd));
+	sd->parent = parent;
+	if (parent)
+		parent->child = sd;
+	cpumask_and(sched_domain_span(sd), sched_domain_span(sd), cpu_map);
 #endif
+	return sd;
+}
 
-		p = sd;
-		sd = &per_cpu(phys_domains, i).sd;
-		SD_INIT(sd, CPU);
-		set_domain_attribute(sd, attr);
-		cpumask_copy(sched_domain_span(sd), nodemask);
-		sd->parent = p;
-		if (p)
-			p->child = sd;
-		cpu_to_phys_group(i, cpu_map, &sd->groups, tmpmask);
+static struct sched_domain *__build_cpu_sched_domain(struct s_data *d,
+	const struct cpumask *cpu_map, struct sched_domain_attr *attr,
+	struct sched_domain *parent, int i)
+{
+	struct sched_domain *sd;
+	sd = &per_cpu(phys_domains, i).sd;
+	SD_INIT(sd, CPU);
+	set_domain_attribute(sd, attr);
+	cpumask_copy(sched_domain_span(sd), d->nodemask);
+	sd->parent = parent;
+	if (parent)
+		parent->child = sd;
+	cpu_to_phys_group(i, cpu_map, &sd->groups, d->tmpmask);
+	return sd;
+}
 
+static struct sched_domain *__build_mc_sched_domain(struct s_data *d,
+	const struct cpumask *cpu_map, struct sched_domain_attr *attr,
+	struct sched_domain *parent, int i)
+{
+	struct sched_domain *sd = parent;
 #ifdef CONFIG_SCHED_MC
-		p = sd;
-		sd = &per_cpu(core_domains, i).sd;
-		SD_INIT(sd, MC);
-		set_domain_attribute(sd, attr);
-		cpumask_and(sched_domain_span(sd), cpu_map,
-						   cpu_coregroup_mask(i));
-		sd->parent = p;
-		p->child = sd;
-		cpu_to_core_group(i, cpu_map, &sd->groups, tmpmask);
+	sd = &per_cpu(core_domains, i).sd;
+	SD_INIT(sd, MC);
+	set_domain_attribute(sd, attr);
+	cpumask_and(sched_domain_span(sd), cpu_map, cpu_coregroup_mask(i));
+	sd->parent = parent;
+	parent->child = sd;
+	cpu_to_core_group(i, cpu_map, &sd->groups, d->tmpmask);
 #endif
+	return sd;
+}
 
+static struct sched_domain *__build_smt_sched_domain(struct s_data *d,
+	const struct cpumask *cpu_map, struct sched_domain_attr *attr,
+	struct sched_domain *parent, int i)
+{
+	struct sched_domain *sd = parent;
 #ifdef CONFIG_SCHED_SMT
-		p = sd;
-		sd = &per_cpu(cpu_domains, i).sd;
-		SD_INIT(sd, SIBLING);
-		set_domain_attribute(sd, attr);
-		cpumask_and(sched_domain_span(sd),
-			    topology_thread_cpumask(i), cpu_map);
-		sd->parent = p;
-		p->child = sd;
-		cpu_to_cpu_group(i, cpu_map, &sd->groups, tmpmask);
+	sd = &per_cpu(cpu_domains, i).sd;
+	SD_INIT(sd, SIBLING);
+	set_domain_attribute(sd, attr);
+	cpumask_and(sched_domain_span(sd), cpu_map, topology_thread_cpumask(i));
+	sd->parent = parent;
+	parent->child = sd;
+	cpu_to_cpu_group(i, cpu_map, &sd->groups, d->tmpmask);
 #endif
-	}
+	return sd;
+}
 
+static void build_sched_groups(struct s_data *d, enum sched_domain_level l,
+			       const struct cpumask *cpu_map, int cpu)
+{
+	switch (l) {
 #ifdef CONFIG_SCHED_SMT
-	/* Set up CPU (sibling) groups */
-	for_each_cpu(i, cpu_map) {
-		cpumask_and(this_sibling_map,
-			    topology_thread_cpumask(i), cpu_map);
-		if (i != cpumask_first(this_sibling_map))
-			continue;
-
-		init_sched_build_groups(this_sibling_map, cpu_map,
-					&cpu_to_cpu_group,
-					send_covered, tmpmask);
-	}
+	case SD_LV_SIBLING: /* set up CPU (sibling) groups */
+		cpumask_and(d->this_sibling_map, cpu_map,
+			    topology_thread_cpumask(cpu));
+		if (cpu == cpumask_first(d->this_sibling_map))
+			init_sched_build_groups(d->this_sibling_map, cpu_map,
+						&cpu_to_cpu_group,
+						d->send_covered, d->tmpmask);
+		break;
 #endif
-
 #ifdef CONFIG_SCHED_MC
-	/* Set up multi-core groups */
-	for_each_cpu(i, cpu_map) {
-		cpumask_and(this_core_map, cpu_coregroup_mask(i), cpu_map);
-		if (i != cpumask_first(this_core_map))
-			continue;
-
-		init_sched_build_groups(this_core_map, cpu_map,
-					&cpu_to_core_group,
-					send_covered, tmpmask);
-	}
+	case SD_LV_MC: /* set up multi-core groups */
+		cpumask_and(d->this_core_map, cpu_map, cpu_coregroup_mask(cpu));
+		if (cpu == cpumask_first(d->this_core_map))
+			init_sched_build_groups(d->this_core_map, cpu_map,
+						&cpu_to_core_group,
+						d->send_covered, d->tmpmask);
+		break;
 #endif
-
-	/* Set up physical groups */
-	for (i = 0; i < nr_node_ids; i++) {
-		cpumask_and(nodemask, cpumask_of_node(i), cpu_map);
-		if (cpumask_empty(nodemask))
-			continue;
-
-		init_sched_build_groups(nodemask, cpu_map,
-					&cpu_to_phys_group,
-					send_covered, tmpmask);
-	}
-
+	case SD_LV_CPU: /* set up physical groups */
+		cpumask_and(d->nodemask, cpumask_of_node(cpu), cpu_map);
+		if (!cpumask_empty(d->nodemask))
+			init_sched_build_groups(d->nodemask, cpu_map,
+						&cpu_to_phys_group,
+						d->send_covered, d->tmpmask);
+		break;
 #ifdef CONFIG_NUMA
-	/* Set up node groups */
-	if (sd_allnodes) {
-		init_sched_build_groups(cpu_map, cpu_map,
-					&cpu_to_allnodes_group,
-					send_covered, tmpmask);
+	case SD_LV_ALLNODES:
+		init_sched_build_groups(cpu_map, cpu_map, &cpu_to_allnodes_group,
+					d->send_covered, d->tmpmask);
+		break;
+#endif
+	default:
+		break;
 	}
+}
 
-	for (i = 0; i < nr_node_ids; i++) {
-		/* Set up node groups */
-		struct sched_group *sg, *prev;
-		int j;
-
-		cpumask_clear(covered);
-		cpumask_and(nodemask, cpumask_of_node(i), cpu_map);
-		if (cpumask_empty(nodemask)) {
-			sched_group_nodes[i] = NULL;
-			continue;
-		}
+/*
+ * Build sched domains for a given set of cpus and attach the sched domains
+ * to the individual cpus
+ */
+static int __build_sched_domains(const struct cpumask *cpu_map,
+				 struct sched_domain_attr *attr)
+{
+	enum s_alloc alloc_state = sa_none;
+	struct s_data d;
+	struct sched_domain *sd;
+	int i;
+#ifdef CONFIG_NUMA
+	d.sd_allnodes = 0;
+#endif
 
-		sched_domain_node_span(i, domainspan);
-		cpumask_and(domainspan, domainspan, cpu_map);
+	alloc_state = __visit_domain_allocation_hell(&d, cpu_map);
+	if (alloc_state != sa_rootdomain)
+		goto error;
+	alloc_state = sa_sched_groups;
 
-		sg = kmalloc_node(sizeof(struct sched_group) + cpumask_size(),
-				  GFP_KERNEL, i);
-		if (!sg) {
-			printk(KERN_WARNING "Can not alloc domain group for "
-				"node %d\n", i);
-			goto error;
-		}
-		sched_group_nodes[i] = sg;
-		for_each_cpu(j, nodemask) {
-			struct sched_domain *sd;
+	/*
+	 * Set up domains for cpus specified by the cpu_map.
+	 */
+	for_each_cpu(i, cpu_map) {
+		cpumask_and(d.nodemask, cpumask_of_node(cpu_to_node(i)),
+			    cpu_map);
 
-			sd = &per_cpu(node_domains, j).sd;
-			sd->groups = sg;
-		}
-		sg->__cpu_power = 0;
-		cpumask_copy(sched_group_cpus(sg), nodemask);
-		sg->next = sg;
-		cpumask_or(covered, covered, nodemask);
-		prev = sg;
+		sd = __build_numa_sched_domains(&d, cpu_map, attr, i);
+		sd = __build_cpu_sched_domain(&d, cpu_map, attr, sd, i);
+		sd = __build_mc_sched_domain(&d, cpu_map, attr, sd, i);
+		sd = __build_smt_sched_domain(&d, cpu_map, attr, sd, i);
+	}
 
-		for (j = 0; j < nr_node_ids; j++) {
-			int n = (i + j) % nr_node_ids;
+	for_each_cpu(i, cpu_map) {
+		build_sched_groups(&d, SD_LV_SIBLING, cpu_map, i);
+		build_sched_groups(&d, SD_LV_MC, cpu_map, i);
+	}
 
-			cpumask_complement(notcovered, covered);
-			cpumask_and(tmpmask, notcovered, cpu_map);
-			cpumask_and(tmpmask, tmpmask, domainspan);
-			if (cpumask_empty(tmpmask))
-				break;
+	/* Set up physical groups */
+	for (i = 0; i < nr_node_ids; i++)
+		build_sched_groups(&d, SD_LV_CPU, cpu_map, i);
 
-			cpumask_and(tmpmask, tmpmask, cpumask_of_node(n));
-			if (cpumask_empty(tmpmask))
-				continue;
+#ifdef CONFIG_NUMA
+	/* Set up node groups */
+	if (d.sd_allnodes)
+		build_sched_groups(&d, SD_LV_ALLNODES, cpu_map, 0);
 
-			sg = kmalloc_node(sizeof(struct sched_group) +
-					  cpumask_size(),
-					  GFP_KERNEL, i);
-			if (!sg) {
-				printk(KERN_WARNING
-				"Can not alloc domain group for node %d\n", j);
-				goto error;
-			}
-			sg->__cpu_power = 0;
-			cpumask_copy(sched_group_cpus(sg), tmpmask);
-			sg->next = prev->next;
-			cpumask_or(covered, covered, tmpmask);
-			prev->next = sg;
-			prev = sg;
-		}
-	}
+	for (i = 0; i < nr_node_ids; i++)
+		if (build_numa_sched_groups(&d, cpu_map, i))
+			goto error;
 #endif
 
 	/* Calculate CPU power for physical packages and nodes */
 #ifdef CONFIG_SCHED_SMT
 	for_each_cpu(i, cpu_map) {
-		struct sched_domain *sd = &per_cpu(cpu_domains, i).sd;
-
+		sd = &per_cpu(cpu_domains, i).sd;
 		init_sched_groups_power(i, sd);
 	}
 #endif
 #ifdef CONFIG_SCHED_MC
 	for_each_cpu(i, cpu_map) {
-		struct sched_domain *sd = &per_cpu(core_domains, i).sd;
-
+		sd = &per_cpu(core_domains, i).sd;
 		init_sched_groups_power(i, sd);
 	}
 #endif
 
 	for_each_cpu(i, cpu_map) {
-		struct sched_domain *sd = &per_cpu(phys_domains, i).sd;
-
+		sd = &per_cpu(phys_domains, i).sd;
 		init_sched_groups_power(i, sd);
 	}
 
 #ifdef CONFIG_NUMA
 	for (i = 0; i < nr_node_ids; i++)
-		init_numa_sched_groups_power(sched_group_nodes[i]);
+		init_numa_sched_groups_power(d.sched_group_nodes[i]);
 
-	if (sd_allnodes) {
+	if (d.sd_allnodes) {
 		struct sched_group *sg;
 
 		cpu_to_allnodes_group(cpumask_first(cpu_map), cpu_map, &sg,
-								tmpmask);
+								d.tmpmask);
 		init_numa_sched_groups_power(sg);
 	}
 #endif
 
 	/* Attach the domains */
 	for_each_cpu(i, cpu_map) {
-		struct sched_domain *sd;
 #ifdef CONFIG_SCHED_SMT
 		sd = &per_cpu(cpu_domains, i).sd;
 #elif defined(CONFIG_SCHED_MC)
@@ -8659,44 +8864,16 @@ static int __build_sched_domains(const struct cpumask *cpu_map,
 #else
 		sd = &per_cpu(phys_domains, i).sd;
 #endif
-		cpu_attach_domain(sd, rd, i);
+		cpu_attach_domain(sd, d.rd, i);
 	}
 
-	err = 0;
-
-free_tmpmask:
-	free_cpumask_var(tmpmask);
-free_send_covered:
-	free_cpumask_var(send_covered);
-free_this_core_map:
-	free_cpumask_var(this_core_map);
-free_this_sibling_map:
-	free_cpumask_var(this_sibling_map);
-free_nodemask:
-	free_cpumask_var(nodemask);
-free_notcovered:
-#ifdef CONFIG_NUMA
-	free_cpumask_var(notcovered);
-free_covered:
-	free_cpumask_var(covered);
-free_domainspan:
-	free_cpumask_var(domainspan);
-out:
-#endif
-	return err;
-
-free_sched_groups:
-#ifdef CONFIG_NUMA
-	kfree(sched_group_nodes);
-#endif
-	goto free_tmpmask;
+	d.sched_group_nodes = NULL; /* don't free this we still need it */
+	__free_domain_allocs(&d, sa_tmpmask, cpu_map);
+	return 0;
 
-#ifdef CONFIG_NUMA
 error:
-	free_sched_groups(cpu_map, tmpmask);
-	free_rootdomain(rd);
-	goto free_tmpmask;
-#endif
+	__free_domain_allocs(&d, alloc_state, cpu_map);
+	return -ENOMEM;
 }
 
 static int build_sched_domains(const struct cpumask *cpu_map)
@@ -9015,6 +9192,7 @@ void __init sched_init_smp(void)
 	cpumask_var_t non_isolated_cpus;
 
 	alloc_cpumask_var(&non_isolated_cpus, GFP_KERNEL);
+	alloc_cpumask_var(&fallback_doms, GFP_KERNEL);
 
 #if defined(CONFIG_NUMA)
 	sched_group_nodes_bycpu = kzalloc(nr_cpu_ids * sizeof(void **),
@@ -9046,7 +9224,6 @@ void __init sched_init_smp(void)
 	sched_init_granularity();
 	free_cpumask_var(non_isolated_cpus);
 
-	alloc_cpumask_var(&fallback_doms, GFP_KERNEL);
 	init_sched_rt_class();
 }
 #else
@@ -9259,6 +9436,10 @@ void __init sched_init(void)
 #endif /* CONFIG_USER_SCHED */
 #endif /* CONFIG_GROUP_SCHED */
 
+#if defined CONFIG_FAIR_GROUP_SCHED && defined CONFIG_SMP
+	update_shares_data = __alloc_percpu(nr_cpu_ids * sizeof(unsigned long),
+					    __alignof__(unsigned long));
+#endif
 	for_each_possible_cpu(i) {
 		struct rq *rq;
 
@@ -9304,11 +9485,11 @@ void __init sched_init(void)
 		 * system cpu resource, based on the weight assigned to root
 		 * user's cpu share (INIT_TASK_GROUP_LOAD). This is accomplished
 		 * by letting tasks of init_task_group sit in a separate cfs_rq
-		 * (init_cfs_rq) and having one entity represent this group of
+		 * (init_tg_cfs_rq) and having one entity represent this group of
 		 * tasks in rq->cfs (i.e init_task_group->se[] != NULL).
 		 */
 		init_tg_cfs_entry(&init_task_group,
-				&per_cpu(init_cfs_rq, i),
+				&per_cpu(init_tg_cfs_rq, i),
 				&per_cpu(init_sched_entity, i), i, 1,
 				root_task_group.se[i]);
 
@@ -9334,6 +9515,7 @@ void __init sched_init(void)
 #ifdef CONFIG_SMP
 		rq->sd = NULL;
 		rq->rd = NULL;
+		rq->post_schedule = 0;
 		rq->active_balance = 0;
 		rq->next_balance = jiffies;
 		rq->push_cpu = 0;
@@ -9383,28 +9565,35 @@ void __init sched_init(void)
 	current->sched_class = &fair_sched_class;
 
 	/* Allocate the nohz_cpu_mask if CONFIG_CPUMASK_OFFSTACK */
-	alloc_cpumask_var(&nohz_cpu_mask, GFP_NOWAIT);
+	zalloc_cpumask_var(&nohz_cpu_mask, GFP_NOWAIT);
 #ifdef CONFIG_SMP
 #ifdef CONFIG_NO_HZ
-	alloc_cpumask_var(&nohz.cpu_mask, GFP_NOWAIT);
+	zalloc_cpumask_var(&nohz.cpu_mask, GFP_NOWAIT);
 	alloc_cpumask_var(&nohz.ilb_grp_nohz_mask, GFP_NOWAIT);
 #endif
-	alloc_cpumask_var(&cpu_isolated_map, GFP_NOWAIT);
+	zalloc_cpumask_var(&cpu_isolated_map, GFP_NOWAIT);
 #endif /* SMP */
 
-	perf_counter_init();
+	perf_event_init();
 
 	scheduler_running = 1;
 }
 
 #ifdef CONFIG_DEBUG_SPINLOCK_SLEEP
-void __might_sleep(char *file, int line)
+static inline int preempt_count_equals(int preempt_offset)
+{
+	int nested = preempt_count() & ~PREEMPT_ACTIVE;
+
+	return (nested == PREEMPT_INATOMIC_BASE + preempt_offset);
+}
+
+void __might_sleep(char *file, int line, int preempt_offset)
 {
 #ifdef in_atomic
 	static unsigned long prev_jiffy;	/* ratelimiting */
 
-	if ((!in_atomic() && !irqs_disabled()) ||
-		    system_state != SYSTEM_RUNNING || oops_in_progress)
+	if ((preempt_count_equals(preempt_offset) && !irqs_disabled()) ||
+	    system_state != SYSTEM_RUNNING || oops_in_progress)
 		return;
 	if (time_before(jiffies, prev_jiffy + HZ) && prev_jiffy)
 		return;
@@ -10157,7 +10346,7 @@ static int sched_rt_global_constraints(void)
 #endif /* CONFIG_RT_GROUP_SCHED */
 
 int sched_rt_handler(struct ctl_table *table, int write,
-		struct file *filp, void __user *buffer, size_t *lenp,
+		void __user *buffer, size_t *lenp,
 		loff_t *ppos)
 {
 	int ret;
@@ -10168,7 +10357,7 @@ int sched_rt_handler(struct ctl_table *table, int write,
 	old_period = sysctl_sched_rt_period;
 	old_runtime = sysctl_sched_rt_runtime;
 
-	ret = proc_dointvec(table, write, filp, buffer, lenp, ppos);
+	ret = proc_dointvec(table, write, buffer, lenp, ppos);
 
 	if (!ret && write) {
 		ret = sched_rt_global_constraints();
@@ -10222,8 +10411,7 @@ cpu_cgroup_destroy(struct cgroup_subsys *ss, struct cgroup *cgrp)
 }
 
 static int
-cpu_cgroup_can_attach(struct cgroup_subsys *ss, struct cgroup *cgrp,
-		      struct task_struct *tsk)
+cpu_cgroup_can_attach_task(struct cgroup *cgrp, struct task_struct *tsk)
 {
 #ifdef CONFIG_RT_GROUP_SCHED
 	if (!sched_rt_can_attach(cgroup_tg(cgrp), tsk))
@@ -10233,15 +10421,45 @@ cpu_cgroup_can_attach(struct cgroup_subsys *ss, struct cgroup *cgrp,
 	if (tsk->sched_class != &fair_sched_class)
 		return -EINVAL;
 #endif
+	return 0;
+}
 
+static int
+cpu_cgroup_can_attach(struct cgroup_subsys *ss, struct cgroup *cgrp,
+		      struct task_struct *tsk, bool threadgroup)
+{
+	int retval = cpu_cgroup_can_attach_task(cgrp, tsk);
+	if (retval)
+		return retval;
+	if (threadgroup) {
+		struct task_struct *c;
+		rcu_read_lock();
+		list_for_each_entry_rcu(c, &tsk->thread_group, thread_group) {
+			retval = cpu_cgroup_can_attach_task(cgrp, c);
+			if (retval) {
+				rcu_read_unlock();
+				return retval;
+			}
+		}
+		rcu_read_unlock();
+	}
 	return 0;
 }
 
 static void
 cpu_cgroup_attach(struct cgroup_subsys *ss, struct cgroup *cgrp,
-			struct cgroup *old_cont, struct task_struct *tsk)
+		  struct cgroup *old_cont, struct task_struct *tsk,
+		  bool threadgroup)
 {
 	sched_move_task(tsk);
+	if (threadgroup) {
+		struct task_struct *c;
+		rcu_read_lock();
+		list_for_each_entry_rcu(c, &tsk->thread_group, thread_group) {
+			sched_move_task(c);
+		}
+		rcu_read_unlock();
+	}
 }
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
@@ -10581,3 +10799,113 @@ struct cgroup_subsys cpuacct_subsys = {
 	.subsys_id = cpuacct_subsys_id,
 };
 #endif	/* CONFIG_CGROUP_CPUACCT */
+
+#ifndef CONFIG_SMP
+
+int rcu_expedited_torture_stats(char *page)
+{
+	return 0;
+}
+EXPORT_SYMBOL_GPL(rcu_expedited_torture_stats);
+
+void synchronize_sched_expedited(void)
+{
+}
+EXPORT_SYMBOL_GPL(synchronize_sched_expedited);
+
+#else /* #ifndef CONFIG_SMP */
+
+static DEFINE_PER_CPU(struct migration_req, rcu_migration_req);
+static DEFINE_MUTEX(rcu_sched_expedited_mutex);
+
+#define RCU_EXPEDITED_STATE_POST -2
+#define RCU_EXPEDITED_STATE_IDLE -1
+
+static int rcu_expedited_state = RCU_EXPEDITED_STATE_IDLE;
+
+int rcu_expedited_torture_stats(char *page)
+{
+	int cnt = 0;
+	int cpu;
+
+	cnt += sprintf(&page[cnt], "state: %d /", rcu_expedited_state);
+	for_each_online_cpu(cpu) {
+		 cnt += sprintf(&page[cnt], " %d:%d",
+				cpu, per_cpu(rcu_migration_req, cpu).dest_cpu);
+	}
+	cnt += sprintf(&page[cnt], "\n");
+	return cnt;
+}
+EXPORT_SYMBOL_GPL(rcu_expedited_torture_stats);
+
+static long synchronize_sched_expedited_count;
+
+/*
+ * Wait for an rcu-sched grace period to elapse, but use "big hammer"
+ * approach to force grace period to end quickly.  This consumes
+ * significant time on all CPUs, and is thus not recommended for
+ * any sort of common-case code.
+ *
+ * Note that it is illegal to call this function while holding any
+ * lock that is acquired by a CPU-hotplug notifier.  Failing to
+ * observe this restriction will result in deadlock.
+ */
+void synchronize_sched_expedited(void)
+{
+	int cpu;
+	unsigned long flags;
+	bool need_full_sync = 0;
+	struct rq *rq;
+	struct migration_req *req;
+	long snap;
+	int trycount = 0;
+
+	smp_mb();  /* ensure prior mod happens before capturing snap. */
+	snap = ACCESS_ONCE(synchronize_sched_expedited_count) + 1;
+	get_online_cpus();
+	while (!mutex_trylock(&rcu_sched_expedited_mutex)) {
+		put_online_cpus();
+		if (trycount++ < 10)
+			udelay(trycount * num_online_cpus());
+		else {
+			synchronize_sched();
+			return;
+		}
+		if (ACCESS_ONCE(synchronize_sched_expedited_count) - snap > 0) {
+			smp_mb(); /* ensure test happens before caller kfree */
+			return;
+		}
+		get_online_cpus();
+	}
+	rcu_expedited_state = RCU_EXPEDITED_STATE_POST;
+	for_each_online_cpu(cpu) {
+		rq = cpu_rq(cpu);
+		req = &per_cpu(rcu_migration_req, cpu);
+		init_completion(&req->done);
+		req->task = NULL;
+		req->dest_cpu = RCU_MIGRATION_NEED_QS;
+		spin_lock_irqsave(&rq->lock, flags);
+		list_add(&req->list, &rq->migration_queue);
+		spin_unlock_irqrestore(&rq->lock, flags);
+		wake_up_process(rq->migration_thread);
+	}
+	for_each_online_cpu(cpu) {
+		rcu_expedited_state = cpu;
+		req = &per_cpu(rcu_migration_req, cpu);
+		rq = cpu_rq(cpu);
+		wait_for_completion(&req->done);
+		spin_lock_irqsave(&rq->lock, flags);
+		if (unlikely(req->dest_cpu == RCU_MIGRATION_MUST_SYNC))
+			need_full_sync = 1;
+		req->dest_cpu = RCU_MIGRATION_IDLE;
+		spin_unlock_irqrestore(&rq->lock, flags);
+	}
+	rcu_expedited_state = RCU_EXPEDITED_STATE_IDLE;
+	mutex_unlock(&rcu_sched_expedited_mutex);
+	put_online_cpus();
+	if (need_full_sync)
+		synchronize_sched();
+}
+EXPORT_SYMBOL_GPL(synchronize_sched_expedited);
+
+#endif /* #else #ifndef CONFIG_SMP */
diff --git a/kernel/sched_clock.c b/kernel/sched_clock.c
index e1d16c9a7680..479ce5682d7c 100644
--- a/kernel/sched_clock.c
+++ b/kernel/sched_clock.c
@@ -48,13 +48,6 @@ static __read_mostly int sched_clock_running;
 __read_mostly int sched_clock_stable;
 
 struct sched_clock_data {
-	/*
-	 * Raw spinlock - this is a special case: this might be called
-	 * from within instrumentation code so we dont want to do any
-	 * instrumentation ourselves.
-	 */
-	raw_spinlock_t		lock;
-
 	u64			tick_raw;
 	u64			tick_gtod;
 	u64			clock;
@@ -80,7 +73,6 @@ void sched_clock_init(void)
 	for_each_possible_cpu(cpu) {
 		struct sched_clock_data *scd = cpu_sdc(cpu);
 
-		scd->lock = (raw_spinlock_t)__RAW_SPIN_LOCK_UNLOCKED;
 		scd->tick_raw = 0;
 		scd->tick_gtod = ktime_now;
 		scd->clock = ktime_now;
@@ -109,14 +101,19 @@ static inline u64 wrap_max(u64 x, u64 y)
  *  - filter out backward motion
  *  - use the GTOD tick value to create a window to filter crazy TSC values
  */
-static u64 __update_sched_clock(struct sched_clock_data *scd, u64 now)
+static u64 sched_clock_local(struct sched_clock_data *scd)
 {
-	s64 delta = now - scd->tick_raw;
-	u64 clock, min_clock, max_clock;
+	u64 now, clock, old_clock, min_clock, max_clock;
+	s64 delta;
 
+again:
+	now = sched_clock();
+	delta = now - scd->tick_raw;
 	if (unlikely(delta < 0))
 		delta = 0;
 
+	old_clock = scd->clock;
+
 	/*
 	 * scd->clock = clamp(scd->tick_gtod + delta,
 	 *		      max(scd->tick_gtod, scd->clock),
@@ -124,84 +121,73 @@ static u64 __update_sched_clock(struct sched_clock_data *scd, u64 now)
 	 */
 
 	clock = scd->tick_gtod + delta;
-	min_clock = wrap_max(scd->tick_gtod, scd->clock);
-	max_clock = wrap_max(scd->clock, scd->tick_gtod + TICK_NSEC);
+	min_clock = wrap_max(scd->tick_gtod, old_clock);
+	max_clock = wrap_max(old_clock, scd->tick_gtod + TICK_NSEC);
 
 	clock = wrap_max(clock, min_clock);
 	clock = wrap_min(clock, max_clock);
 
-	scd->clock = clock;
+	if (cmpxchg64(&scd->clock, old_clock, clock) != old_clock)
+		goto again;
 
-	return scd->clock;
+	return clock;
 }
 
-static void lock_double_clock(struct sched_clock_data *data1,
-				struct sched_clock_data *data2)
+static u64 sched_clock_remote(struct sched_clock_data *scd)
 {
-	if (data1 < data2) {
-		__raw_spin_lock(&data1->lock);
-		__raw_spin_lock(&data2->lock);
+	struct sched_clock_data *my_scd = this_scd();
+	u64 this_clock, remote_clock;
+	u64 *ptr, old_val, val;
+
+	sched_clock_local(my_scd);
+again:
+	this_clock = my_scd->clock;
+	remote_clock = scd->clock;
+
+	/*
+	 * Use the opportunity that we have both locks
+	 * taken to couple the two clocks: we take the
+	 * larger time as the latest time for both
+	 * runqueues. (this creates monotonic movement)
+	 */
+	if (likely((s64)(remote_clock - this_clock) < 0)) {
+		ptr = &scd->clock;
+		old_val = remote_clock;
+		val = this_clock;
 	} else {
-		__raw_spin_lock(&data2->lock);
-		__raw_spin_lock(&data1->lock);
+		/*
+		 * Should be rare, but possible:
+		 */
+		ptr = &my_scd->clock;
+		old_val = this_clock;
+		val = remote_clock;
 	}
+
+	if (cmpxchg64(ptr, old_val, val) != old_val)
+		goto again;
+
+	return val;
 }
 
 u64 sched_clock_cpu(int cpu)
 {
-	u64 now, clock, this_clock, remote_clock;
 	struct sched_clock_data *scd;
+	u64 clock;
+
+	WARN_ON_ONCE(!irqs_disabled());
 
 	if (sched_clock_stable)
 		return sched_clock();
 
-	scd = cpu_sdc(cpu);
-
-	/*
-	 * Normally this is not called in NMI context - but if it is,
-	 * trying to do any locking here is totally lethal.
-	 */
-	if (unlikely(in_nmi()))
-		return scd->clock;
-
 	if (unlikely(!sched_clock_running))
 		return 0ull;
 
-	WARN_ON_ONCE(!irqs_disabled());
-	now = sched_clock();
-
-	if (cpu != raw_smp_processor_id()) {
-		struct sched_clock_data *my_scd = this_scd();
-
-		lock_double_clock(scd, my_scd);
-
-		this_clock = __update_sched_clock(my_scd, now);
-		remote_clock = scd->clock;
-
-		/*
-		 * Use the opportunity that we have both locks
-		 * taken to couple the two clocks: we take the
-		 * larger time as the latest time for both
-		 * runqueues. (this creates monotonic movement)
-		 */
-		if (likely((s64)(remote_clock - this_clock) < 0)) {
-			clock = this_clock;
-			scd->clock = clock;
-		} else {
-			/*
-			 * Should be rare, but possible:
-			 */
-			clock = remote_clock;
-			my_scd->clock = remote_clock;
-		}
-
-		__raw_spin_unlock(&my_scd->lock);
-	} else {
-		__raw_spin_lock(&scd->lock);
-		clock = __update_sched_clock(scd, now);
-	}
+	scd = cpu_sdc(cpu);
 
-	__raw_spin_unlock(&scd->lock);
+	if (cpu != smp_processor_id())
+		clock = sched_clock_remote(scd);
+	else
+		clock = sched_clock_local(scd);
 
 	return clock;
 }
@@ -223,11 +209,9 @@ void sched_clock_tick(void)
 	now_gtod = ktime_to_ns(ktime_get());
 	now = sched_clock();
 
-	__raw_spin_lock(&scd->lock);
 	scd->tick_raw = now;
 	scd->tick_gtod = now_gtod;
-	__update_sched_clock(scd, now);
-	__raw_spin_unlock(&scd->lock);
+	sched_clock_local(scd);
 }
 
 /*
diff --git a/kernel/sched_cpupri.c b/kernel/sched_cpupri.c
index d014efbf947a..0f052fc674d5 100644
--- a/kernel/sched_cpupri.c
+++ b/kernel/sched_cpupri.c
@@ -127,21 +127,11 @@ void cpupri_set(struct cpupri *cp, int cpu, int newpri)
 
 	/*
 	 * If the cpu was currently mapped to a different value, we
-	 * first need to unmap the old value
+	 * need to map it to the new value then remove the old value.
+	 * Note, we must add the new value first, otherwise we risk the
+	 * cpu being cleared from pri_active, and this cpu could be
+	 * missed for a push or pull.
 	 */
-	if (likely(oldpri != CPUPRI_INVALID)) {
-		struct cpupri_vec *vec  = &cp->pri_to_cpu[oldpri];
-
-		spin_lock_irqsave(&vec->lock, flags);
-
-		vec->count--;
-		if (!vec->count)
-			clear_bit(oldpri, cp->pri_active);
-		cpumask_clear_cpu(cpu, vec->mask);
-
-		spin_unlock_irqrestore(&vec->lock, flags);
-	}
-
 	if (likely(newpri != CPUPRI_INVALID)) {
 		struct cpupri_vec *vec = &cp->pri_to_cpu[newpri];
 
@@ -154,6 +144,18 @@ void cpupri_set(struct cpupri *cp, int cpu, int newpri)
 
 		spin_unlock_irqrestore(&vec->lock, flags);
 	}
+	if (likely(oldpri != CPUPRI_INVALID)) {
+		struct cpupri_vec *vec  = &cp->pri_to_cpu[oldpri];
+
+		spin_lock_irqsave(&vec->lock, flags);
+
+		vec->count--;
+		if (!vec->count)
+			clear_bit(oldpri, cp->pri_active);
+		cpumask_clear_cpu(cpu, vec->mask);
+
+		spin_unlock_irqrestore(&vec->lock, flags);
+	}
 
 	*currpri = newpri;
 }
diff --git a/kernel/sched_debug.c b/kernel/sched_debug.c
index 70c7e0b79946..efb84409bc43 100644
--- a/kernel/sched_debug.c
+++ b/kernel/sched_debug.c
@@ -395,6 +395,7 @@ void proc_sched_show_task(struct task_struct *p, struct seq_file *m)
 	PN(se.sum_exec_runtime);
 	PN(se.avg_overlap);
 	PN(se.avg_wakeup);
+	PN(se.avg_running);
 
 	nr_switches = p->nvcsw + p->nivcsw;
 
@@ -409,6 +410,8 @@ void proc_sched_show_task(struct task_struct *p, struct seq_file *m)
 	PN(se.wait_max);
 	PN(se.wait_sum);
 	P(se.wait_count);
+	PN(se.iowait_sum);
+	P(se.iowait_count);
 	P(sched_info.bkl_count);
 	P(se.nr_migrations);
 	P(se.nr_migrations_cold);
@@ -479,6 +482,8 @@ void proc_sched_set_task(struct task_struct *p)
 	p->se.wait_max				= 0;
 	p->se.wait_sum				= 0;
 	p->se.wait_count			= 0;
+	p->se.iowait_sum			= 0;
+	p->se.iowait_count			= 0;
 	p->se.sleep_max				= 0;
 	p->se.sum_sleep_runtime			= 0;
 	p->se.block_max				= 0;
diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index 652e8bdef9aa..37087a7fac22 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -24,7 +24,7 @@
 
 /*
  * Targeted preemption latency for CPU-bound tasks:
- * (default: 20ms * (1 + ilog(ncpus)), units: nanoseconds)
+ * (default: 5ms * (1 + ilog(ncpus)), units: nanoseconds)
  *
  * NOTE: this latency value is not the same as the concept of
  * 'timeslice length' - timeslices in CFS are of variable length
@@ -34,13 +34,13 @@
  * (to see the precise effective timeslice length of your workload,
  *  run vmstat and monitor the context-switches (cs) field)
  */
-unsigned int sysctl_sched_latency = 20000000ULL;
+unsigned int sysctl_sched_latency = 5000000ULL;
 
 /*
  * Minimal preemption granularity for CPU-bound tasks:
- * (default: 4 msec * (1 + ilog(ncpus)), units: nanoseconds)
+ * (default: 1 msec * (1 + ilog(ncpus)), units: nanoseconds)
  */
-unsigned int sysctl_sched_min_granularity = 4000000ULL;
+unsigned int sysctl_sched_min_granularity = 1000000ULL;
 
 /*
  * is kept at sysctl_sched_latency / sysctl_sched_min_granularity
@@ -48,10 +48,10 @@ unsigned int sysctl_sched_min_granularity = 4000000ULL;
 static unsigned int sched_nr_latency = 5;
 
 /*
- * After fork, child runs first. (default) If set to 0 then
+ * After fork, child runs first. If set to 0 (default) then
  * parent will (try to) run first.
  */
-const_debug unsigned int sysctl_sched_child_runs_first = 1;
+unsigned int sysctl_sched_child_runs_first __read_mostly;
 
 /*
  * sys_sched_yield() compat mode
@@ -63,13 +63,13 @@ unsigned int __read_mostly sysctl_sched_compat_yield;
 
 /*
  * SCHED_OTHER wake-up granularity.
- * (default: 5 msec * (1 + ilog(ncpus)), units: nanoseconds)
+ * (default: 1 msec * (1 + ilog(ncpus)), units: nanoseconds)
  *
  * This option delays the preemption effects of decoupled workloads
  * and reduces their over-scheduling. Synchronous workloads will still
  * have immediate wakeup/sleep latencies.
  */
-unsigned int sysctl_sched_wakeup_granularity = 5000000UL;
+unsigned int sysctl_sched_wakeup_granularity = 1000000UL;
 
 const_debug unsigned int sysctl_sched_migration_cost = 500000UL;
 
@@ -79,11 +79,6 @@ static const struct sched_class fair_sched_class;
  * CFS operations on generic schedulable entities:
  */
 
-static inline struct task_struct *task_of(struct sched_entity *se)
-{
-	return container_of(se, struct task_struct, se);
-}
-
 #ifdef CONFIG_FAIR_GROUP_SCHED
 
 /* cpu runqueue to which this cfs_rq is attached */
@@ -95,6 +90,14 @@ static inline struct rq *rq_of(struct cfs_rq *cfs_rq)
 /* An entity is a task if it doesn't "own" a runqueue */
 #define entity_is_task(se)	(!se->my_q)
 
+static inline struct task_struct *task_of(struct sched_entity *se)
+{
+#ifdef CONFIG_SCHED_DEBUG
+	WARN_ON_ONCE(!entity_is_task(se));
+#endif
+	return container_of(se, struct task_struct, se);
+}
+
 /* Walk up scheduling entities hierarchy */
 #define for_each_sched_entity(se) \
 		for (; se; se = se->parent)
@@ -186,7 +189,12 @@ find_matching_se(struct sched_entity **se, struct sched_entity **pse)
 	}
 }
 
-#else	/* CONFIG_FAIR_GROUP_SCHED */
+#else	/* !CONFIG_FAIR_GROUP_SCHED */
+
+static inline struct task_struct *task_of(struct sched_entity *se)
+{
+	return container_of(se, struct task_struct, se);
+}
 
 static inline struct rq *rq_of(struct cfs_rq *cfs_rq)
 {
@@ -376,10 +384,10 @@ static struct sched_entity *__pick_last_entity(struct cfs_rq *cfs_rq)
 
 #ifdef CONFIG_SCHED_DEBUG
 int sched_nr_latency_handler(struct ctl_table *table, int write,
-		struct file *filp, void __user *buffer, size_t *lenp,
+		void __user *buffer, size_t *lenp,
 		loff_t *ppos)
 {
-	int ret = proc_dointvec_minmax(table, write, filp, buffer, lenp, ppos);
+	int ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
 
 	if (ret || !write)
 		return ret;
@@ -505,6 +513,7 @@ static void update_curr(struct cfs_rq *cfs_rq)
 	if (entity_is_task(curr)) {
 		struct task_struct *curtask = task_of(curr);
 
+		trace_sched_stat_runtime(curtask, delta_exec, curr->vruntime);
 		cpuacct_charge(curtask, delta_exec);
 		account_group_exec_runtime(curtask, delta_exec);
 	}
@@ -537,6 +546,12 @@ update_stats_wait_end(struct cfs_rq *cfs_rq, struct sched_entity *se)
 	schedstat_set(se->wait_count, se->wait_count + 1);
 	schedstat_set(se->wait_sum, se->wait_sum +
 			rq_of(cfs_rq)->clock - se->wait_start);
+#ifdef CONFIG_SCHEDSTATS
+	if (entity_is_task(se)) {
+		trace_sched_stat_wait(task_of(se),
+			rq_of(cfs_rq)->clock - se->wait_start);
+	}
+#endif
 	schedstat_set(se->wait_start, 0);
 }
 
@@ -628,8 +643,10 @@ static void enqueue_sleeper(struct cfs_rq *cfs_rq, struct sched_entity *se)
 		se->sleep_start = 0;
 		se->sum_sleep_runtime += delta;
 
-		if (tsk)
+		if (tsk) {
 			account_scheduler_latency(tsk, delta >> 10, 1);
+			trace_sched_stat_sleep(tsk, delta);
+		}
 	}
 	if (se->block_start) {
 		u64 delta = rq_of(cfs_rq)->clock - se->block_start;
@@ -644,6 +661,12 @@ static void enqueue_sleeper(struct cfs_rq *cfs_rq, struct sched_entity *se)
 		se->sum_sleep_runtime += delta;
 
 		if (tsk) {
+			if (tsk->in_iowait) {
+				se->iowait_sum += delta;
+				se->iowait_count++;
+				trace_sched_stat_iowait(tsk, delta);
+			}
+
 			/*
 			 * Blocking time is in units of nanosecs, so shift by
 			 * 20 to get a milliseconds-range estimation of the
@@ -687,29 +710,33 @@ place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int initial)
 	if (initial && sched_feat(START_DEBIT))
 		vruntime += sched_vslice(cfs_rq, se);
 
-	if (!initial) {
-		/* sleeps upto a single latency don't count. */
-		if (sched_feat(NEW_FAIR_SLEEPERS)) {
-			unsigned long thresh = sysctl_sched_latency;
+	/* sleeps up to a single latency don't count. */
+	if (!initial && sched_feat(FAIR_SLEEPERS)) {
+		unsigned long thresh = sysctl_sched_latency;
 
-			/*
-			 * Convert the sleeper threshold into virtual time.
-			 * SCHED_IDLE is a special sub-class.  We care about
-			 * fairness only relative to other SCHED_IDLE tasks,
-			 * all of which have the same weight.
-			 */
-			if (sched_feat(NORMALIZED_SLEEPER) &&
-					(!entity_is_task(se) ||
-					 task_of(se)->policy != SCHED_IDLE))
-				thresh = calc_delta_fair(thresh, se);
+		/*
+		 * Convert the sleeper threshold into virtual time.
+		 * SCHED_IDLE is a special sub-class.  We care about
+		 * fairness only relative to other SCHED_IDLE tasks,
+		 * all of which have the same weight.
+		 */
+		if (sched_feat(NORMALIZED_SLEEPER) && (!entity_is_task(se) ||
+				 task_of(se)->policy != SCHED_IDLE))
+			thresh = calc_delta_fair(thresh, se);
 
-			vruntime -= thresh;
-		}
+		/*
+		 * Halve their sleep time's effect, to allow
+		 * for a gentler effect of sleepers:
+		 */
+		if (sched_feat(GENTLE_FAIR_SLEEPERS))
+			thresh >>= 1;
 
-		/* ensure we never gain time by being placed backwards. */
-		vruntime = max_vruntime(se->vruntime, vruntime);
+		vruntime -= thresh;
 	}
 
+	/* ensure we never gain time by being placed backwards. */
+	vruntime = max_vruntime(se->vruntime, vruntime);
+
 	se->vruntime = vruntime;
 }
 
@@ -735,10 +762,10 @@ enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int wakeup)
 
 static void __clear_buddies(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
-	if (cfs_rq->last == se)
+	if (!se || cfs_rq->last == se)
 		cfs_rq->last = NULL;
 
-	if (cfs_rq->next == se)
+	if (!se || cfs_rq->next == se)
 		cfs_rq->next = NULL;
 }
 
@@ -795,6 +822,26 @@ check_preempt_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr)
 		 * re-elected due to buddy favours.
 		 */
 		clear_buddies(cfs_rq, curr);
+		return;
+	}
+
+	/*
+	 * Ensure that a task that missed wakeup preemption by a
+	 * narrow margin doesn't have to wait for a full slice.
+	 * This also mitigates buddy induced latencies under load.
+	 */
+	if (!sched_feat(WAKEUP_PREEMPT))
+		return;
+
+	if (delta_exec < sysctl_sched_min_granularity)
+		return;
+
+	if (cfs_rq->nr_running > 1) {
+		struct sched_entity *se = __pick_next_entity(cfs_rq);
+		s64 delta = curr->vruntime - se->vruntime;
+
+		if (delta > ideal_runtime)
+			resched_task(rq_of(cfs_rq)->curr);
 	}
 }
 
@@ -834,12 +881,18 @@ wakeup_preempt_entity(struct sched_entity *curr, struct sched_entity *se);
 static struct sched_entity *pick_next_entity(struct cfs_rq *cfs_rq)
 {
 	struct sched_entity *se = __pick_next_entity(cfs_rq);
+	struct sched_entity *left = se;
 
-	if (cfs_rq->next && wakeup_preempt_entity(cfs_rq->next, se) < 1)
-		return cfs_rq->next;
+	if (cfs_rq->next && wakeup_preempt_entity(cfs_rq->next, left) < 1)
+		se = cfs_rq->next;
 
-	if (cfs_rq->last && wakeup_preempt_entity(cfs_rq->last, se) < 1)
-		return cfs_rq->last;
+	/*
+	 * Prefer last buddy, try to return the CPU to a preempted task.
+	 */
+	if (cfs_rq->last && wakeup_preempt_entity(cfs_rq->last, left) < 1)
+		se = cfs_rq->last;
+
+	clear_buddies(cfs_rq, se);
 
 	return se;
 }
@@ -1040,79 +1093,6 @@ static void yield_task_fair(struct rq *rq)
 	se->vruntime = rightmost->vruntime + 1;
 }
 
-/*
- * wake_idle() will wake a task on an idle cpu if task->cpu is
- * not idle and an idle cpu is available.  The span of cpus to
- * search starts with cpus closest then further out as needed,
- * so we always favor a closer, idle cpu.
- * Domains may include CPUs that are not usable for migration,
- * hence we need to mask them out (cpu_active_mask)
- *
- * Returns the CPU we should wake onto.
- */
-#if defined(ARCH_HAS_SCHED_WAKE_IDLE)
-static int wake_idle(int cpu, struct task_struct *p)
-{
-	struct sched_domain *sd;
-	int i;
-	unsigned int chosen_wakeup_cpu;
-	int this_cpu;
-
-	/*
-	 * At POWERSAVINGS_BALANCE_WAKEUP level, if both this_cpu and prev_cpu
-	 * are idle and this is not a kernel thread and this task's affinity
-	 * allows it to be moved to preferred cpu, then just move!
-	 */
-
-	this_cpu = smp_processor_id();
-	chosen_wakeup_cpu =
-		cpu_rq(this_cpu)->rd->sched_mc_preferred_wakeup_cpu;
-
-	if (sched_mc_power_savings >= POWERSAVINGS_BALANCE_WAKEUP &&
-		idle_cpu(cpu) && idle_cpu(this_cpu) &&
-		p->mm && !(p->flags & PF_KTHREAD) &&
-		cpu_isset(chosen_wakeup_cpu, p->cpus_allowed))
-		return chosen_wakeup_cpu;
-
-	/*
-	 * If it is idle, then it is the best cpu to run this task.
-	 *
-	 * This cpu is also the best, if it has more than one task already.
-	 * Siblings must be also busy(in most cases) as they didn't already
-	 * pickup the extra load from this cpu and hence we need not check
-	 * sibling runqueue info. This will avoid the checks and cache miss
-	 * penalities associated with that.
-	 */
-	if (idle_cpu(cpu) || cpu_rq(cpu)->cfs.nr_running > 1)
-		return cpu;
-
-	for_each_domain(cpu, sd) {
-		if ((sd->flags & SD_WAKE_IDLE)
-		    || ((sd->flags & SD_WAKE_IDLE_FAR)
-			&& !task_hot(p, task_rq(p)->clock, sd))) {
-			for_each_cpu_and(i, sched_domain_span(sd),
-					 &p->cpus_allowed) {
-				if (cpu_active(i) && idle_cpu(i)) {
-					if (i != task_cpu(p)) {
-						schedstat_inc(p,
-						       se.nr_wakeups_idle);
-					}
-					return i;
-				}
-			}
-		} else {
-			break;
-		}
-	}
-	return cpu;
-}
-#else /* !ARCH_HAS_SCHED_WAKE_IDLE*/
-static inline int wake_idle(int cpu, struct task_struct *p)
-{
-	return cpu;
-}
-#endif
-
 #ifdef CONFIG_SMP
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
@@ -1199,25 +1179,34 @@ static inline unsigned long effective_load(struct task_group *tg, int cpu,
 
 #endif
 
-static int
-wake_affine(struct sched_domain *this_sd, struct rq *this_rq,
-	    struct task_struct *p, int prev_cpu, int this_cpu, int sync,
-	    int idx, unsigned long load, unsigned long this_load,
-	    unsigned int imbalance)
+static int wake_affine(struct sched_domain *sd, struct task_struct *p, int sync)
 {
-	struct task_struct *curr = this_rq->curr;
-	struct task_group *tg;
-	unsigned long tl = this_load;
+	struct task_struct *curr = current;
+	unsigned long this_load, load;
+	int idx, this_cpu, prev_cpu;
 	unsigned long tl_per_task;
+	unsigned int imbalance;
+	struct task_group *tg;
 	unsigned long weight;
 	int balanced;
 
-	if (!(this_sd->flags & SD_WAKE_AFFINE) || !sched_feat(AFFINE_WAKEUPS))
-		return 0;
+	idx	  = sd->wake_idx;
+	this_cpu  = smp_processor_id();
+	prev_cpu  = task_cpu(p);
+	load	  = source_load(prev_cpu, idx);
+	this_load = target_load(this_cpu, idx);
 
-	if (sync && (curr->se.avg_overlap > sysctl_sched_migration_cost ||
-			p->se.avg_overlap > sysctl_sched_migration_cost))
-		sync = 0;
+	if (sync) {
+	       if (sched_feat(SYNC_LESS) &&
+		   (curr->se.avg_overlap > sysctl_sched_migration_cost ||
+		    p->se.avg_overlap > sysctl_sched_migration_cost))
+		       sync = 0;
+	} else {
+		if (sched_feat(SYNC_MORE) &&
+		    (curr->se.avg_overlap < sysctl_sched_migration_cost &&
+		     p->se.avg_overlap < sysctl_sched_migration_cost))
+			sync = 1;
+	}
 
 	/*
 	 * If sync wakeup then subtract the (maximum possible)
@@ -1228,14 +1217,26 @@ wake_affine(struct sched_domain *this_sd, struct rq *this_rq,
 		tg = task_group(current);
 		weight = current->se.load.weight;
 
-		tl += effective_load(tg, this_cpu, -weight, -weight);
+		this_load += effective_load(tg, this_cpu, -weight, -weight);
 		load += effective_load(tg, prev_cpu, 0, -weight);
 	}
 
 	tg = task_group(p);
 	weight = p->se.load.weight;
 
-	balanced = 100*(tl + effective_load(tg, this_cpu, weight, weight)) <=
+	imbalance = 100 + (sd->imbalance_pct - 100) / 2;
+
+	/*
+	 * In low-load situations, where prev_cpu is idle and this_cpu is idle
+	 * due to the sync cause above having dropped this_load to 0, we'll
+	 * always have an imbalance, but there's really nothing you can do
+	 * about that, so that's good too.
+	 *
+	 * Otherwise check if either cpus are near enough in load to allow this
+	 * task to be woken on this_cpu.
+	 */
+	balanced = !this_load ||
+		100*(this_load + effective_load(tg, this_cpu, weight, weight)) <=
 		imbalance*(load + effective_load(tg, prev_cpu, 0, weight));
 
 	/*
@@ -1249,14 +1250,15 @@ wake_affine(struct sched_domain *this_sd, struct rq *this_rq,
 	schedstat_inc(p, se.nr_wakeups_affine_attempts);
 	tl_per_task = cpu_avg_load_per_task(this_cpu);
 
-	if (balanced || (tl <= load && tl + target_load(prev_cpu, idx) <=
-			tl_per_task)) {
+	if (balanced ||
+	    (this_load <= load &&
+	     this_load + target_load(prev_cpu, idx) <= tl_per_task)) {
 		/*
 		 * This domain has SD_WAKE_AFFINE and
 		 * p is cache cold in this domain, and
 		 * there is no bad imbalance.
 		 */
-		schedstat_inc(this_sd, ttwu_move_affine);
+		schedstat_inc(sd, ttwu_move_affine);
 		schedstat_inc(p, se.nr_wakeups_affine);
 
 		return 1;
@@ -1264,67 +1266,216 @@ wake_affine(struct sched_domain *this_sd, struct rq *this_rq,
 	return 0;
 }
 
-static int select_task_rq_fair(struct task_struct *p, int sync)
+/*
+ * find_idlest_group finds and returns the least busy CPU group within the
+ * domain.
+ */
+static struct sched_group *
+find_idlest_group(struct sched_domain *sd, struct task_struct *p,
+		  int this_cpu, int load_idx)
 {
-	struct sched_domain *sd, *this_sd = NULL;
-	int prev_cpu, this_cpu, new_cpu;
-	unsigned long load, this_load;
-	struct rq *this_rq;
-	unsigned int imbalance;
-	int idx;
+	struct sched_group *idlest = NULL, *this = NULL, *group = sd->groups;
+	unsigned long min_load = ULONG_MAX, this_load = 0;
+	int imbalance = 100 + (sd->imbalance_pct-100)/2;
 
-	prev_cpu	= task_cpu(p);
-	this_cpu	= smp_processor_id();
-	this_rq		= cpu_rq(this_cpu);
-	new_cpu		= prev_cpu;
+	do {
+		unsigned long load, avg_load;
+		int local_group;
+		int i;
 
-	if (prev_cpu == this_cpu)
-		goto out;
-	/*
-	 * 'this_sd' is the first domain that both
-	 * this_cpu and prev_cpu are present in:
-	 */
-	for_each_domain(this_cpu, sd) {
-		if (cpumask_test_cpu(prev_cpu, sched_domain_span(sd))) {
-			this_sd = sd;
-			break;
+		/* Skip over this group if it has no CPUs allowed */
+		if (!cpumask_intersects(sched_group_cpus(group),
+					&p->cpus_allowed))
+			continue;
+
+		local_group = cpumask_test_cpu(this_cpu,
+					       sched_group_cpus(group));
+
+		/* Tally up the load of all CPUs in the group */
+		avg_load = 0;
+
+		for_each_cpu(i, sched_group_cpus(group)) {
+			/* Bias balancing toward cpus of our domain */
+			if (local_group)
+				load = source_load(i, load_idx);
+			else
+				load = target_load(i, load_idx);
+
+			avg_load += load;
+		}
+
+		/* Adjust by relative CPU power of the group */
+		avg_load = (avg_load * SCHED_LOAD_SCALE) / group->cpu_power;
+
+		if (local_group) {
+			this_load = avg_load;
+			this = group;
+		} else if (avg_load < min_load) {
+			min_load = avg_load;
+			idlest = group;
+		}
+	} while (group = group->next, group != sd->groups);
+
+	if (!idlest || 100*this_load < imbalance*min_load)
+		return NULL;
+	return idlest;
+}
+
+/*
+ * find_idlest_cpu - find the idlest cpu among the cpus in group.
+ */
+static int
+find_idlest_cpu(struct sched_group *group, struct task_struct *p, int this_cpu)
+{
+	unsigned long load, min_load = ULONG_MAX;
+	int idlest = -1;
+	int i;
+
+	/* Traverse only the allowed CPUs */
+	for_each_cpu_and(i, sched_group_cpus(group), &p->cpus_allowed) {
+		load = weighted_cpuload(i);
+
+		if (load < min_load || (load == min_load && i == this_cpu)) {
+			min_load = load;
+			idlest = i;
 		}
 	}
 
-	if (unlikely(!cpumask_test_cpu(this_cpu, &p->cpus_allowed)))
-		goto out;
+	return idlest;
+}
 
-	/*
-	 * Check for affine wakeup and passive balancing possibilities.
-	 */
-	if (!this_sd)
+/*
+ * sched_balance_self: balance the current task (running on cpu) in domains
+ * that have the 'flag' flag set. In practice, this is SD_BALANCE_FORK and
+ * SD_BALANCE_EXEC.
+ *
+ * Balance, ie. select the least loaded group.
+ *
+ * Returns the target CPU number, or the same CPU if no balancing is needed.
+ *
+ * preempt must be disabled.
+ */
+static int select_task_rq_fair(struct task_struct *p, int sd_flag, int wake_flags)
+{
+	struct sched_domain *tmp, *affine_sd = NULL, *sd = NULL;
+	int cpu = smp_processor_id();
+	int prev_cpu = task_cpu(p);
+	int new_cpu = cpu;
+	int want_affine = 0;
+	int want_sd = 1;
+	int sync = wake_flags & WF_SYNC;
+
+	if (sd_flag & SD_BALANCE_WAKE) {
+		if (sched_feat(AFFINE_WAKEUPS) &&
+		    cpumask_test_cpu(cpu, &p->cpus_allowed))
+			want_affine = 1;
+		new_cpu = prev_cpu;
+	}
+
+	rcu_read_lock();
+	for_each_domain(cpu, tmp) {
+		/*
+		 * If power savings logic is enabled for a domain, see if we
+		 * are not overloaded, if so, don't balance wider.
+		 */
+		if (tmp->flags & (SD_POWERSAVINGS_BALANCE|SD_PREFER_LOCAL)) {
+			unsigned long power = 0;
+			unsigned long nr_running = 0;
+			unsigned long capacity;
+			int i;
+
+			for_each_cpu(i, sched_domain_span(tmp)) {
+				power += power_of(i);
+				nr_running += cpu_rq(i)->cfs.nr_running;
+			}
+
+			capacity = DIV_ROUND_CLOSEST(power, SCHED_LOAD_SCALE);
+
+			if (tmp->flags & SD_POWERSAVINGS_BALANCE)
+				nr_running /= 2;
+
+			if (nr_running < capacity)
+				want_sd = 0;
+		}
+
+		if (want_affine && (tmp->flags & SD_WAKE_AFFINE) &&
+		    cpumask_test_cpu(prev_cpu, sched_domain_span(tmp))) {
+
+			affine_sd = tmp;
+			want_affine = 0;
+		}
+
+		if (!want_sd && !want_affine)
+			break;
+
+		if (!(tmp->flags & sd_flag))
+			continue;
+
+		if (want_sd)
+			sd = tmp;
+	}
+
+	if (sched_feat(LB_SHARES_UPDATE)) {
+		/*
+		 * Pick the largest domain to update shares over
+		 */
+		tmp = sd;
+		if (affine_sd && (!tmp ||
+				  cpumask_weight(sched_domain_span(affine_sd)) >
+				  cpumask_weight(sched_domain_span(sd))))
+			tmp = affine_sd;
+
+		if (tmp)
+			update_shares(tmp);
+	}
+
+	if (affine_sd && wake_affine(affine_sd, p, sync)) {
+		new_cpu = cpu;
 		goto out;
+	}
 
-	idx = this_sd->wake_idx;
+	while (sd) {
+		int load_idx = sd->forkexec_idx;
+		struct sched_group *group;
+		int weight;
 
-	imbalance = 100 + (this_sd->imbalance_pct - 100) / 2;
+		if (!(sd->flags & sd_flag)) {
+			sd = sd->child;
+			continue;
+		}
 
-	load = source_load(prev_cpu, idx);
-	this_load = target_load(this_cpu, idx);
+		if (sd_flag & SD_BALANCE_WAKE)
+			load_idx = sd->wake_idx;
 
-	if (wake_affine(this_sd, this_rq, p, prev_cpu, this_cpu, sync, idx,
-				     load, this_load, imbalance))
-		return this_cpu;
+		group = find_idlest_group(sd, p, cpu, load_idx);
+		if (!group) {
+			sd = sd->child;
+			continue;
+		}
 
-	/*
-	 * Start passive balancing when half the imbalance_pct
-	 * limit is reached.
-	 */
-	if (this_sd->flags & SD_WAKE_BALANCE) {
-		if (imbalance*this_load <= 100*load) {
-			schedstat_inc(this_sd, ttwu_move_balance);
-			schedstat_inc(p, se.nr_wakeups_passive);
-			return this_cpu;
+		new_cpu = find_idlest_cpu(group, p, cpu);
+		if (new_cpu == -1 || new_cpu == cpu) {
+			/* Now try balancing at a lower domain level of cpu */
+			sd = sd->child;
+			continue;
 		}
+
+		/* Now try balancing at a lower domain level of new_cpu */
+		cpu = new_cpu;
+		weight = cpumask_weight(sched_domain_span(sd));
+		sd = NULL;
+		for_each_domain(cpu, tmp) {
+			if (weight <= cpumask_weight(sched_domain_span(tmp)))
+				break;
+			if (tmp->flags & sd_flag)
+				sd = tmp;
+		}
+		/* while loop will break here if sd == NULL */
 	}
 
 out:
-	return wake_idle(new_cpu, p);
+	rcu_read_unlock();
+	return new_cpu;
 }
 #endif /* CONFIG_SMP */
 
@@ -1437,11 +1588,13 @@ static void set_next_buddy(struct sched_entity *se)
 /*
  * Preempt the current task with a newly woken task if needed:
  */
-static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int sync)
+static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int wake_flags)
 {
 	struct task_struct *curr = rq->curr;
 	struct sched_entity *se = &curr->se, *pse = &p->se;
 	struct cfs_rq *cfs_rq = task_cfs_rq(curr);
+	int sync = wake_flags & WF_SYNC;
+	int scale = cfs_rq->nr_running >= sched_nr_latency;
 
 	update_curr(cfs_rq);
 
@@ -1456,18 +1609,8 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int sync)
 	if (unlikely(se == pse))
 		return;
 
-	/*
-	 * Only set the backward buddy when the current task is still on the
-	 * rq. This can happen when a wakeup gets interleaved with schedule on
-	 * the ->pre_schedule() or idle_balance() point, either of which can
-	 * drop the rq lock.
-	 *
-	 * Also, during early boot the idle thread is in the fair class, for
-	 * obvious reasons its a bad idea to schedule back to the idle thread.
-	 */
-	if (sched_feat(LAST_BUDDY) && likely(se->on_rq && curr != rq->idle))
-		set_last_buddy(se);
-	set_next_buddy(pse);
+	if (sched_feat(NEXT_BUDDY) && scale && !(wake_flags & WF_FORK))
+		set_next_buddy(pse);
 
 	/*
 	 * We can come here with TIF_NEED_RESCHED already set from new task
@@ -1489,22 +1632,45 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int sync)
 		return;
 	}
 
-	if (!sched_feat(WAKEUP_PREEMPT))
-		return;
-
-	if (sched_feat(WAKEUP_OVERLAP) && (sync ||
-			(se->avg_overlap < sysctl_sched_migration_cost &&
-			 pse->avg_overlap < sysctl_sched_migration_cost))) {
+	if ((sched_feat(WAKEUP_SYNC) && sync) ||
+	    (sched_feat(WAKEUP_OVERLAP) &&
+	     (se->avg_overlap < sysctl_sched_migration_cost &&
+	      pse->avg_overlap < sysctl_sched_migration_cost))) {
 		resched_task(curr);
 		return;
 	}
 
+	if (sched_feat(WAKEUP_RUNNING)) {
+		if (pse->avg_running < se->avg_running) {
+			set_next_buddy(pse);
+			resched_task(curr);
+			return;
+		}
+	}
+
+	if (!sched_feat(WAKEUP_PREEMPT))
+		return;
+
 	find_matching_se(&se, &pse);
 
 	BUG_ON(!pse);
 
-	if (wakeup_preempt_entity(se, pse) == 1)
+	if (wakeup_preempt_entity(se, pse) == 1) {
 		resched_task(curr);
+		/*
+		 * Only set the backward buddy when the current task is still
+		 * on the rq. This can happen when a wakeup gets interleaved
+		 * with schedule on the ->pre_schedule() or idle_balance()
+		 * point, either of which can * drop the rq lock.
+		 *
+		 * Also, during early boot the idle thread is in the fair class,
+		 * for obvious reasons its a bad idea to schedule back to it.
+		 */
+		if (unlikely(!se->on_rq || curr == rq->idle))
+			return;
+		if (sched_feat(LAST_BUDDY) && scale && entity_is_task(se))
+			set_last_buddy(se);
+	}
 }
 
 static struct task_struct *pick_next_task_fair(struct rq *rq)
@@ -1518,11 +1684,6 @@ static struct task_struct *pick_next_task_fair(struct rq *rq)
 
 	do {
 		se = pick_next_entity(cfs_rq);
-		/*
-		 * If se was a buddy, clear it so that it will have to earn
-		 * the favour again.
-		 */
-		__clear_buddies(cfs_rq, se);
 		set_next_entity(cfs_rq, se);
 		cfs_rq = group_cfs_rq(se);
 	} while (cfs_rq);
@@ -1721,6 +1882,8 @@ static void task_new_fair(struct rq *rq, struct task_struct *p)
 	sched_info_queued(p);
 
 	update_curr(cfs_rq);
+	if (curr)
+		se->vruntime = curr->vruntime;
 	place_entity(cfs_rq, se, 1);
 
 	/* 'curr' will be NULL if the child belongs to a different group */
@@ -1796,6 +1959,25 @@ static void moved_group_fair(struct task_struct *p)
 }
 #endif
 
+unsigned int get_rr_interval_fair(struct task_struct *task)
+{
+	struct sched_entity *se = &task->se;
+	unsigned long flags;
+	struct rq *rq;
+	unsigned int rr_interval = 0;
+
+	/*
+	 * Time slice is 0 for SCHED_OTHER tasks that are on an otherwise
+	 * idle runqueue:
+	 */
+	rq = task_rq_lock(task, &flags);
+	if (rq->cfs.load.weight)
+		rr_interval = NS_TO_JIFFIES(sched_slice(&rq->cfs, se));
+	task_rq_unlock(rq, &flags);
+
+	return rr_interval;
+}
+
 /*
  * All the scheduling class methods:
  */
@@ -1824,6 +2006,8 @@ static const struct sched_class fair_sched_class = {
 	.prio_changed		= prio_changed_fair,
 	.switched_to		= switched_to_fair,
 
+	.get_rr_interval	= get_rr_interval_fair,
+
 #ifdef CONFIG_FAIR_GROUP_SCHED
 	.moved_group		= moved_group_fair,
 #endif
diff --git a/kernel/sched_features.h b/kernel/sched_features.h
index 4569bfa7df9b..0d94083582c7 100644
--- a/kernel/sched_features.h
+++ b/kernel/sched_features.h
@@ -1,17 +1,123 @@
-SCHED_FEAT(NEW_FAIR_SLEEPERS, 1)
+/*
+ * Disregards a certain amount of sleep time (sched_latency_ns) and
+ * considers the task to be running during that period. This gives it
+ * a service deficit on wakeup, allowing it to run sooner.
+ */
+SCHED_FEAT(FAIR_SLEEPERS, 1)
+
+/*
+ * Only give sleepers 50% of their service deficit. This allows
+ * them to run sooner, but does not allow tons of sleepers to
+ * rip the spread apart.
+ */
+SCHED_FEAT(GENTLE_FAIR_SLEEPERS, 1)
+
+/*
+ * By not normalizing the sleep time, heavy tasks get an effective
+ * longer period, and lighter task an effective shorter period they
+ * are considered running.
+ */
 SCHED_FEAT(NORMALIZED_SLEEPER, 0)
-SCHED_FEAT(ADAPTIVE_GRAN, 1)
-SCHED_FEAT(WAKEUP_PREEMPT, 1)
+
+/*
+ * Place new tasks ahead so that they do not starve already running
+ * tasks
+ */
 SCHED_FEAT(START_DEBIT, 1)
+
+/*
+ * Should wakeups try to preempt running tasks.
+ */
+SCHED_FEAT(WAKEUP_PREEMPT, 1)
+
+/*
+ * Compute wakeup_gran based on task behaviour, clipped to
+ *  [0, sched_wakeup_gran_ns]
+ */
+SCHED_FEAT(ADAPTIVE_GRAN, 1)
+
+/*
+ * When converting the wakeup granularity to virtual time, do it such
+ * that heavier tasks preempting a lighter task have an edge.
+ */
+SCHED_FEAT(ASYM_GRAN, 1)
+
+/*
+ * Always wakeup-preempt SYNC wakeups, see SYNC_WAKEUPS.
+ */
+SCHED_FEAT(WAKEUP_SYNC, 0)
+
+/*
+ * Wakeup preempt based on task behaviour. Tasks that do not overlap
+ * don't get preempted.
+ */
+SCHED_FEAT(WAKEUP_OVERLAP, 0)
+
+/*
+ * Wakeup preemption towards tasks that run short
+ */
+SCHED_FEAT(WAKEUP_RUNNING, 0)
+
+/*
+ * Use the SYNC wakeup hint, pipes and the likes use this to indicate
+ * the remote end is likely to consume the data we just wrote, and
+ * therefore has cache benefit from being placed on the same cpu, see
+ * also AFFINE_WAKEUPS.
+ */
+SCHED_FEAT(SYNC_WAKEUPS, 1)
+
+/*
+ * Based on load and program behaviour, see if it makes sense to place
+ * a newly woken task on the same cpu as the task that woke it --
+ * improve cache locality. Typically used with SYNC wakeups as
+ * generated by pipes and the like, see also SYNC_WAKEUPS.
+ */
 SCHED_FEAT(AFFINE_WAKEUPS, 1)
+
+/*
+ * Weaken SYNC hint based on overlap
+ */
+SCHED_FEAT(SYNC_LESS, 1)
+
+/*
+ * Add SYNC hint based on overlap
+ */
+SCHED_FEAT(SYNC_MORE, 0)
+
+/*
+ * Prefer to schedule the task we woke last (assuming it failed
+ * wakeup-preemption), since its likely going to consume data we
+ * touched, increases cache locality.
+ */
+SCHED_FEAT(NEXT_BUDDY, 0)
+
+/*
+ * Prefer to schedule the task that ran last (when we did
+ * wake-preempt) as that likely will touch the same data, increases
+ * cache locality.
+ */
+SCHED_FEAT(LAST_BUDDY, 1)
+
+/*
+ * Consider buddies to be cache hot, decreases the likelyness of a
+ * cache buddy being migrated away, increases cache locality.
+ */
 SCHED_FEAT(CACHE_HOT_BUDDY, 1)
-SCHED_FEAT(SYNC_WAKEUPS, 1)
+
+/*
+ * Use arch dependent cpu power functions
+ */
+SCHED_FEAT(ARCH_POWER, 0)
+
 SCHED_FEAT(HRTICK, 0)
 SCHED_FEAT(DOUBLE_TICK, 0)
-SCHED_FEAT(ASYM_GRAN, 1)
 SCHED_FEAT(LB_BIAS, 1)
-SCHED_FEAT(LB_WAKEUP_UPDATE, 1)
+SCHED_FEAT(LB_SHARES_UPDATE, 1)
 SCHED_FEAT(ASYM_EFF_LOAD, 1)
-SCHED_FEAT(WAKEUP_OVERLAP, 0)
-SCHED_FEAT(LAST_BUDDY, 1)
+
+/*
+ * Spin-wait on mutex acquisition when the mutex owner is running on
+ * another cpu -- assumes that when the owner is running, it will soon
+ * release the lock. Decreases scheduling overhead.
+ */
 SCHED_FEAT(OWNER_SPIN, 1)
diff --git a/kernel/sched_idletask.c b/kernel/sched_idletask.c
index 499672c10cbd..b133a28fcde3 100644
--- a/kernel/sched_idletask.c
+++ b/kernel/sched_idletask.c
@@ -6,7 +6,7 @@
  */
 
 #ifdef CONFIG_SMP
-static int select_task_rq_idle(struct task_struct *p, int sync)
+static int select_task_rq_idle(struct task_struct *p, int sd_flag, int flags)
 {
 	return task_cpu(p); /* IDLE tasks as never migrated */
 }
@@ -14,7 +14,7 @@ static int select_task_rq_idle(struct task_struct *p, int sync)
 /*
  * Idle tasks are unconditionally rescheduled:
  */
-static void check_preempt_curr_idle(struct rq *rq, struct task_struct *p, int sync)
+static void check_preempt_curr_idle(struct rq *rq, struct task_struct *p, int flags)
 {
 	resched_task(rq->idle);
 }
@@ -97,6 +97,11 @@ static void prio_changed_idle(struct rq *rq, struct task_struct *p,
 		check_preempt_curr(rq, p, 0);
 }
 
+unsigned int get_rr_interval_idle(struct task_struct *task)
+{
+	return 0;
+}
+
 /*
  * Simple, special scheduling class for the per-CPU idle tasks:
  */
@@ -122,6 +127,8 @@ static const struct sched_class idle_sched_class = {
 	.set_curr_task          = set_curr_task_idle,
 	.task_tick		= task_tick_idle,
 
+	.get_rr_interval	= get_rr_interval_idle,
+
 	.prio_changed		= prio_changed_idle,
 	.switched_to		= switched_to_idle,
 
diff --git a/kernel/sched_rt.c b/kernel/sched_rt.c
index 3918e01994e0..a4d790cddb19 100644
--- a/kernel/sched_rt.c
+++ b/kernel/sched_rt.c
@@ -3,15 +3,18 @@
  * policies)
  */
 
+#ifdef CONFIG_RT_GROUP_SCHED
+
+#define rt_entity_is_task(rt_se) (!(rt_se)->my_q)
+
 static inline struct task_struct *rt_task_of(struct sched_rt_entity *rt_se)
 {
+#ifdef CONFIG_SCHED_DEBUG
+	WARN_ON_ONCE(!rt_entity_is_task(rt_se));
+#endif
 	return container_of(rt_se, struct task_struct, rt);
 }
 
-#ifdef CONFIG_RT_GROUP_SCHED
-
-#define rt_entity_is_task(rt_se) (!(rt_se)->my_q)
-
 static inline struct rq *rq_of_rt_rq(struct rt_rq *rt_rq)
 {
 	return rt_rq->rq;
@@ -26,6 +29,11 @@ static inline struct rt_rq *rt_rq_of_se(struct sched_rt_entity *rt_se)
 
 #define rt_entity_is_task(rt_se) (1)
 
+static inline struct task_struct *rt_task_of(struct sched_rt_entity *rt_se)
+{
+	return container_of(rt_se, struct task_struct, rt);
+}
+
 static inline struct rq *rq_of_rt_rq(struct rt_rq *rt_rq)
 {
 	return container_of(rt_rq, struct rq, rt);
@@ -128,6 +136,11 @@ static void dequeue_pushable_task(struct rq *rq, struct task_struct *p)
 	plist_del(&p->pushable_tasks, &rq->rt.pushable_tasks);
 }
 
+static inline int has_pushable_tasks(struct rq *rq)
+{
+	return !plist_head_empty(&rq->rt.pushable_tasks);
+}
+
 #else
 
 static inline void enqueue_pushable_task(struct rq *rq, struct task_struct *p)
@@ -602,6 +615,8 @@ static void update_curr_rt(struct rq *rq)
 	curr->se.exec_start = rq->clock;
 	cpuacct_charge(curr, delta_exec);
 
+	sched_rt_avg_update(rq, delta_exec);
+
 	if (!rt_bandwidth_enabled())
 		return;
 
@@ -874,8 +889,6 @@ static void enqueue_task_rt(struct rq *rq, struct task_struct *p, int wakeup)
 
 	if (!task_current(rq, p) && p->rt.nr_cpus_allowed > 1)
 		enqueue_pushable_task(rq, p);
-
-	inc_cpu_load(rq, p->se.load.weight);
 }
 
 static void dequeue_task_rt(struct rq *rq, struct task_struct *p, int sleep)
@@ -886,8 +899,6 @@ static void dequeue_task_rt(struct rq *rq, struct task_struct *p, int sleep)
 	dequeue_rt_entity(rt_se);
 
 	dequeue_pushable_task(rq, p);
-
-	dec_cpu_load(rq, p->se.load.weight);
 }
 
 /*
@@ -927,10 +938,13 @@ static void yield_task_rt(struct rq *rq)
 #ifdef CONFIG_SMP
 static int find_lowest_rq(struct task_struct *task);
 
-static int select_task_rq_rt(struct task_struct *p, int sync)
+static int select_task_rq_rt(struct task_struct *p, int sd_flag, int flags)
 {
 	struct rq *rq = task_rq(p);
 
+	if (sd_flag != SD_BALANCE_WAKE)
+		return smp_processor_id();
+
 	/*
 	 * If the current task is an RT task, then
 	 * try to see if we can wake this RT task up on another
@@ -988,7 +1002,7 @@ static void check_preempt_equal_prio(struct rq *rq, struct task_struct *p)
 /*
  * Preempt the current task with a newly woken task if needed:
  */
-static void check_preempt_curr_rt(struct rq *rq, struct task_struct *p, int sync)
+static void check_preempt_curr_rt(struct rq *rq, struct task_struct *p, int flags)
 {
 	if (p->prio < rq->curr->prio) {
 		resched_task(rq->curr);
@@ -1064,6 +1078,14 @@ static struct task_struct *pick_next_task_rt(struct rq *rq)
 	if (p)
 		dequeue_pushable_task(rq, p);
 
+#ifdef CONFIG_SMP
+	/*
+	 * We detect this state here so that we can avoid taking the RQ
+	 * lock again later if there is no need to push
+	 */
+	rq->post_schedule = has_pushable_tasks(rq);
+#endif
+
 	return p;
 }
 
@@ -1162,13 +1184,6 @@ static int find_lowest_rq(struct task_struct *task)
 		return -1; /* No targets found */
 
 	/*
-	 * Only consider CPUs that are usable for migration.
-	 * I guess we might want to change cpupri_find() to ignore those
-	 * in the first place.
-	 */
-	cpumask_and(lowest_mask, lowest_mask, cpu_active_mask);
-
-	/*
 	 * At this point we have built a mask of cpus representing the
 	 * lowest priority tasks in the system.  Now we want to elect
 	 * the best one based on our affinity and topology.
@@ -1262,11 +1277,6 @@ 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;
@@ -1466,23 +1476,9 @@ static void pre_schedule_rt(struct rq *rq, struct task_struct *prev)
 		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)
 {
-	/*
-	 * This is only called if needs_post_schedule_rt() indicates that
-	 * we need to push tasks away
-	 */
-	spin_lock_irq(&rq->lock);
 	push_rt_tasks(rq);
-	spin_unlock_irq(&rq->lock);
 }
 
 /*
@@ -1738,6 +1734,17 @@ static void set_curr_task_rt(struct rq *rq)
 	dequeue_pushable_task(rq, p);
 }
 
+unsigned int get_rr_interval_rt(struct task_struct *task)
+{
+	/*
+	 * Time slice is 0 for SCHED_FIFO tasks
+	 */
+	if (task->policy == SCHED_RR)
+		return DEF_TIMESLICE;
+	else
+		return 0;
+}
+
 static const struct sched_class rt_sched_class = {
 	.next			= &fair_sched_class,
 	.enqueue_task		= enqueue_task_rt,
@@ -1758,7 +1765,6 @@ 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,
@@ -1767,6 +1773,8 @@ static const struct sched_class rt_sched_class = {
 	.set_curr_task          = set_curr_task_rt,
 	.task_tick		= task_tick_rt,
 
+	.get_rr_interval	= get_rr_interval_rt,
+
 	.prio_changed		= prio_changed_rt,
 	.switched_to		= switched_to_rt,
 };
diff --git a/kernel/signal.c b/kernel/signal.c
index 64c5deeaca5d..6705320784fd 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -705,7 +705,7 @@ static int prepare_signal(int sig, struct task_struct *p, int from_ancestor_ns)
 
 		if (why) {
 			/*
-			 * The first thread which returns from finish_stop()
+			 * The first thread which returns from do_signal_stop()
 			 * will take ->siglock, notice SIGNAL_CLD_MASK, and
 			 * notify its parent. See get_signal_to_deliver().
 			 */
@@ -971,6 +971,20 @@ specific_send_sig_info(int sig, struct siginfo *info, struct task_struct *t)
 	return send_signal(sig, info, t, 0);
 }
 
+int do_send_sig_info(int sig, struct siginfo *info, struct task_struct *p,
+			bool group)
+{
+	unsigned long flags;
+	int ret = -ESRCH;
+
+	if (lock_task_sighand(p, &flags)) {
+		ret = send_signal(sig, info, p, group);
+		unlock_task_sighand(p, &flags);
+	}
+
+	return ret;
+}
+
 /*
  * Force a signal that the process can't ignore: if necessary
  * we unblock the signal and change any SIG_IGN to SIG_DFL.
@@ -1036,12 +1050,6 @@ void zap_other_threads(struct task_struct *p)
 	}
 }
 
-int __fatal_signal_pending(struct task_struct *tsk)
-{
-	return sigismember(&tsk->pending.signal, SIGKILL);
-}
-EXPORT_SYMBOL(__fatal_signal_pending);
-
 struct sighand_struct *lock_task_sighand(struct task_struct *tsk, unsigned long *flags)
 {
 	struct sighand_struct *sighand;
@@ -1068,18 +1076,10 @@ struct sighand_struct *lock_task_sighand(struct task_struct *tsk, unsigned long
  */
 int group_send_sig_info(int sig, struct siginfo *info, struct task_struct *p)
 {
-	unsigned long flags;
-	int ret;
+	int ret = check_kill_permission(sig, info, p);
 
-	ret = check_kill_permission(sig, info, p);
-
-	if (!ret && sig) {
-		ret = -ESRCH;
-		if (lock_task_sighand(p, &flags)) {
-			ret = __group_send_sig_info(sig, info, p);
-			unlock_task_sighand(p, &flags);
-		}
-	}
+	if (!ret && sig)
+		ret = do_send_sig_info(sig, info, p, true);
 
 	return ret;
 }
@@ -1224,15 +1224,9 @@ static int kill_something_info(int sig, struct siginfo *info, pid_t pid)
  * These are for backward compatibility with the rest of the kernel source.
  */
 
-/*
- * The caller must ensure the task can't exit.
- */
 int
 send_sig_info(int sig, struct siginfo *info, struct task_struct *p)
 {
-	int ret;
-	unsigned long flags;
-
 	/*
 	 * Make sure legacy kernel users don't send in bad values
 	 * (normal paths check this in check_kill_permission).
@@ -1240,10 +1234,7 @@ send_sig_info(int sig, struct siginfo *info, struct task_struct *p)
 	if (!valid_signal(sig))
 		return -EINVAL;
 
-	spin_lock_irqsave(&p->sighand->siglock, flags);
-	ret = specific_send_sig_info(sig, info, p);
-	spin_unlock_irqrestore(&p->sighand->siglock, flags);
-	return ret;
+	return do_send_sig_info(sig, info, p, false);
 }
 
 #define __si_special(priv) \
@@ -1383,15 +1374,6 @@ ret:
 }
 
 /*
- * Wake up any threads in the parent blocked in wait* syscalls.
- */
-static inline void __wake_up_parent(struct task_struct *p,
-				    struct task_struct *parent)
-{
-	wake_up_interruptible_sync(&parent->signal->wait_chldexit);
-}
-
-/*
  * Let a parent know about the death of a child.
  * For a stopped/continued status change, use do_notify_parent_cldstop instead.
  *
@@ -1673,29 +1655,6 @@ void ptrace_notify(int exit_code)
 	spin_unlock_irq(&current->sighand->siglock);
 }
 
-static void
-finish_stop(int stop_count)
-{
-	/*
-	 * If there are no other threads in the group, or if there is
-	 * a group stop in progress and we are the last to stop,
-	 * report to the parent.  When ptraced, every thread reports itself.
-	 */
-	if (tracehook_notify_jctl(stop_count == 0, CLD_STOPPED)) {
-		read_lock(&tasklist_lock);
-		do_notify_parent_cldstop(current, CLD_STOPPED);
-		read_unlock(&tasklist_lock);
-	}
-
-	do {
-		schedule();
-	} while (try_to_freeze());
-	/*
-	 * Now we don't run again until continued.
-	 */
-	current->exit_code = 0;
-}
-
 /*
  * This performs the stopping for SIGSTOP and other stop signals.
  * We have to stop all threads in the thread group.
@@ -1705,15 +1664,9 @@ finish_stop(int stop_count)
 static int do_signal_stop(int signr)
 {
 	struct signal_struct *sig = current->signal;
-	int stop_count;
+	int notify;
 
-	if (sig->group_stop_count > 0) {
-		/*
-		 * There is a group stop in progress.  We don't need to
-		 * start another one.
-		 */
-		stop_count = --sig->group_stop_count;
-	} else {
+	if (!sig->group_stop_count) {
 		struct task_struct *t;
 
 		if (!likely(sig->flags & SIGNAL_STOP_DEQUEUED) ||
@@ -1725,7 +1678,7 @@ static int do_signal_stop(int signr)
 		 */
 		sig->group_exit_code = signr;
 
-		stop_count = 0;
+		sig->group_stop_count = 1;
 		for (t = next_thread(current); t != current; t = next_thread(t))
 			/*
 			 * Setting state to TASK_STOPPED for a group
@@ -1734,19 +1687,44 @@ static int do_signal_stop(int signr)
 			 */
 			if (!(t->flags & PF_EXITING) &&
 			    !task_is_stopped_or_traced(t)) {
-				stop_count++;
+				sig->group_stop_count++;
 				signal_wake_up(t, 0);
 			}
-		sig->group_stop_count = stop_count;
 	}
+	/*
+	 * If there are no other threads in the group, or if there is
+	 * a group stop in progress and we are the last to stop, report
+	 * to the parent.  When ptraced, every thread reports itself.
+	 */
+	notify = sig->group_stop_count == 1 ? CLD_STOPPED : 0;
+	notify = tracehook_notify_jctl(notify, CLD_STOPPED);
+	/*
+	 * tracehook_notify_jctl() can drop and reacquire siglock, so
+	 * we keep ->group_stop_count != 0 before the call. If SIGCONT
+	 * or SIGKILL comes in between ->group_stop_count == 0.
+	 */
+	if (sig->group_stop_count) {
+		if (!--sig->group_stop_count)
+			sig->flags = SIGNAL_STOP_STOPPED;
+		current->exit_code = sig->group_exit_code;
+		__set_current_state(TASK_STOPPED);
+	}
+	spin_unlock_irq(&current->sighand->siglock);
 
-	if (stop_count == 0)
-		sig->flags = SIGNAL_STOP_STOPPED;
-	current->exit_code = sig->group_exit_code;
-	__set_current_state(TASK_STOPPED);
+	if (notify) {
+		read_lock(&tasklist_lock);
+		do_notify_parent_cldstop(current, notify);
+		read_unlock(&tasklist_lock);
+	}
+
+	/* Now we don't run again until woken by SIGCONT or SIGKILL */
+	do {
+		schedule();
+	} while (try_to_freeze());
+
+	tracehook_finish_jctl();
+	current->exit_code = 0;
 
-	spin_unlock_irq(&current->sighand->siglock);
-	finish_stop(stop_count);
 	return 1;
 }
 
@@ -1815,14 +1793,15 @@ relock:
 		int why = (signal->flags & SIGNAL_STOP_CONTINUED)
 				? CLD_CONTINUED : CLD_STOPPED;
 		signal->flags &= ~SIGNAL_CLD_MASK;
-		spin_unlock_irq(&sighand->siglock);
 
-		if (unlikely(!tracehook_notify_jctl(1, why)))
-			goto relock;
+		why = tracehook_notify_jctl(why, CLD_CONTINUED);
+		spin_unlock_irq(&sighand->siglock);
 
-		read_lock(&tasklist_lock);
-		do_notify_parent_cldstop(current->group_leader, why);
-		read_unlock(&tasklist_lock);
+		if (why) {
+			read_lock(&tasklist_lock);
+			do_notify_parent_cldstop(current->group_leader, why);
+			read_unlock(&tasklist_lock);
+		}
 		goto relock;
 	}
 
@@ -1987,14 +1966,14 @@ void exit_signals(struct task_struct *tsk)
 	if (unlikely(tsk->signal->group_stop_count) &&
 			!--tsk->signal->group_stop_count) {
 		tsk->signal->flags = SIGNAL_STOP_STOPPED;
-		group_stop = 1;
+		group_stop = tracehook_notify_jctl(CLD_STOPPED, CLD_STOPPED);
 	}
 out:
 	spin_unlock_irq(&tsk->sighand->siglock);
 
-	if (unlikely(group_stop) && tracehook_notify_jctl(1, CLD_STOPPED)) {
+	if (unlikely(group_stop)) {
 		read_lock(&tasklist_lock);
-		do_notify_parent_cldstop(tsk, CLD_STOPPED);
+		do_notify_parent_cldstop(tsk, group_stop);
 		read_unlock(&tasklist_lock);
 	}
 }
@@ -2290,7 +2269,6 @@ static int
 do_send_specific(pid_t tgid, pid_t pid, int sig, struct siginfo *info)
 {
 	struct task_struct *p;
-	unsigned long flags;
 	int error = -ESRCH;
 
 	rcu_read_lock();
@@ -2300,14 +2278,16 @@ do_send_specific(pid_t tgid, pid_t pid, int sig, struct siginfo *info)
 		/*
 		 * The null signal is a permissions and process existence
 		 * probe.  No signal is actually delivered.
-		 *
-		 * If lock_task_sighand() fails we pretend the task dies
-		 * after receiving the signal. The window is tiny, and the
-		 * signal is private anyway.
 		 */
-		if (!error && sig && lock_task_sighand(p, &flags)) {
-			error = specific_send_sig_info(sig, info, p);
-			unlock_task_sighand(p, &flags);
+		if (!error && sig) {
+			error = do_send_sig_info(sig, info, p, false);
+			/*
+			 * If lock_task_sighand() failed we pretend the task
+			 * dies after receiving the signal. The window is tiny,
+			 * and the signal is private anyway.
+			 */
+			if (unlikely(error == -ESRCH))
+				error = 0;
 		}
 	}
 	rcu_read_unlock();
diff --git a/kernel/slow-work-debugfs.c b/kernel/slow-work-debugfs.c
new file mode 100644
index 000000000000..e45c43645298
--- /dev/null
+++ b/kernel/slow-work-debugfs.c
@@ -0,0 +1,227 @@
+/* Slow work debugging
+ *
+ * Copyright (C) 2009 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.
+ */
+
+#include <linux/module.h>
+#include <linux/slow-work.h>
+#include <linux/fs.h>
+#include <linux/time.h>
+#include <linux/seq_file.h>
+#include "slow-work.h"
+
+#define ITERATOR_SHIFT		(BITS_PER_LONG - 4)
+#define ITERATOR_SELECTOR	(0xfUL << ITERATOR_SHIFT)
+#define ITERATOR_COUNTER	(~ITERATOR_SELECTOR)
+
+void slow_work_new_thread_desc(struct slow_work *work, struct seq_file *m)
+{
+	seq_puts(m, "Slow-work: New thread");
+}
+
+/*
+ * Render the time mark field on a work item into a 5-char time with units plus
+ * a space
+ */
+static void slow_work_print_mark(struct seq_file *m, struct slow_work *work)
+{
+	struct timespec now, diff;
+
+	now = CURRENT_TIME;
+	diff = timespec_sub(now, work->mark);
+
+	if (diff.tv_sec < 0)
+		seq_puts(m, "  -ve ");
+	else if (diff.tv_sec == 0 && diff.tv_nsec < 1000)
+		seq_printf(m, "%3luns ", diff.tv_nsec);
+	else if (diff.tv_sec == 0 && diff.tv_nsec < 1000000)
+		seq_printf(m, "%3luus ", diff.tv_nsec / 1000);
+	else if (diff.tv_sec == 0 && diff.tv_nsec < 1000000000)
+		seq_printf(m, "%3lums ", diff.tv_nsec / 1000000);
+	else if (diff.tv_sec <= 1)
+		seq_puts(m, "   1s ");
+	else if (diff.tv_sec < 60)
+		seq_printf(m, "%4lus ", diff.tv_sec);
+	else if (diff.tv_sec < 60 * 60)
+		seq_printf(m, "%4lum ", diff.tv_sec / 60);
+	else if (diff.tv_sec < 60 * 60 * 24)
+		seq_printf(m, "%4luh ", diff.tv_sec / 3600);
+	else
+		seq_puts(m, "exces ");
+}
+
+/*
+ * Describe a slow work item for debugfs
+ */
+static int slow_work_runqueue_show(struct seq_file *m, void *v)
+{
+	struct slow_work *work;
+	struct list_head *p = v;
+	unsigned long id;
+
+	switch ((unsigned long) v) {
+	case 1:
+		seq_puts(m, "THR PID   ITEM ADDR        FL MARK  DESC\n");
+		return 0;
+	case 2:
+		seq_puts(m, "=== ===== ================ == ===== ==========\n");
+		return 0;
+
+	case 3 ... 3 + SLOW_WORK_THREAD_LIMIT - 1:
+		id = (unsigned long) v - 3;
+
+		read_lock(&slow_work_execs_lock);
+		work = slow_work_execs[id];
+		if (work) {
+			smp_read_barrier_depends();
+
+			seq_printf(m, "%3lu %5d %16p %2lx ",
+				   id, slow_work_pids[id], work, work->flags);
+			slow_work_print_mark(m, work);
+
+			if (work->ops->desc)
+				work->ops->desc(work, m);
+			seq_putc(m, '\n');
+		}
+		read_unlock(&slow_work_execs_lock);
+		return 0;
+
+	default:
+		work = list_entry(p, struct slow_work, link);
+		seq_printf(m, "%3s     - %16p %2lx ",
+			   work->flags & SLOW_WORK_VERY_SLOW ? "vsq" : "sq",
+			   work, work->flags);
+		slow_work_print_mark(m, work);
+
+		if (work->ops->desc)
+			work->ops->desc(work, m);
+		seq_putc(m, '\n');
+		return 0;
+	}
+}
+
+/*
+ * map the iterator to a work item
+ */
+static void *slow_work_runqueue_index(struct seq_file *m, loff_t *_pos)
+{
+	struct list_head *p;
+	unsigned long count, id;
+
+	switch (*_pos >> ITERATOR_SHIFT) {
+	case 0x0:
+		if (*_pos == 0)
+			*_pos = 1;
+		if (*_pos < 3)
+			return (void *)(unsigned long) *_pos;
+		if (*_pos < 3 + SLOW_WORK_THREAD_LIMIT)
+			for (id = *_pos - 3;
+			     id < SLOW_WORK_THREAD_LIMIT;
+			     id++, (*_pos)++)
+				if (slow_work_execs[id])
+					return (void *)(unsigned long) *_pos;
+		*_pos = 0x1UL << ITERATOR_SHIFT;
+
+	case 0x1:
+		count = *_pos & ITERATOR_COUNTER;
+		list_for_each(p, &slow_work_queue) {
+			if (count == 0)
+				return p;
+			count--;
+		}
+		*_pos = 0x2UL << ITERATOR_SHIFT;
+
+	case 0x2:
+		count = *_pos & ITERATOR_COUNTER;
+		list_for_each(p, &vslow_work_queue) {
+			if (count == 0)
+				return p;
+			count--;
+		}
+		*_pos = 0x3UL << ITERATOR_SHIFT;
+
+	default:
+		return NULL;
+	}
+}
+
+/*
+ * set up the iterator to start reading from the first line
+ */
+static void *slow_work_runqueue_start(struct seq_file *m, loff_t *_pos)
+{
+	spin_lock_irq(&slow_work_queue_lock);
+	return slow_work_runqueue_index(m, _pos);
+}
+
+/*
+ * move to the next line
+ */
+static void *slow_work_runqueue_next(struct seq_file *m, void *v, loff_t *_pos)
+{
+	struct list_head *p = v;
+	unsigned long selector = *_pos >> ITERATOR_SHIFT;
+
+	(*_pos)++;
+	switch (selector) {
+	case 0x0:
+		return slow_work_runqueue_index(m, _pos);
+
+	case 0x1:
+		if (*_pos >> ITERATOR_SHIFT == 0x1) {
+			p = p->next;
+			if (p != &slow_work_queue)
+				return p;
+		}
+		*_pos = 0x2UL << ITERATOR_SHIFT;
+		p = &vslow_work_queue;
+
+	case 0x2:
+		if (*_pos >> ITERATOR_SHIFT == 0x2) {
+			p = p->next;
+			if (p != &vslow_work_queue)
+				return p;
+		}
+		*_pos = 0x3UL << ITERATOR_SHIFT;
+
+	default:
+		return NULL;
+	}
+}
+
+/*
+ * clean up after reading
+ */
+static void slow_work_runqueue_stop(struct seq_file *m, void *v)
+{
+	spin_unlock_irq(&slow_work_queue_lock);
+}
+
+static const struct seq_operations slow_work_runqueue_ops = {
+	.start		= slow_work_runqueue_start,
+	.stop		= slow_work_runqueue_stop,
+	.next		= slow_work_runqueue_next,
+	.show		= slow_work_runqueue_show,
+};
+
+/*
+ * open "/sys/kernel/debug/slow_work/runqueue" to list queue contents
+ */
+static int slow_work_runqueue_open(struct inode *inode, struct file *file)
+{
+	return seq_open(file, &slow_work_runqueue_ops);
+}
+
+const struct file_operations slow_work_runqueue_fops = {
+	.owner		= THIS_MODULE,
+	.open		= slow_work_runqueue_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= seq_release,
+};
diff --git a/kernel/slow-work.c b/kernel/slow-work.c
index 09d7519557d3..00889bd3c590 100644
--- a/kernel/slow-work.c
+++ b/kernel/slow-work.c
@@ -16,20 +16,17 @@
 #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 */
+#include <linux/debugfs.h>
+#include "slow-work.h"
 
 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 *,
+static int slow_work_min_threads_sysctl(struct ctl_table *, int,
 					void __user *, size_t *, loff_t *);
 
-static int slow_work_max_threads_sysctl(struct ctl_table *, int , struct file *,
+static int slow_work_max_threads_sysctl(struct ctl_table *, int ,
 					void __user *, size_t *, loff_t *);
 #endif
 
@@ -46,7 +43,7 @@ static unsigned vslow_work_proportion = 50; /* % of threads that may process
 
 #ifdef CONFIG_SYSCTL
 static const int slow_work_min_min_threads = 2;
-static int slow_work_max_max_threads = 255;
+static int slow_work_max_max_threads = SLOW_WORK_THREAD_LIMIT;
 static const int slow_work_min_vslow = 1;
 static const int slow_work_max_vslow = 99;
 
@@ -98,6 +95,56 @@ static DEFINE_TIMER(slow_work_oom_timer, slow_work_oom_timeout, 0, 0);
 static struct slow_work slow_work_new_thread; /* new thread starter */
 
 /*
+ * slow work ID allocation (use slow_work_queue_lock)
+ */
+static DECLARE_BITMAP(slow_work_ids, SLOW_WORK_THREAD_LIMIT);
+
+/*
+ * Unregistration tracking to prevent put_ref() from disappearing during module
+ * unload
+ */
+#ifdef CONFIG_MODULES
+static struct module *slow_work_thread_processing[SLOW_WORK_THREAD_LIMIT];
+static struct module *slow_work_unreg_module;
+static struct slow_work *slow_work_unreg_work_item;
+static DECLARE_WAIT_QUEUE_HEAD(slow_work_unreg_wq);
+static DEFINE_MUTEX(slow_work_unreg_sync_lock);
+
+static void slow_work_set_thread_processing(int id, struct slow_work *work)
+{
+	if (work)
+		slow_work_thread_processing[id] = work->owner;
+}
+static void slow_work_done_thread_processing(int id, struct slow_work *work)
+{
+	struct module *module = slow_work_thread_processing[id];
+
+	slow_work_thread_processing[id] = NULL;
+	smp_mb();
+	if (slow_work_unreg_work_item == work ||
+	    slow_work_unreg_module == module)
+		wake_up_all(&slow_work_unreg_wq);
+}
+static void slow_work_clear_thread_processing(int id)
+{
+	slow_work_thread_processing[id] = NULL;
+}
+#else
+static void slow_work_set_thread_processing(int id, struct slow_work *work) {}
+static void slow_work_done_thread_processing(int id, struct slow_work *work) {}
+static void slow_work_clear_thread_processing(int id) {}
+#endif
+
+/*
+ * Data for tracking currently executing items for indication through /proc
+ */
+#ifdef CONFIG_SLOW_WORK_DEBUG
+struct slow_work *slow_work_execs[SLOW_WORK_THREAD_LIMIT];
+pid_t slow_work_pids[SLOW_WORK_THREAD_LIMIT];
+DEFINE_RWLOCK(slow_work_execs_lock);
+#endif
+
+/*
  * 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.
@@ -105,9 +152,18 @@ static struct slow_work slow_work_new_thread; /* new thread starter */
  * 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);
+LIST_HEAD(slow_work_queue);
+LIST_HEAD(vslow_work_queue);
+DEFINE_SPINLOCK(slow_work_queue_lock);
+
+/*
+ * The following are two wait queues that get pinged when a work item is placed
+ * on an empty queue.  These allow work items that are hogging a thread by
+ * sleeping in a way that could be deferred to yield their thread and enqueue
+ * themselves.
+ */
+static DECLARE_WAIT_QUEUE_HEAD(slow_work_queue_waits_for_occupation);
+static DECLARE_WAIT_QUEUE_HEAD(vslow_work_queue_waits_for_occupation);
 
 /*
  * The thread controls.  A variable used to signal to the threads that they
@@ -126,6 +182,20 @@ static DECLARE_COMPLETION(slow_work_last_thread_exited);
 static int slow_work_user_count;
 static DEFINE_MUTEX(slow_work_user_lock);
 
+static inline int slow_work_get_ref(struct slow_work *work)
+{
+	if (work->ops->get_ref)
+		return work->ops->get_ref(work);
+
+	return 0;
+}
+
+static inline void slow_work_put_ref(struct slow_work *work)
+{
+	if (work->ops->put_ref)
+		work->ops->put_ref(work);
+}
+
 /*
  * Calculate the maximum number of active threads in the pool that are
  * permitted to process very slow work items.
@@ -149,7 +219,7 @@ static unsigned slow_work_calc_vsmax(void)
  * 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)
+static noinline bool slow_work_execute(int id)
 {
 	struct slow_work *work = NULL;
 	unsigned vsmax;
@@ -186,6 +256,13 @@ static bool slow_work_execute(void)
 	} else {
 		very_slow = false; /* avoid the compiler warning */
 	}
+
+	slow_work_set_thread_processing(id, work);
+	if (work) {
+		slow_work_mark_time(work);
+		slow_work_begin_exec(id, work);
+	}
+
 	spin_unlock_irq(&slow_work_queue_lock);
 
 	if (!work)
@@ -194,12 +271,19 @@ static bool slow_work_execute(void)
 	if (!test_and_clear_bit(SLOW_WORK_PENDING, &work->flags))
 		BUG();
 
-	work->ops->execute(work);
+	/* don't execute if the work is in the process of being cancelled */
+	if (!test_bit(SLOW_WORK_CANCELLING, &work->flags))
+		work->ops->execute(work);
 
 	if (very_slow)
 		atomic_dec(&vslow_work_executing_count);
 	clear_bit_unlock(SLOW_WORK_EXECUTING, &work->flags);
 
+	/* wake up anyone waiting for this work to be complete */
+	wake_up_bit(&work->flags, SLOW_WORK_EXECUTING);
+
+	slow_work_end_exec(id, work);
+
 	/* 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
@@ -219,7 +303,10 @@ static bool slow_work_execute(void)
 		spin_unlock_irq(&slow_work_queue_lock);
 	}
 
-	work->ops->put_ref(work);
+	/* sort out the race between module unloading and put_ref() */
+	slow_work_put_ref(work);
+	slow_work_done_thread_processing(id, work);
+
 	return true;
 
 auto_requeue:
@@ -227,15 +314,61 @@ auto_requeue:
 	 * - we transfer our ref on the item back to the appropriate queue
 	 * - don't wake another thread up as we're awake already
 	 */
+	slow_work_mark_time(work);
 	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);
+	slow_work_clear_thread_processing(id);
 	return true;
 }
 
 /**
+ * slow_work_sleep_till_thread_needed - Sleep till thread needed by other work
+ * work: The work item under execution that wants to sleep
+ * _timeout: Scheduler sleep timeout
+ *
+ * Allow a requeueable work item to sleep on a slow-work processor thread until
+ * that thread is needed to do some other work or the sleep is interrupted by
+ * some other event.
+ *
+ * The caller must set up a wake up event before calling this and must have set
+ * the appropriate sleep mode (such as TASK_UNINTERRUPTIBLE) and tested its own
+ * condition before calling this function as no test is made here.
+ *
+ * False is returned if there is nothing on the queue; true is returned if the
+ * work item should be requeued
+ */
+bool slow_work_sleep_till_thread_needed(struct slow_work *work,
+					signed long *_timeout)
+{
+	wait_queue_head_t *wfo_wq;
+	struct list_head *queue;
+
+	DEFINE_WAIT(wait);
+
+	if (test_bit(SLOW_WORK_VERY_SLOW, &work->flags)) {
+		wfo_wq = &vslow_work_queue_waits_for_occupation;
+		queue = &vslow_work_queue;
+	} else {
+		wfo_wq = &slow_work_queue_waits_for_occupation;
+		queue = &slow_work_queue;
+	}
+
+	if (!list_empty(queue))
+		return true;
+
+	add_wait_queue_exclusive(wfo_wq, &wait);
+	if (list_empty(queue))
+		*_timeout = schedule_timeout(*_timeout);
+	finish_wait(wfo_wq, &wait);
+
+	return !list_empty(queue);
+}
+EXPORT_SYMBOL(slow_work_sleep_till_thread_needed);
+
+/**
  * slow_work_enqueue - Schedule a slow work item for processing
  * @work: The work item to queue
  *
@@ -260,16 +393,22 @@ auto_requeue:
  * 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.
+ * Returns 0 if successful, -EAGAIN if not (or -ECANCELED if cancelled work is
+ * attempted queued)
  */
 int slow_work_enqueue(struct slow_work *work)
 {
+	wait_queue_head_t *wfo_wq;
+	struct list_head *queue;
 	unsigned long flags;
+	int ret;
+
+	if (test_bit(SLOW_WORK_CANCELLING, &work->flags))
+		return -ECANCELED;
 
 	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
@@ -280,8 +419,19 @@ int slow_work_enqueue(struct slow_work *work)
 	 * maintaining our promise
 	 */
 	if (!test_and_set_bit_lock(SLOW_WORK_PENDING, &work->flags)) {
+		if (test_bit(SLOW_WORK_VERY_SLOW, &work->flags)) {
+			wfo_wq = &vslow_work_queue_waits_for_occupation;
+			queue = &vslow_work_queue;
+		} else {
+			wfo_wq = &slow_work_queue_waits_for_occupation;
+			queue = &slow_work_queue;
+		}
+
 		spin_lock_irqsave(&slow_work_queue_lock, flags);
 
+		if (unlikely(test_bit(SLOW_WORK_CANCELLING, &work->flags)))
+			goto cancelled;
+
 		/* we promise that we will not attempt to execute the work
 		 * function in more than one thread simultaneously
 		 *
@@ -299,25 +449,221 @@ int slow_work_enqueue(struct slow_work *work)
 		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);
+			ret = slow_work_get_ref(work);
+			if (ret < 0)
+				goto failed;
+			slow_work_mark_time(work);
+			list_add_tail(&work->link, queue);
 			wake_up(&slow_work_thread_wq);
+
+			/* if someone who could be requeued is sleeping on a
+			 * thread, then ask them to yield their thread */
+			if (work->link.prev == queue)
+				wake_up(wfo_wq);
 		}
 
 		spin_unlock_irqrestore(&slow_work_queue_lock, flags);
 	}
 	return 0;
 
-cant_get_ref:
+cancelled:
+	ret = -ECANCELED;
+failed:
 	spin_unlock_irqrestore(&slow_work_queue_lock, flags);
-	return -EAGAIN;
+	return ret;
 }
 EXPORT_SYMBOL(slow_work_enqueue);
 
+static int slow_work_wait(void *word)
+{
+	schedule();
+	return 0;
+}
+
+/**
+ * slow_work_cancel - Cancel a slow work item
+ * @work: The work item to cancel
+ *
+ * This function will cancel a previously enqueued work item. If we cannot
+ * cancel the work item, it is guarenteed to have run when this function
+ * returns.
+ */
+void slow_work_cancel(struct slow_work *work)
+{
+	bool wait = true, put = false;
+
+	set_bit(SLOW_WORK_CANCELLING, &work->flags);
+	smp_mb();
+
+	/* if the work item is a delayed work item with an active timer, we
+	 * need to wait for the timer to finish _before_ getting the spinlock,
+	 * lest we deadlock against the timer routine
+	 *
+	 * the timer routine will leave DELAYED set if it notices the
+	 * CANCELLING flag in time
+	 */
+	if (test_bit(SLOW_WORK_DELAYED, &work->flags)) {
+		struct delayed_slow_work *dwork =
+			container_of(work, struct delayed_slow_work, work);
+		del_timer_sync(&dwork->timer);
+	}
+
+	spin_lock_irq(&slow_work_queue_lock);
+
+	if (test_bit(SLOW_WORK_DELAYED, &work->flags)) {
+		/* the timer routine aborted or never happened, so we are left
+		 * holding the timer's reference on the item and should just
+		 * drop the pending flag and wait for any ongoing execution to
+		 * finish */
+		struct delayed_slow_work *dwork =
+			container_of(work, struct delayed_slow_work, work);
+
+		BUG_ON(timer_pending(&dwork->timer));
+		BUG_ON(!list_empty(&work->link));
+
+		clear_bit(SLOW_WORK_DELAYED, &work->flags);
+		put = true;
+		clear_bit(SLOW_WORK_PENDING, &work->flags);
+
+	} else if (test_bit(SLOW_WORK_PENDING, &work->flags) &&
+		   !list_empty(&work->link)) {
+		/* the link in the pending queue holds a reference on the item
+		 * that we will need to release */
+		list_del_init(&work->link);
+		wait = false;
+		put = true;
+		clear_bit(SLOW_WORK_PENDING, &work->flags);
+
+	} else if (test_and_clear_bit(SLOW_WORK_ENQ_DEFERRED, &work->flags)) {
+		/* the executor is holding our only reference on the item, so
+		 * we merely need to wait for it to finish executing */
+		clear_bit(SLOW_WORK_PENDING, &work->flags);
+	}
+
+	spin_unlock_irq(&slow_work_queue_lock);
+
+	/* the EXECUTING flag is set by the executor whilst the spinlock is set
+	 * and before the item is dequeued - so assuming the above doesn't
+	 * actually dequeue it, simply waiting for the EXECUTING flag to be
+	 * released here should be sufficient */
+	if (wait)
+		wait_on_bit(&work->flags, SLOW_WORK_EXECUTING, slow_work_wait,
+			    TASK_UNINTERRUPTIBLE);
+
+	clear_bit(SLOW_WORK_CANCELLING, &work->flags);
+	if (put)
+		slow_work_put_ref(work);
+}
+EXPORT_SYMBOL(slow_work_cancel);
+
+/*
+ * Handle expiry of the delay timer, indicating that a delayed slow work item
+ * should now be queued if not cancelled
+ */
+static void delayed_slow_work_timer(unsigned long data)
+{
+	wait_queue_head_t *wfo_wq;
+	struct list_head *queue;
+	struct slow_work *work = (struct slow_work *) data;
+	unsigned long flags;
+	bool queued = false, put = false, first = false;
+
+	if (test_bit(SLOW_WORK_VERY_SLOW, &work->flags)) {
+		wfo_wq = &vslow_work_queue_waits_for_occupation;
+		queue = &vslow_work_queue;
+	} else {
+		wfo_wq = &slow_work_queue_waits_for_occupation;
+		queue = &slow_work_queue;
+	}
+
+	spin_lock_irqsave(&slow_work_queue_lock, flags);
+	if (likely(!test_bit(SLOW_WORK_CANCELLING, &work->flags))) {
+		clear_bit(SLOW_WORK_DELAYED, &work->flags);
+
+		if (test_bit(SLOW_WORK_EXECUTING, &work->flags)) {
+			/* we discard the reference the timer was holding in
+			 * favour of the one the executor holds */
+			set_bit(SLOW_WORK_ENQ_DEFERRED, &work->flags);
+			put = true;
+		} else {
+			slow_work_mark_time(work);
+			list_add_tail(&work->link, queue);
+			queued = true;
+			if (work->link.prev == queue)
+				first = true;
+		}
+	}
+
+	spin_unlock_irqrestore(&slow_work_queue_lock, flags);
+	if (put)
+		slow_work_put_ref(work);
+	if (first)
+		wake_up(wfo_wq);
+	if (queued)
+		wake_up(&slow_work_thread_wq);
+}
+
+/**
+ * delayed_slow_work_enqueue - Schedule a delayed slow work item for processing
+ * @dwork: The delayed work item to queue
+ * @delay: When to start executing the work, in jiffies from now
+ *
+ * This is similar to slow_work_enqueue(), but it adds a delay before the work
+ * is actually queued for processing.
+ *
+ * The item can have delayed processing requested on it whilst it is being
+ * executed.  The delay will begin immediately, and if it expires before the
+ * item finishes executing, the item will be placed back on the queue when it
+ * has done executing.
+ */
+int delayed_slow_work_enqueue(struct delayed_slow_work *dwork,
+			      unsigned long delay)
+{
+	struct slow_work *work = &dwork->work;
+	unsigned long flags;
+	int ret;
+
+	if (delay == 0)
+		return slow_work_enqueue(&dwork->work);
+
+	BUG_ON(slow_work_user_count <= 0);
+	BUG_ON(!work);
+	BUG_ON(!work->ops);
+
+	if (test_bit(SLOW_WORK_CANCELLING, &work->flags))
+		return -ECANCELED;
+
+	if (!test_and_set_bit_lock(SLOW_WORK_PENDING, &work->flags)) {
+		spin_lock_irqsave(&slow_work_queue_lock, flags);
+
+		if (test_bit(SLOW_WORK_CANCELLING, &work->flags))
+			goto cancelled;
+
+		/* the timer holds a reference whilst it is pending */
+		ret = work->ops->get_ref(work);
+		if (ret < 0)
+			goto cant_get_ref;
+
+		if (test_and_set_bit(SLOW_WORK_DELAYED, &work->flags))
+			BUG();
+		dwork->timer.expires = jiffies + delay;
+		dwork->timer.data = (unsigned long) work;
+		dwork->timer.function = delayed_slow_work_timer;
+		add_timer(&dwork->timer);
+
+		spin_unlock_irqrestore(&slow_work_queue_lock, flags);
+	}
+
+	return 0;
+
+cancelled:
+	ret = -ECANCELED;
+cant_get_ref:
+	spin_unlock_irqrestore(&slow_work_queue_lock, flags);
+	return ret;
+}
+EXPORT_SYMBOL(delayed_slow_work_enqueue);
+
 /*
  * Schedule a cull of the thread pool at some time in the near future
  */
@@ -368,13 +714,23 @@ static inline bool slow_work_available(int vsmax)
  */
 static int slow_work_thread(void *_data)
 {
-	int vsmax;
+	int vsmax, id;
 
 	DEFINE_WAIT(wait);
 
 	set_freezable();
 	set_user_nice(current, -5);
 
+	/* allocate ourselves an ID */
+	spin_lock_irq(&slow_work_queue_lock);
+	id = find_first_zero_bit(slow_work_ids, SLOW_WORK_THREAD_LIMIT);
+	BUG_ON(id < 0 || id >= SLOW_WORK_THREAD_LIMIT);
+	__set_bit(id, slow_work_ids);
+	slow_work_set_thread_pid(id, current->pid);
+	spin_unlock_irq(&slow_work_queue_lock);
+
+	sprintf(current->comm, "kslowd%03u", id);
+
 	for (;;) {
 		vsmax = vslow_work_proportion;
 		vsmax *= atomic_read(&slow_work_thread_count);
@@ -395,7 +751,7 @@ static int slow_work_thread(void *_data)
 		vsmax *= atomic_read(&slow_work_thread_count);
 		vsmax /= 100;
 
-		if (slow_work_available(vsmax) && slow_work_execute()) {
+		if (slow_work_available(vsmax) && slow_work_execute(id)) {
 			cond_resched();
 			if (list_empty(&slow_work_queue) &&
 			    list_empty(&vslow_work_queue) &&
@@ -412,6 +768,11 @@ static int slow_work_thread(void *_data)
 			break;
 	}
 
+	spin_lock_irq(&slow_work_queue_lock);
+	slow_work_set_thread_pid(id, 0);
+	__clear_bit(id, slow_work_ids);
+	spin_unlock_irq(&slow_work_queue_lock);
+
 	if (atomic_dec_and_test(&slow_work_thread_count))
 		complete_and_exit(&slow_work_last_thread_exited, 0);
 	return 0;
@@ -427,21 +788,6 @@ static void slow_work_cull_timeout(unsigned long data)
 }
 
 /*
- * 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)
@@ -475,9 +821,11 @@ static void slow_work_new_thread_execute(struct slow_work *work)
 }
 
 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,
+	.owner		= THIS_MODULE,
 	.execute	= slow_work_new_thread_execute,
+#ifdef CONFIG_SLOW_WORK_DEBUG
+	.desc		= slow_work_new_thread_desc,
+#endif
 };
 
 /*
@@ -493,10 +841,10 @@ static void slow_work_oom_timeout(unsigned long data)
  * 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,
+					void __user *buffer,
 					size_t *lenp, loff_t *ppos)
 {
-	int ret = proc_dointvec_minmax(table, write, filp, buffer, lenp, ppos);
+	int ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
 	int n;
 
 	if (ret == 0) {
@@ -521,10 +869,10 @@ static int slow_work_min_threads_sysctl(struct ctl_table *table, int write,
  * 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,
+					void __user *buffer,
 					size_t *lenp, loff_t *ppos)
 {
-	int ret = proc_dointvec_minmax(table, write, filp, buffer, lenp, ppos);
+	int ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
 	int n;
 
 	if (ret == 0) {
@@ -546,12 +894,13 @@ static int slow_work_max_threads_sysctl(struct ctl_table *table, int write,
 
 /**
  * slow_work_register_user - Register a user of the facility
+ * @module: The module about to make use 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)
+int slow_work_register_user(struct module *module)
 {
 	struct task_struct *p;
 	int loop;
@@ -598,14 +947,81 @@ error:
 }
 EXPORT_SYMBOL(slow_work_register_user);
 
+/*
+ * wait for all outstanding items from the calling module to complete
+ * - note that more items may be queued whilst we're waiting
+ */
+static void slow_work_wait_for_items(struct module *module)
+{
+#ifdef CONFIG_MODULES
+	DECLARE_WAITQUEUE(myself, current);
+	struct slow_work *work;
+	int loop;
+
+	mutex_lock(&slow_work_unreg_sync_lock);
+	add_wait_queue(&slow_work_unreg_wq, &myself);
+
+	for (;;) {
+		spin_lock_irq(&slow_work_queue_lock);
+
+		/* first of all, we wait for the last queued item in each list
+		 * to be processed */
+		list_for_each_entry_reverse(work, &vslow_work_queue, link) {
+			if (work->owner == module) {
+				set_current_state(TASK_UNINTERRUPTIBLE);
+				slow_work_unreg_work_item = work;
+				goto do_wait;
+			}
+		}
+		list_for_each_entry_reverse(work, &slow_work_queue, link) {
+			if (work->owner == module) {
+				set_current_state(TASK_UNINTERRUPTIBLE);
+				slow_work_unreg_work_item = work;
+				goto do_wait;
+			}
+		}
+
+		/* then we wait for the items being processed to finish */
+		slow_work_unreg_module = module;
+		smp_mb();
+		for (loop = 0; loop < SLOW_WORK_THREAD_LIMIT; loop++) {
+			if (slow_work_thread_processing[loop] == module)
+				goto do_wait;
+		}
+		spin_unlock_irq(&slow_work_queue_lock);
+		break; /* okay, we're done */
+
+	do_wait:
+		spin_unlock_irq(&slow_work_queue_lock);
+		schedule();
+		slow_work_unreg_work_item = NULL;
+		slow_work_unreg_module = NULL;
+	}
+
+	remove_wait_queue(&slow_work_unreg_wq, &myself);
+	mutex_unlock(&slow_work_unreg_sync_lock);
+#endif /* CONFIG_MODULES */
+}
+
 /**
  * slow_work_unregister_user - Unregister a user of the facility
+ * @module: The module whose items should be cleared
  *
  * Unregister a user of the facility, killing all the threads if this was the
  * last one.
+ *
+ * This waits for all the work items belonging to the nominated module to go
+ * away before proceeding.
  */
-void slow_work_unregister_user(void)
+void slow_work_unregister_user(struct module *module)
 {
+	/* first of all, wait for all outstanding items from the calling module
+	 * to complete */
+	if (module)
+		slow_work_wait_for_items(module);
+
+	/* then we can actually go about shutting down the facility if need
+	 * be */
 	mutex_lock(&slow_work_user_lock);
 
 	BUG_ON(slow_work_user_count <= 0);
@@ -639,6 +1055,16 @@ static int __init init_slow_work(void)
 	if (slow_work_max_max_threads < nr_cpus * 2)
 		slow_work_max_max_threads = nr_cpus * 2;
 #endif
+#ifdef CONFIG_SLOW_WORK_DEBUG
+	{
+		struct dentry *dbdir;
+
+		dbdir = debugfs_create_dir("slow_work", NULL);
+		if (dbdir && !IS_ERR(dbdir))
+			debugfs_create_file("runqueue", S_IFREG | 0400, dbdir,
+					    NULL, &slow_work_runqueue_fops);
+	}
+#endif
 	return 0;
 }
 
diff --git a/kernel/slow-work.h b/kernel/slow-work.h
new file mode 100644
index 000000000000..321f3c59d732
--- /dev/null
+++ b/kernel/slow-work.h
@@ -0,0 +1,72 @@
+/* Slow work private definitions
+ *
+ * Copyright (C) 2009 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.
+ */
+
+#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 */
+
+#define SLOW_WORK_THREAD_LIMIT	255	/* abs maximum number of slow-work threads */
+
+/*
+ * slow-work.c
+ */
+#ifdef CONFIG_SLOW_WORK_DEBUG
+extern struct slow_work *slow_work_execs[];
+extern pid_t slow_work_pids[];
+extern rwlock_t slow_work_execs_lock;
+#endif
+
+extern struct list_head slow_work_queue;
+extern struct list_head vslow_work_queue;
+extern spinlock_t slow_work_queue_lock;
+
+/*
+ * slow-work-debugfs.c
+ */
+#ifdef CONFIG_SLOW_WORK_DEBUG
+extern const struct file_operations slow_work_runqueue_fops;
+
+extern void slow_work_new_thread_desc(struct slow_work *, struct seq_file *);
+#endif
+
+/*
+ * Helper functions
+ */
+static inline void slow_work_set_thread_pid(int id, pid_t pid)
+{
+#ifdef CONFIG_SLOW_WORK_PROC
+	slow_work_pids[id] = pid;
+#endif
+}
+
+static inline void slow_work_mark_time(struct slow_work *work)
+{
+#ifdef CONFIG_SLOW_WORK_PROC
+	work->mark = CURRENT_TIME;
+#endif
+}
+
+static inline void slow_work_begin_exec(int id, struct slow_work *work)
+{
+#ifdef CONFIG_SLOW_WORK_PROC
+	slow_work_execs[id] = work;
+#endif
+}
+
+static inline void slow_work_end_exec(int id, struct slow_work *work)
+{
+#ifdef CONFIG_SLOW_WORK_PROC
+	write_lock(&slow_work_execs_lock);
+	slow_work_execs[id] = NULL;
+	write_unlock(&slow_work_execs_lock);
+#endif
+}
diff --git a/kernel/smp.c b/kernel/smp.c
index 94188b8ecc33..c9d1c7835c2f 100644
--- a/kernel/smp.c
+++ b/kernel/smp.c
@@ -29,8 +29,7 @@ enum {
 
 struct call_function_data {
 	struct call_single_data	csd;
-	spinlock_t		lock;
-	unsigned int		refs;
+	atomic_t		refs;
 	cpumask_var_t		cpumask;
 };
 
@@ -39,9 +38,7 @@ struct call_single_queue {
 	spinlock_t		lock;
 };
 
-static DEFINE_PER_CPU(struct call_function_data, cfd_data) = {
-	.lock			= __SPIN_LOCK_UNLOCKED(cfd_data.lock),
-};
+static DEFINE_PER_CPU(struct call_function_data, cfd_data);
 
 static int
 hotplug_cfd(struct notifier_block *nfb, unsigned long action, void *hcpu)
@@ -177,6 +174,11 @@ void generic_smp_call_function_interrupt(void)
 	int cpu = get_cpu();
 
 	/*
+	 * Shouldn't receive this interrupt on a cpu that is not yet online.
+	 */
+	WARN_ON_ONCE(!cpu_online(cpu));
+
+	/*
 	 * 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
@@ -191,25 +193,18 @@ void generic_smp_call_function_interrupt(void)
 	list_for_each_entry_rcu(data, &call_function.queue, csd.list) {
 		int refs;
 
-		spin_lock(&data->lock);
-		if (!cpumask_test_cpu(cpu, data->cpumask)) {
-			spin_unlock(&data->lock);
+		if (!cpumask_test_and_clear_cpu(cpu, data->cpumask))
 			continue;
-		}
-		cpumask_clear_cpu(cpu, data->cpumask);
-		spin_unlock(&data->lock);
 
 		data->csd.func(data->csd.info);
 
-		spin_lock(&data->lock);
-		WARN_ON(data->refs == 0);
-		refs = --data->refs;
+		refs = atomic_dec_return(&data->refs);
+		WARN_ON(refs < 0);
 		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;
@@ -230,6 +225,11 @@ void generic_smp_call_function_single_interrupt(void)
 	unsigned int data_flags;
 	LIST_HEAD(list);
 
+	/*
+	 * Shouldn't receive this interrupt on a cpu that is not yet online.
+	 */
+	WARN_ON_ONCE(!cpu_online(smp_processor_id()));
+
 	spin_lock(&q->lock);
 	list_replace_init(&q->list, &list);
 	spin_unlock(&q->lock);
@@ -285,8 +285,14 @@ int smp_call_function_single(int cpu, void (*func) (void *info), void *info,
 	 */
 	this_cpu = get_cpu();
 
-	/* Can deadlock when called with interrupts disabled */
-	WARN_ON_ONCE(irqs_disabled() && !oops_in_progress);
+	/*
+	 * Can deadlock when called with interrupts disabled.
+	 * We allow cpu's that are not yet online though, as no one else can
+	 * send smp call function interrupt to this cpu and as such deadlocks
+	 * can't happen.
+	 */
+	WARN_ON_ONCE(cpu_online(this_cpu) && irqs_disabled()
+		     && !oops_in_progress);
 
 	if (cpu == this_cpu) {
 		local_irq_save(flags);
@@ -329,19 +335,18 @@ void __smp_call_function_single(int cpu, struct call_single_data *data,
 {
 	csd_lock(data);
 
-	/* Can deadlock when called with interrupts disabled */
-	WARN_ON_ONCE(wait && irqs_disabled() && !oops_in_progress);
+	/*
+	 * Can deadlock when called with interrupts disabled.
+	 * We allow cpu's that are not yet online though, as no one else can
+	 * send smp call function interrupt to this cpu and as such deadlocks
+	 * can't happen.
+	 */
+	WARN_ON_ONCE(cpu_online(smp_processor_id()) && wait && irqs_disabled()
+		     && !oops_in_progress);
 
 	generic_exec_single(cpu, data, wait);
 }
 
-/* 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))
-#endif
-
 /**
  * smp_call_function_many(): Run a function on a set of other CPUs.
  * @mask: The set of cpus to run on (only runs on online subset).
@@ -365,8 +370,14 @@ void smp_call_function_many(const struct cpumask *mask,
 	unsigned long flags;
 	int cpu, next_cpu, this_cpu = smp_processor_id();
 
-	/* Can deadlock when called with interrupts disabled */
-	WARN_ON_ONCE(irqs_disabled() && !oops_in_progress);
+	/*
+	 * Can deadlock when called with interrupts disabled.
+	 * We allow cpu's that are not yet online though, as no one else can
+	 * send smp call function interrupt to this cpu and as such deadlocks
+	 * can't happen.
+	 */
+	WARN_ON_ONCE(cpu_online(this_cpu) && irqs_disabled()
+		     && !oops_in_progress);
 
 	/* So, what's a CPU they want? Ignoring this one. */
 	cpu = cpumask_first_and(mask, cpu_online_mask);
@@ -391,23 +402,20 @@ void smp_call_function_many(const struct cpumask *mask,
 	data = &__get_cpu_var(cfd_data);
 	csd_lock(&data->csd);
 
-	spin_lock_irqsave(&data->lock, flags);
 	data->csd.func = func;
 	data->csd.info = info;
 	cpumask_and(data->cpumask, mask, cpu_online_mask);
 	cpumask_clear_cpu(this_cpu, data->cpumask);
-	data->refs = cpumask_weight(data->cpumask);
+	atomic_set(&data->refs, cpumask_weight(data->cpumask));
 
-	spin_lock(&call_function.lock);
+	spin_lock_irqsave(&call_function.lock, flags);
 	/*
 	 * 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);
+	spin_unlock_irqrestore(&call_function.lock, flags);
 
 	/*
 	 * Make the list addition visible before sending the ipi.
diff --git a/kernel/softirq.c b/kernel/softirq.c
index eb5e131a0485..f8749e5216e0 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -57,7 +57,7 @@ static struct softirq_action softirq_vec[NR_SOFTIRQS] __cacheline_aligned_in_smp
 static DEFINE_PER_CPU(struct task_struct *, ksoftirqd);
 
 char *softirq_to_name[NR_SOFTIRQS] = {
-	"HI", "TIMER", "NET_TX", "NET_RX", "BLOCK",
+	"HI", "TIMER", "NET_TX", "NET_RX", "BLOCK", "BLOCK_IOPOLL",
 	"TASKLET", "SCHED", "HRTIMER",	"RCU"
 };
 
@@ -227,7 +227,7 @@ restart:
 				preempt_count() = prev_count;
 			}
 
-			rcu_bh_qsctr_inc(cpu);
+			rcu_bh_qs(cpu);
 		}
 		h++;
 		pending >>= 1;
@@ -721,7 +721,7 @@ static int ksoftirqd(void * __bind_cpu)
 			preempt_enable_no_resched();
 			cond_resched();
 			preempt_disable();
-			rcu_qsctr_inc((long)__bind_cpu);
+			rcu_sched_qs((long)__bind_cpu);
 		}
 		preempt_enable();
 		set_current_state(TASK_INTERRUPTIBLE);
diff --git a/kernel/softlockup.c b/kernel/softlockup.c
index 88796c330838..81324d12eb35 100644
--- a/kernel/softlockup.c
+++ b/kernel/softlockup.c
@@ -90,11 +90,11 @@ void touch_all_softlockup_watchdogs(void)
 EXPORT_SYMBOL(touch_all_softlockup_watchdogs);
 
 int proc_dosoftlockup_thresh(struct ctl_table *table, int write,
-			     struct file *filp, void __user *buffer,
+			     void __user *buffer,
 			     size_t *lenp, loff_t *ppos)
 {
 	touch_all_softlockup_watchdogs();
-	return proc_dointvec_minmax(table, write, filp, buffer, lenp, ppos);
+	return proc_dointvec_minmax(table, write, buffer, lenp, ppos);
 }
 
 /*
diff --git a/kernel/spinlock.c b/kernel/spinlock.c
index 7932653c4ebd..5ddab730cb2f 100644
--- a/kernel/spinlock.c
+++ b/kernel/spinlock.c
@@ -21,44 +21,29 @@
 #include <linux/debug_locks.h>
 #include <linux/module.h>
 
+#ifndef _spin_trylock
 int __lockfunc _spin_trylock(spinlock_t *lock)
 {
-	preempt_disable();
-	if (_raw_spin_trylock(lock)) {
-		spin_acquire(&lock->dep_map, 0, 1, _RET_IP_);
-		return 1;
-	}
-	
-	preempt_enable();
-	return 0;
+	return __spin_trylock(lock);
 }
 EXPORT_SYMBOL(_spin_trylock);
+#endif
 
+#ifndef _read_trylock
 int __lockfunc _read_trylock(rwlock_t *lock)
 {
-	preempt_disable();
-	if (_raw_read_trylock(lock)) {
-		rwlock_acquire_read(&lock->dep_map, 0, 1, _RET_IP_);
-		return 1;
-	}
-
-	preempt_enable();
-	return 0;
+	return __read_trylock(lock);
 }
 EXPORT_SYMBOL(_read_trylock);
+#endif
 
+#ifndef _write_trylock
 int __lockfunc _write_trylock(rwlock_t *lock)
 {
-	preempt_disable();
-	if (_raw_write_trylock(lock)) {
-		rwlock_acquire(&lock->dep_map, 0, 1, _RET_IP_);
-		return 1;
-	}
-
-	preempt_enable();
-	return 0;
+	return __write_trylock(lock);
 }
 EXPORT_SYMBOL(_write_trylock);
+#endif
 
 /*
  * If lockdep is enabled then we use the non-preemption spin-ops
@@ -67,132 +52,101 @@ EXPORT_SYMBOL(_write_trylock);
  */
 #if !defined(CONFIG_GENERIC_LOCKBREAK) || defined(CONFIG_DEBUG_LOCK_ALLOC)
 
+#ifndef _read_lock
 void __lockfunc _read_lock(rwlock_t *lock)
 {
-	preempt_disable();
-	rwlock_acquire_read(&lock->dep_map, 0, 0, _RET_IP_);
-	LOCK_CONTENDED(lock, _raw_read_trylock, _raw_read_lock);
+	__read_lock(lock);
 }
 EXPORT_SYMBOL(_read_lock);
+#endif
 
+#ifndef _spin_lock_irqsave
 unsigned long __lockfunc _spin_lock_irqsave(spinlock_t *lock)
 {
-	unsigned long flags;
-
-	local_irq_save(flags);
-	preempt_disable();
-	spin_acquire(&lock->dep_map, 0, 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
-	return flags;
+	return __spin_lock_irqsave(lock);
 }
 EXPORT_SYMBOL(_spin_lock_irqsave);
+#endif
 
+#ifndef _spin_lock_irq
 void __lockfunc _spin_lock_irq(spinlock_t *lock)
 {
-	local_irq_disable();
-	preempt_disable();
-	spin_acquire(&lock->dep_map, 0, 0, _RET_IP_);
-	LOCK_CONTENDED(lock, _raw_spin_trylock, _raw_spin_lock);
+	__spin_lock_irq(lock);
 }
 EXPORT_SYMBOL(_spin_lock_irq);
+#endif
 
+#ifndef _spin_lock_bh
 void __lockfunc _spin_lock_bh(spinlock_t *lock)
 {
-	local_bh_disable();
-	preempt_disable();
-	spin_acquire(&lock->dep_map, 0, 0, _RET_IP_);
-	LOCK_CONTENDED(lock, _raw_spin_trylock, _raw_spin_lock);
+	__spin_lock_bh(lock);
 }
 EXPORT_SYMBOL(_spin_lock_bh);
+#endif
 
+#ifndef _read_lock_irqsave
 unsigned long __lockfunc _read_lock_irqsave(rwlock_t *lock)
 {
-	unsigned long flags;
-
-	local_irq_save(flags);
-	preempt_disable();
-	rwlock_acquire_read(&lock->dep_map, 0, 0, _RET_IP_);
-	LOCK_CONTENDED_FLAGS(lock, _raw_read_trylock, _raw_read_lock,
-			     _raw_read_lock_flags, &flags);
-	return flags;
+	return __read_lock_irqsave(lock);
 }
 EXPORT_SYMBOL(_read_lock_irqsave);
+#endif
 
+#ifndef _read_lock_irq
 void __lockfunc _read_lock_irq(rwlock_t *lock)
 {
-	local_irq_disable();
-	preempt_disable();
-	rwlock_acquire_read(&lock->dep_map, 0, 0, _RET_IP_);
-	LOCK_CONTENDED(lock, _raw_read_trylock, _raw_read_lock);
+	__read_lock_irq(lock);
 }
 EXPORT_SYMBOL(_read_lock_irq);
+#endif
 
+#ifndef _read_lock_bh
 void __lockfunc _read_lock_bh(rwlock_t *lock)
 {
-	local_bh_disable();
-	preempt_disable();
-	rwlock_acquire_read(&lock->dep_map, 0, 0, _RET_IP_);
-	LOCK_CONTENDED(lock, _raw_read_trylock, _raw_read_lock);
+	__read_lock_bh(lock);
 }
 EXPORT_SYMBOL(_read_lock_bh);
+#endif
 
+#ifndef _write_lock_irqsave
 unsigned long __lockfunc _write_lock_irqsave(rwlock_t *lock)
 {
-	unsigned long flags;
-
-	local_irq_save(flags);
-	preempt_disable();
-	rwlock_acquire(&lock->dep_map, 0, 0, _RET_IP_);
-	LOCK_CONTENDED_FLAGS(lock, _raw_write_trylock, _raw_write_lock,
-			     _raw_write_lock_flags, &flags);
-	return flags;
+	return __write_lock_irqsave(lock);
 }
 EXPORT_SYMBOL(_write_lock_irqsave);
+#endif
 
+#ifndef _write_lock_irq
 void __lockfunc _write_lock_irq(rwlock_t *lock)
 {
-	local_irq_disable();
-	preempt_disable();
-	rwlock_acquire(&lock->dep_map, 0, 0, _RET_IP_);
-	LOCK_CONTENDED(lock, _raw_write_trylock, _raw_write_lock);
+	__write_lock_irq(lock);
 }
 EXPORT_SYMBOL(_write_lock_irq);
+#endif
 
+#ifndef _write_lock_bh
 void __lockfunc _write_lock_bh(rwlock_t *lock)
 {
-	local_bh_disable();
-	preempt_disable();
-	rwlock_acquire(&lock->dep_map, 0, 0, _RET_IP_);
-	LOCK_CONTENDED(lock, _raw_write_trylock, _raw_write_lock);
+	__write_lock_bh(lock);
 }
 EXPORT_SYMBOL(_write_lock_bh);
+#endif
 
+#ifndef _spin_lock
 void __lockfunc _spin_lock(spinlock_t *lock)
 {
-	preempt_disable();
-	spin_acquire(&lock->dep_map, 0, 0, _RET_IP_);
-	LOCK_CONTENDED(lock, _raw_spin_trylock, _raw_spin_lock);
+	__spin_lock(lock);
 }
-
 EXPORT_SYMBOL(_spin_lock);
+#endif
 
+#ifndef _write_lock
 void __lockfunc _write_lock(rwlock_t *lock)
 {
-	preempt_disable();
-	rwlock_acquire(&lock->dep_map, 0, 0, _RET_IP_);
-	LOCK_CONTENDED(lock, _raw_write_trylock, _raw_write_lock);
+	__write_lock(lock);
 }
-
 EXPORT_SYMBOL(_write_lock);
+#endif
 
 #else /* CONFIG_PREEMPT: */
 
@@ -318,125 +272,109 @@ EXPORT_SYMBOL(_spin_lock_nest_lock);
 
 #endif
 
+#ifndef _spin_unlock
 void __lockfunc _spin_unlock(spinlock_t *lock)
 {
-	spin_release(&lock->dep_map, 1, _RET_IP_);
-	_raw_spin_unlock(lock);
-	preempt_enable();
+	__spin_unlock(lock);
 }
 EXPORT_SYMBOL(_spin_unlock);
+#endif
 
+#ifndef _write_unlock
 void __lockfunc _write_unlock(rwlock_t *lock)
 {
-	rwlock_release(&lock->dep_map, 1, _RET_IP_);
-	_raw_write_unlock(lock);
-	preempt_enable();
+	__write_unlock(lock);
 }
 EXPORT_SYMBOL(_write_unlock);
+#endif
 
+#ifndef _read_unlock
 void __lockfunc _read_unlock(rwlock_t *lock)
 {
-	rwlock_release(&lock->dep_map, 1, _RET_IP_);
-	_raw_read_unlock(lock);
-	preempt_enable();
+	__read_unlock(lock);
 }
 EXPORT_SYMBOL(_read_unlock);
+#endif
 
+#ifndef _spin_unlock_irqrestore
 void __lockfunc _spin_unlock_irqrestore(spinlock_t *lock, unsigned long flags)
 {
-	spin_release(&lock->dep_map, 1, _RET_IP_);
-	_raw_spin_unlock(lock);
-	local_irq_restore(flags);
-	preempt_enable();
+	__spin_unlock_irqrestore(lock, flags);
 }
 EXPORT_SYMBOL(_spin_unlock_irqrestore);
+#endif
 
+#ifndef _spin_unlock_irq
 void __lockfunc _spin_unlock_irq(spinlock_t *lock)
 {
-	spin_release(&lock->dep_map, 1, _RET_IP_);
-	_raw_spin_unlock(lock);
-	local_irq_enable();
-	preempt_enable();
+	__spin_unlock_irq(lock);
 }
 EXPORT_SYMBOL(_spin_unlock_irq);
+#endif
 
+#ifndef _spin_unlock_bh
 void __lockfunc _spin_unlock_bh(spinlock_t *lock)
 {
-	spin_release(&lock->dep_map, 1, _RET_IP_);
-	_raw_spin_unlock(lock);
-	preempt_enable_no_resched();
-	local_bh_enable_ip((unsigned long)__builtin_return_address(0));
+	__spin_unlock_bh(lock);
 }
 EXPORT_SYMBOL(_spin_unlock_bh);
+#endif
 
+#ifndef _read_unlock_irqrestore
 void __lockfunc _read_unlock_irqrestore(rwlock_t *lock, unsigned long flags)
 {
-	rwlock_release(&lock->dep_map, 1, _RET_IP_);
-	_raw_read_unlock(lock);
-	local_irq_restore(flags);
-	preempt_enable();
+	__read_unlock_irqrestore(lock, flags);
 }
 EXPORT_SYMBOL(_read_unlock_irqrestore);
+#endif
 
+#ifndef _read_unlock_irq
 void __lockfunc _read_unlock_irq(rwlock_t *lock)
 {
-	rwlock_release(&lock->dep_map, 1, _RET_IP_);
-	_raw_read_unlock(lock);
-	local_irq_enable();
-	preempt_enable();
+	__read_unlock_irq(lock);
 }
 EXPORT_SYMBOL(_read_unlock_irq);
+#endif
 
+#ifndef _read_unlock_bh
 void __lockfunc _read_unlock_bh(rwlock_t *lock)
 {
-	rwlock_release(&lock->dep_map, 1, _RET_IP_);
-	_raw_read_unlock(lock);
-	preempt_enable_no_resched();
-	local_bh_enable_ip((unsigned long)__builtin_return_address(0));
+	__read_unlock_bh(lock);
 }
 EXPORT_SYMBOL(_read_unlock_bh);
+#endif
 
+#ifndef _write_unlock_irqrestore
 void __lockfunc _write_unlock_irqrestore(rwlock_t *lock, unsigned long flags)
 {
-	rwlock_release(&lock->dep_map, 1, _RET_IP_);
-	_raw_write_unlock(lock);
-	local_irq_restore(flags);
-	preempt_enable();
+	__write_unlock_irqrestore(lock, flags);
 }
 EXPORT_SYMBOL(_write_unlock_irqrestore);
+#endif
 
+#ifndef _write_unlock_irq
 void __lockfunc _write_unlock_irq(rwlock_t *lock)
 {
-	rwlock_release(&lock->dep_map, 1, _RET_IP_);
-	_raw_write_unlock(lock);
-	local_irq_enable();
-	preempt_enable();
+	__write_unlock_irq(lock);
 }
 EXPORT_SYMBOL(_write_unlock_irq);
+#endif
 
+#ifndef _write_unlock_bh
 void __lockfunc _write_unlock_bh(rwlock_t *lock)
 {
-	rwlock_release(&lock->dep_map, 1, _RET_IP_);
-	_raw_write_unlock(lock);
-	preempt_enable_no_resched();
-	local_bh_enable_ip((unsigned long)__builtin_return_address(0));
+	__write_unlock_bh(lock);
 }
 EXPORT_SYMBOL(_write_unlock_bh);
+#endif
 
+#ifndef _spin_trylock_bh
 int __lockfunc _spin_trylock_bh(spinlock_t *lock)
 {
-	local_bh_disable();
-	preempt_disable();
-	if (_raw_spin_trylock(lock)) {
-		spin_acquire(&lock->dep_map, 0, 1, _RET_IP_);
-		return 1;
-	}
-
-	preempt_enable_no_resched();
-	local_bh_enable_ip((unsigned long)__builtin_return_address(0));
-	return 0;
+	return __spin_trylock_bh(lock);
 }
 EXPORT_SYMBOL(_spin_trylock_bh);
+#endif
 
 notrace int in_lock_functions(unsigned long addr)
 {
diff --git a/kernel/sys.c b/kernel/sys.c
index b3f1097c76fa..ce17760d9c51 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -14,7 +14,7 @@
 #include <linux/prctl.h>
 #include <linux/highuid.h>
 #include <linux/fs.h>
-#include <linux/perf_counter.h>
+#include <linux/perf_event.h>
 #include <linux/resource.h>
 #include <linux/kernel.h>
 #include <linux/kexec.h>
@@ -1110,6 +1110,8 @@ SYSCALL_DEFINE0(setsid)
 	err = session;
 out:
 	write_unlock_irq(&tasklist_lock);
+	if (err > 0)
+		proc_sid_connector(group_leader);
 	return err;
 }
 
@@ -1338,6 +1340,7 @@ static void k_getrusage(struct task_struct *p, int who, struct rusage *r)
 	unsigned long flags;
 	cputime_t utime, stime;
 	struct task_cputime cputime;
+	unsigned long maxrss = 0;
 
 	memset((char *) r, 0, sizeof *r);
 	utime = stime = cputime_zero;
@@ -1346,6 +1349,7 @@ static void k_getrusage(struct task_struct *p, int who, struct rusage *r)
 		utime = task_utime(current);
 		stime = task_stime(current);
 		accumulate_thread_rusage(p, r);
+		maxrss = p->signal->maxrss;
 		goto out;
 	}
 
@@ -1363,6 +1367,7 @@ static void k_getrusage(struct task_struct *p, int who, struct rusage *r)
 			r->ru_majflt = p->signal->cmaj_flt;
 			r->ru_inblock = p->signal->cinblock;
 			r->ru_oublock = p->signal->coublock;
+			maxrss = p->signal->cmaxrss;
 
 			if (who == RUSAGE_CHILDREN)
 				break;
@@ -1377,6 +1382,8 @@ static void k_getrusage(struct task_struct *p, int who, struct rusage *r)
 			r->ru_majflt += p->signal->maj_flt;
 			r->ru_inblock += p->signal->inblock;
 			r->ru_oublock += p->signal->oublock;
+			if (maxrss < p->signal->maxrss)
+				maxrss = p->signal->maxrss;
 			t = p;
 			do {
 				accumulate_thread_rusage(t, r);
@@ -1392,6 +1399,15 @@ static void k_getrusage(struct task_struct *p, int who, struct rusage *r)
 out:
 	cputime_to_timeval(utime, &r->ru_utime);
 	cputime_to_timeval(stime, &r->ru_stime);
+
+	if (who != RUSAGE_CHILDREN) {
+		struct mm_struct *mm = get_task_mm(p);
+		if (mm) {
+			setmax_mm_hiwater_rss(&maxrss, mm);
+			mmput(mm);
+		}
+	}
+	r->ru_maxrss = maxrss * (PAGE_SIZE / 1024); /* convert pages to KBs */
 }
 
 int getrusage(struct task_struct *p, int who, struct rusage __user *ru)
@@ -1511,11 +1527,11 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
 		case PR_SET_TSC:
 			error = SET_TSC_CTL(arg2);
 			break;
-		case PR_TASK_PERF_COUNTERS_DISABLE:
-			error = perf_counter_task_disable();
+		case PR_TASK_PERF_EVENTS_DISABLE:
+			error = perf_event_task_disable();
 			break;
-		case PR_TASK_PERF_COUNTERS_ENABLE:
-			error = perf_counter_task_enable();
+		case PR_TASK_PERF_EVENTS_ENABLE:
+			error = perf_event_task_enable();
 			break;
 		case PR_GET_TIMERSLACK:
 			error = current->timer_slack_ns;
@@ -1528,6 +1544,41 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
 				current->timer_slack_ns = arg2;
 			error = 0;
 			break;
+		case PR_MCE_KILL:
+			if (arg4 | arg5)
+				return -EINVAL;
+			switch (arg2) {
+			case PR_MCE_KILL_CLEAR:
+				if (arg3 != 0)
+					return -EINVAL;
+				current->flags &= ~PF_MCE_PROCESS;
+				break;
+			case PR_MCE_KILL_SET:
+				current->flags |= PF_MCE_PROCESS;
+				if (arg3 == PR_MCE_KILL_EARLY)
+					current->flags |= PF_MCE_EARLY;
+				else if (arg3 == PR_MCE_KILL_LATE)
+					current->flags &= ~PF_MCE_EARLY;
+				else if (arg3 == PR_MCE_KILL_DEFAULT)
+					current->flags &=
+						~(PF_MCE_EARLY|PF_MCE_PROCESS);
+				else
+					return -EINVAL;
+				break;
+			default:
+				return -EINVAL;
+			}
+			error = 0;
+			break;
+		case PR_MCE_KILL_GET:
+			if (arg2 | arg3 | arg4 | arg5)
+				return -EINVAL;
+			if (current->flags & PF_MCE_PROCESS)
+				error = (current->flags & PF_MCE_EARLY) ?
+					PR_MCE_KILL_EARLY : PR_MCE_KILL_LATE;
+			else
+				error = PR_MCE_KILL_DEFAULT;
+			break;
 		default:
 			error = -EINVAL;
 			break;
diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c
index 68320f6b07b5..e06d0b8d1951 100644
--- a/kernel/sys_ni.c
+++ b/kernel/sys_ni.c
@@ -49,6 +49,7 @@ cond_syscall(sys_sendmsg);
 cond_syscall(compat_sys_sendmsg);
 cond_syscall(sys_recvmsg);
 cond_syscall(compat_sys_recvmsg);
+cond_syscall(compat_sys_recvfrom);
 cond_syscall(sys_socketcall);
 cond_syscall(sys_futex);
 cond_syscall(compat_sys_futex);
@@ -177,4 +178,4 @@ cond_syscall(sys_eventfd);
 cond_syscall(sys_eventfd2);
 
 /* performance counters: */
-cond_syscall(sys_perf_counter_open);
+cond_syscall(sys_perf_event_open);
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 58be76017fd0..0d949c517412 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -26,7 +26,6 @@
 #include <linux/proc_fs.h>
 #include <linux/security.h>
 #include <linux/ctype.h>
-#include <linux/utsname.h>
 #include <linux/kmemcheck.h>
 #include <linux/smp_lock.h>
 #include <linux/fs.h>
@@ -49,9 +48,8 @@
 #include <linux/acpi.h>
 #include <linux/reboot.h>
 #include <linux/ftrace.h>
-#include <linux/security.h>
 #include <linux/slow-work.h>
-#include <linux/perf_counter.h>
+#include <linux/perf_event.h>
 
 #include <asm/uaccess.h>
 #include <asm/processor.h>
@@ -78,6 +76,7 @@ extern int max_threads;
 extern int core_uses_pid;
 extern int suid_dumpable;
 extern char core_pattern[];
+extern unsigned int core_pipe_limit;
 extern int pid_max;
 extern int min_free_kbytes;
 extern int pid_max_min, pid_max_max;
@@ -92,6 +91,9 @@ extern int sysctl_nr_trim_pages;
 #ifdef CONFIG_RCU_TORTURE_TEST
 extern int rcutorture_runnable;
 #endif /* #ifdef CONFIG_RCU_TORTURE_TEST */
+#ifdef CONFIG_BLOCK
+extern int blk_iopoll_enabled;
+#endif
 
 /* Constants used for minimum and  maximum */
 #ifdef CONFIG_DETECT_SOFTLOCKUP
@@ -104,6 +106,9 @@ static int __maybe_unused one = 1;
 static int __maybe_unused two = 2;
 static unsigned long one_ul = 1;
 static int one_hundred = 100;
+#ifdef CONFIG_PRINTK
+static int ten_thousand = 10000;
+#endif
 
 /* this is needed for the proc_doulongvec_minmax of vm_dirty_bytes */
 static unsigned long dirty_bytes_min = 2 * PAGE_SIZE;
@@ -158,9 +163,9 @@ extern int max_lock_depth;
 #endif
 
 #ifdef CONFIG_PROC_SYSCTL
-static int proc_do_cad_pid(struct ctl_table *table, int write, struct file *filp,
+static int proc_do_cad_pid(struct ctl_table *table, int write,
 		  void __user *buffer, size_t *lenp, loff_t *ppos);
-static int proc_taint(struct ctl_table *table, int write, struct file *filp,
+static int proc_taint(struct ctl_table *table, int write,
 			       void __user *buffer, size_t *lenp, loff_t *ppos);
 #endif
 
@@ -246,6 +251,14 @@ static int max_wakeup_granularity_ns = NSEC_PER_SEC;	/* 1 second */
 #endif
 
 static struct ctl_table kern_table[] = {
+	{
+		.ctl_name	= CTL_UNNUMBERED,
+		.procname	= "sched_child_runs_first",
+		.data		= &sysctl_sched_child_runs_first,
+		.maxlen		= sizeof(unsigned int),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec,
+	},
 #ifdef CONFIG_SCHED_DEBUG
 	{
 		.ctl_name	= CTL_UNNUMBERED,
@@ -300,14 +313,6 @@ static struct ctl_table kern_table[] = {
 	},
 	{
 		.ctl_name	= CTL_UNNUMBERED,
-		.procname	= "sched_child_runs_first",
-		.data		= &sysctl_sched_child_runs_first,
-		.maxlen		= sizeof(unsigned int),
-		.mode		= 0644,
-		.proc_handler	= &proc_dointvec,
-	},
-	{
-		.ctl_name	= CTL_UNNUMBERED,
 		.procname	= "sched_features",
 		.data		= &sysctl_sched_features,
 		.maxlen		= sizeof(unsigned int),
@@ -332,6 +337,14 @@ static struct ctl_table kern_table[] = {
 	},
 	{
 		.ctl_name	= CTL_UNNUMBERED,
+		.procname	= "sched_time_avg",
+		.data		= &sysctl_sched_time_avg,
+		.maxlen		= sizeof(unsigned int),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec,
+	},
+	{
+		.ctl_name	= CTL_UNNUMBERED,
 		.procname	= "timer_migration",
 		.data		= &sysctl_timer_migration,
 		.maxlen		= sizeof(unsigned int),
@@ -411,6 +424,14 @@ static struct ctl_table kern_table[] = {
 		.proc_handler	= &proc_dostring,
 		.strategy	= &sysctl_string,
 	},
+	{
+		.ctl_name	= CTL_UNNUMBERED,
+		.procname	= "core_pipe_limit",
+		.data		= &core_pipe_limit,
+		.maxlen		= sizeof(unsigned int),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec,
+	},
 #ifdef CONFIG_PROC_SYSCTL
 	{
 		.procname	= "tainted",
@@ -712,6 +733,17 @@ static struct ctl_table kern_table[] = {
 		.mode		= 0644,
 		.proc_handler	= &proc_dointvec,
 	},
+	{
+		.ctl_name	= CTL_UNNUMBERED,
+		.procname	= "printk_delay",
+		.data		= &printk_delay_msec,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec_minmax,
+		.strategy	= &sysctl_intvec,
+		.extra1		= &zero,
+		.extra2		= &ten_thousand,
+	},
 #endif
 	{
 		.ctl_name	= KERN_NGROUPS_MAX,
@@ -954,28 +986,28 @@ static struct ctl_table kern_table[] = {
 		.child		= slow_work_sysctls,
 	},
 #endif
-#ifdef CONFIG_PERF_COUNTERS
+#ifdef CONFIG_PERF_EVENTS
 	{
 		.ctl_name	= CTL_UNNUMBERED,
-		.procname	= "perf_counter_paranoid",
-		.data		= &sysctl_perf_counter_paranoid,
-		.maxlen		= sizeof(sysctl_perf_counter_paranoid),
+		.procname	= "perf_event_paranoid",
+		.data		= &sysctl_perf_event_paranoid,
+		.maxlen		= sizeof(sysctl_perf_event_paranoid),
 		.mode		= 0644,
 		.proc_handler	= &proc_dointvec,
 	},
 	{
 		.ctl_name	= CTL_UNNUMBERED,
-		.procname	= "perf_counter_mlock_kb",
-		.data		= &sysctl_perf_counter_mlock,
-		.maxlen		= sizeof(sysctl_perf_counter_mlock),
+		.procname	= "perf_event_mlock_kb",
+		.data		= &sysctl_perf_event_mlock,
+		.maxlen		= sizeof(sysctl_perf_event_mlock),
 		.mode		= 0644,
 		.proc_handler	= &proc_dointvec,
 	},
 	{
 		.ctl_name	= CTL_UNNUMBERED,
-		.procname	= "perf_counter_max_sample_rate",
-		.data		= &sysctl_perf_counter_sample_rate,
-		.maxlen		= sizeof(sysctl_perf_counter_sample_rate),
+		.procname	= "perf_event_max_sample_rate",
+		.data		= &sysctl_perf_event_sample_rate,
+		.maxlen		= sizeof(sysctl_perf_event_sample_rate),
 		.mode		= 0644,
 		.proc_handler	= &proc_dointvec,
 	},
@@ -990,7 +1022,16 @@ static struct ctl_table kern_table[] = {
 		.proc_handler	= &proc_dointvec,
 	},
 #endif
-
+#ifdef CONFIG_BLOCK
+	{
+		.ctl_name	= CTL_UNNUMBERED,
+		.procname	= "blk_iopoll",
+		.data		= &blk_iopoll_enabled,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec,
+	},
+#endif
 /*
  * NOTE: do not add new entries to this table unless you have read
  * Documentation/sysctl/ctl_unnumbered.txt
@@ -1357,6 +1398,31 @@ static struct ctl_table vm_table[] = {
 		.mode		= 0644,
 		.proc_handler	= &scan_unevictable_handler,
 	},
+#ifdef CONFIG_MEMORY_FAILURE
+	{
+		.ctl_name	= CTL_UNNUMBERED,
+		.procname	= "memory_failure_early_kill",
+		.data		= &sysctl_memory_failure_early_kill,
+		.maxlen		= sizeof(sysctl_memory_failure_early_kill),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec_minmax,
+		.strategy	= &sysctl_intvec,
+		.extra1		= &zero,
+		.extra2		= &one,
+	},
+	{
+		.ctl_name	= CTL_UNNUMBERED,
+		.procname	= "memory_failure_recovery",
+		.data		= &sysctl_memory_failure_recovery,
+		.maxlen		= sizeof(sysctl_memory_failure_recovery),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec_minmax,
+		.strategy	= &sysctl_intvec,
+		.extra1		= &zero,
+		.extra2		= &one,
+	},
+#endif
+
 /*
  * NOTE: do not add new entries to this table unless you have read
  * Documentation/sysctl/ctl_unnumbered.txt
@@ -2185,7 +2251,7 @@ void sysctl_head_put(struct ctl_table_header *head)
 #ifdef CONFIG_PROC_SYSCTL
 
 static int _proc_do_string(void* data, int maxlen, int write,
-			   struct file *filp, void __user *buffer,
+			   void __user *buffer,
 			   size_t *lenp, loff_t *ppos)
 {
 	size_t len;
@@ -2246,7 +2312,6 @@ static int _proc_do_string(void* data, int maxlen, int write,
  * proc_dostring - read a string sysctl
  * @table: the sysctl table
  * @write: %TRUE if this is a write to the sysctl file
- * @filp: the file structure
  * @buffer: the user buffer
  * @lenp: the size of the user buffer
  * @ppos: file position
@@ -2260,10 +2325,10 @@ static int _proc_do_string(void* data, int maxlen, int write,
  *
  * Returns 0 on success.
  */
-int proc_dostring(struct ctl_table *table, int write, struct file *filp,
+int proc_dostring(struct ctl_table *table, int write,
 		  void __user *buffer, size_t *lenp, loff_t *ppos)
 {
-	return _proc_do_string(table->data, table->maxlen, write, filp,
+	return _proc_do_string(table->data, table->maxlen, write,
 			       buffer, lenp, ppos);
 }
 
@@ -2288,7 +2353,7 @@ static int do_proc_dointvec_conv(int *negp, unsigned long *lvalp,
 }
 
 static int __do_proc_dointvec(void *tbl_data, struct ctl_table *table,
-		  int write, struct file *filp, void __user *buffer,
+		  int write, void __user *buffer,
 		  size_t *lenp, loff_t *ppos,
 		  int (*conv)(int *negp, unsigned long *lvalp, int *valp,
 			      int write, void *data),
@@ -2395,13 +2460,13 @@ static int __do_proc_dointvec(void *tbl_data, struct ctl_table *table,
 #undef TMPBUFLEN
 }
 
-static int do_proc_dointvec(struct ctl_table *table, int write, struct file *filp,
+static int do_proc_dointvec(struct ctl_table *table, int write,
 		  void __user *buffer, size_t *lenp, loff_t *ppos,
 		  int (*conv)(int *negp, unsigned long *lvalp, int *valp,
 			      int write, void *data),
 		  void *data)
 {
-	return __do_proc_dointvec(table->data, table, write, filp,
+	return __do_proc_dointvec(table->data, table, write,
 			buffer, lenp, ppos, conv, data);
 }
 
@@ -2409,7 +2474,6 @@ static int do_proc_dointvec(struct ctl_table *table, int write, struct file *fil
  * proc_dointvec - read a vector of integers
  * @table: the sysctl table
  * @write: %TRUE if this is a write to the sysctl file
- * @filp: the file structure
  * @buffer: the user buffer
  * @lenp: the size of the user buffer
  * @ppos: file position
@@ -2419,10 +2483,10 @@ static int do_proc_dointvec(struct ctl_table *table, int write, struct file *fil
  *
  * Returns 0 on success.
  */
-int proc_dointvec(struct ctl_table *table, int write, struct file *filp,
+int proc_dointvec(struct ctl_table *table, int write,
 		     void __user *buffer, size_t *lenp, loff_t *ppos)
 {
-    return do_proc_dointvec(table,write,filp,buffer,lenp,ppos,
+    return do_proc_dointvec(table,write,buffer,lenp,ppos,
 		    	    NULL,NULL);
 }
 
@@ -2430,7 +2494,7 @@ int proc_dointvec(struct ctl_table *table, int write, struct file *filp,
  * Taint values can only be increased
  * This means we can safely use a temporary.
  */
-static int proc_taint(struct ctl_table *table, int write, struct file *filp,
+static int proc_taint(struct ctl_table *table, int write,
 			       void __user *buffer, size_t *lenp, loff_t *ppos)
 {
 	struct ctl_table t;
@@ -2442,7 +2506,7 @@ static int proc_taint(struct ctl_table *table, int write, struct file *filp,
 
 	t = *table;
 	t.data = &tmptaint;
-	err = proc_doulongvec_minmax(&t, write, filp, buffer, lenp, ppos);
+	err = proc_doulongvec_minmax(&t, write, buffer, lenp, ppos);
 	if (err < 0)
 		return err;
 
@@ -2494,7 +2558,6 @@ static int do_proc_dointvec_minmax_conv(int *negp, unsigned long *lvalp,
  * proc_dointvec_minmax - read a vector of integers with min/max values
  * @table: the sysctl table
  * @write: %TRUE if this is a write to the sysctl file
- * @filp: the file structure
  * @buffer: the user buffer
  * @lenp: the size of the user buffer
  * @ppos: file position
@@ -2507,19 +2570,18 @@ static int do_proc_dointvec_minmax_conv(int *negp, unsigned long *lvalp,
  *
  * Returns 0 on success.
  */
-int proc_dointvec_minmax(struct ctl_table *table, int write, struct file *filp,
+int proc_dointvec_minmax(struct ctl_table *table, int write,
 		  void __user *buffer, size_t *lenp, loff_t *ppos)
 {
 	struct do_proc_dointvec_minmax_conv_param param = {
 		.min = (int *) table->extra1,
 		.max = (int *) table->extra2,
 	};
-	return do_proc_dointvec(table, write, filp, buffer, lenp, ppos,
+	return do_proc_dointvec(table, write, buffer, lenp, ppos,
 				do_proc_dointvec_minmax_conv, &param);
 }
 
 static int __do_proc_doulongvec_minmax(void *data, struct ctl_table *table, int write,
-				     struct file *filp,
 				     void __user *buffer,
 				     size_t *lenp, loff_t *ppos,
 				     unsigned long convmul,
@@ -2624,21 +2686,19 @@ static int __do_proc_doulongvec_minmax(void *data, struct ctl_table *table, int
 }
 
 static int do_proc_doulongvec_minmax(struct ctl_table *table, int write,
-				     struct file *filp,
 				     void __user *buffer,
 				     size_t *lenp, loff_t *ppos,
 				     unsigned long convmul,
 				     unsigned long convdiv)
 {
 	return __do_proc_doulongvec_minmax(table->data, table, write,
-			filp, buffer, lenp, ppos, convmul, convdiv);
+			buffer, lenp, ppos, convmul, convdiv);
 }
 
 /**
  * proc_doulongvec_minmax - read a vector of long integers with min/max values
  * @table: the sysctl table
  * @write: %TRUE if this is a write to the sysctl file
- * @filp: the file structure
  * @buffer: the user buffer
  * @lenp: the size of the user buffer
  * @ppos: file position
@@ -2651,17 +2711,16 @@ static int do_proc_doulongvec_minmax(struct ctl_table *table, int write,
  *
  * Returns 0 on success.
  */
-int proc_doulongvec_minmax(struct ctl_table *table, int write, struct file *filp,
+int proc_doulongvec_minmax(struct ctl_table *table, int write,
 			   void __user *buffer, size_t *lenp, loff_t *ppos)
 {
-    return do_proc_doulongvec_minmax(table, write, filp, buffer, lenp, ppos, 1l, 1l);
+    return do_proc_doulongvec_minmax(table, write, buffer, lenp, ppos, 1l, 1l);
 }
 
 /**
  * proc_doulongvec_ms_jiffies_minmax - read a vector of millisecond values with min/max values
  * @table: the sysctl table
  * @write: %TRUE if this is a write to the sysctl file
- * @filp: the file structure
  * @buffer: the user buffer
  * @lenp: the size of the user buffer
  * @ppos: file position
@@ -2676,11 +2735,10 @@ int proc_doulongvec_minmax(struct ctl_table *table, int write, struct file *filp
  * Returns 0 on success.
  */
 int proc_doulongvec_ms_jiffies_minmax(struct ctl_table *table, int write,
-				      struct file *filp,
 				      void __user *buffer,
 				      size_t *lenp, loff_t *ppos)
 {
-    return do_proc_doulongvec_minmax(table, write, filp, buffer,
+    return do_proc_doulongvec_minmax(table, write, buffer,
 				     lenp, ppos, HZ, 1000l);
 }
 
@@ -2756,7 +2814,6 @@ static int do_proc_dointvec_ms_jiffies_conv(int *negp, unsigned long *lvalp,
  * proc_dointvec_jiffies - read a vector of integers as seconds
  * @table: the sysctl table
  * @write: %TRUE if this is a write to the sysctl file
- * @filp: the file structure
  * @buffer: the user buffer
  * @lenp: the size of the user buffer
  * @ppos: file position
@@ -2768,10 +2825,10 @@ static int do_proc_dointvec_ms_jiffies_conv(int *negp, unsigned long *lvalp,
  *
  * Returns 0 on success.
  */
-int proc_dointvec_jiffies(struct ctl_table *table, int write, struct file *filp,
+int proc_dointvec_jiffies(struct ctl_table *table, int write,
 			  void __user *buffer, size_t *lenp, loff_t *ppos)
 {
-    return do_proc_dointvec(table,write,filp,buffer,lenp,ppos,
+    return do_proc_dointvec(table,write,buffer,lenp,ppos,
 		    	    do_proc_dointvec_jiffies_conv,NULL);
 }
 
@@ -2779,7 +2836,6 @@ int proc_dointvec_jiffies(struct ctl_table *table, int write, struct file *filp,
  * proc_dointvec_userhz_jiffies - read a vector of integers as 1/USER_HZ seconds
  * @table: the sysctl table
  * @write: %TRUE if this is a write to the sysctl file
- * @filp: the file structure
  * @buffer: the user buffer
  * @lenp: the size of the user buffer
  * @ppos: pointer to the file position
@@ -2791,10 +2847,10 @@ int proc_dointvec_jiffies(struct ctl_table *table, int write, struct file *filp,
  *
  * Returns 0 on success.
  */
-int proc_dointvec_userhz_jiffies(struct ctl_table *table, int write, struct file *filp,
+int proc_dointvec_userhz_jiffies(struct ctl_table *table, int write,
 				 void __user *buffer, size_t *lenp, loff_t *ppos)
 {
-    return do_proc_dointvec(table,write,filp,buffer,lenp,ppos,
+    return do_proc_dointvec(table,write,buffer,lenp,ppos,
 		    	    do_proc_dointvec_userhz_jiffies_conv,NULL);
 }
 
@@ -2802,7 +2858,6 @@ int proc_dointvec_userhz_jiffies(struct ctl_table *table, int write, struct file
  * proc_dointvec_ms_jiffies - read a vector of integers as 1 milliseconds
  * @table: the sysctl table
  * @write: %TRUE if this is a write to the sysctl file
- * @filp: the file structure
  * @buffer: the user buffer
  * @lenp: the size of the user buffer
  * @ppos: file position
@@ -2815,14 +2870,14 @@ int proc_dointvec_userhz_jiffies(struct ctl_table *table, int write, struct file
  *
  * Returns 0 on success.
  */
-int proc_dointvec_ms_jiffies(struct ctl_table *table, int write, struct file *filp,
+int proc_dointvec_ms_jiffies(struct ctl_table *table, int write,
 			     void __user *buffer, size_t *lenp, loff_t *ppos)
 {
-	return do_proc_dointvec(table, write, filp, buffer, lenp, ppos,
+	return do_proc_dointvec(table, write, buffer, lenp, ppos,
 				do_proc_dointvec_ms_jiffies_conv, NULL);
 }
 
-static int proc_do_cad_pid(struct ctl_table *table, int write, struct file *filp,
+static int proc_do_cad_pid(struct ctl_table *table, int write,
 			   void __user *buffer, size_t *lenp, loff_t *ppos)
 {
 	struct pid *new_pid;
@@ -2831,7 +2886,7 @@ static int proc_do_cad_pid(struct ctl_table *table, int write, struct file *filp
 
 	tmp = pid_vnr(cad_pid);
 
-	r = __do_proc_dointvec(&tmp, table, write, filp, buffer,
+	r = __do_proc_dointvec(&tmp, table, write, buffer,
 			       lenp, ppos, NULL, NULL);
 	if (r || !write)
 		return r;
@@ -2846,50 +2901,49 @@ static int proc_do_cad_pid(struct ctl_table *table, int write, struct file *filp
 
 #else /* CONFIG_PROC_FS */
 
-int proc_dostring(struct ctl_table *table, int write, struct file *filp,
+int proc_dostring(struct ctl_table *table, int write,
 		  void __user *buffer, size_t *lenp, loff_t *ppos)
 {
 	return -ENOSYS;
 }
 
-int proc_dointvec(struct ctl_table *table, int write, struct file *filp,
+int proc_dointvec(struct ctl_table *table, int write,
 		  void __user *buffer, size_t *lenp, loff_t *ppos)
 {
 	return -ENOSYS;
 }
 
-int proc_dointvec_minmax(struct ctl_table *table, int write, struct file *filp,
+int proc_dointvec_minmax(struct ctl_table *table, int write,
 		    void __user *buffer, size_t *lenp, loff_t *ppos)
 {
 	return -ENOSYS;
 }
 
-int proc_dointvec_jiffies(struct ctl_table *table, int write, struct file *filp,
+int proc_dointvec_jiffies(struct ctl_table *table, int write,
 		    void __user *buffer, size_t *lenp, loff_t *ppos)
 {
 	return -ENOSYS;
 }
 
-int proc_dointvec_userhz_jiffies(struct ctl_table *table, int write, struct file *filp,
+int proc_dointvec_userhz_jiffies(struct ctl_table *table, int write,
 		    void __user *buffer, size_t *lenp, loff_t *ppos)
 {
 	return -ENOSYS;
 }
 
-int proc_dointvec_ms_jiffies(struct ctl_table *table, int write, struct file *filp,
+int proc_dointvec_ms_jiffies(struct ctl_table *table, int write,
 			     void __user *buffer, size_t *lenp, loff_t *ppos)
 {
 	return -ENOSYS;
 }
 
-int proc_doulongvec_minmax(struct ctl_table *table, int write, struct file *filp,
+int proc_doulongvec_minmax(struct ctl_table *table, int write,
 		    void __user *buffer, size_t *lenp, loff_t *ppos)
 {
 	return -ENOSYS;
 }
 
 int proc_doulongvec_ms_jiffies_minmax(struct ctl_table *table, int write,
-				      struct file *filp,
 				      void __user *buffer,
 				      size_t *lenp, loff_t *ppos)
 {
diff --git a/kernel/sysctl_check.c b/kernel/sysctl_check.c
index b38423ca711a..b6e7aaea4604 100644
--- a/kernel/sysctl_check.c
+++ b/kernel/sysctl_check.c
@@ -1521,7 +1521,7 @@ int sysctl_check_table(struct nsproxy *namespaces, struct ctl_table *table)
 			if (!table->ctl_name && table->strategy)
 				set_fail(&fail, table, "Strategy without ctl_name");
 #endif
-#ifdef CONFIG_PROC_FS
+#ifdef CONFIG_PROC_SYSCTL
 			if (table->procname && !table->proc_handler)
 				set_fail(&fail, table, "No proc_handler");
 #endif
diff --git a/kernel/taskstats.c b/kernel/taskstats.c
index 888adbcca30c..ea8384d3caa7 100644
--- a/kernel/taskstats.c
+++ b/kernel/taskstats.c
@@ -108,7 +108,7 @@ static int prepare_reply(struct genl_info *info, u8 cmd, struct sk_buff **skbp,
 /*
  * Send taskstats data in @skb to listener with nl_pid @pid
  */
-static int send_reply(struct sk_buff *skb, pid_t pid)
+static int send_reply(struct sk_buff *skb, struct genl_info *info)
 {
 	struct genlmsghdr *genlhdr = nlmsg_data(nlmsg_hdr(skb));
 	void *reply = genlmsg_data(genlhdr);
@@ -120,7 +120,7 @@ static int send_reply(struct sk_buff *skb, pid_t pid)
 		return rc;
 	}
 
-	return genlmsg_unicast(skb, pid);
+	return genlmsg_reply(skb, info);
 }
 
 /*
@@ -150,7 +150,7 @@ static void send_cpu_listeners(struct sk_buff *skb,
 			if (!skb_next)
 				break;
 		}
-		rc = genlmsg_unicast(skb_cur, s->pid);
+		rc = genlmsg_unicast(&init_net, skb_cur, s->pid);
 		if (rc == -ECONNREFUSED) {
 			s->valid = 0;
 			delcount++;
@@ -418,7 +418,7 @@ static int cgroupstats_user_cmd(struct sk_buff *skb, struct genl_info *info)
 		goto err;
 	}
 
-	rc = send_reply(rep_skb, info->snd_pid);
+	rc = send_reply(rep_skb, info);
 
 err:
 	fput_light(file, fput_needed);
@@ -487,7 +487,7 @@ free_return_rc:
 	} else
 		goto err;
 
-	return send_reply(rep_skb, info->snd_pid);
+	return send_reply(rep_skb, info);
 err:
 	nlmsg_free(rep_skb);
 	return rc;
diff --git a/kernel/time.c b/kernel/time.c
index 29511943871a..2e2e469a7fec 100644
--- a/kernel/time.c
+++ b/kernel/time.c
@@ -370,13 +370,20 @@ EXPORT_SYMBOL(mktime);
  *	0 <= tv_nsec < NSEC_PER_SEC
  * For negative values only the tv_sec field is negative !
  */
-void set_normalized_timespec(struct timespec *ts, time_t sec, long nsec)
+void set_normalized_timespec(struct timespec *ts, time_t sec, s64 nsec)
 {
 	while (nsec >= NSEC_PER_SEC) {
+		/*
+		 * The following asm() prevents the compiler from
+		 * optimising this loop into a modulo operation. See
+		 * also __iter_div_u64_rem() in include/linux/time.h
+		 */
+		asm("" : "+rm"(nsec));
 		nsec -= NSEC_PER_SEC;
 		++sec;
 	}
 	while (nsec < 0) {
+		asm("" : "+rm"(nsec));
 		nsec += NSEC_PER_SEC;
 		--sec;
 	}
diff --git a/kernel/time/Makefile b/kernel/time/Makefile
index 0b0a6366c9d4..ee266620b06c 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 timecompare.o
+obj-y += timekeeping.o ntp.o clocksource.o jiffies.o timer_list.o timecompare.o timeconv.o
 
 obj-$(CONFIG_GENERIC_CLOCKEVENTS_BUILD)		+= clockevents.o
 obj-$(CONFIG_GENERIC_CLOCKEVENTS)		+= tick-common.o
diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c
index 7466cb811251..5e18c6ab2c6a 100644
--- a/kernel/time/clocksource.c
+++ b/kernel/time/clocksource.c
@@ -21,7 +21,6 @@
  *
  * TODO WishList:
  *   o Allow clocksource drivers to be unregistered
- *   o get rid of clocksource_jiffies extern
  */
 
 #include <linux/clocksource.h>
@@ -30,6 +29,7 @@
 #include <linux/module.h>
 #include <linux/sched.h> /* for spin_unlock_irq() using preempt_count() m68k */
 #include <linux/tick.h>
+#include <linux/kthread.h>
 
 void timecounter_init(struct timecounter *tc,
 		      const struct cyclecounter *cc,
@@ -107,50 +107,35 @@ u64 timecounter_cyc2time(struct timecounter *tc,
 }
 EXPORT_SYMBOL(timecounter_cyc2time);
 
-/* XXX - Would like a better way for initializing curr_clocksource */
-extern struct clocksource clocksource_jiffies;
-
 /*[Clocksource internal variables]---------
  * curr_clocksource:
- *	currently selected clocksource. Initialized to clocksource_jiffies.
- * next_clocksource:
- *	pending next selected clocksource.
+ *	currently selected clocksource.
  * clocksource_list:
  *	linked list with the registered clocksources
- * clocksource_lock:
- *	protects manipulations to curr_clocksource and next_clocksource
- *	and the clocksource_list
+ * clocksource_mutex:
+ *	protects manipulations to curr_clocksource and the clocksource_list
  * override_name:
  *	Name of the user-specified clocksource.
  */
-static struct clocksource *curr_clocksource = &clocksource_jiffies;
-static struct clocksource *next_clocksource;
-static struct clocksource *clocksource_override;
+static struct clocksource *curr_clocksource;
 static LIST_HEAD(clocksource_list);
-static DEFINE_SPINLOCK(clocksource_lock);
+static DEFINE_MUTEX(clocksource_mutex);
 static char override_name[32];
 static int finished_booting;
 
-/* clocksource_done_booting - Called near the end of core bootup
- *
- * Hack to avoid lots of clocksource churn at boot time.
- * We use fs_initcall because we want this to start before
- * device_initcall but after subsys_initcall.
- */
-static int __init clocksource_done_booting(void)
-{
-	finished_booting = 1;
-	return 0;
-}
-fs_initcall(clocksource_done_booting);
-
 #ifdef CONFIG_CLOCKSOURCE_WATCHDOG
+static void clocksource_watchdog_work(struct work_struct *work);
+
 static LIST_HEAD(watchdog_list);
 static struct clocksource *watchdog;
 static struct timer_list watchdog_timer;
+static DECLARE_WORK(watchdog_work, clocksource_watchdog_work);
 static DEFINE_SPINLOCK(watchdog_lock);
 static cycle_t watchdog_last;
-static unsigned long watchdog_resumed;
+static int watchdog_running;
+
+static int clocksource_watchdog_kthread(void *data);
+static void __clocksource_change_rating(struct clocksource *cs, int rating);
 
 /*
  * Interval: 0.5sec Threshold: 0.0625s
@@ -158,135 +143,249 @@ static unsigned long watchdog_resumed;
 #define WATCHDOG_INTERVAL (HZ >> 1)
 #define WATCHDOG_THRESHOLD (NSEC_PER_SEC >> 4)
 
-static void clocksource_ratewd(struct clocksource *cs, int64_t delta)
+static void clocksource_watchdog_work(struct work_struct *work)
 {
-	if (delta > -WATCHDOG_THRESHOLD && delta < WATCHDOG_THRESHOLD)
-		return;
+	/*
+	 * If kthread_run fails the next watchdog scan over the
+	 * watchdog_list will find the unstable clock again.
+	 */
+	kthread_run(clocksource_watchdog_kthread, NULL, "kwatchdog");
+}
+
+static void __clocksource_unstable(struct clocksource *cs)
+{
+	cs->flags &= ~(CLOCK_SOURCE_VALID_FOR_HRES | CLOCK_SOURCE_WATCHDOG);
+	cs->flags |= CLOCK_SOURCE_UNSTABLE;
+	if (finished_booting)
+		schedule_work(&watchdog_work);
+}
 
+static void clocksource_unstable(struct clocksource *cs, int64_t delta)
+{
 	printk(KERN_WARNING "Clocksource %s unstable (delta = %Ld ns)\n",
 	       cs->name, delta);
-	cs->flags &= ~(CLOCK_SOURCE_VALID_FOR_HRES | CLOCK_SOURCE_WATCHDOG);
-	clocksource_change_rating(cs, 0);
-	list_del(&cs->wd_list);
+	__clocksource_unstable(cs);
+}
+
+/**
+ * clocksource_mark_unstable - mark clocksource unstable via watchdog
+ * @cs:		clocksource to be marked unstable
+ *
+ * This function is called instead of clocksource_change_rating from
+ * cpu hotplug code to avoid a deadlock between the clocksource mutex
+ * and the cpu hotplug mutex. It defers the update of the clocksource
+ * to the watchdog thread.
+ */
+void clocksource_mark_unstable(struct clocksource *cs)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&watchdog_lock, flags);
+	if (!(cs->flags & CLOCK_SOURCE_UNSTABLE)) {
+		if (list_empty(&cs->wd_list))
+			list_add(&cs->wd_list, &watchdog_list);
+		__clocksource_unstable(cs);
+	}
+	spin_unlock_irqrestore(&watchdog_lock, flags);
 }
 
 static void clocksource_watchdog(unsigned long data)
 {
-	struct clocksource *cs, *tmp;
+	struct clocksource *cs;
 	cycle_t csnow, wdnow;
 	int64_t wd_nsec, cs_nsec;
-	int resumed;
+	int next_cpu;
 
 	spin_lock(&watchdog_lock);
-
-	resumed = test_and_clear_bit(0, &watchdog_resumed);
+	if (!watchdog_running)
+		goto out;
 
 	wdnow = watchdog->read(watchdog);
-	wd_nsec = cyc2ns(watchdog, (wdnow - watchdog_last) & watchdog->mask);
+	wd_nsec = clocksource_cyc2ns((wdnow - watchdog_last) & watchdog->mask,
+				     watchdog->mult, watchdog->shift);
 	watchdog_last = wdnow;
 
-	list_for_each_entry_safe(cs, tmp, &watchdog_list, wd_list) {
-		csnow = cs->read(cs);
+	list_for_each_entry(cs, &watchdog_list, wd_list) {
 
-		if (unlikely(resumed)) {
-			cs->wd_last = csnow;
+		/* Clocksource already marked unstable? */
+		if (cs->flags & CLOCK_SOURCE_UNSTABLE) {
+			if (finished_booting)
+				schedule_work(&watchdog_work);
 			continue;
 		}
 
-		/* Initialized ? */
+		csnow = cs->read(cs);
+
+		/* Clocksource initialized ? */
 		if (!(cs->flags & CLOCK_SOURCE_WATCHDOG)) {
-			if ((cs->flags & CLOCK_SOURCE_IS_CONTINUOUS) &&
-			    (watchdog->flags & CLOCK_SOURCE_IS_CONTINUOUS)) {
-				cs->flags |= CLOCK_SOURCE_VALID_FOR_HRES;
-				/*
-				 * We just marked the clocksource as
-				 * highres-capable, notify the rest of the
-				 * system as well so that we transition
-				 * into high-res mode:
-				 */
-				tick_clock_notify();
-			}
 			cs->flags |= CLOCK_SOURCE_WATCHDOG;
 			cs->wd_last = csnow;
-		} else {
-			cs_nsec = cyc2ns(cs, (csnow - cs->wd_last) & cs->mask);
-			cs->wd_last = csnow;
-			/* Check the delta. Might remove from the list ! */
-			clocksource_ratewd(cs, cs_nsec - wd_nsec);
+			continue;
 		}
-	}
 
-	if (!list_empty(&watchdog_list)) {
-		/*
-		 * Cycle through CPUs to check if the CPUs stay
-		 * synchronized to each other.
-		 */
-		int next_cpu = cpumask_next(raw_smp_processor_id(),
-					    cpu_online_mask);
+		/* Check the deviation from the watchdog clocksource. */
+		cs_nsec = clocksource_cyc2ns((csnow - cs->wd_last) &
+					     cs->mask, cs->mult, cs->shift);
+		cs->wd_last = csnow;
+		if (abs(cs_nsec - wd_nsec) > WATCHDOG_THRESHOLD) {
+			clocksource_unstable(cs, cs_nsec - wd_nsec);
+			continue;
+		}
 
-		if (next_cpu >= nr_cpu_ids)
-			next_cpu = cpumask_first(cpu_online_mask);
-		watchdog_timer.expires += WATCHDOG_INTERVAL;
-		add_timer_on(&watchdog_timer, next_cpu);
+		if (!(cs->flags & CLOCK_SOURCE_VALID_FOR_HRES) &&
+		    (cs->flags & CLOCK_SOURCE_IS_CONTINUOUS) &&
+		    (watchdog->flags & CLOCK_SOURCE_IS_CONTINUOUS)) {
+			cs->flags |= CLOCK_SOURCE_VALID_FOR_HRES;
+			/*
+			 * We just marked the clocksource as highres-capable,
+			 * notify the rest of the system as well so that we
+			 * transition into high-res mode:
+			 */
+			tick_clock_notify();
+		}
 	}
+
+	/*
+	 * Cycle through CPUs to check if the CPUs stay synchronized
+	 * to each other.
+	 */
+	next_cpu = cpumask_next(raw_smp_processor_id(), cpu_online_mask);
+	if (next_cpu >= nr_cpu_ids)
+		next_cpu = cpumask_first(cpu_online_mask);
+	watchdog_timer.expires += WATCHDOG_INTERVAL;
+	add_timer_on(&watchdog_timer, next_cpu);
+out:
 	spin_unlock(&watchdog_lock);
 }
+
+static inline void clocksource_start_watchdog(void)
+{
+	if (watchdog_running || !watchdog || list_empty(&watchdog_list))
+		return;
+	init_timer(&watchdog_timer);
+	watchdog_timer.function = clocksource_watchdog;
+	watchdog_last = watchdog->read(watchdog);
+	watchdog_timer.expires = jiffies + WATCHDOG_INTERVAL;
+	add_timer_on(&watchdog_timer, cpumask_first(cpu_online_mask));
+	watchdog_running = 1;
+}
+
+static inline void clocksource_stop_watchdog(void)
+{
+	if (!watchdog_running || (watchdog && !list_empty(&watchdog_list)))
+		return;
+	del_timer(&watchdog_timer);
+	watchdog_running = 0;
+}
+
+static inline void clocksource_reset_watchdog(void)
+{
+	struct clocksource *cs;
+
+	list_for_each_entry(cs, &watchdog_list, wd_list)
+		cs->flags &= ~CLOCK_SOURCE_WATCHDOG;
+}
+
 static void clocksource_resume_watchdog(void)
 {
-	set_bit(0, &watchdog_resumed);
+	unsigned long flags;
+
+	spin_lock_irqsave(&watchdog_lock, flags);
+	clocksource_reset_watchdog();
+	spin_unlock_irqrestore(&watchdog_lock, flags);
 }
 
-static void clocksource_check_watchdog(struct clocksource *cs)
+static void clocksource_enqueue_watchdog(struct clocksource *cs)
 {
-	struct clocksource *cse;
 	unsigned long flags;
 
 	spin_lock_irqsave(&watchdog_lock, flags);
 	if (cs->flags & CLOCK_SOURCE_MUST_VERIFY) {
-		int started = !list_empty(&watchdog_list);
-
+		/* cs is a clocksource to be watched. */
 		list_add(&cs->wd_list, &watchdog_list);
-		if (!started && watchdog) {
-			watchdog_last = watchdog->read(watchdog);
-			watchdog_timer.expires = jiffies + WATCHDOG_INTERVAL;
-			add_timer_on(&watchdog_timer,
-				     cpumask_first(cpu_online_mask));
-		}
+		cs->flags &= ~CLOCK_SOURCE_WATCHDOG;
 	} else {
+		/* cs is a watchdog. */
 		if (cs->flags & CLOCK_SOURCE_IS_CONTINUOUS)
 			cs->flags |= CLOCK_SOURCE_VALID_FOR_HRES;
-
+		/* Pick the best watchdog. */
 		if (!watchdog || cs->rating > watchdog->rating) {
-			if (watchdog)
-				del_timer(&watchdog_timer);
 			watchdog = cs;
-			init_timer(&watchdog_timer);
-			watchdog_timer.function = clocksource_watchdog;
-
 			/* Reset watchdog cycles */
-			list_for_each_entry(cse, &watchdog_list, wd_list)
-				cse->flags &= ~CLOCK_SOURCE_WATCHDOG;
-			/* Start if list is not empty */
-			if (!list_empty(&watchdog_list)) {
-				watchdog_last = watchdog->read(watchdog);
-				watchdog_timer.expires =
-					jiffies + WATCHDOG_INTERVAL;
-				add_timer_on(&watchdog_timer,
-					     cpumask_first(cpu_online_mask));
-			}
+			clocksource_reset_watchdog();
+		}
+	}
+	/* Check if the watchdog timer needs to be started. */
+	clocksource_start_watchdog();
+	spin_unlock_irqrestore(&watchdog_lock, flags);
+}
+
+static void clocksource_dequeue_watchdog(struct clocksource *cs)
+{
+	struct clocksource *tmp;
+	unsigned long flags;
+
+	spin_lock_irqsave(&watchdog_lock, flags);
+	if (cs->flags & CLOCK_SOURCE_MUST_VERIFY) {
+		/* cs is a watched clocksource. */
+		list_del_init(&cs->wd_list);
+	} else if (cs == watchdog) {
+		/* Reset watchdog cycles */
+		clocksource_reset_watchdog();
+		/* Current watchdog is removed. Find an alternative. */
+		watchdog = NULL;
+		list_for_each_entry(tmp, &clocksource_list, list) {
+			if (tmp == cs || tmp->flags & CLOCK_SOURCE_MUST_VERIFY)
+				continue;
+			if (!watchdog || tmp->rating > watchdog->rating)
+				watchdog = tmp;
 		}
 	}
+	cs->flags &= ~CLOCK_SOURCE_WATCHDOG;
+	/* Check if the watchdog timer needs to be stopped. */
+	clocksource_stop_watchdog();
 	spin_unlock_irqrestore(&watchdog_lock, flags);
 }
-#else
-static void clocksource_check_watchdog(struct clocksource *cs)
+
+static int clocksource_watchdog_kthread(void *data)
+{
+	struct clocksource *cs, *tmp;
+	unsigned long flags;
+	LIST_HEAD(unstable);
+
+	mutex_lock(&clocksource_mutex);
+	spin_lock_irqsave(&watchdog_lock, flags);
+	list_for_each_entry_safe(cs, tmp, &watchdog_list, wd_list)
+		if (cs->flags & CLOCK_SOURCE_UNSTABLE) {
+			list_del_init(&cs->wd_list);
+			list_add(&cs->wd_list, &unstable);
+		}
+	/* Check if the watchdog timer needs to be stopped. */
+	clocksource_stop_watchdog();
+	spin_unlock_irqrestore(&watchdog_lock, flags);
+
+	/* Needs to be done outside of watchdog lock */
+	list_for_each_entry_safe(cs, tmp, &unstable, wd_list) {
+		list_del_init(&cs->wd_list);
+		__clocksource_change_rating(cs, 0);
+	}
+	mutex_unlock(&clocksource_mutex);
+	return 0;
+}
+
+#else /* CONFIG_CLOCKSOURCE_WATCHDOG */
+
+static void clocksource_enqueue_watchdog(struct clocksource *cs)
 {
 	if (cs->flags & CLOCK_SOURCE_IS_CONTINUOUS)
 		cs->flags |= CLOCK_SOURCE_VALID_FOR_HRES;
 }
 
+static inline void clocksource_dequeue_watchdog(struct clocksource *cs) { }
 static inline void clocksource_resume_watchdog(void) { }
-#endif
+static inline int clocksource_watchdog_kthread(void *data) { return 0; }
+
+#endif /* CONFIG_CLOCKSOURCE_WATCHDOG */
 
 /**
  * clocksource_resume - resume the clocksource(s)
@@ -294,18 +393,12 @@ static inline void clocksource_resume_watchdog(void) { }
 void clocksource_resume(void)
 {
 	struct clocksource *cs;
-	unsigned long flags;
 
-	spin_lock_irqsave(&clocksource_lock, flags);
-
-	list_for_each_entry(cs, &clocksource_list, list) {
+	list_for_each_entry(cs, &clocksource_list, list)
 		if (cs->resume)
 			cs->resume();
-	}
 
 	clocksource_resume_watchdog();
-
-	spin_unlock_irqrestore(&clocksource_lock, flags);
 }
 
 /**
@@ -320,75 +413,94 @@ void clocksource_touch_watchdog(void)
 	clocksource_resume_watchdog();
 }
 
+#ifdef CONFIG_GENERIC_TIME
+
 /**
- * clocksource_get_next - Returns the selected clocksource
+ * clocksource_select - Select the best clocksource available
  *
+ * Private function. Must hold clocksource_mutex when called.
+ *
+ * Select the clocksource with the best rating, or the clocksource,
+ * which is selected by userspace override.
  */
-struct clocksource *clocksource_get_next(void)
+static void clocksource_select(void)
 {
-	unsigned long flags;
+	struct clocksource *best, *cs;
 
-	spin_lock_irqsave(&clocksource_lock, flags);
-	if (next_clocksource && finished_booting) {
-		curr_clocksource = next_clocksource;
-		next_clocksource = NULL;
+	if (!finished_booting || list_empty(&clocksource_list))
+		return;
+	/* First clocksource on the list has the best rating. */
+	best = list_first_entry(&clocksource_list, struct clocksource, list);
+	/* Check for the override clocksource. */
+	list_for_each_entry(cs, &clocksource_list, list) {
+		if (strcmp(cs->name, override_name) != 0)
+			continue;
+		/*
+		 * Check to make sure we don't switch to a non-highres
+		 * capable clocksource if the tick code is in oneshot
+		 * mode (highres or nohz)
+		 */
+		if (!(cs->flags & CLOCK_SOURCE_VALID_FOR_HRES) &&
+		    tick_oneshot_mode_active()) {
+			/* Override clocksource cannot be used. */
+			printk(KERN_WARNING "Override clocksource %s is not "
+			       "HRT compatible. Cannot switch while in "
+			       "HRT/NOHZ mode\n", cs->name);
+			override_name[0] = 0;
+		} else
+			/* Override clocksource can be used. */
+			best = cs;
+		break;
+	}
+	if (curr_clocksource != best) {
+		printk(KERN_INFO "Switching to clocksource %s\n", best->name);
+		curr_clocksource = best;
+		timekeeping_notify(curr_clocksource);
 	}
-	spin_unlock_irqrestore(&clocksource_lock, flags);
-
-	return curr_clocksource;
 }
 
-/**
- * select_clocksource - Selects the best registered clocksource.
- *
- * Private function. Must hold clocksource_lock when called.
+#else /* CONFIG_GENERIC_TIME */
+
+static inline void clocksource_select(void) { }
+
+#endif
+
+/*
+ * clocksource_done_booting - Called near the end of core bootup
  *
- * Select the clocksource with the best rating, or the clocksource,
- * which is selected by userspace override.
+ * Hack to avoid lots of clocksource churn at boot time.
+ * We use fs_initcall because we want this to start before
+ * device_initcall but after subsys_initcall.
  */
-static struct clocksource *select_clocksource(void)
+static int __init clocksource_done_booting(void)
 {
-	struct clocksource *next;
-
-	if (list_empty(&clocksource_list))
-		return NULL;
-
-	if (clocksource_override)
-		next = clocksource_override;
-	else
-		next = list_entry(clocksource_list.next, struct clocksource,
-				  list);
+	finished_booting = 1;
 
-	if (next == curr_clocksource)
-		return NULL;
+	/*
+	 * Run the watchdog first to eliminate unstable clock sources
+	 */
+	clocksource_watchdog_kthread(NULL);
 
-	return next;
+	mutex_lock(&clocksource_mutex);
+	clocksource_select();
+	mutex_unlock(&clocksource_mutex);
+	return 0;
 }
+fs_initcall(clocksource_done_booting);
 
 /*
  * Enqueue the clocksource sorted by rating
  */
-static int clocksource_enqueue(struct clocksource *c)
+static void clocksource_enqueue(struct clocksource *cs)
 {
-	struct list_head *tmp, *entry = &clocksource_list;
+	struct list_head *entry = &clocksource_list;
+	struct clocksource *tmp;
 
-	list_for_each(tmp, &clocksource_list) {
-		struct clocksource *cs;
-
-		cs = list_entry(tmp, struct clocksource, list);
-		if (cs == c)
-			return -EBUSY;
+	list_for_each_entry(tmp, &clocksource_list, list)
 		/* Keep track of the place, where to insert */
-		if (cs->rating >= c->rating)
-			entry = tmp;
-	}
-	list_add(&c->list, entry);
-
-	if (strlen(c->name) == strlen(override_name) &&
-	    !strcmp(c->name, override_name))
-		clocksource_override = c;
-
-	return 0;
+		if (tmp->rating >= cs->rating)
+			entry = &tmp->list;
+	list_add(&cs->list, entry);
 }
 
 /**
@@ -397,52 +509,48 @@ static int clocksource_enqueue(struct clocksource *c)
  *
  * Returns -EBUSY if registration fails, zero otherwise.
  */
-int clocksource_register(struct clocksource *c)
+int clocksource_register(struct clocksource *cs)
 {
-	unsigned long flags;
-	int ret;
-
-	spin_lock_irqsave(&clocksource_lock, flags);
-	ret = clocksource_enqueue(c);
-	if (!ret)
-		next_clocksource = select_clocksource();
-	spin_unlock_irqrestore(&clocksource_lock, flags);
-	if (!ret)
-		clocksource_check_watchdog(c);
-	return ret;
+	mutex_lock(&clocksource_mutex);
+	clocksource_enqueue(cs);
+	clocksource_select();
+	clocksource_enqueue_watchdog(cs);
+	mutex_unlock(&clocksource_mutex);
+	return 0;
 }
 EXPORT_SYMBOL(clocksource_register);
 
+static void __clocksource_change_rating(struct clocksource *cs, int rating)
+{
+	list_del(&cs->list);
+	cs->rating = rating;
+	clocksource_enqueue(cs);
+	clocksource_select();
+}
+
 /**
  * clocksource_change_rating - Change the rating of a registered clocksource
- *
  */
 void clocksource_change_rating(struct clocksource *cs, int rating)
 {
-	unsigned long flags;
-
-	spin_lock_irqsave(&clocksource_lock, flags);
-	list_del(&cs->list);
-	cs->rating = rating;
-	clocksource_enqueue(cs);
-	next_clocksource = select_clocksource();
-	spin_unlock_irqrestore(&clocksource_lock, flags);
+	mutex_lock(&clocksource_mutex);
+	__clocksource_change_rating(cs, rating);
+	mutex_unlock(&clocksource_mutex);
 }
+EXPORT_SYMBOL(clocksource_change_rating);
 
 /**
  * clocksource_unregister - remove a registered clocksource
  */
 void clocksource_unregister(struct clocksource *cs)
 {
-	unsigned long flags;
-
-	spin_lock_irqsave(&clocksource_lock, flags);
+	mutex_lock(&clocksource_mutex);
+	clocksource_dequeue_watchdog(cs);
 	list_del(&cs->list);
-	if (clocksource_override == cs)
-		clocksource_override = NULL;
-	next_clocksource = select_clocksource();
-	spin_unlock_irqrestore(&clocksource_lock, flags);
+	clocksource_select();
+	mutex_unlock(&clocksource_mutex);
 }
+EXPORT_SYMBOL(clocksource_unregister);
 
 #ifdef CONFIG_SYSFS
 /**
@@ -458,9 +566,9 @@ sysfs_show_current_clocksources(struct sys_device *dev,
 {
 	ssize_t count = 0;
 
-	spin_lock_irq(&clocksource_lock);
+	mutex_lock(&clocksource_mutex);
 	count = snprintf(buf, PAGE_SIZE, "%s\n", curr_clocksource->name);
-	spin_unlock_irq(&clocksource_lock);
+	mutex_unlock(&clocksource_mutex);
 
 	return count;
 }
@@ -478,9 +586,7 @@ static ssize_t sysfs_override_clocksource(struct sys_device *dev,
 					  struct sysdev_attribute *attr,
 					  const char *buf, size_t count)
 {
-	struct clocksource *ovr = NULL;
 	size_t ret = count;
-	int len;
 
 	/* strings from sysfs write are not 0 terminated! */
 	if (count >= sizeof(override_name))
@@ -490,44 +596,14 @@ static ssize_t sysfs_override_clocksource(struct sys_device *dev,
 	if (buf[count-1] == '\n')
 		count--;
 
-	spin_lock_irq(&clocksource_lock);
+	mutex_lock(&clocksource_mutex);
 
 	if (count > 0)
 		memcpy(override_name, buf, count);
 	override_name[count] = 0;
+	clocksource_select();
 
-	len = strlen(override_name);
-	if (len) {
-		struct clocksource *cs;
-
-		ovr = clocksource_override;
-		/* try to select it: */
-		list_for_each_entry(cs, &clocksource_list, list) {
-			if (strlen(cs->name) == len &&
-			    !strcmp(cs->name, override_name))
-				ovr = cs;
-		}
-	}
-
-	/*
-	 * Check to make sure we don't switch to a non-highres capable
-	 * clocksource if the tick code is in oneshot mode (highres or nohz)
-	 */
-	if (tick_oneshot_mode_active() && ovr &&
-	    !(ovr->flags & CLOCK_SOURCE_VALID_FOR_HRES)) {
-		printk(KERN_WARNING "%s clocksource is not HRT compatible. "
-			"Cannot switch while in HRT/NOHZ mode\n", ovr->name);
-		ovr = NULL;
-		override_name[0] = 0;
-	}
-
-	/* Reselect, when the override name has changed */
-	if (ovr != clocksource_override) {
-		clocksource_override = ovr;
-		next_clocksource = select_clocksource();
-	}
-
-	spin_unlock_irq(&clocksource_lock);
+	mutex_unlock(&clocksource_mutex);
 
 	return ret;
 }
@@ -547,7 +623,7 @@ sysfs_show_available_clocksources(struct sys_device *dev,
 	struct clocksource *src;
 	ssize_t count = 0;
 
-	spin_lock_irq(&clocksource_lock);
+	mutex_lock(&clocksource_mutex);
 	list_for_each_entry(src, &clocksource_list, list) {
 		/*
 		 * Don't show non-HRES clocksource if the tick code is
@@ -559,7 +635,7 @@ sysfs_show_available_clocksources(struct sys_device *dev,
 				  max((ssize_t)PAGE_SIZE - count, (ssize_t)0),
 				  "%s ", src->name);
 	}
-	spin_unlock_irq(&clocksource_lock);
+	mutex_unlock(&clocksource_mutex);
 
 	count += snprintf(buf + count,
 			  max((ssize_t)PAGE_SIZE - count, (ssize_t)0), "\n");
@@ -614,11 +690,10 @@ device_initcall(init_clocksource_sysfs);
  */
 static int __init boot_override_clocksource(char* str)
 {
-	unsigned long flags;
-	spin_lock_irqsave(&clocksource_lock, flags);
+	mutex_lock(&clocksource_mutex);
 	if (str)
 		strlcpy(override_name, str, sizeof(override_name));
-	spin_unlock_irqrestore(&clocksource_lock, flags);
+	mutex_unlock(&clocksource_mutex);
 	return 1;
 }
 
diff --git a/kernel/time/jiffies.c b/kernel/time/jiffies.c
index c3f6c30816e3..5404a8456909 100644
--- a/kernel/time/jiffies.c
+++ b/kernel/time/jiffies.c
@@ -61,7 +61,6 @@ struct clocksource clocksource_jiffies = {
 	.read		= jiffies_read,
 	.mask		= 0xffffffff, /*32bits*/
 	.mult		= NSEC_PER_JIFFY << JIFFIES_SHIFT, /* details above */
-	.mult_orig	= NSEC_PER_JIFFY << JIFFIES_SHIFT,
 	.shift		= JIFFIES_SHIFT,
 };
 
@@ -71,3 +70,8 @@ static int __init init_jiffies_clocksource(void)
 }
 
 core_initcall(init_jiffies_clocksource);
+
+struct clocksource * __init __weak clocksource_default_clock(void)
+{
+	return &clocksource_jiffies;
+}
diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c
index 7fc64375ff43..4800f933910e 100644
--- a/kernel/time/ntp.c
+++ b/kernel/time/ntp.c
@@ -194,8 +194,7 @@ static enum hrtimer_restart ntp_leap_second(struct hrtimer *timer)
 	case TIME_OK:
 		break;
 	case TIME_INS:
-		xtime.tv_sec--;
-		wall_to_monotonic.tv_sec++;
+		timekeeping_leap_insert(-1);
 		time_state = TIME_OOP;
 		printk(KERN_NOTICE
 			"Clock: inserting leap second 23:59:60 UTC\n");
@@ -203,9 +202,8 @@ static enum hrtimer_restart ntp_leap_second(struct hrtimer *timer)
 		res = HRTIMER_RESTART;
 		break;
 	case TIME_DEL:
-		xtime.tv_sec++;
+		timekeeping_leap_insert(1);
 		time_tai--;
-		wall_to_monotonic.tv_sec--;
 		time_state = TIME_WAIT;
 		printk(KERN_NOTICE
 			"Clock: deleting leap second 23:59:59 UTC\n");
@@ -219,7 +217,6 @@ static enum hrtimer_restart ntp_leap_second(struct hrtimer *timer)
 			time_state = TIME_OK;
 		break;
 	}
-	update_vsyscall(&xtime, clock);
 
 	write_sequnlock(&xtime_lock);
 
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index e0f59a21c061..89aed5933ed4 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -231,6 +231,13 @@ void tick_nohz_stop_sched_tick(int inidle)
 	if (!inidle && !ts->inidle)
 		goto end;
 
+	/*
+	 * Set ts->inidle unconditionally. Even if the system did not
+	 * switch to NOHZ mode the cpu frequency governers rely on the
+	 * update of the idle time accounting in tick_nohz_start_idle().
+	 */
+	ts->inidle = 1;
+
 	now = tick_nohz_start_idle(ts);
 
 	/*
@@ -248,8 +255,6 @@ void tick_nohz_stop_sched_tick(int inidle)
 	if (unlikely(ts->nohz_mode == NOHZ_MODE_INACTIVE))
 		goto end;
 
-	ts->inidle = 1;
-
 	if (need_resched())
 		goto end;
 
diff --git a/kernel/time/timeconv.c b/kernel/time/timeconv.c
new file mode 100644
index 000000000000..86628e755f38
--- /dev/null
+++ b/kernel/time/timeconv.c
@@ -0,0 +1,127 @@
+/*
+ * Copyright (C) 1993, 1994, 1995, 1996, 1997 Free Software Foundation, Inc.
+ * This file is part of the GNU C Library.
+ * Contributed by Paul Eggert (eggert@twinsun.com).
+ *
+ * The GNU C Library is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU Library General Public License as
+ * published by the Free Software Foundation; either version 2 of the
+ * License, or (at your option) any later version.
+ *
+ * The GNU C Library 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
+ * Library General Public License for more details.
+ *
+ * You should have received a copy of the GNU Library General Public
+ * License along with the GNU C Library; see the file COPYING.LIB.  If not,
+ * write to the Free Software Foundation, Inc., 59 Temple Place - Suite 330,
+ * Boston, MA 02111-1307, USA.
+ */
+
+/*
+ * Converts the calendar time to broken-down time representation
+ * Based on code from glibc-2.6
+ *
+ * 2009-7-14:
+ *   Moved from glibc-2.6 to kernel by Zhaolei<zhaolei@cn.fujitsu.com>
+ */
+
+#include <linux/time.h>
+#include <linux/module.h>
+
+/*
+ * Nonzero if YEAR is a leap year (every 4 years,
+ * except every 100th isn't, and every 400th is).
+ */
+static int __isleap(long year)
+{
+	return (year) % 4 == 0 && ((year) % 100 != 0 || (year) % 400 == 0);
+}
+
+/* do a mathdiv for long type */
+static long math_div(long a, long b)
+{
+	return a / b - (a % b < 0);
+}
+
+/* How many leap years between y1 and y2, y1 must less or equal to y2 */
+static long leaps_between(long y1, long y2)
+{
+	long leaps1 = math_div(y1 - 1, 4) - math_div(y1 - 1, 100)
+		+ math_div(y1 - 1, 400);
+	long leaps2 = math_div(y2 - 1, 4) - math_div(y2 - 1, 100)
+		+ math_div(y2 - 1, 400);
+	return leaps2 - leaps1;
+}
+
+/* How many days come before each month (0-12). */
+static const unsigned short __mon_yday[2][13] = {
+	/* Normal years. */
+	{0, 31, 59, 90, 120, 151, 181, 212, 243, 273, 304, 334, 365},
+	/* Leap years. */
+	{0, 31, 60, 91, 121, 152, 182, 213, 244, 274, 305, 335, 366}
+};
+
+#define SECS_PER_HOUR	(60 * 60)
+#define SECS_PER_DAY	(SECS_PER_HOUR * 24)
+
+/**
+ * time_to_tm - converts the calendar time to local broken-down time
+ *
+ * @totalsecs	the number of seconds elapsed since 00:00:00 on January 1, 1970,
+ *		Coordinated Universal Time (UTC).
+ * @offset	offset seconds adding to totalsecs.
+ * @result	pointer to struct tm variable to receive broken-down time
+ */
+void time_to_tm(time_t totalsecs, int offset, struct tm *result)
+{
+	long days, rem, y;
+	const unsigned short *ip;
+
+	days = totalsecs / SECS_PER_DAY;
+	rem = totalsecs % SECS_PER_DAY;
+	rem += offset;
+	while (rem < 0) {
+		rem += SECS_PER_DAY;
+		--days;
+	}
+	while (rem >= SECS_PER_DAY) {
+		rem -= SECS_PER_DAY;
+		++days;
+	}
+
+	result->tm_hour = rem / SECS_PER_HOUR;
+	rem %= SECS_PER_HOUR;
+	result->tm_min = rem / 60;
+	result->tm_sec = rem % 60;
+
+	/* January 1, 1970 was a Thursday. */
+	result->tm_wday = (4 + days) % 7;
+	if (result->tm_wday < 0)
+		result->tm_wday += 7;
+
+	y = 1970;
+
+	while (days < 0 || days >= (__isleap(y) ? 366 : 365)) {
+		/* Guess a corrected year, assuming 365 days per year. */
+		long yg = y + math_div(days, 365);
+
+		/* Adjust DAYS and Y to match the guessed year. */
+		days -= (yg - y) * 365 + leaps_between(y, yg);
+		y = yg;
+	}
+
+	result->tm_year = y - 1900;
+
+	result->tm_yday = days;
+
+	ip = __mon_yday[__isleap(y)];
+	for (y = 11; days < ip[y]; y--)
+		continue;
+	days -= ip[y];
+
+	result->tm_mon = y;
+	result->tm_mday = days + 1;
+}
+EXPORT_SYMBOL(time_to_tm);
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index e8c77d9c633a..c3a4e2907eaa 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -13,12 +13,123 @@
 #include <linux/percpu.h>
 #include <linux/init.h>
 #include <linux/mm.h>
+#include <linux/sched.h>
 #include <linux/sysdev.h>
 #include <linux/clocksource.h>
 #include <linux/jiffies.h>
 #include <linux/time.h>
 #include <linux/tick.h>
+#include <linux/stop_machine.h>
+
+/* Structure holding internal timekeeping values. */
+struct timekeeper {
+	/* Current clocksource used for timekeeping. */
+	struct clocksource *clock;
+	/* The shift value of the current clocksource. */
+	int	shift;
+
+	/* Number of clock cycles in one NTP interval. */
+	cycle_t cycle_interval;
+	/* Number of clock shifted nano seconds in one NTP interval. */
+	u64	xtime_interval;
+	/* Raw nano seconds accumulated per NTP interval. */
+	u32	raw_interval;
+
+	/* Clock shifted nano seconds remainder not stored in xtime.tv_nsec. */
+	u64	xtime_nsec;
+	/* Difference between accumulated time and NTP time in ntp
+	 * shifted nano seconds. */
+	s64	ntp_error;
+	/* Shift conversion between clock shifted nano seconds and
+	 * ntp shifted nano seconds. */
+	int	ntp_error_shift;
+	/* NTP adjusted clock multiplier */
+	u32	mult;
+};
+
+struct timekeeper timekeeper;
+
+/**
+ * timekeeper_setup_internals - Set up internals to use clocksource clock.
+ *
+ * @clock:		Pointer to clocksource.
+ *
+ * Calculates a fixed cycle/nsec interval for a given clocksource/adjustment
+ * pair and interval request.
+ *
+ * Unless you're the timekeeping code, you should not be using this!
+ */
+static void timekeeper_setup_internals(struct clocksource *clock)
+{
+	cycle_t interval;
+	u64 tmp;
+
+	timekeeper.clock = clock;
+	clock->cycle_last = clock->read(clock);
 
+	/* Do the ns -> cycle conversion first, using original mult */
+	tmp = NTP_INTERVAL_LENGTH;
+	tmp <<= clock->shift;
+	tmp += clock->mult/2;
+	do_div(tmp, clock->mult);
+	if (tmp == 0)
+		tmp = 1;
+
+	interval = (cycle_t) tmp;
+	timekeeper.cycle_interval = interval;
+
+	/* Go back from cycles -> shifted ns */
+	timekeeper.xtime_interval = (u64) interval * clock->mult;
+	timekeeper.raw_interval =
+		((u64) interval * clock->mult) >> clock->shift;
+
+	timekeeper.xtime_nsec = 0;
+	timekeeper.shift = clock->shift;
+
+	timekeeper.ntp_error = 0;
+	timekeeper.ntp_error_shift = NTP_SCALE_SHIFT - clock->shift;
+
+	/*
+	 * The timekeeper keeps its own mult values for the currently
+	 * active clocksource. These value will be adjusted via NTP
+	 * to counteract clock drifting.
+	 */
+	timekeeper.mult = clock->mult;
+}
+
+/* Timekeeper helper functions. */
+static inline s64 timekeeping_get_ns(void)
+{
+	cycle_t cycle_now, cycle_delta;
+	struct clocksource *clock;
+
+	/* read clocksource: */
+	clock = timekeeper.clock;
+	cycle_now = clock->read(clock);
+
+	/* calculate the delta since the last update_wall_time: */
+	cycle_delta = (cycle_now - clock->cycle_last) & clock->mask;
+
+	/* return delta convert to nanoseconds using ntp adjusted mult. */
+	return clocksource_cyc2ns(cycle_delta, timekeeper.mult,
+				  timekeeper.shift);
+}
+
+static inline s64 timekeeping_get_ns_raw(void)
+{
+	cycle_t cycle_now, cycle_delta;
+	struct clocksource *clock;
+
+	/* read clocksource: */
+	clock = timekeeper.clock;
+	cycle_now = clock->read(clock);
+
+	/* calculate the delta since the last update_wall_time: */
+	cycle_delta = (cycle_now - clock->cycle_last) & clock->mask;
+
+	/* return delta convert to nanoseconds using ntp adjusted mult. */
+	return clocksource_cyc2ns(cycle_delta, clock->mult, clock->shift);
+}
 
 /*
  * This read-write spinlock protects us from races in SMP while
@@ -44,7 +155,12 @@ __cacheline_aligned_in_smp DEFINE_SEQLOCK(xtime_lock);
  */
 struct timespec xtime __attribute__ ((aligned (16)));
 struct timespec wall_to_monotonic __attribute__ ((aligned (16)));
-static unsigned long total_sleep_time;		/* seconds */
+static struct timespec total_sleep_time;
+
+/*
+ * The raw monotonic time for the CLOCK_MONOTONIC_RAW posix clock.
+ */
+struct timespec raw_time;
 
 /* flag for if timekeeping is suspended */
 int __read_mostly timekeeping_suspended;
@@ -56,35 +172,44 @@ void update_xtime_cache(u64 nsec)
 	timespec_add_ns(&xtime_cache, nsec);
 }
 
-struct clocksource *clock;
-
+/* must hold xtime_lock */
+void timekeeping_leap_insert(int leapsecond)
+{
+	xtime.tv_sec += leapsecond;
+	wall_to_monotonic.tv_sec -= leapsecond;
+	update_vsyscall(&xtime, timekeeper.clock);
+}
 
 #ifdef CONFIG_GENERIC_TIME
+
 /**
- * clocksource_forward_now - update clock to the current time
+ * timekeeping_forward_now - update clock to the current time
  *
  * Forward the current clock to update its state since the last call to
  * update_wall_time(). This is useful before significant clock changes,
  * as it avoids having to deal with this time offset explicitly.
  */
-static void clocksource_forward_now(void)
+static void timekeeping_forward_now(void)
 {
 	cycle_t cycle_now, cycle_delta;
+	struct clocksource *clock;
 	s64 nsec;
 
-	cycle_now = clocksource_read(clock);
+	clock = timekeeper.clock;
+	cycle_now = clock->read(clock);
 	cycle_delta = (cycle_now - clock->cycle_last) & clock->mask;
 	clock->cycle_last = cycle_now;
 
-	nsec = cyc2ns(clock, cycle_delta);
+	nsec = clocksource_cyc2ns(cycle_delta, timekeeper.mult,
+				  timekeeper.shift);
 
 	/* If arch requires, add in gettimeoffset() */
 	nsec += arch_gettimeoffset();
 
 	timespec_add_ns(&xtime, nsec);
 
-	nsec = ((s64)cycle_delta * clock->mult_orig) >> clock->shift;
-	clock->raw_time.tv_nsec += nsec;
+	nsec = clocksource_cyc2ns(cycle_delta, clock->mult, clock->shift);
+	timespec_add_ns(&raw_time, nsec);
 }
 
 /**
@@ -95,7 +220,6 @@ static void clocksource_forward_now(void)
  */
 void getnstimeofday(struct timespec *ts)
 {
-	cycle_t cycle_now, cycle_delta;
 	unsigned long seq;
 	s64 nsecs;
 
@@ -105,15 +229,7 @@ void getnstimeofday(struct timespec *ts)
 		seq = read_seqbegin(&xtime_lock);
 
 		*ts = xtime;
-
-		/* read clocksource: */
-		cycle_now = clocksource_read(clock);
-
-		/* calculate the delta since the last update_wall_time: */
-		cycle_delta = (cycle_now - clock->cycle_last) & clock->mask;
-
-		/* convert to nanoseconds: */
-		nsecs = cyc2ns(clock, cycle_delta);
+		nsecs = timekeeping_get_ns();
 
 		/* If arch requires, add in gettimeoffset() */
 		nsecs += arch_gettimeoffset();
@@ -125,6 +241,57 @@ void getnstimeofday(struct timespec *ts)
 
 EXPORT_SYMBOL(getnstimeofday);
 
+ktime_t ktime_get(void)
+{
+	unsigned int seq;
+	s64 secs, nsecs;
+
+	WARN_ON(timekeeping_suspended);
+
+	do {
+		seq = read_seqbegin(&xtime_lock);
+		secs = xtime.tv_sec + wall_to_monotonic.tv_sec;
+		nsecs = xtime.tv_nsec + wall_to_monotonic.tv_nsec;
+		nsecs += timekeeping_get_ns();
+
+	} while (read_seqretry(&xtime_lock, seq));
+	/*
+	 * Use ktime_set/ktime_add_ns to create a proper ktime on
+	 * 32-bit architectures without CONFIG_KTIME_SCALAR.
+	 */
+	return ktime_add_ns(ktime_set(secs, 0), nsecs);
+}
+EXPORT_SYMBOL_GPL(ktime_get);
+
+/**
+ * ktime_get_ts - get the monotonic clock in timespec format
+ * @ts:		pointer to timespec variable
+ *
+ * The function calculates the monotonic clock from the realtime
+ * clock and the wall_to_monotonic offset and stores the result
+ * in normalized timespec format in the variable pointed to by @ts.
+ */
+void ktime_get_ts(struct timespec *ts)
+{
+	struct timespec tomono;
+	unsigned int seq;
+	s64 nsecs;
+
+	WARN_ON(timekeeping_suspended);
+
+	do {
+		seq = read_seqbegin(&xtime_lock);
+		*ts = xtime;
+		tomono = wall_to_monotonic;
+		nsecs = timekeeping_get_ns();
+
+	} while (read_seqretry(&xtime_lock, seq));
+
+	set_normalized_timespec(ts, ts->tv_sec + tomono.tv_sec,
+				ts->tv_nsec + tomono.tv_nsec + nsecs);
+}
+EXPORT_SYMBOL_GPL(ktime_get_ts);
+
 /**
  * do_gettimeofday - Returns the time of day in a timeval
  * @tv:		pointer to the timeval to be set
@@ -157,7 +324,7 @@ int do_settimeofday(struct timespec *tv)
 
 	write_seqlock_irqsave(&xtime_lock, flags);
 
-	clocksource_forward_now();
+	timekeeping_forward_now();
 
 	ts_delta.tv_sec = tv->tv_sec - xtime.tv_sec;
 	ts_delta.tv_nsec = tv->tv_nsec - xtime.tv_nsec;
@@ -167,10 +334,10 @@ int do_settimeofday(struct timespec *tv)
 
 	update_xtime_cache(0);
 
-	clock->error = 0;
+	timekeeper.ntp_error = 0;
 	ntp_clear();
 
-	update_vsyscall(&xtime, clock);
+	update_vsyscall(&xtime, timekeeper.clock);
 
 	write_sequnlock_irqrestore(&xtime_lock, flags);
 
@@ -187,44 +354,97 @@ EXPORT_SYMBOL(do_settimeofday);
  *
  * Accumulates current time interval and initializes new clocksource
  */
-static void change_clocksource(void)
+static int change_clocksource(void *data)
 {
 	struct clocksource *new, *old;
 
-	new = clocksource_get_next();
+	new = (struct clocksource *) data;
+
+	timekeeping_forward_now();
+	if (!new->enable || new->enable(new) == 0) {
+		old = timekeeper.clock;
+		timekeeper_setup_internals(new);
+		if (old->disable)
+			old->disable(old);
+	}
+	return 0;
+}
 
-	if (clock == new)
+/**
+ * timekeeping_notify - Install a new clock source
+ * @clock:		pointer to the clock source
+ *
+ * This function is called from clocksource.c after a new, better clock
+ * source has been registered. The caller holds the clocksource_mutex.
+ */
+void timekeeping_notify(struct clocksource *clock)
+{
+	if (timekeeper.clock == clock)
 		return;
+	stop_machine(change_clocksource, clock, NULL);
+	tick_clock_notify();
+}
 
-	clocksource_forward_now();
+#else /* GENERIC_TIME */
 
-	if (clocksource_enable(new))
-		return;
+static inline void timekeeping_forward_now(void) { }
 
-	new->raw_time = clock->raw_time;
-	old = clock;
-	clock = new;
-	clocksource_disable(old);
+/**
+ * ktime_get - get the monotonic time in ktime_t format
+ *
+ * returns the time in ktime_t format
+ */
+ktime_t ktime_get(void)
+{
+	struct timespec now;
 
-	clock->cycle_last = 0;
-	clock->cycle_last = clocksource_read(clock);
-	clock->error = 0;
-	clock->xtime_nsec = 0;
-	clocksource_calculate_interval(clock, NTP_INTERVAL_LENGTH);
+	ktime_get_ts(&now);
 
-	tick_clock_notify();
+	return timespec_to_ktime(now);
+}
+EXPORT_SYMBOL_GPL(ktime_get);
 
-	/*
-	 * We're holding xtime lock and waking up klogd would deadlock
-	 * us on enqueue.  So no printing!
-	printk(KERN_INFO "Time: %s clocksource has been installed.\n",
-	       clock->name);
-	 */
+/**
+ * ktime_get_ts - get the monotonic clock in timespec format
+ * @ts:		pointer to timespec variable
+ *
+ * The function calculates the monotonic clock from the realtime
+ * clock and the wall_to_monotonic offset and stores the result
+ * in normalized timespec format in the variable pointed to by @ts.
+ */
+void ktime_get_ts(struct timespec *ts)
+{
+	struct timespec tomono;
+	unsigned long seq;
+
+	do {
+		seq = read_seqbegin(&xtime_lock);
+		getnstimeofday(ts);
+		tomono = wall_to_monotonic;
+
+	} while (read_seqretry(&xtime_lock, seq));
+
+	set_normalized_timespec(ts, ts->tv_sec + tomono.tv_sec,
+				ts->tv_nsec + tomono.tv_nsec);
 }
-#else
-static inline void clocksource_forward_now(void) { }
-static inline void change_clocksource(void) { }
-#endif
+EXPORT_SYMBOL_GPL(ktime_get_ts);
+
+#endif /* !GENERIC_TIME */
+
+/**
+ * ktime_get_real - get the real (wall-) time in ktime_t format
+ *
+ * returns the time in ktime_t format
+ */
+ktime_t ktime_get_real(void)
+{
+	struct timespec now;
+
+	getnstimeofday(&now);
+
+	return timespec_to_ktime(now);
+}
+EXPORT_SYMBOL_GPL(ktime_get_real);
 
 /**
  * getrawmonotonic - Returns the raw monotonic time in a timespec
@@ -236,21 +456,11 @@ void getrawmonotonic(struct timespec *ts)
 {
 	unsigned long seq;
 	s64 nsecs;
-	cycle_t cycle_now, cycle_delta;
 
 	do {
 		seq = read_seqbegin(&xtime_lock);
-
-		/* read clocksource: */
-		cycle_now = clocksource_read(clock);
-
-		/* calculate the delta since the last update_wall_time: */
-		cycle_delta = (cycle_now - clock->cycle_last) & clock->mask;
-
-		/* convert to nanoseconds: */
-		nsecs = ((s64)cycle_delta * clock->mult_orig) >> clock->shift;
-
-		*ts = clock->raw_time;
+		nsecs = timekeeping_get_ns_raw();
+		*ts = raw_time;
 
 	} while (read_seqretry(&xtime_lock, seq));
 
@@ -270,7 +480,7 @@ int timekeeping_valid_for_hres(void)
 	do {
 		seq = read_seqbegin(&xtime_lock);
 
-		ret = clock->flags & CLOCK_SOURCE_VALID_FOR_HRES;
+		ret = timekeeper.clock->flags & CLOCK_SOURCE_VALID_FOR_HRES;
 
 	} while (read_seqretry(&xtime_lock, seq));
 
@@ -278,17 +488,33 @@ int timekeeping_valid_for_hres(void)
 }
 
 /**
- * read_persistent_clock -  Return time in seconds from the persistent clock.
+ * read_persistent_clock -  Return time from the persistent clock.
  *
  * Weak dummy function for arches that do not yet support it.
- * Returns seconds from epoch using the battery backed persistent clock.
- * Returns zero if unsupported.
+ * Reads the time from the battery backed persistent clock.
+ * Returns a timespec with tv_sec=0 and tv_nsec=0 if unsupported.
  *
  *  XXX - Do be sure to remove it once all arches implement it.
  */
-unsigned long __attribute__((weak)) read_persistent_clock(void)
+void __attribute__((weak)) read_persistent_clock(struct timespec *ts)
 {
-	return 0;
+	ts->tv_sec = 0;
+	ts->tv_nsec = 0;
+}
+
+/**
+ * read_boot_clock -  Return time of the system start.
+ *
+ * Weak dummy function for arches that do not yet support it.
+ * Function to read the exact time the system has been started.
+ * Returns a timespec with tv_sec=0 and tv_nsec=0 if unsupported.
+ *
+ *  XXX - Do be sure to remove it once all arches implement it.
+ */
+void __attribute__((weak)) read_boot_clock(struct timespec *ts)
+{
+	ts->tv_sec = 0;
+	ts->tv_nsec = 0;
 }
 
 /*
@@ -296,29 +522,40 @@ unsigned long __attribute__((weak)) read_persistent_clock(void)
  */
 void __init timekeeping_init(void)
 {
+	struct clocksource *clock;
 	unsigned long flags;
-	unsigned long sec = read_persistent_clock();
+	struct timespec now, boot;
+
+	read_persistent_clock(&now);
+	read_boot_clock(&boot);
 
 	write_seqlock_irqsave(&xtime_lock, flags);
 
 	ntp_init();
 
-	clock = clocksource_get_next();
-	clocksource_enable(clock);
-	clocksource_calculate_interval(clock, NTP_INTERVAL_LENGTH);
-	clock->cycle_last = clocksource_read(clock);
-
-	xtime.tv_sec = sec;
-	xtime.tv_nsec = 0;
+	clock = clocksource_default_clock();
+	if (clock->enable)
+		clock->enable(clock);
+	timekeeper_setup_internals(clock);
+
+	xtime.tv_sec = now.tv_sec;
+	xtime.tv_nsec = now.tv_nsec;
+	raw_time.tv_sec = 0;
+	raw_time.tv_nsec = 0;
+	if (boot.tv_sec == 0 && boot.tv_nsec == 0) {
+		boot.tv_sec = xtime.tv_sec;
+		boot.tv_nsec = xtime.tv_nsec;
+	}
 	set_normalized_timespec(&wall_to_monotonic,
-		-xtime.tv_sec, -xtime.tv_nsec);
+				-boot.tv_sec, -boot.tv_nsec);
 	update_xtime_cache(0);
-	total_sleep_time = 0;
+	total_sleep_time.tv_sec = 0;
+	total_sleep_time.tv_nsec = 0;
 	write_sequnlock_irqrestore(&xtime_lock, flags);
 }
 
 /* time in seconds when suspend began */
-static unsigned long timekeeping_suspend_time;
+static struct timespec timekeeping_suspend_time;
 
 /**
  * timekeeping_resume - Resumes the generic timekeeping subsystem.
@@ -331,24 +568,24 @@ static unsigned long timekeeping_suspend_time;
 static int timekeeping_resume(struct sys_device *dev)
 {
 	unsigned long flags;
-	unsigned long now = read_persistent_clock();
+	struct timespec ts;
+
+	read_persistent_clock(&ts);
 
 	clocksource_resume();
 
 	write_seqlock_irqsave(&xtime_lock, flags);
 
-	if (now && (now > timekeeping_suspend_time)) {
-		unsigned long sleep_length = now - timekeeping_suspend_time;
-
-		xtime.tv_sec += sleep_length;
-		wall_to_monotonic.tv_sec -= sleep_length;
-		total_sleep_time += sleep_length;
+	if (timespec_compare(&ts, &timekeeping_suspend_time) > 0) {
+		ts = timespec_sub(ts, timekeeping_suspend_time);
+		xtime = timespec_add_safe(xtime, ts);
+		wall_to_monotonic = timespec_sub(wall_to_monotonic, ts);
+		total_sleep_time = timespec_add_safe(total_sleep_time, ts);
 	}
 	update_xtime_cache(0);
 	/* re-base the last cycle value */
-	clock->cycle_last = 0;
-	clock->cycle_last = clocksource_read(clock);
-	clock->error = 0;
+	timekeeper.clock->cycle_last = timekeeper.clock->read(timekeeper.clock);
+	timekeeper.ntp_error = 0;
 	timekeeping_suspended = 0;
 	write_sequnlock_irqrestore(&xtime_lock, flags);
 
@@ -366,10 +603,10 @@ static int timekeeping_suspend(struct sys_device *dev, pm_message_t state)
 {
 	unsigned long flags;
 
-	timekeeping_suspend_time = read_persistent_clock();
+	read_persistent_clock(&timekeeping_suspend_time);
 
 	write_seqlock_irqsave(&xtime_lock, flags);
-	clocksource_forward_now();
+	timekeeping_forward_now();
 	timekeeping_suspended = 1;
 	write_sequnlock_irqrestore(&xtime_lock, flags);
 
@@ -404,7 +641,7 @@ device_initcall(timekeeping_init_device);
  * If the error is already larger, we look ahead even further
  * to compensate for late or lost adjustments.
  */
-static __always_inline int clocksource_bigadjust(s64 error, s64 *interval,
+static __always_inline int timekeeping_bigadjust(s64 error, s64 *interval,
 						 s64 *offset)
 {
 	s64 tick_error, i;
@@ -420,7 +657,7 @@ static __always_inline int clocksource_bigadjust(s64 error, s64 *interval,
 	 * here.  This is tuned so that an error of about 1 msec is adjusted
 	 * within about 1 sec (or 2^20 nsec in 2^SHIFT_HZ ticks).
 	 */
-	error2 = clock->error >> (NTP_SCALE_SHIFT + 22 - 2 * SHIFT_HZ);
+	error2 = timekeeper.ntp_error >> (NTP_SCALE_SHIFT + 22 - 2 * SHIFT_HZ);
 	error2 = abs(error2);
 	for (look_ahead = 0; error2 > 0; look_ahead++)
 		error2 >>= 2;
@@ -429,8 +666,8 @@ static __always_inline int clocksource_bigadjust(s64 error, s64 *interval,
 	 * Now calculate the error in (1 << look_ahead) ticks, but first
 	 * remove the single look ahead already included in the error.
 	 */
-	tick_error = tick_length >> (NTP_SCALE_SHIFT - clock->shift + 1);
-	tick_error -= clock->xtime_interval >> 1;
+	tick_error = tick_length >> (timekeeper.ntp_error_shift + 1);
+	tick_error -= timekeeper.xtime_interval >> 1;
 	error = ((error - tick_error) >> look_ahead) + tick_error;
 
 	/* Finally calculate the adjustment shift value.  */
@@ -455,18 +692,18 @@ static __always_inline int clocksource_bigadjust(s64 error, s64 *interval,
  * this is optimized for the most common adjustments of -1,0,1,
  * for other values we can do a bit more work.
  */
-static void clocksource_adjust(s64 offset)
+static void timekeeping_adjust(s64 offset)
 {
-	s64 error, interval = clock->cycle_interval;
+	s64 error, interval = timekeeper.cycle_interval;
 	int adj;
 
-	error = clock->error >> (NTP_SCALE_SHIFT - clock->shift - 1);
+	error = timekeeper.ntp_error >> (timekeeper.ntp_error_shift - 1);
 	if (error > interval) {
 		error >>= 2;
 		if (likely(error <= interval))
 			adj = 1;
 		else
-			adj = clocksource_bigadjust(error, &interval, &offset);
+			adj = timekeeping_bigadjust(error, &interval, &offset);
 	} else if (error < -interval) {
 		error >>= 2;
 		if (likely(error >= -interval)) {
@@ -474,15 +711,15 @@ static void clocksource_adjust(s64 offset)
 			interval = -interval;
 			offset = -offset;
 		} else
-			adj = clocksource_bigadjust(error, &interval, &offset);
+			adj = timekeeping_bigadjust(error, &interval, &offset);
 	} else
 		return;
 
-	clock->mult += adj;
-	clock->xtime_interval += interval;
-	clock->xtime_nsec -= offset;
-	clock->error -= (interval - offset) <<
-			(NTP_SCALE_SHIFT - clock->shift);
+	timekeeper.mult += adj;
+	timekeeper.xtime_interval += interval;
+	timekeeper.xtime_nsec -= offset;
+	timekeeper.ntp_error -= (interval - offset) <<
+				timekeeper.ntp_error_shift;
 }
 
 /**
@@ -492,53 +729,59 @@ static void clocksource_adjust(s64 offset)
  */
 void update_wall_time(void)
 {
+	struct clocksource *clock;
 	cycle_t offset;
+	u64 nsecs;
 
 	/* Make sure we're fully resumed: */
 	if (unlikely(timekeeping_suspended))
 		return;
 
+	clock = timekeeper.clock;
 #ifdef CONFIG_GENERIC_TIME
-	offset = (clocksource_read(clock) - clock->cycle_last) & clock->mask;
+	offset = (clock->read(clock) - clock->cycle_last) & clock->mask;
 #else
-	offset = clock->cycle_interval;
+	offset = timekeeper.cycle_interval;
 #endif
-	clock->xtime_nsec = (s64)xtime.tv_nsec << clock->shift;
+	timekeeper.xtime_nsec = (s64)xtime.tv_nsec << timekeeper.shift;
 
 	/* normally this loop will run just once, however in the
 	 * case of lost or late ticks, it will accumulate correctly.
 	 */
-	while (offset >= clock->cycle_interval) {
+	while (offset >= timekeeper.cycle_interval) {
+		u64 nsecps = (u64)NSEC_PER_SEC << timekeeper.shift;
+
 		/* accumulate one interval */
-		offset -= clock->cycle_interval;
-		clock->cycle_last += clock->cycle_interval;
+		offset -= timekeeper.cycle_interval;
+		clock->cycle_last += timekeeper.cycle_interval;
 
-		clock->xtime_nsec += clock->xtime_interval;
-		if (clock->xtime_nsec >= (u64)NSEC_PER_SEC << clock->shift) {
-			clock->xtime_nsec -= (u64)NSEC_PER_SEC << clock->shift;
+		timekeeper.xtime_nsec += timekeeper.xtime_interval;
+		if (timekeeper.xtime_nsec >= nsecps) {
+			timekeeper.xtime_nsec -= nsecps;
 			xtime.tv_sec++;
 			second_overflow();
 		}
 
-		clock->raw_time.tv_nsec += clock->raw_interval;
-		if (clock->raw_time.tv_nsec >= NSEC_PER_SEC) {
-			clock->raw_time.tv_nsec -= NSEC_PER_SEC;
-			clock->raw_time.tv_sec++;
+		raw_time.tv_nsec += timekeeper.raw_interval;
+		if (raw_time.tv_nsec >= NSEC_PER_SEC) {
+			raw_time.tv_nsec -= NSEC_PER_SEC;
+			raw_time.tv_sec++;
 		}
 
 		/* accumulate error between NTP and clock interval */
-		clock->error += tick_length;
-		clock->error -= clock->xtime_interval << (NTP_SCALE_SHIFT - clock->shift);
+		timekeeper.ntp_error += tick_length;
+		timekeeper.ntp_error -= timekeeper.xtime_interval <<
+					timekeeper.ntp_error_shift;
 	}
 
 	/* correct the clock when NTP error is too big */
-	clocksource_adjust(offset);
+	timekeeping_adjust(offset);
 
 	/*
 	 * Since in the loop above, we accumulate any amount of time
 	 * in xtime_nsec over a second into xtime.tv_sec, its possible for
 	 * xtime_nsec to be fairly small after the loop. Further, if we're
-	 * slightly speeding the clocksource up in clocksource_adjust(),
+	 * slightly speeding the clocksource up in timekeeping_adjust(),
 	 * its possible the required corrective factor to xtime_nsec could
 	 * cause it to underflow.
 	 *
@@ -550,24 +793,25 @@ void update_wall_time(void)
 	 * We'll correct this error next time through this function, when
 	 * xtime_nsec is not as small.
 	 */
-	if (unlikely((s64)clock->xtime_nsec < 0)) {
-		s64 neg = -(s64)clock->xtime_nsec;
-		clock->xtime_nsec = 0;
-		clock->error += neg << (NTP_SCALE_SHIFT - clock->shift);
+	if (unlikely((s64)timekeeper.xtime_nsec < 0)) {
+		s64 neg = -(s64)timekeeper.xtime_nsec;
+		timekeeper.xtime_nsec = 0;
+		timekeeper.ntp_error += neg << timekeeper.ntp_error_shift;
 	}
 
 	/* store full nanoseconds into xtime after rounding it up and
 	 * add the remainder to the error difference.
 	 */
-	xtime.tv_nsec = ((s64)clock->xtime_nsec >> clock->shift) + 1;
-	clock->xtime_nsec -= (s64)xtime.tv_nsec << clock->shift;
-	clock->error += clock->xtime_nsec << (NTP_SCALE_SHIFT - clock->shift);
+	xtime.tv_nsec =	((s64) timekeeper.xtime_nsec >> timekeeper.shift) + 1;
+	timekeeper.xtime_nsec -= (s64) xtime.tv_nsec << timekeeper.shift;
+	timekeeper.ntp_error +=	timekeeper.xtime_nsec <<
+				timekeeper.ntp_error_shift;
 
-	update_xtime_cache(cyc2ns(clock, offset));
+	nsecs = clocksource_cyc2ns(offset, timekeeper.mult, timekeeper.shift);
+	update_xtime_cache(nsecs);
 
 	/* check to see if there is a new clocksource to use */
-	change_clocksource();
-	update_vsyscall(&xtime, clock);
+	update_vsyscall(&xtime, timekeeper.clock);
 }
 
 /**
@@ -583,9 +827,12 @@ void update_wall_time(void)
  */
 void getboottime(struct timespec *ts)
 {
-	set_normalized_timespec(ts,
-		- (wall_to_monotonic.tv_sec + total_sleep_time),
-		- wall_to_monotonic.tv_nsec);
+	struct timespec boottime = {
+		.tv_sec = wall_to_monotonic.tv_sec + total_sleep_time.tv_sec,
+		.tv_nsec = wall_to_monotonic.tv_nsec + total_sleep_time.tv_nsec
+	};
+
+	set_normalized_timespec(ts, -boottime.tv_sec, -boottime.tv_nsec);
 }
 
 /**
@@ -594,7 +841,7 @@ void getboottime(struct timespec *ts)
  */
 void monotonic_to_bootbased(struct timespec *ts)
 {
-	ts->tv_sec += total_sleep_time;
+	*ts = timespec_add_safe(*ts, total_sleep_time);
 }
 
 unsigned long get_seconds(void)
@@ -603,6 +850,10 @@ unsigned long get_seconds(void)
 }
 EXPORT_SYMBOL(get_seconds);
 
+struct timespec __current_kernel_time(void)
+{
+	return xtime_cache;
+}
 
 struct timespec current_kernel_time(void)
 {
@@ -618,3 +869,20 @@ struct timespec current_kernel_time(void)
 	return now;
 }
 EXPORT_SYMBOL(current_kernel_time);
+
+struct timespec get_monotonic_coarse(void)
+{
+	struct timespec now, mono;
+	unsigned long seq;
+
+	do {
+		seq = read_seqbegin(&xtime_lock);
+
+		now = xtime_cache;
+		mono = wall_to_monotonic;
+	} while (read_seqretry(&xtime_lock, seq));
+
+	set_normalized_timespec(&now, now.tv_sec + mono.tv_sec,
+				now.tv_nsec + mono.tv_nsec);
+	return now;
+}
diff --git a/kernel/time/timer_list.c b/kernel/time/timer_list.c
index fddd69d16e03..1b5b7aa2fdfd 100644
--- a/kernel/time/timer_list.c
+++ b/kernel/time/timer_list.c
@@ -275,7 +275,7 @@ static int timer_list_open(struct inode *inode, struct file *filp)
 	return single_open(filp, timer_list_show, NULL);
 }
 
-static struct file_operations timer_list_fops = {
+static const struct file_operations timer_list_fops = {
 	.open		= timer_list_open,
 	.read		= seq_read,
 	.llseek		= seq_lseek,
diff --git a/kernel/time/timer_stats.c b/kernel/time/timer_stats.c
index 4cde8b9c716f..ee5681f8d7ec 100644
--- a/kernel/time/timer_stats.c
+++ b/kernel/time/timer_stats.c
@@ -395,7 +395,7 @@ static int tstats_open(struct inode *inode, struct file *filp)
 	return single_open(filp, tstats_show, NULL);
 }
 
-static struct file_operations tstats_fops = {
+static const struct file_operations tstats_fops = {
 	.open		= tstats_open,
 	.read		= seq_read,
 	.write		= tstats_write,
diff --git a/kernel/timer.c b/kernel/timer.c
index a7f07d5a6241..5db5a8d26811 100644
--- a/kernel/timer.c
+++ b/kernel/timer.c
@@ -37,7 +37,7 @@
 #include <linux/delay.h>
 #include <linux/tick.h>
 #include <linux/kallsyms.h>
-#include <linux/perf_counter.h>
+#include <linux/perf_event.h>
 #include <linux/sched.h>
 
 #include <asm/uaccess.h>
@@ -46,6 +46,9 @@
 #include <asm/timex.h>
 #include <asm/io.h>
 
+#define CREATE_TRACE_POINTS
+#include <trace/events/timer.h>
+
 u64 jiffies_64 __cacheline_aligned_in_smp = INITIAL_JIFFIES;
 
 EXPORT_SYMBOL(jiffies_64);
@@ -72,6 +75,7 @@ struct tvec_base {
 	spinlock_t lock;
 	struct timer_list *running_timer;
 	unsigned long timer_jiffies;
+	unsigned long next_timer;
 	struct tvec_root tv1;
 	struct tvec tv2;
 	struct tvec tv3;
@@ -520,6 +524,25 @@ static inline void debug_timer_activate(struct timer_list *timer) { }
 static inline void debug_timer_deactivate(struct timer_list *timer) { }
 #endif
 
+static inline void debug_init(struct timer_list *timer)
+{
+	debug_timer_init(timer);
+	trace_timer_init(timer);
+}
+
+static inline void
+debug_activate(struct timer_list *timer, unsigned long expires)
+{
+	debug_timer_activate(timer);
+	trace_timer_start(timer, expires);
+}
+
+static inline void debug_deactivate(struct timer_list *timer)
+{
+	debug_timer_deactivate(timer);
+	trace_timer_cancel(timer);
+}
+
 static void __init_timer(struct timer_list *timer,
 			 const char *name,
 			 struct lock_class_key *key)
@@ -548,7 +571,7 @@ void init_timer_key(struct timer_list *timer,
 		    const char *name,
 		    struct lock_class_key *key)
 {
-	debug_timer_init(timer);
+	debug_init(timer);
 	__init_timer(timer, name, key);
 }
 EXPORT_SYMBOL(init_timer_key);
@@ -567,7 +590,7 @@ static inline void detach_timer(struct timer_list *timer,
 {
 	struct list_head *entry = &timer->entry;
 
-	debug_timer_deactivate(timer);
+	debug_deactivate(timer);
 
 	__list_del(entry->prev, entry->next);
 	if (clear_pending)
@@ -622,13 +645,16 @@ __mod_timer(struct timer_list *timer, unsigned long expires,
 
 	if (timer_pending(timer)) {
 		detach_timer(timer, 0);
+		if (timer->expires == base->next_timer &&
+		    !tbase_get_deferrable(timer->base))
+			base->next_timer = base->timer_jiffies;
 		ret = 1;
 	} else {
 		if (pending_only)
 			goto out_unlock;
 	}
 
-	debug_timer_activate(timer);
+	debug_activate(timer, expires);
 
 	new_base = __get_cpu_var(tvec_bases);
 
@@ -663,6 +689,9 @@ __mod_timer(struct timer_list *timer, unsigned long expires,
 	}
 
 	timer->expires = expires;
+	if (time_before(timer->expires, base->next_timer) &&
+	    !tbase_get_deferrable(timer->base))
+		base->next_timer = timer->expires;
 	internal_add_timer(base, timer);
 
 out_unlock:
@@ -780,7 +809,10 @@ void add_timer_on(struct timer_list *timer, int cpu)
 	BUG_ON(timer_pending(timer) || !timer->function);
 	spin_lock_irqsave(&base->lock, flags);
 	timer_set_base(timer, base);
-	debug_timer_activate(timer);
+	debug_activate(timer, timer->expires);
+	if (time_before(timer->expires, base->next_timer) &&
+	    !tbase_get_deferrable(timer->base))
+		base->next_timer = timer->expires;
 	internal_add_timer(base, timer);
 	/*
 	 * Check whether the other CPU is idle and needs to be
@@ -817,6 +849,9 @@ int del_timer(struct timer_list *timer)
 		base = lock_timer_base(timer, &flags);
 		if (timer_pending(timer)) {
 			detach_timer(timer, 1);
+			if (timer->expires == base->next_timer &&
+			    !tbase_get_deferrable(timer->base))
+				base->next_timer = base->timer_jiffies;
 			ret = 1;
 		}
 		spin_unlock_irqrestore(&base->lock, flags);
@@ -850,6 +885,9 @@ int try_to_del_timer_sync(struct timer_list *timer)
 	ret = 0;
 	if (timer_pending(timer)) {
 		detach_timer(timer, 1);
+		if (timer->expires == base->next_timer &&
+		    !tbase_get_deferrable(timer->base))
+			base->next_timer = base->timer_jiffies;
 		ret = 1;
 	}
 out:
@@ -984,7 +1022,9 @@ static inline void __run_timers(struct tvec_base *base)
 				 */
 				lock_map_acquire(&lockdep_map);
 
+				trace_timer_expire_entry(timer);
 				fn(data);
+				trace_timer_expire_exit(timer);
 
 				lock_map_release(&lockdep_map);
 
@@ -1007,8 +1047,8 @@ static inline void __run_timers(struct tvec_base *base)
 #ifdef CONFIG_NO_HZ
 /*
  * Find out when the next timer event is due to happen. This
- * is used on S/390 to stop all activity when a cpus is idle.
- * This functions needs to be called disabled.
+ * is used on S/390 to stop all activity when a CPU is idle.
+ * This function needs to be called with interrupts disabled.
  */
 static unsigned long __next_timer_interrupt(struct tvec_base *base)
 {
@@ -1134,7 +1174,9 @@ unsigned long get_next_timer_interrupt(unsigned long now)
 	unsigned long expires;
 
 	spin_lock(&base->lock);
-	expires = __next_timer_interrupt(base);
+	if (time_before_eq(base->next_timer, base->timer_jiffies))
+		base->next_timer = __next_timer_interrupt(base);
+	expires = base->next_timer;
 	spin_unlock(&base->lock);
 
 	if (time_before_eq(expires, now))
@@ -1156,8 +1198,7 @@ void update_process_times(int user_tick)
 	/* Note: this timer irq context must be accounted for as well. */
 	account_process_tick(p, user_tick);
 	run_local_timers();
-	if (rcu_pending(cpu))
-		rcu_check_callbacks(cpu, user_tick);
+	rcu_check_callbacks(cpu, user_tick);
 	printk_tick();
 	scheduler_tick();
 	run_posix_cpu_timers(p);
@@ -1170,7 +1211,7 @@ static void run_timer_softirq(struct softirq_action *h)
 {
 	struct tvec_base *base = __get_cpu_var(tvec_bases);
 
-	perf_counter_do_pending();
+	perf_event_do_pending();
 
 	hrtimer_run_pending();
 
@@ -1523,6 +1564,7 @@ static int __cpuinit init_timers_cpu(int cpu)
 		INIT_LIST_HEAD(base->tv1.vec + j);
 
 	base->timer_jiffies = jiffies;
+	base->next_timer = base->timer_jiffies;
 	return 0;
 }
 
@@ -1535,6 +1577,9 @@ static void migrate_timer_list(struct tvec_base *new_base, struct list_head *hea
 		timer = list_first_entry(head, struct timer_list, entry);
 		detach_timer(timer, 0);
 		timer_set_base(timer, new_base);
+		if (time_before(timer->expires, new_base->next_timer) &&
+		    !tbase_get_deferrable(timer->base))
+			new_base->next_timer = timer->expires;
 		internal_add_timer(new_base, timer);
 	}
 }
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index 019f380fd764..b416512ad17f 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -11,12 +11,18 @@ config NOP_TRACER
 
 config HAVE_FTRACE_NMI_ENTER
 	bool
+	help
+	  See Documentation/trace/ftrace-implementation.txt
 
 config HAVE_FUNCTION_TRACER
 	bool
+	help
+	  See Documentation/trace/ftrace-implementation.txt
 
 config HAVE_FUNCTION_GRAPH_TRACER
 	bool
+	help
+	  See Documentation/trace/ftrace-implementation.txt
 
 config HAVE_FUNCTION_GRAPH_FP_TEST
 	bool
@@ -28,21 +34,25 @@ config HAVE_FUNCTION_GRAPH_FP_TEST
 config HAVE_FUNCTION_TRACE_MCOUNT_TEST
 	bool
 	help
-	 This gets selected when the arch tests the function_trace_stop
-	 variable at the mcount call site. Otherwise, this variable
-	 is tested by the called function.
+	  See Documentation/trace/ftrace-implementation.txt
 
 config HAVE_DYNAMIC_FTRACE
 	bool
+	help
+	  See Documentation/trace/ftrace-implementation.txt
 
 config HAVE_FTRACE_MCOUNT_RECORD
 	bool
+	help
+	  See Documentation/trace/ftrace-implementation.txt
 
 config HAVE_HW_BRANCH_TRACER
 	bool
 
-config HAVE_FTRACE_SYSCALLS
+config HAVE_SYSCALL_TRACEPOINTS
 	bool
+	help
+	  See Documentation/trace/ftrace-implementation.txt
 
 config TRACER_MAX_TRACE
 	bool
@@ -60,15 +70,20 @@ config EVENT_TRACING
 	bool
 
 config CONTEXT_SWITCH_TRACER
-	select MARKERS
 	bool
 
+config RING_BUFFER_ALLOW_SWAP
+	bool
+	help
+	 Allow the use of ring_buffer_swap_cpu.
+	 Adds a very slight overhead to tracing when enabled.
+
 # All tracer options should select GENERIC_TRACER. For those options that are
 # enabled by all tracers (context switch and event tracer) they select TRACING.
 # This allows those options to appear when no other tracer is selected. But the
 # options do not appear when something else selects it. We need the two options
 # GENERIC_TRACER and TRACING to avoid circular dependencies to accomplish the
-# hidding of the automatic options options.
+# hidding of the automatic options.
 
 config TRACING
 	bool
@@ -147,6 +162,7 @@ config IRQSOFF_TRACER
 	select TRACE_IRQFLAGS
 	select GENERIC_TRACER
 	select TRACER_MAX_TRACE
+	select RING_BUFFER_ALLOW_SWAP
 	help
 	  This option measures the time spent in irqs-off critical
 	  sections, with microsecond accuracy.
@@ -168,6 +184,7 @@ config PREEMPT_TRACER
 	depends on PREEMPT
 	select GENERIC_TRACER
 	select TRACER_MAX_TRACE
+	select RING_BUFFER_ALLOW_SWAP
 	help
 	  This option measures the time spent in preemption off critical
 	  sections, with microsecond accuracy.
@@ -211,7 +228,7 @@ config ENABLE_DEFAULT_TRACERS
 
 config FTRACE_SYSCALLS
 	bool "Trace syscalls"
-	depends on HAVE_FTRACE_SYSCALLS
+	depends on HAVE_SYSCALL_TRACEPOINTS
 	select GENERIC_TRACER
 	select KALLSYMS
 	help
@@ -462,6 +479,18 @@ config FTRACE_STARTUP_TEST
 	  functioning properly. It will do tests on all the configured
 	  tracers of ftrace.
 
+config EVENT_TRACE_TEST_SYSCALLS
+	bool "Run selftest on syscall events"
+	depends on FTRACE_STARTUP_TEST
+	help
+	 This option will also enable testing every syscall event.
+	 It only enables the event and disables it and runs various loads
+	 with the event enabled. This adds a bit more time for kernel boot
+	 up since it runs this on every system call defined.
+
+	 TBD - enable a way to actually call the syscalls as we test their
+	       events
+
 config MMIOTRACE
 	bool "Memory mapped IO tracing"
 	depends on HAVE_MMIOTRACE_SUPPORT && PCI
diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile
index 844164dca90a..26f03ac07c2b 100644
--- a/kernel/trace/Makefile
+++ b/kernel/trace/Makefile
@@ -42,7 +42,6 @@ obj-$(CONFIG_BOOT_TRACER) += trace_boot.o
 obj-$(CONFIG_FUNCTION_GRAPH_TRACER) += trace_functions_graph.o
 obj-$(CONFIG_TRACE_BRANCH_PROFILING) += trace_branch.o
 obj-$(CONFIG_HW_BRANCH_TRACER) += trace_hw_branches.o
-obj-$(CONFIG_POWER_TRACER) += trace_power.o
 obj-$(CONFIG_KMEMTRACE) += kmemtrace.o
 obj-$(CONFIG_WORKQUEUE_TRACER) += trace_workqueue.o
 obj-$(CONFIG_BLK_DEV_IO_TRACE) += blktrace.o
@@ -54,5 +53,6 @@ obj-$(CONFIG_EVENT_TRACING) += trace_export.o
 obj-$(CONFIG_FTRACE_SYSCALLS) += trace_syscalls.o
 obj-$(CONFIG_EVENT_PROFILE) += trace_event_profile.o
 obj-$(CONFIG_EVENT_TRACING) += trace_events_filter.o
+obj-$(CONFIG_EVENT_TRACING) += power-traces.o
 
 libftrace-y := ftrace.o
diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c
index 7a34cb563fec..d9d6206e0b14 100644
--- a/kernel/trace/blktrace.c
+++ b/kernel/trace/blktrace.c
@@ -65,13 +65,15 @@ static void trace_note(struct blk_trace *bt, pid_t pid, int action,
 {
 	struct blk_io_trace *t;
 	struct ring_buffer_event *event = NULL;
+	struct ring_buffer *buffer = NULL;
 	int pc = 0;
 	int cpu = smp_processor_id();
 	bool blk_tracer = blk_tracer_enabled;
 
 	if (blk_tracer) {
+		buffer = blk_tr->buffer;
 		pc = preempt_count();
-		event = trace_buffer_lock_reserve(blk_tr, TRACE_BLK,
+		event = trace_buffer_lock_reserve(buffer, TRACE_BLK,
 						  sizeof(*t) + len,
 						  0, pc);
 		if (!event)
@@ -96,7 +98,7 @@ record_it:
 		memcpy((void *) t + sizeof(*t), data, len);
 
 		if (blk_tracer)
-			trace_buffer_unlock_commit(blk_tr, event, 0, pc);
+			trace_buffer_unlock_commit(buffer, event, 0, pc);
 	}
 }
 
@@ -179,6 +181,7 @@ static void __blk_add_trace(struct blk_trace *bt, sector_t sector, int bytes,
 {
 	struct task_struct *tsk = current;
 	struct ring_buffer_event *event = NULL;
+	struct ring_buffer *buffer = NULL;
 	struct blk_io_trace *t;
 	unsigned long flags = 0;
 	unsigned long *sequence;
@@ -204,8 +207,9 @@ static void __blk_add_trace(struct blk_trace *bt, sector_t sector, int bytes,
 	if (blk_tracer) {
 		tracing_record_cmdline(current);
 
+		buffer = blk_tr->buffer;
 		pc = preempt_count();
-		event = trace_buffer_lock_reserve(blk_tr, TRACE_BLK,
+		event = trace_buffer_lock_reserve(buffer, TRACE_BLK,
 						  sizeof(*t) + pdu_len,
 						  0, pc);
 		if (!event)
@@ -252,7 +256,7 @@ record_it:
 			memcpy((void *) t + sizeof(*t), pdu_data, pdu_len);
 
 		if (blk_tracer) {
-			trace_buffer_unlock_commit(blk_tr, event, 0, pc);
+			trace_buffer_unlock_commit(buffer, event, 0, pc);
 			return;
 		}
 	}
@@ -852,6 +856,37 @@ static void blk_add_trace_remap(struct request_queue *q, struct bio *bio,
 }
 
 /**
+ * blk_add_trace_rq_remap - Add a trace for a request-remap operation
+ * @q:		queue the io is for
+ * @rq:		the source request
+ * @dev:	target device
+ * @from:	source sector
+ *
+ * Description:
+ *     Device mapper remaps request to other devices.
+ *     Add a trace for that action.
+ *
+ **/
+static void blk_add_trace_rq_remap(struct request_queue *q,
+				   struct request *rq, dev_t dev,
+				   sector_t from)
+{
+	struct blk_trace *bt = q->blk_trace;
+	struct blk_io_trace_remap r;
+
+	if (likely(!bt))
+		return;
+
+	r.device_from = cpu_to_be32(dev);
+	r.device_to   = cpu_to_be32(disk_devt(rq->rq_disk));
+	r.sector_from = cpu_to_be64(from);
+
+	__blk_add_trace(bt, blk_rq_pos(rq), blk_rq_bytes(rq),
+			rq_data_dir(rq), BLK_TA_REMAP, !!rq->errors,
+			sizeof(r), &r);
+}
+
+/**
  * blk_add_driver_data - Add binary message with driver-specific data
  * @q:		queue the io is for
  * @rq:		io request
@@ -918,10 +953,13 @@ static void blk_register_tracepoints(void)
 	WARN_ON(ret);
 	ret = register_trace_block_remap(blk_add_trace_remap);
 	WARN_ON(ret);
+	ret = register_trace_block_rq_remap(blk_add_trace_rq_remap);
+	WARN_ON(ret);
 }
 
 static void blk_unregister_tracepoints(void)
 {
+	unregister_trace_block_rq_remap(blk_add_trace_rq_remap);
 	unregister_trace_block_remap(blk_add_trace_remap);
 	unregister_trace_block_split(blk_add_trace_split);
 	unregister_trace_block_unplug_io(blk_add_trace_unplug_io);
@@ -1653,6 +1691,11 @@ int blk_trace_init_sysfs(struct device *dev)
 	return sysfs_create_group(&dev->kobj, &blk_trace_attr_group);
 }
 
+void blk_trace_remove_sysfs(struct device *dev)
+{
+	sysfs_remove_group(&dev->kobj, &blk_trace_attr_group);
+}
+
 #endif /* CONFIG_BLK_DEV_IO_TRACE */
 
 #ifdef CONFIG_EVENT_TRACING
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 25edd5cc5935..6dc4e5ef7a01 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -225,7 +225,11 @@ static void ftrace_update_pid_func(void)
 	if (ftrace_trace_function == ftrace_stub)
 		return;
 
+#ifdef CONFIG_HAVE_FUNCTION_TRACE_MCOUNT_TEST
 	func = ftrace_trace_function;
+#else
+	func = __ftrace_trace_function;
+#endif
 
 	if (ftrace_pid_trace) {
 		set_ftrace_pid_function(func);
@@ -736,7 +740,7 @@ ftrace_profile_write(struct file *filp, const char __user *ubuf,
  out:
 	mutex_unlock(&ftrace_profile_lock);
 
-	filp->f_pos += cnt;
+	*ppos += cnt;
 
 	return cnt;
 }
@@ -1016,71 +1020,35 @@ static int
 __ftrace_replace_code(struct dyn_ftrace *rec, int enable)
 {
 	unsigned long ftrace_addr;
-	unsigned long ip, fl;
+	unsigned long flag = 0UL;
 
 	ftrace_addr = (unsigned long)FTRACE_ADDR;
 
-	ip = rec->ip;
-
 	/*
-	 * If this record is not to be traced and
-	 * it is not enabled then do nothing.
+	 * If this record is not to be traced or we want to disable it,
+	 * then disable it.
 	 *
-	 * If this record is not to be traced and
-	 * it is enabled then disable it.
+	 * If we want to enable it and filtering is off, then enable it.
 	 *
+	 * If we want to enable it and filtering is on, enable it only if
+	 * it's filtered
 	 */
-	if (rec->flags & FTRACE_FL_NOTRACE) {
-		if (rec->flags & FTRACE_FL_ENABLED)
-			rec->flags &= ~FTRACE_FL_ENABLED;
-		else
-			return 0;
-
-	} else if (ftrace_filtered && enable) {
-		/*
-		 * Filtering is on:
-		 */
-
-		fl = rec->flags & (FTRACE_FL_FILTER | FTRACE_FL_ENABLED);
-
-		/* Record is filtered and enabled, do nothing */
-		if (fl == (FTRACE_FL_FILTER | FTRACE_FL_ENABLED))
-			return 0;
-
-		/* Record is not filtered or enabled, do nothing */
-		if (!fl)
-			return 0;
-
-		/* Record is not filtered but enabled, disable it */
-		if (fl == FTRACE_FL_ENABLED)
-			rec->flags &= ~FTRACE_FL_ENABLED;
-		else
-		/* Otherwise record is filtered but not enabled, enable it */
-			rec->flags |= FTRACE_FL_ENABLED;
-	} else {
-		/* Disable or not filtered */
-
-		if (enable) {
-			/* if record is enabled, do nothing */
-			if (rec->flags & FTRACE_FL_ENABLED)
-				return 0;
-
-			rec->flags |= FTRACE_FL_ENABLED;
-
-		} else {
+	if (enable && !(rec->flags & FTRACE_FL_NOTRACE)) {
+		if (!ftrace_filtered || (rec->flags & FTRACE_FL_FILTER))
+			flag = FTRACE_FL_ENABLED;
+	}
 
-			/* if record is not enabled, do nothing */
-			if (!(rec->flags & FTRACE_FL_ENABLED))
-				return 0;
+	/* If the state of this record hasn't changed, then do nothing */
+	if ((rec->flags & FTRACE_FL_ENABLED) == flag)
+		return 0;
 
-			rec->flags &= ~FTRACE_FL_ENABLED;
-		}
+	if (flag) {
+		rec->flags |= FTRACE_FL_ENABLED;
+		return ftrace_make_call(rec, ftrace_addr);
 	}
 
-	if (rec->flags & FTRACE_FL_ENABLED)
-		return ftrace_make_call(rec, ftrace_addr);
-	else
-		return ftrace_make_nop(NULL, rec, ftrace_addr);
+	rec->flags &= ~FTRACE_FL_ENABLED;
+	return ftrace_make_nop(NULL, rec, ftrace_addr);
 }
 
 static void ftrace_replace_code(int enable)
@@ -1110,14 +1078,9 @@ static void ftrace_replace_code(int enable)
 		failed = __ftrace_replace_code(rec, enable);
 		if (failed) {
 			rec->flags |= FTRACE_FL_FAILED;
-			if ((system_state == SYSTEM_BOOTING) ||
-			    !core_kernel_text(rec->ip)) {
-				ftrace_free_rec(rec);
-				} else {
-				ftrace_bug(failed, rec->ip);
-					/* Stop processing */
-					return;
-				}
+			ftrace_bug(failed, rec->ip);
+			/* Stop processing */
+			return;
 		}
 	} while_for_each_ftrace_rec();
 }
@@ -1359,11 +1322,10 @@ static int __init ftrace_dyn_table_alloc(unsigned long num_to_init)
 
 enum {
 	FTRACE_ITER_FILTER	= (1 << 0),
-	FTRACE_ITER_CONT	= (1 << 1),
-	FTRACE_ITER_NOTRACE	= (1 << 2),
-	FTRACE_ITER_FAILURES	= (1 << 3),
-	FTRACE_ITER_PRINTALL	= (1 << 4),
-	FTRACE_ITER_HASH	= (1 << 5),
+	FTRACE_ITER_NOTRACE	= (1 << 1),
+	FTRACE_ITER_FAILURES	= (1 << 2),
+	FTRACE_ITER_PRINTALL	= (1 << 3),
+	FTRACE_ITER_HASH	= (1 << 4),
 };
 
 #define FTRACE_BUFF_MAX (KSYM_SYMBOL_LEN+4) /* room for wildcards */
@@ -1373,9 +1335,7 @@ struct ftrace_iterator {
 	int			hidx;
 	int			idx;
 	unsigned		flags;
-	unsigned char		buffer[FTRACE_BUFF_MAX+1];
-	unsigned		buffer_idx;
-	unsigned		filtered;
+	struct trace_parser	parser;
 };
 
 static void *
@@ -1438,18 +1398,13 @@ static int t_hash_show(struct seq_file *m, void *v)
 {
 	struct ftrace_func_probe *rec;
 	struct hlist_node *hnd = v;
-	char str[KSYM_SYMBOL_LEN];
 
 	rec = hlist_entry(hnd, struct ftrace_func_probe, node);
 
 	if (rec->ops->print)
 		return rec->ops->print(m, rec->ip, rec->ops, rec->data);
 
-	kallsyms_lookup(rec->ip, NULL, NULL, NULL, str);
-	seq_printf(m, "%s:", str);
-
-	kallsyms_lookup((unsigned long)rec->ops->func, NULL, NULL, NULL, str);
-	seq_printf(m, "%s", str);
+	seq_printf(m, "%ps:%ps", (void *)rec->ip, (void *)rec->ops->func);
 
 	if (rec->data)
 		seq_printf(m, ":%p", rec->data);
@@ -1547,7 +1502,6 @@ static int t_show(struct seq_file *m, void *v)
 {
 	struct ftrace_iterator *iter = m->private;
 	struct dyn_ftrace *rec = v;
-	char str[KSYM_SYMBOL_LEN];
 
 	if (iter->flags & FTRACE_ITER_HASH)
 		return t_hash_show(m, v);
@@ -1560,14 +1514,12 @@ static int t_show(struct seq_file *m, void *v)
 	if (!rec)
 		return 0;
 
-	kallsyms_lookup(rec->ip, NULL, NULL, NULL, str);
-
-	seq_printf(m, "%s\n", str);
+	seq_printf(m, "%ps\n", (void *)rec->ip);
 
 	return 0;
 }
 
-static struct seq_operations show_ftrace_seq_ops = {
+static const struct seq_operations show_ftrace_seq_ops = {
 	.start = t_start,
 	.next = t_next,
 	.stop = t_stop,
@@ -1601,17 +1553,6 @@ ftrace_avail_open(struct inode *inode, struct file *file)
 	return ret;
 }
 
-int ftrace_avail_release(struct inode *inode, struct file *file)
-{
-	struct seq_file *m = (struct seq_file *)file->private_data;
-	struct ftrace_iterator *iter = m->private;
-
-	seq_release(inode, file);
-	kfree(iter);
-
-	return 0;
-}
-
 static int
 ftrace_failures_open(struct inode *inode, struct file *file)
 {
@@ -1660,6 +1601,11 @@ ftrace_regex_open(struct inode *inode, struct file *file, int enable)
 	if (!iter)
 		return -ENOMEM;
 
+	if (trace_parser_get_init(&iter->parser, FTRACE_BUFF_MAX)) {
+		kfree(iter);
+		return -ENOMEM;
+	}
+
 	mutex_lock(&ftrace_regex_lock);
 	if ((file->f_mode & FMODE_WRITE) &&
 	    (file->f_flags & O_TRUNC))
@@ -1674,8 +1620,10 @@ ftrace_regex_open(struct inode *inode, struct file *file, int enable)
 		if (!ret) {
 			struct seq_file *m = file->private_data;
 			m->private = iter;
-		} else
+		} else {
+			trace_parser_put(&iter->parser);
 			kfree(iter);
+		}
 	} else
 		file->private_data = iter;
 	mutex_unlock(&ftrace_regex_lock);
@@ -2115,9 +2063,9 @@ __unregister_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops,
 	int i, len = 0;
 	char *search;
 
-	if (glob && (strcmp(glob, "*") || !strlen(glob)))
+	if (glob && (strcmp(glob, "*") == 0 || !strlen(glob)))
 		glob = NULL;
-	else {
+	else if (glob) {
 		int not;
 
 		type = ftrace_setup_glob(glob, strlen(glob), &search, &not);
@@ -2252,11 +2200,10 @@ ftrace_regex_write(struct file *file, const char __user *ubuf,
 		   size_t cnt, loff_t *ppos, int enable)
 {
 	struct ftrace_iterator *iter;
-	char ch;
-	size_t read = 0;
-	ssize_t ret;
+	struct trace_parser *parser;
+	ssize_t ret, read;
 
-	if (!cnt || cnt < 0)
+	if (!cnt)
 		return 0;
 
 	mutex_lock(&ftrace_regex_lock);
@@ -2267,71 +2214,21 @@ ftrace_regex_write(struct file *file, const char __user *ubuf,
 	} else
 		iter = file->private_data;
 
-	if (!*ppos) {
-		iter->flags &= ~FTRACE_ITER_CONT;
-		iter->buffer_idx = 0;
-	}
-
-	ret = get_user(ch, ubuf++);
-	if (ret)
-		goto out;
-	read++;
-	cnt--;
-
-	/*
-	 * If the parser haven't finished with the last write,
-	 * continue reading the user input without skipping spaces.
-	 */
-	if (!(iter->flags & FTRACE_ITER_CONT)) {
-		/* skip white space */
-		while (cnt && isspace(ch)) {
-			ret = get_user(ch, ubuf++);
-			if (ret)
-				goto out;
-			read++;
-			cnt--;
-		}
-
-		/* only spaces were written */
-		if (isspace(ch)) {
-			*ppos += read;
-			ret = read;
-			goto out;
-		}
-
-		iter->buffer_idx = 0;
-	}
+	parser = &iter->parser;
+	read = trace_get_user(parser, ubuf, cnt, ppos);
 
-	while (cnt && !isspace(ch)) {
-		if (iter->buffer_idx < FTRACE_BUFF_MAX)
-			iter->buffer[iter->buffer_idx++] = ch;
-		else {
-			ret = -EINVAL;
-			goto out;
-		}
-		ret = get_user(ch, ubuf++);
+	if (read >= 0 && trace_parser_loaded(parser) &&
+	    !trace_parser_cont(parser)) {
+		ret = ftrace_process_regex(parser->buffer,
+					   parser->idx, enable);
 		if (ret)
-			goto out;
-		read++;
-		cnt--;
-	}
+			goto out_unlock;
 
-	if (isspace(ch)) {
-		iter->filtered++;
-		iter->buffer[iter->buffer_idx] = 0;
-		ret = ftrace_process_regex(iter->buffer,
-					   iter->buffer_idx, enable);
-		if (ret)
-			goto out;
-		iter->buffer_idx = 0;
-	} else {
-		iter->flags |= FTRACE_ITER_CONT;
-		iter->buffer[iter->buffer_idx++] = ch;
+		trace_parser_clear(parser);
 	}
 
-	*ppos += read;
 	ret = read;
- out:
+out_unlock:
 	mutex_unlock(&ftrace_regex_lock);
 
 	return ret;
@@ -2438,6 +2335,7 @@ ftrace_regex_release(struct inode *inode, struct file *file, int enable)
 {
 	struct seq_file *m = (struct seq_file *)file->private_data;
 	struct ftrace_iterator *iter;
+	struct trace_parser *parser;
 
 	mutex_lock(&ftrace_regex_lock);
 	if (file->f_mode & FMODE_READ) {
@@ -2447,10 +2345,10 @@ ftrace_regex_release(struct inode *inode, struct file *file, int enable)
 	} else
 		iter = file->private_data;
 
-	if (iter->buffer_idx) {
-		iter->filtered++;
-		iter->buffer[iter->buffer_idx] = 0;
-		ftrace_match_records(iter->buffer, iter->buffer_idx, enable);
+	parser = &iter->parser;
+	if (trace_parser_loaded(parser)) {
+		parser->buffer[parser->idx] = 0;
+		ftrace_match_records(parser->buffer, parser->idx, enable);
 	}
 
 	mutex_lock(&ftrace_lock);
@@ -2458,7 +2356,9 @@ ftrace_regex_release(struct inode *inode, struct file *file, int enable)
 		ftrace_run_update_code(FTRACE_ENABLE_CALLS);
 	mutex_unlock(&ftrace_lock);
 
+	trace_parser_put(parser);
 	kfree(iter);
+
 	mutex_unlock(&ftrace_regex_lock);
 	return 0;
 }
@@ -2479,14 +2379,14 @@ static const struct file_operations ftrace_avail_fops = {
 	.open = ftrace_avail_open,
 	.read = seq_read,
 	.llseek = seq_lseek,
-	.release = ftrace_avail_release,
+	.release = seq_release_private,
 };
 
 static const struct file_operations ftrace_failures_fops = {
 	.open = ftrace_failures_open,
 	.read = seq_read,
 	.llseek = seq_lseek,
-	.release = ftrace_avail_release,
+	.release = seq_release_private,
 };
 
 static const struct file_operations ftrace_filter_fops = {
@@ -2515,11 +2415,9 @@ unsigned long ftrace_graph_funcs[FTRACE_GRAPH_MAX_FUNCS] __read_mostly;
 static void *
 __g_next(struct seq_file *m, loff_t *pos)
 {
-	unsigned long *array = m->private;
-
 	if (*pos >= ftrace_graph_count)
 		return NULL;
-	return &array[*pos];
+	return &ftrace_graph_funcs[*pos];
 }
 
 static void *
@@ -2548,7 +2446,6 @@ static void g_stop(struct seq_file *m, void *p)
 static int g_show(struct seq_file *m, void *v)
 {
 	unsigned long *ptr = v;
-	char str[KSYM_SYMBOL_LEN];
 
 	if (!ptr)
 		return 0;
@@ -2558,14 +2455,12 @@ static int g_show(struct seq_file *m, void *v)
 		return 0;
 	}
 
-	kallsyms_lookup(*ptr, NULL, NULL, NULL, str);
-
-	seq_printf(m, "%s\n", str);
+	seq_printf(m, "%ps\n", (void *)*ptr);
 
 	return 0;
 }
 
-static struct seq_operations ftrace_graph_seq_ops = {
+static const struct seq_operations ftrace_graph_seq_ops = {
 	.start = g_start,
 	.next = g_next,
 	.stop = g_stop,
@@ -2586,16 +2481,10 @@ ftrace_graph_open(struct inode *inode, struct file *file)
 		ftrace_graph_count = 0;
 		memset(ftrace_graph_funcs, 0, sizeof(ftrace_graph_funcs));
 	}
+	mutex_unlock(&graph_lock);
 
-	if (file->f_mode & FMODE_READ) {
+	if (file->f_mode & FMODE_READ)
 		ret = seq_open(file, &ftrace_graph_seq_ops);
-		if (!ret) {
-			struct seq_file *m = file->private_data;
-			m->private = ftrace_graph_funcs;
-		}
-	} else
-		file->private_data = ftrace_graph_funcs;
-	mutex_unlock(&graph_lock);
 
 	return ret;
 }
@@ -2663,12 +2552,8 @@ static ssize_t
 ftrace_graph_write(struct file *file, const char __user *ubuf,
 		   size_t cnt, loff_t *ppos)
 {
-	unsigned char buffer[FTRACE_BUFF_MAX+1];
-	unsigned long *array;
-	size_t read = 0;
-	ssize_t ret;
-	int index = 0;
-	char ch;
+	struct trace_parser parser;
+	ssize_t read, ret;
 
 	if (!cnt || cnt < 0)
 		return 0;
@@ -2677,60 +2562,31 @@ ftrace_graph_write(struct file *file, const char __user *ubuf,
 
 	if (ftrace_graph_count >= FTRACE_GRAPH_MAX_FUNCS) {
 		ret = -EBUSY;
-		goto out;
+		goto out_unlock;
 	}
 
-	if (file->f_mode & FMODE_READ) {
-		struct seq_file *m = file->private_data;
-		array = m->private;
-	} else
-		array = file->private_data;
-
-	ret = get_user(ch, ubuf++);
-	if (ret)
-		goto out;
-	read++;
-	cnt--;
-
-	/* skip white space */
-	while (cnt && isspace(ch)) {
-		ret = get_user(ch, ubuf++);
-		if (ret)
-			goto out;
-		read++;
-		cnt--;
+	if (trace_parser_get_init(&parser, FTRACE_BUFF_MAX)) {
+		ret = -ENOMEM;
+		goto out_unlock;
 	}
 
-	if (isspace(ch)) {
-		*ppos += read;
-		ret = read;
-		goto out;
-	}
+	read = trace_get_user(&parser, ubuf, cnt, ppos);
 
-	while (cnt && !isspace(ch)) {
-		if (index < FTRACE_BUFF_MAX)
-			buffer[index++] = ch;
-		else {
-			ret = -EINVAL;
-			goto out;
-		}
-		ret = get_user(ch, ubuf++);
+	if (read >= 0 && trace_parser_loaded((&parser))) {
+		parser.buffer[parser.idx] = 0;
+
+		/* we allow only one expression at a time */
+		ret = ftrace_set_func(ftrace_graph_funcs, &ftrace_graph_count,
+					parser.buffer);
 		if (ret)
-			goto out;
-		read++;
-		cnt--;
+			goto out_free;
 	}
-	buffer[index] = 0;
-
-	/* we allow only one expression at a time */
-	ret = ftrace_set_func(array, &ftrace_graph_count, buffer);
-	if (ret)
-		goto out;
-
-	file->f_pos += read;
 
 	ret = read;
- out:
+
+out_free:
+	trace_parser_put(&parser);
+out_unlock:
 	mutex_unlock(&graph_lock);
 
 	return ret;
@@ -2801,19 +2657,17 @@ static int ftrace_convert_nops(struct module *mod,
 }
 
 #ifdef CONFIG_MODULES
-void ftrace_release(void *start, void *end)
+void ftrace_release_mod(struct module *mod)
 {
 	struct dyn_ftrace *rec;
 	struct ftrace_page *pg;
-	unsigned long s = (unsigned long)start;
-	unsigned long e = (unsigned long)end;
 
-	if (ftrace_disabled || !start || start == end)
+	if (ftrace_disabled)
 		return;
 
 	mutex_lock(&ftrace_lock);
 	do_for_each_ftrace_rec(pg, rec) {
-		if ((rec->ip >= s) && (rec->ip < e)) {
+		if (within_module_core(rec->ip, mod)) {
 			/*
 			 * rec->ip is changed in ftrace_free_rec()
 			 * It should not between s and e if record was freed.
@@ -2845,9 +2699,7 @@ static int ftrace_module_notify(struct notifier_block *self,
 				   mod->num_ftrace_callsites);
 		break;
 	case MODULE_STATE_GOING:
-		ftrace_release(mod->ftrace_callsites,
-			       mod->ftrace_callsites +
-			       mod->num_ftrace_callsites);
+		ftrace_release_mod(mod);
 		break;
 	}
 
@@ -3161,7 +3013,7 @@ int unregister_ftrace_function(struct ftrace_ops *ops)
 
 int
 ftrace_enable_sysctl(struct ctl_table *table, int write,
-		     struct file *file, void __user *buffer, size_t *lenp,
+		     void __user *buffer, size_t *lenp,
 		     loff_t *ppos)
 {
 	int ret;
@@ -3171,7 +3023,7 @@ ftrace_enable_sysctl(struct ctl_table *table, int write,
 
 	mutex_lock(&ftrace_lock);
 
-	ret  = proc_dointvec(table, write, file, buffer, lenp, ppos);
+	ret  = proc_dointvec(table, write, buffer, lenp, ppos);
 
 	if (ret || !write || (last_ftrace_enabled == !!ftrace_enabled))
 		goto out;
diff --git a/kernel/trace/kmemtrace.c b/kernel/trace/kmemtrace.c
index 1edaa9516e81..a91da69f153a 100644
--- a/kernel/trace/kmemtrace.c
+++ b/kernel/trace/kmemtrace.c
@@ -183,11 +183,9 @@ static void kmemtrace_stop_probes(void)
 
 static int kmem_trace_init(struct trace_array *tr)
 {
-	int cpu;
 	kmemtrace_array = tr;
 
-	for_each_cpu(cpu, cpu_possible_mask)
-		tracing_reset(tr, cpu);
+	tracing_reset_online_cpus(tr);
 
 	kmemtrace_start_probes();
 
@@ -239,12 +237,52 @@ struct kmemtrace_user_event_alloc {
 };
 
 static enum print_line_t
-kmemtrace_print_alloc_user(struct trace_iterator *iter,
-			   struct kmemtrace_alloc_entry *entry)
+kmemtrace_print_alloc(struct trace_iterator *iter, int flags)
 {
-	struct kmemtrace_user_event_alloc *ev_alloc;
 	struct trace_seq *s = &iter->seq;
+	struct kmemtrace_alloc_entry *entry;
+	int ret;
+
+	trace_assign_type(entry, iter->ent);
+
+	ret = trace_seq_printf(s, "type_id %d call_site %pF ptr %lu "
+	    "bytes_req %lu bytes_alloc %lu gfp_flags %lu node %d\n",
+	    entry->type_id, (void *)entry->call_site, (unsigned long)entry->ptr,
+	    (unsigned long)entry->bytes_req, (unsigned long)entry->bytes_alloc,
+	    (unsigned long)entry->gfp_flags, entry->node);
+
+	if (!ret)
+		return TRACE_TYPE_PARTIAL_LINE;
+	return TRACE_TYPE_HANDLED;
+}
+
+static enum print_line_t
+kmemtrace_print_free(struct trace_iterator *iter, int flags)
+{
+	struct trace_seq *s = &iter->seq;
+	struct kmemtrace_free_entry *entry;
+	int ret;
+
+	trace_assign_type(entry, iter->ent);
+
+	ret = trace_seq_printf(s, "type_id %d call_site %pF ptr %lu\n",
+			       entry->type_id, (void *)entry->call_site,
+			       (unsigned long)entry->ptr);
+
+	if (!ret)
+		return TRACE_TYPE_PARTIAL_LINE;
+	return TRACE_TYPE_HANDLED;
+}
+
+static enum print_line_t
+kmemtrace_print_alloc_user(struct trace_iterator *iter, int flags)
+{
+	struct trace_seq *s = &iter->seq;
+	struct kmemtrace_alloc_entry *entry;
 	struct kmemtrace_user_event *ev;
+	struct kmemtrace_user_event_alloc *ev_alloc;
+
+	trace_assign_type(entry, iter->ent);
 
 	ev = trace_seq_reserve(s, sizeof(*ev));
 	if (!ev)
@@ -271,12 +309,14 @@ kmemtrace_print_alloc_user(struct trace_iterator *iter,
 }
 
 static enum print_line_t
-kmemtrace_print_free_user(struct trace_iterator *iter,
-			  struct kmemtrace_free_entry *entry)
+kmemtrace_print_free_user(struct trace_iterator *iter, int flags)
 {
 	struct trace_seq *s = &iter->seq;
+	struct kmemtrace_free_entry *entry;
 	struct kmemtrace_user_event *ev;
 
+	trace_assign_type(entry, iter->ent);
+
 	ev = trace_seq_reserve(s, sizeof(*ev));
 	if (!ev)
 		return TRACE_TYPE_PARTIAL_LINE;
@@ -294,12 +334,14 @@ kmemtrace_print_free_user(struct trace_iterator *iter,
 
 /* The two other following provide a more minimalistic output */
 static enum print_line_t
-kmemtrace_print_alloc_compress(struct trace_iterator *iter,
-					struct kmemtrace_alloc_entry *entry)
+kmemtrace_print_alloc_compress(struct trace_iterator *iter)
 {
+	struct kmemtrace_alloc_entry *entry;
 	struct trace_seq *s = &iter->seq;
 	int ret;
 
+	trace_assign_type(entry, iter->ent);
+
 	/* Alloc entry */
 	ret = trace_seq_printf(s, "  +      ");
 	if (!ret)
@@ -345,29 +387,24 @@ kmemtrace_print_alloc_compress(struct trace_iterator *iter,
 	if (!ret)
 		return TRACE_TYPE_PARTIAL_LINE;
 
-	/* Node */
-	ret = trace_seq_printf(s, "%4d   ", entry->node);
-	if (!ret)
-		return TRACE_TYPE_PARTIAL_LINE;
-
-	/* Call site */
-	ret = seq_print_ip_sym(s, entry->call_site, 0);
+	/* Node and call site*/
+	ret = trace_seq_printf(s, "%4d   %pf\n", entry->node,
+						 (void *)entry->call_site);
 	if (!ret)
 		return TRACE_TYPE_PARTIAL_LINE;
 
-	if (!trace_seq_printf(s, "\n"))
-		return TRACE_TYPE_PARTIAL_LINE;
-
 	return TRACE_TYPE_HANDLED;
 }
 
 static enum print_line_t
-kmemtrace_print_free_compress(struct trace_iterator *iter,
-			      struct kmemtrace_free_entry *entry)
+kmemtrace_print_free_compress(struct trace_iterator *iter)
 {
+	struct kmemtrace_free_entry *entry;
 	struct trace_seq *s = &iter->seq;
 	int ret;
 
+	trace_assign_type(entry, iter->ent);
+
 	/* Free entry */
 	ret = trace_seq_printf(s, "  -      ");
 	if (!ret)
@@ -401,19 +438,11 @@ kmemtrace_print_free_compress(struct trace_iterator *iter,
 	if (!ret)
 		return TRACE_TYPE_PARTIAL_LINE;
 
-	/* Skip node */
-	ret = trace_seq_printf(s, "       ");
+	/* Skip node and print call site*/
+	ret = trace_seq_printf(s, "       %pf\n", (void *)entry->call_site);
 	if (!ret)
 		return TRACE_TYPE_PARTIAL_LINE;
 
-	/* Call site */
-	ret = seq_print_ip_sym(s, entry->call_site, 0);
-	if (!ret)
-		return TRACE_TYPE_PARTIAL_LINE;
-
-	if (!trace_seq_printf(s, "\n"))
-		return TRACE_TYPE_PARTIAL_LINE;
-
 	return TRACE_TYPE_HANDLED;
 }
 
@@ -421,32 +450,31 @@ static enum print_line_t kmemtrace_print_line(struct trace_iterator *iter)
 {
 	struct trace_entry *entry = iter->ent;
 
-	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_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_user(iter, field);
-	}
+	if (!(kmem_tracer_flags.val & TRACE_KMEM_OPT_MINIMAL))
+		return TRACE_TYPE_UNHANDLED;
 
+	switch (entry->type) {
+	case TRACE_KMEM_ALLOC:
+		return kmemtrace_print_alloc_compress(iter);
+	case TRACE_KMEM_FREE:
+		return kmemtrace_print_free_compress(iter);
 	default:
 		return TRACE_TYPE_UNHANDLED;
 	}
 }
 
+static struct trace_event kmem_trace_alloc = {
+	.type			= TRACE_KMEM_ALLOC,
+	.trace			= kmemtrace_print_alloc,
+	.binary			= kmemtrace_print_alloc_user,
+};
+
+static struct trace_event kmem_trace_free = {
+	.type			= TRACE_KMEM_FREE,
+	.trace			= kmemtrace_print_free,
+	.binary			= kmemtrace_print_free_user,
+};
+
 static struct tracer kmem_tracer __read_mostly = {
 	.name			= "kmemtrace",
 	.init			= kmem_trace_init,
@@ -463,6 +491,21 @@ void kmemtrace_init(void)
 
 static int __init init_kmem_tracer(void)
 {
-	return register_tracer(&kmem_tracer);
+	if (!register_ftrace_event(&kmem_trace_alloc)) {
+		pr_warning("Warning: could not register kmem events\n");
+		return 1;
+	}
+
+	if (!register_ftrace_event(&kmem_trace_free)) {
+		pr_warning("Warning: could not register kmem events\n");
+		return 1;
+	}
+
+	if (register_tracer(&kmem_tracer) != 0) {
+		pr_warning("Warning: could not register the kmem tracer\n");
+		return 1;
+	}
+
+	return 0;
 }
 device_initcall(init_kmem_tracer);
diff --git a/kernel/trace/power-traces.c b/kernel/trace/power-traces.c
new file mode 100644
index 000000000000..e06c6e3d56a3
--- /dev/null
+++ b/kernel/trace/power-traces.c
@@ -0,0 +1,20 @@
+/*
+ * Power trace points
+ *
+ * Copyright (C) 2009 Arjan van de Ven <arjan@linux.intel.com>
+ */
+
+#include <linux/string.h>
+#include <linux/types.h>
+#include <linux/workqueue.h>
+#include <linux/sched.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+
+#define CREATE_TRACE_POINTS
+#include <trace/events/power.h>
+
+EXPORT_TRACEPOINT_SYMBOL_GPL(power_start);
+EXPORT_TRACEPOINT_SYMBOL_GPL(power_end);
+EXPORT_TRACEPOINT_SYMBOL_GPL(power_frequency);
+
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index a330513d96ce..5dd017fea6f5 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -201,8 +201,6 @@ int tracing_is_on(void)
 }
 EXPORT_SYMBOL_GPL(tracing_is_on);
 
-#include "trace.h"
-
 #define RB_EVNT_HDR_SIZE (offsetof(struct ring_buffer_event, array))
 #define RB_ALIGNMENT		4U
 #define RB_MAX_SMALL_DATA	(RB_ALIGNMENT * RINGBUF_TYPE_DATA_TYPE_LEN_MAX)
@@ -218,17 +216,12 @@ enum {
 
 static inline int rb_null_event(struct ring_buffer_event *event)
 {
-	return event->type_len == RINGBUF_TYPE_PADDING
-			&& event->time_delta == 0;
-}
-
-static inline int rb_discarded_event(struct ring_buffer_event *event)
-{
-	return event->type_len == RINGBUF_TYPE_PADDING && event->time_delta;
+	return event->type_len == RINGBUF_TYPE_PADDING && !event->time_delta;
 }
 
 static void rb_event_set_padding(struct ring_buffer_event *event)
 {
+	/* padding has a NULL time_delta */
 	event->type_len = RINGBUF_TYPE_PADDING;
 	event->time_delta = 0;
 }
@@ -322,6 +315,14 @@ struct buffer_data_page {
 	unsigned char	 data[];	/* data of buffer page */
 };
 
+/*
+ * Note, the buffer_page list must be first. The buffer pages
+ * are allocated in cache lines, which means that each buffer
+ * page will be at the beginning of a cache line, and thus
+ * the least significant bits will be zero. We use this to
+ * add flags in the list struct pointers, to make the ring buffer
+ * lockless.
+ */
 struct buffer_page {
 	struct list_head list;		/* list of buffer pages */
 	local_t		 write;		/* index for next write */
@@ -330,6 +331,21 @@ struct buffer_page {
 	struct buffer_data_page *page;	/* Actual data page */
 };
 
+/*
+ * The buffer page counters, write and entries, must be reset
+ * atomically when crossing page boundaries. To synchronize this
+ * update, two counters are inserted into the number. One is
+ * the actual counter for the write position or count on the page.
+ *
+ * The other is a counter of updaters. Before an update happens
+ * the update partition of the counter is incremented. This will
+ * allow the updater to update the counter atomically.
+ *
+ * The counter is 20 bits, and the state data is 12.
+ */
+#define RB_WRITE_MASK		0xfffff
+#define RB_WRITE_INTCNT		(1 << 20)
+
 static void rb_init_page(struct buffer_data_page *bpage)
 {
 	local_set(&bpage->commit, 0);
@@ -403,21 +419,20 @@ int ring_buffer_print_page_header(struct trace_seq *s)
 struct ring_buffer_per_cpu {
 	int				cpu;
 	struct ring_buffer		*buffer;
-	spinlock_t			reader_lock; /* serialize readers */
+	spinlock_t			reader_lock;	/* serialize readers */
 	raw_spinlock_t			lock;
 	struct lock_class_key		lock_key;
-	struct list_head		pages;
+	struct list_head		*pages;
 	struct buffer_page		*head_page;	/* read from head */
 	struct buffer_page		*tail_page;	/* write to tail */
 	struct buffer_page		*commit_page;	/* committed pages */
 	struct buffer_page		*reader_page;
-	unsigned long			nmi_dropped;
-	unsigned long			commit_overrun;
-	unsigned long			overrun;
-	unsigned long			read;
+	local_t				commit_overrun;
+	local_t				overrun;
 	local_t				entries;
 	local_t				committing;
 	local_t				commits;
+	unsigned long			read;
 	u64				write_stamp;
 	u64				read_stamp;
 	atomic_t			record_disabled;
@@ -450,20 +465,25 @@ struct ring_buffer_iter {
 };
 
 /* buffer may be either ring_buffer or ring_buffer_per_cpu */
-#define RB_WARN_ON(buffer, cond)				\
-	({							\
-		int _____ret = unlikely(cond);			\
-		if (_____ret) {					\
-			atomic_inc(&buffer->record_disabled);	\
-			WARN_ON(1);				\
-		}						\
-		_____ret;					\
+#define RB_WARN_ON(b, cond)						\
+	({								\
+		int _____ret = unlikely(cond);				\
+		if (_____ret) {						\
+			if (__same_type(*(b), struct ring_buffer_per_cpu)) { \
+				struct ring_buffer_per_cpu *__b =	\
+					(void *)b;			\
+				atomic_inc(&__b->buffer->record_disabled); \
+			} else						\
+				atomic_inc(&b->record_disabled);	\
+			WARN_ON(1);					\
+		}							\
+		_____ret;						\
 	})
 
 /* Up this if you want to test the TIME_EXTENTS and normalization */
 #define DEBUG_SHIFT 0
 
-static inline u64 rb_time_stamp(struct ring_buffer *buffer, int cpu)
+static inline u64 rb_time_stamp(struct ring_buffer *buffer)
 {
 	/* shift to debug/test normalization and TIME_EXTENTS */
 	return buffer->clock() << DEBUG_SHIFT;
@@ -474,7 +494,7 @@ u64 ring_buffer_time_stamp(struct ring_buffer *buffer, int cpu)
 	u64 time;
 
 	preempt_disable_notrace();
-	time = rb_time_stamp(buffer, cpu);
+	time = rb_time_stamp(buffer);
 	preempt_enable_no_resched_notrace();
 
 	return time;
@@ -489,6 +509,390 @@ void ring_buffer_normalize_time_stamp(struct ring_buffer *buffer,
 }
 EXPORT_SYMBOL_GPL(ring_buffer_normalize_time_stamp);
 
+/*
+ * Making the ring buffer lockless makes things tricky.
+ * Although writes only happen on the CPU that they are on,
+ * and they only need to worry about interrupts. Reads can
+ * happen on any CPU.
+ *
+ * The reader page is always off the ring buffer, but when the
+ * reader finishes with a page, it needs to swap its page with
+ * a new one from the buffer. The reader needs to take from
+ * the head (writes go to the tail). But if a writer is in overwrite
+ * mode and wraps, it must push the head page forward.
+ *
+ * Here lies the problem.
+ *
+ * The reader must be careful to replace only the head page, and
+ * not another one. As described at the top of the file in the
+ * ASCII art, the reader sets its old page to point to the next
+ * page after head. It then sets the page after head to point to
+ * the old reader page. But if the writer moves the head page
+ * during this operation, the reader could end up with the tail.
+ *
+ * We use cmpxchg to help prevent this race. We also do something
+ * special with the page before head. We set the LSB to 1.
+ *
+ * When the writer must push the page forward, it will clear the
+ * bit that points to the head page, move the head, and then set
+ * the bit that points to the new head page.
+ *
+ * We also don't want an interrupt coming in and moving the head
+ * page on another writer. Thus we use the second LSB to catch
+ * that too. Thus:
+ *
+ * head->list->prev->next        bit 1          bit 0
+ *                              -------        -------
+ * Normal page                     0              0
+ * Points to head page             0              1
+ * New head page                   1              0
+ *
+ * Note we can not trust the prev pointer of the head page, because:
+ *
+ * +----+       +-----+        +-----+
+ * |    |------>|  T  |---X--->|  N  |
+ * |    |<------|     |        |     |
+ * +----+       +-----+        +-----+
+ *   ^                           ^ |
+ *   |          +-----+          | |
+ *   +----------|  R  |----------+ |
+ *              |     |<-----------+
+ *              +-----+
+ *
+ * Key:  ---X-->  HEAD flag set in pointer
+ *         T      Tail page
+ *         R      Reader page
+ *         N      Next page
+ *
+ * (see __rb_reserve_next() to see where this happens)
+ *
+ *  What the above shows is that the reader just swapped out
+ *  the reader page with a page in the buffer, but before it
+ *  could make the new header point back to the new page added
+ *  it was preempted by a writer. The writer moved forward onto
+ *  the new page added by the reader and is about to move forward
+ *  again.
+ *
+ *  You can see, it is legitimate for the previous pointer of
+ *  the head (or any page) not to point back to itself. But only
+ *  temporarially.
+ */
+
+#define RB_PAGE_NORMAL		0UL
+#define RB_PAGE_HEAD		1UL
+#define RB_PAGE_UPDATE		2UL
+
+
+#define RB_FLAG_MASK		3UL
+
+/* PAGE_MOVED is not part of the mask */
+#define RB_PAGE_MOVED		4UL
+
+/*
+ * rb_list_head - remove any bit
+ */
+static struct list_head *rb_list_head(struct list_head *list)
+{
+	unsigned long val = (unsigned long)list;
+
+	return (struct list_head *)(val & ~RB_FLAG_MASK);
+}
+
+/*
+ * rb_is_head_page - test if the given page is the head page
+ *
+ * Because the reader may move the head_page pointer, we can
+ * not trust what the head page is (it may be pointing to
+ * the reader page). But if the next page is a header page,
+ * its flags will be non zero.
+ */
+static int inline
+rb_is_head_page(struct ring_buffer_per_cpu *cpu_buffer,
+		struct buffer_page *page, struct list_head *list)
+{
+	unsigned long val;
+
+	val = (unsigned long)list->next;
+
+	if ((val & ~RB_FLAG_MASK) != (unsigned long)&page->list)
+		return RB_PAGE_MOVED;
+
+	return val & RB_FLAG_MASK;
+}
+
+/*
+ * rb_is_reader_page
+ *
+ * The unique thing about the reader page, is that, if the
+ * writer is ever on it, the previous pointer never points
+ * back to the reader page.
+ */
+static int rb_is_reader_page(struct buffer_page *page)
+{
+	struct list_head *list = page->list.prev;
+
+	return rb_list_head(list->next) != &page->list;
+}
+
+/*
+ * rb_set_list_to_head - set a list_head to be pointing to head.
+ */
+static void rb_set_list_to_head(struct ring_buffer_per_cpu *cpu_buffer,
+				struct list_head *list)
+{
+	unsigned long *ptr;
+
+	ptr = (unsigned long *)&list->next;
+	*ptr |= RB_PAGE_HEAD;
+	*ptr &= ~RB_PAGE_UPDATE;
+}
+
+/*
+ * rb_head_page_activate - sets up head page
+ */
+static void rb_head_page_activate(struct ring_buffer_per_cpu *cpu_buffer)
+{
+	struct buffer_page *head;
+
+	head = cpu_buffer->head_page;
+	if (!head)
+		return;
+
+	/*
+	 * Set the previous list pointer to have the HEAD flag.
+	 */
+	rb_set_list_to_head(cpu_buffer, head->list.prev);
+}
+
+static void rb_list_head_clear(struct list_head *list)
+{
+	unsigned long *ptr = (unsigned long *)&list->next;
+
+	*ptr &= ~RB_FLAG_MASK;
+}
+
+/*
+ * rb_head_page_dactivate - clears head page ptr (for free list)
+ */
+static void
+rb_head_page_deactivate(struct ring_buffer_per_cpu *cpu_buffer)
+{
+	struct list_head *hd;
+
+	/* Go through the whole list and clear any pointers found. */
+	rb_list_head_clear(cpu_buffer->pages);
+
+	list_for_each(hd, cpu_buffer->pages)
+		rb_list_head_clear(hd);
+}
+
+static int rb_head_page_set(struct ring_buffer_per_cpu *cpu_buffer,
+			    struct buffer_page *head,
+			    struct buffer_page *prev,
+			    int old_flag, int new_flag)
+{
+	struct list_head *list;
+	unsigned long val = (unsigned long)&head->list;
+	unsigned long ret;
+
+	list = &prev->list;
+
+	val &= ~RB_FLAG_MASK;
+
+	ret = cmpxchg((unsigned long *)&list->next,
+		      val | old_flag, val | new_flag);
+
+	/* check if the reader took the page */
+	if ((ret & ~RB_FLAG_MASK) != val)
+		return RB_PAGE_MOVED;
+
+	return ret & RB_FLAG_MASK;
+}
+
+static int rb_head_page_set_update(struct ring_buffer_per_cpu *cpu_buffer,
+				   struct buffer_page *head,
+				   struct buffer_page *prev,
+				   int old_flag)
+{
+	return rb_head_page_set(cpu_buffer, head, prev,
+				old_flag, RB_PAGE_UPDATE);
+}
+
+static int rb_head_page_set_head(struct ring_buffer_per_cpu *cpu_buffer,
+				 struct buffer_page *head,
+				 struct buffer_page *prev,
+				 int old_flag)
+{
+	return rb_head_page_set(cpu_buffer, head, prev,
+				old_flag, RB_PAGE_HEAD);
+}
+
+static int rb_head_page_set_normal(struct ring_buffer_per_cpu *cpu_buffer,
+				   struct buffer_page *head,
+				   struct buffer_page *prev,
+				   int old_flag)
+{
+	return rb_head_page_set(cpu_buffer, head, prev,
+				old_flag, RB_PAGE_NORMAL);
+}
+
+static inline void rb_inc_page(struct ring_buffer_per_cpu *cpu_buffer,
+			       struct buffer_page **bpage)
+{
+	struct list_head *p = rb_list_head((*bpage)->list.next);
+
+	*bpage = list_entry(p, struct buffer_page, list);
+}
+
+static struct buffer_page *
+rb_set_head_page(struct ring_buffer_per_cpu *cpu_buffer)
+{
+	struct buffer_page *head;
+	struct buffer_page *page;
+	struct list_head *list;
+	int i;
+
+	if (RB_WARN_ON(cpu_buffer, !cpu_buffer->head_page))
+		return NULL;
+
+	/* sanity check */
+	list = cpu_buffer->pages;
+	if (RB_WARN_ON(cpu_buffer, rb_list_head(list->prev->next) != list))
+		return NULL;
+
+	page = head = cpu_buffer->head_page;
+	/*
+	 * It is possible that the writer moves the header behind
+	 * where we started, and we miss in one loop.
+	 * A second loop should grab the header, but we'll do
+	 * three loops just because I'm paranoid.
+	 */
+	for (i = 0; i < 3; i++) {
+		do {
+			if (rb_is_head_page(cpu_buffer, page, page->list.prev)) {
+				cpu_buffer->head_page = page;
+				return page;
+			}
+			rb_inc_page(cpu_buffer, &page);
+		} while (page != head);
+	}
+
+	RB_WARN_ON(cpu_buffer, 1);
+
+	return NULL;
+}
+
+static int rb_head_page_replace(struct buffer_page *old,
+				struct buffer_page *new)
+{
+	unsigned long *ptr = (unsigned long *)&old->list.prev->next;
+	unsigned long val;
+	unsigned long ret;
+
+	val = *ptr & ~RB_FLAG_MASK;
+	val |= RB_PAGE_HEAD;
+
+	ret = cmpxchg(ptr, val, (unsigned long)&new->list);
+
+	return ret == val;
+}
+
+/*
+ * rb_tail_page_update - move the tail page forward
+ *
+ * Returns 1 if moved tail page, 0 if someone else did.
+ */
+static int rb_tail_page_update(struct ring_buffer_per_cpu *cpu_buffer,
+			       struct buffer_page *tail_page,
+			       struct buffer_page *next_page)
+{
+	struct buffer_page *old_tail;
+	unsigned long old_entries;
+	unsigned long old_write;
+	int ret = 0;
+
+	/*
+	 * The tail page now needs to be moved forward.
+	 *
+	 * We need to reset the tail page, but without messing
+	 * with possible erasing of data brought in by interrupts
+	 * that have moved the tail page and are currently on it.
+	 *
+	 * We add a counter to the write field to denote this.
+	 */
+	old_write = local_add_return(RB_WRITE_INTCNT, &next_page->write);
+	old_entries = local_add_return(RB_WRITE_INTCNT, &next_page->entries);
+
+	/*
+	 * Just make sure we have seen our old_write and synchronize
+	 * with any interrupts that come in.
+	 */
+	barrier();
+
+	/*
+	 * If the tail page is still the same as what we think
+	 * it is, then it is up to us to update the tail
+	 * pointer.
+	 */
+	if (tail_page == cpu_buffer->tail_page) {
+		/* Zero the write counter */
+		unsigned long val = old_write & ~RB_WRITE_MASK;
+		unsigned long eval = old_entries & ~RB_WRITE_MASK;
+
+		/*
+		 * This will only succeed if an interrupt did
+		 * not come in and change it. In which case, we
+		 * do not want to modify it.
+		 *
+		 * We add (void) to let the compiler know that we do not care
+		 * about the return value of these functions. We use the
+		 * cmpxchg to only update if an interrupt did not already
+		 * do it for us. If the cmpxchg fails, we don't care.
+		 */
+		(void)local_cmpxchg(&next_page->write, old_write, val);
+		(void)local_cmpxchg(&next_page->entries, old_entries, eval);
+
+		/*
+		 * No need to worry about races with clearing out the commit.
+		 * it only can increment when a commit takes place. But that
+		 * only happens in the outer most nested commit.
+		 */
+		local_set(&next_page->page->commit, 0);
+
+		old_tail = cmpxchg(&cpu_buffer->tail_page,
+				   tail_page, next_page);
+
+		if (old_tail == tail_page)
+			ret = 1;
+	}
+
+	return ret;
+}
+
+static int rb_check_bpage(struct ring_buffer_per_cpu *cpu_buffer,
+			  struct buffer_page *bpage)
+{
+	unsigned long val = (unsigned long)bpage;
+
+	if (RB_WARN_ON(cpu_buffer, val & RB_FLAG_MASK))
+		return 1;
+
+	return 0;
+}
+
+/**
+ * rb_check_list - make sure a pointer to a list has the last bits zero
+ */
+static int rb_check_list(struct ring_buffer_per_cpu *cpu_buffer,
+			 struct list_head *list)
+{
+	if (RB_WARN_ON(cpu_buffer, rb_list_head(list->prev) != list->prev))
+		return 1;
+	if (RB_WARN_ON(cpu_buffer, rb_list_head(list->next) != list->next))
+		return 1;
+	return 0;
+}
+
 /**
  * check_pages - integrity check of buffer pages
  * @cpu_buffer: CPU buffer with pages to test
@@ -498,14 +902,19 @@ EXPORT_SYMBOL_GPL(ring_buffer_normalize_time_stamp);
  */
 static int rb_check_pages(struct ring_buffer_per_cpu *cpu_buffer)
 {
-	struct list_head *head = &cpu_buffer->pages;
+	struct list_head *head = cpu_buffer->pages;
 	struct buffer_page *bpage, *tmp;
 
+	rb_head_page_deactivate(cpu_buffer);
+
 	if (RB_WARN_ON(cpu_buffer, head->next->prev != head))
 		return -1;
 	if (RB_WARN_ON(cpu_buffer, head->prev->next != head))
 		return -1;
 
+	if (rb_check_list(cpu_buffer, head))
+		return -1;
+
 	list_for_each_entry_safe(bpage, tmp, head, list) {
 		if (RB_WARN_ON(cpu_buffer,
 			       bpage->list.next->prev != &bpage->list))
@@ -513,25 +922,33 @@ static int rb_check_pages(struct ring_buffer_per_cpu *cpu_buffer)
 		if (RB_WARN_ON(cpu_buffer,
 			       bpage->list.prev->next != &bpage->list))
 			return -1;
+		if (rb_check_list(cpu_buffer, &bpage->list))
+			return -1;
 	}
 
+	rb_head_page_activate(cpu_buffer);
+
 	return 0;
 }
 
 static int rb_allocate_pages(struct ring_buffer_per_cpu *cpu_buffer,
 			     unsigned nr_pages)
 {
-	struct list_head *head = &cpu_buffer->pages;
 	struct buffer_page *bpage, *tmp;
 	unsigned long addr;
 	LIST_HEAD(pages);
 	unsigned i;
 
+	WARN_ON(!nr_pages);
+
 	for (i = 0; i < nr_pages; i++) {
 		bpage = kzalloc_node(ALIGN(sizeof(*bpage), cache_line_size()),
 				    GFP_KERNEL, cpu_to_node(cpu_buffer->cpu));
 		if (!bpage)
 			goto free_pages;
+
+		rb_check_bpage(cpu_buffer, bpage);
+
 		list_add(&bpage->list, &pages);
 
 		addr = __get_free_page(GFP_KERNEL);
@@ -541,7 +958,13 @@ static int rb_allocate_pages(struct ring_buffer_per_cpu *cpu_buffer,
 		rb_init_page(bpage->page);
 	}
 
-	list_splice(&pages, head);
+	/*
+	 * The ring buffer page list is a circular list that does not
+	 * start and end with a list head. All page list items point to
+	 * other pages.
+	 */
+	cpu_buffer->pages = pages.next;
+	list_del(&pages);
 
 	rb_check_pages(cpu_buffer);
 
@@ -573,13 +996,14 @@ rb_allocate_cpu_buffer(struct ring_buffer *buffer, int cpu)
 	spin_lock_init(&cpu_buffer->reader_lock);
 	lockdep_set_class(&cpu_buffer->reader_lock, buffer->reader_lock_key);
 	cpu_buffer->lock = (raw_spinlock_t)__RAW_SPIN_LOCK_UNLOCKED;
-	INIT_LIST_HEAD(&cpu_buffer->pages);
 
 	bpage = kzalloc_node(ALIGN(sizeof(*bpage), cache_line_size()),
 			    GFP_KERNEL, cpu_to_node(cpu));
 	if (!bpage)
 		goto fail_free_buffer;
 
+	rb_check_bpage(cpu_buffer, bpage);
+
 	cpu_buffer->reader_page = bpage;
 	addr = __get_free_page(GFP_KERNEL);
 	if (!addr)
@@ -594,9 +1018,11 @@ rb_allocate_cpu_buffer(struct ring_buffer *buffer, int cpu)
 		goto fail_free_reader;
 
 	cpu_buffer->head_page
-		= list_entry(cpu_buffer->pages.next, struct buffer_page, list);
+		= list_entry(cpu_buffer->pages, struct buffer_page, list);
 	cpu_buffer->tail_page = cpu_buffer->commit_page = cpu_buffer->head_page;
 
+	rb_head_page_activate(cpu_buffer);
+
 	return cpu_buffer;
 
  fail_free_reader:
@@ -609,15 +1035,22 @@ rb_allocate_cpu_buffer(struct ring_buffer *buffer, int cpu)
 
 static void rb_free_cpu_buffer(struct ring_buffer_per_cpu *cpu_buffer)
 {
-	struct list_head *head = &cpu_buffer->pages;
+	struct list_head *head = cpu_buffer->pages;
 	struct buffer_page *bpage, *tmp;
 
 	free_buffer_page(cpu_buffer->reader_page);
 
-	list_for_each_entry_safe(bpage, tmp, head, list) {
-		list_del_init(&bpage->list);
+	rb_head_page_deactivate(cpu_buffer);
+
+	if (head) {
+		list_for_each_entry_safe(bpage, tmp, head, list) {
+			list_del_init(&bpage->list);
+			free_buffer_page(bpage);
+		}
+		bpage = list_entry(head, struct buffer_page, list);
 		free_buffer_page(bpage);
 	}
+
 	kfree(cpu_buffer);
 }
 
@@ -760,18 +1193,22 @@ rb_remove_pages(struct ring_buffer_per_cpu *cpu_buffer, unsigned nr_pages)
 	atomic_inc(&cpu_buffer->record_disabled);
 	synchronize_sched();
 
+	spin_lock_irq(&cpu_buffer->reader_lock);
+	rb_head_page_deactivate(cpu_buffer);
+
 	for (i = 0; i < nr_pages; i++) {
-		if (RB_WARN_ON(cpu_buffer, list_empty(&cpu_buffer->pages)))
+		if (RB_WARN_ON(cpu_buffer, list_empty(cpu_buffer->pages)))
 			return;
-		p = cpu_buffer->pages.next;
+		p = cpu_buffer->pages->next;
 		bpage = list_entry(p, struct buffer_page, list);
 		list_del_init(&bpage->list);
 		free_buffer_page(bpage);
 	}
-	if (RB_WARN_ON(cpu_buffer, list_empty(&cpu_buffer->pages)))
+	if (RB_WARN_ON(cpu_buffer, list_empty(cpu_buffer->pages)))
 		return;
 
 	rb_reset_cpu(cpu_buffer);
+	spin_unlock_irq(&cpu_buffer->reader_lock);
 
 	rb_check_pages(cpu_buffer);
 
@@ -790,15 +1227,19 @@ rb_insert_pages(struct ring_buffer_per_cpu *cpu_buffer,
 	atomic_inc(&cpu_buffer->record_disabled);
 	synchronize_sched();
 
+	spin_lock_irq(&cpu_buffer->reader_lock);
+	rb_head_page_deactivate(cpu_buffer);
+
 	for (i = 0; i < nr_pages; i++) {
 		if (RB_WARN_ON(cpu_buffer, list_empty(pages)))
 			return;
 		p = pages->next;
 		bpage = list_entry(p, struct buffer_page, list);
 		list_del_init(&bpage->list);
-		list_add_tail(&bpage->list, &cpu_buffer->pages);
+		list_add_tail(&bpage->list, cpu_buffer->pages);
 	}
 	rb_reset_cpu(cpu_buffer);
+	spin_unlock_irq(&cpu_buffer->reader_lock);
 
 	rb_check_pages(cpu_buffer);
 
@@ -949,21 +1390,14 @@ rb_reader_event(struct ring_buffer_per_cpu *cpu_buffer)
 }
 
 static inline struct ring_buffer_event *
-rb_head_event(struct ring_buffer_per_cpu *cpu_buffer)
-{
-	return __rb_page_index(cpu_buffer->head_page,
-			       cpu_buffer->head_page->read);
-}
-
-static inline struct ring_buffer_event *
 rb_iter_head_event(struct ring_buffer_iter *iter)
 {
 	return __rb_page_index(iter->head_page, iter->head);
 }
 
-static inline unsigned rb_page_write(struct buffer_page *bpage)
+static inline unsigned long rb_page_write(struct buffer_page *bpage)
 {
-	return local_read(&bpage->write);
+	return local_read(&bpage->write) & RB_WRITE_MASK;
 }
 
 static inline unsigned rb_page_commit(struct buffer_page *bpage)
@@ -971,6 +1405,11 @@ static inline unsigned rb_page_commit(struct buffer_page *bpage)
 	return local_read(&bpage->page->commit);
 }
 
+static inline unsigned long rb_page_entries(struct buffer_page *bpage)
+{
+	return local_read(&bpage->entries) & RB_WRITE_MASK;
+}
+
 /* Size is determined by what has been commited */
 static inline unsigned rb_page_size(struct buffer_page *bpage)
 {
@@ -983,22 +1422,6 @@ rb_commit_index(struct ring_buffer_per_cpu *cpu_buffer)
 	return rb_page_commit(cpu_buffer->commit_page);
 }
 
-static inline unsigned rb_head_size(struct ring_buffer_per_cpu *cpu_buffer)
-{
-	return rb_page_commit(cpu_buffer->head_page);
-}
-
-static inline void rb_inc_page(struct ring_buffer_per_cpu *cpu_buffer,
-			       struct buffer_page **bpage)
-{
-	struct list_head *p = (*bpage)->list.next;
-
-	if (p == &cpu_buffer->pages)
-		p = p->next;
-
-	*bpage = list_entry(p, struct buffer_page, list);
-}
-
 static inline unsigned
 rb_event_index(struct ring_buffer_event *event)
 {
@@ -1024,6 +1447,8 @@ rb_event_is_commit(struct ring_buffer_per_cpu *cpu_buffer,
 static void
 rb_set_commit_to_write(struct ring_buffer_per_cpu *cpu_buffer)
 {
+	unsigned long max_count;
+
 	/*
 	 * We only race with interrupts and NMIs on this CPU.
 	 * If we own the commit event, then we can commit
@@ -1033,9 +1458,16 @@ rb_set_commit_to_write(struct ring_buffer_per_cpu *cpu_buffer)
 	 * assign the commit to the tail.
 	 */
  again:
+	max_count = cpu_buffer->buffer->pages * 100;
+
 	while (cpu_buffer->commit_page != cpu_buffer->tail_page) {
-		cpu_buffer->commit_page->page->commit =
-			cpu_buffer->commit_page->write;
+		if (RB_WARN_ON(cpu_buffer, !(--max_count)))
+			return;
+		if (RB_WARN_ON(cpu_buffer,
+			       rb_is_reader_page(cpu_buffer->tail_page)))
+			return;
+		local_set(&cpu_buffer->commit_page->page->commit,
+			  rb_page_write(cpu_buffer->commit_page));
 		rb_inc_page(cpu_buffer, &cpu_buffer->commit_page);
 		cpu_buffer->write_stamp =
 			cpu_buffer->commit_page->page->time_stamp;
@@ -1044,8 +1476,12 @@ rb_set_commit_to_write(struct ring_buffer_per_cpu *cpu_buffer)
 	}
 	while (rb_commit_index(cpu_buffer) !=
 	       rb_page_write(cpu_buffer->commit_page)) {
-		cpu_buffer->commit_page->page->commit =
-			cpu_buffer->commit_page->write;
+
+		local_set(&cpu_buffer->commit_page->page->commit,
+			  rb_page_write(cpu_buffer->commit_page));
+		RB_WARN_ON(cpu_buffer,
+			   local_read(&cpu_buffer->commit_page->page->commit) &
+			   ~RB_WRITE_MASK);
 		barrier();
 	}
 
@@ -1078,7 +1514,7 @@ static void rb_inc_iter(struct ring_buffer_iter *iter)
 	 * to the head page instead of next.
 	 */
 	if (iter->head_page == cpu_buffer->reader_page)
-		iter->head_page = cpu_buffer->head_page;
+		iter->head_page = rb_set_head_page(cpu_buffer);
 	else
 		rb_inc_page(cpu_buffer, &iter->head_page);
 
@@ -1122,6 +1558,163 @@ rb_update_event(struct ring_buffer_event *event,
 	}
 }
 
+/*
+ * rb_handle_head_page - writer hit the head page
+ *
+ * Returns: +1 to retry page
+ *           0 to continue
+ *          -1 on error
+ */
+static int
+rb_handle_head_page(struct ring_buffer_per_cpu *cpu_buffer,
+		    struct buffer_page *tail_page,
+		    struct buffer_page *next_page)
+{
+	struct buffer_page *new_head;
+	int entries;
+	int type;
+	int ret;
+
+	entries = rb_page_entries(next_page);
+
+	/*
+	 * The hard part is here. We need to move the head
+	 * forward, and protect against both readers on
+	 * other CPUs and writers coming in via interrupts.
+	 */
+	type = rb_head_page_set_update(cpu_buffer, next_page, tail_page,
+				       RB_PAGE_HEAD);
+
+	/*
+	 * type can be one of four:
+	 *  NORMAL - an interrupt already moved it for us
+	 *  HEAD   - we are the first to get here.
+	 *  UPDATE - we are the interrupt interrupting
+	 *           a current move.
+	 *  MOVED  - a reader on another CPU moved the next
+	 *           pointer to its reader page. Give up
+	 *           and try again.
+	 */
+
+	switch (type) {
+	case RB_PAGE_HEAD:
+		/*
+		 * We changed the head to UPDATE, thus
+		 * it is our responsibility to update
+		 * the counters.
+		 */
+		local_add(entries, &cpu_buffer->overrun);
+
+		/*
+		 * The entries will be zeroed out when we move the
+		 * tail page.
+		 */
+
+		/* still more to do */
+		break;
+
+	case RB_PAGE_UPDATE:
+		/*
+		 * This is an interrupt that interrupt the
+		 * previous update. Still more to do.
+		 */
+		break;
+	case RB_PAGE_NORMAL:
+		/*
+		 * An interrupt came in before the update
+		 * and processed this for us.
+		 * Nothing left to do.
+		 */
+		return 1;
+	case RB_PAGE_MOVED:
+		/*
+		 * The reader is on another CPU and just did
+		 * a swap with our next_page.
+		 * Try again.
+		 */
+		return 1;
+	default:
+		RB_WARN_ON(cpu_buffer, 1); /* WTF??? */
+		return -1;
+	}
+
+	/*
+	 * Now that we are here, the old head pointer is
+	 * set to UPDATE. This will keep the reader from
+	 * swapping the head page with the reader page.
+	 * The reader (on another CPU) will spin till
+	 * we are finished.
+	 *
+	 * We just need to protect against interrupts
+	 * doing the job. We will set the next pointer
+	 * to HEAD. After that, we set the old pointer
+	 * to NORMAL, but only if it was HEAD before.
+	 * otherwise we are an interrupt, and only
+	 * want the outer most commit to reset it.
+	 */
+	new_head = next_page;
+	rb_inc_page(cpu_buffer, &new_head);
+
+	ret = rb_head_page_set_head(cpu_buffer, new_head, next_page,
+				    RB_PAGE_NORMAL);
+
+	/*
+	 * Valid returns are:
+	 *  HEAD   - an interrupt came in and already set it.
+	 *  NORMAL - One of two things:
+	 *            1) We really set it.
+	 *            2) A bunch of interrupts came in and moved
+	 *               the page forward again.
+	 */
+	switch (ret) {
+	case RB_PAGE_HEAD:
+	case RB_PAGE_NORMAL:
+		/* OK */
+		break;
+	default:
+		RB_WARN_ON(cpu_buffer, 1);
+		return -1;
+	}
+
+	/*
+	 * It is possible that an interrupt came in,
+	 * set the head up, then more interrupts came in
+	 * and moved it again. When we get back here,
+	 * the page would have been set to NORMAL but we
+	 * just set it back to HEAD.
+	 *
+	 * How do you detect this? Well, if that happened
+	 * the tail page would have moved.
+	 */
+	if (ret == RB_PAGE_NORMAL) {
+		/*
+		 * If the tail had moved passed next, then we need
+		 * to reset the pointer.
+		 */
+		if (cpu_buffer->tail_page != tail_page &&
+		    cpu_buffer->tail_page != next_page)
+			rb_head_page_set_normal(cpu_buffer, new_head,
+						next_page,
+						RB_PAGE_HEAD);
+	}
+
+	/*
+	 * If this was the outer most commit (the one that
+	 * changed the original pointer from HEAD to UPDATE),
+	 * then it is up to us to reset it to NORMAL.
+	 */
+	if (type == RB_PAGE_HEAD) {
+		ret = rb_head_page_set_normal(cpu_buffer, next_page,
+					      tail_page,
+					      RB_PAGE_UPDATE);
+		if (RB_WARN_ON(cpu_buffer,
+			       ret != RB_PAGE_UPDATE))
+			return -1;
+	}
+
+	return 0;
+}
+
 static unsigned rb_calculate_event_length(unsigned length)
 {
 	struct ring_buffer_event event; /* Used only for sizeof array */
@@ -1185,9 +1778,6 @@ rb_reset_tail(struct ring_buffer_per_cpu *cpu_buffer,
 	event->type_len = RINGBUF_TYPE_PADDING;
 	/* time delta must be non zero */
 	event->time_delta = 1;
-	/* Account for this as an entry */
-	local_inc(&tail_page->entries);
-	local_inc(&cpu_buffer->entries);
 
 	/* Set write to end of buffer */
 	length = (tail + length) - BUF_PAGE_SIZE;
@@ -1200,96 +1790,93 @@ rb_move_tail(struct ring_buffer_per_cpu *cpu_buffer,
 	     struct buffer_page *commit_page,
 	     struct buffer_page *tail_page, u64 *ts)
 {
-	struct buffer_page *next_page, *head_page, *reader_page;
 	struct ring_buffer *buffer = cpu_buffer->buffer;
-	bool lock_taken = false;
-	unsigned long flags;
+	struct buffer_page *next_page;
+	int ret;
 
 	next_page = tail_page;
 
-	local_irq_save(flags);
-	/*
-	 * Since the write to the buffer is still not
-	 * fully lockless, we must be careful with NMIs.
-	 * The locks in the writers are taken when a write
-	 * crosses to a new page. The locks protect against
-	 * races with the readers (this will soon be fixed
-	 * with a lockless solution).
-	 *
-	 * Because we can not protect against NMIs, and we
-	 * want to keep traces reentrant, we need to manage
-	 * what happens when we are in an NMI.
-	 *
-	 * NMIs can happen after we take the lock.
-	 * If we are in an NMI, only take the lock
-	 * if it is not already taken. Otherwise
-	 * simply fail.
-	 */
-	if (unlikely(in_nmi())) {
-		if (!__raw_spin_trylock(&cpu_buffer->lock)) {
-			cpu_buffer->nmi_dropped++;
-			goto out_reset;
-		}
-	} else
-		__raw_spin_lock(&cpu_buffer->lock);
-
-	lock_taken = true;
-
 	rb_inc_page(cpu_buffer, &next_page);
 
-	head_page = cpu_buffer->head_page;
-	reader_page = cpu_buffer->reader_page;
-
-	/* we grabbed the lock before incrementing */
-	if (RB_WARN_ON(cpu_buffer, next_page == reader_page))
-		goto out_reset;
-
 	/*
 	 * If for some reason, we had an interrupt storm that made
 	 * it all the way around the buffer, bail, and warn
 	 * about it.
 	 */
 	if (unlikely(next_page == commit_page)) {
-		cpu_buffer->commit_overrun++;
+		local_inc(&cpu_buffer->commit_overrun);
 		goto out_reset;
 	}
 
-	if (next_page == head_page) {
-		if (!(buffer->flags & RB_FL_OVERWRITE))
-			goto out_reset;
-
-		/* tail_page has not moved yet? */
-		if (tail_page == cpu_buffer->tail_page) {
-			/* count overflows */
-			cpu_buffer->overrun +=
-				local_read(&head_page->entries);
+	/*
+	 * This is where the fun begins!
+	 *
+	 * We are fighting against races between a reader that
+	 * could be on another CPU trying to swap its reader
+	 * page with the buffer head.
+	 *
+	 * We are also fighting against interrupts coming in and
+	 * moving the head or tail on us as well.
+	 *
+	 * If the next page is the head page then we have filled
+	 * the buffer, unless the commit page is still on the
+	 * reader page.
+	 */
+	if (rb_is_head_page(cpu_buffer, next_page, &tail_page->list)) {
 
-			rb_inc_page(cpu_buffer, &head_page);
-			cpu_buffer->head_page = head_page;
-			cpu_buffer->head_page->read = 0;
+		/*
+		 * If the commit is not on the reader page, then
+		 * move the header page.
+		 */
+		if (!rb_is_reader_page(cpu_buffer->commit_page)) {
+			/*
+			 * If we are not in overwrite mode,
+			 * this is easy, just stop here.
+			 */
+			if (!(buffer->flags & RB_FL_OVERWRITE))
+				goto out_reset;
+
+			ret = rb_handle_head_page(cpu_buffer,
+						  tail_page,
+						  next_page);
+			if (ret < 0)
+				goto out_reset;
+			if (ret)
+				goto out_again;
+		} else {
+			/*
+			 * We need to be careful here too. The
+			 * commit page could still be on the reader
+			 * page. We could have a small buffer, and
+			 * have filled up the buffer with events
+			 * from interrupts and such, and wrapped.
+			 *
+			 * Note, if the tail page is also the on the
+			 * reader_page, we let it move out.
+			 */
+			if (unlikely((cpu_buffer->commit_page !=
+				      cpu_buffer->tail_page) &&
+				     (cpu_buffer->commit_page ==
+				      cpu_buffer->reader_page))) {
+				local_inc(&cpu_buffer->commit_overrun);
+				goto out_reset;
+			}
 		}
 	}
 
-	/*
-	 * If the tail page is still the same as what we think
-	 * it is, then it is up to us to update the tail
-	 * pointer.
-	 */
-	if (tail_page == cpu_buffer->tail_page) {
-		local_set(&next_page->write, 0);
-		local_set(&next_page->entries, 0);
-		local_set(&next_page->page->commit, 0);
-		cpu_buffer->tail_page = next_page;
-
-		/* reread the time stamp */
-		*ts = rb_time_stamp(buffer, cpu_buffer->cpu);
-		cpu_buffer->tail_page->page->time_stamp = *ts;
+	ret = rb_tail_page_update(cpu_buffer, tail_page, next_page);
+	if (ret) {
+		/*
+		 * Nested commits always have zero deltas, so
+		 * just reread the time stamp
+		 */
+		*ts = rb_time_stamp(buffer);
+		next_page->page->time_stamp = *ts;
 	}
 
-	rb_reset_tail(cpu_buffer, tail_page, tail, length);
+ out_again:
 
-	__raw_spin_unlock(&cpu_buffer->lock);
-	local_irq_restore(flags);
+	rb_reset_tail(cpu_buffer, tail_page, tail, length);
 
 	/* fail and let the caller try again */
 	return ERR_PTR(-EAGAIN);
@@ -1298,9 +1885,6 @@ rb_move_tail(struct ring_buffer_per_cpu *cpu_buffer,
 	/* reset write */
 	rb_reset_tail(cpu_buffer, tail_page, tail, length);
 
-	if (likely(lock_taken))
-		__raw_spin_unlock(&cpu_buffer->lock);
-	local_irq_restore(flags);
 	return NULL;
 }
 
@@ -1317,6 +1901,9 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer,
 	barrier();
 	tail_page = cpu_buffer->tail_page;
 	write = local_add_return(length, &tail_page->write);
+
+	/* set write to only the index of the write */
+	write &= RB_WRITE_MASK;
 	tail = write - length;
 
 	/* See if we shot pass the end of this buffer page */
@@ -1361,12 +1948,16 @@ rb_try_to_discard(struct ring_buffer_per_cpu *cpu_buffer,
 	bpage = cpu_buffer->tail_page;
 
 	if (bpage->page == (void *)addr && rb_page_write(bpage) == old_index) {
+		unsigned long write_mask =
+			local_read(&bpage->write) & ~RB_WRITE_MASK;
 		/*
 		 * This is on the tail page. It is possible that
 		 * a write could come in and move the tail page
 		 * and write to the next page. That is fine
 		 * because we just shorten what is on this page.
 		 */
+		old_index += write_mask;
+		new_index += write_mask;
 		index = local_cmpxchg(&bpage->write, old_index, new_index);
 		if (index == old_index)
 			return 1;
@@ -1482,7 +2073,8 @@ static void rb_end_commit(struct ring_buffer_per_cpu *cpu_buffer)
 }
 
 static struct ring_buffer_event *
-rb_reserve_next_event(struct ring_buffer_per_cpu *cpu_buffer,
+rb_reserve_next_event(struct ring_buffer *buffer,
+		      struct ring_buffer_per_cpu *cpu_buffer,
 		      unsigned long length)
 {
 	struct ring_buffer_event *event;
@@ -1492,6 +2084,21 @@ rb_reserve_next_event(struct ring_buffer_per_cpu *cpu_buffer,
 
 	rb_start_commit(cpu_buffer);
 
+#ifdef CONFIG_RING_BUFFER_ALLOW_SWAP
+	/*
+	 * Due to the ability to swap a cpu buffer from a buffer
+	 * it is possible it was swapped before we committed.
+	 * (committing stops a swap). We check for it here and
+	 * if it happened, we have to fail the write.
+	 */
+	barrier();
+	if (unlikely(ACCESS_ONCE(cpu_buffer->buffer) != buffer)) {
+		local_dec(&cpu_buffer->committing);
+		local_dec(&cpu_buffer->commits);
+		return NULL;
+	}
+#endif
+
 	length = rb_calculate_event_length(length);
  again:
 	/*
@@ -1506,7 +2113,7 @@ rb_reserve_next_event(struct ring_buffer_per_cpu *cpu_buffer,
 	if (RB_WARN_ON(cpu_buffer, ++nr_loops > 1000))
 		goto out_fail;
 
-	ts = rb_time_stamp(cpu_buffer->buffer, cpu_buffer->cpu);
+	ts = rb_time_stamp(cpu_buffer->buffer);
 
 	/*
 	 * Only the first commit can update the timestamp.
@@ -1652,7 +2259,7 @@ ring_buffer_lock_reserve(struct ring_buffer *buffer, unsigned long length)
 	if (length > BUF_MAX_DATA_SIZE)
 		goto out;
 
-	event = rb_reserve_next_event(cpu_buffer, length);
+	event = rb_reserve_next_event(buffer, cpu_buffer, length);
 	if (!event)
 		goto out;
 
@@ -1675,18 +2282,23 @@ ring_buffer_lock_reserve(struct ring_buffer *buffer, unsigned long length)
 }
 EXPORT_SYMBOL_GPL(ring_buffer_lock_reserve);
 
-static void rb_commit(struct ring_buffer_per_cpu *cpu_buffer,
+static void
+rb_update_write_stamp(struct ring_buffer_per_cpu *cpu_buffer,
 		      struct ring_buffer_event *event)
 {
-	local_inc(&cpu_buffer->entries);
-
 	/*
 	 * The event first in the commit queue updates the
 	 * time stamp.
 	 */
 	if (rb_event_is_commit(cpu_buffer, event))
 		cpu_buffer->write_stamp += event->time_delta;
+}
 
+static void rb_commit(struct ring_buffer_per_cpu *cpu_buffer,
+		      struct ring_buffer_event *event)
+{
+	local_inc(&cpu_buffer->entries);
+	rb_update_write_stamp(cpu_buffer, event);
 	rb_end_commit(cpu_buffer);
 }
 
@@ -1733,32 +2345,57 @@ static inline void rb_event_discard(struct ring_buffer_event *event)
 		event->time_delta = 1;
 }
 
-/**
- * ring_buffer_event_discard - discard any event in 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.
+/*
+ * Decrement the entries to the page that an event is on.
+ * The event does not even need to exist, only the pointer
+ * to the page it is on. This may only be called before the commit
+ * takes place.
  */
-void ring_buffer_event_discard(struct ring_buffer_event *event)
+static inline void
+rb_decrement_entry(struct ring_buffer_per_cpu *cpu_buffer,
+		   struct ring_buffer_event *event)
 {
-	rb_event_discard(event);
+	unsigned long addr = (unsigned long)event;
+	struct buffer_page *bpage = cpu_buffer->commit_page;
+	struct buffer_page *start;
+
+	addr &= PAGE_MASK;
+
+	/* Do the likely case first */
+	if (likely(bpage->page == (void *)addr)) {
+		local_dec(&bpage->entries);
+		return;
+	}
+
+	/*
+	 * Because the commit page may be on the reader page we
+	 * start with the next page and check the end loop there.
+	 */
+	rb_inc_page(cpu_buffer, &bpage);
+	start = bpage;
+	do {
+		if (bpage->page == (void *)addr) {
+			local_dec(&bpage->entries);
+			return;
+		}
+		rb_inc_page(cpu_buffer, &bpage);
+	} while (bpage != start);
+
+	/* commit not part of this buffer?? */
+	RB_WARN_ON(cpu_buffer, 1);
 }
-EXPORT_SYMBOL_GPL(ring_buffer_event_discard);
 
 /**
  * ring_buffer_commit_discard - discard an event that has not been committed
  * @buffer: the ring buffer
  * @event: non committed event to discard
  *
- * This is similar to ring_buffer_event_discard but must only be
- * performed on an event that has not been committed yet. The difference
- * is that this will also try to free the event from the ring buffer
+ * Sometimes an 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.
+ *
+ * This function only works if it is called before the the item has been
+ * committed. It will try to free the event from the ring buffer
  * if another event has not been added behind it.
  *
  * If another event has been added behind it, it will set the event
@@ -1786,14 +2423,15 @@ void ring_buffer_discard_commit(struct ring_buffer *buffer,
 	 */
 	RB_WARN_ON(buffer, !local_read(&cpu_buffer->committing));
 
+	rb_decrement_entry(cpu_buffer, event);
 	if (rb_try_to_discard(cpu_buffer, event))
 		goto out;
 
 	/*
 	 * The commit is still visible by the reader, so we
-	 * must increment entries.
+	 * must still update the timestamp.
 	 */
-	local_inc(&cpu_buffer->entries);
+	rb_update_write_stamp(cpu_buffer, event);
  out:
 	rb_end_commit(cpu_buffer);
 
@@ -1854,7 +2492,7 @@ int ring_buffer_write(struct ring_buffer *buffer,
 	if (length > BUF_MAX_DATA_SIZE)
 		goto out;
 
-	event = rb_reserve_next_event(cpu_buffer, length);
+	event = rb_reserve_next_event(buffer, cpu_buffer, length);
 	if (!event)
 		goto out;
 
@@ -1875,9 +2513,13 @@ EXPORT_SYMBOL_GPL(ring_buffer_write);
 static int rb_per_cpu_empty(struct ring_buffer_per_cpu *cpu_buffer)
 {
 	struct buffer_page *reader = cpu_buffer->reader_page;
-	struct buffer_page *head = cpu_buffer->head_page;
+	struct buffer_page *head = rb_set_head_page(cpu_buffer);
 	struct buffer_page *commit = cpu_buffer->commit_page;
 
+	/* In case of error, head will be NULL */
+	if (unlikely(!head))
+		return 1;
+
 	return reader->read == rb_page_commit(reader) &&
 		(commit == reader ||
 		 (commit == head &&
@@ -1968,7 +2610,7 @@ unsigned long ring_buffer_entries_cpu(struct ring_buffer *buffer, int cpu)
 		return 0;
 
 	cpu_buffer = buffer->buffers[cpu];
-	ret = (local_read(&cpu_buffer->entries) - cpu_buffer->overrun)
+	ret = (local_read(&cpu_buffer->entries) - local_read(&cpu_buffer->overrun))
 		- cpu_buffer->read;
 
 	return ret;
@@ -1989,33 +2631,13 @@ unsigned long ring_buffer_overrun_cpu(struct ring_buffer *buffer, int cpu)
 		return 0;
 
 	cpu_buffer = buffer->buffers[cpu];
-	ret = cpu_buffer->overrun;
+	ret = local_read(&cpu_buffer->overrun);
 
 	return ret;
 }
 EXPORT_SYMBOL_GPL(ring_buffer_overrun_cpu);
 
 /**
- * ring_buffer_nmi_dropped_cpu - get the number of nmis that were dropped
- * @buffer: The ring buffer
- * @cpu: The per CPU buffer to get the number of overruns from
- */
-unsigned long ring_buffer_nmi_dropped_cpu(struct ring_buffer *buffer, int cpu)
-{
-	struct ring_buffer_per_cpu *cpu_buffer;
-	unsigned long ret;
-
-	if (!cpumask_test_cpu(cpu, buffer->cpumask))
-		return 0;
-
-	cpu_buffer = buffer->buffers[cpu];
-	ret = cpu_buffer->nmi_dropped;
-
-	return ret;
-}
-EXPORT_SYMBOL_GPL(ring_buffer_nmi_dropped_cpu);
-
-/**
  * ring_buffer_commit_overrun_cpu - get the number of overruns caused by commits
  * @buffer: The ring buffer
  * @cpu: The per CPU buffer to get the number of overruns from
@@ -2030,7 +2652,7 @@ ring_buffer_commit_overrun_cpu(struct ring_buffer *buffer, int cpu)
 		return 0;
 
 	cpu_buffer = buffer->buffers[cpu];
-	ret = cpu_buffer->commit_overrun;
+	ret = local_read(&cpu_buffer->commit_overrun);
 
 	return ret;
 }
@@ -2053,7 +2675,7 @@ unsigned long ring_buffer_entries(struct ring_buffer *buffer)
 	for_each_buffer_cpu(buffer, cpu) {
 		cpu_buffer = buffer->buffers[cpu];
 		entries += (local_read(&cpu_buffer->entries) -
-			    cpu_buffer->overrun) - cpu_buffer->read;
+			    local_read(&cpu_buffer->overrun)) - cpu_buffer->read;
 	}
 
 	return entries;
@@ -2061,7 +2683,7 @@ unsigned long ring_buffer_entries(struct ring_buffer *buffer)
 EXPORT_SYMBOL_GPL(ring_buffer_entries);
 
 /**
- * ring_buffer_overrun_cpu - get the number of overruns in buffer
+ * ring_buffer_overruns - get the number of overruns in buffer
  * @buffer: The ring buffer
  *
  * Returns the total number of overruns in the ring buffer
@@ -2076,7 +2698,7 @@ unsigned long ring_buffer_overruns(struct ring_buffer *buffer)
 	/* if you care about this being correct, lock the buffer */
 	for_each_buffer_cpu(buffer, cpu) {
 		cpu_buffer = buffer->buffers[cpu];
-		overruns += cpu_buffer->overrun;
+		overruns += local_read(&cpu_buffer->overrun);
 	}
 
 	return overruns;
@@ -2089,8 +2711,10 @@ static void rb_iter_reset(struct ring_buffer_iter *iter)
 
 	/* Iterator usage is expected to have record disabled */
 	if (list_empty(&cpu_buffer->reader_page->list)) {
-		iter->head_page = cpu_buffer->head_page;
-		iter->head = cpu_buffer->head_page->read;
+		iter->head_page = rb_set_head_page(cpu_buffer);
+		if (unlikely(!iter->head_page))
+			return;
+		iter->head = iter->head_page->read;
 	} else {
 		iter->head_page = cpu_buffer->reader_page;
 		iter->head = cpu_buffer->reader_page->read;
@@ -2207,6 +2831,7 @@ rb_get_reader_page(struct ring_buffer_per_cpu *cpu_buffer)
 	struct buffer_page *reader = NULL;
 	unsigned long flags;
 	int nr_loops = 0;
+	int ret;
 
 	local_irq_save(flags);
 	__raw_spin_lock(&cpu_buffer->lock);
@@ -2240,30 +2865,56 @@ rb_get_reader_page(struct ring_buffer_per_cpu *cpu_buffer)
 		goto out;
 
 	/*
-	 * Splice the empty reader page into the list around the head.
 	 * Reset the reader page to size zero.
 	 */
+	local_set(&cpu_buffer->reader_page->write, 0);
+	local_set(&cpu_buffer->reader_page->entries, 0);
+	local_set(&cpu_buffer->reader_page->page->commit, 0);
 
-	reader = cpu_buffer->head_page;
+ spin:
+	/*
+	 * Splice the empty reader page into the list around the head.
+	 */
+	reader = rb_set_head_page(cpu_buffer);
 	cpu_buffer->reader_page->list.next = reader->list.next;
 	cpu_buffer->reader_page->list.prev = reader->list.prev;
 
-	local_set(&cpu_buffer->reader_page->write, 0);
-	local_set(&cpu_buffer->reader_page->entries, 0);
-	local_set(&cpu_buffer->reader_page->page->commit, 0);
+	/*
+	 * cpu_buffer->pages just needs to point to the buffer, it
+	 *  has no specific buffer page to point to. Lets move it out
+	 *  of our way so we don't accidently swap it.
+	 */
+	cpu_buffer->pages = reader->list.prev;
 
-	/* Make the reader page now replace the head */
-	reader->list.prev->next = &cpu_buffer->reader_page->list;
-	reader->list.next->prev = &cpu_buffer->reader_page->list;
+	/* The reader page will be pointing to the new head */
+	rb_set_list_to_head(cpu_buffer, &cpu_buffer->reader_page->list);
 
 	/*
-	 * If the tail is on the reader, then we must set the head
-	 * to the inserted page, otherwise we set it one before.
+	 * Here's the tricky part.
+	 *
+	 * We need to move the pointer past the header page.
+	 * But we can only do that if a writer is not currently
+	 * moving it. The page before the header page has the
+	 * flag bit '1' set if it is pointing to the page we want.
+	 * but if the writer is in the process of moving it
+	 * than it will be '2' or already moved '0'.
 	 */
-	cpu_buffer->head_page = cpu_buffer->reader_page;
 
-	if (cpu_buffer->commit_page != reader)
-		rb_inc_page(cpu_buffer, &cpu_buffer->head_page);
+	ret = rb_head_page_replace(reader, cpu_buffer->reader_page);
+
+	/*
+	 * If we did not convert it, then we must try again.
+	 */
+	if (!ret)
+		goto spin;
+
+	/*
+	 * Yeah! We succeeded in replacing the page.
+	 *
+	 * Now make the new head point back to the reader page.
+	 */
+	reader->list.next->prev = &cpu_buffer->reader_page->list;
+	rb_inc_page(cpu_buffer, &cpu_buffer->head_page);
 
 	/* Finally update the reader page to the new head */
 	cpu_buffer->reader_page = reader;
@@ -2292,8 +2943,7 @@ static void rb_advance_reader(struct ring_buffer_per_cpu *cpu_buffer)
 
 	event = rb_reader_event(cpu_buffer);
 
-	if (event->type_len <= RINGBUF_TYPE_DATA_TYPE_LEN_MAX
-			|| rb_discarded_event(event))
+	if (event->type_len <= RINGBUF_TYPE_DATA_TYPE_LEN_MAX)
 		cpu_buffer->read++;
 
 	rb_update_read_stamp(cpu_buffer, event);
@@ -2347,15 +2997,12 @@ static void rb_advance_iter(struct ring_buffer_iter *iter)
 }
 
 static struct ring_buffer_event *
-rb_buffer_peek(struct ring_buffer *buffer, int cpu, u64 *ts)
+rb_buffer_peek(struct ring_buffer_per_cpu *cpu_buffer, u64 *ts)
 {
-	struct ring_buffer_per_cpu *cpu_buffer;
 	struct ring_buffer_event *event;
 	struct buffer_page *reader;
 	int nr_loops = 0;
 
-	cpu_buffer = buffer->buffers[cpu];
-
  again:
 	/*
 	 * We repeat when a timestamp is encountered. It is possible
@@ -2399,7 +3046,7 @@ 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(buffer,
+			ring_buffer_normalize_time_stamp(cpu_buffer->buffer,
 							 cpu_buffer->cpu, ts);
 		}
 		return event;
@@ -2518,17 +3165,15 @@ ring_buffer_peek(struct ring_buffer *buffer, int cpu, u64 *ts)
 	local_irq_save(flags);
 	if (dolock)
 		spin_lock(&cpu_buffer->reader_lock);
-	event = rb_buffer_peek(buffer, cpu, ts);
+	event = rb_buffer_peek(cpu_buffer, ts);
 	if (event && event->type_len == RINGBUF_TYPE_PADDING)
 		rb_advance_reader(cpu_buffer);
 	if (dolock)
 		spin_unlock(&cpu_buffer->reader_lock);
 	local_irq_restore(flags);
 
-	if (event && event->type_len == RINGBUF_TYPE_PADDING) {
-		cpu_relax();
+	if (event && event->type_len == RINGBUF_TYPE_PADDING)
 		goto again;
-	}
 
 	return event;
 }
@@ -2553,10 +3198,8 @@ ring_buffer_iter_peek(struct ring_buffer_iter *iter, u64 *ts)
 	event = rb_iter_peek(iter, ts);
 	spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
 
-	if (event && event->type_len == RINGBUF_TYPE_PADDING) {
-		cpu_relax();
+	if (event && event->type_len == RINGBUF_TYPE_PADDING)
 		goto again;
-	}
 
 	return event;
 }
@@ -2591,7 +3234,7 @@ ring_buffer_consume(struct ring_buffer *buffer, int cpu, u64 *ts)
 	if (dolock)
 		spin_lock(&cpu_buffer->reader_lock);
 
-	event = rb_buffer_peek(buffer, cpu, ts);
+	event = rb_buffer_peek(cpu_buffer, ts);
 	if (event)
 		rb_advance_reader(cpu_buffer);
 
@@ -2602,10 +3245,8 @@ ring_buffer_consume(struct ring_buffer *buffer, int cpu, u64 *ts)
  out:
 	preempt_enable();
 
-	if (event && event->type_len == RINGBUF_TYPE_PADDING) {
-		cpu_relax();
+	if (event && event->type_len == RINGBUF_TYPE_PADDING)
 		goto again;
-	}
 
 	return event;
 }
@@ -2685,21 +3326,19 @@ 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);
+ again:
 	event = rb_iter_peek(iter, ts);
 	if (!event)
 		goto out;
 
+	if (event->type_len == RINGBUF_TYPE_PADDING)
+		goto again;
+
 	rb_advance_iter(iter);
  out:
 	spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
 
-	if (event && event->type_len == RINGBUF_TYPE_PADDING) {
-		cpu_relax();
-		goto again;
-	}
-
 	return event;
 }
 EXPORT_SYMBOL_GPL(ring_buffer_read);
@@ -2717,8 +3356,10 @@ EXPORT_SYMBOL_GPL(ring_buffer_size);
 static void
 rb_reset_cpu(struct ring_buffer_per_cpu *cpu_buffer)
 {
+	rb_head_page_deactivate(cpu_buffer);
+
 	cpu_buffer->head_page
-		= list_entry(cpu_buffer->pages.next, struct buffer_page, list);
+		= list_entry(cpu_buffer->pages, struct buffer_page, list);
 	local_set(&cpu_buffer->head_page->write, 0);
 	local_set(&cpu_buffer->head_page->entries, 0);
 	local_set(&cpu_buffer->head_page->page->commit, 0);
@@ -2734,16 +3375,17 @@ rb_reset_cpu(struct ring_buffer_per_cpu *cpu_buffer)
 	local_set(&cpu_buffer->reader_page->page->commit, 0);
 	cpu_buffer->reader_page->read = 0;
 
-	cpu_buffer->nmi_dropped = 0;
-	cpu_buffer->commit_overrun = 0;
-	cpu_buffer->overrun = 0;
-	cpu_buffer->read = 0;
+	local_set(&cpu_buffer->commit_overrun, 0);
+	local_set(&cpu_buffer->overrun, 0);
 	local_set(&cpu_buffer->entries, 0);
 	local_set(&cpu_buffer->committing, 0);
 	local_set(&cpu_buffer->commits, 0);
+	cpu_buffer->read = 0;
 
 	cpu_buffer->write_stamp = 0;
 	cpu_buffer->read_stamp = 0;
+
+	rb_head_page_activate(cpu_buffer);
 }
 
 /**
@@ -2763,12 +3405,16 @@ void ring_buffer_reset_cpu(struct ring_buffer *buffer, int cpu)
 
 	spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
 
+	if (RB_WARN_ON(cpu_buffer, local_read(&cpu_buffer->committing)))
+		goto out;
+
 	__raw_spin_lock(&cpu_buffer->lock);
 
 	rb_reset_cpu(cpu_buffer);
 
 	__raw_spin_unlock(&cpu_buffer->lock);
 
+ out:
 	spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
 
 	atomic_dec(&cpu_buffer->record_disabled);
@@ -2851,6 +3497,7 @@ int ring_buffer_empty_cpu(struct ring_buffer *buffer, int cpu)
 }
 EXPORT_SYMBOL_GPL(ring_buffer_empty_cpu);
 
+#ifdef CONFIG_RING_BUFFER_ALLOW_SWAP
 /**
  * ring_buffer_swap_cpu - swap a CPU buffer between two ring buffers
  * @buffer_a: One buffer to swap with
@@ -2905,20 +3552,28 @@ int ring_buffer_swap_cpu(struct ring_buffer *buffer_a,
 	atomic_inc(&cpu_buffer_a->record_disabled);
 	atomic_inc(&cpu_buffer_b->record_disabled);
 
+	ret = -EBUSY;
+	if (local_read(&cpu_buffer_a->committing))
+		goto out_dec;
+	if (local_read(&cpu_buffer_b->committing))
+		goto out_dec;
+
 	buffer_a->buffers[cpu] = cpu_buffer_b;
 	buffer_b->buffers[cpu] = cpu_buffer_a;
 
 	cpu_buffer_b->buffer = buffer_a;
 	cpu_buffer_a->buffer = buffer_b;
 
+	ret = 0;
+
+out_dec:
 	atomic_dec(&cpu_buffer_a->record_disabled);
 	atomic_dec(&cpu_buffer_b->record_disabled);
-
-	ret = 0;
 out:
 	return ret;
 }
 EXPORT_SYMBOL_GPL(ring_buffer_swap_cpu);
+#endif /* CONFIG_RING_BUFFER_ALLOW_SWAP */
 
 /**
  * ring_buffer_alloc_read_page - allocate a page to read from buffer
@@ -3091,7 +3746,7 @@ int ring_buffer_read_page(struct ring_buffer *buffer,
 		read = 0;
 	} else {
 		/* update the entry counter */
-		cpu_buffer->read += local_read(&reader->entries);
+		cpu_buffer->read += rb_page_entries(reader);
 
 		/* swap the pages */
 		rb_init_page(bpage);
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 8c358395d338..b20d3ec75de9 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -43,14 +43,11 @@
 
 #define TRACE_BUFFER_FLAGS	(RB_FL_OVERWRITE)
 
-unsigned long __read_mostly	tracing_max_latency;
-unsigned long __read_mostly	tracing_thresh;
-
 /*
  * On boot up, the ring buffer is set to the minimum size, so that
  * we do not waste memory on systems that are not using tracing.
  */
-static int ring_buffer_expanded;
+int ring_buffer_expanded;
 
 /*
  * We need to change this state when a selftest is running.
@@ -64,7 +61,7 @@ static bool __read_mostly tracing_selftest_running;
 /*
  * If a tracer is running, we do not want to run SELFTEST.
  */
-static bool __read_mostly tracing_selftest_disabled;
+bool __read_mostly tracing_selftest_disabled;
 
 /* For tracers that don't implement custom flags */
 static struct tracer_opt dummy_tracer_opt[] = {
@@ -89,7 +86,7 @@ static int dummy_set_flag(u32 old_flags, u32 bit, int set)
  */
 static int tracing_disabled = 1;
 
-static DEFINE_PER_CPU(local_t, ftrace_cpu_disabled);
+DEFINE_PER_CPU(local_t, ftrace_cpu_disabled);
 
 static inline void ftrace_disable_cpu(void)
 {
@@ -128,13 +125,13 @@ int ftrace_dump_on_oops;
 
 static int tracing_set_tracer(const char *buf);
 
-#define BOOTUP_TRACER_SIZE		100
-static char bootup_tracer_buf[BOOTUP_TRACER_SIZE] __initdata;
+#define MAX_TRACER_SIZE		100
+static char bootup_tracer_buf[MAX_TRACER_SIZE] __initdata;
 static char *default_bootup_tracer;
 
 static int __init set_ftrace(char *str)
 {
-	strncpy(bootup_tracer_buf, str, BOOTUP_TRACER_SIZE);
+	strncpy(bootup_tracer_buf, str, MAX_TRACER_SIZE);
 	default_bootup_tracer = bootup_tracer_buf;
 	/* We are using ftrace early, expand it */
 	ring_buffer_expanded = 1;
@@ -172,10 +169,11 @@ static struct trace_array	global_trace;
 
 static DEFINE_PER_CPU(struct trace_array_cpu, global_trace_cpu);
 
-int filter_current_check_discard(struct ftrace_event_call *call, void *rec,
+int filter_current_check_discard(struct ring_buffer *buffer,
+				 struct ftrace_event_call *call, void *rec,
 				 struct ring_buffer_event *event)
 {
-	return filter_check_discard(call, rec, global_trace.buffer, event);
+	return filter_check_discard(call, rec, buffer, event);
 }
 EXPORT_SYMBOL_GPL(filter_current_check_discard);
 
@@ -244,13 +242,6 @@ static struct tracer		*trace_types __read_mostly;
 static struct tracer		*current_trace __read_mostly;
 
 /*
- * max_tracer_type_len is used to simplify the allocating of
- * buffers to read userspace tracer names. We keep track of
- * the longest tracer name registered.
- */
-static int			max_tracer_type_len;
-
-/*
  * trace_types_lock is used to protect the trace_types list.
  * This lock is also used to keep user access serialized.
  * Accesses from userspace will grab this lock while userspace
@@ -266,6 +257,9 @@ unsigned long trace_flags = TRACE_ITER_PRINT_PARENT | TRACE_ITER_PRINTK |
 	TRACE_ITER_ANNOTATE | TRACE_ITER_CONTEXT_INFO | TRACE_ITER_SLEEP_TIME |
 	TRACE_ITER_GRAPH_TIME;
 
+static int trace_stop_count;
+static DEFINE_SPINLOCK(tracing_start_lock);
+
 /**
  * trace_wake_up - wake up tasks waiting for trace input
  *
@@ -274,12 +268,18 @@ unsigned long trace_flags = TRACE_ITER_PRINT_PARENT | TRACE_ITER_PRINTK |
  */
 void trace_wake_up(void)
 {
+	int cpu;
+
+	if (trace_flags & TRACE_ITER_BLOCK)
+		return;
 	/*
 	 * The runqueue_is_locked() can fail, but this is the best we
 	 * have for now:
 	 */
-	if (!(trace_flags & TRACE_ITER_BLOCK) && !runqueue_is_locked())
+	cpu = get_cpu();
+	if (!runqueue_is_locked(cpu))
 		wake_up(&trace_wait);
+	put_cpu();
 }
 
 static int __init set_buf_size(char *str)
@@ -323,49 +323,125 @@ static const char *trace_options[] = {
 	"printk-msg-only",
 	"context-info",
 	"latency-format",
-	"global-clock",
 	"sleep-time",
 	"graph-time",
 	NULL
 };
 
+static struct {
+	u64 (*func)(void);
+	const char *name;
+} trace_clocks[] = {
+	{ trace_clock_local,	"local" },
+	{ trace_clock_global,	"global" },
+};
+
+int trace_clock_id;
+
 /*
- * ftrace_max_lock is used to protect the swapping of buffers
- * when taking a max snapshot. The buffers themselves are
- * protected by per_cpu spinlocks. But the action of the swap
- * needs its own lock.
- *
- * This is defined as a raw_spinlock_t in order to help
- * with performance when lockdep debugging is enabled.
+ * trace_parser_get_init - gets the buffer for trace parser
  */
-static raw_spinlock_t ftrace_max_lock =
-	(raw_spinlock_t)__RAW_SPIN_LOCK_UNLOCKED;
+int trace_parser_get_init(struct trace_parser *parser, int size)
+{
+	memset(parser, 0, sizeof(*parser));
+
+	parser->buffer = kmalloc(size, GFP_KERNEL);
+	if (!parser->buffer)
+		return 1;
+
+	parser->size = size;
+	return 0;
+}
 
 /*
- * Copy the new maximum trace into the separate maximum-trace
- * structure. (this way the maximum trace is permanently saved,
- * for later retrieval via /sys/kernel/debug/tracing/latency_trace)
+ * trace_parser_put - frees the buffer for trace parser
  */
-static void
-__update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu)
+void trace_parser_put(struct trace_parser *parser)
 {
-	struct trace_array_cpu *data = tr->data[cpu];
+	kfree(parser->buffer);
+}
 
-	max_tr.cpu = cpu;
-	max_tr.time_start = data->preempt_timestamp;
+/*
+ * trace_get_user - reads the user input string separated by  space
+ * (matched by isspace(ch))
+ *
+ * For each string found the 'struct trace_parser' is updated,
+ * and the function returns.
+ *
+ * Returns number of bytes read.
+ *
+ * See kernel/trace/trace.h for 'struct trace_parser' details.
+ */
+int trace_get_user(struct trace_parser *parser, const char __user *ubuf,
+	size_t cnt, loff_t *ppos)
+{
+	char ch;
+	size_t read = 0;
+	ssize_t ret;
 
-	data = max_tr.data[cpu];
-	data->saved_latency = tracing_max_latency;
+	if (!*ppos)
+		trace_parser_clear(parser);
 
-	memcpy(data->comm, tsk->comm, TASK_COMM_LEN);
-	data->pid = tsk->pid;
-	data->uid = task_uid(tsk);
-	data->nice = tsk->static_prio - 20 - MAX_RT_PRIO;
-	data->policy = tsk->policy;
-	data->rt_priority = tsk->rt_priority;
+	ret = get_user(ch, ubuf++);
+	if (ret)
+		goto out;
 
-	/* record this tasks comm */
-	tracing_record_cmdline(tsk);
+	read++;
+	cnt--;
+
+	/*
+	 * The parser is not finished with the last write,
+	 * continue reading the user input without skipping spaces.
+	 */
+	if (!parser->cont) {
+		/* skip white space */
+		while (cnt && isspace(ch)) {
+			ret = get_user(ch, ubuf++);
+			if (ret)
+				goto out;
+			read++;
+			cnt--;
+		}
+
+		/* only spaces were written */
+		if (isspace(ch)) {
+			*ppos += read;
+			ret = read;
+			goto out;
+		}
+
+		parser->idx = 0;
+	}
+
+	/* read the non-space input */
+	while (cnt && !isspace(ch)) {
+		if (parser->idx < parser->size - 1)
+			parser->buffer[parser->idx++] = ch;
+		else {
+			ret = -EINVAL;
+			goto out;
+		}
+		ret = get_user(ch, ubuf++);
+		if (ret)
+			goto out;
+		read++;
+		cnt--;
+	}
+
+	/* We either got finished input or we have to wait for another call. */
+	if (isspace(ch)) {
+		parser->buffer[parser->idx] = 0;
+		parser->cont = false;
+	} else {
+		parser->cont = true;
+		parser->buffer[parser->idx++] = ch;
+	}
+
+	*ppos += read;
+	ret = read;
+
+out:
+	return ret;
 }
 
 ssize_t trace_seq_to_user(struct trace_seq *s, char __user *ubuf, size_t cnt)
@@ -411,6 +487,56 @@ static ssize_t trace_seq_to_buffer(struct trace_seq *s, void *buf, size_t cnt)
 	return cnt;
 }
 
+/*
+ * ftrace_max_lock is used to protect the swapping of buffers
+ * when taking a max snapshot. The buffers themselves are
+ * protected by per_cpu spinlocks. But the action of the swap
+ * needs its own lock.
+ *
+ * This is defined as a raw_spinlock_t in order to help
+ * with performance when lockdep debugging is enabled.
+ *
+ * It is also used in other places outside the update_max_tr
+ * so it needs to be defined outside of the
+ * CONFIG_TRACER_MAX_TRACE.
+ */
+static raw_spinlock_t ftrace_max_lock =
+	(raw_spinlock_t)__RAW_SPIN_LOCK_UNLOCKED;
+
+#ifdef CONFIG_TRACER_MAX_TRACE
+unsigned long __read_mostly	tracing_max_latency;
+unsigned long __read_mostly	tracing_thresh;
+
+/*
+ * Copy the new maximum trace into the separate maximum-trace
+ * structure. (this way the maximum trace is permanently saved,
+ * for later retrieval via /sys/kernel/debug/tracing/latency_trace)
+ */
+static void
+__update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu)
+{
+	struct trace_array_cpu *data = tr->data[cpu];
+	struct trace_array_cpu *max_data = tr->data[cpu];
+
+	max_tr.cpu = cpu;
+	max_tr.time_start = data->preempt_timestamp;
+
+	max_data = max_tr.data[cpu];
+	max_data->saved_latency = tracing_max_latency;
+	max_data->critical_start = data->critical_start;
+	max_data->critical_end = data->critical_end;
+
+	memcpy(data->comm, tsk->comm, TASK_COMM_LEN);
+	max_data->pid = tsk->pid;
+	max_data->uid = task_uid(tsk);
+	max_data->nice = tsk->static_prio - 20 - MAX_RT_PRIO;
+	max_data->policy = tsk->policy;
+	max_data->rt_priority = tsk->rt_priority;
+
+	/* record this tasks comm */
+	tracing_record_cmdline(tsk);
+}
+
 /**
  * update_max_tr - snapshot all trace buffers from global_trace to max_tr
  * @tr: tracer
@@ -425,16 +551,15 @@ update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu)
 {
 	struct ring_buffer *buf = tr->buffer;
 
+	if (trace_stop_count)
+		return;
+
 	WARN_ON_ONCE(!irqs_disabled());
 	__raw_spin_lock(&ftrace_max_lock);
 
 	tr->buffer = max_tr.buffer;
 	max_tr.buffer = buf;
 
-	ftrace_disable_cpu();
-	ring_buffer_reset(tr->buffer);
-	ftrace_enable_cpu();
-
 	__update_max_tr(tr, tsk, cpu);
 	__raw_spin_unlock(&ftrace_max_lock);
 }
@@ -452,21 +577,35 @@ update_max_tr_single(struct trace_array *tr, struct task_struct *tsk, int cpu)
 {
 	int ret;
 
+	if (trace_stop_count)
+		return;
+
 	WARN_ON_ONCE(!irqs_disabled());
 	__raw_spin_lock(&ftrace_max_lock);
 
 	ftrace_disable_cpu();
 
-	ring_buffer_reset(max_tr.buffer);
 	ret = ring_buffer_swap_cpu(max_tr.buffer, tr->buffer, cpu);
 
+	if (ret == -EBUSY) {
+		/*
+		 * We failed to swap the buffer due to a commit taking
+		 * place on this CPU. We fail to record, but we reset
+		 * the max trace buffer (no one writes directly to it)
+		 * and flag that it failed.
+		 */
+		trace_array_printk(&max_tr, _THIS_IP_,
+			"Failed to swap buffers due to commit in progress\n");
+	}
+
 	ftrace_enable_cpu();
 
-	WARN_ON_ONCE(ret && ret != -EAGAIN);
+	WARN_ON_ONCE(ret && ret != -EAGAIN && ret != -EBUSY);
 
 	__update_max_tr(tr, tsk, cpu);
 	__raw_spin_unlock(&ftrace_max_lock);
 }
+#endif /* CONFIG_TRACER_MAX_TRACE */
 
 /**
  * register_tracer - register a tracer with the ftrace system.
@@ -479,7 +618,6 @@ __releases(kernel_lock)
 __acquires(kernel_lock)
 {
 	struct tracer *t;
-	int len;
 	int ret = 0;
 
 	if (!type->name) {
@@ -487,6 +625,11 @@ __acquires(kernel_lock)
 		return -1;
 	}
 
+	if (strlen(type->name) > MAX_TRACER_SIZE) {
+		pr_info("Tracer has a name longer than %d\n", MAX_TRACER_SIZE);
+		return -1;
+	}
+
 	/*
 	 * When this gets called we hold the BKL which means that
 	 * preemption is disabled. Various trace selftests however
@@ -501,7 +644,7 @@ __acquires(kernel_lock)
 	for (t = trace_types; t; t = t->next) {
 		if (strcmp(type->name, t->name) == 0) {
 			/* already found */
-			pr_info("Trace %s already registered\n",
+			pr_info("Tracer %s already registered\n",
 				type->name);
 			ret = -1;
 			goto out;
@@ -523,7 +666,6 @@ __acquires(kernel_lock)
 	if (type->selftest && !tracing_selftest_disabled) {
 		struct tracer *saved_tracer = current_trace;
 		struct trace_array *tr = &global_trace;
-		int i;
 
 		/*
 		 * Run a selftest on this tracer.
@@ -532,8 +674,7 @@ __acquires(kernel_lock)
 		 * internal tracing to verify that everything is in order.
 		 * If we fail, we do not register this tracer.
 		 */
-		for_each_tracing_cpu(i)
-			tracing_reset(tr, i);
+		tracing_reset_online_cpus(tr);
 
 		current_trace = type;
 		/* the test is responsible for initializing and enabling */
@@ -546,8 +687,7 @@ __acquires(kernel_lock)
 			goto out;
 		}
 		/* Only reset on passing, to avoid touching corrupted buffers */
-		for_each_tracing_cpu(i)
-			tracing_reset(tr, i);
+		tracing_reset_online_cpus(tr);
 
 		printk(KERN_CONT "PASSED\n");
 	}
@@ -555,9 +695,6 @@ __acquires(kernel_lock)
 
 	type->next = trace_types;
 	trace_types = type;
-	len = strlen(type->name);
-	if (len > max_tracer_type_len)
-		max_tracer_type_len = len;
 
  out:
 	tracing_selftest_running = false;
@@ -566,7 +703,7 @@ __acquires(kernel_lock)
 	if (ret || !default_bootup_tracer)
 		goto out_unlock;
 
-	if (strncmp(default_bootup_tracer, type->name, BOOTUP_TRACER_SIZE))
+	if (strncmp(default_bootup_tracer, type->name, MAX_TRACER_SIZE))
 		goto out_unlock;
 
 	printk(KERN_INFO "Starting tracer '%s'\n", type->name);
@@ -588,14 +725,13 @@ __acquires(kernel_lock)
 void unregister_tracer(struct tracer *type)
 {
 	struct tracer **t;
-	int len;
 
 	mutex_lock(&trace_types_lock);
 	for (t = &trace_types; *t; t = &(*t)->next) {
 		if (*t == type)
 			goto found;
 	}
-	pr_info("Trace %s not registered\n", type->name);
+	pr_info("Tracer %s not registered\n", type->name);
 	goto out;
 
  found:
@@ -608,35 +744,46 @@ void unregister_tracer(struct tracer *type)
 			current_trace->stop(&global_trace);
 		current_trace = &nop_trace;
 	}
-
-	if (strlen(type->name) != max_tracer_type_len)
-		goto out;
-
-	max_tracer_type_len = 0;
-	for (t = &trace_types; *t; t = &(*t)->next) {
-		len = strlen((*t)->name);
-		if (len > max_tracer_type_len)
-			max_tracer_type_len = len;
-	}
- out:
+out:
 	mutex_unlock(&trace_types_lock);
 }
 
-void tracing_reset(struct trace_array *tr, int cpu)
+static void __tracing_reset(struct trace_array *tr, int cpu)
 {
 	ftrace_disable_cpu();
 	ring_buffer_reset_cpu(tr->buffer, cpu);
 	ftrace_enable_cpu();
 }
 
+void tracing_reset(struct trace_array *tr, int cpu)
+{
+	struct ring_buffer *buffer = tr->buffer;
+
+	ring_buffer_record_disable(buffer);
+
+	/* Make sure all commits have finished */
+	synchronize_sched();
+	__tracing_reset(tr, cpu);
+
+	ring_buffer_record_enable(buffer);
+}
+
 void tracing_reset_online_cpus(struct trace_array *tr)
 {
+	struct ring_buffer *buffer = tr->buffer;
 	int cpu;
 
+	ring_buffer_record_disable(buffer);
+
+	/* Make sure all commits have finished */
+	synchronize_sched();
+
 	tr->time_start = ftrace_now(tr->cpu);
 
 	for_each_online_cpu(cpu)
-		tracing_reset(tr, cpu);
+		__tracing_reset(tr, cpu);
+
+	ring_buffer_record_enable(buffer);
 }
 
 void tracing_reset_current(int cpu)
@@ -667,8 +814,10 @@ static void trace_init_cmdlines(void)
 	cmdline_idx = 0;
 }
 
-static int trace_stop_count;
-static DEFINE_SPINLOCK(tracing_start_lock);
+int is_tracing_stopped(void)
+{
+	return trace_stop_count;
+}
 
 /**
  * ftrace_off_permanent - disable all ftrace code permanently
@@ -837,7 +986,7 @@ tracing_generic_entry_update(struct trace_entry *entry, unsigned long flags,
 
 	entry->preempt_count		= pc & 0xff;
 	entry->pid			= (tsk) ? tsk->pid : 0;
-	entry->tgid			= (tsk) ? tsk->tgid : 0;
+	entry->lock_depth		= (tsk) ? tsk->lock_depth : 0;
 	entry->flags =
 #ifdef CONFIG_TRACE_IRQFLAGS_SUPPORT
 		(irqs_disabled_flags(flags) ? TRACE_FLAG_IRQS_OFF : 0) |
@@ -850,14 +999,15 @@ tracing_generic_entry_update(struct trace_entry *entry, unsigned long flags,
 }
 EXPORT_SYMBOL_GPL(tracing_generic_entry_update);
 
-struct ring_buffer_event *trace_buffer_lock_reserve(struct trace_array *tr,
-						    int type,
-						    unsigned long len,
-						    unsigned long flags, int pc)
+struct ring_buffer_event *
+trace_buffer_lock_reserve(struct ring_buffer *buffer,
+			  int type,
+			  unsigned long len,
+			  unsigned long flags, int pc)
 {
 	struct ring_buffer_event *event;
 
-	event = ring_buffer_lock_reserve(tr->buffer, len);
+	event = ring_buffer_lock_reserve(buffer, len);
 	if (event != NULL) {
 		struct trace_entry *ent = ring_buffer_event_data(event);
 
@@ -867,58 +1017,60 @@ struct ring_buffer_event *trace_buffer_lock_reserve(struct trace_array *tr,
 
 	return event;
 }
-static void ftrace_trace_stack(struct trace_array *tr,
-			       unsigned long flags, int skip, int pc);
-static void ftrace_trace_userstack(struct trace_array *tr,
-				   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)
+static inline void
+__trace_buffer_unlock_commit(struct ring_buffer *buffer,
+			     struct ring_buffer_event *event,
+			     unsigned long flags, int pc,
+			     int wake)
 {
-	ring_buffer_unlock_commit(tr->buffer, event);
+	ring_buffer_unlock_commit(buffer, event);
 
-	ftrace_trace_stack(tr, flags, 6, pc);
-	ftrace_trace_userstack(tr, flags, pc);
+	ftrace_trace_stack(buffer, flags, 6, pc);
+	ftrace_trace_userstack(buffer, flags, pc);
 
 	if (wake)
 		trace_wake_up();
 }
 
-void trace_buffer_unlock_commit(struct trace_array *tr,
-					struct ring_buffer_event *event,
-					unsigned long flags, int pc)
+void trace_buffer_unlock_commit(struct ring_buffer *buffer,
+				struct ring_buffer_event *event,
+				unsigned long flags, int pc)
 {
-	__trace_buffer_unlock_commit(tr, event, flags, pc, 1);
+	__trace_buffer_unlock_commit(buffer, event, flags, pc, 1);
 }
 
 struct ring_buffer_event *
-trace_current_buffer_lock_reserve(int type, unsigned long len,
+trace_current_buffer_lock_reserve(struct ring_buffer **current_rb,
+				  int type, unsigned long len,
 				  unsigned long flags, int pc)
 {
-	return trace_buffer_lock_reserve(&global_trace,
+	*current_rb = global_trace.buffer;
+	return trace_buffer_lock_reserve(*current_rb,
 					 type, len, flags, pc);
 }
 EXPORT_SYMBOL_GPL(trace_current_buffer_lock_reserve);
 
-void trace_current_buffer_unlock_commit(struct ring_buffer_event *event,
+void trace_current_buffer_unlock_commit(struct ring_buffer *buffer,
+					struct ring_buffer_event *event,
 					unsigned long flags, int pc)
 {
-	__trace_buffer_unlock_commit(&global_trace, event, flags, pc, 1);
+	__trace_buffer_unlock_commit(buffer, event, flags, pc, 1);
 }
 EXPORT_SYMBOL_GPL(trace_current_buffer_unlock_commit);
 
-void trace_nowake_buffer_unlock_commit(struct ring_buffer_event *event,
-					unsigned long flags, int pc)
+void trace_nowake_buffer_unlock_commit(struct ring_buffer *buffer,
+				       struct ring_buffer_event *event,
+				       unsigned long flags, int pc)
 {
-	__trace_buffer_unlock_commit(&global_trace, event, flags, pc, 0);
+	__trace_buffer_unlock_commit(buffer, event, flags, pc, 0);
 }
 EXPORT_SYMBOL_GPL(trace_nowake_buffer_unlock_commit);
 
-void trace_current_buffer_discard_commit(struct ring_buffer_event *event)
+void trace_current_buffer_discard_commit(struct ring_buffer *buffer,
+					 struct ring_buffer_event *event)
 {
-	ring_buffer_discard_commit(global_trace.buffer, event);
+	ring_buffer_discard_commit(buffer, event);
 }
 EXPORT_SYMBOL_GPL(trace_current_buffer_discard_commit);
 
@@ -928,6 +1080,7 @@ trace_function(struct trace_array *tr,
 	       int pc)
 {
 	struct ftrace_event_call *call = &event_function;
+	struct ring_buffer *buffer = tr->buffer;
 	struct ring_buffer_event *event;
 	struct ftrace_entry *entry;
 
@@ -935,7 +1088,7 @@ trace_function(struct trace_array *tr,
 	if (unlikely(local_read(&__get_cpu_var(ftrace_cpu_disabled))))
 		return;
 
-	event = trace_buffer_lock_reserve(tr, TRACE_FN, sizeof(*entry),
+	event = trace_buffer_lock_reserve(buffer, TRACE_FN, sizeof(*entry),
 					  flags, pc);
 	if (!event)
 		return;
@@ -943,57 +1096,9 @@ trace_function(struct trace_array *tr,
 	entry->ip			= ip;
 	entry->parent_ip		= parent_ip;
 
-	if (!filter_check_discard(call, entry, tr->buffer, event))
-		ring_buffer_unlock_commit(tr->buffer, event);
-}
-
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
-static int __trace_graph_entry(struct trace_array *tr,
-				struct ftrace_graph_ent *trace,
-				unsigned long flags,
-				int pc)
-{
-	struct ftrace_event_call *call = &event_funcgraph_entry;
-	struct ring_buffer_event *event;
-	struct ftrace_graph_ent_entry *entry;
-
-	if (unlikely(local_read(&__get_cpu_var(ftrace_cpu_disabled))))
-		return 0;
-
-	event = trace_buffer_lock_reserve(&global_trace, TRACE_GRAPH_ENT,
-					  sizeof(*entry), flags, pc);
-	if (!event)
-		return 0;
-	entry	= ring_buffer_event_data(event);
-	entry->graph_ent			= *trace;
-	if (!filter_current_check_discard(call, entry, event))
-		ring_buffer_unlock_commit(global_trace.buffer, event);
-
-	return 1;
-}
-
-static void __trace_graph_return(struct trace_array *tr,
-				struct ftrace_graph_ret *trace,
-				unsigned long flags,
-				int pc)
-{
-	struct ftrace_event_call *call = &event_funcgraph_exit;
-	struct ring_buffer_event *event;
-	struct ftrace_graph_ret_entry *entry;
-
-	if (unlikely(local_read(&__get_cpu_var(ftrace_cpu_disabled))))
-		return;
-
-	event = trace_buffer_lock_reserve(&global_trace, TRACE_GRAPH_RET,
-					  sizeof(*entry), flags, pc);
-	if (!event)
-		return;
-	entry	= ring_buffer_event_data(event);
-	entry->ret				= *trace;
-	if (!filter_current_check_discard(call, entry, event))
-		ring_buffer_unlock_commit(global_trace.buffer, event);
+	if (!filter_check_discard(call, entry, buffer, event))
+		ring_buffer_unlock_commit(buffer, event);
 }
-#endif
 
 void
 ftrace(struct trace_array *tr, struct trace_array_cpu *data,
@@ -1004,17 +1109,17 @@ ftrace(struct trace_array *tr, struct trace_array_cpu *data,
 		trace_function(tr, ip, parent_ip, flags, pc);
 }
 
-static void __ftrace_trace_stack(struct trace_array *tr,
+#ifdef CONFIG_STACKTRACE
+static void __ftrace_trace_stack(struct ring_buffer *buffer,
 				 unsigned long flags,
 				 int skip, int pc)
 {
-#ifdef CONFIG_STACKTRACE
 	struct ftrace_event_call *call = &event_kernel_stack;
 	struct ring_buffer_event *event;
 	struct stack_entry *entry;
 	struct stack_trace trace;
 
-	event = trace_buffer_lock_reserve(tr, TRACE_STACK,
+	event = trace_buffer_lock_reserve(buffer, TRACE_STACK,
 					  sizeof(*entry), flags, pc);
 	if (!event)
 		return;
@@ -1027,32 +1132,28 @@ static void __ftrace_trace_stack(struct trace_array *tr,
 	trace.entries		= entry->caller;
 
 	save_stack_trace(&trace);
-	if (!filter_check_discard(call, entry, tr->buffer, event))
-		ring_buffer_unlock_commit(tr->buffer, event);
-#endif
+	if (!filter_check_discard(call, entry, buffer, event))
+		ring_buffer_unlock_commit(buffer, event);
 }
 
-static void ftrace_trace_stack(struct trace_array *tr,
-			       unsigned long flags,
-			       int skip, int pc)
+void ftrace_trace_stack(struct ring_buffer *buffer, unsigned long flags,
+			int skip, int pc)
 {
 	if (!(trace_flags & TRACE_ITER_STACKTRACE))
 		return;
 
-	__ftrace_trace_stack(tr, flags, skip, pc);
+	__ftrace_trace_stack(buffer, flags, skip, pc);
 }
 
-void __trace_stack(struct trace_array *tr,
-		   unsigned long flags,
-		   int skip, int pc)
+void __trace_stack(struct trace_array *tr, unsigned long flags, int skip,
+		   int pc)
 {
-	__ftrace_trace_stack(tr, flags, skip, pc);
+	__ftrace_trace_stack(tr->buffer, flags, skip, pc);
 }
 
-static void ftrace_trace_userstack(struct trace_array *tr,
-				   unsigned long flags, int pc)
+void
+ftrace_trace_userstack(struct ring_buffer *buffer, unsigned long flags, int pc)
 {
-#ifdef CONFIG_STACKTRACE
 	struct ftrace_event_call *call = &event_user_stack;
 	struct ring_buffer_event *event;
 	struct userstack_entry *entry;
@@ -1061,12 +1162,13 @@ static void ftrace_trace_userstack(struct trace_array *tr,
 	if (!(trace_flags & TRACE_ITER_USERSTACKTRACE))
 		return;
 
-	event = trace_buffer_lock_reserve(tr, TRACE_USER_STACK,
+	event = trace_buffer_lock_reserve(buffer, TRACE_USER_STACK,
 					  sizeof(*entry), flags, pc);
 	if (!event)
 		return;
 	entry	= ring_buffer_event_data(event);
 
+	entry->tgid		= current->tgid;
 	memset(&entry->caller, 0, sizeof(entry->caller));
 
 	trace.nr_entries	= 0;
@@ -1075,9 +1177,8 @@ static void ftrace_trace_userstack(struct trace_array *tr,
 	trace.entries		= entry->caller;
 
 	save_stack_trace_user(&trace);
-	if (!filter_check_discard(call, entry, tr->buffer, event))
-		ring_buffer_unlock_commit(tr->buffer, event);
-#endif
+	if (!filter_check_discard(call, entry, buffer, event))
+		ring_buffer_unlock_commit(buffer, event);
 }
 
 #ifdef UNUSED
@@ -1087,16 +1188,20 @@ static void __trace_userstack(struct trace_array *tr, unsigned long flags)
 }
 #endif /* UNUSED */
 
+#endif /* CONFIG_STACKTRACE */
+
 static void
 ftrace_trace_special(void *__tr,
 		     unsigned long arg1, unsigned long arg2, unsigned long arg3,
 		     int pc)
 {
+	struct ftrace_event_call *call = &event_special;
 	struct ring_buffer_event *event;
 	struct trace_array *tr = __tr;
+	struct ring_buffer *buffer = tr->buffer;
 	struct special_entry *entry;
 
-	event = trace_buffer_lock_reserve(tr, TRACE_SPECIAL,
+	event = trace_buffer_lock_reserve(buffer, TRACE_SPECIAL,
 					  sizeof(*entry), 0, pc);
 	if (!event)
 		return;
@@ -1104,7 +1209,9 @@ ftrace_trace_special(void *__tr,
 	entry->arg1			= arg1;
 	entry->arg2			= arg2;
 	entry->arg3			= arg3;
-	trace_buffer_unlock_commit(tr, event, 0, pc);
+
+	if (!filter_check_discard(call, entry, buffer, event))
+		trace_buffer_unlock_commit(buffer, event, 0, pc);
 }
 
 void
@@ -1115,62 +1222,6 @@ __trace_special(void *__tr, void *__data,
 }
 
 void
-tracing_sched_switch_trace(struct trace_array *tr,
-			   struct task_struct *prev,
-			   struct task_struct *next,
-			   unsigned long flags, int pc)
-{
-	struct ftrace_event_call *call = &event_context_switch;
-	struct ring_buffer_event *event;
-	struct ctx_switch_entry *entry;
-
-	event = trace_buffer_lock_reserve(tr, TRACE_CTX,
-					  sizeof(*entry), flags, pc);
-	if (!event)
-		return;
-	entry	= ring_buffer_event_data(event);
-	entry->prev_pid			= prev->pid;
-	entry->prev_prio		= prev->prio;
-	entry->prev_state		= prev->state;
-	entry->next_pid			= next->pid;
-	entry->next_prio		= next->prio;
-	entry->next_state		= next->state;
-	entry->next_cpu	= task_cpu(next);
-
-	if (!filter_check_discard(call, entry, tr->buffer, event))
-		trace_buffer_unlock_commit(tr, event, flags, pc);
-}
-
-void
-tracing_sched_wakeup_trace(struct trace_array *tr,
-			   struct task_struct *wakee,
-			   struct task_struct *curr,
-			   unsigned long flags, int pc)
-{
-	struct ftrace_event_call *call = &event_wakeup;
-	struct ring_buffer_event *event;
-	struct ctx_switch_entry *entry;
-
-	event = trace_buffer_lock_reserve(tr, TRACE_WAKE,
-					  sizeof(*entry), flags, pc);
-	if (!event)
-		return;
-	entry	= ring_buffer_event_data(event);
-	entry->prev_pid			= curr->pid;
-	entry->prev_prio		= curr->prio;
-	entry->prev_state		= curr->state;
-	entry->next_pid			= wakee->pid;
-	entry->next_prio		= wakee->prio;
-	entry->next_state		= wakee->state;
-	entry->next_cpu			= task_cpu(wakee);
-
-	if (!filter_check_discard(call, entry, tr->buffer, event))
-		ring_buffer_unlock_commit(tr->buffer, event);
-	ftrace_trace_stack(tr, flags, 6, pc);
-	ftrace_trace_userstack(tr, flags, pc);
-}
-
-void
 ftrace_special(unsigned long arg1, unsigned long arg2, unsigned long arg3)
 {
 	struct trace_array *tr = &global_trace;
@@ -1194,68 +1245,6 @@ ftrace_special(unsigned long arg1, unsigned long arg2, unsigned long arg3)
 	local_irq_restore(flags);
 }
 
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
-int trace_graph_entry(struct ftrace_graph_ent *trace)
-{
-	struct trace_array *tr = &global_trace;
-	struct trace_array_cpu *data;
-	unsigned long flags;
-	long disabled;
-	int ret;
-	int cpu;
-	int pc;
-
-	if (!ftrace_trace_task(current))
-		return 0;
-
-	if (!ftrace_graph_addr(trace->func))
-		return 0;
-
-	local_irq_save(flags);
-	cpu = raw_smp_processor_id();
-	data = tr->data[cpu];
-	disabled = atomic_inc_return(&data->disabled);
-	if (likely(disabled == 1)) {
-		pc = preempt_count();
-		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 ret;
-}
-
-void trace_graph_return(struct ftrace_graph_ret *trace)
-{
-	struct trace_array *tr = &global_trace;
-	struct trace_array_cpu *data;
-	unsigned long flags;
-	long disabled;
-	int cpu;
-	int pc;
-
-	local_irq_save(flags);
-	cpu = raw_smp_processor_id();
-	data = tr->data[cpu];
-	disabled = atomic_inc_return(&data->disabled);
-	if (likely(disabled == 1)) {
-		pc = preempt_count();
-		__trace_graph_return(tr, trace, flags, pc);
-	}
-	if (!trace->depth)
-		clear_tsk_trace_graph(current);
-	atomic_dec(&data->disabled);
-	local_irq_restore(flags);
-}
-#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
-
-
 /**
  * trace_vbprintk - write binary msg to tracing buffer
  *
@@ -1268,6 +1257,7 @@ int trace_vbprintk(unsigned long ip, const char *fmt, va_list args)
 
 	struct ftrace_event_call *call = &event_bprint;
 	struct ring_buffer_event *event;
+	struct ring_buffer *buffer;
 	struct trace_array *tr = &global_trace;
 	struct trace_array_cpu *data;
 	struct bprint_entry *entry;
@@ -1300,7 +1290,9 @@ int trace_vbprintk(unsigned long ip, const char *fmt, va_list args)
 		goto out_unlock;
 
 	size = sizeof(*entry) + sizeof(u32) * len;
-	event = trace_buffer_lock_reserve(tr, TRACE_BPRINT, size, flags, pc);
+	buffer = tr->buffer;
+	event = trace_buffer_lock_reserve(buffer, TRACE_BPRINT, size,
+					  flags, pc);
 	if (!event)
 		goto out_unlock;
 	entry = ring_buffer_event_data(event);
@@ -1308,8 +1300,8 @@ int trace_vbprintk(unsigned long ip, const char *fmt, va_list args)
 	entry->fmt			= fmt;
 
 	memcpy(entry->buf, trace_buf, sizeof(u32) * len);
-	if (!filter_check_discard(call, entry, tr->buffer, event))
-		ring_buffer_unlock_commit(tr->buffer, event);
+	if (!filter_check_discard(call, entry, buffer, event))
+		ring_buffer_unlock_commit(buffer, event);
 
 out_unlock:
 	__raw_spin_unlock(&trace_buf_lock);
@@ -1324,14 +1316,30 @@ out:
 }
 EXPORT_SYMBOL_GPL(trace_vbprintk);
 
-int trace_vprintk(unsigned long ip, const char *fmt, va_list args)
+int trace_array_printk(struct trace_array *tr,
+		       unsigned long ip, const char *fmt, ...)
+{
+	int ret;
+	va_list ap;
+
+	if (!(trace_flags & TRACE_ITER_PRINTK))
+		return 0;
+
+	va_start(ap, fmt);
+	ret = trace_array_vprintk(tr, ip, fmt, ap);
+	va_end(ap);
+	return ret;
+}
+
+int trace_array_vprintk(struct trace_array *tr,
+			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];
 
 	struct ftrace_event_call *call = &event_print;
 	struct ring_buffer_event *event;
-	struct trace_array *tr = &global_trace;
+	struct ring_buffer *buffer;
 	struct trace_array_cpu *data;
 	int cpu, len = 0, size, pc;
 	struct print_entry *entry;
@@ -1359,7 +1367,9 @@ int trace_vprintk(unsigned long ip, const char *fmt, va_list args)
 	trace_buf[len] = 0;
 
 	size = sizeof(*entry) + len + 1;
-	event = trace_buffer_lock_reserve(tr, TRACE_PRINT, size, irq_flags, pc);
+	buffer = tr->buffer;
+	event = trace_buffer_lock_reserve(buffer, TRACE_PRINT, size,
+					  irq_flags, pc);
 	if (!event)
 		goto out_unlock;
 	entry = ring_buffer_event_data(event);
@@ -1367,8 +1377,8 @@ int trace_vprintk(unsigned long ip, const char *fmt, va_list args)
 
 	memcpy(&entry->buf, trace_buf, len);
 	entry->buf[len] = 0;
-	if (!filter_check_discard(call, entry, tr->buffer, event))
-		ring_buffer_unlock_commit(tr->buffer, event);
+	if (!filter_check_discard(call, entry, buffer, event))
+		ring_buffer_unlock_commit(buffer, event);
 
  out_unlock:
 	__raw_spin_unlock(&trace_buf_lock);
@@ -1380,6 +1390,11 @@ int trace_vprintk(unsigned long ip, const char *fmt, va_list args)
 
 	return len;
 }
+
+int trace_vprintk(unsigned long ip, const char *fmt, va_list args)
+{
+	return trace_array_vprintk(&global_trace, ip, fmt, args);
+}
 EXPORT_SYMBOL_GPL(trace_vprintk);
 
 enum trace_file_type {
@@ -1519,6 +1534,37 @@ static void *s_next(struct seq_file *m, void *v, loff_t *pos)
 	return ent;
 }
 
+static void tracing_iter_reset(struct trace_iterator *iter, int cpu)
+{
+	struct trace_array *tr = iter->tr;
+	struct ring_buffer_event *event;
+	struct ring_buffer_iter *buf_iter;
+	unsigned long entries = 0;
+	u64 ts;
+
+	tr->data[cpu]->skipped_entries = 0;
+
+	if (!iter->buffer_iter[cpu])
+		return;
+
+	buf_iter = iter->buffer_iter[cpu];
+	ring_buffer_iter_reset(buf_iter);
+
+	/*
+	 * We could have the case with the max latency tracers
+	 * that a reset never took place on a cpu. This is evident
+	 * by the timestamp being before the start of the buffer.
+	 */
+	while ((event = ring_buffer_iter_peek(buf_iter, &ts))) {
+		if (ts >= iter->tr->time_start)
+			break;
+		entries++;
+		ring_buffer_read(buf_iter, NULL);
+	}
+
+	tr->data[cpu]->skipped_entries = entries;
+}
+
 /*
  * No necessary locking here. The worst thing which can
  * happen is loosing events consumed at the same time
@@ -1557,10 +1603,9 @@ static void *s_start(struct seq_file *m, loff_t *pos)
 
 		if (cpu_file == TRACE_PIPE_ALL_CPU) {
 			for_each_tracing_cpu(cpu)
-				ring_buffer_iter_reset(iter->buffer_iter[cpu]);
+				tracing_iter_reset(iter, cpu);
 		} else
-			ring_buffer_iter_reset(iter->buffer_iter[cpu_file]);
-
+			tracing_iter_reset(iter, cpu_file);
 
 		ftrace_enable_cpu();
 
@@ -1589,10 +1634,10 @@ static void print_lat_help_header(struct seq_file *m)
 	seq_puts(m, "#                | / _----=> need-resched    \n");
 	seq_puts(m, "#                || / _---=> hardirq/softirq \n");
 	seq_puts(m, "#                ||| / _--=> preempt-depth   \n");
-	seq_puts(m, "#                |||| /                      \n");
-	seq_puts(m, "#                |||||     delay             \n");
-	seq_puts(m, "#  cmd     pid   ||||| time  |   caller      \n");
-	seq_puts(m, "#     \\   /      |||||   \\   |   /           \n");
+	seq_puts(m, "#                |||| /_--=> lock-depth       \n");
+	seq_puts(m, "#                |||||/     delay             \n");
+	seq_puts(m, "#  cmd     pid   |||||| time  |   caller      \n");
+	seq_puts(m, "#     \\   /      ||||||   \\   |   /           \n");
 }
 
 static void print_func_help_header(struct seq_file *m)
@@ -1609,16 +1654,32 @@ print_trace_header(struct seq_file *m, struct trace_iterator *iter)
 	struct trace_array *tr = iter->tr;
 	struct trace_array_cpu *data = tr->data[tr->cpu];
 	struct tracer *type = current_trace;
-	unsigned long total;
-	unsigned long entries;
+	unsigned long entries = 0;
+	unsigned long total = 0;
+	unsigned long count;
 	const char *name = "preemption";
+	int cpu;
 
 	if (type)
 		name = type->name;
 
-	entries = ring_buffer_entries(iter->tr->buffer);
-	total = entries +
-		ring_buffer_overruns(iter->tr->buffer);
+
+	for_each_tracing_cpu(cpu) {
+		count = ring_buffer_entries_cpu(tr->buffer, cpu);
+		/*
+		 * If this buffer has skipped entries, then we hold all
+		 * entries for the trace and we need to ignore the
+		 * ones before the time stamp.
+		 */
+		if (tr->data[cpu]->skipped_entries) {
+			count -= tr->data[cpu]->skipped_entries;
+			/* total is the same as the entries */
+			total += count;
+		} else
+			total += count +
+				ring_buffer_overrun_cpu(tr->buffer, cpu);
+		entries += count;
+	}
 
 	seq_printf(m, "# %s latency trace v1.1.5 on %s\n",
 		   name, UTS_RELEASE);
@@ -1660,7 +1721,7 @@ print_trace_header(struct seq_file *m, struct trace_iterator *iter)
 		seq_puts(m, "\n#  => ended at:   ");
 		seq_print_ip_sym(&iter->seq, data->critical_end, sym_flags);
 		trace_print_seq(m, &iter->seq);
-		seq_puts(m, "#\n");
+		seq_puts(m, "\n#\n");
 	}
 
 	seq_puts(m, "#\n");
@@ -1679,6 +1740,9 @@ static void test_cpu_buff_start(struct trace_iterator *iter)
 	if (cpumask_test_cpu(iter->cpu, iter->started))
 		return;
 
+	if (iter->tr->data[iter->cpu]->skipped_entries)
+		return;
+
 	cpumask_set_cpu(iter->cpu, iter->started);
 
 	/* Don't print started cpu buffer for the first entry of the trace */
@@ -1885,7 +1949,7 @@ static int s_show(struct seq_file *m, void *v)
 	return 0;
 }
 
-static struct seq_operations tracer_seq_ops = {
+static const struct seq_operations tracer_seq_ops = {
 	.start		= s_start,
 	.next		= s_next,
 	.stop		= s_stop,
@@ -1920,11 +1984,9 @@ __tracing_open(struct inode *inode, struct file *file)
 	if (current_trace)
 		*iter->trace = *current_trace;
 
-	if (!alloc_cpumask_var(&iter->started, GFP_KERNEL))
+	if (!zalloc_cpumask_var(&iter->started, GFP_KERNEL))
 		goto fail;
 
-	cpumask_clear(iter->started);
-
 	if (current_trace && current_trace->print_max)
 		iter->tr = &max_tr;
 	else
@@ -1941,19 +2003,23 @@ __tracing_open(struct inode *inode, struct file *file)
 	if (ring_buffer_overruns(iter->tr->buffer))
 		iter->iter_flags |= TRACE_FILE_ANNOTATE;
 
+	/* stop the trace while dumping */
+	tracing_stop();
+
 	if (iter->cpu_file == TRACE_PIPE_ALL_CPU) {
 		for_each_tracing_cpu(cpu) {
 
 			iter->buffer_iter[cpu] =
 				ring_buffer_read_start(iter->tr->buffer, cpu);
+			tracing_iter_reset(iter, cpu);
 		}
 	} else {
 		cpu = iter->cpu_file;
 		iter->buffer_iter[cpu] =
 				ring_buffer_read_start(iter->tr->buffer, cpu);
+		tracing_iter_reset(iter, cpu);
 	}
 
-	/* TODO stop tracer */
 	ret = seq_open(file, &tracer_seq_ops);
 	if (ret < 0) {
 		fail_ret = ERR_PTR(ret);
@@ -1963,9 +2029,6 @@ __tracing_open(struct inode *inode, struct file *file)
 	m = file->private_data;
 	m->private = iter;
 
-	/* stop the trace while dumping */
-	tracing_stop();
-
 	mutex_unlock(&trace_types_lock);
 
 	return iter;
@@ -1976,6 +2039,7 @@ __tracing_open(struct inode *inode, struct file *file)
 			ring_buffer_read_finish(iter->buffer_iter[cpu]);
 	}
 	free_cpumask_var(iter->started);
+	tracing_start();
  fail:
 	mutex_unlock(&trace_types_lock);
 	kfree(iter->trace);
@@ -2097,7 +2161,7 @@ static int t_show(struct seq_file *m, void *v)
 	return 0;
 }
 
-static struct seq_operations show_traces_seq_ops = {
+static const struct seq_operations show_traces_seq_ops = {
 	.start		= t_start,
 	.next		= t_next,
 	.stop		= t_stop,
@@ -2257,8 +2321,8 @@ tracing_trace_options_read(struct file *filp, char __user *ubuf,
 		len += 3; /* "no" and newline */
 	}
 
-	/* +2 for \n and \0 */
-	buf = kmalloc(len + 2, GFP_KERNEL);
+	/* +1 for \0 */
+	buf = kmalloc(len + 1, GFP_KERNEL);
 	if (!buf) {
 		mutex_unlock(&trace_types_lock);
 		return -ENOMEM;
@@ -2281,7 +2345,7 @@ tracing_trace_options_read(struct file *filp, char __user *ubuf,
 	}
 	mutex_unlock(&trace_types_lock);
 
-	WARN_ON(r >= len + 2);
+	WARN_ON(r >= len + 1);
 
 	r = simple_read_from_buffer(ubuf, cnt, ppos, buf, r);
 
@@ -2292,23 +2356,23 @@ tracing_trace_options_read(struct file *filp, char __user *ubuf,
 /* Try to assign a tracer specific option */
 static int set_tracer_option(struct tracer *trace, char *cmp, int neg)
 {
-	struct tracer_flags *trace_flags = trace->flags;
+	struct tracer_flags *tracer_flags = trace->flags;
 	struct tracer_opt *opts = NULL;
 	int ret = 0, i = 0;
 	int len;
 
-	for (i = 0; trace_flags->opts[i].name; i++) {
-		opts = &trace_flags->opts[i];
+	for (i = 0; tracer_flags->opts[i].name; i++) {
+		opts = &tracer_flags->opts[i];
 		len = strlen(opts->name);
 
 		if (strncmp(cmp, opts->name, len) == 0) {
-			ret = trace->set_flag(trace_flags->val,
+			ret = trace->set_flag(tracer_flags->val,
 				opts->bit, !neg);
 			break;
 		}
 	}
 	/* Not found */
-	if (!trace_flags->opts[i].name)
+	if (!tracer_flags->opts[i].name)
 		return -EINVAL;
 
 	/* Refused to handle */
@@ -2316,9 +2380,9 @@ static int set_tracer_option(struct tracer *trace, char *cmp, int neg)
 		return ret;
 
 	if (neg)
-		trace_flags->val &= ~opts->bit;
+		tracer_flags->val &= ~opts->bit;
 	else
-		trace_flags->val |= opts->bit;
+		tracer_flags->val |= opts->bit;
 
 	return 0;
 }
@@ -2333,22 +2397,6 @@ static void set_tracer_flags(unsigned int mask, int 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
@@ -2392,7 +2440,7 @@ tracing_trace_options_write(struct file *filp, const char __user *ubuf,
 			return ret;
 	}
 
-	filp->f_pos += cnt;
+	*ppos += cnt;
 
 	return cnt;
 }
@@ -2534,7 +2582,7 @@ tracing_ctrl_write(struct file *filp, const char __user *ubuf,
 	}
 	mutex_unlock(&trace_types_lock);
 
-	filp->f_pos += cnt;
+	*ppos += cnt;
 
 	return cnt;
 }
@@ -2543,7 +2591,7 @@ static ssize_t
 tracing_set_trace_read(struct file *filp, char __user *ubuf,
 		       size_t cnt, loff_t *ppos)
 {
-	char buf[max_tracer_type_len+2];
+	char buf[MAX_TRACER_SIZE+2];
 	int r;
 
 	mutex_lock(&trace_types_lock);
@@ -2693,15 +2741,15 @@ static ssize_t
 tracing_set_trace_write(struct file *filp, const char __user *ubuf,
 			size_t cnt, loff_t *ppos)
 {
-	char buf[max_tracer_type_len+1];
+	char buf[MAX_TRACER_SIZE+1];
 	int i;
 	size_t ret;
 	int err;
 
 	ret = cnt;
 
-	if (cnt > max_tracer_type_len)
-		cnt = max_tracer_type_len;
+	if (cnt > MAX_TRACER_SIZE)
+		cnt = MAX_TRACER_SIZE;
 
 	if (copy_from_user(&buf, ubuf, cnt))
 		return -EFAULT;
@@ -2716,7 +2764,7 @@ tracing_set_trace_write(struct file *filp, const char __user *ubuf,
 	if (err)
 		return err;
 
-	filp->f_pos += ret;
+	*ppos += ret;
 
 	return ret;
 }
@@ -3251,7 +3299,7 @@ tracing_entries_write(struct file *filp, const char __user *ubuf,
 		}
 	}
 
-	filp->f_pos += cnt;
+	*ppos += cnt;
 
 	/* If check pages failed, return ENOMEM */
 	if (tracing_disabled)
@@ -3316,6 +3364,62 @@ tracing_mark_write(struct file *filp, const char __user *ubuf,
 	return cnt;
 }
 
+static ssize_t tracing_clock_read(struct file *filp, char __user *ubuf,
+				  size_t cnt, loff_t *ppos)
+{
+	char buf[64];
+	int bufiter = 0;
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(trace_clocks); i++)
+		bufiter += snprintf(buf + bufiter, sizeof(buf) - bufiter,
+			"%s%s%s%s", i ? " " : "",
+			i == trace_clock_id ? "[" : "", trace_clocks[i].name,
+			i == trace_clock_id ? "]" : "");
+	bufiter += snprintf(buf + bufiter, sizeof(buf) - bufiter, "\n");
+
+	return simple_read_from_buffer(ubuf, cnt, ppos, buf, bufiter);
+}
+
+static ssize_t tracing_clock_write(struct file *filp, const char __user *ubuf,
+				   size_t cnt, loff_t *fpos)
+{
+	char buf[64];
+	const char *clockstr;
+	int i;
+
+	if (cnt >= sizeof(buf))
+		return -EINVAL;
+
+	if (copy_from_user(&buf, ubuf, cnt))
+		return -EFAULT;
+
+	buf[cnt] = 0;
+
+	clockstr = strstrip(buf);
+
+	for (i = 0; i < ARRAY_SIZE(trace_clocks); i++) {
+		if (strcmp(trace_clocks[i].name, clockstr) == 0)
+			break;
+	}
+	if (i == ARRAY_SIZE(trace_clocks))
+		return -EINVAL;
+
+	trace_clock_id = i;
+
+	mutex_lock(&trace_types_lock);
+
+	ring_buffer_set_clock(global_trace.buffer, trace_clocks[i].func);
+	if (max_tr.buffer)
+		ring_buffer_set_clock(max_tr.buffer, trace_clocks[i].func);
+
+	mutex_unlock(&trace_types_lock);
+
+	*fpos += cnt;
+
+	return cnt;
+}
+
 static const struct file_operations tracing_max_lat_fops = {
 	.open		= tracing_open_generic,
 	.read		= tracing_max_lat_read,
@@ -3353,6 +3457,12 @@ static const struct file_operations tracing_mark_fops = {
 	.write		= tracing_mark_write,
 };
 
+static const struct file_operations trace_clock_fops = {
+	.open		= tracing_open_generic,
+	.read		= tracing_clock_read,
+	.write		= tracing_clock_write,
+};
+
 struct ftrace_buffer_info {
 	struct trace_array	*tr;
 	void			*spare;
@@ -3633,9 +3743,6 @@ tracing_stats_read(struct file *filp, char __user *ubuf,
 	cnt = ring_buffer_commit_overrun_cpu(tr->buffer, cpu);
 	trace_seq_printf(s, "commit overrun: %ld\n", cnt);
 
-	cnt = ring_buffer_nmi_dropped_cpu(tr->buffer, cpu);
-	trace_seq_printf(s, "nmi dropped: %ld\n", cnt);
-
 	count = simple_read_from_buffer(ubuf, count, ppos, s->buffer, s->len);
 
 	kfree(s);
@@ -4066,11 +4173,13 @@ static __init int tracer_init_debugfs(void)
 	trace_create_file("current_tracer", 0644, d_tracer,
 			&global_trace, &set_tracer_fops);
 
+#ifdef CONFIG_TRACER_MAX_TRACE
 	trace_create_file("tracing_max_latency", 0644, d_tracer,
 			&tracing_max_latency, &tracing_max_lat_fops);
 
 	trace_create_file("tracing_thresh", 0644, d_tracer,
 			&tracing_thresh, &tracing_max_lat_fops);
+#endif
 
 	trace_create_file("README", 0444, d_tracer,
 			NULL, &tracing_readme_fops);
@@ -4087,6 +4196,9 @@ static __init int tracer_init_debugfs(void)
 	trace_create_file("saved_cmdlines", 0444, d_tracer,
 			NULL, &tracing_saved_cmdlines_fops);
 
+	trace_create_file("trace_clock", 0644, d_tracer, NULL,
+			  &trace_clock_fops);
+
 #ifdef CONFIG_DYNAMIC_FTRACE
 	trace_create_file("dyn_ftrace_total_info", 0444, d_tracer,
 			&ftrace_update_tot_cnt, &tracing_dyn_info_fops);
@@ -4265,7 +4377,6 @@ void ftrace_dump(void)
 
 __init static int tracer_alloc_buffers(void)
 {
-	struct trace_array_cpu *data;
 	int ring_buf_size;
 	int i;
 	int ret = -ENOMEM;
@@ -4276,7 +4387,7 @@ __init static int tracer_alloc_buffers(void)
 	if (!alloc_cpumask_var(&tracing_cpumask, GFP_KERNEL))
 		goto out_free_buffer_mask;
 
-	if (!alloc_cpumask_var(&tracing_reader_cpumask, GFP_KERNEL))
+	if (!zalloc_cpumask_var(&tracing_reader_cpumask, GFP_KERNEL))
 		goto out_free_tracing_cpumask;
 
 	/* To save memory, keep the ring buffer size to its minimum */
@@ -4287,7 +4398,6 @@ __init static int tracer_alloc_buffers(void)
 
 	cpumask_copy(tracing_buffer_mask, cpu_possible_mask);
 	cpumask_copy(tracing_cpumask, cpu_all_mask);
-	cpumask_clear(tracing_reader_cpumask);
 
 	/* TODO: make the number of buffers hot pluggable with CPUS */
 	global_trace.buffer = ring_buffer_alloc(ring_buf_size,
@@ -4315,7 +4425,7 @@ __init static int tracer_alloc_buffers(void)
 
 	/* Allocate the first page for all buffers */
 	for_each_tracing_cpu(i) {
-		data = global_trace.data[i] = &per_cpu(global_trace_cpu, i);
+		global_trace.data[i] = &per_cpu(global_trace_cpu, i);
 		max_tr.data[i] = &per_cpu(max_data, i);
 	}
 
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 8b9f4f6e9559..405cb850b75d 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -7,10 +7,10 @@
 #include <linux/clocksource.h>
 #include <linux/ring_buffer.h>
 #include <linux/mmiotrace.h>
+#include <linux/tracepoint.h>
 #include <linux/ftrace.h>
 #include <trace/boot.h>
 #include <linux/kmemtrace.h>
-#include <trace/power.h>
 
 #include <linux/trace_seq.h>
 #include <linux/ftrace_event.h>
@@ -34,167 +34,61 @@ enum trace_type {
 	TRACE_GRAPH_ENT,
 	TRACE_USER_STACK,
 	TRACE_HW_BRANCHES,
-	TRACE_SYSCALL_ENTER,
-	TRACE_SYSCALL_EXIT,
 	TRACE_KMEM_ALLOC,
 	TRACE_KMEM_FREE,
-	TRACE_POWER,
 	TRACE_BLK,
 
 	__TRACE_LAST_TYPE,
 };
 
-/*
- * Function trace entry - function address and parent function addres:
- */
-struct ftrace_entry {
-	struct trace_entry	ent;
-	unsigned long		ip;
-	unsigned long		parent_ip;
-};
-
-/* Function call entry */
-struct ftrace_graph_ent_entry {
-	struct trace_entry		ent;
-	struct ftrace_graph_ent		graph_ent;
+enum kmemtrace_type_id {
+	KMEMTRACE_TYPE_KMALLOC = 0,	/* kmalloc() or kfree(). */
+	KMEMTRACE_TYPE_CACHE,		/* kmem_cache_*(). */
+	KMEMTRACE_TYPE_PAGES,		/* __get_free_pages() and friends. */
 };
 
-/* Function return entry */
-struct ftrace_graph_ret_entry {
-	struct trace_entry		ent;
-	struct ftrace_graph_ret		ret;
-};
 extern struct tracer boot_tracer;
 
-/*
- * Context switch trace entry - which task (and prio) we switched from/to:
- */
-struct ctx_switch_entry {
-	struct trace_entry	ent;
-	unsigned int		prev_pid;
-	unsigned char		prev_prio;
-	unsigned char		prev_state;
-	unsigned int		next_pid;
-	unsigned char		next_prio;
-	unsigned char		next_state;
-	unsigned int		next_cpu;
-};
+#undef __field
+#define __field(type, item)		type	item;
 
-/*
- * Special (free-form) trace entry:
- */
-struct special_entry {
-	struct trace_entry	ent;
-	unsigned long		arg1;
-	unsigned long		arg2;
-	unsigned long		arg3;
-};
+#undef __field_struct
+#define __field_struct(type, item)	__field(type, item)
 
-/*
- * Stack-trace entry:
- */
+#undef __field_desc
+#define __field_desc(type, container, item)
 
-#define FTRACE_STACK_ENTRIES	8
+#undef __array
+#define __array(type, item, size)	type	item[size];
 
-struct stack_entry {
-	struct trace_entry	ent;
-	unsigned long		caller[FTRACE_STACK_ENTRIES];
-};
+#undef __array_desc
+#define __array_desc(type, container, item, size)
 
-struct userstack_entry {
-	struct trace_entry	ent;
-	unsigned long		caller[FTRACE_STACK_ENTRIES];
-};
+#undef __dynamic_array
+#define __dynamic_array(type, item)	type	item[];
 
-/*
- * trace_printk entry:
- */
-struct bprint_entry {
-	struct trace_entry	ent;
-	unsigned long		ip;
-	const char		*fmt;
-	u32			buf[];
-};
+#undef F_STRUCT
+#define F_STRUCT(args...)		args
 
-struct print_entry {
-	struct trace_entry	ent;
-	unsigned long		ip;
-	char			buf[];
-};
-
-#define TRACE_OLD_SIZE		88
-
-struct trace_field_cont {
-	unsigned char		type;
-	/* Temporary till we get rid of this completely */
-	char			buf[TRACE_OLD_SIZE - 1];
-};
-
-struct trace_mmiotrace_rw {
-	struct trace_entry	ent;
-	struct mmiotrace_rw	rw;
-};
-
-struct trace_mmiotrace_map {
-	struct trace_entry	ent;
-	struct mmiotrace_map	map;
-};
-
-struct trace_boot_call {
-	struct trace_entry	ent;
-	struct boot_trace_call boot_call;
-};
-
-struct trace_boot_ret {
-	struct trace_entry	ent;
-	struct boot_trace_ret boot_ret;
-};
-
-#define TRACE_FUNC_SIZE 30
-#define TRACE_FILE_SIZE 20
-struct trace_branch {
-	struct trace_entry	ent;
-	unsigned	        line;
-	char			func[TRACE_FUNC_SIZE+1];
-	char			file[TRACE_FILE_SIZE+1];
-	char			correct;
-};
-
-struct hw_branch_entry {
-	struct trace_entry	ent;
-	u64			from;
-	u64			to;
-};
+#undef FTRACE_ENTRY
+#define FTRACE_ENTRY(name, struct_name, id, tstruct, print)	\
+	struct struct_name {					\
+		struct trace_entry	ent;			\
+		tstruct						\
+	}
 
-struct trace_power {
-	struct trace_entry	ent;
-	struct power_trace	state_data;
-};
+#undef TP_ARGS
+#define TP_ARGS(args...)	args
 
-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;
-	unsigned long call_site;
-	const void *ptr;
-	size_t bytes_req;
-	size_t bytes_alloc;
-	gfp_t gfp_flags;
-	int node;
-};
+#undef FTRACE_ENTRY_DUP
+#define FTRACE_ENTRY_DUP(name, name_struct, id, tstruct, printk)
 
-struct kmemtrace_free_entry {
-	struct trace_entry	ent;
-	enum kmemtrace_type_id type_id;
-	unsigned long call_site;
-	const void *ptr;
-};
+#include "trace_entries.h"
 
+/*
+ * syscalls are special, and need special handling, this is why
+ * they are not included in trace_entries.h
+ */
 struct syscall_trace_enter {
 	struct trace_entry	ent;
 	int			nr;
@@ -207,13 +101,12 @@ struct syscall_trace_exit {
 	unsigned long		ret;
 };
 
-
 /*
  * trace_flag_type is an enumeration that holds different
  * states when a trace occurs. These are:
  *  IRQS_OFF		- interrupts were disabled
  *  IRQS_NOSUPPORT	- arch does not support irqs_disabled_flags
- *  NEED_RESCED		- reschedule is requested
+ *  NEED_RESCHED	- reschedule is requested
  *  HARDIRQ		- inside an interrupt handler
  *  SOFTIRQ		- inside a softirq handler
  */
@@ -236,9 +129,6 @@ struct trace_array_cpu {
 	atomic_t		disabled;
 	void			*buffer_page;	/* ring buffer spare */
 
-	/* these fields get copied into max-trace: */
-	unsigned long		trace_idx;
-	unsigned long		overrun;
 	unsigned long		saved_latency;
 	unsigned long		critical_start;
 	unsigned long		critical_end;
@@ -246,6 +136,7 @@ struct trace_array_cpu {
 	unsigned long		nice;
 	unsigned long		policy;
 	unsigned long		rt_priority;
+	unsigned long		skipped_entries;
 	cycle_t			preempt_timestamp;
 	pid_t			pid;
 	uid_t			uid;
@@ -314,15 +205,10 @@ extern void __ftrace_bad_type(void);
 		IF_ASSIGN(var, ent, struct ftrace_graph_ret_entry,	\
 			  TRACE_GRAPH_RET);		\
 		IF_ASSIGN(var, ent, struct hw_branch_entry, TRACE_HW_BRANCHES);\
-		IF_ASSIGN(var, ent, struct trace_power, TRACE_POWER); \
 		IF_ASSIGN(var, ent, struct kmemtrace_alloc_entry,	\
 			  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)
 
@@ -398,7 +284,6 @@ struct tracer {
 	struct tracer		*next;
 	int			print_max;
 	struct tracer_flags	*flags;
-	struct tracer_stat	*stats;
 };
 
 
@@ -423,12 +308,13 @@ void init_tracer_sysprof_debugfs(struct dentry *d_tracer);
 
 struct ring_buffer_event;
 
-struct ring_buffer_event *trace_buffer_lock_reserve(struct trace_array *tr,
-						    int type,
-						    unsigned long len,
-						    unsigned long flags,
-						    int pc);
-void trace_buffer_unlock_commit(struct trace_array *tr,
+struct ring_buffer_event *
+trace_buffer_lock_reserve(struct ring_buffer *buffer,
+			  int type,
+			  unsigned long len,
+			  unsigned long flags,
+			  int pc);
+void trace_buffer_unlock_commit(struct ring_buffer *buffer,
 				struct ring_buffer_event *event,
 				unsigned long flags, int pc);
 
@@ -467,6 +353,7 @@ void trace_function(struct trace_array *tr,
 
 void trace_graph_return(struct ftrace_graph_ret *trace);
 int trace_graph_entry(struct ftrace_graph_ent *trace);
+void set_graph_array(struct trace_array *tr);
 
 void tracing_start_cmdline_record(void);
 void tracing_stop_cmdline_record(void);
@@ -475,35 +362,46 @@ void tracing_stop_sched_switch_record(void);
 void tracing_start_sched_switch_record(void);
 int register_tracer(struct tracer *type);
 void unregister_tracer(struct tracer *type);
+int is_tracing_stopped(void);
 
 extern unsigned long nsecs_to_usecs(unsigned long nsecs);
 
+#ifdef CONFIG_TRACER_MAX_TRACE
 extern unsigned long tracing_max_latency;
 extern unsigned long tracing_thresh;
 
 void update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu);
 void update_max_tr_single(struct trace_array *tr,
 			  struct task_struct *tsk, int cpu);
+#endif /* CONFIG_TRACER_MAX_TRACE */
 
-void __trace_stack(struct trace_array *tr,
-		   unsigned long flags,
-		   int skip, int pc);
+#ifdef CONFIG_STACKTRACE
+void ftrace_trace_stack(struct ring_buffer *buffer, unsigned long flags,
+			int skip, int pc);
 
-extern cycle_t ftrace_now(int cpu);
+void ftrace_trace_userstack(struct ring_buffer *buffer, unsigned long flags,
+			    int pc);
 
-#ifdef CONFIG_CONTEXT_SWITCH_TRACER
-typedef void
-(*tracer_switch_func_t)(void *private,
-			void *__rq,
-			struct task_struct *prev,
-			struct task_struct *next);
-
-struct tracer_switch_ops {
-	tracer_switch_func_t		func;
-	void				*private;
-	struct tracer_switch_ops	*next;
-};
-#endif /* CONFIG_CONTEXT_SWITCH_TRACER */
+void __trace_stack(struct trace_array *tr, unsigned long flags, int skip,
+		   int pc);
+#else
+static inline void ftrace_trace_stack(struct trace_array *tr,
+				      unsigned long flags, int skip, int pc)
+{
+}
+
+static inline void ftrace_trace_userstack(struct trace_array *tr,
+					  unsigned long flags, int pc)
+{
+}
+
+static inline void __trace_stack(struct trace_array *tr, unsigned long flags,
+				 int skip, int pc)
+{
+}
+#endif /* CONFIG_STACKTRACE */
+
+extern cycle_t ftrace_now(int cpu);
 
 extern void trace_find_cmdline(int pid, char comm[]);
 
@@ -513,6 +411,10 @@ extern unsigned long ftrace_update_tot_cnt;
 extern int DYN_FTRACE_TEST_NAME(void);
 #endif
 
+extern int ring_buffer_expanded;
+extern bool tracing_selftest_disabled;
+DECLARE_PER_CPU(local_t, ftrace_cpu_disabled);
+
 #ifdef CONFIG_FTRACE_STARTUP_TEST
 extern int trace_selftest_startup_function(struct tracer *trace,
 					   struct trace_array *tr);
@@ -544,9 +446,16 @@ extern int
 trace_vbprintk(unsigned long ip, const char *fmt, va_list args);
 extern int
 trace_vprintk(unsigned long ip, const char *fmt, va_list args);
+extern int
+trace_array_vprintk(struct trace_array *tr,
+		    unsigned long ip, const char *fmt, va_list args);
+int trace_array_printk(struct trace_array *tr,
+		       unsigned long ip, const char *fmt, ...);
 
 extern unsigned long trace_flags;
 
+extern int trace_clock_id;
+
 /* Standard output formatting function used for function return traces */
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 extern enum print_line_t print_graph_function(struct trace_iterator *iter);
@@ -609,6 +518,41 @@ static inline int ftrace_trace_task(struct task_struct *task)
 #endif
 
 /*
+ * struct trace_parser - servers for reading the user input separated by spaces
+ * @cont: set if the input is not complete - no final space char was found
+ * @buffer: holds the parsed user input
+ * @idx: user input lenght
+ * @size: buffer size
+ */
+struct trace_parser {
+	bool		cont;
+	char		*buffer;
+	unsigned	idx;
+	unsigned	size;
+};
+
+static inline bool trace_parser_loaded(struct trace_parser *parser)
+{
+	return (parser->idx != 0);
+}
+
+static inline bool trace_parser_cont(struct trace_parser *parser)
+{
+	return parser->cont;
+}
+
+static inline void trace_parser_clear(struct trace_parser *parser)
+{
+	parser->cont = false;
+	parser->idx = 0;
+}
+
+extern int trace_parser_get_init(struct trace_parser *parser, int size);
+extern void trace_parser_put(struct trace_parser *parser);
+extern int trace_get_user(struct trace_parser *parser, const char __user *ubuf,
+	size_t cnt, loff_t *ppos);
+
+/*
  * trace_iterator_flags is an enumeration that defines bit
  * positions into trace_flags that controls the output.
  *
@@ -635,9 +579,8 @@ 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,
-	TRACE_ITER_GRAPH_TIME		= 0x200000,
+	TRACE_ITER_SLEEP_TIME		= 0x80000,
+	TRACE_ITER_GRAPH_TIME		= 0x100000,
 };
 
 /*
@@ -734,6 +677,7 @@ struct ftrace_event_field {
 	struct list_head	link;
 	char			*name;
 	char			*type;
+	int			filter_type;
 	int			offset;
 	int			size;
 	int			is_signed;
@@ -743,13 +687,15 @@ struct event_filter {
 	int			n_preds;
 	struct filter_pred	**preds;
 	char			*filter_string;
+	bool			no_reset;
 };
 
 struct event_subsystem {
 	struct list_head	list;
 	const char		*name;
 	struct dentry		*entry;
-	void			*filter;
+	struct event_filter	*filter;
+	int			nr_events;
 };
 
 struct filter_pred;
@@ -777,6 +723,7 @@ extern int apply_subsystem_event_filter(struct event_subsystem *system,
 					char *filter_string);
 extern void print_subsystem_event_filter(struct event_subsystem *system,
 					 struct trace_seq *s);
+extern int filter_assign_type(const char *type);
 
 static inline int
 filter_check_discard(struct ftrace_event_call *call, void *rec,
@@ -791,58 +738,18 @@ filter_check_discard(struct ftrace_event_call *call, void *rec,
 	return 0;
 }
 
-#define DEFINE_COMPARISON_PRED(type)					\
-static int filter_pred_##type(struct filter_pred *pred, void *event,	\
-			      int val1, int val2)			\
-{									\
-	type *addr = (type *)(event + pred->offset);			\
-	type val = (type)pred->val;					\
-	int match = 0;							\
-									\
-	switch (pred->op) {						\
-	case OP_LT:							\
-		match = (*addr < val);					\
-		break;							\
-	case OP_LE:							\
-		match = (*addr <= val);					\
-		break;							\
-	case OP_GT:							\
-		match = (*addr > val);					\
-		break;							\
-	case OP_GE:							\
-		match = (*addr >= val);					\
-		break;							\
-	default:							\
-		break;							\
-	}								\
-									\
-	return match;							\
-}
-
-#define DEFINE_EQUALITY_PRED(size)					\
-static int filter_pred_##size(struct filter_pred *pred, void *event,	\
-			      int val1, int val2)			\
-{									\
-	u##size *addr = (u##size *)(event + pred->offset);		\
-	u##size val = (u##size)pred->val;				\
-	int match;							\
-									\
-	match = (val == *addr) ^ pred->not;				\
-									\
-	return match;							\
-}
-
 extern struct mutex event_mutex;
 extern struct list_head ftrace_events;
 
 extern const char *__start___trace_bprintk_fmt[];
 extern const char *__stop___trace_bprintk_fmt[];
 
-#undef TRACE_EVENT_FORMAT
-#define TRACE_EVENT_FORMAT(call, proto, args, fmt, tstruct, tpfmt)	\
+#undef FTRACE_ENTRY
+#define FTRACE_ENTRY(call, struct_name, id, tstruct, print)		\
 	extern struct ftrace_event_call event_##call;
-#undef TRACE_EVENT_FORMAT_NOFILTER
-#define TRACE_EVENT_FORMAT_NOFILTER(call, proto, args, fmt, tstruct, tpfmt)
-#include "trace_event_types.h"
+#undef FTRACE_ENTRY_DUP
+#define FTRACE_ENTRY_DUP(call, struct_name, id, tstruct, print)		\
+	FTRACE_ENTRY(call, struct_name, id, PARAMS(tstruct), PARAMS(print))
+#include "trace_entries.h"
 
 #endif /* _LINUX_KERNEL_TRACE_H */
diff --git a/kernel/trace/trace_boot.c b/kernel/trace/trace_boot.c
index a29ef23ffb47..c21d5f3956ad 100644
--- a/kernel/trace/trace_boot.c
+++ b/kernel/trace/trace_boot.c
@@ -41,14 +41,12 @@ void disable_boot_trace(void)
 
 static int boot_trace_init(struct trace_array *tr)
 {
-	int cpu;
 	boot_trace = tr;
 
 	if (!tr)
 		return 0;
 
-	for_each_cpu(cpu, cpu_possible_mask)
-		tracing_reset(tr, cpu);
+	tracing_reset_online_cpus(tr);
 
 	tracing_sched_switch_assign_trace(tr);
 	return 0;
@@ -131,7 +129,9 @@ struct tracer boot_tracer __read_mostly =
 
 void trace_boot_call(struct boot_trace_call *bt, initcall_t fn)
 {
+	struct ftrace_event_call *call = &event_boot_call;
 	struct ring_buffer_event *event;
+	struct ring_buffer *buffer;
 	struct trace_boot_call *entry;
 	struct trace_array *tr = boot_trace;
 
@@ -144,20 +144,24 @@ void trace_boot_call(struct boot_trace_call *bt, initcall_t fn)
 	sprint_symbol(bt->func, (unsigned long)fn);
 	preempt_disable();
 
-	event = trace_buffer_lock_reserve(tr, TRACE_BOOT_CALL,
+	buffer = tr->buffer;
+	event = trace_buffer_lock_reserve(buffer, TRACE_BOOT_CALL,
 					  sizeof(*entry), 0, 0);
 	if (!event)
 		goto out;
 	entry	= ring_buffer_event_data(event);
 	entry->boot_call = *bt;
-	trace_buffer_unlock_commit(tr, event, 0, 0);
+	if (!filter_check_discard(call, entry, buffer, event))
+		trace_buffer_unlock_commit(buffer, event, 0, 0);
  out:
 	preempt_enable();
 }
 
 void trace_boot_ret(struct boot_trace_ret *bt, initcall_t fn)
 {
+	struct ftrace_event_call *call = &event_boot_ret;
 	struct ring_buffer_event *event;
+	struct ring_buffer *buffer;
 	struct trace_boot_ret *entry;
 	struct trace_array *tr = boot_trace;
 
@@ -167,13 +171,15 @@ void trace_boot_ret(struct boot_trace_ret *bt, initcall_t fn)
 	sprint_symbol(bt->func, (unsigned long)fn);
 	preempt_disable();
 
-	event = trace_buffer_lock_reserve(tr, TRACE_BOOT_RET,
+	buffer = tr->buffer;
+	event = trace_buffer_lock_reserve(buffer, TRACE_BOOT_RET,
 					  sizeof(*entry), 0, 0);
 	if (!event)
 		goto out;
 	entry	= ring_buffer_event_data(event);
 	entry->boot_ret = *bt;
-	trace_buffer_unlock_commit(tr, event, 0, 0);
+	if (!filter_check_discard(call, entry, buffer, event))
+		trace_buffer_unlock_commit(buffer, event, 0, 0);
  out:
 	preempt_enable();
 }
diff --git a/kernel/trace/trace_branch.c b/kernel/trace/trace_branch.c
index 7a7a9fd249a9..4a194f08f88c 100644
--- a/kernel/trace/trace_branch.c
+++ b/kernel/trace/trace_branch.c
@@ -34,6 +34,7 @@ probe_likely_condition(struct ftrace_branch_data *f, int val, int expect)
 	struct trace_array *tr = branch_tracer;
 	struct ring_buffer_event *event;
 	struct trace_branch *entry;
+	struct ring_buffer *buffer;
 	unsigned long flags;
 	int cpu, pc;
 	const char *p;
@@ -54,7 +55,8 @@ probe_likely_condition(struct ftrace_branch_data *f, int val, int expect)
 		goto out;
 
 	pc = preempt_count();
-	event = trace_buffer_lock_reserve(tr, TRACE_BRANCH,
+	buffer = tr->buffer;
+	event = trace_buffer_lock_reserve(buffer, TRACE_BRANCH,
 					  sizeof(*entry), flags, pc);
 	if (!event)
 		goto out;
@@ -74,8 +76,8 @@ probe_likely_condition(struct ftrace_branch_data *f, int val, int expect)
 	entry->line = f->line;
 	entry->correct = val == expect;
 
-	if (!filter_check_discard(call, entry, tr->buffer, event))
-		ring_buffer_unlock_commit(tr->buffer, event);
+	if (!filter_check_discard(call, entry, buffer, event))
+		ring_buffer_unlock_commit(buffer, event);
 
  out:
 	atomic_dec(&tr->data[cpu]->disabled);
diff --git a/kernel/trace/trace_clock.c b/kernel/trace/trace_clock.c
index b588fd81f7f9..20c5f92e28a8 100644
--- a/kernel/trace/trace_clock.c
+++ b/kernel/trace/trace_clock.c
@@ -66,10 +66,14 @@ u64 notrace trace_clock(void)
  * Used by plugins that need globally coherent timestamps.
  */
 
-static u64 prev_trace_clock_time;
-
-static raw_spinlock_t trace_clock_lock ____cacheline_aligned_in_smp =
-	(raw_spinlock_t)__RAW_SPIN_LOCK_UNLOCKED;
+/* keep prev_time and lock in the same cacheline. */
+static struct {
+	u64 prev_time;
+	raw_spinlock_t lock;
+} trace_clock_struct ____cacheline_aligned_in_smp =
+	{
+		.lock = (raw_spinlock_t)__RAW_SPIN_LOCK_UNLOCKED,
+	};
 
 u64 notrace trace_clock_global(void)
 {
@@ -88,19 +92,19 @@ u64 notrace trace_clock_global(void)
 	if (unlikely(in_nmi()))
 		goto out;
 
-	__raw_spin_lock(&trace_clock_lock);
+	__raw_spin_lock(&trace_clock_struct.lock);
 
 	/*
 	 * TODO: if this happens often then maybe we should reset
-	 * my_scd->clock to prev_trace_clock_time+1, to make sure
+	 * my_scd->clock to prev_time+1, to make sure
 	 * we start ticking with the local clock from now on?
 	 */
-	if ((s64)(now - prev_trace_clock_time) < 0)
-		now = prev_trace_clock_time + 1;
+	if ((s64)(now - trace_clock_struct.prev_time) < 0)
+		now = trace_clock_struct.prev_time + 1;
 
-	prev_trace_clock_time = now;
+	trace_clock_struct.prev_time = now;
 
-	__raw_spin_unlock(&trace_clock_lock);
+	__raw_spin_unlock(&trace_clock_struct.lock);
 
  out:
 	raw_local_irq_restore(flags);
diff --git a/kernel/trace/trace_entries.h b/kernel/trace/trace_entries.h
new file mode 100644
index 000000000000..ead3d724599d
--- /dev/null
+++ b/kernel/trace/trace_entries.h
@@ -0,0 +1,366 @@
+/*
+ * This file defines the trace event structures that go into the ring
+ * buffer directly. They are created via macros so that changes for them
+ * appear in the format file. Using macros will automate this process.
+ *
+ * The macro used to create a ftrace data structure is:
+ *
+ * FTRACE_ENTRY( name, struct_name, id, structure, print )
+ *
+ * @name: the name used the event name, as well as the name of
+ *   the directory that holds the format file.
+ *
+ * @struct_name: the name of the structure that is created.
+ *
+ * @id: The event identifier that is used to detect what event
+ *    this is from the ring buffer.
+ *
+ * @structure: the structure layout
+ *
+ *  - __field(	type,	item	)
+ *	  This is equivalent to declaring
+ *		type	item;
+ *	  in the structure.
+ *  - __array(	type,	item,	size	)
+ *	  This is equivalent to declaring
+ *		type	item[size];
+ *	  in the structure.
+ *
+ *   * for structures within structures, the format of the internal
+ *	structure is layed out. This allows the internal structure
+ *	to be deciphered for the format file. Although these macros
+ *	may become out of sync with the internal structure, they
+ *	will create a compile error if it happens. Since the
+ *	internel structures are just tracing helpers, this is not
+ *	an issue.
+ *
+ *	When an internal structure is used, it should use:
+ *
+ *	__field_struct(	type,	item	)
+ *
+ *	instead of __field. This will prevent it from being shown in
+ *	the output file. The fields in the structure should use.
+ *
+ *	__field_desc(	type,	container,	item		)
+ *	__array_desc(	type,	container,	item,	len	)
+ *
+ *	type, item and len are the same as __field and __array, but
+ *	container is added. This is the name of the item in
+ *	__field_struct that this is describing.
+ *
+ *
+ * @print: the print format shown to users in the format file.
+ */
+
+/*
+ * Function trace entry - function address and parent function addres:
+ */
+FTRACE_ENTRY(function, ftrace_entry,
+
+	TRACE_FN,
+
+	F_STRUCT(
+		__field(	unsigned long,	ip		)
+		__field(	unsigned long,	parent_ip	)
+	),
+
+	F_printk(" %lx <-- %lx", __entry->ip, __entry->parent_ip)
+);
+
+/* Function call entry */
+FTRACE_ENTRY(funcgraph_entry, ftrace_graph_ent_entry,
+
+	TRACE_GRAPH_ENT,
+
+	F_STRUCT(
+		__field_struct(	struct ftrace_graph_ent,	graph_ent	)
+		__field_desc(	unsigned long,	graph_ent,	func		)
+		__field_desc(	int,		graph_ent,	depth		)
+	),
+
+	F_printk("--> %lx (%d)", __entry->func, __entry->depth)
+);
+
+/* Function return entry */
+FTRACE_ENTRY(funcgraph_exit, ftrace_graph_ret_entry,
+
+	TRACE_GRAPH_RET,
+
+	F_STRUCT(
+		__field_struct(	struct ftrace_graph_ret,	ret	)
+		__field_desc(	unsigned long,	ret,		func	)
+		__field_desc(	unsigned long long, ret,	calltime)
+		__field_desc(	unsigned long long, ret,	rettime	)
+		__field_desc(	unsigned long,	ret,		overrun	)
+		__field_desc(	int,		ret,		depth	)
+	),
+
+	F_printk("<-- %lx (%d) (start: %llx  end: %llx) over: %d",
+		 __entry->func, __entry->depth,
+		 __entry->calltime, __entry->rettime,
+		 __entry->depth)
+);
+
+/*
+ * Context switch trace entry - which task (and prio) we switched from/to:
+ *
+ * This is used for both wakeup and context switches. We only want
+ * to create one structure, but we need two outputs for it.
+ */
+#define FTRACE_CTX_FIELDS					\
+	__field(	unsigned int,	prev_pid	)	\
+	__field(	unsigned char,	prev_prio	)	\
+	__field(	unsigned char,	prev_state	)	\
+	__field(	unsigned int,	next_pid	)	\
+	__field(	unsigned char,	next_prio	)	\
+	__field(	unsigned char,	next_state	)	\
+	__field(	unsigned int,	next_cpu	)
+
+FTRACE_ENTRY(context_switch, ctx_switch_entry,
+
+	TRACE_CTX,
+
+	F_STRUCT(
+		FTRACE_CTX_FIELDS
+	),
+
+	F_printk("%u:%u:%u  ==> %u:%u:%u [%03u]",
+		 __entry->prev_pid, __entry->prev_prio, __entry->prev_state,
+		 __entry->next_pid, __entry->next_prio, __entry->next_state,
+		 __entry->next_cpu
+		)
+);
+
+/*
+ * FTRACE_ENTRY_DUP only creates the format file, it will not
+ *  create another structure.
+ */
+FTRACE_ENTRY_DUP(wakeup, ctx_switch_entry,
+
+	TRACE_WAKE,
+
+	F_STRUCT(
+		FTRACE_CTX_FIELDS
+	),
+
+	F_printk("%u:%u:%u  ==+ %u:%u:%u [%03u]",
+		 __entry->prev_pid, __entry->prev_prio, __entry->prev_state,
+		 __entry->next_pid, __entry->next_prio, __entry->next_state,
+		 __entry->next_cpu
+		)
+);
+
+/*
+ * Special (free-form) trace entry:
+ */
+FTRACE_ENTRY(special, special_entry,
+
+	TRACE_SPECIAL,
+
+	F_STRUCT(
+		__field(	unsigned long,	arg1	)
+		__field(	unsigned long,	arg2	)
+		__field(	unsigned long,	arg3	)
+	),
+
+	F_printk("(%08lx) (%08lx) (%08lx)",
+		 __entry->arg1, __entry->arg2, __entry->arg3)
+);
+
+/*
+ * Stack-trace entry:
+ */
+
+#define FTRACE_STACK_ENTRIES	8
+
+FTRACE_ENTRY(kernel_stack, stack_entry,
+
+	TRACE_STACK,
+
+	F_STRUCT(
+		__array(	unsigned long,	caller, FTRACE_STACK_ENTRIES	)
+	),
+
+	F_printk("\t=> (%08lx)\n\t=> (%08lx)\n\t=> (%08lx)\n\t=> (%08lx)\n"
+		 "\t=> (%08lx)\n\t=> (%08lx)\n\t=> (%08lx)\n\t=> (%08lx)\n",
+		 __entry->caller[0], __entry->caller[1], __entry->caller[2],
+		 __entry->caller[3], __entry->caller[4], __entry->caller[5],
+		 __entry->caller[6], __entry->caller[7])
+);
+
+FTRACE_ENTRY(user_stack, userstack_entry,
+
+	TRACE_USER_STACK,
+
+	F_STRUCT(
+		__field(	unsigned int,	tgid	)
+		__array(	unsigned long,	caller, FTRACE_STACK_ENTRIES	)
+	),
+
+	F_printk("\t=> (%08lx)\n\t=> (%08lx)\n\t=> (%08lx)\n\t=> (%08lx)\n"
+		 "\t=> (%08lx)\n\t=> (%08lx)\n\t=> (%08lx)\n\t=> (%08lx)\n",
+		 __entry->caller[0], __entry->caller[1], __entry->caller[2],
+		 __entry->caller[3], __entry->caller[4], __entry->caller[5],
+		 __entry->caller[6], __entry->caller[7])
+);
+
+/*
+ * trace_printk entry:
+ */
+FTRACE_ENTRY(bprint, bprint_entry,
+
+	TRACE_BPRINT,
+
+	F_STRUCT(
+		__field(	unsigned long,	ip	)
+		__field(	const char *,	fmt	)
+		__dynamic_array(	u32,	buf	)
+	),
+
+	F_printk("%08lx fmt:%p",
+		 __entry->ip, __entry->fmt)
+);
+
+FTRACE_ENTRY(print, print_entry,
+
+	TRACE_PRINT,
+
+	F_STRUCT(
+		__field(	unsigned long,	ip	)
+		__dynamic_array(	char,	buf	)
+	),
+
+	F_printk("%08lx %s",
+		 __entry->ip, __entry->buf)
+);
+
+FTRACE_ENTRY(mmiotrace_rw, trace_mmiotrace_rw,
+
+	TRACE_MMIO_RW,
+
+	F_STRUCT(
+		__field_struct(	struct mmiotrace_rw,	rw	)
+		__field_desc(	resource_size_t, rw,	phys	)
+		__field_desc(	unsigned long,	rw,	value	)
+		__field_desc(	unsigned long,	rw,	pc	)
+		__field_desc(	int, 		rw,	map_id	)
+		__field_desc(	unsigned char,	rw,	opcode	)
+		__field_desc(	unsigned char,	rw,	width	)
+	),
+
+	F_printk("%lx %lx %lx %d %x %x",
+		 (unsigned long)__entry->phys, __entry->value, __entry->pc,
+		 __entry->map_id, __entry->opcode, __entry->width)
+);
+
+FTRACE_ENTRY(mmiotrace_map, trace_mmiotrace_map,
+
+	TRACE_MMIO_MAP,
+
+	F_STRUCT(
+		__field_struct(	struct mmiotrace_map,	map	)
+		__field_desc(	resource_size_t, map,	phys	)
+		__field_desc(	unsigned long,	map,	virt	)
+		__field_desc(	unsigned long,	map,	len	)
+		__field_desc(	int, 		map,	map_id	)
+		__field_desc(	unsigned char,	map,	opcode	)
+	),
+
+	F_printk("%lx %lx %lx %d %x",
+		 (unsigned long)__entry->phys, __entry->virt, __entry->len,
+		 __entry->map_id, __entry->opcode)
+);
+
+FTRACE_ENTRY(boot_call, trace_boot_call,
+
+	TRACE_BOOT_CALL,
+
+	F_STRUCT(
+		__field_struct(	struct boot_trace_call,	boot_call	)
+		__field_desc(	pid_t,	boot_call,	caller		)
+		__array_desc(	char,	boot_call,	func,	KSYM_SYMBOL_LEN)
+	),
+
+	F_printk("%d  %s", __entry->caller, __entry->func)
+);
+
+FTRACE_ENTRY(boot_ret, trace_boot_ret,
+
+	TRACE_BOOT_RET,
+
+	F_STRUCT(
+		__field_struct(	struct boot_trace_ret,	boot_ret	)
+		__array_desc(	char,	boot_ret,	func,	KSYM_SYMBOL_LEN)
+		__field_desc(	int,	boot_ret,	result		)
+		__field_desc(	unsigned long, boot_ret, duration	)
+	),
+
+	F_printk("%s %d %lx",
+		 __entry->func, __entry->result, __entry->duration)
+);
+
+#define TRACE_FUNC_SIZE 30
+#define TRACE_FILE_SIZE 20
+
+FTRACE_ENTRY(branch, trace_branch,
+
+	TRACE_BRANCH,
+
+	F_STRUCT(
+		__field(	unsigned int,	line				)
+		__array(	char,		func,	TRACE_FUNC_SIZE+1	)
+		__array(	char,		file,	TRACE_FILE_SIZE+1	)
+		__field(	char,		correct				)
+	),
+
+	F_printk("%u:%s:%s (%u)",
+		 __entry->line,
+		 __entry->func, __entry->file, __entry->correct)
+);
+
+FTRACE_ENTRY(hw_branch, hw_branch_entry,
+
+	TRACE_HW_BRANCHES,
+
+	F_STRUCT(
+		__field(	u64,	from	)
+		__field(	u64,	to	)
+	),
+
+	F_printk("from: %llx to: %llx", __entry->from, __entry->to)
+);
+
+FTRACE_ENTRY(kmem_alloc, kmemtrace_alloc_entry,
+
+	TRACE_KMEM_ALLOC,
+
+	F_STRUCT(
+		__field(	enum kmemtrace_type_id,	type_id		)
+		__field(	unsigned long,		call_site	)
+		__field(	const void *,		ptr		)
+		__field(	size_t,			bytes_req	)
+		__field(	size_t,			bytes_alloc	)
+		__field(	gfp_t,			gfp_flags	)
+		__field(	int,			node		)
+	),
+
+	F_printk("type:%u call_site:%lx ptr:%p req:%zi alloc:%zi"
+		 " flags:%x node:%d",
+		 __entry->type_id, __entry->call_site, __entry->ptr,
+		 __entry->bytes_req, __entry->bytes_alloc,
+		 __entry->gfp_flags, __entry->node)
+);
+
+FTRACE_ENTRY(kmem_free, kmemtrace_free_entry,
+
+	TRACE_KMEM_FREE,
+
+	F_STRUCT(
+		__field(	enum kmemtrace_type_id,	type_id		)
+		__field(	unsigned long,		call_site	)
+		__field(	const void *,		ptr		)
+	),
+
+	F_printk("type:%u call_site:%lx ptr:%p",
+		 __entry->type_id, __entry->call_site, __entry->ptr)
+);
diff --git a/kernel/trace/trace_event_profile.c b/kernel/trace/trace_event_profile.c
index 11ba5bb4ed0a..8d5c171cc998 100644
--- a/kernel/trace/trace_event_profile.c
+++ b/kernel/trace/trace_event_profile.c
@@ -5,8 +5,65 @@
  *
  */
 
+#include <linux/module.h>
 #include "trace.h"
 
+/*
+ * We can't use a size but a type in alloc_percpu()
+ * So let's create a dummy type that matches the desired size
+ */
+typedef struct {char buf[FTRACE_MAX_PROFILE_SIZE];} profile_buf_t;
+
+char		*trace_profile_buf;
+EXPORT_SYMBOL_GPL(trace_profile_buf);
+
+char		*trace_profile_buf_nmi;
+EXPORT_SYMBOL_GPL(trace_profile_buf_nmi);
+
+/* Count the events in use (per event id, not per instance) */
+static int	total_profile_count;
+
+static int ftrace_profile_enable_event(struct ftrace_event_call *event)
+{
+	char *buf;
+	int ret = -ENOMEM;
+
+	if (atomic_inc_return(&event->profile_count))
+		return 0;
+
+	if (!total_profile_count) {
+		buf = (char *)alloc_percpu(profile_buf_t);
+		if (!buf)
+			goto fail_buf;
+
+		rcu_assign_pointer(trace_profile_buf, buf);
+
+		buf = (char *)alloc_percpu(profile_buf_t);
+		if (!buf)
+			goto fail_buf_nmi;
+
+		rcu_assign_pointer(trace_profile_buf_nmi, buf);
+	}
+
+	ret = event->profile_enable();
+	if (!ret) {
+		total_profile_count++;
+		return 0;
+	}
+
+fail_buf_nmi:
+	if (!total_profile_count) {
+		free_percpu(trace_profile_buf_nmi);
+		free_percpu(trace_profile_buf);
+		trace_profile_buf_nmi = NULL;
+		trace_profile_buf = NULL;
+	}
+fail_buf:
+	atomic_dec(&event->profile_count);
+
+	return ret;
+}
+
 int ftrace_profile_enable(int event_id)
 {
 	struct ftrace_event_call *event;
@@ -14,8 +71,9 @@ int ftrace_profile_enable(int event_id)
 
 	mutex_lock(&event_mutex);
 	list_for_each_entry(event, &ftrace_events, list) {
-		if (event->id == event_id && event->profile_enable) {
-			ret = event->profile_enable(event);
+		if (event->id == event_id && event->profile_enable &&
+		    try_module_get(event->mod)) {
+			ret = ftrace_profile_enable_event(event);
 			break;
 		}
 	}
@@ -24,6 +82,33 @@ int ftrace_profile_enable(int event_id)
 	return ret;
 }
 
+static void ftrace_profile_disable_event(struct ftrace_event_call *event)
+{
+	char *buf, *nmi_buf;
+
+	if (!atomic_add_negative(-1, &event->profile_count))
+		return;
+
+	event->profile_disable();
+
+	if (!--total_profile_count) {
+		buf = trace_profile_buf;
+		rcu_assign_pointer(trace_profile_buf, NULL);
+
+		nmi_buf = trace_profile_buf_nmi;
+		rcu_assign_pointer(trace_profile_buf_nmi, NULL);
+
+		/*
+		 * Ensure every events in profiling have finished before
+		 * releasing the buffers
+		 */
+		synchronize_sched();
+
+		free_percpu(buf);
+		free_percpu(nmi_buf);
+	}
+}
+
 void ftrace_profile_disable(int event_id)
 {
 	struct ftrace_event_call *event;
@@ -31,7 +116,8 @@ void ftrace_profile_disable(int event_id)
 	mutex_lock(&event_mutex);
 	list_for_each_entry(event, &ftrace_events, list) {
 		if (event->id == event_id) {
-			event->profile_disable(event);
+			ftrace_profile_disable_event(event);
+			module_put(event->mod);
 			break;
 		}
 	}
diff --git a/kernel/trace/trace_event_types.h b/kernel/trace/trace_event_types.h
deleted file mode 100644
index 6db005e12487..000000000000
--- a/kernel/trace/trace_event_types.h
+++ /dev/null
@@ -1,178 +0,0 @@
-#undef TRACE_SYSTEM
-#define TRACE_SYSTEM	ftrace
-
-/*
- * We cheat and use the proto type field as the ID
- * and args as the entry type (minus 'struct')
- */
-TRACE_EVENT_FORMAT(function, TRACE_FN, ftrace_entry, ignore,
-	TRACE_STRUCT(
-		TRACE_FIELD(unsigned long, ip, ip)
-		TRACE_FIELD(unsigned long, parent_ip, parent_ip)
-	),
-	TP_RAW_FMT(" %lx <-- %lx")
-);
-
-TRACE_EVENT_FORMAT(funcgraph_entry, TRACE_GRAPH_ENT,
-		   ftrace_graph_ent_entry, ignore,
-	TRACE_STRUCT(
-		TRACE_FIELD(unsigned long, graph_ent.func, func)
-		TRACE_FIELD(int, graph_ent.depth, depth)
-	),
-	TP_RAW_FMT("--> %lx (%d)")
-);
-
-TRACE_EVENT_FORMAT(funcgraph_exit, TRACE_GRAPH_RET,
-		   ftrace_graph_ret_entry, ignore,
-	TRACE_STRUCT(
-		TRACE_FIELD(unsigned long, ret.func, func)
-		TRACE_FIELD(unsigned long long, ret.calltime, calltime)
-		TRACE_FIELD(unsigned long long, ret.rettime, rettime)
-		TRACE_FIELD(unsigned long, ret.overrun, overrun)
-		TRACE_FIELD(int, ret.depth, depth)
-	),
-	TP_RAW_FMT("<-- %lx (%d)")
-);
-
-TRACE_EVENT_FORMAT(wakeup, TRACE_WAKE, ctx_switch_entry, ignore,
-	TRACE_STRUCT(
-		TRACE_FIELD(unsigned int, prev_pid, prev_pid)
-		TRACE_FIELD(unsigned char, prev_prio, prev_prio)
-		TRACE_FIELD(unsigned char, prev_state, prev_state)
-		TRACE_FIELD(unsigned int, next_pid, next_pid)
-		TRACE_FIELD(unsigned char, next_prio, next_prio)
-		TRACE_FIELD(unsigned char, next_state, next_state)
-		TRACE_FIELD(unsigned int, next_cpu, next_cpu)
-	),
-	TP_RAW_FMT("%u:%u:%u  ==+ %u:%u:%u [%03u]")
-);
-
-TRACE_EVENT_FORMAT(context_switch, TRACE_CTX, ctx_switch_entry, ignore,
-	TRACE_STRUCT(
-		TRACE_FIELD(unsigned int, prev_pid, prev_pid)
-		TRACE_FIELD(unsigned char, prev_prio, prev_prio)
-		TRACE_FIELD(unsigned char, prev_state, prev_state)
-		TRACE_FIELD(unsigned int, next_pid, next_pid)
-		TRACE_FIELD(unsigned char, next_prio, next_prio)
-		TRACE_FIELD(unsigned char, next_state, next_state)
-		TRACE_FIELD(unsigned int, next_cpu, next_cpu)
-	),
-	TP_RAW_FMT("%u:%u:%u  ==+ %u:%u:%u [%03u]")
-);
-
-TRACE_EVENT_FORMAT_NOFILTER(special, TRACE_SPECIAL, special_entry, ignore,
-	TRACE_STRUCT(
-		TRACE_FIELD(unsigned long, arg1, arg1)
-		TRACE_FIELD(unsigned long, arg2, arg2)
-		TRACE_FIELD(unsigned long, arg3, arg3)
-	),
-	TP_RAW_FMT("(%08lx) (%08lx) (%08lx)")
-);
-
-/*
- * Stack-trace entry:
- */
-
-/* #define FTRACE_STACK_ENTRIES   8 */
-
-TRACE_EVENT_FORMAT(kernel_stack, TRACE_STACK, stack_entry, ignore,
-	TRACE_STRUCT(
-		TRACE_FIELD(unsigned long, caller[0], stack0)
-		TRACE_FIELD(unsigned long, caller[1], stack1)
-		TRACE_FIELD(unsigned long, caller[2], stack2)
-		TRACE_FIELD(unsigned long, caller[3], stack3)
-		TRACE_FIELD(unsigned long, caller[4], stack4)
-		TRACE_FIELD(unsigned long, caller[5], stack5)
-		TRACE_FIELD(unsigned long, caller[6], stack6)
-		TRACE_FIELD(unsigned long, caller[7], stack7)
-	),
-	TP_RAW_FMT("\t=> (%08lx)\n\t=> (%08lx)\n\t=> (%08lx)\n\t=> (%08lx)\n"
-		 "\t=> (%08lx)\n\t=> (%08lx)\n\t=> (%08lx)\n\t=> (%08lx)\n")
-);
-
-TRACE_EVENT_FORMAT(user_stack, TRACE_USER_STACK, userstack_entry, ignore,
-	TRACE_STRUCT(
-		TRACE_FIELD(unsigned long, caller[0], stack0)
-		TRACE_FIELD(unsigned long, caller[1], stack1)
-		TRACE_FIELD(unsigned long, caller[2], stack2)
-		TRACE_FIELD(unsigned long, caller[3], stack3)
-		TRACE_FIELD(unsigned long, caller[4], stack4)
-		TRACE_FIELD(unsigned long, caller[5], stack5)
-		TRACE_FIELD(unsigned long, caller[6], stack6)
-		TRACE_FIELD(unsigned long, caller[7], stack7)
-	),
-	TP_RAW_FMT("\t=> (%08lx)\n\t=> (%08lx)\n\t=> (%08lx)\n\t=> (%08lx)\n"
-		 "\t=> (%08lx)\n\t=> (%08lx)\n\t=> (%08lx)\n\t=> (%08lx)\n")
-);
-
-TRACE_EVENT_FORMAT(bprint, TRACE_BPRINT, bprint_entry, ignore,
-	TRACE_STRUCT(
-		TRACE_FIELD(unsigned long, ip, ip)
-		TRACE_FIELD(char *, fmt, fmt)
-		TRACE_FIELD_ZERO_CHAR(buf)
-	),
-	TP_RAW_FMT("%08lx (%d) fmt:%p %s")
-);
-
-TRACE_EVENT_FORMAT(print, TRACE_PRINT, print_entry, ignore,
-	TRACE_STRUCT(
-		TRACE_FIELD(unsigned long, ip, ip)
-		TRACE_FIELD_ZERO_CHAR(buf)
-	),
-	TP_RAW_FMT("%08lx (%d) fmt:%p %s")
-);
-
-TRACE_EVENT_FORMAT(branch, TRACE_BRANCH, trace_branch, ignore,
-	TRACE_STRUCT(
-		TRACE_FIELD(unsigned int, line, line)
-		TRACE_FIELD_SPECIAL(char func[TRACE_FUNC_SIZE+1], func,
-				    TRACE_FUNC_SIZE+1, func)
-		TRACE_FIELD_SPECIAL(char file[TRACE_FUNC_SIZE+1], file,
-				    TRACE_FUNC_SIZE+1, file)
-		TRACE_FIELD(char, correct, correct)
-	),
-	TP_RAW_FMT("%u:%s:%s (%u)")
-);
-
-TRACE_EVENT_FORMAT(hw_branch, TRACE_HW_BRANCHES, hw_branch_entry, ignore,
-	TRACE_STRUCT(
-		TRACE_FIELD(u64, from, from)
-		TRACE_FIELD(u64, to, to)
-	),
-	TP_RAW_FMT("from: %llx to: %llx")
-);
-
-TRACE_EVENT_FORMAT(power, TRACE_POWER, trace_power, ignore,
-	TRACE_STRUCT(
-		TRACE_FIELD_SIGN(ktime_t, state_data.stamp, stamp, 1)
-		TRACE_FIELD_SIGN(ktime_t, state_data.end, end, 1)
-		TRACE_FIELD(int, state_data.type, type)
-		TRACE_FIELD(int, state_data.state, state)
-	),
-	TP_RAW_FMT("%llx->%llx type:%u state:%u")
-);
-
-TRACE_EVENT_FORMAT(kmem_alloc, TRACE_KMEM_ALLOC, kmemtrace_alloc_entry, ignore,
-	TRACE_STRUCT(
-		TRACE_FIELD(enum kmemtrace_type_id, type_id, type_id)
-		TRACE_FIELD(unsigned long, call_site, call_site)
-		TRACE_FIELD(const void *, ptr, ptr)
-		TRACE_FIELD(size_t, bytes_req, bytes_req)
-		TRACE_FIELD(size_t, bytes_alloc, bytes_alloc)
-		TRACE_FIELD(gfp_t, gfp_flags, gfp_flags)
-		TRACE_FIELD(int, node, node)
-	),
-	TP_RAW_FMT("type:%u call_site:%lx ptr:%p req:%lu alloc:%lu"
-		 " flags:%x node:%d")
-);
-
-TRACE_EVENT_FORMAT(kmem_free, TRACE_KMEM_FREE, kmemtrace_free_entry, ignore,
-	TRACE_STRUCT(
-		TRACE_FIELD(enum kmemtrace_type_id, type_id, type_id)
-		TRACE_FIELD(unsigned long, call_site, call_site)
-		TRACE_FIELD(const void *, ptr, ptr)
-	),
-	TP_RAW_FMT("type:%u call_site:%lx ptr:%p")
-);
-
-#undef TRACE_SYSTEM
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index e75276a49cf5..d128f65778e6 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -17,16 +17,20 @@
 #include <linux/ctype.h>
 #include <linux/delay.h>
 
+#include <asm/setup.h>
+
 #include "trace_output.h"
 
+#undef TRACE_SYSTEM
 #define TRACE_SYSTEM "TRACE_SYSTEM"
 
 DEFINE_MUTEX(event_mutex);
 
 LIST_HEAD(ftrace_events);
 
-int trace_define_field(struct ftrace_event_call *call, char *type,
-		       char *name, int offset, int size, int is_signed)
+int trace_define_field(struct ftrace_event_call *call, const char *type,
+		       const char *name, int offset, int size, int is_signed,
+		       int filter_type)
 {
 	struct ftrace_event_field *field;
 
@@ -42,9 +46,15 @@ int trace_define_field(struct ftrace_event_call *call, char *type,
 	if (!field->type)
 		goto err;
 
+	if (filter_type == FILTER_OTHER)
+		field->filter_type = filter_assign_type(type);
+	else
+		field->filter_type = filter_type;
+
 	field->offset = offset;
 	field->size = size;
 	field->is_signed = is_signed;
+
 	list_add(&field->link, &call->fields);
 
 	return 0;
@@ -60,6 +70,29 @@ err:
 }
 EXPORT_SYMBOL_GPL(trace_define_field);
 
+#define __common_field(type, item)					\
+	ret = trace_define_field(call, #type, "common_" #item,		\
+				 offsetof(typeof(ent), item),		\
+				 sizeof(ent.item),			\
+				 is_signed_type(type), FILTER_OTHER);	\
+	if (ret)							\
+		return ret;
+
+int trace_define_common_fields(struct ftrace_event_call *call)
+{
+	int ret;
+	struct trace_entry ent;
+
+	__common_field(unsigned short, type);
+	__common_field(unsigned char, flags);
+	__common_field(unsigned char, preempt_count);
+	__common_field(int, pid);
+	__common_field(int, lock_depth);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(trace_define_common_fields);
+
 #ifdef CONFIG_MODULES
 
 static void trace_destroy_fields(struct ftrace_event_call *call)
@@ -84,14 +117,14 @@ static void ftrace_event_enable_disable(struct ftrace_event_call *call,
 		if (call->enabled) {
 			call->enabled = 0;
 			tracing_stop_cmdline_record();
-			call->unregfunc();
+			call->unregfunc(call->data);
 		}
 		break;
 	case 1:
 		if (!call->enabled) {
 			call->enabled = 1;
 			tracing_start_cmdline_record();
-			call->regfunc();
+			call->regfunc(call->data);
 		}
 		break;
 	}
@@ -198,73 +231,38 @@ static ssize_t
 ftrace_event_write(struct file *file, const char __user *ubuf,
 		   size_t cnt, loff_t *ppos)
 {
-	size_t read = 0;
-	int i, set = 1;
-	ssize_t ret;
-	char *buf;
-	char ch;
+	struct trace_parser parser;
+	ssize_t read, ret;
 
-	if (!cnt || cnt < 0)
+	if (!cnt)
 		return 0;
 
 	ret = tracing_update_buffers();
 	if (ret < 0)
 		return ret;
 
-	ret = get_user(ch, ubuf++);
-	if (ret)
-		return ret;
-	read++;
-	cnt--;
-
-	/* skip white space */
-	while (cnt && isspace(ch)) {
-		ret = get_user(ch, ubuf++);
-		if (ret)
-			return ret;
-		read++;
-		cnt--;
-	}
-
-	/* Only white space found? */
-	if (isspace(ch)) {
-		file->f_pos += read;
-		ret = read;
-		return ret;
-	}
-
-	buf = kmalloc(EVENT_BUF_SIZE+1, GFP_KERNEL);
-	if (!buf)
+	if (trace_parser_get_init(&parser, EVENT_BUF_SIZE + 1))
 		return -ENOMEM;
 
-	if (cnt > EVENT_BUF_SIZE)
-		cnt = EVENT_BUF_SIZE;
+	read = trace_get_user(&parser, ubuf, cnt, ppos);
 
-	i = 0;
-	while (cnt && !isspace(ch)) {
-		if (!i && ch == '!')
+	if (read >= 0 && trace_parser_loaded((&parser))) {
+		int set = 1;
+
+		if (*parser.buffer == '!')
 			set = 0;
-		else
-			buf[i++] = ch;
 
-		ret = get_user(ch, ubuf++);
+		parser.buffer[parser.idx] = 0;
+
+		ret = ftrace_set_clr_event(parser.buffer + !set, set);
 		if (ret)
-			goto out_free;
-		read++;
-		cnt--;
+			goto out_put;
 	}
-	buf[i] = 0;
-
-	file->f_pos += read;
-
-	ret = ftrace_set_clr_event(buf, set);
-	if (ret)
-		goto out_free;
 
 	ret = read;
 
- out_free:
-	kfree(buf);
+ out_put:
+	trace_parser_put(&parser);
 
 	return ret;
 }
@@ -272,42 +270,32 @@ ftrace_event_write(struct file *file, const char __user *ubuf,
 static void *
 t_next(struct seq_file *m, void *v, loff_t *pos)
 {
-	struct list_head *list = m->private;
-	struct ftrace_event_call *call;
+	struct ftrace_event_call *call = v;
 
 	(*pos)++;
 
-	for (;;) {
-		if (list == &ftrace_events)
-			return NULL;
-
-		call = list_entry(list, struct ftrace_event_call, list);
-
+	list_for_each_entry_continue(call, &ftrace_events, list) {
 		/*
 		 * The ftrace subsystem is for showing formats only.
 		 * They can not be enabled or disabled via the event files.
 		 */
 		if (call->regfunc)
-			break;
-
-		list = list->next;
+			return call;
 	}
 
-	m->private = list->next;
-
-	return call;
+	return NULL;
 }
 
 static void *t_start(struct seq_file *m, loff_t *pos)
 {
-	struct ftrace_event_call *call = NULL;
+	struct ftrace_event_call *call;
 	loff_t l;
 
 	mutex_lock(&event_mutex);
 
-	m->private = ftrace_events.next;
+	call = list_entry(&ftrace_events, struct ftrace_event_call, list);
 	for (l = 0; l <= *pos; ) {
-		call = t_next(m, NULL, &l);
+		call = t_next(m, call, &l);
 		if (!call)
 			break;
 	}
@@ -317,37 +305,28 @@ static void *t_start(struct seq_file *m, loff_t *pos)
 static void *
 s_next(struct seq_file *m, void *v, loff_t *pos)
 {
-	struct list_head *list = m->private;
-	struct ftrace_event_call *call;
+	struct ftrace_event_call *call = v;
 
 	(*pos)++;
 
- retry:
-	if (list == &ftrace_events)
-		return NULL;
-
-	call = list_entry(list, struct ftrace_event_call, list);
-
-	if (!call->enabled) {
-		list = list->next;
-		goto retry;
+	list_for_each_entry_continue(call, &ftrace_events, list) {
+		if (call->enabled)
+			return call;
 	}
 
-	m->private = list->next;
-
-	return call;
+	return NULL;
 }
 
 static void *s_start(struct seq_file *m, loff_t *pos)
 {
-	struct ftrace_event_call *call = NULL;
+	struct ftrace_event_call *call;
 	loff_t l;
 
 	mutex_lock(&event_mutex);
 
-	m->private = ftrace_events.next;
+	call = list_entry(&ftrace_events, struct ftrace_event_call, list);
 	for (l = 0; l <= *pos; ) {
-		call = s_next(m, NULL, &l);
+		call = s_next(m, call, &l);
 		if (!call)
 			break;
 	}
@@ -546,7 +525,7 @@ static int trace_write_header(struct trace_seq *s)
 				FIELD(unsigned char, flags),
 				FIELD(unsigned char, preempt_count),
 				FIELD(int, pid),
-				FIELD(int, tgid));
+				FIELD(int, lock_depth));
 }
 
 static ssize_t
@@ -574,7 +553,7 @@ event_format_read(struct file *filp, char __user *ubuf, size_t cnt,
 	trace_seq_printf(s, "format:\n");
 	trace_write_header(s);
 
-	r = call->show_format(s);
+	r = call->show_format(call, s);
 	if (!r) {
 		/*
 		 * ug!  The format output is bigger than a PAGE!!
@@ -849,8 +828,10 @@ event_subsystem_dir(const char *name, struct dentry *d_events)
 
 	/* First see if we did not already create this dir */
 	list_for_each_entry(system, &event_subsystems, list) {
-		if (strcmp(system->name, name) == 0)
+		if (strcmp(system->name, name) == 0) {
+			system->nr_events++;
 			return system->entry;
+		}
 	}
 
 	/* need to create new entry */
@@ -869,6 +850,7 @@ event_subsystem_dir(const char *name, struct dentry *d_events)
 		return d_events;
 	}
 
+	system->nr_events = 1;
 	system->name = kstrdup(name, GFP_KERNEL);
 	if (!system->name) {
 		debugfs_remove(system->entry);
@@ -920,15 +902,6 @@ event_create_dir(struct ftrace_event_call *call, struct dentry *d_events,
 	if (strcmp(call->system, TRACE_SYSTEM) != 0)
 		d_events = event_subsystem_dir(call->system, d_events);
 
-	if (call->raw_init) {
-		ret = call->raw_init();
-		if (ret < 0) {
-			pr_warning("Could not initialize trace point"
-				   " events/%s\n", call->name);
-			return ret;
-		}
-	}
-
 	call->dir = debugfs_create_dir(call->name, d_events);
 	if (!call->dir) {
 		pr_warning("Could not create debugfs "
@@ -945,7 +918,7 @@ event_create_dir(struct ftrace_event_call *call, struct dentry *d_events,
 					  id);
 
 	if (call->define_fields) {
-		ret = call->define_fields();
+		ret = call->define_fields(call);
 		if (ret < 0) {
 			pr_warning("Could not initialize trace point"
 				   " events/%s\n", call->name);
@@ -987,6 +960,32 @@ struct ftrace_module_file_ops {
 	struct file_operations		filter;
 };
 
+static void remove_subsystem_dir(const char *name)
+{
+	struct event_subsystem *system;
+
+	if (strcmp(name, TRACE_SYSTEM) == 0)
+		return;
+
+	list_for_each_entry(system, &event_subsystems, list) {
+		if (strcmp(system->name, name) == 0) {
+			if (!--system->nr_events) {
+				struct event_filter *filter = system->filter;
+
+				debugfs_remove_recursive(system->entry);
+				list_del(&system->list);
+				if (filter) {
+					kfree(filter->filter_string);
+					kfree(filter);
+				}
+				kfree(system->name);
+				kfree(system);
+			}
+			break;
+		}
+	}
+}
+
 static struct ftrace_module_file_ops *
 trace_create_file_ops(struct module *mod)
 {
@@ -1027,6 +1026,7 @@ static void trace_module_add_events(struct module *mod)
 	struct ftrace_module_file_ops *file_ops = NULL;
 	struct ftrace_event_call *call, *start, *end;
 	struct dentry *d_events;
+	int ret;
 
 	start = mod->trace_events;
 	end = mod->trace_events + mod->num_trace_events;
@@ -1042,7 +1042,15 @@ static void trace_module_add_events(struct module *mod)
 		/* The linker may leave blanks */
 		if (!call->name)
 			continue;
-
+		if (call->raw_init) {
+			ret = call->raw_init();
+			if (ret < 0) {
+				if (ret != -ENOSYS)
+					pr_warning("Could not initialize trace "
+					"point events/%s\n", call->name);
+				continue;
+			}
+		}
 		/*
 		 * This module has events, create file ops for this module
 		 * if not already done.
@@ -1077,6 +1085,7 @@ static void trace_module_remove_events(struct module *mod)
 			list_del(&call->list);
 			trace_destroy_fields(call);
 			destroy_preds(call);
+			remove_subsystem_dir(call->system);
 		}
 	}
 
@@ -1125,7 +1134,7 @@ static int trace_module_notify(struct notifier_block *self,
 }
 #endif /* CONFIG_MODULES */
 
-struct notifier_block trace_module_nb = {
+static struct notifier_block trace_module_nb = {
 	.notifier_call = trace_module_notify,
 	.priority = 0,
 };
@@ -1133,6 +1142,18 @@ struct notifier_block trace_module_nb = {
 extern struct ftrace_event_call __start_ftrace_events[];
 extern struct ftrace_event_call __stop_ftrace_events[];
 
+static char bootup_event_buf[COMMAND_LINE_SIZE] __initdata;
+
+static __init int setup_trace_event(char *str)
+{
+	strlcpy(bootup_event_buf, str, COMMAND_LINE_SIZE);
+	ring_buffer_expanded = 1;
+	tracing_selftest_disabled = 1;
+
+	return 1;
+}
+__setup("trace_event=", setup_trace_event);
+
 static __init int event_trace_init(void)
 {
 	struct ftrace_event_call *call;
@@ -1140,6 +1161,8 @@ static __init int event_trace_init(void)
 	struct dentry *entry;
 	struct dentry *d_events;
 	int ret;
+	char *buf = bootup_event_buf;
+	char *token;
 
 	d_tracer = tracing_init_dentry();
 	if (!d_tracer)
@@ -1179,12 +1202,34 @@ static __init int event_trace_init(void)
 		/* The linker may leave blanks */
 		if (!call->name)
 			continue;
+		if (call->raw_init) {
+			ret = call->raw_init();
+			if (ret < 0) {
+				if (ret != -ENOSYS)
+					pr_warning("Could not initialize trace "
+					"point events/%s\n", call->name);
+				continue;
+			}
+		}
 		list_add(&call->list, &ftrace_events);
 		event_create_dir(call, d_events, &ftrace_event_id_fops,
 				 &ftrace_enable_fops, &ftrace_event_filter_fops,
 				 &ftrace_event_format_fops);
 	}
 
+	while (true) {
+		token = strsep(&buf, ",");
+
+		if (!token)
+			break;
+		if (!*token)
+			continue;
+
+		ret = ftrace_set_clr_event(token, 1);
+		if (ret)
+			pr_warning("Failed to enable trace event: %s\n", token);
+	}
+
 	ret = register_module_notifier(&trace_module_nb);
 	if (ret)
 		pr_warning("Failed to register trace events module notifier\n");
@@ -1261,6 +1306,18 @@ static __init void event_trace_self_tests(void)
 		if (!call->regfunc)
 			continue;
 
+/*
+ * Testing syscall events here is pretty useless, but
+ * we still do it if configured. But this is time consuming.
+ * What we really need is a user thread to perform the
+ * syscalls as we test.
+ */
+#ifndef CONFIG_EVENT_TRACE_TEST_SYSCALLS
+		if (call->system &&
+		    strcmp(call->system, "syscalls") == 0)
+			continue;
+#endif
+
 		pr_info("Testing event %s: ", call->name);
 
 		/*
@@ -1334,12 +1391,13 @@ static __init void event_trace_self_tests(void)
 
 #ifdef CONFIG_FUNCTION_TRACER
 
-static DEFINE_PER_CPU(atomic_t, test_event_disable);
+static DEFINE_PER_CPU(atomic_t, ftrace_test_event_disable);
 
 static void
 function_test_events_call(unsigned long ip, unsigned long parent_ip)
 {
 	struct ring_buffer_event *event;
+	struct ring_buffer *buffer;
 	struct ftrace_entry *entry;
 	unsigned long flags;
 	long disabled;
@@ -1350,14 +1408,15 @@ function_test_events_call(unsigned long ip, unsigned long parent_ip)
 	pc = preempt_count();
 	resched = ftrace_preempt_disable();
 	cpu = raw_smp_processor_id();
-	disabled = atomic_inc_return(&per_cpu(test_event_disable, cpu));
+	disabled = atomic_inc_return(&per_cpu(ftrace_test_event_disable, cpu));
 
 	if (disabled != 1)
 		goto out;
 
 	local_save_flags(flags);
 
-	event = trace_current_buffer_lock_reserve(TRACE_FN, sizeof(*entry),
+	event = trace_current_buffer_lock_reserve(&buffer,
+						  TRACE_FN, sizeof(*entry),
 						  flags, pc);
 	if (!event)
 		goto out;
@@ -1365,10 +1424,10 @@ function_test_events_call(unsigned long ip, unsigned long parent_ip)
 	entry->ip			= ip;
 	entry->parent_ip		= parent_ip;
 
-	trace_nowake_buffer_unlock_commit(event, flags, pc);
+	trace_nowake_buffer_unlock_commit(buffer, event, flags, pc);
 
  out:
-	atomic_dec(&per_cpu(test_event_disable, cpu));
+	atomic_dec(&per_cpu(ftrace_test_event_disable, cpu));
 	ftrace_preempt_enable(resched);
 }
 
@@ -1392,10 +1451,10 @@ static __init void event_trace_self_test_with_function(void)
 
 static __init int event_trace_self_tests_init(void)
 {
-
-	event_trace_self_tests();
-
-	event_trace_self_test_with_function();
+	if (!tracing_selftest_disabled) {
+		event_trace_self_tests();
+		event_trace_self_test_with_function();
+	}
 
 	return 0;
 }
diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c
index f32dc9d1ea7b..98a6cc5c64ed 100644
--- a/kernel/trace/trace_events_filter.c
+++ b/kernel/trace/trace_events_filter.c
@@ -121,6 +121,47 @@ struct filter_parse_state {
 	} operand;
 };
 
+#define DEFINE_COMPARISON_PRED(type)					\
+static int filter_pred_##type(struct filter_pred *pred, void *event,	\
+			      int val1, int val2)			\
+{									\
+	type *addr = (type *)(event + pred->offset);			\
+	type val = (type)pred->val;					\
+	int match = 0;							\
+									\
+	switch (pred->op) {						\
+	case OP_LT:							\
+		match = (*addr < val);					\
+		break;							\
+	case OP_LE:							\
+		match = (*addr <= val);					\
+		break;							\
+	case OP_GT:							\
+		match = (*addr > val);					\
+		break;							\
+	case OP_GE:							\
+		match = (*addr >= val);					\
+		break;							\
+	default:							\
+		break;							\
+	}								\
+									\
+	return match;							\
+}
+
+#define DEFINE_EQUALITY_PRED(size)					\
+static int filter_pred_##size(struct filter_pred *pred, void *event,	\
+			      int val1, int val2)			\
+{									\
+	u##size *addr = (u##size *)(event + pred->offset);		\
+	u##size val = (u##size)pred->val;				\
+	int match;							\
+									\
+	match = (val == *addr) ^ pred->not;				\
+									\
+	return match;							\
+}
+
 DEFINE_COMPARISON_PRED(s64);
 DEFINE_COMPARISON_PRED(u64);
 DEFINE_COMPARISON_PRED(s32);
@@ -163,6 +204,20 @@ static int filter_pred_string(struct filter_pred *pred, void *event,
 	return match;
 }
 
+/* Filter predicate for char * pointers */
+static int filter_pred_pchar(struct filter_pred *pred, void *event,
+			     int val1, int val2)
+{
+	char **addr = (char **)(event + pred->offset);
+	int cmp, match;
+
+	cmp = strncmp(*addr, pred->str_val, pred->str_len);
+
+	match = (!cmp) ^ pred->not;
+
+	return match;
+}
+
 /*
  * Filter predicate for dynamic sized arrays of characters.
  * These are implemented through a list of strings at the end
@@ -176,11 +231,13 @@ static int filter_pred_string(struct filter_pred *pred, void *event,
 static int filter_pred_strloc(struct filter_pred *pred, void *event,
 			      int val1, int val2)
 {
-	unsigned short str_loc = *(unsigned short *)(event + pred->offset);
+	u32 str_item = *(u32 *)(event + pred->offset);
+	int str_loc = str_item & 0xffff;
+	int str_len = str_item >> 16;
 	char *addr = (char *)(event + str_loc);
 	int cmp, match;
 
-	cmp = strncmp(addr, pred->str_val, pred->str_len);
+	cmp = strncmp(addr, pred->str_val, str_len);
 
 	match = (!cmp) ^ pred->not;
 
@@ -293,7 +350,7 @@ void print_event_filter(struct ftrace_event_call *call, struct trace_seq *s)
 	struct event_filter *filter = call->filter;
 
 	mutex_lock(&event_mutex);
-	if (filter->filter_string)
+	if (filter && filter->filter_string)
 		trace_seq_printf(s, "%s\n", filter->filter_string);
 	else
 		trace_seq_printf(s, "none\n");
@@ -306,7 +363,7 @@ void print_subsystem_event_filter(struct event_subsystem *system,
 	struct event_filter *filter = system->filter;
 
 	mutex_lock(&event_mutex);
-	if (filter->filter_string)
+	if (filter && filter->filter_string)
 		trace_seq_printf(s, "%s\n", filter->filter_string);
 	else
 		trace_seq_printf(s, "none\n");
@@ -374,6 +431,9 @@ void destroy_preds(struct ftrace_event_call *call)
 	struct event_filter *filter = call->filter;
 	int i;
 
+	if (!filter)
+		return;
+
 	for (i = 0; i < MAX_FILTER_PRED; i++) {
 		if (filter->preds[i])
 			filter_free_pred(filter->preds[i]);
@@ -384,17 +444,19 @@ void destroy_preds(struct ftrace_event_call *call)
 	call->filter = NULL;
 }
 
-int init_preds(struct ftrace_event_call *call)
+static int init_preds(struct ftrace_event_call *call)
 {
 	struct event_filter *filter;
 	struct filter_pred *pred;
 	int i;
 
+	if (call->filter)
+		return 0;
+
 	filter = call->filter = kzalloc(sizeof(*filter), GFP_KERNEL);
 	if (!call->filter)
 		return -ENOMEM;
 
-	call->filter_active = 0;
 	filter->n_preds = 0;
 
 	filter->preds = kzalloc(MAX_FILTER_PRED * sizeof(pred), GFP_KERNEL);
@@ -416,30 +478,55 @@ oom:
 
 	return -ENOMEM;
 }
-EXPORT_SYMBOL_GPL(init_preds);
 
-static void filter_free_subsystem_preds(struct event_subsystem *system)
+static int init_subsystem_preds(struct event_subsystem *system)
 {
-	struct event_filter *filter = system->filter;
 	struct ftrace_event_call *call;
-	int i;
+	int err;
 
-	if (filter->n_preds) {
-		for (i = 0; i < filter->n_preds; i++)
-			filter_free_pred(filter->preds[i]);
-		kfree(filter->preds);
-		filter->preds = NULL;
-		filter->n_preds = 0;
+	list_for_each_entry(call, &ftrace_events, list) {
+		if (!call->define_fields)
+			continue;
+
+		if (strcmp(call->system, system->name) != 0)
+			continue;
+
+		err = init_preds(call);
+		if (err)
+			return err;
 	}
 
+	return 0;
+}
+
+enum {
+	FILTER_DISABLE_ALL,
+	FILTER_INIT_NO_RESET,
+	FILTER_SKIP_NO_RESET,
+};
+
+static void filter_free_subsystem_preds(struct event_subsystem *system,
+					int flag)
+{
+	struct ftrace_event_call *call;
+
 	list_for_each_entry(call, &ftrace_events, list) {
 		if (!call->define_fields)
 			continue;
 
-		if (!strcmp(call->system, system->name)) {
-			filter_disable_preds(call);
-			remove_filter_string(call->filter);
+		if (strcmp(call->system, system->name) != 0)
+			continue;
+
+		if (flag == FILTER_INIT_NO_RESET) {
+			call->filter->no_reset = false;
+			continue;
 		}
+
+		if (flag == FILTER_SKIP_NO_RESET && call->filter->no_reset)
+			continue;
+
+		filter_disable_preds(call);
+		remove_filter_string(call->filter);
 	}
 }
 
@@ -468,12 +555,7 @@ static int filter_add_pred_fn(struct filter_parse_state *ps,
 	return 0;
 }
 
-enum {
-	FILTER_STATIC_STRING = 1,
-	FILTER_DYN_STRING
-};
-
-static int is_string_field(const char *type)
+int filter_assign_type(const char *type)
 {
 	if (strstr(type, "__data_loc") && strstr(type, "char"))
 		return FILTER_DYN_STRING;
@@ -481,12 +563,19 @@ static int is_string_field(const char *type)
 	if (strchr(type, '[') && strstr(type, "char"))
 		return FILTER_STATIC_STRING;
 
-	return 0;
+	return FILTER_OTHER;
+}
+
+static bool is_string_field(struct ftrace_event_field *field)
+{
+	return field->filter_type == FILTER_DYN_STRING ||
+	       field->filter_type == FILTER_STATIC_STRING ||
+	       field->filter_type == FILTER_PTR_STRING;
 }
 
 static int is_legal_op(struct ftrace_event_field *field, int op)
 {
-	if (is_string_field(field->type) && (op != OP_EQ && op != OP_NE))
+	if (is_string_field(field) && (op != OP_EQ && op != OP_NE))
 		return 0;
 
 	return 1;
@@ -537,22 +626,24 @@ static filter_pred_fn_t select_comparison_fn(int op, int field_size,
 
 static int filter_add_pred(struct filter_parse_state *ps,
 			   struct ftrace_event_call *call,
-			   struct filter_pred *pred)
+			   struct filter_pred *pred,
+			   bool dry_run)
 {
 	struct ftrace_event_field *field;
 	filter_pred_fn_t fn;
 	unsigned long long val;
-	int string_type;
 	int ret;
 
 	pred->fn = filter_pred_none;
 
 	if (pred->op == OP_AND) {
 		pred->pop_n = 2;
-		return filter_add_pred_fn(ps, call, pred, filter_pred_and);
+		fn = filter_pred_and;
+		goto add_pred_fn;
 	} else if (pred->op == OP_OR) {
 		pred->pop_n = 2;
-		return filter_add_pred_fn(ps, call, pred, filter_pred_or);
+		fn = filter_pred_or;
+		goto add_pred_fn;
 	}
 
 	field = find_event_field(call, pred->field_name);
@@ -568,16 +659,17 @@ static int filter_add_pred(struct filter_parse_state *ps,
 		return -EINVAL;
 	}
 
-	string_type = is_string_field(field->type);
-	if (string_type) {
-		if (string_type == FILTER_STATIC_STRING)
+	if (is_string_field(field)) {
+		pred->str_len = field->size;
+
+		if (field->filter_type == FILTER_STATIC_STRING)
 			fn = filter_pred_string;
-		else
+		else if (field->filter_type == FILTER_DYN_STRING)
 			fn = filter_pred_strloc;
-		pred->str_len = field->size;
-		if (pred->op == OP_NE)
-			pred->not = 1;
-		return filter_add_pred_fn(ps, call, pred, fn);
+		else {
+			fn = filter_pred_pchar;
+			pred->str_len = strlen(pred->str_val);
+		}
 	} else {
 		if (field->is_signed)
 			ret = strict_strtoll(pred->str_val, 0, &val);
@@ -588,41 +680,33 @@ static int filter_add_pred(struct filter_parse_state *ps,
 			return -EINVAL;
 		}
 		pred->val = val;
-	}
 
-	fn = select_comparison_fn(pred->op, field->size, field->is_signed);
-	if (!fn) {
-		parse_error(ps, FILT_ERR_INVALID_OP, 0);
-		return -EINVAL;
+		fn = select_comparison_fn(pred->op, field->size,
+					  field->is_signed);
+		if (!fn) {
+			parse_error(ps, FILT_ERR_INVALID_OP, 0);
+			return -EINVAL;
+		}
 	}
 
 	if (pred->op == OP_NE)
 		pred->not = 1;
 
-	return filter_add_pred_fn(ps, call, pred, fn);
+add_pred_fn:
+	if (!dry_run)
+		return filter_add_pred_fn(ps, call, pred, fn);
+	return 0;
 }
 
 static int filter_add_subsystem_pred(struct filter_parse_state *ps,
 				     struct event_subsystem *system,
 				     struct filter_pred *pred,
-				     char *filter_string)
+				     char *filter_string,
+				     bool dry_run)
 {
-	struct event_filter *filter = system->filter;
 	struct ftrace_event_call *call;
 	int err = 0;
-
-	if (!filter->preds) {
-		filter->preds = kzalloc(MAX_FILTER_PRED * sizeof(pred),
-					GFP_KERNEL);
-
-		if (!filter->preds)
-			return -ENOMEM;
-	}
-
-	if (filter->n_preds == MAX_FILTER_PRED) {
-		parse_error(ps, FILT_ERR_TOO_MANY_PREDS, 0);
-		return -ENOSPC;
-	}
+	bool fail = true;
 
 	list_for_each_entry(call, &ftrace_events, list) {
 
@@ -632,19 +716,24 @@ static int filter_add_subsystem_pred(struct filter_parse_state *ps,
 		if (strcmp(call->system, system->name))
 			continue;
 
-		err = filter_add_pred(ps, call, pred);
-		if (err) {
-			filter_free_subsystem_preds(system);
-			parse_error(ps, FILT_ERR_BAD_SUBSYS_FILTER, 0);
-			goto out;
-		}
-		replace_filter_string(call->filter, filter_string);
+		if (call->filter->no_reset)
+			continue;
+
+		err = filter_add_pred(ps, call, pred, dry_run);
+		if (err)
+			call->filter->no_reset = true;
+		else
+			fail = false;
+
+		if (!dry_run)
+			replace_filter_string(call->filter, filter_string);
 	}
 
-	filter->preds[filter->n_preds] = pred;
-	filter->n_preds++;
-out:
-	return err;
+	if (fail) {
+		parse_error(ps, FILT_ERR_BAD_SUBSYS_FILTER, 0);
+		return err;
+	}
+	return 0;
 }
 
 static void parse_init(struct filter_parse_state *ps,
@@ -844,8 +933,9 @@ static void postfix_clear(struct filter_parse_state *ps)
 
 	while (!list_empty(&ps->postfix)) {
 		elt = list_first_entry(&ps->postfix, struct postfix_elt, list);
-		kfree(elt->operand);
 		list_del(&elt->list);
+		kfree(elt->operand);
+		kfree(elt);
 	}
 }
 
@@ -1003,12 +1093,14 @@ static int check_preds(struct filter_parse_state *ps)
 static int replace_preds(struct event_subsystem *system,
 			 struct ftrace_event_call *call,
 			 struct filter_parse_state *ps,
-			 char *filter_string)
+			 char *filter_string,
+			 bool dry_run)
 {
 	char *operand1 = NULL, *operand2 = NULL;
 	struct filter_pred *pred;
 	struct postfix_elt *elt;
 	int err;
+	int n_preds = 0;
 
 	err = check_preds(ps);
 	if (err)
@@ -1027,24 +1119,14 @@ static int replace_preds(struct event_subsystem *system,
 			continue;
 		}
 
+		if (n_preds++ == MAX_FILTER_PRED) {
+			parse_error(ps, FILT_ERR_TOO_MANY_PREDS, 0);
+			return -ENOSPC;
+		}
+
 		if (elt->op == OP_AND || elt->op == OP_OR) {
 			pred = create_logical_pred(elt->op);
-			if (!pred)
-				return -ENOMEM;
-			if (call) {
-				err = filter_add_pred(ps, call, pred);
-				filter_free_pred(pred);
-			} else {
-				err = filter_add_subsystem_pred(ps, system,
-							pred, filter_string);
-				if (err)
-					filter_free_pred(pred);
-			}
-			if (err)
-				return err;
-
-			operand1 = operand2 = NULL;
-			continue;
+			goto add_pred;
 		}
 
 		if (!operand1 || !operand2) {
@@ -1053,17 +1135,15 @@ static int replace_preds(struct event_subsystem *system,
 		}
 
 		pred = create_pred(elt->op, operand1, operand2);
+add_pred:
 		if (!pred)
 			return -ENOMEM;
-		if (call) {
-			err = filter_add_pred(ps, call, pred);
-			filter_free_pred(pred);
-		} else {
+		if (call)
+			err = filter_add_pred(ps, call, pred, false);
+		else
 			err = filter_add_subsystem_pred(ps, system, pred,
-							filter_string);
-			if (err)
-				filter_free_pred(pred);
-		}
+						filter_string, dry_run);
+		filter_free_pred(pred);
 		if (err)
 			return err;
 
@@ -1081,6 +1161,10 @@ int apply_event_filter(struct ftrace_event_call *call, char *filter_string)
 
 	mutex_lock(&event_mutex);
 
+	err = init_preds(call);
+	if (err)
+		goto out_unlock;
+
 	if (!strcmp(strstrip(filter_string), "0")) {
 		filter_disable_preds(call);
 		remove_filter_string(call->filter);
@@ -1103,7 +1187,7 @@ int apply_event_filter(struct ftrace_event_call *call, char *filter_string)
 		goto out;
 	}
 
-	err = replace_preds(NULL, call, ps, filter_string);
+	err = replace_preds(NULL, call, ps, filter_string, false);
 	if (err)
 		append_filter_err(ps, call->filter);
 
@@ -1126,8 +1210,12 @@ int apply_subsystem_event_filter(struct event_subsystem *system,
 
 	mutex_lock(&event_mutex);
 
+	err = init_subsystem_preds(system);
+	if (err)
+		goto out_unlock;
+
 	if (!strcmp(strstrip(filter_string), "0")) {
-		filter_free_subsystem_preds(system);
+		filter_free_subsystem_preds(system, FILTER_DISABLE_ALL);
 		remove_filter_string(system->filter);
 		mutex_unlock(&event_mutex);
 		return 0;
@@ -1138,7 +1226,6 @@ int apply_subsystem_event_filter(struct event_subsystem *system,
 	if (!ps)
 		goto out_unlock;
 
-	filter_free_subsystem_preds(system);
 	replace_filter_string(system->filter, filter_string);
 
 	parse_init(ps, filter_ops, filter_string);
@@ -1148,9 +1235,23 @@ int apply_subsystem_event_filter(struct event_subsystem *system,
 		goto out;
 	}
 
-	err = replace_preds(system, NULL, ps, filter_string);
-	if (err)
+	filter_free_subsystem_preds(system, FILTER_INIT_NO_RESET);
+
+	/* try to see the filter can be applied to which events */
+	err = replace_preds(system, NULL, ps, filter_string, true);
+	if (err) {
 		append_filter_err(ps, system->filter);
+		goto out;
+	}
+
+	filter_free_subsystem_preds(system, FILTER_SKIP_NO_RESET);
+
+	/* really apply the filter to the events */
+	err = replace_preds(system, NULL, ps, filter_string, false);
+	if (err) {
+		append_filter_err(ps, system->filter);
+		filter_free_subsystem_preds(system, 2);
+	}
 
 out:
 	filter_opstack_clear(ps);
diff --git a/kernel/trace/trace_export.c b/kernel/trace/trace_export.c
index d06cf898dc86..9753fcc61bc5 100644
--- a/kernel/trace/trace_export.c
+++ b/kernel/trace/trace_export.c
@@ -15,116 +15,209 @@
 
 #include "trace_output.h"
 
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM	ftrace
 
-#undef TRACE_STRUCT
-#define TRACE_STRUCT(args...) args
+/* not needed for this file */
+#undef __field_struct
+#define __field_struct(type, item)
 
-extern void __bad_type_size(void);
+#undef __field
+#define __field(type, item)				type item;
 
-#undef TRACE_FIELD
-#define TRACE_FIELD(type, item, assign)					\
-	if (sizeof(type) != sizeof(field.item))				\
-		__bad_type_size();					\
+#undef __field_desc
+#define __field_desc(type, container, item)		type item;
+
+#undef __array
+#define __array(type, item, size)			type item[size];
+
+#undef __array_desc
+#define __array_desc(type, container, item, size)	type item[size];
+
+#undef __dynamic_array
+#define __dynamic_array(type, item)			type item[];
+
+#undef F_STRUCT
+#define F_STRUCT(args...)				args
+
+#undef F_printk
+#define F_printk(fmt, args...) fmt, args
+
+#undef FTRACE_ENTRY
+#define FTRACE_ENTRY(name, struct_name, id, tstruct, print)	\
+struct ____ftrace_##name {					\
+	tstruct							\
+};								\
+static void __used ____ftrace_check_##name(void)		\
+{								\
+	struct ____ftrace_##name *__entry = NULL;		\
+								\
+	/* force cmpile-time check on F_printk() */		\
+	printk(print);						\
+}
+
+#undef FTRACE_ENTRY_DUP
+#define FTRACE_ENTRY_DUP(name, struct_name, id, tstruct, print)	\
+	FTRACE_ENTRY(name, struct_name, id, PARAMS(tstruct), PARAMS(print))
+
+#include "trace_entries.h"
+
+
+#undef __field
+#define __field(type, item)						\
 	ret = trace_seq_printf(s, "\tfield:" #type " " #item ";\t"	\
-			       "offset:%u;\tsize:%u;\n",		\
-			       (unsigned int)offsetof(typeof(field), item), \
-			       (unsigned int)sizeof(field.item));	\
+			       "offset:%zu;\tsize:%zu;\n",		\
+			       offsetof(typeof(field), item),		\
+			       sizeof(field.item));			\
 	if (!ret)							\
 		return 0;
 
+#undef __field_desc
+#define __field_desc(type, container, item)				\
+	ret = trace_seq_printf(s, "\tfield:" #type " " #item ";\t"	\
+			       "offset:%zu;\tsize:%zu;\n",		\
+			       offsetof(typeof(field), container.item),	\
+			       sizeof(field.container.item));		\
+	if (!ret)							\
+		return 0;
+
+#undef __array
+#define __array(type, item, len)					\
+	ret = trace_seq_printf(s, "\tfield:" #type " " #item "[" #len "];\t" \
+			       "offset:%zu;\tsize:%zu;\n",		\
+			       offsetof(typeof(field), item),	\
+			       sizeof(field.item));		\
+	if (!ret)							\
+		return 0;
 
-#undef TRACE_FIELD_SPECIAL
-#define TRACE_FIELD_SPECIAL(type_item, item, len, cmd)			\
-	ret = trace_seq_printf(s, "\tfield special:" #type_item ";\t"	\
-			       "offset:%u;\tsize:%u;\n",		\
-			       (unsigned int)offsetof(typeof(field), item), \
-			       (unsigned int)sizeof(field.item));	\
+#undef __array_desc
+#define __array_desc(type, container, item, len)			\
+	ret = trace_seq_printf(s, "\tfield:" #type " " #item "[" #len "];\t" \
+			       "offset:%zu;\tsize:%zu;\n",		\
+			       offsetof(typeof(field), container.item),	\
+			       sizeof(field.container.item));		\
 	if (!ret)							\
 		return 0;
 
-#undef TRACE_FIELD_ZERO_CHAR
-#define TRACE_FIELD_ZERO_CHAR(item)					\
-	ret = trace_seq_printf(s, "\tfield:char " #item ";\t"		\
-			       "offset:%u;\tsize:0;\n",			\
-			       (unsigned int)offsetof(typeof(field), item)); \
+#undef __dynamic_array
+#define __dynamic_array(type, item)					\
+	ret = trace_seq_printf(s, "\tfield:" #type " " #item ";\t"	\
+			       "offset:%zu;\tsize:0;\n",		\
+			       offsetof(typeof(field), item));		\
 	if (!ret)							\
 		return 0;
 
-#undef TRACE_FIELD_SIGN
-#define TRACE_FIELD_SIGN(type, item, assign, is_signed)	\
-	TRACE_FIELD(type, item, assign)
+#undef F_printk
+#define F_printk(fmt, args...) "%s, %s\n", #fmt, __stringify(args)
 
-#undef TP_RAW_FMT
-#define TP_RAW_FMT(args...) args
+#undef __entry
+#define __entry REC
 
-#undef TRACE_EVENT_FORMAT
-#define TRACE_EVENT_FORMAT(call, proto, args, fmt, tstruct, tpfmt)	\
+#undef FTRACE_ENTRY
+#define FTRACE_ENTRY(name, struct_name, id, tstruct, print)		\
 static int								\
-ftrace_format_##call(struct trace_seq *s)				\
+ftrace_format_##name(struct ftrace_event_call *unused,			\
+		     struct trace_seq *s)				\
 {									\
-	struct args field;						\
-	int ret;							\
+	struct struct_name field __attribute__((unused));		\
+	int ret = 0;							\
 									\
 	tstruct;							\
 									\
-	trace_seq_printf(s, "\nprint fmt: \"%s\"\n", tpfmt);		\
+	trace_seq_printf(s, "\nprint fmt: " print);			\
 									\
 	return ret;							\
 }
 
-#undef TRACE_EVENT_FORMAT_NOFILTER
-#define TRACE_EVENT_FORMAT_NOFILTER(call, proto, args, fmt, tstruct,	\
-				    tpfmt)				\
-static int								\
-ftrace_format_##call(struct trace_seq *s)				\
+#include "trace_entries.h"
+
+
+#undef __field
+#define __field(type, item)						\
+	ret = trace_define_field(event_call, #type, #item,		\
+				 offsetof(typeof(field), item),		\
+				 sizeof(field.item),			\
+				 is_signed_type(type), FILTER_OTHER);	\
+	if (ret)							\
+		return ret;
+
+#undef __field_desc
+#define __field_desc(type, container, item)	\
+	ret = trace_define_field(event_call, #type, #item,		\
+				 offsetof(typeof(field),		\
+					  container.item),		\
+				 sizeof(field.container.item),		\
+				 is_signed_type(type), FILTER_OTHER);	\
+	if (ret)							\
+		return ret;
+
+#undef __array
+#define __array(type, item, len)					\
+	BUILD_BUG_ON(len > MAX_FILTER_STR_VAL);				\
+	ret = trace_define_field(event_call, #type "[" #len "]", #item,	\
+				 offsetof(typeof(field), item),		\
+				 sizeof(field.item), 0, FILTER_OTHER);	\
+	if (ret)							\
+		return ret;
+
+#undef __array_desc
+#define __array_desc(type, container, item, len)			\
+	BUILD_BUG_ON(len > MAX_FILTER_STR_VAL);				\
+	ret = trace_define_field(event_call, #type "[" #len "]", #item,	\
+				 offsetof(typeof(field),		\
+					  container.item),		\
+				 sizeof(field.container.item), 0,	\
+				 FILTER_OTHER);				\
+	if (ret)							\
+		return ret;
+
+#undef __dynamic_array
+#define __dynamic_array(type, item)
+
+#undef FTRACE_ENTRY
+#define FTRACE_ENTRY(name, struct_name, id, tstruct, print)		\
+int									\
+ftrace_define_fields_##name(struct ftrace_event_call *event_call)	\
 {									\
-	struct args field;						\
+	struct struct_name field;					\
 	int ret;							\
 									\
-	tstruct;							\
+	ret = trace_define_common_fields(event_call);			\
+	if (ret)							\
+		return ret;						\
 									\
-	trace_seq_printf(s, "\nprint fmt: \"%s\"\n", tpfmt);		\
+	tstruct;							\
 									\
 	return ret;							\
 }
 
-#include "trace_event_types.h"
-
-#undef TRACE_ZERO_CHAR
-#define TRACE_ZERO_CHAR(arg)
+#include "trace_entries.h"
 
-#undef TRACE_FIELD
-#define TRACE_FIELD(type, item, assign)\
-	entry->item = assign;
 
-#undef TRACE_FIELD
-#define TRACE_FIELD(type, item, assign)\
-	entry->item = assign;
+#undef __field
+#define __field(type, item)
 
-#undef TRACE_FIELD_SIGN
-#define TRACE_FIELD_SIGN(type, item, assign, is_signed)	\
-	TRACE_FIELD(type, item, assign)
+#undef __field_desc
+#define __field_desc(type, container, item)
 
-#undef TP_CMD
-#define TP_CMD(cmd...)	cmd
+#undef __array
+#define __array(type, item, len)
 
-#undef TRACE_ENTRY
-#define TRACE_ENTRY	entry
+#undef __array_desc
+#define __array_desc(type, container, item, len)
 
-#undef TRACE_FIELD_SPECIAL
-#define TRACE_FIELD_SPECIAL(type_item, item, len, cmd)	\
-	cmd;
+#undef __dynamic_array
+#define __dynamic_array(type, item)
 
-#undef TRACE_EVENT_FORMAT
-#define TRACE_EVENT_FORMAT(call, proto, args, fmt, tstruct, tpfmt)	\
-int ftrace_define_fields_##call(void);					\
+#undef FTRACE_ENTRY
+#define FTRACE_ENTRY(call, struct_name, type, tstruct, print)		\
 static int ftrace_raw_init_event_##call(void);				\
 									\
 struct ftrace_event_call __used						\
 __attribute__((__aligned__(4)))						\
 __attribute__((section("_ftrace_events"))) event_##call = {		\
 	.name			= #call,				\
-	.id			= proto,				\
+	.id			= type,					\
 	.system			= __stringify(TRACE_SYSTEM),		\
 	.raw_init		= ftrace_raw_init_event_##call,		\
 	.show_format		= ftrace_format_##call,			\
@@ -133,74 +226,7 @@ __attribute__((section("_ftrace_events"))) event_##call = {		\
 static int ftrace_raw_init_event_##call(void)				\
 {									\
 	INIT_LIST_HEAD(&event_##call.fields);				\
-	init_preds(&event_##call);					\
 	return 0;							\
 }									\
 
-#undef TRACE_EVENT_FORMAT_NOFILTER
-#define TRACE_EVENT_FORMAT_NOFILTER(call, proto, args, fmt, tstruct,	\
-				    tpfmt)				\
-									\
-struct ftrace_event_call __used						\
-__attribute__((__aligned__(4)))						\
-__attribute__((section("_ftrace_events"))) event_##call = {		\
-	.name			= #call,				\
-	.id			= proto,				\
-	.system			= __stringify(TRACE_SYSTEM),		\
-	.show_format		= ftrace_format_##call,			\
-};
-
-#include "trace_event_types.h"
-
-#undef TRACE_FIELD
-#define TRACE_FIELD(type, item, assign)					\
-	ret = trace_define_field(event_call, #type, #item,		\
-				 offsetof(typeof(field), item),		\
-				 sizeof(field.item), is_signed_type(type));	\
-	if (ret)							\
-		return ret;
-
-#undef TRACE_FIELD_SPECIAL
-#define TRACE_FIELD_SPECIAL(type, item, len, cmd)			\
-	ret = trace_define_field(event_call, #type "[" #len "]", #item,	\
-				 offsetof(typeof(field), item),		\
-				 sizeof(field.item), 0);		\
-	if (ret)							\
-		return ret;
-
-#undef TRACE_FIELD_SIGN
-#define TRACE_FIELD_SIGN(type, item, assign, is_signed)			\
-	ret = trace_define_field(event_call, #type, #item,		\
-				 offsetof(typeof(field), item),		\
-				 sizeof(field.item), is_signed);	\
-	if (ret)							\
-		return ret;
-
-#undef TRACE_FIELD_ZERO_CHAR
-#define TRACE_FIELD_ZERO_CHAR(item)
-
-#undef TRACE_EVENT_FORMAT
-#define TRACE_EVENT_FORMAT(call, proto, args, fmt, tstruct, tpfmt)	\
-int									\
-ftrace_define_fields_##call(void)					\
-{									\
-	struct ftrace_event_call *event_call = &event_##call;		\
-	struct args field;						\
-	int ret;							\
-									\
-	__common_field(unsigned char, type, 0);				\
-	__common_field(unsigned char, flags, 0);			\
-	__common_field(unsigned char, preempt_count, 0);		\
-	__common_field(int, pid, 1);					\
-	__common_field(int, tgid, 1);					\
-									\
-	tstruct;							\
-									\
-	return ret;							\
-}
-
-#undef TRACE_EVENT_FORMAT_NOFILTER
-#define TRACE_EVENT_FORMAT_NOFILTER(call, proto, args, fmt, tstruct,	\
-				    tpfmt)
-
-#include "trace_event_types.h"
+#include "trace_entries.h"
diff --git a/kernel/trace/trace_functions.c b/kernel/trace/trace_functions.c
index 75ef000613c3..b3f3776b0cd6 100644
--- a/kernel/trace/trace_functions.c
+++ b/kernel/trace/trace_functions.c
@@ -288,11 +288,9 @@ static int
 ftrace_trace_onoff_print(struct seq_file *m, unsigned long ip,
 			 struct ftrace_probe_ops *ops, void *data)
 {
-	char str[KSYM_SYMBOL_LEN];
 	long count = (long)data;
 
-	kallsyms_lookup(ip, NULL, NULL, NULL, str);
-	seq_printf(m, "%s:", str);
+	seq_printf(m, "%ps:", (void *)ip);
 
 	if (ops == &traceon_probe_ops)
 		seq_printf(m, "traceon");
diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c
index 420ec3487579..45e6c01b2e4d 100644
--- a/kernel/trace/trace_functions_graph.c
+++ b/kernel/trace/trace_functions_graph.c
@@ -52,7 +52,7 @@ static struct tracer_flags tracer_flags = {
 	.opts = trace_opts
 };
 
-/* pid on the last trace processed */
+static struct trace_array *graph_array;
 
 
 /* Add a function return address to the trace stack on thread info.*/
@@ -124,7 +124,7 @@ ftrace_pop_return_trace(struct ftrace_graph_ret *trace, unsigned long *ret,
 	if (unlikely(current->ret_stack[index].fp != frame_pointer)) {
 		ftrace_graph_stop();
 		WARN(1, "Bad frame pointer: expected %lx, received %lx\n"
-		     "  from func %pF return to %lx\n",
+		     "  from func %ps return to %lx\n",
 		     current->ret_stack[index].fp,
 		     frame_pointer,
 		     (void *)current->ret_stack[index].func,
@@ -166,10 +166,123 @@ unsigned long ftrace_return_to_handler(unsigned long frame_pointer)
 	return ret;
 }
 
+static int __trace_graph_entry(struct trace_array *tr,
+				struct ftrace_graph_ent *trace,
+				unsigned long flags,
+				int pc)
+{
+	struct ftrace_event_call *call = &event_funcgraph_entry;
+	struct ring_buffer_event *event;
+	struct ring_buffer *buffer = tr->buffer;
+	struct ftrace_graph_ent_entry *entry;
+
+	if (unlikely(local_read(&__get_cpu_var(ftrace_cpu_disabled))))
+		return 0;
+
+	event = trace_buffer_lock_reserve(buffer, TRACE_GRAPH_ENT,
+					  sizeof(*entry), flags, pc);
+	if (!event)
+		return 0;
+	entry	= ring_buffer_event_data(event);
+	entry->graph_ent			= *trace;
+	if (!filter_current_check_discard(buffer, call, entry, event))
+		ring_buffer_unlock_commit(buffer, event);
+
+	return 1;
+}
+
+int trace_graph_entry(struct ftrace_graph_ent *trace)
+{
+	struct trace_array *tr = graph_array;
+	struct trace_array_cpu *data;
+	unsigned long flags;
+	long disabled;
+	int ret;
+	int cpu;
+	int pc;
+
+	if (unlikely(!tr))
+		return 0;
+
+	if (!ftrace_trace_task(current))
+		return 0;
+
+	if (!ftrace_graph_addr(trace->func))
+		return 0;
+
+	local_irq_save(flags);
+	cpu = raw_smp_processor_id();
+	data = tr->data[cpu];
+	disabled = atomic_inc_return(&data->disabled);
+	if (likely(disabled == 1)) {
+		pc = preempt_count();
+		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 ret;
+}
+
+static void __trace_graph_return(struct trace_array *tr,
+				struct ftrace_graph_ret *trace,
+				unsigned long flags,
+				int pc)
+{
+	struct ftrace_event_call *call = &event_funcgraph_exit;
+	struct ring_buffer_event *event;
+	struct ring_buffer *buffer = tr->buffer;
+	struct ftrace_graph_ret_entry *entry;
+
+	if (unlikely(local_read(&__get_cpu_var(ftrace_cpu_disabled))))
+		return;
+
+	event = trace_buffer_lock_reserve(buffer, TRACE_GRAPH_RET,
+					  sizeof(*entry), flags, pc);
+	if (!event)
+		return;
+	entry	= ring_buffer_event_data(event);
+	entry->ret				= *trace;
+	if (!filter_current_check_discard(buffer, call, entry, event))
+		ring_buffer_unlock_commit(buffer, event);
+}
+
+void trace_graph_return(struct ftrace_graph_ret *trace)
+{
+	struct trace_array *tr = graph_array;
+	struct trace_array_cpu *data;
+	unsigned long flags;
+	long disabled;
+	int cpu;
+	int pc;
+
+	local_irq_save(flags);
+	cpu = raw_smp_processor_id();
+	data = tr->data[cpu];
+	disabled = atomic_inc_return(&data->disabled);
+	if (likely(disabled == 1)) {
+		pc = preempt_count();
+		__trace_graph_return(tr, trace, flags, pc);
+	}
+	if (!trace->depth)
+		clear_tsk_trace_graph(current);
+	atomic_dec(&data->disabled);
+	local_irq_restore(flags);
+}
+
 static int graph_trace_init(struct trace_array *tr)
 {
-	int ret = register_ftrace_graph(&trace_graph_return,
-					&trace_graph_entry);
+	int ret;
+
+	graph_array = tr;
+	ret = register_ftrace_graph(&trace_graph_return,
+				    &trace_graph_entry);
 	if (ret)
 		return ret;
 	tracing_start_cmdline_record();
@@ -177,49 +290,30 @@ static int graph_trace_init(struct trace_array *tr)
 	return 0;
 }
 
+void set_graph_array(struct trace_array *tr)
+{
+	graph_array = tr;
+}
+
 static void graph_trace_reset(struct trace_array *tr)
 {
 	tracing_stop_cmdline_record();
 	unregister_ftrace_graph();
 }
 
-static inline int log10_cpu(int nb)
-{
-	if (nb / 100)
-		return 3;
-	if (nb / 10)
-		return 2;
-	return 1;
-}
+static int max_bytes_for_cpu;
 
 static enum print_line_t
 print_graph_cpu(struct trace_seq *s, int cpu)
 {
-	int i;
 	int ret;
-	int log10_this = log10_cpu(cpu);
-	int log10_all = log10_cpu(cpumask_weight(cpu_online_mask));
-
 
 	/*
 	 * Start with a space character - to make it stand out
 	 * to the right a bit when trace output is pasted into
 	 * email:
 	 */
-	ret = trace_seq_printf(s, " ");
-
-	/*
-	 * Tricky - we space the CPU field according to the max
-	 * number of online CPUs. On a 2-cpu system it would take
-	 * a maximum of 1 digit - on a 128 cpu system it would
-	 * take up to 3 digits:
-	 */
-	for (i = 0; i < log10_all - log10_this; i++) {
-		ret = trace_seq_printf(s, " ");
-		if (!ret)
-			return TRACE_TYPE_PARTIAL_LINE;
-	}
-	ret = trace_seq_printf(s, "%d) ", cpu);
+	ret = trace_seq_printf(s, " %*d) ", max_bytes_for_cpu, cpu);
 	if (!ret)
 		return TRACE_TYPE_PARTIAL_LINE;
 
@@ -270,6 +364,15 @@ print_graph_proc(struct trace_seq *s, pid_t pid)
 }
 
 
+static enum print_line_t
+print_graph_lat_fmt(struct trace_seq *s, struct trace_entry *entry)
+{
+	if (!trace_seq_putc(s, ' '))
+		return 0;
+
+	return trace_print_lat_fmt(s, entry);
+}
+
 /* 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, struct fgraph_data *data)
@@ -427,6 +530,7 @@ print_graph_irq(struct trace_iterator *iter, unsigned long addr,
 		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, pid);
@@ -565,11 +669,7 @@ print_graph_entry_leaf(struct trace_iterator *iter,
 			return TRACE_TYPE_PARTIAL_LINE;
 	}
 
-	ret = seq_print_ip_sym(s, call->func, 0);
-	if (!ret)
-		return TRACE_TYPE_PARTIAL_LINE;
-
-	ret = trace_seq_printf(s, "();\n");
+	ret = trace_seq_printf(s, "%ps();\n", (void *)call->func);
 	if (!ret)
 		return TRACE_TYPE_PARTIAL_LINE;
 
@@ -612,11 +712,7 @@ print_graph_entry_nested(struct trace_iterator *iter,
 			return TRACE_TYPE_PARTIAL_LINE;
 	}
 
-	ret = seq_print_ip_sym(s, call->func, 0);
-	if (!ret)
-		return TRACE_TYPE_PARTIAL_LINE;
-
-	ret = trace_seq_printf(s, "() {\n");
+	ret = trace_seq_printf(s, "%ps() {\n", (void *)call->func);
 	if (!ret)
 		return TRACE_TYPE_PARTIAL_LINE;
 
@@ -672,6 +768,13 @@ print_graph_prologue(struct trace_iterator *iter, struct trace_seq *s,
 			return TRACE_TYPE_PARTIAL_LINE;
 	}
 
+	/* Latency format */
+	if (trace_flags & TRACE_ITER_LATENCY_FMT) {
+		ret = print_graph_lat_fmt(s, ent);
+		if (ret == TRACE_TYPE_PARTIAL_LINE)
+			return TRACE_TYPE_PARTIAL_LINE;
+	}
+
 	return 0;
 }
 
@@ -866,28 +969,59 @@ print_graph_function(struct trace_iterator *iter)
 	return TRACE_TYPE_HANDLED;
 }
 
+static void print_lat_header(struct seq_file *s)
+{
+	static const char spaces[] = "                "	/* 16 spaces */
+		"    "					/* 4 spaces */
+		"                 ";			/* 17 spaces */
+	int size = 0;
+
+	if (tracer_flags.val & TRACE_GRAPH_PRINT_ABS_TIME)
+		size += 16;
+	if (tracer_flags.val & TRACE_GRAPH_PRINT_CPU)
+		size += 4;
+	if (tracer_flags.val & TRACE_GRAPH_PRINT_PROC)
+		size += 17;
+
+	seq_printf(s, "#%.*s  _-----=> irqs-off        \n", size, spaces);
+	seq_printf(s, "#%.*s / _----=> need-resched    \n", size, spaces);
+	seq_printf(s, "#%.*s| / _---=> hardirq/softirq \n", size, spaces);
+	seq_printf(s, "#%.*s|| / _--=> preempt-depth   \n", size, spaces);
+	seq_printf(s, "#%.*s||| / _-=> lock-depth      \n", size, spaces);
+	seq_printf(s, "#%.*s|||| /                     \n", size, spaces);
+}
+
 static void print_graph_headers(struct seq_file *s)
 {
+	int lat = trace_flags & TRACE_ITER_LATENCY_FMT;
+
+	if (lat)
+		print_lat_header(s);
+
 	/* 1st line */
-	seq_printf(s, "# ");
+	seq_printf(s, "#");
 	if (tracer_flags.val & TRACE_GRAPH_PRINT_ABS_TIME)
 		seq_printf(s, "     TIME       ");
 	if (tracer_flags.val & TRACE_GRAPH_PRINT_CPU)
-		seq_printf(s, "CPU");
+		seq_printf(s, " CPU");
 	if (tracer_flags.val & TRACE_GRAPH_PRINT_PROC)
-		seq_printf(s, "  TASK/PID      ");
+		seq_printf(s, "  TASK/PID       ");
+	if (lat)
+		seq_printf(s, "|||||");
 	if (tracer_flags.val & TRACE_GRAPH_PRINT_DURATION)
 		seq_printf(s, "  DURATION   ");
 	seq_printf(s, "               FUNCTION CALLS\n");
 
 	/* 2nd line */
-	seq_printf(s, "# ");
+	seq_printf(s, "#");
 	if (tracer_flags.val & TRACE_GRAPH_PRINT_ABS_TIME)
 		seq_printf(s, "      |         ");
 	if (tracer_flags.val & TRACE_GRAPH_PRINT_CPU)
-		seq_printf(s, "|  ");
+		seq_printf(s, " |  ");
 	if (tracer_flags.val & TRACE_GRAPH_PRINT_PROC)
-		seq_printf(s, "  |    |        ");
+		seq_printf(s, "   |    |        ");
+	if (lat)
+		seq_printf(s, "|||||");
 	if (tracer_flags.val & TRACE_GRAPH_PRINT_DURATION)
 		seq_printf(s, "   |   |      ");
 	seq_printf(s, "               |   |   |   |\n");
@@ -934,6 +1068,8 @@ static struct tracer graph_trace __read_mostly = {
 
 static __init int init_graph_trace(void)
 {
+	max_bytes_for_cpu = snprintf(NULL, 0, "%d", nr_cpu_ids - 1);
+
 	return register_tracer(&graph_trace);
 }
 
diff --git a/kernel/trace/trace_hw_branches.c b/kernel/trace/trace_hw_branches.c
index ca7d7c4d0c2a..69543a905cd5 100644
--- a/kernel/trace/trace_hw_branches.c
+++ b/kernel/trace/trace_hw_branches.c
@@ -155,7 +155,7 @@ static enum print_line_t bts_trace_print_line(struct trace_iterator *iter)
 		    seq_print_ip_sym(seq, it->from, symflags) &&
 		    trace_seq_printf(seq, "\n"))
 			return TRACE_TYPE_HANDLED;
-		return TRACE_TYPE_PARTIAL_LINE;;
+		return TRACE_TYPE_PARTIAL_LINE;
 	}
 	return TRACE_TYPE_UNHANDLED;
 }
@@ -165,6 +165,7 @@ void trace_hw_branch(u64 from, u64 to)
 	struct ftrace_event_call *call = &event_hw_branch;
 	struct trace_array *tr = hw_branch_trace;
 	struct ring_buffer_event *event;
+	struct ring_buffer *buf;
 	struct hw_branch_entry *entry;
 	unsigned long irq1;
 	int cpu;
@@ -180,7 +181,8 @@ void trace_hw_branch(u64 from, u64 to)
 	if (atomic_inc_return(&tr->data[cpu]->disabled) != 1)
 		goto out;
 
-	event = trace_buffer_lock_reserve(tr, TRACE_HW_BRANCHES,
+	buf = tr->buffer;
+	event = trace_buffer_lock_reserve(buf, TRACE_HW_BRANCHES,
 					  sizeof(*entry), 0, 0);
 	if (!event)
 		goto out;
@@ -189,8 +191,8 @@ void trace_hw_branch(u64 from, u64 to)
 	entry->ent.type = TRACE_HW_BRANCHES;
 	entry->from = from;
 	entry->to   = to;
-	if (!filter_check_discard(call, entry, tr->buffer, event))
-		trace_buffer_unlock_commit(tr, event, 0, 0);
+	if (!filter_check_discard(call, entry, buf, event))
+		trace_buffer_unlock_commit(buf, event, 0, 0);
 
  out:
 	atomic_dec(&tr->data[cpu]->disabled);
diff --git a/kernel/trace/trace_irqsoff.c b/kernel/trace/trace_irqsoff.c
index b923d13e2fad..3aa7eaa2114c 100644
--- a/kernel/trace/trace_irqsoff.c
+++ b/kernel/trace/trace_irqsoff.c
@@ -129,15 +129,10 @@ check_critical_timing(struct trace_array *tr,
 		      unsigned long parent_ip,
 		      int cpu)
 {
-	unsigned long latency, t0, t1;
 	cycle_t T0, T1, delta;
 	unsigned long flags;
 	int pc;
 
-	/*
-	 * usecs conversion is slow so we try to delay the conversion
-	 * as long as possible:
-	 */
 	T0 = data->preempt_timestamp;
 	T1 = ftrace_now(cpu);
 	delta = T1-T0;
@@ -157,18 +152,15 @@ check_critical_timing(struct trace_array *tr,
 
 	trace_function(tr, CALLER_ADDR0, parent_ip, flags, pc);
 
-	latency = nsecs_to_usecs(delta);
-
 	if (data->critical_sequence != max_sequence)
 		goto out_unlock;
 
-	tracing_max_latency = delta;
-	t0 = nsecs_to_usecs(T0);
-	t1 = nsecs_to_usecs(T1);
-
 	data->critical_end = parent_ip;
 
-	update_max_tr_single(tr, current, cpu);
+	if (likely(!is_tracing_stopped())) {
+		tracing_max_latency = delta;
+		update_max_tr_single(tr, current, cpu);
+	}
 
 	max_sequence++;
 
@@ -178,7 +170,6 @@ out_unlock:
 out:
 	data->critical_sequence = max_sequence;
 	data->preempt_timestamp = ftrace_now(cpu);
-	tracing_reset(tr, cpu);
 	trace_function(tr, CALLER_ADDR0, parent_ip, flags, pc);
 }
 
@@ -208,7 +199,6 @@ start_critical_timing(unsigned long ip, unsigned long parent_ip)
 	data->critical_sequence = max_sequence;
 	data->preempt_timestamp = ftrace_now(cpu);
 	data->critical_start = parent_ip ? : ip;
-	tracing_reset(tr, cpu);
 
 	local_save_flags(flags);
 
@@ -379,6 +369,7 @@ static void __irqsoff_tracer_init(struct trace_array *tr)
 	irqsoff_trace = tr;
 	/* make sure that the tracer is visible */
 	smp_wmb();
+	tracing_reset_online_cpus(tr);
 	start_irqsoff_tracer(tr);
 }
 
diff --git a/kernel/trace/trace_mmiotrace.c b/kernel/trace/trace_mmiotrace.c
index d53b45ed0806..0acd834659ed 100644
--- a/kernel/trace/trace_mmiotrace.c
+++ b/kernel/trace/trace_mmiotrace.c
@@ -307,11 +307,13 @@ static void __trace_mmiotrace_rw(struct trace_array *tr,
 				struct trace_array_cpu *data,
 				struct mmiotrace_rw *rw)
 {
+	struct ftrace_event_call *call = &event_mmiotrace_rw;
+	struct ring_buffer *buffer = tr->buffer;
 	struct ring_buffer_event *event;
 	struct trace_mmiotrace_rw *entry;
 	int pc = preempt_count();
 
-	event = trace_buffer_lock_reserve(tr, TRACE_MMIO_RW,
+	event = trace_buffer_lock_reserve(buffer, TRACE_MMIO_RW,
 					  sizeof(*entry), 0, pc);
 	if (!event) {
 		atomic_inc(&dropped_count);
@@ -319,7 +321,9 @@ static void __trace_mmiotrace_rw(struct trace_array *tr,
 	}
 	entry	= ring_buffer_event_data(event);
 	entry->rw			= *rw;
-	trace_buffer_unlock_commit(tr, event, 0, pc);
+
+	if (!filter_check_discard(call, entry, buffer, event))
+		trace_buffer_unlock_commit(buffer, event, 0, pc);
 }
 
 void mmio_trace_rw(struct mmiotrace_rw *rw)
@@ -333,11 +337,13 @@ static void __trace_mmiotrace_map(struct trace_array *tr,
 				struct trace_array_cpu *data,
 				struct mmiotrace_map *map)
 {
+	struct ftrace_event_call *call = &event_mmiotrace_map;
+	struct ring_buffer *buffer = tr->buffer;
 	struct ring_buffer_event *event;
 	struct trace_mmiotrace_map *entry;
 	int pc = preempt_count();
 
-	event = trace_buffer_lock_reserve(tr, TRACE_MMIO_MAP,
+	event = trace_buffer_lock_reserve(buffer, TRACE_MMIO_MAP,
 					  sizeof(*entry), 0, pc);
 	if (!event) {
 		atomic_inc(&dropped_count);
@@ -345,7 +351,9 @@ static void __trace_mmiotrace_map(struct trace_array *tr,
 	}
 	entry	= ring_buffer_event_data(event);
 	entry->map			= *map;
-	trace_buffer_unlock_commit(tr, event, 0, pc);
+
+	if (!filter_check_discard(call, entry, buffer, event))
+		trace_buffer_unlock_commit(buffer, event, 0, pc);
 }
 
 void mmio_trace_mapping(struct mmiotrace_map *map)
diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c
index e0c2545622e8..b6c12c6a1bcd 100644
--- a/kernel/trace/trace_output.c
+++ b/kernel/trace/trace_output.c
@@ -69,6 +69,9 @@ enum print_line_t trace_print_printk_msg_only(struct trace_iterator *iter)
  * @s: trace sequence descriptor
  * @fmt: printf format string
  *
+ * It returns 0 if the trace oversizes the buffer's free
+ * space, 1 otherwise.
+ *
  * The tracer may use either sequence operations or its own
  * copy to user routines. To simplify formating of a trace
  * trace_seq_printf is used to store strings into a special
@@ -95,7 +98,7 @@ trace_seq_printf(struct trace_seq *s, const char *fmt, ...)
 
 	s->len += ret;
 
-	return len;
+	return 1;
 }
 EXPORT_SYMBOL_GPL(trace_seq_printf);
 
@@ -407,7 +410,7 @@ seq_print_userip_objs(const struct userstack_entry *entry, struct trace_seq *s,
 		 * since individual threads might have already quit!
 		 */
 		rcu_read_lock();
-		task = find_task_by_vpid(entry->ent.tgid);
+		task = find_task_by_vpid(entry->tgid);
 		if (task)
 			mm = get_task_mm(task);
 		rcu_read_unlock();
@@ -460,18 +463,23 @@ seq_print_ip_sym(struct trace_seq *s, unsigned long ip, unsigned long sym_flags)
 	return ret;
 }
 
-static int
-lat_print_generic(struct trace_seq *s, struct trace_entry *entry, int cpu)
+/**
+ * trace_print_lat_fmt - print the irq, preempt and lockdep fields
+ * @s: trace seq struct to write to
+ * @entry: The trace entry field from the ring buffer
+ *
+ * Prints the generic fields of irqs off, in hard or softirq, preempt
+ * count and lock depth.
+ */
+int trace_print_lat_fmt(struct trace_seq *s, struct trace_entry *entry)
 {
 	int hardirq, softirq;
-	char comm[TASK_COMM_LEN];
+	int ret;
 
-	trace_find_cmdline(entry->pid, comm);
 	hardirq = entry->flags & TRACE_FLAG_HARDIRQ;
 	softirq = entry->flags & TRACE_FLAG_SOFTIRQ;
 
-	if (!trace_seq_printf(s, "%8.8s-%-5d %3d%c%c%c",
-			      comm, entry->pid, cpu,
+	if (!trace_seq_printf(s, "%c%c%c",
 			      (entry->flags & TRACE_FLAG_IRQS_OFF) ? 'd' :
 				(entry->flags & TRACE_FLAG_IRQS_NOSUPPORT) ?
 				  'X' : '.',
@@ -482,8 +490,31 @@ lat_print_generic(struct trace_seq *s, struct trace_entry *entry, int cpu)
 		return 0;
 
 	if (entry->preempt_count)
-		return trace_seq_printf(s, "%x", entry->preempt_count);
-	return trace_seq_puts(s, ".");
+		ret = trace_seq_printf(s, "%x", entry->preempt_count);
+	else
+		ret = trace_seq_putc(s, '.');
+
+	if (!ret)
+		return 0;
+
+	if (entry->lock_depth < 0)
+		return trace_seq_putc(s, '.');
+
+	return trace_seq_printf(s, "%d", entry->lock_depth);
+}
+
+static int
+lat_print_generic(struct trace_seq *s, struct trace_entry *entry, int cpu)
+{
+	char comm[TASK_COMM_LEN];
+
+	trace_find_cmdline(entry->pid, comm);
+
+	if (!trace_seq_printf(s, "%8.8s-%-5d %3d",
+			      comm, entry->pid, cpu))
+		return 0;
+
+	return trace_print_lat_fmt(s, entry);
 }
 
 static unsigned long preempt_mark_thresh = 100;
@@ -857,7 +888,7 @@ static int trace_ctxwake_raw(struct trace_iterator *iter, char S)
 	trace_assign_type(field, iter->ent);
 
 	if (!S)
-		task_state_char(field->prev_state);
+		S = task_state_char(field->prev_state);
 	T = task_state_char(field->next_state);
 	if (!trace_seq_printf(&iter->seq, "%d %d %c %d %d %d %c\n",
 			      field->prev_pid,
@@ -892,7 +923,7 @@ static int trace_ctxwake_hex(struct trace_iterator *iter, char S)
 	trace_assign_type(field, iter->ent);
 
 	if (!S)
-		task_state_char(field->prev_state);
+		S = task_state_char(field->prev_state);
 	T = task_state_char(field->next_state);
 
 	SEQ_PUT_HEX_FIELD_RET(s, field->prev_pid);
diff --git a/kernel/trace/trace_output.h b/kernel/trace/trace_output.h
index d38bec4a9c30..9d91c72ba38b 100644
--- a/kernel/trace/trace_output.h
+++ b/kernel/trace/trace_output.h
@@ -26,6 +26,8 @@ extern struct trace_event *ftrace_find_event(int type);
 
 extern enum print_line_t trace_nop_print(struct trace_iterator *iter,
 					 int flags);
+extern int
+trace_print_lat_fmt(struct trace_seq *s, struct trace_entry *entry);
 
 /* used by module unregistering */
 extern int __unregister_ftrace_event(struct trace_event *event);
diff --git a/kernel/trace/trace_power.c b/kernel/trace/trace_power.c
deleted file mode 100644
index 8a30d9874cd4..000000000000
--- a/kernel/trace/trace_power.c
+++ /dev/null
@@ -1,214 +0,0 @@
-/*
- * ring buffer based C-state tracer
- *
- * Arjan van de Ven <arjan@linux.intel.com>
- * Copyright (C) 2008 Intel Corporation
- *
- * Much is borrowed from trace_boot.c which is
- * Copyright (C) 2008 Frederic Weisbecker <fweisbec@gmail.com>
- *
- */
-
-#include <linux/init.h>
-#include <linux/debugfs.h>
-#include <trace/power.h>
-#include <linux/kallsyms.h>
-#include <linux/module.h>
-
-#include "trace.h"
-#include "trace_output.h"
-
-static struct trace_array *power_trace;
-static int __read_mostly trace_power_enabled;
-
-static void probe_power_start(struct power_trace *it, unsigned int type,
-				unsigned int level)
-{
-	if (!trace_power_enabled)
-		return;
-
-	memset(it, 0, sizeof(struct power_trace));
-	it->state = level;
-	it->type = type;
-	it->stamp = ktime_get();
-}
-
-
-static void probe_power_end(struct power_trace *it)
-{
-	struct ftrace_event_call *call = &event_power;
-	struct ring_buffer_event *event;
-	struct trace_power *entry;
-	struct trace_array_cpu *data;
-	struct trace_array *tr = power_trace;
-
-	if (!trace_power_enabled)
-		return;
-
-	preempt_disable();
-	it->end = ktime_get();
-	data = tr->data[smp_processor_id()];
-
-	event = trace_buffer_lock_reserve(tr, TRACE_POWER,
-					  sizeof(*entry), 0, 0);
-	if (!event)
-		goto out;
-	entry	= ring_buffer_event_data(event);
-	entry->state_data = *it;
-	if (!filter_check_discard(call, entry, tr->buffer, event))
-		trace_buffer_unlock_commit(tr, event, 0, 0);
- out:
-	preempt_enable();
-}
-
-static void probe_power_mark(struct power_trace *it, unsigned int type,
-				unsigned int level)
-{
-	struct ftrace_event_call *call = &event_power;
-	struct ring_buffer_event *event;
-	struct trace_power *entry;
-	struct trace_array_cpu *data;
-	struct trace_array *tr = power_trace;
-
-	if (!trace_power_enabled)
-		return;
-
-	memset(it, 0, sizeof(struct power_trace));
-	it->state = level;
-	it->type = type;
-	it->stamp = ktime_get();
-	preempt_disable();
-	it->end = it->stamp;
-	data = tr->data[smp_processor_id()];
-
-	event = trace_buffer_lock_reserve(tr, TRACE_POWER,
-					  sizeof(*entry), 0, 0);
-	if (!event)
-		goto out;
-	entry	= ring_buffer_event_data(event);
-	entry->state_data = *it;
-	if (!filter_check_discard(call, entry, tr->buffer, event))
-		trace_buffer_unlock_commit(tr, event, 0, 0);
- out:
-	preempt_enable();
-}
-
-static int tracing_power_register(void)
-{
-	int ret;
-
-	ret = register_trace_power_start(probe_power_start);
-	if (ret) {
-		pr_info("power trace: Couldn't activate tracepoint"
-			" probe to trace_power_start\n");
-		return ret;
-	}
-	ret = register_trace_power_end(probe_power_end);
-	if (ret) {
-		pr_info("power trace: Couldn't activate tracepoint"
-			" probe to trace_power_end\n");
-		goto fail_start;
-	}
-	ret = register_trace_power_mark(probe_power_mark);
-	if (ret) {
-		pr_info("power trace: Couldn't activate tracepoint"
-			" probe to trace_power_mark\n");
-		goto fail_end;
-	}
-	return ret;
-fail_end:
-	unregister_trace_power_end(probe_power_end);
-fail_start:
-	unregister_trace_power_start(probe_power_start);
-	return ret;
-}
-
-static void start_power_trace(struct trace_array *tr)
-{
-	trace_power_enabled = 1;
-}
-
-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);
-}
-
-
-static int power_trace_init(struct trace_array *tr)
-{
-	int cpu;
-	power_trace = tr;
-
-	trace_power_enabled = 1;
-	tracing_power_register();
-
-	for_each_cpu(cpu, cpu_possible_mask)
-		tracing_reset(tr, cpu);
-	return 0;
-}
-
-static enum print_line_t power_print_line(struct trace_iterator *iter)
-{
-	int ret = 0;
-	struct trace_entry *entry = iter->ent;
-	struct trace_power *field ;
-	struct power_trace *it;
-	struct trace_seq *s = &iter->seq;
-	struct timespec stamp;
-	struct timespec duration;
-
-	trace_assign_type(field, entry);
-	it = &field->state_data;
-	stamp = ktime_to_timespec(it->stamp);
-	duration = ktime_to_timespec(ktime_sub(it->end, it->stamp));
-
-	if (entry->type == TRACE_POWER) {
-		if (it->type == POWER_CSTATE)
-			ret = trace_seq_printf(s, "[%5ld.%09ld] CSTATE: Going to C%i on cpu %i for %ld.%09ld\n",
-					  stamp.tv_sec,
-					  stamp.tv_nsec,
-					  it->state, iter->cpu,
-					  duration.tv_sec,
-					  duration.tv_nsec);
-		if (it->type == POWER_PSTATE)
-			ret = trace_seq_printf(s, "[%5ld.%09ld] PSTATE: Going to P%i on cpu %i\n",
-					  stamp.tv_sec,
-					  stamp.tv_nsec,
-					  it->state, iter->cpu);
-		if (!ret)
-			return TRACE_TYPE_PARTIAL_LINE;
-		return TRACE_TYPE_HANDLED;
-	}
-	return TRACE_TYPE_UNHANDLED;
-}
-
-static void power_print_header(struct seq_file *s)
-{
-	seq_puts(s, "#   TIMESTAMP      STATE  EVENT\n");
-	seq_puts(s, "#       |            |      |\n");
-}
-
-static struct tracer power_tracer __read_mostly =
-{
-	.name		= "power",
-	.init		= power_trace_init,
-	.start		= start_power_trace,
-	.stop		= stop_power_trace,
-	.reset		= power_trace_reset,
-	.print_line	= power_print_line,
-	.print_header	= power_print_header,
-};
-
-static int init_power_trace(void)
-{
-	return register_tracer(&power_tracer);
-}
-device_initcall(init_power_trace);
diff --git a/kernel/trace/trace_printk.c b/kernel/trace/trace_printk.c
index 687699d365ae..2547d8813cf0 100644
--- a/kernel/trace/trace_printk.c
+++ b/kernel/trace/trace_printk.c
@@ -11,7 +11,6 @@
 #include <linux/ftrace.h>
 #include <linux/string.h>
 #include <linux/module.h>
-#include <linux/marker.h>
 #include <linux/mutex.h>
 #include <linux/ctype.h>
 #include <linux/list.h>
diff --git a/kernel/trace/trace_sched_switch.c b/kernel/trace/trace_sched_switch.c
index a98106dd979c..5fca0f51fde4 100644
--- a/kernel/trace/trace_sched_switch.c
+++ b/kernel/trace/trace_sched_switch.c
@@ -20,6 +20,35 @@ static int			sched_ref;
 static DEFINE_MUTEX(sched_register_mutex);
 static int			sched_stopped;
 
+
+void
+tracing_sched_switch_trace(struct trace_array *tr,
+			   struct task_struct *prev,
+			   struct task_struct *next,
+			   unsigned long flags, int pc)
+{
+	struct ftrace_event_call *call = &event_context_switch;
+	struct ring_buffer *buffer = tr->buffer;
+	struct ring_buffer_event *event;
+	struct ctx_switch_entry *entry;
+
+	event = trace_buffer_lock_reserve(buffer, TRACE_CTX,
+					  sizeof(*entry), flags, pc);
+	if (!event)
+		return;
+	entry	= ring_buffer_event_data(event);
+	entry->prev_pid			= prev->pid;
+	entry->prev_prio		= prev->prio;
+	entry->prev_state		= prev->state;
+	entry->next_pid			= next->pid;
+	entry->next_prio		= next->prio;
+	entry->next_state		= next->state;
+	entry->next_cpu	= task_cpu(next);
+
+	if (!filter_check_discard(call, entry, buffer, event))
+		trace_buffer_unlock_commit(buffer, event, flags, pc);
+}
+
 static void
 probe_sched_switch(struct rq *__rq, struct task_struct *prev,
 			struct task_struct *next)
@@ -49,6 +78,36 @@ probe_sched_switch(struct rq *__rq, struct task_struct *prev,
 	local_irq_restore(flags);
 }
 
+void
+tracing_sched_wakeup_trace(struct trace_array *tr,
+			   struct task_struct *wakee,
+			   struct task_struct *curr,
+			   unsigned long flags, int pc)
+{
+	struct ftrace_event_call *call = &event_wakeup;
+	struct ring_buffer_event *event;
+	struct ctx_switch_entry *entry;
+	struct ring_buffer *buffer = tr->buffer;
+
+	event = trace_buffer_lock_reserve(buffer, TRACE_WAKE,
+					  sizeof(*entry), flags, pc);
+	if (!event)
+		return;
+	entry	= ring_buffer_event_data(event);
+	entry->prev_pid			= curr->pid;
+	entry->prev_prio		= curr->prio;
+	entry->prev_state		= curr->state;
+	entry->next_pid			= wakee->pid;
+	entry->next_prio		= wakee->prio;
+	entry->next_state		= wakee->state;
+	entry->next_cpu			= task_cpu(wakee);
+
+	if (!filter_check_discard(call, entry, buffer, event))
+		ring_buffer_unlock_commit(buffer, event);
+	ftrace_trace_stack(tr->buffer, flags, 6, pc);
+	ftrace_trace_userstack(tr->buffer, flags, pc);
+}
+
 static void
 probe_sched_wakeup(struct rq *__rq, struct task_struct *wakee, int success)
 {
diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c
index eacb27225173..26185d727676 100644
--- a/kernel/trace/trace_sched_wakeup.c
+++ b/kernel/trace/trace_sched_wakeup.c
@@ -24,6 +24,7 @@ static int __read_mostly	tracer_enabled;
 
 static struct task_struct	*wakeup_task;
 static int			wakeup_cpu;
+static int			wakeup_current_cpu;
 static unsigned			wakeup_prio = -1;
 static int			wakeup_rt;
 
@@ -56,33 +57,23 @@ wakeup_tracer_call(unsigned long ip, unsigned long parent_ip)
 	resched = ftrace_preempt_disable();
 
 	cpu = raw_smp_processor_id();
+	if (cpu != wakeup_current_cpu)
+		goto out_enable;
+
 	data = tr->data[cpu];
 	disabled = atomic_inc_return(&data->disabled);
 	if (unlikely(disabled != 1))
 		goto out;
 
 	local_irq_save(flags);
-	__raw_spin_lock(&wakeup_lock);
-
-	if (unlikely(!wakeup_task))
-		goto unlock;
-
-	/*
-	 * The task can't disappear because it needs to
-	 * wake up first, and we have the wakeup_lock.
-	 */
-	if (task_cpu(wakeup_task) != cpu)
-		goto unlock;
 
 	trace_function(tr, ip, parent_ip, flags, pc);
 
- unlock:
-	__raw_spin_unlock(&wakeup_lock);
 	local_irq_restore(flags);
 
  out:
 	atomic_dec(&data->disabled);
-
+ out_enable:
 	ftrace_preempt_enable(resched);
 }
 
@@ -107,11 +98,18 @@ static int report_latency(cycle_t delta)
 	return 1;
 }
 
+static void probe_wakeup_migrate_task(struct task_struct *task, int cpu)
+{
+	if (task != wakeup_task)
+		return;
+
+	wakeup_current_cpu = cpu;
+}
+
 static void notrace
 probe_wakeup_sched_switch(struct rq *rq, struct task_struct *prev,
 	struct task_struct *next)
 {
-	unsigned long latency = 0, t0 = 0, t1 = 0;
 	struct trace_array_cpu *data;
 	cycle_t T0, T1, delta;
 	unsigned long flags;
@@ -157,10 +155,6 @@ probe_wakeup_sched_switch(struct rq *rq, struct task_struct *prev,
 	trace_function(wakeup_trace, CALLER_ADDR0, CALLER_ADDR1, flags, pc);
 	tracing_sched_switch_trace(wakeup_trace, prev, next, flags, pc);
 
-	/*
-	 * usecs conversion is slow so we try to delay the conversion
-	 * as long as possible:
-	 */
 	T0 = data->preempt_timestamp;
 	T1 = ftrace_now(cpu);
 	delta = T1-T0;
@@ -168,13 +162,10 @@ probe_wakeup_sched_switch(struct rq *rq, struct task_struct *prev,
 	if (!report_latency(delta))
 		goto out_unlock;
 
-	latency = nsecs_to_usecs(delta);
-
-	tracing_max_latency = delta;
-	t0 = nsecs_to_usecs(T0);
-	t1 = nsecs_to_usecs(T1);
-
-	update_max_tr(wakeup_trace, wakeup_task, wakeup_cpu);
+	if (likely(!is_tracing_stopped())) {
+		tracing_max_latency = delta;
+		update_max_tr(wakeup_trace, wakeup_task, wakeup_cpu);
+	}
 
 out_unlock:
 	__wakeup_reset(wakeup_trace);
@@ -186,11 +177,6 @@ out:
 
 static void __wakeup_reset(struct trace_array *tr)
 {
-	int cpu;
-
-	for_each_possible_cpu(cpu)
-		tracing_reset(tr, cpu);
-
 	wakeup_cpu = -1;
 	wakeup_prio = -1;
 
@@ -204,6 +190,8 @@ static void wakeup_reset(struct trace_array *tr)
 {
 	unsigned long flags;
 
+	tracing_reset_online_cpus(tr);
+
 	local_irq_save(flags);
 	__raw_spin_lock(&wakeup_lock);
 	__wakeup_reset(tr);
@@ -247,6 +235,7 @@ probe_wakeup(struct rq *rq, struct task_struct *p, int success)
 	__wakeup_reset(wakeup_trace);
 
 	wakeup_cpu = task_cpu(p);
+	wakeup_current_cpu = wakeup_cpu;
 	wakeup_prio = p->prio;
 
 	wakeup_task = p;
@@ -296,6 +285,13 @@ static void start_wakeup_tracer(struct trace_array *tr)
 		goto fail_deprobe_wake_new;
 	}
 
+	ret = register_trace_sched_migrate_task(probe_wakeup_migrate_task);
+	if (ret) {
+		pr_info("wakeup trace: Couldn't activate tracepoint"
+			" probe to kernel_sched_migrate_task\n");
+		return;
+	}
+
 	wakeup_reset(tr);
 
 	/*
@@ -328,6 +324,7 @@ static void stop_wakeup_tracer(struct trace_array *tr)
 	unregister_trace_sched_switch(probe_wakeup_sched_switch);
 	unregister_trace_sched_wakeup_new(probe_wakeup);
 	unregister_trace_sched_wakeup(probe_wakeup);
+	unregister_trace_sched_migrate_task(probe_wakeup_migrate_task);
 }
 
 static int __wakeup_tracer_init(struct trace_array *tr)
diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c
index 00dd6485bdd7..d2cdbabb4ead 100644
--- a/kernel/trace/trace_selftest.c
+++ b/kernel/trace/trace_selftest.c
@@ -288,6 +288,7 @@ trace_selftest_startup_function_graph(struct tracer *trace,
 	 * to detect and recover from possible hangs
 	 */
 	tracing_reset_online_cpus(tr);
+	set_graph_array(tr);
 	ret = register_ftrace_graph(&trace_graph_return,
 				    &trace_graph_entry_watchdog);
 	if (ret) {
diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c
index 6a2a9d484cd6..8504ac71e4e8 100644
--- a/kernel/trace/trace_stack.c
+++ b/kernel/trace/trace_stack.c
@@ -186,43 +186,33 @@ static const struct file_operations stack_max_size_fops = {
 };
 
 static void *
-t_next(struct seq_file *m, void *v, loff_t *pos)
+__next(struct seq_file *m, loff_t *pos)
 {
-	long i;
+	long n = *pos - 1;
 
-	(*pos)++;
-
-	if (v == SEQ_START_TOKEN)
-		i = 0;
-	else {
-		i = *(long *)v;
-		i++;
-	}
-
-	if (i >= max_stack_trace.nr_entries ||
-	    stack_dump_trace[i] == ULONG_MAX)
+	if (n >= max_stack_trace.nr_entries || stack_dump_trace[n] == ULONG_MAX)
 		return NULL;
 
-	m->private = (void *)i;
-
+	m->private = (void *)n;
 	return &m->private;
 }
 
-static void *t_start(struct seq_file *m, loff_t *pos)
+static void *
+t_next(struct seq_file *m, void *v, loff_t *pos)
 {
-	void *t = SEQ_START_TOKEN;
-	loff_t l = 0;
+	(*pos)++;
+	return __next(m, pos);
+}
 
+static void *t_start(struct seq_file *m, loff_t *pos)
+{
 	local_irq_disable();
 	__raw_spin_lock(&max_stack_lock);
 
 	if (*pos == 0)
 		return SEQ_START_TOKEN;
 
-	for (; t && l < *pos; t = t_next(m, t, &l))
-		;
-
-	return t;
+	return __next(m, pos);
 }
 
 static void t_stop(struct seq_file *m, void *p)
@@ -234,15 +224,8 @@ static void t_stop(struct seq_file *m, void *p)
 static int trace_lookup_stack(struct seq_file *m, long i)
 {
 	unsigned long addr = stack_dump_trace[i];
-#ifdef CONFIG_KALLSYMS
-	char str[KSYM_SYMBOL_LEN];
-
-	sprint_symbol(str, addr);
 
-	return seq_printf(m, "%s\n", str);
-#else
-	return seq_printf(m, "%p\n", (void*)addr);
-#endif
+	return seq_printf(m, "%pF\n", (void *)addr);
 }
 
 static void print_disabled(struct seq_file *m)
@@ -313,14 +296,14 @@ static const struct file_operations stack_trace_fops = {
 
 int
 stack_trace_sysctl(struct ctl_table *table, int write,
-		   struct file *file, void __user *buffer, size_t *lenp,
+		   void __user *buffer, size_t *lenp,
 		   loff_t *ppos)
 {
 	int ret;
 
 	mutex_lock(&stack_sysctl_mutex);
 
-	ret = proc_dointvec(table, write, file, buffer, lenp, ppos);
+	ret = proc_dointvec(table, write, buffer, lenp, ppos);
 
 	if (ret || !write ||
 	    (last_stack_tracer_enabled == !!stack_tracer_enabled))
diff --git a/kernel/trace/trace_stat.c b/kernel/trace/trace_stat.c
index aea321c82fa0..a4bb239eb987 100644
--- a/kernel/trace/trace_stat.c
+++ b/kernel/trace/trace_stat.c
@@ -49,7 +49,8 @@ static struct dentry		*stat_dir;
  * but it will at least advance closer to the next one
  * to be released.
  */
-static struct rb_node *release_next(struct rb_node *node)
+static struct rb_node *release_next(struct tracer_stat *ts,
+				    struct rb_node *node)
 {
 	struct stat_node *snode;
 	struct rb_node *parent = rb_parent(node);
@@ -67,6 +68,8 @@ static struct rb_node *release_next(struct rb_node *node)
 			parent->rb_right = NULL;
 
 		snode = container_of(node, struct stat_node, node);
+		if (ts->stat_release)
+			ts->stat_release(snode->stat);
 		kfree(snode);
 
 		return parent;
@@ -78,7 +81,7 @@ static void __reset_stat_session(struct stat_session *session)
 	struct rb_node *node = session->stat_root.rb_node;
 
 	while (node)
-		node = release_next(node);
+		node = release_next(session->ts, node);
 
 	session->stat_root = RB_ROOT;
 }
@@ -200,17 +203,21 @@ static void *stat_seq_start(struct seq_file *s, loff_t *pos)
 {
 	struct stat_session *session = s->private;
 	struct rb_node *node;
+	int n = *pos;
 	int i;
 
 	/* Prevent from tracer switch or rbtree modification */
 	mutex_lock(&session->stat_mutex);
 
 	/* If we are in the beginning of the file, print the headers */
-	if (!*pos && session->ts->stat_headers)
-		return SEQ_START_TOKEN;
+	if (session->ts->stat_headers) {
+		if (n == 0)
+			return SEQ_START_TOKEN;
+		n--;
+	}
 
 	node = rb_first(&session->stat_root);
-	for (i = 0; node && i < *pos; i++)
+	for (i = 0; node && i < n; i++)
 		node = rb_next(node);
 
 	return node;
diff --git a/kernel/trace/trace_stat.h b/kernel/trace/trace_stat.h
index f3546a2cd826..8f03914b9a6a 100644
--- a/kernel/trace/trace_stat.h
+++ b/kernel/trace/trace_stat.h
@@ -18,6 +18,8 @@ struct tracer_stat {
 	int			(*stat_cmp)(void *p1, void *p2);
 	/* Print a stat entry */
 	int			(*stat_show)(struct seq_file *s, void *p);
+	/* Release an entry */
+	void			(*stat_release)(void *stat);
 	/* Print the headers of your stat entries */
 	int			(*stat_headers)(struct seq_file *s);
 };
diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c
index 5e579645ac86..527e17eae575 100644
--- a/kernel/trace/trace_syscalls.c
+++ b/kernel/trace/trace_syscalls.c
@@ -1,30 +1,18 @@
 #include <trace/syscall.h>
+#include <trace/events/syscalls.h>
 #include <linux/kernel.h>
+#include <linux/ftrace.h>
+#include <linux/perf_event.h>
 #include <asm/syscall.h>
 
 #include "trace_output.h"
 #include "trace.h"
 
-/* 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
-};
+static int sys_refcount_enter;
+static int sys_refcount_exit;
+static DECLARE_BITMAP(enabled_enter_syscalls, NR_syscalls);
+static DECLARE_BITMAP(enabled_exit_syscalls, NR_syscalls);
 
 enum print_line_t
 print_syscall_enter(struct trace_iterator *iter, int flags)
@@ -35,35 +23,46 @@ print_syscall_enter(struct trace_iterator *iter, int flags)
 	struct syscall_metadata *entry;
 	int i, ret, syscall;
 
-	trace_assign_type(trace, ent);
-
+	trace = (typeof(trace))ent;
 	syscall = trace->nr;
-
 	entry = syscall_nr_to_meta(syscall);
+
 	if (!entry)
 		goto end;
 
+	if (entry->enter_id != ent->type) {
+		WARN_ON_ONCE(1);
+		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) {
+		if (trace_flags & TRACE_ITER_VERBOSE) {
 			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],
+		ret = trace_seq_printf(s, "%s: %lx%s", entry->args[i],
 				       trace->args[i],
-				       i == entry->nb_args - 1 ? ")" : ",");
+				       i == entry->nb_args - 1 ? "" : ", ");
 		if (!ret)
 			return TRACE_TYPE_PARTIAL_LINE;
 	}
 
+	ret = trace_seq_putc(s, ')');
+	if (!ret)
+		return TRACE_TYPE_PARTIAL_LINE;
+
 end:
-	trace_seq_printf(s, "\n");
+	ret =  trace_seq_putc(s, '\n');
+	if (!ret)
+		return TRACE_TYPE_PARTIAL_LINE;
+
 	return TRACE_TYPE_HANDLED;
 }
 
@@ -77,16 +76,20 @@ print_syscall_exit(struct trace_iterator *iter, int flags)
 	struct syscall_metadata *entry;
 	int ret;
 
-	trace_assign_type(trace, ent);
-
+	trace = (typeof(trace))ent;
 	syscall = trace->nr;
-
 	entry = syscall_nr_to_meta(syscall);
+
 	if (!entry) {
 		trace_seq_printf(s, "\n");
 		return TRACE_TYPE_HANDLED;
 	}
 
+	if (entry->exit_id != ent->type) {
+		WARN_ON_ONCE(1);
+		return TRACE_TYPE_UNHANDLED;
+	}
+
 	ret = trace_seq_printf(s, "%s -> 0x%lx\n", entry->name,
 				trace->ret);
 	if (!ret)
@@ -95,62 +98,140 @@ print_syscall_exit(struct trace_iterator *iter, int flags)
 	return TRACE_TYPE_HANDLED;
 }
 
-void start_ftrace_syscalls(void)
+extern char *__bad_type_size(void);
+
+#define SYSCALL_FIELD(type, name)					\
+	sizeof(type) != sizeof(trace.name) ?				\
+		__bad_type_size() :					\
+		#type, #name, offsetof(typeof(trace), name), sizeof(trace.name)
+
+int syscall_enter_format(struct ftrace_event_call *call, struct trace_seq *s)
 {
-	unsigned long flags;
-	struct task_struct *g, *t;
+	int i;
+	int nr;
+	int ret;
+	struct syscall_metadata *entry;
+	struct syscall_trace_enter trace;
+	int offset = offsetof(struct syscall_trace_enter, args);
 
-	mutex_lock(&syscall_trace_lock);
+	nr = syscall_name_to_nr(call->data);
+	entry = syscall_nr_to_meta(nr);
 
-	/* Don't enable the flag on the tasks twice */
-	if (++refcount != 1)
-		goto unlock;
+	if (!entry)
+		return 0;
 
-	arch_init_ftrace_syscalls();
-	read_lock_irqsave(&tasklist_lock, flags);
+	ret = trace_seq_printf(s, "\tfield:%s %s;\toffset:%zu;\tsize:%zu;\n",
+			       SYSCALL_FIELD(int, nr));
+	if (!ret)
+		return 0;
 
-	do_each_thread(g, t) {
-		set_tsk_thread_flag(t, TIF_SYSCALL_FTRACE);
-	} while_each_thread(g, t);
+	for (i = 0; i < entry->nb_args; i++) {
+		ret = trace_seq_printf(s, "\tfield:%s %s;", entry->types[i],
+				        entry->args[i]);
+		if (!ret)
+			return 0;
+		ret = trace_seq_printf(s, "\toffset:%d;\tsize:%zu;\n", offset,
+				       sizeof(unsigned long));
+		if (!ret)
+			return 0;
+		offset += sizeof(unsigned long);
+	}
 
-	read_unlock_irqrestore(&tasklist_lock, flags);
+	trace_seq_puts(s, "\nprint fmt: \"");
+	for (i = 0; i < entry->nb_args; i++) {
+		ret = trace_seq_printf(s, "%s: 0x%%0%zulx%s", entry->args[i],
+				        sizeof(unsigned long),
+					i == entry->nb_args - 1 ? "" : ", ");
+		if (!ret)
+			return 0;
+	}
+	trace_seq_putc(s, '"');
 
-unlock:
-	mutex_unlock(&syscall_trace_lock);
+	for (i = 0; i < entry->nb_args; i++) {
+		ret = trace_seq_printf(s, ", ((unsigned long)(REC->%s))",
+				       entry->args[i]);
+		if (!ret)
+			return 0;
+	}
+
+	return trace_seq_putc(s, '\n');
 }
 
-void stop_ftrace_syscalls(void)
+int syscall_exit_format(struct ftrace_event_call *call, struct trace_seq *s)
 {
-	unsigned long flags;
-	struct task_struct *g, *t;
+	int ret;
+	struct syscall_trace_exit trace;
 
-	mutex_lock(&syscall_trace_lock);
+	ret = trace_seq_printf(s,
+			       "\tfield:%s %s;\toffset:%zu;\tsize:%zu;\n"
+			       "\tfield:%s %s;\toffset:%zu;\tsize:%zu;\n",
+			       SYSCALL_FIELD(int, nr),
+			       SYSCALL_FIELD(long, ret));
+	if (!ret)
+		return 0;
 
-	/* There are perhaps still some users */
-	if (--refcount)
-		goto unlock;
+	return trace_seq_printf(s, "\nprint fmt: \"0x%%lx\", REC->ret\n");
+}
 
-	read_lock_irqsave(&tasklist_lock, flags);
+int syscall_enter_define_fields(struct ftrace_event_call *call)
+{
+	struct syscall_trace_enter trace;
+	struct syscall_metadata *meta;
+	int ret;
+	int nr;
+	int i;
+	int offset = offsetof(typeof(trace), args);
+
+	nr = syscall_name_to_nr(call->data);
+	meta = syscall_nr_to_meta(nr);
+
+	if (!meta)
+		return 0;
+
+	ret = trace_define_common_fields(call);
+	if (ret)
+		return ret;
+
+	for (i = 0; i < meta->nb_args; i++) {
+		ret = trace_define_field(call, meta->types[i],
+					 meta->args[i], offset,
+					 sizeof(unsigned long), 0,
+					 FILTER_OTHER);
+		offset += sizeof(unsigned long);
+	}
 
-	do_each_thread(g, t) {
-		clear_tsk_thread_flag(t, TIF_SYSCALL_FTRACE);
-	} while_each_thread(g, t);
+	return ret;
+}
 
-	read_unlock_irqrestore(&tasklist_lock, flags);
+int syscall_exit_define_fields(struct ftrace_event_call *call)
+{
+	struct syscall_trace_exit trace;
+	int ret;
 
-unlock:
-	mutex_unlock(&syscall_trace_lock);
+	ret = trace_define_common_fields(call);
+	if (ret)
+		return ret;
+
+	ret = trace_define_field(call, SYSCALL_FIELD(long, ret), 0,
+				 FILTER_OTHER);
+
+	return ret;
 }
 
-void ftrace_syscall_enter(struct pt_regs *regs)
+void ftrace_syscall_enter(struct pt_regs *regs, long id)
 {
 	struct syscall_trace_enter *entry;
 	struct syscall_metadata *sys_data;
 	struct ring_buffer_event *event;
+	struct ring_buffer *buffer;
 	int size;
 	int syscall_nr;
 
 	syscall_nr = syscall_get_nr(current, regs);
+	if (syscall_nr < 0)
+		return;
+	if (!test_bit(syscall_nr, enabled_enter_syscalls))
+		return;
 
 	sys_data = syscall_nr_to_meta(syscall_nr);
 	if (!sys_data)
@@ -158,8 +239,8 @@ void ftrace_syscall_enter(struct pt_regs *regs)
 
 	size = sizeof(*entry) + sizeof(unsigned long) * sys_data->nb_args;
 
-	event = trace_current_buffer_lock_reserve(TRACE_SYSCALL_ENTER, size,
-							0, 0);
+	event = trace_current_buffer_lock_reserve(&buffer, sys_data->enter_id,
+						  size, 0, 0);
 	if (!event)
 		return;
 
@@ -167,24 +248,30 @@ void ftrace_syscall_enter(struct pt_regs *regs)
 	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();
+	if (!filter_current_check_discard(buffer, sys_data->enter_event,
+					  entry, event))
+		trace_current_buffer_unlock_commit(buffer, event, 0, 0);
 }
 
-void ftrace_syscall_exit(struct pt_regs *regs)
+void ftrace_syscall_exit(struct pt_regs *regs, long ret)
 {
 	struct syscall_trace_exit *entry;
 	struct syscall_metadata *sys_data;
 	struct ring_buffer_event *event;
+	struct ring_buffer *buffer;
 	int syscall_nr;
 
 	syscall_nr = syscall_get_nr(current, regs);
+	if (syscall_nr < 0)
+		return;
+	if (!test_bit(syscall_nr, enabled_exit_syscalls))
+		return;
 
 	sys_data = syscall_nr_to_meta(syscall_nr);
 	if (!sys_data)
 		return;
 
-	event = trace_current_buffer_lock_reserve(TRACE_SYSCALL_EXIT,
+	event = trace_current_buffer_lock_reserve(&buffer, sys_data->exit_id,
 				sizeof(*entry), 0, 0);
 	if (!event)
 		return;
@@ -193,58 +280,303 @@ void ftrace_syscall_exit(struct pt_regs *regs)
 	entry->nr = syscall_nr;
 	entry->ret = syscall_get_return_value(current, regs);
 
-	trace_current_buffer_unlock_commit(event, 0, 0);
-	trace_wake_up();
+	if (!filter_current_check_discard(buffer, sys_data->exit_event,
+					  entry, event))
+		trace_current_buffer_unlock_commit(buffer, event, 0, 0);
 }
 
-static int init_syscall_tracer(struct trace_array *tr)
+int reg_event_syscall_enter(void *ptr)
 {
-	start_ftrace_syscalls();
+	int ret = 0;
+	int num;
+	char *name;
+
+	name = (char *)ptr;
+	num = syscall_name_to_nr(name);
+	if (num < 0 || num >= NR_syscalls)
+		return -ENOSYS;
+	mutex_lock(&syscall_trace_lock);
+	if (!sys_refcount_enter)
+		ret = register_trace_sys_enter(ftrace_syscall_enter);
+	if (ret) {
+		pr_info("event trace: Could not activate"
+				"syscall entry trace point");
+	} else {
+		set_bit(num, enabled_enter_syscalls);
+		sys_refcount_enter++;
+	}
+	mutex_unlock(&syscall_trace_lock);
+	return ret;
+}
+
+void unreg_event_syscall_enter(void *ptr)
+{
+	int num;
+	char *name;
 
-	return 0;
+	name = (char *)ptr;
+	num = syscall_name_to_nr(name);
+	if (num < 0 || num >= NR_syscalls)
+		return;
+	mutex_lock(&syscall_trace_lock);
+	sys_refcount_enter--;
+	clear_bit(num, enabled_enter_syscalls);
+	if (!sys_refcount_enter)
+		unregister_trace_sys_enter(ftrace_syscall_enter);
+	mutex_unlock(&syscall_trace_lock);
 }
 
-static void reset_syscall_tracer(struct trace_array *tr)
+int reg_event_syscall_exit(void *ptr)
 {
-	stop_ftrace_syscalls();
-	tracing_reset_online_cpus(tr);
+	int ret = 0;
+	int num;
+	char *name;
+
+	name = (char *)ptr;
+	num = syscall_name_to_nr(name);
+	if (num < 0 || num >= NR_syscalls)
+		return -ENOSYS;
+	mutex_lock(&syscall_trace_lock);
+	if (!sys_refcount_exit)
+		ret = register_trace_sys_exit(ftrace_syscall_exit);
+	if (ret) {
+		pr_info("event trace: Could not activate"
+				"syscall exit trace point");
+	} else {
+		set_bit(num, enabled_exit_syscalls);
+		sys_refcount_exit++;
+	}
+	mutex_unlock(&syscall_trace_lock);
+	return ret;
 }
 
-static struct trace_event syscall_enter_event = {
-	.type	 	= TRACE_SYSCALL_ENTER,
-	.trace		= print_syscall_enter,
-};
+void unreg_event_syscall_exit(void *ptr)
+{
+	int num;
+	char *name;
+
+	name = (char *)ptr;
+	num = syscall_name_to_nr(name);
+	if (num < 0 || num >= NR_syscalls)
+		return;
+	mutex_lock(&syscall_trace_lock);
+	sys_refcount_exit--;
+	clear_bit(num, enabled_exit_syscalls);
+	if (!sys_refcount_exit)
+		unregister_trace_sys_exit(ftrace_syscall_exit);
+	mutex_unlock(&syscall_trace_lock);
+}
 
-static struct trace_event syscall_exit_event = {
-	.type	 	= TRACE_SYSCALL_EXIT,
-	.trace		= print_syscall_exit,
+struct trace_event event_syscall_enter = {
+	.trace			= print_syscall_enter,
 };
 
-static struct tracer syscall_tracer __read_mostly = {
-	.name	     	= "syscall",
-	.init		= init_syscall_tracer,
-	.reset		= reset_syscall_tracer,
-	.flags		= &syscalls_flags,
+struct trace_event event_syscall_exit = {
+	.trace			= print_syscall_exit,
 };
 
-__init int register_ftrace_syscalls(void)
+#ifdef CONFIG_EVENT_PROFILE
+
+static DECLARE_BITMAP(enabled_prof_enter_syscalls, NR_syscalls);
+static DECLARE_BITMAP(enabled_prof_exit_syscalls, NR_syscalls);
+static int sys_prof_refcount_enter;
+static int sys_prof_refcount_exit;
+
+static void prof_syscall_enter(struct pt_regs *regs, long id)
 {
-	int ret;
+	struct syscall_metadata *sys_data;
+	struct syscall_trace_enter *rec;
+	unsigned long flags;
+	char *raw_data;
+	int syscall_nr;
+	int size;
+	int cpu;
 
-	ret = register_ftrace_event(&syscall_enter_event);
-	if (!ret) {
-		printk(KERN_WARNING "event %d failed to register\n",
-		       syscall_enter_event.type);
-		WARN_ON_ONCE(1);
+	syscall_nr = syscall_get_nr(current, regs);
+	if (!test_bit(syscall_nr, enabled_prof_enter_syscalls))
+		return;
+
+	sys_data = syscall_nr_to_meta(syscall_nr);
+	if (!sys_data)
+		return;
+
+	/* get the size after alignment with the u32 buffer size field */
+	size = sizeof(unsigned long) * sys_data->nb_args + sizeof(*rec);
+	size = ALIGN(size + sizeof(u32), sizeof(u64));
+	size -= sizeof(u32);
+
+	if (WARN_ONCE(size > FTRACE_MAX_PROFILE_SIZE,
+		      "profile buffer not large enough"))
+		return;
+
+	/* Protect the per cpu buffer, begin the rcu read side */
+	local_irq_save(flags);
+
+	cpu = smp_processor_id();
+
+	if (in_nmi())
+		raw_data = rcu_dereference(trace_profile_buf_nmi);
+	else
+		raw_data = rcu_dereference(trace_profile_buf);
+
+	if (!raw_data)
+		goto end;
+
+	raw_data = per_cpu_ptr(raw_data, cpu);
+
+	/* zero the dead bytes from align to not leak stack to user */
+	*(u64 *)(&raw_data[size - sizeof(u64)]) = 0ULL;
+
+	rec = (struct syscall_trace_enter *) raw_data;
+	tracing_generic_entry_update(&rec->ent, 0, 0);
+	rec->ent.type = sys_data->enter_id;
+	rec->nr = syscall_nr;
+	syscall_get_arguments(current, regs, 0, sys_data->nb_args,
+			       (unsigned long *)&rec->args);
+	perf_tp_event(sys_data->enter_id, 0, 1, rec, size);
+
+end:
+	local_irq_restore(flags);
+}
+
+int reg_prof_syscall_enter(char *name)
+{
+	int ret = 0;
+	int num;
+
+	num = syscall_name_to_nr(name);
+	if (num < 0 || num >= NR_syscalls)
+		return -ENOSYS;
+
+	mutex_lock(&syscall_trace_lock);
+	if (!sys_prof_refcount_enter)
+		ret = register_trace_sys_enter(prof_syscall_enter);
+	if (ret) {
+		pr_info("event trace: Could not activate"
+				"syscall entry trace point");
+	} else {
+		set_bit(num, enabled_prof_enter_syscalls);
+		sys_prof_refcount_enter++;
 	}
+	mutex_unlock(&syscall_trace_lock);
+	return ret;
+}
 
-	ret = register_ftrace_event(&syscall_exit_event);
-	if (!ret) {
-		printk(KERN_WARNING "event %d failed to register\n",
-		       syscall_exit_event.type);
-		WARN_ON_ONCE(1);
+void unreg_prof_syscall_enter(char *name)
+{
+	int num;
+
+	num = syscall_name_to_nr(name);
+	if (num < 0 || num >= NR_syscalls)
+		return;
+
+	mutex_lock(&syscall_trace_lock);
+	sys_prof_refcount_enter--;
+	clear_bit(num, enabled_prof_enter_syscalls);
+	if (!sys_prof_refcount_enter)
+		unregister_trace_sys_enter(prof_syscall_enter);
+	mutex_unlock(&syscall_trace_lock);
+}
+
+static void prof_syscall_exit(struct pt_regs *regs, long ret)
+{
+	struct syscall_metadata *sys_data;
+	struct syscall_trace_exit *rec;
+	unsigned long flags;
+	int syscall_nr;
+	char *raw_data;
+	int size;
+	int cpu;
+
+	syscall_nr = syscall_get_nr(current, regs);
+	if (!test_bit(syscall_nr, enabled_prof_exit_syscalls))
+		return;
+
+	sys_data = syscall_nr_to_meta(syscall_nr);
+	if (!sys_data)
+		return;
+
+	/* We can probably do that at build time */
+	size = ALIGN(sizeof(*rec) + sizeof(u32), sizeof(u64));
+	size -= sizeof(u32);
+
+	/*
+	 * Impossible, but be paranoid with the future
+	 * How to put this check outside runtime?
+	 */
+	if (WARN_ONCE(size > FTRACE_MAX_PROFILE_SIZE,
+		"exit event has grown above profile buffer size"))
+		return;
+
+	/* Protect the per cpu buffer, begin the rcu read side */
+	local_irq_save(flags);
+	cpu = smp_processor_id();
+
+	if (in_nmi())
+		raw_data = rcu_dereference(trace_profile_buf_nmi);
+	else
+		raw_data = rcu_dereference(trace_profile_buf);
+
+	if (!raw_data)
+		goto end;
+
+	raw_data = per_cpu_ptr(raw_data, cpu);
+
+	/* zero the dead bytes from align to not leak stack to user */
+	*(u64 *)(&raw_data[size - sizeof(u64)]) = 0ULL;
+
+	rec = (struct syscall_trace_exit *)raw_data;
+
+	tracing_generic_entry_update(&rec->ent, 0, 0);
+	rec->ent.type = sys_data->exit_id;
+	rec->nr = syscall_nr;
+	rec->ret = syscall_get_return_value(current, regs);
+
+	perf_tp_event(sys_data->exit_id, 0, 1, rec, size);
+
+end:
+	local_irq_restore(flags);
+}
+
+int reg_prof_syscall_exit(char *name)
+{
+	int ret = 0;
+	int num;
+
+	num = syscall_name_to_nr(name);
+	if (num < 0 || num >= NR_syscalls)
+		return -ENOSYS;
+
+	mutex_lock(&syscall_trace_lock);
+	if (!sys_prof_refcount_exit)
+		ret = register_trace_sys_exit(prof_syscall_exit);
+	if (ret) {
+		pr_info("event trace: Could not activate"
+				"syscall entry trace point");
+	} else {
+		set_bit(num, enabled_prof_exit_syscalls);
+		sys_prof_refcount_exit++;
 	}
+	mutex_unlock(&syscall_trace_lock);
+	return ret;
+}
+
+void unreg_prof_syscall_exit(char *name)
+{
+	int num;
+
+	num = syscall_name_to_nr(name);
+	if (num < 0 || num >= NR_syscalls)
+		return;
 
-	return register_tracer(&syscall_tracer);
+	mutex_lock(&syscall_trace_lock);
+	sys_prof_refcount_exit--;
+	clear_bit(num, enabled_prof_exit_syscalls);
+	if (!sys_prof_refcount_exit)
+		unregister_trace_sys_exit(prof_syscall_exit);
+	mutex_unlock(&syscall_trace_lock);
 }
-device_initcall(register_ftrace_syscalls);
+
+#endif
+
+
diff --git a/kernel/trace/trace_workqueue.c b/kernel/trace/trace_workqueue.c
index 97fcea4acce1..40cafb07dffd 100644
--- a/kernel/trace/trace_workqueue.c
+++ b/kernel/trace/trace_workqueue.c
@@ -9,6 +9,7 @@
 #include <trace/events/workqueue.h>
 #include <linux/list.h>
 #include <linux/percpu.h>
+#include <linux/kref.h>
 #include "trace_stat.h"
 #include "trace.h"
 
@@ -16,6 +17,7 @@
 /* A cpu workqueue thread */
 struct cpu_workqueue_stats {
 	struct list_head            list;
+	struct kref                 kref;
 	int		            cpu;
 	pid_t			    pid;
 /* Can be inserted from interrupt or user context, need to be atomic */
@@ -39,6 +41,11 @@ struct workqueue_global_stats {
 static DEFINE_PER_CPU(struct workqueue_global_stats, all_workqueue_stat);
 #define workqueue_cpu_stat(cpu) (&per_cpu(all_workqueue_stat, cpu))
 
+static void cpu_workqueue_stat_free(struct kref *kref)
+{
+	kfree(container_of(kref, struct cpu_workqueue_stats, kref));
+}
+
 /* Insertion of a work */
 static void
 probe_workqueue_insertion(struct task_struct *wq_thread,
@@ -96,8 +103,8 @@ static void probe_workqueue_creation(struct task_struct *wq_thread, int cpu)
 		return;
 	}
 	INIT_LIST_HEAD(&cws->list);
+	kref_init(&cws->kref);
 	cws->cpu = cpu;
-
 	cws->pid = wq_thread->pid;
 
 	spin_lock_irqsave(&workqueue_cpu_stat(cpu)->lock, flags);
@@ -118,7 +125,7 @@ static void probe_workqueue_destruction(struct task_struct *wq_thread)
 							list) {
 		if (node->pid == wq_thread->pid) {
 			list_del(&node->list);
-			kfree(node);
+			kref_put(&node->kref, cpu_workqueue_stat_free);
 			goto found;
 		}
 	}
@@ -137,9 +144,11 @@ static struct cpu_workqueue_stats *workqueue_stat_start_cpu(int cpu)
 
 	spin_lock_irqsave(&workqueue_cpu_stat(cpu)->lock, flags);
 
-	if (!list_empty(&workqueue_cpu_stat(cpu)->list))
+	if (!list_empty(&workqueue_cpu_stat(cpu)->list)) {
 		ret = list_entry(workqueue_cpu_stat(cpu)->list.next,
 				 struct cpu_workqueue_stats, list);
+		kref_get(&ret->kref);
+	}
 
 	spin_unlock_irqrestore(&workqueue_cpu_stat(cpu)->lock, flags);
 
@@ -162,9 +171,9 @@ static void *workqueue_stat_start(struct tracer_stat *trace)
 static void *workqueue_stat_next(void *prev, int idx)
 {
 	struct cpu_workqueue_stats *prev_cws = prev;
+	struct cpu_workqueue_stats *ret;
 	int cpu = prev_cws->cpu;
 	unsigned long flags;
-	void *ret = NULL;
 
 	spin_lock_irqsave(&workqueue_cpu_stat(cpu)->lock, flags);
 	if (list_is_last(&prev_cws->list, &workqueue_cpu_stat(cpu)->list)) {
@@ -175,11 +184,14 @@ static void *workqueue_stat_next(void *prev, int idx)
 				return NULL;
 		} while (!(ret = workqueue_stat_start_cpu(cpu)));
 		return ret;
+	} else {
+		ret = list_entry(prev_cws->list.next,
+				 struct cpu_workqueue_stats, list);
+		kref_get(&ret->kref);
 	}
 	spin_unlock_irqrestore(&workqueue_cpu_stat(cpu)->lock, flags);
 
-	return list_entry(prev_cws->list.next, struct cpu_workqueue_stats,
-			  list);
+	return ret;
 }
 
 static int workqueue_stat_show(struct seq_file *s, void *p)
@@ -203,6 +215,13 @@ static int workqueue_stat_show(struct seq_file *s, void *p)
 	return 0;
 }
 
+static void workqueue_stat_release(void *stat)
+{
+	struct cpu_workqueue_stats *node = stat;
+
+	kref_put(&node->kref, cpu_workqueue_stat_free);
+}
+
 static int workqueue_stat_headers(struct seq_file *s)
 {
 	seq_printf(s, "# CPU  INSERTED  EXECUTED   NAME\n");
@@ -215,6 +234,7 @@ struct tracer_stat workqueue_stats __read_mostly = {
 	.stat_start = workqueue_stat_start,
 	.stat_next = workqueue_stat_next,
 	.stat_show = workqueue_stat_show,
+	.stat_release = workqueue_stat_release,
 	.stat_headers = workqueue_stat_headers
 };
 
diff --git a/kernel/tracepoint.c b/kernel/tracepoint.c
index 1ef5d3a601c7..cc89be5bc0f8 100644
--- a/kernel/tracepoint.c
+++ b/kernel/tracepoint.c
@@ -24,6 +24,7 @@
 #include <linux/tracepoint.h>
 #include <linux/err.h>
 #include <linux/slab.h>
+#include <linux/sched.h>
 
 extern struct tracepoint __start___tracepoints[];
 extern struct tracepoint __stop___tracepoints[];
@@ -47,7 +48,7 @@ static struct hlist_head tracepoint_table[TRACEPOINT_TABLE_SIZE];
 
 /*
  * Note about RCU :
- * It is used to to delay the free of multiple probes array until a quiescent
+ * It is used to delay the free of multiple probes array until a quiescent
  * state is reached.
  * Tracepoint entries modifications are protected by the tracepoints_mutex.
  */
@@ -242,6 +243,11 @@ static void set_tracepoint(struct tracepoint_entry **entry,
 {
 	WARN_ON(strcmp((*entry)->name, elem->name) != 0);
 
+	if (elem->regfunc && !elem->state && active)
+		elem->regfunc();
+	else if (elem->unregfunc && elem->state && !active)
+		elem->unregfunc();
+
 	/*
 	 * rcu_assign_pointer has a smp_wmb() which makes sure that the new
 	 * probe callbacks array is consistent before setting a pointer to it.
@@ -261,6 +267,9 @@ static void set_tracepoint(struct tracepoint_entry **entry,
  */
 static void disable_tracepoint(struct tracepoint *elem)
 {
+	if (elem->unregfunc && elem->state)
+		elem->unregfunc();
+
 	elem->state = 0;
 	rcu_assign_pointer(elem->funcs, NULL);
 }
@@ -554,9 +563,6 @@ int tracepoint_module_notify(struct notifier_block *self,
 
 	switch (val) {
 	case MODULE_STATE_COMING:
-		tracepoint_update_probe_range(mod->tracepoints,
-			mod->tracepoints + mod->num_tracepoints);
-		break;
 	case MODULE_STATE_GOING:
 		tracepoint_update_probe_range(mod->tracepoints,
 			mod->tracepoints + mod->num_tracepoints);
@@ -577,3 +583,41 @@ static int init_tracepoints(void)
 __initcall(init_tracepoints);
 
 #endif /* CONFIG_MODULES */
+
+#ifdef CONFIG_HAVE_SYSCALL_TRACEPOINTS
+
+/* NB: reg/unreg are called while guarded with the tracepoints_mutex */
+static int sys_tracepoint_refcount;
+
+void syscall_regfunc(void)
+{
+	unsigned long flags;
+	struct task_struct *g, *t;
+
+	if (!sys_tracepoint_refcount) {
+		read_lock_irqsave(&tasklist_lock, flags);
+		do_each_thread(g, t) {
+			/* Skip kernel threads. */
+			if (t->mm)
+				set_tsk_thread_flag(t, TIF_SYSCALL_TRACEPOINT);
+		} while_each_thread(g, t);
+		read_unlock_irqrestore(&tasklist_lock, flags);
+	}
+	sys_tracepoint_refcount++;
+}
+
+void syscall_unregfunc(void)
+{
+	unsigned long flags;
+	struct task_struct *g, *t;
+
+	sys_tracepoint_refcount--;
+	if (!sys_tracepoint_refcount) {
+		read_lock_irqsave(&tasklist_lock, flags);
+		do_each_thread(g, t) {
+			clear_tsk_thread_flag(t, TIF_SYSCALL_TRACEPOINT);
+		} while_each_thread(g, t);
+		read_unlock_irqrestore(&tasklist_lock, flags);
+	}
+}
+#endif
diff --git a/kernel/uid16.c b/kernel/uid16.c
index 0314501688b9..419209893d87 100644
--- a/kernel/uid16.c
+++ b/kernel/uid16.c
@@ -4,7 +4,6 @@
  */
 
 #include <linux/mm.h>
-#include <linux/utsname.h>
 #include <linux/mman.h>
 #include <linux/notifier.h>
 #include <linux/reboot.h>
diff --git a/kernel/user.c b/kernel/user.c
index 2c000e7132ac..46d0165ca70c 100644
--- a/kernel/user.c
+++ b/kernel/user.c
@@ -330,9 +330,9 @@ done:
  */
 static void free_user(struct user_struct *up, unsigned long flags)
 {
-	spin_unlock_irqrestore(&uidhash_lock, flags);
 	INIT_DELAYED_WORK(&up->work, cleanup_user_struct);
 	schedule_delayed_work(&up->work, msecs_to_jiffies(1000));
+	spin_unlock_irqrestore(&uidhash_lock, flags);
 }
 
 #else	/* CONFIG_USER_SCHED && CONFIG_SYSFS */
diff --git a/kernel/utsname_sysctl.c b/kernel/utsname_sysctl.c
index 92359cc747a7..69eae358a726 100644
--- a/kernel/utsname_sysctl.c
+++ b/kernel/utsname_sysctl.c
@@ -42,14 +42,14 @@ static void put_uts(ctl_table *table, int write, void *which)
  *	Special case of dostring for the UTS structure. This has locks
  *	to observe. Should this be in kernel/sys.c ????
  */
-static int proc_do_uts_string(ctl_table *table, int write, struct file *filp,
+static int proc_do_uts_string(ctl_table *table, int write,
 		  void __user *buffer, size_t *lenp, loff_t *ppos)
 {
 	struct ctl_table uts_table;
 	int r;
 	memcpy(&uts_table, table, sizeof(uts_table));
 	uts_table.data = get_uts(table, write);
-	r = proc_dostring(&uts_table,write,filp,buffer,lenp, ppos);
+	r = proc_dostring(&uts_table,write,buffer,lenp, ppos);
 	put_uts(table, write, uts_table.data);
 	return r;
 }
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 0668795d8818..67e526b6ae81 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -317,8 +317,6 @@ static int worker_thread(void *__cwq)
 	if (cwq->wq->freezeable)
 		set_freezable();
 
-	set_user_nice(current, -5);
-
 	for (;;) {
 		prepare_to_wait(&cwq->more_work, &wait, TASK_INTERRUPTIBLE);
 		if (!freezing(current) &&
@@ -600,7 +598,12 @@ static struct workqueue_struct *keventd_wq __read_mostly;
  * schedule_work - put work task in global workqueue
  * @work: job to be done
  *
- * This puts a job in the kernel-global workqueue.
+ * Returns zero if @work was already on the kernel-global workqueue and
+ * non-zero otherwise.
+ *
+ * This puts a job in the kernel-global workqueue if it was not already
+ * queued and leaves it in the same position on the kernel-global
+ * workqueue otherwise.
  */
 int schedule_work(struct work_struct *work)
 {
@@ -637,6 +640,24 @@ int schedule_delayed_work(struct delayed_work *dwork,
 EXPORT_SYMBOL(schedule_delayed_work);
 
 /**
+ * flush_delayed_work - block until a dwork_struct's callback has terminated
+ * @dwork: the delayed work which is to be flushed
+ *
+ * Any timeout is cancelled, and any pending work is run immediately.
+ */
+void flush_delayed_work(struct delayed_work *dwork)
+{
+	if (del_timer_sync(&dwork->timer)) {
+		struct cpu_workqueue_struct *cwq;
+		cwq = wq_per_cpu(keventd_wq, get_cpu());
+		__queue_work(cwq, &dwork->work);
+		put_cpu();
+	}
+	flush_work(&dwork->work);
+}
+EXPORT_SYMBOL(flush_delayed_work);
+
+/**
  * schedule_delayed_work_on - queue work in global workqueue on CPU after delay
  * @cpu: cpu to use
  * @dwork: job to be done
@@ -664,6 +685,7 @@ EXPORT_SYMBOL(schedule_delayed_work_on);
 int schedule_on_each_cpu(work_func_t func)
 {
 	int cpu;
+	int orig = -1;
 	struct work_struct *works;
 
 	works = alloc_percpu(struct work_struct);
@@ -671,14 +693,28 @@ int schedule_on_each_cpu(work_func_t func)
 		return -ENOMEM;
 
 	get_online_cpus();
+
+	/*
+	 * When running in keventd don't schedule a work item on
+	 * itself.  Can just call directly because the work queue is
+	 * already bound.  This also is faster.
+	 */
+	if (current_is_keventd())
+		orig = raw_smp_processor_id();
+
 	for_each_online_cpu(cpu) {
 		struct work_struct *work = per_cpu_ptr(works, cpu);
 
 		INIT_WORK(work, func);
-		schedule_work_on(cpu, work);
+		if (cpu != orig)
+			schedule_work_on(cpu, work);
 	}
+	if (orig >= 0)
+		func(per_cpu_ptr(works, orig));
+
 	for_each_online_cpu(cpu)
 		flush_work(per_cpu_ptr(works, cpu));
+
 	put_online_cpus();
 	free_percpu(works);
 	return 0;