Merge commit 'v2.6.32-rc6' into perf/core

Conflicts:
	tools/perf/Makefile

Merge reason: Resolve the conflict, merge to upstream and merge in
              perf fixes so we can add a dependent patch.

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

21 files changed, 266 insertions, 136 deletions

diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index ca83b73fba19..0249f4be9b5c 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -1710,14 +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);
@@ -1753,8 +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:
diff --git a/kernel/exit.c b/kernel/exit.c
index e61891f80123..f7864ac2ecc1 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -359,10 +359,8 @@ void __set_special_pids(struct pid *pid)
 {
 	struct task_struct *curr = current->group_leader;
 
-	if (task_session(curr) != pid) {
+	if (task_session(curr) != pid)
 		change_pid(curr, PIDTYPE_SID, pid);
-		proc_sid_connector(curr);
-	}
 
 	if (task_pgrp(curr) != pid)
 		change_pid(curr, PIDTYPE_PGID, pid);
diff --git a/kernel/fork.c b/kernel/fork.c
index 4c20fff8c13a..166b8c49257c 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -91,7 +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;
diff --git a/kernel/futex.c b/kernel/futex.c
index 4949d336d88d..fb65e822fc41 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -150,7 +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);
 }
@@ -1028,7 +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;
 
@@ -1226,6 +1226,7 @@ retry_private:
 		 */
 		if (ret == 1) {
 			WARN_ON(pi_state);
+			drop_count++;
 			task_count++;
 			ret = get_futex_value_locked(&curval2, uaddr2);
 			if (!ret)
@@ -1304,6 +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 */
@@ -1791,6 +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)
@@ -1808,9 +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;
@@ -2118,9 +2126,11 @@ int handle_early_requeue_pi_wakeup(struct futex_hash_bucket *hb,
 		 */
 		plist_del(&q->list, &q->list.plist);
 
+		/* Handle spurious wakeups gracefully */
+		ret = -EWOULDBLOCK;
 		if (timeout && !timeout->task)
 			ret = -ETIMEDOUT;
-		else
+		else if (signal_pending(current))
 			ret = -ERESTARTNOINTR;
 	}
 	return ret;
diff --git a/kernel/params.c b/kernel/params.c
index 9da58eabdcb2..d656c276508d 100644
--- a/kernel/params.c
+++ b/kernel/params.c
@@ -218,15 +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;
@@ -304,6 +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;
@@ -313,6 +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) {
@@ -358,7 +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)
@@ -605,11 +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_event.c b/kernel/perf_event.c
index 9ecaa45ab6b2..a69d4ed6a666 100644
--- a/kernel/perf_event.c
+++ b/kernel/perf_event.c
@@ -3976,8 +3976,9 @@ static enum hrtimer_restart perf_swevent_hrtimer(struct hrtimer *hrtimer)
 		regs = task_pt_regs(current);
 
 	if (regs) {
-		if (perf_event_overflow(event, 0, &data, regs))
-			ret = HRTIMER_NORESTART;
+		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);
@@ -3986,6 +3987,42 @@ static enum hrtimer_restart perf_swevent_hrtimer(struct hrtimer *hrtimer)
 	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
  */
@@ -4008,22 +4045,14 @@ static int cpu_clock_perf_event_enable(struct perf_event *event)
 	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_swevent_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);
-	}
+	perf_swevent_start_hrtimer(event);
 
 	return 0;
 }
 
 static void cpu_clock_perf_event_disable(struct perf_event *event)
 {
-	if (event->hw.sample_period)
-		hrtimer_cancel(&event->hw.hrtimer);
+	perf_swevent_cancel_hrtimer(event);
 	cpu_clock_perf_event_update(event);
 }
 
@@ -4060,22 +4089,15 @@ static int task_clock_perf_event_enable(struct perf_event *event)
 	now = event->ctx->time;
 
 	atomic64_set(&hwc->prev_count, now);
-	hrtimer_init(&hwc->hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
-	hwc->hrtimer.function = perf_swevent_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);
-	}
+
+	perf_swevent_start_hrtimer(event);
 
 	return 0;
 }
 
 static void task_clock_perf_event_disable(struct perf_event *event)
 {
-	if (event->hw.sample_period)
-		hrtimer_cancel(&event->hw.hrtimer);
+	perf_swevent_cancel_hrtimer(event);
 	task_clock_perf_event_update(event, event->ctx->time);
 
 }
diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c
index 04b3a83d686f..04a9e90d248f 100644
--- a/kernel/power/hibernate.c
+++ b/kernel/power/hibernate.c
@@ -693,21 +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();
@@ -719,6 +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);
 
@@ -737,6 +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/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 b101cdc4df3f..890f6b11b1d3 100644
--- a/kernel/power/swap.c
+++ b/kernel/power/swap.c
@@ -314,7 +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;
@@ -329,26 +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;
 }
 
 /**
@@ -536,7 +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;
 }
@@ -572,8 +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
@@ -596,7 +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);
@@ -604,8 +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/rcutree.c b/kernel/rcutree.c
index 705f02ac7433..0536125b0497 100644
--- a/kernel/rcutree.c
+++ b/kernel/rcutree.c
@@ -913,7 +913,20 @@ static void __rcu_offline_cpu(int cpu, struct rcu_state *rsp)
 			spin_unlock(&rnp->lock); /* irqs remain disabled. */
 			break;
 		}
-		rcu_preempt_offline_tasks(rsp, rnp, rdp);
+
+		/*
+		 * 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 remain disabled. */
 		rnp = rnp->parent;
@@ -958,7 +971,7 @@ 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;
@@ -1011,6 +1024,13 @@ 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. */
@@ -1224,7 +1244,7 @@ __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);
 }
 
 /*
@@ -1288,10 +1308,20 @@ __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);
@@ -1523,6 +1553,8 @@ rcu_init_percpu_data(int cpu, struct rcu_state *rsp, int preemptable)
 	rdp->beenonline = 1;	 /* We have now been online. */
 	rdp->preemptable = preemptable;
 	rdp->passed_quiesc_completed = lastcomp - 1;
+	rdp->qlen_last_fqs_check = 0;
+	rdp->n_force_qs_snap = rsp->n_force_qs;
 	rdp->blimit = blimit;
 	spin_unlock(&rnp->lock);		/* irqs remain disabled. */
 
diff --git a/kernel/rcutree.h b/kernel/rcutree.h
index b40ac5706040..1823c6e20609 100644
--- a/kernel/rcutree.h
+++ b/kernel/rcutree.h
@@ -167,6 +167,10 @@ struct rcu_data {
 	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
@@ -302,9 +306,9 @@ 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 void rcu_preempt_offline_tasks(struct rcu_state *rsp,
-				      struct rcu_node *rnp,
-				      struct rcu_data *rdp);
+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);
diff --git a/kernel/rcutree_plugin.h b/kernel/rcutree_plugin.h
index c0cb783aa16a..ef2a58c2b9d5 100644
--- a/kernel/rcutree_plugin.h
+++ b/kernel/rcutree_plugin.h
@@ -304,21 +304,25 @@ static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp)
  * 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 void rcu_preempt_offline_tasks(struct rcu_state *rsp,
-				      struct rcu_node *rnp,
-				      struct rcu_data *rdp)
+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;  /* Shouldn't happen: at least one CPU online. */
+		return 0;  /* Shouldn't happen: at least one CPU online. */
 	}
 	WARN_ON_ONCE(rnp != rdp->mynode &&
 		     (!list_empty(&rnp->blocked_tasks[0]) ||
@@ -342,6 +346,8 @@ static void rcu_preempt_offline_tasks(struct rcu_state *rsp,
 			spin_unlock(&rnp_root->lock); /* irqs remain disabled */
 		}
 	}
+
+	return retval;
 }
 
 /*
@@ -393,6 +399,17 @@ void call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu))
 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.
  */
@@ -521,12 +538,15 @@ static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp)
 
 /*
  * Because preemptable RCU does not exist, it never needs to migrate
- * tasks that were blocked within RCU read-side critical sections.
+ * 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 void rcu_preempt_offline_tasks(struct rcu_state *rsp,
-				      struct rcu_node *rnp,
-				      struct rcu_data *rdp)
+static int rcu_preempt_offline_tasks(struct rcu_state *rsp,
+				     struct rcu_node *rnp,
+				     struct rcu_data *rdp)
 {
+	return 0;
 }
 
 /*
@@ -565,6 +585,16 @@ void call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu))
 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)
diff --git a/kernel/sched.c b/kernel/sched.c
index e88689522e66..a455dca884a6 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -1564,11 +1564,7 @@ static unsigned long cpu_avg_load_per_task(int cpu)
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
 
-struct update_shares_data {
-	unsigned long rq_weight[NR_CPUS];
-};
-
-static DEFINE_PER_CPU(struct update_shares_data, update_shares_data);
+static __read_mostly unsigned long *update_shares_data;
 
 static void __set_se_shares(struct sched_entity *se, unsigned long shares);
 
@@ -1578,12 +1574,12 @@ static void __set_se_shares(struct sched_entity *se, unsigned long shares);
 static void update_group_shares_cpu(struct task_group *tg, int cpu,
 				    unsigned long sd_shares,
 				    unsigned long sd_rq_weight,
-				    struct update_shares_data *usd)
+				    unsigned long *usd_rq_weight)
 {
 	unsigned long shares, rq_weight;
 	int boost = 0;
 
-	rq_weight = usd->rq_weight[cpu];
+	rq_weight = usd_rq_weight[cpu];
 	if (!rq_weight) {
 		boost = 1;
 		rq_weight = NICE_0_LOAD;
@@ -1618,7 +1614,7 @@ static void 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, shares = 0;
-	struct update_shares_data *usd;
+	unsigned long *usd_rq_weight;
 	struct sched_domain *sd = data;
 	unsigned long flags;
 	int i;
@@ -1627,11 +1623,11 @@ static int tg_shares_up(struct task_group *tg, void *data)
 		return 0;
 
 	local_irq_save(flags);
-	usd = &__get_cpu_var(update_shares_data);
+	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;
+		usd_rq_weight[i] = weight;
 
 		/*
 		 * If there are currently no tasks on the cpu pretend there
@@ -1652,7 +1648,7 @@ 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, usd);
+		update_group_shares_cpu(tg, i, shares, rq_weight, usd_rq_weight);
 
 	local_irq_restore(flags);
 
@@ -9407,6 +9403,10 @@ 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;
 
diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index 4e777b47eeda..c32c3e643daa 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -861,12 +861,21 @@ 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 *buddy;
 
-	if (cfs_rq->next && wakeup_preempt_entity(cfs_rq->next, se) < 1)
-		return cfs_rq->next;
+	if (cfs_rq->next) {
+		buddy = cfs_rq->next;
+		cfs_rq->next = NULL;
+		if (wakeup_preempt_entity(buddy, se) < 1)
+			return buddy;
+	}
 
-	if (cfs_rq->last && wakeup_preempt_entity(cfs_rq->last, se) < 1)
-		return cfs_rq->last;
+	if (cfs_rq->last) {
+		buddy = cfs_rq->last;
+		cfs_rq->last = NULL;
+		if (wakeup_preempt_entity(buddy, se) < 1)
+			return buddy;
+	}
 
 	return se;
 }
@@ -1654,16 +1663,6 @@ 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.
-		 *
-		 * If se was not a buddy, clear the buddies because neither
-		 * was elegible to run, let them earn it again.
-		 *
-		 * IOW. unconditionally clear buddies.
-		 */
-		__clear_buddies(cfs_rq, NULL);
 		set_next_entity(cfs_rq, se);
 		cfs_rq = group_cfs_rq(se);
 	} while (cfs_rq);
diff --git a/kernel/sys.c b/kernel/sys.c
index 255475d163e0..ce17760d9c51 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -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;
 }
 
@@ -1546,24 +1548,37 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
 			if (arg4 | arg5)
 				return -EINVAL;
 			switch (arg2) {
-			case 0:
+			case PR_MCE_KILL_CLEAR:
 				if (arg3 != 0)
 					return -EINVAL;
 				current->flags &= ~PF_MCE_PROCESS;
 				break;
-			case 1:
+			case PR_MCE_KILL_SET:
 				current->flags |= PF_MCE_PROCESS;
-				if (arg3 != 0)
+				if (arg3 == PR_MCE_KILL_EARLY)
 					current->flags |= PF_MCE_EARLY;
-				else
+				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/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/trace/ftrace.c b/kernel/trace/ftrace.c
index b10c0d90a6ff..1ed514fe3a30 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -751,7 +751,7 @@ ftrace_profile_write(struct file *filp, const char __user *ubuf,
  out:
 	mutex_unlock(&ftrace_profile_lock);
 
-	filp->f_pos += cnt;
+	*ppos += cnt;
 
 	return cnt;
 }
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index e43c928356ee..63446f12e470 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -486,7 +486,7 @@ struct ring_buffer_iter {
 /* 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;
@@ -497,7 +497,7 @@ 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;
@@ -602,7 +602,7 @@ static struct list_head *rb_list_head(struct list_head *list)
 }
 
 /*
- * rb_is_head_page - test if the give page is the head page
+ * 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
@@ -1871,7 +1871,7 @@ rb_move_tail(struct ring_buffer_per_cpu *cpu_buffer,
 		 * Nested commits always have zero deltas, so
 		 * just reread the time stamp
 		 */
-		*ts = rb_time_stamp(buffer, cpu_buffer->cpu);
+		*ts = rb_time_stamp(buffer);
 		next_page->page->time_stamp = *ts;
 	}
 
@@ -2114,7 +2114,7 @@ rb_reserve_next_event(struct ring_buffer *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.
@@ -2684,7 +2684,7 @@ 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
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 026e715a0c7a..9d3067a62d43 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -2440,7 +2440,7 @@ tracing_trace_options_write(struct file *filp, const char __user *ubuf,
 			return ret;
 	}
 
-	filp->f_pos += cnt;
+	*ppos += cnt;
 
 	return cnt;
 }
@@ -2582,7 +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;
 }
@@ -2764,7 +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;
 }
@@ -3299,7 +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)
diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c
index ed17565826b0..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);
 
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index ccefe574dcf7..12328147132c 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -647,7 +647,7 @@ EXPORT_SYMBOL(schedule_delayed_work);
  */
 void flush_delayed_work(struct delayed_work *dwork)
 {
-	if (del_timer(&dwork->timer)) {
+	if (del_timer_sync(&dwork->timer)) {
 		struct cpu_workqueue_struct *cwq;
 		cwq = wq_per_cpu(keventd_wq, get_cpu());
 		__queue_work(cwq, &dwork->work);
@@ -685,21 +685,38 @@ 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);
 	if (!works)
 		return -ENOMEM;
 
+	/*
+	 * 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.
+	 * Make this a generic parameter for other workqueues?
+	 */
+	if (current_is_keventd()) {
+		orig = raw_smp_processor_id();
+		INIT_WORK(per_cpu_ptr(works, orig), func);
+		func(per_cpu_ptr(works, orig));
+	}
+
 	get_online_cpus();
 	for_each_online_cpu(cpu) {
 		struct work_struct *work = per_cpu_ptr(works, cpu);
 
+		if (cpu == orig)
+			continue;
 		INIT_WORK(work, func);
 		schedule_work_on(cpu, work);
 	}
-	for_each_online_cpu(cpu)
-		flush_work(per_cpu_ptr(works, cpu));
+	for_each_online_cpu(cpu) {
+		if (cpu != orig)
+			flush_work(per_cpu_ptr(works, cpu));
+	}
 	put_online_cpus();
 	free_percpu(works);
 	return 0;