Merge branch 'timers/urgent' into timers/core

Reason: Update to upstream changes to avoid further conflicts.
Fixup a trivial merge conflict in kernel/time/tick-sched.c

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

22 files changed, 1061 insertions, 394 deletions

diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 72fcd3069a9..b303dfc7dce 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -255,12 +255,17 @@ int cgroup_lock_is_held(void)
 
 EXPORT_SYMBOL_GPL(cgroup_lock_is_held);
 
+static int css_unbias_refcnt(int refcnt)
+{
+	return refcnt >= 0 ? refcnt : refcnt - CSS_DEACT_BIAS;
+}
+
 /* the current nr of refs, always >= 0 whether @css is deactivated or not */
 static int css_refcnt(struct cgroup_subsys_state *css)
 {
 	int v = atomic_read(&css->refcnt);
 
-	return v >= 0 ? v : v - CSS_DEACT_BIAS;
+	return css_unbias_refcnt(v);
 }
 
 /* convenient tests for these bits */
@@ -896,13 +901,10 @@ static void cgroup_diput(struct dentry *dentry, struct inode *inode)
 		mutex_unlock(&cgroup_mutex);
 
 		/*
-		 * We want to drop the active superblock reference from the
-		 * cgroup creation after all the dentry refs are gone -
-		 * kill_sb gets mighty unhappy otherwise.  Mark
-		 * dentry->d_fsdata with cgroup_diput() to tell
-		 * cgroup_d_release() to call deactivate_super().
+		 * Drop the active superblock reference that we took when we
+		 * created the cgroup
 		 */
-		dentry->d_fsdata = cgroup_diput;
+		deactivate_super(cgrp->root->sb);
 
 		/*
 		 * if we're getting rid of the cgroup, refcount should ensure
@@ -928,13 +930,6 @@ static int cgroup_delete(const struct dentry *d)
 	return 1;
 }
 
-static void cgroup_d_release(struct dentry *dentry)
-{
-	/* did cgroup_diput() tell me to deactivate super? */
-	if (dentry->d_fsdata == cgroup_diput)
-		deactivate_super(dentry->d_sb);
-}
-
 static void remove_dir(struct dentry *d)
 {
 	struct dentry *parent = dget(d->d_parent);
@@ -1542,7 +1537,6 @@ static int cgroup_get_rootdir(struct super_block *sb)
 	static const struct dentry_operations cgroup_dops = {
 		.d_iput = cgroup_diput,
 		.d_delete = cgroup_delete,
-		.d_release = cgroup_d_release,
 	};
 
 	struct inode *inode =
@@ -3889,8 +3883,12 @@ static void css_dput_fn(struct work_struct *work)
 {
 	struct cgroup_subsys_state *css =
 		container_of(work, struct cgroup_subsys_state, dput_work);
+	struct dentry *dentry = css->cgroup->dentry;
+	struct super_block *sb = dentry->d_sb;
 
-	dput(css->cgroup->dentry);
+	atomic_inc(&sb->s_active);
+	dput(dentry);
+	deactivate_super(sb);
 }
 
 static void init_cgroup_css(struct cgroup_subsys_state *css,
@@ -4982,10 +4980,12 @@ EXPORT_SYMBOL_GPL(__css_tryget);
 void __css_put(struct cgroup_subsys_state *css)
 {
 	struct cgroup *cgrp = css->cgroup;
+	int v;
 
 	rcu_read_lock();
-	atomic_dec(&css->refcnt);
-	switch (css_refcnt(css)) {
+	v = css_unbias_refcnt(atomic_dec_return(&css->refcnt));
+
+	switch (v) {
 	case 1:
 		if (notify_on_release(cgrp)) {
 			set_bit(CGRP_RELEASABLE, &cgrp->flags);
diff --git a/kernel/events/core.c b/kernel/events/core.c
index f85c0154b33..d7d71d6ec97 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -253,9 +253,9 @@ perf_cgroup_match(struct perf_event *event)
 	return !event->cgrp || event->cgrp == cpuctx->cgrp;
 }
 
-static inline void perf_get_cgroup(struct perf_event *event)
+static inline bool perf_tryget_cgroup(struct perf_event *event)
 {
-	css_get(&event->cgrp->css);
+	return css_tryget(&event->cgrp->css);
 }
 
 static inline void perf_put_cgroup(struct perf_event *event)
@@ -484,7 +484,11 @@ static inline int perf_cgroup_connect(int fd, struct perf_event *event,
 	event->cgrp = cgrp;
 
 	/* must be done before we fput() the file */
-	perf_get_cgroup(event);
+	if (!perf_tryget_cgroup(event)) {
+		event->cgrp = NULL;
+		ret = -ENOENT;
+		goto out;
+	}
 
 	/*
 	 * all events in a group must monitor
diff --git a/kernel/exit.c b/kernel/exit.c
index 34867cc5b42..2f59cc33451 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -72,6 +72,18 @@ static void __unhash_process(struct task_struct *p, bool group_dead)
 		list_del_rcu(&p->tasks);
 		list_del_init(&p->sibling);
 		__this_cpu_dec(process_counts);
+		/*
+		 * If we are the last child process in a pid namespace to be
+		 * reaped, notify the reaper sleeping zap_pid_ns_processes().
+		 */
+		if (IS_ENABLED(CONFIG_PID_NS)) {
+			struct task_struct *parent = p->real_parent;
+
+			if ((task_active_pid_ns(parent)->child_reaper == parent) &&
+			    list_empty(&parent->children) &&
+			    (parent->flags & PF_EXITING))
+				wake_up_process(parent);
+		}
 	}
 	list_del_rcu(&p->thread_group);
 }
@@ -643,6 +655,7 @@ static void exit_mm(struct task_struct * tsk)
 	mm_release(tsk, mm);
 	if (!mm)
 		return;
+	sync_mm_rss(mm);
 	/*
 	 * Serialize with any possible pending coredump.
 	 * We must hold mmap_sem around checking core_state
@@ -719,12 +732,6 @@ static struct task_struct *find_new_reaper(struct task_struct *father)
 
 		zap_pid_ns_processes(pid_ns);
 		write_lock_irq(&tasklist_lock);
-		/*
-		 * We can not clear ->child_reaper or leave it alone.
-		 * There may by stealth EXIT_DEAD tasks on ->children,
-		 * forget_original_parent() must move them somewhere.
-		 */
-		pid_ns->child_reaper = init_pid_ns.child_reaper;
 	} else if (father->signal->has_child_subreaper) {
 		struct task_struct *reaper;
 
diff --git a/kernel/fork.c b/kernel/fork.c
index ab5211b9e62..f00e319d837 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -304,12 +304,17 @@ static struct task_struct *dup_task_struct(struct task_struct *orig)
 	}
 
 	err = arch_dup_task_struct(tsk, orig);
-	if (err)
-		goto out;
 
+	/*
+	 * We defer looking at err, because we will need this setup
+	 * for the clean up path to work correctly.
+	 */
 	tsk->stack = ti;
-
 	setup_thread_stack(tsk, orig);
+
+	if (err)
+		goto out;
+
 	clear_user_return_notifier(tsk);
 	clear_tsk_need_resched(tsk);
 	stackend = end_of_stack(tsk);
diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c
index ae34bf51682..6db7a5ed52b 100644
--- a/kernel/hrtimer.c
+++ b/kernel/hrtimer.c
@@ -657,6 +657,14 @@ static inline int hrtimer_enqueue_reprogram(struct hrtimer *timer,
 	return 0;
 }
 
+static inline ktime_t hrtimer_update_base(struct hrtimer_cpu_base *base)
+{
+	ktime_t *offs_real = &base->clock_base[HRTIMER_BASE_REALTIME].offset;
+	ktime_t *offs_boot = &base->clock_base[HRTIMER_BASE_BOOTTIME].offset;
+
+	return ktime_get_update_offsets(offs_real, offs_boot);
+}
+
 /*
  * Retrigger next event is called after clock was set
  *
@@ -665,22 +673,12 @@ static inline int hrtimer_enqueue_reprogram(struct hrtimer *timer,
 static void retrigger_next_event(void *arg)
 {
 	struct hrtimer_cpu_base *base = &__get_cpu_var(hrtimer_bases);
-	struct timespec realtime_offset, xtim, wtm, sleep;
 
 	if (!hrtimer_hres_active())
 		return;
 
-	/* Optimized out for !HIGH_RES */
-	get_xtime_and_monotonic_and_sleep_offset(&xtim, &wtm, &sleep);
-	set_normalized_timespec(&realtime_offset, -wtm.tv_sec, -wtm.tv_nsec);
-
-	/* Adjust CLOCK_REALTIME offset */
 	raw_spin_lock(&base->lock);
-	base->clock_base[HRTIMER_BASE_REALTIME].offset =
-		timespec_to_ktime(realtime_offset);
-	base->clock_base[HRTIMER_BASE_BOOTTIME].offset =
-		timespec_to_ktime(sleep);
-
+	hrtimer_update_base(base);
 	hrtimer_force_reprogram(base, 0);
 	raw_spin_unlock(&base->lock);
 }
@@ -710,13 +708,25 @@ static int hrtimer_switch_to_hres(void)
 		base->clock_base[i].resolution = KTIME_HIGH_RES;
 
 	tick_setup_sched_timer();
-
 	/* "Retrigger" the interrupt to get things going */
 	retrigger_next_event(NULL);
 	local_irq_restore(flags);
 	return 1;
 }
 
+/*
+ * Called from timekeeping code to reprogramm the hrtimer interrupt
+ * device. If called from the timer interrupt context we defer it to
+ * softirq context.
+ */
+void clock_was_set_delayed(void)
+{
+	struct hrtimer_cpu_base *cpu_base = &__get_cpu_var(hrtimer_bases);
+
+	cpu_base->clock_was_set = 1;
+	__raise_softirq_irqoff(HRTIMER_SOFTIRQ);
+}
+
 #else
 
 static inline int hrtimer_hres_active(void) { return 0; }
@@ -1250,11 +1260,10 @@ void hrtimer_interrupt(struct clock_event_device *dev)
 	cpu_base->nr_events++;
 	dev->next_event.tv64 = KTIME_MAX;
 
-	entry_time = now = ktime_get();
+	raw_spin_lock(&cpu_base->lock);
+	entry_time = now = hrtimer_update_base(cpu_base);
 retry:
 	expires_next.tv64 = KTIME_MAX;
-
-	raw_spin_lock(&cpu_base->lock);
 	/*
 	 * We set expires_next to KTIME_MAX here with cpu_base->lock
 	 * held to prevent that a timer is enqueued in our queue via
@@ -1330,8 +1339,12 @@ retry:
 	 * We need to prevent that we loop forever in the hrtimer
 	 * interrupt routine. We give it 3 attempts to avoid
 	 * overreacting on some spurious event.
+	 *
+	 * Acquire base lock for updating the offsets and retrieving
+	 * the current time.
 	 */
-	now = ktime_get();
+	raw_spin_lock(&cpu_base->lock);
+	now = hrtimer_update_base(cpu_base);
 	cpu_base->nr_retries++;
 	if (++retries < 3)
 		goto retry;
@@ -1343,6 +1356,7 @@ retry:
 	 */
 	cpu_base->nr_hangs++;
 	cpu_base->hang_detected = 1;
+	raw_spin_unlock(&cpu_base->lock);
 	delta = ktime_sub(now, entry_time);
 	if (delta.tv64 > cpu_base->max_hang_time.tv64)
 		cpu_base->max_hang_time = delta;
@@ -1395,6 +1409,13 @@ void hrtimer_peek_ahead_timers(void)
 
 static void run_hrtimer_softirq(struct softirq_action *h)
 {
+	struct hrtimer_cpu_base *cpu_base = &__get_cpu_var(hrtimer_bases);
+
+	if (cpu_base->clock_was_set) {
+		cpu_base->clock_was_set = 0;
+		clock_was_set();
+	}
+
 	hrtimer_peek_ahead_timers();
 }
 
diff --git a/kernel/panic.c b/kernel/panic.c
index 8ed89a175d7..d2a5f4ecc6d 100644
--- a/kernel/panic.c
+++ b/kernel/panic.c
@@ -27,7 +27,7 @@
 #define PANIC_TIMER_STEP 100
 #define PANIC_BLINK_SPD 18
 
-int panic_on_oops;
+int panic_on_oops = CONFIG_PANIC_ON_OOPS_VALUE;
 static unsigned long tainted_mask;
 static int pause_on_oops;
 static int pause_on_oops_flag;
@@ -108,8 +108,6 @@ void panic(const char *fmt, ...)
 	 */
 	crash_kexec(NULL);
 
-	kmsg_dump(KMSG_DUMP_PANIC);
-
 	/*
 	 * Note smp_send_stop is the usual smp shutdown function, which
 	 * unfortunately means it may not be hardened to work in a panic
@@ -117,6 +115,8 @@ void panic(const char *fmt, ...)
 	 */
 	smp_send_stop();
 
+	kmsg_dump(KMSG_DUMP_PANIC);
+
 	atomic_notifier_call_chain(&panic_notifier_list, 0, buf);
 
 	bust_spinlocks(0);
diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c
index 16b20e38c4a..b3c7fd55425 100644
--- a/kernel/pid_namespace.c
+++ b/kernel/pid_namespace.c
@@ -184,11 +184,31 @@ void zap_pid_ns_processes(struct pid_namespace *pid_ns)
 	}
 	read_unlock(&tasklist_lock);
 
+	/* Firstly reap the EXIT_ZOMBIE children we may have. */
 	do {
 		clear_thread_flag(TIF_SIGPENDING);
 		rc = sys_wait4(-1, NULL, __WALL, NULL);
 	} while (rc != -ECHILD);
 
+	/*
+	 * sys_wait4() above can't reap the TASK_DEAD children.
+	 * Make sure they all go away, see __unhash_process().
+	 */
+	for (;;) {
+		bool need_wait = false;
+
+		read_lock(&tasklist_lock);
+		if (!list_empty(&current->children)) {
+			__set_current_state(TASK_UNINTERRUPTIBLE);
+			need_wait = true;
+		}
+		read_unlock(&tasklist_lock);
+
+		if (!need_wait)
+			break;
+		schedule();
+	}
+
 	if (pid_ns->reboot)
 		current->signal->group_exit_code = pid_ns->reboot;
 
diff --git a/kernel/printk.c b/kernel/printk.c
index 32462d2b364..177fa49357a 100644
--- a/kernel/printk.c
+++ b/kernel/printk.c
@@ -193,12 +193,21 @@ static int console_may_schedule;
  * separated by ',', and find the message after the ';' character.
  */
 
+enum log_flags {
+	LOG_NOCONS	= 1,	/* already flushed, do not print to console */
+	LOG_NEWLINE	= 2,	/* text ended with a newline */
+	LOG_PREFIX	= 4,	/* text started with a prefix */
+	LOG_CONT	= 8,	/* text is a fragment of a continuation line */
+};
+
 struct log {
 	u64 ts_nsec;		/* timestamp in nanoseconds */
 	u16 len;		/* length of entire record */
 	u16 text_len;		/* length of text buffer */
 	u16 dict_len;		/* length of dictionary buffer */
-	u16 level;		/* syslog level + facility */
+	u8 facility;		/* syslog facility */
+	u8 flags:5;		/* internal record flags */
+	u8 level:3;		/* syslog level */
 };
 
 /*
@@ -210,6 +219,8 @@ static DEFINE_RAW_SPINLOCK(logbuf_lock);
 /* the next printk record to read by syslog(READ) or /proc/kmsg */
 static u64 syslog_seq;
 static u32 syslog_idx;
+static enum log_flags syslog_prev;
+static size_t syslog_partial;
 
 /* index and sequence number of the first record stored in the buffer */
 static u64 log_first_seq;
@@ -227,10 +238,10 @@ static u32 clear_idx;
 #define LOG_LINE_MAX 1024
 
 /* record buffer */
-#if !defined(CONFIG_64BIT) || defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS)
+#if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS)
 #define LOG_ALIGN 4
 #else
-#define LOG_ALIGN 8
+#define LOG_ALIGN __alignof__(struct log)
 #endif
 #define __LOG_BUF_LEN (1 << CONFIG_LOG_BUF_SHIFT)
 static char __log_buf[__LOG_BUF_LEN] __aligned(LOG_ALIGN);
@@ -286,6 +297,7 @@ static u32 log_next(u32 idx)
 
 /* insert record into the buffer, discard old ones, update heads */
 static void log_store(int facility, int level,
+		      enum log_flags flags, u64 ts_nsec,
 		      const char *dict, u16 dict_len,
 		      const char *text, u16 text_len)
 {
@@ -329,8 +341,13 @@ static void log_store(int facility, int level,
 	msg->text_len = text_len;
 	memcpy(log_dict(msg), dict, dict_len);
 	msg->dict_len = dict_len;
-	msg->level = (facility << 3) | (level & 7);
-	msg->ts_nsec = local_clock();
+	msg->facility = facility;
+	msg->level = level & 7;
+	msg->flags = flags & 0x1f;
+	if (ts_nsec > 0)
+		msg->ts_nsec = ts_nsec;
+	else
+		msg->ts_nsec = local_clock();
 	memset(log_dict(msg) + dict_len, 0, pad_len);
 	msg->len = sizeof(struct log) + text_len + dict_len + pad_len;
 
@@ -414,21 +431,23 @@ static ssize_t devkmsg_read(struct file *file, char __user *buf,
 	if (!user)
 		return -EBADF;
 
-	mutex_lock(&user->lock);
-	raw_spin_lock(&logbuf_lock);
+	ret = mutex_lock_interruptible(&user->lock);
+	if (ret)
+		return ret;
+	raw_spin_lock_irq(&logbuf_lock);
 	while (user->seq == log_next_seq) {
 		if (file->f_flags & O_NONBLOCK) {
 			ret = -EAGAIN;
-			raw_spin_unlock(&logbuf_lock);
+			raw_spin_unlock_irq(&logbuf_lock);
 			goto out;
 		}
 
-		raw_spin_unlock(&logbuf_lock);
+		raw_spin_unlock_irq(&logbuf_lock);
 		ret = wait_event_interruptible(log_wait,
 					       user->seq != log_next_seq);
 		if (ret)
 			goto out;
-		raw_spin_lock(&logbuf_lock);
+		raw_spin_lock_irq(&logbuf_lock);
 	}
 
 	if (user->seq < log_first_seq) {
@@ -436,7 +455,7 @@ static ssize_t devkmsg_read(struct file *file, char __user *buf,
 		user->idx = log_first_idx;
 		user->seq = log_first_seq;
 		ret = -EPIPE;
-		raw_spin_unlock(&logbuf_lock);
+		raw_spin_unlock_irq(&logbuf_lock);
 		goto out;
 	}
 
@@ -444,13 +463,13 @@ static ssize_t devkmsg_read(struct file *file, char __user *buf,
 	ts_usec = msg->ts_nsec;
 	do_div(ts_usec, 1000);
 	len = sprintf(user->buf, "%u,%llu,%llu;",
-		      msg->level, user->seq, ts_usec);
+		      (msg->facility << 3) | msg->level, user->seq, ts_usec);
 
 	/* escape non-printable characters */
 	for (i = 0; i < msg->text_len; i++) {
 		unsigned char c = log_text(msg)[i];
 
-		if (c < ' ' || c >= 128)
+		if (c < ' ' || c >= 127 || c == '\\')
 			len += sprintf(user->buf + len, "\\x%02x", c);
 		else
 			user->buf[len++] = c;
@@ -474,7 +493,7 @@ static ssize_t devkmsg_read(struct file *file, char __user *buf,
 				continue;
 			}
 
-			if (c < ' ' || c >= 128) {
+			if (c < ' ' || c >= 127 || c == '\\') {
 				len += sprintf(user->buf + len, "\\x%02x", c);
 				continue;
 			}
@@ -486,7 +505,7 @@ static ssize_t devkmsg_read(struct file *file, char __user *buf,
 
 	user->idx = log_next(user->idx);
 	user->seq++;
-	raw_spin_unlock(&logbuf_lock);
+	raw_spin_unlock_irq(&logbuf_lock);
 
 	if (len > count) {
 		ret = -EINVAL;
@@ -513,7 +532,7 @@ static loff_t devkmsg_llseek(struct file *file, loff_t offset, int whence)
 	if (offset)
 		return -ESPIPE;
 
-	raw_spin_lock(&logbuf_lock);
+	raw_spin_lock_irq(&logbuf_lock);
 	switch (whence) {
 	case SEEK_SET:
 		/* the first record */
@@ -537,7 +556,7 @@ static loff_t devkmsg_llseek(struct file *file, loff_t offset, int whence)
 	default:
 		ret = -EINVAL;
 	}
-	raw_spin_unlock(&logbuf_lock);
+	raw_spin_unlock_irq(&logbuf_lock);
 	return ret;
 }
 
@@ -551,14 +570,14 @@ static unsigned int devkmsg_poll(struct file *file, poll_table *wait)
 
 	poll_wait(file, &log_wait, wait);
 
-	raw_spin_lock(&logbuf_lock);
+	raw_spin_lock_irq(&logbuf_lock);
 	if (user->seq < log_next_seq) {
 		/* return error when data has vanished underneath us */
 		if (user->seq < log_first_seq)
 			ret = POLLIN|POLLRDNORM|POLLERR|POLLPRI;
 		ret = POLLIN|POLLRDNORM;
 	}
-	raw_spin_unlock(&logbuf_lock);
+	raw_spin_unlock_irq(&logbuf_lock);
 
 	return ret;
 }
@@ -582,10 +601,10 @@ static int devkmsg_open(struct inode *inode, struct file *file)
 
 	mutex_init(&user->lock);
 
-	raw_spin_lock(&logbuf_lock);
+	raw_spin_lock_irq(&logbuf_lock);
 	user->idx = log_first_idx;
 	user->seq = log_first_seq;
-	raw_spin_unlock(&logbuf_lock);
+	raw_spin_unlock_irq(&logbuf_lock);
 
 	file->private_data = user;
 	return 0;
@@ -785,44 +804,64 @@ static bool printk_time;
 #endif
 module_param_named(time, printk_time, bool, S_IRUGO | S_IWUSR);
 
+static size_t print_time(u64 ts, char *buf)
+{
+	unsigned long rem_nsec;
+
+	if (!printk_time)
+		return 0;
+
+	if (!buf)
+		return 15;
+
+	rem_nsec = do_div(ts, 1000000000);
+	return sprintf(buf, "[%5lu.%06lu] ",
+		       (unsigned long)ts, rem_nsec / 1000);
+}
+
 static size_t print_prefix(const struct log *msg, bool syslog, char *buf)
 {
 	size_t len = 0;
+	unsigned int prefix = (msg->facility << 3) | msg->level;
 
 	if (syslog) {
 		if (buf) {
-			len += sprintf(buf, "<%u>", msg->level);
+			len += sprintf(buf, "<%u>", prefix);
 		} else {
 			len += 3;
-			if (msg->level > 9)
-				len++;
-			if (msg->level > 99)
+			if (prefix > 999)
+				len += 3;
+			else if (prefix > 99)
+				len += 2;
+			else if (prefix > 9)
 				len++;
 		}
 	}
 
-	if (printk_time) {
-		if (buf) {
-			unsigned long long ts = msg->ts_nsec;
-			unsigned long rem_nsec = do_div(ts, 1000000000);
-
-			len += sprintf(buf + len, "[%5lu.%06lu] ",
-					 (unsigned long) ts, rem_nsec / 1000);
-		} else {
-			len += 15;
-		}
-	}
-
+	len += print_time(msg->ts_nsec, buf ? buf + len : NULL);
 	return len;
 }
 
-static size_t msg_print_text(const struct log *msg, bool syslog,
-			     char *buf, size_t size)
+static size_t msg_print_text(const struct log *msg, enum log_flags prev,
+			     bool syslog, char *buf, size_t size)
 {
 	const char *text = log_text(msg);
 	size_t text_size = msg->text_len;
+	bool prefix = true;
+	bool newline = true;
 	size_t len = 0;
 
+	if ((prev & LOG_CONT) && !(msg->flags & LOG_PREFIX))
+		prefix = false;
+
+	if (msg->flags & LOG_CONT) {
+		if ((prev & LOG_CONT) && !(prev & LOG_NEWLINE))
+			prefix = false;
+
+		if (!(msg->flags & LOG_NEWLINE))
+			newline = false;
+	}
+
 	do {
 		const char *next = memchr(text, '\n', text_size);
 		size_t text_len;
@@ -840,16 +879,22 @@ static size_t msg_print_text(const struct log *msg, bool syslog,
 			    text_len + 1>= size - len)
 				break;
 
-			len += print_prefix(msg, syslog, buf + len);
+			if (prefix)
+				len += print_prefix(msg, syslog, buf + len);
 			memcpy(buf + len, text, text_len);
 			len += text_len;
-			buf[len++] = '\n';
+			if (next || newline)
+				buf[len++] = '\n';
 		} else {
 			/* SYSLOG_ACTION_* buffer size only calculation */
-			len += print_prefix(msg, syslog, NULL);
-			len += text_len + 1;
+			if (prefix)
+				len += print_prefix(msg, syslog, NULL);
+			len += text_len;
+			if (next || newline)
+				len++;
 		}
 
+		prefix = true;
 		text = next;
 	} while (text);
 
@@ -860,26 +905,60 @@ static int syslog_print(char __user *buf, int size)
 {
 	char *text;
 	struct log *msg;
-	int len;
+	int len = 0;
 
 	text = kmalloc(LOG_LINE_MAX, GFP_KERNEL);
 	if (!text)
 		return -ENOMEM;
 
-	raw_spin_lock_irq(&logbuf_lock);
-	if (syslog_seq < log_first_seq) {
-		/* messages are gone, move to first one */
-		syslog_seq = log_first_seq;
-		syslog_idx = log_first_idx;
-	}
-	msg = log_from_idx(syslog_idx);
-	len = msg_print_text(msg, true, text, LOG_LINE_MAX);
-	syslog_idx = log_next(syslog_idx);
-	syslog_seq++;
-	raw_spin_unlock_irq(&logbuf_lock);
+	while (size > 0) {
+		size_t n;
+		size_t skip;
+
+		raw_spin_lock_irq(&logbuf_lock);
+		if (syslog_seq < log_first_seq) {
+			/* messages are gone, move to first one */
+			syslog_seq = log_first_seq;
+			syslog_idx = log_first_idx;
+			syslog_prev = 0;
+			syslog_partial = 0;
+		}
+		if (syslog_seq == log_next_seq) {
+			raw_spin_unlock_irq(&logbuf_lock);
+			break;
+		}
+
+		skip = syslog_partial;
+		msg = log_from_idx(syslog_idx);
+		n = msg_print_text(msg, syslog_prev, true, text, LOG_LINE_MAX);
+		if (n - syslog_partial <= size) {
+			/* message fits into buffer, move forward */
+			syslog_idx = log_next(syslog_idx);
+			syslog_seq++;
+			syslog_prev = msg->flags;
+			n -= syslog_partial;
+			syslog_partial = 0;
+		} else if (!len){
+			/* partial read(), remember position */
+			n = size;
+			syslog_partial += n;
+		} else
+			n = 0;
+		raw_spin_unlock_irq(&logbuf_lock);
+
+		if (!n)
+			break;
+
+		if (copy_to_user(buf, text + skip, n)) {
+			if (!len)
+				len = -EFAULT;
+			break;
+		}
 
-	if (len > 0 && copy_to_user(buf, text, len))
-		len = -EFAULT;
+		len += n;
+		size -= n;
+		buf += n;
+	}
 
 	kfree(text);
 	return len;
@@ -899,6 +978,7 @@ static int syslog_print_all(char __user *buf, int size, bool clear)
 		u64 next_seq;
 		u64 seq;
 		u32 idx;
+		enum log_flags prev;
 
 		if (clear_seq < log_first_seq) {
 			/* messages are gone, move to first available one */
@@ -909,41 +989,47 @@ static int syslog_print_all(char __user *buf, int size, bool clear)
 		/*
 		 * Find first record that fits, including all following records,
 		 * into the user-provided buffer for this dump.
-		*/
+		 */
 		seq = clear_seq;
 		idx = clear_idx;
+		prev = 0;
 		while (seq < log_next_seq) {
 			struct log *msg = log_from_idx(idx);
 
-			len += msg_print_text(msg, true, NULL, 0);
+			len += msg_print_text(msg, prev, true, NULL, 0);
 			idx = log_next(idx);
 			seq++;
 		}
+
+		/* move first record forward until length fits into the buffer */
 		seq = clear_seq;
 		idx = clear_idx;
+		prev = 0;
 		while (len > size && seq < log_next_seq) {
 			struct log *msg = log_from_idx(idx);
 
-			len -= msg_print_text(msg, true, NULL, 0);
+			len -= msg_print_text(msg, prev, true, NULL, 0);
 			idx = log_next(idx);
 			seq++;
 		}
 
-		/* last message in this dump */
+		/* last message fitting into this dump */
 		next_seq = log_next_seq;
 
 		len = 0;
+		prev = 0;
 		while (len >= 0 && seq < next_seq) {
 			struct log *msg = log_from_idx(idx);
 			int textlen;
 
-			textlen = msg_print_text(msg, true, text, LOG_LINE_MAX);
+			textlen = msg_print_text(msg, prev, true, text, LOG_LINE_MAX);
 			if (textlen < 0) {
 				len = textlen;
 				break;
 			}
 			idx = log_next(idx);
 			seq++;
+			prev = msg->flags;
 
 			raw_spin_unlock_irq(&logbuf_lock);
 			if (copy_to_user(buf + len, text, textlen))
@@ -956,6 +1042,7 @@ static int syslog_print_all(char __user *buf, int size, bool clear)
 				/* messages are gone, move to next one */
 				seq = log_first_seq;
 				idx = log_first_idx;
+				prev = 0;
 			}
 		}
 	}
@@ -1027,6 +1114,7 @@ int do_syslog(int type, char __user *buf, int len, bool from_file)
 	/* Clear ring buffer */
 	case SYSLOG_ACTION_CLEAR:
 		syslog_print_all(NULL, 0, true);
+		break;
 	/* Disable logging to console */
 	case SYSLOG_ACTION_CONSOLE_OFF:
 		if (saved_console_loglevel == -1)
@@ -1059,6 +1147,8 @@ int do_syslog(int type, char __user *buf, int len, bool from_file)
 			/* messages are gone, move to first one */
 			syslog_seq = log_first_seq;
 			syslog_idx = log_first_idx;
+			syslog_prev = 0;
+			syslog_partial = 0;
 		}
 		if (from_file) {
 			/*
@@ -1068,19 +1158,20 @@ int do_syslog(int type, char __user *buf, int len, bool from_file)
 			 */
 			error = log_next_idx - syslog_idx;
 		} else {
-			u64 seq;
-			u32 idx;
+			u64 seq = syslog_seq;
+			u32 idx = syslog_idx;
+			enum log_flags prev = syslog_prev;
 
 			error = 0;
-			seq = syslog_seq;
-			idx = syslog_idx;
 			while (seq < log_next_seq) {
 				struct log *msg = log_from_idx(idx);
 
-				error += msg_print_text(msg, true, NULL, 0);
+				error += msg_print_text(msg, prev, true, NULL, 0);
 				idx = log_next(idx);
 				seq++;
+				prev = msg->flags;
 			}
+			error -= syslog_partial;
 		}
 		raw_spin_unlock_irq(&logbuf_lock);
 		break;
@@ -1259,22 +1350,98 @@ static inline void printk_delay(void)
 	}
 }
 
+/*
+ * Continuation lines are buffered, and not committed to the record buffer
+ * until the line is complete, or a race forces it. The line fragments
+ * though, are printed immediately to the consoles to ensure everything has
+ * reached the console in case of a kernel crash.
+ */
+static struct cont {
+	char buf[LOG_LINE_MAX];
+	size_t len;			/* length == 0 means unused buffer */
+	size_t cons;			/* bytes written to console */
+	struct task_struct *owner;	/* task of first print*/
+	u64 ts_nsec;			/* time of first print */
+	u8 level;			/* log level of first message */
+	u8 facility;			/* log level of first message */
+	bool flushed:1;			/* buffer sealed and committed */
+} cont;
+
+static void cont_flush(void)
+{
+	if (cont.flushed)
+		return;
+	if (cont.len == 0)
+		return;
+
+	log_store(cont.facility, cont.level, LOG_NOCONS, cont.ts_nsec,
+		  NULL, 0, cont.buf, cont.len);
+
+	cont.flushed = true;
+}
+
+static bool cont_add(int facility, int level, const char *text, size_t len)
+{
+	if (cont.len && cont.flushed)
+		return false;
+
+	if (cont.len + len > sizeof(cont.buf)) {
+		cont_flush();
+		return false;
+	}
+
+	if (!cont.len) {
+		cont.facility = facility;
+		cont.level = level;
+		cont.owner = current;
+		cont.ts_nsec = local_clock();
+		cont.cons = 0;
+		cont.flushed = false;
+	}
+
+	memcpy(cont.buf + cont.len, text, len);
+	cont.len += len;
+	return true;
+}
+
+static size_t cont_print_text(char *text, size_t size)
+{
+	size_t textlen = 0;
+	size_t len;
+
+	if (cont.cons == 0) {
+		textlen += print_time(cont.ts_nsec, text);
+		size -= textlen;
+	}
+
+	len = cont.len - cont.cons;
+	if (len > 0) {
+		if (len+1 > size)
+			len = size-1;
+		memcpy(text + textlen, cont.buf + cont.cons, len);
+		textlen += len;
+		cont.cons = cont.len;
+	}
+
+	if (cont.flushed) {
+		text[textlen++] = '\n';
+		/* got everything, release buffer */
+		cont.len = 0;
+	}
+	return textlen;
+}
+
 asmlinkage int vprintk_emit(int facility, int level,
 			    const char *dict, size_t dictlen,
 			    const char *fmt, va_list args)
 {
 	static int recursion_bug;
-	static char cont_buf[LOG_LINE_MAX];
-	static size_t cont_len;
-	static int cont_level;
-	static struct task_struct *cont_task;
 	static char textbuf[LOG_LINE_MAX];
 	char *text = textbuf;
 	size_t text_len;
+	enum log_flags lflags = 0;
 	unsigned long flags;
 	int this_cpu;
-	bool newline = false;
-	bool prefix = false;
 	int printed_len = 0;
 
 	boot_delay_msec();
@@ -1313,7 +1480,8 @@ asmlinkage int vprintk_emit(int facility, int level,
 		recursion_bug = 0;
 		printed_len += strlen(recursion_msg);
 		/* emit KERN_CRIT message */
-		log_store(0, 2, NULL, 0, recursion_msg, printed_len);
+		log_store(0, 2, LOG_PREFIX|LOG_NEWLINE, 0,
+			  NULL, 0, recursion_msg, printed_len);
 	}
 
 	/*
@@ -1325,7 +1493,7 @@ asmlinkage int vprintk_emit(int facility, int level,
 	/* mark and strip a trailing newline */
 	if (text_len && text[text_len-1] == '\n') {
 		text_len--;
-		newline = true;
+		lflags |= LOG_NEWLINE;
 	}
 
 	/* strip syslog prefix and extract log level or control flags */
@@ -1335,7 +1503,7 @@ asmlinkage int vprintk_emit(int facility, int level,
 			if (level == -1)
 				level = text[1] - '0';
 		case 'd':	/* KERN_DEFAULT */
-			prefix = true;
+			lflags |= LOG_PREFIX;
 		case 'c':	/* KERN_CONT */
 			text += 3;
 			text_len -= 3;
@@ -1345,61 +1513,41 @@ asmlinkage int vprintk_emit(int facility, int level,
 	if (level == -1)
 		level = default_message_loglevel;
 
-	if (dict) {
-		prefix = true;
-		newline = true;
-	}
+	if (dict)
+		lflags |= LOG_PREFIX|LOG_NEWLINE;
 
-	if (!newline) {
-		if (cont_len && (prefix || cont_task != current)) {
-			/*
-			 * Flush earlier buffer, which is either from a
-			 * different thread, or when we got a new prefix.
-			 */
-			log_store(facility, cont_level, NULL, 0, cont_buf, cont_len);
-			cont_len = 0;
-		}
-
-		if (!cont_len) {
-			cont_level = level;
-			cont_task = current;
-		}
+	if (!(lflags & LOG_NEWLINE)) {
+		/*
+		 * Flush the conflicting buffer. An earlier newline was missing,
+		 * or another task also prints continuation lines.
+		 */
+		if (cont.len && (lflags & LOG_PREFIX || cont.owner != current))
+			cont_flush();
 
-		/* buffer or append to earlier buffer from the same thread */
-		if (cont_len + text_len > sizeof(cont_buf))
-			text_len = sizeof(cont_buf) - cont_len;
-		memcpy(cont_buf + cont_len, text, text_len);
-		cont_len += text_len;
+		/* buffer line if possible, otherwise store it right away */
+		if (!cont_add(facility, level, text, text_len))
+			log_store(facility, level, lflags | LOG_CONT, 0,
+				  dict, dictlen, text, text_len);
 	} else {
-		if (cont_len && cont_task == current) {
-			if (prefix) {
-				/*
-				 * New prefix from the same thread; flush. We
-				 * either got no earlier newline, or we race
-				 * with an interrupt.
-				 */
-				log_store(facility, cont_level,
-					  NULL, 0, cont_buf, cont_len);
-				cont_len = 0;
-			}
+		bool stored = false;
 
-			/* append to the earlier buffer and flush */
-			if (cont_len + text_len > sizeof(cont_buf))
-				text_len = sizeof(cont_buf) - cont_len;
-			memcpy(cont_buf + cont_len, text, text_len);
-			cont_len += text_len;
-			log_store(facility, cont_level,
-				  NULL, 0, cont_buf, cont_len);
-			cont_len = 0;
-			cont_task = NULL;
-			printed_len = cont_len;
-		} else {
-			/* ordinary single and terminated line */
-			log_store(facility, level,
-				  dict, dictlen, text, text_len);
-			printed_len = text_len;
+		/*
+		 * If an earlier newline was missing and it was the same task,
+		 * either merge it with the current buffer and flush, or if
+		 * there was a race with interrupts (prefix == true) then just
+		 * flush it out and store this line separately.
+		 */
+		if (cont.len && cont.owner == current) {
+			if (!(lflags & LOG_PREFIX))
+				stored = cont_add(facility, level, text, text_len);
+			cont_flush();
 		}
+
+		if (!stored)
+			log_store(facility, level, lflags, 0,
+				  dict, dictlen, text, text_len);
 	}
+	printed_len += text_len;
 
 	/*
 	 * Try to acquire and then immediately release the console semaphore.
@@ -1486,11 +1634,18 @@ EXPORT_SYMBOL(printk);
 #else
 
 #define LOG_LINE_MAX 0
+static struct cont {
+	size_t len;
+	size_t cons;
+	u8 level;
+	bool flushed:1;
+} cont;
 static struct log *log_from_idx(u32 idx) { return NULL; }
 static u32 log_next(u32 idx) { return 0; }
 static void call_console_drivers(int level, const char *text, size_t len) {}
-static size_t msg_print_text(const struct log *msg, bool syslog,
-			     char *buf, size_t size) { return 0; }
+static size_t msg_print_text(const struct log *msg, enum log_flags prev,
+			     bool syslog, char *buf, size_t size) { return 0; }
+static size_t cont_print_text(char *text, size_t size) { return 0; }
 
 #endif /* CONFIG_PRINTK */
 
@@ -1765,6 +1920,7 @@ void wake_up_klogd(void)
 /* the next printk record to write to the console */
 static u64 console_seq;
 static u32 console_idx;
+static enum log_flags console_prev;
 
 /**
  * console_unlock - unlock the console system
@@ -1782,6 +1938,7 @@ static u32 console_idx;
  */
 void console_unlock(void)
 {
+	static char text[LOG_LINE_MAX];
 	static u64 seen_seq;
 	unsigned long flags;
 	bool wake_klogd = false;
@@ -1794,10 +1951,23 @@ void console_unlock(void)
 
 	console_may_schedule = 0;
 
+	/* flush buffered message fragment immediately to console */
+	raw_spin_lock_irqsave(&logbuf_lock, flags);
+	if (cont.len && (cont.cons < cont.len || cont.flushed)) {
+		size_t len;
+
+		len = cont_print_text(text, sizeof(text));
+		raw_spin_unlock(&logbuf_lock);
+		stop_critical_timings();
+		call_console_drivers(cont.level, text, len);
+		start_critical_timings();
+		local_irq_restore(flags);
+	} else
+		raw_spin_unlock_irqrestore(&logbuf_lock, flags);
+
 again:
 	for (;;) {
 		struct log *msg;
-		static char text[LOG_LINE_MAX];
 		size_t len;
 		int level;
 
@@ -1811,18 +1981,35 @@ again:
 			/* messages are gone, move to first one */
 			console_seq = log_first_seq;
 			console_idx = log_first_idx;
+			console_prev = 0;
 		}
-
+skip:
 		if (console_seq == log_next_seq)
 			break;
 
 		msg = log_from_idx(console_idx);
-		level = msg->level & 7;
-
-		len = msg_print_text(msg, false, text, sizeof(text));
+		if (msg->flags & LOG_NOCONS) {
+			/*
+			 * Skip record we have buffered and already printed
+			 * directly to the console when we received it.
+			 */
+			console_idx = log_next(console_idx);
+			console_seq++;
+			/*
+			 * We will get here again when we register a new
+			 * CON_PRINTBUFFER console. Clear the flag so we
+			 * will properly dump everything later.
+			 */
+			msg->flags &= ~LOG_NOCONS;
+			goto skip;
+		}
 
+		level = msg->level;
+		len = msg_print_text(msg, console_prev, false,
+				     text, sizeof(text));
 		console_idx = log_next(console_idx);
 		console_seq++;
+		console_prev = msg->flags;
 		raw_spin_unlock(&logbuf_lock);
 
 		stop_critical_timings();	/* don't trace print latency */
@@ -2085,6 +2272,7 @@ void register_console(struct console *newcon)
 		raw_spin_lock_irqsave(&logbuf_lock, flags);
 		console_seq = syslog_seq;
 		console_idx = syslog_idx;
+		console_prev = syslog_prev;
 		raw_spin_unlock_irqrestore(&logbuf_lock, flags);
 		/*
 		 * We're about to replay the log buffer.  Only do this to the
@@ -2300,48 +2488,214 @@ module_param_named(always_kmsg_dump, always_kmsg_dump, bool, S_IRUGO | S_IWUSR);
  * kmsg_dump - dump kernel log to kernel message dumpers.
  * @reason: the reason (oops, panic etc) for dumping
  *
- * Iterate through each of the dump devices and call the oops/panic
- * callbacks with the log buffer.
+ * Call each of the registered dumper's dump() callback, which can
+ * retrieve the kmsg records with kmsg_dump_get_line() or
+ * kmsg_dump_get_buffer().
  */
 void kmsg_dump(enum kmsg_dump_reason reason)
 {
-	u64 idx;
 	struct kmsg_dumper *dumper;
-	const char *s1, *s2;
-	unsigned long l1, l2;
 	unsigned long flags;
 
 	if ((reason > KMSG_DUMP_OOPS) && !always_kmsg_dump)
 		return;
 
-	/* Theoretically, the log could move on after we do this, but
-	   there's not a lot we can do about that. The new messages
-	   will overwrite the start of what we dump. */
+	rcu_read_lock();
+	list_for_each_entry_rcu(dumper, &dump_list, list) {
+		if (dumper->max_reason && reason > dumper->max_reason)
+			continue;
+
+		/* initialize iterator with data about the stored records */
+		dumper->active = true;
+
+		raw_spin_lock_irqsave(&logbuf_lock, flags);
+		dumper->cur_seq = clear_seq;
+		dumper->cur_idx = clear_idx;
+		dumper->next_seq = log_next_seq;
+		dumper->next_idx = log_next_idx;
+		raw_spin_unlock_irqrestore(&logbuf_lock, flags);
+
+		/* invoke dumper which will iterate over records */
+		dumper->dump(dumper, reason);
+
+		/* reset iterator */
+		dumper->active = false;
+	}
+	rcu_read_unlock();
+}
+
+/**
+ * kmsg_dump_get_line - retrieve one kmsg log line
+ * @dumper: registered kmsg dumper
+ * @syslog: include the "<4>" prefixes
+ * @line: buffer to copy the line to
+ * @size: maximum size of the buffer
+ * @len: length of line placed into buffer
+ *
+ * Start at the beginning of the kmsg buffer, with the oldest kmsg
+ * record, and copy one record into the provided buffer.
+ *
+ * Consecutive calls will return the next available record moving
+ * towards the end of the buffer with the youngest messages.
+ *
+ * A return value of FALSE indicates that there are no more records to
+ * read.
+ */
+bool kmsg_dump_get_line(struct kmsg_dumper *dumper, bool syslog,
+			char *line, size_t size, size_t *len)
+{
+	unsigned long flags;
+	struct log *msg;
+	size_t l = 0;
+	bool ret = false;
+
+	if (!dumper->active)
+		goto out;
 
 	raw_spin_lock_irqsave(&logbuf_lock, flags);
-	if (syslog_seq < log_first_seq)
-		idx = syslog_idx;
-	else
-		idx = log_first_idx;
+	if (dumper->cur_seq < log_first_seq) {
+		/* messages are gone, move to first available one */
+		dumper->cur_seq = log_first_seq;
+		dumper->cur_idx = log_first_idx;
+	}
 
-	if (idx > log_next_idx) {
-		s1 = log_buf;
-		l1 = log_next_idx;
+	/* last entry */
+	if (dumper->cur_seq >= log_next_seq) {
+		raw_spin_unlock_irqrestore(&logbuf_lock, flags);
+		goto out;
+	}
 
-		s2 = log_buf + idx;
-		l2 = log_buf_len - idx;
-	} else {
-		s1 = "";
-		l1 = 0;
+	msg = log_from_idx(dumper->cur_idx);
+	l = msg_print_text(msg, 0, syslog, line, size);
+
+	dumper->cur_idx = log_next(dumper->cur_idx);
+	dumper->cur_seq++;
+	ret = true;
+	raw_spin_unlock_irqrestore(&logbuf_lock, flags);
+out:
+	if (len)
+		*len = l;
+	return ret;
+}
+EXPORT_SYMBOL_GPL(kmsg_dump_get_line);
+
+/**
+ * kmsg_dump_get_buffer - copy kmsg log lines
+ * @dumper: registered kmsg dumper
+ * @syslog: include the "<4>" prefixes
+ * @buf: buffer to copy the line to
+ * @size: maximum size of the buffer
+ * @len: length of line placed into buffer
+ *
+ * Start at the end of the kmsg buffer and fill the provided buffer
+ * with as many of the the *youngest* kmsg records that fit into it.
+ * If the buffer is large enough, all available kmsg records will be
+ * copied with a single call.
+ *
+ * Consecutive calls will fill the buffer with the next block of
+ * available older records, not including the earlier retrieved ones.
+ *
+ * A return value of FALSE indicates that there are no more records to
+ * read.
+ */
+bool kmsg_dump_get_buffer(struct kmsg_dumper *dumper, bool syslog,
+			  char *buf, size_t size, size_t *len)
+{
+	unsigned long flags;
+	u64 seq;
+	u32 idx;
+	u64 next_seq;
+	u32 next_idx;
+	enum log_flags prev;
+	size_t l = 0;
+	bool ret = false;
+
+	if (!dumper->active)
+		goto out;
+
+	raw_spin_lock_irqsave(&logbuf_lock, flags);
+	if (dumper->cur_seq < log_first_seq) {
+		/* messages are gone, move to first available one */
+		dumper->cur_seq = log_first_seq;
+		dumper->cur_idx = log_first_idx;
+	}
+
+	/* last entry */
+	if (dumper->cur_seq >= dumper->next_seq) {
+		raw_spin_unlock_irqrestore(&logbuf_lock, flags);
+		goto out;
+	}
+
+	/* calculate length of entire buffer */
+	seq = dumper->cur_seq;
+	idx = dumper->cur_idx;
+	prev = 0;
+	while (seq < dumper->next_seq) {
+		struct log *msg = log_from_idx(idx);
+
+		l += msg_print_text(msg, prev, true, NULL, 0);
+		idx = log_next(idx);
+		seq++;
+		prev = msg->flags;
+	}
 
-		s2 = log_buf + idx;
-		l2 = log_next_idx - idx;
+	/* move first record forward until length fits into the buffer */
+	seq = dumper->cur_seq;
+	idx = dumper->cur_idx;
+	prev = 0;
+	while (l > size && seq < dumper->next_seq) {
+		struct log *msg = log_from_idx(idx);
+
+		l -= msg_print_text(msg, prev, true, NULL, 0);
+		idx = log_next(idx);
+		seq++;
+		prev = msg->flags;
 	}
+
+	/* last message in next interation */
+	next_seq = seq;
+	next_idx = idx;
+
+	l = 0;
+	prev = 0;
+	while (seq < dumper->next_seq) {
+		struct log *msg = log_from_idx(idx);
+
+		l += msg_print_text(msg, prev, syslog, buf + l, size - l);
+		idx = log_next(idx);
+		seq++;
+		prev = msg->flags;
+	}
+
+	dumper->next_seq = next_seq;
+	dumper->next_idx = next_idx;
+	ret = true;
 	raw_spin_unlock_irqrestore(&logbuf_lock, flags);
+out:
+	if (len)
+		*len = l;
+	return ret;
+}
+EXPORT_SYMBOL_GPL(kmsg_dump_get_buffer);
 
-	rcu_read_lock();
-	list_for_each_entry_rcu(dumper, &dump_list, list)
-		dumper->dump(dumper, reason, s1, l1, s2, l2);
-	rcu_read_unlock();
+/**
+ * kmsg_dump_rewind - reset the interator
+ * @dumper: registered kmsg dumper
+ *
+ * Reset the dumper's iterator so that kmsg_dump_get_line() and
+ * kmsg_dump_get_buffer() can be called again and used multiple
+ * times within the same dumper.dump() callback.
+ */
+void kmsg_dump_rewind(struct kmsg_dumper *dumper)
+{
+	unsigned long flags;
+
+	raw_spin_lock_irqsave(&logbuf_lock, flags);
+	dumper->cur_seq = clear_seq;
+	dumper->cur_idx = clear_idx;
+	dumper->next_seq = log_next_seq;
+	dumper->next_idx = log_next_idx;
+	raw_spin_unlock_irqrestore(&logbuf_lock, flags);
 }
+EXPORT_SYMBOL_GPL(kmsg_dump_rewind);
 #endif
diff --git a/kernel/rcutree.c b/kernel/rcutree.c
index 0da7b88d92d..4b97bba7396 100644
--- a/kernel/rcutree.c
+++ b/kernel/rcutree.c
@@ -201,6 +201,7 @@ void rcu_note_context_switch(int cpu)
 {
 	trace_rcu_utilization("Start context switch");
 	rcu_sched_qs(cpu);
+	rcu_preempt_note_context_switch(cpu);
 	trace_rcu_utilization("End context switch");
 }
 EXPORT_SYMBOL_GPL(rcu_note_context_switch);
@@ -1397,6 +1398,8 @@ static void rcu_adopt_orphan_cbs(struct rcu_state *rsp)
 	rdp->qlen_lazy += rsp->qlen_lazy;
 	rdp->qlen += rsp->qlen;
 	rdp->n_cbs_adopted += rsp->qlen;
+	if (rsp->qlen_lazy != rsp->qlen)
+		rcu_idle_count_callbacks_posted();
 	rsp->qlen_lazy = 0;
 	rsp->qlen = 0;
 
@@ -1528,7 +1531,7 @@ static void rcu_do_batch(struct rcu_state *rsp, struct rcu_data *rdp)
 {
 	unsigned long flags;
 	struct rcu_head *next, *list, **tail;
-	int bl, count, count_lazy;
+	int bl, count, count_lazy, i;
 
 	/* If no callbacks are ready, just return.*/
 	if (!cpu_has_callbacks_ready_to_invoke(rdp)) {
@@ -1551,9 +1554,9 @@ static void rcu_do_batch(struct rcu_state *rsp, struct rcu_data *rdp)
 	rdp->nxtlist = *rdp->nxttail[RCU_DONE_TAIL];
 	*rdp->nxttail[RCU_DONE_TAIL] = NULL;
 	tail = rdp->nxttail[RCU_DONE_TAIL];
-	for (count = RCU_NEXT_SIZE - 1; count >= 0; count--)
-		if (rdp->nxttail[count] == rdp->nxttail[RCU_DONE_TAIL])
-			rdp->nxttail[count] = &rdp->nxtlist;
+	for (i = RCU_NEXT_SIZE - 1; i >= 0; i--)
+		if (rdp->nxttail[i] == rdp->nxttail[RCU_DONE_TAIL])
+			rdp->nxttail[i] = &rdp->nxtlist;
 	local_irq_restore(flags);
 
 	/* Invoke callbacks. */
@@ -1581,9 +1584,9 @@ static void rcu_do_batch(struct rcu_state *rsp, struct rcu_data *rdp)
 	if (list != NULL) {
 		*tail = rdp->nxtlist;
 		rdp->nxtlist = list;
-		for (count = 0; count < RCU_NEXT_SIZE; count++)
-			if (&rdp->nxtlist == rdp->nxttail[count])
-				rdp->nxttail[count] = tail;
+		for (i = 0; i < RCU_NEXT_SIZE; i++)
+			if (&rdp->nxtlist == rdp->nxttail[i])
+				rdp->nxttail[i] = tail;
 			else
 				break;
 	}
diff --git a/kernel/rcutree.h b/kernel/rcutree.h
index 7f5d138dedf..19b61ac1079 100644
--- a/kernel/rcutree.h
+++ b/kernel/rcutree.h
@@ -84,6 +84,20 @@ struct rcu_dynticks {
 				    /* Process level is worth LLONG_MAX/2. */
 	int dynticks_nmi_nesting;   /* Track NMI nesting level. */
 	atomic_t dynticks;	    /* Even value for idle, else odd. */
+#ifdef CONFIG_RCU_FAST_NO_HZ
+	int dyntick_drain;	    /* Prepare-for-idle state variable. */
+	unsigned long dyntick_holdoff;
+				    /* No retries for the jiffy of failure. */
+	struct timer_list idle_gp_timer;
+				    /* Wake up CPU sleeping with callbacks. */
+	unsigned long idle_gp_timer_expires;
+				    /* When to wake up CPU (for repost). */
+	bool idle_first_pass;	    /* First pass of attempt to go idle? */
+	unsigned long nonlazy_posted;
+				    /* # times non-lazy CBs posted to CPU. */
+	unsigned long nonlazy_posted_snap;
+				    /* idle-period nonlazy_posted snapshot. */
+#endif /* #ifdef CONFIG_RCU_FAST_NO_HZ */
 };
 
 /* RCU's kthread states for tracing. */
@@ -430,6 +444,7 @@ DECLARE_PER_CPU(char, rcu_cpu_has_work);
 /* Forward declarations for rcutree_plugin.h */
 static void rcu_bootup_announce(void);
 long rcu_batches_completed(void);
+static void rcu_preempt_note_context_switch(int cpu);
 static int rcu_preempt_blocked_readers_cgp(struct rcu_node *rnp);
 #ifdef CONFIG_HOTPLUG_CPU
 static void rcu_report_unblock_qs_rnp(struct rcu_node *rnp,
diff --git a/kernel/rcutree_plugin.h b/kernel/rcutree_plugin.h
index 2411000d986..3e4899459f3 100644
--- a/kernel/rcutree_plugin.h
+++ b/kernel/rcutree_plugin.h
@@ -153,7 +153,7 @@ static void rcu_preempt_qs(int cpu)
  *
  * Caller must disable preemption.
  */
-void rcu_preempt_note_context_switch(void)
+static void rcu_preempt_note_context_switch(int cpu)
 {
 	struct task_struct *t = current;
 	unsigned long flags;
@@ -164,7 +164,7 @@ void rcu_preempt_note_context_switch(void)
 	    (t->rcu_read_unlock_special & RCU_READ_UNLOCK_BLOCKED) == 0) {
 
 		/* Possibly blocking in an RCU read-side critical section. */
-		rdp = __this_cpu_ptr(rcu_preempt_state.rda);
+		rdp = per_cpu_ptr(rcu_preempt_state.rda, cpu);
 		rnp = rdp->mynode;
 		raw_spin_lock_irqsave(&rnp->lock, flags);
 		t->rcu_read_unlock_special |= RCU_READ_UNLOCK_BLOCKED;
@@ -228,7 +228,7 @@ void rcu_preempt_note_context_switch(void)
 	 * means that we continue to block the current grace period.
 	 */
 	local_irq_save(flags);
-	rcu_preempt_qs(smp_processor_id());
+	rcu_preempt_qs(cpu);
 	local_irq_restore(flags);
 }
 
@@ -1002,6 +1002,14 @@ void rcu_force_quiescent_state(void)
 EXPORT_SYMBOL_GPL(rcu_force_quiescent_state);
 
 /*
+ * Because preemptible 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 preemptible RCU does not exist, there are never any preempted
  * RCU readers.
  */
@@ -1886,8 +1894,9 @@ static void __cpuinit rcu_prepare_kthreads(int cpu)
  * Because we not have RCU_FAST_NO_HZ, just check whether this CPU needs
  * any flavor of RCU.
  */
-int rcu_needs_cpu(int cpu)
+int rcu_needs_cpu(int cpu, unsigned long *delta_jiffies)
 {
+	*delta_jiffies = ULONG_MAX;
 	return rcu_cpu_has_callbacks(cpu);
 }
 
@@ -1962,41 +1971,6 @@ static void rcu_idle_count_callbacks_posted(void)
 #define RCU_IDLE_GP_DELAY 6		/* Roughly one grace period. */
 #define RCU_IDLE_LAZY_GP_DELAY (6 * HZ)	/* Roughly six seconds. */
 
-/* Loop counter for rcu_prepare_for_idle(). */
-static DEFINE_PER_CPU(int, rcu_dyntick_drain);
-/* If rcu_dyntick_holdoff==jiffies, don't try to enter dyntick-idle mode. */
-static DEFINE_PER_CPU(unsigned long, rcu_dyntick_holdoff);
-/* Timer to awaken the CPU if it enters dyntick-idle mode with callbacks. */
-static DEFINE_PER_CPU(struct timer_list, rcu_idle_gp_timer);
-/* Scheduled expiry time for rcu_idle_gp_timer to allow reposting. */
-static DEFINE_PER_CPU(unsigned long, rcu_idle_gp_timer_expires);
-/* Enable special processing on first attempt to enter dyntick-idle mode. */
-static DEFINE_PER_CPU(bool, rcu_idle_first_pass);
-/* Running count of non-lazy callbacks posted, never decremented. */
-static DEFINE_PER_CPU(unsigned long, rcu_nonlazy_posted);
-/* Snapshot of rcu_nonlazy_posted to detect meaningful exits from idle. */
-static DEFINE_PER_CPU(unsigned long, rcu_nonlazy_posted_snap);
-
-/*
- * Allow the CPU to enter dyntick-idle mode if either: (1) There are no
- * callbacks on this CPU, (2) this CPU has not yet attempted to enter
- * dyntick-idle mode, or (3) this CPU is in the process of attempting to
- * enter dyntick-idle mode.  Otherwise, if we have recently tried and failed
- * to enter dyntick-idle mode, we refuse to try to enter it.  After all,
- * it is better to incur scheduling-clock interrupts than to spin
- * continuously for the same time duration!
- */
-int rcu_needs_cpu(int cpu)
-{
-	/* Flag a new idle sojourn to the idle-entry state machine. */
-	per_cpu(rcu_idle_first_pass, cpu) = 1;
-	/* If no callbacks, RCU doesn't need the CPU. */
-	if (!rcu_cpu_has_callbacks(cpu))
-		return 0;
-	/* Otherwise, RCU needs the CPU only if it recently tried and failed. */
-	return per_cpu(rcu_dyntick_holdoff, cpu) == jiffies;
-}
-
 /*
  * Does the specified flavor of RCU have non-lazy callbacks pending on
  * the specified CPU?  Both RCU flavor and CPU are specified by the
@@ -2040,6 +2014,47 @@ static bool rcu_cpu_has_nonlazy_callbacks(int cpu)
 }
 
 /*
+ * Allow the CPU to enter dyntick-idle mode if either: (1) There are no
+ * callbacks on this CPU, (2) this CPU has not yet attempted to enter
+ * dyntick-idle mode, or (3) this CPU is in the process of attempting to
+ * enter dyntick-idle mode.  Otherwise, if we have recently tried and failed
+ * to enter dyntick-idle mode, we refuse to try to enter it.  After all,
+ * it is better to incur scheduling-clock interrupts than to spin
+ * continuously for the same time duration!
+ *
+ * The delta_jiffies argument is used to store the time when RCU is
+ * going to need the CPU again if it still has callbacks.  The reason
+ * for this is that rcu_prepare_for_idle() might need to post a timer,
+ * but if so, it will do so after tick_nohz_stop_sched_tick() has set
+ * the wakeup time for this CPU.  This means that RCU's timer can be
+ * delayed until the wakeup time, which defeats the purpose of posting
+ * a timer.
+ */
+int rcu_needs_cpu(int cpu, unsigned long *delta_jiffies)
+{
+	struct rcu_dynticks *rdtp = &per_cpu(rcu_dynticks, cpu);
+
+	/* Flag a new idle sojourn to the idle-entry state machine. */
+	rdtp->idle_first_pass = 1;
+	/* If no callbacks, RCU doesn't need the CPU. */
+	if (!rcu_cpu_has_callbacks(cpu)) {
+		*delta_jiffies = ULONG_MAX;
+		return 0;
+	}
+	if (rdtp->dyntick_holdoff == jiffies) {
+		/* RCU recently tried and failed, so don't try again. */
+		*delta_jiffies = 1;
+		return 1;
+	}
+	/* Set up for the possibility that RCU will post a timer. */
+	if (rcu_cpu_has_nonlazy_callbacks(cpu))
+		*delta_jiffies = RCU_IDLE_GP_DELAY;
+	else
+		*delta_jiffies = RCU_IDLE_LAZY_GP_DELAY;
+	return 0;
+}
+
+/*
  * Handler for smp_call_function_single().  The only point of this
  * handler is to wake the CPU up, so the handler does only tracing.
  */
@@ -2075,21 +2090,24 @@ static void rcu_idle_gp_timer_func(unsigned long cpu_in)
  */
 static void rcu_prepare_for_idle_init(int cpu)
 {
-	per_cpu(rcu_dyntick_holdoff, cpu) = jiffies - 1;
-	setup_timer(&per_cpu(rcu_idle_gp_timer, cpu),
-		    rcu_idle_gp_timer_func, cpu);
-	per_cpu(rcu_idle_gp_timer_expires, cpu) = jiffies - 1;
-	per_cpu(rcu_idle_first_pass, cpu) = 1;
+	struct rcu_dynticks *rdtp = &per_cpu(rcu_dynticks, cpu);
+
+	rdtp->dyntick_holdoff = jiffies - 1;
+	setup_timer(&rdtp->idle_gp_timer, rcu_idle_gp_timer_func, cpu);
+	rdtp->idle_gp_timer_expires = jiffies - 1;
+	rdtp->idle_first_pass = 1;
 }
 
 /*
  * Clean up for exit from idle.  Because we are exiting from idle, there
- * is no longer any point to rcu_idle_gp_timer, so cancel it.  This will
+ * is no longer any point to ->idle_gp_timer, so cancel it.  This will
  * do nothing if this timer is not active, so just cancel it unconditionally.
  */
 static void rcu_cleanup_after_idle(int cpu)
 {
-	del_timer(&per_cpu(rcu_idle_gp_timer, cpu));
+	struct rcu_dynticks *rdtp = &per_cpu(rcu_dynticks, cpu);
+
+	del_timer(&rdtp->idle_gp_timer);
 	trace_rcu_prep_idle("Cleanup after idle");
 }
 
@@ -2108,42 +2126,41 @@ static void rcu_cleanup_after_idle(int cpu)
  * Because it is not legal to invoke rcu_process_callbacks() with irqs
  * disabled, we do one pass of force_quiescent_state(), then do a
  * invoke_rcu_core() to cause rcu_process_callbacks() to be invoked
- * later.  The per-cpu rcu_dyntick_drain variable controls the sequencing.
+ * later.  The ->dyntick_drain field controls the sequencing.
  *
  * The caller must have disabled interrupts.
  */
 static void rcu_prepare_for_idle(int cpu)
 {
 	struct timer_list *tp;
+	struct rcu_dynticks *rdtp = &per_cpu(rcu_dynticks, cpu);
 
 	/*
 	 * If this is an idle re-entry, for example, due to use of
 	 * RCU_NONIDLE() or the new idle-loop tracing API within the idle
 	 * loop, then don't take any state-machine actions, unless the
 	 * momentary exit from idle queued additional non-lazy callbacks.
-	 * Instead, repost the rcu_idle_gp_timer if this CPU has callbacks
+	 * Instead, repost the ->idle_gp_timer if this CPU has callbacks
 	 * pending.
 	 */
-	if (!per_cpu(rcu_idle_first_pass, cpu) &&
-	    (per_cpu(rcu_nonlazy_posted, cpu) ==
-	     per_cpu(rcu_nonlazy_posted_snap, cpu))) {
+	if (!rdtp->idle_first_pass &&
+	    (rdtp->nonlazy_posted == rdtp->nonlazy_posted_snap)) {
 		if (rcu_cpu_has_callbacks(cpu)) {
-			tp = &per_cpu(rcu_idle_gp_timer, cpu);
-			mod_timer_pinned(tp, per_cpu(rcu_idle_gp_timer_expires, cpu));
+			tp = &rdtp->idle_gp_timer;
+			mod_timer_pinned(tp, rdtp->idle_gp_timer_expires);
 		}
 		return;
 	}
-	per_cpu(rcu_idle_first_pass, cpu) = 0;
-	per_cpu(rcu_nonlazy_posted_snap, cpu) =
-		per_cpu(rcu_nonlazy_posted, cpu) - 1;
+	rdtp->idle_first_pass = 0;
+	rdtp->nonlazy_posted_snap = rdtp->nonlazy_posted - 1;
 
 	/*
 	 * If there are no callbacks on this CPU, enter dyntick-idle mode.
 	 * Also reset state to avoid prejudicing later attempts.
 	 */
 	if (!rcu_cpu_has_callbacks(cpu)) {
-		per_cpu(rcu_dyntick_holdoff, cpu) = jiffies - 1;
-		per_cpu(rcu_dyntick_drain, cpu) = 0;
+		rdtp->dyntick_holdoff = jiffies - 1;
+		rdtp->dyntick_drain = 0;
 		trace_rcu_prep_idle("No callbacks");
 		return;
 	}
@@ -2152,36 +2169,37 @@ static void rcu_prepare_for_idle(int cpu)
 	 * If in holdoff mode, just return.  We will presumably have
 	 * refrained from disabling the scheduling-clock tick.
 	 */
-	if (per_cpu(rcu_dyntick_holdoff, cpu) == jiffies) {
+	if (rdtp->dyntick_holdoff == jiffies) {
 		trace_rcu_prep_idle("In holdoff");
 		return;
 	}
 
-	/* Check and update the rcu_dyntick_drain sequencing. */
-	if (per_cpu(rcu_dyntick_drain, cpu) <= 0) {
+	/* Check and update the ->dyntick_drain sequencing. */
+	if (rdtp->dyntick_drain <= 0) {
 		/* First time through, initialize the counter. */
-		per_cpu(rcu_dyntick_drain, cpu) = RCU_IDLE_FLUSHES;
-	} else if (per_cpu(rcu_dyntick_drain, cpu) <= RCU_IDLE_OPT_FLUSHES &&
+		rdtp->dyntick_drain = RCU_IDLE_FLUSHES;
+	} else if (rdtp->dyntick_drain <= RCU_IDLE_OPT_FLUSHES &&
 		   !rcu_pending(cpu) &&
 		   !local_softirq_pending()) {
 		/* Can we go dyntick-idle despite still having callbacks? */
-		trace_rcu_prep_idle("Dyntick with callbacks");
-		per_cpu(rcu_dyntick_drain, cpu) = 0;
-		per_cpu(rcu_dyntick_holdoff, cpu) = jiffies;
-		if (rcu_cpu_has_nonlazy_callbacks(cpu))
-			per_cpu(rcu_idle_gp_timer_expires, cpu) =
+		rdtp->dyntick_drain = 0;
+		rdtp->dyntick_holdoff = jiffies;
+		if (rcu_cpu_has_nonlazy_callbacks(cpu)) {
+			trace_rcu_prep_idle("Dyntick with callbacks");
+			rdtp->idle_gp_timer_expires =
 					   jiffies + RCU_IDLE_GP_DELAY;
-		else
-			per_cpu(rcu_idle_gp_timer_expires, cpu) =
+		} else {
+			rdtp->idle_gp_timer_expires =
 					   jiffies + RCU_IDLE_LAZY_GP_DELAY;
-		tp = &per_cpu(rcu_idle_gp_timer, cpu);
-		mod_timer_pinned(tp, per_cpu(rcu_idle_gp_timer_expires, cpu));
-		per_cpu(rcu_nonlazy_posted_snap, cpu) =
-			per_cpu(rcu_nonlazy_posted, cpu);
+			trace_rcu_prep_idle("Dyntick with lazy callbacks");
+		}
+		tp = &rdtp->idle_gp_timer;
+		mod_timer_pinned(tp, rdtp->idle_gp_timer_expires);
+		rdtp->nonlazy_posted_snap = rdtp->nonlazy_posted;
 		return; /* Nothing more to do immediately. */
-	} else if (--per_cpu(rcu_dyntick_drain, cpu) <= 0) {
+	} else if (--(rdtp->dyntick_drain) <= 0) {
 		/* We have hit the limit, so time to give up. */
-		per_cpu(rcu_dyntick_holdoff, cpu) = jiffies;
+		rdtp->dyntick_holdoff = jiffies;
 		trace_rcu_prep_idle("Begin holdoff");
 		invoke_rcu_core();  /* Force the CPU out of dyntick-idle. */
 		return;
@@ -2227,7 +2245,7 @@ static void rcu_prepare_for_idle(int cpu)
  */
 static void rcu_idle_count_callbacks_posted(void)
 {
-	__this_cpu_add(rcu_nonlazy_posted, 1);
+	__this_cpu_add(rcu_dynticks.nonlazy_posted, 1);
 }
 
 #endif /* #else #if !defined(CONFIG_RCU_FAST_NO_HZ) */
@@ -2238,11 +2256,12 @@ static void rcu_idle_count_callbacks_posted(void)
 
 static void print_cpu_stall_fast_no_hz(char *cp, int cpu)
 {
-	struct timer_list *tltp = &per_cpu(rcu_idle_gp_timer, cpu);
+	struct rcu_dynticks *rdtp = &per_cpu(rcu_dynticks, cpu);
+	struct timer_list *tltp = &rdtp->idle_gp_timer;
 
 	sprintf(cp, "drain=%d %c timer=%lu",
-		per_cpu(rcu_dyntick_drain, cpu),
-		per_cpu(rcu_dyntick_holdoff, cpu) == jiffies ? 'H' : '.',
+		rdtp->dyntick_drain,
+		rdtp->dyntick_holdoff == jiffies ? 'H' : '.',
 		timer_pending(tltp) ? tltp->expires - jiffies : -1);
 }
 
diff --git a/kernel/relay.c b/kernel/relay.c
index ab56a1764d4..e8cd2027abb 100644
--- a/kernel/relay.c
+++ b/kernel/relay.c
@@ -1235,6 +1235,7 @@ static ssize_t subbuf_splice_actor(struct file *in,
 	struct splice_pipe_desc spd = {
 		.pages = pages,
 		.nr_pages = 0,
+		.nr_pages_max = PIPE_DEF_BUFFERS,
 		.partial = partial,
 		.flags = flags,
 		.ops = &relay_pipe_buf_ops,
@@ -1302,8 +1303,8 @@ static ssize_t subbuf_splice_actor(struct file *in,
                 ret += padding;
 
 out:
-	splice_shrink_spd(pipe, &spd);
-        return ret;
+	splice_shrink_spd(&spd);
+	return ret;
 }
 
 static ssize_t relay_file_splice_read(struct file *in,
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index d5594a4268d..468bdd44c1b 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -2081,7 +2081,6 @@ context_switch(struct rq *rq, struct task_struct *prev,
 #endif
 
 	/* Here we just switch the register state and the stack. */
-	rcu_switch_from(prev);
 	switch_to(prev, next, prev);
 
 	barrier();
@@ -2161,11 +2160,73 @@ unsigned long this_cpu_load(void)
 }
 
 
+/*
+ * Global load-average calculations
+ *
+ * We take a distributed and async approach to calculating the global load-avg
+ * in order to minimize overhead.
+ *
+ * The global load average is an exponentially decaying average of nr_running +
+ * nr_uninterruptible.
+ *
+ * Once every LOAD_FREQ:
+ *
+ *   nr_active = 0;
+ *   for_each_possible_cpu(cpu)
+ *   	nr_active += cpu_of(cpu)->nr_running + cpu_of(cpu)->nr_uninterruptible;
+ *
+ *   avenrun[n] = avenrun[0] * exp_n + nr_active * (1 - exp_n)
+ *
+ * Due to a number of reasons the above turns in the mess below:
+ *
+ *  - for_each_possible_cpu() is prohibitively expensive on machines with
+ *    serious number of cpus, therefore we need to take a distributed approach
+ *    to calculating nr_active.
+ *
+ *        \Sum_i x_i(t) = \Sum_i x_i(t) - x_i(t_0) | x_i(t_0) := 0
+ *                      = \Sum_i { \Sum_j=1 x_i(t_j) - x_i(t_j-1) }
+ *
+ *    So assuming nr_active := 0 when we start out -- true per definition, we
+ *    can simply take per-cpu deltas and fold those into a global accumulate
+ *    to obtain the same result. See calc_load_fold_active().
+ *
+ *    Furthermore, in order to avoid synchronizing all per-cpu delta folding
+ *    across the machine, we assume 10 ticks is sufficient time for every
+ *    cpu to have completed this task.
+ *
+ *    This places an upper-bound on the IRQ-off latency of the machine. Then
+ *    again, being late doesn't loose the delta, just wrecks the sample.
+ *
+ *  - cpu_rq()->nr_uninterruptible isn't accurately tracked per-cpu because
+ *    this would add another cross-cpu cacheline miss and atomic operation
+ *    to the wakeup path. Instead we increment on whatever cpu the task ran
+ *    when it went into uninterruptible state and decrement on whatever cpu
+ *    did the wakeup. This means that only the sum of nr_uninterruptible over
+ *    all cpus yields the correct result.
+ *
+ *  This covers the NO_HZ=n code, for extra head-aches, see the comment below.
+ */
+
 /* Variables and functions for calc_load */
 static atomic_long_t calc_load_tasks;
 static unsigned long calc_load_update;
 unsigned long avenrun[3];
-EXPORT_SYMBOL(avenrun);
+EXPORT_SYMBOL(avenrun); /* should be removed */
+
+/**
+ * get_avenrun - get the load average array
+ * @loads:	pointer to dest load array
+ * @offset:	offset to add
+ * @shift:	shift count to shift the result left
+ *
+ * These values are estimates at best, so no need for locking.
+ */
+void get_avenrun(unsigned long *loads, unsigned long offset, int shift)
+{
+	loads[0] = (avenrun[0] + offset) << shift;
+	loads[1] = (avenrun[1] + offset) << shift;
+	loads[2] = (avenrun[2] + offset) << shift;
+}
 
 static long calc_load_fold_active(struct rq *this_rq)
 {
@@ -2182,6 +2243,9 @@ static long calc_load_fold_active(struct rq *this_rq)
 	return delta;
 }
 
+/*
+ * a1 = a0 * e + a * (1 - e)
+ */
 static unsigned long
 calc_load(unsigned long load, unsigned long exp, unsigned long active)
 {
@@ -2193,30 +2257,118 @@ calc_load(unsigned long load, unsigned long exp, unsigned long active)
 
 #ifdef CONFIG_NO_HZ
 /*
- * For NO_HZ we delay the active fold to the next LOAD_FREQ update.
+ * Handle NO_HZ for the global load-average.
+ *
+ * Since the above described distributed algorithm to compute the global
+ * load-average relies on per-cpu sampling from the tick, it is affected by
+ * NO_HZ.
+ *
+ * The basic idea is to fold the nr_active delta into a global idle-delta upon
+ * entering NO_HZ state such that we can include this as an 'extra' cpu delta
+ * when we read the global state.
+ *
+ * Obviously reality has to ruin such a delightfully simple scheme:
+ *
+ *  - When we go NO_HZ idle during the window, we can negate our sample
+ *    contribution, causing under-accounting.
+ *
+ *    We avoid this by keeping two idle-delta counters and flipping them
+ *    when the window starts, thus separating old and new NO_HZ load.
+ *
+ *    The only trick is the slight shift in index flip for read vs write.
+ *
+ *        0s            5s            10s           15s
+ *          +10           +10           +10           +10
+ *        |-|-----------|-|-----------|-|-----------|-|
+ *    r:0 0 1           1 0           0 1           1 0
+ *    w:0 1 1           0 0           1 1           0 0
+ *
+ *    This ensures we'll fold the old idle contribution in this window while
+ *    accumlating the new one.
+ *
+ *  - When we wake up from NO_HZ idle during the window, we push up our
+ *    contribution, since we effectively move our sample point to a known
+ *    busy state.
+ *
+ *    This is solved by pushing the window forward, and thus skipping the
+ *    sample, for this cpu (effectively using the idle-delta for this cpu which
+ *    was in effect at the time the window opened). This also solves the issue
+ *    of having to deal with a cpu having been in NOHZ idle for multiple
+ *    LOAD_FREQ intervals.
  *
  * When making the ILB scale, we should try to pull this in as well.
  */
-static atomic_long_t calc_load_tasks_idle;
+static atomic_long_t calc_load_idle[2];
+static int calc_load_idx;
 
-void calc_load_account_idle(struct rq *this_rq)
+static inline int calc_load_write_idx(void)
 {
+	int idx = calc_load_idx;
+
+	/*
+	 * See calc_global_nohz(), if we observe the new index, we also
+	 * need to observe the new update time.
+	 */
+	smp_rmb();
+
+	/*
+	 * If the folding window started, make sure we start writing in the
+	 * next idle-delta.
+	 */
+	if (!time_before(jiffies, calc_load_update))
+		idx++;
+
+	return idx & 1;
+}
+
+static inline int calc_load_read_idx(void)
+{
+	return calc_load_idx & 1;
+}
+
+void calc_load_enter_idle(void)
+{
+	struct rq *this_rq = this_rq();
 	long delta;
 
+	/*
+	 * We're going into NOHZ mode, if there's any pending delta, fold it
+	 * into the pending idle delta.
+	 */
 	delta = calc_load_fold_active(this_rq);
-	if (delta)
-		atomic_long_add(delta, &calc_load_tasks_idle);
+	if (delta) {
+		int idx = calc_load_write_idx();
+		atomic_long_add(delta, &calc_load_idle[idx]);
+	}
 }
 
-static long calc_load_fold_idle(void)
+void calc_load_exit_idle(void)
 {
-	long delta = 0;
+	struct rq *this_rq = this_rq();
+
+	/*
+	 * If we're still before the sample window, we're done.
+	 */
+	if (time_before(jiffies, this_rq->calc_load_update))
+		return;
 
 	/*
-	 * Its got a race, we don't care...
+	 * We woke inside or after the sample window, this means we're already
+	 * accounted through the nohz accounting, so skip the entire deal and
+	 * sync up for the next window.
 	 */
-	if (atomic_long_read(&calc_load_tasks_idle))
-		delta = atomic_long_xchg(&calc_load_tasks_idle, 0);
+	this_rq->calc_load_update = calc_load_update;
+	if (time_before(jiffies, this_rq->calc_load_update + 10))
+		this_rq->calc_load_update += LOAD_FREQ;
+}
+
+static long calc_load_fold_idle(void)
+{
+	int idx = calc_load_read_idx();
+	long delta = 0;
+
+	if (atomic_long_read(&calc_load_idle[idx]))
+		delta = atomic_long_xchg(&calc_load_idle[idx], 0);
 
 	return delta;
 }
@@ -2302,66 +2454,39 @@ static void calc_global_nohz(void)
 {
 	long delta, active, n;
 
-	/*
-	 * If we crossed a calc_load_update boundary, make sure to fold
-	 * any pending idle changes, the respective CPUs might have
-	 * missed the tick driven calc_load_account_active() update
-	 * due to NO_HZ.
-	 */
-	delta = calc_load_fold_idle();
-	if (delta)
-		atomic_long_add(delta, &calc_load_tasks);
-
-	/*
-	 * It could be the one fold was all it took, we done!
-	 */
-	if (time_before(jiffies, calc_load_update + 10))
-		return;
-
-	/*
-	 * Catch-up, fold however many we are behind still
-	 */
-	delta = jiffies - calc_load_update - 10;
-	n = 1 + (delta / LOAD_FREQ);
+	if (!time_before(jiffies, calc_load_update + 10)) {
+		/*
+		 * Catch-up, fold however many we are behind still
+		 */
+		delta = jiffies - calc_load_update - 10;
+		n = 1 + (delta / LOAD_FREQ);
 
-	active = atomic_long_read(&calc_load_tasks);
-	active = active > 0 ? active * FIXED_1 : 0;
+		active = atomic_long_read(&calc_load_tasks);
+		active = active > 0 ? active * FIXED_1 : 0;
 
-	avenrun[0] = calc_load_n(avenrun[0], EXP_1, active, n);
-	avenrun[1] = calc_load_n(avenrun[1], EXP_5, active, n);
-	avenrun[2] = calc_load_n(avenrun[2], EXP_15, active, n);
+		avenrun[0] = calc_load_n(avenrun[0], EXP_1, active, n);
+		avenrun[1] = calc_load_n(avenrun[1], EXP_5, active, n);
+		avenrun[2] = calc_load_n(avenrun[2], EXP_15, active, n);
 
-	calc_load_update += n * LOAD_FREQ;
-}
-#else
-void calc_load_account_idle(struct rq *this_rq)
-{
-}
+		calc_load_update += n * LOAD_FREQ;
+	}
 
-static inline long calc_load_fold_idle(void)
-{
-	return 0;
+	/*
+	 * Flip the idle index...
+	 *
+	 * Make sure we first write the new time then flip the index, so that
+	 * calc_load_write_idx() will see the new time when it reads the new
+	 * index, this avoids a double flip messing things up.
+	 */
+	smp_wmb();
+	calc_load_idx++;
 }
+#else /* !CONFIG_NO_HZ */
 
-static void calc_global_nohz(void)
-{
-}
-#endif
+static inline long calc_load_fold_idle(void) { return 0; }
+static inline void calc_global_nohz(void) { }
 
-/**
- * get_avenrun - get the load average array
- * @loads:	pointer to dest load array
- * @offset:	offset to add
- * @shift:	shift count to shift the result left
- *
- * These values are estimates at best, so no need for locking.
- */
-void get_avenrun(unsigned long *loads, unsigned long offset, int shift)
-{
-	loads[0] = (avenrun[0] + offset) << shift;
-	loads[1] = (avenrun[1] + offset) << shift;
-	loads[2] = (avenrun[2] + offset) << shift;
-}
+#endif /* CONFIG_NO_HZ */
 
 /*
  * calc_load - update the avenrun load estimates 10 ticks after the
@@ -2369,11 +2494,18 @@ void get_avenrun(unsigned long *loads, unsigned long offset, int shift)
  */
 void calc_global_load(unsigned long ticks)
 {
-	long active;
+	long active, delta;
 
 	if (time_before(jiffies, calc_load_update + 10))
 		return;
 
+	/*
+	 * Fold the 'old' idle-delta to include all NO_HZ cpus.
+	 */
+	delta = calc_load_fold_idle();
+	if (delta)
+		atomic_long_add(delta, &calc_load_tasks);
+
 	active = atomic_long_read(&calc_load_tasks);
 	active = active > 0 ? active * FIXED_1 : 0;
 
@@ -2384,12 +2516,7 @@ void calc_global_load(unsigned long ticks)
 	calc_load_update += LOAD_FREQ;
 
 	/*
-	 * Account one period with whatever state we found before
-	 * folding in the nohz state and ageing the entire idle period.
-	 *
-	 * This avoids loosing a sample when we go idle between 
-	 * calc_load_account_active() (10 ticks ago) and now and thus
-	 * under-accounting.
+	 * In case we idled for multiple LOAD_FREQ intervals, catch up in bulk.
 	 */
 	calc_global_nohz();
 }
@@ -2406,7 +2533,6 @@ static void calc_load_account_active(struct rq *this_rq)
 		return;
 
 	delta  = calc_load_fold_active(this_rq);
-	delta += calc_load_fold_idle();
 	if (delta)
 		atomic_long_add(delta, &calc_load_tasks);
 
@@ -2414,6 +2540,10 @@ static void calc_load_account_active(struct rq *this_rq)
 }
 
 /*
+ * End of global load-average stuff
+ */
+
+/*
  * The exact cpuload at various idx values, calculated at every tick would be
  * load = (2^idx - 1) / 2^idx * load + 1 / 2^idx * cur_load
  *
diff --git a/kernel/sched/idle_task.c b/kernel/sched/idle_task.c
index b44d604b35d..b6baf370cae 100644
--- a/kernel/sched/idle_task.c
+++ b/kernel/sched/idle_task.c
@@ -25,7 +25,6 @@ static void check_preempt_curr_idle(struct rq *rq, struct task_struct *p, int fl
 static struct task_struct *pick_next_task_idle(struct rq *rq)
 {
 	schedstat_inc(rq, sched_goidle);
-	calc_load_account_idle(rq);
 	return rq->idle;
 }
 
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 6d52cea7f33..55844f24435 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -942,8 +942,6 @@ static inline u64 sched_avg_period(void)
 	return (u64)sysctl_sched_time_avg * NSEC_PER_MSEC / 2;
 }
 
-void calc_load_account_idle(struct rq *this_rq);
-
 #ifdef CONFIG_SCHED_HRTICK
 
 /*
diff --git a/kernel/sys.c b/kernel/sys.c
index f0ec44dcd41..2d39a84cd85 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -1788,7 +1788,6 @@ SYSCALL_DEFINE1(umask, int, mask)
 #ifdef CONFIG_CHECKPOINT_RESTORE
 static int prctl_set_mm_exe_file(struct mm_struct *mm, unsigned int fd)
 {
-	struct vm_area_struct *vma;
 	struct file *exe_file;
 	struct dentry *dentry;
 	int err;
@@ -1816,13 +1815,17 @@ static int prctl_set_mm_exe_file(struct mm_struct *mm, unsigned int fd)
 	down_write(&mm->mmap_sem);
 
 	/*
-	 * Forbid mm->exe_file change if there are mapped other files.
+	 * Forbid mm->exe_file change if old file still mapped.
 	 */
 	err = -EBUSY;
-	for (vma = mm->mmap; vma; vma = vma->vm_next) {
-		if (vma->vm_file && !path_equal(&vma->vm_file->f_path,
-						&exe_file->f_path))
-			goto exit_unlock;
+	if (mm->exe_file) {
+		struct vm_area_struct *vma;
+
+		for (vma = mm->mmap; vma; vma = vma->vm_next)
+			if (vma->vm_file &&
+			    path_equal(&vma->vm_file->f_path,
+				       &mm->exe_file->f_path))
+				goto exit_unlock;
 	}
 
 	/*
@@ -1835,6 +1838,7 @@ static int prctl_set_mm_exe_file(struct mm_struct *mm, unsigned int fd)
 	if (test_and_set_bit(MMF_EXE_FILE_CHANGED, &mm->flags))
 		goto exit_unlock;
 
+	err = 0;
 	set_mm_exe_file(mm, exe_file);
 exit_unlock:
 	up_write(&mm->mmap_sem);
@@ -2127,9 +2131,6 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
 				else
 					return -EINVAL;
 				break;
-		case PR_GET_TID_ADDRESS:
-			error = prctl_get_tid_address(me, (int __user **)arg2);
-			break;
 			default:
 				return -EINVAL;
 			}
@@ -2147,6 +2148,9 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
 		case PR_SET_MM:
 			error = prctl_set_mm(arg2, arg3, arg4, arg5);
 			break;
+		case PR_GET_TID_ADDRESS:
+			error = prctl_get_tid_address(me, (int __user **)arg2);
+			break;
 		case PR_SET_CHILD_SUBREAPER:
 			me->signal->is_child_subreaper = !!arg2;
 			error = 0;
diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c
index 70b33abcc7b..b7fbadc5c97 100644
--- a/kernel/time/ntp.c
+++ b/kernel/time/ntp.c
@@ -409,7 +409,9 @@ int second_overflow(unsigned long secs)
 			time_state = TIME_DEL;
 		break;
 	case TIME_INS:
-		if (secs % 86400 == 0) {
+		if (!(time_status & STA_INS))
+			time_state = TIME_OK;
+		else if (secs % 86400 == 0) {
 			leap = -1;
 			time_state = TIME_OOP;
 			time_tai++;
@@ -418,7 +420,9 @@ int second_overflow(unsigned long secs)
 		}
 		break;
 	case TIME_DEL:
-		if ((secs + 1) % 86400 == 0) {
+		if (!(time_status & STA_DEL))
+			time_state = TIME_OK;
+		else if ((secs + 1) % 86400 == 0) {
 			leap = 1;
 			time_tai--;
 			time_state = TIME_WAIT;
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 60c9c60e910..41be02250e0 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -276,10 +276,10 @@ static ktime_t tick_nohz_stop_sched_tick(struct tick_sched *ts,
 {
 	unsigned long seq, last_jiffies, next_jiffies, delta_jiffies;
 	ktime_t last_update, expires, ret = { .tv64 = 0 };
+	unsigned long rcu_delta_jiffies;
 	struct clock_event_device *dev = __get_cpu_var(tick_cpu_device).evtdev;
 	u64 time_delta;
 
-
 	/* Read jiffies and the time when jiffies were updated last */
 	do {
 		seq = read_seqbegin(&xtime_lock);
@@ -288,7 +288,7 @@ static ktime_t tick_nohz_stop_sched_tick(struct tick_sched *ts,
 		time_delta = timekeeping_max_deferment();
 	} while (read_seqretry(&xtime_lock, seq));
 
-	if (rcu_needs_cpu(cpu) || printk_needs_cpu(cpu) ||
+	if (rcu_needs_cpu(cpu, &rcu_delta_jiffies) || printk_needs_cpu(cpu) ||
 	    arch_needs_cpu(cpu)) {
 		next_jiffies = last_jiffies + 1;
 		delta_jiffies = 1;
@@ -296,6 +296,10 @@ static ktime_t tick_nohz_stop_sched_tick(struct tick_sched *ts,
 		/* Get the next timer wheel timer */
 		next_jiffies = get_next_timer_interrupt(last_jiffies);
 		delta_jiffies = next_jiffies - last_jiffies;
+		if (rcu_delta_jiffies < delta_jiffies) {
+			next_jiffies = last_jiffies + rcu_delta_jiffies;
+			delta_jiffies = rcu_delta_jiffies;
+		}
 	}
 	/*
 	 * Do not stop the tick, if we are only one off
@@ -369,6 +373,7 @@ static ktime_t tick_nohz_stop_sched_tick(struct tick_sched *ts,
 		 */
 		if (!ts->tick_stopped) {
 			select_nohz_load_balancer(1);
+			calc_load_enter_idle();
 
 			ts->last_tick = hrtimer_get_expires(&ts->sched_timer);
 			ts->tick_stopped = 1;
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index 6f46a00a1e8..269b1fe5f2a 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -70,6 +70,12 @@ struct timekeeper {
 	/* The raw monotonic time for the CLOCK_MONOTONIC_RAW posix clock. */
 	struct timespec raw_time;
 
+	/* Offset clock monotonic -> clock realtime */
+	ktime_t offs_real;
+
+	/* Offset clock monotonic -> clock boottime */
+	ktime_t offs_boot;
+
 	/* Seqlock for all timekeeper values */
 	seqlock_t lock;
 };
@@ -172,6 +178,14 @@ static inline s64 timekeeping_get_ns_raw(void)
 	return clocksource_cyc2ns(cycle_delta, clock->mult, clock->shift);
 }
 
+static void update_rt_offset(void)
+{
+	struct timespec tmp, *wtm = &timekeeper.wall_to_monotonic;
+
+	set_normalized_timespec(&tmp, -wtm->tv_sec, -wtm->tv_nsec);
+	timekeeper.offs_real = timespec_to_ktime(tmp);
+}
+
 /* must hold write on timekeeper.lock */
 static void timekeeping_update(bool clearntp)
 {
@@ -179,6 +193,7 @@ static void timekeeping_update(bool clearntp)
 		timekeeper.ntp_error = 0;
 		ntp_clear();
 	}
+	update_rt_offset();
 	update_vsyscall(&timekeeper.xtime, &timekeeper.wall_to_monotonic,
 			 timekeeper.clock, timekeeper.mult);
 }
@@ -604,6 +619,7 @@ void __init timekeeping_init(void)
 	}
 	set_normalized_timespec(&timekeeper.wall_to_monotonic,
 				-boot.tv_sec, -boot.tv_nsec);
+	update_rt_offset();
 	timekeeper.total_sleep_time.tv_sec = 0;
 	timekeeper.total_sleep_time.tv_nsec = 0;
 	write_sequnlock_irqrestore(&timekeeper.lock, flags);
@@ -612,6 +628,12 @@ void __init timekeeping_init(void)
 /* time in seconds when suspend began */
 static struct timespec timekeeping_suspend_time;
 
+static void update_sleep_time(struct timespec t)
+{
+	timekeeper.total_sleep_time = t;
+	timekeeper.offs_boot = timespec_to_ktime(t);
+}
+
 /**
  * __timekeeping_inject_sleeptime - Internal function to add sleep interval
  * @delta: pointer to a timespec delta value
@@ -630,8 +652,7 @@ static void __timekeeping_inject_sleeptime(struct timespec *delta)
 	timekeeper.xtime = timespec_add(timekeeper.xtime, *delta);
 	timekeeper.wall_to_monotonic =
 			timespec_sub(timekeeper.wall_to_monotonic, *delta);
-	timekeeper.total_sleep_time = timespec_add(
-					timekeeper.total_sleep_time, *delta);
+	update_sleep_time(timespec_add(timekeeper.total_sleep_time, *delta));
 }
 
 
@@ -963,6 +984,8 @@ static cycle_t logarithmic_accumulation(cycle_t offset, int shift)
 		leap = second_overflow(timekeeper.xtime.tv_sec);
 		timekeeper.xtime.tv_sec += leap;
 		timekeeper.wall_to_monotonic.tv_sec -= leap;
+		if (leap)
+			clock_was_set_delayed();
 	}
 
 	/* Accumulate raw time */
@@ -1079,6 +1102,8 @@ static void update_wall_time(void)
 		leap = second_overflow(timekeeper.xtime.tv_sec);
 		timekeeper.xtime.tv_sec += leap;
 		timekeeper.wall_to_monotonic.tv_sec -= leap;
+		if (leap)
+			clock_was_set_delayed();
 	}
 
 	timekeeping_update(false);
@@ -1246,6 +1271,40 @@ void get_xtime_and_monotonic_and_sleep_offset(struct timespec *xtim,
 	} while (read_seqretry(&timekeeper.lock, seq));
 }
 
+#ifdef CONFIG_HIGH_RES_TIMERS
+/**
+ * ktime_get_update_offsets - hrtimer helper
+ * @offs_real:	pointer to storage for monotonic -> realtime offset
+ * @offs_boot:	pointer to storage for monotonic -> boottime offset
+ *
+ * Returns current monotonic time and updates the offsets
+ * Called from hrtimer_interupt() or retrigger_next_event()
+ */
+ktime_t ktime_get_update_offsets(ktime_t *offs_real, ktime_t *offs_boot)
+{
+	ktime_t now;
+	unsigned int seq;
+	u64 secs, nsecs;
+
+	do {
+		seq = read_seqbegin(&timekeeper.lock);
+
+		secs = timekeeper.xtime.tv_sec;
+		nsecs = timekeeper.xtime.tv_nsec;
+		nsecs += timekeeping_get_ns();
+		/* If arch requires, add in gettimeoffset() */
+		nsecs += arch_gettimeoffset();
+
+		*offs_real = timekeeper.offs_real;
+		*offs_boot = timekeeper.offs_boot;
+	} while (read_seqretry(&timekeeper.lock, seq));
+
+	now = ktime_add_ns(ktime_set(secs, 0), nsecs);
+	now = ktime_sub(now, *offs_real);
+	return now;
+}
+#endif
+
 /**
  * ktime_get_monotonic_offset() - get wall_to_monotonic in ktime_t format
  */
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 1d0f6a8a0e5..f765465bffe 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -1075,6 +1075,7 @@ rb_allocate_cpu_buffer(struct ring_buffer *buffer, int nr_pages, int cpu)
 	rb_init_page(bpage->page);
 
 	INIT_LIST_HEAD(&cpu_buffer->reader_page->list);
+	INIT_LIST_HEAD(&cpu_buffer->new_pages);
 
 	ret = rb_allocate_pages(cpu_buffer, nr_pages);
 	if (ret < 0)
@@ -1346,10 +1347,9 @@ rb_remove_pages(struct ring_buffer_per_cpu *cpu_buffer, unsigned int nr_pages)
 			 * If something was added to this page, it was full
 			 * since it is not the tail page. So we deduct the
 			 * bytes consumed in ring buffer from here.
-			 * No need to update overruns, since this page is
-			 * deleted from ring buffer and its entries are
-			 * already accounted for.
+			 * Increment overrun to account for the lost events.
 			 */
+			local_add(page_entries, &cpu_buffer->overrun);
 			local_sub(BUF_PAGE_SIZE, &cpu_buffer->entries_bytes);
 		}
 
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 68032c6177d..a7fa0702be1 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -371,7 +371,7 @@ EXPORT_SYMBOL_GPL(tracing_on);
 void tracing_off(void)
 {
 	if (global_trace.buffer)
-		ring_buffer_record_on(global_trace.buffer);
+		ring_buffer_record_off(global_trace.buffer);
 	/*
 	 * This flag is only looked at when buffers haven't been
 	 * allocated yet. We don't really care about the race
@@ -3609,6 +3609,7 @@ static ssize_t tracing_splice_read_pipe(struct file *filp,
 		.pages		= pages_def,
 		.partial	= partial_def,
 		.nr_pages	= 0, /* This gets updated below. */
+		.nr_pages_max	= PIPE_DEF_BUFFERS,
 		.flags		= flags,
 		.ops		= &tracing_pipe_buf_ops,
 		.spd_release	= tracing_spd_release_pipe,
@@ -3680,7 +3681,7 @@ static ssize_t tracing_splice_read_pipe(struct file *filp,
 
 	ret = splice_to_pipe(pipe, &spd);
 out:
-	splice_shrink_spd(pipe, &spd);
+	splice_shrink_spd(&spd);
 	return ret;
 
 out_err:
@@ -4231,6 +4232,7 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
 	struct splice_pipe_desc spd = {
 		.pages		= pages_def,
 		.partial	= partial_def,
+		.nr_pages_max	= PIPE_DEF_BUFFERS,
 		.flags		= flags,
 		.ops		= &buffer_pipe_buf_ops,
 		.spd_release	= buffer_spd_release,
@@ -4318,7 +4320,7 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
 	}
 
 	ret = splice_to_pipe(pipe, &spd);
-	splice_shrink_spd(pipe, &spd);
+	splice_shrink_spd(&spd);
 out:
 	return ret;
 }
diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index e5e1d85b8c7..4b1dfba70f7 100644
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -372,6 +372,13 @@ static int watchdog(void *unused)
 
 
 #ifdef CONFIG_HARDLOCKUP_DETECTOR
+/*
+ * People like the simple clean cpu node info on boot.
+ * Reduce the watchdog noise by only printing messages
+ * that are different from what cpu0 displayed.
+ */
+static unsigned long cpu0_err;
+
 static int watchdog_nmi_enable(int cpu)
 {
 	struct perf_event_attr *wd_attr;
@@ -390,11 +397,21 @@ static int watchdog_nmi_enable(int cpu)
 
 	/* Try to register using hardware perf events */
 	event = perf_event_create_kernel_counter(wd_attr, cpu, NULL, watchdog_overflow_callback, NULL);
+
+	/* save cpu0 error for future comparision */
+	if (cpu == 0 && IS_ERR(event))
+		cpu0_err = PTR_ERR(event);
+
 	if (!IS_ERR(event)) {
-		pr_info("enabled, takes one hw-pmu counter.\n");
+		/* only print for cpu0 or different than cpu0 */
+		if (cpu == 0 || cpu0_err)
+			pr_info("enabled on all CPUs, permanently consumes one hw-PMU counter.\n");
 		goto out_save;
 	}
 
+	/* skip displaying the same error again */
+	if (cpu > 0 && (PTR_ERR(event) == cpu0_err))
+		return PTR_ERR(event);
 
 	/* vary the KERN level based on the returned errno */
 	if (PTR_ERR(event) == -EOPNOTSUPP)