Merge branch 'topic/hda' into for-next

This is a large chunk merge for 3.6 HD-audio things

24 files changed, 996 insertions, 384 deletions

diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 0f3527d6184a..2097684cf194 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 */
@@ -896,10 +901,13 @@ static void cgroup_diput(struct dentry *dentry, struct inode *inode)
 		mutex_unlock(&cgroup_mutex);
 
 		/*
-		 * Drop the active superblock reference that we took when we
-		 * created the cgroup
+		 * 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().
 		 */
-		deactivate_super(cgrp->root->sb);
+		dentry->d_fsdata = cgroup_diput;
 
 		/*
 		 * if we're getting rid of the cgroup, refcount should ensure
@@ -925,6 +933,13 @@ 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);
@@ -1532,6 +1547,7 @@ 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 =
@@ -4971,10 +4987,12 @@ 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 5b06cbbf6931..d7d71d6ec972 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
@@ -3181,7 +3185,6 @@ static void perf_event_for_each(struct perf_event *event,
 	event = event->group_leader;
 
 	perf_event_for_each_child(event, func);
-	func(event);
 	list_for_each_entry(sibling, &event->sibling_list, group_entry)
 		perf_event_for_each_child(sibling, func);
 	mutex_unlock(&ctx->mutex);
diff --git a/kernel/exit.c b/kernel/exit.c
index 34867cc5b42a..2f59cc334516 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/irq/chip.c b/kernel/irq/chip.c
index fc275e4f629b..eebd6d5cfb44 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -275,8 +275,10 @@ void handle_nested_irq(unsigned int irq)
 	kstat_incr_irqs_this_cpu(irq, desc);
 
 	action = desc->action;
-	if (unlikely(!action || irqd_irq_disabled(&desc->irq_data)))
+	if (unlikely(!action || irqd_irq_disabled(&desc->irq_data))) {
+		desc->istate |= IRQS_PENDING;
 		goto out_unlock;
+	}
 
 	irqd_set(&desc->irq_data, IRQD_IRQ_INPROGRESS);
 	raw_spin_unlock_irq(&desc->lock);
@@ -324,8 +326,10 @@ handle_simple_irq(unsigned int irq, struct irq_desc *desc)
 	desc->istate &= ~(IRQS_REPLAY | IRQS_WAITING);
 	kstat_incr_irqs_this_cpu(irq, desc);
 
-	if (unlikely(!desc->action || irqd_irq_disabled(&desc->irq_data)))
+	if (unlikely(!desc->action || irqd_irq_disabled(&desc->irq_data))) {
+		desc->istate |= IRQS_PENDING;
 		goto out_unlock;
+	}
 
 	handle_irq_event(desc);
 
diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h
index 8e5c56b3b7d9..001fa5bab490 100644
--- a/kernel/irq/internals.h
+++ b/kernel/irq/internals.h
@@ -101,6 +101,9 @@ extern int irq_select_affinity_usr(unsigned int irq, struct cpumask *mask);
 
 extern void irq_set_thread_affinity(struct irq_desc *desc);
 
+extern int irq_do_set_affinity(struct irq_data *data,
+			       const struct cpumask *dest, bool force);
+
 /* Inline functions for support of irq chips on slow busses */
 static inline void chip_bus_lock(struct irq_desc *desc)
 {
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index ea0c6c2ae6f7..8c548232ba39 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -142,6 +142,25 @@ static inline void
 irq_get_pending(struct cpumask *mask, struct irq_desc *desc) { }
 #endif
 
+int irq_do_set_affinity(struct irq_data *data, const struct cpumask *mask,
+			bool force)
+{
+	struct irq_desc *desc = irq_data_to_desc(data);
+	struct irq_chip *chip = irq_data_get_irq_chip(data);
+	int ret;
+
+	ret = chip->irq_set_affinity(data, mask, false);
+	switch (ret) {
+	case IRQ_SET_MASK_OK:
+		cpumask_copy(data->affinity, mask);
+	case IRQ_SET_MASK_OK_NOCOPY:
+		irq_set_thread_affinity(desc);
+		ret = 0;
+	}
+
+	return ret;
+}
+
 int __irq_set_affinity_locked(struct irq_data *data, const struct cpumask *mask)
 {
 	struct irq_chip *chip = irq_data_get_irq_chip(data);
@@ -152,14 +171,7 @@ int __irq_set_affinity_locked(struct irq_data *data, const struct cpumask *mask)
 		return -EINVAL;
 
 	if (irq_can_move_pcntxt(data)) {
-		ret = chip->irq_set_affinity(data, mask, false);
-		switch (ret) {
-		case IRQ_SET_MASK_OK:
-			cpumask_copy(data->affinity, mask);
-		case IRQ_SET_MASK_OK_NOCOPY:
-			irq_set_thread_affinity(desc);
-			ret = 0;
-		}
+		ret = irq_do_set_affinity(data, mask, false);
 	} else {
 		irqd_set_move_pending(data);
 		irq_copy_pending(desc, mask);
@@ -283,9 +295,8 @@ EXPORT_SYMBOL_GPL(irq_set_affinity_notifier);
 static int
 setup_affinity(unsigned int irq, struct irq_desc *desc, struct cpumask *mask)
 {
-	struct irq_chip *chip = irq_desc_get_chip(desc);
 	struct cpumask *set = irq_default_affinity;
-	int ret, node = desc->irq_data.node;
+	int node = desc->irq_data.node;
 
 	/* Excludes PER_CPU and NO_BALANCE interrupts */
 	if (!irq_can_set_affinity(irq))
@@ -311,13 +322,7 @@ setup_affinity(unsigned int irq, struct irq_desc *desc, struct cpumask *mask)
 		if (cpumask_intersects(mask, nodemask))
 			cpumask_and(mask, mask, nodemask);
 	}
-	ret = chip->irq_set_affinity(&desc->irq_data, mask, false);
-	switch (ret) {
-	case IRQ_SET_MASK_OK:
-		cpumask_copy(desc->irq_data.affinity, mask);
-	case IRQ_SET_MASK_OK_NOCOPY:
-		irq_set_thread_affinity(desc);
-	}
+	irq_do_set_affinity(&desc->irq_data, mask, false);
 	return 0;
 }
 #else
diff --git a/kernel/irq/migration.c b/kernel/irq/migration.c
index c3c89751b327..ca3f4aaff707 100644
--- a/kernel/irq/migration.c
+++ b/kernel/irq/migration.c
@@ -42,17 +42,8 @@ void irq_move_masked_irq(struct irq_data *idata)
 	 * For correct operation this depends on the caller
 	 * masking the irqs.
 	 */
-	if (likely(cpumask_any_and(desc->pending_mask, cpu_online_mask)
-		   < nr_cpu_ids)) {
-		int ret = chip->irq_set_affinity(&desc->irq_data,
-						 desc->pending_mask, false);
-		switch (ret) {
-		case IRQ_SET_MASK_OK:
-			cpumask_copy(desc->irq_data.affinity, desc->pending_mask);
-		case IRQ_SET_MASK_OK_NOCOPY:
-			irq_set_thread_affinity(desc);
-		}
-	}
+	if (cpumask_any_and(desc->pending_mask, cpu_online_mask) < nr_cpu_ids)
+		irq_do_set_affinity(&desc->irq_data, desc->pending_mask, false);
 
 	cpumask_clear(desc->pending_mask);
 }
diff --git a/kernel/panic.c b/kernel/panic.c
index 8ed89a175d79..d2a5f4ecc6dd 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 16b20e38c4a1..b3c7fd554250 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 32462d2b364a..dba18211685e 100644
--- a/kernel/printk.c
+++ b/kernel/printk.c
@@ -193,12 +193,19 @@ static int console_may_schedule;
  * separated by ',', and find the message after the ';' character.
  */
 
+enum log_flags {
+	LOG_DEFAULT = 0,
+	LOG_NOCONS = 1,		/* already flushed, do not print to console */
+};
+
 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 */
 };
 
 /*
@@ -227,10 +234,10 @@ 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 +293,7 @@ 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 +337,13 @@ 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;
 
@@ -414,7 +427,9 @@ static ssize_t devkmsg_read(struct file *file, char __user *buf,
 	if (!user)
 		return -EBADF;
 
-	mutex_lock(&user->lock);
+	ret = mutex_lock_interruptible(&user->lock);
+	if (ret)
+		return ret;
 	raw_spin_lock(&logbuf_lock);
 	while (user->seq == log_next_seq) {
 		if (file->f_flags & O_NONBLOCK) {
@@ -444,7 +459,7 @@ 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++) {
@@ -785,6 +800,21 @@ 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;
@@ -801,18 +831,7 @@ static size_t print_prefix(const struct log *msg, bool syslog, char *buf)
 		}
 	}
 
-	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;
 }
 
@@ -860,26 +879,49 @@ 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;
+
+		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;
+		}
+		if (syslog_seq == log_next_seq) {
+			raw_spin_unlock_irq(&logbuf_lock);
+			break;
+		}
+		msg = log_from_idx(syslog_idx);
+		n = msg_print_text(msg, true, text, LOG_LINE_MAX);
+		if (n <= size) {
+			syslog_idx = log_next(syslog_idx);
+			syslog_seq++;
+		} else
+			n = 0;
+		raw_spin_unlock_irq(&logbuf_lock);
+
+		if (!n)
+			break;
+
+		len += n;
+		size -= n;
+		buf += n;
+		n = copy_to_user(buf - n, text, n);
 
-	if (len > 0 && copy_to_user(buf, text, len))
-		len = -EFAULT;
+		if (n) {
+			len -= n;
+			if (!len)
+				len = -EFAULT;
+			break;
+		}
+	}
 
 	kfree(text);
 	return len;
@@ -909,7 +951,7 @@ 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;
 		while (seq < log_next_seq) {
@@ -919,6 +961,8 @@ static int syslog_print_all(char __user *buf, int size, bool clear)
 			idx = log_next(idx);
 			seq++;
 		}
+
+		/* move first record forward until length fits into the buffer */
 		seq = clear_seq;
 		idx = clear_idx;
 		while (len > size && seq < log_next_seq) {
@@ -929,7 +973,7 @@ static int syslog_print_all(char __user *buf, int size, bool clear)
 			seq++;
 		}
 
-		/* last message in this dump */
+		/* last message fitting into this dump */
 		next_seq = log_next_seq;
 
 		len = 0;
@@ -974,6 +1018,7 @@ int do_syslog(int type, char __user *buf, int len, bool from_file)
 {
 	bool clear = false;
 	static int saved_console_loglevel = -1;
+	static DEFINE_MUTEX(syslog_mutex);
 	int error;
 
 	error = check_syslog_permissions(type, from_file);
@@ -1000,11 +1045,17 @@ int do_syslog(int type, char __user *buf, int len, bool from_file)
 			error = -EFAULT;
 			goto out;
 		}
+		error = mutex_lock_interruptible(&syslog_mutex);
+		if (error)
+			goto out;
 		error = wait_event_interruptible(log_wait,
 						 syslog_seq != log_next_seq);
-		if (error)
+		if (error) {
+			mutex_unlock(&syslog_mutex);
 			goto out;
+		}
 		error = syslog_print(buf, len);
+		mutex_unlock(&syslog_mutex);
 		break;
 	/* Read/clear last kernel messages */
 	case SYSLOG_ACTION_READ_CLEAR:
@@ -1027,6 +1078,7 @@ 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)
@@ -1259,15 +1311,92 @@ 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;
@@ -1313,7 +1442,8 @@ 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_DEFAULT, 0,
+			  NULL, 0, recursion_msg, printed_len);
 	}
 
 	/*
@@ -1351,55 +1481,37 @@ asmlinkage int vprintk_emit(int facility, int level,
 	}
 
 	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;
-		}
+		/*
+		 * Flush the conflicting buffer. An earlier newline was missing,
+		 * or another task also prints continuation lines.
+		 */
+		if (cont.len && (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, LOG_DEFAULT, 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 (!prefix)
+				stored = cont_add(facility, level, text, text_len);
+			cont_flush();
 		}
+
+		if (!stored)
+			log_store(facility, level, LOG_DEFAULT, 0,
+				  dict, dictlen, text, text_len);
 	}
+	printed_len += text_len;
 
 	/*
 	 * Try to acquire and then immediately release the console semaphore.
@@ -1486,11 +1598,18 @@ 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 cont_print_text(char *text, size_t size) { return 0; }
 
 #endif /* CONFIG_PRINTK */
 
@@ -1782,6 +1901,7 @@ 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 +1914,23 @@ 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;
 
@@ -1812,13 +1945,22 @@ again:
 			console_seq = log_first_seq;
 			console_idx = log_first_idx;
 		}
-
+skip:
 		if (console_seq == log_next_seq)
 			break;
 
 		msg = log_from_idx(console_idx);
-		level = msg->level & 7;
+		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++;
+			goto skip;
+		}
 
+		level = msg->level;
 		len = msg_print_text(msg, false, text, sizeof(text));
 
 		console_idx = log_next(console_idx);
@@ -2300,48 +2442,210 @@ 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