Merge tag 'trace-3.10' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace

Pull tracing updates from Steven Rostedt:
 "Along with the usual minor fixes and clean ups there are a few major
  changes with this pull request.

   1) Multiple buffers for the ftrace facility

  This feature has been requested by many people over the last few
  years.  I even heard that Google was about to implement it themselves.
  I finally had time and cleaned up the code such that you can now
  create multiple instances of the ftrace buffer and have different
  events go to different buffers.  This way, a low frequency event will
  not be lost in the noise of a high frequency event.

  Note, currently only events can go to different buffers, the tracers
  (ie function, function_graph and the latency tracers) still can only
  be written to the main buffer.

   2) The function tracer triggers have now been extended.

  The function tracer had two triggers.  One to enable tracing when a
  function is hit, and one to disable tracing.  Now you can record a
  stack trace on a single (or many) function(s), take a snapshot of the
  buffer (copy it to the snapshot buffer), and you can enable or disable
  an event to be traced when a function is hit.

   3) A perf clock has been added.

  A "perf" clock can be chosen to be used when tracing.  This will cause
  ftrace to use the same clock as perf uses, and hopefully this will
  make it easier to interleave the perf and ftrace data for analysis."

* tag 'trace-3.10' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace: (82 commits)
  tracepoints: Prevent null probe from being added
  tracing: Compare to 1 instead of zero for is_signed_type()
  tracing: Remove obsolete macro guard _TRACE_PROFILE_INIT
  ftrace: Get rid of ftrace_profile_bits
  tracing: Check return value of tracing_init_dentry()
  tracing: Get rid of unneeded key calculation in ftrace_hash_move()
  tracing: Reset ftrace_graph_filter_enabled if count is zero
  tracing: Fix off-by-one on allocating stat->pages
  kernel: tracing: Use strlcpy instead of strncpy
  tracing: Update debugfs README file
  tracing: Fix ftrace_dump()
  tracing: Rename trace_event_mutex to trace_event_sem
  tracing: Fix comment about prefix in arch_syscall_match_sym_name()
  tracing: Convert trace_destroy_fields() to static
  tracing: Move find_event_field() into trace_events.c
  tracing: Use TRACE_MAX_PRINT instead of constant
  tracing: Use pr_warn_once instead of open coded implementation
  ring-buffer: Add ring buffer startup selftest
  tracing: Bring Documentation/trace/ftrace.txt up to date
  tracing: Add "perf" trace_clock
  ...

Conflicts:
	kernel/trace/ftrace.c
	kernel/trace/trace.c

26 files changed, 4013 insertions, 1248 deletions

diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index fc382d6e2765..5e9efd4b83a4 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -176,6 +176,8 @@ config IRQSOFF_TRACER
 	select GENERIC_TRACER
 	select TRACER_MAX_TRACE
 	select RING_BUFFER_ALLOW_SWAP
+	select TRACER_SNAPSHOT
+	select TRACER_SNAPSHOT_PER_CPU_SWAP
 	help
 	  This option measures the time spent in irqs-off critical
 	  sections, with microsecond accuracy.
@@ -198,6 +200,8 @@ config PREEMPT_TRACER
 	select GENERIC_TRACER
 	select TRACER_MAX_TRACE
 	select RING_BUFFER_ALLOW_SWAP
+	select TRACER_SNAPSHOT
+	select TRACER_SNAPSHOT_PER_CPU_SWAP
 	help
 	  This option measures the time spent in preemption-off critical
 	  sections, with microsecond accuracy.
@@ -217,6 +221,7 @@ config SCHED_TRACER
 	select GENERIC_TRACER
 	select CONTEXT_SWITCH_TRACER
 	select TRACER_MAX_TRACE
+	select TRACER_SNAPSHOT
 	help
 	  This tracer tracks the latency of the highest priority task
 	  to be scheduled in, starting from the point it has woken up.
@@ -248,6 +253,27 @@ config TRACER_SNAPSHOT
 	      echo 1 > /sys/kernel/debug/tracing/snapshot
 	      cat snapshot
 
+config TRACER_SNAPSHOT_PER_CPU_SWAP
+        bool "Allow snapshot to swap per CPU"
+	depends on TRACER_SNAPSHOT
+	select RING_BUFFER_ALLOW_SWAP
+	help
+	  Allow doing a snapshot of a single CPU buffer instead of a
+	  full swap (all buffers). If this is set, then the following is
+	  allowed:
+
+	      echo 1 > /sys/kernel/debug/tracing/per_cpu/cpu2/snapshot
+
+	  After which, only the tracing buffer for CPU 2 was swapped with
+	  the main tracing buffer, and the other CPU buffers remain the same.
+
+	  When this is enabled, this adds a little more overhead to the
+	  trace recording, as it needs to add some checks to synchronize
+	  recording with swaps. But this does not affect the performance
+	  of the overall system. This is enabled by default when the preempt
+	  or irq latency tracers are enabled, as those need to swap as well
+	  and already adds the overhead (plus a lot more).
+
 config TRACE_BRANCH_PROFILING
 	bool
 	select GENERIC_TRACER
@@ -524,6 +550,29 @@ config RING_BUFFER_BENCHMARK
 
 	  If unsure, say N.
 
+config RING_BUFFER_STARTUP_TEST
+       bool "Ring buffer startup self test"
+       depends on RING_BUFFER
+       help
+         Run a simple self test on the ring buffer on boot up. Late in the
+	 kernel boot sequence, the test will start that kicks off
+	 a thread per cpu. Each thread will write various size events
+	 into the ring buffer. Another thread is created to send IPIs
+	 to each of the threads, where the IPI handler will also write
+	 to the ring buffer, to test/stress the nesting ability.
+	 If any anomalies are discovered, a warning will be displayed
+	 and all ring buffers will be disabled.
+
+	 The test runs for 10 seconds. This will slow your boot time
+	 by at least 10 more seconds.
+
+	 At the end of the test, statics and more checks are done.
+	 It will output the stats of each per cpu buffer. What
+	 was written, the sizes, what was read, what was lost, and
+	 other similar details.
+
+	 If unsure, say N
+
 endif # FTRACE
 
 endif # TRACING_SUPPORT
diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c
index 5a0f781cd729..ed58a3216a6d 100644
--- a/kernel/trace/blktrace.c
+++ b/kernel/trace/blktrace.c
@@ -72,7 +72,7 @@ static void trace_note(struct blk_trace *bt, pid_t pid, int action,
 	bool blk_tracer = blk_tracer_enabled;
 
 	if (blk_tracer) {
-		buffer = blk_tr->buffer;
+		buffer = blk_tr->trace_buffer.buffer;
 		pc = preempt_count();
 		event = trace_buffer_lock_reserve(buffer, TRACE_BLK,
 						  sizeof(*t) + len,
@@ -218,7 +218,7 @@ static void __blk_add_trace(struct blk_trace *bt, sector_t sector, int bytes,
 	if (blk_tracer) {
 		tracing_record_cmdline(current);
 
-		buffer = blk_tr->buffer;
+		buffer = blk_tr->trace_buffer.buffer;
 		pc = preempt_count();
 		event = trace_buffer_lock_reserve(buffer, TRACE_BLK,
 						  sizeof(*t) + pdu_len,
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index b3fde6d7b7fc..8a5c017bb50c 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -486,7 +486,6 @@ struct ftrace_profile_stat {
 #define PROFILES_PER_PAGE					\
 	(PROFILE_RECORDS_SIZE / sizeof(struct ftrace_profile))
 
-static int ftrace_profile_bits __read_mostly;
 static int ftrace_profile_enabled __read_mostly;
 
 /* ftrace_profile_lock - synchronize the enable and disable of the profiler */
@@ -494,7 +493,8 @@ static DEFINE_MUTEX(ftrace_profile_lock);
 
 static DEFINE_PER_CPU(struct ftrace_profile_stat, ftrace_profile_stats);
 
-#define FTRACE_PROFILE_HASH_SIZE 1024 /* must be power of 2 */
+#define FTRACE_PROFILE_HASH_BITS 10
+#define FTRACE_PROFILE_HASH_SIZE (1 << FTRACE_PROFILE_HASH_BITS)
 
 static void *
 function_stat_next(void *v, int idx)
@@ -676,7 +676,7 @@ int ftrace_profile_pages_init(struct ftrace_profile_stat *stat)
 
 	pages = DIV_ROUND_UP(functions, PROFILES_PER_PAGE);
 
-	for (i = 0; i < pages; i++) {
+	for (i = 1; i < pages; i++) {
 		pg->next = (void *)get_zeroed_page(GFP_KERNEL);
 		if (!pg->next)
 			goto out_free;
@@ -724,13 +724,6 @@ static int ftrace_profile_init_cpu(int cpu)
 	if (!stat->hash)
 		return -ENOMEM;
 
-	if (!ftrace_profile_bits) {
-		size--;
-
-		for (; size; size >>= 1)
-			ftrace_profile_bits++;
-	}
-
 	/* Preallocate the function profiling pages */
 	if (ftrace_profile_pages_init(stat) < 0) {
 		kfree(stat->hash);
@@ -763,7 +756,7 @@ ftrace_find_profiled_func(struct ftrace_profile_stat *stat, unsigned long ip)
 	struct hlist_head *hhd;
 	unsigned long key;
 
-	key = hash_long(ip, ftrace_profile_bits);
+	key = hash_long(ip, FTRACE_PROFILE_HASH_BITS);
 	hhd = &stat->hash[key];
 
 	if (hlist_empty(hhd))
@@ -782,7 +775,7 @@ static void ftrace_add_profile(struct ftrace_profile_stat *stat,
 {
 	unsigned long key;
 
-	key = hash_long(rec->ip, ftrace_profile_bits);
+	key = hash_long(rec->ip, FTRACE_PROFILE_HASH_BITS);
 	hlist_add_head_rcu(&rec->node, &stat->hash[key]);
 }
 
@@ -1079,7 +1072,7 @@ struct ftrace_func_probe {
 	unsigned long		flags;
 	unsigned long		ip;
 	void			*data;
-	struct rcu_head		rcu;
+	struct list_head	free_list;
 };
 
 struct ftrace_func_entry {
@@ -1329,7 +1322,6 @@ ftrace_hash_move(struct ftrace_ops *ops, int enable,
 	struct hlist_head *hhd;
 	struct ftrace_hash *old_hash;
 	struct ftrace_hash *new_hash;
-	unsigned long key;
 	int size = src->count;
 	int bits = 0;
 	int ret;
@@ -1372,10 +1364,6 @@ ftrace_hash_move(struct ftrace_ops *ops, int enable,
 	for (i = 0; i < size; i++) {
 		hhd = &src->buckets[i];
 		hlist_for_each_entry_safe(entry, tn, hhd, hlist) {
-			if (bits > 0)
-				key = hash_long(entry->ip, bits);
-			else
-				key = 0;
 			remove_hash_entry(src, entry);
 			__add_hash_entry(new_hash, entry);
 		}
@@ -2973,28 +2961,27 @@ static void __disable_ftrace_function_probe(void)
 }
 
 
-static void ftrace_free_entry_rcu(struct rcu_head *rhp)
+static void ftrace_free_entry(struct ftrace_func_probe *entry)
 {
-	struct ftrace_func_probe *entry =
-		container_of(rhp, struct ftrace_func_probe, rcu);
-
 	if (entry->ops->free)
-		entry->ops->free(&entry->data);
+		entry->ops->free(entry->ops, entry->ip, &entry->data);
 	kfree(entry);
 }
 
-
 int
 register_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops,
 			      void *data)
 {
 	struct ftrace_func_probe *entry;
+	struct ftrace_hash **orig_hash = &trace_probe_ops.filter_hash;
+	struct ftrace_hash *hash;
 	struct ftrace_page *pg;
 	struct dyn_ftrace *rec;
 	int type, len, not;
 	unsigned long key;
 	int count = 0;
 	char *search;
+	int ret;
 
 	type = filter_parse_regex(glob, strlen(glob), &search, &not);
 	len = strlen(search);
@@ -3005,8 +2992,16 @@ register_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops,
 
 	mutex_lock(&ftrace_lock);
 
-	if (unlikely(ftrace_disabled))
+	hash = alloc_and_copy_ftrace_hash(FTRACE_HASH_DEFAULT_BITS, *orig_hash);
+	if (!hash) {
+		count = -ENOMEM;
 		goto out_unlock;
+	}
+
+	if (unlikely(ftrace_disabled)) {
+		count = -ENODEV;
+		goto out_unlock;
+	}
 
 	do_for_each_ftrace_rec(pg, rec) {
 
@@ -3030,14 +3025,21 @@ register_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops,
 		 * for each function we find. We call the callback
 		 * to give the caller an opportunity to do so.
 		 */
-		if (ops->callback) {
-			if (ops->callback(rec->ip, &entry->data) < 0) {
+		if (ops->init) {
+			if (ops->init(ops, rec->ip, &entry->data) < 0) {
 				/* caller does not like this func */
 				kfree(entry);
 				continue;
 			}
 		}
 
+		ret = enter_record(hash, rec, 0);
+		if (ret < 0) {
+			kfree(entry);
+			count = ret;
+			goto out_unlock;
+		}
+
 		entry->ops = ops;
 		entry->ip = rec->ip;
 
@@ -3045,10 +3047,16 @@ register_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops,
 		hlist_add_head_rcu(&entry->node, &ftrace_func_hash[key]);
 
 	} while_for_each_ftrace_rec();
+
+	ret = ftrace_hash_move(&trace_probe_ops, 1, orig_hash, hash);
+	if (ret < 0)
+		count = ret;
+
 	__enable_ftrace_function_probe();
 
  out_unlock:
 	mutex_unlock(&ftrace_lock);
+	free_ftrace_hash(hash);
 
 	return count;
 }
@@ -3062,7 +3070,12 @@ static void
 __unregister_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops,
 				  void *data, int flags)
 {
+	struct ftrace_func_entry *rec_entry;
 	struct ftrace_func_probe *entry;
+	struct ftrace_func_probe *p;
+	struct ftrace_hash **orig_hash = &trace_probe_ops.filter_hash;
+	struct list_head free_list;
+	struct ftrace_hash *hash;
 	struct hlist_node *tmp;
 	char str[KSYM_SYMBOL_LEN];
 	int type = MATCH_FULL;
@@ -3083,6 +3096,14 @@ __unregister_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops,
 	}
 
 	mutex_lock(&ftrace_lock);
+
+	hash = alloc_and_copy_ftrace_hash(FTRACE_HASH_DEFAULT_BITS, *orig_hash);
+	if (!hash)
+		/* Hmm, should report this somehow */
+		goto out_unlock;
+
+	INIT_LIST_HEAD(&free_list);
+
 	for (i = 0; i < FTRACE_FUNC_HASHSIZE; i++) {
 		struct hlist_head *hhd = &ftrace_func_hash[i];
 
@@ -3103,12 +3124,30 @@ __unregister_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops,
 					continue;
 			}
 
+			rec_entry = ftrace_lookup_ip(hash, entry->ip);
+			/* It is possible more than one entry had this ip */
+			if (rec_entry)
+				free_hash_entry(hash, rec_entry);
+
 			hlist_del_rcu(&entry->node);
-			call_rcu_sched(&entry->rcu, ftrace_free_entry_rcu);
+			list_add(&entry->free_list, &free_list);
 		}
 	}
 	__disable_ftrace_function_probe();
+	/*
+	 * Remove after the disable is called. Otherwise, if the last
+	 * probe is removed, a null hash means *all enabled*.
+	 */
+	ftrace_hash_move(&trace_probe_ops, 1, orig_hash, hash);
+	synchronize_sched();
+	list_for_each_entry_safe(entry, p, &free_list, free_list) {
+		list_del(&entry->free_list);
+		ftrace_free_entry(entry);
+	}
+		
+ out_unlock:
 	mutex_unlock(&ftrace_lock);
+	free_ftrace_hash(hash);
 }
 
 void
@@ -3736,7 +3775,8 @@ out:
 	if (fail)
 		return -EINVAL;
 
-	ftrace_graph_filter_enabled = 1;
+	ftrace_graph_filter_enabled = !!(*idx);
+
 	return 0;
 }
 
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 6989df2ba194..b59aea2c48c2 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -8,13 +8,16 @@
 #include <linux/trace_clock.h>
 #include <linux/trace_seq.h>
 #include <linux/spinlock.h>
+#include <linux/irq_work.h>
 #include <linux/debugfs.h>
 #include <linux/uaccess.h>
 #include <linux/hardirq.h>
+#include <linux/kthread.h>	/* for self test */
 #include <linux/kmemcheck.h>
 #include <linux/module.h>
 #include <linux/percpu.h>
 #include <linux/mutex.h>
+#include <linux/delay.h>
 #include <linux/slab.h>
 #include <linux/init.h>
 #include <linux/hash.h>
@@ -444,6 +447,12 @@ int ring_buffer_print_page_header(struct trace_seq *s)
 	return ret;
 }
 
+struct rb_irq_work {
+	struct irq_work			work;
+	wait_queue_head_t		waiters;
+	bool				waiters_pending;
+};
+
 /*
  * head_page == tail_page && head == tail then buffer is empty.
  */
@@ -478,6 +487,8 @@ struct ring_buffer_per_cpu {
 	struct list_head		new_pages; /* new pages to add */
 	struct work_struct		update_pages_work;
 	struct completion		update_done;
+
+	struct rb_irq_work		irq_work;
 };
 
 struct ring_buffer {
@@ -497,6 +508,8 @@ struct ring_buffer {
 	struct notifier_block		cpu_notify;
 #endif
 	u64				(*clock)(void);
+
+	struct rb_irq_work		irq_work;
 };
 
 struct ring_buffer_iter {
@@ -508,6 +521,118 @@ struct ring_buffer_iter {
 	u64				read_stamp;
 };
 
+/*
+ * rb_wake_up_waiters - wake up tasks waiting for ring buffer input
+ *
+ * Schedules a delayed work to wake up any task that is blocked on the
+ * ring buffer waiters queue.
+ */
+static void rb_wake_up_waiters(struct irq_work *work)
+{
+	struct rb_irq_work *rbwork = container_of(work, struct rb_irq_work, work);
+
+	wake_up_all(&rbwork->waiters);
+}
+
+/**
+ * ring_buffer_wait - wait for input to the ring buffer
+ * @buffer: buffer to wait on
+ * @cpu: the cpu buffer to wait on
+ *
+ * If @cpu == RING_BUFFER_ALL_CPUS then the task will wake up as soon
+ * as data is added to any of the @buffer's cpu buffers. Otherwise
+ * it will wait for data to be added to a specific cpu buffer.
+ */
+void ring_buffer_wait(struct ring_buffer *buffer, int cpu)
+{
+	struct ring_buffer_per_cpu *cpu_buffer;
+	DEFINE_WAIT(wait);
+	struct rb_irq_work *work;
+
+	/*
+	 * Depending on what the caller is waiting for, either any
+	 * data in any cpu buffer, or a specific buffer, put the
+	 * caller on the appropriate wait queue.
+	 */
+	if (cpu == RING_BUFFER_ALL_CPUS)
+		work = &buffer->irq_work;
+	else {
+		cpu_buffer = buffer->buffers[cpu];
+		work = &cpu_buffer->irq_work;
+	}
+
+
+	prepare_to_wait(&work->waiters, &wait, TASK_INTERRUPTIBLE);
+
+	/*
+	 * The events can happen in critical sections where
+	 * checking a work queue can cause deadlocks.
+	 * After adding a task to the queue, this flag is set
+	 * only to notify events to try to wake up the queue
+	 * using irq_work.
+	 *
+	 * We don't clear it even if the buffer is no longer
+	 * empty. The flag only causes the next event to run
+	 * irq_work to do the work queue wake up. The worse
+	 * that can happen if we race with !trace_empty() is that
+	 * an event will cause an irq_work to try to wake up
+	 * an empty queue.
+	 *
+	 * There's no reason to protect this flag either, as
+	 * the work queue and irq_work logic will do the necessary
+	 * synchronization for the wake ups. The only thing
+	 * that is necessary is that the wake up happens after
+	 * a task has been queued. It's OK for spurious wake ups.
+	 */
+	work->waiters_pending = true;
+
+	if ((cpu == RING_BUFFER_ALL_CPUS && ring_buffer_empty(buffer)) ||
+	    (cpu != RING_BUFFER_ALL_CPUS && ring_buffer_empty_cpu(buffer, cpu)))
+		schedule();
+
+	finish_wait(&work->waiters, &wait);
+}
+
+/**
+ * ring_buffer_poll_wait - poll on buffer input
+ * @buffer: buffer to wait on
+ * @cpu: the cpu buffer to wait on
+ * @filp: the file descriptor
+ * @poll_table: The poll descriptor
+ *
+ * If @cpu == RING_BUFFER_ALL_CPUS then the task will wake up as soon
+ * as data is added to any of the @buffer's cpu buffers. Otherwise
+ * it will wait for data to be added to a specific cpu buffer.
+ *
+ * Returns POLLIN | POLLRDNORM if data exists in the buffers,
+ * zero otherwise.
+ */
+int ring_buffer_poll_wait(struct ring_buffer *buffer, int cpu,
+			  struct file *filp, poll_table *poll_table)
+{
+	struct ring_buffer_per_cpu *cpu_buffer;
+	struct rb_irq_work *work;
+
+	if ((cpu == RING_BUFFER_ALL_CPUS && !ring_buffer_empty(buffer)) ||
+	    (cpu != RING_BUFFER_ALL_CPUS && !ring_buffer_empty_cpu(buffer, cpu)))
+		return POLLIN | POLLRDNORM;
+
+	if (cpu == RING_BUFFER_ALL_CPUS)
+		work = &buffer->irq_work;
+	else {
+		cpu_buffer = buffer->buffers[cpu];
+		work = &cpu_buffer->irq_work;
+	}
+
+	work->waiters_pending = true;
+	poll_wait(filp, &work->waiters, poll_table);
+
+	if ((cpu == RING_BUFFER_ALL_CPUS && !ring_buffer_empty(buffer)) ||
+	    (cpu != RING_BUFFER_ALL_CPUS && !ring_buffer_empty_cpu(buffer, cpu)))
+		return POLLIN | POLLRDNORM;
+	return 0;
+}
+
 /* buffer may be either ring_buffer or ring_buffer_per_cpu */
 #define RB_WARN_ON(b, cond)						\
 	({								\
@@ -1063,6 +1188,8 @@ rb_allocate_cpu_buffer(struct ring_buffer *buffer, int nr_pages, int cpu)
 	cpu_buffer->lock = (arch_spinlock_t)__ARCH_SPIN_LOCK_UNLOCKED;
 	INIT_WORK(&cpu_buffer->update_pages_work, update_pages_handler);
 	init_completion(&cpu_buffer->update_done);
+	init_irq_work(&cpu_buffer->irq_work.work, rb_wake_up_waiters);
+	init_waitqueue_head(&cpu_buffer->irq_work.waiters);
 
 	bpage = kzalloc_node(ALIGN(sizeof(*bpage), cache_line_size()),
 			    GFP_KERNEL, cpu_to_node(cpu));
@@ -1158,6 +1285,9 @@ struct ring_buffer *__ring_buffer_alloc(unsigned long size, unsigned flags,
 	buffer->clock = trace_clock_local;
 	buffer->reader_lock_key = key;
 
+	init_irq_work(&buffer->irq_work.work, rb_wake_up_waiters);
+	init_waitqueue_head(&buffer->irq_work.waiters);
+
 	/* need at least two pages */
 	if (nr_pages < 2)
 		nr_pages = 2;
@@ -1553,11 +1683,22 @@ int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size,
 			if (!cpu_buffer->nr_pages_to_update)
 				continue;
 
-			if (cpu_online(cpu))
+			/* The update must run on the CPU that is being updated. */
+			preempt_disable();
+			if (cpu == smp_processor_id() || !cpu_online(cpu)) {
+				rb_update_pages(cpu_buffer);
+				cpu_buffer->nr_pages_to_update = 0;
+			} else {
+				/*
+				 * Can not disable preemption for schedule_work_on()
+				 * on PREEMPT_RT.
+				 */
+				preempt_enable();
 				schedule_work_on(cpu,
 						&cpu_buffer->update_pages_work);
-			else
-				rb_update_pages(cpu_buffer);
+				preempt_disable();
+			}
+			preempt_enable();
 		}
 
 		/* wait for all the updates to complete */
@@ -1595,12 +1736,22 @@ int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size,
 
 		get_online_cpus();
 
-		if (cpu_online(cpu_id)) {
+		preempt_disable();
+		/* The update must run on the CPU that is being updated. */
+		if (cpu_id == smp_processor_id() || !cpu_online(cpu_id))
+			rb_update_pages(cpu_buffer);
+		else {
+			/*
+			 * Can not disable preemption for schedule_work_on()
+			 * on PREEMPT_RT.
+			 */
+			preempt_enable();
 			schedule_work_on(cpu_id,
 					 &cpu_buffer->update_pages_work);
 			wait_for_completion(&cpu_buffer->update_done);
-		} else
-			rb_update_pages(cpu_buffer);
+			preempt_disable();
+		}
+		preempt_enable();
 
 		cpu_buffer->nr_pages_to_update = 0;
 		put_online_cpus();
@@ -2612,6 +2763,22 @@ static void rb_commit(struct ring_buffer_per_cpu *cpu_buffer,
 	rb_end_commit(cpu_buffer);
 }
 
+static __always_inline void
+rb_wakeups(struct ring_buffer *buffer, struct ring_buffer_per_cpu *cpu_buffer)
+{
+	if (buffer->irq_work.waiters_pending) {
+		buffer->irq_work.waiters_pending = false;
+		/* irq_work_queue() supplies it's own memory barriers */
+		irq_work_queue(&buffer->irq_work.work);
+	}
+
+	if (cpu_buffer->irq_work.waiters_pending) {
+		cpu_buffer->irq_work.waiters_pending = false;
+		/* irq_work_queue() supplies it's own memory barriers */
+		irq_work_queue(&cpu_buffer->irq_work.work);
+	}
+}
+
 /**
  * ring_buffer_unlock_commit - commit a reserved
  * @buffer: The buffer to commit to
@@ -2631,6 +2798,8 @@ int ring_buffer_unlock_commit(struct ring_buffer *buffer,
 
 	rb_commit(cpu_buffer, event);
 
+	rb_wakeups(buffer, cpu_buffer);
+
 	trace_recursive_unlock();
 
 	preempt_enable_notrace();
@@ -2803,6 +2972,8 @@ int ring_buffer_write(struct ring_buffer *buffer,
 
 	rb_commit(cpu_buffer, event);
 
+	rb_wakeups(buffer, cpu_buffer);
+
 	ret = 0;
  out:
 	preempt_enable_notrace();
@@ -4467,3 +4638,320 @@ static int rb_cpu_notify(struct notifier_block *self,
 	return NOTIFY_OK;
 }
 #endif
+
+#ifdef CONFIG_RING_BUFFER_STARTUP_TEST
+/*
+ * This is a basic integrity check of the ring buffer.
+ * Late in the boot cycle this test will run when configured in.
+ * It will kick off a thread per CPU that will go into a loop
+ * writing to the per cpu ring buffer various sizes of data.
+ * Some of the data will be large items, some small.
+ *
+ * Another thread is created that goes into a spin, sending out
+ * IPIs to the other CPUs to also write into the ring buffer.
+ * this is to test the nesting ability of the buffer.
+ *
+ * Basic stats are recorded and reported. If something in the
+ * ring buffer should happen that's not expected, a big warning
+ * is displayed and all ring buffers are disabled.
+ */
+static struct task_struct *rb_threads[NR_CPUS] __initdata;
+
+struct rb_test_data {
+	struct ring_buffer	*buffer;
+	unsigned long		events;
+	unsigned long		bytes_written;
+	unsigned long		bytes_alloc;
+	unsigned long		bytes_dropped;
+	unsigned long		events_nested;
+	unsigned long		bytes_written_nested;
+	unsigned long		bytes_alloc_nested;
+	unsigned long		bytes_dropped_nested;
+	int			min_size_nested;
+	int			max_size_nested;
+	int			max_size;
+	int			min_size;
+	int			cpu;
+	int			cnt;
+};
+
+static struct rb_test_data rb_data[NR_CPUS] __initdata;
+
+/* 1 meg per cpu */
+#define RB_TEST_BUFFER_SIZE	1048576
+
+static char rb_string[] __initdata =
+	"abcdefghijklmnopqrstuvwxyz1234567890!@#$%^&*()?+\\"
+	"?+|:';\",.<>/?abcdefghijklmnopqrstuvwxyz1234567890"
+	"!@#$%^&*()?+\\?+|:';\",.<>/?abcdefghijklmnopqrstuv";
+
+static bool rb_test_started __initdata;
+
+struct rb_item {
+	int size;
+	char str[];
+};
+
+static __init int rb_write_something(struct rb_test_data *data, bool nested)
+{
+	struct ring_buffer_event *event;
+	struct rb_item *item;
+	bool started;
+	int event_len;
+	int size;
+	int len;
+	int cnt;
+
+	/* Have nested writes different that what is written */
+	cnt = data->cnt + (nested ? 27 : 0);
+
+	/* Multiply cnt by ~e, to make some unique increment */
+	size = (data->cnt * 68 / 25) % (sizeof(rb_string) - 1);
+
+	len = size + sizeof(struct rb_item);
+
+	started = rb_test_started;
+	/* read rb_test_started before checking buffer enabled */
+	smp_rmb();
+
+	event = ring_buffer_lock_reserve(data->buffer, len);
+	if (!event) {
+		/* Ignore dropped events before test starts. */
+		if (started) {
+			if (nested)
+				data->bytes_dropped += len;
+			else
+				data->bytes_dropped_nested += len;
+		}
+		return len;
+	}
+
+	event_len = ring_buffer_event_length(event);
+
+	if (RB_WARN_ON(data->buffer, event_len < len))
+		goto out;
+
+	item = ring_buffer_event_data(event);
+	item->size = size;
+	memcpy(item->str, rb_string, size);
+
+	if (nested) {
+		data->bytes_alloc_nested += event_len;
+		data->bytes_written_nested += len;
+		data->events_nested++;
+		if (!data->min_size_nested || len < data->min_size_nested)
+			data->min_size_nested = len;
+		if (len > data->max_size_nested)
+			data->max_size_nested = len;
+	} else {
+		data->bytes_alloc += event_len;
+		data->bytes_written += len;
+		data->events++;
+		if (!data->min_size || len < data->min_size)
+			data->max_size = len;
+		if (len > data->max_size)
+			data->max_size = len;
+	}
+
+ out:
+	ring_buffer_unlock_commit(data->buffer, event);
+
+	return 0;
+}
+
+static __init int rb_test(void *arg)
+{
+	struct rb_test_data *data = arg;
+
+	while (!kthread_should_stop()) {
+		rb_write_something(data, false);
+		data->cnt++;
+
+		set_current_state(TASK_INTERRUPTIBLE);
+		/* Now sleep between a min of 100-300us and a max of 1ms */
+		usleep_range(((data->cnt % 3) + 1) * 100, 1000);
+	}
+
+	return 0;
+}
+
+static __init void rb_ipi(void *ignore)
+{
+	struct rb_test_data *data;
+	int cpu = smp_processor_id();
+
+	data = &rb_data[cpu];
+	rb_write_something(data, true);
+}
+
+static __init int rb_hammer_test(void *arg)
+{
+	while (!kthread_should_stop()) {
+
+		/* Send an IPI to all cpus to write data! */
+		smp_call_function(rb_ipi, NULL, 1);
+		/* No sleep, but for non preempt, let others run */
+		schedule();
+	}
+
+	return 0;
+}
+
+static __init int test_ringbuffer(void)
+{
+	struct task_struct *rb_hammer;
+	struct ring_buffer *buffer;
+	int cpu;
+	int ret = 0;
+
+	pr_info("Running ring buffer tests...\n");
+
+	buffer = ring_buffer_alloc(RB_TEST_BUFFER_SIZE, RB_FL_OVERWRITE);
+	if (WARN_ON(!buffer))
+		return 0;
+
+	/* Disable buffer so that threads can't write to it yet */
+	ring_buffer_record_off(buffer);
+
+	for_each_online_cpu(cpu) {
+		rb_data[cpu].buffer = buffer;
+		rb_data[cpu].cpu = cpu;
+		rb_data[cpu].cnt = cpu;
+		rb_threads[cpu] = kthread_create(rb_test, &rb_data[cpu],
+						 "rbtester/%d", cpu);
+		if (WARN_ON(!rb_threads[cpu])) {
+			pr_cont("FAILED\n");
+			ret = -1;
+			goto out_free;
+		}
+
+		kthread_bind(rb_threads[cpu], cpu);
+ 		wake_up_process(rb_threads[cpu]);
+	}
+
+	/* Now create the rb hammer! */
+	rb_hammer = kthread_run(rb_hammer_test, NULL, "rbhammer");
+	if (WARN_ON(!rb_hammer)) {
+		pr_cont("FAILED\n");
+		ret = -1;
+		goto out_free;
+	}
+
+	ring_buffer_record_on(buffer);