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

1 files changed, 1543 insertions, 661 deletions

diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 66338c4f7f4b..581630a6387d 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -1,7 +1,7 @@
 /*
  * ring buffer based function tracer
  *
- * Copyright (C) 2007-2008 Steven Rostedt <srostedt@redhat.com>
+ * Copyright (C) 2007-2012 Steven Rostedt <srostedt@redhat.com>
  * Copyright (C) 2008 Ingo Molnar <mingo@redhat.com>
  *
  * Originally taken from the RT patch by:
@@ -19,7 +19,6 @@
 #include <linux/seq_file.h>
 #include <linux/notifier.h>
 #include <linux/irqflags.h>
-#include <linux/irq_work.h>
 #include <linux/debugfs.h>
 #include <linux/pagemap.h>
 #include <linux/hardirq.h>
@@ -48,7 +47,7 @@
  * On boot up, the ring buffer is set to the minimum size, so that
  * we do not waste memory on systems that are not using tracing.
  */
-int ring_buffer_expanded;
+bool ring_buffer_expanded;
 
 /*
  * We need to change this state when a selftest is running.
@@ -87,14 +86,6 @@ static int dummy_set_flag(u32 old_flags, u32 bit, int set)
 static DEFINE_PER_CPU(bool, trace_cmdline_save);
 
 /*
- * When a reader is waiting for data, then this variable is
- * set to true.
- */
-static bool trace_wakeup_needed;
-
-static struct irq_work trace_work_wakeup;
-
-/*
  * Kill all tracing for good (never come back).
  * It is initialized to 1 but will turn to zero if the initialization
  * of the tracer is successful. But that is the only place that sets
@@ -130,12 +121,14 @@ static int tracing_set_tracer(const char *buf);
 static char bootup_tracer_buf[MAX_TRACER_SIZE] __initdata;
 static char *default_bootup_tracer;
 
+static bool allocate_snapshot;
+
 static int __init set_cmdline_ftrace(char *str)
 {
 	strlcpy(bootup_tracer_buf, str, MAX_TRACER_SIZE);
 	default_bootup_tracer = bootup_tracer_buf;
 	/* We are using ftrace early, expand it */
-	ring_buffer_expanded = 1;
+	ring_buffer_expanded = true;
 	return 1;
 }
 __setup("ftrace=", set_cmdline_ftrace);
@@ -156,6 +149,15 @@ static int __init set_ftrace_dump_on_oops(char *str)
 }
 __setup("ftrace_dump_on_oops", set_ftrace_dump_on_oops);
 
+static int __init boot_alloc_snapshot(char *str)
+{
+	allocate_snapshot = true;
+	/* We also need the main ring buffer expanded */
+	ring_buffer_expanded = true;
+	return 1;
+}
+__setup("alloc_snapshot", boot_alloc_snapshot);
+
 
 static char trace_boot_options_buf[MAX_TRACER_SIZE] __initdata;
 static char *trace_boot_options __initdata;
@@ -189,7 +191,7 @@ unsigned long long ns2usecs(cycle_t nsec)
  */
 static struct trace_array	global_trace;
 
-static DEFINE_PER_CPU(struct trace_array_cpu, global_trace_cpu);
+LIST_HEAD(ftrace_trace_arrays);
 
 int filter_current_check_discard(struct ring_buffer *buffer,
 				 struct ftrace_event_call *call, void *rec,
@@ -204,29 +206,15 @@ cycle_t ftrace_now(int cpu)
 	u64 ts;
 
 	/* Early boot up does not have a buffer yet */
-	if (!global_trace.buffer)
+	if (!global_trace.trace_buffer.buffer)
 		return trace_clock_local();
 
-	ts = ring_buffer_time_stamp(global_trace.buffer, cpu);
-	ring_buffer_normalize_time_stamp(global_trace.buffer, cpu, &ts);
+	ts = ring_buffer_time_stamp(global_trace.trace_buffer.buffer, cpu);
+	ring_buffer_normalize_time_stamp(global_trace.trace_buffer.buffer, cpu, &ts);
 
 	return ts;
 }
 
-/*
- * The max_tr is used to snapshot the global_trace when a maximum
- * latency is reached. Some tracers will use this to store a maximum
- * trace while it continues examining live traces.
- *
- * The buffers for the max_tr are set up the same as the global_trace.
- * When a snapshot is taken, the link list of the max_tr is swapped
- * with the link list of the global_trace and the buffers are reset for
- * the global_trace so the tracing can continue.
- */
-static struct trace_array	max_tr;
-
-static DEFINE_PER_CPU(struct trace_array_cpu, max_tr_data);
-
 int tracing_is_enabled(void)
 {
 	return tracing_is_on();
@@ -249,9 +237,6 @@ static unsigned long		trace_buf_size = TRACE_BUF_SIZE_DEFAULT;
 /* trace_types holds a link list of available tracers. */
 static struct tracer		*trace_types __read_mostly;
 
-/* current_trace points to the tracer that is currently active */
-static struct tracer		*current_trace __read_mostly = &nop_trace;
-
 /*
  * trace_types_lock is used to protect the trace_types list.
  */
@@ -285,13 +270,13 @@ static DEFINE_PER_CPU(struct mutex, cpu_access_lock);
 
 static inline void trace_access_lock(int cpu)
 {
-	if (cpu == TRACE_PIPE_ALL_CPU) {
+	if (cpu == RING_BUFFER_ALL_CPUS) {
 		/* gain it for accessing the whole ring buffer. */
 		down_write(&all_cpu_access_lock);
 	} else {
 		/* gain it for accessing a cpu ring buffer. */
 
-		/* Firstly block other trace_access_lock(TRACE_PIPE_ALL_CPU). */
+		/* Firstly block other trace_access_lock(RING_BUFFER_ALL_CPUS). */
 		down_read(&all_cpu_access_lock);
 
 		/* Secondly block other access to this @cpu ring buffer. */
@@ -301,7 +286,7 @@ static inline void trace_access_lock(int cpu)
 
 static inline void trace_access_unlock(int cpu)
 {
-	if (cpu == TRACE_PIPE_ALL_CPU) {
+	if (cpu == RING_BUFFER_ALL_CPUS) {
 		up_write(&all_cpu_access_lock);
 	} else {
 		mutex_unlock(&per_cpu(cpu_access_lock, cpu));
@@ -339,30 +324,11 @@ static inline void trace_access_lock_init(void)
 
 #endif
 
-/* trace_wait is a waitqueue for tasks blocked on trace_poll */
-static DECLARE_WAIT_QUEUE_HEAD(trace_wait);
-
 /* trace_flags holds trace_options default values */
 unsigned long trace_flags = TRACE_ITER_PRINT_PARENT | TRACE_ITER_PRINTK |
 	TRACE_ITER_ANNOTATE | TRACE_ITER_CONTEXT_INFO | TRACE_ITER_SLEEP_TIME |
 	TRACE_ITER_GRAPH_TIME | TRACE_ITER_RECORD_CMD | TRACE_ITER_OVERWRITE |
-	TRACE_ITER_IRQ_INFO | TRACE_ITER_MARKERS;
-
-static int trace_stop_count;
-static DEFINE_RAW_SPINLOCK(tracing_start_lock);
-
-/**
- * trace_wake_up - wake up tasks waiting for trace input
- *
- * Schedules a delayed work to wake up any task that is blocked on the
- * trace_wait queue. These is used with trace_poll for tasks polling the
- * trace.
- */
-static void trace_wake_up(struct irq_work *work)
-{
-	wake_up_all(&trace_wait);
-
-}
+	TRACE_ITER_IRQ_INFO | TRACE_ITER_MARKERS | TRACE_ITER_FUNCTION;
 
 /**
  * tracing_on - enable tracing buffers
@@ -372,8 +338,8 @@ static void trace_wake_up(struct irq_work *work)
  */
 void tracing_on(void)
 {
-	if (global_trace.buffer)
-		ring_buffer_record_on(global_trace.buffer);
+	if (global_trace.trace_buffer.buffer)
+		ring_buffer_record_on(global_trace.trace_buffer.buffer);
 	/*
 	 * This flag is only looked at when buffers haven't been
 	 * allocated yet. We don't really care about the race
@@ -385,6 +351,196 @@ void tracing_on(void)
 EXPORT_SYMBOL_GPL(tracing_on);
 
 /**
+ * __trace_puts - write a constant string into the trace buffer.
+ * @ip:	   The address of the caller
+ * @str:   The constant string to write
+ * @size:  The size of the string.
+ */
+int __trace_puts(unsigned long ip, const char *str, int size)
+{
+	struct ring_buffer_event *event;
+	struct ring_buffer *buffer;
+	struct print_entry *entry;
+	unsigned long irq_flags;
+	int alloc;
+
+	alloc = sizeof(*entry) + size + 2; /* possible \n added */
+
+	local_save_flags(irq_flags);
+	buffer = global_trace.trace_buffer.buffer;
+	event = trace_buffer_lock_reserve(buffer, TRACE_PRINT, alloc, 
+					  irq_flags, preempt_count());
+	if (!event)
+		return 0;
+
+	entry = ring_buffer_event_data(event);
+	entry->ip = ip;
+
+	memcpy(&entry->buf, str, size);
+
+	/* Add a newline if necessary */
+	if (entry->buf[size - 1] != '\n') {
+		entry->buf[size] = '\n';
+		entry->buf[size + 1] = '\0';
+	} else
+		entry->buf[size] = '\0';
+
+	__buffer_unlock_commit(buffer, event);
+
+	return size;
+}
+EXPORT_SYMBOL_GPL(__trace_puts);
+
+/**
+ * __trace_bputs - write the pointer to a constant string into trace buffer
+ * @ip:	   The address of the caller
+ * @str:   The constant string to write to the buffer to
+ */
+int __trace_bputs(unsigned long ip, const char *str)
+{
+	struct ring_buffer_event *event;
+	struct ring_buffer *buffer;
+	struct bputs_entry *entry;
+	unsigned long irq_flags;
+	int size = sizeof(struct bputs_entry);
+
+	local_save_flags(irq_flags);
+	buffer = global_trace.trace_buffer.buffer;
+	event = trace_buffer_lock_reserve(buffer, TRACE_BPUTS, size,
+					  irq_flags, preempt_count());
+	if (!event)
+		return 0;
+
+	entry = ring_buffer_event_data(event);
+	entry->ip			= ip;
+	entry->str			= str;
+
+	__buffer_unlock_commit(buffer, event);
+
+	return 1;
+}
+EXPORT_SYMBOL_GPL(__trace_bputs);
+
+#ifdef CONFIG_TRACER_SNAPSHOT
+/**
+ * trace_snapshot - take a snapshot of the current buffer.
+ *
+ * This causes a swap between the snapshot buffer and the current live
+ * tracing buffer. You can use this to take snapshots of the live
+ * trace when some condition is triggered, but continue to trace.
+ *
+ * Note, make sure to allocate the snapshot with either
+ * a tracing_snapshot_alloc(), or by doing it manually
+ * with: echo 1 > /sys/kernel/debug/tracing/snapshot
+ *
+ * If the snapshot buffer is not allocated, it will stop tracing.
+ * Basically making a permanent snapshot.
+ */
+void tracing_snapshot(void)
+{
+	struct trace_array *tr = &global_trace;
+	struct tracer *tracer = tr->current_trace;
+	unsigned long flags;
+
+	if (in_nmi()) {
+		internal_trace_puts("*** SNAPSHOT CALLED FROM NMI CONTEXT ***\n");
+		internal_trace_puts("*** snapshot is being ignored        ***\n");
+		return;
+	}
+
+	if (!tr->allocated_snapshot) {
+		internal_trace_puts("*** SNAPSHOT NOT ALLOCATED ***\n");
+		internal_trace_puts("*** stopping trace here!   ***\n");
+		tracing_off();
+		return;
+	}
+
+	/* Note, snapshot can not be used when the tracer uses it */
+	if (tracer->use_max_tr) {
+		internal_trace_puts("*** LATENCY TRACER ACTIVE ***\n");
+		internal_trace_puts("*** Can not use snapshot (sorry) ***\n");
+		return;
+	}
+
+	local_irq_save(flags);
+	update_max_tr(tr, current, smp_processor_id());
+	local_irq_restore(flags);
+}
+EXPORT_SYMBOL_GPL(tracing_snapshot);
+
+static int resize_buffer_duplicate_size(struct trace_buffer *trace_buf,
+					struct trace_buffer *size_buf, int cpu_id);
+static void set_buffer_entries(struct trace_buffer *buf, unsigned long val);
+
+static int alloc_snapshot(struct trace_array *tr)
+{
+	int ret;
+
+	if (!tr->allocated_snapshot) {
+
+		/* allocate spare buffer */
+		ret = resize_buffer_duplicate_size(&tr->max_buffer,
+				   &tr->trace_buffer, RING_BUFFER_ALL_CPUS);
+		if (ret < 0)
+			return ret;
+
+		tr->allocated_snapshot = true;
+	}
+
+	return 0;
+}
+
+void free_snapshot(struct trace_array *tr)
+{
+	/*
+	 * We don't free the ring buffer. instead, resize it because
+	 * The max_tr ring buffer has some state (e.g. ring->clock) and
+	 * we want preserve it.
+	 */
+	ring_buffer_resize(tr->max_buffer.buffer, 1, RING_BUFFER_ALL_CPUS);
+	set_buffer_entries(&tr->max_buffer, 1);
+	tracing_reset_online_cpus(&tr->max_buffer);
+	tr->allocated_snapshot = false;
+}
+
+/**
+ * trace_snapshot_alloc - allocate and take a snapshot of the current buffer.
+ *
+ * This is similar to trace_snapshot(), but it will allocate the
+ * snapshot buffer if it isn't already allocated. Use this only
+ * where it is safe to sleep, as the allocation may sleep.
+ *
+ * This causes a swap between the snapshot buffer and the current live
+ * tracing buffer. You can use this to take snapshots of the live
+ * trace when some condition is triggered, but continue to trace.
+ */
+void tracing_snapshot_alloc(void)
+{
+	struct trace_array *tr = &global_trace;
+	int ret;
+
+	ret = alloc_snapshot(tr);
+	if (WARN_ON(ret < 0))
+		return;
+
+	tracing_snapshot();
+}
+EXPORT_SYMBOL_GPL(tracing_snapshot_alloc);
+#else
+void tracing_snapshot(void)
+{
+	WARN_ONCE(1, "Snapshot feature not enabled, but internal snapshot used");
+}
+EXPORT_SYMBOL_GPL(tracing_snapshot);
+void tracing_snapshot_alloc(void)
+{
+	/* Give warning */
+	tracing_snapshot();
+}
+EXPORT_SYMBOL_GPL(tracing_snapshot_alloc);
+#endif /* CONFIG_TRACER_SNAPSHOT */
+
+/**
  * tracing_off - turn off tracing buffers
  *
  * This function stops the tracing buffers from recording data.
@@ -394,8 +550,8 @@ EXPORT_SYMBOL_GPL(tracing_on);
  */
 void tracing_off(void)
 {
-	if (global_trace.buffer)
-		ring_buffer_record_off(global_trace.buffer);
+	if (global_trace.trace_buffer.buffer)
+		ring_buffer_record_off(global_trace.trace_buffer.buffer);
 	/*
 	 * This flag is only looked at when buffers haven't been
 	 * allocated yet. We don't really care about the race
@@ -411,8 +567,8 @@ EXPORT_SYMBOL_GPL(tracing_off);
  */
 int tracing_is_on(void)
 {
-	if (global_trace.buffer)
-		return ring_buffer_record_is_on(global_trace.buffer);
+	if (global_trace.trace_buffer.buffer)
+		return ring_buffer_record_is_on(global_trace.trace_buffer.buffer);
 	return !global_trace.buffer_disabled;
 }
 EXPORT_SYMBOL_GPL(tracing_is_on);
@@ -479,6 +635,7 @@ static const char *trace_options[] = {
 	"disable_on_free",
 	"irq-info",
 	"markers",
+	"function-trace",
 	NULL
 };
 
@@ -490,6 +647,8 @@ static struct {
 	{ trace_clock_local,	"local",	1 },
 	{ trace_clock_global,	"global",	1 },
 	{ trace_clock_counter,	"counter",	0 },
+	{ trace_clock_jiffies,	"uptime",	1 },
+	{ trace_clock,		"perf",		1 },
 	ARCH_TRACE_CLOCKS
 };
 
@@ -670,13 +829,14 @@ unsigned long __read_mostly	tracing_max_latency;
 static void
 __update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu)
 {
-	struct trace_array_cpu *data = tr->data[cpu];
-	struct trace_array_cpu *max_data;
+	struct trace_buffer *trace_buf = &tr->trace_buffer;
+	struct trace_buffer *max_buf = &tr->max_buffer;
+	struct trace_array_cpu *data = per_cpu_ptr(trace_buf->data, cpu);
+	struct trace_array_cpu *max_data = per_cpu_ptr(max_buf->data, cpu);
 
-	max_tr.cpu = cpu;
-	max_tr.time_start = data->preempt_timestamp;
+	max_buf->cpu = cpu;
+	max_buf->time_start = data->preempt_timestamp;
 
-	max_data = max_tr.data[cpu];
 	max_data->saved_latency = tracing_max_latency;
 	max_data->critical_start = data->critical_start;
 	max_data->critical_end = data->critical_end;
@@ -706,22 +866,22 @@ update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu)
 {
 	struct ring_buffer *buf;
 
-	if (trace_stop_count)
+	if (tr->stop_count)
 		return;
 
 	WARN_ON_ONCE(!irqs_disabled());
 
-	if (!current_trace->allocated_snapshot) {
+	if (!tr->allocated_snapshot) {
 		/* Only the nop tracer should hit this when disabling */
-		WARN_ON_ONCE(current_trace != &nop_trace);
+		WARN_ON_ONCE(tr->current_trace != &nop_trace);
 		return;
 	}
 
 	arch_spin_lock(&ftrace_max_lock);
 
-	buf = tr->buffer;
-	tr->buffer = max_tr.buffer;
-	max_tr.buffer = buf;
+	buf = tr->trace_buffer.buffer;
+	tr->trace_buffer.buffer = tr->max_buffer.buffer;
+	tr->max_buffer.buffer = buf;
 
 	__update_max_tr(tr, tsk, cpu);
 	arch_spin_unlock(&ftrace_max_lock);
@@ -740,19 +900,19 @@ update_max_tr_single(struct trace_array *tr, struct task_struct *tsk, int cpu)
 {
 	int ret;
 
-	if (trace_stop_count)
+	if (tr->stop_count)
 		return;
 
 	WARN_ON_ONCE(!irqs_disabled());
-	if (!current_trace->allocated_snapshot) {
+	if (tr->allocated_snapshot) {
 		/* Only the nop tracer should hit this when disabling */
-		WARN_ON_ONCE(current_trace != &nop_trace);
+		WARN_ON_ONCE(tr->current_trace != &nop_trace);
 		return;
 	}
 
 	arch_spin_lock(&ftrace_max_lock);
 
-	ret = ring_buffer_swap_cpu(max_tr.buffer, tr->buffer, cpu);
+	ret = ring_buffer_swap_cpu(tr->max_buffer.buffer, tr->trace_buffer.buffer, cpu);
 
 	if (ret == -EBUSY) {
 		/*
@@ -761,7 +921,7 @@ update_max_tr_single(struct trace_array *tr, struct task_struct *tsk, int cpu)
 		 * the max trace buffer (no one writes directly to it)
 		 * and flag that it failed.
 		 */
-		trace_array_printk(&max_tr, _THIS_IP_,
+		trace_array_printk_buf(tr->max_buffer.buffer, _THIS_IP_,
 			"Failed to swap buffers due to commit in progress\n");
 	}
 
@@ -774,37 +934,78 @@ update_max_tr_single(struct trace_array *tr, struct task_struct *tsk, int cpu)
 
 static void default_wait_pipe(struct trace_iterator *iter)
 {
-	DEFINE_WAIT(wait);
+	/* Iterators are static, they should be filled or empty */
+	if (trace_buffer_iter(iter, iter->cpu_file))
+		return;
+
+	ring_buffer_wait(iter->trace_buffer->buffer, iter->cpu_file);
+}
+
+#ifdef CONFIG_FTRACE_STARTUP_TEST
+static int run_tracer_selftest(struct tracer *type)
+{
+	struct trace_array *tr = &global_trace;
+	struct tracer *saved_tracer = tr->current_trace;
+	int ret;
 
-	prepare_to_wait(&trace_wait, &wait, TASK_INTERRUPTIBLE);
+	if (!type->selftest || tracing_selftest_disabled)
+		return 0;
 
 	/*
-	 * 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.
+	 * Run a selftest on this tracer.
+	 * Here we reset the trace buffer, and set the current
+	 * tracer to be this tracer. The tracer can then run some
+	 * internal tracing to verify that everything is in order.
+	 * If we fail, we do not register this tracer.
 	 */
-	trace_wakeup_needed = true;
+	tracing_reset_online_cpus(&tr->trace_buffer);
 
-	if (trace_empty(iter))
-		schedule();
+	tr->current_trace = type;
 
-	finish_wait(&trace_wait, &wait);
+#ifdef CONFIG_TRACER_MAX_TRACE
+	if (type->use_max_tr) {
+		/* If we expanded the buffers, make sure the max is expanded too */
+		if (ring_buffer_expanded)
+			ring_buffer_resize(tr->max_buffer.buffer, trace_buf_size,
+					   RING_BUFFER_ALL_CPUS);
+		tr->allocated_snapshot = true;
+	}
+#endif
+
+	/* the test is responsible for initializing and enabling */
+	pr_info("Testing tracer %s: ", type->name);
+	ret = type->selftest(type, tr);
+	/* the test is responsible for resetting too */
+	tr->current_trace = saved_tracer;
+	if (ret) {
+		printk(KERN_CONT "FAILED!\n");
+		/* Add the warning after printing 'FAILED' */
+		WARN_ON(1);
+		return -1;
+	}
+	/* Only reset on passing, to avoid touching corrupted buffers */
+	tracing_reset_online_cpus(&tr->trace_buffer);
+
+#ifdef CONFIG_TRACER_MAX_TRACE
+	if (type->use_max_tr) {
+		tr->allocated_snapshot = false;
+
+		/* Shrink the max buffer again */
+		if (ring_buffer_expanded)
+			ring_buffer_resize(tr->max_buffer.buffer, 1,
+					   RING_BUFFER_ALL_CPUS);
+	}
+#endif
+
+	printk(KERN_CONT "PASSED\n");
+	return 0;
+}
+#else
+static inline int run_tracer_selftest(struct tracer *type)
+{
+	return 0;
 }
+#endif /* CONFIG_FTRACE_STARTUP_TEST */
 
 /**
  * register_tracer - register a tracer with the ftrace system.
@@ -851,57 +1052,9 @@ int register_tracer(struct tracer *type)
 	if (!type->wait_pipe)
 		type->wait_pipe = default_wait_pipe;
 
-
-#ifdef CONFIG_FTRACE_STARTUP_TEST
-	if (type->selftest && !tracing_selftest_disabled) {
-		struct tracer *saved_tracer = current_trace;
-		struct trace_array *tr = &global_trace;
-
-		/*
-		 * Run a selftest on this tracer.
-		 * Here we reset the trace buffer, and set the current
-		 * tracer to be this tracer. The tracer can then run some
-		 * internal tracing to verify that everything is in order.
-		 * If we fail, we do not register this tracer.
-		 */
-		tracing_reset_online_cpus(tr);
-
-		current_trace = type;
-
-		if (type->use_max_tr) {
-			/* If we expanded the buffers, make sure the max is expanded too */
-			if (ring_buffer_expanded)
-				ring_buffer_resize(max_tr.buffer, trace_buf_size,
-						   RING_BUFFER_ALL_CPUS);
-			type->allocated_snapshot = true;
-		}
-
-		/* the test is responsible for initializing and enabling */
-		pr_info("Testing tracer %s: ", type->name);
-		ret = type->selftest(type, tr);
-		/* the test is responsible for resetting too */
-		current_trace = saved_tracer;
-		if (ret) {
-			printk(KERN_CONT "FAILED!\n");
-			/* Add the warning after printing 'FAILED' */
-			WARN_ON(1);
-			goto out;
-		}
-		/* Only reset on passing, to avoid touching corrupted buffers */
-		tracing_reset_online_cpus(tr);
-
-		if (type->use_max_tr) {
-			type->allocated_snapshot = false;
-
-			/* Shrink the max buffer again */
-			if (ring_buffer_expanded)
-				ring_buffer_resize(max_tr.buffer, 1,
-						   RING_BUFFER_ALL_CPUS);
-		}
-
-		printk(KERN_CONT "PASSED\n");
-	}
-#endif
+	ret = run_tracer_selftest(type);
+	if (ret < 0)
+		goto out;
 
 	type->next = trace_types;
 	trace_types = type;
@@ -921,7 +1074,7 @@ int register_tracer(struct tracer *type)
 	tracing_set_tracer(type->name);
 	default_bootup_tracer = NULL;
 	/* disable other selftests, since this will break it. */
-	tracing_selftest_disabled = 1;
+	tracing_selftest_disabled = true;
 #ifdef CONFIG_FTRACE_STARTUP_TEST
 	printk(KERN_INFO "Disabling FTRACE selftests due to running tracer '%s'\n",
 	       type->name);
@@ -931,9 +1084,9 @@ int register_tracer(struct tracer *type)
 	return ret;
 }
 
-void tracing_reset(struct trace_array *tr, int cpu)
+void tracing_reset(struct trace_buffer *buf, int cpu)
 {
-	struct ring_buffer *buffer = tr->buffer;
+	struct ring_buffer *buffer = buf->buffer;
 
 	if (!buffer)
 		return;
@@ -947,9 +1100,9 @@ void tracing_reset(struct trace_array *tr, int cpu)
 	ring_buffer_record_enable(buffer);
 }
 
-void tracing_reset_online_cpus(struct trace_array *tr)
+void tracing_reset_online_cpus(struct trace_buffer *buf)
 {
-	struct ring_buffer *buffer = tr->buffer;
+	struct ring_buffer *buffer = buf->buffer;
 	int cpu;
 
 	if (!buffer)
@@ -960,7 +1113,7 @@ void tracing_reset_online_cpus(struct trace_array *tr)
 	/* Make sure all commits have finished */
 	synchronize_sched();
 
-	tr->time_start = ftrace_now(tr->cpu);
+	buf->time_start = ftrace_now(buf->cpu);
 
 	for_each_online_cpu(cpu)
 		ring_buffer_reset_cpu(buffer, cpu);
@@ -970,12 +1123,21 @@ void tracing_reset_online_cpus(struct trace_array *tr)
 
 void tracing_reset_current(int cpu)
 {
-	tracing_reset(&global_trace, cpu);
+	tracing_reset(&global_trace.trace_buffer, cpu);
 }
 
-void tracing_reset_current_online_cpus(void)
+void tracing_reset_all_online_cpus(void)
 {
-	tracing_reset_online_cpus(&global_trace);
+	struct trace_array *tr;
+
+	mutex_lock(&trace_types_lock);
+	list_for_each_entry(tr, &ftrace_trace_arrays, list) {
+		tracing_reset_online_cpus(&tr->trace_buffer);
+#ifdef CONFIG_TRACER_MAX_TRACE
+		tracing_reset_online_cpus(&tr->max_buffer);
+#endif
+	}
+	mutex_unlock(&trace_types_lock);
 }
 
 #define SAVED_CMDLINES 128
@@ -998,7 +1160,7 @@ static void trace_init_cmdlines(void)
 
 int is_tracing_stopped(void)
 {
-	return trace_stop_count;
+	return global_trace.stop_count;
 }
 
 /**
@@ -1030,12 +1192,12 @@ void tracing_start(void)
 	if (tracing_disabled)
 		return;
 
-	raw_spin_lock_irqsave(&tracing_start_lock, flags);
-	if (--trace_stop_count) {
-		if (trace_stop_count < 0) {
+	raw_spin_lock_irqsave(&global_trace.start_lock, flags);
+	if (--global_trace.stop_count) {
+		if (global_trace.stop_count < 0) {
 			/* Someone screwed up their debugging */
 			WARN_ON_ONCE(1);
-			trace_stop_count = 0;
+			global_trace.stop_count = 0;
 		}
 		goto out;
 	}
@@ -1043,19 +1205,52 @@ void tracing_start(void)
 	/* Prevent the buffers from switching */
 	arch_spin_lock(&ftrace_max_lock);
 
-	buffer = global_trace.buffer;
+	buffer = global_trace.trace_buffer.buffer;
 	if (buffer)
 		ring_buffer_record_enable(buffer);
 
-	buffer = max_tr.buffer;
+#ifdef CONFIG_TRACER_MAX_TRACE
+	buffer = global_trace.max_buffer.buffer;
 	if (buffer)
 		ring_buffer_record_enable(buffer);
+#endif
 
 	arch_spin_unlock(&ftrace_max_lock);
 
 	ftrace_start();
  out:
-	raw_spin_unlock_irqrestore(&tracing_start_lock, flags);
+	raw_spin_unlock_irqrestore(&global_trace.start_lock, flags);
+}
+
+static void tracing_start_tr(struct trace_array *tr)
+{
+	struct ring_buffer *buffer;
+	unsigned long flags;
+
+	if (tracing_disabled)
+		return;
+
+	/* If global, we need to also start the max tracer */
+	if (tr->flags & TRACE_ARRAY_FL_GLOBAL)
+		return tracing_start();
+
+	raw_spin_lock_irqsave(&tr->start_lock, flags);
+
+	if (--tr->stop_count) {
+		if (tr->stop_count < 0) {
+			/* Someone screwed up their debugging */
+			WARN_ON_ONCE(1);
+			tr->stop_count = 0;
+		}
+		goto out;
+	}
+
+	buffer = tr->trace_buffer.buffer;
+	if (buffer)
+		ring_buffer_record_enable(buffer);
+
+ out:
+	raw_spin_unlock_irqrestore(&tr->start_lock, flags);
 }
 
 /**
@@ -1070,25 +1265,48 @@ void tracing_stop(void)
 	unsigned long flags;
 
 	ftrace_stop();
-	raw_spin_lock_irqsave(&tracing_start_lock, flags);
-	if (trace_stop_count++)
+	raw_spin_lock_irqsave(&global_trace.start_lock, flags);
+	if (global_trace.stop_count++)
 		goto out;
 
 	/* Prevent the buffers from switching */
 	arch_spin_lock(&ftrace_max_lock);
 
-	buffer = global_trace.buffer;
+	buffer = global_trace.trace_buffer.buffer;
 	if (buffer)
 		ring_buffer_record_disable(buffer);
 
-	buffer = max_tr.buffer;
+#ifdef CONFIG_TRACER_MAX_TRACE
+	buffer = global_trace.max_buffer.buffer;
 	if (buffer)
 		ring_buffer_record_disable(buffer);
+#endif
 
 	arch_spin_unlock(&ftrace_max_lock);
 
  out:
-	raw_spin_unlock_irqrestore(&tracing_start_lock, flags);
+	raw_spin_unlock_irqrestore(&global_trace.start_lock, flags);
+}
+
+static void tracing_stop_tr(struct trace_array *tr)
+{
+	struct ring_buffer *buffer;
+	unsigned long flags;
+
+	/* If global, we need to also stop the max tracer */
+	if (tr->flags & TRACE_ARRAY_FL_GLOBAL)
+		return tracing_stop();
+
+	raw_spin_lock_irqsave(&tr->start_lock, flags);
+	if (tr->stop_count++)
+		goto out;
+
+	buffer = tr->trace_buffer.buffer;
+	if (buffer)
+		ring_buffer_record_disable(buffer);
+
+ out:
+	raw_spin_unlock_irqrestore(&tr->start_lock, flags);
 }
 
 void trace_stop_cmdline_recording(void);
@@ -1221,11 +1439,6 @@ void
 __buffer_unlock_commit(struct ring_buffer *buffer, struct ring_buffer_event *event)
 {
 	__this_cpu_write(trace_cmdline_save, true);
-	if (trace_wakeup_needed) {
-		trace_wakeup_needed = false;
-		/* irq_work_queue() supplies it's own memory barriers */
-		irq_work_queue(&trace_work_wakeup);
-	}
 	ring_buffer_unlock_commit(buffer, event);
 }
 
@@ -1249,11 +1462,23 @@ void trace_buffer_unlock_commit(struct ring_buffer *buffer,
 EXPORT_SYMBOL_GPL(trace_buffer_unlock_commit);
 
 struct ring_buffer_event *
+trace_event_buffer_lock_reserve(struct ring_buffer **current_rb,
+			  struct ftrace_event_file *ftrace_file,
+			  int type, unsigned long len,
+			  unsigned long flags, int pc)
+{
+	*current_rb = ftrace_file->tr->trace_buffer.buffer;
+	return trace_buffer_lock_reserve(*current_rb,
+					 type, len, flags, pc);
+}
+EXPORT_SYMBOL_GPL(trace_event_buffer_lock_reserve);
+
+struct ring_buffer_event *
 trace_current_buffer_lock_reserve(struct ring_buffer **current_rb,
 				  int type, unsigned long len,
 				  unsigned long flags, int pc)
 {
-	*current_rb = global_trace.buffer;
+	*current_rb = global_trace.trace_buffer.buffer;
 	return trace_buffer_lock_reserve(*current_rb,
 					 type, len, flags, pc);
 }
@@ -1292,7 +1517,7 @@ trace_function(struct trace_array *tr,
 	       int pc)
 {
 	struct ftrace_event_call *call = &event_function;
-	struct ring_buffer *buffer = tr->buffer;
+	struct ring_buffer *buffer = tr->trace_buffer.buffer;
 	struct ring_buffer_event *event;
 	struct ftrace_entry *entry;
 
@@ -1433,13 +1658,14 @@ void ftrace_trace_stack(struct ring_buffer *buffer, unsigned long flags,
 void __trace_stack(struct trace_array *tr, unsigned long flags, int skip,
 		   int pc)
 {
-	__ftrace_trace_stack(tr->buffer, flags, skip, pc, NULL);
+	__ftrace_trace_stack(tr->trace_buffer.buffer, flags, skip, pc, NULL);
 }
 
 /**
  * trace_dump_stack - record a stack back trace in the trace buffer
+ * @skip: Number of functions to skip (helper handlers)
  */
-void trace_dump_stack(void)
+void trace_dump_stack(int skip)
 {
 	unsigned long flags;
 
@@ -1448,8 +1674,13 @@ void trace_dump_stack(void)
 
 	local_save_flags(flags);
 
-	/* skipping 3 traces, seems to get us at the caller of this function */
-	__ftrace_trace_stack(global_trace.buffer, flags, 3, preempt_count(), NULL);
+	/*
+	 * Skip 3 more, seems to get us at the caller of
+	 * this function.
+	 */
+	skip += 3;
+	__ftrace_trace_stack(global_trace.trace_buffer.buffer,
+			     flags, skip, preempt_count(), NULL);
 }
 
 static DEFINE_PER_CPU(int, user_stack_count);
@@ -1619,7 +1850,7 @@ void trace_printk_init_buffers(void)
 	 * directly here. If the global_trace.buffer is already
 	 * allocated here, then this was called by module code.
 	 */
-	if (global_trace.buffer)
+	if (global_trace.trace_buffer.buffer)
 		tracing_start_cmdline_record();
 }
 
@@ -1679,7 +1910,7 @@ int trace_vbprintk(unsigned long ip, const char *fmt, va_list args)
 
 	local_save_flags(flags);
 	size = sizeof(*entry) + sizeof(u32) * len;
-	buffer = tr->buffer;
+	buffer = tr->trace_buffer.buffer;
 	event = trace_buffer_lock_reserve(buffer, TRACE_BPRINT, size,
 					  flags, pc);
 	if (!event)
@@ -1702,27 +1933,12 @@ out:
 }
 EXPORT_SYMBOL_GPL(trace_vbprintk);
 
-int trace_array_printk(struct trace_array *tr,
-		       unsigned long ip, const char *fmt, ...)
-{
-	int ret;
-	va_list ap;
-
-	if (!(trace_flags & TRACE_ITER_PRINTK))
-		return 0;
-
-	va_start(ap, fmt);
-	ret = trace_array_vprintk(tr, ip, fmt, ap);
-	va_end(ap);
-	return ret;
-}
-
-int trace_array_vprintk(struct trace_array *tr,
-			unsigned long ip, const char *fmt, va_list args)
+static int
+__trace_array_vprintk(struct ring_buffer *buffer,
+		      unsigned long ip, const char *fmt, va_list args)
 {
 	struct ftrace_event_call *call = &event_print;
 	struct ring_buffer_event *event;
-	struct ring_buffer *buffer;
 	int len = 0, size, pc;
 	struct print_entry *entry;
 	unsigned long flags;
@@ -1750,7 +1966,6 @@ int trace_array_vprintk(struct trace_array *tr,
 
 	local_save_flags(flags);
 	size = sizeof(*entry) + len + 1;
-	buffer = tr->buffer;
 	event = trace_buffer_lock_reserve(buffer, TRACE_PRINT, size,
 					  flags, pc);
 	if (!event)
@@ -1771,6 +1986,42 @@ int trace_array_vprintk(struct trace_array *tr,
 	return len;
 }
 
+int trace_array_vprintk(struct trace_array *tr,
+			unsigned long ip, const char *fmt, va_list args)
+{
+	return __trace_array_vprintk(tr->trace_buffer.buffer, ip, fmt, args);
+}
+
+int trace_array_printk(struct trace_array *tr,
+		       unsigned long ip, const char *fmt, ...)
+{