23 files changed, 1433 insertions, 279 deletions

diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index b0a46f88965..8a4d7293104 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -63,7 +63,11 @@ config TRACING
 #
 config TRACING_SUPPORT
 	bool
-	depends on TRACE_IRQFLAGS_SUPPORT
+	# PPC32 has no irqflags tracing support, but it can use most of the
+	# tracers anyway, they were tested to build and work. Note that new
+	# exceptions to this list aren't welcomed, better implement the
+	# irqflags tracing for your architecture.
+	depends on TRACE_IRQFLAGS_SUPPORT || PPC32
 	depends on STACKTRACE_SUPPORT
 	default y
 
diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile
index c3feea01c3e..2630f5121ec 100644
--- a/kernel/trace/Makefile
+++ b/kernel/trace/Makefile
@@ -44,5 +44,7 @@ obj-$(CONFIG_EVENT_TRACER) += trace_events.o
 obj-$(CONFIG_EVENT_TRACER) += events.o
 obj-$(CONFIG_EVENT_TRACER) += trace_export.o
 obj-$(CONFIG_FTRACE_SYSCALLS) += trace_syscalls.o
+obj-$(CONFIG_EVENT_PROFILE) += trace_event_profile.o
+obj-$(CONFIG_EVENT_TRACER) += trace_events_filter.o
 
 libftrace-y := ftrace.o
diff --git a/kernel/trace/events.c b/kernel/trace/events.c
index 9fc918da404..246f2aa6dc4 100644
--- a/kernel/trace/events.c
+++ b/kernel/trace/events.c
@@ -12,4 +12,3 @@
 #include "trace_events_stage_2.h"
 #include "trace_events_stage_3.h"
 
-#include <trace/trace_event_types.h>
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 7847806eefe..1752a63f37c 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -29,6 +29,8 @@
 #include <linux/list.h>
 #include <linux/hash.h>
 
+#include <trace/sched.h>
+
 #include <asm/ftrace.h>
 
 #include "trace.h"
@@ -339,7 +341,7 @@ static inline int record_frozen(struct dyn_ftrace *rec)
 
 static void ftrace_free_rec(struct dyn_ftrace *rec)
 {
-	rec->ip = (unsigned long)ftrace_free_records;
+	rec->freelist = ftrace_free_records;
 	ftrace_free_records = rec;
 	rec->flags |= FTRACE_FL_FREE;
 }
@@ -356,9 +358,14 @@ void ftrace_release(void *start, unsigned long size)
 
 	mutex_lock(&ftrace_lock);
 	do_for_each_ftrace_rec(pg, rec) {
-		if ((rec->ip >= s) && (rec->ip < e) &&
-		    !(rec->flags & FTRACE_FL_FREE))
+		if ((rec->ip >= s) && (rec->ip < e)) {
+			/*
+			 * rec->ip is changed in ftrace_free_rec()
+			 * It should not between s and e if record was freed.
+			 */
+			FTRACE_WARN_ON(rec->flags & FTRACE_FL_FREE);
 			ftrace_free_rec(rec);
+		}
 	} while_for_each_ftrace_rec();
 	mutex_unlock(&ftrace_lock);
 }
@@ -377,7 +384,7 @@ static struct dyn_ftrace *ftrace_alloc_dyn_node(unsigned long ip)
 			return NULL;
 		}
 
-		ftrace_free_records = (void *)rec->ip;
+		ftrace_free_records = rec->freelist;
 		memset(rec, 0, sizeof(*rec));
 		return rec;
 	}
@@ -409,7 +416,7 @@ ftrace_record_ip(unsigned long ip)
 		return NULL;
 
 	rec->ip = ip;
-	rec->flags = (unsigned long)ftrace_new_addrs;
+	rec->newlist = ftrace_new_addrs;
 	ftrace_new_addrs = rec;
 
 	return rec;
@@ -729,7 +736,7 @@ static int ftrace_update_code(struct module *mod)
 			return -1;
 
 		p = ftrace_new_addrs;
-		ftrace_new_addrs = (struct dyn_ftrace *)p->flags;
+		ftrace_new_addrs = p->newlist;
 		p->flags = 0L;
 
 		/* convert record (i.e, patch mcount-call with NOP) */
@@ -2262,7 +2269,7 @@ ftrace_pid_read(struct file *file, char __user *ubuf,
 	if (ftrace_pid_trace == ftrace_swapper_pid)
 		r = sprintf(buf, "swapper tasks\n");
 	else if (ftrace_pid_trace)
-		r = sprintf(buf, "%u\n", pid_nr(ftrace_pid_trace));
+		r = sprintf(buf, "%u\n", pid_vnr(ftrace_pid_trace));
 	else
 		r = sprintf(buf, "no pid\n");
 
@@ -2590,6 +2597,38 @@ free:
 	return ret;
 }
 
+static void
+ftrace_graph_probe_sched_switch(struct rq *__rq, struct task_struct *prev,
+				struct task_struct *next)
+{
+	unsigned long long timestamp;
+	int index;
+
+	/*
+	 * Does the user want to count the time a function was asleep.
+	 * If so, do not update the time stamps.
+	 */
+	if (trace_flags & TRACE_ITER_SLEEP_TIME)
+		return;
+
+	timestamp = trace_clock_local();
+
+	prev->ftrace_timestamp = timestamp;
+
+	/* only process tasks that we timestamped */
+	if (!next->ftrace_timestamp)
+		return;
+
+	/*
+	 * Update all the counters in next to make up for the
+	 * time next was sleeping.
+	 */
+	timestamp -= next->ftrace_timestamp;
+
+	for (index = next->curr_ret_stack; index >= 0; index--)
+		next->ret_stack[index].calltime += timestamp;
+}
+
 /* Allocate a return stack for each task */
 static int start_graph_tracing(void)
 {
@@ -2611,6 +2650,13 @@ static int start_graph_tracing(void)
 		ret = alloc_retstack_tasklist(ret_stack_list);
 	} while (ret == -EAGAIN);
 
+	if (!ret) {
+		ret = register_trace_sched_switch(ftrace_graph_probe_sched_switch);
+		if (ret)
+			pr_info("ftrace_graph: Couldn't activate tracepoint"
+				" probe to kernel_sched_switch\n");
+	}
+
 	kfree(ret_stack_list);
 	return ret;
 }
@@ -2643,6 +2689,12 @@ int register_ftrace_graph(trace_func_graph_ret_t retfunc,
 
 	mutex_lock(&ftrace_lock);
 
+	/* we currently allow only one tracer registered at a time */
+	if (atomic_read(&ftrace_graph_active)) {
+		ret = -EBUSY;
+		goto out;
+	}
+
 	ftrace_suspend_notifier.notifier_call = ftrace_suspend_notifier_call;
 	register_pm_notifier(&ftrace_suspend_notifier);
 
@@ -2668,6 +2720,7 @@ void unregister_ftrace_graph(void)
 	mutex_lock(&ftrace_lock);
 
 	atomic_dec(&ftrace_graph_active);
+	unregister_trace_sched_switch(ftrace_graph_probe_sched_switch);
 	ftrace_graph_return = (trace_func_graph_ret_t)ftrace_stub;
 	ftrace_graph_entry = ftrace_graph_entry_stub;
 	ftrace_shutdown(FTRACE_STOP_FUNC_RET);
@@ -2688,6 +2741,7 @@ void ftrace_graph_init_task(struct task_struct *t)
 		t->curr_ret_stack = -1;
 		atomic_set(&t->tracing_graph_pause, 0);
 		atomic_set(&t->trace_overrun, 0);
+		t->ftrace_timestamp = 0;
 	} else
 		t->ret_stack = NULL;
 }
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 384ca5d9d72..edce2ff3894 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -189,16 +189,65 @@ enum {
 	RB_LEN_TIME_STAMP = 16,
 };
 
-/* inline for ring buffer fast paths */
+static inline int rb_null_event(struct ring_buffer_event *event)
+{
+	return event->type == RINGBUF_TYPE_PADDING && event->time_delta == 0;
+}
+
+static inline int rb_discarded_event(struct ring_buffer_event *event)
+{
+	return event->type == RINGBUF_TYPE_PADDING && event->time_delta;
+}
+
+static void rb_event_set_padding(struct ring_buffer_event *event)
+{
+	event->type = RINGBUF_TYPE_PADDING;
+	event->time_delta = 0;
+}
+
+/**
+ * ring_buffer_event_discard - discard an event in the ring buffer
+ * @buffer: the ring buffer
+ * @event: the event to discard
+ *
+ * Sometimes a event that is in the ring buffer needs to be ignored.
+ * This function lets the user discard an event in the ring buffer
+ * and then that event will not be read later.
+ *
+ * Note, it is up to the user to be careful with this, and protect
+ * against races. If the user discards an event that has been consumed
+ * it is possible that it could corrupt the ring buffer.
+ */
+void ring_buffer_event_discard(struct ring_buffer_event *event)
+{
+	event->type = RINGBUF_TYPE_PADDING;
+	/* time delta must be non zero */
+	if (!event->time_delta)
+		event->time_delta = 1;
+}
+
 static unsigned
-rb_event_length(struct ring_buffer_event *event)
+rb_event_data_length(struct ring_buffer_event *event)
 {
 	unsigned length;
 
+	if (event->len)
+		length = event->len * RB_ALIGNMENT;
+	else
+		length = event->array[0];
+	return length + RB_EVNT_HDR_SIZE;
+}
+
+/* inline for ring buffer fast paths */
+static unsigned
+rb_event_length(struct ring_buffer_event *event)
+{
 	switch (event->type) {
 	case RINGBUF_TYPE_PADDING:
-		/* undefined */
-		return -1;
+		if (rb_null_event(event))
+			/* undefined */
+			return -1;
+		return rb_event_data_length(event);
 
 	case RINGBUF_TYPE_TIME_EXTEND:
 		return RB_LEN_TIME_EXTEND;
@@ -207,11 +256,7 @@ rb_event_length(struct ring_buffer_event *event)
 		return RB_LEN_TIME_STAMP;
 
 	case RINGBUF_TYPE_DATA:
-		if (event->len)
-			length = event->len * RB_ALIGNMENT;
-		else
-			length = event->array[0];
-		return length + RB_EVNT_HDR_SIZE;
+		return rb_event_data_length(event);
 	default:
 		BUG();
 	}
@@ -535,8 +580,8 @@ static void rb_free_cpu_buffer(struct ring_buffer_per_cpu *cpu_buffer)
 extern int ring_buffer_page_too_big(void);
 
 #ifdef CONFIG_HOTPLUG_CPU
-static int __cpuinit rb_cpu_notify(struct notifier_block *self,
-				   unsigned long action, void *hcpu);
+static int rb_cpu_notify(struct notifier_block *self,
+			 unsigned long action, void *hcpu);
 #endif
 
 /**
@@ -845,11 +890,6 @@ int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size)
 }
 EXPORT_SYMBOL_GPL(ring_buffer_resize);
 
-static inline int rb_null_event(struct ring_buffer_event *event)
-{
-	return event->type == RINGBUF_TYPE_PADDING;
-}
-
 static inline void *
 __rb_data_page_index(struct buffer_data_page *bpage, unsigned index)
 {
@@ -1219,7 +1259,7 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer,
 		if (tail < BUF_PAGE_SIZE) {
 			/* Mark the rest of the page with padding */
 			event = __rb_page_index(tail_page, tail);
-			event->type = RINGBUF_TYPE_PADDING;
+			rb_event_set_padding(event);
 		}
 
 		if (tail <= BUF_PAGE_SIZE)
@@ -1969,7 +2009,7 @@ static void rb_advance_reader(struct ring_buffer_per_cpu *cpu_buffer)
 
 	event = rb_reader_event(cpu_buffer);
 
-	if (event->type == RINGBUF_TYPE_DATA)
+	if (event->type == RINGBUF_TYPE_DATA || rb_discarded_event(event))
 		cpu_buffer->entries--;
 
 	rb_update_read_stamp(cpu_buffer, event);
@@ -2052,9 +2092,18 @@ rb_buffer_peek(struct ring_buffer *buffer, int cpu, u64 *ts)
 
 	switch (event->type) {
 	case RINGBUF_TYPE_PADDING:
-		RB_WARN_ON(cpu_buffer, 1);
+		if (rb_null_event(event))
+			RB_WARN_ON(cpu_buffer, 1);
+		/*
+		 * Because the writer could be discarding every
+		 * event it creates (which would probably be bad)
+		 * if we were to go back to "again" then we may never
+		 * catch up, and will trigger the warn on, or lock
+		 * the box. Return the padding, and we will release
+		 * the current locks, and try again.
+		 */
 		rb_advance_reader(cpu_buffer);
-		return NULL;
+		return event;
 
 	case RINGBUF_TYPE_TIME_EXTEND:
 		/* Internal data, OK to advance */
@@ -2115,8 +2164,12 @@ rb_iter_peek(struct ring_buffer_iter *iter, u64 *ts)
 
 	switch (event->type) {
 	case RINGBUF_TYPE_PADDING:
-		rb_inc_iter(iter);
-		goto again;
+		if (rb_null_event(event)) {
+			rb_inc_iter(iter);
+			goto again;
+		}
+		rb_advance_iter(iter);
+		return event;
 
 	case RINGBUF_TYPE_TIME_EXTEND:
 		/* Internal data, OK to advance */
@@ -2163,10 +2216,16 @@ ring_buffer_peek(struct ring_buffer *buffer, int cpu, u64 *ts)
 	if (!cpumask_test_cpu(cpu, buffer->cpumask))
 		return NULL;
 
+ again:
 	spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
 	event = rb_buffer_peek(buffer, cpu, ts);
 	spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
 
+	if (event && event->type == RINGBUF_TYPE_PADDING) {
+		cpu_relax();
+		goto again;
+	}
+
 	return event;
 }
 
@@ -2185,10 +2244,16 @@ ring_buffer_iter_peek(struct ring_buffer_iter *iter, u64 *ts)
 	struct ring_buffer_event *event;
 	unsigned long flags;
 
+ again:
 	spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
 	event = rb_iter_peek(iter, ts);
 	spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
 
+	if (event && event->type == RINGBUF_TYPE_PADDING) {
+		cpu_relax();
+		goto again;
+	}
+
 	return event;
 }
 
@@ -2207,6 +2272,7 @@ ring_buffer_consume(struct ring_buffer *buffer, int cpu, u64 *ts)
 	struct ring_buffer_event *event = NULL;
 	unsigned long flags;
 
+ again:
 	/* might be called in atomic */
 	preempt_disable();
 
@@ -2228,6 +2294,11 @@ ring_buffer_consume(struct ring_buffer *buffer, int cpu, u64 *ts)
  out:
 	preempt_enable();
 
+	if (event && event->type == RINGBUF_TYPE_PADDING) {
+		cpu_relax();
+		goto again;
+	}
+
 	return event;
 }
 EXPORT_SYMBOL_GPL(ring_buffer_consume);
@@ -2306,6 +2377,7 @@ ring_buffer_read(struct ring_buffer_iter *iter, u64 *ts)
 	struct ring_buffer_per_cpu *cpu_buffer = iter->cpu_buffer;
 	unsigned long flags;
 
+ again:
 	spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
 	event = rb_iter_peek(iter, ts);
 	if (!event)
@@ -2315,6 +2387,11 @@ ring_buffer_read(struct ring_buffer_iter *iter, u64 *ts)
  out:
 	spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
 
+	if (event && event->type == RINGBUF_TYPE_PADDING) {
+		cpu_relax();
+		goto again;
+	}
+
 	return event;
 }
 EXPORT_SYMBOL_GPL(ring_buffer_read);
@@ -2784,8 +2861,8 @@ static __init int rb_init_debugfs(void)
 fs_initcall(rb_init_debugfs);
 
 #ifdef CONFIG_HOTPLUG_CPU
-static int __cpuinit rb_cpu_notify(struct notifier_block *self,
-				   unsigned long action, void *hcpu)
+static int rb_cpu_notify(struct notifier_block *self,
+			 unsigned long action, void *hcpu)
 {
 	struct ring_buffer *buffer =
 		container_of(self, struct ring_buffer, cpu_notify);
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index c95b7292be7..a0174a40c56 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -255,7 +255,7 @@ 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_ANNOTATE | TRACE_ITER_CONTEXT_INFO | TRACE_ITER_SLEEP_TIME;
 
 /**
  * trace_wake_up - wake up tasks waiting for trace input
@@ -316,6 +316,7 @@ static const char *trace_options[] = {
 	"context-info",
 	"latency-format",
 	"global-clock",
+	"sleep-time",
 	NULL
 };
 
@@ -382,7 +383,7 @@ ssize_t trace_seq_to_user(struct trace_seq *s, char __user *ubuf, size_t cnt)
 	return cnt;
 }
 
-ssize_t trace_seq_to_buffer(struct trace_seq *s, void *buf, size_t cnt)
+static ssize_t trace_seq_to_buffer(struct trace_seq *s, void *buf, size_t cnt)
 {
 	int len;
 	void *ret;
@@ -860,15 +861,25 @@ static void ftrace_trace_stack(struct trace_array *tr,
 static void ftrace_trace_userstack(struct trace_array *tr,
 				   unsigned long flags, int pc);
 
-void trace_buffer_unlock_commit(struct trace_array *tr,
-				struct ring_buffer_event *event,
-				unsigned long flags, int pc)
+static inline void __trace_buffer_unlock_commit(struct trace_array *tr,
+					struct ring_buffer_event *event,
+					unsigned long flags, int pc,
+					int wake)
 {
 	ring_buffer_unlock_commit(tr->buffer, event);
 
 	ftrace_trace_stack(tr, flags, 6, pc);
 	ftrace_trace_userstack(tr, flags, pc);
-	trace_wake_up();
+
+	if (wake)
+		trace_wake_up();
+}
+
+void trace_buffer_unlock_commit(struct trace_array *tr,
+					struct ring_buffer_event *event,
+					unsigned long flags, int pc)
+{
+	__trace_buffer_unlock_commit(tr, event, flags, pc, 1);
 }
 
 struct ring_buffer_event *
@@ -882,7 +893,13 @@ trace_current_buffer_lock_reserve(unsigned char type, unsigned long len,
 void trace_current_buffer_unlock_commit(struct ring_buffer_event *event,
 					unsigned long flags, int pc)
 {
-	return trace_buffer_unlock_commit(&global_trace, event, flags, pc);
+	return __trace_buffer_unlock_commit(&global_trace, event, flags, pc, 1);
+}
+
+void trace_nowake_buffer_unlock_commit(struct ring_buffer_event *event,
+					unsigned long flags, int pc)
+{
+	return __trace_buffer_unlock_commit(&global_trace, event, flags, pc, 0);
 }
 
 void
@@ -908,7 +925,7 @@ trace_function(struct trace_array *tr,
 }
 
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
-static void __trace_graph_entry(struct trace_array *tr,
+static int __trace_graph_entry(struct trace_array *tr,
 				struct ftrace_graph_ent *trace,
 				unsigned long flags,
 				int pc)
@@ -917,15 +934,17 @@ static void __trace_graph_entry(struct trace_array *tr,
 	struct ftrace_graph_ent_entry *entry;
 
 	if (unlikely(local_read(&__get_cpu_var(ftrace_cpu_disabled))))
-		return;
+		return 0;
 
 	event = trace_buffer_lock_reserve(&global_trace, TRACE_GRAPH_ENT,
 					  sizeof(*entry), flags, pc);
 	if (!event)
-		return;
+		return 0;
 	entry	= ring_buffer_event_data(event);
 	entry->graph_ent			= *trace;
 	ring_buffer_unlock_commit(global_trace.buffer, event);
+
+	return 1;
 }
 
 static void __trace_graph_return(struct trace_array *tr,
@@ -1146,6 +1165,7 @@ int trace_graph_entry(struct ftrace_graph_ent *trace)
 	struct trace_array_cpu *data;
 	unsigned long flags;
 	long disabled;
+	int ret;
 	int cpu;
 	int pc;
 
@@ -1161,15 +1181,18 @@ int trace_graph_entry(struct ftrace_graph_ent *trace)
 	disabled = atomic_inc_return(&data->disabled);
 	if (likely(disabled == 1)) {
 		pc = preempt_count();
-		__trace_graph_entry(tr, trace, flags, pc);
+		ret = __trace_graph_entry(tr, trace, flags, pc);
+	} else {
+		ret = 0;
 	}
 	/* Only do the atomic if it is not already set */
 	if (!test_tsk_trace_graph(current))
 		set_tsk_trace_graph(current);
+
 	atomic_dec(&data->disabled);
 	local_irq_restore(flags);
 
-	return 1;
+	return ret;
 }
 
 void trace_graph_return(struct ftrace_graph_ret *trace)
@@ -1201,7 +1224,7 @@ void trace_graph_return(struct ftrace_graph_ret *trace)
  * trace_vbprintk - write binary msg to tracing buffer
  *
  */
-int trace_vbprintk(unsigned long ip, int depth, const char *fmt, va_list args)
+int trace_vbprintk(unsigned long ip, const char *fmt, va_list args)
 {
 	static raw_spinlock_t trace_buf_lock =
 		(raw_spinlock_t)__RAW_SPIN_LOCK_UNLOCKED;
@@ -1243,7 +1266,6 @@ int trace_vbprintk(unsigned long ip, int depth, const char *fmt, va_list args)
 		goto out_unlock;
 	entry = ring_buffer_event_data(event);
 	entry->ip			= ip;
-	entry->depth			= depth;
 	entry->fmt			= fmt;
 
 	memcpy(entry->buf, trace_buf, sizeof(u32) * len);
@@ -1261,7 +1283,7 @@ out:
 }
 EXPORT_SYMBOL_GPL(trace_vbprintk);
 
-int trace_vprintk(unsigned long ip, int depth, const char *fmt, va_list args)
+int trace_vprintk(unsigned long ip, const char *fmt, va_list args)
 {
 	static raw_spinlock_t trace_buf_lock = __RAW_SPIN_LOCK_UNLOCKED;
 	static char trace_buf[TRACE_BUF_SIZE];
@@ -1298,7 +1320,6 @@ int trace_vprintk(unsigned long ip, int depth, const char *fmt, va_list args)
 		goto out_unlock;
 	entry = ring_buffer_event_data(event);
 	entry->ip			= ip;
-	entry->depth			= depth;
 
 	memcpy(&entry->buf, trace_buf, len);
 	entry->buf[len] = 0;
@@ -1701,38 +1722,6 @@ static enum print_line_t print_hex_fmt(struct trace_iterator *iter)
 	return TRACE_TYPE_HANDLED;
 }
 
-static enum print_line_t print_bprintk_msg_only(struct trace_iterator *iter)
-{
-	struct trace_seq *s = &iter->seq;
-	struct trace_entry *entry = iter->ent;
-	struct bprint_entry *field;
-	int ret;
-
-	trace_assign_type(field, entry);
-
-	ret = trace_seq_bprintf(s, field->fmt, field->buf);
-	if (!ret)
-		return TRACE_TYPE_PARTIAL_LINE;
-
-	return TRACE_TYPE_HANDLED;
-}
-
-static enum print_line_t print_printk_msg_only(struct trace_iterator *iter)
-{
-	struct trace_seq *s = &iter->seq;
-	struct trace_entry *entry = iter->ent;
-	struct print_entry *field;
-	int ret;
-
-	trace_assign_type(field, entry);
-
-	ret = trace_seq_printf(s, "%s", field->buf);
-	if (!ret)
-		return TRACE_TYPE_PARTIAL_LINE;
-
-	return TRACE_TYPE_HANDLED;
-}
-
 static enum print_line_t print_bin_fmt(struct trace_iterator *iter)
 {
 	struct trace_seq *s = &iter->seq;
@@ -1794,12 +1783,12 @@ static enum print_line_t print_trace_line(struct trace_iterator *iter)
 	if (iter->ent->type == TRACE_BPRINT &&
 			trace_flags & TRACE_ITER_PRINTK &&
 			trace_flags & TRACE_ITER_PRINTK_MSGONLY)
-		return print_bprintk_msg_only(iter);
+		return trace_print_bprintk_msg_only(iter);
 
 	if (iter->ent->type == TRACE_PRINT &&
 			trace_flags & TRACE_ITER_PRINTK &&
 			trace_flags & TRACE_ITER_PRINTK_MSGONLY)
-		return print_printk_msg_only(iter);
+		return trace_print_printk_msg_only(iter);
 
 	if (trace_flags & TRACE_ITER_BIN)
 		return print_bin_fmt(iter);
@@ -1948,9 +1937,14 @@ int tracing_open_generic(struct inode *inode, struct file *filp)
 static int tracing_release(struct inode *inode, struct file *file)
 {
 	struct seq_file *m = (struct seq_file *)file->private_data;
-	struct trace_iterator *iter = m->private;
+	struct trace_iterator *iter;
 	int cpu;
 
+	if (!(file->f_mode & FMODE_READ))
+		return 0;
+
+	iter = m->private;
+
 	mutex_lock(&trace_types_lock);
 	for_each_tracing_cpu(cpu) {
 		if (iter->buffer_iter[cpu])
@@ -1976,12 +1970,24 @@ static int tracing_open(struct inode *inode, struct file *file)
 	struct trace_iterator *iter;
 	int ret = 0;
 
-	iter = __tracing_open(inode, file);
-	if (IS_ERR(iter))
-		ret = PTR_ERR(iter);
-	else if (trace_flags & TRACE_ITER_LATENCY_FMT)
-		iter->iter_flags |= TRACE_FILE_LAT_FMT;
+	/* If this file was open for write, then erase contents */
+	if ((file->f_mode & FMODE_WRITE) &&
+	    !(file->f_flags & O_APPEND)) {
+		long cpu = (long) inode->i_private;
 
+		if (cpu == TRACE_PIPE_ALL_CPU)
+			tracing_reset_online_cpus(&global_trace);
+		else
+			tracing_reset(&global_trace, cpu);
+	}
+
+	if (file->f_mode & FMODE_READ) {
+		iter = __tracing_open(inode, file);
+		if (IS_ERR(iter))
+			ret = PTR_ERR(iter);
+		else if (trace_flags & TRACE_ITER_LATENCY_FMT)
+			iter->iter_flags |= TRACE_FILE_LAT_FMT;
+	}
 	return ret;
 }
 
@@ -2056,9 +2062,17 @@ static int show_traces_open(struct inode *inode, struct file *file)
 	return ret;
 }
 
+static ssize_t
+tracing_write_stub(struct file *filp, const char __user *ubuf,
+		   size_t count, loff_t *ppos)
+{
+	return count;
+}
+
 static const struct file_operations tracing_fops = {
 	.open		= tracing_open,
 	.read		= seq_read,
+	.write		= tracing_write_stub,
 	.llseek		= seq_lseek,
 	.release	= tracing_release,
 };
@@ -3154,7 +3168,7 @@ static int mark_printk(const char *fmt, ...)
 	int ret;
 	va_list args;
 	va_start(args, fmt);
-	ret = trace_vprintk(0, -1, fmt, args);
+	ret = trace_vprintk(0, fmt, args);
 	va_end(args);
 	return ret;
 }
@@ -3522,6 +3536,9 @@ struct dentry *tracing_init_dentry(void)
 	if (d_tracer)
 		return d_tracer;
 
+	if (!debugfs_initialized())
+		return NULL;
+
 	d_tracer = debugfs_create_dir("tracing", NULL);
 
 	if (!d_tracer && !once) {
@@ -3583,7 +3600,7 @@ static void tracing_init_debugfs_percpu(long cpu)
 		pr_warning("Could not create debugfs 'trace_pipe' entry\n");
 
 	/* per cpu trace */
-	entry = debugfs_create_file("trace", 0444, d_cpu,
+	entry = debugfs_create_file("trace", 0644, d_cpu,
 				(void *) cpu, &tracing_fops);
 	if (!entry)
 		pr_warning("Could not create debugfs 'trace' entry\n");
@@ -3897,7 +3914,7 @@ static __init int tracer_init_debugfs(void)
 	if (!entry)
 		pr_warning("Could not create debugfs 'tracing_cpumask' entry\n");
 
-	entry = debugfs_create_file("trace", 0444, d_tracer,
+	entry = debugfs_create_file("trace", 0644, d_tracer,
 				 (void *) TRACE_PIPE_ALL_CPU, &tracing_fops);
 	if (!entry)
 		pr_warning("Could not create debugfs 'trace' entry\n");
@@ -4027,11 +4044,12 @@ trace_printk_seq(struct trace_seq *s)
 	trace_seq_init(s);
 }
 
-void ftrace_dump(void)
+static void __ftrace_dump(bool disable_tracing)
 {
 	static DEFINE_SPINLOCK(ftrace_dump_lock);
 	/* use static because iter can be a bit big for the stack */
 	static struct trace_iterator iter;
+	unsigned int old_userobj;
 	static int dump_ran;
 	unsigned long flags;
 	int cnt = 0, cpu;
@@ -4043,14 +4061,17 @@ void ftrace_dump(void)
 
 	dump_ran = 1;
 
-	/* No turning back! */
 	tracing_off();
-	ftrace_kill();
+
+	if (disable_tracing)
+		ftrace_kill();
 
 	for_each_tracing_cpu(cpu) {
 		atomic_inc(&global_trace.data[cpu]->disabled);
 	}
 
+	old_userobj = trace_flags & TRACE_ITER_SYM_USEROBJ;
+
 	/* don't look at user memory in panic mode */
 	trace_flags &= ~TRACE_ITER_SYM_USEROBJ;
 
@@ -4095,10 +4116,26 @@ void ftrace_dump(void)
 	else
 		printk(KERN_TRACE "---------------------------------\n");
 
+	/* Re-enable tracing if requested */
+	if (!disable_tracing) {
+		trace_flags |= old_userobj;
+
+		for_each_tracing_cpu(cpu) {
+			atomic_dec(&global_trace.data[cpu]->disabled);
+		}
+		tracing_on();
+	}
+
  out:
 	spin_unlock_irqrestore(&ftrace_dump_lock, flags);
 }
 
+/* By default: disable tracing after the dump */
+void ftrace_dump(void)
+{
+	__ftrace_dump(true);
+}
+
 __init static int tracer_alloc_buffers(void)
 {
 	struct trace_array_cpu *data;
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 38276d1638e..cb0ce3fc36d 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -123,7 +123,6 @@ struct userstack_entry {
 struct bprint_entry {
 	struct trace_entry	ent;
 	unsigned long		ip;
-	int			depth;
 	const char		*fmt;
 	u32			buf[];
 };
@@ -131,7 +130,6 @@ struct bprint_entry {
 struct print_entry {
 	struct trace_entry	ent;
 	unsigned long		ip;
-	int			depth;
 	char			buf[];
 };
 
@@ -485,6 +483,8 @@ trace_current_buffer_lock_reserve(unsigned char type, unsigned long len,
 				  unsigned long flags, int pc);
 void trace_current_buffer_unlock_commit(struct ring_buffer_event *event,
 					unsigned long flags, int pc);
+void trace_nowake_buffer_unlock_commit(struct ring_buffer_event *event,
+					unsigned long flags, int pc);
 
 struct trace_entry *tracing_get_trace_entry(struct trace_array *tr,
 						struct trace_array_cpu *data);
@@ -598,9 +598,9 @@ extern int trace_selftest_startup_branch(struct tracer *trace,
 extern void *head_page(struct trace_array_cpu *data);
 extern long ns2usecs(cycle_t nsec);
 extern int
-trace_vbprintk(unsigned long ip, int depth, const char *fmt, va_list args);
+trace_vbprintk(unsigned long ip, const char *fmt, va_list args);
 extern int
-trace_vprintk(unsigned long ip, int depth, const char *fmt, va_list args);
+trace_vprintk(unsigned long ip, const char *fmt, va_list args);
 
 extern unsigned long trace_flags;
 
@@ -685,6 +685,7 @@ enum trace_iterator_flags {
 	TRACE_ITER_CONTEXT_INFO		= 0x20000, /* Print pid/cpu/time */
 	TRACE_ITER_LATENCY_FMT		= 0x40000,
 	TRACE_ITER_GLOBAL_CLK		= 0x80000,
+	TRACE_ITER_SLEEP_TIME		= 0x100000,
 };
 
 /*
@@ -777,22 +778,89 @@ enum {
 	TRACE_EVENT_TYPE_RAW		= 2,
 };
 
+struct ftrace_event_field {
+	struct list_head	link;
+	char			*name;
+	char			*type;
+	int			offset;
+	int			size;
+};
+
 struct ftrace_event_call {
-	char		*name;
-	char		*system;
-	struct dentry	*dir;
-	int		enabled;
-	int		(*regfunc)(void);
-	void		(*unregfunc)(void);
-	int		id;
-	int		(*raw_init)(void);
-	int		(*show_format)(struct trace_seq *s);
+	char			*name;
+	char			*system;
+	struct dentry		*dir;
+	int			enabled;
+	int			(*regfunc)(void);
+	void			(*unregfunc)(void);
+	int			id;
+	int			(*raw_init)(void);
+	int			(*show_format)(struct trace_seq *s);
+	int			(*define_fields)(void);
+	struct list_head	fields;
+	struct filter_pred	**preds;
+
+#ifdef CONFIG_EVENT_PROFILE
+	atomic_t	profile_count;
+	int		(*profile_enable)(struct ftrace_event_call *);
+	void		(*profile_disable)(struct ftrace_event_call *);
+#endif
 };
 
+struct event_subsystem {
+	struct list_head	list;
+	const char		*name;
+	struct dentry		*entry;
+	struct filter_pred	**preds;
+};
+
+#define events_for_each(event)						\
+	for (event = __start_ftrace_events;				\
+	     (unsigned long)event < (unsigned long)__stop_ftrace_events; \
+	     event++)
+
+#define MAX_FILTER_PRED 8
+