Merge branch 'tip/perf/urgent' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-2.6-trace into perf/core

10 files changed, 398 insertions, 128 deletions

diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index c7683fd8a03a..538501c6ea50 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -153,7 +153,7 @@ config IRQSOFF_TRACER
 	bool "Interrupts-off Latency Tracer"
 	default n
 	depends on TRACE_IRQFLAGS_SUPPORT
-	depends on GENERIC_TIME
+	depends on !ARCH_USES_GETTIMEOFFSET
 	select TRACE_IRQFLAGS
 	select GENERIC_TRACER
 	select TRACER_MAX_TRACE
@@ -175,7 +175,7 @@ config IRQSOFF_TRACER
 config PREEMPT_TRACER
 	bool "Preemption-off Latency Tracer"
 	default n
-	depends on GENERIC_TIME
+	depends on !ARCH_USES_GETTIMEOFFSET
 	depends on PREEMPT
 	select GENERIC_TRACER
 	select TRACER_MAX_TRACE
@@ -323,17 +323,6 @@ config STACK_TRACER
 
 	  Say N if unsure.
 
-config WORKQUEUE_TRACER
-	bool "Trace workqueues"
-	select GENERIC_TRACER
-	help
-	  The workqueue tracer provides some statistical information
-          about each cpu workqueue thread such as the number of the
-          works inserted and executed since their creation. It can help
-          to evaluate the amount of work each of them has to perform.
-          For example it can help a developer to decide whether he should
-          choose a per-cpu workqueue instead of a singlethreaded one.
-
 config BLK_DEV_IO_TRACE
 	bool "Support for tracing block IO actions"
 	depends on SYSFS
diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile
index 438e84a56ab3..53f338190b26 100644
--- a/kernel/trace/Makefile
+++ b/kernel/trace/Makefile
@@ -53,5 +53,8 @@ endif
 obj-$(CONFIG_EVENT_TRACING) += trace_events_filter.o
 obj-$(CONFIG_KPROBE_EVENT) += trace_kprobe.o
 obj-$(CONFIG_EVENT_TRACING) += power-traces.o
+ifeq ($(CONFIG_TRACING),y)
+obj-$(CONFIG_KGDB_KDB) += trace_kdb.o
+endif
 
 libftrace-y := ftrace.o
diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c
index 638711c17504..959f8d6c8cc1 100644
--- a/kernel/trace/blktrace.c
+++ b/kernel/trace/blktrace.c
@@ -169,9 +169,12 @@ static int act_log_check(struct blk_trace *bt, u32 what, sector_t sector,
 static const u32 ddir_act[2] = { BLK_TC_ACT(BLK_TC_READ),
 				 BLK_TC_ACT(BLK_TC_WRITE) };
 
+#define BLK_TC_HARDBARRIER	BLK_TC_BARRIER
+#define BLK_TC_RAHEAD		BLK_TC_AHEAD
+
 /* The ilog2() calls fall out because they're constant */
-#define MASK_TC_BIT(rw, __name) ((rw & (1 << BIO_RW_ ## __name)) << \
-	  (ilog2(BLK_TC_ ## __name) + BLK_TC_SHIFT - BIO_RW_ ## __name))
+#define MASK_TC_BIT(rw, __name) ((rw & REQ_ ## __name) << \
+	  (ilog2(BLK_TC_ ## __name) + BLK_TC_SHIFT - __REQ_ ## __name))
 
 /*
  * The worker for the various blk_add_trace*() types. Fills out a
@@ -194,9 +197,9 @@ static void __blk_add_trace(struct blk_trace *bt, sector_t sector, int bytes,
 		return;
 
 	what |= ddir_act[rw & WRITE];
-	what |= MASK_TC_BIT(rw, BARRIER);
-	what |= MASK_TC_BIT(rw, SYNCIO);
-	what |= MASK_TC_BIT(rw, AHEAD);
+	what |= MASK_TC_BIT(rw, HARDBARRIER);
+	what |= MASK_TC_BIT(rw, SYNC);
+	what |= MASK_TC_BIT(rw, RAHEAD);
 	what |= MASK_TC_BIT(rw, META);
 	what |= MASK_TC_BIT(rw, DISCARD);
 
@@ -549,6 +552,41 @@ int blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
 }
 EXPORT_SYMBOL_GPL(blk_trace_setup);
 
+#if defined(CONFIG_COMPAT) && defined(CONFIG_X86_64)
+static int compat_blk_trace_setup(struct request_queue *q, char *name,
+				  dev_t dev, struct block_device *bdev,
+				  char __user *arg)
+{
+	struct blk_user_trace_setup buts;
+	struct compat_blk_user_trace_setup cbuts;
+	int ret;
+
+	if (copy_from_user(&cbuts, arg, sizeof(cbuts)))
+		return -EFAULT;
+
+	buts = (struct blk_user_trace_setup) {
+		.act_mask = cbuts.act_mask,
+		.buf_size = cbuts.buf_size,
+		.buf_nr = cbuts.buf_nr,
+		.start_lba = cbuts.start_lba,
+		.end_lba = cbuts.end_lba,
+		.pid = cbuts.pid,
+	};
+	memcpy(&buts.name, &cbuts.name, 32);
+
+	ret = do_blk_trace_setup(q, name, dev, bdev, &buts);
+	if (ret)
+		return ret;
+
+	if (copy_to_user(arg, &buts.name, 32)) {
+		blk_trace_remove(q);
+		return -EFAULT;
+	}
+
+	return 0;
+}
+#endif
+
 int blk_trace_startstop(struct request_queue *q, int start)
 {
 	int ret;
@@ -601,6 +639,7 @@ int blk_trace_ioctl(struct block_device *bdev, unsigned cmd, char __user *arg)
 	if (!q)
 		return -ENXIO;
 
+	lock_kernel();
 	mutex_lock(&bdev->bd_mutex);
 
 	switch (cmd) {
@@ -608,6 +647,12 @@ int blk_trace_ioctl(struct block_device *bdev, unsigned cmd, char __user *arg)
 		bdevname(bdev, b);
 		ret = blk_trace_setup(q, b, bdev->bd_dev, bdev, arg);
 		break;
+#if defined(CONFIG_COMPAT) && defined(CONFIG_X86_64)
+	case BLKTRACESETUP32:
+		bdevname(bdev, b);
+		ret = compat_blk_trace_setup(q, b, bdev->bd_dev, bdev, arg);
+		break;
+#endif
 	case BLKTRACESTART:
 		start = 1;
 	case BLKTRACESTOP:
@@ -622,6 +667,7 @@ int blk_trace_ioctl(struct block_device *bdev, unsigned cmd, char __user *arg)
 	}
 
 	mutex_unlock(&bdev->bd_mutex);
+	unlock_kernel();
 	return ret;
 }
 
@@ -661,10 +707,13 @@ static void blk_add_trace_rq(struct request_queue *q, struct request *rq,
 	if (likely(!bt))
 		return;
 
-	if (blk_discard_rq(rq))
-		rw |= (1 << BIO_RW_DISCARD);
+	if (rq->cmd_flags & REQ_DISCARD)
+		rw |= REQ_DISCARD;
+
+	if (rq->cmd_flags & REQ_SECURE)
+		rw |= REQ_SECURE;
 
-	if (blk_pc_request(rq)) {
+	if (rq->cmd_type == REQ_TYPE_BLOCK_PC) {
 		what |= BLK_TC_ACT(BLK_TC_PC);
 		__blk_add_trace(bt, 0, blk_rq_bytes(rq), rw,
 				what, rq->errors, rq->cmd_len, rq->cmd);
@@ -925,7 +974,7 @@ void blk_add_driver_data(struct request_queue *q,
 	if (likely(!bt))
 		return;
 
-	if (blk_pc_request(rq))
+	if (rq->cmd_type == REQ_TYPE_BLOCK_PC)
 		__blk_add_trace(bt, 0, blk_rq_bytes(rq), 0,
 				BLK_TA_DRV_DATA, rq->errors, len, data);
 	else
@@ -1730,7 +1779,7 @@ void blk_dump_cmd(char *buf, struct request *rq)
 	int len = rq->cmd_len;
 	unsigned char *cmd = rq->cmd;
 
-	if (!blk_pc_request(rq)) {
+	if (rq->cmd_type != REQ_TYPE_BLOCK_PC) {
 		buf[0] = '\0';
 		return;
 	}
@@ -1755,21 +1804,23 @@ void blk_fill_rwbs(char *rwbs, u32 rw, int bytes)
 
 	if (rw & WRITE)
 		rwbs[i++] = 'W';
-	else if (rw & 1 << BIO_RW_DISCARD)
+	else if (rw & REQ_DISCARD)
 		rwbs[i++] = 'D';
 	else if (bytes)
 		rwbs[i++] = 'R';
 	else
 		rwbs[i++] = 'N';
 
-	if (rw & 1 << BIO_RW_AHEAD)
+	if (rw & REQ_RAHEAD)
 		rwbs[i++] = 'A';
-	if (rw & 1 << BIO_RW_BARRIER)
+	if (rw & REQ_HARDBARRIER)
 		rwbs[i++] = 'B';
-	if (rw & 1 << BIO_RW_SYNCIO)
+	if (rw & REQ_SYNC)
 		rwbs[i++] = 'S';
-	if (rw & 1 << BIO_RW_META)
+	if (rw & REQ_META)
 		rwbs[i++] = 'M';
+	if (rw & REQ_SECURE)
+		rwbs[i++] = 'E';
 
 	rwbs[i] = '\0';
 }
@@ -1779,8 +1830,11 @@ void blk_fill_rwbs_rq(char *rwbs, struct request *rq)
 	int rw = rq->cmd_flags & 0x03;
 	int bytes;
 
-	if (blk_discard_rq(rq))
-		rw |= (1 << BIO_RW_DISCARD);
+	if (rq->cmd_flags & REQ_DISCARD)
+		rw |= REQ_DISCARD;
+
+	if (rq->cmd_flags & REQ_SECURE)
+		rw |= REQ_SECURE;
 
 	bytes = blk_rq_bytes(rq);
 
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 3632ce87674f..19cccc3c3028 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -3846,6 +3846,9 @@ int ring_buffer_read_page(struct ring_buffer *buffer,
 			rpos = reader->read;
 			pos += size;
 
+			if (rpos >= commit)
+				break;
+
 			event = rb_reader_event(cpu_buffer);
 			size = rb_event_length(event);
 		} while (len > size);
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 4b1122d0df37..9ec59f541156 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -101,10 +101,7 @@ static inline void ftrace_enable_cpu(void)
 	preempt_enable();
 }
 
-static cpumask_var_t __read_mostly	tracing_buffer_mask;
-
-#define for_each_tracing_cpu(cpu)	\
-	for_each_cpu(cpu, tracing_buffer_mask)
+cpumask_var_t __read_mostly	tracing_buffer_mask;
 
 /*
  * ftrace_dump_on_oops - variable to dump ftrace buffer on oops
@@ -744,13 +741,6 @@ __acquires(kernel_lock)
 		return -1;
 	}
 
-	/*
-	 * When this gets called we hold the BKL which means that
-	 * preemption is disabled. Various trace selftests however
-	 * need to disable and enable preemption for successful tests.
-	 * So we drop the BKL here and grab it after the tests again.
-	 */
-	unlock_kernel();
 	mutex_lock(&trace_types_lock);
 
 	tracing_selftest_running = true;
@@ -832,7 +822,6 @@ __acquires(kernel_lock)
 #endif
 
  out_unlock:
-	lock_kernel();
 	return ret;
 }
 
@@ -1493,11 +1482,6 @@ int trace_vprintk(unsigned long ip, const char *fmt, va_list args)
 }
 EXPORT_SYMBOL_GPL(trace_vprintk);
 
-enum trace_file_type {
-	TRACE_FILE_LAT_FMT	= 1,
-	TRACE_FILE_ANNOTATE	= 2,
-};
-
 static void trace_iterator_increment(struct trace_iterator *iter)
 {
 	/* Don't allow ftrace to trace into the ring buffers */
@@ -1595,7 +1579,7 @@ struct trace_entry *trace_find_next_entry(struct trace_iterator *iter,
 }
 
 /* Find the next real entry, and increment the iterator to the next entry */
-static void *find_next_entry_inc(struct trace_iterator *iter)
+void *trace_find_next_entry_inc(struct trace_iterator *iter)
 {
 	iter->ent = __find_next_entry(iter, &iter->cpu,
 				      &iter->lost_events, &iter->ts);
@@ -1630,19 +1614,19 @@ static void *s_next(struct seq_file *m, void *v, loff_t *pos)
 		return NULL;
 
 	if (iter->idx < 0)
-		ent = find_next_entry_inc(iter);
+		ent = trace_find_next_entry_inc(iter);
 	else
 		ent = iter;
 
 	while (ent && iter->idx < i)
-		ent = find_next_entry_inc(iter);
+		ent = trace_find_next_entry_inc(iter);
 
 	iter->pos = *pos;
 
 	return ent;
 }
 
-static void tracing_iter_reset(struct trace_iterator *iter, int cpu)
+void tracing_iter_reset(struct trace_iterator *iter, int cpu)
 {
 	struct trace_array *tr = iter->tr;
 	struct ring_buffer_event *event;
@@ -2003,7 +1987,7 @@ int trace_empty(struct trace_iterator *iter)
 }
 
 /*  Called with trace_event_read_lock() held. */
-static enum print_line_t print_trace_line(struct trace_iterator *iter)
+enum print_line_t print_trace_line(struct trace_iterator *iter)
 {
 	enum print_line_t ret;
 
@@ -3193,7 +3177,7 @@ waitagain:
 
 	trace_event_read_lock();
 	trace_access_lock(iter->cpu_file);
-	while (find_next_entry_inc(iter) != NULL) {
+	while (trace_find_next_entry_inc(iter) != NULL) {
 		enum print_line_t ret;
 		int len = iter->seq.len;
 
@@ -3276,7 +3260,7 @@ tracing_fill_pipe_page(size_t rem, struct trace_iterator *iter)
 		if (ret != TRACE_TYPE_NO_CONSUME)
 			trace_consume(iter);
 		rem -= count;
-		if (!find_next_entry_inc(iter))	{
+		if (!trace_find_next_entry_inc(iter))	{
 			rem = 0;
 			iter->ent = NULL;
 			break;
@@ -3332,7 +3316,7 @@ static ssize_t tracing_splice_read_pipe(struct file *filp,
 	if (ret <= 0)
 		goto out_err;
 
-	if (!iter->ent && !find_next_entry_inc(iter)) {
+	if (!iter->ent && !trace_find_next_entry_inc(iter)) {
 		ret = -EFAULT;
 		goto out_err;
 	}
@@ -3479,6 +3463,7 @@ tracing_mark_write(struct file *filp, const char __user *ubuf,
 					size_t cnt, loff_t *fpos)
 {
 	char *buf;
+	size_t written;
 
 	if (tracing_disabled)
 		return -EINVAL;
@@ -3500,11 +3485,15 @@ tracing_mark_write(struct file *filp, const char __user *ubuf,
 	} else
 		buf[cnt] = '\0';
 
-	cnt = mark_printk("%s", buf);
+	written = mark_printk("%s", buf);
 	kfree(buf);
-	*fpos += cnt;
+	*fpos += written;
 
-	return cnt;
+	/* don't tell userspace we wrote more - it might confuse them */
+	if (written > cnt)
+		written = cnt;
+
+	return written;
 }
 
 static int tracing_clock_show(struct seq_file *m, void *v)
@@ -4402,7 +4391,7 @@ static struct notifier_block trace_die_notifier = {
  */
 #define KERN_TRACE		KERN_EMERG
 
-static void
+void
 trace_printk_seq(struct trace_seq *s)
 {
 	/* Probably should print a warning here. */
@@ -4417,6 +4406,13 @@ trace_printk_seq(struct trace_seq *s)
 	trace_seq_init(s);
 }
 
+void trace_init_global_iter(struct trace_iterator *iter)
+{
+	iter->tr = &global_trace;
+	iter->trace = current_trace;
+	iter->cpu_file = TRACE_PIPE_ALL_CPU;
+}
+
 static void
 __ftrace_dump(bool disable_tracing, enum ftrace_dump_mode oops_dump_mode)
 {
@@ -4442,8 +4438,10 @@ __ftrace_dump(bool disable_tracing, enum ftrace_dump_mode oops_dump_mode)
 	if (disable_tracing)
 		ftrace_kill();
 
+	trace_init_global_iter(&iter);
+
 	for_each_tracing_cpu(cpu) {
-		atomic_inc(&global_trace.data[cpu]->disabled);
+		atomic_inc(&iter.tr->data[cpu]->disabled);
 	}
 
 	old_userobj = trace_flags & TRACE_ITER_SYM_USEROBJ;
@@ -4492,7 +4490,7 @@ __ftrace_dump(bool disable_tracing, enum ftrace_dump_mode oops_dump_mode)
 		iter.iter_flags |= TRACE_FILE_LAT_FMT;
 		iter.pos = -1;
 
-		if (find_next_entry_inc(&iter) != NULL) {
+		if (trace_find_next_entry_inc(&iter) != NULL) {
 			int ret;
 
 			ret = print_trace_line(&iter);
@@ -4514,7 +4512,7 @@ __ftrace_dump(bool disable_tracing, enum ftrace_dump_mode oops_dump_mode)
 		trace_flags |= old_userobj;
 
 		for_each_tracing_cpu(cpu) {
-			atomic_dec(&global_trace.data[cpu]->disabled);
+			atomic_dec(&iter.tr->data[cpu]->disabled);
 		}
 		tracing_on();
 	}
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index d05c873dd4b2..d39b3c5454a5 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -314,6 +314,14 @@ struct trace_entry *tracing_get_trace_entry(struct trace_array *tr,
 struct trace_entry *trace_find_next_entry(struct trace_iterator *iter,
 					  int *ent_cpu, u64 *ent_ts);
 
+int trace_empty(struct trace_iterator *iter);
+
+void *trace_find_next_entry_inc(struct trace_iterator *iter);
+
+void trace_init_global_iter(struct trace_iterator *iter);
+
+void tracing_iter_reset(struct trace_iterator *iter, int cpu);
+
 void default_wait_pipe(struct trace_iterator *iter);
 void poll_wait_pipe(struct trace_iterator *iter);
 
@@ -351,6 +359,15 @@ void tracing_start_sched_switch_record(void);
 int register_tracer(struct tracer *type);
 void unregister_tracer(struct tracer *type);
 int is_tracing_stopped(void);
+enum trace_file_type {
+	TRACE_FILE_LAT_FMT	= 1,
+	TRACE_FILE_ANNOTATE	= 2,
+};
+
+extern cpumask_var_t __read_mostly tracing_buffer_mask;
+
+#define for_each_tracing_cpu(cpu)	\
+	for_each_cpu(cpu, tracing_buffer_mask)
 
 extern unsigned long nsecs_to_usecs(unsigned long nsecs);
 
@@ -436,6 +453,8 @@ trace_array_vprintk(struct trace_array *tr,
 		    unsigned long ip, const char *fmt, va_list args);
 int trace_array_printk(struct trace_array *tr,
 		       unsigned long ip, const char *fmt, ...);
+void trace_printk_seq(struct trace_seq *s);
+enum print_line_t print_trace_line(struct trace_iterator *iter);
 
 extern unsigned long trace_flags;
 
diff --git a/kernel/trace/trace_clock.c b/kernel/trace/trace_clock.c
index 52fda6c04ac3..685a67d55db0 100644
--- a/kernel/trace/trace_clock.c
+++ b/kernel/trace/trace_clock.c
@@ -55,7 +55,7 @@ u64 notrace trace_clock_local(void)
  */
 u64 notrace trace_clock(void)
 {
-	return cpu_clock(raw_smp_processor_id());
+	return local_clock();
 }
 
 
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 09b4fa6e4d3b..398c0e8b332c 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -598,88 +598,146 @@ out:
 	return ret;
 }
 
-static void print_event_fields(struct trace_seq *s, struct list_head *head)
+enum {
+	FORMAT_HEADER		= 1,
+	FORMAT_FIELD_SEPERATOR	= 2,
+	FORMAT_PRINTFMT		= 3,
+};
+
+static void *f_next(struct seq_file *m, void *v, loff_t *pos)
 {
+	struct ftrace_event_call *call = m->private;
 	struct ftrace_event_field *field;
+	struct list_head *common_head = &ftrace_common_fields;
+	struct list_head *head = trace_get_fields(call);
 
-	list_for_each_entry_reverse(field, head, link) {
-		/*
-		 * Smartly shows the array type(except dynamic array).
-		 * Normal:
-		 *	field:TYPE VAR
-		 * If TYPE := TYPE[LEN], it is shown:
-		 *	field:TYPE VAR[LEN]
-		 */
-		const char *array_descriptor = strchr(field->type, '[');
+	(*pos)++;
 
-		if (!strncmp(field->type, "__data_loc", 10))
-			array_descriptor = NULL;
+	switch ((unsigned long)v) {
+	case FORMAT_HEADER:
+		if (unlikely(list_empty(common_head)))
+			return NULL;
 
-		if (!array_descriptor) {
-			trace_seq_printf(s, "\tfield:%s %s;\toffset:%u;"
-					"\tsize:%u;\tsigned:%d;\n",
-					field->type, field->name, field->offset,
-					field->size, !!field->is_signed);
-		} else {
-			trace_seq_printf(s, "\tfield:%.*s %s%s;\toffset:%u;"
-					"\tsize:%u;\tsigned:%d;\n",
-					(int)(array_descriptor - field->type),
-					field->type, field->name,
-					array_descriptor, field->offset,
-					field->size, !!field->is_signed);
-		}
+		field = list_entry(common_head->prev,
+				   struct ftrace_event_field, link);
+		return field;
+
+	case FORMAT_FIELD_SEPERATOR:
+		if (unlikely(list_empty(head)))
+			return NULL;
+
+		field = list_entry(head->prev, struct ftrace_event_field, link);
+		return field;
+
+	case FORMAT_PRINTFMT:
+		/* all done */
+		return NULL;
 	}
+
+	field = v;
+	if (field->link.prev == common_head)
+		return (void *)FORMAT_FIELD_SEPERATOR;
+	else if (field->link.prev == head)
+		return (void *)FORMAT_PRINTFMT;
+
+	field = list_entry(field->link.prev, struct ftrace_event_field, link);
+
+	return field;
 }
 
-static ssize_t
-event_format_read(struct file *filp, char __user *ubuf, size_t cnt,
-		  loff_t *ppos)
+static void *f_start(struct seq_file *m, loff_t *pos)
 {
-	struct ftrace_event_call *call = filp->private_data;
-	struct list_head *head;
-	struct trace_seq *s;
-	char *buf;
-	int r;
+	loff_t l = 0;
+	void *p;
 
-	if (*ppos)
+	/* Start by showing the header */
+	if (!*pos)
+		return (void *)FORMAT_HEADER;
+
+	p = (void *)FORMAT_HEADER;
+	do {
+		p = f_next(m, p, &l);
+	} while (p && l < *pos);
+
+	return p;
+}
+
+static int f_show(struct seq_file *m, void *v)
+{
+	struct ftrace_event_call *call = m->private;
+	struct ftrace_event_field *field;
+	const char *array_descriptor;
+
+	switch ((unsigned long)v) {
+	case FORMAT_HEADER:
+		seq_printf(m, "name: %s\n", call->name);
+		seq_printf(m, "ID: %d\n", call->event.type);
+		seq_printf(m, "format:\n");
 		return 0;
 
-	s = kmalloc(sizeof(*s), GFP_KERNEL);
-	if (!s)
-		return -ENOMEM;
+	case FORMAT_FIELD_SEPERATOR:
+		seq_putc(m, '\n');
+		return 0;
 
-	trace_seq_init(s);
+	case FORMAT_PRINTFMT:
+		seq_printf(m, "\nprint fmt: %s\n",
+			   call->print_fmt);
+		return 0;
+	}
 
-	trace_seq_printf(s, "name: %s\n", call->name);
-	trace_seq_printf(s, "ID: %d\n", call->event.type);
-	trace_seq_printf(s, "format:\n");
+	field = v;
 
-	/* print common fields */
-	print_event_fields(s, &ftrace_common_fields);
+	/*
+	 * Smartly shows the array type(except dynamic array).
+	 * Normal:
+	 *	field:TYPE VAR
+	 * If TYPE := TYPE[LEN], it is shown:
+	 *	field:TYPE VAR[LEN]
+	 */
+	array_descriptor = strchr(field->type, '[');
 
-	trace_seq_putc(s, '\n');
+	if (!strncmp(field->type, "__data_loc", 10))
+		array_descriptor = NULL;
 
-	/* print event specific fields */
-	head = trace_get_fields(call);
-	print_event_fields(s, head);
+	if (!array_descriptor)
+		seq_printf(m, "\tfield:%s %s;\toffset:%u;\tsize:%u;\tsigned:%d;\n",
+			   field->type, field->name, field->offset,
+			   field->size, !!field->is_signed);
+	else
+		seq_printf(m, "\tfield:%.*s %s%s;\toffset:%u;\tsize:%u;\tsigned:%d;\n",
+			   (int)(array_descriptor - field->type),
+			   field->type, field->name,
+			   array_descriptor, field->offset,
+			   field->size, !!field->is_signed);
 
-	r = trace_seq_printf(s, "\nprint fmt: %s\n", call->print_fmt);
+	return 0;
+}
 
-	if (!r) {
-		/*
-		 * ug!  The format output is bigger than a PAGE!!
-		 */
-		buf = "FORMAT TOO BIG\n";
-		r = simple_read_from_buffer(ubuf, cnt, ppos,
-					      buf, strlen(buf));
-		goto out;
-	}
+static void f_stop(struct seq_file *m, void *p)
+{
+}
 
-	r = simple_read_from_buffer(ubuf, cnt, ppos,
-				    s->buffer, s->len);
- out:
-	kfree(s);
-	return r;
+static const struct seq_operations trace_format_seq_ops = {
+	.start		= f_start,
+	.next		= f_next,
+	.stop		= f_stop,
+	.show		= f_show,
+};
+
+static int trace_format_open(struct inode *inode, struct file *file)
+{
+	struct ftrace_event_call *call = inode->i_private;
+	struct seq_file *m;
+	int ret;
+
+	ret = seq_open(file, &trace_format_seq_ops);
+	if (ret < 0)
+		return ret;
+
+	m = file->private_data;
+	m->private = call;
+
+	return 0;
 }
 
 static ssize_t
@@ -877,8 +935,10 @@ static const struct file_operations ftrace_enable_fops = {
 };
 
 static const struct file_operations ftrace_event_format_fops = {
-	.open = tracing_open_generic,
-	.read = event_format_read,
+	.open = trace_format_open,
+	.read = seq_read,
+	.llseek = seq_lseek,
+	.release = seq_release,
 };
 
 static const struct file_operations ftrace_event_id_fops = {
diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c
index fcb5a542cd21..c93bcb248638 100644
--- a/kernel/trace/trace_functions_graph.c
+++ b/kernel/trace/trace_functions_graph.c
@@ -507,7 +507,15 @@ get_return_for_leaf(struct trace_iterator *iter,
 			 * if the output fails.
 			 */
 			data->ent = *curr;
-			data->ret = *next;
+			/*
+			 * If the next event is not a return type, then
+			 * we only care about what type it is. Otherwise we can
+			 * safely copy the entire event.
+			 */
+			if (next->ent.type == TRACE_GRAPH_RET)
+				data->ret = *next;
+			else
+				data->ret.ent.type = next->ent.type;
 		}
 	}
 
diff --git a/kernel/trace/trace_kdb.c b/kernel/trace/trace_kdb.c
new file mode 100644
index 000000000000..7b8ecd751d93
--- /dev/null
+++ b/kernel/trace/trace_kdb.c
@@ -0,0 +1,136 @@
+/*
+ * kdb helper for dumping the ftrace buffer
+ *
+ * Copyright (C) 2010 Jason Wessel <jason.wessel@windriver.com>
+ *
+ * ftrace_dump_buf based on ftrace_dump:
+ * Copyright (C) 2007-2008 Steven Rostedt <srostedt@redhat.com>
+ * Copyright (C) 2008 Ingo Molnar <mingo@redhat.com>
+ *
+ */
+#include <linux/init.h>
+#include <linux/kgdb.h>
+#include <linux/kdb.h>
+#include <linux/ftrace.h>
+
+#include "../debug/kdb/kdb_private.h"
+#include "trace.h"
+#include "trace_output.h"
+
+static void ftrace_dump_buf(int skip_lines, long cpu_file)
+{
+	/* use static because iter can be a bit big for the stack */
+	static struct trace_iterator iter;
+	unsigned int old_userobj;
+	int cnt = 0, cpu;
+
+	trace_init_global_iter(&iter);
+
+	for_each_tracing_cpu(cpu) {
+		atomic_inc(&iter.tr->data[cpu]->disabled);
+	}
+
+	old_userobj = trace_flags;
+
+	/* don't look at user memory in panic mode */
+	trace_flags &= ~TRACE_ITER_SYM_USEROBJ;
+
+	kdb_printf("Dumping ftrace buffer:\n");
+
+	/* reset all but tr, trace, and overruns */
+	memset(&iter.seq, 0,
+		   sizeof(struct trace_iterator) -
+		   offsetof(struct trace_iterator, seq));
+	iter.iter_flags |= TRACE_FILE_LAT_FMT;
+	iter.pos = -1;
+
+	if (cpu_file == TRACE_PIPE_ALL_CPU) {
+		for_each_tracing_cpu(cpu) {
+			iter.buffer_iter[cpu] =
+			ring_buffer_read_prepare(iter.tr->buffer, cpu);
+			ring_buffer_read_start(iter.buffer_iter[cpu]);
+			tracing_iter_reset(&iter, cpu);
+		}
+	} else {
+		iter.cpu_file = cpu_file;
+		iter.buffer_iter[cpu_file] =
+			ring_buffer_read_prepare(iter.tr->buffer, cpu_file);
+		ring_buffer_read_start(iter.buffer_iter[cpu_file]);
+		tracing_iter_reset(&iter, cpu_file);
+	}
+	if (!trace_empty(&iter))
+		trace_find_next_entry_inc(&iter);
+	while (!trace_empty(&iter)) {
+		if (!cnt)
+			kdb_printf("---------------------------------\n");
+		cnt++;
+
+		if (trace_find_next_entry_inc(&iter) != NULL && !skip_lines)
+			print_trace_line(&iter);
+		if (!skip_lines)
+			trace_printk_seq(&iter.seq);
+		else
+			skip_lines--;
+		if (KDB_FLAG(CMD_INTERRUPT))
+			goto out;
+	}
+
+	if (!cnt)
+		kdb_printf("   (ftrace buffer empty)\n");
+	else
+		kdb_printf("---------------------------------\n");
+
+out:
+	trace_flags = old_userobj;
+
+	for_each_tracing_cpu(cpu) {
+		atomic_dec(&iter.tr->data[cpu]->disabled);
+	}
+
+	for_each_tracing_cpu(cpu)
+		if (iter.buffer_iter[cpu])
+			ring_buffer_read_finish(iter.buffer_iter[cpu]);
+}
+
+/*
+ * kdb_ftdump - Dump the ftrace log buffer
+ */
+static int kdb_ftdump(int argc, const char **argv)
+{
+	int skip_lines = 0;
+	long cpu_file;
+	char *cp;
+
+	if (argc > 2)
+		return KDB_ARGCOUNT;
+
+	if (argc) {
+		skip_lines = simple_strtol(argv[1], &cp, 0);
+		if (*cp)
+			skip_lines = 0;
+	}
+
+	if (argc == 2) {
+		cpu_file = simple_strtol(argv[2], &cp, 0);
+		if (*cp || cpu_file >= NR_CPUS || cpu_file < 0 ||
+		    !cpu_online(cpu_file))
+			return KDB_BADINT;
+	} else {
+		cpu_file = TRACE_PIPE_ALL_CPU;
+	}
+
+	kdb_trap_printk++;
+	ftrace_dump_buf(skip_lines, cpu_file);
+	kdb_trap_printk--;
+
+	return 0;
+}
+
+static __init int kdb_ftrace_register(void)
+{
+	kdb_register_repeat("ftdump", kdb_ftdump, "[skip_#lines] [cpu]",
+			    "Dump ftrace log", 0, KDB_REPEAT_NONE);
+	return 0;
+}
+
+late_initcall(kdb_ftrace_register);