Merge branch 'tip/tracing/ftrace-4' of...

Merge branch 'tip/tracing/ftrace-4' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-2.6-trace into tracing/ftrace

include/trace/ftrace.h

@@ -104,6 +104,7 @@
  *	field = (typeof(field))entry;
  *
  *	p = get_cpu_var(ftrace_event_seq);
+ *	trace_seq_init(p);
  *	ret = trace_seq_printf(s, <TP_printk> "\n");
  *	put_cpu();
  *	if (!ret)
@@ -167,6 +168,7 @@ ftrace_raw_output_##call(struct trace_iterator *iter, int flags)	\
 	field = (typeof(field))entry;					\
 									\
 	p = &get_cpu_var(ftrace_event_seq);				\
+	trace_seq_init(p);						\
 	ret = trace_seq_printf(s, #call ": " print);			\
 	put_cpu();							\
 	if (!ret)							\

kernel/trace/ring_buffer.c

@@ -370,6 +370,9 @@ static inline int test_time_stamp(u64 delta)
 /* Max payload is BUF_PAGE_SIZE - header (8bytes) */
 #define BUF_MAX_DATA_SIZE (BUF_PAGE_SIZE - (sizeof(u32) * 2))
 
+/* Max number of timestamps that can fit on a page */
+#define RB_TIMESTAMPS_PER_PAGE	(BUF_PAGE_SIZE / RB_LEN_TIME_STAMP)
+
 int ring_buffer_print_page_header(struct trace_seq *s)
 {
 	struct buffer_data_page field;
@@ -1335,6 +1338,38 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer,
 	return event;
 }
 
+static inline int
+rb_try_to_discard(struct ring_buffer_per_cpu *cpu_buffer,
+		  struct ring_buffer_event *event)
+{
+	unsigned long new_index, old_index;
+	struct buffer_page *bpage;
+	unsigned long index;
+	unsigned long addr;
+
+	new_index = rb_event_index(event);
+	old_index = new_index + rb_event_length(event);
+	addr = (unsigned long)event;
+	addr &= PAGE_MASK;
+
+	bpage = cpu_buffer->tail_page;
+
+	if (bpage->page == (void *)addr && rb_page_write(bpage) == old_index) {
+		/*
+		 * This is on the tail page. It is possible that
+		 * a write could come in and move the tail page
+		 * and write to the next page. That is fine
+		 * because we just shorten what is on this page.
+		 */
+		index = local_cmpxchg(&bpage->write, old_index, new_index);
+		if (index == old_index)
+			return 1;
+	}
+
+	/* could not discard */
+	return 0;
+}
+
 static int
 rb_add_time_stamp(struct ring_buffer_per_cpu *cpu_buffer,
 		  u64 *ts, u64 *delta)
@@ -1377,18 +1412,25 @@ rb_add_time_stamp(struct ring_buffer_per_cpu *cpu_buffer,
 			event->array[0] = *delta >> TS_SHIFT;
 		} else {
 			cpu_buffer->commit_page->page->time_stamp = *ts;
+			/* try to discard, since we do not need this */
+			if (!rb_try_to_discard(cpu_buffer, event)) {
+				/* nope, just zero it */
 				event->time_delta = 0;
 				event->array[0] = 0;
 			}
+		}
 		cpu_buffer->write_stamp = *ts;
 		/* let the caller know this was the commit */
 		ret = 1;
 	} else {
+		/* Try to discard the event */
+		if (!rb_try_to_discard(cpu_buffer, event)) {
 			/* Darn, this is just wasted space */
 			event->time_delta = 0;
 			event->array[0] = 0;
 			ret = 0;
 		}
+	}
 
 	*delta = 0;
 
@@ -1682,10 +1724,6 @@ void ring_buffer_discard_commit(struct ring_buffer *buffer,
 				struct ring_buffer_event *event)
 {
 	struct ring_buffer_per_cpu *cpu_buffer;
-	unsigned long new_index, old_index;
-	struct buffer_page *bpage;
-	unsigned long index;
-	unsigned long addr;
 	int cpu;
 
 	/* The event is discarded regardless */
@@ -1701,24 +1739,8 @@ void ring_buffer_discard_commit(struct ring_buffer *buffer,
 	cpu = smp_processor_id();
 	cpu_buffer = buffer->buffers[cpu];
 
-	new_index = rb_event_index(event);
-	old_index = new_index + rb_event_length(event);
-	addr = (unsigned long)event;
-	addr &= PAGE_MASK;
-
-	bpage = cpu_buffer->tail_page;
-
-	if (bpage == (void *)addr && rb_page_write(bpage) == old_index) {
-		/*
-		 * This is on the tail page. It is possible that
-		 * a write could come in and move the tail page
-		 * and write to the next page. That is fine
-		 * because we just shorten what is on this page.
-		 */
-		index = local_cmpxchg(&bpage->write, old_index, new_index);
-		if (index == old_index)
+	if (!rb_try_to_discard(cpu_buffer, event))
 		goto out;
-	}
 
 	/*
 	 * The commit is still visible by the reader, so we
@@ -2253,8 +2275,8 @@ static void rb_advance_iter(struct ring_buffer_iter *iter)
 	 * Check if we are at the end of the buffer.
 	 */
 	if (iter->head >= rb_page_size(iter->head_page)) {
-		if (RB_WARN_ON(buffer,
-			       iter->head_page == cpu_buffer->commit_page))
+		/* discarded commits can make the page empty */
+		if (iter->head_page == cpu_buffer->commit_page)
 			return;
 		rb_inc_iter(iter);
 		return;
@@ -2297,12 +2319,10 @@ rb_buffer_peek(struct ring_buffer *buffer, int cpu, u64 *ts)
 	/*
 	 * We repeat when a timestamp is encountered. It is possible
 	 * to get multiple timestamps from an interrupt entering just
-	 * as one timestamp is about to be written. The max times
-	 * that this can happen is the number of nested interrupts we
-	 * can have.  Nesting 10 deep of interrupts is clearly
-	 * an anomaly.
+	 * as one timestamp is about to be written, or from discarded
+	 * commits. The most that we can have is the number on a single page.
 	 */
-	if (RB_WARN_ON(cpu_buffer, ++nr_loops > 10))
+	if (RB_WARN_ON(cpu_buffer, ++nr_loops > RB_TIMESTAMPS_PER_PAGE))
 		return NULL;
 
 	reader = rb_get_reader_page(cpu_buffer);
@@ -2368,14 +2388,14 @@ rb_iter_peek(struct ring_buffer_iter *iter, u64 *ts)
 
  again:
 	/*
-	 * We repeat when a timestamp is encountered. It is possible
-	 * to get multiple timestamps from an interrupt entering just
-	 * as one timestamp is about to be written. The max times
-	 * that this can happen is the number of nested interrupts we
-	 * can have. Nesting 10 deep of interrupts is clearly
-	 * an anomaly.
-	 */
-	if (RB_WARN_ON(cpu_buffer, ++nr_loops > 10))
+	 * We repeat when a timestamp is encountered.
+	 * We can get multiple timestamps by nested interrupts or also
+	 * if filtering is on (discarding commits). Since discarding
+	 * commits can be frequent we can get a lot of timestamps.
+	 * But we limit them by not adding timestamps if they begin
+	 * at the start of a page.
+	 */
+	if (RB_WARN_ON(cpu_buffer, ++nr_loops > RB_TIMESTAMPS_PER_PAGE))
 		return NULL;
 
 	if (rb_per_cpu_empty(cpu_buffer))

kernel/trace/trace_output.c

@@ -223,10 +223,9 @@ ftrace_print_flags_seq(struct trace_seq *p, const char *delim,
 {
 	unsigned long mask;
 	const char *str;
+	const char *ret = p->buffer + p->len;
 	int i;
 
-	trace_seq_init(p);
-
 	for (i = 0;  flag_array[i].name && flags; i++) {
 
 		mask = flag_array[i].mask;
@@ -249,7 +248,7 @@ ftrace_print_flags_seq(struct trace_seq *p, const char *delim,
 
 	trace_seq_putc(p, 0);
 
-	return p->buffer;
+	return ret;
 }
 EXPORT_SYMBOL(ftrace_print_flags_seq);
 
@@ -258,8 +257,7 @@ ftrace_print_symbols_seq(struct trace_seq *p, unsigned long val,
 			 const struct trace_print_flags *symbol_array)
 {
 	int i;
-
-	trace_seq_init(p);
+	const char *ret = p->buffer + p->len;
 
 	for (i = 0;  symbol_array[i].name; i++) {
 
@@ -275,7 +273,7 @@ ftrace_print_symbols_seq(struct trace_seq *p, unsigned long val,
 		
 	trace_seq_putc(p, 0);
 
-	return p->buffer;
+	return ret;
 }
 EXPORT_SYMBOL(ftrace_print_symbols_seq);
 
@@ -389,17 +387,20 @@ seq_print_userip_objs(const struct userstack_entry *entry, struct trace_seq *s,
 
 		if (ip == ULONG_MAX || !ret)
 			break;
-		if (i && ret)
-			ret = trace_seq_puts(s, " <- ");
+		if (ret)
+			ret = trace_seq_puts(s, " => ");
 		if (!ip) {
 			if (ret)
 				ret = trace_seq_puts(s, "??");
+			if (ret)
+				ret = trace_seq_puts(s, "\n");
 			continue;
 		}
 		if (!ret)
 			break;
 		if (ret)
 			ret = seq_print_user_ip(s, mm, ip, sym_flags);
+		ret = trace_seq_puts(s, "\n");
 	}
 
 	if (mm)
@@ -975,16 +976,16 @@ static enum print_line_t trace_stack_print(struct trace_iterator *iter,
 
 	trace_assign_type(field, iter->ent);
 
+	if (!trace_seq_puts(s, "<stack trace>\n"))
+		goto partial;
 	for (i = 0; i < FTRACE_STACK_ENTRIES; i++) {
-		if (!field->caller[i])
+		if (!field->caller[i] || (field->caller[i] == ULONG_MAX))
 			break;
-		if (i) {
-			if (!trace_seq_puts(s, " <= "))
+		if (!trace_seq_puts(s, " => "))
 			goto partial;
 
 		if (!seq_print_ip_sym(s, field->caller[i], flags))
 			goto partial;
-		}
 		if (!trace_seq_puts(s, "\n"))
 			goto partial;
 	}
@@ -1012,10 +1013,10 @@ static enum print_line_t trace_user_stack_print(struct trace_iterator *iter,
 
 	trace_assign_type(field, iter->ent);
 
-	if (!seq_print_userip_objs(field, s, flags))
+	if (!trace_seq_puts(s, "<user stack trace>\n"))
 		goto partial;
 
-	if (!trace_seq_putc(s, '\n'))
+	if (!seq_print_userip_objs(field, s, flags))
 		goto partial;
 
 	return TRACE_TYPE_HANDLED;

kernel/trace/trace_stack.c

@@ -265,7 +265,7 @@ static int t_show(struct seq_file *m, void *v)
 		seq_printf(m, "        Depth    Size   Location"
 			   "    (%d entries)\n"
 			   "        -----    ----   --------\n",
-			   max_stack_trace.nr_entries);
+			   max_stack_trace.nr_entries - 1);
 
 		if (!stack_tracer_enabled && !max_stack_size)
 			print_disabled(m);