tracing: updates

index a510b75..814566c 100644
@@ -100,18 +100,7 @@ TRACE_EVENT(signal_deliver,
 		  __entry->sa_handler, __entry->sa_flags)
 );
 
-/**
- * signal_overflow_fail - called when signal queue is overflow
- * @sig: signal number
- * @group: signal to process group or not (bool)
- * @info: pointer to struct siginfo
- *
- * Kernel fails to generate 'sig' signal with 'info' siginfo, because
- * siginfo queue is overflow, and the signal is dropped.
- * 'group' is not 0 if the signal will be sent to a process group.
- * 'sig' is always one of RT signals.
- */
-TRACE_EVENT(signal_overflow_fail,
+DECLARE_EVENT_CLASS(signal_queue_overflow,
 
 	TP_PROTO(int sig, int group, struct siginfo *info),
 

@@ -135,6 +124,24 @@ TRACE_EVENT(signal_overflow_fail,
 );
 
 /**
+ * signal_overflow_fail - called when signal queue is overflow
+ * @sig: signal number
+ * @group: signal to process group or not (bool)
+ * @info: pointer to struct siginfo
+ *
+ * Kernel fails to generate 'sig' signal with 'info' siginfo, because
+ * siginfo queue is overflow, and the signal is dropped.
+ * 'group' is not 0 if the signal will be sent to a process group.
+ * 'sig' is always one of RT signals.
+ */
+DEFINE_EVENT(signal_queue_overflow, signal_overflow_fail,
+
+	TP_PROTO(int sig, int group, struct siginfo *info),
+
+	TP_ARGS(sig, group, info)
+);
+
+/**
  * signal_lose_info - called when siginfo is lost
  * @sig: signal number
  * @group: signal to process group or not (bool)

@@ -145,28 +152,13 @@ TRACE_EVENT(signal_overflow_fail,
  * 'group' is not 0 if the signal will be sent to a process group.
  * 'sig' is always one of non-RT signals.
  */
-TRACE_EVENT(signal_lose_info,
+DEFINE_EVENT(signal_queue_overflow, signal_lose_info,
 
 	TP_PROTO(int sig, int group, struct siginfo *info),
 
-	TP_ARGS(sig, group, info),
-
-	TP_STRUCT__entry(
-		__field(	int,	sig	)
-		__field(	int,	group	)
-		__field(	int,	errno	)
-		__field(	int,	code	)
-	),
-
-	TP_fast_assign(
-		__entry->sig	= sig;
-		__entry->group	= group;
-		TP_STORE_SIGINFO(__entry, info);
-	),
-
-	TP_printk("sig=%d group=%d errno=%d code=%d",
-		  __entry->sig, __entry->group, __entry->errno, __entry->code)
+	TP_ARGS(sig, group, info)
 );
+
 #endif /* _TRACE_SIGNAL_H */
 
 /* This part must be outside protection */

index ea6f9d4..75dd778 100644
@@ -154,9 +154,11 @@
  *
  *	field = (typeof(field))entry;
  *
- *	p = get_cpu_var(ftrace_event_seq);
+ *	p = &get_cpu_var(ftrace_event_seq);
  *	trace_seq_init(p);
- *	ret = trace_seq_printf(s, <TP_printk> "\n");
+ *	ret = trace_seq_printf(s, "%s: ", <call>);
+ *	if (ret)
+ *		ret = trace_seq_printf(s, <TP_printk> "\n");
  *	put_cpu();
  *	if (!ret)
  *		return TRACE_TYPE_PARTIAL_LINE;

@@ -450,38 +452,38 @@ perf_trace_disable_##name(struct ftrace_event_call *unused)		\
  *
  * static void ftrace_raw_event_<call>(proto)
  * {
+ *	struct ftrace_data_offsets_<call> __maybe_unused __data_offsets;
  *	struct ring_buffer_event *event;
  *	struct ftrace_raw_<call> *entry; <-- defined in stage 1
  *	struct ring_buffer *buffer;
  *	unsigned long irq_flags;
+ *	int __data_size;
  *	int pc;
  *
  *	local_save_flags(irq_flags);
  *	pc = preempt_count();
  *
+ *	__data_size = ftrace_get_offsets_<call>(&__data_offsets, args);
+ *
  *	event = trace_current_buffer_lock_reserve(&buffer,
  *				  event_<call>.id,
- *				  sizeof(struct ftrace_raw_<call>),
+ *				  sizeof(*entry) + __data_size,
  *				  irq_flags, pc);
  *	if (!event)
  *		return;
  *	entry	= ring_buffer_event_data(event);
  *
- *	<assign>;  <-- Here we assign the entries by the __field and
- *			__array macros.
+ *	{ <assign>; }  <-- Here we assign the entries by the __field and
+ *			   __array macros.
  *
- *	trace_current_buffer_unlock_commit(buffer, event, irq_flags, pc);
+ *	if (!filter_current_check_discard(buffer, event_call, entry, event))
+ *		trace_current_buffer_unlock_commit(buffer,
+ *						   event, irq_flags, pc);
  * }
  *
  * static int ftrace_raw_reg_event_<call>(struct ftrace_event_call *unused)
  * {
- *	int ret;
- *
- *	ret = register_trace_<call>(ftrace_raw_event_<call>);
- *	if (!ret)
- *		pr_info("event trace: Could not activate trace point "
- *			"probe to <call>");
- *	return ret;
+ *	return register_trace_<call>(ftrace_raw_event_<call>);
  * }
  *
  * static void ftrace_unreg_event_<call>(struct ftrace_event_call *unused)

@@ -493,6 +495,8 @@ perf_trace_disable_##name(struct ftrace_event_call *unused)		\
  *	.trace			= ftrace_raw_output_<call>, <-- stage 2
  * };
  *
+ * static const char print_fmt_<call>[] = <TP_printk>;
+ *
  * static struct ftrace_event_call __used
  * __attribute__((__aligned__(4)))
  * __attribute__((section("_ftrace_events"))) event_<call> = {

@@ -501,6 +505,8 @@ perf_trace_disable_##name(struct ftrace_event_call *unused)		\
  *	.raw_init		= trace_event_raw_init,
  *	.regfunc		= ftrace_reg_event_<call>,
  *	.unregfunc		= ftrace_unreg_event_<call>,
+ *	.print_fmt		= print_fmt_<call>,
+ *	.define_fields		= ftrace_define_fields_<call>,
  * }
  *
  */

@@ -569,7 +575,6 @@ ftrace_raw_event_id_##call(struct ftrace_event_call *event_call,	\
 		return;							\
 	entry	= ring_buffer_event_data(event);			\
 									\
-									\
 	tstruct								\
 									\
 	{ assign; }							\

index 5e869ff..393ec39 100644
@@ -460,8 +460,7 @@ static inline void __module_get(struct module *module)
 	if (module) {
 		preempt_disable();
 		__this_cpu_inc(module->refptr->count);
-		trace_module_get(module, _THIS_IP_,
-				 __this_cpu_read(module->refptr->count));
+		trace_module_get(module, _THIS_IP_);
 		preempt_enable();
 	}
 }

@@ -475,8 +474,7 @@ static inline int try_module_get(struct module *module)
 
 		if (likely(module_is_live(module))) {
 			__this_cpu_inc(module->refptr->count);
-			trace_module_get(module, _THIS_IP_,
-				__this_cpu_read(module->refptr->count));
+			trace_module_get(module, _THIS_IP_);
 		}
 		else
 			ret = 0;

index 4b0f48b..a585f81 100644
@@ -53,9 +53,9 @@ TRACE_EVENT(module_free,
 
 DECLARE_EVENT_CLASS(module_refcnt,
 
-	TP_PROTO(struct module *mod, unsigned long ip, int refcnt),
+	TP_PROTO(struct module *mod, unsigned long ip),
 
-	TP_ARGS(mod, ip, refcnt),
+	TP_ARGS(mod, ip),
 
 	TP_STRUCT__entry(
 		__field(	unsigned long,	ip		)

@@ -65,7 +65,7 @@ DECLARE_EVENT_CLASS(module_refcnt,
 
 	TP_fast_assign(
 		__entry->ip	= ip;
-		__entry->refcnt	= refcnt;
+		__entry->refcnt	= __this_cpu_read(mod->refptr->count);
 		__assign_str(name, mod->name);
 	),
 

@@ -75,16 +75,16 @@ DECLARE_EVENT_CLASS(module_refcnt,
 
 DEFINE_EVENT(module_refcnt, module_get,
 
-	TP_PROTO(struct module *mod, unsigned long ip, int refcnt),
+	TP_PROTO(struct module *mod, unsigned long ip),
 
-	TP_ARGS(mod, ip, refcnt)
+	TP_ARGS(mod, ip)
 );
 
 DEFINE_EVENT(module_refcnt, module_put,
 
-	TP_PROTO(struct module *mod, unsigned long ip, int refcnt),
+	TP_PROTO(struct module *mod, unsigned long ip),
 
-	TP_ARGS(mod, ip, refcnt)
+	TP_ARGS(mod, ip)
 );
 
 TRACE_EVENT(module_request,

index c968d36..21591ad 100644
@@ -800,8 +800,7 @@ void module_put(struct module *module)
 		preempt_disable();
 		__this_cpu_dec(module->refptr->count);
 
-		trace_module_put(module, _RET_IP_,
-				 __this_cpu_read(module->refptr->count));
+		trace_module_put(module, _RET_IP_);
 		/* Maybe they're waiting for us to drop reference? */
 		if (unlikely(!module_is_live(module)))
 			wake_up_process(module->waiter);

index a585f81..f07b44a 100644
@@ -51,6 +51,9 @@ TRACE_EVENT(module_free,
 	TP_printk("%s", __get_str(name))
 );
 
+#ifdef CONFIG_MODULE_UNLOAD
+/* trace_module_get/put are only used if CONFIG_MODULE_UNLOAD is defined */
+
 DECLARE_EVENT_CLASS(module_refcnt,
 
 	TP_PROTO(struct module *mod, unsigned long ip),

@@ -86,6 +89,7 @@ DEFINE_EVENT(module_refcnt, module_put,
 
 	TP_ARGS(mod, ip)
 );
+#endif /* CONFIG_MODULE_UNLOAD */
 
 TRACE_EVENT(module_request,
 

index 21591ad..d9e2379 100644
@@ -59,8 +59,6 @@
 #define CREATE_TRACE_POINTS
 #include <trace/events/module.h>
 
-EXPORT_TRACEPOINT_SYMBOL(module_get);
-
 #if 0
 #define DEBUGP printk
 #else

@@ -467,6 +465,9 @@ MODINFO_ATTR(srcversion);
 static char last_unloaded_module[MODULE_NAME_LEN+1];
 
 #ifdef CONFIG_MODULE_UNLOAD
+
+EXPORT_TRACEPOINT_SYMBOL(module_get);
+
 /* Init the unload section of the module. */
 static void module_unload_init(struct module *mod)
 {

index 166b67e..7581dbe 100644
@@ -186,14 +186,14 @@ int op_cpu_buffer_write_commit(struct op_entry *entry)
 struct op_sample *op_cpu_buffer_read_entry(struct op_entry *entry, int cpu)
 {
 	struct ring_buffer_event *e;
-	e = ring_buffer_consume(op_ring_buffer_read, cpu, NULL);
+	e = ring_buffer_consume(op_ring_buffer_read, cpu, NULL, NULL);
 	if (e)
 		goto event;
 	if (ring_buffer_swap_cpu(op_ring_buffer_read,
 				 op_ring_buffer_write,
 				 cpu))
 		return NULL;
-	e = ring_buffer_consume(op_ring_buffer_read, cpu, NULL);
+	e = ring_buffer_consume(op_ring_buffer_read, cpu, NULL, NULL);
 	if (e)
 		goto event;
 	return NULL;

index 5fcc31e..c829776 100644
@@ -120,9 +120,11 @@ int ring_buffer_write(struct ring_buffer *buffer,
 		      unsigned long length, void *data);
 
 struct ring_buffer_event *
-ring_buffer_peek(struct ring_buffer *buffer, int cpu, u64 *ts);
+ring_buffer_peek(struct ring_buffer *buffer, int cpu, u64 *ts,
+		 unsigned long *lost_events);
 struct ring_buffer_event *
-ring_buffer_consume(struct ring_buffer *buffer, int cpu, u64 *ts);
+ring_buffer_consume(struct ring_buffer *buffer, int cpu, u64 *ts,
+		    unsigned long *lost_events);
 
 struct ring_buffer_iter *
 ring_buffer_read_start(struct ring_buffer *buffer, int cpu);

181 lines not on this page · raw message

index df74c79..dc56556 100644
@@ -81,7 +81,7 @@ static enum event_status read_event(int cpu)
 	int *entry;
 	u64 ts;
 
-	event = ring_buffer_consume(buffer, cpu, &ts);
+	event = ring_buffer_consume(buffer, cpu, &ts, NULL);
 	if (!event)
 		return EVENT_DROPPED;
 

index 3ec2ee6..fabb003 100644
@@ -1556,7 +1556,7 @@ peek_next_entry(struct trace_iterator *iter, int cpu, u64 *ts)
 	if (buf_iter)
 		event = ring_buffer_iter_peek(buf_iter, ts);
 	else
-		event = ring_buffer_peek(iter->tr->buffer, cpu, ts);
+		event = ring_buffer_peek(iter->tr->buffer, cpu, ts, NULL);
 
 	ftrace_enable_cpu();
 

@@ -1635,7 +1635,7 @@ static void trace_consume(struct trace_iterator *iter)
 {
 	/* Don't allow ftrace to trace into the ring buffers */
 	ftrace_disable_cpu();
-	ring_buffer_consume(iter->tr->buffer, iter->cpu, &iter->ts);
+	ring_buffer_consume(iter->tr->buffer, iter->cpu, &iter->ts, NULL);
 	ftrace_enable_cpu();
 }
 

index e6989d9..a7f75fb 100644
@@ -489,9 +489,10 @@ get_return_for_leaf(struct trace_iterator *iter,
 			 * We need to consume the current entry to see
 			 * the next one.
 			 */
-			ring_buffer_consume(iter->tr->buffer, iter->cpu, NULL);
+			ring_buffer_consume(iter->tr->buffer, iter->cpu,
+					    NULL, NULL);
 			event = ring_buffer_peek(iter->tr->buffer, iter->cpu,
-						 NULL);
+						 NULL, NULL);
 		}
 
 		if (!event)

index 280fea4..e501808 100644
@@ -29,7 +29,7 @@ static int trace_test_buffer_cpu(struct trace_array *tr, int cpu)
 	struct trace_entry *entry;
 	unsigned int loops = 0;
 
-	while ((event = ring_buffer_consume(tr->buffer, cpu, NULL))) {
+	while ((event = ring_buffer_consume(tr->buffer, cpu, NULL, NULL))) {
 		entry = ring_buffer_event_data(event);
 
 		/*

index c0f4b36..39e71b0 100644
@@ -58,6 +58,7 @@ struct trace_iterator {
 	/* The below is zeroed out in pipe_read */
 	struct trace_seq	seq;
 	struct trace_entry	*ent;
+	unsigned long		lost_events;
 	int			leftover;
 	int			cpu;
 	u64			ts;

index fabb003..0498beb 100644
@@ -1545,7 +1545,8 @@ static void trace_iterator_increment(struct trace_iterator *iter)
 }
 
 static struct trace_entry *
-peek_next_entry(struct trace_iterator *iter, int cpu, u64 *ts)
+peek_next_entry(struct trace_iterator *iter, int cpu, u64 *ts,
+		unsigned long *lost_events)
 {
 	struct ring_buffer_event *event;
 	struct ring_buffer_iter *buf_iter = iter->buffer_iter[cpu];

@@ -1556,7 +1557,8 @@ peek_next_entry(struct trace_iterator *iter, int cpu, u64 *ts)
 	if (buf_iter)
 		event = ring_buffer_iter_peek(buf_iter, ts);
 	else
-		event = ring_buffer_peek(iter->tr->buffer, cpu, ts, NULL);
+		event = ring_buffer_peek(iter->tr->buffer, cpu, ts,
+					 lost_events);
 
 	ftrace_enable_cpu();
 

@@ -1564,10 +1566,12 @@ peek_next_entry(struct trace_iterator *iter, int cpu, u64 *ts)
 }
 
 static struct trace_entry *
-__find_next_entry(struct trace_iterator *iter, int *ent_cpu, u64 *ent_ts)
+__find_next_entry(struct trace_iterator *iter, int *ent_cpu,
+		  unsigned long *missing_events, u64 *ent_ts)
 {
 	struct ring_buffer *buffer = iter->tr->buffer;
 	struct trace_entry *ent, *next = NULL;
+	unsigned long lost_events, next_lost = 0;
 	int cpu_file = iter->cpu_file;
 	u64 next_ts = 0, ts;
 	int next_cpu = -1;

@@ -1580,7 +1584,7 @@ __find_next_entry(struct trace_iterator *iter, int *ent_cpu, u64 *ent_ts)
 	if (cpu_file > TRACE_PIPE_ALL_CPU) {
 		if (ring_buffer_empty_cpu(buffer, cpu_file))
 			return NULL;
-		ent = peek_next_entry(iter, cpu_file, ent_ts);
+		ent = peek_next_entry(iter, cpu_file, ent_ts, missing_events);
 		if (ent_cpu)
 			*ent_cpu = cpu_file;
 

@@ -1592,7 +1596,7 @@ __find_next_entry(struct trace_iterator *iter, int *ent_cpu, u64 *ent_ts)
 		if (ring_buffer_empty_cpu(buffer, cpu))
 			continue;
 
-		ent = peek_next_entry(iter, cpu, &ts);
+		ent = peek_next_entry(iter, cpu, &ts, &lost_events);
 
 		/*
 		 * Pick the entry with the smallest timestamp:

@@ -1601,6 +1605,7 @@ __find_next_entry(struct trace_iterator *iter, int *ent_cpu, u64 *ent_ts)
 			next = ent;
 			next_cpu = cpu;
 			next_ts = ts;
+			next_lost = lost_events;
 		}
 	}
 

@@ -1610,6 +1615,9 @@ __find_next_entry(struct trace_iterator *iter, int *ent_cpu, u64 *ent_ts)
 	if (ent_ts)
 		*ent_ts = next_ts;
 
+	if (missing_events)
+		*missing_events = next_lost;
+
 	return next;
 }
 

@@ -1617,13 +1625,14 @@ __find_next_entry(struct trace_iterator *iter, int *ent_cpu, u64 *ent_ts)
 struct trace_entry *trace_find_next_entry(struct trace_iterator *iter,
 					  int *ent_cpu, u64 *ent_ts)
 {
-	return __find_next_entry(iter, ent_cpu, ent_ts);
+	return __find_next_entry(iter, ent_cpu, NULL, ent_ts);
 }
 
 /* Find the next real entry, and increment the iterator to the next entry */
 static void *find_next_entry_inc(struct trace_iterator *iter)
 {
-	iter->ent = __find_next_entry(iter, &iter->cpu, &iter->ts);
+	iter->ent = __find_next_entry(iter, &iter->cpu,
+				      &iter->lost_events, &iter->ts);
 
 	if (iter->ent)
 		trace_iterator_increment(iter);

@@ -1635,7 +1644,8 @@ static void trace_consume(struct trace_iterator *iter)
 {
 	/* Don't allow ftrace to trace into the ring buffers */
 	ftrace_disable_cpu();
-	ring_buffer_consume(iter->tr->buffer, iter->cpu, &iter->ts, NULL);
+	ring_buffer_consume(iter->tr->buffer, iter->cpu, &iter->ts,
+			    &iter->lost_events);
 	ftrace_enable_cpu();
 }
 

@@ -2030,6 +2040,10 @@ static enum print_line_t print_trace_line(struct trace_iterator *iter)
 {
 	enum print_line_t ret;
 
+	if (iter->lost_events)
+		trace_seq_printf(&iter->seq, "CPU:%d [LOST %lu EVENTS]\n",
+				 iter->cpu, iter->lost_events);
+
 	if (iter->trace && iter->trace->print_line) {
 		ret = iter->trace->print_line(iter);
 		if (ret != TRACE_TYPE_UNHANDLED)

index 8295650..dc6d563 100644
@@ -320,6 +320,8 @@ EXPORT_SYMBOL_GPL(ring_buffer_event_data);
 
 /* Flag when events were overwritten */
 #define RB_MISSED_EVENTS	(1 << 31)
+/* Missed count stored at end */
+#define RB_MISSED_STORED	(1 << 30)
 
 struct buffer_data_page {
 	u64		 time_stamp;	/* page time stamp */

@@ -340,6 +342,7 @@ struct buffer_page {
 	local_t		 write;		/* index for next write */
 	unsigned	 read;		/* index for next read */
 	local_t		 entries;	/* entries on this page */
+	unsigned long	 real_end;	/* real end of data */
 	struct buffer_data_page *page;	/* Actual data page */
 };
 

@@ -1770,6 +1773,13 @@ rb_reset_tail(struct ring_buffer_per_cpu *cpu_buffer,
 	kmemcheck_annotate_bitfield(event, bitfield);
 
 	/*
+	 * Save the original length to the meta data.
+	 * This will be used by the reader to add lost event
+	 * counter.
+	 */
+	tail_page->real_end = tail;
+
+	/*
 	 * If this event is bigger than the minimum size, then
 	 * we need to be careful that we don't subtract the
 	 * write counter enough to allow another writer to slip

@@ -2888,6 +2898,7 @@ rb_get_reader_page(struct ring_buffer_per_cpu *cpu_buffer)
 	local_set(&cpu_buffer->reader_page->write, 0);
 	local_set(&cpu_buffer->reader_page->entries, 0);
 	local_set(&cpu_buffer->reader_page->page->commit, 0);
+	cpu_buffer->reader_page->real_end = 0;
 
  spin:
 	/*

@@ -3728,11 +3739,11 @@ int ring_buffer_read_page(struct ring_buffer *buffer,
 	struct ring_buffer_event *event;
 	struct buffer_data_page *bpage;
 	struct buffer_page *reader;
+	unsigned long missed_events;
 	unsigned long flags;
 	unsigned int commit;
 	unsigned int read;
 	u64 save_timestamp;
-	int missed_events = 0;
 	int ret = -1;
 
 	if (!cpumask_test_cpu(cpu, buffer->cpumask))

@@ -3766,8 +3777,7 @@ int ring_buffer_read_page(struct ring_buffer *buffer,
 	commit = rb_page_commit(reader);
 
 	/* Check if any events were dropped */
-	if (cpu_buffer->lost_events)
-		missed_events = 1;
+	missed_events = cpu_buffer->lost_events;
 
 	/*
 	 * If this page has been partially read or

@@ -3829,6 +3839,14 @@ int ring_buffer_read_page(struct ring_buffer *buffer,
 		local_set(&reader->entries, 0);
 		reader->read = 0;
 		*data_page = bpage;
+
+		/*
+		 * Use the real_end for the data size,
+		 * This gives us a chance to store the lost events
+		 * on the page.
+		 */
+		if (reader->real_end)
+			local_set(&bpage->commit, reader->real_end);
 	}
 	ret = read;
 

@@ -3836,8 +3854,19 @@ int ring_buffer_read_page(struct ring_buffer *buffer,
 	/*
 	 * Set a flag in the commit field if we lost events
 	 */
-	if (missed_events)
+	if (missed_events) {
+		commit = local_read(&bpage->commit);
+
+		/* If there is room at the end of the page to save the
+		 * missed events, then record it there.
+		 */
+		if (BUF_PAGE_SIZE - commit >= sizeof(missed_events)) {
+			memcpy(&bpage->data[commit], &missed_events,
+			       sizeof(missed_events));
+			local_add(RB_MISSED_STORED, &bpage->commit);
+		}
 		local_add(RB_MISSED_EVENTS, &bpage->commit);
+	}
 
  out_unlock:
 	spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);