tracing: Added hardware latency tracer

The hardware latency tracer has been in the PREEMPT_RT patch for some time.
It is used to detect possible SMIs or any other hardware interruptions that
the kernel is unaware of. Note, NMIs may also be detected, but that may be
good to note as well.

The logic is pretty simple. It simply creates a thread that spins on a
single CPU for a specified amount of time (width) within a periodic window
(window). These numbers may be adjusted by their cooresponding names in

   /sys/kernel/tracing/hwlat_detector/

The defaults are window = 1000000 us (1 second)
                 width  =  500000 us (1/2 second)

The loop consists of:

	t1 = trace_clock_local();
	t2 = trace_clock_local();

Where trace_clock_local() is a variant of sched_clock().

The difference of t2 - t1 is recorded as the "inner" timestamp and also the
timestamp  t1 - prev_t2 is recorded as the "outer" timestamp. If either of
these differences are greater than the time denoted in
/sys/kernel/tracing/tracing_thresh then it records the event.

When this tracer is started, and tracing_thresh is zero, it changes to the
default threshold of 10 us.

The hwlat tracer in the PREEMPT_RT patch was originally written by
Jon Masters. I have modified it quite a bit and turned it into a
tracer.

Based-on-code-by: Jon Masters <[email protected]>
Signed-off-by: Steven Rostedt <[email protected]>

kernel/trace/Kconfig

@@ -221,6 +221,41 @@ config SCHED_TRACER
 	  This tracer tracks the latency of the highest priority task
 	  to be scheduled in, starting from the point it has woken up.
 
+config HWLAT_TRACER
+	bool "Tracer to detect hardware latencies (like SMIs)"
+	select GENERIC_TRACER
+	help
+	 This tracer, when enabled will create one or more kernel threads,
+	 depening on what the cpumask file is set to, which each thread
+	 spinning in a loop looking for interruptions caused by
+	 something other than the kernel. For example, if a
+	 System Management Interrupt (SMI) takes a noticeable amount of
+	 time, this tracer will detect it. This is useful for testing
+	 if a system is reliable for Real Time tasks.
+
+	 Some files are created in the tracing directory when this
+	 is enabled:
+
+	   hwlat_detector/width   - time in usecs for how long to spin for
+	   hwlat_detector/window  - time in usecs between the start of each
+				     iteration
+
+	 A kernel thread is created that will spin with interrupts disabled
+	 for "width" microseconds in every "widow" cycle. It will not spin
+	 for "window - width" microseconds, where the system can
+	 continue to operate.
+
+	 The output will appear in the trace and trace_pipe files.
+
+	 When the tracer is not running, it has no affect on the system,
+	 but when it is running, it can cause the system to be
+	 periodically non responsive. Do not run this tracer on a
+	 production system.
+
+	 To enable this tracer, echo in "hwlat" into the current_tracer
+	 file. Every time a latency is greater than tracing_thresh, it will
+	 be recorded into the ring buffer.
+
 config ENABLE_DEFAULT_TRACERS
 	bool "Trace process context switches and events"
 	depends on !GENERIC_TRACER

kernel/trace/Makefile

@@ -41,6 +41,7 @@ obj-$(CONFIG_FUNCTION_TRACER) += trace_functions.o
 obj-$(CONFIG_IRQSOFF_TRACER) += trace_irqsoff.o
 obj-$(CONFIG_PREEMPT_TRACER) += trace_irqsoff.o
 obj-$(CONFIG_SCHED_TRACER) += trace_sched_wakeup.o
+obj-$(CONFIG_HWLAT_TRACER) += trace_hwlat.o
 obj-$(CONFIG_NOP_TRACER) += trace_nop.o
 obj-$(CONFIG_STACK_TRACER) += trace_stack.o
 obj-$(CONFIG_MMIOTRACE) += trace_mmiotrace.o

kernel/trace/trace.c

@@ -1047,7 +1047,7 @@ void disable_trace_on_warning(void)
  *
  * Shows real state of the ring buffer if it is enabled or not.
  */
-static int tracer_tracing_is_on(struct trace_array *tr)
+int tracer_tracing_is_on(struct trace_array *tr)
 {
 	if (tr->trace_buffer.buffer)
 		return ring_buffer_record_is_on(tr->trace_buffer.buffer);

kernel/trace/trace.h

@@ -38,6 +38,7 @@ enum trace_type {
 	TRACE_USER_STACK,
 	TRACE_BLK,
 	TRACE_BPUTS,
+	TRACE_HWLAT,
 
 	__TRACE_LAST_TYPE,
 };
@@ -326,6 +327,7 @@ extern void __ftrace_bad_type(void);
 		IF_ASSIGN(var, ent, struct print_entry, TRACE_PRINT);	\
 		IF_ASSIGN(var, ent, struct bprint_entry, TRACE_BPRINT);	\
 		IF_ASSIGN(var, ent, struct bputs_entry, TRACE_BPUTS);	\
+		IF_ASSIGN(var, ent, struct hwlat_entry, TRACE_HWLAT);	\
 		IF_ASSIGN(var, ent, struct trace_mmiotrace_rw,		\
 			  TRACE_MMIO_RW);				\
 		IF_ASSIGN(var, ent, struct trace_mmiotrace_map,		\
@@ -571,6 +573,7 @@ void tracing_reset_current(int cpu);
 void tracing_reset_all_online_cpus(void);
 int tracing_open_generic(struct inode *inode, struct file *filp);
 bool tracing_is_disabled(void);
+int tracer_tracing_is_on(struct trace_array *tr);
 struct dentry *trace_create_file(const char *name,
 				 umode_t mode,
 				 struct dentry *parent,

kernel/trace/trace_entries.h

@@ -322,3 +322,26 @@ FTRACE_ENTRY(branch, trace_branch,
 	FILTER_OTHER
 );
 
+
+FTRACE_ENTRY(hwlat, hwlat_entry,
+
+	TRACE_HWLAT,
+
+	F_STRUCT(
+		__field(	u64,			duration	)
+		__field(	u64,			outer_duration	)
+		__field_struct( struct timespec,	timestamp	)
+		__field_desc(	long,	timestamp,	tv_sec		)
+		__field_desc(	long,	timestamp,	tv_nsec		)
+		__field(	unsigned int,		seqnum		)
+	),
+
+	F_printk("cnt:%u\tts:%010lu.%010lu\tinner:%llu\touter:%llu\n",
+		 __entry->seqnum,
+		 __entry->tv_sec,
+		 __entry->tv_nsec,
+		 __entry->duration,
+		 __entry->outer_duration),
+
+	FILTER_OTHER
+);