Merge branch 'tip/perf/core' of...

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

Pull tracing updated from Steve Rostedt.
Signed-off-by: Ingo Molnar <mingo@kernel.org>

Documentation/trace/ftrace.txt

@@ -1842,6 +1842,89 @@ an error.
  # cat buffer_size_kb
 85
 
+Snapshot
+--------
+CONFIG_TRACER_SNAPSHOT makes a generic snapshot feature
+available to all non latency tracers. (Latency tracers which
+record max latency, such as "irqsoff" or "wakeup", can't use
+this feature, since those are already using the snapshot
+mechanism internally.)
+
+Snapshot preserves a current trace buffer at a particular point
+in time without stopping tracing. Ftrace swaps the current
+buffer with a spare buffer, and tracing continues in the new
+current (=previous spare) buffer.
+
+The following debugfs files in "tracing" are related to this
+feature:
+
+  snapshot:
+
+	This is used to take a snapshot and to read the output
+	of the snapshot. Echo 1 into this file to allocate a
+	spare buffer and to take a snapshot (swap), then read
+	the snapshot from this file in the same format as
+	"trace" (described above in the section "The File
+	System"). Both reads snapshot and tracing are executable
+	in parallel. When the spare buffer is allocated, echoing
+	0 frees it, and echoing else (positive) values clear the
+	snapshot contents.
+	More details are shown in the table below.
+
+	status\input  |     0      |     1      |    else    |
+	--------------+------------+------------+------------+
+	not allocated |(do nothing)| alloc+swap |   EINVAL   |
+	--------------+------------+------------+------------+
+	allocated     |    free    |    swap    |   clear    |
+	--------------+------------+------------+------------+
+
+Here is an example of using the snapshot feature.
+
+ # echo 1 > events/sched/enable
+ # echo 1 > snapshot
+ # cat snapshot
+# tracer: nop
+#
+# entries-in-buffer/entries-written: 71/71   #P:8
+#
+#                              _-----=> irqs-off
+#                             / _----=> need-resched
+#                            | / _---=> hardirq/softirq
+#                            || / _--=> preempt-depth
+#                            ||| /     delay
+#           TASK-PID   CPU#  ||||    TIMESTAMP  FUNCTION
+#              | |       |   ||||       |         |
+          <idle>-0     [005] d...  2440.603828: sched_switch: prev_comm=swapper/5 prev_pid=0 prev_prio=120 prev_state=R ==> next_comm=snapshot-test-2 next_pid=2242 next_prio=120
+           sleep-2242  [005] d...  2440.603846: sched_switch: prev_comm=snapshot-test-2 prev_pid=2242 prev_prio=120 prev_state=R ==> next_comm=kworker/5:1 next_pid=60 next_prio=120
+[...]
+          <idle>-0     [002] d...  2440.707230: sched_switch: prev_comm=swapper/2 prev_pid=0 prev_prio=120 prev_state=R ==> next_comm=snapshot-test-2 next_pid=2229 next_prio=120
+
+ # cat trace
+# tracer: nop
+#
+# entries-in-buffer/entries-written: 77/77   #P:8
+#
+#                              _-----=> irqs-off
+#                             / _----=> need-resched
+#                            | / _---=> hardirq/softirq
+#                            || / _--=> preempt-depth
+#                            ||| /     delay
+#           TASK-PID   CPU#  ||||    TIMESTAMP  FUNCTION
+#              | |       |   ||||       |         |
+          <idle>-0     [007] d...  2440.707395: sched_switch: prev_comm=swapper/7 prev_pid=0 prev_prio=120 prev_state=R ==> next_comm=snapshot-test-2 next_pid=2243 next_prio=120
+ snapshot-test-2-2229  [002] d...  2440.707438: sched_switch: prev_comm=snapshot-test-2 prev_pid=2229 prev_prio=120 prev_state=S ==> next_comm=swapper/2 next_pid=0 next_prio=120
+[...]
+
+
+If you try to use this snapshot feature when current tracer is
+one of the latency tracers, you will get the following results.
+
+ # echo wakeup > current_tracer
+ # echo 1 > snapshot
+bash: echo: write error: Device or resource busy
+ # cat snapshot
+cat: snapshot: Device or resource busy
+
 -----------
 
 More details can be found in the source code, in the

include/linux/ftrace_event.h

@@ -83,6 +83,9 @@ struct trace_iterator {
 	long			idx;
 
 	cpumask_var_t		started;
+
+	/* it's true when current open file is snapshot */
+	bool			snapshot;
 };
 
 enum trace_iter_flags {

include/linux/ring_buffer.h

@@ -167,6 +167,7 @@ unsigned long ring_buffer_entries_cpu(struct ring_buffer *buffer, int cpu);
 unsigned long ring_buffer_overrun_cpu(struct ring_buffer *buffer, int cpu);
 unsigned long ring_buffer_commit_overrun_cpu(struct ring_buffer *buffer, int cpu);
 unsigned long ring_buffer_dropped_events_cpu(struct ring_buffer *buffer, int cpu);
+unsigned long ring_buffer_read_events_cpu(struct ring_buffer *buffer, int cpu);
 
 u64 ring_buffer_time_stamp(struct ring_buffer *buffer, int cpu);
 void ring_buffer_normalize_time_stamp(struct ring_buffer *buffer,

kernel/trace/Kconfig

@@ -253,6 +253,16 @@ config FTRACE_SYSCALLS
 	help
 	  Basic tracer to catch the syscall entry and exit events.
 
+config TRACER_SNAPSHOT
+	bool "Create a snapshot trace buffer"
+	select TRACER_MAX_TRACE
+	help
+	  Allow tracing users to take snapshot of the current buffer using the
+	  ftrace interface, e.g.:
+
+	      echo 1 > /sys/kernel/debug/tracing/snapshot
+	      cat snapshot
+
 config TRACE_BRANCH_PROFILING
 	bool
 	select GENERIC_TRACER

kernel/trace/ring_buffer.c

@@ -3102,6 +3102,24 @@ ring_buffer_dropped_events_cpu(struct ring_buffer *buffer, int cpu)
 }
 EXPORT_SYMBOL_GPL(ring_buffer_dropped_events_cpu);
 
+/**
+ * ring_buffer_read_events_cpu - get the number of events successfully read
+ * @buffer: The ring buffer
+ * @cpu: The per CPU buffer to get the number of events read
+ */
+unsigned long
+ring_buffer_read_events_cpu(struct ring_buffer *buffer, int cpu)
+{
+	struct ring_buffer_per_cpu *cpu_buffer;
+
+	if (!cpumask_test_cpu(cpu, buffer->cpumask))
+		return 0;
+
+	cpu_buffer = buffer->buffers[cpu];
+	return cpu_buffer->read;
+}
+EXPORT_SYMBOL_GPL(ring_buffer_read_events_cpu);
+
 /**
  * ring_buffer_entries - get the number of entries in a buffer
  * @buffer: The ring buffer

kernel/trace/trace.h

@@ -287,6 +287,7 @@ struct tracer {
 	struct tracer_flags	*flags;
 	bool			print_max;
 	bool			use_max_tr;
+	bool			allocated_snapshot;
 };
 
 

kernel/trace/trace_clock.c

@@ -84,7 +84,7 @@ u64 notrace trace_clock_global(void)
 	local_irq_save(flags);
 
 	this_cpu = raw_smp_processor_id();
-	now = cpu_clock(this_cpu);
+	now = sched_clock_cpu(this_cpu);
 	/*
 	 * If in an NMI context then dont risk lockups and return the
 	 * cpu_clock() time:

kernel/trace/trace_functions_graph.c

@@ -191,10 +191,16 @@ unsigned long ftrace_return_to_handler(unsigned long frame_pointer)
 
 	ftrace_pop_return_trace(&trace, &ret, frame_pointer);
 	trace.rettime = trace_clock_local();
-	ftrace_graph_return(&trace);
 	barrier();
 	current->curr_ret_stack--;
 
+	/*
+	 * The trace should run after decrementing the ret counter
+	 * in case an interrupt were to come in. We don't want to
+	 * lose the interrupt if max_depth is set.
+	 */
+	ftrace_graph_return(&trace);
+
 	if (unlikely(!ret)) {
 		ftrace_graph_stop();
 		WARN_ON(1);

samples/Kconfig

@@ -5,12 +5,6 @@ menuconfig SAMPLES
 
 if SAMPLES
 
-config SAMPLE_TRACEPOINTS
-	tristate "Build tracepoints examples -- loadable modules only"
-	depends on TRACEPOINTS && m
-	help
-	  This build tracepoints example modules.
-
 config SAMPLE_TRACE_EVENTS
 	tristate "Build trace_events examples -- loadable modules only"
 	depends on EVENT_TRACING && m

samples/Makefile

 # Makefile for Linux samples code
 
-obj-$(CONFIG_SAMPLES)	+= kobject/ kprobes/ tracepoints/ trace_events/ \
+obj-$(CONFIG_SAMPLES)	+= kobject/ kprobes/ trace_events/ \
 			   hw_breakpoint/ kfifo/ kdb/ hidraw/ rpmsg/ seccomp/

samples/tracepoints/Makefile

-# builds the tracepoint example kernel modules;
-# then to use one (as root):  insmod <module_name.ko>
-
-obj-$(CONFIG_SAMPLE_TRACEPOINTS) += tracepoint-sample.o
-obj-$(CONFIG_SAMPLE_TRACEPOINTS) += tracepoint-probe-sample.o
-obj-$(CONFIG_SAMPLE_TRACEPOINTS) += tracepoint-probe-sample2.o

samples/tracepoints/tp-samples-trace.h

-#ifndef _TP_SAMPLES_TRACE_H
-#define _TP_SAMPLES_TRACE_H
-
-#include <linux/proc_fs.h>	/* for struct inode and struct file */
-#include <linux/tracepoint.h>
-
-DECLARE_TRACE(subsys_event,
-	TP_PROTO(struct inode *inode, struct file *file),
-	TP_ARGS(inode, file));
-DECLARE_TRACE_NOARGS(subsys_eventb);
-#endif

samples/tracepoints/tracepoint-probe-sample.c

-/*
- * tracepoint-probe-sample.c
- *
- * sample tracepoint probes.
- */
-
-#include <linux/module.h>
-#include <linux/file.h>
-#include <linux/dcache.h>
-#include "tp-samples-trace.h"
-
-/*
- * Here the caller only guarantees locking for struct file and struct inode.
- * Locking must therefore be done in the probe to use the dentry.
- */
-static void probe_subsys_event(void *ignore,
-			       struct inode *inode, struct file *file)
-{
-	path_get(&file->f_path);
-	dget(file->f_path.dentry);
-	printk(KERN_INFO "Event is encountered with filename %s\n",
-		file->f_path.dentry->d_name.name);
-	dput(file->f_path.dentry);
-	path_put(&file->f_path);
-}
-
-static void probe_subsys_eventb(void *ignore)
-{
-	printk(KERN_INFO "Event B is encountered\n");
-}
-
-static int __init tp_sample_trace_init(void)
-{
-	int ret;
-
-	ret = register_trace_subsys_event(probe_subsys_event, NULL);
-	WARN_ON(ret);
-	ret = register_trace_subsys_eventb(probe_subsys_eventb, NULL);
-	WARN_ON(ret);
-
-	return 0;
-}
-
-module_init(tp_sample_trace_init);
-
-static void __exit tp_sample_trace_exit(void)
-{
-	unregister_trace_subsys_eventb(probe_subsys_eventb, NULL);
-	unregister_trace_subsys_event(probe_subsys_event, NULL);
-	tracepoint_synchronize_unregister();
-}
-
-module_exit(tp_sample_trace_exit);
-
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Mathieu Desnoyers");
-MODULE_DESCRIPTION("Tracepoint Probes Samples");

samples/tracepoints/tracepoint-probe-sample2.c

-/*
- * tracepoint-probe-sample2.c
- *
- * 2nd sample tracepoint probes.
- */
-
-#include <linux/module.h>
-#include <linux/fs.h>
-#include "tp-samples-trace.h"
-
-/*
- * Here the caller only guarantees locking for struct file and struct inode.
- * Locking must therefore be done in the probe to use the dentry.
- */
-static void probe_subsys_event(void *ignore,
-			       struct inode *inode, struct file *file)
-{
-	printk(KERN_INFO "Event is encountered with inode number %lu\n",
-		inode->i_ino);
-}
-
-static int __init tp_sample_trace_init(void)
-{
-	int ret;
-
-	ret = register_trace_subsys_event(probe_subsys_event, NULL);
-	WARN_ON(ret);
-
-	return 0;
-}
-
-module_init(tp_sample_trace_init);
-
-static void __exit tp_sample_trace_exit(void)
-{
-	unregister_trace_subsys_event(probe_subsys_event, NULL);
-	tracepoint_synchronize_unregister();
-}
-
-module_exit(tp_sample_trace_exit);
-
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Mathieu Desnoyers");
-MODULE_DESCRIPTION("Tracepoint Probes Samples");

samples/tracepoints/tracepoint-sample.c

-/* tracepoint-sample.c
- *
- * Executes a tracepoint when /proc/tracepoint-sample is opened.
- *
- * (C) Copyright 2007 Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>
- *
- * This file is released under the GPLv2.
- * See the file COPYING for more details.
- */
-
-#include <linux/module.h>
-#include <linux/sched.h>
-#include <linux/proc_fs.h>
-#include "tp-samples-trace.h"
-
-DEFINE_TRACE(subsys_event);
-DEFINE_TRACE(subsys_eventb);
-
-struct proc_dir_entry *pentry_sample;
-
-static int my_open(struct inode *inode, struct file *file)
-{
-	int i;
-
-	trace_subsys_event(inode, file);
-	for (i = 0; i < 10; i++)
-		trace_subsys_eventb();
-	return -EPERM;
-}
-
-static const struct file_operations mark_ops = {
-	.open = my_open,
-	.llseek = noop_llseek,
-};
-
-static int __init sample_init(void)
-{
-	printk(KERN_ALERT "sample init\n");
-	pentry_sample = proc_create("tracepoint-sample", 0444, NULL,
-		&mark_ops);
-	if (!pentry_sample)
-		return -EPERM;
-	return 0;
-}
-
-static void __exit sample_exit(void)
-{
-	printk(KERN_ALERT "sample exit\n");
-	remove_proc_entry("tracepoint-sample", NULL);
-}
-
-module_init(sample_init)
-module_exit(sample_exit)
-
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Mathieu Desnoyers");
-MODULE_DESCRIPTION("Tracepoint sample");