From 4104d326b670c2b66f575d2004daa28b2d1b4c8d Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (Red Hat)" <rostedt@goodmis.org>
Date: Fri, 10 Jan 2014 17:01:58 -0500
Subject: ftrace: Remove global function list and call function directly

Instead of having a list of global functions that are called,
as only one global function is allow to be enabled at a time, there's
no reason to have a list.

Instead, simply have all the users of the global ops, use the global ops
directly, instead of registering their own ftrace_ops. Just switch what
function is used before enabling the function tracer.

This removes a lot of code as well as the complexity involved with it.

Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 kernel/trace/trace.c | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'kernel/trace/trace.c')

diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 737b0efa1a6..fdd33aacdf0 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -6629,6 +6629,8 @@ __init static int tracer_alloc_buffers(void)
 	 */
 	global_trace.current_trace = &nop_trace;
 
+	ftrace_init_global_array_ops(&global_trace);
+
 	register_tracer(&nop_trace);
 
 	/* All seems OK, enable tracing */
-- 
cgit v1.2.3-70-g09d2


From 6d9b3fa5e7f663bbfb9d2d80d46136f75319cb28 Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (Red Hat)" <rostedt@goodmis.org>
Date: Tue, 14 Jan 2014 11:28:38 -0500
Subject: tracing: Move tracing_max_latency into trace_array

In preparation for letting the latency tracers be used by instances,
remove the global tracing_max_latency variable and add a max_latency
field to the trace_array that the latency tracers will now use.

Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 kernel/trace/trace.c              | 14 ++++++--------
 kernel/trace/trace.h              |  3 +--
 kernel/trace/trace_irqsoff.c      | 14 +++++++-------
 kernel/trace/trace_sched_wakeup.c | 12 ++++++------
 kernel/trace/trace_selftest.c     | 26 +++++++++++++-------------
 5 files changed, 33 insertions(+), 36 deletions(-)

(limited to 'kernel/trace/trace.c')

diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index fdd33aacdf0..f5fc56bf022 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -982,8 +982,6 @@ static arch_spinlock_t ftrace_max_lock =
 unsigned long __read_mostly	tracing_thresh;
 
 #ifdef CONFIG_TRACER_MAX_TRACE
-unsigned long __read_mostly	tracing_max_latency;
-
 /*
  * Copy the new maximum trace into the separate maximum-trace
  * structure. (this way the maximum trace is permanently saved,
@@ -1000,7 +998,7 @@ __update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu)
 	max_buf->cpu = cpu;
 	max_buf->time_start = data->preempt_timestamp;
 
-	max_data->saved_latency = tracing_max_latency;
+	max_data->saved_latency = tr->max_latency;
 	max_data->critical_start = data->critical_start;
 	max_data->critical_end = data->critical_end;
 
@@ -6328,6 +6326,11 @@ init_tracer_debugfs(struct trace_array *tr, struct dentry *d_tracer)
 	trace_create_file("tracing_on", 0644, d_tracer,
 			  tr, &rb_simple_fops);
 
+#ifdef CONFIG_TRACER_MAX_TRACE
+	trace_create_file("tracing_max_latency", 0644, d_tracer,
+			&tr->max_latency, &tracing_max_lat_fops);
+#endif
+
 	if (ftrace_create_function_files(tr, d_tracer))
 		WARN(1, "Could not allocate function filter files");
 
@@ -6353,11 +6356,6 @@ static __init int tracer_init_debugfs(void)
 
 	init_tracer_debugfs(&global_trace, d_tracer);
 
-#ifdef CONFIG_TRACER_MAX_TRACE
-	trace_create_file("tracing_max_latency", 0644, d_tracer,
-			&tracing_max_latency, &tracing_max_lat_fops);
-#endif
-
 	trace_create_file("tracing_thresh", 0644, d_tracer,
 			&tracing_thresh, &tracing_max_lat_fops);
 
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index df5256be64c..644a8b533e1 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -190,6 +190,7 @@ struct trace_array {
 	 */
 	struct trace_buffer	max_buffer;
 	bool			allocated_snapshot;
+	unsigned long		max_latency;
 #endif
 	int			buffer_disabled;
 #ifdef CONFIG_FTRACE_SYSCALLS
@@ -599,8 +600,6 @@ extern unsigned long nsecs_to_usecs(unsigned long nsecs);
 extern unsigned long tracing_thresh;
 
 #ifdef CONFIG_TRACER_MAX_TRACE
-extern unsigned long tracing_max_latency;
-
 void update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu);
 void update_max_tr_single(struct trace_array *tr,
 			  struct task_struct *tsk, int cpu);
diff --git a/kernel/trace/trace_irqsoff.c b/kernel/trace/trace_irqsoff.c
index b5cb047df3e..40aa300d349 100644
--- a/kernel/trace/trace_irqsoff.c
+++ b/kernel/trace/trace_irqsoff.c
@@ -170,7 +170,7 @@ irqsoff_set_flag(struct trace_array *tr, u32 old_flags, u32 bit, int set)
 	for_each_possible_cpu(cpu)
 		per_cpu(tracing_cpu, cpu) = 0;
 
-	tracing_max_latency = 0;
+	tr->max_latency = 0;
 	tracing_reset_online_cpus(&irqsoff_trace->trace_buffer);
 
 	return start_irqsoff_tracer(irqsoff_trace, set);
@@ -297,13 +297,13 @@ static void irqsoff_print_header(struct seq_file *s)
 /*
  * Should this new latency be reported/recorded?
  */
-static int report_latency(cycle_t delta)
+static int report_latency(struct trace_array *tr, cycle_t delta)
 {
 	if (tracing_thresh) {
 		if (delta < tracing_thresh)
 			return 0;
 	} else {
-		if (delta <= tracing_max_latency)
+		if (delta <= tr->max_latency)
 			return 0;
 	}
 	return 1;
@@ -327,13 +327,13 @@ check_critical_timing(struct trace_array *tr,
 
 	pc = preempt_count();
 
-	if (!report_latency(delta))
+	if (!report_latency(tr, delta))
 		goto out;
 
 	raw_spin_lock_irqsave(&max_trace_lock, flags);
 
 	/* check if we are still the max latency */
-	if (!report_latency(delta))
+	if (!report_latency(tr, delta))
 		goto out_unlock;
 
 	__trace_function(tr, CALLER_ADDR0, parent_ip, flags, pc);
@@ -346,7 +346,7 @@ check_critical_timing(struct trace_array *tr,
 	data->critical_end = parent_ip;
 
 	if (likely(!is_tracing_stopped())) {
-		tracing_max_latency = delta;
+		tr->max_latency = delta;
 		update_max_tr_single(tr, current, cpu);
 	}
 
@@ -605,7 +605,7 @@ static void __irqsoff_tracer_init(struct trace_array *tr)
 	set_tracer_flag(tr, TRACE_ITER_OVERWRITE, 1);
 	set_tracer_flag(tr, TRACE_ITER_LATENCY_FMT, 1);
 
-	tracing_max_latency = 0;
+	tr->max_latency = 0;
 	irqsoff_trace = tr;
 	/* make sure that the tracer is visible */
 	smp_wmb();
diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c
index 4dd986defa6..41e0b8aa78e 100644
--- a/kernel/trace/trace_sched_wakeup.c
+++ b/kernel/trace/trace_sched_wakeup.c
@@ -218,7 +218,7 @@ wakeup_set_flag(struct trace_array *tr, u32 old_flags, u32 bit, int set)
 	stop_func_tracer(tr, !set);
 
 	wakeup_reset(wakeup_trace);
-	tracing_max_latency = 0;
+	tr->max_latency = 0;
 
 	return start_func_tracer(tr, set);
 }
@@ -344,13 +344,13 @@ static void wakeup_print_header(struct seq_file *s)
 /*
  * Should this new latency be reported/recorded?
  */
-static int report_latency(cycle_t delta)
+static int report_latency(struct trace_array *tr, cycle_t delta)
 {
 	if (tracing_thresh) {
 		if (delta < tracing_thresh)
 			return 0;
 	} else {
-		if (delta <= tracing_max_latency)
+		if (delta <= tr->max_latency)
 			return 0;
 	}
 	return 1;
@@ -418,11 +418,11 @@ probe_wakeup_sched_switch(void *ignore,
 	T1 = ftrace_now(cpu);
 	delta = T1-T0;
 
-	if (!report_latency(delta))
+	if (!report_latency(wakeup_trace, delta))
 		goto out_unlock;
 
 	if (likely(!is_tracing_stopped())) {
-		tracing_max_latency = delta;
+		wakeup_trace->max_latency = delta;
 		update_max_tr(wakeup_trace, wakeup_task, wakeup_cpu);
 	}
 
@@ -609,7 +609,7 @@ static int __wakeup_tracer_init(struct trace_array *tr)
 	set_tracer_flag(tr, TRACE_ITER_OVERWRITE, 1);
 	set_tracer_flag(tr, TRACE_ITER_LATENCY_FMT, 1);
 
-	tracing_max_latency = 0;
+	tr->max_latency = 0;
 	wakeup_trace = tr;
 	ftrace_init_array_ops(tr, wakeup_tracer_call);
 	start_wakeup_tracer(tr);
diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c
index 519d04affe3..ac318589296 100644
--- a/kernel/trace/trace_selftest.c
+++ b/kernel/trace/trace_selftest.c
@@ -807,7 +807,7 @@ out:
 int
 trace_selftest_startup_irqsoff(struct tracer *trace, struct trace_array *tr)
 {
-	unsigned long save_max = tracing_max_latency;
+	unsigned long save_max = tr->max_latency;
 	unsigned long count;
 	int ret;
 
@@ -819,7 +819,7 @@ trace_selftest_startup_irqsoff(struct tracer *trace, struct trace_array *tr)
 	}
 
 	/* reset the max latency */
-	tracing_max_latency = 0;
+	tr->max_latency = 0;
 	/* disable interrupts for a bit */
 	local_irq_disable();
 	udelay(100);
@@ -846,7 +846,7 @@ trace_selftest_startup_irqsoff(struct tracer *trace, struct trace_array *tr)
 		ret = -1;
 	}
 
-	tracing_max_latency = save_max;
+	tr->max_latency = save_max;
 
 	return ret;
 }
@@ -856,7 +856,7 @@ trace_selftest_startup_irqsoff(struct tracer *trace, struct trace_array *tr)
 int
 trace_selftest_startup_preemptoff(struct tracer *trace, struct trace_array *tr)
 {
-	unsigned long save_max = tracing_max_latency;
+	unsigned long save_max = tr->max_latency;
 	unsigned long count;
 	int ret;
 
@@ -881,7 +881,7 @@ trace_selftest_startup_preemptoff(struct tracer *trace, struct trace_array *tr)
 	}
 
 	/* reset the max latency */
-	tracing_max_latency = 0;
+	tr->max_latency = 0;
 	/* disable preemption for a bit */
 	preempt_disable();
 	udelay(100);
@@ -908,7 +908,7 @@ trace_selftest_startup_preemptoff(struct tracer *trace, struct trace_array *tr)
 		ret = -1;
 	}
 
-	tracing_max_latency = save_max;
+	tr->max_latency = save_max;
 
 	return ret;
 }
@@ -918,7 +918,7 @@ trace_selftest_startup_preemptoff(struct tracer *trace, struct trace_array *tr)
 int
 trace_selftest_startup_preemptirqsoff(struct tracer *trace, struct trace_array *tr)
 {
-	unsigned long save_max = tracing_max_latency;
+	unsigned long save_max = tr->max_latency;
 	unsigned long count;
 	int ret;
 
@@ -943,7 +943,7 @@ trace_selftest_startup_preemptirqsoff(struct tracer *trace, struct trace_array *
 	}
 
 	/* reset the max latency */
-	tracing_max_latency = 0;
+	tr->max_latency = 0;
 
 	/* disable preemption and interrupts for a bit */
 	preempt_disable();
@@ -978,7 +978,7 @@ trace_selftest_startup_preemptirqsoff(struct tracer *trace, struct trace_array *
 	}
 
 	/* do the test by disabling interrupts first this time */
-	tracing_max_latency = 0;
+	tr->max_latency = 0;
 	tracing_start();
 	trace->start(tr);
 
@@ -1009,7 +1009,7 @@ out:
 	tracing_start();
 out_no_start:
 	trace->reset(tr);
-	tracing_max_latency = save_max;
+	tr->max_latency = save_max;
 
 	return ret;
 }
@@ -1062,7 +1062,7 @@ static int trace_wakeup_test_thread(void *data)
 int
 trace_selftest_startup_wakeup(struct tracer *trace, struct trace_array *tr)
 {
-	unsigned long save_max = tracing_max_latency;
+	unsigned long save_max = tr->max_latency;
 	struct task_struct *p;
 	struct completion is_ready;
 	unsigned long count;
@@ -1088,7 +1088,7 @@ trace_selftest_startup_wakeup(struct tracer *trace, struct trace_array *tr)
 	}
 
 	/* reset the max latency */
-	tracing_max_latency = 0;
+	tr->max_latency = 0;
 
 	while (p->on_rq) {
 		/*
@@ -1118,7 +1118,7 @@ trace_selftest_startup_wakeup(struct tracer *trace, struct trace_array *tr)
 	trace->reset(tr);
 	tracing_start();
 
-	tracing_max_latency = save_max;
+	tr->max_latency = save_max;
 
 	/* kill the thread */
 	kthread_stop(p);
-- 
cgit v1.2.3-70-g09d2


From 0b9b12c1b884eb34773312f15c194220025e0416 Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (Red Hat)" <rostedt@goodmis.org>
Date: Tue, 14 Jan 2014 10:04:59 -0500
Subject: tracing: Move ftrace_max_lock into trace_array

In preparation for having tracers enabled in instances, the max_lock
should be unique as updating the max for one tracer is a separate
operation than updating it for another tracer using a different max.

Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 kernel/trace/trace.c          | 40 ++++++++++++++--------------------------
 kernel/trace/trace.h          | 14 ++++++++++++++
 kernel/trace/trace_selftest.c |  4 ++--
 3 files changed, 30 insertions(+), 28 deletions(-)

(limited to 'kernel/trace/trace.c')

diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index f5fc56bf022..bb5147a55be 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -963,22 +963,6 @@ static ssize_t trace_seq_to_buffer(struct trace_seq *s, void *buf, size_t cnt)
 	return cnt;
 }
 
-/*
- * ftrace_max_lock is used to protect the swapping of buffers
- * when taking a max snapshot. The buffers themselves are
- * protected by per_cpu spinlocks. But the action of the swap
- * needs its own lock.
- *
- * This is defined as a arch_spinlock_t in order to help
- * with performance when lockdep debugging is enabled.
- *
- * It is also used in other places outside the update_max_tr
- * so it needs to be defined outside of the
- * CONFIG_TRACER_MAX_TRACE.
- */
-static arch_spinlock_t ftrace_max_lock =
-	(arch_spinlock_t)__ARCH_SPIN_LOCK_UNLOCKED;
-
 unsigned long __read_mostly	tracing_thresh;
 
 #ifdef CONFIG_TRACER_MAX_TRACE
@@ -1046,14 +1030,14 @@ update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu)
 		return;
 	}
 
-	arch_spin_lock(&ftrace_max_lock);
+	arch_spin_lock(&tr->max_lock);
 
 	buf = tr->trace_buffer.buffer;
 	tr->trace_buffer.buffer = tr->max_buffer.buffer;
 	tr->max_buffer.buffer = buf;
 
 	__update_max_tr(tr, tsk, cpu);
-	arch_spin_unlock(&ftrace_max_lock);
+	arch_spin_unlock(&tr->max_lock);
 }
 
 /**
@@ -1079,7 +1063,7 @@ update_max_tr_single(struct trace_array *tr, struct task_struct *tsk, int cpu)
 		return;
 	}
 
-	arch_spin_lock(&ftrace_max_lock);
+	arch_spin_lock(&tr->max_lock);
 
 	ret = ring_buffer_swap_cpu(tr->max_buffer.buffer, tr->trace_buffer.buffer, cpu);
 
@@ -1097,7 +1081,7 @@ update_max_tr_single(struct trace_array *tr, struct task_struct *tsk, int cpu)
 	WARN_ON_ONCE(ret && ret != -EAGAIN && ret != -EBUSY);
 
 	__update_max_tr(tr, tsk, cpu);
-	arch_spin_unlock(&ftrace_max_lock);
+	arch_spin_unlock(&tr->max_lock);
 }
 #endif /* CONFIG_TRACER_MAX_TRACE */
 
@@ -1351,7 +1335,7 @@ void tracing_start(void)
 	}
 
 	/* Prevent the buffers from switching */
-	arch_spin_lock(&ftrace_max_lock);
+	arch_spin_lock(&global_trace.max_lock);
 
 	buffer = global_trace.trace_buffer.buffer;
 	if (buffer)
@@ -1363,7 +1347,7 @@ void tracing_start(void)
 		ring_buffer_record_enable(buffer);
 #endif
 
-	arch_spin_unlock(&ftrace_max_lock);
+	arch_spin_unlock(&global_trace.max_lock);
 
 	ftrace_start();
  out:
@@ -1418,7 +1402,7 @@ void tracing_stop(void)
 		goto out;
 
 	/* Prevent the buffers from switching */
-	arch_spin_lock(&ftrace_max_lock);
+	arch_spin_lock(&global_trace.max_lock);
 
 	buffer = global_trace.trace_buffer.buffer;
 	if (buffer)
@@ -1430,7 +1414,7 @@ void tracing_stop(void)
 		ring_buffer_record_disable(buffer);
 #endif
 
-	arch_spin_unlock(&ftrace_max_lock);
+	arch_spin_unlock(&global_trace.max_lock);
 
  out:
 	raw_spin_unlock_irqrestore(&global_trace.start_lock, flags);
@@ -3331,7 +3315,7 @@ tracing_cpumask_write(struct file *filp, const char __user *ubuf,
 	mutex_lock(&tracing_cpumask_update_lock);
 
 	local_irq_disable();
-	arch_spin_lock(&ftrace_max_lock);
+	arch_spin_lock(&tr->max_lock);
 	for_each_tracing_cpu(cpu) {
 		/*
 		 * Increase/decrease the disabled counter if we are
@@ -3348,7 +3332,7 @@ tracing_cpumask_write(struct file *filp, const char __user *ubuf,
 			ring_buffer_record_enable_cpu(tr->trace_buffer.buffer, cpu);
 		}
 	}
-	arch_spin_unlock(&ftrace_max_lock);
+	arch_spin_unlock(&tr->max_lock);
 	local_irq_enable();
 
 	cpumask_copy(tr->tracing_cpumask, tracing_cpumask_new);
@@ -6129,6 +6113,8 @@ static int new_instance_create(const char *name)
 
 	raw_spin_lock_init(&tr->start_lock);
 
+	tr->max_lock = (arch_spinlock_t)__ARCH_SPIN_LOCK_UNLOCKED;
+
 	tr->current_trace = &nop_trace;
 
 	INIT_LIST_HEAD(&tr->systems);
@@ -6627,6 +6613,8 @@ __init static int tracer_alloc_buffers(void)
 	 */
 	global_trace.current_trace = &nop_trace;
 
+	global_trace.max_lock = (arch_spinlock_t)__ARCH_SPIN_LOCK_UNLOCKED;
+
 	ftrace_init_global_array_ops(&global_trace);
 
 	register_tracer(&nop_trace);
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 644a8b533e1..5d2f07d6746 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -192,6 +192,20 @@ struct trace_array {
 	bool			allocated_snapshot;
 	unsigned long		max_latency;
 #endif
+	/*
+	 * max_lock is used to protect the swapping of buffers
+	 * when taking a max snapshot. The buffers themselves are
+	 * protected by per_cpu spinlocks. But the action of the swap
+	 * needs its own lock.
+	 *
+	 * This is defined as a arch_spinlock_t in order to help
+	 * with performance when lockdep debugging is enabled.
+	 *
+	 * It is also used in other places outside the update_max_tr
+	 * so it needs to be defined outside of the
+	 * CONFIG_TRACER_MAX_TRACE.
+	 */
+	arch_spinlock_t		max_lock;
 	int			buffer_disabled;
 #ifdef CONFIG_FTRACE_SYSCALLS
 	int			sys_refcount_enter;
diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c
index ac318589296..1c95cd7a98c 100644
--- a/kernel/trace/trace_selftest.c
+++ b/kernel/trace/trace_selftest.c
@@ -65,7 +65,7 @@ static int trace_test_buffer(struct trace_buffer *buf, unsigned long *count)
 
 	/* Don't allow flipping of max traces now */
 	local_irq_save(flags);
-	arch_spin_lock(&ftrace_max_lock);
+	arch_spin_lock(&buf->tr->max_lock);
 
 	cnt = ring_buffer_entries(buf->buffer);
 
@@ -83,7 +83,7 @@ static int trace_test_buffer(struct trace_buffer *buf, unsigned long *count)
 			break;
 	}
 	tracing_on();
-	arch_spin_unlock(&ftrace_max_lock);
+	arch_spin_unlock(&buf->tr->max_lock);
 	local_irq_restore(flags);
 
 	if (count)
-- 
cgit v1.2.3-70-g09d2


From ad1438a076e275b70d1a04de1364bc483e5a81db Mon Sep 17 00:00:00 2001
From: Fabian Frederick <fabf@skynet.be>
Date: Thu, 17 Apr 2014 21:44:42 +0200
Subject: tracing: Add static to local functions

This patch adds static to the following functions:
-cycle_t buffer_ftrace_now
-void free_snapshot
-int trace_selftest_startup_dynamic_tracing

Link: http://lkml.kernel.org/p/20140417214442.d7abc7c0b0e4b90e7fedecc9@skynet.be

Signed-off-by: Fabian Frederick <fabf@skynet.be>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 kernel/trace/trace.c          | 4 ++--
 kernel/trace/trace_selftest.c | 6 +++---
 2 files changed, 5 insertions(+), 5 deletions(-)

(limited to 'kernel/trace/trace.c')

diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index bb5147a55be..cb41e98cc64 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -275,7 +275,7 @@ int call_filter_check_discard(struct ftrace_event_call *call, void *rec,
 }
 EXPORT_SYMBOL_GPL(call_filter_check_discard);
 
-cycle_t buffer_ftrace_now(struct trace_buffer *buf, int cpu)
+static cycle_t buffer_ftrace_now(struct trace_buffer *buf, int cpu)
 {
 	u64 ts;
 
@@ -599,7 +599,7 @@ static int alloc_snapshot(struct trace_array *tr)
 	return 0;
 }
 
-void free_snapshot(struct trace_array *tr)
+static void free_snapshot(struct trace_array *tr)
 {
 	/*
 	 * We don't free the ring buffer. instead, resize it because
diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c
index 1c95cd7a98c..5ef60499dc8 100644
--- a/kernel/trace/trace_selftest.c
+++ b/kernel/trace/trace_selftest.c
@@ -320,9 +320,9 @@ static int trace_selftest_ops(struct trace_array *tr, int cnt)
 }
 
 /* Test dynamic code modification and ftrace filters */
-int trace_selftest_startup_dynamic_tracing(struct tracer *trace,
-					   struct trace_array *tr,
-					   int (*func)(void))
+static int trace_selftest_startup_dynamic_tracing(struct tracer *trace,
+						  struct trace_array *tr,
+						  int (*func)(void))
 {
 	int save_ftrace_enabled = ftrace_enabled;
 	unsigned long count;
-- 
cgit v1.2.3-70-g09d2


From f4874261049e3abdd481359d82cafa5068369ebd Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (Red Hat)" <rostedt@goodmis.org>
Date: Tue, 29 Apr 2014 16:07:28 -0400
Subject: tracing: Break out of tracing_wait_pipe() before wait_pipe() is
 called

When reading from trace_pipe, if tracing is off but nothing was read
it should block. If something is read and tracing is off, then EOF
is returned. If tracing is on and there's nothing to read, it will block.

But because the check of whether tracing is off and something was read
is done after the block on the pipe, it is hit or miss if the EOF is
returned or not leading to inconsistent behavior.

Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 kernel/trace/trace.c | 18 +++++++++---------
 1 file changed, 9 insertions(+), 9 deletions(-)

(limited to 'kernel/trace/trace.c')

diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index cb41e98cc64..e058c6091e4 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -4237,15 +4237,6 @@ static int tracing_wait_pipe(struct file *filp)
 			return -EAGAIN;
 		}
 
-		mutex_unlock(&iter->mutex);
-
-		iter->trace->wait_pipe(iter);
-
-		mutex_lock(&iter->mutex);
-
-		if (signal_pending(current))
-			return -EINTR;
-
 		/*
 		 * We block until we read something and tracing is disabled.
 		 * We still block if tracing is disabled, but we have never
@@ -4257,6 +4248,15 @@ static int tracing_wait_pipe(struct file *filp)
 		 */
 		if (!tracing_is_on() && iter->pos)
 			break;
+
+		mutex_unlock(&iter->mutex);
+
+		iter->trace->wait_pipe(iter);
+
+		mutex_lock(&iter->mutex);
+
+		if (signal_pending(current))
+			return -EINTR;
 	}
 
 	return 1;
-- 
cgit v1.2.3-70-g09d2


From b1169cc69ba96b124df820904a6d3eb775491d7f Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (Red Hat)" <rostedt@goodmis.org>
Date: Tue, 29 Apr 2014 17:54:37 -0400
Subject: tracing: Remove mock up poll wait function

Now that the ring buffer has a built in way to wake up readers
when there's data, using irq_work such that it is safe to do it
in any context. But it was still using the old "poor man's"
wait polling that checks every 1/10 of a second to see if it
should wake up a waiter. This makes the latency for a wake up
excruciatingly long. No need to do that anymore.

Completely remove the different wait_poll types from the tracers
and have them all use the default one now.

Reported-by: Johannes Berg <johannes@sipsolutions.net>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 kernel/trace/trace.c                 | 29 ++++-------------------------
 kernel/trace/trace.h                 |  4 ----
 kernel/trace/trace_functions.c       |  1 -
 kernel/trace/trace_functions_graph.c |  1 -
 kernel/trace/trace_nop.c             |  1 -
 kernel/trace/trace_sched_wakeup.c    |  2 --
 6 files changed, 4 insertions(+), 34 deletions(-)

(limited to 'kernel/trace/trace.c')

diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index e058c6091e4..4c392c8238b 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -1085,7 +1085,7 @@ update_max_tr_single(struct trace_array *tr, struct task_struct *tsk, int cpu)
 }
 #endif /* CONFIG_TRACER_MAX_TRACE */
 
-static void default_wait_pipe(struct trace_iterator *iter)
+static void wait_on_pipe(struct trace_iterator *iter)
 {
 	/* Iterators are static, they should be filled or empty */
 	if (trace_buffer_iter(iter, iter->cpu_file))
@@ -1202,8 +1202,6 @@ int register_tracer(struct tracer *type)
 	else
 		if (!type->flags->opts)
 			type->flags->opts = dummy_tracer_opt;
-	if (!type->wait_pipe)
-		type->wait_pipe = default_wait_pipe;
 
 	ret = run_tracer_selftest(type);
 	if (ret < 0)
@@ -4207,25 +4205,6 @@ tracing_poll_pipe(struct file *filp, poll_table *poll_table)
 	return trace_poll(iter, filp, poll_table);
 }
 
-/*
- * This is a make-shift waitqueue.
- * A tracer might use this callback on some rare cases:
- *
- *  1) the current tracer might hold the runqueue lock when it wakes up
- *     a reader, hence a deadlock (sched, function, and function graph tracers)
- *  2) the function tracers, trace all functions, we don't want
- *     the overhead of calling wake_up and friends
- *     (and tracing them too)
- *
- *     Anyway, this is really very primitive wakeup.
- */
-void poll_wait_pipe(struct trace_iterator *iter)
-{
-	set_current_state(TASK_INTERRUPTIBLE);
-	/* sleep for 100 msecs, and try again. */
-	schedule_timeout(HZ / 10);
-}
-
 /* Must be called with trace_types_lock mutex held. */
 static int tracing_wait_pipe(struct file *filp)
 {
@@ -4251,7 +4230,7 @@ static int tracing_wait_pipe(struct file *filp)
 
 		mutex_unlock(&iter->mutex);
 
-		iter->trace->wait_pipe(iter);
+		wait_on_pipe(iter);
 
 		mutex_lock(&iter->mutex);
 
@@ -5179,7 +5158,7 @@ tracing_buffers_read(struct file *filp, char __user *ubuf,
 				goto out_unlock;
 			}
 			mutex_unlock(&trace_types_lock);
-			iter->trace->wait_pipe(iter);
+			wait_on_pipe(iter);
 			mutex_lock(&trace_types_lock);
 			if (signal_pending(current)) {
 				size = -EINTR;
@@ -5390,7 +5369,7 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
 			goto out;
 		}
 		mutex_unlock(&trace_types_lock);
-		iter->trace->wait_pipe(iter);
+		wait_on_pipe(iter);
 		mutex_lock(&trace_types_lock);
 		if (signal_pending(current)) {
 			ret = -EINTR;
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 8624b504146..3b3e09e61f3 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -338,7 +338,6 @@ struct tracer_flags {
  * @stop: called when tracing is paused (echo 0 > tracing_enabled)
  * @open: called when the trace file is opened
  * @pipe_open: called when the trace_pipe file is opened
- * @wait_pipe: override how the user waits for traces on trace_pipe
  * @close: called when the trace file is released
  * @pipe_close: called when the trace_pipe file is released
  * @read: override the default read callback on trace_pipe
@@ -357,7 +356,6 @@ struct tracer {
 	void			(*stop)(struct trace_array *tr);
 	void			(*open)(struct trace_iterator *iter);
 	void			(*pipe_open)(struct trace_iterator *iter);
-	void			(*wait_pipe)(struct trace_iterator *iter);
 	void			(*close)(struct trace_iterator *iter);
 	void			(*pipe_close)(struct trace_iterator *iter);
 	ssize_t			(*read)(struct trace_iterator *iter,
@@ -566,8 +564,6 @@ void trace_init_global_iter(struct trace_iterator *iter);
 
 void tracing_iter_reset(struct trace_iterator *iter, int cpu);
 
-void poll_wait_pipe(struct trace_iterator *iter);
-
 void tracing_sched_switch_trace(struct trace_array *tr,
 				struct task_struct *prev,
 				struct task_struct *next,
diff --git a/kernel/trace/trace_functions.c b/kernel/trace/trace_functions.c
index 2d9482b8f26..57f0ec962d2 100644
--- a/kernel/trace/trace_functions.c
+++ b/kernel/trace/trace_functions.c
@@ -252,7 +252,6 @@ static struct tracer function_trace __tracer_data =
 	.init		= function_trace_init,
 	.reset		= function_trace_reset,
 	.start		= function_trace_start,
-	.wait_pipe	= poll_wait_pipe,
 	.flags		= &func_flags,
 	.set_flag	= func_set_flag,
 	.allow_instances = true,
diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c
index deff1120026..b86dd4d8c6a 100644
--- a/kernel/trace/trace_functions_graph.c
+++ b/kernel/trace/trace_functions_graph.c
@@ -1505,7 +1505,6 @@ static struct tracer graph_trace __tracer_data = {
 	.pipe_open	= graph_trace_open,
 	.close		= graph_trace_close,
 	.pipe_close	= graph_trace_close,
-	.wait_pipe	= poll_wait_pipe,
 	.init		= graph_trace_init,
 	.reset		= graph_trace_reset,
 	.print_line	= print_graph_function,
diff --git a/kernel/trace/trace_nop.c b/kernel/trace/trace_nop.c
index 69a5cc94c01..fcf0a9e4891 100644
--- a/kernel/trace/trace_nop.c
+++ b/kernel/trace/trace_nop.c
@@ -91,7 +91,6 @@ struct tracer nop_trace __read_mostly =
 	.name		= "nop",
 	.init		= nop_trace_init,
 	.reset		= nop_trace_reset,
-	.wait_pipe	= poll_wait_pipe,
 #ifdef CONFIG_FTRACE_SELFTEST
 	.selftest	= trace_selftest_startup_nop,
 #endif
diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c
index 1573c03640d..19bd8928ce9 100644
--- a/kernel/trace/trace_sched_wakeup.c
+++ b/kernel/trace/trace_sched_wakeup.c
@@ -705,7 +705,6 @@ static struct tracer wakeup_rt_tracer __read_mostly =
 	.reset		= wakeup_tracer_reset,
 	.start		= wakeup_tracer_start,
 	.stop		= wakeup_tracer_stop,
-	.wait_pipe	= poll_wait_pipe,
 	.print_max	= true,
 	.print_header	= wakeup_print_header,
 	.print_line	= wakeup_print_line,
@@ -728,7 +727,6 @@ static struct tracer wakeup_dl_tracer __read_mostly =
 	.reset		= wakeup_tracer_reset,
 	.start		= wakeup_tracer_start,
 	.stop		= wakeup_tracer_stop,
-	.wait_pipe	= poll_wait_pipe,
 	.print_max	= true,
 	.print_header	= wakeup_print_header,
 	.print_line	= wakeup_print_line,
-- 
cgit v1.2.3-70-g09d2


From bdffd893a0e9c431304142d12d9a0a21d365c502 Mon Sep 17 00:00:00 2001
From: Christoph Lameter <cl@linux.com>
Date: Tue, 29 Apr 2014 14:17:40 -0500
Subject: tracing: Replace __get_cpu_var uses with this_cpu_ptr

Replace uses of &__get_cpu_var for address calculation with this_cpu_ptr.

Link: http://lkml.kernel.org/p/alpine.DEB.2.10.1404291415560.18364@gentwo.org

Acked-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Signed-off-by: Christoph Lameter <cl@linux.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 include/linux/kprobes.h | 2 +-
 kernel/trace/ftrace.c   | 4 ++--
 kernel/trace/trace.c    | 2 +-
 3 files changed, 4 insertions(+), 4 deletions(-)

(limited to 'kernel/trace/trace.c')

diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h
index 925eaf28fca..7bd2ad01e39 100644
--- a/include/linux/kprobes.h
+++ b/include/linux/kprobes.h
@@ -355,7 +355,7 @@ static inline void reset_current_kprobe(void)
 
 static inline struct kprobe_ctlblk *get_kprobe_ctlblk(void)
 {
-	return (&__get_cpu_var(kprobe_ctlblk));
+	return this_cpu_ptr(&kprobe_ctlblk);
 }
 
 int register_kprobe(struct kprobe *p);
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 9eb1aa03a18..38e5cf73b9a 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -822,7 +822,7 @@ function_profile_call(unsigned long ip, unsigned long parent_ip,
 
 	local_irq_save(flags);
 
-	stat = &__get_cpu_var(ftrace_profile_stats);
+	stat = this_cpu_ptr(&ftrace_profile_stats);
 	if (!stat->hash || !ftrace_profile_enabled)
 		goto out;
 
@@ -853,7 +853,7 @@ static void profile_graph_return(struct ftrace_graph_ret *trace)
 	unsigned long flags;
 
 	local_irq_save(flags);
-	stat = &__get_cpu_var(ftrace_profile_stats);
+	stat = this_cpu_ptr(&ftrace_profile_stats);
 	if (!stat->hash || !ftrace_profile_enabled)
 		goto out;
 
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 4c392c8238b..05431696b10 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -1726,7 +1726,7 @@ static void __ftrace_trace_stack(struct ring_buffer *buffer,
 	 */
 	barrier();
 	if (use_stack == 1) {
-		trace.entries		= &__get_cpu_var(ftrace_stack).calls[0];
+		trace.entries		= this_cpu_ptr(ftrace_stack.calls);
 		trace.max_entries	= FTRACE_STACK_MAX_ENTRIES;
 
 		if (regs)
-- 
cgit v1.2.3-70-g09d2


From 2184db46e425c2b84a783eeead0e2b24ce67cd7f Mon Sep 17 00:00:00 2001
From: Steven Rostedt <rostedt@goodmis.org>
Date: Wed, 28 May 2014 13:14:40 -0400
Subject: tracing: Print nasty banner when trace_printk() is in use

trace_printk() is used to debug fast paths within the kernel. Places
that gets called in any context (interrupt or NMI) or thousands of
times a second. Something you do not want to do with a printk().

In order to make it completely lockless as it needs a temporary buffer
to handle some of the string formatting, a page is created per cpu for
every context (four per cpu; normal, softirq, irq, NMI).

Since trace_printk() should only be used for debugging purposes,
there's no reason to waste memory on these buffers on a production
system. That means, trace_printk() should never be used unless a
developer is debugging their kernel. There's macro magic to allocate
the buffers if trace_printk() is used anywhere in the kernel.

To help enforce that trace_printk() isn't used outside of development,
when it is used, a nasty banner is displayed on bootup (or when a module
is loaded that uses trace_printk() and the kernel core does not).

Here's the banner:

 **********************************************************
 **   NOTICE NOTICE NOTICE NOTICE NOTICE NOTICE NOTICE   **
 **                                                      **
 ** trace_printk() being used. Allocating extra memory.  **
 **                                                      **
 ** This means that this is a DEBUG kernel and it is     **
 ** unsafe for produciton use.                           **
 **                                                      **
 ** If you see this message and you are not debugging    **
 ** the kernel, report this immediately to your vendor!  **
 **                                                      **
 **   NOTICE NOTICE NOTICE NOTICE NOTICE NOTICE NOTICE   **
 **********************************************************

That should hopefully keep developers from trying to sneak in a
trace_printk() or two.

Link: http://lkml.kernel.org/p/20140528131440.2283213c@gandalf.local.home

Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 kernel/trace/trace.c | 16 +++++++++++++++-
 1 file changed, 15 insertions(+), 1 deletion(-)

(limited to 'kernel/trace/trace.c')

diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 05431696b10..eb228b9de17 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -1975,7 +1975,21 @@ void trace_printk_init_buffers(void)
 	if (alloc_percpu_trace_buffer())
 		return;
 
-	pr_info("ftrace: Allocated trace_printk buffers\n");
+	/* trace_printk() is for debug use only. Don't use it in production. */
+
+	pr_warning("\n**********************************************************\n");
+	pr_warning("**   NOTICE NOTICE NOTICE NOTICE NOTICE NOTICE NOTICE   **\n");
+	pr_warning("**                                                      **\n");
+	pr_warning("** trace_printk() being used. Allocating extra memory.  **\n");
+	pr_warning("**                                                      **\n");
+	pr_warning("** This means that this is a DEBUG kernel and it is     **\n");
+	pr_warning("** unsafe for produciton use.                           **\n");
+	pr_warning("**                                                      **\n");
+	pr_warning("** If you see this message and you are not debugging    **\n");
+	pr_warning("** the kernel, report this immediately to your vendor!  **\n");
+	pr_warning("**                                                      **\n");
+	pr_warning("**   NOTICE NOTICE NOTICE NOTICE NOTICE NOTICE NOTICE   **\n");
+	pr_warning("**********************************************************\n");
 
 	/* Expand the buffers to set size */
 	tracing_update_buffers();
-- 
cgit v1.2.3-70-g09d2


From 42584c81c5adc1737a6fe0687facc5e62a5dc8c1 Mon Sep 17 00:00:00 2001
From: Yoshihiro YUNOMAE <yoshihiro.yunomae.ez@hitachi.com>
Date: Thu, 20 Feb 2014 17:44:31 +0900
Subject: tracing: Have saved_cmdlines use the seq_read infrastructure

Current tracing_saved_cmdlines_read() implementation is naive; It allocates
a large buffer, constructs output data to that buffer for each read
operation, and then copies a portion of the buffer to the user space
buffer. This has several issues such as slow memory allocation, high
CPU usage, and even corruption of the output data.

The seq_read infrastructure is made to handle this type of work.
By converting it to use seq_read() the code becomes smaller, simplified,
as well as correct.

Link: http://lkml.kernel.org/p/20140220084431.3839.51793.stgit@yunodevel

Signed-off-by: Hidehiro Kawai <hidehiro.kawai.ez@hitachi.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Signed-off-by: Yoshihiro YUNOMAE <yoshihiro.yunomae.ez@hitachi.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 kernel/trace/trace.c | 89 +++++++++++++++++++++++++++++++---------------------
 1 file changed, 54 insertions(+), 35 deletions(-)

(limited to 'kernel/trace/trace.c')

diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index eb228b9de17..1855dae73f3 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -3699,55 +3699,74 @@ static const struct file_operations tracing_readme_fops = {
 	.llseek		= generic_file_llseek,
 };
 
-static ssize_t
-tracing_saved_cmdlines_read(struct file *file, char __user *ubuf,
-				size_t cnt, loff_t *ppos)
+static void *saved_cmdlines_next(struct seq_file *m, void *v, loff_t *pos)
 {
-	char *buf_comm;
-	char *file_buf;
-	char *buf;
-	int len = 0;
-	int pid;
-	int i;
+	unsigned int *ptr = v;
 
-	file_buf = kmalloc(SAVED_CMDLINES*(16+TASK_COMM_LEN), GFP_KERNEL);
-	if (!file_buf)
-		return -ENOMEM;
+	if (*pos || m->count)
+		ptr++;
 
-	buf_comm = kmalloc(TASK_COMM_LEN, GFP_KERNEL);
-	if (!buf_comm) {
-		kfree(file_buf);
-		return -ENOMEM;
-	}
+	(*pos)++;
+
+	for (; ptr < &map_cmdline_to_pid[SAVED_CMDLINES]; ptr++) {
+		if (*ptr == -1 || *ptr == NO_CMDLINE_MAP)
+			continue;
 
-	buf = file_buf;
+		return ptr;
+	}
 
-	for (i = 0; i < SAVED_CMDLINES; i++) {
-		int r;
+	return NULL;
+}
 
-		pid = map_cmdline_to_pid[i];
-		if (pid == -1 || pid == NO_CMDLINE_MAP)
-			continue;
+static void *saved_cmdlines_start(struct seq_file *m, loff_t *pos)
+{
+	void *v;
+	loff_t l = 0;
 
-		trace_find_cmdline(pid, buf_comm);
-		r = sprintf(buf, "%d %s\n", pid, buf_comm);
-		buf += r;
-		len += r;
+	v = &map_cmdline_to_pid[0];
+	while (l <= *pos) {
+		v = saved_cmdlines_next(m, v, &l);
+		if (!v)
+			return NULL;
 	}
 
-	len = simple_read_from_buffer(ubuf, cnt, ppos,
-				      file_buf, len);
+	return v;
+}
 
-	kfree(file_buf);
-	kfree(buf_comm);
+static void saved_cmdlines_stop(struct seq_file *m, void *v)
+{
+}
 
-	return len;
+static int saved_cmdlines_show(struct seq_file *m, void *v)
+{
+	char buf[TASK_COMM_LEN];
+	unsigned int *pid = v;
+
+	trace_find_cmdline(*pid, buf);
+	seq_printf(m, "%d %s\n", *pid, buf);
+	return 0;
+}
+
+static const struct seq_operations tracing_saved_cmdlines_seq_ops = {
+	.start		= saved_cmdlines_start,
+	.next		= saved_cmdlines_next,
+	.stop		= saved_cmdlines_stop,
+	.show		= saved_cmdlines_show,
+};
+
+static int tracing_saved_cmdlines_open(struct inode *inode, struct file *filp)
+{
+	if (tracing_disabled)
+		return -ENODEV;
+
+	return seq_open(filp, &tracing_saved_cmdlines_seq_ops);
 }
 
 static const struct file_operations tracing_saved_cmdlines_fops = {
-    .open       = tracing_open_generic,
-    .read       = tracing_saved_cmdlines_read,
-    .llseek	= generic_file_llseek,
+	.open		= tracing_saved_cmdlines_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= seq_release,
 };
 
 static ssize_t
-- 
cgit v1.2.3-70-g09d2


From 379cfdac37923653c9d4242d10052378b7563005 Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (Red Hat)" <rostedt@goodmis.org>
Date: Fri, 30 May 2014 09:42:39 -0400
Subject: tracing: Try again for saved cmdline if failed due to locking

In order to prevent the saved cmdline cache from being filled when
tracing is not active, the comms are only recorded after a trace event
is recorded.

The problem is, a comm can fail to be recorded if the trace_cmdline_lock
is held. That lock is taken via a trylock to allow it to happen from
any context (including NMI). If the lock fails to be taken, the comm
is skipped. No big deal, as we will try again later.

But! Because of the code that was added to only record after an event,
we may not try again later as the recording is made as a oneshot per
event per CPU.

Only disable the recording of the comm if the comm is actually recorded.

Fixes: 7ffbd48d5cab "tracing: Cache comms only after an event occurred"
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 kernel/trace/trace.c | 13 +++++++------
 1 file changed, 7 insertions(+), 6 deletions(-)

(limited to 'kernel/trace/trace.c')

diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 1855dae73f3..22a902e2ded 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -1441,12 +1441,12 @@ static void tracing_stop_tr(struct trace_array *tr)
 
 void trace_stop_cmdline_recording(void);
 
-static void trace_save_cmdline(struct task_struct *tsk)
+static int trace_save_cmdline(struct task_struct *tsk)
 {
 	unsigned pid, idx;
 
 	if (!tsk->pid || unlikely(tsk->pid > PID_MAX_DEFAULT))
-		return;
+		return 0;
 
 	/*
 	 * It's not the end of the world if we don't get
@@ -1455,7 +1455,7 @@ static void trace_save_cmdline(struct task_struct *tsk)
 	 * so if we miss here, then better luck next time.
 	 */
 	if (!arch_spin_trylock(&trace_cmdline_lock))
-		return;
+		return 0;
 
 	idx = map_pid_to_cmdline[tsk->pid];
 	if (idx == NO_CMDLINE_MAP) {
@@ -1480,6 +1480,8 @@ static void trace_save_cmdline(struct task_struct *tsk)
 	memcpy(&saved_cmdlines[idx], tsk->comm, TASK_COMM_LEN);
 
 	arch_spin_unlock(&trace_cmdline_lock);
+
+	return 1;
 }
 
 void trace_find_cmdline(int pid, char comm[])
@@ -1521,9 +1523,8 @@ void tracing_record_cmdline(struct task_struct *tsk)
 	if (!__this_cpu_read(trace_cmdline_save))
 		return;
 
-	__this_cpu_write(trace_cmdline_save, false);
-
-	trace_save_cmdline(tsk);
+	if (trace_save_cmdline(tsk))
+		__this_cpu_write(trace_cmdline_save, false);
 }
 
 void
-- 
cgit v1.2.3-70-g09d2


From 4c27e756bc019ec1c11232893af036fdae720a97 Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (Red Hat)" <rostedt@goodmis.org>
Date: Fri, 30 May 2014 10:49:46 -0400
Subject: tracing: Move locking of trace_cmdline_lock into start/stop seq calls

With the conversion of the saved_cmdlines output to use seq_read, there
is now a race between accessing the values of the saved_cmdlines and
the writing to them. The trace_cmdline_lock needs to be taken at
the start and stop of the seq calls.

A new __trace_find_cmdline() call is created to allow for the look up
to happen without taking the lock.

Fixes: 42584c81c5ad tracing: Have saved_cmdlines use the seq_read infrastructure
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 kernel/trace/trace.c | 19 +++++++++++++++----
 1 file changed, 15 insertions(+), 4 deletions(-)

(limited to 'kernel/trace/trace.c')

diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 22a902e2ded..626dbfde5d5 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -1484,7 +1484,7 @@ static int trace_save_cmdline(struct task_struct *tsk)
 	return 1;
 }
 
-void trace_find_cmdline(int pid, char comm[])
+static void __trace_find_cmdline(int pid, char comm[])
 {
 	unsigned map;
 
@@ -1503,13 +1503,19 @@ void trace_find_cmdline(int pid, char comm[])
 		return;
 	}
 
-	preempt_disable();
-	arch_spin_lock(&trace_cmdline_lock);
 	map = map_pid_to_cmdline[pid];
 	if (map != NO_CMDLINE_MAP)
 		strcpy(comm, saved_cmdlines[map]);
 	else
 		strcpy(comm, "<...>");
+}
+
+void trace_find_cmdline(int pid, char comm[])
+{
+	preempt_disable();
+	arch_spin_lock(&trace_cmdline_lock);
+
+	__trace_find_cmdline(pid, comm);
 
 	arch_spin_unlock(&trace_cmdline_lock);
 	preempt_enable();
@@ -3724,6 +3730,9 @@ static void *saved_cmdlines_start(struct seq_file *m, loff_t *pos)
 	void *v;
 	loff_t l = 0;
 
+	preempt_disable();
+	arch_spin_lock(&trace_cmdline_lock);
+
 	v = &map_cmdline_to_pid[0];
 	while (l <= *pos) {
 		v = saved_cmdlines_next(m, v, &l);
@@ -3736,6 +3745,8 @@ static void *saved_cmdlines_start(struct seq_file *m, loff_t *pos)
 
 static void saved_cmdlines_stop(struct seq_file *m, void *v)
 {
+	arch_spin_unlock(&trace_cmdline_lock);
+	preempt_enable();
 }
 
 static int saved_cmdlines_show(struct seq_file *m, void *v)
@@ -3743,7 +3754,7 @@ static int saved_cmdlines_show(struct seq_file *m, void *v)
 	char buf[TASK_COMM_LEN];
 	unsigned int *pid = v;
 
-	trace_find_cmdline(*pid, buf);
+	__trace_find_cmdline(*pid, buf);
 	seq_printf(m, "%d %s\n", *pid, buf);
 	return 0;
 }
-- 
cgit v1.2.3-70-g09d2


From 198376cd8877a612cc6494201b815c36d1e40391 Mon Sep 17 00:00:00 2001
From: Yoshihiro YUNOMAE <yoshihiro.yunomae.ez@hitachi.com>
Date: Tue, 3 Jun 2014 13:28:03 +0900
Subject: tracing: Eliminate double free on failure of allocation on boot up

If allocation of the max_buffer fails on boot up, the error path will
free both per_cpu data structures from the buffers. With the new redesign
of the code, those structures are freed if allocations failed. That is,
the helper function that allocates the buffers will free the per cpu data
on failure. No need to do it again. In fact, the second free will cause
a bug as the code can not handle a double free.

Link: http://lkml.kernel.org/p/20140603042803.27308.30956.stgit@yunodevel

Signed-off-by: Yoshihiro YUNOMAE <yoshihiro.yunomae.ez@hitachi.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 kernel/trace/trace.c | 4 ----
 1 file changed, 4 deletions(-)

(limited to 'kernel/trace/trace.c')

diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 626dbfde5d5..135af323608 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -6671,10 +6671,6 @@ __init static int tracer_alloc_buffers(void)
 out_free_temp_buffer:
 	ring_buffer_free(temp_buffer);
 out_free_cpumask:
-	free_percpu(global_trace.trace_buffer.data);
-#ifdef CONFIG_TRACER_MAX_TRACE
-	free_percpu(global_trace.max_buffer.data);
-#endif
 	free_cpumask_var(global_trace.tracing_cpumask);
 out_free_buffer_mask:
 	free_cpumask_var(tracing_buffer_mask);
-- 
cgit v1.2.3-70-g09d2


From 939c7a4f04fcd2162109744e8bf88194948a6e65 Mon Sep 17 00:00:00 2001
From: Yoshihiro YUNOMAE <yoshihiro.yunomae.ez@hitachi.com>
Date: Thu, 5 Jun 2014 10:24:27 +0900
Subject: tracing: Introduce saved_cmdlines_size file

Introduce saved_cmdlines_size file for changing the number of saved pid-comms.
saved_cmdlines currently stores 128 command names using SAVED_CMDLINES, but
'no-existing processes' names are often lost in saved_cmdlines when we
read the trace data. So, by introducing saved_cmdlines_size file, we can
now change the 128 command names saved to something much larger if needed.

When we write a value to saved_cmdlines_size, the number of the value will
be stored in pid-comm list:

	# echo 1024 > /sys/kernel/debug/tracing/saved_cmdlines_size

Here, 1024 command names can be stored. The default number is 128 and the maximum
number is PID_MAX_DEFAULT (=32768 if CONFIG_BASE_SMALL is not set). So, if we
want to avoid losing any command names, we need to set 32768 to
saved_cmdlines_size.

We can read the maximum number of the list:

	# cat /sys/kernel/debug/tracing/saved_cmdlines_size
	128

Link: http://lkml.kernel.org/p/20140605012427.22115.16173.stgit@yunodevel

Signed-off-by: Yoshihiro YUNOMAE <yoshihiro.yunomae.ez@hitachi.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 kernel/trace/trace.c | 178 ++++++++++++++++++++++++++++++++++++++++++++-------
 1 file changed, 154 insertions(+), 24 deletions(-)

(limited to 'kernel/trace/trace.c')

diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 135af323608..e29edee1542 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -1285,22 +1285,71 @@ void tracing_reset_all_online_cpus(void)
 	}
 }
 
-#define SAVED_CMDLINES 128
+#define SAVED_CMDLINES_DEFAULT 128
 #define NO_CMDLINE_MAP UINT_MAX
-static unsigned map_pid_to_cmdline[PID_MAX_DEFAULT+1];
-static unsigned map_cmdline_to_pid[SAVED_CMDLINES];
-static char saved_cmdlines[SAVED_CMDLINES][TASK_COMM_LEN];
-static int cmdline_idx;
 static arch_spinlock_t trace_cmdline_lock = __ARCH_SPIN_LOCK_UNLOCKED;
+struct saved_cmdlines_buffer {
+	unsigned map_pid_to_cmdline[PID_MAX_DEFAULT+1];
+	unsigned *map_cmdline_to_pid;
+	unsigned cmdline_num;
+	int cmdline_idx;
+	char *saved_cmdlines;
+};
+static struct saved_cmdlines_buffer *savedcmd;
 
 /* temporary disable recording */
 static atomic_t trace_record_cmdline_disabled __read_mostly;
 
-static void trace_init_cmdlines(void)
+static inline char *get_saved_cmdlines(int idx)
+{
+	return &savedcmd->saved_cmdlines[idx * TASK_COMM_LEN];
+}
+
+static inline void set_cmdline(int idx, const char *cmdline)
 {
-	memset(&map_pid_to_cmdline, NO_CMDLINE_MAP, sizeof(map_pid_to_cmdline));
-	memset(&map_cmdline_to_pid, NO_CMDLINE_MAP, sizeof(map_cmdline_to_pid));
-	cmdline_idx = 0;
+	memcpy(get_saved_cmdlines(idx), cmdline, TASK_COMM_LEN);
+}
+
+static int allocate_cmdlines_buffer(unsigned int val,
+				    struct saved_cmdlines_buffer *s)
+{
+	s->map_cmdline_to_pid = kmalloc(val * sizeof(*s->map_cmdline_to_pid),
+					GFP_KERNEL);
+	if (!s->map_cmdline_to_pid)
+		return -ENOMEM;
+
+	s->saved_cmdlines = kmalloc(val * TASK_COMM_LEN, GFP_KERNEL);
+	if (!s->saved_cmdlines) {
+		kfree(s->map_cmdline_to_pid);
+		return -ENOMEM;
+	}
+
+	s->cmdline_idx = 0;
+	s->cmdline_num = val;
+	memset(&s->map_pid_to_cmdline, NO_CMDLINE_MAP,
+	       sizeof(s->map_pid_to_cmdline));
+	memset(s->map_cmdline_to_pid, NO_CMDLINE_MAP,
+	       val * sizeof(*s->map_cmdline_to_pid));
+
+	return 0;
+}
+
+static int trace_create_savedcmd(void)
+{
+	int ret;
+
+	savedcmd = kmalloc(sizeof(struct saved_cmdlines_buffer), GFP_KERNEL);
+	if (!savedcmd)
+		return -ENOMEM;
+
+	ret = allocate_cmdlines_buffer(SAVED_CMDLINES_DEFAULT, savedcmd);
+	if (ret < 0) {
+		kfree(savedcmd);
+		savedcmd = NULL;
+		return -ENOMEM;
+	}
+
+	return 0;
 }
 
 int is_tracing_stopped(void)
@@ -1457,9 +1506,9 @@ static int trace_save_cmdline(struct task_struct *tsk)
 	if (!arch_spin_trylock(&trace_cmdline_lock))
 		return 0;
 
-	idx = map_pid_to_cmdline[tsk->pid];
+	idx = savedcmd->map_pid_to_cmdline[tsk->pid];
 	if (idx == NO_CMDLINE_MAP) {
-		idx = (cmdline_idx + 1) % SAVED_CMDLINES;
+		idx = (savedcmd->cmdline_idx + 1) % savedcmd->cmdline_num;
 
 		/*
 		 * Check whether the cmdline buffer at idx has a pid
@@ -1467,17 +1516,17 @@ static int trace_save_cmdline(struct task_struct *tsk)
 		 * need to clear the map_pid_to_cmdline. Otherwise we
 		 * would read the new comm for the old pid.
 		 */
-		pid = map_cmdline_to_pid[idx];
+		pid = savedcmd->map_cmdline_to_pid[idx];
 		if (pid != NO_CMDLINE_MAP)
-			map_pid_to_cmdline[pid] = NO_CMDLINE_MAP;
+			savedcmd->map_pid_to_cmdline[pid] = NO_CMDLINE_MAP;
 
-		map_cmdline_to_pid[idx] = tsk->pid;
-		map_pid_to_cmdline[tsk->pid] = idx;
+		savedcmd->map_cmdline_to_pid[idx] = tsk->pid;
+		savedcmd->map_pid_to_cmdline[tsk->pid] = idx;
 
-		cmdline_idx = idx;
+		savedcmd->cmdline_idx = idx;
 	}
 
-	memcpy(&saved_cmdlines[idx], tsk->comm, TASK_COMM_LEN);
+	set_cmdline(idx, tsk->comm);
 
 	arch_spin_unlock(&trace_cmdline_lock);
 
@@ -1503,9 +1552,9 @@ static void __trace_find_cmdline(int pid, char comm[])
 		return;
 	}
 
-	map = map_pid_to_cmdline[pid];
+	map = savedcmd->map_pid_to_cmdline[pid];
 	if (map != NO_CMDLINE_MAP)
-		strcpy(comm, saved_cmdlines[map]);
+		strcpy(comm, get_saved_cmdlines(map));
 	else
 		strcpy(comm, "<...>");
 }
@@ -3593,6 +3642,7 @@ static const char readme_msg[] =
 	"  trace_options\t\t- Set format or modify how tracing happens\n"
 	"\t\t\t  Disable an option by adding a suffix 'no' to the\n"
 	"\t\t\t  option name\n"
+	"  saved_cmdlines_size\t- echo command number in here to store comm-pid list\n"
 #ifdef CONFIG_DYNAMIC_FTRACE
 	"\n  available_filter_functions - list of functions that can be filtered on\n"
 	"  set_ftrace_filter\t- echo function name in here to only trace these\n"
@@ -3715,7 +3765,8 @@ static void *saved_cmdlines_next(struct seq_file *m, void *v, loff_t *pos)
 
 	(*pos)++;
 
-	for (; ptr < &map_cmdline_to_pid[SAVED_CMDLINES]; ptr++) {
+	for (; ptr < &savedcmd->map_cmdline_to_pid[savedcmd->cmdline_num];
+	     ptr++) {
 		if (*ptr == -1 || *ptr == NO_CMDLINE_MAP)
 			continue;
 
@@ -3733,7 +3784,7 @@ static void *saved_cmdlines_start(struct seq_file *m, loff_t *pos)
 	preempt_disable();
 	arch_spin_lock(&trace_cmdline_lock);
 
-	v = &map_cmdline_to_pid[0];
+	v = &savedcmd->map_cmdline_to_pid[0];
 	while (l <= *pos) {
 		v = saved_cmdlines_next(m, v, &l);
 		if (!v)
@@ -3781,6 +3832,79 @@ static const struct file_operations tracing_saved_cmdlines_fops = {
 	.release	= seq_release,
 };
 
+static ssize_t
+tracing_saved_cmdlines_size_read(struct file *filp, char __user *ubuf,
+				 size_t cnt, loff_t *ppos)
+{
+	char buf[64];
+	int r;
+
+	arch_spin_lock(&trace_cmdline_lock);
+	r = sprintf(buf, "%u\n", savedcmd->cmdline_num);
+	arch_spin_unlock(&trace_cmdline_lock);
+
+	return simple_read_from_buffer(ubuf, cnt, ppos, buf, r);
+}
+
+static void free_saved_cmdlines_buffer(struct saved_cmdlines_buffer *s)
+{
+	kfree(s->saved_cmdlines);
+	kfree(s->map_cmdline_to_pid);
+	kfree(s);
+}
+
+static int tracing_resize_saved_cmdlines(unsigned int val)
+{
+	struct saved_cmdlines_buffer *s, *savedcmd_temp;
+
+	s = kmalloc(sizeof(struct saved_cmdlines_buffer), GFP_KERNEL);
+	if (!s)
+		return -ENOMEM;
+
+	if (allocate_cmdlines_buffer(val, s) < 0) {
+		kfree(s);
+		return -ENOMEM;
+	}
+
+	arch_spin_lock(&trace_cmdline_lock);
+	savedcmd_temp = savedcmd;
+	savedcmd = s;
+	arch_spin_unlock(&trace_cmdline_lock);
+	free_saved_cmdlines_buffer(savedcmd_temp);
+
+	return 0;
+}
+
+static ssize_t
+tracing_saved_cmdlines_size_write(struct file *filp, const char __user *ubuf,
+				  size_t cnt, loff_t *ppos)
+{
+	unsigned long val;
+	int ret;
+
+	ret = kstrtoul_from_user(ubuf, cnt, 10, &val);
+	if (ret)
+		return ret;
+
+	/* must have at least 1 entry or less than PID_MAX_DEFAULT */
+	if (!val || val > PID_MAX_DEFAULT)
+		return -EINVAL;
+
+	ret = tracing_resize_saved_cmdlines((unsigned int)val);
+	if (ret < 0)
+		return ret;
+
+	*ppos += cnt;
+
+	return cnt;
+}
+
+static const struct file_operations tracing_saved_cmdlines_size_fops = {
+	.open		= tracing_open_generic,
+	.read		= tracing_saved_cmdlines_size_read,
+	.write		= tracing_saved_cmdlines_size_write,
+};
+
 static ssize_t
 tracing_set_trace_read(struct file *filp, char __user *ubuf,
 		       size_t cnt, loff_t *ppos)
@@ -6375,6 +6499,9 @@ static __init int tracer_init_debugfs(void)
 	trace_create_file("saved_cmdlines", 0444, d_tracer,
 			NULL, &tracing_saved_cmdlines_fops);
 
+	trace_create_file("saved_cmdlines_size", 0644, d_tracer,
+			  NULL, &tracing_saved_cmdlines_size_fops);
+
 #ifdef CONFIG_DYNAMIC_FTRACE
 	trace_create_file("dyn_ftrace_total_info", 0444, d_tracer,
 			&ftrace_update_tot_cnt, &tracing_dyn_info_fops);
@@ -6611,18 +6738,19 @@ __init static int tracer_alloc_buffers(void)
 	if (!temp_buffer)
 		goto out_free_cpumask;
 
+	if (trace_create_savedcmd() < 0)
+		goto out_free_temp_buffer;
+
 	/* TODO: make the number of buffers hot pluggable with CPUS */
 	if (allocate_trace_buffers(&global_trace, ring_buf_size) < 0) {
 		printk(KERN_ERR "tracer: failed to allocate ring buffer!\n");
 		WARN_ON(1);
-		goto out_free_temp_buffer;
+		goto out_free_savedcmd;
 	}
 
 	if (global_trace.buffer_disabled)
 		tracing_off();
 
-	trace_init_cmdlines();
-
 	if (trace_boot_clock) {
 		ret = tracing_set_clock(&global_trace, trace_boot_clock);
 		if (ret < 0)
@@ -6668,6 +6796,8 @@ __init static int tracer_alloc_buffers(void)
 
 	return 0;
 
+out_free_savedcmd:
+	free_saved_cmdlines_buffer(savedcmd);
 out_free_temp_buffer:
 	ring_buffer_free(temp_buffer);
 out_free_cpumask:
-- 
cgit v1.2.3-70-g09d2


From 23aaa3c18e33fe048671b419781b5e44175efafe Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (Red Hat)" <rostedt@goodmis.org>
Date: Fri, 6 Jun 2014 00:01:46 -0400
Subject: tracing: Fix leak of ring buffer data when new instances creation
 fails

Yoshihiro Yunomae reported that the ring buffer data for a trace
instance does not get properly cleaned up when it fails. He proposed
a patch that manually cleaned the data up and addad a bunch of labels.
The labels are not needed because all trace array is allocated with
a kzalloc which initializes it to 0 and all kfree()s can take a NULL
pointer and will ignore it.

Adding a new helper function free_trace_buffers() that can also take
null buffers to free the buffers that were allocated by
allocate_trace_buffers().

Link: http://lkml.kernel.org/r/20140605223522.32311.31664.stgit@yunodevel

Reported-by: Yoshihiro YUNOMAE <yoshihiro.yunomae.ez@hitachi.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 kernel/trace/trace.c | 22 ++++++++++++++++++++--
 1 file changed, 20 insertions(+), 2 deletions(-)

(limited to 'kernel/trace/trace.c')

diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index e29edee1542..26cfff38e2a 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -6232,6 +6232,25 @@ static int allocate_trace_buffers(struct trace_array *tr, int size)
 	return 0;
 }
 
+static void free_trace_buffers(struct trace_array *tr)
+{
+	if (!tr)
+		return;
+
+	if (tr->trace_buffer.buffer) {
+		ring_buffer_free(tr->trace_buffer.buffer);
+		tr->trace_buffer.buffer = NULL;
+		free_percpu(tr->trace_buffer.data);
+	}
+
+#ifdef CONFIG_TRACER_MAX_TRACE
+	if (tr->max_buffer.buffer) {
+		ring_buffer_free(tr->max_buffer.buffer);
+		tr->max_buffer.buffer = NULL;
+	}
+#endif
+}
+
 static int new_instance_create(const char *name)
 {
 	struct trace_array *tr;
@@ -6290,8 +6309,7 @@ static int new_instance_create(const char *name)
 	return 0;
 
  out_free_tr:
-	if (tr->trace_buffer.buffer)
-		ring_buffer_free(tr->trace_buffer.buffer);
+	free_trace_buffers(tr);
 	free_cpumask_var(tr->tracing_cpumask);
 	kfree(tr->name);
 	kfree(tr);
-- 
cgit v1.2.3-70-g09d2


From a9fcaaac37b3baba1343f906f52aeb65c4d4e356 Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (Red Hat)" <rostedt@goodmis.org>
Date: Fri, 6 Jun 2014 23:17:28 -0400
Subject: tracing: Fix memory leak on instance deletion

When an instance is created, it also gets a snapshot ring buffer
allocated (with minimum of pages). But when it is deleted the snapshot
buffer is not. There was a helper function added to match the allocation
of these ring buffers to a way to free them, but it wasn't used by
the deletion of an instance. Using that helper function solves this
memory leak.

Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 kernel/trace/trace.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

(limited to 'kernel/trace/trace.c')

diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 26cfff38e2a..16f7038d1f4 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -6349,8 +6349,7 @@ static int instance_delete(const char *name)
 	event_trace_del_tracer(tr);
 	ftrace_destroy_function_files(tr);
 	debugfs_remove_recursive(tr->dir);
-	free_percpu(tr->trace_buffer.data);
-	ring_buffer_free(tr->trace_buffer.buffer);
+	free_trace_buffers(tr);
 
 	kfree(tr->name);
 	kfree(tr);
-- 
cgit v1.2.3-70-g09d2


From 8b8b36834d0fff67fc8668093f4312dd04dcf21d Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (Red Hat)" <rostedt@goodmis.org>
Date: Tue, 10 Jun 2014 09:46:00 -0400
Subject: ring-buffer: Check if buffer exists before polling

The per_cpu buffers are created one per possible CPU. But these do
not mean that those CPUs are online, nor do they even exist.

With the addition of the ring buffer polling, it assumes that the
caller polls on an existing buffer. But this is not the case if
the user reads trace_pipe from a CPU that does not exist, and this
causes the kernel to crash.

Simple fix is to check the cpu against buffer bitmask against to see
if the buffer was allocated or not and return -ENODEV if it is
not.

More updates were done to pass the -ENODEV back up to userspace.

Link: http://lkml.kernel.org/r/5393DB61.6060707@oracle.com

Reported-by: Sasha Levin <sasha.levin@oracle.com>
Cc: stable@vger.kernel.org # 3.10+
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 include/linux/ring_buffer.h |  2 +-
 kernel/trace/ring_buffer.c  |  5 ++++-
 kernel/trace/trace.c        | 22 ++++++++++++++++------
 3 files changed, 21 insertions(+), 8 deletions(-)

(limited to 'kernel/trace/trace.c')

diff --git a/include/linux/ring_buffer.h b/include/linux/ring_buffer.h
index d69cf637a15..49a4d6f5910 100644
--- a/include/linux/ring_buffer.h
+++ b/include/linux/ring_buffer.h
@@ -97,7 +97,7 @@ __ring_buffer_alloc(unsigned long size, unsigned flags, struct lock_class_key *k
 	__ring_buffer_alloc((size), (flags), &__key);	\
 })
 
-void ring_buffer_wait(struct ring_buffer *buffer, int cpu);
+int ring_buffer_wait(struct ring_buffer *buffer, int cpu);
 int ring_buffer_poll_wait(struct ring_buffer *buffer, int cpu,
 			  struct file *filp, poll_table *poll_table);
 
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index c634868c292..7c56c3d0694 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -543,7 +543,7 @@ static void rb_wake_up_waiters(struct irq_work *work)
  * as data is added to any of the @buffer's cpu buffers. Otherwise
  * it will wait for data to be added to a specific cpu buffer.
  */
-void ring_buffer_wait(struct ring_buffer *buffer, int cpu)
+int ring_buffer_wait(struct ring_buffer *buffer, int cpu)
 {
 	struct ring_buffer_per_cpu *cpu_buffer;
 	DEFINE_WAIT(wait);
@@ -557,6 +557,8 @@ void ring_buffer_wait(struct ring_buffer *buffer, int cpu)
 	if (cpu == RING_BUFFER_ALL_CPUS)
 		work = &buffer->irq_work;
 	else {
+		if (!cpumask_test_cpu(cpu, buffer->cpumask))
+			return -ENODEV;
 		cpu_buffer = buffer->buffers[cpu];
 		work = &cpu_buffer->irq_work;
 	}
@@ -591,6 +593,7 @@ void ring_buffer_wait(struct ring_buffer *buffer, int cpu)
 		schedule();
 
 	finish_wait(&work->waiters, &wait);
+	return 0;
 }
 
 /**
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 16f7038d1f4..56422f1decb 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -1085,13 +1085,13 @@ update_max_tr_single(struct trace_array *tr, struct task_struct *tsk, int cpu)
 }
 #endif /* CONFIG_TRACER_MAX_TRACE */
 
-static void wait_on_pipe(struct trace_iterator *iter)
+static int wait_on_pipe(struct trace_iterator *iter)
 {
 	/* Iterators are static, they should be filled or empty */
 	if (trace_buffer_iter(iter, iter->cpu_file))
-		return;
+		return 0;
 
-	ring_buffer_wait(iter->trace_buffer->buffer, iter->cpu_file);
+	return ring_buffer_wait(iter->trace_buffer->buffer, iter->cpu_file);
 }
 
 #ifdef CONFIG_FTRACE_STARTUP_TEST
@@ -4378,6 +4378,7 @@ tracing_poll_pipe(struct file *filp, poll_table *poll_table)
 static int tracing_wait_pipe(struct file *filp)
 {
 	struct trace_iterator *iter = filp->private_data;
+	int ret;
 
 	while (trace_empty(iter)) {
 
@@ -4399,10 +4400,13 @@ static int tracing_wait_pipe(struct file *filp)
 
 		mutex_unlock(&iter->mutex);
 
-		wait_on_pipe(iter);
+		ret = wait_on_pipe(iter);
 
 		mutex_lock(&iter->mutex);
 
+		if (ret)
+			return ret;
+
 		if (signal_pending(current))
 			return -EINTR;
 	}
@@ -5327,8 +5331,12 @@ tracing_buffers_read(struct file *filp, char __user *ubuf,
 				goto out_unlock;
 			}
 			mutex_unlock(&trace_types_lock);
-			wait_on_pipe(iter);
+			ret = wait_on_pipe(iter);
 			mutex_lock(&trace_types_lock);
+			if (ret) {
+				size = ret;
+				goto out_unlock;
+			}
 			if (signal_pending(current)) {
 				size = -EINTR;
 				goto out_unlock;
@@ -5538,8 +5546,10 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
 			goto out;
 		}
 		mutex_unlock(&trace_types_lock);
-		wait_on_pipe(iter);
+		ret = wait_on_pipe(iter);
 		mutex_lock(&trace_types_lock);
+		if (ret)
+			goto out;
 		if (signal_pending(current)) {
 			ret = -EINTR;
 			goto out;
-- 
cgit v1.2.3-70-g09d2


From a6af8fbf17989e41fef5cacf3988a724fb687d78 Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Tue, 10 Jun 2014 16:11:35 +0900
Subject: tracing: Cleanup saved_cmdlines_size changes

The recent addition of saved_cmdlines_size file had some remaining
(minor - mostly coding style) issues.  Fix them by passing pointer
name to sizeof() and using scnprintf().

Link: http://lkml.kernel.org/p/1402384295-23680-1-git-send-email-namhyung@kernel.org

Cc: Namhyung Kim <namhyung.kim@lge.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Yoshihiro YUNOMAE <yoshihiro.yunomae.ez@hitachi.com>
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 kernel/trace/trace.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

(limited to 'kernel/trace/trace.c')

diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 56422f1decb..2b458c60e0d 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -1338,7 +1338,7 @@ static int trace_create_savedcmd(void)
 {
 	int ret;
 
-	savedcmd = kmalloc(sizeof(struct saved_cmdlines_buffer), GFP_KERNEL);
+	savedcmd = kmalloc(sizeof(*savedcmd), GFP_KERNEL);
 	if (!savedcmd)
 		return -ENOMEM;
 
@@ -3840,7 +3840,7 @@ tracing_saved_cmdlines_size_read(struct file *filp, char __user *ubuf,
 	int r;
 
 	arch_spin_lock(&trace_cmdline_lock);
-	r = sprintf(buf, "%u\n", savedcmd->cmdline_num);
+	r = scnprintf(buf, sizeof(buf), "%u\n", savedcmd->cmdline_num);
 	arch_spin_unlock(&trace_cmdline_lock);
 
 	return simple_read_from_buffer(ubuf, cnt, ppos, buf, r);
@@ -3857,7 +3857,7 @@ static int tracing_resize_saved_cmdlines(unsigned int val)
 {
 	struct saved_cmdlines_buffer *s, *savedcmd_temp;
 
-	s = kmalloc(sizeof(struct saved_cmdlines_buffer), GFP_KERNEL);
+	s = kmalloc(sizeof(*s), GFP_KERNEL);
 	if (!s)
 		return -ENOMEM;
 
-- 
cgit v1.2.3-70-g09d2


From f0b70cc48cc282cb326a4d71b3d1dda7d8fafd2a Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (Red Hat)" <rostedt@goodmis.org>
Date: Tue, 10 Jun 2014 12:06:30 -0400
Subject: tracing: Fix leak of per cpu max data in instances

The freeing of an instance, if max data is configured, there will be
per cpu data structures created. But these are not freed when the instance
is deleted, which causes a memory leak.

A new helper function is added that frees the individual buffers within a
trace array, instead of duplicating the code. This way changes made for one
are applied to the other (normal buffer vs max buffer).

Link: http://lkml.kernel.org/r/87k38pbake.fsf@sejong.aot.lge.com

Reported-by: Namhyung Kim <namhyung@gmail.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 kernel/trace/trace.c | 21 ++++++++++++---------
 1 file changed, 12 insertions(+), 9 deletions(-)

(limited to 'kernel/trace/trace.c')

diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 2b458c60e0d..384ede31171 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -6242,22 +6242,25 @@ static int allocate_trace_buffers(struct trace_array *tr, int size)
 	return 0;
 }
 
+static void free_trace_buffer(struct trace_buffer *buf)
+{
+	if (buf->buffer) {
+		ring_buffer_free(buf->buffer);
+		buf->buffer = NULL;
+		free_percpu(buf->data);
+		buf->data = NULL;
+	}
+}
+
 static void free_trace_buffers(struct trace_array *tr)
 {
 	if (!tr)
 		return;
 
-	if (tr->trace_buffer.buffer) {
-		ring_buffer_free(tr->trace_buffer.buffer);
-		tr->trace_buffer.buffer = NULL;
-		free_percpu(tr->trace_buffer.data);
-	}
+	free_trace_buffer(&tr->trace_buffer);
 
 #ifdef CONFIG_TRACER_MAX_TRACE
-	if (tr->max_buffer.buffer) {
-		ring_buffer_free(tr->max_buffer.buffer);
-		tr->max_buffer.buffer = NULL;
-	}
+	free_trace_buffer(&tr->max_buffer);
 #endif
 }
 
-- 
cgit v1.2.3-70-g09d2


From 099ed151675cd1d2dbeae1dac697975f6a68716d Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (Red Hat)" <rostedt@goodmis.org>
Date: Tue, 24 Jun 2014 23:50:09 -0400
Subject: tracing: Remove ftrace_stop/start() from reading the trace file

Disabling reading and writing to the trace file should not be able to
disable all function tracing callbacks. There's other users today
(like kprobes and perf). Reading a trace file should not stop those
from happening.

Cc: stable@vger.kernel.org # 3.0+
Reviewed-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 kernel/trace/trace.c | 2 --
 1 file changed, 2 deletions(-)

(limited to 'kernel/trace/trace.c')

diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 384ede31171..f243444a377 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -1396,7 +1396,6 @@ void tracing_start(void)
 
 	arch_spin_unlock(&global_trace.max_lock);
 
-	ftrace_start();
  out:
 	raw_spin_unlock_irqrestore(&global_trace.start_lock, flags);
 }
@@ -1443,7 +1442,6 @@ void tracing_stop(void)
 	struct ring_buffer *buffer;
 	unsigned long flags;
 
-	ftrace_stop();
 	raw_spin_lock_irqsave(&global_trace.start_lock, flags);
 	if (global_trace.stop_count++)
 		goto out;
-- 
cgit v1.2.3-70-g09d2


From 8abfb8727f4a724d31f9ccfd8013fbd16d539445 Mon Sep 17 00:00:00 2001
From: "zhangwei(Jovi)" <jovi.zhangwei@huawei.com>
Date: Thu, 18 Jul 2013 16:31:05 +0800
Subject: tracing: Add ftrace_trace_stack into __trace_puts/__trace_bputs

Currently trace option stacktrace is not applicable for
trace_printk with constant string argument, the reason is
in __trace_puts/__trace_bputs ftrace_trace_stack is missing.

In contrast, when using trace_printk with non constant string
argument(will call into __trace_printk/__trace_bprintk), then
trace option stacktrace is workable, this inconstant result
will confuses users a lot.

Link: http://lkml.kernel.org/p/51E7A7C9.9040401@huawei.com

Cc: stable@vger.kernel.org # 3.10+
Signed-off-by: zhangwei(Jovi) <jovi.zhangwei@huawei.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 kernel/trace/trace.c | 12 ++++++++++--
 1 file changed, 10 insertions(+), 2 deletions(-)

(limited to 'kernel/trace/trace.c')

diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index f243444a377..a6ffc8918dd 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -466,6 +466,9 @@ int __trace_puts(unsigned long ip, const char *str, int size)
 	struct print_entry *entry;
 	unsigned long irq_flags;
 	int alloc;
+	int pc;
+
+	pc = preempt_count();
 
 	if (unlikely(tracing_selftest_running || tracing_disabled))
 		return 0;
@@ -475,7 +478,7 @@ int __trace_puts(unsigned long ip, const char *str, int size)
 	local_save_flags(irq_flags);
 	buffer = global_trace.trace_buffer.buffer;
 	event = trace_buffer_lock_reserve(buffer, TRACE_PRINT, alloc, 
-					  irq_flags, preempt_count());
+					  irq_flags, pc);
 	if (!event)
 		return 0;
 
@@ -492,6 +495,7 @@ int __trace_puts(unsigned long ip, const char *str, int size)
 		entry->buf[size] = '\0';
 
 	__buffer_unlock_commit(buffer, event);
+	ftrace_trace_stack(buffer, irq_flags, 4, pc);
 
 	return size;
 }
@@ -509,6 +513,9 @@ int __trace_bputs(unsigned long ip, const char *str)
 	struct bputs_entry *entry;
 	unsigned long irq_flags;
 	int size = sizeof(struct bputs_entry);
+	int pc;
+
+	pc = preempt_count();
 
 	if (unlikely(tracing_selftest_running || tracing_disabled))
 		return 0;
@@ -516,7 +523,7 @@ int __trace_bputs(unsigned long ip, const char *str)
 	local_save_flags(irq_flags);
 	buffer = global_trace.trace_buffer.buffer;
 	event = trace_buffer_lock_reserve(buffer, TRACE_BPUTS, size,
-					  irq_flags, preempt_count());
+					  irq_flags, pc);
 	if (!event)
 		return 0;
 
@@ -525,6 +532,7 @@ int __trace_bputs(unsigned long ip, const char *str)
 	entry->str			= str;
 
 	__buffer_unlock_commit(buffer, event);
+	ftrace_trace_stack(buffer, irq_flags, 4, pc);
 
 	return 1;
 }
-- 
cgit v1.2.3-70-g09d2


From f0160a5a2912267c02cfe692eac955c360de5fdf Mon Sep 17 00:00:00 2001
From: "zhangwei(Jovi)" <jovi.zhangwei@huawei.com>
Date: Thu, 18 Jul 2013 16:31:18 +0800
Subject: tracing: Add TRACE_ITER_PRINTK flag check in
 __trace_puts/__trace_bputs

The TRACE_ITER_PRINTK check in __trace_puts/__trace_bputs is missing,
so add it, to be consistent with __trace_printk/__trace_bprintk.
Those functions are all called by the same function: trace_printk().

Link: http://lkml.kernel.org/p/51E7A7D6.8090900@huawei.com

Cc: stable@vger.kernel.org # 3.11+
Signed-off-by: zhangwei(Jovi) <jovi.zhangwei@huawei.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 kernel/trace/trace.c | 6 ++++++
 1 file changed, 6 insertions(+)

(limited to 'kernel/trace/trace.c')

diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index a6ffc8918dd..bda9621638c 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -468,6 +468,9 @@ int __trace_puts(unsigned long ip, const char *str, int size)
 	int alloc;
 	int pc;
 
+	if (!(trace_flags & TRACE_ITER_PRINTK))
+		return 0;
+
 	pc = preempt_count();
 
 	if (unlikely(tracing_selftest_running || tracing_disabled))
@@ -515,6 +518,9 @@ int __trace_bputs(unsigned long ip, const char *str)
 	int size = sizeof(struct bputs_entry);
 	int pc;
 
+	if (!(trace_flags & TRACE_ITER_PRINTK))
+		return 0;
+
 	pc = preempt_count();
 
 	if (unlikely(tracing_selftest_running || tracing_disabled))
-- 
cgit v1.2.3-70-g09d2