Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]

Groups > linux.kernel > #1620580 > unrolled thread

[PATCH 0/7 v3] tracing: Add usecase of synchronize_rcu_tasks() and stack_tracer_disable()

Back to article view | Back to linux.kernel

Contents

  [PATCH 0/7 v3] tracing: Add usecase of synchronize_rcu_tasks()  and stack_tracer_disable() Steven Rostedt <rostedt@goodmis.org> - 2017-04-10 20:20 +0200
    [PATCH 6/7 v3] rcu/tracing: Add rcu_disabled to denote when rcu_irq_enter() will not  work Steven Rostedt <rostedt@goodmis.org> - 2017-04-10 20:20 +0200
    [PATCH 4/7 v3] tracing: Rename trace_active to disable_stack_tracer and inline its  modification Steven Rostedt <rostedt@goodmis.org> - 2017-04-10 20:20 +0200
      Re: [PATCH 4/7 v3] tracing: Rename trace_active to  disable_stack_tracer and inline its modification "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> - 2017-04-10 20:40 +0200
    [PATCH 5/7 v3] rcu: Fix dyntick-idle tracing Steven Rostedt <rostedt@goodmis.org> - 2017-04-10 20:20 +0200

#1620580 — [PATCH 0/7 v3] tracing: Add usecase of synchronize_rcu_tasks() and stack_tracer_disable()

Hopefully this is the final version before I push this to linux-next.

Paul, can I get an ack on the last patch from you?

-- Steve

Paul E. McKenney (1):
      rcu: Fix dyntick-idle tracing

Steven Rostedt (VMware) (6):
      ftrace: Add use of synchronize_rcu_tasks() with dynamic trampolines
      tracing: Replace the per_cpu() with __this_cpu*() in trace_stack.c
      tracing: Add stack_tracer_disable/enable() functions
      tracing: Rename trace_active to disable_stack_tracer and inline its modification
      rcu/tracing: Add rcu_disabled to denote when rcu_irq_enter() will not work
      tracing: Make sure rcu_irq_enter() can work for trace_*_rcuidle() trace events

----
 include/linux/ftrace.h     | 38 ++++++++++++++++++++++++++++
 include/linux/rcupdate.h   |  5 ++++
 include/linux/tracepoint.h | 19 ++++++++------
 kernel/rcu/tree.c          | 62 +++++++++++++++++++++++++++-------------------
 kernel/trace/Kconfig       |  3 ++-
 kernel/trace/ftrace.c      | 42 ++++++++++++++-----------------
 kernel/trace/trace_stack.c | 35 +++++++++++++-------------
 7 files changed, 128 insertions(+), 76 deletions(-)

Diff against v2 (not counting the last two patches at the end of this series)

diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index 4bde7ff..06b2990 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -323,7 +323,7 @@ static inline void stack_tracer_enable(void)
 }
 #else
 static inline void stack_tracer_disable(void) { }
-static inline void stack_tracer_enabe(void) { }
+static inline void stack_tracer_enable(void) { }
 #endif
 
 struct ftrace_func_command {
diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c
index 84fafb6..f2f02ff 100644
--- a/kernel/trace/trace_stack.c
+++ b/kernel/trace/trace_stack.c
@@ -211,8 +211,8 @@ stack_trace_call(unsigned long ip, unsigned long parent_ip,
 	preempt_disable_notrace();
 
 	/* no atomic needed, we only modify this variable by this cpu */
-	this_cpu_inc(disable_stack_tracer);
-	if (this_cpu_read(disable_stack_tracer) != 1)
+	__this_cpu_inc(disable_stack_tracer);
+	if (__this_cpu_read(disable_stack_tracer) != 1)
 		goto out;
 
 	ip += MCOUNT_INSN_SIZE;
@@ -220,7 +220,7 @@ stack_trace_call(unsigned long ip, unsigned long parent_ip,
 	check_stack(ip, &stack);
 
  out:
-	this_cpu_dec(disable_stack_tracer);
+	__this_cpu_dec(disable_stack_tracer);
 	/* prevent recursion in schedule */
 	preempt_enable_notrace();
 }
@@ -264,13 +264,13 @@ stack_max_size_write(struct file *filp, const char __user *ubuf,
 	 * we will cause circular lock, so we also need to increase
 	 * the percpu disable_stack_tracer here.
 	 */
-	this_cpu_inc(disable_stack_tracer);
+	__this_cpu_inc(disable_stack_tracer);
 
 	arch_spin_lock(&stack_trace_max_lock);
 	*ptr = val;
 	arch_spin_unlock(&stack_trace_max_lock);
 
-	this_cpu_dec(disable_stack_tracer);
+	__this_cpu_dec(disable_stack_tracer);
 	local_irq_restore(flags);
 
 	return count;
@@ -306,7 +306,7 @@ static void *t_start(struct seq_file *m, loff_t *pos)
 {
 	local_irq_disable();
 
-	this_cpu_inc(disable_stack_tracer);
+	__this_cpu_inc(disable_stack_tracer);
 
 	arch_spin_lock(&stack_trace_max_lock);
 
@@ -320,7 +320,7 @@ static void t_stop(struct seq_file *m, void *p)
 {
 	arch_spin_unlock(&stack_trace_max_lock);
 
-	this_cpu_dec(disable_stack_tracer);
+	__this_cpu_dec(disable_stack_tracer);
 
 	local_irq_enable();
 }

[toc] | [next] | [standalone]

#1620581 — [PATCH 6/7 v3] rcu/tracing: Add rcu_disabled to denote when rcu_irq_enter() will not work

From: "Steven Rostedt (VMware)" <rostedt@goodmis.org>

Tracing uses rcu_irq_enter() as a way to make sure that RCU is watching when
it needs to use rcu_read_lock() and friends. This is because tracing can
happen as RCU is about to enter user space, or about to go idle, and RCU
does not watch for RCU read side critical sections as it makes the
transition.

There is a small location within the RCU infrastructure that rcu_irq_enter()
itself will not work. If tracing were to occur in that section it will break
if it tries to use rcu_irq_enter().

Originally, this happens with the stack_tracer, because it will call
save_stack_trace when it encounters stack usage that is greater than any
stack usage it had encountered previously. There was a case where that
happened in the RCU section where rcu_irq_enter() did not work, and lockdep
complained loudly about it. To fix it, stack tracing added a call to be
disabled and RCU would disable stack tracing during the critical section
that rcu_irq_enter() was inoperable. This solution worked, but there are
other cases that use rcu_irq_enter() and it would be a good idea to let RCU
give a way to let others know that rcu_irq_enter() will not work. For
example, in trace events.

Another helpful aspect of this change is that it also moves the per cpu
variable called in the RCU critical section into a cache locale along with
other RCU per cpu variables used in that same location.

I'm keeping the stack_trace_disable() code, as that still could be used in
the future by places that really need to disable it. And since it's only a
static inline, it wont take up any kernel text if it is not used.

Link: http://lkml.kernel.org/r/20170405093207.404f8deb@gandalf.local.home

Acked-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 include/linux/rcupdate.h   |  5 +++++
 kernel/rcu/tree.c          | 18 ++++++++++++++++--
 kernel/trace/trace_stack.c |  8 ++++++++
 3 files changed, 29 insertions(+), 2 deletions(-)

diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index de88b33c0974..dea8f17b2fe3 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -97,6 +97,7 @@ void do_trace_rcu_torture_read(const char *rcutorturename,
 			       unsigned long secs,
 			       unsigned long c_old,
 			       unsigned long c);
+bool rcu_irq_enter_disabled(void);
 #else
 static inline void rcutorture_get_gp_data(enum rcutorture_type test_type,
 					  int *flags,
@@ -113,6 +114,10 @@ static inline void rcutorture_record_test_transition(void)
 static inline void rcutorture_record_progress(unsigned long vernum)
 {
 }
+static inline bool rcu_irq_enter_disabled(void)
+{
+	return false;
+}
 #ifdef CONFIG_RCU_TRACE
 void do_trace_rcu_torture_read(const char *rcutorturename,
 			       struct rcu_head *rhp,
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 8b4d273331e4..a6dcf3bd244f 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -285,6 +285,20 @@ static DEFINE_PER_CPU(struct rcu_dynticks, rcu_dynticks) = {
 };
 
 /*
+ * There's a few places, currently just in the tracing infrastructure,
+ * that uses rcu_irq_enter() to make sure RCU is watching. But there's
+ * a small location where that will not even work. In those cases
+ * rcu_irq_enter_disabled() needs to be checked to make sure rcu_irq_enter()
+ * can be called.
+ */
+static DEFINE_PER_CPU(bool, disable_rcu_irq_enter);
+
+bool rcu_irq_enter_disabled(void)
+{
+	return this_cpu_read(disable_rcu_irq_enter);
+}
+
+/*
  * Record entry into an extended quiescent state.  This is only to be
  * called when not already in an extended quiescent state.
  */
@@ -800,10 +814,10 @@ static void rcu_eqs_enter_common(bool user)
 		do_nocb_deferred_wakeup(rdp);
 	}
 	rcu_prepare_for_idle();
-	stack_tracer_disable();
+	__this_cpu_inc(disable_rcu_irq_enter);
 	rdtp->dynticks_nesting = 0; /* Breaks tracing momentarily. */
 	rcu_dynticks_eqs_enter(); /* After this, tracing works again. */
-	stack_tracer_enable();
+	__this_cpu_dec(disable_rcu_irq_enter);
 	rcu_dynticks_task_enter();
 
 	/*
diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c
index f2f02ff350d4..76aa04d4c925 100644
--- a/kernel/trace/trace_stack.c
+++ b/kernel/trace/trace_stack.c
@@ -96,6 +96,14 @@ check_stack(unsigned long ip, unsigned long *stack)
 	if (in_nmi())
 		return;
 
+	/*
+	 * There's a slight chance that we are tracing inside the
+	 * RCU infrastructure, and rcu_irq_enter() will not work
+	 * as expected.
+	 */
+	if (unlikely(rcu_irq_enter_disabled()))
+		return;
+
 	local_irq_save(flags);
 	arch_spin_lock(&stack_trace_max_lock);
 
-- 
2.10.2

[toc] | [prev] | [next] | [standalone]

#1620590 — [PATCH 4/7 v3] tracing: Rename trace_active to disable_stack_tracer and inline its modification

From: "Steven Rostedt (VMware)" <rostedt@goodmis.org>

In order to eliminate a function call, make "trace_active" into
"disable_stack_tracer" and convert stack_tracer_disable() and friends into
static inline functions.

Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 include/linux/ftrace.h     | 36 +++++++++++++++++++++++++++++++--
 kernel/trace/trace_stack.c | 50 +++++++++-------------------------------------
 2 files changed, 43 insertions(+), 43 deletions(-)

diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index 7b4e6572ab21..06b2990a35e4 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -287,8 +287,40 @@ stack_trace_sysctl(struct ctl_table *table, int write,
 		   void __user *buffer, size_t *lenp,
 		   loff_t *ppos);
 
-void stack_tracer_disable(void);
-void stack_tracer_enable(void);
+/* DO NOT MODIFY THIS VARIABLE DIRECTLY! */
+DECLARE_PER_CPU(int, disable_stack_tracer);
+
+/**
+ * stack_tracer_disable - temporarily disable the stack tracer
+ *
+ * There's a few locations (namely in RCU) where stack tracing
+ * cannot be executed. This function is used to disable stack
+ * tracing during those critical sections.
+ *
+ * This function must be called with preemption or interrupts
+ * disabled and stack_tracer_enable() must be called shortly after
+ * while preemption or interrupts are still disabled.
+ */
+static inline void stack_tracer_disable(void)
+{
+	/* Preemption or interupts must be disabled */
+	if (IS_ENABLED(CONFIG_PREEMPT_DEBUG))
+		WARN_ON_ONCE(!preempt_count() || !irqs_disabled());
+	this_cpu_inc(disable_stack_tracer);
+}
+
+/**
+ * stack_tracer_enable - re-enable the stack tracer
+ *
+ * After stack_tracer_disable() is called, stack_tracer_enable()
+ * must be called shortly afterward.
+ */
+static inline void stack_tracer_enable(void)
+{
+	if (IS_ENABLED(CONFIG_PREEMPT_DEBUG))
+		WARN_ON_ONCE(!preempt_count() || !irqs_disabled());
+	this_cpu_dec(disable_stack_tracer);
+}
 #else
 static inline void stack_tracer_disable(void) { }
 static inline void stack_tracer_enable(void) { }
diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c
index 21e536cf66e4..f2f02ff350d4 100644
--- a/kernel/trace/trace_stack.c
+++ b/kernel/trace/trace_stack.c
@@ -35,44 +35,12 @@ unsigned long stack_trace_max_size;
 arch_spinlock_t stack_trace_max_lock =
 	(arch_spinlock_t)__ARCH_SPIN_LOCK_UNLOCKED;
 
-static DEFINE_PER_CPU(int, trace_active);
+DEFINE_PER_CPU(int, disable_stack_tracer);
 static DEFINE_MUTEX(stack_sysctl_mutex);
 
 int stack_tracer_enabled;
 static int last_stack_tracer_enabled;
 
-/**
- * stack_tracer_disable - temporarily disable the stack tracer
- *
- * There's a few locations (namely in RCU) where stack tracing
- * cannot be executed. This function is used to disable stack
- * tracing during those critical sections.
- *
- * This function must be called with preemption or interrupts
- * disabled and stack_tracer_enable() must be called shortly after
- * while preemption or interrupts are still disabled.
- */
-void stack_tracer_disable(void)
-{
-	/* Preemption or interupts must be disabled */
-	if (IS_ENABLED(CONFIG_PREEMPT_DEBUG))
-		WARN_ON_ONCE(!preempt_count() || !irqs_disabled());
-	this_cpu_inc(trace_active);
-}
-
-/**
- * stack_tracer_enable - re-enable the stack tracer
- *
- * After stack_tracer_disable() is called, stack_tracer_enable()
- * must be called shortly afterward.
- */
-void stack_tracer_enable(void)
-{
-	if (IS_ENABLED(CONFIG_PREEMPT_DEBUG))
-		WARN_ON_ONCE(!preempt_count() || !irqs_disabled());
-	this_cpu_dec(trace_active);
-}
-
 void stack_trace_print(void)
 {
 	long i;
@@ -243,8 +211,8 @@ stack_trace_call(unsigned long ip, unsigned long parent_ip,
 	preempt_disable_notrace();
 
 	/* no atomic needed, we only modify this variable by this cpu */
-	__this_cpu_inc(trace_active);
-	if (__this_cpu_read(trace_active) != 1)
+	__this_cpu_inc(disable_stack_tracer);
+	if (__this_cpu_read(disable_stack_tracer) != 1)
 		goto out;
 
 	ip += MCOUNT_INSN_SIZE;
@@ -252,7 +220,7 @@ stack_trace_call(unsigned long ip, unsigned long parent_ip,
 	check_stack(ip, &stack);
 
  out:
-	__this_cpu_dec(trace_active);
+	__this_cpu_dec(disable_stack_tracer);
 	/* prevent recursion in schedule */
 	preempt_enable_notrace();
 }
@@ -294,15 +262,15 @@ stack_max_size_write(struct file *filp, const char __user *ubuf,
 	/*
 	 * In case we trace inside arch_spin_lock() or after (NMI),
 	 * we will cause circular lock, so we also need to increase
-	 * the percpu trace_active here.
+	 * the percpu disable_stack_tracer here.
 	 */
-	__this_cpu_inc(trace_active);
+	__this_cpu_inc(disable_stack_tracer);
 
 	arch_spin_lock(&stack_trace_max_lock);
 	*ptr = val;
 	arch_spin_unlock(&stack_trace_max_lock);
 
-	__this_cpu_dec(trace_active);
+	__this_cpu_dec(disable_stack_tracer);
 	local_irq_restore(flags);
 
 	return count;
@@ -338,7 +306,7 @@ static void *t_start(struct seq_file *m, loff_t *pos)
 {
 	local_irq_disable();
 
-	__this_cpu_inc(trace_active);
+	__this_cpu_inc(disable_stack_tracer);
 
 	arch_spin_lock(&stack_trace_max_lock);
 
@@ -352,7 +320,7 @@ static void t_stop(struct seq_file *m, void *p)
 {
 	arch_spin_unlock(&stack_trace_max_lock);
 
-	__this_cpu_dec(trace_active);
+	__this_cpu_dec(disable_stack_tracer);
 
 	local_irq_enable();
 }
-- 
2.10.2

[toc] | [prev] | [next] | [standalone]

#1620606 — Re: [PATCH 4/7 v3] tracing: Rename trace_active to disable_stack_tracer and inline its modification

On Mon, Apr 10, 2017 at 02:10:09PM -0400, Steven Rostedt wrote:
> From: "Steven Rostedt (VMware)" <rostedt@goodmis.org>
> 
> In order to eliminate a function call, make "trace_active" into
> "disable_stack_tracer" and convert stack_tracer_disable() and friends into
> static inline functions.
> 
> Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>

Acked-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>

> ---
>  include/linux/ftrace.h     | 36 +++++++++++++++++++++++++++++++--
>  kernel/trace/trace_stack.c | 50 +++++++++-------------------------------------
>  2 files changed, 43 insertions(+), 43 deletions(-)
> 
> diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
> index 7b4e6572ab21..06b2990a35e4 100644
> --- a/include/linux/ftrace.h
> +++ b/include/linux/ftrace.h
> @@ -287,8 +287,40 @@ stack_trace_sysctl(struct ctl_table *table, int write,
>  		   void __user *buffer, size_t *lenp,
>  		   loff_t *ppos);
> 
> -void stack_tracer_disable(void);
> -void stack_tracer_enable(void);
> +/* DO NOT MODIFY THIS VARIABLE DIRECTLY! */
> +DECLARE_PER_CPU(int, disable_stack_tracer);
> +
> +/**
> + * stack_tracer_disable - temporarily disable the stack tracer
> + *
> + * There's a few locations (namely in RCU) where stack tracing
> + * cannot be executed. This function is used to disable stack
> + * tracing during those critical sections.
> + *
> + * This function must be called with preemption or interrupts
> + * disabled and stack_tracer_enable() must be called shortly after
> + * while preemption or interrupts are still disabled.
> + */
> +static inline void stack_tracer_disable(void)
> +{
> +	/* Preemption or interupts must be disabled */
> +	if (IS_ENABLED(CONFIG_PREEMPT_DEBUG))
> +		WARN_ON_ONCE(!preempt_count() || !irqs_disabled());
> +	this_cpu_inc(disable_stack_tracer);
> +}
> +
> +/**
> + * stack_tracer_enable - re-enable the stack tracer
> + *
> + * After stack_tracer_disable() is called, stack_tracer_enable()
> + * must be called shortly afterward.
> + */
> +static inline void stack_tracer_enable(void)
> +{
> +	if (IS_ENABLED(CONFIG_PREEMPT_DEBUG))
> +		WARN_ON_ONCE(!preempt_count() || !irqs_disabled());
> +	this_cpu_dec(disable_stack_tracer);
> +}
>  #else
>  static inline void stack_tracer_disable(void) { }
>  static inline void stack_tracer_enable(void) { }
> diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c
> index 21e536cf66e4..f2f02ff350d4 100644
> --- a/kernel/trace/trace_stack.c
> +++ b/kernel/trace/trace_stack.c
> @@ -35,44 +35,12 @@ unsigned long stack_trace_max_size;
>  arch_spinlock_t stack_trace_max_lock =
>  	(arch_spinlock_t)__ARCH_SPIN_LOCK_UNLOCKED;
> 
> -static DEFINE_PER_CPU(int, trace_active);
> +DEFINE_PER_CPU(int, disable_stack_tracer);
>  static DEFINE_MUTEX(stack_sysctl_mutex);
> 
>  int stack_tracer_enabled;
>  static int last_stack_tracer_enabled;
> 
> -/**
> - * stack_tracer_disable - temporarily disable the stack tracer
> - *
> - * There's a few locations (namely in RCU) where stack tracing
> - * cannot be executed. This function is used to disable stack
> - * tracing during those critical sections.
> - *
> - * This function must be called with preemption or interrupts
> - * disabled and stack_tracer_enable() must be called shortly after
> - * while preemption or interrupts are still disabled.
> - */
> -void stack_tracer_disable(void)
> -{
> -	/* Preemption or interupts must be disabled */
> -	if (IS_ENABLED(CONFIG_PREEMPT_DEBUG))
> -		WARN_ON_ONCE(!preempt_count() || !irqs_disabled());
> -	this_cpu_inc(trace_active);
> -}
> -
> -/**
> - * stack_tracer_enable - re-enable the stack tracer
> - *
> - * After stack_tracer_disable() is called, stack_tracer_enable()
> - * must be called shortly afterward.
> - */
> -void stack_tracer_enable(void)
> -{
> -	if (IS_ENABLED(CONFIG_PREEMPT_DEBUG))
> -		WARN_ON_ONCE(!preempt_count() || !irqs_disabled());
> -	this_cpu_dec(trace_active);
> -}
> -
>  void stack_trace_print(void)
>  {
>  	long i;
> @@ -243,8 +211,8 @@ stack_trace_call(unsigned long ip, unsigned long parent_ip,
>  	preempt_disable_notrace();
> 
>  	/* no atomic needed, we only modify this variable by this cpu */
> -	__this_cpu_inc(trace_active);
> -	if (__this_cpu_read(trace_active) != 1)
> +	__this_cpu_inc(disable_stack_tracer);
> +	if (__this_cpu_read(disable_stack_tracer) != 1)
>  		goto out;
> 
>  	ip += MCOUNT_INSN_SIZE;
> @@ -252,7 +220,7 @@ stack_trace_call(unsigned long ip, unsigned long parent_ip,
>  	check_stack(ip, &stack);
> 
>   out:
> -	__this_cpu_dec(trace_active);
> +	__this_cpu_dec(disable_stack_tracer);
>  	/* prevent recursion in schedule */
>  	preempt_enable_notrace();
>  }
> @@ -294,15 +262,15 @@ stack_max_size_write(struct file *filp, const char __user *ubuf,
>  	/*
>  	 * In case we trace inside arch_spin_lock() or after (NMI),
>  	 * we will cause circular lock, so we also need to increase
> -	 * the percpu trace_active here.
> +	 * the percpu disable_stack_tracer here.
>  	 */
> -	__this_cpu_inc(trace_active);
> +	__this_cpu_inc(disable_stack_tracer);
> 
>  	arch_spin_lock(&stack_trace_max_lock);
>  	*ptr = val;
>  	arch_spin_unlock(&stack_trace_max_lock);
> 
> -	__this_cpu_dec(trace_active);
> +	__this_cpu_dec(disable_stack_tracer);
>  	local_irq_restore(flags);
> 
>  	return count;
> @@ -338,7 +306,7 @@ static void *t_start(struct seq_file *m, loff_t *pos)
>  {
>  	local_irq_disable();
> 
> -	__this_cpu_inc(trace_active);
> +	__this_cpu_inc(disable_stack_tracer);
> 
>  	arch_spin_lock(&stack_trace_max_lock);
> 
> @@ -352,7 +320,7 @@ static void t_stop(struct seq_file *m, void *p)
>  {
>  	arch_spin_unlock(&stack_trace_max_lock);
> 
> -	__this_cpu_dec(trace_active);
> +	__this_cpu_dec(disable_stack_tracer);
> 
>  	local_irq_enable();
>  }
> -- 
> 2.10.2
> 
> 

[toc] | [prev] | [next] | [standalone]

#1620593 — [PATCH 5/7 v3] rcu: Fix dyntick-idle tracing

From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>

The tracing subsystem started using rcu_irq_entry() and rcu_irq_exit()
(with my blessing) to allow the current _rcuidle alternative tracepoint
name to be dispensed with while still maintaining good performance.
Unfortunately, this causes RCU's dyntick-idle entry code's tracing to
appear to RCU like an interrupt that occurs where RCU is not designed
to handle interrupts.

This commit fixes this problem by moving the zeroing of ->dynticks_nesting
after the offending trace_rcu_dyntick() statement, which narrows the
window of vulnerability to a pair of adjacent statements that are now
marked with comments to that effect.

Link: http://lkml.kernel.org/r/20170405093207.404f8deb@gandalf.local.home
Link: http://lkml.kernel.org/r/20170405193928.GM1600@linux.vnet.ibm.com

Reported-by: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 kernel/rcu/tree.c | 48 +++++++++++++++++++++++-------------------------
 1 file changed, 23 insertions(+), 25 deletions(-)

diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 50fee7689e71..8b4d273331e4 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -57,6 +57,7 @@
 #include <linux/random.h>
 #include <linux/trace_events.h>
 #include <linux/suspend.h>
+#include <linux/ftrace.h>
 
 #include "tree.h"
 #include "rcu.h"
@@ -771,25 +772,24 @@ cpu_needs_another_gp(struct rcu_state *rsp, struct rcu_data *rdp)
 }
 
 /*
- * rcu_eqs_enter_common - current CPU is moving towards extended quiescent state
+ * rcu_eqs_enter_common - current CPU is entering an extended quiescent state
  *
- * If the new value of the ->dynticks_nesting counter now is zero,
- * we really have entered idle, and must do the appropriate accounting.
- * The caller must have disabled interrupts.
+ * Enter idle, doing appropriate accounting.  The caller must have
+ * disabled interrupts.
  */
-static void rcu_eqs_enter_common(long long oldval, bool user)
+static void rcu_eqs_enter_common(bool user)
 {
 	struct rcu_state *rsp;
 	struct rcu_data *rdp;
-	RCU_TRACE(struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks);)
+	struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks);
 
-	trace_rcu_dyntick(TPS("Start"), oldval, rdtp->dynticks_nesting);
+	trace_rcu_dyntick(TPS("Start"), rdtp->dynticks_nesting, 0);
 	if (IS_ENABLED(CONFIG_RCU_EQS_DEBUG) &&
 	    !user && !is_idle_task(current)) {
 		struct task_struct *idle __maybe_unused =
 			idle_task(smp_processor_id());
 
-		trace_rcu_dyntick(TPS("Error on entry: not idle task"), oldval, 0);
+		trace_rcu_dyntick(TPS("Error on entry: not idle task"), rdtp->dynticks_nesting, 0);
 		rcu_ftrace_dump(DUMP_ORIG);
 		WARN_ONCE(1, "Current pid: %d comm: %s / Idle pid: %d comm: %s",
 			  current->pid, current->comm,
@@ -800,7 +800,10 @@ static void rcu_eqs_enter_common(long long oldval, bool user)
 		do_nocb_deferred_wakeup(rdp);
 	}
 	rcu_prepare_for_idle();
-	rcu_dynticks_eqs_enter();
+	stack_tracer_disable();
+	rdtp->dynticks_nesting = 0; /* Breaks tracing momentarily. */
+	rcu_dynticks_eqs_enter(); /* After this, tracing works again. */
+	stack_tracer_enable();
 	rcu_dynticks_task_enter();
 
 	/*
@@ -821,19 +824,15 @@ static void rcu_eqs_enter_common(long long oldval, bool user)
  */
 static void rcu_eqs_enter(bool user)
 {
-	long long oldval;
 	struct rcu_dynticks *rdtp;
 
 	rdtp = this_cpu_ptr(&rcu_dynticks);
-	oldval = rdtp->dynticks_nesting;
 	WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) &&
-		     (oldval & DYNTICK_TASK_NEST_MASK) == 0);
-	if ((oldval & DYNTICK_TASK_NEST_MASK) == DYNTICK_TASK_NEST_VALUE) {
-		rdtp->dynticks_nesting = 0;
-		rcu_eqs_enter_common(oldval, user);
-	} else {
+		     (rdtp->dynticks_nesting & DYNTICK_TASK_NEST_MASK) == 0);
+	if ((rdtp->dynticks_nesting & DYNTICK_TASK_NEST_MASK) == DYNTICK_TASK_NEST_VALUE)
+		rcu_eqs_enter_common(user);
+	else
 		rdtp->dynticks_nesting -= DYNTICK_TASK_NEST_VALUE;
-	}
 }
 
 /**
@@ -892,19 +891,18 @@ void rcu_user_enter(void)
  */
 void rcu_irq_exit(void)
 {
-	long long oldval;
 	struct rcu_dynticks *rdtp;
 
 	RCU_LOCKDEP_WARN(!irqs_disabled(), "rcu_irq_exit() invoked with irqs enabled!!!");
 	rdtp = this_cpu_ptr(&rcu_dynticks);
-	oldval = rdtp->dynticks_nesting;
-	rdtp->dynticks_nesting--;
 	WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) &&
-		     rdtp->dynticks_nesting < 0);
-	if (rdtp->dynticks_nesting)
-		trace_rcu_dyntick(TPS("--="), oldval, rdtp->dynticks_nesting);
-	else
-		rcu_eqs_enter_common(oldval, true);
+		     rdtp->dynticks_nesting < 1);
+	if (rdtp->dynticks_nesting <= 1) {
+		rcu_eqs_enter_common(true);
+	} else {
+		trace_rcu_dyntick(TPS("--="), rdtp->dynticks_nesting, rdtp->dynticks_nesting - 1);
+		rdtp->dynticks_nesting--;
+	}
 	rcu_sysidle_enter(1);
 }
 
-- 
2.10.2

[toc] | [prev] | [standalone]

Back to top | Article view | linux.kernel

csiph-web