tracing: Stack tracing and rcu modification updates

58 lines not on this page · raw message

index 5fb1f2c87e6b..338d076a06da 100644
@@ -207,13 +207,12 @@ stack_trace_call(unsigned long ip, unsigned long parent_ip,
 		 struct ftrace_ops *op, struct pt_regs *pt_regs)
 {
 	unsigned long stack;
-	int cpu;
 
 	preempt_disable_notrace();
 
-	cpu = raw_smp_processor_id();
 	/* no atomic needed, we only modify this variable by this cpu */
-	if (per_cpu(trace_active, cpu)++ != 0)
+	__this_cpu_inc(trace_active);
+	if (__this_cpu_read(trace_active) != 1)
 		goto out;
 
 	ip += MCOUNT_INSN_SIZE;

@@ -221,7 +220,7 @@ stack_trace_call(unsigned long ip, unsigned long parent_ip,
 	check_stack(ip, &stack);
 
  out:
-	per_cpu(trace_active, cpu)--;
+	__this_cpu_dec(trace_active);
 	/* prevent recursion in schedule */
 	preempt_enable_notrace();
 }

@@ -253,7 +252,6 @@ stack_max_size_write(struct file *filp, const char __user *ubuf,
 	long *ptr = filp->private_data;
 	unsigned long val, flags;
 	int ret;
-	int cpu;
 
 	ret = kstrtoul_from_user(ubuf, count, 10, &val);
 	if (ret)

@@ -266,14 +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 trace_active here.
 	 */
-	cpu = smp_processor_id();
-	per_cpu(trace_active, cpu)++;
+	__this_cpu_inc(trace_active);
 
 	arch_spin_lock(&stack_trace_max_lock);
 	*ptr = val;
 	arch_spin_unlock(&stack_trace_max_lock);
 
-	per_cpu(trace_active, cpu)--;
+	__this_cpu_dec(trace_active);
 	local_irq_restore(flags);
 
 	return count;

@@ -307,12 +304,9 @@ t_next(struct seq_file *m, void *v, loff_t *pos)
 
 static void *t_start(struct seq_file *m, loff_t *pos)
 {
-	int cpu;
-
 	local_irq_disable();
 
-	cpu = smp_processor_id();
-	per_cpu(trace_active, cpu)++;
+	__this_cpu_inc(trace_active);
 
 	arch_spin_lock(&stack_trace_max_lock);
 

@@ -324,12 +318,9 @@ static void *t_start(struct seq_file *m, loff_t *pos)
 
 static void t_stop(struct seq_file *m, void *p)
 {
-	int cpu;
-
 	arch_spin_unlock(&stack_trace_max_lock);
 
-	cpu = smp_processor_id();
-	per_cpu(trace_active, cpu)--;
+	__this_cpu_dec(trace_active);
 
 	local_irq_enable();
 }

index ef7123219f14..7b4e6572ab21 100644
@@ -286,6 +286,12 @@ int
 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);
+#else
+static inline void stack_tracer_disable(void) { }
+static inline void stack_tracer_enable(void) { }
 #endif
 
 struct ftrace_func_command {

index 338d076a06da..21e536cf66e4 100644
@@ -41,6 +41,38 @@ 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;

index 7b4e6572ab21..06b2990a35e4 100644
@@ -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) { }

97 lines not on this page · raw message

index 50fee7689e71..8b4d273331e4 100644
@@ -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);
 }
 

index de88b33c0974..dea8f17b2fe3 100644
@@ -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,

index 8b4d273331e4..a6dcf3bd244f 100644
@@ -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();
 
 	/*

index f2f02ff350d4..76aa04d4c925 100644
@@ -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);
 

index f72fcfe0e66a..cc48cb2ce209 100644
@@ -128,7 +128,7 @@ extern void syscall_unregfunc(void);
  * as "(void *, void)". The DECLARE_TRACE_NOARGS() will pass in just
  * "void *data", where as the DECLARE_TRACE() will pass in "void *data, proto".
  */
-#define __DO_TRACE(tp, proto, args, cond, prercu, postrcu)		\
+#define __DO_TRACE(tp, proto, args, cond, rcucheck)			\
 	do {								\
 		struct tracepoint_func *it_func_ptr;			\
 		void *it_func;						\

@@ -136,7 +136,11 @@ extern void syscall_unregfunc(void);
 									\
 		if (!(cond))						\
 			return;						\
-		prercu;							\
+		if (rcucheck) {						\
+			if (WARN_ON_ONCE(rcu_irq_enter_disabled()))	\
+				return;					\
+			rcu_irq_enter_irqson();				\
+		}							\
 		rcu_read_lock_sched_notrace();				\
 		it_func_ptr = rcu_dereference_sched((tp)->funcs);	\
 		if (it_func_ptr) {					\

@@ -147,20 +151,19 @@ extern void syscall_unregfunc(void);
 			} while ((++it_func_ptr)->func);		\
 		}							\
 		rcu_read_unlock_sched_notrace();			\
-		postrcu;						\
+		if (rcucheck)						\
+			rcu_irq_exit_irqson();				\
 	} while (0)
 
 #ifndef MODULE
-#define __DECLARE_TRACE_RCU(name, proto, args, cond, data_proto, data_args)	\
+#define __DECLARE_TRACE_RCU(name, proto, args, cond, data_proto, data_args) \
 	static inline void trace_##name##_rcuidle(proto)		\
 	{								\
 		if (static_key_false(&__tracepoint_##name.key))		\
 			__DO_TRACE(&__tracepoint_##name,		\
 				TP_PROTO(data_proto),			\
 				TP_ARGS(data_args),			\
-				TP_CONDITION(cond),			\
-				rcu_irq_enter_irqson(),			\
-				rcu_irq_exit_irqson());			\
+				TP_CONDITION(cond), 1);			\
 	}
 #else
 #define __DECLARE_TRACE_RCU(name, proto, args, cond, data_proto, data_args)

@@ -186,7 +189,7 @@ extern void syscall_unregfunc(void);
 			__DO_TRACE(&__tracepoint_##name,		\
 				TP_PROTO(data_proto),			\
 				TP_ARGS(data_args),			\
-				TP_CONDITION(cond),,);			\
+				TP_CONDITION(cond), 0);			\
 		if (IS_ENABLED(CONFIG_LOCKDEP) && (cond)) {		\
 			rcu_read_lock_sched_notrace();			\
 			rcu_dereference_sched(__tracepoint_##name.funcs);\