Skip to contentSkip to conversation

Some new features for the preempt/irqsoff tracers

PATCH Superseded Viktor Rosendahl 6 participants 19 messages Sep 3, 2019 – Sep 5, 2019

Subsystems (5)
Tracing Scheduler ftrace Printk +1 more subsystems

v5 of 10 Superseded Latest is v10 →

lore
Share & tools
lore
#0 lore raw

v5 cover Some new features for the preempt/irqsoff tracers

Hello all,

Changes in v5:
- [PATCH 1/4]:
* trace_disable_fsnotify() => latency_fsnotify_disable(), in order to avoid naming conflicts with trace points.

* Using more appropriate operations for the percpu variables.

* Moved around the calls to latency_fsnotify_enable/disable() a bit.

* Added static branches to reduce overhead when the facility is not in use.

* Does not add any trace points anymore. Instead using explicit function calls from sched and idle code.

* Unfortunately still adds some gunk to sched and idle code. I do not know how to avoid this.

This series is meant to address two issues with the latency tracing.

The first three patches provide a method to trace latencies that always occurs very close to each other and to differentiate between them, in spite of the fact that the latency tracers work in overwrite mode.

[PATCH 1/4] This implement fs notification for tracing_max_latency. It makes it possible for userspace to detect when a new latency has been detected.

[PATCH 2/4] This extends the preemptirq_delay_test module so that it can be used to generate a burst of closely occurring latencies.

[PATCH 3/4] This adds a user space program to the tools directory that utilizes the fs notification feature and a randomized algorithm to print out any of the latencies in a burst with approximately equal probability.

The last patch is not directly connected but earlier it didn't apply cleanly on its own. However, now it does, so in principle it could be applied separately from the others.

[PATCH 4/4] This adds the option console-latency to the trace options. This makes it possible to enable tracing of console latencies.

best regards,

Viktor

Viktor Rosendahl (4):
ftrace: Implement fs notification for tracing_max_latency
preemptirq_delay_test: Add the burst feature and a sysfs trigger Add the latency-collector to tools
ftrace: Add an option for tracing console latencies

 include/linux/ftrace.h               |   31 +
 include/linux/irqflags.h             |   21 +
 kernel/printk/printk.c               |    6 +-
 kernel/sched/core.c                  |    3 +
 kernel/sched/idle.c                  |    3 +
 kernel/sched/sched.h                 |    1 +
 kernel/trace/Kconfig                 |    6 +-
 kernel/trace/preemptirq_delay_test.c |  145 ++-
 kernel/trace/trace.c                 |  112 ++-
 kernel/trace/trace.h                 |   23 +
 kernel/trace/trace_hwlat.c           |    4 +-
 kernel/trace/trace_irqsoff.c         |   16 +
 kernel/trace/trace_sched_wakeup.c    |    4 +
 tools/Makefile                       |   14 +-
 tools/trace/Makefile                 |   20 +
 tools/trace/latency-collector.c      | 1211 ++++++++++++++++++++++++++
 16 files changed, 1587 insertions(+), 33 deletions(-)
 create mode 100644 tools/trace/Makefile
 create mode 100644 tools/trace/latency-collector.c
Signature · 1 line
2.17.1
#1 lore raw

PATCH v5 1/4 ftrace: Implement fs notification for tracing_max_latency

This patch implements the feature that the tracing_max_latency file, e.g. /sys/kernel/debug/tracing/tracing_max_latency will receive notifications through the fsnotify framework when a new latency is available.

One particularly interesting use of this facility is when enabling threshold tracing, through /sys/kernel/debug/tracing/tracing_thresh, together with the preempt/irqsoff tracers. This makes it possible to implement a user space program that can, with equal probability, obtain traces of latencies that occur immediately after each other in spite of the fact that the preempt/irqsoff tracers operate in overwrite mode.

This facility works with the hwlat, preempt/irqsoff, and wakeup tracers.

This patch also adds some unfortunate calls from __schedule() and do_idle(). Those calls to the latency_fsnotify_disable/enable() are needed because we cannot wake up the workqueue from these critical sections without risking a deadlock. Similar problems would also arise if we try to schedule a tasklet, raise a softirq, or wake up a kernel thread. If a notification event would happen in the forbidden sections, we schedule the fsnotify work as soon as we have exited them.

There was a suggestion to remove this latency_fsnotify_enable/disable() gunk, or at least to combine it with the start_critical_timings() and stop_critical_timings(). I have however not been able to come up with a way to do it.

It seems like it would be possible to simply replace the calls to latency_fsnotify_enable/disable() with calls to start/stop_critical_timings(). However, the main problem is that it would not work for the wakup tracer. The wakeup tracer needs a facility that postpones the notifications, not one that prevents the measurements because all its measurements takes place in the middle of __schedule(). On the other hand, in some places, like in idle and the console we need start stop functions that prevents the measurements from being make.

---
 include/linux/ftrace.h            |  31 +++++++++
 kernel/sched/core.c               |   3 +
 kernel/sched/idle.c               |   3 +
 kernel/sched/sched.h              |   1 +
 kernel/trace/trace.c              | 112 +++++++++++++++++++++++++++++-
 kernel/trace/trace.h              |  22 ++++++
 kernel/trace/trace_hwlat.c        |   4 +-
 kernel/trace/trace_irqsoff.c      |   4 ++
 kernel/trace/trace_sched_wakeup.c |   4 ++
 9 files changed, 181 insertions(+), 3 deletions(-)
include/linux/ftrace.h +31 -0
index 8a8cb3c401b2..b4d9700ef917 100644
@@ -907,4 +907,35 @@ unsigned long arch_syscall_addr(int nr);
 
 #endif /* CONFIG_FTRACE_SYSCALLS */
 
+#if (defined(CONFIG_TRACER_MAX_TRACE) || defined(CONFIG_HWLAT_TRACER)) && \
+	defined(CONFIG_FSNOTIFY)
+
+DECLARE_PER_CPU(int, latency_notify_disable);
+DECLARE_STATIC_KEY_FALSE(latency_notify_key);
+
+void latency_fsnotify_process(void);
+
+/*
+ * Disable/enable fsnotify while in scheduler and idle code. Trying to wake
+ * anything up from there, such as calling queue_work() is prone to deadlock.
+ */
+static inline void latency_fsnotify_disable(void)
+{
+	this_cpu_inc(latency_notify_disable);
+}
+
+static inline void latency_fsnotify_enable(void)
+{
+	this_cpu_dec(latency_notify_disable);
+	if (static_branch_unlikely(&latency_notify_key))
+		latency_fsnotify_process();
+}
+
+#else
+
+#define latency_fsnotify_disable() do { } while (0)
+#define latency_fsnotify_enable()  do { } while (0)
+
+#endif
+
 #endif /* _LINUX_FTRACE_H */
kernel/sched/core.c +3 -0
index 010d578118d6..e3c1dc801073 100644
@@ -3198,6 +3198,7 @@ asmlinkage __visible void schedule_tail(struct task_struct *prev)
 	 */
 
 	rq = finish_task_switch(prev);
+	latency_fsnotify_enable();
 	balance_callback(rq);
 	preempt_enable();
 
@@ -3820,6 +3821,7 @@ static void __sched notrace __schedule(bool preempt)
 
 	local_irq_disable();
 	rcu_note_context_switch(preempt);
+	latency_fsnotify_disable();
 
 	/*
 	 * Make sure that signal_pending_state()->signal_pending() below
@@ -3883,6 +3885,7 @@ static void __sched notrace __schedule(bool preempt)
 		rq_unlock_irq(rq, &rf);
 	}
 
+	latency_fsnotify_enable();
 	balance_callback(rq);
 }
 
kernel/sched/idle.c +3 -0
index 80940939b733..5fc87d99a407 100644
@@ -236,6 +236,7 @@ static void do_idle(void)
 
 	__current_set_polling();
 	tick_nohz_idle_enter();
+	latency_fsnotify_disable();
 
 	while (!need_resched()) {
 		check_pgt_cache();
@@ -265,6 +266,8 @@ static void do_idle(void)
 		arch_cpu_idle_exit();
 	}
 
+	latency_fsnotify_enable();
+
 	/*
 	 * Since we fell out of the loop above, we know TIF_NEED_RESCHED must
 	 * be set, propagate it into PREEMPT_NEED_RESCHED.
kernel/sched/sched.h +1 -0
index 802b1f3405f2..467d6ad03f16 100644
@@ -46,6 +46,7 @@
 #include <linux/debugfs.h>
 #include <linux/delayacct.h>
 #include <linux/energy_model.h>
+#include <linux/ftrace.h>
 #include <linux/init_task.h>
 #include <linux/kprobes.h>
 #include <linux/kthread.h>
kernel/trace/trace.c +110 -2

136 lines not on this page · raw message

kernel/trace/trace.h +22 -0
index 005f08629b8b..d9f83b2aaa71 100644
@@ -16,6 +16,7 @@
 #include <linux/trace_events.h>
 #include <linux/compiler.h>
 #include <linux/glob.h>
+#include <linux/workqueue.h>
 
 #ifdef CONFIG_FTRACE_SYSCALLS
 #include <asm/unistd.h>		/* For NR_SYSCALLS	     */
@@ -264,6 +265,12 @@ struct trace_array {
 #endif
 #if defined(CONFIG_TRACER_MAX_TRACE) || defined(CONFIG_HWLAT_TRACER)
 	unsigned long		max_latency;
+#ifdef CONFIG_FSNOTIFY
+	struct dentry		*d_max_latency;
+	struct work_struct	fsnotify_work;
+	atomic_t		notify_pending;
+	struct llist_node	notify_ll;
+#endif
 #endif
 	struct trace_pid_list	__rcu *filtered_pids;
 	/*
@@ -785,6 +792,21 @@ void update_max_tr_single(struct trace_array *tr,
 			  struct task_struct *tsk, int cpu);
 #endif /* CONFIG_TRACER_MAX_TRACE */
 
+#if (defined(CONFIG_TRACER_MAX_TRACE) || defined(CONFIG_HWLAT_TRACER)) && \
+	defined(CONFIG_FSNOTIFY)
+
+void latency_fsnotify(struct trace_array *tr);
+void latency_fsnotify_start(void);
+void latency_fsnotify_stop(void);
+
+#else
+
+#define latency_fsnotify(tr)     do { } while (0)
+#define latency_fsnotify_start() do { } while (0)
+#define latency_fsnotify_stop()  do { } while (0)
+
+#endif
+
 #ifdef CONFIG_STACKTRACE
 void __trace_stack(struct trace_array *tr, unsigned long flags, int skip,
 		   int pc);
kernel/trace/trace_hwlat.c +3 -1
index fa95139445b2..9c379261ee89 100644
@@ -254,8 +254,10 @@ static int get_sample(void)
 		trace_hwlat_sample(&s);
 
 		/* Keep a running maximum ever recorded hardware latency */
-		if (sample > tr->max_latency)
+		if (sample > tr->max_latency) {
 			tr->max_latency = sample;
+			latency_fsnotify(tr);
+		}
 	}
 
 out:
kernel/trace/trace_irqsoff.c +4 -0
index a745b0cee5d3..29403a83a5f0 100644
@@ -557,6 +557,7 @@ static int __irqsoff_tracer_init(struct trace_array *tr)
 	if (irqsoff_busy)
 		return -EBUSY;
 
+	latency_fsnotify_start();
 	save_flags = tr->trace_flags;
 
 	/* non overwrite screws up the latency tracers */
@@ -591,16 +592,19 @@ static void __irqsoff_tracer_reset(struct trace_array *tr)
 	ftrace_reset_array_ops(tr);
 
 	irqsoff_busy = false;
+	latency_fsnotify_stop();
 }
 
 static void irqsoff_tracer_start(struct trace_array *tr)
 {
+	latency_fsnotify_start();
 	tracer_enabled = 1;
 }
 
 static void irqsoff_tracer_stop(struct trace_array *tr)
 {
 	tracer_enabled = 0;
+	latency_fsnotify_stop();
 }
 
 #ifdef CONFIG_IRQSOFF_TRACER
kernel/trace/trace_sched_wakeup.c +4 -0
index 743b2b520d34..3dc90d9f605b 100644
@@ -669,6 +669,7 @@ static bool wakeup_busy;
 
 static int __wakeup_tracer_init(struct trace_array *tr)
 {
+	latency_fsnotify_start();
 	save_flags = tr->trace_flags;
 
 	/* non overwrite screws up the latency tracers */
@@ -727,10 +728,12 @@ static void wakeup_tracer_reset(struct trace_array *tr)
 	set_tracer_flag(tr, TRACE_ITER_OVERWRITE, overwrite_flag);
 	ftrace_reset_array_ops(tr);
 	wakeup_busy = false;
+	latency_fsnotify_stop();
 }
 
 static void wakeup_tracer_start(struct trace_array *tr)
 {
+	latency_fsnotify_start();
 	wakeup_reset(tr);
 	tracer_enabled = 1;
 }
@@ -738,6 +741,7 @@ static void wakeup_tracer_start(struct trace_array *tr)
 static void wakeup_tracer_stop(struct trace_array *tr)
 {
 	tracer_enabled = 0;
+	latency_fsnotify_stop();
 }
 
 static struct tracer wakeup_tracer __read_mostly =
Signature · 1 line
2.17.1
#2 lore raw

Re: [PATCH v5 1/4] ftrace: Implement fs notification for tracing_max_latency

[ Resending since I messed up my last email's headers! ]

Quoted 5 lines · Viktor Rosendahl

This patch implements the feature that the tracing_max_latency file, e.g. /sys/kernel/debug/tracing/tracing_max_latency will receive notifications through the fsnotify framework when a new latency is available.

Quoted 7 lines

One particularly interesting use of this facility is when enabling threshold tracing, through /sys/kernel/debug/tracing/tracing_thresh, together with the preempt/irqsoff tracers. This makes it possible to implement a user space program that can, with equal probability, obtain traces of latencies that occur immediately after each other in spite of the fact that the preempt/irqsoff tracers operate in overwrite mode.

Adding Paul since RCU faces similar situations, i.e. raising softirq risks scheduler deadlock in rcu_read_unlock_special() -- but RCU's solution is to avoid raising the softirq and instead use irq_work.

I was wondering, if we can rename __raise_softirq_irqoff() to raise_softirq_irqoff_no_wake() and call that from places where there is risk of scheduler related deadlocks. Then I think this can be used from Viktor's code. Let us discuss - what would happen if the softirq is raised, but ksoftirqd is not awakened for this latency notification path? Is this really an issue considering the softirq will execute during the next interrupt exit?

thanks,

- Joel

Quoted 415 lines

This facility works with the hwlat, preempt/irqsoff, and wakeup tracers.

This patch also adds some unfortunate calls from __schedule() and do_idle(). Those calls to the latency_fsnotify_disable/enable() are needed because we cannot wake up the workqueue from these critical sections without risking a deadlock. Similar problems would also arise if we try to schedule a tasklet, raise a softirq, or wake up a kernel thread. If a notification event would happen in the forbidden sections, we schedule the fsnotify work as soon as we have exited them.

There was a suggestion to remove this latency_fsnotify_enable/disable() gunk, or at least to combine it with the start_critical_timings() and stop_critical_timings(). I have however not been able to come up with a way to do it.

It seems like it would be possible to simply replace the calls to latency_fsnotify_enable/disable() with calls to start/stop_critical_timings(). However, the main problem is that it would not work for the wakup tracer. The wakeup tracer needs a facility that postpones the notifications, not one that prevents the measurements because all its measurements takes place in the middle of __schedule(). On the other hand, in some places, like in idle and the console we need start stop functions that prevents the measurements from being make.

---
 include/linux/ftrace.h            |  31 +++++++++
 kernel/sched/core.c               |   3 +
 kernel/sched/idle.c               |   3 +
 kernel/sched/sched.h              |   1 +
 kernel/trace/trace.c              | 112 +++++++++++++++++++++++++++++-
 kernel/trace/trace.h              |  22 ++++++
 kernel/trace/trace_hwlat.c        |   4 +-
 kernel/trace/trace_irqsoff.c      |   4 ++
 kernel/trace/trace_sched_wakeup.c |   4 ++
 9 files changed, 181 insertions(+), 3 deletions(-)
include/linux/ftrace.h +31 -0
index 8a8cb3c401b2..b4d9700ef917 100644
@@ -907,4 +907,35 @@ unsigned long arch_syscall_addr(int nr);
 
 #endif /* CONFIG_FTRACE_SYSCALLS */
 
+#if (defined(CONFIG_TRACER_MAX_TRACE) || defined(CONFIG_HWLAT_TRACER)) && \
+	defined(CONFIG_FSNOTIFY)
+
+DECLARE_PER_CPU(int, latency_notify_disable);
+DECLARE_STATIC_KEY_FALSE(latency_notify_key);
+
+void latency_fsnotify_process(void);
+
+/*
+ * Disable/enable fsnotify while in scheduler and idle code. Trying to wake
+ * anything up from there, such as calling queue_work() is prone to deadlock.
+ */
+static inline void latency_fsnotify_disable(void)
+{
+	this_cpu_inc(latency_notify_disable);
+}
+
+static inline void latency_fsnotify_enable(void)
+{
+	this_cpu_dec(latency_notify_disable);
+	if (static_branch_unlikely(&latency_notify_key))
+		latency_fsnotify_process();
+}
+
+#else
+
+#define latency_fsnotify_disable() do { } while (0)
+#define latency_fsnotify_enable()  do { } while (0)
+
+#endif
+
 #endif /* _LINUX_FTRACE_H */
kernel/sched/core.c +3 -0
index 010d578118d6..e3c1dc801073 100644
@@ -3198,6 +3198,7 @@ asmlinkage __visible void schedule_tail(struct task_struct *prev)
 	 */
 
 	rq = finish_task_switch(prev);
+	latency_fsnotify_enable();
 	balance_callback(rq);
 	preempt_enable();
 
@@ -3820,6 +3821,7 @@ static void __sched notrace __schedule(bool preempt)
 
 	local_irq_disable();
 	rcu_note_context_switch(preempt);
+	latency_fsnotify_disable();
 
 	/*
 	 * Make sure that signal_pending_state()->signal_pending() below
@@ -3883,6 +3885,7 @@ static void __sched notrace __schedule(bool preempt)
 		rq_unlock_irq(rq, &rf);
 	}
 
+	latency_fsnotify_enable();
 	balance_callback(rq);
 }
 
kernel/sched/idle.c +3 -0
index 80940939b733..5fc87d99a407 100644
@@ -236,6 +236,7 @@ static void do_idle(void)
 
 	__current_set_polling();
 	tick_nohz_idle_enter();
+	latency_fsnotify_disable();
 
 	while (!need_resched()) {
 		check_pgt_cache();
@@ -265,6 +266,8 @@ static void do_idle(void)
 		arch_cpu_idle_exit();
 	}
 
+	latency_fsnotify_enable();
+
 	/*
 	 * Since we fell out of the loop above, we know TIF_NEED_RESCHED must
 	 * be set, propagate it into PREEMPT_NEED_RESCHED.
kernel/sched/sched.h +1 -0
index 802b1f3405f2..467d6ad03f16 100644
@@ -46,6 +46,7 @@
 #include <linux/debugfs.h>
 #include <linux/delayacct.h>
 #include <linux/energy_model.h>
+#include <linux/ftrace.h>
 #include <linux/init_task.h>
 #include <linux/kprobes.h>
 #include <linux/kthread.h>
kernel/trace/trace.c +110 -2
index 563e80f9006a..a622263a69e4 100644
@@ -44,6 +44,10 @@
 #include <linux/trace.h>
 #include <linux/sched/clock.h>
 #include <linux/sched/rt.h>
+#include <linux/fsnotify.h>
+#include <linux/workqueue.h>
+#include <trace/events/power.h>
+#include <trace/events/sched.h>
 
 #include "trace.h"
 #include "trace_output.h"
@@ -1480,6 +1484,110 @@ static ssize_t trace_seq_to_buffer(struct trace_seq *s, void *buf, size_t cnt)
 
 unsigned long __read_mostly	tracing_thresh;
 
+#if (defined(CONFIG_TRACER_MAX_TRACE) || defined(CONFIG_HWLAT_TRACER)) && \
+	defined(CONFIG_FSNOTIFY)
+
+static const struct file_operations tracing_max_lat_fops;
+static struct workqueue_struct *fsnotify_wq;
+static DEFINE_PER_CPU(struct llist_head, notify_list);
+
+DEFINE_PER_CPU(int, latency_notify_disable);
+DEFINE_STATIC_KEY_FALSE(latency_notify_key);
+
+static void latency_fsnotify_workfn(struct work_struct *work)
+{
+	struct trace_array *tr = container_of(work, struct trace_array,
+					      fsnotify_work);
+	fsnotify(tr->d_max_latency->d_inode, FS_MODIFY,
+		 tr->d_max_latency->d_inode, FSNOTIFY_EVENT_INODE, NULL, 0);
+}
+
+static void trace_create_maxlat_file(struct trace_array *tr,
+				     struct dentry *d_tracer)
+{
+	INIT_WORK(&tr->fsnotify_work, latency_fsnotify_workfn);
+	atomic_set(&tr->notify_pending, 0);
+	tr->d_max_latency = trace_create_file("tracing_max_latency", 0644,
+					      d_tracer, &tr->max_latency,
+					      &tracing_max_lat_fops);
+}
+
+void latency_fsnotify_stop(void)
+{
+	/* Make sure all CPUs see caller's previous actions to stop tracer */
+	smp_wmb();
+	static_branch_disable(&latency_notify_key);
+	latency_fsnotify_process();
+}
+
+void latency_fsnotify_start(void)
+{
+	static_branch_enable(&latency_notify_key);
+	/* Make sure all CPUs see key value before caller continue */
+	smp_wmb();
+}
+
+void latency_fsnotify_process(void)
+{
+	struct trace_array *tr;
+	struct llist_head *list;
+	struct llist_node *node;
+
+	if (this_cpu_read(latency_notify_disable))
+		return;
+
+	list = this_cpu_ptr(&notify_list);
+	for (node = llist_del_first(list); node != NULL;
+	     node = llist_del_first(list)) {
+		tr = llist_entry(node, struct trace_array, notify_ll);
+		atomic_set(&tr->notify_pending, 0);
+		queue_work(fsnotify_wq, &tr->fsnotify_work);
+	}
+}
+
+__init static int latency_fsnotify_init(void)
+{
+	fsnotify_wq = alloc_workqueue("tr_max_lat_wq",
+				      WQ_UNBOUND | WQ_HIGHPRI, 0);
+	if (!fsnotify_wq) {
+		pr_err("Unable to allocate tr_max_lat_wq\n");
+		return -ENOMEM;
+	}
+	return 0;
+}
+
+late_initcall_sync(latency_fsnotify_init);
+
+void latency_fsnotify(struct trace_array *tr)
+{
+	if (!fsnotify_wq)
+		return;
+
+	if (!this_cpu_read(latency_notify_disable))
+		queue_work(fsnotify_wq, &tr->fsnotify_work);
+	else {
+		/*
+		 * notify_pending prevents us from adding the same entry to
+		 * more than one notify_list. It will get queued in
+		 * latency_enable_fsnotify()
+		 */
+		if (!atomic_xchg(&tr->notify_pending, 1))
+			llist_add(&tr->notify_ll, this_cpu_ptr(&notify_list));
+	}
+}
+
+/*
+ * (defined(CONFIG_TRACER_MAX_TRACE) || defined(CONFIG_HWLAT_TRACER)) && \
+ *  defined(CONFIG_FSNOTIFY)
+ */
+#else
+
+#define trace_create_maxlat_file(tr, d_tracer)				\
+	trace_create_file("tracing_max_latency", 0644, d_tracer,	\
+			  &tr->max_latency, &tracing_max_lat_fops)
+
+#endif
+
 #ifdef CONFIG_TRACER_MAX_TRACE
 /*
  * Copy the new maximum trace into the separate maximum-trace
@@ -1518,6 +1626,7 @@ __update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu)
 
 	/* record this tasks comm */
 	tracing_record_cmdline(tsk);
+	latency_fsnotify(tr);
 }
 
 /**
@@ -8550,8 +8659,7 @@ init_tracer_tracefs(struct trace_array *tr, struct dentry *d_tracer)
 	create_trace_options_dir(tr);
 
 #if defined(CONFIG_TRACER_MAX_TRACE) || defined(CONFIG_HWLAT_TRACER)
-	trace_create_file("tracing_max_latency", 0644, d_tracer,
-			&tr->max_latency, &tracing_max_lat_fops);
+	trace_create_maxlat_file(tr, d_tracer);
 #endif
 
 	if (ftrace_create_function_files(tr, d_tracer))
kernel/trace/trace.h +22 -0
index 005f08629b8b..d9f83b2aaa71 100644
@@ -16,6 +16,7 @@
 #include <linux/trace_events.h>
 #include <linux/compiler.h>
 #include <linux/glob.h>
+#include <linux/workqueue.h>
 
 #ifdef CONFIG_FTRACE_SYSCALLS
 #include <asm/unistd.h>		/* For NR_SYSCALLS	     */
@@ -264,6 +265,12 @@ struct trace_array {
 #endif
 #if defined(CONFIG_TRACER_MAX_TRACE) || defined(CONFIG_HWLAT_TRACER)
 	unsigned long		max_latency;
+#ifdef CONFIG_FSNOTIFY
+	struct dentry		*d_max_latency;
+	struct work_struct	fsnotify_work;
+	atomic_t		notify_pending;
+	struct llist_node	notify_ll;
+#endif
 #endif
 	struct trace_pid_list	__rcu *filtered_pids;
 	/*
@@ -785,6 +792,21 @@ void update_max_tr_single(struct trace_array *tr,
 			  struct task_struct *tsk, int cpu);
 #endif /* CONFIG_TRACER_MAX_TRACE */
 
+#if (defined(CONFIG_TRACER_MAX_TRACE) || defined(CONFIG_HWLAT_TRACER)) && \
+	defined(CONFIG_FSNOTIFY)
+
+void latency_fsnotify(struct trace_array *tr);
+void latency_fsnotify_start(void);
+void latency_fsnotify_stop(void);
+
+#else
+
+#define latency_fsnotify(tr)     do { } while (0)
+#define latency_fsnotify_start() do { } while (0)
+#define latency_fsnotify_stop()  do { } while (0)
+
+#endif
+
 #ifdef CONFIG_STACKTRACE
 void __trace_stack(struct trace_array *tr, unsigned long flags, int skip,
 		   int pc);
kernel/trace/trace_hwlat.c +3 -1
index fa95139445b2..9c379261ee89 100644
@@ -254,8 +254,10 @@ static int get_sample(void)
 		trace_hwlat_sample(&s);
 
 		/* Keep a running maximum ever recorded hardware latency */
-		if (sample > tr->max_latency)
+		if (sample > tr->max_latency) {
 			tr->max_latency = sample;
+			latency_fsnotify(tr);
+		}
 	}
 
 out:
kernel/trace/trace_irqsoff.c +4 -0
index a745b0cee5d3..29403a83a5f0 100644
@@ -557,6 +557,7 @@ static int __irqsoff_tracer_init(struct trace_array *tr)
 	if (irqsoff_busy)
 		return -EBUSY;
 
+	latency_fsnotify_start();
 	save_flags = tr->trace_flags;
 
 	/* non overwrite screws up the latency tracers */
@@ -591,16 +592,19 @@ static void __irqsoff_tracer_reset(struct trace_array *tr)
 	ftrace_reset_array_ops(tr);
 
 	irqsoff_busy = false;
+	latency_fsnotify_stop();
 }
 
 static void irqsoff_tracer_start(struct trace_array *tr)
 {
+	latency_fsnotify_start();
 	tracer_enabled = 1;
 }
 
 static void irqsoff_tracer_stop(struct trace_array *tr)
 {
 	tracer_enabled = 0;
+	latency_fsnotify_stop();
 }
 
 #ifdef CONFIG_IRQSOFF_TRACER
kernel/trace/trace_sched_wakeup.c +4 -0
index 743b2b520d34..3dc90d9f605b 100644
@@ -669,6 +669,7 @@ static bool wakeup_busy;
 
 static int __wakeup_tracer_init(struct trace_array *tr)
 {
+	latency_fsnotify_start();
 	save_flags = tr->trace_flags;
 
 	/* non overwrite screws up the latency tracers */
@@ -727,10 +728,12 @@ static void wakeup_tracer_reset(struct trace_array *tr)
 	set_tracer_flag(tr, TRACE_ITER_OVERWRITE, overwrite_flag);
 	ftrace_reset_array_ops(tr);
 	wakeup_busy = false;
+	latency_fsnotify_stop();
 }
 
 static void wakeup_tracer_start(struct trace_array *tr)
 {
+	latency_fsnotify_start();
 	wakeup_reset(tr);
 	tracer_enabled = 1;
 }
@@ -738,6 +741,7 @@ static void wakeup_tracer_start(struct trace_array *tr)
 static void wakeup_tracer_stop(struct trace_array *tr)
 {
 	tracer_enabled = 0;
+	latency_fsnotify_stop();
 }
 
 static struct tracer wakeup_tracer __read_mostly =
Signature · 1 line
2.17.1
maintainer
#3 lore raw

Re: [PATCH v5 1/4] ftrace: Implement fs notification for tracing_max_latency

Quoted 16 lines · Joel Fernandes

[ Resending since I messed up my last email's headers! ]

Quoted 5 lines · Viktor Rosendahl

This patch implements the feature that the tracing_max_latency file, e.g. /sys/kernel/debug/tracing/tracing_max_latency will receive notifications through the fsnotify framework when a new latency is available.

Quoted 7 lines

One particularly interesting use of this facility is when enabling threshold tracing, through /sys/kernel/debug/tracing/tracing_thresh, together with the preempt/irqsoff tracers. This makes it possible to implement a user space program that can, with equal probability, obtain traces of latencies that occur immediately after each other in spite of the fact that the preempt/irqsoff tracers operate in overwrite mode.

Quoted 3 lines

Adding Paul since RCU faces similar situations, i.e. raising softirq risks scheduler deadlock in rcu_read_unlock_special() -- but RCU's solution is to avoid raising the softirq and instead use irq_work.

Which is right.

Quoted 6 lines

I was wondering, if we can rename __raise_softirq_irqoff() to raise_softirq_irqoff_no_wake() and call that from places where there is risk of scheduler related deadlocks. Then I think this can be used from Viktor's code. Let us discuss - what would happen if the softirq is raised, but ksoftirqd is not awakened for this latency notification path? Is this really an issue considering the softirq will execute during the next interrupt exit?

You'd get unbounded latency for processing the softirq and warnings on going idle with softirqs pending.

I really don't see why we should/want to be using softirq here.

#4 lore raw

Re: [PATCH v5 1/4] ftrace: Implement fs notification for tracing_max_latency

Quoted 17 lines · Peter Zijlstra
Quoted 16 lines · Joel Fernandes

[ Resending since I messed up my last email's headers! ]

Quoted 12 lines · Viktor Rosendahl

This patch implements the feature that the tracing_max_latency file, e.g. /sys/kernel/debug/tracing/tracing_max_latency will receive notifications through the fsnotify framework when a new latency is available.

One particularly interesting use of this facility is when enabling threshold tracing, through /sys/kernel/debug/tracing/tracing_thresh, together with the preempt/irqsoff tracers. This makes it possible to implement a user space program that can, with equal probability, obtain traces of latencies that occur immediately after each other in spite of the fact that the preempt/irqsoff tracers operate in overwrite mode.

Quoted 5 lines
Quoted 3 lines

Adding Paul since RCU faces similar situations, i.e. raising softirq risks scheduler deadlock in rcu_read_unlock_special() -- but RCU's solution is to avoid raising the softirq and instead use irq_work.

Which is right.

Cool.

Quoted 9 lines
Quoted 6 lines

I was wondering, if we can rename __raise_softirq_irqoff() to raise_softirq_irqoff_no_wake() and call that from places where there is risk of scheduler related deadlocks. Then I think this can be used from Viktor's code. Let us discuss - what would happen if the softirq is raised, but ksoftirqd is not awakened for this latency notification path? Is this really an issue considering the softirq will execute during the next interrupt exit?

You'd get unbounded latency for processing the softirq and warnings on going idle with softirqs pending.

Thanks for sharing that.

Quoted 1 line

I really don't see why we should/want to be using softirq here.

Sure. makes sense.

thanks,

- Joel

#5 lore raw

Re: [PATCH v5 1/4] ftrace: Implement fs notification for tracing_max_latency

In reply to Peter Zijlstra
Quoted 7 lines · Peter Zijlstra
Quoted 4 lines

Adding Paul since RCU faces similar situations, i.e. raising softirq risks scheduler deadlock in rcu_read_unlock_special() -- but RCU's solution is to avoid raising the softirq and instead use irq_work.

Which is right.

Thanks Joel and Peter for suggesting the irq_work facility.

I was ignorant of the existence of this facility.

It looks like it is the Holy Grail of deferred work, for this particular type of problem :)

It looks like it will be possible to both avoid deadlock and also avoid the ugly additions to the sched and idle code. In addition, the rest of the code will become a lot simpler.

best regards,

Viktor

#6 lore raw

Re: [PATCH v5 1/4] ftrace: Implement fs notification for tracing_max_latency

In reply to Joel Fernandes
Quoted 16 lines · Joel Fernandes

[ Resending since I messed up my last email's headers! ]

Quoted 5 lines · Viktor Rosendahl

This patch implements the feature that the tracing_max_latency file, e.g. /sys/kernel/debug/tracing/tracing_max_latency will receive notifications through the fsnotify framework when a new latency is available.

Quoted 7 lines

One particularly interesting use of this facility is when enabling threshold tracing, through /sys/kernel/debug/tracing/tracing_thresh, together with the preempt/irqsoff tracers. This makes it possible to implement a user space program that can, with equal probability, obtain traces of latencies that occur immediately after each other in spite of the fact that the preempt/irqsoff tracers operate in overwrite mode.

Quoted 3 lines

Adding Paul since RCU faces similar situations, i.e. raising softirq risks scheduler deadlock in rcu_read_unlock_special() -- but RCU's solution is to avoid raising the softirq and instead use irq_work.

Peter's solution, actually. ;-)

Thanx, Paul

Quoted 427 lines

I was wondering, if we can rename __raise_softirq_irqoff() to raise_softirq_irqoff_no_wake() and call that from places where there is risk of scheduler related deadlocks. Then I think this can be used from Viktor's code. Let us discuss - what would happen if the softirq is raised, but ksoftirqd is not awakened for this latency notification path? Is this really an issue considering the softirq will execute during the next interrupt exit?

thanks,

- Joel

Quoted 415 lines

This facility works with the hwlat, preempt/irqsoff, and wakeup tracers.

This patch also adds some unfortunate calls from __schedule() and do_idle(). Those calls to the latency_fsnotify_disable/enable() are needed because we cannot wake up the workqueue from these critical sections without risking a deadlock. Similar problems would also arise if we try to schedule a tasklet, raise a softirq, or wake up a kernel thread. If a notification event would happen in the forbidden sections, we schedule the fsnotify work as soon as we have exited them.

There was a suggestion to remove this latency_fsnotify_enable/disable() gunk, or at least to combine it with the start_critical_timings() and stop_critical_timings(). I have however not been able to come up with a way to do it.

It seems like it would be possible to simply replace the calls to latency_fsnotify_enable/disable() with calls to start/stop_critical_timings(). However, the main problem is that it would not work for the wakup tracer. The wakeup tracer needs a facility that postpones the notifications, not one that prevents the measurements because all its measurements takes place in the middle of __schedule(). On the other hand, in some places, like in idle and the console we need start stop functions that prevents the measurements from being make.

---
 include/linux/ftrace.h            |  31 +++++++++
 kernel/sched/core.c               |   3 +
 kernel/sched/idle.c               |   3 +
 kernel/sched/sched.h              |   1 +
 kernel/trace/trace.c              | 112 +++++++++++++++++++++++++++++-
 kernel/trace/trace.h              |  22 ++++++
 kernel/trace/trace_hwlat.c        |   4 +-
 kernel/trace/trace_irqsoff.c      |   4 ++
 kernel/trace/trace_sched_wakeup.c |   4 ++
 9 files changed, 181 insertions(+), 3 deletions(-)
include/linux/ftrace.h +31 -0
index 8a8cb3c401b2..b4d9700ef917 100644
@@ -907,4 +907,35 @@ unsigned long arch_syscall_addr(int nr);
 
 #endif /* CONFIG_FTRACE_SYSCALLS */
 
+#if (defined(CONFIG_TRACER_MAX_TRACE) || defined(CONFIG_HWLAT_TRACER)) && \
+	defined(CONFIG_FSNOTIFY)
+
+DECLARE_PER_CPU(int, latency_notify_disable);
+DECLARE_STATIC_KEY_FALSE(latency_notify_key);
+
+void latency_fsnotify_process(void);
+
+/*
+ * Disable/enable fsnotify while in scheduler and idle code. Trying to wake
+ * anything up from there, such as calling queue_work() is prone to deadlock.
+ */
+static inline void latency_fsnotify_disable(void)
+{
+	this_cpu_inc(latency_notify_disable);
+}
+
+static inline void latency_fsnotify_enable(void)
+{
+	this_cpu_dec(latency_notify_disable);
+	if (static_branch_unlikely(&latency_notify_key))
+		latency_fsnotify_process();
+}
+
+#else
+
+#define latency_fsnotify_disable() do { } while (0)
+#define latency_fsnotify_enable()  do { } while (0)
+
+#endif
+
 #endif /* _LINUX_FTRACE_H */
kernel/sched/core.c +3 -0
index 010d578118d6..e3c1dc801073 100644
@@ -3198,6 +3198,7 @@ asmlinkage __visible void schedule_tail(struct task_struct *prev)
 	 */
 
 	rq = finish_task_switch(prev);
+	latency_fsnotify_enable();
 	balance_callback(rq);
 	preempt_enable();
 
@@ -3820,6 +3821,7 @@ static void __sched notrace __schedule(bool preempt)
 
 	local_irq_disable();
 	rcu_note_context_switch(preempt);
+	latency_fsnotify_disable();
 
 	/*
 	 * Make sure that signal_pending_state()->signal_pending() below
@@ -3883,6 +3885,7 @@ static void __sched notrace __schedule(bool preempt)
 		rq_unlock_irq(rq, &rf);
 	}
 
+	latency_fsnotify_enable();
 	balance_callback(rq);
 }
 
kernel/sched/idle.c +3 -0
index 80940939b733..5fc87d99a407 100644
@@ -236,6 +236,7 @@ static void do_idle(void)
 
 	__current_set_polling();
 	tick_nohz_idle_enter();
+	latency_fsnotify_disable();
 
 	while (!need_resched()) {
 		check_pgt_cache();
@@ -265,6 +266,8 @@ static void do_idle(void)
 		arch_cpu_idle_exit();
 	}
 
+	latency_fsnotify_enable();
+
 	/*
 	 * Since we fell out of the loop above, we know TIF_NEED_RESCHED must
 	 * be set, propagate it into PREEMPT_NEED_RESCHED.
kernel/sched/sched.h +1 -0
index 802b1f3405f2..467d6ad03f16 100644
@@ -46,6 +46,7 @@
 #include <linux/debugfs.h>
 #include <linux/delayacct.h>
 #include <linux/energy_model.h>
+#include <linux/ftrace.h>
 #include <linux/init_task.h>
 #include <linux/kprobes.h>
 #include <linux/kthread.h>
kernel/trace/trace.c +110 -2
index 563e80f9006a..a622263a69e4 100644
@@ -44,6 +44,10 @@
 #include <linux/trace.h>
 #include <linux/sched/clock.h>
 #include <linux/sched/rt.h>
+#include <linux/fsnotify.h>
+#include <linux/workqueue.h>
+#include <trace/events/power.h>
+#include <trace/events/sched.h>
 
 #include "trace.h"
 #include "trace_output.h"
@@ -1480,6 +1484,110 @@ static ssize_t trace_seq_to_buffer(struct trace_seq *s, void *buf, size_t cnt)
 
 unsigned long __read_mostly	tracing_thresh;
 
+#if (defined(CONFIG_TRACER_MAX_TRACE) || defined(CONFIG_HWLAT_TRACER)) && \
+	defined(CONFIG_FSNOTIFY)
+
+static const struct file_operations tracing_max_lat_fops;
+static struct workqueue_struct *fsnotify_wq;
+static DEFINE_PER_CPU(struct llist_head, notify_list);
+
+DEFINE_PER_CPU(int, latency_notify_disable);
+DEFINE_STATIC_KEY_FALSE(latency_notify_key);
+
+static void latency_fsnotify_workfn(struct work_struct *work)
+{
+	struct trace_array *tr = container_of(work, struct trace_array,
+					      fsnotify_work);
+	fsnotify(tr->d_max_latency->d_inode, FS_MODIFY,
+		 tr->d_max_latency->d_inode, FSNOTIFY_EVENT_INODE, NULL, 0);
+}
+
+static void trace_create_maxlat_file(struct trace_array *tr,
+				     struct dentry *d_tracer)
+{
+	INIT_WORK(&tr->fsnotify_work, latency_fsnotify_workfn);
+	atomic_set(&tr->notify_pending, 0);
+	tr->d_max_latency = trace_create_file("tracing_max_latency", 0644,
+					      d_tracer, &tr->max_latency,
+					      &tracing_max_lat_fops);
+}
+
+void latency_fsnotify_stop(void)
+{
+	/* Make sure all CPUs see caller's previous actions to stop tracer */
+	smp_wmb();
+	static_branch_disable(&latency_notify_key);
+	latency_fsnotify_process();
+}
+
+void latency_fsnotify_start(void)
+{
+	static_branch_enable(&latency_notify_key);
+	/* Make sure all CPUs see key value before caller continue */
+	smp_wmb();
+}
+
+void latency_fsnotify_process(void)
+{
+	struct trace_array *tr;
+	struct llist_head *list;
+	struct llist_node *node;
+
+	if (this_cpu_read(latency_notify_disable))
+		return;
+
+	list = this_cpu_ptr(&notify_list);
+	for (node = llist_del_first(list); node != NULL;
+	     node = llist_del_first(list)) {
+		tr = llist_entry(node, struct trace_array, notify_ll);
+		atomic_set(&tr->notify_pending, 0);
+		queue_work(fsnotify_wq, &tr->fsnotify_work);
+	}
+}
+
+__init static int latency_fsnotify_init(void)
+{
+	fsnotify_wq = alloc_workqueue("tr_max_lat_wq",
+				      WQ_UNBOUND | WQ_HIGHPRI, 0);
+	if (!fsnotify_wq) {
+		pr_err("Unable to allocate tr_max_lat_wq\n");
+		return -ENOMEM;
+	}
+	return 0;
+}
+
+late_initcall_sync(latency_fsnotify_init);
+
+void latency_fsnotify(struct trace_array *tr)
+{
+	if (!fsnotify_wq)
+		return;
+
+	if (!this_cpu_read(latency_notify_disable))
+		queue_work(fsnotify_wq, &tr->fsnotify_work);
+	else {
+		/*
+		 * notify_pending prevents us from adding the same entry to
+		 * more than one notify_list. It will get queued in
+		 * latency_enable_fsnotify()
+		 */
+		if (!atomic_xchg(&tr->notify_pending, 1))
+			llist_add(&tr->notify_ll, this_cpu_ptr(&notify_list));
+	}
+}
+
+/*
+ * (defined(CONFIG_TRACER_MAX_TRACE) || defined(CONFIG_HWLAT_TRACER)) && \
+ *  defined(CONFIG_FSNOTIFY)
+ */
+#else
+
+#define trace_create_maxlat_file(tr, d_tracer)				\
+	trace_create_file("tracing_max_latency", 0644, d_tracer,	\
+			  &tr->max_latency, &tracing_max_lat_fops)
+
+#endif
+
 #ifdef CONFIG_TRACER_MAX_TRACE
 /*
  * Copy the new maximum trace into the separate maximum-trace
@@ -1518,6 +1626,7 @@ __update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu)
 
 	/* record this tasks comm */
 	tracing_record_cmdline(tsk);
+	latency_fsnotify(tr);
 }
 
 /**
@@ -8550,8 +8659,7 @@ init_tracer_tracefs(struct trace_array *tr, struct dentry *d_tracer)
 	create_trace_options_dir(tr);
 
 #if defined(CONFIG_TRACER_MAX_TRACE) || defined(CONFIG_HWLAT_TRACER)
-	trace_create_file("tracing_max_latency", 0644, d_tracer,
-			&tr->max_latency, &tracing_max_lat_fops);
+	trace_create_maxlat_file(tr, d_tracer);
 #endif
 
 	if (ftrace_create_function_files(tr, d_tracer))
kernel/trace/trace.h +22 -0
index 005f08629b8b..d9f83b2aaa71 100644
@@ -16,6 +16,7 @@
 #include <linux/trace_events.h>
 #include <linux/compiler.h>
 #include <linux/glob.h>
+#include <linux/workqueue.h>
 
 #ifdef CONFIG_FTRACE_SYSCALLS
 #include <asm/unistd.h>		/* For NR_SYSCALLS	     */
@@ -264,6 +265,12 @@ struct trace_array {
 #endif
 #if defined(CONFIG_TRACER_MAX_TRACE) || defined(CONFIG_HWLAT_TRACER)
 	unsigned long		max_latency;
+#ifdef CONFIG_FSNOTIFY
+	struct dentry		*d_max_latency;
+	struct work_struct	fsnotify_work;
+	atomic_t		notify_pending;
+	struct llist_node	notify_ll;
+#endif
 #endif
 	struct trace_pid_list	__rcu *filtered_pids;
 	/*
@@ -785,6 +792,21 @@ void update_max_tr_single(struct trace_array *tr,
 			  struct task_struct *tsk, int cpu);
 #endif /* CONFIG_TRACER_MAX_TRACE */
 
+#if (defined(CONFIG_TRACER_MAX_TRACE) || defined(CONFIG_HWLAT_TRACER)) && \
+	defined(CONFIG_FSNOTIFY)
+
+void latency_fsnotify(struct trace_array *tr);
+void latency_fsnotify_start(void);
+void latency_fsnotify_stop(void);
+
+#else
+
+#define latency_fsnotify(tr)     do { } while (0)
+#define latency_fsnotify_start() do { } while (0)
+#define latency_fsnotify_stop()  do { } while (0)
+
+#endif
+
 #ifdef CONFIG_STACKTRACE
 void __trace_stack(struct trace_array *tr, unsigned long flags, int skip,
 		   int pc);
kernel/trace/trace_hwlat.c +3 -1
index fa95139445b2..9c379261ee89 100644
@@ -254,8 +254,10 @@ static int get_sample(void)
 		trace_hwlat_sample(&s);
 
 		/* Keep a running maximum ever recorded hardware latency */
-		if (sample > tr->max_latency)
+		if (sample > tr->max_latency) {
 			tr->max_latency = sample;
+			latency_fsnotify(tr);
+		}
 	}
 
 out:
kernel/trace/trace_irqsoff.c +4 -0
index a745b0cee5d3..29403a83a5f0 100644
@@ -557,6 +557,7 @@ static int __irqsoff_tracer_init(struct trace_array *tr)
 	if (irqsoff_busy)
 		return -EBUSY;
 
+	latency_fsnotify_start();
 	save_flags = tr->trace_flags;
 
 	/* non overwrite screws up the latency tracers */
@@ -591,16 +592,19 @@ static void __irqsoff_tracer_reset(struct trace_array *tr)
 	ftrace_reset_array_ops(tr);
 
 	irqsoff_busy = false;
+	latency_fsnotify_stop();
 }
 
 static void irqsoff_tracer_start(struct trace_array *tr)
 {
+	latency_fsnotify_start();
 	tracer_enabled = 1;
 }
 
 static void irqsoff_tracer_stop(struct trace_array *tr)
 {
 	tracer_enabled = 0;
+	latency_fsnotify_stop();
 }
 
 #ifdef CONFIG_IRQSOFF_TRACER
kernel/trace/trace_sched_wakeup.c +4 -0
index 743b2b520d34..3dc90d9f605b 100644
@@ -669,6 +669,7 @@ static bool wakeup_busy;
 
 static int __wakeup_tracer_init(struct trace_array *tr)
 {
+	latency_fsnotify_start();
 	save_flags = tr->trace_flags;
 
 	/* non overwrite screws up the latency tracers */
@@ -727,10 +728,12 @@ static void wakeup_tracer_reset(struct trace_array *tr)
 	set_tracer_flag(tr, TRACE_ITER_OVERWRITE, overwrite_flag);
 	ftrace_reset_array_ops(tr);
 	wakeup_busy = false;
+	latency_fsnotify_stop();
 }
 
 static void wakeup_tracer_start(struct trace_array *tr)
 {
+	latency_fsnotify_start();
 	wakeup_reset(tr);
 	tracer_enabled = 1;
 }
@@ -738,6 +741,7 @@ static void wakeup_tracer_start(struct trace_array *tr)
 static void wakeup_tracer_stop(struct trace_array *tr)
 {
 	tracer_enabled = 0;
+	latency_fsnotify_stop();
 }
 
 static struct tracer wakeup_tracer __read_mostly =
Signature · 1 line
2.17.1
maintainer
#7 lore raw

Re: [PATCH v5 1/4] ftrace: Implement fs notification for tracing_max_latency

In reply to Viktor Rosendahl
Quoted 9 lines · Viktor Rosendahl

It seems like it would be possible to simply replace the calls to latency_fsnotify_enable/disable() with calls to start/stop_critical_timings(). However, the main problem is that it would not work for the wakup tracer. The wakeup tracer needs a facility that postpones the notifications, not one that prevents the measurements because all its measurements takes place in the middle of __schedule(). On the other hand, in some places, like in idle and the console we need start stop functions that prevents the measurements from being make.

Like Joel already mentioned; you can use irq_work here.

maintainer
#8 lore raw

Re: [PATCH v5 1/4] ftrace: Implement fs notification for tracing_max_latency

Quoted 12 lines · On Wed, 4 Sep 2019 10:20:46 +0200 Peter Zijlstra <[email protected]> wrote:
Quoted 9 lines · Viktor Rosendahl

It seems like it would be possible to simply replace the calls to latency_fsnotify_enable/disable() with calls to start/stop_critical_timings(). However, the main problem is that it would not work for the wakup tracer. The wakeup tracer needs a facility that postpones the notifications, not one that prevents the measurements because all its measurements takes place in the middle of __schedule(). On the other hand, in some places, like in idle and the console we need start stop functions that prevents the measurements from being make.

Quoted 1 line

Like Joel already mentioned; you can use irq_work here.

And I was thinking the exact same thing here too ;-)

-- Steve

maintainer
#9 lore raw

Re: [PATCH v5 1/4] ftrace: Implement fs notification for tracing_max_latency

In reply to Viktor Rosendahl

kernel/trace/trace.c static ssize_t trace_seq_to_buffer(struct trace_seq *s, void *buf, size_t cnt) · line 1518

Quoted 4 lines · On Tue, 3 Sep 2019 15:25:59 +0200 Viktor Rosendahl…
kernel/trace/trace.c +4 -0
+void latency_fsnotify_stop(void)
+{
+	/* Make sure all CPUs see caller's previous actions to stop tracer */
+	smp_wmb();

These memory barriers just look wrong. What exactly are you trying to protect here?

Where's the matching rmbs?

-- Steve

Quoted 11 lines
kernel/trace/trace.c +11 -0
+	static_branch_disable(&latency_notify_key);
+	latency_fsnotify_process();
+}
+
+void latency_fsnotify_start(void)
+{
+	static_branch_enable(&latency_notify_key);
+	/* Make sure all CPUs see key value before caller continue */
+	smp_wmb();
+}
+
#10 lore raw

Re: [PATCH v5 1/4] ftrace: Implement fs notification for tracing_max_latency

Quoted 12 lines · Steven Rostedt

kernel/trace/trace.c static ssize_t trace_seq_to_buffer(struct trace_seq *s, void *buf, size_t cnt) · line 1518

Quoted 4 lines · On Tue, 3 Sep 2019 15:25:59 +0200 Viktor Rosendahl…
kernel/trace/trace.c +4 -0
+void latency_fsnotify_stop(void)
+{
+	/* Make sure all CPUs see caller's previous actions to stop tracer */
+	smp_wmb();

These memory barriers just look wrong. What exactly are you trying to protect here?

Where's the matching rmbs?

Thanks for reviewing.

However, since these functions will disappear when I take the irq_work facility into use, we should perhaps not spend too much time discussing what would have been.

There are no matching rmbs, I was thinking that the smp_wmb() would
merely enforce the order of the memory writes, as seen by other CPUs, so that the tracer would be stopped, before the latency fsnotify is disabled.

E.g. in case of the preemptirqsoff tracer the idea was that it doesn't matter exactly when a CPU sees the "tracer_enabled = 0;" in stop_irqsoff_tracer() but that it needs to be seen before the writes in latency_fsnotify_stop() are seen.

best regards,

Viktor

#11 lore raw

PATCH v5 2/4 preemptirq_delay_test: Add the burst feature and a sysfs trigger

In reply to Viktor Rosendahl

This burst feature enables the user to generate a burst of preempt/irqsoff latencies. This makes it possible to test whether we are able to detect latencies that systematically occur very close to each other.

The maximum burst size is 10. We also create 10 identical test functions, so that we get 10 different backtraces; this is useful when we want to test whether we can detect all the latencies in a burst. Otherwise, there would be no easy way of differentiating between which latency in a burst was captured by the tracer.

In addition, there is a sysfs trigger, so that it's not necessary to reload the module to repeat the test. The trigger will appear as /sys/kernel/preemptirq_delay_test/trigger in sysfs.

---
 kernel/trace/Kconfig                 |   6 +-
 kernel/trace/preemptirq_delay_test.c | 145 +++++++++++++++++++++++----
 2 files changed, 129 insertions(+), 22 deletions(-)
kernel/trace/Kconfig +3 -3
index 98da8998c25c..5ff573d844e4 100644
@@ -751,9 +751,9 @@ config PREEMPTIRQ_DELAY_TEST
 	  configurable delay. The module busy waits for the duration of the
 	  critical section.
 
-	  For example, the following invocation forces a one-time irq-disabled
-	  critical section for 500us:
-	  modprobe preemptirq_delay_test test_mode=irq delay=500000
+	  For example, the following invocation generates a burst of three
+	  irq-disabled critical sections for 500us:
+	  modprobe preemptirq_delay_test test_mode=irq delay=500 burst_size=3
 
 	  If unsure, say N
 
kernel/trace/preemptirq_delay_test.c +126 -19

187 lines not on this page · raw message

Signature · 1 line
2.17.1
maintainer
#12 lore raw

Re: [PATCH v5 2/4] preemptirq_delay_test: Add the burst feature and a sysfs trigger

kernel/trace/preemptirq_delay_test.c line 6

Quoted 9 lines · On Tue, 3 Sep 2019 15:26:00 +0200 Viktor Rosendahl…
kernel/trace/preemptirq_delay_test.c +1 -0
index d8765c952fab..dc281fa75198 100644
@@ -3,6 +3,7 @@
  * Preempt / IRQ disable delay thread to test latency tracers
  *
  * Copyright (C) 2018 Joel Fernandes (Google) <[email protected]>
+ * Copyright (C) 2018, 2019 BMW Car IT GmbH

A name and what you did should also be attached here. Ideally, we leave these out as git history is usually enough.

-- Steve

Quoted 15 lines
kernel/trace/preemptirq_delay_test.c +2 -0
  */
 
 #include <linux/trace_clock.h>
@@ -10,18 +11,25 @@
 #include <linux/interrupt.h>
 #include <linux/irq.h>
 #include <linux/kernel.h>
+#include <linux/kobject.h>
 #include <linux/kthread.h>
 #include <linux/module.h>
 #include <linux/printk.h>
 #include <linux/string.h>
+#include <linux/sysfs.h>
 
 
#13 lore raw

Re: [PATCH v5 2/4] preemptirq_delay_test: Add the burst feature and a sysfs trigger

Quoted 14 lines · Steven Rostedt

kernel/trace/preemptirq_delay_test.c line 6

Quoted 9 lines · On Tue, 3 Sep 2019 15:26:00 +0200 Viktor Rosendahl…
kernel/trace/preemptirq_delay_test.c +1 -0
index d8765c952fab..dc281fa75198 100644
@@ -3,6 +3,7 @@
   * Preempt / IRQ disable delay thread to test latency tracers
   *
   * Copyright (C) 2018 Joel Fernandes (Google) <[email protected]>
+ * Copyright (C) 2018, 2019 BMW Car IT GmbH

A name and what you did should also be attached here. Ideally, we leave these out as git history is usually enough.

I am not so keen to clutter source files with a new copyright message. My problem is that git-send-email doesn't work well with my work email address, so I am forced to use my private gmail, which may create a false impression that I as a private individual would be the copyright holder.

best regards,

Viktor

maintainer
#14 lore raw

Re: [PATCH v5 2/4] preemptirq_delay_test: Add the burst feature and a sysfs trigger

Quoted 16 lines · On Wed, 4 Sep 2019 21:10:38 +0200 Viktor Rosendahl…
Quoted 14 lines · Steven Rostedt

kernel/trace/preemptirq_delay_test.c line 6

Quoted 9 lines · On Tue, 3 Sep 2019 15:26:00 +0200 Viktor Rosendahl…
kernel/trace/preemptirq_delay_test.c +1 -0
index d8765c952fab..dc281fa75198 100644
@@ -3,6 +3,7 @@
   * Preempt / IRQ disable delay thread to test latency tracers
   *
   * Copyright (C) 2018 Joel Fernandes (Google) <[email protected]>
+ * Copyright (C) 2018, 2019 BMW Car IT GmbH  

A name and what you did should also be attached here. Ideally, we leave these out as git history is usually enough.

Quoted 6 lines

I am not so keen to clutter source files with a new copyright message. My problem is that git-send-email doesn't work well with my work email address, so I am forced to use my private gmail, which may create a false impression that I as a private individual would be the copyright holder.

Then do what I do:

Steven Rostedt (VMware) <[email protected]>

I did "(Red Hat)" when I worked for Red Hat.

-- Steve

#15 lore raw

Re: [PATCH v5 2/4] preemptirq_delay_test: Add the burst feature and a sysfs trigger

Quoted 12 lines · Steven Rostedt
Quoted 8 lines · On Wed, 4 Sep 2019 21:10:38 +0200 Viktor Rosendahl…

On 9/4/19 1:42 PM, Steven Rostedt wrote:

I am not so keen to clutter source files with a new copyright message. My problem is that git-send-email doesn't work well with my work email address, so I am forced to use my private gmail, which may create a false impression that I as a private individual would be the copyright holder.

Quoted 8 lines

Then do what I do:

Steven Rostedt (VMware) <[email protected]>

I did "(Red Hat)" when I worked for Red Hat.

-- Steve

Ok, that seems simple and effective. I will update accordingly for v7 of the patches.

best regards,

Viktor

#16 lore raw

PATCH v5 3/4 Add the latency-collector to tools

In reply to Viktor Rosendahl

This is a tool that is intended to work around the fact that the preemptoff, irqsoff, and preemptirqsoff tracers only work in overwrite mode. The idea is to act randomly in such a way that we do not systematically lose any latencies, so that if enough testing is done, all latencies will be captured. If the same burst of latencies is repeated, then sooner or later we will have captured all the latencies.

It also works with the wakeup_dl, wakeup_rt, wakeup, and hwlat tracers. However, in that case it is probably not useful to use the random sleep functionality.

The reason why it may be desirable to catch all latencies with a long test campaign is that for some organizations, it's necessary to test the kernel in the field and not practical for developers to work iteratively with field testers. Because of cost and project schedules it is not possible to start a new test campaign every time a latency problem has been fixed.

It uses inotify to detect changes to /sys/kernel/debug/tracing/trace. When a latency is detected, it will either sleep or print immediately, depending on a function that act as an unfair coin toss.

If immediate print is chosen, it means that we open /sys/kernel/debug/tracing/trace and thereby cause a blackout period that will hide any subsequent latencies.

If sleep is chosen, it means that we wait before opening /sys/kernel/debug/tracing/trace, by default for 1000 ms, to see if there is another latency during this period. If there is, then we will lose the previous latency. The coin will be tossed again with a different probability, and we will either print the new latency, or possibly a subsequent one.

The probability for the unfair coin toss is chosen so that there is equal probability to obtain any of the latencies in a burst. However, this assumes that we make an assumption of how many latencies there can be. By default the program assumes that there are no more than 2 latencies in a burst, the probability of immediate printout will be:

1/2 and 1

Thus, the probability of getting each of the two latencies will be 1/2.

If we ever find that there is more than one latency in a series, meaning that we reach the probability of 1, then the table will be expanded to:

1/3, 1/2, and 1

Thus, we assume that there are no more than three latencies and each with a probability of 1/3 of being captured. If the probability of 1 is reached in the new table, that is we see more than two closely occurring latencies, then the table will again be extended, and so on.

On my systems, it seems like this scheme works fairly well, as long as the latencies we trace are long enough, 300 us seems to be enough. This userspace program receive the inotify event at the end of a latency, and it has time until the end of the next latency to react, that is to open /sys/kernel/debug/tracing/trace. Thus, if we trace latencies that are >300 us, then we have at least 300 us to react.

The minimum latency will of course not be 300 us on all systems, it will depend on the hardware, kernel version, workload and configuration.

Example output:

root@myhost:~# echo 100 > /sys/kernel/debug/tracing/tracing_thresh
root@myhost:~# echo preemptirqsoff > /sys/kernel/debug/tracing/current_tracer
root@myhost:~# latency-collector -rvv -a 11 &
[1] 4915
root@myhost:~# Running with policy rr and priority 99. Using 3 print threads.
/sys/kernel/debug/tracing/trace will be printed with random delay
Start size of the probability table:                    11
Print a message when prob. table table changes size:    true
Print a warning when an event has been lost:            true
Sleep time is:                                          1000 ms
Initializing probability table to 11
Thread 4916 runs with policy rr and priority 99
Thread 4917 runs with policy rr and priority 99
Thread 4918 runs with policy rr and priority 99
Thread 4919 runs with policy rr and priority 99
root@myhost:~# modprobe preemptirq_delay_test delay=105 test_mode=alternate burst_size=10
2850.638308 Latency 1 printout skipped due to random delay
2850.638383 Latency 2 printout skipped due to random delay
2850.638497 Latency 3 immediate print
Quoted 1 line
Quoted 1 line
Quoted 1 line
Quoted 1 line
Quoted 1 line
Quoted 1 line
Quoted 1 line
Quoted 1 line
Quoted 1 line
Quoted 1 line
Quoted 1 line
Quoted 1 line
Quoted 1 line

BEGIN <<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<

alternat-4922    6d...    0us!: execute_preemptirqtest <-preemptirqtest_2
alternat-4922    6d...  106us : execute_preemptirqtest <-preemptirqtest_2
alternat-4922    6d...  106us : tracer_hardirqs_on <-preemptirqtest_2
alternat-4922    6d...  108us : <stack trace>

=> preemptirqtest_2
=> preemptirq_delay_run
=> kthread
=> ret_from_fork

Quoted 1 line
Quoted 1 line
Quoted 1 line
Quoted 1 line
Quoted 1 line
Quoted 1 line
Quoted 1 line
Quoted 1 line
Quoted 1 line
Quoted 1 line
Quoted 1 line
Quoted 1 line
Quoted 1 line

END <<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<

In the example above, we randomly, happened to get the third latency in a burst burst of 10. If the experiment is repeated enough times, we will get all 10.

Sometimes, there will be lost latencies, so that we get:

3054.078294 Latency 44 printout skipped due to inotify loop ..or:

3211.957685 Latency 112 printout skipped due to print loop

In my experience, these are not frequent enough to be a problem.

Also, we do not really lose any latency in these cases, it's more like we get another latency than what was intended by the design.

---
 tools/Makefile                  |   14 +-
 tools/trace/Makefile            |   20 +
 tools/trace/latency-collector.c | 1211 +++++++++++++++++++++++++++++++
 3 files changed, 1239 insertions(+), 6 deletions(-)
 create mode 100644 tools/trace/Makefile
 create mode 100644 tools/trace/latency-collector.c
tools/Makefile +8 -6
index 68defd7ecf5d..2b3738e66280 100644
@@ -30,6 +30,7 @@ help:
 	@echo '  spi                    - spi tools'
 	@echo '  objtool                - an ELF object analysis tool'
 	@echo '  tmon                   - thermal monitoring and tuning tool'
+	@echo '  trace                  - misc tracing tools'
 	@echo '  turbostat              - Intel CPU idle stats and freq reporting tool'
 	@echo '  usb                    - USB testing tools'
 	@echo '  virtio                 - vhost test module'
@@ -63,7 +64,7 @@ acpi: FORCE
 cpupower: FORCE
 	$(call descend,power/$@)
 
-cgroup firewire hv guest spi usb virtio vm bpf iio gpio objtool leds wmi pci firmware debugging: FORCE
+cgroup firewire hv guest spi usb virtio vm bpf iio gpio objtool leds wmi pci firmware debugging trace: FORCE
 	$(call descend,$@)
 
 liblockdep: FORCE
@@ -99,7 +100,7 @@ all: acpi cgroup cpupower gpio hv firewire liblockdep \
 		perf selftests spi turbostat usb \
 		virtio vm bpf x86_energy_perf_policy \
 		tmon freefall iio objtool kvm_stat wmi \
-		pci debugging
+		pci debugging trace
 
 acpi_install:
 	$(call descend,power/$(@:_install=),install)
@@ -107,7 +108,7 @@ acpi_install:
 cpupower_install:
 	$(call descend,power/$(@:_install=),install)
 
-cgroup_install firewire_install gpio_install hv_install iio_install perf_install spi_install usb_install virtio_install vm_install bpf_install objtool_install wmi_install pci_install debugging_install:
+cgroup_install firewire_install gpio_install hv_install iio_install perf_install spi_install usb_install virtio_install vm_install bpf_install objtool_install wmi_install pci_install debugging_install trace_install:
 	$(call descend,$(@:_install=),install)
 
 liblockdep_install:
@@ -133,7 +134,8 @@ install: acpi_install cgroup_install cpupower_install gpio_install \
 		perf_install selftests_install turbostat_install usb_install \
 		virtio_install vm_install bpf_install x86_energy_perf_policy_install \
 		tmon_install freefall_install objtool_install kvm_stat_install \
-		wmi_install pci_install debugging_install intel-speed-select_install
+		wmi_install pci_install debugging_install intel-speed-select_install \
+		trace_install
 
 acpi_clean:
 	$(call descend,power/acpi,clean)
@@ -141,7 +143,7 @@ acpi_clean:
 cpupower_clean:
 	$(call descend,power/cpupower,clean)
 
-cgroup_clean hv_clean firewire_clean spi_clean usb_clean virtio_clean vm_clean wmi_clean bpf_clean iio_clean gpio_clean objtool_clean leds_clean pci_clean firmware_clean debugging_clean:
+cgroup_clean hv_clean firewire_clean spi_clean usb_clean virtio_clean vm_clean wmi_clean bpf_clean iio_clean gpio_clean objtool_clean leds_clean pci_clean firmware_clean debugging_clean trace_clean:
 	$(call descend,$(@:_clean=),clean)
 
 liblockdep_clean:
@@ -180,6 +182,6 @@ clean: acpi_clean cgroup_clean cpupower_clean hv_clean firewire_clean \
 		vm_clean bpf_clean iio_clean x86_energy_perf_policy_clean tmon_clean \
 		freefall_clean build_clean libbpf_clean libsubcmd_clean liblockdep_clean \
 		gpio_clean objtool_clean leds_clean wmi_clean pci_clean firmware_clean debugging_clean \
-		intel-speed-select_clean
+		intel-speed-select_clean trace_clean
 
 .PHONY: FORCE
tools/trace/Makefile new file +20 -0
new file mode 100644
index 000000000000..59cd483ab01f
@@ -0,0 +1,20 @@
+# SPDX-License-Identifier: GPL-2.0
+# Makefile for vm tools
+#
+TARGETS = latency-collector
+CFLAGS = -Wall -Wextra -g -O2
+LDFLAGS = -lpthread
+
+all: $(TARGETS)
+
+%: %.c
+	$(CC) $(CFLAGS) -o $@ $< $(LDFLAGS)
+
+clean:
+	$(RM) latency-collector
+
+sbindir ?= /usr/sbin
+
+install: all
+	install -d $(DESTDIR)$(sbindir)
+	install -m 755 -p $(TARGETS) $(DESTDIR)$(sbindir)
tools/trace/latency-collector.c new file +1211 -0

1,211 lines not on this page · raw message

Signature · 1 line
2.17.1
#17 lore raw

PATCH v5 4/4 ftrace: Add an option for tracing console latencies

In reply to Viktor Rosendahl

This new trace option "console-latency" will enable the latency tracers to trace the console latencies. Previously this has always been implicitely disabled. I guess this is because they are considered to be well known and unavoidable.

However, for some organizations it may nevertheless be desirable to trace them. Basically, we want to be able to tell that there are latencies in the system under test because someone has incorrectly enabled the serial console.

---
 include/linux/irqflags.h     | 21 +++++++++++++++++++++
 kernel/printk/printk.c       |  6 ++++--
 kernel/trace/trace.h         |  1 +
 kernel/trace/trace_irqsoff.c | 12 ++++++++++++
 4 files changed, 38 insertions(+), 2 deletions(-)
include/linux/irqflags.h +21 -0
index 21619c92c377..34b0424a32dc 100644
@@ -68,9 +68,30 @@ do {						\
 	defined(CONFIG_PREEMPT_TRACER)
  extern void stop_critical_timings(void);
  extern void start_critical_timings(void);
+ extern bool console_tracing_disabled(void);
+
+# define console_stop_critical_timings(flag)		\
+	do {						\
+		typecheck(bool, flag);			\
+		flag = console_tracing_disabled();	\
+		if (flag)				\
+			stop_critical_timings();	\
+	} while (0)
+
+# define console_start_critical_timings(flag)		 \
+	do {						 \
+		typecheck(bool, flag);			 \
+		if (flag)				 \
+			start_critical_timings();	 \
+	} while (0)
+
 #else
 # define stop_critical_timings() do { } while (0)
 # define start_critical_timings() do { } while (0)
+# define console_stop_critical_timings(flag)	\
+	do { typecheck(bool, flag); } while (0)
+# define console_start_critical_timings(flag)	\
+	do { typecheck(bool, flag); } while (0)
 #endif
 
 /*
kernel/printk/printk.c +4 -2
index 1888f6a3b694..036460a7e4cd 100644
@@ -2359,6 +2359,7 @@ void console_unlock(void)
 	static char ext_text[CONSOLE_EXT_LOG_MAX];
 	static char text[LOG_LINE_MAX + PREFIX_MAX];
 	unsigned long flags;
+	bool cflag;
 	bool do_cond_resched, retry;
 
 	if (console_suspended) {
@@ -2459,9 +2460,10 @@ void console_unlock(void)
 		 */
 		console_lock_spinning_enable();
 
-		stop_critical_timings();	/* don't trace print latency */
+		/* don't trace print latency if it's disabled */
+		console_stop_critical_timings(cflag);
 		call_console_drivers(ext_text, ext_len, text, len);
-		start_critical_timings();
+		console_start_critical_timings(cflag);
 
 		if (console_lock_spinning_disable_and_check()) {
 			printk_safe_exit_irqrestore(flags);
kernel/trace/trace.h +1 -0
index d9f83b2aaa71..8e4c9736a801 100644
@@ -1266,6 +1266,7 @@ extern int trace_get_user(struct trace_parser *parser, const char __user *ubuf,
 		C(PRINTK_MSGONLY,	"printk-msg-only"),	\
 		C(CONTEXT_INFO,		"context-info"),   /* Print pid/cpu/time */ \
 		C(LATENCY_FMT,		"latency-format"),	\
+		C(CONSOLE_LATENCY,	"console-latency"),	\
 		C(RECORD_CMD,		"record-cmd"),		\
 		C(RECORD_TGID,		"record-tgid"),		\
 		C(OVERWRITE,		"overwrite"),		\
kernel/trace/trace_irqsoff.c +12 -0
index 29403a83a5f0..c8d17c4c1c91 100644
@@ -456,6 +456,18 @@ void stop_critical_timings(void)
 EXPORT_SYMBOL_GPL(stop_critical_timings);
 NOKPROBE_SYMBOL(stop_critical_timings);
 
+bool console_tracing_disabled(void)
+{
+	struct trace_array *tr = irqsoff_trace;
+	int pc = preempt_count();
+
+	if (!preempt_trace(pc) && !irq_trace())
+		return false;
+
+	return !(tr->trace_flags & TRACE_ITER_CONSOLE_LATENCY);
+}
+EXPORT_SYMBOL_GPL(console_tracing_disabled);
+
 #ifdef CONFIG_FUNCTION_TRACER
 static bool function_enabled;
 
Signature · 1 line
2.17.1
#18 lore raw

Re: [PATCH v5 4/4] ftrace: Add an option for tracing console latencies

Thank you for the patch! Yet something to improve:

Hi Viktor,

Thank you for the patch! Yet something to improve:

[auto build test ERROR on linus/master]
[cannot apply to v5.3-rc7 next-20190903]
[if your patch is applied to the wrong git tree, please drop us a note to help improve the system]

url: https://github.com/0day-ci/linux/commits/Viktor-Rosendahl/Some-new-features-for-the-preempt-irqsoff-tracers/20190904-083632
config: sh-allmodconfig (attached as .config)
compiler: sh4-linux-gcc (GCC) 7.4.0
reproduce:
wget https://raw.githubusercontent.com/intel/lkp-tests/master/sbin/make.cross -O ~/bin/make.cross chmod +x ~/bin/make.cross
# save the attached .config to linux build tree
GCC_VERSION=7.4.0 make.cross ARCH=sh

If you fix the issue, kindly add following tag

All errors (new ones prefixed by >>):

In file included from kernel/events/hw_breakpoint.c:20:0:

>> include/linux/irqflags.h:71:9: error: unknown type name 'bool'
     extern bool console_tracing_disabled(void);
            ^~~~

vim +/bool +71 include/linux/irqflags.h

    66	
    67	#if defined(CONFIG_IRQSOFF_TRACER) || \
    68		defined(CONFIG_PREEMPT_TRACER)
    69	 extern void stop_critical_timings(void);
    70	 extern void start_critical_timings(void);
  > 71	 extern bool console_tracing_disabled(void);
    72	

---
0-DAY kernel test infrastructure Open Source Technology Center
https://lists.01.org/pipermail/kbuild-all Intel Corporation