time: Remove CONFIG_TIMER_STATS

Currently CONFIG_TIMER_STATS exposes process information across namespaces:

kernel/time/timer_list.c print_timer():

        SEQ_printf(m, ", %s/%d", tmp, timer->start_pid);

/proc/timer_list:

 #11: <0000000000000000>, hrtimer_wakeup, S:01, do_nanosleep, cron/2570

Given that the tracer can give the same information, this patch entirely
removes CONFIG_TIMER_STATS.
Suggested-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Kees Cook <keescook@chromium.org>
Acked-by: John Stultz <john.stultz@linaro.org>
Cc: Nicolas Pitre <nicolas.pitre@linaro.org>
Cc: linux-doc@vger.kernel.org
Cc: Lai Jiangshan <jiangshanlai@gmail.com>
Cc: Shuah Khan <shuah@kernel.org>
Cc: Xing Gao <xgao01@email.wm.edu>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Jessica Frazelle <me@jessfraz.com>
Cc: kernel-hardening@lists.openwall.com
Cc: Nicolas Iooss <nicolas.iooss_linux@m4x.org>
Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Cc: Petr Mladek <pmladek@suse.com>
Cc: Richard Cochran <richardcochran@gmail.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: Michal Marek <mmarek@suse.com>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Dmitry Vyukov <dvyukov@google.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>
Cc: Olof Johansson <olof@lixom.net>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: linux-api@vger.kernel.org
Cc: Arjan van de Ven <arjan@linux.intel.com>
Link: http://lkml.kernel.org/r/20170208192659.GA32582@beastSigned-off-by: Thomas Gleixner <tglx@linutronix.de>

Documentation/timers/timer_stats.txt

-timer_stats - timer usage statistics
-------------------------------------
-
-timer_stats is a debugging facility to make the timer (ab)usage in a Linux
-system visible to kernel and userspace developers. If enabled in the config
-but not used it has almost zero runtime overhead, and a relatively small
-data structure overhead. Even if collection is enabled runtime all the
-locking is per-CPU and lookup is hashed.
-
-timer_stats should be used by kernel and userspace developers to verify that
-their code does not make unduly use of timers. This helps to avoid unnecessary
-wakeups, which should be avoided to optimize power consumption.
-
-It can be enabled by CONFIG_TIMER_STATS in the "Kernel hacking" configuration
-section.
-
-timer_stats collects information about the timer events which are fired in a
-Linux system over a sample period:
-
-- the pid of the task(process) which initialized the timer
-- the name of the process which initialized the timer
-- the function where the timer was initialized
-- the callback function which is associated to the timer
-- the number of events (callbacks)
-
-timer_stats adds an entry to /proc: /proc/timer_stats
-
-This entry is used to control the statistics functionality and to read out the
-sampled information.
-
-The timer_stats functionality is inactive on bootup.
-
-To activate a sample period issue:
-# echo 1 >/proc/timer_stats
-
-To stop a sample period issue:
-# echo 0 >/proc/timer_stats
-
-The statistics can be retrieved by:
-# cat /proc/timer_stats
-
-While sampling is enabled, each readout from /proc/timer_stats will see
-newly updated statistics. Once sampling is disabled, the sampled information
-is kept until a new sample period is started. This allows multiple readouts.
-
-Sample output of /proc/timer_stats:
-
-Timerstats sample period: 3.888770 s
-  12,     0 swapper          hrtimer_stop_sched_tick (hrtimer_sched_tick)
-  15,     1 swapper          hcd_submit_urb (rh_timer_func)
-   4,   959 kedac            schedule_timeout (process_timeout)
-   1,     0 swapper          page_writeback_init (wb_timer_fn)
-  28,     0 swapper          hrtimer_stop_sched_tick (hrtimer_sched_tick)
-  22,  2948 IRQ 4            tty_flip_buffer_push (delayed_work_timer_fn)
-   3,  3100 bash             schedule_timeout (process_timeout)
-   1,     1 swapper          queue_delayed_work_on (delayed_work_timer_fn)
-   1,     1 swapper          queue_delayed_work_on (delayed_work_timer_fn)
-   1,     1 swapper          neigh_table_init_no_netlink (neigh_periodic_timer)
-   1,  2292 ip               __netdev_watchdog_up (dev_watchdog)
-   1,    23 events/1         do_cache_clean (delayed_work_timer_fn)
-90 total events, 30.0 events/sec
-
-The first column is the number of events, the second column the pid, the third
-column is the name of the process. The forth column shows the function which
-initialized the timer and in parenthesis the callback function which was
-executed on expiry.
-
-    Thomas, Ingo
-
-Added flag to indicate 'deferrable timer' in /proc/timer_stats. A deferrable
-timer will appear as follows
-  10D,     1 swapper          queue_delayed_work_on (delayed_work_timer_fn)
-

include/linux/hrtimer.h

@@ -88,12 +88,6 @@ enum hrtimer_restart {
  * @base:	pointer to the timer base (per cpu and per clock)
  * @state:	state information (See bit values above)
  * @is_rel:	Set if the timer was armed relative
- * @start_pid:  timer statistics field to store the pid of the task which
- *		started the timer
- * @start_site:	timer statistics field to store the site where the timer
- *		was started
- * @start_comm: timer statistics field to store the name of the process which
- *		started the timer
  *
  * The hrtimer structure must be initialized by hrtimer_init()
  */
@@ -104,11 +98,6 @@ struct hrtimer {
 	struct hrtimer_clock_base	*base;
 	u8				state;
 	u8				is_rel;
-#ifdef CONFIG_TIMER_STATS
-	int				start_pid;
-	void				*start_site;
-	char				start_comm[16];
-#endif
 };
 
 /**

include/linux/timer.h

@@ -20,11 +20,6 @@ struct timer_list {
 	unsigned long		data;
 	u32			flags;
 
-#ifdef CONFIG_TIMER_STATS
-	int			start_pid;
-	void			*start_site;
-	char			start_comm[16];
-#endif
 #ifdef CONFIG_LOCKDEP
 	struct lockdep_map	lockdep_map;
 #endif
@@ -197,46 +192,6 @@ extern int mod_timer_pending(struct timer_list *timer, unsigned long expires);
  */
 #define NEXT_TIMER_MAX_DELTA	((1UL << 30) - 1)
 
-/*
- * Timer-statistics info:
- */
-#ifdef CONFIG_TIMER_STATS
-
-extern int timer_stats_active;
-
-extern void init_timer_stats(void);
-
-extern void timer_stats_update_stats(void *timer, pid_t pid, void *startf,
-				     void *timerf, char *comm, u32 flags);
-
-extern void __timer_stats_timer_set_start_info(struct timer_list *timer,
-					       void *addr);
-
-static inline void timer_stats_timer_set_start_info(struct timer_list *timer)
-{
-	if (likely(!timer_stats_active))
-		return;
-	__timer_stats_timer_set_start_info(timer, __builtin_return_address(0));
-}
-
-static inline void timer_stats_timer_clear_start_info(struct timer_list *timer)
-{
-	timer->start_site = NULL;
-}
-#else
-static inline void init_timer_stats(void)
-{
-}
-
-static inline void timer_stats_timer_set_start_info(struct timer_list *timer)
-{
-}
-
-static inline void timer_stats_timer_clear_start_info(struct timer_list *timer)
-{
-}
-#endif
-
 extern void add_timer(struct timer_list *timer);
 
 extern int try_to_del_timer_sync(struct timer_list *timer);

kernel/kthread.c

@@ -850,7 +850,6 @@ void __kthread_queue_delayed_work(struct kthread_worker *worker,
 
 	list_add(&work->node, &worker->delayed_work_list);
 	work->worker = worker;
-	timer_stats_timer_set_start_info(&dwork->timer);
 	timer->expires = jiffies + delay;
 	add_timer(timer);
 }

kernel/time/Makefile

@@ -15,6 +15,5 @@ ifeq ($(CONFIG_GENERIC_CLOCKEVENTS_BROADCAST),y)
 endif
 obj-$(CONFIG_GENERIC_SCHED_CLOCK)		+= sched_clock.o
 obj-$(CONFIG_TICK_ONESHOT)			+= tick-oneshot.o tick-sched.o
-obj-$(CONFIG_TIMER_STATS)			+= timer_stats.o
 obj-$(CONFIG_DEBUG_FS)				+= timekeeping_debug.o
 obj-$(CONFIG_TEST_UDELAY)			+= test_udelay.o

kernel/time/hrtimer.c

@@ -766,34 +766,6 @@ void hrtimers_resume(void)
 	clock_was_set_delayed();
 }
 
-static inline void timer_stats_hrtimer_set_start_info(struct hrtimer *timer)
-{
-#ifdef CONFIG_TIMER_STATS
-	if (timer->start_site)
-		return;
-	timer->start_site = __builtin_return_address(0);
-	memcpy(timer->start_comm, current->comm, TASK_COMM_LEN);
-	timer->start_pid = current->pid;
-#endif
-}
-
-static inline void timer_stats_hrtimer_clear_start_info(struct hrtimer *timer)
-{
-#ifdef CONFIG_TIMER_STATS
-	timer->start_site = NULL;
-#endif
-}
-
-static inline void timer_stats_account_hrtimer(struct hrtimer *timer)
-{
-#ifdef CONFIG_TIMER_STATS
-	if (likely(!timer_stats_active))
-		return;
-	timer_stats_update_stats(timer, timer->start_pid, timer->start_site,
-				 timer->function, timer->start_comm, 0);
-#endif
-}
-
 /*
  * Counterpart to lock_hrtimer_base above:
  */
@@ -932,7 +904,6 @@ remove_hrtimer(struct hrtimer *timer, struct hrtimer_clock_base *base, bool rest
 		 * rare case and less expensive than a smp call.
 		 */
 		debug_deactivate(timer);
-		timer_stats_hrtimer_clear_start_info(timer);
 		reprogram = base->cpu_base == this_cpu_ptr(&hrtimer_bases);
 
 		if (!restart)
@@ -990,8 +961,6 @@ void hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim,
 	/* Switch the timer base, if necessary: */
 	new_base = switch_hrtimer_base(timer, base, mode & HRTIMER_MODE_PINNED);
 
-	timer_stats_hrtimer_set_start_info(timer);
-
 	leftmost = enqueue_hrtimer(timer, new_base);
 	if (!leftmost)
 		goto unlock;
@@ -1128,12 +1097,6 @@ static void __hrtimer_init(struct hrtimer *timer, clockid_t clock_id,
 	base = hrtimer_clockid_to_base(clock_id);
 	timer->base = &cpu_base->clock_base[base];
 	timerqueue_init(&timer->node);
-
-#ifdef CONFIG_TIMER_STATS
-	timer->start_site = NULL;
-	timer->start_pid = -1;
-	memset(timer->start_comm, 0, TASK_COMM_LEN);
-#endif
 }
 
 /**
@@ -1217,7 +1180,6 @@ static void __run_hrtimer(struct hrtimer_cpu_base *cpu_base,
 	raw_write_seqcount_barrier(&cpu_base->seq);
 
 	__remove_hrtimer(timer, base, HRTIMER_STATE_INACTIVE, 0);
-	timer_stats_account_hrtimer(timer);
 	fn = timer->function;
 
 	/*

kernel/time/timer.c

@@ -571,38 +571,6 @@ internal_add_timer(struct timer_base *base, struct timer_list *timer)
 	trigger_dyntick_cpu(base, timer);
 }
 
-#ifdef CONFIG_TIMER_STATS
-void __timer_stats_timer_set_start_info(struct timer_list *timer, void *addr)
-{
-	if (timer->start_site)
-		return;
-
-	timer->start_site = addr;
-	memcpy(timer->start_comm, current->comm, TASK_COMM_LEN);
-	timer->start_pid = current->pid;
-}
-
-static void timer_stats_account_timer(struct timer_list *timer)
-{
-	void *site;
-
-	/*
-	 * start_site can be concurrently reset by
-	 * timer_stats_timer_clear_start_info()
-	 */
-	site = READ_ONCE(timer->start_site);
-	if (likely(!site))
-		return;
-
-	timer_stats_update_stats(timer, timer->start_pid, site,
-				 timer->function, timer->start_comm,
-				 timer->flags);
-}
-
-#else
-static void timer_stats_account_timer(struct timer_list *timer) {}
-#endif
-
 #ifdef CONFIG_DEBUG_OBJECTS_TIMERS
 
 static struct debug_obj_descr timer_debug_descr;
@@ -789,11 +757,6 @@ static void do_init_timer(struct timer_list *timer, unsigned int flags,
 {
 	timer->entry.pprev = NULL;
 	timer->flags = flags | raw_smp_processor_id();
-#ifdef CONFIG_TIMER_STATS
-	timer->start_site = NULL;
-	timer->start_pid = -1;
-	memset(timer->start_comm, 0, TASK_COMM_LEN);
-#endif
 	lockdep_init_map(&timer->lockdep_map, name, key, 0);
 }
 
@@ -1001,8 +964,6 @@ __mod_timer(struct timer_list *timer, unsigned long expires, bool pending_only)
 		base = lock_timer_base(timer, &flags);
 	}
 
-	timer_stats_timer_set_start_info(timer);
-
 	ret = detach_if_pending(timer, base, false);
 	if (!ret && pending_only)
 		goto out_unlock;
@@ -1130,7 +1091,6 @@ void add_timer_on(struct timer_list *timer, int cpu)
 	struct timer_base *new_base, *base;
 	unsigned long flags;
 
-	timer_stats_timer_set_start_info(timer);
 	BUG_ON(timer_pending(timer) || !timer->function);
 
 	new_base = get_timer_cpu_base(timer->flags, cpu);
@@ -1176,7 +1136,6 @@ int del_timer(struct timer_list *timer)
 
 	debug_assert_init(timer);
 
-	timer_stats_timer_clear_start_info(timer);
 	if (timer_pending(timer)) {
 		base = lock_timer_base(timer, &flags);
 		ret = detach_if_pending(timer, base, true);
@@ -1204,10 +1163,9 @@ int try_to_del_timer_sync(struct timer_list *timer)
 
 	base = lock_timer_base(timer, &flags);
 
-	if (base->running_timer != timer) {
-		timer_stats_timer_clear_start_info(timer);
+	if (base->running_timer != timer)
 		ret = detach_if_pending(timer, base, true);
-	}
+
 	spin_unlock_irqrestore(&base->lock, flags);
 
 	return ret;
@@ -1331,7 +1289,6 @@ static void expire_timers(struct timer_base *base, struct hlist_head *head)
 		unsigned long data;
 
 		timer = hlist_entry(head->first, struct timer_list, entry);
-		timer_stats_account_timer(timer);
 
 		base->running_timer = timer;
 		detach_timer(timer, true);
@@ -1868,7 +1825,6 @@ static void __init init_timer_cpus(void)
 void __init init_timers(void)
 {
 	init_timer_cpus();
-	init_timer_stats();
 	open_softirq(TIMER_SOFTIRQ, run_timer_softirq);
 }
 

kernel/time/timer_list.c

@@ -62,21 +62,11 @@ static void
 print_timer(struct seq_file *m, struct hrtimer *taddr, struct hrtimer *timer,
 	    int idx, u64 now)
 {
-#ifdef CONFIG_TIMER_STATS
-	char tmp[TASK_COMM_LEN + 1];
-#endif
 	SEQ_printf(m, " #%d: ", idx);
 	print_name_offset(m, taddr);
 	SEQ_printf(m, ", ");
 	print_name_offset(m, timer->function);
 	SEQ_printf(m, ", S:%02x", timer->state);
-#ifdef CONFIG_TIMER_STATS
-	SEQ_printf(m, ", ");
-	print_name_offset(m, timer->start_site);
-	memcpy(tmp, timer->start_comm, TASK_COMM_LEN);
-	tmp[TASK_COMM_LEN] = 0;
-	SEQ_printf(m, ", %s/%d", tmp, timer->start_pid);
-#endif
 	SEQ_printf(m, "\n");
 	SEQ_printf(m, " # expires at %Lu-%Lu nsecs [in %Ld to %Ld nsecs]\n",
 		(unsigned long long)ktime_to_ns(hrtimer_get_softexpires(timer)),

kernel/workqueue.c

@@ -1523,8 +1523,6 @@ static void __queue_delayed_work(int cpu, struct workqueue_struct *wq,
 		return;
 	}
 
-	timer_stats_timer_set_start_info(&dwork->timer);
-
 	dwork->wq = wq;
 	dwork->cpu = cpu;
 	timer->expires = jiffies + delay;

lib/Kconfig.debug

@@ -980,20 +980,6 @@ config DEBUG_TIMEKEEPING
 
 	  If unsure, say N.
 
-config TIMER_STATS
-	bool "Collect kernel timers statistics"
-	depends on DEBUG_KERNEL && PROC_FS
-	help
-	  If you say Y here, additional code will be inserted into the
-	  timer routines to collect statistics about kernel timers being
-	  reprogrammed. The statistics can be read from /proc/timer_stats.
-	  The statistics collection is started by writing 1 to /proc/timer_stats,
-	  writing 0 stops it. This feature is useful to collect information
-	  about timer usage patterns in kernel and userspace. This feature
-	  is lightweight if enabled in the kernel config but not activated
-	  (it defaults to deactivated on bootup and will only be activated
-	  if some application like powertop activates it explicitly).
-
 config DEBUG_PREEMPT
 	bool "Debug preemptible kernel"
 	depends on DEBUG_KERNEL && PREEMPT && TRACE_IRQFLAGS_SUPPORT