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@beast
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

5 files changed, 2 insertions, 520 deletions

diff --git a/kernel/time/Makefile b/kernel/time/Makefile
index 976840d29a71..938dbf33ef49 100644
--- a/kernel/time/Makefile
+++ b/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
diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c
index c6ecedd3b839..edabde646e58 100644
--- a/kernel/time/hrtimer.c
+++ b/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;
 
 	/*
diff --git a/kernel/time/timer.c b/kernel/time/timer.c
index ec33a6933eae..82a6bfa0c307 100644
--- a/kernel/time/timer.c
+++ b/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);
 }
 
diff --git a/kernel/time/timer_list.c b/kernel/time/timer_list.c
index afe6cd1944fc..387a3a5aa388 100644
--- a/kernel/time/timer_list.c
+++ b/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)),
diff --git a/kernel/time/timer_stats.c b/kernel/time/timer_stats.c
deleted file mode 100644
index afddded947df..000000000000
--- a/kernel/time/timer_stats.c
+++ /dev/null
@@ -1,425 +0,0 @@
-/*
- * kernel/time/timer_stats.c
- *
- * Collect timer usage statistics.
- *
- * Copyright(C) 2006, Red Hat, Inc., Ingo Molnar
- * Copyright(C) 2006 Timesys Corp., Thomas Gleixner <tglx@timesys.com>
- *
- * timer_stats is based on timer_top, a similar functionality which was part of
- * Con Kolivas dyntick patch set. It was developed by Daniel Petrini at the
- * Instituto Nokia de Tecnologia - INdT - Manaus. timer_top's design was based
- * on dynamic allocation of the statistics entries and linear search based
- * lookup combined with a global lock, rather than the static array, hash
- * and per-CPU locking which is used by timer_stats. It was written for the
- * pre hrtimer kernel code and therefore did not take hrtimers into account.
- * Nevertheless it provided the base for the timer_stats implementation and
- * was a helpful source of inspiration. Kudos to Daniel and the Nokia folks
- * for this effort.
- *
- * timer_top.c is
- *	Copyright (C) 2005 Instituto Nokia de Tecnologia - INdT - Manaus
- *	Written by Daniel Petrini <d.pensator@gmail.com>
- *	timer_top.c was released under the GNU General Public License version 2
- *
- * We export the addresses and counting of timer functions being called,
- * the pid and cmdline from the owner process if applicable.
- *
- * Start/stop data collection:
- * # echo [1|0] >/proc/timer_stats
- *
- * Display the information collected so far:
- * # cat /proc/timer_stats
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#include <linux/proc_fs.h>
-#include <linux/module.h>
-#include <linux/spinlock.h>
-#include <linux/sched.h>
-#include <linux/seq_file.h>
-#include <linux/kallsyms.h>
-
-#include <linux/uaccess.h>
-
-/*
- * This is our basic unit of interest: a timer expiry event identified
- * by the timer, its start/expire functions and the PID of the task that
- * started the timer. We count the number of times an event happens:
- */
-struct entry {
-	/*
-	 * Hash list:
-	 */
-	struct entry		*next;
-
-	/*
-	 * Hash keys:
-	 */
-	void			*timer;
-	void			*start_func;
-	void			*expire_func;
-	pid_t			pid;
-
-	/*
-	 * Number of timeout events:
-	 */
-	unsigned long		count;
-	u32			flags;
-
-	/*
-	 * We save the command-line string to preserve
-	 * this information past task exit:
-	 */
-	char			comm[TASK_COMM_LEN + 1];
-
-} ____cacheline_aligned_in_smp;
-
-/*
- * Spinlock protecting the tables - not taken during lookup:
- */
-static DEFINE_RAW_SPINLOCK(table_lock);
-
-/*
- * Per-CPU lookup locks for fast hash lookup:
- */
-static DEFINE_PER_CPU(raw_spinlock_t, tstats_lookup_lock);
-
-/*
- * Mutex to serialize state changes with show-stats activities:
- */
-static DEFINE_MUTEX(show_mutex);
-
-/*
- * Collection status, active/inactive:
- */
-int __read_mostly timer_stats_active;
-
-/*
- * Beginning/end timestamps of measurement:
- */
-static ktime_t time_start, time_stop;
-
-/*
- * tstat entry structs only get allocated while collection is
- * active and never freed during that time - this simplifies
- * things quite a bit.
- *
- * They get freed when a new collection period is started.
- */
-#define MAX_ENTRIES_BITS	10
-#define MAX_ENTRIES		(1UL << MAX_ENTRIES_BITS)
-
-static unsigned long nr_entries;
-static struct entry entries[MAX_ENTRIES];
-
-static atomic_t overflow_count;
-
-/*
- * The entries are in a hash-table, for fast lookup:
- */
-#define TSTAT_HASH_BITS		(MAX_ENTRIES_BITS - 1)
-#define TSTAT_HASH_SIZE		(1UL << TSTAT_HASH_BITS)
-#define TSTAT_HASH_MASK		(TSTAT_HASH_SIZE - 1)
-
-#define __tstat_hashfn(entry)						\
-	(((unsigned long)(entry)->timer       ^				\
-	  (unsigned long)(entry)->start_func  ^				\
-	  (unsigned long)(entry)->expire_func ^				\
-	  (unsigned long)(entry)->pid		) & TSTAT_HASH_MASK)
-
-#define tstat_hashentry(entry)	(tstat_hash_table + __tstat_hashfn(entry))
-
-static struct entry *tstat_hash_table[TSTAT_HASH_SIZE] __read_mostly;
-
-static void reset_entries(void)
-{
-	nr_entries = 0;
-	memset(entries, 0, sizeof(entries));
-	memset(tstat_hash_table, 0, sizeof(tstat_hash_table));
-	atomic_set(&overflow_count, 0);
-}
-
-static struct entry *alloc_entry(void)
-{
-	if (nr_entries >= MAX_ENTRIES)
-		return NULL;
-
-	return entries + nr_entries++;
-}
-
-static int match_entries(struct entry *entry1, struct entry *entry2)
-{
-	return entry1->timer       == entry2->timer	  &&
-	       entry1->start_func  == entry2->start_func  &&
-	       entry1->expire_func == entry2->expire_func &&
-	       entry1->pid	   == entry2->pid;
-}
-
-/*
- * Look up whether an entry matching this item is present
- * in the hash already. Must be called with irqs off and the
- * lookup lock held:
- */
-static struct entry *tstat_lookup(struct entry *entry, char *comm)
-{
-	struct entry **head, *curr, *prev;
-
-	head = tstat_hashentry(entry);
-	curr = *head;
-
-	/*
-	 * The fastpath is when the entry is already hashed,
-	 * we do this with the lookup lock held, but with the
-	 * table lock not held:
-	 */
-	while (curr) {
-		if (match_entries(curr, entry))
-			return curr;
-
-		curr = curr->next;
-	}
-	/*
-	 * Slowpath: allocate, set up and link a new hash entry:
-	 */
-	prev = NULL;
-	curr = *head;
-
-	raw_spin_lock(&table_lock);
-	/*
-	 * Make sure we have not raced with another CPU:
-	 */
-	while (curr) {
-		if (match_entries(curr, entry))
-			goto out_unlock;
-
-		prev = curr;
-		curr = curr->next;
-	}
-
-	curr = alloc_entry();
-	if (curr) {
-		*curr = *entry;
-		curr->count = 0;
-		curr->next = NULL;
-		memcpy(curr->comm, comm, TASK_COMM_LEN);
-
-		smp_mb(); /* Ensure that curr is initialized before insert */
-
-		if (prev)
-			prev->next = curr;
-		else
-			*head = curr;
-	}
- out_unlock:
-	raw_spin_unlock(&table_lock);
-
-	return curr;
-}
-
-/**
- * timer_stats_update_stats - Update the statistics for a timer.
- * @timer:	pointer to either a timer_list or a hrtimer
- * @pid:	the pid of the task which set up the timer
- * @startf:	pointer to the function which did the timer setup
- * @timerf:	pointer to the timer callback function of the timer
- * @comm:	name of the process which set up the timer
- * @tflags:	The flags field of the timer
- *
- * When the timer is already registered, then the event counter is
- * incremented. Otherwise the timer is registered in a free slot.
- */
-void timer_stats_update_stats(void *timer, pid_t pid, void *startf,
-			      void *timerf, char *comm, u32 tflags)
-{
-	/*
-	 * It doesn't matter which lock we take:
-	 */
-	raw_spinlock_t *lock;
-	struct entry *entry, input;
-	unsigned long flags;
-
-	if (likely(!timer_stats_active))
-		return;
-
-	lock = &per_cpu(tstats_lookup_lock, raw_smp_processor_id());
-
-	input.timer = timer;
-	input.start_func = startf;
-	input.expire_func = timerf;
-	input.pid = pid;
-	input.flags = tflags;
-
-	raw_spin_lock_irqsave(lock, flags);
-	if (!timer_stats_active)
-		goto out_unlock;
-
-	entry = tstat_lookup(&input, comm);
-	if (likely(entry))
-		entry->count++;
-	else
-		atomic_inc(&overflow_count);
-
- out_unlock:
-	raw_spin_unlock_irqrestore(lock, flags);
-}
-
-static void print_name_offset(struct seq_file *m, unsigned long addr)
-{
-	char symname[KSYM_NAME_LEN];
-
-	if (lookup_symbol_name(addr, symname) < 0)
-		seq_printf(m, "<%p>", (void *)addr);
-	else
-		seq_printf(m, "%s", symname);
-}
-
-static int tstats_show(struct seq_file *m, void *v)
-{
-	struct timespec64 period;
-	struct entry *entry;
-	unsigned long ms;
-	long events = 0;
-	ktime_t time;
-	int i;
-
-	mutex_lock(&show_mutex);
-	/*
-	 * If still active then calculate up to now:
-	 */
-	if (timer_stats_active)
-		time_stop = ktime_get();
-
-	time = ktime_sub(time_stop, time_start);
-
-	period = ktime_to_timespec64(time);
-	ms = period.tv_nsec / 1000000;
-
-	seq_puts(m, "Timer Stats Version: v0.3\n");
-	seq_printf(m, "Sample period: %ld.%03ld s\n", (long)period.tv_sec, ms);
-	if (atomic_read(&overflow_count))
-		seq_printf(m, "Overflow: %d entries\n", atomic_read(&overflow_count));
-	seq_printf(m, "Collection: %s\n", timer_stats_active ? "active" : "inactive");
-
-	for (i = 0; i < nr_entries; i++) {
-		entry = entries + i;
-		if (entry->flags & TIMER_DEFERRABLE) {
-			seq_printf(m, "%4luD, %5d %-16s ",
-				entry->count, entry->pid, entry->comm);
-		} else {
-			seq_printf(m, " %4lu, %5d %-16s ",
-				entry->count, entry->pid, entry->comm);
-		}
-
-		print_name_offset(m, (unsigned long)entry->start_func);
-		seq_puts(m, " (");
-		print_name_offset(m, (unsigned long)entry->expire_func);
-		seq_puts(m, ")\n");
-
-		events += entry->count;
-	}
-
-	ms += period.tv_sec * 1000;
-	if (!ms)
-		ms = 1;
-
-	if (events && period.tv_sec)
-		seq_printf(m, "%ld total events, %ld.%03ld events/sec\n",
-			   events, events * 1000 / ms,
-			   (events * 1000000 / ms) % 1000);
-	else
-		seq_printf(m, "%ld total events\n", events);
-
-	mutex_unlock(&show_mutex);
-
-	return 0;
-}
-
-/*
- * After a state change, make sure all concurrent lookup/update
- * activities have stopped:
- */
-static void sync_access(void)
-{
-	unsigned long flags;
-	int cpu;
-
-	for_each_online_cpu(cpu) {
-		raw_spinlock_t *lock = &per_cpu(tstats_lookup_lock, cpu);
-
-		raw_spin_lock_irqsave(lock, flags);
-		/* nothing */
-		raw_spin_unlock_irqrestore(lock, flags);
-	}
-}
-
-static ssize_t tstats_write(struct file *file, const char __user *buf,
-			    size_t count, loff_t *offs)
-{
-	char ctl[2];
-
-	if (count != 2 || *offs)
-		return -EINVAL;
-
-	if (copy_from_user(ctl, buf, count))
-		return -EFAULT;
-
-	mutex_lock(&show_mutex);
-	switch (ctl[0]) {
-	case '0':
-		if (timer_stats_active) {
-			timer_stats_active = 0;
-			time_stop = ktime_get();
-			sync_access();
-		}
-		break;
-	case '1':
-		if (!timer_stats_active) {
-			reset_entries();
-			time_start = ktime_get();
-			smp_mb();
-			timer_stats_active = 1;
-		}
-		break;
-	default:
-		count = -EINVAL;
-	}
-	mutex_unlock(&show_mutex);
-
-	return count;
-}
-
-static int tstats_open(struct inode *inode, struct file *filp)
-{
-	return single_open(filp, tstats_show, NULL);
-}
-
-static const struct file_operations tstats_fops = {
-	.open		= tstats_open,
-	.read		= seq_read,
-	.write		= tstats_write,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
-void __init init_timer_stats(void)
-{
-	int cpu;
-
-	for_each_possible_cpu(cpu)
-		raw_spin_lock_init(&per_cpu(tstats_lookup_lock, cpu));
-}
-
-static int __init init_tstats_procfs(void)
-{
-	struct proc_dir_entry *pe;
-
-	pe = proc_create("timer_stats", 0644, NULL, &tstats_fops);
-	if (!pe)
-		return -ENOMEM;
-	return 0;
-}
-__initcall(init_tstats_procfs);