From 40d9f82750044f846005d2ac4eec65e39c1c0f7c Mon Sep 17 00:00:00 2001 From: Stephen Boyd Date: Wed, 7 Dec 2016 14:33:23 -0800 Subject: timekeeping: Remove unused timekeeping_{get,set}_tai_offset() The last caller to timekeeping_set_tai_offset() was in commit 0b5154fb9040 (timekeeping: Simplify tai updating from do_adjtimex, 2013-03-22) and the last caller to timekeeping_get_tai_offset() was in commit 76f4108892d9 (hrtimer: Cleanup hrtimer accessors to the timekepeing state, 2014-07-16). Remove these unused functions now that we handle TAI offsets differently. Cc: John Stultz Signed-off-by: Stephen Boyd Signed-off-by: John Stultz --- kernel/time/timekeeping.c | 39 +-------------------------------------- kernel/time/timekeeping.h | 2 -- 2 files changed, 1 insertion(+), 40 deletions(-) (limited to 'kernel') diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index db087d7e106d..95b258dd75db 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -1275,27 +1275,8 @@ error: /* even if we error out, we forwarded the time, so call update */ } EXPORT_SYMBOL(timekeeping_inject_offset); - -/** - * timekeeping_get_tai_offset - Returns current TAI offset from UTC - * - */ -s32 timekeeping_get_tai_offset(void) -{ - struct timekeeper *tk = &tk_core.timekeeper; - unsigned int seq; - s32 ret; - - do { - seq = read_seqcount_begin(&tk_core.seq); - ret = tk->tai_offset; - } while (read_seqcount_retry(&tk_core.seq, seq)); - - return ret; -} - /** - * __timekeeping_set_tai_offset - Lock free worker function + * __timekeeping_set_tai_offset - Sets the TAI offset from UTC and monotonic * */ static void __timekeeping_set_tai_offset(struct timekeeper *tk, s32 tai_offset) @@ -1304,24 +1285,6 @@ static void __timekeeping_set_tai_offset(struct timekeeper *tk, s32 tai_offset) tk->offs_tai = ktime_add(tk->offs_real, ktime_set(tai_offset, 0)); } -/** - * timekeeping_set_tai_offset - Sets the current TAI offset from UTC - * - */ -void timekeeping_set_tai_offset(s32 tai_offset) -{ - struct timekeeper *tk = &tk_core.timekeeper; - unsigned long flags; - - raw_spin_lock_irqsave(&timekeeper_lock, flags); - write_seqcount_begin(&tk_core.seq); - __timekeeping_set_tai_offset(tk, tai_offset); - timekeeping_update(tk, TK_MIRROR | TK_CLOCK_WAS_SET); - write_seqcount_end(&tk_core.seq); - raw_spin_unlock_irqrestore(&timekeeper_lock, flags); - clock_was_set(); -} - /** * change_clocksource - Swaps clocksources if a new one is available * diff --git a/kernel/time/timekeeping.h b/kernel/time/timekeeping.h index 704f595ce83f..d0914676d4c5 100644 --- a/kernel/time/timekeeping.h +++ b/kernel/time/timekeeping.h @@ -11,8 +11,6 @@ extern ktime_t ktime_get_update_offsets_now(unsigned int *cwsseq, extern int timekeeping_valid_for_hres(void); extern u64 timekeeping_max_deferment(void); extern int timekeeping_inject_offset(struct timespec *ts); -extern s32 timekeeping_get_tai_offset(void); -extern void timekeeping_set_tai_offset(s32 tai_offset); extern int timekeeping_suspend(void); extern void timekeeping_resume(void); -- cgit v1.2.3 From b18b6a9cef7f30e9a8b7738d5fc8d568cf660855 Mon Sep 17 00:00:00 2001 From: Nicolas Pitre Date: Sat, 21 Jan 2017 00:09:08 -0500 Subject: timers: Omit POSIX timer stuff from task_struct when disabled When CONFIG_POSIX_TIMERS is disabled, it is preferable to remove related structures from struct task_struct and struct signal_struct as they won't contain anything useful and shouldn't be relied upon by mistake. Code still referencing those structures is also disabled here. Signed-off-by: Nicolas Pitre Signed-off-by: John Stultz --- fs/proc/base.c | 4 ++-- include/linux/init_task.h | 40 +++++++++++++++++++++++++--------------- include/linux/sched.h | 13 ++++++++++--- kernel/fork.c | 10 +++++++++- kernel/sched/rt.c | 4 ++++ kernel/sched/stats.h | 32 ++++++++++++++++++++------------ 6 files changed, 70 insertions(+), 33 deletions(-) (limited to 'kernel') diff --git a/fs/proc/base.c b/fs/proc/base.c index 8e7e61b28f31..03deeac1e835 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -2179,7 +2179,7 @@ static const struct file_operations proc_map_files_operations = { .llseek = generic_file_llseek, }; -#ifdef CONFIG_CHECKPOINT_RESTORE +#if defined(CONFIG_CHECKPOINT_RESTORE) && defined(CONFIG_POSIX_TIMERS) struct timers_private { struct pid *pid; struct task_struct *task; @@ -2936,7 +2936,7 @@ static const struct pid_entry tgid_base_stuff[] = { REG("projid_map", S_IRUGO|S_IWUSR, proc_projid_map_operations), REG("setgroups", S_IRUGO|S_IWUSR, proc_setgroups_operations), #endif -#ifdef CONFIG_CHECKPOINT_RESTORE +#if defined(CONFIG_CHECKPOINT_RESTORE) && defined(CONFIG_POSIX_TIMERS) REG("timers", S_IRUGO, proc_timers_operations), #endif REG("timerslack_ns", S_IRUGO|S_IWUGO, proc_pid_set_timerslack_ns_operations), diff --git a/include/linux/init_task.h b/include/linux/init_task.h index 325f649d77ff..3a85d61f7614 100644 --- a/include/linux/init_task.h +++ b/include/linux/init_task.h @@ -42,6 +42,27 @@ extern struct fs_struct init_fs; #define INIT_PREV_CPUTIME(x) #endif +#ifdef CONFIG_POSIX_TIMERS +#define INIT_POSIX_TIMERS(s) \ + .posix_timers = LIST_HEAD_INIT(s.posix_timers), +#define INIT_CPU_TIMERS(s) \ + .cpu_timers = { \ + LIST_HEAD_INIT(s.cpu_timers[0]), \ + LIST_HEAD_INIT(s.cpu_timers[1]), \ + LIST_HEAD_INIT(s.cpu_timers[2]), \ + }, +#define INIT_CPUTIMER(s) \ + .cputimer = { \ + .cputime_atomic = INIT_CPUTIME_ATOMIC, \ + .running = false, \ + .checking_timer = false, \ + }, +#else +#define INIT_POSIX_TIMERS(s) +#define INIT_CPU_TIMERS(s) +#define INIT_CPUTIMER(s) +#endif + #define INIT_SIGNALS(sig) { \ .nr_threads = 1, \ .thread_head = LIST_HEAD_INIT(init_task.thread_node), \ @@ -49,14 +70,10 @@ extern struct fs_struct init_fs; .shared_pending = { \ .list = LIST_HEAD_INIT(sig.shared_pending.list), \ .signal = {{0}}}, \ - .posix_timers = LIST_HEAD_INIT(sig.posix_timers), \ - .cpu_timers = INIT_CPU_TIMERS(sig.cpu_timers), \ + INIT_POSIX_TIMERS(sig) \ + INIT_CPU_TIMERS(sig) \ .rlim = INIT_RLIMITS, \ - .cputimer = { \ - .cputime_atomic = INIT_CPUTIME_ATOMIC, \ - .running = false, \ - .checking_timer = false, \ - }, \ + INIT_CPUTIMER(sig) \ INIT_PREV_CPUTIME(sig) \ .cred_guard_mutex = \ __MUTEX_INITIALIZER(sig.cred_guard_mutex), \ @@ -247,7 +264,7 @@ extern struct task_group root_task_group; .blocked = {{0}}, \ .alloc_lock = __SPIN_LOCK_UNLOCKED(tsk.alloc_lock), \ .journal_info = NULL, \ - .cpu_timers = INIT_CPU_TIMERS(tsk.cpu_timers), \ + INIT_CPU_TIMERS(tsk) \ .pi_lock = __RAW_SPIN_LOCK_UNLOCKED(tsk.pi_lock), \ .timer_slack_ns = 50000, /* 50 usec default slack */ \ .pids = { \ @@ -274,13 +291,6 @@ extern struct task_group root_task_group; } -#define INIT_CPU_TIMERS(cpu_timers) \ -{ \ - LIST_HEAD_INIT(cpu_timers[0]), \ - LIST_HEAD_INIT(cpu_timers[1]), \ - LIST_HEAD_INIT(cpu_timers[2]), \ -} - /* Attach to the init_task data structure for proper alignment */ #define __init_task_data __attribute__((__section__(".data..init_task"))) diff --git a/include/linux/sched.h b/include/linux/sched.h index 4d1905245c7a..e8f6af59726d 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -734,13 +734,14 @@ struct signal_struct { unsigned int is_child_subreaper:1; unsigned int has_child_subreaper:1; +#ifdef CONFIG_POSIX_TIMERS + /* POSIX.1b Interval Timers */ int posix_timer_id; struct list_head posix_timers; /* ITIMER_REAL timer for the process */ struct hrtimer real_timer; - struct pid *leader_pid; ktime_t it_real_incr; /* @@ -759,12 +760,16 @@ struct signal_struct { /* Earliest-expiration cache. */ struct task_cputime cputime_expires; + struct list_head cpu_timers[3]; + +#endif + + struct pid *leader_pid; + #ifdef CONFIG_NO_HZ_FULL atomic_t tick_dep_mask; #endif - struct list_head cpu_timers[3]; - struct pid *tty_old_pgrp; /* boolean value for session group leader */ @@ -1681,8 +1686,10 @@ struct task_struct { /* mm fault and swap info: this can arguably be seen as either mm-specific or thread-specific */ unsigned long min_flt, maj_flt; +#ifdef CONFIG_POSIX_TIMERS struct task_cputime cputime_expires; struct list_head cpu_timers[3]; +#endif /* process credentials */ const struct cred __rcu *ptracer_cred; /* Tracer's credentials at attach */ diff --git a/kernel/fork.c b/kernel/fork.c index 11c5c8ab827c..105c6676d93b 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1304,6 +1304,7 @@ void __cleanup_sighand(struct sighand_struct *sighand) } } +#ifdef CONFIG_POSIX_TIMERS /* * Initialize POSIX timer handling for a thread group. */ @@ -1322,6 +1323,9 @@ static void posix_cpu_timers_init_group(struct signal_struct *sig) INIT_LIST_HEAD(&sig->cpu_timers[1]); INIT_LIST_HEAD(&sig->cpu_timers[2]); } +#else +static inline void posix_cpu_timers_init_group(struct signal_struct *sig) { } +#endif static int copy_signal(unsigned long clone_flags, struct task_struct *tsk) { @@ -1346,11 +1350,11 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk) init_waitqueue_head(&sig->wait_chldexit); sig->curr_target = tsk; init_sigpending(&sig->shared_pending); - INIT_LIST_HEAD(&sig->posix_timers); seqlock_init(&sig->stats_lock); prev_cputime_init(&sig->prev_cputime); #ifdef CONFIG_POSIX_TIMERS + INIT_LIST_HEAD(&sig->posix_timers); hrtimer_init(&sig->real_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); sig->real_timer.function = it_real_fn; #endif @@ -1425,6 +1429,7 @@ static void rt_mutex_init_task(struct task_struct *p) #endif } +#ifdef CONFIG_POSIX_TIMERS /* * Initialize POSIX timer handling for a single task. */ @@ -1437,6 +1442,9 @@ static void posix_cpu_timers_init(struct task_struct *tsk) INIT_LIST_HEAD(&tsk->cpu_timers[1]); INIT_LIST_HEAD(&tsk->cpu_timers[2]); } +#else +static inline void posix_cpu_timers_init(struct task_struct *tsk) { } +#endif static inline void init_task_pid(struct task_struct *task, enum pid_type type, struct pid *pid) diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c index 2516b8df6dbb..a688a8206727 100644 --- a/kernel/sched/rt.c +++ b/kernel/sched/rt.c @@ -2246,6 +2246,7 @@ prio_changed_rt(struct rq *rq, struct task_struct *p, int oldprio) } } +#ifdef CONFIG_POSIX_TIMERS static void watchdog(struct rq *rq, struct task_struct *p) { unsigned long soft, hard; @@ -2267,6 +2268,9 @@ static void watchdog(struct rq *rq, struct task_struct *p) p->cputime_expires.sched_exp = p->se.sum_exec_runtime; } } +#else +static inline void watchdog(struct rq *rq, struct task_struct *p) { } +#endif static void task_tick_rt(struct rq *rq, struct task_struct *p, int queued) { diff --git a/kernel/sched/stats.h b/kernel/sched/stats.h index 34659a853505..c69a9870ab79 100644 --- a/kernel/sched/stats.h +++ b/kernel/sched/stats.h @@ -172,18 +172,19 @@ sched_info_switch(struct rq *rq, */ /** - * cputimer_running - return true if cputimer is running + * get_running_cputimer - return &tsk->signal->cputimer if cputimer is running * * @tsk: Pointer to target task. */ -static inline bool cputimer_running(struct task_struct *tsk) - +#ifdef CONFIG_POSIX_TIMERS +static inline +struct thread_group_cputimer *get_running_cputimer(struct task_struct *tsk) { struct thread_group_cputimer *cputimer = &tsk->signal->cputimer; /* Check if cputimer isn't running. This is accessed without locking. */ if (!READ_ONCE(cputimer->running)) - return false; + return NULL; /* * After we flush the task's sum_exec_runtime to sig->sum_sched_runtime @@ -200,10 +201,17 @@ static inline bool cputimer_running(struct task_struct *tsk) * clock delta is behind the expiring timer value. */ if (unlikely(!tsk->sighand)) - return false; + return NULL; - return true; + return cputimer; +} +#else +static inline +struct thread_group_cputimer *get_running_cputimer(struct task_struct *tsk) +{ + return NULL; } +#endif /** * account_group_user_time - Maintain utime for a thread group. @@ -218,9 +226,9 @@ static inline bool cputimer_running(struct task_struct *tsk) static inline void account_group_user_time(struct task_struct *tsk, cputime_t cputime) { - struct thread_group_cputimer *cputimer = &tsk->signal->cputimer; + struct thread_group_cputimer *cputimer = get_running_cputimer(tsk); - if (!cputimer_running(tsk)) + if (!cputimer) return; atomic64_add(cputime, &cputimer->cputime_atomic.utime); @@ -239,9 +247,9 @@ static inline void account_group_user_time(struct task_struct *tsk, static inline void account_group_system_time(struct task_struct *tsk, cputime_t cputime) { - struct thread_group_cputimer *cputimer = &tsk->signal->cputimer; + struct thread_group_cputimer *cputimer = get_running_cputimer(tsk); - if (!cputimer_running(tsk)) + if (!cputimer) return; atomic64_add(cputime, &cputimer->cputime_atomic.stime); @@ -260,9 +268,9 @@ static inline void account_group_system_time(struct task_struct *tsk, static inline void account_group_exec_runtime(struct task_struct *tsk, unsigned long long ns) { - struct thread_group_cputimer *cputimer = &tsk->signal->cputimer; + struct thread_group_cputimer *cputimer = get_running_cputimer(tsk); - if (!cputimer_running(tsk)) + if (!cputimer) return; atomic64_add(ns, &cputimer->cputime_atomic.sum_exec_runtime); -- cgit v1.2.3 From 668802c25729a8e3423015c33c05f1c3be3858e9 Mon Sep 17 00:00:00 2001 From: Waiman Long Date: Mon, 30 Jan 2017 12:57:43 -0500 Subject: tick/broadcast: Reduce lock cacheline contention It was observed that on an Intel x86 system without the ARAT (Always running APIC timer) feature and with fairly large number of CPUs as well as CPUs coming in and out of intel_idle frequently, the lock contention on the tick_broadcast_lock can become significant. To reduce contention, the lock is put into its own cacheline and all the cpumask_var_t variables are put into the __read_mostly section. Running the SP benchmark of the NAS Parallel Benchmarks on a 4-socket 16-core 32-thread Nehalam system, the performance number improved from 3353.94 Mop/s to 3469.31 Mop/s when this patch was applied on a 4.9.6 kernel. This is a 3.4% improvement. Signed-off-by: Waiman Long Cc: "Peter Zijlstra (Intel)" Cc: Andrew Morton Link: http://lkml.kernel.org/r/1485799063-20857-1-git-send-email-longman@redhat.com Signed-off-by: Thomas Gleixner --- include/linux/cpumask.h | 7 ++++++- kernel/time/tick-broadcast.c | 15 ++++++++------- 2 files changed, 14 insertions(+), 8 deletions(-) (limited to 'kernel') diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h index c717f5ea88cb..23c1a6d09ec5 100644 --- a/include/linux/cpumask.h +++ b/include/linux/cpumask.h @@ -649,11 +649,15 @@ static inline size_t cpumask_size(void) * used. Please use this_cpu_cpumask_var_t in those cases. The direct use * of this_cpu_ptr() or this_cpu_read() will lead to failures when the * other type of cpumask_var_t implementation is configured. + * + * Please also note that __cpumask_var_read_mostly can be used to declare + * a cpumask_var_t variable itself (not its content) as read mostly. */ #ifdef CONFIG_CPUMASK_OFFSTACK typedef struct cpumask *cpumask_var_t; -#define this_cpu_cpumask_var_ptr(x) this_cpu_read(x) +#define this_cpu_cpumask_var_ptr(x) this_cpu_read(x) +#define __cpumask_var_read_mostly __read_mostly bool alloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, int node); bool alloc_cpumask_var(cpumask_var_t *mask, gfp_t flags); @@ -667,6 +671,7 @@ void free_bootmem_cpumask_var(cpumask_var_t mask); typedef struct cpumask cpumask_var_t[1]; #define this_cpu_cpumask_var_ptr(x) this_cpu_ptr(x) +#define __cpumask_var_read_mostly static inline bool alloc_cpumask_var(cpumask_var_t *mask, gfp_t flags) { diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c index 3109204c87cc..244c93544150 100644 --- a/kernel/time/tick-broadcast.c +++ b/kernel/time/tick-broadcast.c @@ -29,12 +29,13 @@ */ static struct tick_device tick_broadcast_device; -static cpumask_var_t tick_broadcast_mask; -static cpumask_var_t tick_broadcast_on; -static cpumask_var_t tmpmask; -static DEFINE_RAW_SPINLOCK(tick_broadcast_lock); +static cpumask_var_t tick_broadcast_mask __cpumask_var_read_mostly; +static cpumask_var_t tick_broadcast_on __cpumask_var_read_mostly; +static cpumask_var_t tmpmask __cpumask_var_read_mostly; static int tick_broadcast_forced; +static __cacheline_aligned_in_smp DEFINE_RAW_SPINLOCK(tick_broadcast_lock); + #ifdef CONFIG_TICK_ONESHOT static void tick_broadcast_clear_oneshot(int cpu); static void tick_resume_broadcast_oneshot(struct clock_event_device *bc); @@ -517,9 +518,9 @@ void tick_resume_broadcast(void) #ifdef CONFIG_TICK_ONESHOT -static cpumask_var_t tick_broadcast_oneshot_mask; -static cpumask_var_t tick_broadcast_pending_mask; -static cpumask_var_t tick_broadcast_force_mask; +static cpumask_var_t tick_broadcast_oneshot_mask __cpumask_var_read_mostly; +static cpumask_var_t tick_broadcast_pending_mask __cpumask_var_read_mostly; +static cpumask_var_t tick_broadcast_force_mask __cpumask_var_read_mostly; /* * Exposed for debugging: see timer_list.c -- cgit v1.2.3 From dfb4357da6ddbdf57d583ba64361c9d792b0e0b1 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Wed, 8 Feb 2017 11:26:59 -0800 Subject: 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 Signed-off-by: Kees Cook Acked-by: John Stultz Cc: Nicolas Pitre Cc: linux-doc@vger.kernel.org Cc: Lai Jiangshan Cc: Shuah Khan Cc: Xing Gao Cc: Jonathan Corbet Cc: Jessica Frazelle Cc: kernel-hardening@lists.openwall.com Cc: Nicolas Iooss Cc: "Paul E. McKenney" Cc: Petr Mladek Cc: Richard Cochran Cc: Tejun Heo Cc: Michal Marek Cc: Josh Poimboeuf Cc: Dmitry Vyukov Cc: Oleg Nesterov Cc: "Eric W. Biederman" Cc: Olof Johansson Cc: Andrew Morton Cc: linux-api@vger.kernel.org Cc: Arjan van de Ven Link: http://lkml.kernel.org/r/20170208192659.GA32582@beast Signed-off-by: Thomas Gleixner --- Documentation/timers/timer_stats.txt | 73 ------ include/linux/hrtimer.h | 11 - include/linux/timer.h | 45 ---- kernel/kthread.c | 1 - kernel/time/Makefile | 1 - kernel/time/hrtimer.c | 38 ---- kernel/time/timer.c | 48 +--- kernel/time/timer_list.c | 10 - kernel/time/timer_stats.c | 425 ----------------------------------- kernel/workqueue.c | 2 - lib/Kconfig.debug | 14 -- 11 files changed, 2 insertions(+), 666 deletions(-) delete mode 100644 Documentation/timers/timer_stats.txt delete mode 100644 kernel/time/timer_stats.c (limited to 'kernel') diff --git a/Documentation/timers/timer_stats.txt b/Documentation/timers/timer_stats.txt deleted file mode 100644 index de835ee97455..000000000000 --- a/Documentation/timers/timer_stats.txt +++ /dev/null @@ -1,73 +0,0 @@ -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) - diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h index cdab81ba29f8..e52b427223ba 100644 --- a/include/linux/hrtimer.h +++ b/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 }; /** diff --git a/include/linux/timer.h b/include/linux/timer.h index 51d601f192d4..5a209b84fd9e 100644 --- a/include/linux/timer.h +++ b/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); diff --git a/kernel/kthread.c b/kernel/kthread.c index 2318fba86277..8461a4372e8a 100644 --- a/kernel/kthread.c +++ b/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); } 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 - * - * 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 - * 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 -#include -#include -#include -#include -#include - -#include - -/* - * 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); diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 1d9fb6543a66..072cbc9b175d 100644 --- a/kernel/workqueue.c +++ b/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; diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index eb9e9a7870fa..132af338d6dd 100644 --- a/lib/Kconfig.debug +++ b/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 -- cgit v1.2.3 From 7551b02b94ad1daee3a79d667dc3c46d08328f87 Mon Sep 17 00:00:00 2001 From: Mars Cheng Date: Thu, 9 Feb 2017 15:50:15 +0800 Subject: timer_list: Remove useless cast when printing hrtimer_resolution is already unsigned int, not necessary to cast it when printing. Signed-off-by: Mars Cheng Cc: CC Hwang Cc: wsd_upstream@mediatek.com Cc: Loda Chou Cc: Jades Shih Cc: Miles Chen Cc: John Stultz Cc: My Chuang Cc: Matthias Brugger Cc: Yingjoe Chen Link: http://lkml.kernel.org/r/1486626615-5879-1-git-send-email-mars.cheng@mediatek.com Signed-off-by: Thomas Gleixner --- kernel/time/timer_list.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/time/timer_list.c b/kernel/time/timer_list.c index 387a3a5aa388..ff8d5c13d04b 100644 --- a/kernel/time/timer_list.c +++ b/kernel/time/timer_list.c @@ -117,7 +117,7 @@ print_base(struct seq_file *m, struct hrtimer_clock_base *base, u64 now) SEQ_printf(m, " .base: %pK\n", base); SEQ_printf(m, " .index: %d\n", base->index); - SEQ_printf(m, " .resolution: %u nsecs\n", (unsigned) hrtimer_resolution); + SEQ_printf(m, " .resolution: %u nsecs\n", hrtimer_resolution); SEQ_printf(m, " .get_time: "); print_name_offset(m, base->get_time); -- cgit v1.2.3 From 336a9cde10d641e70bac67d90ae91b3190c3edca Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Fri, 15 Jan 2016 17:41:09 +0000 Subject: hrtimer: Catch invalid clockids again commit 82e88ff1ea94 ("hrtimer: Revert CLOCK_MONOTONIC_RAW support") removed unfortunately a sanity check in the hrtimer code which was part of that MONOTONIC_RAW patch series. It would have caught the bogus usage of CLOCK_MONOTONIC_RAW in the wireless code. So bring it back. It is way too easy to take any random clockid and feed it to the hrtimer subsystem. At best, it gets mapped to a monotonic base, but it would be better to just catch illegal values as early as possible. Detect invalid clockids, map them to CLOCK_MONOTONIC and emit a warning. [ tglx: Replaced the BUG by a WARN and gracefully map to CLOCK_MONOTONIC ] Signed-off-by: Marc Zyngier Cc: Tomasz Nowicki Cc: Christoffer Dall Link: http://lkml.kernel.org/r/1452879670-16133-3-git-send-email-marc.zyngier@arm.com Signed-off-by: Thomas Gleixner --- kernel/time/hrtimer.c | 20 +++++++++++++++----- 1 file changed, 15 insertions(+), 5 deletions(-) (limited to 'kernel') diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c index edabde646e58..8e11d8d9f419 100644 --- a/kernel/time/hrtimer.c +++ b/kernel/time/hrtimer.c @@ -94,17 +94,15 @@ DEFINE_PER_CPU(struct hrtimer_cpu_base, hrtimer_bases) = }; static const int hrtimer_clock_to_base_table[MAX_CLOCKS] = { + /* Make sure we catch unsupported clockids */ + [0 ... MAX_CLOCKS - 1] = HRTIMER_MAX_CLOCK_BASES, + [CLOCK_REALTIME] = HRTIMER_BASE_REALTIME, [CLOCK_MONOTONIC] = HRTIMER_BASE_MONOTONIC, [CLOCK_BOOTTIME] = HRTIMER_BASE_BOOTTIME, [CLOCK_TAI] = HRTIMER_BASE_TAI, }; -static inline int hrtimer_clockid_to_base(clockid_t clock_id) -{ - return hrtimer_clock_to_base_table[clock_id]; -} - /* * Functions and macros which are different for UP/SMP systems are kept in a * single place @@ -1081,6 +1079,18 @@ u64 hrtimer_get_next_event(void) } #endif +static inline int hrtimer_clockid_to_base(clockid_t clock_id) +{ + if (likely(clock_id < MAX_CLOCKS)) { + int base = hrtimer_clock_to_base_table[clock_id]; + + if (likely(base != HRTIMER_MAX_CLOCK_BASES)) + return base; + } + WARN(1, "Invalid clockid %d. Using MONOTONIC\n", clock_id); + return HRTIMER_BASE_MONOTONIC; +} + static void __hrtimer_init(struct hrtimer *timer, clockid_t clock_id, enum hrtimer_mode mode) { -- cgit v1.2.3