From bfdb4d9f0f611687d71cf6a460efc9e755f4a462 Mon Sep 17 00:00:00 2001 From: Arun R Bharadwaj Date: Tue, 23 Jun 2009 10:00:58 +0530 Subject: [PATCH 1/2] timers: Fix timer_migration interface which accepts any number as input Poornima Nayek reported: | Timer migration interface /proc/sys/kernel/timer_migration in | 2.6.30-git9 accepts any numerical value as input. | | Steps to reproduce: | 1. echo -6666666 > /proc/sys/kernel/timer_migration | 2. cat /proc/sys/kernel/timer_migration | -6666666 | | 1. echo 44444444444444444444444444444444444444444444444444444444444 > /proc/sys/kernel/timer_migration | 2. cat /proc/sys/kernel/timer_migration | -1357789412 | | Expected behavior: Should 'echo: write error: Invalid argument' while | setting any value other then 0 & 1 Restrict valid values to 0 and 1. Reported-by: Poornima Nayak Tested-by: Poornima Nayak Signed-off-by: Arun R Bharadwaj Cc: poornima nayak Cc: Arun Bharadwaj LKML-Reference: <20090623043058.GA3249@linux.vnet.ibm.com> Signed-off-by: Ingo Molnar --- kernel/sysctl.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 62e4ff9968b5..c428ba161db1 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -335,7 +335,10 @@ static struct ctl_table kern_table[] = { .data = &sysctl_timer_migration, .maxlen = sizeof(unsigned int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = &proc_dointvec_minmax, + .strategy = &sysctl_intvec, + .extra1 = &zero, + .extra2 = &one, }, #endif { From 507e123151149e578c9aae33eb876c49824da5f8 Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Tue, 23 Jun 2009 17:38:15 +0200 Subject: [PATCH 2/2] timer stats: Optimize by adding quick check to avoid function calls When the kernel is configured with CONFIG_TIMER_STATS but timer stats are runtime disabled we still get calls to __timer_stats_timer_set_start_info which initializes some fields in the corresponding struct timer_list. So add some quick checks in the the timer stats setup functions to avoid function calls to __timer_stats_timer_set_start_info when timer stats are disabled. In an artificial workload that does nothing but playing ping pong with a single tcp packet via loopback this decreases cpu consumption by 1 - 1.5%. This is part of a modified function trace output on SLES11: perl-2497 [00] 28630647177732388 [+ 125]: sk_reset_timer <-tcp_v4_rcv perl-2497 [00] 28630647177732513 [+ 125]: mod_timer <-sk_reset_timer perl-2497 [00] 28630647177732638 [+ 125]: __timer_stats_timer_set_start_info <-mod_timer perl-2497 [00] 28630647177732763 [+ 125]: __mod_timer <-mod_timer perl-2497 [00] 28630647177732888 [+ 125]: __timer_stats_timer_set_start_info <-__mod_timer perl-2497 [00] 28630647177733013 [+ 93]: lock_timer_base <-__mod_timer Signed-off-by: Heiko Carstens Cc: Andrew Morton Cc: Martin Schwidefsky Cc: Mustafa Mesanovic Cc: Arjan van de Ven LKML-Reference: <20090623153811.GA4641@osiris.boeblingen.de.ibm.com> Signed-off-by: Ingo Molnar --- include/linux/hrtimer.h | 5 +++++ include/linux/timer.h | 4 ++++ kernel/time/timer_stats.c | 16 ++++++++-------- kernel/timer.c | 2 ++ 4 files changed, 19 insertions(+), 8 deletions(-) diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h index 7400900de94a..54648e625efd 100644 --- a/include/linux/hrtimer.h +++ b/include/linux/hrtimer.h @@ -21,6 +21,7 @@ #include #include #include +#include struct hrtimer_clock_base; @@ -447,6 +448,8 @@ extern void timer_stats_update_stats(void *timer, pid_t pid, void *startf, static inline void timer_stats_account_hrtimer(struct hrtimer *timer) { + if (likely(!timer->start_pid)) + return; timer_stats_update_stats(timer, timer->start_pid, timer->start_site, timer->function, timer->start_comm, 0); } @@ -456,6 +459,8 @@ extern void __timer_stats_hrtimer_set_start_info(struct hrtimer *timer, static inline void timer_stats_hrtimer_set_start_info(struct hrtimer *timer) { + if (likely(!timer_stats_active)) + return; __timer_stats_hrtimer_set_start_info(timer, __builtin_return_address(0)); } diff --git a/include/linux/timer.h b/include/linux/timer.h index ccf882eed8f8..be62ec2ebea5 100644 --- a/include/linux/timer.h +++ b/include/linux/timer.h @@ -190,6 +190,8 @@ extern unsigned long get_next_timer_interrupt(unsigned long now); */ #ifdef CONFIG_TIMER_STATS +extern int timer_stats_active; + #define TIMER_STATS_FLAG_DEFERRABLE 0x1 extern void init_timer_stats(void); @@ -203,6 +205,8 @@ extern void __timer_stats_timer_set_start_info(struct timer_list *timer, 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)); } diff --git a/kernel/time/timer_stats.c b/kernel/time/timer_stats.c index c994530d166d..4cde8b9c716f 100644 --- a/kernel/time/timer_stats.c +++ b/kernel/time/timer_stats.c @@ -96,7 +96,7 @@ static DEFINE_MUTEX(show_mutex); /* * Collection status, active/inactive: */ -static int __read_mostly active; +int __read_mostly timer_stats_active; /* * Beginning/end timestamps of measurement: @@ -242,7 +242,7 @@ void timer_stats_update_stats(void *timer, pid_t pid, void *startf, struct entry *entry, input; unsigned long flags; - if (likely(!active)) + if (likely(!timer_stats_active)) return; lock = &per_cpu(lookup_lock, raw_smp_processor_id()); @@ -254,7 +254,7 @@ void timer_stats_update_stats(void *timer, pid_t pid, void *startf, input.timer_flag = timer_flag; spin_lock_irqsave(lock, flags); - if (!active) + if (!timer_stats_active) goto out_unlock; entry = tstat_lookup(&input, comm); @@ -290,7 +290,7 @@ static int tstats_show(struct seq_file *m, void *v) /* * If still active then calculate up to now: */ - if (active) + if (timer_stats_active) time_stop = ktime_get(); time = ktime_sub(time_stop, time_start); @@ -368,18 +368,18 @@ static ssize_t tstats_write(struct file *file, const char __user *buf, mutex_lock(&show_mutex); switch (ctl[0]) { case '0': - if (active) { - active = 0; + if (timer_stats_active) { + timer_stats_active = 0; time_stop = ktime_get(); sync_access(); } break; case '1': - if (!active) { + if (!timer_stats_active) { reset_entries(); time_start = ktime_get(); smp_mb(); - active = 1; + timer_stats_active = 1; } break; default: diff --git a/kernel/timer.c b/kernel/timer.c index 54d3912f8cad..0b36b9e5cc8b 100644 --- a/kernel/timer.c +++ b/kernel/timer.c @@ -380,6 +380,8 @@ static void timer_stats_account_timer(struct timer_list *timer) { unsigned int flag = 0; + if (likely(!timer->start_site)) + return; if (unlikely(tbase_get_deferrable(timer->base))) flag |= TIMER_STATS_FLAG_DEFERRABLE;