From 39be350127ec60a078edffe5b4915dafba4ba514 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 26 Jan 2012 12:44:34 +0100 Subject: sched, block: Unify cache detection The block layer has some code trying to determine if two CPUs share a cache, the scheduler has a similar function. Expose the function used by the scheduler and make the block layer use it, thereby removing the block layers usage of CONFIG_SCHED* and topology bits. Signed-off-by: Peter Zijlstra Acked-by: Jens Axboe Link: http://lkml.kernel.org/r/1327579450.2446.95.camel@twins --- include/linux/sched.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include') diff --git a/include/linux/sched.h b/include/linux/sched.h index 513f52459872..0e1959568836 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1052,6 +1052,8 @@ static inline int test_sd_parent(struct sched_domain *sd, int flag) unsigned long default_scale_freq_power(struct sched_domain *sd, int cpu); unsigned long default_scale_smt_power(struct sched_domain *sd, int cpu); +bool cpus_share_cache(int this_cpu, int that_cpu); + #else /* CONFIG_SMP */ struct sched_domain_attr; @@ -1061,6 +1063,12 @@ partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[], struct sched_domain_attr *dattr_new) { } + +static inline bool cpus_share_cache(int this_cpu, int that_cpu) +{ + return true; +} + #endif /* !CONFIG_SMP */ -- cgit v1.2.3 From 4ec4412e1e91f44a3dcb97b6c9172a13fc78bac9 Mon Sep 17 00:00:00 2001 From: Vincent Guittot Date: Mon, 12 Dec 2011 20:21:08 +0100 Subject: sched: Ensure cpu_power periodic update With a lot of small tasks, the softirq sched is nearly never called when no_hz is enabled. In this case load_balance() is mainly called with the newly_idle mode which doesn't update the cpu_power. Add a next_update field which ensure a maximum update period when there is short activity. Having stale cpu_power information can skew the load-balancing decisions, this is cured by the guaranteed update. Signed-off-by: Vincent Guittot Signed-off-by: Peter Zijlstra Link: http://lkml.kernel.org/r/1323717668-2143-1-git-send-email-vincent.guittot@linaro.org --- include/linux/sched.h | 1 + kernel/sched/fair.c | 24 ++++++++++++++++-------- 2 files changed, 17 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/linux/sched.h b/include/linux/sched.h index 0e1959568836..92313a3f6f77 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -905,6 +905,7 @@ struct sched_group_power { * single CPU. */ unsigned int power, power_orig; + unsigned long next_update; /* * Number of busy cpus in this group. */ diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 7c6414fc669d..8e77a6bd597b 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -215,6 +215,8 @@ calc_delta_mine(unsigned long delta_exec, unsigned long weight, const struct sched_class fair_sched_class; +static unsigned long __read_mostly max_load_balance_interval = HZ/10; + /************************************************************** * CFS operations on generic schedulable entities: */ @@ -3776,6 +3778,11 @@ void update_group_power(struct sched_domain *sd, int cpu) struct sched_domain *child = sd->child; struct sched_group *group, *sdg = sd->groups; unsigned long power; + unsigned long interval; + + interval = msecs_to_jiffies(sd->balance_interval); + interval = clamp(interval, 1UL, max_load_balance_interval); + sdg->sgp->next_update = jiffies + interval; if (!child) { update_cpu_power(sd, cpu); @@ -3883,12 +3890,15 @@ static inline void update_sg_lb_stats(struct sched_domain *sd, * domains. In the newly idle case, we will allow all the cpu's * to do the newly idle load balance. */ - if (idle != CPU_NEWLY_IDLE && local_group) { - if (balance_cpu != this_cpu) { - *balance = 0; - return; - } - update_group_power(sd, this_cpu); + if (local_group) { + if (idle != CPU_NEWLY_IDLE) { + if (balance_cpu != this_cpu) { + *balance = 0; + return; + } + update_group_power(sd, this_cpu); + } else if (time_after_eq(jiffies, group->sgp->next_update)) + update_group_power(sd, this_cpu); } /* Adjust by relative CPU power of the group */ @@ -4945,8 +4955,6 @@ static int __cpuinit sched_ilb_notifier(struct notifier_block *nfb, static DEFINE_SPINLOCK(balancing); -static unsigned long __read_mostly max_load_balance_interval = HZ/10; - /* * Scale the max load_balance interval with the number of CPUs in the system. * This trades load-balance latency on larger machines for less cross talk. -- cgit v1.2.3 From 9388dc3047a88bedfd867e9ba3e1980c815ac524 Mon Sep 17 00:00:00 2001 From: Anton Vorontsov Date: Thu, 9 Feb 2012 20:45:19 +0400 Subject: sched: Turn lock_task_sighand() into a static inline It appears that sparse tool understands static inline functions for context balance checking, so let's turn the macros into an inline func. This makes the code a little bit more robust. Suggested-by: Oleg Nesterov Signed-off-by: Anton Vorontsov Cc: KOSAKI Motohiro Cc: Greg KH Cc: Arve Cc: San Mehat Cc: Colin Cross Cc: Eric W. Biederman Cc: Paul E. McKenney Cc: kernel-team@android.com Cc: linaro-kernel@lists.linaro.org Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/20120209164519.GA10266@oksana.dev.rtsoft.ru Signed-off-by: Ingo Molnar --- include/linux/sched.h | 15 +++++++++------ 1 file changed, 9 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/sched.h b/include/linux/sched.h index 92313a3f6f77..5dba2ad52431 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -2393,12 +2393,15 @@ static inline void task_unlock(struct task_struct *p) extern struct sighand_struct *__lock_task_sighand(struct task_struct *tsk, unsigned long *flags); -#define lock_task_sighand(tsk, flags) \ -({ struct sighand_struct *__ss; \ - __cond_lock(&(tsk)->sighand->siglock, \ - (__ss = __lock_task_sighand(tsk, flags))); \ - __ss; \ -}) \ +static inline struct sighand_struct *lock_task_sighand(struct task_struct *tsk, + unsigned long *flags) +{ + struct sighand_struct *ret; + + ret = __lock_task_sighand(tsk, flags); + (void)__cond_lock(&tsk->sighand->siglock, ret); + return ret; +} static inline void unlock_task_sighand(struct task_struct *tsk, unsigned long *flags) -- cgit v1.2.3 From de5bdff7a72acc281219be2b8edeeca1fd81c542 Mon Sep 17 00:00:00 2001 From: Hiroshi Shimamoto Date: Thu, 16 Feb 2012 14:52:21 +0900 Subject: sched: Make initial SCHED_RR timeslace DEF_TIMESLICE Current the initial SCHED_RR timeslice of init_task is HZ, which means 1s, and is not same as the default SCHED_RR timeslice DEF_TIMESLICE. Change that initial timeslice to the DEF_TIMESLICE. Signed-off-by: Hiroshi Shimamoto [ s/DEF_TIMESLICE/RR_TIMESLICE/g ] Signed-off-by: Peter Zijlstra Link: http://lkml.kernel.org/r/4F3C9995.3010800@ct.jp.nec.com Signed-off-by: Ingo Molnar --- include/linux/init_task.h | 2 +- include/linux/sched.h | 6 ++++++ kernel/sched/rt.c | 4 ++-- kernel/sched/sched.h | 4 ---- 4 files changed, 9 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/linux/init_task.h b/include/linux/init_task.h index 9c66b1ada9d7..f994d51f70f2 100644 --- a/include/linux/init_task.h +++ b/include/linux/init_task.h @@ -149,7 +149,7 @@ extern struct cred init_cred; }, \ .rt = { \ .run_list = LIST_HEAD_INIT(tsk.rt.run_list), \ - .time_slice = HZ, \ + .time_slice = RR_TIMESLICE, \ .nr_cpus_allowed = NR_CPUS, \ }, \ .tasks = LIST_HEAD_INIT(tsk.tasks), \ diff --git a/include/linux/sched.h b/include/linux/sched.h index 5dba2ad52431..eb5de466f099 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1234,6 +1234,12 @@ struct sched_rt_entity { #endif }; +/* + * default timeslice is 100 msecs (used only for SCHED_RR tasks). + * Timeslices get refilled after they expire. + */ +#define RR_TIMESLICE (100 * HZ / 1000) + struct rcu_node; enum perf_event_task_context { diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c index f42ae7fb5ec5..f70206c2c802 100644 --- a/kernel/sched/rt.c +++ b/kernel/sched/rt.c @@ -1972,7 +1972,7 @@ static void task_tick_rt(struct rq *rq, struct task_struct *p, int queued) if (--p->rt.time_slice) return; - p->rt.time_slice = DEF_TIMESLICE; + p->rt.time_slice = RR_TIMESLICE; /* * Requeue to the end of queue if we are not the only element @@ -2000,7 +2000,7 @@ static unsigned int get_rr_interval_rt(struct rq *rq, struct task_struct *task) * Time slice is 0 for SCHED_FIFO tasks */ if (task->policy == SCHED_RR) - return DEF_TIMESLICE; + return RR_TIMESLICE; else return 0; } diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 8a2c768d2f98..c0660a1a0cd1 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -36,11 +36,7 @@ extern __read_mostly int scheduler_running; /* * These are the 'tuning knobs' of the scheduler: - * - * default timeslice is 100 msecs (used only for SCHED_RR tasks). - * Timeslices get refilled after they expire. */ -#define DEF_TIMESLICE (100 * HZ / 1000) /* * single value that denotes runtime == period, ie unlimited time. -- cgit v1.2.3 From c5491ea779793f977d282754db478157cc409d82 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Mon, 21 Mar 2011 12:09:35 +0100 Subject: sched/rt: Add schedule_preempt_disabled() Add helper to get rid of the ever repeating: preempt_enable_no_resched(); schedule(); preempt_disable(); patterns. Signed-off-by: Thomas Gleixner Acked-by: Peter Zijlstra Link: http://lkml.kernel.org/n/tip-wxx7btox7coby6ifv5vzhzgp@git.kernel.org Signed-off-by: Ingo Molnar --- include/linux/sched.h | 1 + kernel/sched/core.c | 12 ++++++++++++ 2 files changed, 13 insertions(+) (limited to 'include') diff --git a/include/linux/sched.h b/include/linux/sched.h index 1a6398424fab..03dd224d0667 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -361,6 +361,7 @@ extern signed long schedule_timeout_interruptible(signed long timeout); extern signed long schedule_timeout_killable(signed long timeout); extern signed long schedule_timeout_uninterruptible(signed long timeout); asmlinkage void schedule(void); +extern void schedule_preempt_disabled(void); extern int mutex_spin_on_owner(struct mutex *lock, struct task_struct *owner); struct nsproxy; diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 91fe6a0e9098..73022395c00e 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -3246,6 +3246,18 @@ asmlinkage void __sched schedule(void) } EXPORT_SYMBOL(schedule); +/** + * schedule_preempt_disabled - called with preemption disabled + * + * Returns with preemption disabled. Note: preempt_count must be 1 + */ +void __sched schedule_preempt_disabled(void) +{ + preempt_enable_no_resched(); + schedule(); + preempt_disable(); +} + #ifdef CONFIG_MUTEX_SPIN_ON_OWNER static inline bool owner_running(struct mutex *lock, struct task_struct *owner) -- cgit v1.2.3 From ba74c1448f127649046615ec017bded7b2a76f29 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Mon, 21 Mar 2011 13:32:17 +0100 Subject: sched/rt: Document scheduler related skip-resched-check sites Create a distinction between scheduler related preempt_enable_no_resched() calls and the nearly one hundred other places in the kernel that do not want to reschedule, for one reason or another. This distinction matters for -rt, where the scheduler and the non-scheduler preempt models (and checks) are different. For upstream it's purely documentational. Signed-off-by: Thomas Gleixner Link: http://lkml.kernel.org/n/tip-gs88fvx2mdv5psnzxnv575ke@git.kernel.org Signed-off-by: Ingo Molnar --- arch/powerpc/kernel/idle.c | 2 +- arch/sparc/kernel/process_64.c | 2 +- include/linux/preempt.h | 5 ++++- kernel/sched/core.c | 6 +++--- kernel/softirq.c | 4 ++-- 5 files changed, 11 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/arch/powerpc/kernel/idle.c b/arch/powerpc/kernel/idle.c index 65035141552b..c97fc60c790c 100644 --- a/arch/powerpc/kernel/idle.c +++ b/arch/powerpc/kernel/idle.c @@ -102,7 +102,7 @@ void cpu_idle(void) rcu_idle_exit(); tick_nohz_idle_exit(); if (cpu_should_die()) { - preempt_enable_no_resched(); + sched_preempt_enable_no_resched(); cpu_die(); } schedule_preempt_disabled(); diff --git a/arch/sparc/kernel/process_64.c b/arch/sparc/kernel/process_64.c index ab9a29268213..06b5b5fc20c7 100644 --- a/arch/sparc/kernel/process_64.c +++ b/arch/sparc/kernel/process_64.c @@ -106,7 +106,7 @@ void cpu_idle(void) #ifdef CONFIG_HOTPLUG_CPU if (cpu_is_offline(cpu)) { - preempt_enable_no_resched(); + sched_preempt_enable_no_resched(); cpu_play_dead(); } #endif diff --git a/include/linux/preempt.h b/include/linux/preempt.h index 58969b2a8a82..5a710b9c578e 100644 --- a/include/linux/preempt.h +++ b/include/linux/preempt.h @@ -48,12 +48,14 @@ do { \ barrier(); \ } while (0) -#define preempt_enable_no_resched() \ +#define sched_preempt_enable_no_resched() \ do { \ barrier(); \ dec_preempt_count(); \ } while (0) +#define preempt_enable_no_resched() sched_preempt_enable_no_resched() + #define preempt_enable() \ do { \ preempt_enable_no_resched(); \ @@ -92,6 +94,7 @@ do { \ #else /* !CONFIG_PREEMPT_COUNT */ #define preempt_disable() do { } while (0) +#define sched_preempt_enable_no_resched() do { } while (0) #define preempt_enable_no_resched() do { } while (0) #define preempt_enable() do { } while (0) diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 73022395c00e..643cc37fcb23 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -3220,7 +3220,7 @@ need_resched: post_schedule(rq); - preempt_enable_no_resched(); + sched_preempt_enable_no_resched(); if (need_resched()) goto need_resched; } @@ -3253,7 +3253,7 @@ EXPORT_SYMBOL(schedule); */ void __sched schedule_preempt_disabled(void) { - preempt_enable_no_resched(); + sched_preempt_enable_no_resched(); schedule(); preempt_disable(); } @@ -4486,7 +4486,7 @@ SYSCALL_DEFINE0(sched_yield) __release(rq->lock); spin_release(&rq->lock.dep_map, 1, _THIS_IP_); do_raw_spin_unlock(&rq->lock); - preempt_enable_no_resched(); + sched_preempt_enable_no_resched(); schedule(); diff --git a/kernel/softirq.c b/kernel/softirq.c index 79b524767a24..f268369ebe1f 100644 --- a/kernel/softirq.c +++ b/kernel/softirq.c @@ -353,7 +353,7 @@ void irq_exit(void) tick_nohz_irq_exit(); #endif rcu_irq_exit(); - preempt_enable_no_resched(); + sched_preempt_enable_no_resched(); } /* @@ -759,7 +759,7 @@ static int run_ksoftirqd(void * __bind_cpu) if (local_softirq_pending()) __do_softirq(); local_irq_enable(); - preempt_enable_no_resched(); + sched_preempt_enable_no_resched(); cond_resched(); preempt_disable(); rcu_note_context_switch((long)__bind_cpu); -- cgit v1.2.3 From 63b2001169e75cd71e917ec953fdab572e3f944a Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Thu, 1 Dec 2011 00:04:00 +0100 Subject: sched/wait: Add __wake_up_all_locked() API For code which protects the waitqueue itself with another lock it makes no sense to acquire the waitqueue lock for wakeup all. Provide __wake_up_all_locked(). This is an optimization on the vanilla kernel (to be used by the PCI code) and an important semantic distinction on -rt. Signed-off-by: Thomas Gleixner Acked-by: Peter Zijlstra Link: http://lkml.kernel.org/n/tip-ux6m4b8jonb9inx8xafh77ds@git.kernel.org Signed-off-by: Ingo Molnar --- include/linux/wait.h | 5 +++-- kernel/sched/core.c | 4 ++-- 2 files changed, 5 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/wait.h b/include/linux/wait.h index a9ce45e8501c..7d9a9e990ce6 100644 --- a/include/linux/wait.h +++ b/include/linux/wait.h @@ -157,7 +157,7 @@ void __wake_up(wait_queue_head_t *q, unsigned int mode, int nr, void *key); void __wake_up_locked_key(wait_queue_head_t *q, unsigned int mode, void *key); void __wake_up_sync_key(wait_queue_head_t *q, unsigned int mode, int nr, void *key); -void __wake_up_locked(wait_queue_head_t *q, unsigned int mode); +void __wake_up_locked(wait_queue_head_t *q, unsigned int mode, int nr); void __wake_up_sync(wait_queue_head_t *q, unsigned int mode, int nr); void __wake_up_bit(wait_queue_head_t *, void *, int); int __wait_on_bit(wait_queue_head_t *, struct wait_bit_queue *, int (*)(void *), unsigned); @@ -170,7 +170,8 @@ wait_queue_head_t *bit_waitqueue(void *, int); #define wake_up(x) __wake_up(x, TASK_NORMAL, 1, NULL) #define wake_up_nr(x, nr) __wake_up(x, TASK_NORMAL, nr, NULL) #define wake_up_all(x) __wake_up(x, TASK_NORMAL, 0, NULL) -#define wake_up_locked(x) __wake_up_locked((x), TASK_NORMAL) +#define wake_up_locked(x) __wake_up_locked((x), TASK_NORMAL, 1) +#define wake_up_all_locked(x) __wake_up_locked((x), TASK_NORMAL, 0) #define wake_up_interruptible(x) __wake_up(x, TASK_INTERRUPTIBLE, 1, NULL) #define wake_up_interruptible_nr(x, nr) __wake_up(x, TASK_INTERRUPTIBLE, nr, NULL) diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 643cc37fcb23..820f7453fda9 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -3418,9 +3418,9 @@ EXPORT_SYMBOL(__wake_up); /* * Same as __wake_up but called with the spinlock in wait_queue_head_t held. */ -void __wake_up_locked(wait_queue_head_t *q, unsigned int mode) +void __wake_up_locked(wait_queue_head_t *q, unsigned int mode, int nr) { - __wake_up_common(q, mode, 1, 0, NULL); + __wake_up_common(q, mode, nr, 0, NULL); } EXPORT_SYMBOL_GPL(__wake_up_locked); -- cgit v1.2.3 From 3c7d51843b03a6839e9ec7cda724e54d2319a63a Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Sun, 17 Jul 2011 20:46:52 +0200 Subject: sched/rt: Do not submit new work when PI-blocked When we are PI-blocked then we want to get things done ASAP. Signed-off-by: Thomas Gleixner Acked-by: Peter Zijlstra Link: http://lkml.kernel.org/n/tip-vw8et3445km5b8mpihf4trae@git.kernel.org Signed-off-by: Ingo Molnar --- include/linux/sched.h | 8 ++++++++ kernel/sched/core.c | 2 +- 2 files changed, 9 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/sched.h b/include/linux/sched.h index 03dd224d0667..c628a9151437 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -2082,12 +2082,20 @@ extern unsigned int sysctl_sched_cfs_bandwidth_slice; extern int rt_mutex_getprio(struct task_struct *p); extern void rt_mutex_setprio(struct task_struct *p, int prio); extern void rt_mutex_adjust_pi(struct task_struct *p); +static inline bool tsk_is_pi_blocked(struct task_struct *tsk) +{ + return tsk->pi_blocked_on != NULL; +} #else static inline int rt_mutex_getprio(struct task_struct *p) { return p->normal_prio; } # define rt_mutex_adjust_pi(p) do { } while (0) +static inline bool tsk_is_pi_blocked(struct task_struct *tsk) +{ + return false; +} #endif extern bool yield_to(struct task_struct *p, bool preempt); diff --git a/kernel/sched/core.c b/kernel/sched/core.c index c2bbdecaa27d..25e06a5e048b 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -3227,7 +3227,7 @@ need_resched: static inline void sched_submit_work(struct task_struct *tsk) { - if (!tsk->state) + if (!tsk->state || tsk_is_pi_blocked(tsk)) return; /* * If we are going to sleep and we have plugged IO queued, -- cgit v1.2.3 From 2e5b5b3a1b7768c89fbfeca18e75f8ee377e924c Mon Sep 17 00:00:00 2001 From: Hiroshi Shimamoto Date: Thu, 23 Feb 2012 17:41:27 +0900 Subject: sched: Clean up parameter passing of proc_sched_autogroup_set_nice() Pass nice as a value to proc_sched_autogroup_set_nice(). No side effect is expected, and the variable err will be overwritten with the return value. Signed-off-by: Hiroshi Shimamoto Signed-off-by: Peter Zijlstra Link: http://lkml.kernel.org/r/4F45FBB7.5090607@ct.jp.nec.com Signed-off-by: Ingo Molnar --- fs/proc/base.c | 3 +-- include/linux/sched.h | 2 +- kernel/sched/auto_group.c | 12 ++++++------ 3 files changed, 8 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/fs/proc/base.c b/fs/proc/base.c index d4548dd49b02..965d4bde3a3b 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -1310,8 +1310,7 @@ sched_autogroup_write(struct file *file, const char __user *buf, if (!p) return -ESRCH; - err = nice; - err = proc_sched_autogroup_set_nice(p, &err); + err = proc_sched_autogroup_set_nice(p, nice); if (err) count = err; diff --git a/include/linux/sched.h b/include/linux/sched.h index c628a9151437..c298fb9cf5ad 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -2065,7 +2065,7 @@ extern void sched_autogroup_fork(struct signal_struct *sig); extern void sched_autogroup_exit(struct signal_struct *sig); #ifdef CONFIG_PROC_FS extern void proc_sched_autogroup_show_task(struct task_struct *p, struct seq_file *m); -extern int proc_sched_autogroup_set_nice(struct task_struct *p, int *nice); +extern int proc_sched_autogroup_set_nice(struct task_struct *p, int nice); #endif #else static inline void sched_autogroup_create_attach(struct task_struct *p) { } diff --git a/kernel/sched/auto_group.c b/kernel/sched/auto_group.c index e8a1f83ee0e7..0984a21076a3 100644 --- a/kernel/sched/auto_group.c +++ b/kernel/sched/auto_group.c @@ -195,20 +195,20 @@ __setup("noautogroup", setup_autogroup); #ifdef CONFIG_PROC_FS -int proc_sched_autogroup_set_nice(struct task_struct *p, int *nice) +int proc_sched_autogroup_set_nice(struct task_struct *p, int nice) { static unsigned long next = INITIAL_JIFFIES; struct autogroup *ag; int err; - if (*nice < -20 || *nice > 19) + if (nice < -20 || nice > 19) return -EINVAL; - err = security_task_setnice(current, *nice); + err = security_task_setnice(current, nice); if (err) return err; - if (*nice < 0 && !can_nice(current, *nice)) + if (nice < 0 && !can_nice(current, nice)) return -EPERM; /* this is a heavy operation taking global locks.. */ @@ -219,9 +219,9 @@ int proc_sched_autogroup_set_nice(struct task_struct *p, int *nice) ag = autogroup_task_get(p); down_write(&ag->lock); - err = sched_group_set_shares(ag->tg, prio_to_weight[*nice + 20]); + err = sched_group_set_shares(ag->tg, prio_to_weight[nice + 20]); if (!err) - ag->nice = *nice; + ag->nice = nice; up_write(&ag->lock); autogroup_kref_put(ag); -- cgit v1.2.3 From 3ccf3e8306156a28213adc720aba807e9a901ad5 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Mon, 27 Feb 2012 10:47:00 +0100 Subject: printk/sched: Introduce special printk_sched() for those awkward moments There's a few awkward printk()s inside of scheduler guts that people prefer to keep but really are rather deadlock prone. Fudge around it by storing the text in a per-cpu buffer and poll it using the existing printk_tick() handler. This will drop output when its more frequent than once a tick, however only the affinity thing could possible go that fast and for that just one should suffice to notify the admin he's done something silly.. Signed-off-by: Peter Zijlstra Cc: Linus Torvalds Cc: Andrew Morton Link: http://lkml.kernel.org/n/tip-wua3lmkt3dg8nfts66o6brne@git.kernel.org Signed-off-by: Ingo Molnar --- include/linux/printk.h | 10 ++++++++++ kernel/printk.c | 40 +++++++++++++++++++++++++++++++++++++--- kernel/sched/core.c | 2 +- kernel/sched/rt.c | 8 +++++++- 4 files changed, 55 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/printk.h b/include/linux/printk.h index f0e22f75143f..1f77a4174ee0 100644 --- a/include/linux/printk.h +++ b/include/linux/printk.h @@ -100,6 +100,11 @@ int vprintk(const char *fmt, va_list args); asmlinkage __printf(1, 2) __cold int printk(const char *fmt, ...); +/* + * Special printk facility for scheduler use only, _DO_NOT_USE_ ! + */ +__printf(1, 2) __cold int printk_sched(const char *fmt, ...); + /* * Please don't use printk_ratelimit(), because it shares ratelimiting state * with all other unrelated printk_ratelimit() callsites. Instead use @@ -127,6 +132,11 @@ int printk(const char *s, ...) { return 0; } +static inline __printf(1, 2) __cold +int printk_sched(const char *s, ...) +{ + return 0; +} static inline int printk_ratelimit(void) { return 0; diff --git a/kernel/printk.c b/kernel/printk.c index 13c0a1143f49..7ca7ba591e21 100644 --- a/kernel/printk.c +++ b/kernel/printk.c @@ -1208,13 +1208,47 @@ int is_console_locked(void) return console_locked; } +/* + * Delayed printk facility, for scheduler-internal messages: + */ +#define PRINTK_BUF_SIZE 512 + +#define PRINTK_PENDING_WAKEUP 0x01 +#define PRINTK_PENDING_SCHED 0x02 + static DEFINE_PER_CPU(int, printk_pending); +static DEFINE_PER_CPU(char [PRINTK_BUF_SIZE], printk_sched_buf); + +int printk_sched(const char *fmt, ...) +{ + unsigned long flags; + va_list args; + char *buf; + int r; + + local_irq_save(flags); + buf = __get_cpu_var(printk_sched_buf); + + va_start(args, fmt); + r = vsnprintf(buf, PRINTK_BUF_SIZE, fmt, args); + va_end(args); + + __this_cpu_or(printk_pending, PRINTK_PENDING_SCHED); + local_irq_restore(flags); + + return r; +} void printk_tick(void) { if (__this_cpu_read(printk_pending)) { - __this_cpu_write(printk_pending, 0); - wake_up_interruptible(&log_wait); + int pending = __this_cpu_xchg(printk_pending, 0); + if (pending & PRINTK_PENDING_SCHED) { + char *buf = __get_cpu_var(printk_sched_buf); + printk(KERN_WARNING "[sched_delayed] %s", buf); + } + if (pending & PRINTK_PENDING_WAKEUP) + wake_up_interruptible(&log_wait); } } @@ -1228,7 +1262,7 @@ int printk_needs_cpu(int cpu) void wake_up_klogd(void) { if (waitqueue_active(&log_wait)) - this_cpu_write(printk_pending, 1); + this_cpu_or(printk_pending, PRINTK_PENDING_WAKEUP); } /** diff --git a/kernel/sched/core.c b/kernel/sched/core.c index b1ccce819ce2..8781cec7c3e6 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -1284,7 +1284,7 @@ static int select_fallback_rq(int cpu, struct task_struct *p) * leave kernel. */ if (p->mm && printk_ratelimit()) { - printk(KERN_INFO "process %d (%s) no longer affine to cpu%d\n", + printk_sched("process %d (%s) no longer affine to cpu%d\n", task_pid_nr(p), p->comm, cpu); } diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c index 7f7e7cdcb472..b60dad720173 100644 --- a/kernel/sched/rt.c +++ b/kernel/sched/rt.c @@ -864,8 +864,14 @@ static int sched_rt_runtime_exceeded(struct rt_rq *rt_rq) * but accrue some time due to boosting. */ if (likely(rt_b->rt_runtime)) { + static bool once = false; + rt_rq->rt_throttled = 1; - printk_once(KERN_WARNING "sched: RT throttling activated\n"); + + if (!once) { + once = true; + printk_sched("sched: RT throttling activated\n"); + } } else { /* * In case we did anyway, make it go away, -- cgit v1.2.3 From 9993bc635d01a6ee7f6b833b4ee65ce7c06350b1 Mon Sep 17 00:00:00 2001 From: Salman Qazi Date: Fri, 9 Mar 2012 16:41:01 -0800 Subject: sched/x86: Fix overflow in cyc2ns_offset When a machine boots up, the TSC generally gets reset. However, when kexec is used to boot into a kernel, the TSC value would be carried over from the previous kernel. The computation of cycns_offset in set_cyc2ns_scale is prone to an overflow, if the machine has been up more than 208 days prior to the kexec. The overflow happens when we multiply *scale, even though there is enough room to store the final answer. We fix this issue by decomposing tsc_now into the quotient and remainder of division by CYC2NS_SCALE_FACTOR and then performing the multiplication separately on the two components. Refactor code to share the calculation with the previous fix in __cycles_2_ns(). Signed-off-by: Salman Qazi Acked-by: John Stultz Acked-by: Peter Zijlstra Cc: Paul Turner Cc: john stultz Link: http://lkml.kernel.org/r/20120310004027.19291.88460.stgit@dungbeetle.mtv.corp.google.com Signed-off-by: Ingo Molnar --- arch/x86/include/asm/timer.h | 8 ++------ arch/x86/kernel/tsc.c | 3 ++- include/linux/kernel.h | 13 +++++++++++++ 3 files changed, 17 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/arch/x86/include/asm/timer.h b/arch/x86/include/asm/timer.h index 431793e5d484..34baa0eb5d0c 100644 --- a/arch/x86/include/asm/timer.h +++ b/arch/x86/include/asm/timer.h @@ -57,14 +57,10 @@ DECLARE_PER_CPU(unsigned long long, cyc2ns_offset); static inline unsigned long long __cycles_2_ns(unsigned long long cyc) { - unsigned long long quot; - unsigned long long rem; int cpu = smp_processor_id(); unsigned long long ns = per_cpu(cyc2ns_offset, cpu); - quot = (cyc >> CYC2NS_SCALE_FACTOR); - rem = cyc & ((1ULL << CYC2NS_SCALE_FACTOR) - 1); - ns += quot * per_cpu(cyc2ns, cpu) + - ((rem * per_cpu(cyc2ns, cpu)) >> CYC2NS_SCALE_FACTOR); + ns += mult_frac(cyc, per_cpu(cyc2ns, cpu), + (1UL << CYC2NS_SCALE_FACTOR)); return ns; } diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index a62c201c97ec..183c5925a9fe 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -620,7 +620,8 @@ static void set_cyc2ns_scale(unsigned long cpu_khz, int cpu) if (cpu_khz) { *scale = (NSEC_PER_MSEC << CYC2NS_SCALE_FACTOR)/cpu_khz; - *offset = ns_now - (tsc_now * *scale >> CYC2NS_SCALE_FACTOR); + *offset = ns_now - mult_frac(tsc_now, *scale, + (1UL << CYC2NS_SCALE_FACTOR)); } sched_clock_idle_wakeup_event(0); diff --git a/include/linux/kernel.h b/include/linux/kernel.h index e8343422240a..d801acb5e680 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -85,6 +85,19 @@ } \ ) +/* + * Multiplies an integer by a fraction, while avoiding unnecessary + * overflow or loss of precision. + */ +#define mult_frac(x, numer, denom)( \ +{ \ + typeof(x) quot = (x) / (denom); \ + typeof(x) rem = (x) % (denom); \ + (quot * (numer)) + ((rem * (numer)) / (denom)); \ +} \ +) + + #define _RET_IP_ (unsigned long)__builtin_return_address(0) #define _THIS_IP_ ({ __label__ __here; __here: (unsigned long)&&__here; }) -- cgit v1.2.3