From 19a37d1cd5465c10d669a296a2ea24b4c985363b Mon Sep 17 00:00:00 2001 From: Li Zefan Date: Tue, 5 Mar 2013 16:05:28 +0800 Subject: sched: Remove some dummy functions No one will call those functions if CONFIG_SCHED_DEBUG=n. Signed-off-by: Li Zefan Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/5135A748.3050206@huawei.com Signed-off-by: Ingo Molnar diff --git a/include/linux/sched.h b/include/linux/sched.h index d35d2b6..2715fbb 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -127,18 +127,6 @@ extern void proc_sched_show_task(struct task_struct *p, struct seq_file *m); extern void proc_sched_set_task(struct task_struct *p); extern void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq); -#else -static inline void -proc_sched_show_task(struct task_struct *p, struct seq_file *m) -{ -} -static inline void proc_sched_set_task(struct task_struct *p) -{ -} -static inline void -print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq) -{ -} #endif /* -- cgit v0.10.2 From 090b582f27ac7b6714661020033160130e5297bd Mon Sep 17 00:00:00 2001 From: Li Zefan Date: Tue, 5 Mar 2013 16:05:51 +0800 Subject: sched: Remove test_sd_parent() It's unused. Signed-off-by: Li Zefan Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/5135A75F.4070202@huawei.com Signed-off-by: Ingo Molnar diff --git a/include/linux/sched.h b/include/linux/sched.h index 2715fbb..e880d7d 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -959,15 +959,6 @@ extern void partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[], cpumask_var_t *alloc_sched_domains(unsigned int ndoms); void free_sched_domains(cpumask_var_t doms[], unsigned int ndoms); -/* Test a flag in parent sched domain */ -static inline int test_sd_parent(struct sched_domain *sd, int flag) -{ - if (sd->parent && (sd->parent->flags & flag)) - return 1; - - return 0; -} - unsigned long default_scale_freq_power(struct sched_domain *sd, int cpu); unsigned long default_scale_smt_power(struct sched_domain *sd, int cpu); -- cgit v0.10.2 From cc1f4b1f3faed9f2040eff2a75f510b424b3cf18 Mon Sep 17 00:00:00 2001 From: Li Zefan Date: Tue, 5 Mar 2013 16:06:09 +0800 Subject: sched: Move SCHED_LOAD_SHIFT macros to kernel/sched/sched.h They are used internally only. Signed-off-by: Li Zefan Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/5135A771.4070104@huawei.com Signed-off-by: Ingo Molnar diff --git a/include/linux/sched.h b/include/linux/sched.h index e880d7d..f8826d0 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -756,31 +756,6 @@ enum cpu_idle_type { }; /* - * Increase resolution of nice-level calculations for 64-bit architectures. - * The extra resolution improves shares distribution and load balancing of - * low-weight task groups (eg. nice +19 on an autogroup), deeper taskgroup - * hierarchies, especially on larger systems. This is not a user-visible change - * and does not change the user-interface for setting shares/weights. - * - * We increase resolution only if we have enough bits to allow this increased - * resolution (i.e. BITS_PER_LONG > 32). The costs for increasing resolution - * when BITS_PER_LONG <= 32 are pretty high and the returns do not justify the - * increased costs. - */ -#if 0 /* BITS_PER_LONG > 32 -- currently broken: it increases power usage under light load */ -# define SCHED_LOAD_RESOLUTION 10 -# define scale_load(w) ((w) << SCHED_LOAD_RESOLUTION) -# define scale_load_down(w) ((w) >> SCHED_LOAD_RESOLUTION) -#else -# define SCHED_LOAD_RESOLUTION 0 -# define scale_load(w) (w) -# define scale_load_down(w) (w) -#endif - -#define SCHED_LOAD_SHIFT (10 + SCHED_LOAD_RESOLUTION) -#define SCHED_LOAD_SCALE (1L << SCHED_LOAD_SHIFT) - -/* * Increase resolution of cpu_power calculations */ #define SCHED_POWER_SHIFT 10 diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index cc03cfd..709a30c 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -33,6 +33,31 @@ extern __read_mostly int scheduler_running; */ #define NS_TO_JIFFIES(TIME) ((unsigned long)(TIME) / (NSEC_PER_SEC / HZ)) +/* + * Increase resolution of nice-level calculations for 64-bit architectures. + * The extra resolution improves shares distribution and load balancing of + * low-weight task groups (eg. nice +19 on an autogroup), deeper taskgroup + * hierarchies, especially on larger systems. This is not a user-visible change + * and does not change the user-interface for setting shares/weights. + * + * We increase resolution only if we have enough bits to allow this increased + * resolution (i.e. BITS_PER_LONG > 32). The costs for increasing resolution + * when BITS_PER_LONG <= 32 are pretty high and the returns do not justify the + * increased costs. + */ +#if 0 /* BITS_PER_LONG > 32 -- currently broken: it increases power usage under light load */ +# define SCHED_LOAD_RESOLUTION 10 +# define scale_load(w) ((w) << SCHED_LOAD_RESOLUTION) +# define scale_load_down(w) ((w) >> SCHED_LOAD_RESOLUTION) +#else +# define SCHED_LOAD_RESOLUTION 0 +# define scale_load(w) (w) +# define scale_load_down(w) (w) +#endif + +#define SCHED_LOAD_SHIFT (10 + SCHED_LOAD_RESOLUTION) +#define SCHED_LOAD_SCALE (1L << SCHED_LOAD_SHIFT) + #define NICE_0_LOAD SCHED_LOAD_SCALE #define NICE_0_SHIFT SCHED_LOAD_SHIFT @@ -784,7 +809,6 @@ static inline void finish_lock_switch(struct rq *rq, struct task_struct *prev) } #endif /* __ARCH_WANT_UNLOCKED_CTXSW */ - static inline void update_load_add(struct load_weight *lw, unsigned long inc) { lw->weight += inc; -- cgit v0.10.2 From 5e6521eaa1ee581a13b904f35b80c5efeb2baccb Mon Sep 17 00:00:00 2001 From: Li Zefan Date: Tue, 5 Mar 2013 16:06:23 +0800 Subject: sched: Move struct sched_group to kernel/sched/sched.h Move struct sched_group_power and sched_group and related inline functions to kernel/sched/sched.h, as they are used internally only. Signed-off-by: Li Zefan Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/5135A77F.2010705@huawei.com Signed-off-by: Ingo Molnar diff --git a/include/linux/sched.h b/include/linux/sched.h index f8826d0..0d64130 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -780,62 +780,6 @@ enum cpu_idle_type { extern int __weak arch_sd_sibiling_asym_packing(void); -struct sched_group_power { - atomic_t ref; - /* - * CPU power of this group, SCHED_LOAD_SCALE being max power for a - * single CPU. - */ - unsigned int power, power_orig; - unsigned long next_update; - /* - * Number of busy cpus in this group. - */ - atomic_t nr_busy_cpus; - - unsigned long cpumask[0]; /* iteration mask */ -}; - -struct sched_group { - struct sched_group *next; /* Must be a circular list */ - atomic_t ref; - - unsigned int group_weight; - struct sched_group_power *sgp; - - /* - * The CPUs this group covers. - * - * NOTE: this field is variable length. (Allocated dynamically - * by attaching extra space to the end of the structure, - * depending on how many CPUs the kernel has booted up with) - */ - unsigned long cpumask[0]; -}; - -static inline struct cpumask *sched_group_cpus(struct sched_group *sg) -{ - return to_cpumask(sg->cpumask); -} - -/* - * cpumask masking which cpus in the group are allowed to iterate up the domain - * tree. - */ -static inline struct cpumask *sched_group_mask(struct sched_group *sg) -{ - return to_cpumask(sg->sgp->cpumask); -} - -/** - * group_first_cpu - Returns the first cpu in the cpumask of a sched_group. - * @group: The group whose first cpu is to be returned. - */ -static inline unsigned int group_first_cpu(struct sched_group *group) -{ - return cpumask_first(sched_group_cpus(group)); -} - struct sched_domain_attr { int relax_domain_level; }; @@ -846,6 +790,8 @@ struct sched_domain_attr { extern int sched_domain_level_max; +struct sched_group; + struct sched_domain { /* These fields must be setup */ struct sched_domain *parent; /* top domain must be null terminated */ diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 709a30c..1a4a2b1 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -572,6 +572,62 @@ static inline struct sched_domain *highest_flag_domain(int cpu, int flag) DECLARE_PER_CPU(struct sched_domain *, sd_llc); DECLARE_PER_CPU(int, sd_llc_id); +struct sched_group_power { + atomic_t ref; + /* + * CPU power of this group, SCHED_LOAD_SCALE being max power for a + * single CPU. + */ + unsigned int power, power_orig; + unsigned long next_update; + /* + * Number of busy cpus in this group. + */ + atomic_t nr_busy_cpus; + + unsigned long cpumask[0]; /* iteration mask */ +}; + +struct sched_group { + struct sched_group *next; /* Must be a circular list */ + atomic_t ref; + + unsigned int group_weight; + struct sched_group_power *sgp; + + /* + * The CPUs this group covers. + * + * NOTE: this field is variable length. (Allocated dynamically + * by attaching extra space to the end of the structure, + * depending on how many CPUs the kernel has booted up with) + */ + unsigned long cpumask[0]; +}; + +static inline struct cpumask *sched_group_cpus(struct sched_group *sg) +{ + return to_cpumask(sg->cpumask); +} + +/* + * cpumask masking which cpus in the group are allowed to iterate up the domain + * tree. + */ +static inline struct cpumask *sched_group_mask(struct sched_group *sg) +{ + return to_cpumask(sg->sgp->cpumask); +} + +/** + * group_first_cpu - Returns the first cpu in the cpumask of a sched_group. + * @group: The group whose first cpu is to be returned. + */ +static inline unsigned int group_first_cpu(struct sched_group *group) +{ + return cpumask_first(sched_group_cpus(group)); +} + extern int group_balance_cpu(struct sched_group *sg); #endif /* CONFIG_SMP */ -- cgit v0.10.2 From b13095f07f25464de65f5ce5ea94e16813d67488 Mon Sep 17 00:00:00 2001 From: Li Zefan Date: Tue, 5 Mar 2013 16:06:38 +0800 Subject: sched: Move wake flags to kernel/sched/sched.h They are used internally only. Signed-off-by: Li Zefan Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/5135A78E.7040609@huawei.com Signed-off-by: Ingo Molnar diff --git a/include/linux/sched.h b/include/linux/sched.h index 0d64130..863b505 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -920,13 +920,6 @@ struct uts_namespace; struct rq; struct sched_domain; -/* - * wake flags - */ -#define WF_SYNC 0x01 /* waker goes to sleep after wakup */ -#define WF_FORK 0x02 /* child wakeup after fork */ -#define WF_MIGRATED 0x04 /* internal use, task got migrated */ - #define ENQUEUE_WAKEUP 1 #define ENQUEUE_HEAD 2 #ifdef CONFIG_SMP diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 1a4a2b1..4e5c2af 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -865,6 +865,13 @@ static inline void finish_lock_switch(struct rq *rq, struct task_struct *prev) } #endif /* __ARCH_WANT_UNLOCKED_CTXSW */ +/* + * wake flags + */ +#define WF_SYNC 0x01 /* waker goes to sleep after wakeup */ +#define WF_FORK 0x02 /* child wakeup after fork */ +#define WF_MIGRATED 0x4 /* internal use, task got migrated */ + static inline void update_load_add(struct load_weight *lw, unsigned long inc) { lw->weight += inc; -- cgit v0.10.2 From c82ba9fa7588dfd02d4dc99ad1af486304bc424c Mon Sep 17 00:00:00 2001 From: Li Zefan Date: Tue, 5 Mar 2013 16:06:55 +0800 Subject: sched: Move struct sched_class to kernel/sched/sched.h It's used internally only. Signed-off-by: Li Zefan Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/5135A79F.8090502@huawei.com Signed-off-by: Ingo Molnar diff --git a/include/linux/sched.h b/include/linux/sched.h index 863b505..04b834f 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -917,65 +917,6 @@ struct mempolicy; struct pipe_inode_info; struct uts_namespace; -struct rq; -struct sched_domain; - -#define ENQUEUE_WAKEUP 1 -#define ENQUEUE_HEAD 2 -#ifdef CONFIG_SMP -#define ENQUEUE_WAKING 4 /* sched_class::task_waking was called */ -#else -#define ENQUEUE_WAKING 0 -#endif - -#define DEQUEUE_SLEEP 1 - -struct sched_class { - const struct sched_class *next; - - void (*enqueue_task) (struct rq *rq, struct task_struct *p, int flags); - void (*dequeue_task) (struct rq *rq, struct task_struct *p, int flags); - void (*yield_task) (struct rq *rq); - bool (*yield_to_task) (struct rq *rq, struct task_struct *p, bool preempt); - - void (*check_preempt_curr) (struct rq *rq, struct task_struct *p, int flags); - - struct task_struct * (*pick_next_task) (struct rq *rq); - void (*put_prev_task) (struct rq *rq, struct task_struct *p); - -#ifdef CONFIG_SMP - int (*select_task_rq)(struct task_struct *p, int sd_flag, int flags); - void (*migrate_task_rq)(struct task_struct *p, int next_cpu); - - void (*pre_schedule) (struct rq *this_rq, struct task_struct *task); - void (*post_schedule) (struct rq *this_rq); - void (*task_waking) (struct task_struct *task); - void (*task_woken) (struct rq *this_rq, struct task_struct *task); - - void (*set_cpus_allowed)(struct task_struct *p, - const struct cpumask *newmask); - - void (*rq_online)(struct rq *rq); - void (*rq_offline)(struct rq *rq); -#endif - - void (*set_curr_task) (struct rq *rq); - void (*task_tick) (struct rq *rq, struct task_struct *p, int queued); - void (*task_fork) (struct task_struct *p); - - void (*switched_from) (struct rq *this_rq, struct task_struct *task); - void (*switched_to) (struct rq *this_rq, struct task_struct *task); - void (*prio_changed) (struct rq *this_rq, struct task_struct *task, - int oldprio); - - unsigned int (*get_rr_interval) (struct rq *rq, - struct task_struct *task); - -#ifdef CONFIG_FAIR_GROUP_SCHED - void (*task_move_group) (struct task_struct *p, int on_rq); -#endif -}; - struct load_weight { unsigned long weight, inv_weight; }; diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 4e5c2af..eca526d 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -951,6 +951,61 @@ enum cpuacct_stat_index { CPUACCT_STAT_NSTATS, }; +#define ENQUEUE_WAKEUP 1 +#define ENQUEUE_HEAD 2 +#ifdef CONFIG_SMP +#define ENQUEUE_WAKING 4 /* sched_class::task_waking was called */ +#else +#define ENQUEUE_WAKING 0 +#endif + +#define DEQUEUE_SLEEP 1 + +struct sched_class { + const struct sched_class *next; + + void (*enqueue_task) (struct rq *rq, struct task_struct *p, int flags); + void (*dequeue_task) (struct rq *rq, struct task_struct *p, int flags); + void (*yield_task) (struct rq *rq); + bool (*yield_to_task) (struct rq *rq, struct task_struct *p, bool preempt); + + void (*check_preempt_curr) (struct rq *rq, struct task_struct *p, int flags); + + struct task_struct * (*pick_next_task) (struct rq *rq); + void (*put_prev_task) (struct rq *rq, struct task_struct *p); + +#ifdef CONFIG_SMP + int (*select_task_rq)(struct task_struct *p, int sd_flag, int flags); + void (*migrate_task_rq)(struct task_struct *p, int next_cpu); + + void (*pre_schedule) (struct rq *this_rq, struct task_struct *task); + void (*post_schedule) (struct rq *this_rq); + void (*task_waking) (struct task_struct *task); + void (*task_woken) (struct rq *this_rq, struct task_struct *task); + + void (*set_cpus_allowed)(struct task_struct *p, + const struct cpumask *newmask); + + void (*rq_online)(struct rq *rq); + void (*rq_offline)(struct rq *rq); +#endif + + void (*set_curr_task) (struct rq *rq); + void (*task_tick) (struct rq *rq, struct task_struct *p, int queued); + void (*task_fork) (struct task_struct *p); + + void (*switched_from) (struct rq *this_rq, struct task_struct *task); + void (*switched_to) (struct rq *this_rq, struct task_struct *task); + void (*prio_changed) (struct rq *this_rq, struct task_struct *task, + int oldprio); + + unsigned int (*get_rr_interval) (struct rq *rq, + struct task_struct *task); + +#ifdef CONFIG_FAIR_GROUP_SCHED + void (*task_move_group) (struct task_struct *p, int on_rq); +#endif +}; #define sched_class_highest (&stop_sched_class) #define for_each_class(class) \ -- cgit v0.10.2 From 15f803c94bd92b17708aad9e74226fd0b2c9130c Mon Sep 17 00:00:00 2001 From: Li Zefan Date: Tue, 5 Mar 2013 16:07:11 +0800 Subject: sched: Make default_scale_freq_power() static As default_scale_{freq,smt}_power() and update_rt_power() are used in kernel/sched/fair.c only, annotate them as static functions. Signed-off-by: Li Zefan Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/5135A7AF.8010900@huawei.com Signed-off-by: Ingo Molnar diff --git a/include/linux/sched.h b/include/linux/sched.h index 04b834f..eadd113 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -880,9 +880,6 @@ extern void partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[], cpumask_var_t *alloc_sched_domains(unsigned int ndoms); void free_sched_domains(cpumask_var_t doms[], unsigned int ndoms); -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 */ diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 7a33e59..9f23112 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -4245,7 +4245,7 @@ static inline int get_sd_load_idx(struct sched_domain *sd, return load_idx; } -unsigned long default_scale_freq_power(struct sched_domain *sd, int cpu) +static unsigned long default_scale_freq_power(struct sched_domain *sd, int cpu) { return SCHED_POWER_SCALE; } @@ -4255,7 +4255,7 @@ unsigned long __weak arch_scale_freq_power(struct sched_domain *sd, int cpu) return default_scale_freq_power(sd, cpu); } -unsigned long default_scale_smt_power(struct sched_domain *sd, int cpu) +static unsigned long default_scale_smt_power(struct sched_domain *sd, int cpu) { unsigned long weight = sd->span_weight; unsigned long smt_gain = sd->smt_gain; @@ -4270,7 +4270,7 @@ unsigned long __weak arch_scale_smt_power(struct sched_domain *sd, int cpu) return default_scale_smt_power(sd, cpu); } -unsigned long scale_rt_power(int cpu) +static unsigned long scale_rt_power(int cpu) { struct rq *rq = cpu_rq(cpu); u64 total, available, age_stamp, avg; -- cgit v0.10.2 From 25cc7da7e6336d3bb6a5bad3d3fa96fce9a81d5b Mon Sep 17 00:00:00 2001 From: Li Zefan Date: Tue, 5 Mar 2013 16:07:33 +0800 Subject: sched: Move group scheduling functions out of include/linux/sched.h - Make sched_group_{set_,}runtime(), sched_group_{set_,}period() and sched_rt_can_attach() static. - Move sched_{create,destroy,online,offline}_group() to kernel/sched/sched.h. - Remove declaration of sched_group_shares(). Signed-off-by: Li Zefan Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/5135A7C5.3000708@huawei.com Signed-off-by: Ingo Molnar diff --git a/include/linux/sched.h b/include/linux/sched.h index eadd113..fc039ce 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -2512,28 +2512,7 @@ extern long sched_setaffinity(pid_t pid, const struct cpumask *new_mask); extern long sched_getaffinity(pid_t pid, struct cpumask *mask); #ifdef CONFIG_CGROUP_SCHED - extern struct task_group root_task_group; - -extern struct task_group *sched_create_group(struct task_group *parent); -extern void sched_online_group(struct task_group *tg, - struct task_group *parent); -extern void sched_destroy_group(struct task_group *tg); -extern void sched_offline_group(struct task_group *tg); -extern void sched_move_task(struct task_struct *tsk); -#ifdef CONFIG_FAIR_GROUP_SCHED -extern int sched_group_set_shares(struct task_group *tg, unsigned long shares); -extern unsigned long sched_group_shares(struct task_group *tg); -#endif -#ifdef CONFIG_RT_GROUP_SCHED -extern int sched_group_set_rt_runtime(struct task_group *tg, - long rt_runtime_us); -extern long sched_group_rt_runtime(struct task_group *tg); -extern int sched_group_set_rt_period(struct task_group *tg, - long rt_period_us); -extern long sched_group_rt_period(struct task_group *tg); -extern int sched_rt_can_attach(struct task_group *tg, struct task_struct *tsk); -#endif #endif /* CONFIG_CGROUP_SCHED */ extern int task_can_switch_user(struct user_struct *up, diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 7f12624..9ad26c9 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -7455,7 +7455,7 @@ unlock: return err; } -int sched_group_set_rt_runtime(struct task_group *tg, long rt_runtime_us) +static int sched_group_set_rt_runtime(struct task_group *tg, long rt_runtime_us) { u64 rt_runtime, rt_period; @@ -7467,7 +7467,7 @@ int sched_group_set_rt_runtime(struct task_group *tg, long rt_runtime_us) return tg_set_rt_bandwidth(tg, rt_period, rt_runtime); } -long sched_group_rt_runtime(struct task_group *tg) +static long sched_group_rt_runtime(struct task_group *tg) { u64 rt_runtime_us; @@ -7479,7 +7479,7 @@ long sched_group_rt_runtime(struct task_group *tg) return rt_runtime_us; } -int sched_group_set_rt_period(struct task_group *tg, long rt_period_us) +static int sched_group_set_rt_period(struct task_group *tg, long rt_period_us) { u64 rt_runtime, rt_period; @@ -7492,7 +7492,7 @@ int sched_group_set_rt_period(struct task_group *tg, long rt_period_us) return tg_set_rt_bandwidth(tg, rt_period, rt_runtime); } -long sched_group_rt_period(struct task_group *tg) +static long sched_group_rt_period(struct task_group *tg) { u64 rt_period_us; @@ -7527,7 +7527,7 @@ static int sched_rt_global_constraints(void) return ret; } -int sched_rt_can_attach(struct task_group *tg, struct task_struct *tsk) +static int sched_rt_can_attach(struct task_group *tg, struct task_struct *tsk) { /* Don't accept realtime tasks when there is no way for them to run */ if (rt_task(tsk) && tg->rt_bandwidth.rt_runtime == 0) diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index eca526d..304fc1c 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -221,6 +221,18 @@ extern void init_tg_rt_entry(struct task_group *tg, struct rt_rq *rt_rq, struct sched_rt_entity *rt_se, int cpu, struct sched_rt_entity *parent); +extern struct task_group *sched_create_group(struct task_group *parent); +extern void sched_online_group(struct task_group *tg, + struct task_group *parent); +extern void sched_destroy_group(struct task_group *tg); +extern void sched_offline_group(struct task_group *tg); + +extern void sched_move_task(struct task_struct *tsk); + +#ifdef CONFIG_FAIR_GROUP_SCHED +extern int sched_group_set_shares(struct task_group *tg, unsigned long shares); +#endif + #else /* CONFIG_CGROUP_SCHED */ struct cfs_bandwidth { }; -- cgit v0.10.2 From 27b4b9319a3c2e8654d45df99ce584c7c2cfe100 Mon Sep 17 00:00:00 2001 From: Li Zefan Date: Tue, 5 Mar 2013 16:07:52 +0800 Subject: sched: Remove double declaration of root_task_group It's already declared in include/linux/sched.h Signed-off-by: Li Zefan Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/5135A7D8.7000107@huawei.com Signed-off-by: Ingo Molnar diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 9ad26c9..42ecbcb 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -6861,6 +6861,10 @@ int in_sched_functions(unsigned long addr) } #ifdef CONFIG_CGROUP_SCHED +/* + * Default task group. + * Every task in system belongs to this group at bootup. + */ struct task_group root_task_group; LIST_HEAD(task_groups); #endif diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 304fc1c..30bebb9 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -179,11 +179,6 @@ struct task_group { #define MAX_SHARES (1UL << 18) #endif -/* Default task group. - * Every task in system belong to this group at bootup. - */ -extern struct task_group root_task_group; - typedef int (*tg_visitor)(struct task_group *, void *); extern int walk_tg_tree_from(struct task_group *from, -- cgit v0.10.2 From 56dd9470d7c8734f055da2a6bac553caf4a468eb Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Sun, 24 Feb 2013 00:23:25 +0100 Subject: context_tracking: Move exception handling to generic code Exceptions handling on context tracking should share common treatment: on entry we exit user mode if the exception triggered in that context. Then on exception exit we return to that previous context. Generalize this to avoid duplication across archs. Signed-off-by: Frederic Weisbecker Cc: Li Zhong Cc: Kevin Hilman Cc: Mats Liljegren Cc: Peter Zijlstra Cc: Ingo Molnar Cc: Steven Rostedt Cc: Namhyung Kim Cc: Andrew Morton Cc: Thomas Gleixner Cc: Paul E. McKenney diff --git a/arch/x86/include/asm/context_tracking.h b/arch/x86/include/asm/context_tracking.h index 1616562..1fe4970 100644 --- a/arch/x86/include/asm/context_tracking.h +++ b/arch/x86/include/asm/context_tracking.h @@ -1,31 +1,10 @@ #ifndef _ASM_X86_CONTEXT_TRACKING_H #define _ASM_X86_CONTEXT_TRACKING_H -#ifndef __ASSEMBLY__ -#include -#include - -static inline void exception_enter(struct pt_regs *regs) -{ - user_exit(); -} - -static inline void exception_exit(struct pt_regs *regs) -{ -#ifdef CONFIG_CONTEXT_TRACKING - if (user_mode(regs)) - user_enter(); -#endif -} - -#else /* __ASSEMBLY__ */ - #ifdef CONFIG_CONTEXT_TRACKING # define SCHEDULE_USER call schedule_user #else # define SCHEDULE_USER call schedule #endif -#endif /* !__ASSEMBLY__ */ - #endif diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index b686a90..e8bb0d6 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -20,6 +20,7 @@ * Authors: Anthony Liguori */ +#include #include #include #include @@ -43,7 +44,6 @@ #include #include #include -#include static int kvmapf = 1; diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index 68bda7a..ecc4ccb 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -12,6 +12,7 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt +#include #include #include #include @@ -55,8 +56,6 @@ #include #include #include -#include - #include #ifdef CONFIG_X86_64 diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index 2b97525..f946e6c 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -13,12 +13,12 @@ #include /* perf_sw_event */ #include /* hstate_index_to_shift */ #include /* prefetchw */ +#include /* exception_enter(), ... */ #include /* dotraplinkage, ... */ #include /* pgd_*(), ... */ #include /* kmemcheck_*(), ... */ #include /* VSYSCALL_START */ -#include /* exception_enter(), ... */ /* * Page fault error code bits: diff --git a/include/linux/context_tracking.h b/include/linux/context_tracking.h index b28d161..5a69273 100644 --- a/include/linux/context_tracking.h +++ b/include/linux/context_tracking.h @@ -1,10 +1,11 @@ #ifndef _LINUX_CONTEXT_TRACKING_H #define _LINUX_CONTEXT_TRACKING_H -#ifdef CONFIG_CONTEXT_TRACKING #include #include +#include +#ifdef CONFIG_CONTEXT_TRACKING struct context_tracking { /* * When active is false, probes are unset in order @@ -33,12 +34,26 @@ static inline bool context_tracking_active(void) extern void user_enter(void); extern void user_exit(void); + +static inline void exception_enter(struct pt_regs *regs) +{ + user_exit(); +} + +static inline void exception_exit(struct pt_regs *regs) +{ + if (user_mode(regs)) + user_enter(); +} + extern void context_tracking_task_switch(struct task_struct *prev, struct task_struct *next); #else static inline bool context_tracking_in_user(void) { return false; } static inline void user_enter(void) { } static inline void user_exit(void) { } +static inline void exception_enter(struct pt_regs *regs) { } +static inline void exception_exit(struct pt_regs *regs) { } static inline void context_tracking_task_switch(struct task_struct *prev, struct task_struct *next) { } #endif /* !CONFIG_CONTEXT_TRACKING */ -- cgit v0.10.2 From 6c1e0256fad84a843d915414e4b5973b7443d48d Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Sun, 24 Feb 2013 01:19:14 +0100 Subject: context_tracking: Restore correct previous context state on exception exit On exception exit, we restore the previous context tracking state based on the regs of the interrupted frame. Iff that frame is in user mode as stated by user_mode() helper, we restore the context tracking user mode. However there is a tiny chunck of low level arch code after we pass through user_enter() and until the CPU eventually resumes userspace. If an exception happens in this tiny area, exception_enter() correctly exits the context tracking user mode but exception_exit() won't restore it because of the value returned by user_mode(regs). As a result we may return to userspace with the wrong context tracking state. To fix this, change exception_enter() to return the context tracking state prior to its call and pass this saved state to exception_exit(). This restores the real context tracking state of the interrupted frame. (May be this patch was suggested to me, I don't recall exactly. If so, sorry for the missing credit). Signed-off-by: Frederic Weisbecker Cc: Li Zhong Cc: Kevin Hilman Cc: Mats Liljegren Cc: Peter Zijlstra Cc: Ingo Molnar Cc: Steven Rostedt Cc: Namhyung Kim Cc: Andrew Morton Cc: Thomas Gleixner Cc: Paul E. McKenney diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index e8bb0d6..cd6d9a5 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -254,16 +254,18 @@ EXPORT_SYMBOL_GPL(kvm_read_and_reset_pf_reason); dotraplinkage void __kprobes do_async_page_fault(struct pt_regs *regs, unsigned long error_code) { + enum ctx_state prev_state; + switch (kvm_read_and_reset_pf_reason()) { default: do_page_fault(regs, error_code); break; case KVM_PV_REASON_PAGE_NOT_PRESENT: /* page is swapped out by the host. */ - exception_enter(regs); + prev_state = exception_enter(); exit_idle(); kvm_async_pf_task_wait((u32)read_cr2()); - exception_exit(regs); + exception_exit(prev_state); break; case KVM_PV_REASON_PAGE_READY: rcu_irq_enter(); diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index ecc4ccb..ff6d227 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -175,34 +175,38 @@ do_trap(int trapnr, int signr, char *str, struct pt_regs *regs, #define DO_ERROR(trapnr, signr, str, name) \ dotraplinkage void do_##name(struct pt_regs *regs, long error_code) \ { \ - exception_enter(regs); \ + enum ctx_state prev_state; \ + \ + prev_state = exception_enter(); \ if (notify_die(DIE_TRAP, str, regs, error_code, \ trapnr, signr) == NOTIFY_STOP) { \ - exception_exit(regs); \ + exception_exit(prev_state); \ return; \ } \ conditional_sti(regs); \ do_trap(trapnr, signr, str, regs, error_code, NULL); \ - exception_exit(regs); \ + exception_exit(prev_state); \ } #define DO_ERROR_INFO(trapnr, signr, str, name, sicode, siaddr) \ dotraplinkage void do_##name(struct pt_regs *regs, long error_code) \ { \ siginfo_t info; \ + enum ctx_state prev_state; \ + \ info.si_signo = signr; \ info.si_errno = 0; \ info.si_code = sicode; \ info.si_addr = (void __user *)siaddr; \ - exception_enter(regs); \ + prev_state = exception_enter(); \ if (notify_die(DIE_TRAP, str, regs, error_code, \ trapnr, signr) == NOTIFY_STOP) { \ - exception_exit(regs); \ + exception_exit(prev_state); \ return; \ } \ conditional_sti(regs); \ do_trap(trapnr, signr, str, regs, error_code, &info); \ - exception_exit(regs); \ + exception_exit(prev_state); \ } DO_ERROR_INFO(X86_TRAP_DE, SIGFPE, "divide error", divide_error, FPE_INTDIV, @@ -225,14 +229,16 @@ DO_ERROR_INFO(X86_TRAP_AC, SIGBUS, "alignment check", alignment_check, /* Runs on IST stack */ dotraplinkage void do_stack_segment(struct pt_regs *regs, long error_code) { - exception_enter(regs); + enum ctx_state prev_state; + + prev_state = exception_enter(); if (notify_die(DIE_TRAP, "stack segment", regs, error_code, X86_TRAP_SS, SIGBUS) != NOTIFY_STOP) { preempt_conditional_sti(regs); do_trap(X86_TRAP_SS, SIGBUS, "stack segment", regs, error_code, NULL); preempt_conditional_cli(regs); } - exception_exit(regs); + exception_exit(prev_state); } dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code) @@ -240,7 +246,7 @@ dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code) static const char str[] = "double fault"; struct task_struct *tsk = current; - exception_enter(regs); + exception_enter(); /* Return not checked because double check cannot be ignored */ notify_die(DIE_TRAP, str, regs, error_code, X86_TRAP_DF, SIGSEGV); @@ -260,8 +266,9 @@ dotraplinkage void __kprobes do_general_protection(struct pt_regs *regs, long error_code) { struct task_struct *tsk; + enum ctx_state prev_state; - exception_enter(regs); + prev_state = exception_enter(); conditional_sti(regs); #ifdef CONFIG_X86_32 @@ -299,12 +306,14 @@ do_general_protection(struct pt_regs *regs, long error_code) force_sig(SIGSEGV, tsk); exit: - exception_exit(regs); + exception_exit(prev_state); } /* May run on IST stack. */ dotraplinkage void __kprobes notrace do_int3(struct pt_regs *regs, long error_code) { + enum ctx_state prev_state; + #ifdef CONFIG_DYNAMIC_FTRACE /* * ftrace must be first, everything else may cause a recursive crash. @@ -314,7 +323,7 @@ dotraplinkage void __kprobes notrace do_int3(struct pt_regs *regs, long error_co ftrace_int3_handler(regs)) return; #endif - exception_enter(regs); + prev_state = exception_enter(); #ifdef CONFIG_KGDB_LOW_LEVEL_TRAP if (kgdb_ll_trap(DIE_INT3, "int3", regs, error_code, X86_TRAP_BP, SIGTRAP) == NOTIFY_STOP) @@ -335,7 +344,7 @@ dotraplinkage void __kprobes notrace do_int3(struct pt_regs *regs, long error_co preempt_conditional_cli(regs); debug_stack_usage_dec(); exit: - exception_exit(regs); + exception_exit(prev_state); } #ifdef CONFIG_X86_64 @@ -392,11 +401,12 @@ asmlinkage __kprobes struct pt_regs *sync_regs(struct pt_regs *eregs) dotraplinkage void __kprobes do_debug(struct pt_regs *regs, long error_code) { struct task_struct *tsk = current; + enum ctx_state prev_state; int user_icebp = 0; unsigned long dr6; int si_code; - exception_enter(regs); + prev_state = exception_enter(); get_debugreg(dr6, 6); @@ -466,7 +476,7 @@ dotraplinkage void __kprobes do_debug(struct pt_regs *regs, long error_code) debug_stack_usage_dec(); exit: - exception_exit(regs); + exception_exit(prev_state); } /* @@ -560,17 +570,21 @@ void math_error(struct pt_regs *regs, int error_code, int trapnr) dotraplinkage void do_coprocessor_error(struct pt_regs *regs, long error_code) { - exception_enter(regs); + enum ctx_state prev_state; + + prev_state = exception_enter(); math_error(regs, error_code, X86_TRAP_MF); - exception_exit(regs); + exception_exit(prev_state); } dotraplinkage void do_simd_coprocessor_error(struct pt_regs *regs, long error_code) { - exception_enter(regs); + enum ctx_state prev_state; + + prev_state = exception_enter(); math_error(regs, error_code, X86_TRAP_XF); - exception_exit(regs); + exception_exit(prev_state); } dotraplinkage void @@ -638,7 +652,9 @@ EXPORT_SYMBOL_GPL(math_state_restore); dotraplinkage void __kprobes do_device_not_available(struct pt_regs *regs, long error_code) { - exception_enter(regs); + enum ctx_state prev_state; + + prev_state = exception_enter(); BUG_ON(use_eager_fpu()); #ifdef CONFIG_MATH_EMULATION @@ -649,7 +665,7 @@ do_device_not_available(struct pt_regs *regs, long error_code) info.regs = regs; math_emulate(&info); - exception_exit(regs); + exception_exit(prev_state); return; } #endif @@ -657,15 +673,16 @@ do_device_not_available(struct pt_regs *regs, long error_code) #ifdef CONFIG_X86_32 conditional_sti(regs); #endif - exception_exit(regs); + exception_exit(prev_state); } #ifdef CONFIG_X86_32 dotraplinkage void do_iret_error(struct pt_regs *regs, long error_code) { siginfo_t info; + enum ctx_state prev_state; - exception_enter(regs); + prev_state = exception_enter(); local_irq_enable(); info.si_signo = SIGILL; @@ -677,7 +694,7 @@ dotraplinkage void do_iret_error(struct pt_regs *regs, long error_code) do_trap(X86_TRAP_IRET, SIGILL, "iret exception", regs, error_code, &info); } - exception_exit(regs); + exception_exit(prev_state); } #endif diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index f946e6c..fa8c02d 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -1222,7 +1222,9 @@ good_area: dotraplinkage void __kprobes do_page_fault(struct pt_regs *regs, unsigned long error_code) { - exception_enter(regs); + enum ctx_state prev_state; + + prev_state = exception_enter(); __do_page_fault(regs, error_code); - exception_exit(regs); + exception_exit(prev_state); } diff --git a/include/linux/context_tracking.h b/include/linux/context_tracking.h index 5a69273..365f4a6 100644 --- a/include/linux/context_tracking.h +++ b/include/linux/context_tracking.h @@ -5,7 +5,6 @@ #include #include -#ifdef CONFIG_CONTEXT_TRACKING struct context_tracking { /* * When active is false, probes are unset in order @@ -14,12 +13,13 @@ struct context_tracking { * may be further optimized using static keys. */ bool active; - enum { + enum ctx_state { IN_KERNEL = 0, IN_USER, } state; }; +#ifdef CONFIG_CONTEXT_TRACKING DECLARE_PER_CPU(struct context_tracking, context_tracking); static inline bool context_tracking_in_user(void) @@ -35,14 +35,19 @@ static inline bool context_tracking_active(void) extern void user_enter(void); extern void user_exit(void); -static inline void exception_enter(struct pt_regs *regs) +static inline enum ctx_state exception_enter(void) { + enum ctx_state prev_ctx; + + prev_ctx = this_cpu_read(context_tracking.state); user_exit(); + + return prev_ctx; } -static inline void exception_exit(struct pt_regs *regs) +static inline void exception_exit(enum ctx_state prev_ctx) { - if (user_mode(regs)) + if (prev_ctx == IN_USER) user_enter(); } @@ -52,8 +57,8 @@ extern void context_tracking_task_switch(struct task_struct *prev, static inline bool context_tracking_in_user(void) { return false; } static inline void user_enter(void) { } static inline void user_exit(void) { } -static inline void exception_enter(struct pt_regs *regs) { } -static inline void exception_exit(struct pt_regs *regs) { } +static inline enum ctx_state exception_enter(void) { return 0; } +static inline void exception_exit(enum ctx_state prev_ctx) { } static inline void context_tracking_task_switch(struct task_struct *prev, struct task_struct *next) { } #endif /* !CONFIG_CONTEXT_TRACKING */ -- cgit v0.10.2 From b22366cd54c6fe05db426f20adb10f461c19ec06 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Sun, 24 Feb 2013 12:59:30 +0100 Subject: context_tracking: Restore preempted context state after preempt_schedule_irq() From the context tracking POV, preempt_schedule_irq() behaves pretty much like an exception: It can be called anytime and schedule another task. But currently it doesn't restore the context tracking state of the preempted code on preempt_schedule_irq() return. As a result, if preempt_schedule_irq() is called in the tiny frame between user_enter() and the actual return to userspace, we resume userspace with the wrong context tracking state. Fix this by using exception_enter/exit() which are a perfect fit for this kind of issue. Signed-off-by: Frederic Weisbecker Cc: Li Zhong Cc: Kevin Hilman Cc: Mats Liljegren Cc: Peter Zijlstra Cc: Ingo Molnar Cc: Steven Rostedt Cc: Namhyung Kim Cc: Andrew Morton Cc: Thomas Gleixner Cc: Paul E. McKenney diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 7f12624..af7a8c8 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -3082,11 +3082,13 @@ EXPORT_SYMBOL(preempt_schedule); asmlinkage void __sched preempt_schedule_irq(void) { struct thread_info *ti = current_thread_info(); + enum ctx_state prev_state; /* Catch callers which need to be fixed */ BUG_ON(ti->preempt_count || !irqs_disabled()); - user_exit(); + prev_state = exception_enter(); + do { add_preempt_count(PREEMPT_ACTIVE); local_irq_enable(); @@ -3100,6 +3102,8 @@ asmlinkage void __sched preempt_schedule_irq(void) */ barrier(); } while (need_resched()); + + exception_exit(prev_state); } #endif /* CONFIG_PREEMPT */ -- cgit v0.10.2 From 9fbc42eac1f6917081dc3b39922b2f1c57fdff28 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Mon, 25 Feb 2013 17:25:39 +0100 Subject: cputime: Dynamically scale cputime for full dynticks accounting The full dynticks cputime accounting is able to account either using the tick or the context tracking subsystem. This way the housekeeping CPU can keep the low overhead tick based solution. This latter mode has a low jiffies resolution granularity and need to be scaled against CFS precise runtime accounting to improve its result. We are doing this for CONFIG_TICK_CPU_ACCOUNTING, now we also need to expand it to full dynticks accounting dynamic off-case as well. Signed-off-by: Frederic Weisbecker Cc: Li Zhong Cc: Kevin Hilman Cc: Mats Liljegren Cc: Peter Zijlstra Cc: Ingo Molnar Cc: Steven Rostedt Cc: Namhyung Kim Cc: Andrew Morton Cc: Thomas Gleixner Cc: Paul E. McKenney diff --git a/include/linux/sched.h b/include/linux/sched.h index d35d2b6..8d1b603 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -570,7 +570,7 @@ struct signal_struct { cputime_t utime, stime, cutime, cstime; cputime_t gtime; cputime_t cgtime; -#ifndef CONFIG_VIRT_CPU_ACCOUNTING +#ifndef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE struct cputime prev_cputime; #endif unsigned long nvcsw, nivcsw, cnvcsw, cnivcsw; @@ -1327,7 +1327,7 @@ struct task_struct { cputime_t utime, stime, utimescaled, stimescaled; cputime_t gtime; -#ifndef CONFIG_VIRT_CPU_ACCOUNTING +#ifndef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE struct cputime prev_cputime; #endif #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN diff --git a/kernel/fork.c b/kernel/fork.c index 8d932b1..f3146ed 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1230,7 +1230,7 @@ static struct task_struct *copy_process(unsigned long clone_flags, p->utime = p->stime = p->gtime = 0; p->utimescaled = p->stimescaled = 0; -#ifndef CONFIG_VIRT_CPU_ACCOUNTING +#ifndef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE p->prev_cputime.utime = p->prev_cputime.stime = 0; #endif #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c index ed12cbb..024fe19 100644 --- a/kernel/sched/cputime.c +++ b/kernel/sched/cputime.c @@ -388,82 +388,10 @@ static inline void irqtime_account_process_tick(struct task_struct *p, int user_ struct rq *rq) {} #endif /* CONFIG_IRQ_TIME_ACCOUNTING */ -#ifndef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE -/* - * Account a single tick of cpu time. - * @p: the process that the cpu time gets accounted to - * @user_tick: indicates if the tick is a user or a system tick - */ -void account_process_tick(struct task_struct *p, int user_tick) -{ - cputime_t one_jiffy_scaled = cputime_to_scaled(cputime_one_jiffy); - struct rq *rq = this_rq(); - - if (vtime_accounting_enabled()) - return; - - if (sched_clock_irqtime) { - irqtime_account_process_tick(p, user_tick, rq); - return; - } - - if (steal_account_process_tick()) - return; - - if (user_tick) - account_user_time(p, cputime_one_jiffy, one_jiffy_scaled); - else if ((p != rq->idle) || (irq_count() != HARDIRQ_OFFSET)) - account_system_time(p, HARDIRQ_OFFSET, cputime_one_jiffy, - one_jiffy_scaled); - else - account_idle_time(cputime_one_jiffy); -} - -/* - * Account multiple ticks of steal time. - * @p: the process from which the cpu time has been stolen - * @ticks: number of stolen ticks - */ -void account_steal_ticks(unsigned long ticks) -{ - account_steal_time(jiffies_to_cputime(ticks)); -} - -/* - * Account multiple ticks of idle time. - * @ticks: number of stolen ticks - */ -void account_idle_ticks(unsigned long ticks) -{ - - if (sched_clock_irqtime) { - irqtime_account_idle_ticks(ticks); - return; - } - - account_idle_time(jiffies_to_cputime(ticks)); -} -#endif /* !CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */ - /* * Use precise platform statistics if available: */ #ifdef CONFIG_VIRT_CPU_ACCOUNTING -void task_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime_t *st) -{ - *ut = p->utime; - *st = p->stime; -} - -void thread_group_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime_t *st) -{ - struct task_cputime cputime; - - thread_group_cputime(p, &cputime); - - *ut = cputime.utime; - *st = cputime.stime; -} #ifndef __ARCH_HAS_VTIME_TASK_SWITCH void vtime_task_switch(struct task_struct *prev) @@ -518,8 +446,80 @@ void vtime_account_irq_enter(struct task_struct *tsk) } EXPORT_SYMBOL_GPL(vtime_account_irq_enter); #endif /* __ARCH_HAS_VTIME_ACCOUNT */ +#endif /* CONFIG_VIRT_CPU_ACCOUNTING */ + + +#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE +void task_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime_t *st) +{ + *ut = p->utime; + *st = p->stime; +} -#else /* !CONFIG_VIRT_CPU_ACCOUNTING */ +void thread_group_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime_t *st) +{ + struct task_cputime cputime; + + thread_group_cputime(p, &cputime); + + *ut = cputime.utime; + *st = cputime.stime; +} +#else /* !CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */ +/* + * Account a single tick of cpu time. + * @p: the process that the cpu time gets accounted to + * @user_tick: indicates if the tick is a user or a system tick + */ +void account_process_tick(struct task_struct *p, int user_tick) +{ + cputime_t one_jiffy_scaled = cputime_to_scaled(cputime_one_jiffy); + struct rq *rq = this_rq(); + + if (vtime_accounting_enabled()) + return; + + if (sched_clock_irqtime) { + irqtime_account_process_tick(p, user_tick, rq); + return; + } + + if (steal_account_process_tick()) + return; + + if (user_tick) + account_user_time(p, cputime_one_jiffy, one_jiffy_scaled); + else if ((p != rq->idle) || (irq_count() != HARDIRQ_OFFSET)) + account_system_time(p, HARDIRQ_OFFSET, cputime_one_jiffy, + one_jiffy_scaled); + else + account_idle_time(cputime_one_jiffy); +} + +/* + * Account multiple ticks of steal time. + * @p: the process from which the cpu time has been stolen + * @ticks: number of stolen ticks + */ +void account_steal_ticks(unsigned long ticks) +{ + account_steal_time(jiffies_to_cputime(ticks)); +} + +/* + * Account multiple ticks of idle time. + * @ticks: number of stolen ticks + */ +void account_idle_ticks(unsigned long ticks) +{ + + if (sched_clock_irqtime) { + irqtime_account_idle_ticks(ticks); + return; + } + + account_idle_time(jiffies_to_cputime(ticks)); +} static cputime_t scale_stime(cputime_t stime, cputime_t rtime, cputime_t total) { @@ -545,6 +545,12 @@ static void cputime_adjust(struct task_cputime *curr, { cputime_t rtime, stime, total; + if (vtime_accounting_enabled()) { + *ut = curr->utime; + *st = curr->stime; + return; + } + stime = curr->stime; total = stime + curr->utime; @@ -597,7 +603,7 @@ void thread_group_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime thread_group_cputime(p, &cputime); cputime_adjust(&cputime, &p->signal->prev_cputime, ut, st); } -#endif /* !CONFIG_VIRT_CPU_ACCOUNTING */ +#endif /* !CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */ #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN static unsigned long long vtime_delta(struct task_struct *tsk) -- cgit v0.10.2 From 8b43876643a737bb74a0e1e557f634eb2453948b Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Tue, 26 Feb 2013 15:37:59 +0100 Subject: context_tracking: Enable probes by default for selftesting Until we provide the nohz_mask boot parameter, keeping the context tracking probes disabled by default is pointless since what we want is to runtime test this code anyway. It's furthermore confusing for the users which don't expect the probes to be off when they select RCU user mode or full dynticks cputime accounting. Let's enable these probes selftests by default for now. Suggested: Steven Rostedt Signed-off-by: Frederic Weisbecker Cc: Li Zhong Cc: Kevin Hilman Cc: Mats Liljegren Cc: Peter Zijlstra Cc: Ingo Molnar Cc: Steven Rostedt Cc: Namhyung Kim Cc: Andrew Morton Cc: Thomas Gleixner Cc: Paul E. McKenney diff --git a/init/Kconfig b/init/Kconfig index 22616cd..8a1dac2 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -509,6 +509,7 @@ config RCU_USER_QS config CONTEXT_TRACKING_FORCE bool "Force context tracking" depends on CONTEXT_TRACKING + default CONTEXT_TRACKING help Probe on user/kernel boundaries by default in order to test the features that rely on it such as userspace RCU extended -- cgit v0.10.2 From b719203b846284e77f5c50fca04b458b6484aeae Mon Sep 17 00:00:00 2001 From: Li Zefan Date: Thu, 7 Mar 2013 10:00:26 +0800 Subject: sched: Fix update_group_power() prototype placement to fix build warning when !CONFIG_SMP All warnings: In file included from kernel/sched/core.c:85:0: kernel/sched/sched.h:1036:39: warning: 'struct sched_domain' declared inside parameter list kernel/sched/sched.h:1036:39: warning: its scope is only this definition or declaration, which is probably not what you want It's because struct sched_domain is defined inside #if CONFIG_SMP, while update_group_power() is declared unconditionally. Fix this warning by declaring update_group_power() only if CONFIG_SMP=n. Build tested with CONFIG_SMP enabled and then disabled. Reported-by: Fengguang Wu Signed-off-by: Li Zefan Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/5137F4BA.2060101@huawei.com Signed-off-by: Ingo Molnar diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 30bebb9..3bd15a4 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -1026,6 +1026,8 @@ extern const struct sched_class idle_sched_class; #ifdef CONFIG_SMP +extern void update_group_power(struct sched_domain *sd, int cpu); + extern void trigger_load_balance(struct rq *rq, int cpu); extern void idle_balance(int this_cpu, struct rq *this_rq); @@ -1040,7 +1042,6 @@ static inline void idle_balance(int cpu, struct rq *rq) extern void sysrq_sched_debug_show(void); extern void sched_init_granularity(void); extern void update_max_interval(void); -extern void update_group_power(struct sched_domain *sd, int cpu); extern int update_runtime(struct notifier_block *nfb, unsigned long action, void *hcpu); extern void init_sched_rt_class(void); extern void init_sched_fair_class(void); -- cgit v0.10.2 From 660cc00f8c6f7a2e16c25918590b470e86de19ec Mon Sep 17 00:00:00 2001 From: Andrei Epure Date: Mon, 11 Mar 2013 12:03:20 +0200 Subject: sched: Spelling fix Signed-off-by: Andrei Epure Cc: trivial@kernel.org Cc: peterz@infradead.org Link: http://lkml.kernel.org/r/1362996200-2674-1-git-send-email-epure.andrei@gmail.com Signed-off-by: Ingo Molnar diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 9f23112..22bd9e6 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -652,7 +652,7 @@ static u64 sched_slice(struct cfs_rq *cfs_rq, struct sched_entity *se) } /* - * We calculate the vruntime slice of a to be inserted task + * We calculate the vruntime slice of a to-be-inserted task. * * vs = s/w */ -- cgit v0.10.2 From f792685006274a850e6cc0ea9ade275ccdfc90bc Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Tue, 5 Mar 2013 18:05:46 +0100 Subject: math64: New div64_u64_rem helper Provide an extended version of div64_u64() that also returns the remainder of the division. We are going to need this to refine the cputime scaling code. Signed-off-by: Frederic Weisbecker Cc: Stanislaw Gruszka Cc: Steven Rostedt Cc: Peter Zijlstra Cc: Ingo Molnar Cc: Andrew Morton diff --git a/include/linux/math64.h b/include/linux/math64.h index b8ba855..931a619 100644 --- a/include/linux/math64.h +++ b/include/linux/math64.h @@ -30,6 +30,15 @@ static inline s64 div_s64_rem(s64 dividend, s32 divisor, s32 *remainder) } /** + * div64_u64_rem - unsigned 64bit divide with 64bit divisor + */ +static inline u64 div64_u64_rem(u64 dividend, u64 divisor, u64 *remainder) +{ + *remainder = dividend % divisor; + return dividend / divisor; +} + +/** * div64_u64 - unsigned 64bit divide with 64bit divisor */ static inline u64 div64_u64(u64 dividend, u64 divisor) @@ -61,8 +70,16 @@ static inline u64 div_u64_rem(u64 dividend, u32 divisor, u32 *remainder) extern s64 div_s64_rem(s64 dividend, s32 divisor, s32 *remainder); #endif +#ifndef div64_u64_rem +extern u64 div64_u64_rem(u64 dividend, u64 divisor, u64 *remainder); +#endif + #ifndef div64_u64 -extern u64 div64_u64(u64 dividend, u64 divisor); +static inline u64 div64_u64(u64 dividend, u64 divisor) +{ + u64 remainder; + return div64_u64_rem(dividend, divisor, &remainder); +} #endif #ifndef div64_s64 diff --git a/lib/div64.c b/lib/div64.c index a163b6c..3af5728 100644 --- a/lib/div64.c +++ b/lib/div64.c @@ -79,9 +79,10 @@ EXPORT_SYMBOL(div_s64_rem); #endif /** - * div64_u64 - unsigned 64bit divide with 64bit divisor + * div64_u64_rem - unsigned 64bit divide with 64bit divisor and 64bit remainder * @dividend: 64bit dividend * @divisor: 64bit divisor + * @remainder: 64bit remainder * * This implementation is a modified version of the algorithm proposed * by the book 'Hacker's Delight'. The original source and full proof @@ -89,27 +90,33 @@ EXPORT_SYMBOL(div_s64_rem); * * 'http://www.hackersdelight.org/HDcode/newCode/divDouble.c.txt' */ -#ifndef div64_u64 -u64 div64_u64(u64 dividend, u64 divisor) +#ifndef div64_u64_rem +u64 div64_u64_rem(u64 dividend, u64 divisor, u64 *remainder) { u32 high = divisor >> 32; u64 quot; if (high == 0) { - quot = div_u64(dividend, divisor); + u32 rem32; + quot = div_u64_rem(dividend, divisor, &rem32); + *remainder = rem32; } else { int n = 1 + fls(high); quot = div_u64(dividend >> n, divisor >> n); if (quot != 0) quot--; - if ((dividend - quot * divisor) >= divisor) + + *remainder = dividend - quot * divisor; + if (*remainder >= divisor) { quot++; + *remainder -= divisor; + } } return quot; } -EXPORT_SYMBOL(div64_u64); +EXPORT_SYMBOL(div64_u64_rem); #endif /** -- cgit v0.10.2 From d9a3c9823a2e6a543eb7807fb3d15d8233817ec5 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Wed, 20 Feb 2013 18:54:55 +0100 Subject: sched: Lower chances of cputime scaling overflow Some users have reported that after running a process with hundreds of threads on intensive CPU-bound loads, the cputime of the group started to freeze after a few days. This is due to how we scale the tick-based cputime against the scheduler precise execution time value. We add the values of all threads in the group and we multiply that against the sum of the scheduler exec runtime of the whole group. This easily overflows after a few days/weeks of execution. A proposed solution to solve this was to compute that multiplication on stime instead of utime: 62188451f0d63add7ad0cd2a1ae269d600c1663d ("cputime: Avoid multiplication overflow on utime scaling") The rationale behind that was that it's easy for a thread to spend most of its time in userspace under intensive CPU-bound workload but it's much harder to do CPU-bound intensive long run in the kernel. This postulate got defeated when a user recently reported he was still seeing cputime freezes after the above patch. The workload that triggers this issue relates to intensive networking workloads where most of the cputime is consumed in the kernel. To reduce much more the opportunities for multiplication overflow, lets reduce the multiplication factors to the remainders of the division between sched exec runtime and cputime. Assuming the difference between these shouldn't ever be that large, it could work on many situations. This gets the same results as in the upstream scaling code except for a small difference: the upstream code always rounds the results to the nearest integer not greater to what would be the precise result. The new code rounds to the nearest integer either greater or not greater. In practice this difference probably shouldn't matter but it's worth mentioning. If this solution appears not to be enough in the end, we'll need to partly revert back to the behaviour prior to commit 0cf55e1ec08bb5a22e068309e2d8ba1180ab4239 ("sched, cputime: Introduce thread_group_times()") Back then, the scaling was done on exit() time before adding the cputime of an exiting thread to the signal struct. And then we'll need to scale one-by-one the live threads cputime in thread_group_cputime(). The drawback may be a slightly slower code on exit time. Signed-off-by: Frederic Weisbecker Cc: Stanislaw Gruszka Cc: Steven Rostedt Cc: Peter Zijlstra Cc: Ingo Molnar Cc: Andrew Morton diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c index 024fe19..699d597 100644 --- a/kernel/sched/cputime.c +++ b/kernel/sched/cputime.c @@ -521,18 +521,36 @@ void account_idle_ticks(unsigned long ticks) account_idle_time(jiffies_to_cputime(ticks)); } -static cputime_t scale_stime(cputime_t stime, cputime_t rtime, cputime_t total) +/* + * Perform (stime * rtime) / total with reduced chances + * of multiplication overflows by using smaller factors + * like quotient and remainders of divisions between + * rtime and total. + */ +static cputime_t scale_stime(u64 stime, u64 rtime, u64 total) { - u64 temp = (__force u64) rtime; + u64 rem, res, scaled; - temp *= (__force u64) stime; - - if (sizeof(cputime_t) == 4) - temp = div_u64(temp, (__force u32) total); - else - temp = div64_u64(temp, (__force u64) total); + if (rtime >= total) { + /* + * Scale up to rtime / total then add + * the remainder scaled to stime / total. + */ + res = div64_u64_rem(rtime, total, &rem); + scaled = stime * res; + scaled += div64_u64(stime * rem, total); + } else { + /* + * Same in reverse: scale down to total / rtime + * then substract that result scaled to + * to the remaining part. + */ + res = div64_u64_rem(total, rtime, &rem); + scaled = div64_u64(stime, res); + scaled -= div64_u64(scaled * rem, total); + } - return (__force cputime_t) temp; + return (__force cputime_t) scaled; } /* @@ -566,10 +584,14 @@ static void cputime_adjust(struct task_cputime *curr, */ rtime = nsecs_to_cputime(curr->sum_exec_runtime); - if (total) - stime = scale_stime(stime, rtime, total); - else + if (!rtime) { + stime = 0; + } else if (!total) { stime = rtime; + } else { + stime = scale_stime((__force u64)stime, + (__force u64)rtime, (__force u64)total); + } /* * If the tick based count grows faster than the scheduler one, -- cgit v0.10.2 From 1bf08230f745e48fea9c18ee34a73581631fe7c9 Mon Sep 17 00:00:00 2001 From: Andrei Epure Date: Tue, 12 Mar 2013 21:12:24 +0200 Subject: sched: Fix variable name misnomer, add comments The min_vruntime variable actually stores the maximum value. The added comment was taken from place_entity function. Signed-off-by: Andrei Epure Cc: peterz@infradead.org Link: http://lkml.kernel.org/r/1363115544-1964-1-git-send-email-epure.andrei@gmail.com Signed-off-by: Ingo Molnar diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 22bd9e6..539760e 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -431,13 +431,13 @@ void account_cfs_rq_runtime(struct cfs_rq *cfs_rq, unsigned long delta_exec); * Scheduling class tree data structure manipulation methods: */ -static inline u64 max_vruntime(u64 min_vruntime, u64 vruntime) +static inline u64 max_vruntime(u64 max_vruntime, u64 vruntime) { - s64 delta = (s64)(vruntime - min_vruntime); + s64 delta = (s64)(vruntime - max_vruntime); if (delta > 0) - min_vruntime = vruntime; + max_vruntime = vruntime; - return min_vruntime; + return max_vruntime; } static inline u64 min_vruntime(u64 min_vruntime, u64 vruntime) @@ -473,6 +473,7 @@ static void update_min_vruntime(struct cfs_rq *cfs_rq) vruntime = min_vruntime(vruntime, se->vruntime); } + /* ensure we never gain time by being placed backwards. */ cfs_rq->min_vruntime = max_vruntime(cfs_rq->min_vruntime, vruntime); #ifndef CONFIG_64BIT smp_wmb(); -- cgit v0.10.2 From a8d7ad52a7befbde896276d05c75c90fed48b5bf Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 14 Mar 2013 10:48:39 +0100 Subject: sched/tracing: Allow tracing the preemption decision on wakeup Thomas noted that we do the wakeup preemption check after the wakeup trace point, this means the tracepoint cannot test/report this decision; which is rather important for latency sensitive workloads. Therefore move the tracepoint after doing the preemption check. Suggested-by: Thomas Gleixner Signed-off-by: Peter Zijlstra Acked-by: Steven Rostedt Acked-by: Paul Turner Cc: Mike Galbraith Link: http://lkml.kernel.org/r/1363254519.26965.9.camel@laptop Signed-off-by: Ingo Molnar diff --git a/kernel/sched/core.c b/kernel/sched/core.c index b36635e..849deb9 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -1288,8 +1288,8 @@ static void ttwu_activate(struct rq *rq, struct task_struct *p, int en_flags) static void ttwu_do_wakeup(struct rq *rq, struct task_struct *p, int wake_flags) { - trace_sched_wakeup(p, true); check_preempt_curr(rq, p, wake_flags); + trace_sched_wakeup(p, true); p->state = TASK_RUNNING; #ifdef CONFIG_SMP -- cgit v0.10.2 From 28b4a521f618d9722bc780ea38b44718ce0fe283 Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Fri, 5 Apr 2013 16:26:46 +0530 Subject: sched: Fix typo inside comment Fix typo: sched_domains_nume_distance -> sched_domains_numa_distance Signed-off-by: Viresh Kumar Cc: linaro-kernel@lists.linaro.org Cc: patches@linaro.org Cc: robin.randhawa@arm.com Cc: Steve.Bannister@arm.com Cc: Liviu.Dudau@arm.com Cc: charles.garcia-tobin@arm.com Cc: arvind.chauhan@arm.com Cc: peterz@infradead.org Link: http://lkml.kernel.org/r/cd8084746ac932106d6fa6be388b8f2d6aa9617c.1365159023.git.viresh.kumar@linaro.org Signed-off-by: Ingo Molnar diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 849deb9..f5e1aa5 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -6252,7 +6252,7 @@ static void sched_init_numa(void) * 'level' contains the number of unique distances, excluding the * identity distance node_distance(i,i). * - * The sched_domains_nume_distance[] array includes the actual distance + * The sched_domains_numa_distance[] array includes the actual distance * numbers. */ -- cgit v0.10.2 From 4e2dcb73aecbde9fe4e3137c9ea35cb6aa6cb286 Mon Sep 17 00:00:00 2001 From: Zhang Hang Date: Wed, 10 Apr 2013 14:04:55 +0800 Subject: sched: Simplify can_migrate_task() At this point tsk_cache_hot is always true, so no need to check it. Signed-off-by: Zhang Hang Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/51650107.9040606@huawei.com [ Also remove unnecessary schedstat #ifdefs. ] Signed-off-by: Ingo Molnar diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 539760e..bf8ab4f 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -3921,20 +3921,17 @@ int can_migrate_task(struct task_struct *p, struct lb_env *env) tsk_cache_hot = task_hot(p, env->src_rq->clock_task, env->sd); if (!tsk_cache_hot || env->sd->nr_balance_failed > env->sd->cache_nice_tries) { -#ifdef CONFIG_SCHEDSTATS + if (tsk_cache_hot) { schedstat_inc(env->sd, lb_hot_gained[env->idle]); schedstat_inc(p, se.statistics.nr_forced_migrations); } -#endif + return 1; } - if (tsk_cache_hot) { - schedstat_inc(p, se.statistics.nr_failed_migrations_hot); - return 0; - } - return 1; + schedstat_inc(p, se.statistics.nr_failed_migrations_hot); + return 0; } /* -- cgit v0.10.2 From b9b0853a4b377f84a5e6ed091816a9a2d6b10918 Mon Sep 17 00:00:00 2001 From: Libin Date: Mon, 1 Apr 2013 19:14:01 +0800 Subject: sched: Fix comment in rebalance_domains() A comment in function rebalance_domains() mentions arch_init_sched_domains(), but that function does not exist anymore. The proper function is init_sched_domains(). Signed-off-by: Libin Cc: Link: http://lkml.kernel.org/r/1364814841-49156-1-git-send-email-huawei.libin@huawei.com Signed-off-by: Ingo Molnar diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index bf8ab4f..155783b 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -5466,7 +5466,7 @@ void update_max_interval(void) * It checks each scheduling domain to see if it is due to be balanced, * and initiates a balancing operation if so. * - * Balancing parameters are set up in arch_init_sched_domains. + * Balancing parameters are set up in init_sched_domains. */ static void rebalance_domains(int cpu, enum cpu_idle_type idle) { -- cgit v0.10.2 From 2e76c24d72372db35f226a49c2b99d0fd8cfd400 Mon Sep 17 00:00:00 2001 From: Li Zefan Date: Fri, 29 Mar 2013 14:36:31 +0800 Subject: sched: Split cpuacct code out of core.c Signed-off-by: Li Zefan Acked-by: Peter Zijlstra Link: http://lkml.kernel.org/r/5155366F.5060404@huawei.com Signed-off-by: Ingo Molnar diff --git a/kernel/sched/Makefile b/kernel/sched/Makefile index f06d249..deaf90e 100644 --- a/kernel/sched/Makefile +++ b/kernel/sched/Makefile @@ -16,3 +16,4 @@ obj-$(CONFIG_SMP) += cpupri.o obj-$(CONFIG_SCHED_AUTOGROUP) += auto_group.o obj-$(CONFIG_SCHEDSTATS) += stats.o obj-$(CONFIG_SCHED_DEBUG) += debug.o +obj-$(CONFIG_CGROUP_CPUACCT) += cpuacct.o diff --git a/kernel/sched/core.c b/kernel/sched/core.c index f5e1aa5..c28222f 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -8043,226 +8043,6 @@ struct cgroup_subsys cpu_cgroup_subsys = { #endif /* CONFIG_CGROUP_SCHED */ -#ifdef CONFIG_CGROUP_CPUACCT - -/* - * CPU accounting code for task groups. - * - * Based on the work by Paul Menage (menage@google.com) and Balbir Singh - * (balbir@in.ibm.com). - */ - -struct cpuacct root_cpuacct; - -/* create a new cpu accounting group */ -static struct cgroup_subsys_state *cpuacct_css_alloc(struct cgroup *cgrp) -{ - struct cpuacct *ca; - - if (!cgrp->parent) - return &root_cpuacct.css; - - ca = kzalloc(sizeof(*ca), GFP_KERNEL); - if (!ca) - goto out; - - ca->cpuusage = alloc_percpu(u64); - if (!ca->cpuusage) - goto out_free_ca; - - ca->cpustat = alloc_percpu(struct kernel_cpustat); - if (!ca->cpustat) - goto out_free_cpuusage; - - return &ca->css; - -out_free_cpuusage: - free_percpu(ca->cpuusage); -out_free_ca: - kfree(ca); -out: - return ERR_PTR(-ENOMEM); -} - -/* destroy an existing cpu accounting group */ -static void cpuacct_css_free(struct cgroup *cgrp) -{ - struct cpuacct *ca = cgroup_ca(cgrp); - - free_percpu(ca->cpustat); - free_percpu(ca->cpuusage); - kfree(ca); -} - -static u64 cpuacct_cpuusage_read(struct cpuacct *ca, int cpu) -{ - u64 *cpuusage = per_cpu_ptr(ca->cpuusage, cpu); - u64 data; - -#ifndef CONFIG_64BIT - /* - * Take rq->lock to make 64-bit read safe on 32-bit platforms. - */ - raw_spin_lock_irq(&cpu_rq(cpu)->lock); - data = *cpuusage; - raw_spin_unlock_irq(&cpu_rq(cpu)->lock); -#else - data = *cpuusage; -#endif - - return data; -} - -static void cpuacct_cpuusage_write(struct cpuacct *ca, int cpu, u64 val) -{ - u64 *cpuusage = per_cpu_ptr(ca->cpuusage, cpu); - -#ifndef CONFIG_64BIT - /* - * Take rq->lock to make 64-bit write safe on 32-bit platforms. - */ - raw_spin_lock_irq(&cpu_rq(cpu)->lock); - *cpuusage = val; - raw_spin_unlock_irq(&cpu_rq(cpu)->lock); -#else - *cpuusage = val; -#endif -} - -/* return total cpu usage (in nanoseconds) of a group */ -static u64 cpuusage_read(struct cgroup *cgrp, struct cftype *cft) -{ - struct cpuacct *ca = cgroup_ca(cgrp); - u64 totalcpuusage = 0; - int i; - - for_each_present_cpu(i) - totalcpuusage += cpuacct_cpuusage_read(ca, i); - - return totalcpuusage; -} - -static int cpuusage_write(struct cgroup *cgrp, struct cftype *cftype, - u64 reset) -{ - struct cpuacct *ca = cgroup_ca(cgrp); - int err = 0; - int i; - - if (reset) { - err = -EINVAL; - goto out; - } - - for_each_present_cpu(i) - cpuacct_cpuusage_write(ca, i, 0); - -out: - return err; -} - -static int cpuacct_percpu_seq_read(struct cgroup *cgroup, struct cftype *cft, - struct seq_file *m) -{ - struct cpuacct *ca = cgroup_ca(cgroup); - u64 percpu; - int i; - - for_each_present_cpu(i) { - percpu = cpuacct_cpuusage_read(ca, i); - seq_printf(m, "%llu ", (unsigned long long) percpu); - } - seq_printf(m, "\n"); - return 0; -} - -static const char *cpuacct_stat_desc[] = { - [CPUACCT_STAT_USER] = "user", - [CPUACCT_STAT_SYSTEM] = "system", -}; - -static int cpuacct_stats_show(struct cgroup *cgrp, struct cftype *cft, - struct cgroup_map_cb *cb) -{ - struct cpuacct *ca = cgroup_ca(cgrp); - int cpu; - s64 val = 0; - - for_each_online_cpu(cpu) { - struct kernel_cpustat *kcpustat = per_cpu_ptr(ca->cpustat, cpu); - val += kcpustat->cpustat[CPUTIME_USER]; - val += kcpustat->cpustat[CPUTIME_NICE]; - } - val = cputime64_to_clock_t(val); - cb->fill(cb, cpuacct_stat_desc[CPUACCT_STAT_USER], val); - - val = 0; - for_each_online_cpu(cpu) { - struct kernel_cpustat *kcpustat = per_cpu_ptr(ca->cpustat, cpu); - val += kcpustat->cpustat[CPUTIME_SYSTEM]; - val += kcpustat->cpustat[CPUTIME_IRQ]; - val += kcpustat->cpustat[CPUTIME_SOFTIRQ]; - } - - val = cputime64_to_clock_t(val); - cb->fill(cb, cpuacct_stat_desc[CPUACCT_STAT_SYSTEM], val); - - return 0; -} - -static struct cftype files[] = { - { - .name = "usage", - .read_u64 = cpuusage_read, - .write_u64 = cpuusage_write, - }, - { - .name = "usage_percpu", - .read_seq_string = cpuacct_percpu_seq_read, - }, - { - .name = "stat", - .read_map = cpuacct_stats_show, - }, - { } /* terminate */ -}; - -/* - * charge this task's execution time to its accounting group. - * - * called with rq->lock held. - */ -void cpuacct_charge(struct task_struct *tsk, u64 cputime) -{ - struct cpuacct *ca; - int cpu; - - if (unlikely(!cpuacct_subsys.active)) - return; - - cpu = task_cpu(tsk); - - rcu_read_lock(); - - ca = task_ca(tsk); - - for (; ca; ca = parent_ca(ca)) { - u64 *cpuusage = per_cpu_ptr(ca->cpuusage, cpu); - *cpuusage += cputime; - } - - rcu_read_unlock(); -} - -struct cgroup_subsys cpuacct_subsys = { - .name = "cpuacct", - .css_alloc = cpuacct_css_alloc, - .css_free = cpuacct_css_free, - .subsys_id = cpuacct_subsys_id, - .base_cftypes = files, -}; -#endif /* CONFIG_CGROUP_CPUACCT */ - void dump_cpu_task(int cpu) { pr_info("Task dump for CPU %d:\n", cpu); diff --git a/kernel/sched/cpuacct.c b/kernel/sched/cpuacct.c new file mode 100644 index 0000000..50ec24b --- /dev/null +++ b/kernel/sched/cpuacct.c @@ -0,0 +1,227 @@ +#include +#include +#include +#include +#include +#include +#include +#include + +#include "sched.h" + +/* + * CPU accounting code for task groups. + * + * Based on the work by Paul Menage (menage@google.com) and Balbir Singh + * (balbir@in.ibm.com). + */ + +struct cpuacct root_cpuacct; + +/* create a new cpu accounting group */ +static struct cgroup_subsys_state *cpuacct_css_alloc(struct cgroup *cgrp) +{ + struct cpuacct *ca; + + if (!cgrp->parent) + return &root_cpuacct.css; + + ca = kzalloc(sizeof(*ca), GFP_KERNEL); + if (!ca) + goto out; + + ca->cpuusage = alloc_percpu(u64); + if (!ca->cpuusage) + goto out_free_ca; + + ca->cpustat = alloc_percpu(struct kernel_cpustat); + if (!ca->cpustat) + goto out_free_cpuusage; + + return &ca->css; + +out_free_cpuusage: + free_percpu(ca->cpuusage); +out_free_ca: + kfree(ca); +out: + return ERR_PTR(-ENOMEM); +} + +/* destroy an existing cpu accounting group */ +static void cpuacct_css_free(struct cgroup *cgrp) +{ + struct cpuacct *ca = cgroup_ca(cgrp); + + free_percpu(ca->cpustat); + free_percpu(ca->cpuusage); + kfree(ca); +} + +static u64 cpuacct_cpuusage_read(struct cpuacct *ca, int cpu) +{ + u64 *cpuusage = per_cpu_ptr(ca->cpuusage, cpu); + u64 data; + +#ifndef CONFIG_64BIT + /* + * Take rq->lock to make 64-bit read safe on 32-bit platforms. + */ + raw_spin_lock_irq(&cpu_rq(cpu)->lock); + data = *cpuusage; + raw_spin_unlock_irq(&cpu_rq(cpu)->lock); +#else + data = *cpuusage; +#endif + + return data; +} + +static void cpuacct_cpuusage_write(struct cpuacct *ca, int cpu, u64 val) +{ + u64 *cpuusage = per_cpu_ptr(ca->cpuusage, cpu); + +#ifndef CONFIG_64BIT + /* + * Take rq->lock to make 64-bit write safe on 32-bit platforms. + */ + raw_spin_lock_irq(&cpu_rq(cpu)->lock); + *cpuusage = val; + raw_spin_unlock_irq(&cpu_rq(cpu)->lock); +#else + *cpuusage = val; +#endif +} + +/* return total cpu usage (in nanoseconds) of a group */ +static u64 cpuusage_read(struct cgroup *cgrp, struct cftype *cft) +{ + struct cpuacct *ca = cgroup_ca(cgrp); + u64 totalcpuusage = 0; + int i; + + for_each_present_cpu(i) + totalcpuusage += cpuacct_cpuusage_read(ca, i); + + return totalcpuusage; +} + +static int cpuusage_write(struct cgroup *cgrp, struct cftype *cftype, + u64 reset) +{ + struct cpuacct *ca = cgroup_ca(cgrp); + int err = 0; + int i; + + if (reset) { + err = -EINVAL; + goto out; + } + + for_each_present_cpu(i) + cpuacct_cpuusage_write(ca, i, 0); + +out: + return err; +} + +static int cpuacct_percpu_seq_read(struct cgroup *cgroup, struct cftype *cft, + struct seq_file *m) +{ + struct cpuacct *ca = cgroup_ca(cgroup); + u64 percpu; + int i; + + for_each_present_cpu(i) { + percpu = cpuacct_cpuusage_read(ca, i); + seq_printf(m, "%llu ", (unsigned long long) percpu); + } + seq_printf(m, "\n"); + return 0; +} + +static const char * const cpuacct_stat_desc[] = { + [CPUACCT_STAT_USER] = "user", + [CPUACCT_STAT_SYSTEM] = "system", +}; + +static int cpuacct_stats_show(struct cgroup *cgrp, struct cftype *cft, + struct cgroup_map_cb *cb) +{ + struct cpuacct *ca = cgroup_ca(cgrp); + int cpu; + s64 val = 0; + + for_each_online_cpu(cpu) { + struct kernel_cpustat *kcpustat = per_cpu_ptr(ca->cpustat, cpu); + val += kcpustat->cpustat[CPUTIME_USER]; + val += kcpustat->cpustat[CPUTIME_NICE]; + } + val = cputime64_to_clock_t(val); + cb->fill(cb, cpuacct_stat_desc[CPUACCT_STAT_USER], val); + + val = 0; + for_each_online_cpu(cpu) { + struct kernel_cpustat *kcpustat = per_cpu_ptr(ca->cpustat, cpu); + val += kcpustat->cpustat[CPUTIME_SYSTEM]; + val += kcpustat->cpustat[CPUTIME_IRQ]; + val += kcpustat->cpustat[CPUTIME_SOFTIRQ]; + } + + val = cputime64_to_clock_t(val); + cb->fill(cb, cpuacct_stat_desc[CPUACCT_STAT_SYSTEM], val); + + return 0; +} + +static struct cftype files[] = { + { + .name = "usage", + .read_u64 = cpuusage_read, + .write_u64 = cpuusage_write, + }, + { + .name = "usage_percpu", + .read_seq_string = cpuacct_percpu_seq_read, + }, + { + .name = "stat", + .read_map = cpuacct_stats_show, + }, + { } /* terminate */ +}; + +/* + * charge this task's execution time to its accounting group. + * + * called with rq->lock held. + */ +void cpuacct_charge(struct task_struct *tsk, u64 cputime) +{ + struct cpuacct *ca; + int cpu; + + if (unlikely(!cpuacct_subsys.active)) + return; + + cpu = task_cpu(tsk); + + rcu_read_lock(); + + ca = task_ca(tsk); + + for (; ca; ca = parent_ca(ca)) { + u64 *cpuusage = per_cpu_ptr(ca->cpuusage, cpu); + *cpuusage += cputime; + } + + rcu_read_unlock(); +} + +struct cgroup_subsys cpuacct_subsys = { + .name = "cpuacct", + .css_alloc = cpuacct_css_alloc, + .css_free = cpuacct_css_free, + .subsys_id = cpuacct_subsys_id, + .base_cftypes = files, +}; -- cgit v0.10.2 From 60fed7891d4115be0ed7ff9ce6851eda80533c64 Mon Sep 17 00:00:00 2001 From: Li Zefan Date: Fri, 29 Mar 2013 14:36:43 +0800 Subject: sched: Split cpuacct code out of sched.h Add cpuacct.h and let sched.h include it. Signed-off-by: Li Zefan Acked-by: Peter Zijlstra Link: http://lkml.kernel.org/r/5155367B.2060506@huawei.com Signed-off-by: Ingo Molnar diff --git a/kernel/sched/cpuacct.h b/kernel/sched/cpuacct.h new file mode 100644 index 0000000..a7f3d4a --- /dev/null +++ b/kernel/sched/cpuacct.h @@ -0,0 +1,52 @@ +/* Time spent by the tasks of the cpu accounting group executing in ... */ +enum cpuacct_stat_index { + CPUACCT_STAT_USER, /* ... user mode */ + CPUACCT_STAT_SYSTEM, /* ... kernel mode */ + + CPUACCT_STAT_NSTATS, +}; + +#ifdef CONFIG_CGROUP_CPUACCT + +#include +/* track cpu usage of a group of tasks and its child groups */ +struct cpuacct { + struct cgroup_subsys_state css; + /* cpuusage holds pointer to a u64-type object on every cpu */ + u64 __percpu *cpuusage; + struct kernel_cpustat __percpu *cpustat; +}; + +extern struct cgroup_subsys cpuacct_subsys; +extern struct cpuacct root_cpuacct; + +/* return cpu accounting group corresponding to this container */ +static inline struct cpuacct *cgroup_ca(struct cgroup *cgrp) +{ + return container_of(cgroup_subsys_state(cgrp, cpuacct_subsys_id), + struct cpuacct, css); +} + +/* return cpu accounting group to which this task belongs */ +static inline struct cpuacct *task_ca(struct task_struct *tsk) +{ + return container_of(task_subsys_state(tsk, cpuacct_subsys_id), + struct cpuacct, css); +} + +static inline struct cpuacct *parent_ca(struct cpuacct *ca) +{ + if (!ca || !ca->css.cgroup->parent) + return NULL; + return cgroup_ca(ca->css.cgroup->parent); +} + +extern void cpuacct_charge(struct task_struct *tsk, u64 cputime); + +#else + +static inline void cpuacct_charge(struct task_struct *tsk, u64 cputime) +{ +} + +#endif diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 3bd15a4..8116cf8 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -7,6 +7,7 @@ #include #include "cpupri.h" +#include "cpuacct.h" extern __read_mostly int scheduler_running; @@ -950,14 +951,6 @@ static const u32 prio_to_wmult[40] = { /* 15 */ 119304647, 148102320, 186737708, 238609294, 286331153, }; -/* Time spent by the tasks of the cpu accounting group executing in ... */ -enum cpuacct_stat_index { - CPUACCT_STAT_USER, /* ... user mode */ - CPUACCT_STAT_SYSTEM, /* ... kernel mode */ - - CPUACCT_STAT_NSTATS, -}; - #define ENQUEUE_WAKEUP 1 #define ENQUEUE_HEAD 2 #ifdef CONFIG_SMP @@ -1054,45 +1047,6 @@ extern void init_rt_bandwidth(struct rt_bandwidth *rt_b, u64 period, u64 runtime extern void update_idle_cpu_load(struct rq *this_rq); -#ifdef CONFIG_CGROUP_CPUACCT -#include -/* track cpu usage of a group of tasks and its child groups */ -struct cpuacct { - struct cgroup_subsys_state css; - /* cpuusage holds pointer to a u64-type object on every cpu */ - u64 __percpu *cpuusage; - struct kernel_cpustat __percpu *cpustat; -}; - -extern struct cgroup_subsys cpuacct_subsys; -extern struct cpuacct root_cpuacct; - -/* return cpu accounting group corresponding to this container */ -static inline struct cpuacct *cgroup_ca(struct cgroup *cgrp) -{ - return container_of(cgroup_subsys_state(cgrp, cpuacct_subsys_id), - struct cpuacct, css); -} - -/* return cpu accounting group to which this task belongs */ -static inline struct cpuacct *task_ca(struct task_struct *tsk) -{ - return container_of(task_subsys_state(tsk, cpuacct_subsys_id), - struct cpuacct, css); -} - -static inline struct cpuacct *parent_ca(struct cpuacct *ca) -{ - if (!ca || !ca->css.cgroup->parent) - return NULL; - return cgroup_ca(ca->css.cgroup->parent); -} - -extern void cpuacct_charge(struct task_struct *tsk, u64 cputime); -#else -static inline void cpuacct_charge(struct task_struct *tsk, u64 cputime) {} -#endif - #ifdef CONFIG_PARAVIRT static inline u64 steal_ticks(u64 steal) { -- cgit v0.10.2 From dbe4b41f9800223949ce72e4289814697e0ea91a Mon Sep 17 00:00:00 2001 From: Li Zefan Date: Fri, 29 Mar 2013 14:36:55 +0800 Subject: sched/cpuacct: Add cpuacct_init() So we don't open-coded initialization of cpuacct in core.c. Signed-off-by: Li Zefan Acked-by: Peter Zijlstra Link: http://lkml.kernel.org/r/51553687.1060906@huawei.com Signed-off-by: Ingo Molnar diff --git a/kernel/sched/core.c b/kernel/sched/core.c index c28222f..92930a8 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -6936,12 +6936,8 @@ void __init sched_init(void) #endif /* CONFIG_CGROUP_SCHED */ -#ifdef CONFIG_CGROUP_CPUACCT - root_cpuacct.cpustat = &kernel_cpustat; - root_cpuacct.cpuusage = alloc_percpu(u64); - /* Too early, not expected to fail */ - BUG_ON(!root_cpuacct.cpuusage); -#endif + cpuacct_init(); + for_each_possible_cpu(i) { struct rq *rq; diff --git a/kernel/sched/cpuacct.c b/kernel/sched/cpuacct.c index 50ec24b..48b5e91 100644 --- a/kernel/sched/cpuacct.c +++ b/kernel/sched/cpuacct.c @@ -218,6 +218,13 @@ void cpuacct_charge(struct task_struct *tsk, u64 cputime) rcu_read_unlock(); } +void __init cpuacct_init(void) +{ + root_cpuacct.cpustat = &kernel_cpustat; + root_cpuacct.cpuusage = alloc_percpu(u64); + BUG_ON(!root_cpuacct.cpuusage); /* Too early, not expected to fail */ +} + struct cgroup_subsys cpuacct_subsys = { .name = "cpuacct", .css_alloc = cpuacct_css_alloc, diff --git a/kernel/sched/cpuacct.h b/kernel/sched/cpuacct.h index a7f3d4a..551acd7 100644 --- a/kernel/sched/cpuacct.h +++ b/kernel/sched/cpuacct.h @@ -41,10 +41,15 @@ static inline struct cpuacct *parent_ca(struct cpuacct *ca) return cgroup_ca(ca->css.cgroup->parent); } +extern void cpuacct_init(void); extern void cpuacct_charge(struct task_struct *tsk, u64 cputime); #else +static inline void cpuacct_init(void) +{ +} + static inline void cpuacct_charge(struct task_struct *tsk, u64 cputime) { } -- cgit v0.10.2 From 1966aaf7d54608e8ddb7ac454b461840e763409a Mon Sep 17 00:00:00 2001 From: Li Zefan Date: Fri, 29 Mar 2013 14:37:06 +0800 Subject: sched/cpuacct: Add cpuacct_acount_field() So we can remove open-coded cpuacct code in cputime.c. Signed-off-by: Li Zefan Acked-by: Peter Zijlstra Link: http://lkml.kernel.org/r/51553692.9060008@huawei.com Signed-off-by: Ingo Molnar diff --git a/kernel/sched/cpuacct.c b/kernel/sched/cpuacct.c index 48b5e91..72bd971 100644 --- a/kernel/sched/cpuacct.c +++ b/kernel/sched/cpuacct.c @@ -218,6 +218,29 @@ void cpuacct_charge(struct task_struct *tsk, u64 cputime) rcu_read_unlock(); } +/* + * Add user/system time to cpuacct. + * + * Note: it's the caller that updates the account of the root cgroup. + */ +void cpuacct_account_field(struct task_struct *p, int index, u64 val) +{ + struct kernel_cpustat *kcpustat; + struct cpuacct *ca; + + if (unlikely(!cpuacct_subsys.active)) + return; + + rcu_read_lock(); + ca = task_ca(p); + while (ca && (ca != &root_cpuacct)) { + kcpustat = this_cpu_ptr(ca->cpustat); + kcpustat->cpustat[index] += val; + ca = parent_ca(ca); + } + rcu_read_unlock(); +} + void __init cpuacct_init(void) { root_cpuacct.cpustat = &kernel_cpustat; diff --git a/kernel/sched/cpuacct.h b/kernel/sched/cpuacct.h index 551acd7..bd0409b 100644 --- a/kernel/sched/cpuacct.h +++ b/kernel/sched/cpuacct.h @@ -43,6 +43,7 @@ static inline struct cpuacct *parent_ca(struct cpuacct *ca) extern void cpuacct_init(void); extern void cpuacct_charge(struct task_struct *tsk, u64 cputime); +extern void cpuacct_account_field(struct task_struct *p, int index, u64 val); #else @@ -54,4 +55,9 @@ static inline void cpuacct_charge(struct task_struct *tsk, u64 cputime) { } +static inline void +cpuacct_account_field(struct task_struct *p, int index, u64 val) +{ +} + #endif diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c index 699d597..33508dc 100644 --- a/kernel/sched/cputime.c +++ b/kernel/sched/cputime.c @@ -115,10 +115,6 @@ static int irqtime_account_si_update(void) static inline void task_group_account_field(struct task_struct *p, int index, u64 tmp) { -#ifdef CONFIG_CGROUP_CPUACCT - struct kernel_cpustat *kcpustat; - struct cpuacct *ca; -#endif /* * Since all updates are sure to touch the root cgroup, we * get ourselves ahead and touch it first. If the root cgroup @@ -127,19 +123,7 @@ static inline void task_group_account_field(struct task_struct *p, int index, */ __get_cpu_var(kernel_cpustat).cpustat[index] += tmp; -#ifdef CONFIG_CGROUP_CPUACCT - if (unlikely(!cpuacct_subsys.active)) - return; - - rcu_read_lock(); - ca = task_ca(p); - while (ca && (ca != &root_cpuacct)) { - kcpustat = this_cpu_ptr(ca->cpustat); - kcpustat->cpustat[index] += tmp; - ca = parent_ca(ca); - } - rcu_read_unlock(); -#endif + cpuacct_account_field(p, index, tmp); } /* -- cgit v0.10.2 From 543bc0e76e6bb84300eaf9833edc5a481f788678 Mon Sep 17 00:00:00 2001 From: Li Zefan Date: Fri, 29 Mar 2013 14:37:29 +0800 Subject: sched/cpuacct: Remove redundant NULL checks in cpuacct_charge() This is a micro optimization for the hot path. - We don't need to check if @ca is NULL in parent_ca(). - We don't need to check if @ca is NULL in the beginning of the for loop. Signed-off-by: Li Zefan Acked-by: Peter Zijlstra Link: http://lkml.kernel.org/r/515536A9.5000700@huawei.com Signed-off-by: Ingo Molnar diff --git a/kernel/sched/cpuacct.c b/kernel/sched/cpuacct.c index 72bd971..b2aaaba 100644 --- a/kernel/sched/cpuacct.c +++ b/kernel/sched/cpuacct.c @@ -210,9 +210,13 @@ void cpuacct_charge(struct task_struct *tsk, u64 cputime) ca = task_ca(tsk); - for (; ca; ca = parent_ca(ca)) { + while (true) { u64 *cpuusage = per_cpu_ptr(ca->cpuusage, cpu); *cpuusage += cputime; + + ca = parent_ca(ca); + if (!ca) + break; } rcu_read_unlock(); diff --git a/kernel/sched/cpuacct.h b/kernel/sched/cpuacct.h index bd0409b..45c1682 100644 --- a/kernel/sched/cpuacct.h +++ b/kernel/sched/cpuacct.h @@ -36,7 +36,7 @@ static inline struct cpuacct *task_ca(struct task_struct *tsk) static inline struct cpuacct *parent_ca(struct cpuacct *ca) { - if (!ca || !ca->css.cgroup->parent) + if (!ca->css.cgroup->parent) return NULL; return cgroup_ca(ca->css.cgroup->parent); } -- cgit v0.10.2 From 5f40d804325e925409907e29f46ecb012090b6c2 Mon Sep 17 00:00:00 2001 From: Li Zefan Date: Fri, 29 Mar 2013 14:37:43 +0800 Subject: sched/cpuacct: Remove redundant NULL checks in cpuacct_acount_field() This is a micro optimazation for a hot path. - We don't need to check if @ca returned from task_ca() is NULL. - We don't need to check if @ca returned from parent_ca() is NULL. Signed-off-by: Li Zefan Acked-by: Peter Zijlstra Link: http://lkml.kernel.org/r/515536B7.6060602@huawei.com Signed-off-by: Ingo Molnar diff --git a/kernel/sched/cpuacct.c b/kernel/sched/cpuacct.c index b2aaaba..071ae8d 100644 --- a/kernel/sched/cpuacct.c +++ b/kernel/sched/cpuacct.c @@ -237,10 +237,10 @@ void cpuacct_account_field(struct task_struct *p, int index, u64 val) rcu_read_lock(); ca = task_ca(p); - while (ca && (ca != &root_cpuacct)) { + while (ca != &root_cpuacct) { kcpustat = this_cpu_ptr(ca->cpustat); kcpustat->cpustat[index] += val; - ca = parent_ca(ca); + ca = __parent_ca(ca); } rcu_read_unlock(); } diff --git a/kernel/sched/cpuacct.h b/kernel/sched/cpuacct.h index 45c1682..b2f79ad1 100644 --- a/kernel/sched/cpuacct.h +++ b/kernel/sched/cpuacct.h @@ -34,6 +34,11 @@ static inline struct cpuacct *task_ca(struct task_struct *tsk) struct cpuacct, css); } +static inline struct cpuacct *__parent_ca(struct cpuacct *ca) +{ + return cgroup_ca(ca->css.cgroup->parent); +} + static inline struct cpuacct *parent_ca(struct cpuacct *ca) { if (!ca->css.cgroup->parent) -- cgit v0.10.2 From d1712796a880bea0a44739941116001923f3275b Mon Sep 17 00:00:00 2001 From: Li Zefan Date: Fri, 29 Mar 2013 14:38:13 +0800 Subject: sched/cpuacct: Clean up cpuacct.h Now most of the code in cpuacct.h can be moved to cpuacct.c Signed-off-by: Li Zefan Acked-by: Peter Zijlstra Link: http://lkml.kernel.org/r/515536D5.2080401@huawei.com Signed-off-by: Ingo Molnar diff --git a/kernel/sched/cpuacct.c b/kernel/sched/cpuacct.c index 071ae8d..9305fd2 100644 --- a/kernel/sched/cpuacct.c +++ b/kernel/sched/cpuacct.c @@ -16,7 +16,49 @@ * (balbir@in.ibm.com). */ -struct cpuacct root_cpuacct; +/* Time spent by the tasks of the cpu accounting group executing in ... */ +enum cpuacct_stat_index { + CPUACCT_STAT_USER, /* ... user mode */ + CPUACCT_STAT_SYSTEM, /* ... kernel mode */ + + CPUACCT_STAT_NSTATS, +}; + +/* track cpu usage of a group of tasks and its child groups */ +struct cpuacct { + struct cgroup_subsys_state css; + /* cpuusage holds pointer to a u64-type object on every cpu */ + u64 __percpu *cpuusage; + struct kernel_cpustat __percpu *cpustat; +}; + +/* return cpu accounting group corresponding to this container */ +static inline struct cpuacct *cgroup_ca(struct cgroup *cgrp) +{ + return container_of(cgroup_subsys_state(cgrp, cpuacct_subsys_id), + struct cpuacct, css); +} + +/* return cpu accounting group to which this task belongs */ +static inline struct cpuacct *task_ca(struct task_struct *tsk) +{ + return container_of(task_subsys_state(tsk, cpuacct_subsys_id), + struct cpuacct, css); +} + +static inline struct cpuacct *__parent_ca(struct cpuacct *ca) +{ + return cgroup_ca(ca->css.cgroup->parent); +} + +static inline struct cpuacct *parent_ca(struct cpuacct *ca) +{ + if (!ca->css.cgroup->parent) + return NULL; + return cgroup_ca(ca->css.cgroup->parent); +} + +static struct cpuacct root_cpuacct; /* create a new cpu accounting group */ static struct cgroup_subsys_state *cpuacct_css_alloc(struct cgroup *cgrp) diff --git a/kernel/sched/cpuacct.h b/kernel/sched/cpuacct.h index b2f79ad1..51cd76e 100644 --- a/kernel/sched/cpuacct.h +++ b/kernel/sched/cpuacct.h @@ -1,51 +1,5 @@ -/* Time spent by the tasks of the cpu accounting group executing in ... */ -enum cpuacct_stat_index { - CPUACCT_STAT_USER, /* ... user mode */ - CPUACCT_STAT_SYSTEM, /* ... kernel mode */ - - CPUACCT_STAT_NSTATS, -}; - #ifdef CONFIG_CGROUP_CPUACCT -#include -/* track cpu usage of a group of tasks and its child groups */ -struct cpuacct { - struct cgroup_subsys_state css; - /* cpuusage holds pointer to a u64-type object on every cpu */ - u64 __percpu *cpuusage; - struct kernel_cpustat __percpu *cpustat; -}; - -extern struct cgroup_subsys cpuacct_subsys; -extern struct cpuacct root_cpuacct; - -/* return cpu accounting group corresponding to this container */ -static inline struct cpuacct *cgroup_ca(struct cgroup *cgrp) -{ - return container_of(cgroup_subsys_state(cgrp, cpuacct_subsys_id), - struct cpuacct, css); -} - -/* return cpu accounting group to which this task belongs */ -static inline struct cpuacct *task_ca(struct task_struct *tsk) -{ - return container_of(task_subsys_state(tsk, cpuacct_subsys_id), - struct cpuacct, css); -} - -static inline struct cpuacct *__parent_ca(struct cpuacct *ca) -{ - return cgroup_ca(ca->css.cgroup->parent); -} - -static inline struct cpuacct *parent_ca(struct cpuacct *ca) -{ - if (!ca->css.cgroup->parent) - return NULL; - return cgroup_ca(ca->css.cgroup->parent); -} - extern void cpuacct_init(void); extern void cpuacct_charge(struct task_struct *tsk, u64 cputime); extern void cpuacct_account_field(struct task_struct *p, int index, u64 val); -- cgit v0.10.2 From 7943e15a3e91db78a7a3fbc84e45cf9d1c7c7d23 Mon Sep 17 00:00:00 2001 From: Li Zefan Date: Fri, 29 Mar 2013 14:43:46 +0800 Subject: sched/cpuacct: Allocate per_cpu cpuusage for root cpuacct statically This is a preparation, so later we can initialize cpuacct earlier. Signed-off-by: Li Zefan Cc: Tejun Heo Acked-by: Peter Zijlstra Link: http://lkml.kernel.org/r/51553822.5000403@huawei.com Signed-off-by: Ingo Molnar diff --git a/kernel/sched/cpuacct.c b/kernel/sched/cpuacct.c index 9305fd2..a691c4d 100644 --- a/kernel/sched/cpuacct.c +++ b/kernel/sched/cpuacct.c @@ -58,6 +58,7 @@ static inline struct cpuacct *parent_ca(struct cpuacct *ca) return cgroup_ca(ca->css.cgroup->parent); } +static DEFINE_PER_CPU(u64, root_cpuacct_cpuusage); static struct cpuacct root_cpuacct; /* create a new cpu accounting group */ @@ -290,8 +291,7 @@ void cpuacct_account_field(struct task_struct *p, int index, u64 val) void __init cpuacct_init(void) { root_cpuacct.cpustat = &kernel_cpustat; - root_cpuacct.cpuusage = alloc_percpu(u64); - BUG_ON(!root_cpuacct.cpuusage); /* Too early, not expected to fail */ + root_cpuacct.cpuusage = &root_cpuacct_cpuusage; } struct cgroup_subsys cpuacct_subsys = { -- cgit v0.10.2 From 14c6d3c8a47ced185b6375c4940b5b393f1a294e Mon Sep 17 00:00:00 2001 From: Li Zefan Date: Fri, 29 Mar 2013 14:44:04 +0800 Subject: sched/cpuacct: Initialize root cpuacct earlier Now we don't need cpuacct_init(), and instead we just initialize root_cpuacct when it's defined. Signed-off-by: Li Zefan Cc: Tejun Heo Acked-by: Peter Zijlstra Link: http://lkml.kernel.org/r/51553834.9090701@huawei.com Signed-off-by: Ingo Molnar diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 92930a8..ee8c1bd 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -6936,8 +6936,6 @@ void __init sched_init(void) #endif /* CONFIG_CGROUP_SCHED */ - cpuacct_init(); - for_each_possible_cpu(i) { struct rq *rq; diff --git a/kernel/sched/cpuacct.c b/kernel/sched/cpuacct.c index a691c4d..0425581 100644 --- a/kernel/sched/cpuacct.c +++ b/kernel/sched/cpuacct.c @@ -59,7 +59,10 @@ static inline struct cpuacct *parent_ca(struct cpuacct *ca) } static DEFINE_PER_CPU(u64, root_cpuacct_cpuusage); -static struct cpuacct root_cpuacct; +static struct cpuacct root_cpuacct = { + .cpustat = &kernel_cpustat, + .cpuusage = &root_cpuacct_cpuusage, +}; /* create a new cpu accounting group */ static struct cgroup_subsys_state *cpuacct_css_alloc(struct cgroup *cgrp) @@ -288,12 +291,6 @@ void cpuacct_account_field(struct task_struct *p, int index, u64 val) rcu_read_unlock(); } -void __init cpuacct_init(void) -{ - root_cpuacct.cpustat = &kernel_cpustat; - root_cpuacct.cpuusage = &root_cpuacct_cpuusage; -} - struct cgroup_subsys cpuacct_subsys = { .name = "cpuacct", .css_alloc = cpuacct_css_alloc, diff --git a/kernel/sched/cpuacct.h b/kernel/sched/cpuacct.h index 51cd76e..ed60562 100644 --- a/kernel/sched/cpuacct.h +++ b/kernel/sched/cpuacct.h @@ -1,15 +1,10 @@ #ifdef CONFIG_CGROUP_CPUACCT -extern void cpuacct_init(void); extern void cpuacct_charge(struct task_struct *tsk, u64 cputime); extern void cpuacct_account_field(struct task_struct *p, int index, u64 val); #else -static inline void cpuacct_init(void) -{ -} - static inline void cpuacct_charge(struct task_struct *tsk, u64 cputime) { } -- cgit v0.10.2 From 621e2de02403a6f776852c564b79c38bf3cc9032 Mon Sep 17 00:00:00 2001 From: Li Zefan Date: Fri, 29 Mar 2013 14:44:15 +0800 Subject: sched/cpuacct: Initialize cpuacct subsystem earlier Initialize cpuacct before the scheduler is functioning, so when cpuacct_charge() and cpuacct_account_field() are called, task_ca() won't return NULL. Signed-off-by: Li Zefan Cc: Tejun Heo Acked-by: Peter Zijlstra Link: http://lkml.kernel.org/r/5155383F.8000005@huawei.com Signed-off-by: Ingo Molnar diff --git a/kernel/sched/cpuacct.c b/kernel/sched/cpuacct.c index 0425581..75e46d2 100644 --- a/kernel/sched/cpuacct.c +++ b/kernel/sched/cpuacct.c @@ -292,9 +292,10 @@ void cpuacct_account_field(struct task_struct *p, int index, u64 val) } struct cgroup_subsys cpuacct_subsys = { - .name = "cpuacct", - .css_alloc = cpuacct_css_alloc, - .css_free = cpuacct_css_free, - .subsys_id = cpuacct_subsys_id, - .base_cftypes = files, + .name = "cpuacct", + .css_alloc = cpuacct_css_alloc, + .css_free = cpuacct_css_free, + .subsys_id = cpuacct_subsys_id, + .base_cftypes = files, + .early_init = 1, }; -- cgit v0.10.2 From a2b0ae25fc8bfeeb4022b8e847ab811b3c8368d1 Mon Sep 17 00:00:00 2001 From: Li Zefan Date: Fri, 29 Mar 2013 14:44:28 +0800 Subject: sched/cpuacct: No need to check subsys active state Now we're guaranteed when cpuacct_charge() and cpuacct_account_field() are called, cpuacct has already been properly initialized, so we no longer need those checks. Signed-off-by: Li Zefan Cc: Tejun Heo Acked-by: Peter Zijlstra Link: http://lkml.kernel.org/r/5155384C.7000508@huawei.com Signed-off-by: Ingo Molnar diff --git a/kernel/sched/cpuacct.c b/kernel/sched/cpuacct.c index 75e46d2..ef57ab6 100644 --- a/kernel/sched/cpuacct.c +++ b/kernel/sched/cpuacct.c @@ -247,9 +247,6 @@ void cpuacct_charge(struct task_struct *tsk, u64 cputime) struct cpuacct *ca; int cpu; - if (unlikely(!cpuacct_subsys.active)) - return; - cpu = task_cpu(tsk); rcu_read_lock(); @@ -278,9 +275,6 @@ void cpuacct_account_field(struct task_struct *p, int index, u64 val) struct kernel_cpustat *kcpustat; struct cpuacct *ca; - if (unlikely(!cpuacct_subsys.active)) - return; - rcu_read_lock(); ca = task_ca(p); while (ca != &root_cpuacct) { -- cgit v0.10.2 From 479f614110b889d5783acdaec865ede3cdb96b97 Mon Sep 17 00:00:00 2001 From: Li Zefan Date: Fri, 29 Mar 2013 14:44:42 +0800 Subject: cgroup: Kill subsys.active flag The only user was cpuacct. Acked-by: Tejun Heo Signed-off-by: Li Zefan Acked-by: Peter Zijlstra Link: http://lkml.kernel.org/r/5155385A.4040207@huawei.com Signed-off-by: Ingo Molnar diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 900af59..95c02c0 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -458,7 +458,6 @@ struct cgroup_subsys { void (*bind)(struct cgroup *root); int subsys_id; - int active; int disabled; int early_init; /* diff --git a/kernel/cgroup.c b/kernel/cgroup.c index a32f943..5c46281 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -4468,7 +4468,6 @@ static void __init cgroup_init_subsys(struct cgroup_subsys *ss) * need to invoke fork callbacks here. */ BUG_ON(!list_empty(&init_task.tasks)); - ss->active = 1; BUG_ON(online_css(ss, dummytop)); mutex_unlock(&cgroup_mutex); @@ -4573,7 +4572,6 @@ int __init_or_module cgroup_load_subsys(struct cgroup_subsys *ss) } write_unlock(&css_set_lock); - ss->active = 1; ret = online_css(ss, dummytop); if (ret) goto err_unload; @@ -4614,7 +4612,6 @@ void cgroup_unload_subsys(struct cgroup_subsys *ss) mutex_lock(&cgroup_mutex); offline_css(ss, dummytop); - ss->active = 0; if (ss->use_id) idr_destroy(&ss->idr); -- cgit v0.10.2 From b329fd5b018ffd64cfef6a2551bb2ca4bbfbacf2 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Wed, 10 Apr 2013 15:10:50 +0200 Subject: sched/cpuacct/UML: Fix header file dependency bug on the UML build The cpuacct split caused this build failure on UML: kernel/sched/cpuacct.c:94:2: error: implicit declaration of function 'ERR_PTR' Cc: Li Zefan Cc: Peter Zijlstra Signed-off-by: Ingo Molnar diff --git a/kernel/sched/cpuacct.c b/kernel/sched/cpuacct.c index ef57ab6..dbb7e2c 100644 --- a/kernel/sched/cpuacct.c +++ b/kernel/sched/cpuacct.c @@ -6,6 +6,7 @@ #include #include #include +#include #include "sched.h" -- cgit v0.10.2 From 9b89f6ba2ab56e4d9c00e7e591d6bc333137895e Mon Sep 17 00:00:00 2001 From: Andrei Epure Date: Thu, 11 Apr 2013 20:30:29 +0300 Subject: sched: Document task_struct::personality field Signed-off-by: Andrei Epure Cc: Linus Torvalds Cc: Andrew Morton Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/1365701429-4721-1-git-send-email-epure.andrei@gmail.com Signed-off-by: Ingo Molnar diff --git a/include/linux/sched.h b/include/linux/sched.h index 9004f6e..6bdaa73 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1105,8 +1105,10 @@ struct task_struct { int exit_code, exit_signal; int pdeath_signal; /* The signal sent when the parent dies */ unsigned int jobctl; /* JOBCTL_*, siglock protected */ - /* ??? */ + + /* Used for emulating ABI behavior of previous Linux versions */ unsigned int personality; + unsigned did_exec:1; unsigned in_execve:1; /* Tell the LSMs that the process is doing an * execve */ -- cgit v0.10.2 From 642dbc39ab1ea00f47e0fee1b8e8a27da036d940 Mon Sep 17 00:00:00 2001 From: Vincent Guittot Date: Thu, 18 Apr 2013 18:34:26 +0200 Subject: sched: Fix wrong rq's runnable_avg update with rt tasks The current update of the rq's load can be erroneous when RT tasks are involved. The update of the load of a rq that becomes idle, is done only if the avg_idle is less than sysctl_sched_migration_cost. If RT tasks and short idle duration alternate, the runnable_avg will not be updated correctly and the time will be accounted as idle time when a CFS task wakes up. A new idle_enter function is called when the next task is the idle function so the elapsed time will be accounted as run time in the load of the rq, whatever the average idle time is. The function update_rq_runnable_avg is removed from idle_balance. When a RT task is scheduled on an idle CPU, the update of the rq's load is not done when the rq exit idle state because CFS's functions are not called. Then, the idle_balance, which is called just before entering the idle function, updates the rq's load and makes the assumption that the elapsed time since the last update, was only running time. As a consequence, the rq's load of a CPU that only runs a periodic RT task, is close to LOAD_AVG_MAX whatever the running duration of the RT task is. A new idle_exit function is called when the prev task is the idle function so the elapsed time will be accounted as idle time in the rq's load. Signed-off-by: Vincent Guittot Acked-by: Peter Zijlstra Acked-by: Steven Rostedt Cc: linaro-kernel@lists.linaro.org Cc: peterz@infradead.org Cc: pjt@google.com Cc: fweisbec@gmail.com Cc: efault@gmx.de Link: http://lkml.kernel.org/r/1366302867-5055-1-git-send-email-vincent.guittot@linaro.org Signed-off-by: Ingo Molnar diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 155783b..1c97735 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -1563,6 +1563,27 @@ static inline void dequeue_entity_load_avg(struct cfs_rq *cfs_rq, se->avg.decay_count = atomic64_read(&cfs_rq->decay_counter); } /* migrations, e.g. sleep=0 leave decay_count == 0 */ } + +/* + * Update the rq's load with the elapsed running time before entering + * idle. if the last scheduled task is not a CFS task, idle_enter will + * be the only way to update the runnable statistic. + */ +void idle_enter_fair(struct rq *this_rq) +{ + update_rq_runnable_avg(this_rq, 1); +} + +/* + * Update the rq's load with the elapsed idle time before a task is + * scheduled. if the newly scheduled task is not a CFS task, idle_exit will + * be the only way to update the runnable statistic. + */ +void idle_exit_fair(struct rq *this_rq) +{ + update_rq_runnable_avg(this_rq, 0); +} + #else static inline void update_entity_load_avg(struct sched_entity *se, int update_cfs_rq) {} @@ -5217,8 +5238,6 @@ void idle_balance(int this_cpu, struct rq *this_rq) if (this_rq->avg_idle < sysctl_sched_migration_cost) return; - update_rq_runnable_avg(this_rq, 1); - /* * Drop the rq->lock, but keep IRQ/preempt disabled. */ diff --git a/kernel/sched/idle_task.c b/kernel/sched/idle_task.c index b6baf37..b8ce773 100644 --- a/kernel/sched/idle_task.c +++ b/kernel/sched/idle_task.c @@ -13,6 +13,16 @@ select_task_rq_idle(struct task_struct *p, int sd_flag, int flags) { return task_cpu(p); /* IDLE tasks as never migrated */ } + +static void pre_schedule_idle(struct rq *rq, struct task_struct *prev) +{ + idle_exit_fair(rq); +} + +static void post_schedule_idle(struct rq *rq) +{ + idle_enter_fair(rq); +} #endif /* CONFIG_SMP */ /* * Idle tasks are unconditionally rescheduled: @@ -25,6 +35,10 @@ static void check_preempt_curr_idle(struct rq *rq, struct task_struct *p, int fl static struct task_struct *pick_next_task_idle(struct rq *rq) { schedstat_inc(rq, sched_goidle); +#ifdef CONFIG_SMP + /* Trigger the post schedule to do an idle_enter for CFS */ + rq->post_schedule = 1; +#endif return rq->idle; } @@ -86,6 +100,8 @@ const struct sched_class idle_sched_class = { #ifdef CONFIG_SMP .select_task_rq = select_task_rq_idle, + .pre_schedule = pre_schedule_idle, + .post_schedule = post_schedule_idle, #endif .set_curr_task = set_curr_task_idle, diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 8116cf8..605426a 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -1024,6 +1024,18 @@ extern void update_group_power(struct sched_domain *sd, int cpu); extern void trigger_load_balance(struct rq *rq, int cpu); extern void idle_balance(int this_cpu, struct rq *this_rq); +/* + * Only depends on SMP, FAIR_GROUP_SCHED may be removed when runnable_avg + * becomes useful in lb + */ +#if defined(CONFIG_FAIR_GROUP_SCHED) +extern void idle_enter_fair(struct rq *this_rq); +extern void idle_exit_fair(struct rq *this_rq); +#else +static inline void idle_enter_fair(struct rq *this_rq) {} +static inline void idle_exit_fair(struct rq *this_rq) {} +#endif + #else /* CONFIG_SMP */ static inline void idle_balance(int cpu, struct rq *rq) -- cgit v0.10.2 From f1cd0858100c67273f2c74344e0c464344c4a982 Mon Sep 17 00:00:00 2001 From: Joonsoo Kim Date: Tue, 23 Apr 2013 17:27:37 +0900 Subject: sched: Change position of resched_cpu() in load_balance() cur_ld_moved is reset if env.flags hit LBF_NEED_BREAK. So, there is possibility that we miss doing resched_cpu(). Correct it as changing position of resched_cpu() before checking LBF_NEED_BREAK. Signed-off-by: Joonsoo Kim Tested-by: Jason Low Acked-by: Peter Zijlstra Cc: Srivatsa Vaddagiri Cc: Davidlohr Bueso Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1366705662-3587-2-git-send-email-iamjoonsoo.kim@lge.com Signed-off-by: Ingo Molnar diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 1c97735..25aaf93 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -5080,17 +5080,17 @@ more_balance: double_rq_unlock(env.dst_rq, busiest); local_irq_restore(flags); - if (env.flags & LBF_NEED_BREAK) { - env.flags &= ~LBF_NEED_BREAK; - goto more_balance; - } - /* * some other cpu did the load balance for us. */ if (cur_ld_moved && env.dst_cpu != smp_processor_id()) resched_cpu(env.dst_cpu); + if (env.flags & LBF_NEED_BREAK) { + env.flags &= ~LBF_NEED_BREAK; + goto more_balance; + } + /* * Revisit (affine) tasks on src_cpu that couldn't be moved to * us and move them to an alternate dst_cpu in our sched_group -- cgit v0.10.2 From de5eb2dd7f171ee8a45d23cd41aa2efe9ab922b3 Mon Sep 17 00:00:00 2001 From: Joonsoo Kim Date: Tue, 23 Apr 2013 17:27:38 +0900 Subject: sched: Explicitly cpu_idle_type checking in rebalance_domains() After commit 88b8dac0, dst-cpu can be changed in load_balance(), then we can't know cpu_idle_type of dst-cpu when load_balance() return positive. So, add explicit cpu_idle_type checking. Signed-off-by: Joonsoo Kim Tested-by: Jason Low Acked-by: Peter Zijlstra Cc: Srivatsa Vaddagiri Cc: Davidlohr Bueso Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1366705662-3587-3-git-send-email-iamjoonsoo.kim@lge.com Signed-off-by: Ingo Molnar diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 25aaf93..726e129 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -5523,10 +5523,11 @@ static void rebalance_domains(int cpu, enum cpu_idle_type idle) if (time_after_eq(jiffies, sd->last_balance + interval)) { if (load_balance(cpu, rq, sd, idle, &balance)) { /* - * We've pulled tasks over so either we're no - * longer idle. + * The LBF_SOME_PINNED logic could have changed + * env->dst_cpu, so we can't know our idle + * state even if we migrated tasks. Update it. */ - idle = CPU_NOT_IDLE; + idle = idle_cpu(cpu) ? CPU_IDLE : CPU_NOT_IDLE; } sd->last_balance = jiffies; } -- cgit v0.10.2 From cfc03118047172f5bdc58d63c607d16d33ce5305 Mon Sep 17 00:00:00 2001 From: Joonsoo Kim Date: Tue, 23 Apr 2013 17:27:39 +0900 Subject: sched: Don't consider other cpus in our group in case of NEWLY_IDLE Commit 88b8dac0 makes load_balance() consider other cpus in its group, regardless of idle type. When we do NEWLY_IDLE balancing, we should not consider it, because a motivation of NEWLY_IDLE balancing is to turn this cpu to non idle state if needed. This is not the case of other cpus. So, change code not to consider other cpus for NEWLY_IDLE balancing. With this patch, assign 'if (pulled_task) this_rq->idle_stamp = 0' in idle_balance() is corrected, because NEWLY_IDLE balancing doesn't consider other cpus. Assigning to 'this_rq->idle_stamp' is now valid. Signed-off-by: Joonsoo Kim Tested-by: Jason Low Acked-by: Peter Zijlstra Cc: Srivatsa Vaddagiri Cc: Davidlohr Bueso Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1366705662-3587-4-git-send-email-iamjoonsoo.kim@lge.com Signed-off-by: Ingo Molnar diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 726e129..dfa92b7 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -5026,8 +5026,21 @@ static int load_balance(int this_cpu, struct rq *this_rq, .cpus = cpus, }; + /* + * For NEWLY_IDLE load_balancing, we don't need to consider + * other cpus in our group + */ + if (idle == CPU_NEWLY_IDLE) { + env.dst_grpmask = NULL; + /* + * we don't care max_lb_iterations in this case, + * in following patch, this will be removed + */ + max_lb_iterations = 0; + } else + max_lb_iterations = cpumask_weight(env.dst_grpmask); + cpumask_copy(cpus, cpu_active_mask); - max_lb_iterations = cpumask_weight(env.dst_grpmask); schedstat_inc(sd, lb_count[idle]); -- cgit v0.10.2 From d31980846f9688db3ee3e5863525c6ff8ace4c7c Mon Sep 17 00:00:00 2001 From: Joonsoo Kim Date: Tue, 23 Apr 2013 17:27:40 +0900 Subject: sched: Move up affinity check to mitigate useless redoing overhead Currently, LBF_ALL_PINNED is cleared after affinity check is passed. So, if task migration is skipped by small load value or small imbalance value in move_tasks(), we don't clear LBF_ALL_PINNED. At last, we trigger 'redo' in load_balance(). Imbalance value is often so small that any tasks cannot be moved to other cpus and, of course, this situation may be continued after we change the target cpu. So this patch move up affinity check code and clear LBF_ALL_PINNED before evaluating load value in order to mitigate useless redoing overhead. In addition, re-order some comments correctly. Signed-off-by: Joonsoo Kim Acked-by: Peter Zijlstra Tested-by: Jason Low Cc: Srivatsa Vaddagiri Cc: Davidlohr Bueso Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1366705662-3587-5-git-send-email-iamjoonsoo.kim@lge.com Signed-off-by: Ingo Molnar diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index dfa92b7..b8ef321 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -3896,10 +3896,14 @@ int can_migrate_task(struct task_struct *p, struct lb_env *env) int tsk_cache_hot = 0; /* * We do not migrate tasks that are: - * 1) running (obviously), or + * 1) throttled_lb_pair, or * 2) cannot be migrated to this CPU due to cpus_allowed, or - * 3) are cache-hot on their current CPU. + * 3) running (obviously), or + * 4) are cache-hot on their current CPU. */ + if (throttled_lb_pair(task_group(p), env->src_cpu, env->dst_cpu)) + return 0; + if (!cpumask_test_cpu(env->dst_cpu, tsk_cpus_allowed(p))) { int new_dst_cpu; @@ -3967,9 +3971,6 @@ static int move_one_task(struct lb_env *env) struct task_struct *p, *n; list_for_each_entry_safe(p, n, &env->src_rq->cfs_tasks, se.group_node) { - if (throttled_lb_pair(task_group(p), env->src_rq->cpu, env->dst_cpu)) - continue; - if (!can_migrate_task(p, env)) continue; @@ -4021,7 +4022,7 @@ static int move_tasks(struct lb_env *env) break; } - if (throttled_lb_pair(task_group(p), env->src_cpu, env->dst_cpu)) + if (!can_migrate_task(p, env)) goto next; load = task_h_load(p); @@ -4032,9 +4033,6 @@ static int move_tasks(struct lb_env *env) if ((load / 2) > env->imbalance) goto next; - if (!can_migrate_task(p, env)) - goto next; - move_task(p, env); pulled++; env->imbalance -= load; -- cgit v0.10.2 From e6252c3ef4b9cd251b53f7b68035f395d20b044e Mon Sep 17 00:00:00 2001 From: Joonsoo Kim Date: Tue, 23 Apr 2013 17:27:41 +0900 Subject: sched: Rename load_balance_tmpmask to load_balance_mask This name doesn't represent specific meaning. So rename it to imply it's purpose. Signed-off-by: Joonsoo Kim Acked-by: Peter Zijlstra Tested-by: Jason Low Cc: Srivatsa Vaddagiri Cc: Davidlohr Bueso Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1366705662-3587-6-git-send-email-iamjoonsoo.kim@lge.com Signed-off-by: Ingo Molnar diff --git a/kernel/sched/core.c b/kernel/sched/core.c index ee8c1bd..cb49b2a 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -6873,7 +6873,7 @@ struct task_group root_task_group; LIST_HEAD(task_groups); #endif -DECLARE_PER_CPU(cpumask_var_t, load_balance_tmpmask); +DECLARE_PER_CPU(cpumask_var_t, load_balance_mask); void __init sched_init(void) { @@ -6910,7 +6910,7 @@ void __init sched_init(void) #endif /* CONFIG_RT_GROUP_SCHED */ #ifdef CONFIG_CPUMASK_OFFSTACK for_each_possible_cpu(i) { - per_cpu(load_balance_tmpmask, i) = (void *)ptr; + per_cpu(load_balance_mask, i) = (void *)ptr; ptr += cpumask_size(); } #endif /* CONFIG_CPUMASK_OFFSTACK */ diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index b8ef321..5b1e966 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -4977,7 +4977,7 @@ static struct rq *find_busiest_queue(struct lb_env *env, #define MAX_PINNED_INTERVAL 512 /* Working cpumask for load_balance and load_balance_newidle. */ -DEFINE_PER_CPU(cpumask_var_t, load_balance_tmpmask); +DEFINE_PER_CPU(cpumask_var_t, load_balance_mask); static int need_active_balance(struct lb_env *env) { @@ -5012,7 +5012,7 @@ static int load_balance(int this_cpu, struct rq *this_rq, struct sched_group *group; struct rq *busiest; unsigned long flags; - struct cpumask *cpus = __get_cpu_var(load_balance_tmpmask); + struct cpumask *cpus = __get_cpu_var(load_balance_mask); struct lb_env env = { .sd = sd, -- cgit v0.10.2 From e02e60c109ca70935bad1131976bdbf5160cf576 Mon Sep 17 00:00:00 2001 From: Joonsoo Kim Date: Tue, 23 Apr 2013 17:27:42 +0900 Subject: sched: Prevent to re-select dst-cpu in load_balance() Commit 88b8dac0 makes load_balance() consider other cpus in its group. But, in that, there is no code for preventing to re-select dst-cpu. So, same dst-cpu can be selected over and over. This patch add functionality to load_balance() in order to exclude cpu which is selected once. We prevent to re-select dst_cpu via env's cpus, so now, env's cpus is a candidate not only for src_cpus, but also dst_cpus. With this patch, we can remove lb_iterations and max_lb_iterations, because we decide whether we can go ahead or not via env's cpus. Signed-off-by: Joonsoo Kim Acked-by: Peter Zijlstra Tested-by: Jason Low Cc: Srivatsa Vaddagiri Cc: Davidlohr Bueso Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1366705662-3587-7-git-send-email-iamjoonsoo.kim@lge.com Signed-off-by: Ingo Molnar diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 5b1e966..acaf567 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -3905,7 +3905,7 @@ int can_migrate_task(struct task_struct *p, struct lb_env *env) return 0; if (!cpumask_test_cpu(env->dst_cpu, tsk_cpus_allowed(p))) { - int new_dst_cpu; + int cpu; schedstat_inc(p, se.statistics.nr_failed_migrations_affine); @@ -3920,12 +3920,15 @@ int can_migrate_task(struct task_struct *p, struct lb_env *env) if (!env->dst_grpmask || (env->flags & LBF_SOME_PINNED)) return 0; - new_dst_cpu = cpumask_first_and(env->dst_grpmask, - tsk_cpus_allowed(p)); - if (new_dst_cpu < nr_cpu_ids) { - env->flags |= LBF_SOME_PINNED; - env->new_dst_cpu = new_dst_cpu; + /* Prevent to re-select dst_cpu via env's cpus */ + for_each_cpu_and(cpu, env->dst_grpmask, env->cpus) { + if (cpumask_test_cpu(cpu, tsk_cpus_allowed(p))) { + env->flags |= LBF_SOME_PINNED; + env->new_dst_cpu = cpu; + break; + } } + return 0; } @@ -5008,7 +5011,6 @@ static int load_balance(int this_cpu, struct rq *this_rq, int *balance) { int ld_moved, cur_ld_moved, active_balance = 0; - int lb_iterations, max_lb_iterations; struct sched_group *group; struct rq *busiest; unsigned long flags; @@ -5028,15 +5030,8 @@ static int load_balance(int this_cpu, struct rq *this_rq, * For NEWLY_IDLE load_balancing, we don't need to consider * other cpus in our group */ - if (idle == CPU_NEWLY_IDLE) { + if (idle == CPU_NEWLY_IDLE) env.dst_grpmask = NULL; - /* - * we don't care max_lb_iterations in this case, - * in following patch, this will be removed - */ - max_lb_iterations = 0; - } else - max_lb_iterations = cpumask_weight(env.dst_grpmask); cpumask_copy(cpus, cpu_active_mask); @@ -5064,7 +5059,6 @@ redo: schedstat_add(sd, lb_imbalance[idle], env.imbalance); ld_moved = 0; - lb_iterations = 1; if (busiest->nr_running > 1) { /* * Attempt to move tasks. If find_busiest_group has found @@ -5121,14 +5115,17 @@ more_balance: * moreover subsequent load balance cycles should correct the * excess load moved. */ - if ((env.flags & LBF_SOME_PINNED) && env.imbalance > 0 && - lb_iterations++ < max_lb_iterations) { + if ((env.flags & LBF_SOME_PINNED) && env.imbalance > 0) { env.dst_rq = cpu_rq(env.new_dst_cpu); env.dst_cpu = env.new_dst_cpu; env.flags &= ~LBF_SOME_PINNED; env.loop = 0; env.loop_break = sched_nr_migrate_break; + + /* Prevent to re-select dst_cpu via env's cpus */ + cpumask_clear_cpu(env.dst_cpu, env.cpus); + /* * Go back to "more_balance" rather than "redo" since we * need to continue with same src_cpu. -- cgit v0.10.2 From 25f55d9d01ad7a7ad248fd5af1d22675ffd202c5 Mon Sep 17 00:00:00 2001 From: Vincent Guittot Date: Tue, 23 Apr 2013 16:59:02 +0200 Subject: sched: Fix init NOHZ_IDLE flag On my SMP platform which is made of 5 cores in 2 clusters, I have the nr_busy_cpu field of sched_group_power struct that is not null when the platform is fully idle - which makes the scheduler unhappy. The root cause is: During the boot sequence, some CPUs reach the idle loop and set their NOHZ_IDLE flag while waiting for others CPUs to boot. But the nr_busy_cpus field is initialized later with the assumption that all CPUs are in the busy state whereas some CPUs have already set their NOHZ_IDLE flag. More generally, the NOHZ_IDLE flag must be initialized when new sched_domains are created in order to ensure that NOHZ_IDLE and nr_busy_cpus are aligned. This condition can be ensured by adding a synchronize_rcu() between the destruction of old sched_domains and the creation of new ones so the NOHZ_IDLE flag will not be updated with old sched_domain once it has been initialized. But this solution introduces a additionnal latency in the rebuild sequence that is called during cpu hotplug. As suggested by Frederic Weisbecker, another solution is to have the same rcu lifecycle for both NOHZ_IDLE and sched_domain struct. A new nohz_idle field is added to sched_domain so both status and sched_domain will share the same RCU lifecycle and will be always synchronized. In addition, there is no more need to protect nohz_idle against concurrent access as it is only modified by 2 exclusive functions called by local cpu. This solution has been prefered to the creation of a new struct with an extra pointer indirection for sched_domain. The synchronization is done at the cost of : - An additional indirection and a rcu_dereference for accessing nohz_idle. - We use only the nohz_idle field of the top sched_domain. Signed-off-by: Vincent Guittot Acked-by: Peter Zijlstra Cc: linaro-kernel@lists.linaro.org Cc: peterz@infradead.org Cc: fweisbec@gmail.com Cc: pjt@google.com Cc: rostedt@goodmis.org Cc: efault@gmx.de Link: http://lkml.kernel.org/r/1366729142-14662-1-git-send-email-vincent.guittot@linaro.org [ Fixed !NO_HZ build bug. ] Signed-off-by: Ingo Molnar diff --git a/include/linux/sched.h b/include/linux/sched.h index 6bdaa73..a25168f 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -808,6 +808,8 @@ struct sched_domain { unsigned int wake_idx; unsigned int forkexec_idx; unsigned int smt_gain; + + int nohz_idle; /* NOHZ IDLE status */ int flags; /* See SD_* */ int level; diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index acaf567..8bf7081 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -5420,13 +5420,16 @@ static inline void set_cpu_sd_state_busy(void) struct sched_domain *sd; int cpu = smp_processor_id(); - if (!test_bit(NOHZ_IDLE, nohz_flags(cpu))) - return; - clear_bit(NOHZ_IDLE, nohz_flags(cpu)); - rcu_read_lock(); - for_each_domain(cpu, sd) + sd = rcu_dereference_check_sched_domain(cpu_rq(cpu)->sd); + + if (!sd || !sd->nohz_idle) + goto unlock; + sd->nohz_idle = 0; + + for (; sd; sd = sd->parent) atomic_inc(&sd->groups->sgp->nr_busy_cpus); +unlock: rcu_read_unlock(); } @@ -5435,13 +5438,16 @@ void set_cpu_sd_state_idle(void) struct sched_domain *sd; int cpu = smp_processor_id(); - if (test_bit(NOHZ_IDLE, nohz_flags(cpu))) - return; - set_bit(NOHZ_IDLE, nohz_flags(cpu)); - rcu_read_lock(); - for_each_domain(cpu, sd) + sd = rcu_dereference_check_sched_domain(cpu_rq(cpu)->sd); + + if (!sd || sd->nohz_idle) + goto unlock; + sd->nohz_idle = 1; + + for (; sd; sd = sd->parent) atomic_dec(&sd->groups->sgp->nr_busy_cpus); +unlock: rcu_read_unlock(); } diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 605426a..4c225c4 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -1303,7 +1303,6 @@ extern void account_cfs_bandwidth_used(int enabled, int was_enabled); enum rq_nohz_flag_bits { NOHZ_TICK_STOPPED, NOHZ_BALANCE_KICK, - NOHZ_IDLE, }; #define nohz_flags(cpu) (&cpu_rq(cpu)->nohz_flags) -- cgit v0.10.2