From a42548a18866e87092db93b771e6c5b060d78401 Mon Sep 17 00:00:00 2001 From: Stanislaw Gruszka Date: Wed, 29 Jul 2009 12:15:29 +0200 Subject: cputime: Optimize jiffies_to_cputime(1) For powerpc with CONFIG_VIRT_CPU_ACCOUNTING jiffies_to_cputime(1) is not compile time constant and run time calculations are quite expensive. To optimize we use precomputed value. For all other architectures is is preprocessor definition. Signed-off-by: Stanislaw Gruszka Acked-by: Peter Zijlstra Acked-by: Thomas Gleixner Cc: Oleg Nesterov Cc: Andrew Morton Cc: Paul Mackerras Cc: Benjamin Herrenschmidt LKML-Reference: <1248862529-6063-5-git-send-email-sgruszka@redhat.com> Signed-off-by: Ingo Molnar --- kernel/sched.c | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) (limited to 'kernel/sched.c') diff --git a/kernel/sched.c b/kernel/sched.c index 1b59e265273b..8f977d5cc515 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -5031,17 +5031,16 @@ void account_idle_time(cputime_t cputime) */ void account_process_tick(struct task_struct *p, int user_tick) { - cputime_t one_jiffy = jiffies_to_cputime(1); - cputime_t one_jiffy_scaled = cputime_to_scaled(one_jiffy); + cputime_t one_jiffy_scaled = cputime_to_scaled(cputime_one_jiffy); struct rq *rq = this_rq(); if (user_tick) - account_user_time(p, one_jiffy, one_jiffy_scaled); + 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, one_jiffy, + account_system_time(p, HARDIRQ_OFFSET, cputime_one_jiffy, one_jiffy_scaled); else - account_idle_time(one_jiffy); + account_idle_time(cputime_one_jiffy); } /* -- cgit v1.2.2 From b78bb868c54bebbf8d8786a3f8320700d6d2b864 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 15 Sep 2009 14:23:18 +0200 Subject: sched: Fix double_rq_lock() compile warning Signed-off-by: Peter Zijlstra LKML-Reference: Signed-off-by: Ingo Molnar --- kernel/sched.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'kernel/sched.c') diff --git a/kernel/sched.c b/kernel/sched.c index e27a53685ed9..17e4391ec2de 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -119,8 +119,6 @@ */ #define RUNTIME_INF ((u64)~0ULL) -static void double_rq_lock(struct rq *rq1, struct rq *rq2); - static inline int rt_policy(int policy) { if (unlikely(policy == SCHED_FIFO || policy == SCHED_RR)) @@ -1695,6 +1693,8 @@ static inline void update_shares_locked(struct rq *rq, struct sched_domain *sd) #ifdef CONFIG_PREEMPT +static void double_rq_lock(struct rq *rq1, struct rq *rq2); + /* * fair double_lock_balance: Safely acquires both rq->locks in a fair * way at the expense of forcing extra atomic operations in all -- cgit v1.2.2 From f5f08f39ee4c5fd0a757d25d9e04d696676b3df7 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 10 Sep 2009 13:35:28 +0200 Subject: sched: Move code around In preparation to other code movement, move weighted_cpuload(), source_load() and target_load() before the class includes. Signed-off-by: Peter Zijlstra LKML-Reference: Signed-off-by: Ingo Molnar --- kernel/sched.c | 81 ++++++++++++++++++++++++++++------------------------------ 1 file changed, 39 insertions(+), 42 deletions(-) (limited to 'kernel/sched.c') diff --git a/kernel/sched.c b/kernel/sched.c index 17e4391ec2de..b56d1505d058 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -1507,8 +1507,45 @@ static int tg_nop(struct task_group *tg, void *data) #endif #ifdef CONFIG_SMP -static unsigned long source_load(int cpu, int type); -static unsigned long target_load(int cpu, int type); +/* Used instead of source_load when we know the type == 0 */ +static unsigned long weighted_cpuload(const int cpu) +{ + return cpu_rq(cpu)->load.weight; +} + +/* + * Return a low guess at the load of a migration-source cpu weighted + * according to the scheduling class and "nice" value. + * + * We want to under-estimate the load of migration sources, to + * balance conservatively. + */ +static unsigned long source_load(int cpu, int type) +{ + struct rq *rq = cpu_rq(cpu); + unsigned long total = weighted_cpuload(cpu); + + if (type == 0 || !sched_feat(LB_BIAS)) + return total; + + return min(rq->cpu_load[type-1], total); +} + +/* + * Return a high guess at the load of a migration-target cpu weighted + * according to the scheduling class and "nice" value. + */ +static unsigned long target_load(int cpu, int type) +{ + struct rq *rq = cpu_rq(cpu); + unsigned long total = weighted_cpuload(cpu); + + if (type == 0 || !sched_feat(LB_BIAS)) + return total; + + return max(rq->cpu_load[type-1], total); +} + static int task_hot(struct task_struct *p, u64 now, struct sched_domain *sd); static unsigned long cpu_avg_load_per_task(int cpu) @@ -1959,13 +1996,6 @@ static inline void check_class_changed(struct rq *rq, struct task_struct *p, } #ifdef CONFIG_SMP - -/* Used instead of source_load when we know the type == 0 */ -static unsigned long weighted_cpuload(const int cpu) -{ - return cpu_rq(cpu)->load.weight; -} - /* * Is this task likely cache-hot: */ @@ -2240,39 +2270,6 @@ void kick_process(struct task_struct *p) } EXPORT_SYMBOL_GPL(kick_process); -/* - * Return a low guess at the load of a migration-source cpu weighted - * according to the scheduling class and "nice" value. - * - * We want to under-estimate the load of migration sources, to - * balance conservatively. - */ -static unsigned long source_load(int cpu, int type) -{ - struct rq *rq = cpu_rq(cpu); - unsigned long total = weighted_cpuload(cpu); - - if (type == 0 || !sched_feat(LB_BIAS)) - return total; - - return min(rq->cpu_load[type-1], total); -} - -/* - * Return a high guess at the load of a migration-target cpu weighted - * according to the scheduling class and "nice" value. - */ -static unsigned long target_load(int cpu, int type) -{ - struct rq *rq = cpu_rq(cpu); - unsigned long total = weighted_cpuload(cpu); - - if (type == 0 || !sched_feat(LB_BIAS)) - return total; - - return max(rq->cpu_load[type-1], total); -} - /* * find_idlest_group finds and returns the least busy CPU group within the * domain. -- cgit v1.2.2 From aaee1203ca52b9db799433c33c9bffc33cdf8909 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 10 Sep 2009 13:36:25 +0200 Subject: sched: Move sched_balance_self() into sched_fair.c Move the sched_balance_self() code into sched_fair.c This facilitates the merger of sched_balance_self() and sched_fair::select_task_rq(). Signed-off-by: Peter Zijlstra LKML-Reference: Signed-off-by: Ingo Molnar --- kernel/sched.c | 146 --------------------------------------------------------- 1 file changed, 146 deletions(-) (limited to 'kernel/sched.c') diff --git a/kernel/sched.c b/kernel/sched.c index b56d1505d058..60400a22401f 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -2269,152 +2269,6 @@ void kick_process(struct task_struct *p) preempt_enable(); } EXPORT_SYMBOL_GPL(kick_process); - -/* - * find_idlest_group finds and returns the least busy CPU group within the - * domain. - */ -static struct sched_group * -find_idlest_group(struct sched_domain *sd, struct task_struct *p, int this_cpu) -{ - struct sched_group *idlest = NULL, *this = NULL, *group = sd->groups; - unsigned long min_load = ULONG_MAX, this_load = 0; - int load_idx = sd->forkexec_idx; - int imbalance = 100 + (sd->imbalance_pct-100)/2; - - do { - unsigned long load, avg_load; - int local_group; - int i; - - /* Skip over this group if it has no CPUs allowed */ - if (!cpumask_intersects(sched_group_cpus(group), - &p->cpus_allowed)) - continue; - - local_group = cpumask_test_cpu(this_cpu, - sched_group_cpus(group)); - - /* Tally up the load of all CPUs in the group */ - avg_load = 0; - - for_each_cpu(i, sched_group_cpus(group)) { - /* Bias balancing toward cpus of our domain */ - if (local_group) - load = source_load(i, load_idx); - else - load = target_load(i, load_idx); - - avg_load += load; - } - - /* Adjust by relative CPU power of the group */ - avg_load = (avg_load * SCHED_LOAD_SCALE) / group->cpu_power; - - if (local_group) { - this_load = avg_load; - this = group; - } else if (avg_load < min_load) { - min_load = avg_load; - idlest = group; - } - } while (group = group->next, group != sd->groups); - - if (!idlest || 100*this_load < imbalance*min_load) - return NULL; - return idlest; -} - -/* - * find_idlest_cpu - find the idlest cpu among the cpus in group. - */ -static int -find_idlest_cpu(struct sched_group *group, struct task_struct *p, int this_cpu) -{ - unsigned long load, min_load = ULONG_MAX; - int idlest = -1; - int i; - - /* Traverse only the allowed CPUs */ - for_each_cpu_and(i, sched_group_cpus(group), &p->cpus_allowed) { - load = weighted_cpuload(i); - - if (load < min_load || (load == min_load && i == this_cpu)) { - min_load = load; - idlest = i; - } - } - - return idlest; -} - -/* - * sched_balance_self: balance the current task (running on cpu) in domains - * that have the 'flag' flag set. In practice, this is SD_BALANCE_FORK and - * SD_BALANCE_EXEC. - * - * Balance, ie. select the least loaded group. - * - * Returns the target CPU number, or the same CPU if no balancing is needed. - * - * preempt must be disabled. - */ -static int sched_balance_self(int cpu, int flag) -{ - struct task_struct *t = current; - struct sched_domain *tmp, *sd = NULL; - - for_each_domain(cpu, tmp) { - /* - * If power savings logic is enabled for a domain, stop there. - */ - if (tmp->flags & SD_POWERSAVINGS_BALANCE) - break; - if (tmp->flags & flag) - sd = tmp; - } - - if (sd) - update_shares(sd); - - while (sd) { - struct sched_group *group; - int new_cpu, weight; - - if (!(sd->flags & flag)) { - sd = sd->child; - continue; - } - - group = find_idlest_group(sd, t, cpu); - if (!group) { - sd = sd->child; - continue; - } - - new_cpu = find_idlest_cpu(group, t, cpu); - if (new_cpu == -1 || new_cpu == cpu) { - /* Now try balancing at a lower domain level of cpu */ - sd = sd->child; - continue; - } - - /* Now try balancing at a lower domain level of new_cpu */ - cpu = new_cpu; - weight = cpumask_weight(sched_domain_span(sd)); - sd = NULL; - for_each_domain(cpu, tmp) { - if (weight <= cpumask_weight(sched_domain_span(tmp))) - break; - if (tmp->flags & flag) - sd = tmp; - } - /* while loop will break here if sd == NULL */ - } - - return cpu; -} - #endif /* CONFIG_SMP */ /** -- cgit v1.2.2 From 5f3edc1b1ead6d9bd45a85c551f44eff8fe76b9f Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 10 Sep 2009 13:42:00 +0200 Subject: sched: Hook sched_balance_self() into sched_class::select_task_rq() Rather ugly patch to fully place the sched_balance_self() code inside the fair class. Signed-off-by: Peter Zijlstra LKML-Reference: Signed-off-by: Ingo Molnar --- kernel/sched.c | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) (limited to 'kernel/sched.c') diff --git a/kernel/sched.c b/kernel/sched.c index 60400a22401f..32b7a81230c2 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -2350,7 +2350,7 @@ static int try_to_wake_up(struct task_struct *p, unsigned int state, int sync) if (unlikely(task_running(rq, p))) goto out_activate; - cpu = p->sched_class->select_task_rq(p, sync); + cpu = p->sched_class->select_task_rq(p, SD_BALANCE_WAKE, sync); if (cpu != orig_cpu) { set_task_cpu(p, cpu); task_rq_unlock(rq, &flags); @@ -2525,11 +2525,6 @@ void sched_fork(struct task_struct *p, int clone_flags) __sched_fork(p); -#ifdef CONFIG_SMP - cpu = sched_balance_self(cpu, SD_BALANCE_FORK); -#endif - set_task_cpu(p, cpu); - /* * Make sure we do not leak PI boosting priority to the child. */ @@ -2560,6 +2555,11 @@ void sched_fork(struct task_struct *p, int clone_flags) if (!rt_prio(p->prio)) p->sched_class = &fair_sched_class; +#ifdef CONFIG_SMP + cpu = p->sched_class->select_task_rq(p, SD_BALANCE_FORK, 0); +#endif + set_task_cpu(p, cpu); + #if defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT) if (likely(sched_info_on())) memset(&p->sched_info, 0, sizeof(p->sched_info)); @@ -3114,7 +3114,7 @@ out: void sched_exec(void) { int new_cpu, this_cpu = get_cpu(); - new_cpu = sched_balance_self(this_cpu, SD_BALANCE_EXEC); + new_cpu = current->sched_class->select_task_rq(current, SD_BALANCE_EXEC, 0); put_cpu(); if (new_cpu != this_cpu) sched_migrate_task(current, new_cpu); -- cgit v1.2.2 From e9c8431185d6c406887190519f6dbdd112641686 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 15 Sep 2009 14:43:03 +0200 Subject: sched: Add TASK_WAKING We're going to want to drop rq->lock in try_to_wake_up() for a longer period of time, however we also want to deal with concurrent waking of the same task, which is currently handled by holding rq->lock. So introduce a new TASK state, namely TASK_WAKING, which indicates someone is already waking the task (other wakers will fail p->state & state). We also keep preemption disabled over the whole ttwu(). Signed-off-by: Peter Zijlstra LKML-Reference: Signed-off-by: Ingo Molnar --- kernel/sched.c | 31 +++++++++++++++---------------- 1 file changed, 15 insertions(+), 16 deletions(-) (limited to 'kernel/sched.c') diff --git a/kernel/sched.c b/kernel/sched.c index 32b7a81230c2..fc6fda881d2e 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -2310,7 +2310,6 @@ static int try_to_wake_up(struct task_struct *p, unsigned int state, int sync) { int cpu, orig_cpu, this_cpu, success = 0; unsigned long flags; - long old_state; struct rq *rq; if (!sched_feat(SYNC_WAKEUPS)) @@ -2332,11 +2331,12 @@ static int try_to_wake_up(struct task_struct *p, unsigned int state, int sync) } #endif + this_cpu = get_cpu(); + smp_wmb(); rq = task_rq_lock(p, &flags); update_rq_clock(rq); - old_state = p->state; - if (!(old_state & state)) + if (!(p->state & state)) goto out; if (p->se.on_rq) @@ -2344,27 +2344,25 @@ static int try_to_wake_up(struct task_struct *p, unsigned int state, int sync) cpu = task_cpu(p); orig_cpu = cpu; - this_cpu = smp_processor_id(); #ifdef CONFIG_SMP if (unlikely(task_running(rq, p))) goto out_activate; + /* + * In order to handle concurrent wakeups and release the rq->lock + * we put the task in TASK_WAKING state. + */ + p->state = TASK_WAKING; + task_rq_unlock(rq, &flags); + cpu = p->sched_class->select_task_rq(p, SD_BALANCE_WAKE, sync); - if (cpu != orig_cpu) { + if (cpu != orig_cpu) set_task_cpu(p, cpu); - task_rq_unlock(rq, &flags); - /* might preempt at this point */ - rq = task_rq_lock(p, &flags); - old_state = p->state; - if (!(old_state & state)) - goto out; - if (p->se.on_rq) - goto out_running; - this_cpu = smp_processor_id(); - cpu = task_cpu(p); - } + rq = task_rq_lock(p, &flags); + WARN_ON(p->state != TASK_WAKING); + cpu = task_cpu(p); #ifdef CONFIG_SCHEDSTATS schedstat_inc(rq, ttwu_count); @@ -2422,6 +2420,7 @@ out_running: #endif out: task_rq_unlock(rq, &flags); + put_cpu(); return success; } -- cgit v1.2.2 From c88d5910890ad35af283344417891344604f0438 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 10 Sep 2009 13:50:02 +0200 Subject: sched: Merge select_task_rq_fair() and sched_balance_self() The problem with wake_idle() is that is doesn't respect things like cpu_power, which means it doesn't deal well with SMT nor the recent RT interaction. To cure this, it needs to do what sched_balance_self() does, which leads to the possibility of merging select_task_rq_fair() and sched_balance_self(). Modify sched_balance_self() to: - update_shares() when walking up the domain tree, (it only called it for the top domain, but it should have done this anyway), which allows us to remove this ugly bit from try_to_wake_up(). - do wake_affine() on the smallest domain that contains both this (the waking) and the prev (the wakee) cpu for WAKE invocations. Then use the top-down balance steps it had to replace wake_idle(). This leads to the dissapearance of SD_WAKE_BALANCE and SD_WAKE_IDLE_FAR, with SD_WAKE_IDLE replaced with SD_BALANCE_WAKE. SD_WAKE_AFFINE needs SD_BALANCE_WAKE to be effective. Touch all topology bits to replace the old with new SD flags -- platforms might need re-tuning, enabling SD_BALANCE_WAKE conditionally on a NUMA distance seems like a good additional feature, magny-core and small nehalem systems would want this enabled, systems with slow interconnects would not. Signed-off-by: Peter Zijlstra LKML-Reference: Signed-off-by: Ingo Molnar --- kernel/sched.c | 41 +++-------------------------------------- 1 file changed, 3 insertions(+), 38 deletions(-) (limited to 'kernel/sched.c') diff --git a/kernel/sched.c b/kernel/sched.c index fc6fda881d2e..6c819f338b11 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -512,14 +512,6 @@ struct root_domain { #ifdef CONFIG_SMP struct cpupri cpupri; #endif -#if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT) - /* - * Preferred wake up cpu nominated by sched_mc balance that will be - * used when most cpus are idle in the system indicating overall very - * low system utilisation. Triggered at POWERSAVINGS_BALANCE_WAKEUP(2) - */ - unsigned int sched_mc_preferred_wakeup_cpu; -#endif }; /* @@ -2315,22 +2307,6 @@ static int try_to_wake_up(struct task_struct *p, unsigned int state, int sync) if (!sched_feat(SYNC_WAKEUPS)) sync = 0; -#ifdef CONFIG_SMP - if (sched_feat(LB_WAKEUP_UPDATE) && !root_task_group_empty()) { - struct sched_domain *sd; - - this_cpu = raw_smp_processor_id(); - cpu = task_cpu(p); - - for_each_domain(this_cpu, sd) { - if (cpumask_test_cpu(cpu, sched_domain_span(sd))) { - update_shares(sd); - break; - } - } - } -#endif - this_cpu = get_cpu(); smp_wmb(); @@ -3533,11 +3509,6 @@ static inline int check_power_save_busiest_group(struct sd_lb_stats *sds, *imbalance = sds->min_load_per_task; sds->busiest = sds->group_min; - if (sched_mc_power_savings >= POWERSAVINGS_BALANCE_WAKEUP) { - cpu_rq(this_cpu)->rd->sched_mc_preferred_wakeup_cpu = - group_first_cpu(sds->group_leader); - } - return 1; } @@ -7850,9 +7821,7 @@ static int sd_degenerate(struct sched_domain *sd) } /* Following flags don't use groups */ - if (sd->flags & (SD_WAKE_IDLE | - SD_WAKE_AFFINE | - SD_WAKE_BALANCE)) + if (sd->flags & (SD_WAKE_AFFINE)) return 0; return 1; @@ -7869,10 +7838,6 @@ sd_parent_degenerate(struct sched_domain *sd, struct sched_domain *parent) if (!cpumask_equal(sched_domain_span(sd), sched_domain_span(parent))) return 0; - /* Does parent contain flags not in child? */ - /* WAKE_BALANCE is a subset of WAKE_AFFINE */ - if (cflags & SD_WAKE_AFFINE) - pflags &= ~SD_WAKE_BALANCE; /* Flags needing groups don't count if only 1 group in parent */ if (parent->groups == parent->groups->next) { pflags &= ~(SD_LOAD_BALANCE | @@ -8558,10 +8523,10 @@ static void set_domain_attribute(struct sched_domain *sd, request = attr->relax_domain_level; if (request < sd->level) { /* turn off idle balance on this domain */ - sd->flags &= ~(SD_WAKE_IDLE|SD_BALANCE_NEWIDLE); + sd->flags &= ~(SD_BALANCE_WAKE|SD_BALANCE_NEWIDLE); } else { /* turn on idle balance on this domain */ - sd->flags |= (SD_WAKE_IDLE_FAR|SD_BALANCE_NEWIDLE); + sd->flags |= (SD_BALANCE_WAKE|SD_BALANCE_NEWIDLE); } } -- cgit v1.2.2 From ae154be1f34a674e6cbb43ccf6e442f56acd7a70 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 10 Sep 2009 14:40:57 +0200 Subject: sched: Weaken SD_POWERSAVINGS_BALANCE One of the problems of power-saving balancing is that under certain scenarios it is too slow and allows tons of real work to pile up. Avoid this by ignoring the powersave stuff when there's real work to be done. Signed-off-by: Peter Zijlstra LKML-Reference: Signed-off-by: Ingo Molnar --- kernel/sched.c | 40 ++++++++++++++++++++-------------------- 1 file changed, 20 insertions(+), 20 deletions(-) (limited to 'kernel/sched.c') diff --git a/kernel/sched.c b/kernel/sched.c index 6c819f338b11..f0ccb8b926c8 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -1538,6 +1538,26 @@ static unsigned long target_load(int cpu, int type) return max(rq->cpu_load[type-1], total); } +static struct sched_group *group_of(int cpu) +{ + struct sched_domain *sd = rcu_dereference(cpu_rq(cpu)->sd); + + if (!sd) + return NULL; + + return sd->groups; +} + +static unsigned long power_of(int cpu) +{ + struct sched_group *group = group_of(cpu); + + if (!group) + return SCHED_LOAD_SCALE; + + return group->cpu_power; +} + static int task_hot(struct task_struct *p, u64 now, struct sched_domain *sd); static unsigned long cpu_avg_load_per_task(int cpu) @@ -3982,26 +4002,6 @@ ret: return NULL; } -static struct sched_group *group_of(int cpu) -{ - struct sched_domain *sd = rcu_dereference(cpu_rq(cpu)->sd); - - if (!sd) - return NULL; - - return sd->groups; -} - -static unsigned long power_of(int cpu) -{ - struct sched_group *group = group_of(cpu); - - if (!group) - return SCHED_LOAD_SCALE; - - return group->cpu_power; -} - /* * find_busiest_queue - find the busiest runqueue among the cpus in group. */ -- cgit v1.2.2 From d6a59aa3a2b1ca8411884c833a313b33b5f76e20 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 2 Sep 2009 13:28:02 +0200 Subject: sched: Provide arch_scale_freq_power Provide an ach specific hook for cpufreq based scaling of cpu_power. Signed-off-by: Peter Zijlstra [ego@in.ibm.com: spotting bugs] LKML-Reference: Signed-off-by: Ingo Molnar --- kernel/sched.c | 21 +++++++++++++++++++-- 1 file changed, 19 insertions(+), 2 deletions(-) (limited to 'kernel/sched.c') diff --git a/kernel/sched.c b/kernel/sched.c index f0ccb8b926c8..c210321adcb9 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -3552,7 +3552,18 @@ static inline int check_power_save_busiest_group(struct sd_lb_stats *sds, } #endif /* CONFIG_SCHED_MC || CONFIG_SCHED_SMT */ -unsigned long __weak arch_scale_smt_power(struct sched_domain *sd, int cpu) + +unsigned long default_scale_freq_power(struct sched_domain *sd, int cpu) +{ + return SCHED_LOAD_SCALE; +} + +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) { unsigned long weight = cpumask_weight(sched_domain_span(sd)); unsigned long smt_gain = sd->smt_gain; @@ -3562,6 +3573,11 @@ unsigned long __weak arch_scale_smt_power(struct sched_domain *sd, int cpu) return smt_gain; } +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) { struct rq *rq = cpu_rq(cpu); @@ -3586,7 +3602,8 @@ static void update_cpu_power(struct sched_domain *sd, int cpu) unsigned long power = SCHED_LOAD_SCALE; struct sched_group *sdg = sd->groups; - /* here we could scale based on cpufreq */ + power *= arch_scale_freq_power(sd, cpu); + power >>= SCHED_LOAD_SHIFT; if ((sd->flags & SD_SHARE_CPUPOWER) && weight > 1) { power *= arch_scale_smt_power(sd, cpu); -- cgit v1.2.2 From 8e6598af3f35629c37249a610cf13e73f70db279 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 3 Sep 2009 13:20:03 +0200 Subject: sched: Feature to disable APERF/MPERF cpu_power I suspect a feed-back loop between cpuidle and the aperf/mperf cpu_power bits, where when we have idle C-states lower the ratio, which leads to lower cpu_power and then less load, which generates more idle time, etc.. Put in a knob to disable it. Signed-off-by: Peter Zijlstra LKML-Reference: Signed-off-by: Ingo Molnar --- kernel/sched.c | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) (limited to 'kernel/sched.c') diff --git a/kernel/sched.c b/kernel/sched.c index c210321adcb9..e8e603bf8761 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -3602,11 +3602,19 @@ static void update_cpu_power(struct sched_domain *sd, int cpu) unsigned long power = SCHED_LOAD_SCALE; struct sched_group *sdg = sd->groups; - power *= arch_scale_freq_power(sd, cpu); + if (sched_feat(ARCH_POWER)) + power *= arch_scale_freq_power(sd, cpu); + else + power *= default_scale_freq_power(sd, cpu); + power >>= SCHED_LOAD_SHIFT; if ((sd->flags & SD_SHARE_CPUPOWER) && weight > 1) { - power *= arch_scale_smt_power(sd, cpu); + if (sched_feat(ARCH_POWER)) + power *= arch_scale_smt_power(sd, cpu); + else + power *= default_scale_smt_power(sd, cpu); + power >>= SCHED_LOAD_SHIFT; } -- cgit v1.2.2 From 7d47872146398dbede13223299fe1cb368ebc781 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Mon, 14 Sep 2009 19:55:44 +0200 Subject: sched: Rename sync arguments In order to extend the functions to have more than 1 flag (sync), rename the argument to flags, and explicitly define a WF_ space for individual flags. Signed-off-by: Peter Zijlstra LKML-Reference: Signed-off-by: Ingo Molnar --- kernel/sched.c | 30 ++++++++++++++++-------------- 1 file changed, 16 insertions(+), 14 deletions(-) (limited to 'kernel/sched.c') diff --git a/kernel/sched.c b/kernel/sched.c index e8e603bf8761..4da335cec8ee 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -636,9 +636,10 @@ struct rq { static DEFINE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues); -static inline void check_preempt_curr(struct rq *rq, struct task_struct *p, int sync) +static inline +void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags) { - rq->curr->sched_class->check_preempt_curr(rq, p, sync); + rq->curr->sched_class->check_preempt_curr(rq, p, flags); } static inline int cpu_of(struct rq *rq) @@ -2318,14 +2319,15 @@ void task_oncpu_function_call(struct task_struct *p, * * returns failure only if the task is already active. */ -static int try_to_wake_up(struct task_struct *p, unsigned int state, int sync) +static int try_to_wake_up(struct task_struct *p, unsigned int state, + int wake_flags) { int cpu, orig_cpu, this_cpu, success = 0; unsigned long flags; struct rq *rq; if (!sched_feat(SYNC_WAKEUPS)) - sync = 0; + wake_flags &= ~WF_SYNC; this_cpu = get_cpu(); @@ -2352,7 +2354,7 @@ static int try_to_wake_up(struct task_struct *p, unsigned int state, int sync) p->state = TASK_WAKING; task_rq_unlock(rq, &flags); - cpu = p->sched_class->select_task_rq(p, SD_BALANCE_WAKE, sync); + cpu = p->sched_class->select_task_rq(p, SD_BALANCE_WAKE, wake_flags); if (cpu != orig_cpu) set_task_cpu(p, cpu); @@ -2378,7 +2380,7 @@ static int try_to_wake_up(struct task_struct *p, unsigned int state, int sync) out_activate: #endif /* CONFIG_SMP */ schedstat_inc(p, se.nr_wakeups); - if (sync) + if (wake_flags & WF_SYNC) schedstat_inc(p, se.nr_wakeups_sync); if (orig_cpu != cpu) schedstat_inc(p, se.nr_wakeups_migrate); @@ -2407,7 +2409,7 @@ out_activate: out_running: trace_sched_wakeup(rq, p, success); - check_preempt_curr(rq, p, sync); + check_preempt_curr(rq, p, wake_flags); p->state = TASK_RUNNING; #ifdef CONFIG_SMP @@ -5562,10 +5564,10 @@ asmlinkage void __sched preempt_schedule_irq(void) #endif /* CONFIG_PREEMPT */ -int default_wake_function(wait_queue_t *curr, unsigned mode, int sync, +int default_wake_function(wait_queue_t *curr, unsigned mode, int flags, void *key) { - return try_to_wake_up(curr->private, mode, sync); + return try_to_wake_up(curr->private, mode, flags); } EXPORT_SYMBOL(default_wake_function); @@ -5579,14 +5581,14 @@ EXPORT_SYMBOL(default_wake_function); * zero in this (rare) case, and we handle it by continuing to scan the queue. */ static void __wake_up_common(wait_queue_head_t *q, unsigned int mode, - int nr_exclusive, int sync, void *key) + int nr_exclusive, int flags, void *key) { wait_queue_t *curr, *next; list_for_each_entry_safe(curr, next, &q->task_list, task_list) { unsigned flags = curr->flags; - if (curr->func(curr, mode, sync, key) && + if (curr->func(curr, mode, flags, key) && (flags & WQ_FLAG_EXCLUSIVE) && !--nr_exclusive) break; } @@ -5647,16 +5649,16 @@ void __wake_up_sync_key(wait_queue_head_t *q, unsigned int mode, int nr_exclusive, void *key) { unsigned long flags; - int sync = 1; + int wake_flags = WF_SYNC; if (unlikely(!q)) return; if (unlikely(!nr_exclusive)) - sync = 0; + wake_flags = 0; spin_lock_irqsave(&q->lock, flags); - __wake_up_common(q, mode, nr_exclusive, sync, key); + __wake_up_common(q, mode, nr_exclusive, wake_flags, key); spin_unlock_irqrestore(&q->lock, flags); } EXPORT_SYMBOL_GPL(__wake_up_sync_key); -- cgit v1.2.2 From a7558e01056f5191ff2ecff53b075dcb9e484188 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Mon, 14 Sep 2009 20:02:34 +0200 Subject: sched: Add WF_FORK Avoid the cache buddies from biasing the time distribution away from fork()ers. Normally the next buddy will be the preferred scheduling target, but this makes fork()s prefer to run the new child, whereas we prefer to run the parent, since that will generate more work. Signed-off-by: Peter Zijlstra LKML-Reference: Signed-off-by: Ingo Molnar --- kernel/sched.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel/sched.c') diff --git a/kernel/sched.c b/kernel/sched.c index 4da335cec8ee..0d4c4fea3317 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -2602,7 +2602,7 @@ void wake_up_new_task(struct task_struct *p, unsigned long clone_flags) inc_nr_running(rq); } trace_sched_wakeup_new(rq, p, 1); - check_preempt_curr(rq, p, 0); + check_preempt_curr(rq, p, WF_FORK); #ifdef CONFIG_SMP if (p->sched_class->task_wake_up) p->sched_class->task_wake_up(rq, p); -- cgit v1.2.2 From 63859d4fe4c97b737e7adbfe60acb1c2b2e668cb Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 15 Sep 2009 19:14:42 +0200 Subject: sched: Fix sync wakeups again The sync argument rename to introduce WF_* broke stuff by missing a local alias for an argument in __wake_up_common, fix it by using the more descriptive wake_flags name. This restores WF_SYNC propagation, which fixes wake_affine() behaviour, which fixes pipe-test. Signed-off-by: Peter Zijlstra LKML-Reference: Signed-off-by: Ingo Molnar --- kernel/sched.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'kernel/sched.c') diff --git a/kernel/sched.c b/kernel/sched.c index 0d4c4fea3317..af04ede6dd2f 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -5564,10 +5564,10 @@ asmlinkage void __sched preempt_schedule_irq(void) #endif /* CONFIG_PREEMPT */ -int default_wake_function(wait_queue_t *curr, unsigned mode, int flags, +int default_wake_function(wait_queue_t *curr, unsigned mode, int wake_flags, void *key) { - return try_to_wake_up(curr->private, mode, flags); + return try_to_wake_up(curr->private, mode, wake_flags); } EXPORT_SYMBOL(default_wake_function); @@ -5581,14 +5581,14 @@ EXPORT_SYMBOL(default_wake_function); * zero in this (rare) case, and we handle it by continuing to scan the queue. */ static void __wake_up_common(wait_queue_head_t *q, unsigned int mode, - int nr_exclusive, int flags, void *key) + int nr_exclusive, int wake_flags, void *key) { wait_queue_t *curr, *next; list_for_each_entry_safe(curr, next, &q->task_list, task_list) { unsigned flags = curr->flags; - if (curr->func(curr, mode, flags, key) && + if (curr->func(curr, mode, wake_flags, key) && (flags & WQ_FLAG_EXCLUSIVE) && !--nr_exclusive) break; } -- cgit v1.2.2 From 3b6408942206f940dd538e980e9904e48f4b64f8 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 16 Sep 2009 13:44:33 +0200 Subject: sched: Optimize cgroup vs wakeup a bit We don't need to call update_shares() for each domain we iterate, just got the largets one. However, we should call it before wake_affine() as well, so that that can use up-to-date values too. Signed-off-by: Peter Zijlstra LKML-Reference: Signed-off-by: Ingo Molnar --- kernel/sched.c | 7 ------- 1 file changed, 7 deletions(-) (limited to 'kernel/sched.c') diff --git a/kernel/sched.c b/kernel/sched.c index af04ede6dd2f..5049d959bb26 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -376,13 +376,6 @@ static inline void set_task_rq(struct task_struct *p, unsigned int cpu) #else -#ifdef CONFIG_SMP -static int root_task_group_empty(void) -{ - return 1; -} -#endif - static inline void set_task_rq(struct task_struct *p, unsigned int cpu) { } static inline struct task_group *task_group(struct task_struct *p) { -- cgit v1.2.2 From eb24073bc1fe3e569a855cf38d529fb650c35524 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Wed, 16 Sep 2009 21:09:13 +0200 Subject: sched: Fix TASK_WAKING & loadaverage breakage Fix this: top - 21:54:00 up 2:59, 1 user, load average: 432512.33, 426421.74, 417432.74 Which happens because we now set TASK_WAKING before activate_task(). Cc: Peter Zijlstra Cc: Mike Galbraith LKML-Reference: Signed-off-by: Ingo Molnar --- kernel/sched.c | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'kernel/sched.c') diff --git a/kernel/sched.c b/kernel/sched.c index 5049d959bb26..969dfaef2465 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -2343,7 +2343,11 @@ static int try_to_wake_up(struct task_struct *p, unsigned int state, /* * In order to handle concurrent wakeups and release the rq->lock * we put the task in TASK_WAKING state. + * + * First fix up the nr_uninterruptible count: */ + if (task_contributes_to_load(p)) + rq->nr_uninterruptible--; p->state = TASK_WAKING; task_rq_unlock(rq, &flags); -- cgit v1.2.2 From ad4b78bbcbab66998b05d422ac6106b645796e54 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 16 Sep 2009 12:31:31 +0200 Subject: sched: Add new wakeup preemption mode: WAKEUP_RUNNING Create a new wakeup preemption mode, preempt towards tasks that run shorter on avg. It sets next buddy to be sure we actually run the task we preempted for. Test results: root@twins:~# while :; do :; done & [1] 6537 root@twins:~# while :; do :; done & [2] 6538 root@twins:~# while :; do :; done & [3] 6539 root@twins:~# while :; do :; done & [4] 6540 root@twins:/home/peter# ./latt -c4 sleep 4 Entries: 48 (clients=4) Averages: ------------------------------ Max 4750 usec Avg 497 usec Stdev 737 usec root@twins:/home/peter# echo WAKEUP_RUNNING > /debug/sched_features root@twins:/home/peter# ./latt -c4 sleep 4 Entries: 48 (clients=4) Averages: ------------------------------ Max 14 usec Avg 5 usec Stdev 3 usec Disabled by default - needs more testing. Signed-off-by: Peter Zijlstra Acked-by: Mike Galbraith Signed-off-by: Ingo Molnar LKML-Reference: --- kernel/sched.c | 17 ++++++++++------- 1 file changed, 10 insertions(+), 7 deletions(-) (limited to 'kernel/sched.c') diff --git a/kernel/sched.c b/kernel/sched.c index 969dfaef2465..3bb4ea2ee6f0 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -2458,6 +2458,7 @@ static void __sched_fork(struct task_struct *p) p->se.avg_overlap = 0; p->se.start_runtime = 0; p->se.avg_wakeup = sysctl_sched_wakeup_granularity; + p->se.avg_running = 0; #ifdef CONFIG_SCHEDSTATS p->se.wait_start = 0; @@ -5310,14 +5311,13 @@ static inline void schedule_debug(struct task_struct *prev) #endif } -static void put_prev_task(struct rq *rq, struct task_struct *prev) +static void put_prev_task(struct rq *rq, struct task_struct *p) { - if (prev->state == TASK_RUNNING) { - u64 runtime = prev->se.sum_exec_runtime; + u64 runtime = p->se.sum_exec_runtime - p->se.prev_sum_exec_runtime; - runtime -= prev->se.prev_sum_exec_runtime; - runtime = min_t(u64, runtime, 2*sysctl_sched_migration_cost); + update_avg(&p->se.avg_running, runtime); + if (p->state == TASK_RUNNING) { /* * In order to avoid avg_overlap growing stale when we are * indeed overlapping and hence not getting put to sleep, grow @@ -5327,9 +5327,12 @@ static void put_prev_task(struct rq *rq, struct task_struct *prev) * correlates to the amount of cache footprint a task can * build up. */ - update_avg(&prev->se.avg_overlap, runtime); + runtime = min_t(u64, runtime, 2*sysctl_sched_migration_cost); + update_avg(&p->se.avg_overlap, runtime); + } else { + update_avg(&p->se.avg_running, 0); } - prev->sched_class->put_prev_task(rq, prev); + p->sched_class->put_prev_task(rq, p); } /* -- cgit v1.2.2 From 89f19f04dc72363d912fd007a399cb10310eff6e Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Sat, 19 Sep 2009 11:55:44 -0700 Subject: sched: Fix raciness in runqueue_is_locked() runqueue_is_locked() is unavoidably racy due to a poor interface design. It does cpu = get_cpu() ret = some_perpcu_thing(cpu); put_cpu(cpu); return ret; Its return value is unreliable. Fix. Signed-off-by: Andrew Morton Acked-by: Steven Rostedt Cc: Peter Zijlstra LKML-Reference: <200909191855.n8JItiko022148@imap1.linux-foundation.org> Signed-off-by: Ingo Molnar --- kernel/sched.c | 10 ++-------- 1 file changed, 2 insertions(+), 8 deletions(-) (limited to 'kernel/sched.c') diff --git a/kernel/sched.c b/kernel/sched.c index faf4d463bbff..575fb0139038 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -681,15 +681,9 @@ inline void update_rq_clock(struct rq *rq) * This interface allows printk to be called with the runqueue lock * held and know whether or not it is OK to wake up the klogd. */ -int runqueue_is_locked(void) +int runqueue_is_locked(int cpu) { - int cpu = get_cpu(); - struct rq *rq = cpu_rq(cpu); - int ret; - - ret = spin_is_locked(&rq->lock); - put_cpu(); - return ret; + return spin_is_locked(&cpu_rq(cpu)->lock); } /* -- cgit v1.2.2 From cb5fd13f1178dee4302646b2890d884c380160e1 Mon Sep 17 00:00:00 2001 From: Yong Zhang Date: Mon, 14 Sep 2009 20:20:16 +0800 Subject: sched: Fix potential NULL derference of doms_cur If CONFIG_CPUMASK_OFFSTACK is enabled but doms_cur alloc failed in arch_init_sched_domains(), doms_cur will move back to fallback_doms. But this time, fallback_doms has not been initialized yet. Signed-off-by: Yong Zhang Cc: a.p.zijlstra@chello.nl LKML-Reference: <1252930816-7672-1-git-send-email-yong.zhang0@gmail.com> Signed-off-by: Ingo Molnar --- kernel/sched.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel/sched.c') diff --git a/kernel/sched.c b/kernel/sched.c index 575fb0139038..1b900fb1c6e1 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -9165,6 +9165,7 @@ void __init sched_init_smp(void) cpumask_var_t non_isolated_cpus; alloc_cpumask_var(&non_isolated_cpus, GFP_KERNEL); + alloc_cpumask_var(&fallback_doms, GFP_KERNEL); #if defined(CONFIG_NUMA) sched_group_nodes_bycpu = kzalloc(nr_cpu_ids * sizeof(void **), @@ -9196,7 +9197,6 @@ void __init sched_init_smp(void) sched_init_granularity(); free_cpumask_var(non_isolated_cpus); - alloc_cpumask_var(&fallback_doms, GFP_KERNEL); init_sched_rt_class(); } #else -- cgit v1.2.2 From 0d721ceadbeaa24d7f9dd41b3e5e29912327a7e1 Mon Sep 17 00:00:00 2001 From: Peter Williams Date: Mon, 21 Sep 2009 01:31:53 +0000 Subject: sched: Simplify sys_sched_rr_get_interval() system call By removing the need for it to know details of scheduling classes. This allows PlugSched to define orthogonal scheduling classes. Signed-off-by: Peter Williams Acked-by: Peter Zijlstra Cc: Mike Galbraith LKML-Reference: <06d1b89ee15a0eef82d7.1253496713@mudlark.pw.nest> Signed-off-by: Ingo Molnar --- kernel/sched.c | 17 +---------------- 1 file changed, 1 insertion(+), 16 deletions(-) (limited to 'kernel/sched.c') diff --git a/kernel/sched.c b/kernel/sched.c index 1b900fb1c6e1..830967e18285 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -6819,23 +6819,8 @@ SYSCALL_DEFINE2(sched_rr_get_interval, pid_t, pid, if (retval) goto out_unlock; - /* - * Time slice is 0 for SCHED_FIFO tasks and for SCHED_OTHER - * tasks that are on an otherwise idle runqueue: - */ - time_slice = 0; - if (p->policy == SCHED_RR) { - time_slice = DEF_TIMESLICE; - } else if (p->policy != SCHED_FIFO) { - struct sched_entity *se = &p->se; - unsigned long flags; - struct rq *rq; + time_slice = p->sched_class->get_rr_interval(p); - rq = task_rq_lock(p, &flags); - if (rq->cfs.load.weight) - time_slice = NS_TO_JIFFIES(sched_slice(&rq->cfs, se)); - task_rq_unlock(rq, &flags); - } read_unlock(&tasklist_lock); jiffies_to_timespec(time_slice, &t); retval = copy_to_user(interval, &t, sizeof(t)) ? -EFAULT : 0; -- cgit v1.2.2 From cdd6c482c9ff9c55475ee7392ec8f672eddb7be6 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Mon, 21 Sep 2009 12:02:48 +0200 Subject: perf: Do the big rename: Performance Counters -> Performance Events Bye-bye Performance Counters, welcome Performance Events! In the past few months the perfcounters subsystem has grown out its initial role of counting hardware events, and has become (and is becoming) a much broader generic event enumeration, reporting, logging, monitoring, analysis facility. Naming its core object 'perf_counter' and naming the subsystem 'perfcounters' has become more and more of a misnomer. With pending code like hw-breakpoints support the 'counter' name is less and less appropriate. All in one, we've decided to rename the subsystem to 'performance events' and to propagate this rename through all fields, variables and API names. (in an ABI compatible fashion) The word 'event' is also a bit shorter than 'counter' - which makes it slightly more convenient to write/handle as well. Thanks goes to Stephane Eranian who first observed this misnomer and suggested a rename. User-space tooling and ABI compatibility is not affected - this patch should be function-invariant. (Also, defconfigs were not touched to keep the size down.) This patch has been generated via the following script: FILES=$(find * -type f | grep -vE 'oprofile|[^K]config') sed -i \ -e 's/PERF_EVENT_/PERF_RECORD_/g' \ -e 's/PERF_COUNTER/PERF_EVENT/g' \ -e 's/perf_counter/perf_event/g' \ -e 's/nb_counters/nb_events/g' \ -e 's/swcounter/swevent/g' \ -e 's/tpcounter_event/tp_event/g' \ $FILES for N in $(find . -name perf_counter.[ch]); do M=$(echo $N | sed 's/perf_counter/perf_event/g') mv $N $M done FILES=$(find . -name perf_event.*) sed -i \ -e 's/COUNTER_MASK/REG_MASK/g' \ -e 's/COUNTER/EVENT/g' \ -e 's/\/event_id/g' \ -e 's/counter/event/g' \ -e 's/Counter/Event/g' \ $FILES ... to keep it as correct as possible. This script can also be used by anyone who has pending perfcounters patches - it converts a Linux kernel tree over to the new naming. We tried to time this change to the point in time where the amount of pending patches is the smallest: the end of the merge window. Namespace clashes were fixed up in a preparatory patch - and some stylistic fallout will be fixed up in a subsequent patch. ( NOTE: 'counters' are still the proper terminology when we deal with hardware registers - and these sed scripts are a bit over-eager in renaming them. I've undone some of that, but in case there's something left where 'counter' would be better than 'event' we can undo that on an individual basis instead of touching an otherwise nicely automated patch. ) Suggested-by: Stephane Eranian Acked-by: Peter Zijlstra Acked-by: Paul Mackerras Reviewed-by: Arjan van de Ven Cc: Mike Galbraith Cc: Arnaldo Carvalho de Melo Cc: Frederic Weisbecker Cc: Steven Rostedt Cc: Benjamin Herrenschmidt Cc: David Howells Cc: Kyle McMartin Cc: Martin Schwidefsky Cc: "David S. Miller" Cc: Thomas Gleixner Cc: "H. Peter Anvin" Cc: LKML-Reference: Signed-off-by: Ingo Molnar --- kernel/sched.c | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) (limited to 'kernel/sched.c') diff --git a/kernel/sched.c b/kernel/sched.c index faf4d463bbff..291c8d213d13 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -39,7 +39,7 @@ #include #include #include -#include +#include #include #include #include @@ -2059,7 +2059,7 @@ void set_task_cpu(struct task_struct *p, unsigned int new_cpu) if (task_hot(p, old_rq->clock, NULL)) schedstat_inc(p, se.nr_forced2_migrations); #endif - perf_swcounter_event(PERF_COUNT_SW_CPU_MIGRATIONS, + perf_sw_event(PERF_COUNT_SW_CPU_MIGRATIONS, 1, 1, NULL, 0); } p->se.vruntime -= old_cfsrq->min_vruntime - @@ -2724,7 +2724,7 @@ static void finish_task_switch(struct rq *rq, struct task_struct *prev) */ prev_state = prev->state; finish_arch_switch(prev); - perf_counter_task_sched_in(current, cpu_of(rq)); + perf_event_task_sched_in(current, cpu_of(rq)); finish_lock_switch(rq, prev); fire_sched_in_preempt_notifiers(current); @@ -5199,7 +5199,7 @@ void scheduler_tick(void) curr->sched_class->task_tick(rq, curr, 0); spin_unlock(&rq->lock); - perf_counter_task_tick(curr, cpu); + perf_event_task_tick(curr, cpu); #ifdef CONFIG_SMP rq->idle_at_tick = idle_cpu(cpu); @@ -5415,7 +5415,7 @@ need_resched_nonpreemptible: if (likely(prev != next)) { sched_info_switch(prev, next); - perf_counter_task_sched_out(prev, next, cpu); + perf_event_task_sched_out(prev, next, cpu); rq->nr_switches++; rq->curr = next; @@ -7692,7 +7692,7 @@ migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu) /* * Register at high priority so that task migration (migrate_all_tasks) * happens before everything else. This has to be lower priority than - * the notifier in the perf_counter subsystem, though. + * the notifier in the perf_event subsystem, though. */ static struct notifier_block __cpuinitdata migration_notifier = { .notifier_call = migration_call, @@ -9549,7 +9549,7 @@ void __init sched_init(void) alloc_cpumask_var(&cpu_isolated_map, GFP_NOWAIT); #endif /* SMP */ - perf_counter_init(); + perf_event_init(); scheduler_running = 1; } -- cgit v1.2.2 From 69d25870f20c4b2563304f2b79c5300dd60a067e Mon Sep 17 00:00:00 2001 From: Arjan van de Ven Date: Mon, 21 Sep 2009 17:04:08 -0700 Subject: cpuidle: fix the menu governor to boost IO performance Fix the menu idle governor which balances power savings, energy efficiency and performance impact. The reason for a reworked governor is that there have been serious performance issues reported with the existing code on Nehalem server systems. To show this I'm sure Andrew wants to see benchmark results: (benchmark is "fio", "no cstates" is using "idle=poll") no cstates current linux new algorithm 1 disk 107 Mb/s 85 Mb/s 105 Mb/s 2 disks 215 Mb/s 123 Mb/s 209 Mb/s 12 disks 590 Mb/s 320 Mb/s 585 Mb/s In various power benchmark measurements, no degredation was found by our measurement&diagnostics team. Obviously a small percentage more power was used in the "fio" benchmark, due to the much higher performance. While it would be a novel idea to describe the new algorithm in this commit message, I cheaped out and described it in comments in the code instead. [changes since first post: spelling fixes from akpm, review feedback, folded menu-tng into menu.c] Signed-off-by: Arjan van de Ven Cc: Venkatesh Pallipadi Cc: Len Brown Cc: Ingo Molnar Cc: Peter Zijlstra Cc: Yanmin Zhang Acked-by: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/sched.c | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'kernel/sched.c') diff --git a/kernel/sched.c b/kernel/sched.c index 91843ba7f237..0ac9053c21d6 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -2904,6 +2904,19 @@ unsigned long nr_iowait(void) return sum; } +unsigned long nr_iowait_cpu(void) +{ + struct rq *this = this_rq(); + return atomic_read(&this->nr_iowait); +} + +unsigned long this_cpu_load(void) +{ + struct rq *this = this_rq(); + return this->cpu_load[0]; +} + + /* Variables and functions for calc_load */ static atomic_long_t calc_load_tasks; static unsigned long calc_load_update; -- cgit v1.2.2 From be367d09927023d081f9199665c8500f69f14d22 Mon Sep 17 00:00:00 2001 From: Ben Blum Date: Wed, 23 Sep 2009 15:56:31 -0700 Subject: cgroups: let ss->can_attach and ss->attach do whole threadgroups at a time Alter the ss->can_attach and ss->attach functions to be able to deal with a whole threadgroup at a time, for use in cgroup_attach_proc. (This is a pre-patch to cgroup-procs-writable.patch.) Currently, new mode of the attach function can only tell the subsystem about the old cgroup of the threadgroup leader. No subsystem currently needs that information for each thread that's being moved, but if one were to be added (for example, one that counts tasks within a group) this bit would need to be reworked a bit to tell the subsystem the right information. [hidave.darkstar@gmail.com: fix build] Signed-off-by: Ben Blum Signed-off-by: Paul Menage Acked-by: Li Zefan Reviewed-by: Matt Helsley Cc: "Eric W. Biederman" Cc: Oleg Nesterov Cc: Peter Zijlstra Cc: Ingo Molnar Cc: Dave Young Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/sched.c | 35 ++++++++++++++++++++++++++++++++--- 1 file changed, 32 insertions(+), 3 deletions(-) (limited to 'kernel/sched.c') diff --git a/kernel/sched.c b/kernel/sched.c index 2f76e06bea58..0d0361b9dbb3 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -10377,8 +10377,7 @@ cpu_cgroup_destroy(struct cgroup_subsys *ss, struct cgroup *cgrp) } static int -cpu_cgroup_can_attach(struct cgroup_subsys *ss, struct cgroup *cgrp, - struct task_struct *tsk) +cpu_cgroup_can_attach_task(struct cgroup *cgrp, struct task_struct *tsk) { #ifdef CONFIG_RT_GROUP_SCHED if (!sched_rt_can_attach(cgroup_tg(cgrp), tsk)) @@ -10388,15 +10387,45 @@ cpu_cgroup_can_attach(struct cgroup_subsys *ss, struct cgroup *cgrp, if (tsk->sched_class != &fair_sched_class) return -EINVAL; #endif + return 0; +} +static int +cpu_cgroup_can_attach(struct cgroup_subsys *ss, struct cgroup *cgrp, + struct task_struct *tsk, bool threadgroup) +{ + int retval = cpu_cgroup_can_attach_task(cgrp, tsk); + if (retval) + return retval; + if (threadgroup) { + struct task_struct *c; + rcu_read_lock(); + list_for_each_entry_rcu(c, &tsk->thread_group, thread_group) { + retval = cpu_cgroup_can_attach_task(cgrp, c); + if (retval) { + rcu_read_unlock(); + return retval; + } + } + rcu_read_unlock(); + } return 0; } static void cpu_cgroup_attach(struct cgroup_subsys *ss, struct cgroup *cgrp, - struct cgroup *old_cont, struct task_struct *tsk) + struct cgroup *old_cont, struct task_struct *tsk, + bool threadgroup) { sched_move_task(tsk); + if (threadgroup) { + struct task_struct *c; + rcu_read_lock(); + list_for_each_entry_rcu(c, &tsk->thread_group, thread_group) { + sched_move_task(c); + } + rcu_read_unlock(); + } } #ifdef CONFIG_FAIR_GROUP_SCHED -- cgit v1.2.2 From 8d65af789f3e2cf4cfbdbf71a0f7a61ebcd41d38 Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Wed, 23 Sep 2009 15:57:19 -0700 Subject: sysctl: remove "struct file *" argument of ->proc_handler It's unused. It isn't needed -- read or write flag is already passed and sysctl shouldn't care about the rest. It _was_ used in two places at arch/frv for some reason. Signed-off-by: Alexey Dobriyan Cc: David Howells Cc: "Eric W. Biederman" Cc: Al Viro Cc: Ralf Baechle Cc: Martin Schwidefsky Cc: Ingo Molnar Cc: "David S. Miller" Cc: James Morris Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/sched.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'kernel/sched.c') diff --git a/kernel/sched.c b/kernel/sched.c index 0d0361b9dbb3..ee61f454a98b 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -10312,7 +10312,7 @@ static int sched_rt_global_constraints(void) #endif /* CONFIG_RT_GROUP_SCHED */ int sched_rt_handler(struct ctl_table *table, int write, - struct file *filp, void __user *buffer, size_t *lenp, + void __user *buffer, size_t *lenp, loff_t *ppos) { int ret; @@ -10323,7 +10323,7 @@ int sched_rt_handler(struct ctl_table *table, int write, old_period = sysctl_sched_rt_period; old_runtime = sysctl_sched_rt_runtime; - ret = proc_dointvec(table, write, filp, buffer, lenp, ppos); + ret = proc_dointvec(table, write, buffer, lenp, ppos); if (!ret && write) { ret = sched_rt_global_constraints(); -- cgit v1.2.2 From 828c09509b9695271bcbdc53e9fc9a6a737148d2 Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Thu, 1 Oct 2009 15:43:56 -0700 Subject: const: constify remaining file_operations [akpm@linux-foundation.org: fix KVM] Signed-off-by: Alexey Dobriyan Acked-by: Mike Frysinger Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/sched.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel/sched.c') diff --git a/kernel/sched.c b/kernel/sched.c index ee61f454a98b..1535f3884b88 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -780,7 +780,7 @@ static int sched_feat_open(struct inode *inode, struct file *filp) return single_open(filp, sched_feat_show, NULL); } -static struct file_operations sched_feat_fops = { +static const struct file_operations sched_feat_fops = { .open = sched_feat_open, .write = sched_feat_write, .read = seq_read, -- cgit v1.2.2 From f83f9ac2632732bd1678150b5a03d152f912fe72 Mon Sep 17 00:00:00 2001 From: Peter Williams Date: Thu, 24 Sep 2009 06:47:10 +0000 Subject: sched: Set correct normal_prio and prio values in sched_fork() normal_prio should be updated if policy changes from RT to SCHED_MORMAL or if static_prio/nice is changed. Some paths through sched_fork() ignore this requirement and may result in normal_prio having an invalid value. Fixing this issue allows the call to effective_prio() in wake_up_new_task() to be removed. Signed-off-by: Peter Williams Acked-by: Peter Zijlstra Cc: Mike Galbraith LKML-Reference: Signed-off-by: Ingo Molnar --- kernel/sched.c | 20 +++++++++----------- 1 file changed, 9 insertions(+), 11 deletions(-) (limited to 'kernel/sched.c') diff --git a/kernel/sched.c b/kernel/sched.c index 1535f3884b88..76c0e9691fc0 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -2514,23 +2514,18 @@ void sched_fork(struct task_struct *p, int clone_flags) __sched_fork(p); - /* - * Make sure we do not leak PI boosting priority to the child. - */ - p->prio = current->normal_prio; - /* * Revert to default priority/policy on fork if requested. */ if (unlikely(p->sched_reset_on_fork)) { - if (p->policy == SCHED_FIFO || p->policy == SCHED_RR) + if (p->policy == SCHED_FIFO || p->policy == SCHED_RR) { p->policy = SCHED_NORMAL; - - if (p->normal_prio < DEFAULT_PRIO) - p->prio = DEFAULT_PRIO; + p->normal_prio = p->static_prio; + } if (PRIO_TO_NICE(p->static_prio) < 0) { p->static_prio = NICE_TO_PRIO(0); + p->normal_prio = p->static_prio; set_load_weight(p); } @@ -2541,6 +2536,11 @@ void sched_fork(struct task_struct *p, int clone_flags) p->sched_reset_on_fork = 0; } + /* + * Make sure we do not leak PI boosting priority to the child. + */ + p->prio = current->normal_prio; + if (!rt_prio(p->prio)) p->sched_class = &fair_sched_class; @@ -2581,8 +2581,6 @@ void wake_up_new_task(struct task_struct *p, unsigned long clone_flags) BUG_ON(p->state != TASK_RUNNING); update_rq_clock(rq); - p->prio = effective_prio(p); - if (!p->sched_class->task_new || !current->se.on_rq) { activate_task(rq, p, 0); } else { -- cgit v1.2.2 From d25105e8911bff1dbd68e387f12901c5b1a15fe8 Mon Sep 17 00:00:00 2001 From: Wu Fengguang Date: Fri, 9 Oct 2009 12:40:42 +0200 Subject: writeback: account IO throttling wait as iowait It makes sense to do IOWAIT when someone is blocked due to IO throttle, as suggested by Kame and Peter. There is an old comment for not doing IOWAIT on throttle, however it has been mismatching the code for a long time. If we stop accounting IOWAIT for 2.6.32, it could be an undesirable behavior change. So restore the io_schedule. CC: KAMEZAWA Hiroyuki CC: Peter Zijlstra Signed-off-by: Wu Fengguang Signed-off-by: Jens Axboe --- kernel/sched.c | 3 --- 1 file changed, 3 deletions(-) (limited to 'kernel/sched.c') diff --git a/kernel/sched.c b/kernel/sched.c index 1535f3884b88..074f753f7449 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -6720,9 +6720,6 @@ EXPORT_SYMBOL(yield); /* * This task is about to go to sleep on IO. Increment rq->nr_iowait so * that process accounting knows that this is a task in IO wait state. - * - * But don't do that if it is a deliberate, throttling IO wait (this task - * has set its backing_dev_info: the queue against which it should throttle) */ void __sched io_schedule(void) { -- cgit v1.2.2 From f5dc37530ba8a35aae0f7f4f13781d1904f71e94 Mon Sep 17 00:00:00 2001 From: Mike Galbraith Date: Fri, 9 Oct 2009 08:35:03 +0200 Subject: sched: Update the clock of runqueue select_task_rq() selected In try_to_wake_up(), we update the runqueue clock, but select_task_rq() may select a different runqueue than the one we updated, leaving the new runqueue's clock stale for a bit. This patch cures occasional huge latencies reported by latencytop when coming out of idle on a mostly idle NO_HZ box. Signed-off-by: Mike Galbraith Signed-off-by: Peter Zijlstra LKML-Reference: <1255070103.7639.30.camel@marge.simson.net> Signed-off-by: Ingo Molnar --- kernel/sched.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'kernel/sched.c') diff --git a/kernel/sched.c b/kernel/sched.c index 76c0e9691fc0..e3f8f4f61c8e 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -2311,7 +2311,7 @@ static int try_to_wake_up(struct task_struct *p, unsigned int state, { int cpu, orig_cpu, this_cpu, success = 0; unsigned long flags; - struct rq *rq; + struct rq *rq, *orig_rq; if (!sched_feat(SYNC_WAKEUPS)) wake_flags &= ~WF_SYNC; @@ -2319,7 +2319,7 @@ static int try_to_wake_up(struct task_struct *p, unsigned int state, this_cpu = get_cpu(); smp_wmb(); - rq = task_rq_lock(p, &flags); + rq = orig_rq = task_rq_lock(p, &flags); update_rq_clock(rq); if (!(p->state & state)) goto out; @@ -2350,6 +2350,10 @@ static int try_to_wake_up(struct task_struct *p, unsigned int state, set_task_cpu(p, cpu); rq = task_rq_lock(p, &flags); + + if (rq != orig_rq) + update_rq_clock(rq); + WARN_ON(p->state != TASK_WAKING); cpu = task_cpu(p); -- cgit v1.2.2 From e17b38bf9e70d74f3739a600db75240078ac1407 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Sun, 11 Oct 2009 19:12:00 -0700 Subject: sched: Fix missing kernel-doc notation The following htmldocs warnings: Warning(kernel/sched.c:685): No description found for parameter 'cpu' Warning(kernel/sched.c:3676): No description found for parameter 'sd' Trigger because new parameters were added to update_rq_clock() and update_group_power() without updating the kernel-doc notation. Signed-off-by: Jaswinder Singh Rajput Signed-off-by: Randy Dunlap Cc: Andrew Morton Cc: Steven Rostedt Cc: Peter Zijlstra LKML-Reference: <4AD29070.7070002@oracle.com> Signed-off-by: Ingo Molnar --- kernel/sched.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'kernel/sched.c') diff --git a/kernel/sched.c b/kernel/sched.c index e3f8f4f61c8e..789001da0a94 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -676,6 +676,7 @@ inline void update_rq_clock(struct rq *rq) /** * runqueue_is_locked + * @cpu: the processor in question. * * Returns true if the current cpu runqueue is locked. * This interface allows printk to be called with the runqueue lock @@ -3660,6 +3661,7 @@ static void update_group_power(struct sched_domain *sd, int cpu) /** * update_sg_lb_stats - Update sched_group's statistics for load balancing. + * @sd: The sched_domain whose statistics are to be updated. * @group: sched_group whose statistics are to be updated. * @this_cpu: Cpu for which load balance is currently performed. * @idle: Idle status of this_cpu -- cgit v1.2.2