diff options
| -rw-r--r-- | Documentation/feature-removal-schedule.txt | 15 | ||||
| -rw-r--r-- | Documentation/filesystems/proc.txt | 3 | ||||
| -rw-r--r-- | Documentation/kernel-parameters.txt | 2 | ||||
| -rw-r--r-- | fs/proc/array.c | 23 | ||||
| -rw-r--r-- | fs/proc/stat.c | 19 | ||||
| -rw-r--r-- | include/linux/jiffies.h | 1 | ||||
| -rw-r--r-- | include/linux/kernel_stat.h | 1 | ||||
| -rw-r--r-- | include/linux/preempt.h | 5 | ||||
| -rw-r--r-- | include/linux/sched.h | 22 | ||||
| -rw-r--r-- | kernel/cpuset.c | 27 | ||||
| -rw-r--r-- | kernel/exit.c | 22 | ||||
| -rw-r--r-- | kernel/fork.c | 5 | ||||
| -rw-r--r-- | kernel/kgdb.c | 2 | ||||
| -rw-r--r-- | kernel/sched.c | 270 | ||||
| -rw-r--r-- | kernel/sched_debug.c | 4 | ||||
| -rw-r--r-- | kernel/sched_fair.c | 65 | ||||
| -rw-r--r-- | kernel/sched_rt.c | 61 | ||||
| -rw-r--r-- | kernel/sys.c | 21 | ||||
| -rw-r--r-- | kernel/time.c | 30 |
19 files changed, 397 insertions, 201 deletions
diff --git a/Documentation/feature-removal-schedule.txt b/Documentation/feature-removal-schedule.txt index bc693fffabe..f613df8ec7b 100644 --- a/Documentation/feature-removal-schedule.txt +++ b/Documentation/feature-removal-schedule.txt @@ -6,6 +6,21 @@ be removed from this file. --------------------------- +What: USER_SCHED +When: 2.6.34 + +Why: USER_SCHED was implemented as a proof of concept for group scheduling. + The effect of USER_SCHED can already be achieved from userspace with + the help of libcgroup. The removal of USER_SCHED will also simplify + the scheduler code with the removal of one major ifdef. There are also + issues USER_SCHED has with USER_NS. A decision was taken not to fix + those and instead remove USER_SCHED. Also new group scheduling + features will not be implemented for USER_SCHED. + +Who: Dhaval Giani <dhaval@linux.vnet.ibm.com> + +--------------------------- + What: PRISM54 When: 2.6.34 diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.txt index 2c48f945546..4af0018533f 100644 --- a/Documentation/filesystems/proc.txt +++ b/Documentation/filesystems/proc.txt @@ -1072,7 +1072,8 @@ second). The meanings of the columns are as follows, from left to right: - irq: servicing interrupts - softirq: servicing softirqs - steal: involuntary wait -- guest: running a guest +- guest: running a normal guest +- guest_nice: running a niced guest The "intr" line gives counts of interrupts serviced since boot time, for each of the possible system interrupts. The first column is the total of all diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index 51138b3dc8c..5820eb0cd7e 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -2186,6 +2186,8 @@ and is between 256 and 4096 characters. It is defined in the file sbni= [NET] Granch SBNI12 leased line adapter + sched_debug [KNL] Enables verbose scheduler debug messages. + sc1200wdt= [HW,WDT] SC1200 WDT (watchdog) driver Format: <io>[,<timeout>[,<isapnp>]] diff --git a/fs/proc/array.c b/fs/proc/array.c index 822c2d50651..4badde179b1 100644 --- a/fs/proc/array.c +++ b/fs/proc/array.c @@ -410,6 +410,16 @@ static void task_show_stack_usage(struct seq_file *m, struct task_struct *task) } #endif /* CONFIG_MMU */ +static void task_cpus_allowed(struct seq_file *m, struct task_struct *task) +{ + seq_printf(m, "Cpus_allowed:\t"); + seq_cpumask(m, &task->cpus_allowed); + seq_printf(m, "\n"); + seq_printf(m, "Cpus_allowed_list:\t"); + seq_cpumask_list(m, &task->cpus_allowed); + seq_printf(m, "\n"); +} + int proc_pid_status(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *task) { @@ -424,6 +434,7 @@ int proc_pid_status(struct seq_file *m, struct pid_namespace *ns, } task_sig(m, task); task_cap(m, task); + task_cpus_allowed(m, task); cpuset_task_status_allowed(m, task); #if defined(CONFIG_S390) task_show_regs(m, task); @@ -495,20 +506,17 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns, /* add up live thread stats at the group level */ if (whole) { - struct task_cputime cputime; struct task_struct *t = task; do { min_flt += t->min_flt; maj_flt += t->maj_flt; - gtime = cputime_add(gtime, task_gtime(t)); + gtime = cputime_add(gtime, t->gtime); t = next_thread(t); } while (t != task); min_flt += sig->min_flt; maj_flt += sig->maj_flt; - thread_group_cputime(task, &cputime); - utime = cputime.utime; - stime = cputime.stime; + thread_group_times(task, &utime, &stime); gtime = cputime_add(gtime, sig->gtime); } @@ -524,9 +532,8 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns, if (!whole) { min_flt = task->min_flt; maj_flt = task->maj_flt; - utime = task_utime(task); - stime = task_stime(task); - gtime = task_gtime(task); + task_times(task, &utime, &stime); + gtime = task->gtime; } /* scale priority and nice values from timeslices to -20..20 */ diff --git a/fs/proc/stat.c b/fs/proc/stat.c index 7cc726c6d70..b9b7aad2003 100644 --- a/fs/proc/stat.c +++ b/fs/proc/stat.c @@ -27,7 +27,7 @@ static int show_stat(struct seq_file *p, void *v) int i, j; unsigned long jif; cputime64_t user, nice, system, idle, iowait, irq, softirq, steal; - cputime64_t guest; + cputime64_t guest, guest_nice; u64 sum = 0; u64 sum_softirq = 0; unsigned int per_softirq_sums[NR_SOFTIRQS] = {0}; @@ -36,7 +36,7 @@ static int show_stat(struct seq_file *p, void *v) user = nice = system = idle = iowait = irq = softirq = steal = cputime64_zero; - guest = cputime64_zero; + guest = guest_nice = cputime64_zero; getboottime(&boottime); jif = boottime.tv_sec; @@ -51,6 +51,8 @@ static int show_stat(struct seq_file *p, void *v) softirq = cputime64_add(softirq, kstat_cpu(i).cpustat.softirq); steal = cputime64_add(steal, kstat_cpu(i).cpustat.steal); guest = cputime64_add(guest, kstat_cpu(i).cpustat.guest); + guest_nice = cputime64_add(guest_nice, + kstat_cpu(i).cpustat.guest_nice); for_each_irq_nr(j) { sum += kstat_irqs_cpu(j, i); } @@ -65,7 +67,8 @@ static int show_stat(struct seq_file *p, void *v) } sum += arch_irq_stat(); - seq_printf(p, "cpu %llu %llu %llu %llu %llu %llu %llu %llu %llu\n", + seq_printf(p, "cpu %llu %llu %llu %llu %llu %llu %llu %llu %llu " + "%llu\n", (unsigned long long)cputime64_to_clock_t(user), (unsigned long long)cputime64_to_clock_t(nice), (unsigned long long)cputime64_to_clock_t(system), @@ -74,7 +77,8 @@ static int show_stat(struct seq_file *p, void *v) (unsigned long long)cputime64_to_clock_t(irq), (unsigned long long)cputime64_to_clock_t(softirq), (unsigned long long)cputime64_to_clock_t(steal), - (unsigned long long)cputime64_to_clock_t(guest)); + (unsigned long long)cputime64_to_clock_t(guest), + (unsigned long long)cputime64_to_clock_t(guest_nice)); for_each_online_cpu(i) { /* Copy values here to work around gcc-2.95.3, gcc-2.96 */ @@ -88,8 +92,10 @@ static int show_stat(struct seq_file *p, void *v) softirq = kstat_cpu(i).cpustat.softirq; steal = kstat_cpu(i).cpustat.steal; guest = kstat_cpu(i).cpustat.guest; + guest_nice = kstat_cpu(i).cpustat.guest_nice; seq_printf(p, - "cpu%d %llu %llu %llu %llu %llu %llu %llu %llu %llu\n", + "cpu%d %llu %llu %llu %llu %llu %llu %llu %llu %llu " + "%llu\n", i, (unsigned long long)cputime64_to_clock_t(user), (unsigned long long)cputime64_to_clock_t(nice), @@ -99,7 +105,8 @@ static int show_stat(struct seq_file *p, void *v) (unsigned long long)cputime64_to_clock_t(irq), (unsigned long long)cputime64_to_clock_t(softirq), (unsigned long long)cputime64_to_clock_t(steal), - (unsigned long long)cputime64_to_clock_t(guest)); + (unsigned long long)cputime64_to_clock_t(guest), + (unsigned long long)cputime64_to_clock_t(guest_nice)); } seq_printf(p, "intr %llu", (unsigned long long)sum); diff --git a/include/linux/jiffies.h b/include/linux/jiffies.h index 1a9cf78bfce..6811f4bfc6e 100644 --- a/include/linux/jiffies.h +++ b/include/linux/jiffies.h @@ -307,6 +307,7 @@ extern clock_t jiffies_to_clock_t(long x); extern unsigned long clock_t_to_jiffies(unsigned long x); extern u64 jiffies_64_to_clock_t(u64 x); extern u64 nsec_to_clock_t(u64 x); +extern unsigned long nsecs_to_jiffies(u64 n); #define TIMESTAMP_SIZE 30 diff --git a/include/linux/kernel_stat.h b/include/linux/kernel_stat.h index 348fa8874b5..c059044bc6d 100644 --- a/include/linux/kernel_stat.h +++ b/include/linux/kernel_stat.h @@ -25,6 +25,7 @@ struct cpu_usage_stat { cputime64_t iowait; cputime64_t steal; cputime64_t guest; + cputime64_t guest_nice; }; struct kernel_stat { diff --git a/include/linux/preempt.h b/include/linux/preempt.h index 72b1a10a59b..2e681d9555b 100644 --- a/include/linux/preempt.h +++ b/include/linux/preempt.h @@ -105,6 +105,11 @@ struct preempt_notifier; * @sched_out: we've just been preempted * notifier: struct preempt_notifier for the task being preempted * next: the task that's kicking us out + * + * Please note that sched_in and out are called under different + * contexts. sched_out is called with rq lock held and irq disabled + * while sched_in is called without rq lock and irq enabled. This + * difference is intentional and depended upon by its users. */ struct preempt_ops { void (*sched_in)(struct preempt_notifier *notifier, int cpu); diff --git a/include/linux/sched.h b/include/linux/sched.h index 882dc48163b..89115ec7d43 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -145,7 +145,6 @@ extern unsigned long this_cpu_load(void); extern void calc_global_load(void); -extern u64 cpu_nr_migrations(int cpu); extern unsigned long get_parent_ip(unsigned long addr); @@ -171,8 +170,6 @@ print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq) } #endif -extern unsigned long long time_sync_thresh; - /* * Task state bitmask. NOTE! These bits are also * encoded in fs/proc/array.c: get_task_state(). @@ -349,7 +346,6 @@ extern signed long schedule_timeout(signed long timeout); extern signed long schedule_timeout_interruptible(signed long timeout); extern signed long schedule_timeout_killable(signed long timeout); extern signed long schedule_timeout_uninterruptible(signed long timeout); -asmlinkage void __schedule(void); asmlinkage void schedule(void); extern int mutex_spin_on_owner(struct mutex *lock, struct thread_info *owner); @@ -628,6 +624,9 @@ struct signal_struct { cputime_t utime, stime, cutime, cstime; cputime_t gtime; cputime_t cgtime; +#ifndef CONFIG_VIRT_CPU_ACCOUNTING + cputime_t prev_utime, prev_stime; +#endif unsigned long nvcsw, nivcsw, cnvcsw, cnivcsw; unsigned long min_flt, maj_flt, cmin_flt, cmaj_flt; unsigned long inblock, oublock, cinblock, coublock; @@ -1013,9 +1012,13 @@ static inline struct cpumask *sched_domain_span(struct sched_domain *sd) return to_cpumask(sd->span); } -extern void partition_sched_domains(int ndoms_new, struct cpumask *doms_new, +extern void partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[], struct sched_domain_attr *dattr_new); +/* Allocate an array of sched domains, for partition_sched_domains(). */ +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) { @@ -1033,7 +1036,7 @@ unsigned long default_scale_smt_power(struct sched_domain *sd, int cpu); struct sched_domain_attr; static inline void -partition_sched_domains(int ndoms_new, struct cpumask *doms_new, +partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[], struct sched_domain_attr *dattr_new) { } @@ -1331,7 +1334,9 @@ struct task_struct { cputime_t utime, stime, utimescaled, stimescaled; cputime_t gtime; +#ifndef CONFIG_VIRT_CPU_ACCOUNTING cputime_t prev_utime, prev_stime; +#endif unsigned long nvcsw, nivcsw; /* context switch counts */ struct timespec start_time; /* monotonic time */ struct timespec real_start_time; /* boot based time */ @@ -1720,9 +1725,8 @@ static inline void put_task_struct(struct task_struct *t) __put_task_struct(t); } -extern cputime_t task_utime(struct task_struct *p); -extern cputime_t task_stime(struct task_struct *p); -extern cputime_t task_gtime(struct task_struct *p); +extern void task_times(struct task_struct *p, cputime_t *ut, cputime_t *st); +extern void thread_group_times(struct task_struct *p, cputime_t *ut, cputime_t *st); /* * Per process flags diff --git a/kernel/cpuset.c b/kernel/cpuset.c index b5cb469d254..3cf2183b472 100644 --- a/kernel/cpuset.c +++ b/kernel/cpuset.c @@ -537,8 +537,7 @@ update_domain_attr_tree(struct sched_domain_attr *dattr, struct cpuset *c) * element of the partition (one sched domain) to be passed to * partition_sched_domains(). */ -/* FIXME: see the FIXME in partition_sched_domains() */ -static int generate_sched_domains(struct cpumask **domains, +static int generate_sched_domains(cpumask_var_t **domains, struct sched_domain_attr **attributes) { LIST_HEAD(q); /* queue of cpusets to be scanned */ @@ -546,7 +545,7 @@ static int generate_sched_domains(struct cpumask **domains, struct cpuset **csa; /* array of all cpuset ptrs */ int csn; /* how many cpuset ptrs in csa so far */ int i, j, k; /* indices for partition finding loops */ - struct cpumask *doms; /* resulting partition; i.e. sched domains */ + cpumask_var_t *doms; /* resulting partition; i.e. sched domains */ struct sched_domain_attr *dattr; /* attributes for custom domains */ int ndoms = 0; /* number of sched domains in result */ int nslot; /* next empty doms[] struct cpumask slot */ @@ -557,7 +556,8 @@ static int generate_sched_domains(struct cpumask **domains, /* Special case for the 99% of systems with one, full, sched domain */ if (is_sched_load_balance(&top_cpuset)) { - doms = kmalloc(cpumask_size(), GFP_KERNEL); + ndoms = 1; + doms = alloc_sched_domains(ndoms); if (!doms) goto done; @@ -566,9 +566,8 @@ static int generate_sched_domains(struct cpumask **domains, *dattr = SD_ATTR_INIT; update_domain_attr_tree(dattr, &top_cpuset); } - cpumask_copy(doms, top_cpuset.cpus_allowed); + cpumask_copy(doms[0], top_cpuset.cpus_allowed); - ndoms = 1; goto done; } @@ -636,7 +635,7 @@ restart: * Now we know how many domains to create. * Convert <csn, csa> to <ndoms, doms> and populate cpu masks. */ - doms = kmalloc(ndoms * cpumask_size(), GFP_KERNEL); + doms = alloc_sched_domains(ndoms); if (!doms) goto done; @@ -656,7 +655,7 @@ restart: continue; } - dp = doms + nslot; + dp = doms[nslot]; if (nslot == ndoms) { static int warnings = 10; @@ -718,7 +717,7 @@ done: static void do_rebuild_sched_domains(struct work_struct *unused) { struct sched_domain_attr *attr; - struct cpumask *doms; + cpumask_var_t *doms; int ndoms; get_online_cpus(); @@ -2052,7 +2051,7 @@ static int cpuset_track_online_cpus(struct notifier_block *unused_nb, unsigned long phase, void *unused_cpu) { struct sched_domain_attr *attr; - struct cpumask *doms; + cpumask_var_t *doms; int ndoms; switch (phase) { @@ -2537,15 +2536,9 @@ const struct file_operations proc_cpuset_operations = { }; #endif /* CONFIG_PROC_PID_CPUSET */ -/* Display task cpus_allowed, mems_allowed in /proc/<pid>/status file. */ +/* Display task mems_allowed in /proc/<pid>/status file. */ void cpuset_task_status_allowed(struct seq_file *m, struct task_struct *task) { - seq_printf(m, "Cpus_allowed:\t"); - seq_cpumask(m, &task->cpus_allowed); - seq_printf(m, "\n"); - seq_printf(m, "Cpus_allowed_list:\t"); - seq_cpumask_list(m, &task->cpus_allowed); - seq_printf(m, "\n"); seq_printf(m, "Mems_allowed:\t"); seq_nodemask(m, &task->mems_allowed); seq_printf(m, "\n"); diff --git a/kernel/exit.c b/kernel/exit.c index 3f45e3cf931..80ae941cfd2 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -111,9 +111,9 @@ static void __exit_signal(struct task_struct *tsk) * We won't ever get here for the group leader, since it * will have been the last reference on the signal_struct. */ - sig->utime = cputime_add(sig->utime, task_utime(tsk)); - sig->stime = cputime_add(sig->stime, task_stime(tsk)); - sig->gtime = cputime_add(sig->gtime, task_gtime(tsk)); + sig->utime = cputime_add(sig->utime, tsk->utime); + sig->stime = cputime_add(sig->stime, tsk->stime); + sig->gtime = cputime_add(sig->gtime, tsk->gtime); sig->min_flt += tsk->min_flt; sig->maj_flt += tsk->maj_flt; sig->nvcsw += tsk->nvcsw; @@ -1210,6 +1210,7 @@ static int wait_task_zombie(struct wait_opts *wo, struct task_struct *p) struct signal_struct *psig; struct signal_struct *sig; unsigned long maxrss; + cputime_t tgutime, tgstime; /* * The resource counters for the group leader are in its @@ -1225,20 +1226,23 @@ static int wait_task_zombie(struct wait_opts *wo, struct task_struct *p) * need to protect the access to parent->signal fields, * as other threads in the parent group can be right * here reaping other children at the same time. + * + * We use thread_group_times() to get times for the thread + * group, which consolidates times for all threads in the + * group including the group leader. */ + thread_group_times(p, &tgutime, &tgstime); spin_lock_irq(&p->real_parent->sighand->siglock); psig = p->real_parent->signal; sig = p->signal; psig->cutime = cputime_add(psig->cutime, - cputime_add(p->utime, - cputime_add(sig->utime, - sig->cutime))); + cputime_add(tgutime, + sig->cutime)); psig->cstime = cputime_add(psig->cstime, - cputime_add(p->stime, - cputime_add(sig->stime, - sig->cstime))); + cputime_add(tgstime, + sig->cstime)); psig->cgtime = cputime_add(psig->cgtime, cputime_add(p->gtime, diff --git a/kernel/fork.c b/kernel/fork.c index 166b8c49257..3d6f121bbe8 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -884,6 +884,9 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk) sig->utime = sig->stime = sig->cutime = sig->cstime = cputime_zero; sig->gtime = cputime_zero; sig->cgtime = cputime_zero; +#ifndef CONFIG_VIRT_CPU_ACCOUNTING + sig->prev_utime = sig->prev_stime = cputime_zero; +#endif sig->nvcsw = sig->nivcsw = sig->cnvcsw = sig->cnivcsw = 0; sig->min_flt = sig->maj_flt = sig->cmin_flt = sig->cmaj_flt = 0; sig->inblock = sig->oublock = sig->cinblock = sig->coublock = 0; @@ -1066,8 +1069,10 @@ static struct task_struct *copy_process(unsigned long clone_flags, p->gtime = cputime_zero; p->utimescaled = cputime_zero; p->stimescaled = cputime_zero; +#ifndef CONFIG_VIRT_CPU_ACCOUNTING p->prev_utime = cputime_zero; p->prev_stime = cputime_zero; +#endif p->default_timer_slack_ns = current->timer_slack_ns; diff --git a/kernel/kgdb.c b/kernel/kgdb.c index 9147a3190c9..7d701463402 100644 --- a/kernel/kgdb.c +++ b/kernel/kgdb.c @@ -870,7 +870,7 @@ static void gdb_cmd_getregs(struct kgdb_state *ks) /* * All threads that don't have debuggerinfo should be - * in __schedule() sleeping, since all other CPUs + * in schedule() sleeping, since all other CPUs * are in kgdb_wait, and thus have debuggerinfo. */ if (local_debuggerinfo) { diff --git a/kernel/sched.c b/kernel/sched.c index 6ae2739b8f1..aa31244caa9 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -535,14 +535,12 @@ struct rq { #define CPU_LOAD_IDX_MAX 5 unsigned long cpu_load[CPU_LOAD_IDX_MAX]; #ifdef CONFIG_NO_HZ - unsigned long last_tick_seen; unsigned char in_nohz_recently; #endif /* capture load from *all* tasks on this cpu: */ struct load_weight load; unsigned long nr_load_updates; u64 nr_switches; - u64 nr_migrations_in; struct cfs_rq cfs; struct rt_rq rt; @@ -591,6 +589,8 @@ struct rq { u64 rt_avg; u64 age_stamp; + u64 idle_stamp; + u64 avg_idle; #endif /* calc_load related fields */ @@ -772,7 +772,7 @@ sched_feat_write(struct file *filp, const char __user *ubuf, if (!sched_feat_names[i]) return -EINVAL; - filp->f_pos += cnt; + *ppos += cnt; return cnt; } @@ -2017,6 +2017,7 @@ void kthread_bind(struct task_struct *p, unsigned int cpu) } spin_lock_irqsave(&rq->lock, flags); + update_rq_clock(rq); set_task_cpu(p, cpu); p->cpus_allowed = cpumask_of_cpu(cpu); p->rt.nr_cpus_allowed = 1; @@ -2078,7 +2079,6 @@ void set_task_cpu(struct task_struct *p, unsigned int new_cpu) #endif if (old_cpu != new_cpu) { p->se.nr_migrations++; - new_rq->nr_migrations_in++; #ifdef CONFIG_SCHEDSTATS if (task_hot(p, old_rq->clock, NULL)) schedstat_inc(p, se.nr_forced2_migrations); @@ -2115,6 +2115,7 @@ migrate_task(struct task_struct *p, int dest_cpu, struct migration_req *req) * it is sufficient to simply update the task's cpu field. */ if (!p->se.on_rq && !task_running(rq, p)) { + update_rq_clock(rq); set_task_cpu(p, dest_cpu); return 0; } @@ -2376,14 +2377,15 @@ static int try_to_wake_up(struct task_struct *p, unsigned int state, task_rq_unlock(rq, &flags); cpu = p->sched_class->select_task_rq(p, SD_BALANCE_WAKE, wake_flags); - if (cpu != orig_cpu) + if (cpu != orig_cpu) { + local_irq_save(flags); + rq = cpu_rq(cpu); + update_rq_clock(rq); set_task_cpu(p, cpu); - + local_irq_restore(flags); + } rq = task_rq_lock(p, &flags); - if (rq != orig_rq) - update_rq_clock(rq); - WARN_ON(p->state != TASK_WAKING); cpu = task_cpu(p); @@ -2440,6 +2442,17 @@ out_running: #ifdef CONFIG_SMP if (p->sched_class->task_wake_up) p->sched_class->task_wake_up(rq, p); + + if (unlikely(rq->idle_stamp)) { + u64 delta = rq->clock - rq->idle_stamp; + u64 max = 2*sysctl_sched_migration_cost; + + if (delta > max) + rq->avg_idle = max; + else + update_avg(&rq->avg_idle, delta); + rq->idle_stamp = 0; + } #endif out: task_rq_unlock(rq, &flags); @@ -2545,6 +2558,7 @@ static void __sched_fork(struct task_struct *p) void sched_fork(struct task_struct *p, int clone_flags) { int cpu = get_cpu(); + unsigned long flags; __sched_fork(p); @@ -2581,7 +2595,10 @@ void sched_fork(struct task_struct *p, int clone_flags) #ifdef CONFIG_SMP cpu = p->sched_class->select_task_rq(p, SD_BALANCE_FORK, 0); #endif + local_irq_save(flags); + update_rq_clock(cpu_rq(cpu)); set_task_cpu(p, cpu); + local_irq_restore(flags); #if defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT) if (likely(sched_info_on())) @@ -2848,14 +2865,14 @@ context_switch(struct rq *rq, struct task_struct *prev, */ arch_start_context_switch(prev); - if (unlikely(!mm)) { + if (likely(!mm)) { next->active_mm = oldmm; atomic_inc(&oldmm->mm_count); enter_lazy_tlb(oldmm, next); } else switch_mm(oldmm, mm, next); - if (unlikely(!prev->mm)) { + if (likely(!prev->mm)) { prev->active_mm = NULL; rq->prev_mm = oldmm; } @@ -3018,15 +3035,6 @@ static void calc_load_account_active(struct rq *this_rq) } /* - * Externally visible per-cpu scheduler statistics: - * cpu_nr_migrations(cpu) - number of migrations into that cpu - */ -u64 cpu_nr_migrations(int cpu) -{ - return cpu_rq(cpu)->nr_migrations_in; -} - -/* * Update rq->cpu_load[] statistics. This function is usually called every * scheduler tick (TICK_NSEC). */ @@ -4126,7 +4134,7 @@ static int load_balance(int this_cpu, struct rq *this_rq, unsigned long flags; struct cpumask *cpus = __get_cpu_var(load_balance_tmpmask); - cpumask_setall(cpus); + cpumask_copy(cpus, cpu_online_mask); /* * When power savings policy is enabled for the parent domain, idle @@ -4289,7 +4297,7 @@ load_balance_newidle(int this_cpu, struct rq *this_rq, struct sched_domain *sd) int all_pinned = 0; struct cpumask *cpus = __get_cpu_var(load_balance_tmpmask); - cpumask_setall(cpus); + cpumask_copy(cpus, cpu_online_mask); /* * When power savings policy is enabled for the parent domain, idle @@ -4429,6 +4437,11 @@ static void idle_balance(int this_cpu, struct rq *this_rq) int pulled_task = 0; unsigned long next_balance = jiffies + HZ; + this_rq->idle_stamp = this_rq->clock; + + if (this_rq->avg_idle < sysctl_sched_migration_cost) + return; + for_each_domain(this_cpu, sd) { unsigned long interval; @@ -4443,8 +4456,10 @@ static void idle_balance(int this_cpu, struct rq *this_rq) interval = msecs_to_jiffies(sd->balance_interval); if (time_after(next_balance, sd->last_balance + interval)) next_balance = sd->last_balance + interval; - if (pulled_task) + if (pulled_task) { + this_rq->idle_stamp = 0; break; + } } if (pulled_task || time_after(jiffies, this_rq->next_balance)) { /* @@ -5046,8 +5061,13 @@ static void account_guest_time(struct task_struct *p, cputime_t cputime, p->gtime = cputime_add(p->gtime, cputime); /* Add guest time to cpustat. */ - cpustat->user = cputime64_add(cpustat->user, tmp); - cpustat->guest = cputime64_add(cpustat->guest, tmp); + if (TASK_NICE(p) > 0) { + cpustat->nice = cputime64_add(cpustat->nice, tmp); + cpustat->guest_nice = cputime64_add(cpustat->guest_nice, tmp); + } else { + cpustat->user = cputime64_add(cpustat->user, tmp); + cpustat->guest = cputime64_add(cpustat->guest, tmp); + } } /* @@ -5162,60 +5182,86 @@ void account_idle_ticks(unsigned long ticks) * Use precise platform statistics if available: */ #ifdef CONFIG_VIRT_CPU_ACCOUNTING -cputime_t task_utime(struct task_struct *p) +void task_times(struct task_struct *p, cputime_t *ut, cputime_t *st) { - return p->utime; + *ut = p->utime; + *st = p->stime; } -cputime_t task_stime(struct task_struct *p) +void thread_group_times(struct task_struct *p, cputime_t *ut, cputime_t *st) { - return p->stime; + struct task_cputime cputime; + + thread_group_cputime(p, &cputime); + + *ut = cputime.utime; + *st = cputime.stime; } #else -cputime_t task_utime(struct task_struct *p) + +#ifndef nsecs_to_cputime +# define nsecs_to_cputime(__nsecs) nsecs_to_jiffies(__nsecs) +#endif + +void task_times(struct task_struct *p, cputime_t *ut, cputime_t *st) { - clock_t utime = cputime_to_clock_t(p->utime), - total = utime + cputime_to_clock_t(p->stime); - u64 temp; + cputime_t rtime, utime = p->utime, total = cputime_add(utime, p->stime); /* * Use CFS's precise accounting: */ - temp = (u64)nsec_to_clock_t(p->se.sum_exec_runtime); + rtime = nsecs_to_cputime(p->se.sum_exec_runtime); if (total) { - temp *= utime; + u64 temp; + + temp = (u64)(rtime * utime); do_div(temp, total); - } - utime = (clock_t)temp; + utime = (cputime_t)temp; + } else + utime = rtime; + + /* + * Compare with previous values, to keep monotonicity: + */ + p->prev_utime = max(p->prev_utime, utime); + p->prev_stime = max(p->prev_stime, cputime_sub(rtime, p->prev_utime)); - p->prev_utime = max(p->prev_utime, clock_t_to_cputime(utime)); - return p->prev_utime; + *ut = p->prev_utime; + *st = p->prev_stime; } -cputime_t task_stime(struct task_struct *p) +/* + * Must be called with siglock held. + */ +void thread_group_times(struct task_struct *p, cputime_t *ut, cputime_t *st) { - clock_t stime; + struct signal_struct *sig = p->signal; + struct task_cputime cputime; + cputime_t rtime, utime, total; - /* - * Use CFS's precise accounting. (we subtract utime from - * the total, to make sure the total observed by userspace - * grows monotonically - apps rely on that): - */ - stime = nsec_to_clock_t(p->se.sum_exec_runtime) - - cputime_to_clock_t(task_utime(p)); + thread_group_cputime(p, &cputime); - if (stime >= 0) - p->prev_stime = max(p->prev_stime, clock_t_to_cputime(stime)); + total = cputime_add(cputime.utime, cputime.stime); + rtime = nsecs_to_cputime(cputime.sum_exec_runtime); - return p->prev_stime; -} -#endif + if (total) { + u64 temp; -inline cputime_t task_gtime(struct task_struct *p) -{ - return p->gtime; + temp = (u64)(rtime * cputime.utime); + do_div(temp, total); + utime = (cputime_t)temp; + } else + utime = rtime; + + sig->prev_utime = max(sig->prev_utime, utime); + sig->prev_stime = max(sig->prev_stime, + cputime_sub(rtime, sig->prev_utime)); + + *ut = sig->prev_utime; + *st = sig->prev_stime; } +#endif /* * This function gets called by the timer code, with HZ frequency. @@ -6175,22 +6221,14 @@ __setscheduler(struct rq *rq, struct task_struct *p, int policy, int prio) BUG_ON(p->se.on_rq); p->policy = policy; - switch (p->policy) { - case SCHED_NORMAL: - case SCHED_BATCH: - case SCHED_IDLE: - p->sched_class = &fair_sched_class; - break; - case SCHED_FIFO: - case SCHED_RR: - p->sched_class = &rt_sched_class; - break; - } - p->rt_priority = prio; p->normal_prio = normal_prio(p); /* we are holding p->pi_lock already */ p->prio = rt_mutex_getprio(p); + if (rt_prio(p->prio)) + p->sched_class = &rt_sched_class; + else + p->sched_class = &fair_sched_class; set_load_weight(p); } @@ -6935,7 +6973,7 @@ void show_state_filter(unsigned long state_filter) /* * Only show locks if all tasks are dumped: */ - if (state_filter == -1) + if (!state_filter) debug_show_all_locks(); } @@ -7740,6 +7778,16 @@ early_initcall(migration_init); #ifdef CONFIG_SCHED_DEBUG +static __read_mostly int sched_domain_debug_enabled; + +static int __init sched_domain_debug_setup(char *str) +{ + sched_domain_debug_enabled = 1; + + return 0; +} +early_param("sched_debug", sched_domain_debug_setup); + static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level, struct cpumask *groupmask) { @@ -7826,6 +7874,9 @@ static void sched_domain_debug(struct sched_domain *sd, int cpu) cpumask_var_t groupmask; int level = 0; + if (!sched_domain_debug_enabled) + return; + if (!sd) { printk(KERN_DEBUG "CPU%d attaching NULL sched-domain.\n", cpu); return; @@ -7905,6 +7956,8 @@ sd_parent_degenerate(struct sched_domain *sd, struct sched_domain *parent) static void free_rootdomain(struct root_domain *rd) { + synchronize_sched(); + cpupri_cleanup(&rd->cpupri); free_cpumask_var(rd->rto_mask); @@ -8045,6 +8098,7 @@ static cpumask_var_t cpu_isolated_map; /* Setup the mask of cpus configured for isolated domains */ static int __init isolated_cpu_setup(char *str) { + alloc_bootmem_cpumask_var(&cpu_isolated_map); cpulist_parse(str, cpu_isolated_map); return 1; } @@ -8881,7 +8935,7 @@ static int build_sched_domains(const struct cpumask *cpu_map) return __build_sched_domains(cpu_map, NULL); } -static struct cpumask *doms_cur; /* current sched domains */ +static cpumask_var_t *doms_cur; /* current sched domains */ static int ndoms_cur; /* number of sched domains in 'doms_cur' */ static struct sched_domain_attr *dattr_cur; /* attribues of custom domains in 'doms_cur' */ @@ -8903,6 +8957,31 @@ int __attribute__((weak)) arch_update_cpu_topology(void) return 0; } +cpumask_var_t *alloc_sched_domains(unsigned int ndoms) +{ + int i; + cpumask_var_t *doms; + + do |