Merge branch 'sched/urgent'; commit 'v2.6.29-rc5' into sched/core

This commit is contained in:
Ingo Molnar 2009-02-15 21:15:16 +01:00
commit 5274f8354d
233 changed files with 15577 additions and 11029 deletions

View file

@ -2351,7 +2351,7 @@ static void cgroup_lock_hierarchy(struct cgroupfs_root *root)
for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
struct cgroup_subsys *ss = subsys[i];
if (ss->root == root)
mutex_lock_nested(&ss->hierarchy_mutex, i);
mutex_lock(&ss->hierarchy_mutex);
}
}
@ -2637,6 +2637,7 @@ static void __init cgroup_init_subsys(struct cgroup_subsys *ss)
BUG_ON(!list_empty(&init_task.tasks));
mutex_init(&ss->hierarchy_mutex);
lockdep_set_class(&ss->hierarchy_mutex, &ss->subsys_key);
ss->active = 1;
}

View file

@ -118,6 +118,8 @@ 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->min_flt += tsk->min_flt;
sig->maj_flt += tsk->maj_flt;
@ -126,6 +128,7 @@ static void __exit_signal(struct task_struct *tsk)
sig->inblock += task_io_get_inblock(tsk);
sig->oublock += task_io_get_oublock(tsk);
task_io_accounting_add(&sig->ioac, &tsk->ioac);
sig->sum_sched_runtime += tsk->se.sum_exec_runtime;
sig = NULL; /* Marker for below. */
}

View file

@ -851,13 +851,14 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk)
sig->tty_old_pgrp = NULL;
sig->tty = NULL;
sig->cutime = sig->cstime = cputime_zero;
sig->utime = sig->stime = sig->cutime = sig->cstime = cputime_zero;
sig->gtime = cputime_zero;
sig->cgtime = cputime_zero;
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;
task_io_accounting_init(&sig->ioac);
sig->sum_sched_runtime = 0;
taskstats_tgid_init(sig);
task_lock(current->group_leader);
@ -1094,7 +1095,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
#ifdef CONFIG_DEBUG_MUTEXES
p->blocked_on = NULL; /* not blocked yet */
#endif
if (unlikely(ptrace_reparented(current)))
if (unlikely(current->ptrace))
ptrace_fork(p, clone_flags);
/* Perform scheduler related setup. Assign this task to a CPU. */

View file

@ -62,7 +62,7 @@ int do_getitimer(int which, struct itimerval *value)
struct task_cputime cputime;
cputime_t utime;
thread_group_cputime(tsk, &cputime);
thread_group_cputimer(tsk, &cputime);
utime = cputime.utime;
if (cputime_le(cval, utime)) { /* about to fire */
cval = jiffies_to_cputime(1);
@ -82,7 +82,7 @@ int do_getitimer(int which, struct itimerval *value)
struct task_cputime times;
cputime_t ptime;
thread_group_cputime(tsk, &times);
thread_group_cputimer(tsk, &times);
ptime = cputime_add(times.utime, times.stime);
if (cputime_le(cval, ptime)) { /* about to fire */
cval = jiffies_to_cputime(1);

View file

@ -230,6 +230,71 @@ static int cpu_clock_sample(const clockid_t which_clock, struct task_struct *p,
return 0;
}
void thread_group_cputime(struct task_struct *tsk, struct task_cputime *times)
{
struct sighand_struct *sighand;
struct signal_struct *sig;
struct task_struct *t;
*times = INIT_CPUTIME;
rcu_read_lock();
sighand = rcu_dereference(tsk->sighand);
if (!sighand)
goto out;
sig = tsk->signal;
t = tsk;
do {
times->utime = cputime_add(times->utime, t->utime);
times->stime = cputime_add(times->stime, t->stime);
times->sum_exec_runtime += t->se.sum_exec_runtime;
t = next_thread(t);
} while (t != tsk);
times->utime = cputime_add(times->utime, sig->utime);
times->stime = cputime_add(times->stime, sig->stime);
times->sum_exec_runtime += sig->sum_sched_runtime;
out:
rcu_read_unlock();
}
static void update_gt_cputime(struct task_cputime *a, struct task_cputime *b)
{
if (cputime_gt(b->utime, a->utime))
a->utime = b->utime;
if (cputime_gt(b->stime, a->stime))
a->stime = b->stime;
if (b->sum_exec_runtime > a->sum_exec_runtime)
a->sum_exec_runtime = b->sum_exec_runtime;
}
void thread_group_cputimer(struct task_struct *tsk, struct task_cputime *times)
{
struct thread_group_cputimer *cputimer = &tsk->signal->cputimer;
struct task_cputime sum;
unsigned long flags;
spin_lock_irqsave(&cputimer->lock, flags);
if (!cputimer->running) {
cputimer->running = 1;
/*
* The POSIX timer interface allows for absolute time expiry
* values through the TIMER_ABSTIME flag, therefore we have
* to synchronize the timer to the clock every time we start
* it.
*/
thread_group_cputime(tsk, &sum);
update_gt_cputime(&cputimer->cputime, &sum);
}
*times = cputimer->cputime;
spin_unlock_irqrestore(&cputimer->lock, flags);
}
/*
* Sample a process (thread group) clock for the given group_leader task.
* Must be called with tasklist_lock held for reading.
@ -457,7 +522,7 @@ void posix_cpu_timers_exit_group(struct task_struct *tsk)
{
struct task_cputime cputime;
thread_group_cputime(tsk, &cputime);
thread_group_cputimer(tsk, &cputime);
cleanup_timers(tsk->signal->cpu_timers,
cputime.utime, cputime.stime, cputime.sum_exec_runtime);
}
@ -964,6 +1029,19 @@ static void check_thread_timers(struct task_struct *tsk,
}
}
static void stop_process_timers(struct task_struct *tsk)
{
struct thread_group_cputimer *cputimer = &tsk->signal->cputimer;
unsigned long flags;
if (!cputimer->running)
return;
spin_lock_irqsave(&cputimer->lock, flags);
cputimer->running = 0;
spin_unlock_irqrestore(&cputimer->lock, flags);
}
/*
* Check for any per-thread CPU timers that have fired and move them
* off the tsk->*_timers list onto the firing list. Per-thread timers
@ -987,13 +1065,15 @@ static void check_process_timers(struct task_struct *tsk,
sig->rlim[RLIMIT_CPU].rlim_cur == RLIM_INFINITY &&
list_empty(&timers[CPUCLOCK_VIRT]) &&
cputime_eq(sig->it_virt_expires, cputime_zero) &&
list_empty(&timers[CPUCLOCK_SCHED]))
list_empty(&timers[CPUCLOCK_SCHED])) {
stop_process_timers(tsk);
return;
}
/*
* Collect the current process totals.
*/
thread_group_cputime(tsk, &cputime);
thread_group_cputimer(tsk, &cputime);
utime = cputime.utime;
ptime = cputime_add(utime, cputime.stime);
sum_sched_runtime = cputime.sum_exec_runtime;
@ -1259,7 +1339,7 @@ static inline int fastpath_timer_check(struct task_struct *tsk)
if (!task_cputime_zero(&sig->cputime_expires)) {
struct task_cputime group_sample;
thread_group_cputime(tsk, &group_sample);
thread_group_cputimer(tsk, &group_sample);
if (task_cputime_expired(&group_sample, &sig->cputime_expires))
return 1;
}
@ -1328,6 +1408,33 @@ void run_posix_cpu_timers(struct task_struct *tsk)
}
}
/*
* Sample a process (thread group) timer for the given group_leader task.
* Must be called with tasklist_lock held for reading.
*/
static int cpu_timer_sample_group(const clockid_t which_clock,
struct task_struct *p,
union cpu_time_count *cpu)
{
struct task_cputime cputime;
thread_group_cputimer(p, &cputime);
switch (CPUCLOCK_WHICH(which_clock)) {
default:
return -EINVAL;
case CPUCLOCK_PROF:
cpu->cpu = cputime_add(cputime.utime, cputime.stime);
break;
case CPUCLOCK_VIRT:
cpu->cpu = cputime.utime;
break;
case CPUCLOCK_SCHED:
cpu->sched = cputime.sum_exec_runtime + task_delta_exec(p);
break;
}
return 0;
}
/*
* Set one of the process-wide special case CPU timers.
* The tsk->sighand->siglock must be held by the caller.
@ -1341,7 +1448,7 @@ void set_process_cpu_timer(struct task_struct *tsk, unsigned int clock_idx,
struct list_head *head;
BUG_ON(clock_idx == CPUCLOCK_SCHED);
cpu_clock_sample_group(clock_idx, tsk, &now);
cpu_timer_sample_group(clock_idx, tsk, &now);
if (oldval) {
if (!cputime_eq(*oldval, cputime_zero)) {

View file

@ -114,12 +114,15 @@ int __ref profile_init(void)
if (!slab_is_available()) {
prof_buffer = alloc_bootmem(buffer_bytes);
alloc_bootmem_cpumask_var(&prof_cpu_mask);
cpumask_copy(prof_cpu_mask, cpu_possible_mask);
return 0;
}
if (!alloc_cpumask_var(&prof_cpu_mask, GFP_KERNEL))
return -ENOMEM;
cpumask_copy(prof_cpu_mask, cpu_possible_mask);
prof_buffer = kzalloc(buffer_bytes, GFP_KERNEL);
if (prof_buffer)
return 0;

View file

@ -2317,16 +2317,6 @@ static int try_to_wake_up(struct task_struct *p, unsigned int state, int sync)
if (!sched_feat(SYNC_WAKEUPS))
sync = 0;
if (!sync) {
if (current->se.avg_overlap < sysctl_sched_migration_cost &&
p->se.avg_overlap < sysctl_sched_migration_cost)
sync = 1;
} else {
if (current->se.avg_overlap >= sysctl_sched_migration_cost ||
p->se.avg_overlap >= sysctl_sched_migration_cost)
sync = 0;
}
#ifdef CONFIG_SMP
if (sched_feat(LB_WAKEUP_UPDATE)) {
struct sched_domain *sd;
@ -7045,20 +7035,26 @@ static void free_rootdomain(struct root_domain *rd)
static void rq_attach_root(struct rq *rq, struct root_domain *rd)
{
struct root_domain *old_rd = NULL;
unsigned long flags;
spin_lock_irqsave(&rq->lock, flags);
if (rq->rd) {
struct root_domain *old_rd = rq->rd;
old_rd = rq->rd;
if (cpumask_test_cpu(rq->cpu, old_rd->online))
set_rq_offline(rq);
cpumask_clear_cpu(rq->cpu, old_rd->span);
if (atomic_dec_and_test(&old_rd->refcount))
free_rootdomain(old_rd);
/*
* If we dont want to free the old_rt yet then
* set old_rd to NULL to skip the freeing later
* in this function:
*/
if (!atomic_dec_and_test(&old_rd->refcount))
old_rd = NULL;
}
atomic_inc(&rd->refcount);
@ -7069,6 +7065,9 @@ static void rq_attach_root(struct rq *rq, struct root_domain *rd)
set_rq_online(rq);
spin_unlock_irqrestore(&rq->lock, flags);
if (old_rd)
free_rootdomain(old_rd);
}
static int __init_refok init_rootdomain(struct root_domain *rd, bool bootmem)

View file

@ -1191,15 +1191,20 @@ wake_affine(struct sched_domain *this_sd, struct rq *this_rq,
int idx, unsigned long load, unsigned long this_load,
unsigned int imbalance)
{
struct task_struct *curr = this_rq->curr;
struct task_group *tg;
unsigned long tl = this_load;
unsigned long tl_per_task;
struct task_group *tg;
unsigned long weight;
int balanced;
if (!(this_sd->flags & SD_WAKE_AFFINE) || !sched_feat(AFFINE_WAKEUPS))
return 0;
if (sync && (curr->se.avg_overlap > sysctl_sched_migration_cost ||
p->se.avg_overlap > sysctl_sched_migration_cost))
sync = 0;
/*
* If sync wakeup then subtract the (maximum possible)
* effect of the currently running task from the load
@ -1473,7 +1478,9 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int sync)
if (!sched_feat(WAKEUP_PREEMPT))
return;
if (sched_feat(WAKEUP_OVERLAP) && sync) {
if (sched_feat(WAKEUP_OVERLAP) && (sync ||
(se->avg_overlap < sysctl_sched_migration_cost &&
pse->avg_overlap < sysctl_sched_migration_cost))) {
resched_task(curr);
return;
}

View file

@ -296,19 +296,21 @@ sched_info_switch(struct task_struct *prev, struct task_struct *next)
static inline void account_group_user_time(struct task_struct *tsk,
cputime_t cputime)
{
struct task_cputime *times;
struct signal_struct *sig;
struct thread_group_cputimer *cputimer;
/* tsk == current, ensure it is safe to use ->signal */
if (unlikely(tsk->exit_state))
return;
sig = tsk->signal;
times = &sig->cputime.totals;
cputimer = &tsk->signal->cputimer;
spin_lock(&times->lock);
times->utime = cputime_add(times->utime, cputime);
spin_unlock(&times->lock);
if (!cputimer->running)
return;
spin_lock(&cputimer->lock);
cputimer->cputime.utime =
cputime_add(cputimer->cputime.utime, cputime);
spin_unlock(&cputimer->lock);
}
/**
@ -324,19 +326,21 @@ static inline void account_group_user_time(struct task_struct *tsk,
static inline void account_group_system_time(struct task_struct *tsk,
cputime_t cputime)
{
struct task_cputime *times;
struct signal_struct *sig;
struct thread_group_cputimer *cputimer;
/* tsk == current, ensure it is safe to use ->signal */
if (unlikely(tsk->exit_state))
return;
sig = tsk->signal;
times = &sig->cputime.totals;
cputimer = &tsk->signal->cputimer;
spin_lock(&times->lock);
times->stime = cputime_add(times->stime, cputime);
spin_unlock(&times->lock);
if (!cputimer->running)
return;
spin_lock(&cputimer->lock);
cputimer->cputime.stime =
cputime_add(cputimer->cputime.stime, cputime);
spin_unlock(&cputimer->lock);
}
/**
@ -352,7 +356,7 @@ static inline void account_group_system_time(struct task_struct *tsk,
static inline void account_group_exec_runtime(struct task_struct *tsk,
unsigned long long ns)
{
struct task_cputime *times;
struct thread_group_cputimer *cputimer;
struct signal_struct *sig;
sig = tsk->signal;
@ -361,9 +365,12 @@ static inline void account_group_exec_runtime(struct task_struct *tsk,
if (unlikely(!sig))
return;
times = &sig->cputime.totals;
cputimer = &sig->cputimer;
spin_lock(&times->lock);
times->sum_exec_runtime += ns;
spin_unlock(&times->lock);
if (!cputimer->running)
return;
spin_lock(&cputimer->lock);
cputimer->cputime.sum_exec_runtime += ns;
spin_unlock(&cputimer->lock);
}

View file

@ -1367,7 +1367,6 @@ int do_notify_parent(struct task_struct *tsk, int sig)
struct siginfo info;
unsigned long flags;
struct sighand_struct *psig;
struct task_cputime cputime;
int ret = sig;
BUG_ON(sig == -1);
@ -1397,9 +1396,10 @@ int do_notify_parent(struct task_struct *tsk, int sig)
info.si_uid = __task_cred(tsk)->uid;
rcu_read_unlock();
thread_group_cputime(tsk, &cputime);
info.si_utime = cputime_to_jiffies(cputime.utime);
info.si_stime = cputime_to_jiffies(cputime.stime);
info.si_utime = cputime_to_clock_t(cputime_add(tsk->utime,
tsk->signal->utime));
info.si_stime = cputime_to_clock_t(cputime_add(tsk->stime,
tsk->signal->stime));
info.si_status = tsk->exit_code & 0x7f;
if (tsk->exit_code & 0x80)

View file

@ -101,6 +101,7 @@ static int two = 2;
static int zero;
static int one = 1;
static unsigned long one_ul = 1;
static int one_hundred = 100;
/* this is needed for the proc_dointvec_minmax for [fs_]overflow UID and GID */
@ -974,7 +975,7 @@ static struct ctl_table vm_table[] = {
.mode = 0644,
.proc_handler = &dirty_background_bytes_handler,
.strategy = &sysctl_intvec,
.extra1 = &one,
.extra1 = &one_ul,
},
{
.ctl_name = VM_DIRTY_RATIO,
@ -995,7 +996,7 @@ static struct ctl_table vm_table[] = {
.mode = 0644,
.proc_handler = &dirty_bytes_handler,
.strategy = &sysctl_intvec,
.extra1 = &one,
.extra1 = &one_ul,
},
{
.procname = "dirty_writeback_centisecs",

View file

@ -72,6 +72,7 @@ static void uid_hash_insert(struct user_struct *up, struct hlist_head *hashent)
static void uid_hash_remove(struct user_struct *up)
{
hlist_del_init(&up->uidhash_node);
put_user_ns(up->user_ns);
}
static struct user_struct *uid_hash_find(uid_t uid, struct hlist_head *hashent)
@ -334,7 +335,6 @@ static void free_user(struct user_struct *up, unsigned long flags)
atomic_inc(&up->__count);
spin_unlock_irqrestore(&uidhash_lock, flags);
put_user_ns(up->user_ns);
INIT_WORK(&up->work, remove_user_sysfs_dir);
schedule_work(&up->work);
}
@ -357,7 +357,6 @@ static void free_user(struct user_struct *up, unsigned long flags)
sched_destroy_user(up);
key_put(up->uid_keyring);
key_put(up->session_keyring);
put_user_ns(up->user_ns);
kmem_cache_free(uid_cachep, up);
}