extern void cpu_init (void);
extern void trap_init(void);
-extern void account_process_tick(struct task_struct *task, int user);
extern void update_process_times(int user);
extern void scheduler_tick(void);
(mm)->hiwater_vm = (mm)->total_vm; \
} while (0)
+#define get_mm_hiwater_rss(mm) max((mm)->hiwater_rss, get_mm_rss(mm))
+#define get_mm_hiwater_vm(mm) max((mm)->hiwater_vm, (mm)->total_vm)
+
extern void set_dumpable(struct mm_struct *mm, int value);
extern int get_dumpable(struct mm_struct *mm);
*/
struct rlimit rlim[RLIM_NLIMITS];
- /* keep the process-shared keyrings here so that they do the right
- * thing in threads created with CLONE_THREAD */
-#ifdef CONFIG_KEYS
- struct key *session_keyring; /* keyring inherited over fork */
- struct key *process_keyring; /* keyring private to this process */
-#endif
#ifdef CONFIG_BSD_PROCESS_ACCT
struct pacct_struct pacct; /* per-process accounting information */
#endif
/* Hash table maintenance information */
struct hlist_node uidhash_node;
uid_t uid;
+ struct user_namespace *user_ns;
#ifdef CONFIG_USER_SCHED
struct task_group *tg;
extern struct user_struct root_user;
#define INIT_USER (&root_user)
+
struct backing_dev_info;
struct reclaim_state;
struct sched_info {
/* cumulative counters */
unsigned long pcount; /* # of times run on this cpu */
- unsigned long long cpu_time, /* time spent on the cpu */
- run_delay; /* time spent waiting on a runqueue */
+ unsigned long long run_delay; /* time spent waiting on a runqueue */
/* timestamps */
unsigned long long last_arrival,/* when we last ran on a cpu */
extern void partition_sched_domains(int ndoms_new, struct cpumask *doms_new,
struct sched_domain_attr *dattr_new);
-extern int arch_reinit_sched_domains(void);
/* Test a flag in parent sched domain */
static inline int test_sd_parent(struct sched_domain *sd, int flag)
#endif /* !CONFIG_SMP */
struct io_context; /* See blkdev.h */
-#define NGROUPS_SMALL 32
-#define NGROUPS_PER_BLOCK ((unsigned int)(PAGE_SIZE / sizeof(gid_t)))
-struct group_info {
- int ngroups;
- atomic_t usage;
- gid_t small_block[NGROUPS_SMALL];
- int nblocks;
- gid_t *blocks[0];
-};
-
-/*
- * get_group_info() must be called with the owning task locked (via task_lock())
- * when task != current. The reason being that the vast majority of callers are
- * looking at current->group_info, which can not be changed except by the
- * current task. Changing current->group_info requires the task lock, too.
- */
-#define get_group_info(group_info) do { \
- atomic_inc(&(group_info)->usage); \
-} while (0)
-
-#define put_group_info(group_info) do { \
- if (atomic_dec_and_test(&(group_info)->usage)) \
- groups_free(group_info); \
-} while (0)
-extern struct group_info *groups_alloc(int gidsetsize);
-extern void groups_free(struct group_info *group_info);
-extern int set_current_groups(struct group_info *group_info);
-extern int groups_search(struct group_info *group_info, gid_t grp);
-/* access the groups "array" with this macro */
-#define GROUP_AT(gi, i) \
- ((gi)->blocks[(i)/NGROUPS_PER_BLOCK][(i)%NGROUPS_PER_BLOCK])
#ifdef ARCH_HAS_PREFETCH_SWITCH_STACK
extern void prefetch_stack(struct task_struct *t);
struct rq *busiest, struct sched_domain *sd,
enum cpu_idle_type idle);
void (*pre_schedule) (struct rq *this_rq, struct task_struct *task);
+ int (*needs_post_schedule) (struct rq *this_rq);
void (*post_schedule) (struct rq *this_rq);
void (*task_wake_up) (struct rq *this_rq, struct task_struct *task);
#endif
struct list_head tasks;
+ struct plist_node pushable_tasks;
struct mm_struct *mm, *active_mm;
* The buffer to hold the BTS data.
*/
void *bts_buffer;
+ size_t bts_size;
#endif /* CONFIG_X86_PTRACE_BTS */
/* PID/PID hash table linkage. */
struct list_head cpu_timers[3];
/* process credentials */
- uid_t uid,euid,suid,fsuid;
- gid_t gid,egid,sgid,fsgid;
- struct group_info *group_info;
- kernel_cap_t cap_effective, cap_inheritable, cap_permitted, cap_bset;
- struct user_struct *user;
- unsigned securebits;
-#ifdef CONFIG_KEYS
- unsigned char jit_keyring; /* default keyring to attach requested keys to */
- struct key *request_key_auth; /* assumed request_key authority */
- struct key *thread_keyring; /* keyring private to this thread */
-#endif
+ const struct cred *real_cred; /* objective and real subjective task
+ * credentials (COW) */
+ const struct cred *cred; /* effective (overridable) subjective task
+ * credentials (COW) */
+ struct mutex cred_exec_mutex; /* execve vs ptrace cred calculation mutex */
+
char comm[TASK_COMM_LEN]; /* executable name excluding path
- access with [gs]et_task_comm (which lock
it with task_lock())
int (*notifier)(void *priv);
void *notifier_data;
sigset_t *notifier_mask;
-#ifdef CONFIG_SECURITY
- void *security;
-#endif
struct audit_context *audit_context;
#ifdef CONFIG_AUDITSYSCALL
uid_t loginuid;
static inline void wake_up_idle_cpu(int cpu) { }
#endif
-#ifdef CONFIG_SCHED_DEBUG
extern unsigned int sysctl_sched_latency;
extern unsigned int sysctl_sched_min_granularity;
extern unsigned int sysctl_sched_wakeup_granularity;
+extern unsigned int sysctl_sched_shares_ratelimit;
+extern unsigned int sysctl_sched_shares_thresh;
+#ifdef CONFIG_SCHED_DEBUG
extern unsigned int sysctl_sched_child_runs_first;
extern unsigned int sysctl_sched_features;
extern unsigned int sysctl_sched_migration_cost;
extern unsigned int sysctl_sched_nr_migrate;
-extern unsigned int sysctl_sched_shares_ratelimit;
-extern unsigned int sysctl_sched_shares_thresh;
int sched_nr_latency_handler(struct ctl_table *table, int write,
struct file *file, void __user *buffer, size_t *length,
return u;
}
extern void free_uid(struct user_struct *);
-extern void switch_uid(struct user_struct *);
extern void release_uids(struct user_namespace *ns);
#include <asm/current.h>
extern void sched_fork(struct task_struct *p, int clone_flags);
extern void sched_dead(struct task_struct *p);
-extern int in_group_p(gid_t);
-extern int in_egroup_p(gid_t);
-
extern void proc_caches_init(void);
extern void flush_signals(struct task_struct *);
extern void ignore_signals(struct task_struct *);
#define for_each_process(p) \
for (p = &init_task ; (p = next_task(p)) != &init_task ; )
+extern bool is_single_threaded(struct task_struct *);
+
/*
* Careful: do_each_thread/while_each_thread is a double loop so
* 'break' will not work as expected - use goto instead.
hrtimer_init(&rt_b->rt_period_timer,
CLOCK_MONOTONIC, HRTIMER_MODE_REL);
rt_b->rt_period_timer.function = sched_rt_period_timer;
- rt_b->rt_period_timer.cb_mode = HRTIMER_CB_IRQSAFE_UNLOCKED;
}
static inline int rt_bandwidth_enabled(void)
struct task_group *tg;
#ifdef CONFIG_USER_SCHED
- tg = p->user->tg;
+ rcu_read_lock();
+ tg = __task_cred(p)->user->tg;
+ rcu_read_unlock();
#elif defined(CONFIG_CGROUP_SCHED)
tg = container_of(task_subsys_state(p, cpu_cgroup_subsys_id),
struct task_group, css);
struct rt_prio_array active;
unsigned long rt_nr_running;
#if defined CONFIG_SMP || defined CONFIG_RT_GROUP_SCHED
- int highest_prio; /* highest queued rt task prio */
+ struct {
+ int curr; /* highest queued rt task prio */
+ int next; /* next highest */
+ } highest_prio;
#endif
#ifdef CONFIG_SMP
unsigned long rt_nr_migratory;
int overloaded;
+ struct plist_head pushable_tasks;
#endif
int rt_throttled;
u64 rt_time;
#ifdef CONFIG_SCHEDSTATS
/* latency stats */
struct sched_info rq_sched_info;
+ unsigned long long rq_cpu_time;
+ /* could above be rq->cfs_rq.exec_clock + rq->rt_rq.rt_runtime ? */
/* sys_sched_yield() stats */
unsigned int yld_exp_empty;
hrtimer_init(&rq->hrtick_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
rq->hrtick_timer.function = hrtick;
- rq->hrtick_timer.cb_mode = HRTIMER_CB_IRQSAFE_PERCPU;
}
#else /* CONFIG_SCHED_HRTICK */
static inline void hrtick_clear(struct rq *rq)
#endif
+ #ifdef CONFIG_PREEMPT
+
/*
- * double_lock_balance - lock the busiest runqueue, this_rq is locked already.
+ * fair double_lock_balance: Safely acquires both rq->locks in a fair
+ * way at the expense of forcing extra atomic operations in all
+ * invocations. This assures that the double_lock is acquired using the
+ * same underlying policy as the spinlock_t on this architecture, which
+ * reduces latency compared to the unfair variant below. However, it
+ * also adds more overhead and therefore may reduce throughput.
*/
- static int double_lock_balance(struct rq *this_rq, struct rq *busiest)
+ static inline int _double_lock_balance(struct rq *this_rq, struct rq *busiest)
+ __releases(this_rq->lock)
+ __acquires(busiest->lock)
+ __acquires(this_rq->lock)
+ {
+ spin_unlock(&this_rq->lock);
+ double_rq_lock(this_rq, busiest);
+
+ return 1;
+ }
+
+ #else
+ /*
+ * Unfair double_lock_balance: Optimizes throughput at the expense of
+ * latency by eliminating extra atomic operations when the locks are
+ * already in proper order on entry. This favors lower cpu-ids and will
+ * grant the double lock to lower cpus over higher ids under contention,
+ * regardless of entry order into the function.
+ */
+ static int _double_lock_balance(struct rq *this_rq, struct rq *busiest)
__releases(this_rq->lock)
__acquires(busiest->lock)
__acquires(this_rq->lock)
{
int ret = 0;
- if (unlikely(!irqs_disabled())) {
- /* printk() doesn't work good under rq->lock */
- spin_unlock(&this_rq->lock);
- BUG_ON(1);
- }
if (unlikely(!spin_trylock(&busiest->lock))) {
if (busiest < this_rq) {
spin_unlock(&this_rq->lock);
return ret;
}
+ #endif /* CONFIG_PREEMPT */
+
+ /*
+ * double_lock_balance - lock the busiest runqueue, this_rq is locked already.
+ */
+ static int double_lock_balance(struct rq *this_rq, struct rq *busiest)
+ {
+ if (unlikely(!irqs_disabled())) {
+ /* printk() doesn't work good under rq->lock */
+ spin_unlock(&this_rq->lock);
+ BUG_ON(1);
+ }
+
+ return _double_lock_balance(this_rq, busiest);
+ }
+
static inline void double_unlock_balance(struct rq *this_rq, struct rq *busiest)
__releases(busiest->lock)
{
clock_offset = old_rq->clock - new_rq->clock;
+ trace_sched_migrate_task(p, task_cpu(p), new_cpu);
+
#ifdef CONFIG_SCHEDSTATS
if (p->se.wait_start)
p->se.wait_start -= clock_offset;
smp_wmb();
rq = task_rq_lock(p, &flags);
+ update_rq_clock(rq);
old_state = p->state;
if (!(old_state & state))
goto out;
schedstat_inc(p, se.nr_wakeups_local);
else
schedstat_inc(p, se.nr_wakeups_remote);
- update_rq_clock(rq);
activate_task(rq, p, 1);
success = 1;
out_running:
- trace_sched_wakeup(rq, p);
+ trace_sched_wakeup(rq, p, success);
check_preempt_curr(rq, p, sync);
p->state = TASK_RUNNING;
/* Want to start with kernel preemption disabled. */
task_thread_info(p)->preempt_count = 1;
#endif
+ plist_node_init(&p->pushable_tasks, MAX_PRIO);
+
put_cpu();
}
p->sched_class->task_new(rq, p);
inc_nr_running(rq);
}
- trace_sched_wakeup_new(rq, p);
+ trace_sched_wakeup_new(rq, p, 1);
check_preempt_curr(rq, p, 0);
#ifdef CONFIG_SMP
if (p->sched_class->task_wake_up)
{
struct mm_struct *mm = rq->prev_mm;
long prev_state;
+ #ifdef CONFIG_SMP
+ int post_schedule = 0;
+
+ if (current->sched_class->needs_post_schedule)
+ post_schedule = current->sched_class->needs_post_schedule(rq);
+ #endif
rq->prev_mm = NULL;
finish_arch_switch(prev);
finish_lock_switch(rq, prev);
#ifdef CONFIG_SMP
- if (current->sched_class->post_schedule)
+ if (post_schedule)
current->sched_class->post_schedule(rq);
#endif
|| unlikely(!cpu_active(dest_cpu)))
goto out;
- trace_sched_migrate_task(rq, p, dest_cpu);
/* force the process onto the specified CPU */
if (migrate_task(p, dest_cpu, &req)) {
/* Need to wait for migration thread (might exit: take ref). */
pulled++;
rem_load_move -= p->se.load.weight;
+ #ifdef CONFIG_PREEMPT
+ /*
+ * NEWIDLE balancing is a source of latency, so preemptible kernels
+ * will stop after the first task is pulled to minimize the critical
+ * section.
+ */
+ if (idle == CPU_NEWLY_IDLE)
+ goto out;
+ #endif
+
/*
* We only want to steal up to the prescribed amount of weighted load.
*/
sd, idle, all_pinned, &this_best_prio);
class = class->next;
+ #ifdef CONFIG_PREEMPT
+ /*
+ * NEWIDLE balancing is a source of latency, so preemptible
+ * kernels will stop after the first task is pulled to minimize
+ * the critical section.
+ */
if (idle == CPU_NEWLY_IDLE && this_rq->nr_running)
break;
-
+ #endif
} while (class && max_load_move > total_load_moved);
return total_load_moved > 0;
* don't kick the migration_thread, if the curr
* task on busiest cpu can't be moved to this_cpu
*/
- if (!cpu_isset(this_cpu, busiest->curr->cpus_allowed)) {
+ if (!cpumask_test_cpu(this_cpu, &busiest->curr->cpus_allowed)) {
double_unlock_balance(this_rq, busiest);
all_pinned = 1;
return ld_moved;
}
double_unlock_balance(this_rq, busiest);
+ /*
+ * Should not call ttwu while holding a rq->lock
+ */
+ spin_unlock(&this_rq->lock);
if (active_balance)
wake_up_process(busiest->migration_thread);
+ spin_lock(&this_rq->lock);
} else
sd->nr_balance_failed = 0;
* Account user cpu time to a process.
* @p: the process that the cpu time gets accounted to
* @cputime: the cpu time spent in user space since the last update
+ * @cputime_scaled: cputime scaled by cpu frequency
*/
-void account_user_time(struct task_struct *p, cputime_t cputime)
+void account_user_time(struct task_struct *p, cputime_t cputime,
+ cputime_t cputime_scaled)
{
struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat;
cputime64_t tmp;
+ /* Add user time to process. */
p->utime = cputime_add(p->utime, cputime);
+ p->utimescaled = cputime_add(p->utimescaled, cputime_scaled);
account_group_user_time(p, cputime);
/* Add user time to cpustat. */
* Account guest cpu time to a process.
* @p: the process that the cpu time gets accounted to
* @cputime: the cpu time spent in virtual machine since the last update
+ * @cputime_scaled: cputime scaled by cpu frequency
*/
-static void account_guest_time(struct task_struct *p, cputime_t cputime)
+static void account_guest_time(struct task_struct *p, cputime_t cputime,
+ cputime_t cputime_scaled)
{
cputime64_t tmp;
struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat;
tmp = cputime_to_cputime64(cputime);
+ /* Add guest time to process. */
p->utime = cputime_add(p->utime, cputime);
+ p->utimescaled = cputime_add(p->utimescaled, cputime_scaled);
account_group_user_time(p, 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);
}
-/*
- * Account scaled user cpu time to a process.
- * @p: the process that the cpu time gets accounted to
- * @cputime: the cpu time spent in user space since the last update
- */
-void account_user_time_scaled(struct task_struct *p, cputime_t cputime)
-{
- p->utimescaled = cputime_add(p->utimescaled, cputime);
-}
-
/*
* Account system cpu time to a process.
* @p: the process that the cpu time gets accounted to
* @hardirq_offset: the offset to subtract from hardirq_count()
* @cputime: the cpu time spent in kernel space since the last update
+ * @cputime_scaled: cputime scaled by cpu frequency
*/
void account_system_time(struct task_struct *p, int hardirq_offset,
- cputime_t cputime)
+ cputime_t cputime, cputime_t cputime_scaled)
{
struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat;
- struct rq *rq = this_rq();
cputime64_t tmp;
if ((p->flags & PF_VCPU) && (irq_count() - hardirq_offset == 0)) {
- account_guest_time(p, cputime);
+ account_guest_time(p, cputime, cputime_scaled);
return;
}
+ /* Add system time to process. */
p->stime = cputime_add(p->stime, cputime);
+ p->stimescaled = cputime_add(p->stimescaled, cputime_scaled);
account_group_system_time(p, cputime);
/* Add system time to cpustat. */
cpustat->irq = cputime64_add(cpustat->irq, tmp);
else if (softirq_count())
cpustat->softirq = cputime64_add(cpustat->softirq, tmp);
- else if (p != rq->idle)
- cpustat->system = cputime64_add(cpustat->system, tmp);
- else if (atomic_read(&rq->nr_iowait) > 0)
- cpustat->iowait = cputime64_add(cpustat->iowait, tmp);
else
- cpustat->idle = cputime64_add(cpustat->idle, tmp);
+ cpustat->system = cputime64_add(cpustat->system, tmp);
+
/* Account for system time used */
acct_update_integrals(p);
}
/*
- * Account scaled system cpu time to a process.
- * @p: the process that the cpu time gets accounted to
- * @hardirq_offset: the offset to subtract from hardirq_count()
- * @cputime: the cpu time spent in kernel space since the last update
+ * Account for involuntary wait time.
+ * @steal: the cpu time spent in involuntary wait
*/
-void account_system_time_scaled(struct task_struct *p, cputime_t cputime)
+void account_steal_time(cputime_t cputime)
{
- p->stimescaled = cputime_add(p->stimescaled, cputime);
+ struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat;
+ cputime64_t cputime64 = cputime_to_cputime64(cputime);
+
+ cpustat->steal = cputime64_add(cpustat->steal, cputime64);
}
/*
- * Account for involuntary wait time.
- * @p: the process from which the cpu time has been stolen
- * @steal: the cpu time spent in involuntary wait
+ * Account for idle time.
+ * @cputime: the cpu time spent in idle wait
*/
-void account_steal_time(struct task_struct *p, cputime_t steal)
+void account_idle_time(cputime_t cputime)
{
struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat;
- cputime64_t tmp = cputime_to_cputime64(steal);
+ cputime64_t cputime64 = cputime_to_cputime64(cputime);
struct rq *rq = this_rq();
- if (p == rq->idle) {
- p->stime = cputime_add(p->stime, steal);
- if (atomic_read(&rq->nr_iowait) > 0)
- cpustat->iowait = cputime64_add(cpustat->iowait, tmp);
- else
- cpustat->idle = cputime64_add(cpustat->idle, tmp);
- } else
- cpustat->steal = cputime64_add(cpustat->steal, tmp);
+ if (atomic_read(&rq->nr_iowait) > 0)
+ cpustat->iowait = cputime64_add(cpustat->iowait, cputime64);
+ else
+ cpustat->idle = cputime64_add(cpustat->idle, cputime64);
+}
+
+#ifndef CONFIG_VIRT_CPU_ACCOUNTING
+
+/*
+ * Account a single tick of cpu time.
+ * @p: the process that the cpu time gets accounted to
+ * @user_tick: indicates if the tick is a user or a system tick
+ */
+void account_process_tick(struct task_struct *p, int user_tick)
+{
+ cputime_t one_jiffy = jiffies_to_cputime(1);
+ cputime_t one_jiffy_scaled = cputime_to_scaled(one_jiffy);
+ struct rq *rq = this_rq();
+
+ if (user_tick)
+ account_user_time(p, one_jiffy, one_jiffy_scaled);
+ else if (p != rq->idle)
+ account_system_time(p, HARDIRQ_OFFSET, one_jiffy,
+ one_jiffy_scaled);
+ else
+ account_idle_time(one_jiffy);
+}
+
+/*
+ * Account multiple ticks of steal time.
+ * @p: the process from which the cpu time has been stolen
+ * @ticks: number of stolen ticks
+ */
+void account_steal_ticks(unsigned long ticks)
+{
+ account_steal_time(jiffies_to_cputime(ticks));
+}
+
+/*
+ * Account multiple ticks of idle time.
+ * @ticks: number of stolen ticks
+ */
+void account_idle_ticks(unsigned long ticks)
+{
+ account_idle_time(jiffies_to_cputime(ticks));
}
+#endif
+
/*
* Use precise platform statistics if available:
*/
set_load_weight(p);
}
+/*
+ * check the target process has a UID that matches the current process's
+ */
+static bool check_same_owner(struct task_struct *p)
+{
+ const struct cred *cred = current_cred(), *pcred;
+ bool match;
+
+ rcu_read_lock();
+ pcred = __task_cred(p);
+ match = (cred->euid == pcred->euid ||
+ cred->euid == pcred->uid);
+ rcu_read_unlock();
+ return match;
+}
+
static int __sched_setscheduler(struct task_struct *p, int policy,
struct sched_param *param, bool user)
{
return -EPERM;
/* can't change other user's priorities */
- if ((current->euid != p->euid) &&
- (current->euid != p->uid))
+ if (!check_same_owner(p))
return -EPERM;
}
goto out_free_cpus_allowed;
}
retval = -EPERM;
- if ((current->euid != p->euid) && (current->euid != p->uid) &&
- !capable(CAP_SYS_NICE))
+ if (!check_same_owner(p) && !capable(CAP_SYS_NICE))
goto out_unlock;
retval = security_task_setscheduler(p, 0, NULL);
static void move_task_off_dead_cpu(int dead_cpu, struct task_struct *p)
{
int dest_cpu;
- /* FIXME: Use cpumask_of_node here. */
- cpumask_t _nodemask = node_to_cpumask(cpu_to_node(dead_cpu));
- const struct cpumask *nodemask = &_nodemask;
+ const struct cpumask *nodemask = cpumask_of_node(cpu_to_node(dead_cpu));
again:
/* Look for allowed, online CPU in same node. */
spin_unlock_irqrestore(&rq->lock, flags);
}
-static int init_rootdomain(struct root_domain *rd, bool bootmem)
+static int __init_refok init_rootdomain(struct root_domain *rd, bool bootmem)
{
memset(rd, 0, sizeof(*rd));
}
if (!alloc_cpumask_var(&rd->span, GFP_KERNEL))
- goto free_rd;
+ goto out;
if (!alloc_cpumask_var(&rd->online, GFP_KERNEL))
goto free_span;
if (!alloc_cpumask_var(&rd->rto_mask, GFP_KERNEL))
free_cpumask_var(rd->online);
free_span:
free_cpumask_var(rd->span);
-free_rd:
- kfree(rd);
+out:
return -ENOMEM;
}
static void sched_domain_node_span(int node, struct cpumask *span)
{
nodemask_t used_nodes;
- /* FIXME: use cpumask_of_node() */
- node_to_cpumask_ptr(nodemask, node);
int i;
- cpus_clear(*span);
+ cpumask_clear(span);
nodes_clear(used_nodes);
- cpus_or(*span, *span, *nodemask);
+ cpumask_or(span, span, cpumask_of_node(node));
node_set(node, used_nodes);
for (i = 1; i < SD_NODES_PER_DOMAIN; i++) {
int next_node = find_next_best_node(node, &used_nodes);
- node_to_cpumask_ptr_next(nodemask, next_node);
- cpus_or(*span, *span, *nodemask);
+ cpumask_or(span, span, cpumask_of_node(next_node));
}
}
#endif /* CONFIG_NUMA */
{
int group;
#ifdef CONFIG_SCHED_MC
- /* FIXME: Use cpu_coregroup_mask. */
- *mask = cpu_coregroup_map(cpu);
- cpus_and(*mask, *mask, *cpu_map);
+ cpumask_and(mask, cpu_coregroup_mask(cpu), cpu_map);
group = cpumask_first(mask);
#elif defined(CONFIG_SCHED_SMT)
cpumask_and(mask, &per_cpu(cpu_sibling_map, cpu), cpu_map);
struct cpumask *nodemask)
{
int group;
- /* FIXME: use cpumask_of_node */
- node_to_cpumask_ptr(pnodemask, cpu_to_node(cpu));
- cpumask_and(nodemask, pnodemask, cpu_map);
+ cpumask_and(nodemask, cpumask_of_node(cpu_to_node(cpu)), cpu_map);
group = cpumask_first(nodemask);
if (sg)
for (i = 0; i < nr_node_ids; i++) {
struct sched_group *oldsg, *sg = sched_group_nodes[i];
- /* FIXME: Use cpumask_of_node */
- node_to_cpumask_ptr(pnodemask, i);
- cpus_and(*nodemask, *pnodemask, *cpu_map);
+ cpumask_and(nodemask, cpumask_of_node(i), cpu_map);
if (cpumask_empty(nodemask))
continue;
for_each_cpu(i, cpu_map) {
struct sched_domain *sd = NULL, *p;
- /* FIXME: use cpumask_of_node */
- *nodemask = node_to_cpumask(cpu_to_node(i));
- cpus_and(*nodemask, *nodemask, *cpu_map);
+ cpumask_and(nodemask, cpumask_of_node(cpu_to_node(i)), cpu_map);
#ifdef CONFIG_NUMA
if (cpumask_weight(cpu_map) >
sd = &per_cpu(core_domains, i).sd;
SD_INIT(sd, MC);
set_domain_attribute(sd, attr);
- *sched_domain_span(sd) = cpu_coregroup_map(i);
- cpumask_and(sched_domain_span(sd),
- sched_domain_span(sd), cpu_map);
+ cpumask_and(sched_domain_span(sd), cpu_map,
+ cpu_coregroup_mask(i));
sd->parent = p;
p->child = sd;
cpu_to_core_group(i, cpu_map, &sd->groups, tmpmask);
#ifdef CONFIG_SCHED_MC
/* Set up multi-core groups */
for_each_cpu(i, cpu_map) {
- /* FIXME: Use cpu_coregroup_mask */
- *this_core_map = cpu_coregroup_map(i);
- cpus_and(*this_core_map, *this_core_map, *cpu_map);
+ cpumask_and(this_core_map, cpu_coregroup_mask(i), cpu_map);
if (i != cpumask_first(this_core_map))
continue;
/* Set up physical groups */
for (i = 0; i < nr_node_ids; i++) {
- /* FIXME: Use cpumask_of_node */
- *nodemask = node_to_cpumask(i);
- cpus_and(*nodemask, *nodemask, *cpu_map);
+ cpumask_and(nodemask, cpumask_of_node(i), cpu_map);
if (cpumask_empty(nodemask))
continue;
struct sched_group *sg, *prev;
int j;
- /* FIXME: Use cpumask_of_node */
- *nodemask = node_to_cpumask(i);
cpumask_clear(covered);
-
- cpus_and(*nodemask, *nodemask, *cpu_map);
+ cpumask_and(nodemask, cpumask_of_node(i), cpu_map);
if (cpumask_empty(nodemask)) {
sched_group_nodes[i] = NULL;
continue;
for (j = 0; j < nr_node_ids; j++) {
int n = (i + j) % nr_node_ids;
- /* FIXME: Use cpumask_of_node */
- node_to_cpumask_ptr(pnodemask, n);
cpumask_complement(notcovered, covered);
cpumask_and(tmpmask, notcovered, cpu_map);
if (cpumask_empty(tmpmask))
break;
- cpumask_and(tmpmask, tmpmask, pnodemask);
+ cpumask_and(tmpmask, tmpmask, cpumask_of_node(n));
if (cpumask_empty(tmpmask))
continue;
}
#if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT)
-int arch_reinit_sched_domains(void)
+static void arch_reinit_sched_domains(void)
{
get_online_cpus();
rebuild_sched_domains();
put_online_cpus();
-
- return 0;
}
static ssize_t sched_power_savings_store(const char *buf, size_t count, int smt)
{
- int ret;
unsigned int level = 0;
if (sscanf(buf, "%u", &level) != 1)
else
sched_mc_power_savings = level;
- ret = arch_reinit_sched_domains();
+ arch_reinit_sched_domains();
- return ret ? ret : count;
+ return count;
}
#ifdef CONFIG_SCHED_MC
sched_smt_power_savings_store);
#endif
-int sched_create_sysfs_power_savings_entries(struct sysdev_class *cls)
+int __init sched_create_sysfs_power_savings_entries(struct sysdev_class *cls)
{
int err = 0;
__set_bit(MAX_RT_PRIO, array->bitmap);
#if defined CONFIG_SMP || defined CONFIG_RT_GROUP_SCHED
- rt_rq->highest_prio = MAX_RT_PRIO;
+ rt_rq->highest_prio.curr = MAX_RT_PRIO;
+ rt_rq->highest_prio.next = MAX_RT_PRIO;
#endif
#ifdef CONFIG_SMP
rt_rq->rt_nr_migratory = 0;
rt_rq->overloaded = 0;
+ plist_head_init(&rq->rt.pushable_tasks, &rq->lock);
#endif
rt_rq->rt_time = 0;
kfree(ca);
}
+static u64 cpuacct_cpuusage_read(struct cpuacct *ca, int cpu)
+{
+ u64 *cpuusage = percpu_ptr(ca->cpuusage, cpu);
+ u64 data;
+
+#ifndef CONFIG_64BIT
+ /*
+ * Take rq->lock to make 64-bit read safe on 32-bit platforms.
+ */
+ spin_lock_irq(&cpu_rq(cpu)->lock);
+ data = *cpuusage;
+ spin_unlock_irq(&cpu_rq(cpu)->lock);
+#else
+ data = *cpuusage;
+#endif
+
+ return data;
+}
+
+static void cpuacct_cpuusage_write(struct cpuacct *ca, int cpu, u64 val)
+{
+ u64 *cpuusage = percpu_ptr(ca->cpuusage, cpu);
+
+#ifndef CONFIG_64BIT
+ /*
+ * Take rq->lock to make 64-bit write safe on 32-bit platforms.
+ */
+ spin_lock_irq(&cpu_rq(cpu)->lock);
+ *cpuusage = val;
+ spin_unlock_irq(&cpu_rq(cpu)->lock);
+#else
+ *cpuusage = val;
+#endif
+}
+
/* return total cpu usage (in nanoseconds) of a group */
static u64 cpuusage_read(struct cgroup *cgrp, struct cftype *cft)
{
u64 totalcpuusage = 0;
int i;
- for_each_possible_cpu(i) {
- u64 *cpuusage = percpu_ptr(ca->cpuusage, i);
-
- /*
- * Take rq->lock to make 64-bit addition safe on 32-bit
- * platforms.
- */
- spin_lock_irq(&cpu_rq(i)->lock);
- totalcpuusage += *cpuusage;
- spin_unlock_irq(&cpu_rq(i)->lock);
- }
+ for_each_present_cpu(i)
+ totalcpuusage += cpuacct_cpuusage_read(ca, i);
return totalcpuusage;
}
goto out;
}
- for_each_possible_cpu(i) {
- u64 *cpuusage = percpu_ptr(ca->cpuusage, i);
+ for_each_present_cpu(i)
+ cpuacct_cpuusage_write(ca, i, 0);
- spin_lock_irq(&cpu_rq(i)->lock);
- *cpuusage = 0;
- spin_unlock_irq(&cpu_rq(i)->lock);
- }
out:
return err;
}
+static int cpuacct_percpu_seq_read(struct cgroup *cgroup, struct cftype *cft,
+ struct seq_file *m)
+{
+ struct cpuacct *ca = cgroup_ca(cgroup);
+ u64 percpu;
+ int i;
+
+ for_each_present_cpu(i) {
+ percpu = cpuacct_cpuusage_read(ca, i);
+ seq_printf(m, "%llu ", (unsigned long long) percpu);
+ }
+ seq_printf(m, "\n");
+ return 0;
+}
+
static struct cftype files[] = {
{
.name = "usage",
.read_u64 = cpuusage_read,
.write_u64 = cpuusage_write,
},
+ {
+ .name = "usage_percpu",
+ .read_seq_string = cpuacct_percpu_seq_read,
+ },
+
};
static int cpuacct_populate(struct cgroup_subsys *ss, struct cgroup *cgrp)
rq->rt.overloaded = 0;
}
}
+
+ static void enqueue_pushable_task(struct rq *rq, struct task_struct *p)
+ {
+ plist_del(&p->pushable_tasks, &rq->rt.pushable_tasks);
+ plist_node_init(&p->pushable_tasks, p->prio);
+ plist_add(&p->pushable_tasks, &rq->rt.pushable_tasks);
+ }
+
+ static void dequeue_pushable_task(struct rq *rq, struct task_struct *p)
+ {
+ plist_del(&p->pushable_tasks, &rq->rt.pushable_tasks);
+ }
+
+ #else
+
+ #define enqueue_pushable_task(rq, p) do { } while (0)
+ #define dequeue_pushable_task(rq, p) do { } while (0)
+
#endif /* CONFIG_SMP */
static inline struct task_struct *rt_task_of(struct sched_rt_entity *rt_se)
}
#define for_each_leaf_rt_rq(rt_rq, rq) \
- list_for_each_entry(rt_rq, &rq->leaf_rt_rq_list, leaf_rt_rq_list)
+ list_for_each_entry_rcu(rt_rq, &rq->leaf_rt_rq_list, leaf_rt_rq_list)
static inline struct rq *rq_of_rt_rq(struct rt_rq *rt_rq)
{
if (rt_rq->rt_nr_running) {
if (rt_se && !on_rt_rq(rt_se))
enqueue_rt_entity(rt_se);
- if (rt_rq->highest_prio < curr->prio)
+ if (rt_rq->highest_prio.curr < curr->prio)
resched_task(curr);
}
}
struct rt_rq *rt_rq = group_rt_rq(rt_se);
if (rt_rq)
- return rt_rq->highest_prio;
+ return rt_rq->highest_prio.curr;
#endif
return rt_task_of(rt_se)->prio;
}
}
+ #if defined CONFIG_SMP || defined CONFIG_RT_GROUP_SCHED
+
+ static struct task_struct *pick_next_highest_task_rt(struct rq *rq, int cpu);
+
+ static inline int next_prio(struct rq *rq)
+ {
+ struct task_struct *next = pick_next_highest_task_rt(rq, rq->cpu);
+
+ if (next && rt_prio(next->prio))
+ return next->prio;
+ else
+ return MAX_RT_PRIO;
+ }
+ #endif
+
static inline
void inc_rt_tasks(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq)
{
- WARN_ON(!rt_prio(rt_se_prio(rt_se)));
- rt_rq->rt_nr_running++;
- #if defined CONFIG_SMP || defined CONFIG_RT_GROUP_SCHED
- if (rt_se_prio(rt_se) < rt_rq->highest_prio) {
+ int prio = rt_se_prio(rt_se);
#ifdef CONFIG_SMP
- struct rq *rq = rq_of_rt_rq(rt_rq);
+ struct rq *rq = rq_of_rt_rq(rt_rq);
#endif
- rt_rq->highest_prio = rt_se_prio(rt_se);
+ WARN_ON(!rt_prio(prio));
+ rt_rq->rt_nr_running++;
+ #if defined CONFIG_SMP || defined CONFIG_RT_GROUP_SCHED
+ if (prio < rt_rq->highest_prio.curr) {
+
+ /*
+ * If the new task is higher in priority than anything on the
+ * run-queue, we have a new high that must be published to
+ * the world. We also know that the previous high becomes
+ * our next-highest.
+ */
+ rt_rq->highest_prio.next = rt_rq->highest_prio.curr;
+ rt_rq->highest_prio.curr = prio;
#ifdef CONFIG_SMP
if (rq->online)
- cpupri_set(&rq->rd->cpupri, rq->cpu,
- rt_se_prio(rt_se));
+ cpupri_set(&rq->rd->cpupri, rq->cpu, prio);
#endif
- }
+ } else if (prio == rt_rq->highest_prio.curr)
+ /*
+ * If the next task is equal in priority to the highest on
+ * the run-queue, then we implicitly know that the next highest
+ * task cannot be any lower than current
+ */
+ rt_rq->highest_prio.next = prio;
+ else if (prio < rt_rq->highest_prio.next)
+ /*
+ * Otherwise, we need to recompute next-highest
+ */
+ rt_rq->highest_prio.next = next_prio(rq);
#endif
#ifdef CONFIG_SMP
- if (rt_se->nr_cpus_allowed > 1) {
- struct rq *rq = rq_of_rt_rq(rt_rq);
-
+ if (rt_se->nr_cpus_allowed > 1)
rq->rt.rt_nr_migratory++;
- }
- update_rt_migration(rq_of_rt_rq(rt_rq));
+ update_rt_migration(rq);
#endif
#ifdef CONFIG_RT_GROUP_SCHED
if (rt_se_boosted(rt_se))
void dec_rt_tasks(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq)
{
#ifdef CONFIG_SMP
- int highest_prio = rt_rq->highest_prio;
+ struct rq *rq = rq_of_rt_rq(rt_rq);
+ int highest_prio = rt_rq->highest_prio.curr;
#endif
WARN_ON(!rt_prio(rt_se_prio(rt_se)));
rt_rq->rt_nr_running--;
#if defined CONFIG_SMP || defined CONFIG_RT_GROUP_SCHED
if (rt_rq->rt_nr_running) {
- struct rt_prio_array *array;
+ int prio = rt_se_prio(rt_se);
- WARN_ON(rt_se_prio(rt_se) < rt_rq->highest_prio);
- if (rt_se_prio(rt_se) == rt_rq->highest_prio) {
- /* recalculate */
- array = &rt_rq->active;
- rt_rq->highest_prio =
+ WARN_ON(prio < rt_rq->highest_prio.curr);
+
+ /*
+ * This may have been our highest or next-highest priority
+ * task and therefore we may have some recomputation to do
+ */
+ if (prio == rt_rq->highest_prio.curr) {
+ struct rt_prio_array *array = &rt_rq->active;
+
+ rt_rq->highest_prio.curr =
sched_find_first_bit(array->bitmap);
- } /* otherwise leave rq->highest prio alone */
+ }
+
+ if (prio <= rt_rq->highest_prio.next)
+ rt_rq->highest_prio.next = next_prio(rq);
} else
- rt_rq->highest_prio = MAX_RT_PRIO;
+ rt_rq->highest_prio.curr = MAX_RT_PRIO;
#endif
#ifdef CONFIG_SMP
- if (rt_se->nr_cpus_allowed > 1) {
- struct rq *rq = rq_of_rt_rq(rt_rq);
+ if (rt_se->nr_cpus_allowed > 1)
rq->rt.rt_nr_migratory--;
- }
- if (rt_rq->highest_prio != highest_prio) {
- struct rq *rq = rq_of_rt_rq(rt_rq);
+ if (rq->online && rt_rq->highest_prio.curr != highest_prio)
+ cpupri_set(&rq->rd->cpupri, rq->cpu, rt_rq->highest_prio.curr);
- if (rq->online)
- cpupri_set(&rq->rd->cpupri, rq->cpu,
- rt_rq->highest_prio);
- }
-
- update_rt_migration(rq_of_rt_rq(rt_rq));
+ update_rt_migration(rq);
#endif /* CONFIG_SMP */
#ifdef CONFIG_RT_GROUP_SCHED
if (rt_se_boosted(rt_se))
enqueue_rt_entity(rt_se);
+ if (!task_current(rq, p) && p->rt.nr_cpus_allowed > 1)
+ enqueue_pushable_task(rq, p);
+
inc_cpu_load(rq, p->se.load.weight);
}
update_curr_rt(rq);
dequeue_rt_entity(rt_se);
+ dequeue_pushable_task(rq, p);
+
dec_cpu_load(rq, p->se.load.weight);
}
return next;
}
- static struct task_struct *pick_next_task_rt(struct rq *rq)
+ static struct task_struct *_pick_next_task_rt(struct rq *rq)
{
struct sched_rt_entity *rt_se;
struct task_struct *p;
p = rt_task_of(rt_se);
p->se.exec_start = rq->clock;
+
+ return p;
+ }
+
+ static struct task_struct *pick_next_task_rt(struct rq *rq)
+ {
+ struct task_struct *p = _pick_next_task_rt(rq);
+
+ /* The running task is never eligible for pushing */
+ if (p)
+ dequeue_pushable_task(rq, p);
+
return p;
}
{
update_curr_rt(rq);
p->se.exec_start = 0;
+
+ /*
+ * The previous task needs to be made eligible for pushing
+ * if it is still active
+ */
+ if (p->se.on_rq && p->rt.nr_cpus_allowed > 1)
+ enqueue_pushable_task(rq, p);
}
#ifdef CONFIG_SMP
}
/* If this rq is still suitable use it. */
- if (lowest_rq->rt.highest_prio > task->prio)
+ if (lowest_rq->rt.highest_prio.curr > task->prio)
break;
/* try again */
return lowest_rq;
}
+ static inline int has_pushable_tasks(struct rq *rq)
+ {
+ return !plist_head_empty(&rq->rt.pushable_tasks);
+ }
+
+ static struct task_struct *pick_next_pushable_task(struct rq *rq)
+ {
+ struct task_struct *p;
+
+ if (!has_pushable_tasks(rq))
+ return NULL;
+
+ p = plist_first_entry(&rq->rt.pushable_tasks,
+ struct task_struct, pushable_tasks);
+
+ BUG_ON(rq->cpu != task_cpu(p));
+ BUG_ON(task_current(rq, p));
+ BUG_ON(p->rt.nr_cpus_allowed <= 1);
+
+ BUG_ON(!p->se.on_rq);
+ BUG_ON(!rt_task(p));
+
+ return p;
+ }
+
/*
* If the current CPU has more than one RT task, see if the non
* running task can migrate over to a CPU that is running a task
{
struct task_struct *next_task;
struct rq *lowest_rq;
- int ret = 0;
- int paranoid = RT_MAX_TRIES;
if (!rq->rt.overloaded)
return 0;
- next_task = pick_next_highest_task_rt(rq, -1);
+ next_task = pick_next_pushable_task(rq);
if (!next_task)
return 0;
struct task_struct *task;
/*
* find lock_lowest_rq releases rq->lock
- * so it is possible that next_task has changed.
- * If it has, then try again.
+ * so it is possible that next_task has migrated.
+ *
+ * We need to make sure that the task is still on the same
+ * run-queue and is also still the next task eligible for
+ * pushing.
*/
- task = pick_next_highest_task_rt(rq, -1);
- if (unlikely(task != next_task) && task && paranoid--) {
- put_task_struct(next_task);
- next_task = task;
- goto retry;
+ task = pick_next_pushable_task(rq);
+ if (task_cpu(next_task) == rq->cpu && task == next_task) {
+ /*
+ * If we get here, the task hasnt moved at all, but
+ * it has failed to push. We will not try again,
+ * since the other cpus will pull from us when they
+ * are ready.
+ */
+ dequeue_pushable_task(rq, next_task);
+ goto out;
}
- goto out;
+
+ if (!task)
+ /* No more tasks, just exit */
+ goto out;
+
+ /*
+ * Something has shifted, try again.
+ */
+ put_task_struct(next_task);
+ next_task = task;
+ goto retry;
}
deactivate_task(rq, next_task, 0);
double_unlock_balance(rq, lowest_rq);
- ret = 1;
out:
put_task_struct(next_task);
- return ret;
+ return 1;
}
- /*
- * TODO: Currently we just use the second highest prio task on
- * the queue, and stop when it can't migrate (or there's
- * no more RT tasks). There may be a case where a lower
- * priority RT task has a different affinity than the
- * higher RT task. In this case the lower RT task could
- * possibly be able to migrate where as the higher priority
- * RT task could not. We currently ignore this issue.
- * Enhancements are welcome!
- */
static void push_rt_tasks(struct rq *rq)
{
/* push_rt_task will return true if it moved an RT */
static int pull_rt_task(struct rq *this_rq)
{
int this_cpu = this_rq->cpu, ret = 0, cpu;
- struct task_struct *p, *next;
+ struct task_struct *p;
struct rq *src_rq;
if (likely(!rt_overloaded(this_rq)))
return 0;
- next = pick_next_task_rt(this_rq);
-
for_each_cpu(cpu, this_rq->rd->rto_mask) {
if (this_cpu == cpu)
continue;
src_rq = cpu_rq(cpu);
+
+ /*
+ * Don't bother taking the src_rq->lock if the next highest
+ * task is known to be lower-priority than our current task.
+ * This may look racy, but if this value is about to go
+ * logically higher, the src_rq will push this task away.
+ * And if its going logically lower, we do not care
+ */
+ if (src_rq->rt.highest_prio.next >=
+ this_rq->rt.highest_prio.curr)
+ continue;
+
/*
* We can potentially drop this_rq's lock in
* double_lock_balance, and another CPU could
- * steal our next task - hence we must cause
- * the caller to recalculate the next task
- * in that case:
+ * alter this_rq
*/
- if (double_lock_balance(this_rq, src_rq)) {
- struct task_struct *old_next = next;
-
- next = pick_next_task_rt(this_rq);
- if (next != old_next)
- ret = 1;
- }
+ double_lock_balance(this_rq, src_rq);
/*
* Are there still pullable RT tasks?
* Do we have an RT task that preempts
* the to-be-scheduled task?
*/
- if (p && (!next || (p->prio < next->prio))) {
+ if (p && (p->prio < this_rq->rt.highest_prio.curr)) {
WARN_ON(p == src_rq->curr);
WARN_ON(!p->se.on_rq);
* This is just that p is wakeing up and hasn't
* had a chance to schedule. We only pull
* p if it is lower in priority than the
- * current task on the run queue or
- * this_rq next task is lower in prio than
- * the current task on that rq.
+ * current task on the run queue
*/
- if (p->prio < src_rq->curr->prio ||
- (next && next->prio < src_rq->curr->prio))
+ if (p->prio < src_rq->curr->prio)
goto skip;
ret = 1;
* case there's an even higher prio task
* in another runqueue. (low likelyhood
* but possible)
- *
- * Update next so that we won't pick a task
- * on another cpu with a priority lower (or equal)
- * than the one we just picked.
*/
- next = p;
-
}
skip:
double_unlock_balance(this_rq, src_rq);
static void pre_schedule_rt(struct rq *rq, struct task_struct *prev)
{
/* Try to pull RT tasks here if we lower this rq's prio */
- if (unlikely(rt_task(prev)) && rq->rt.highest_prio > prev->prio)
+ if (unlikely(rt_task(prev)) && rq->rt.highest_prio.curr > prev->prio)
pull_rt_task(rq);
}
+ /*
+ * assumes rq->lock is held
+ */
+ static int needs_post_schedule_rt(struct rq *rq)
+ {
+ return has_pushable_tasks(rq);
+ }
+
static void post_schedule_rt(struct rq *rq)
{
/*
- * If we have more than one rt_task queued, then
- * see if we can push the other rt_tasks off to other CPUS.
- * Note we may release the rq lock, and since
- * the lock was owned by prev, we need to release it
- * first via finish_lock_switch and then reaquire it here.
+ * This is only called if needs_post_schedule_rt() indicates that
+ * we need to push tasks away
*/
- if (unlikely(rq->rt.overloaded)) {
- spin_lock_irq(&rq->lock);
- push_rt_tasks(rq);
- spin_unlock_irq(&rq->lock);
- }
+ spin_lock_irq(&rq->lock);
+ push_rt_tasks(rq);
+ spin_unlock_irq(&rq->lock);
}
/*
{
if (!task_running(rq, p) &&
!test_tsk_need_resched(rq->curr) &&
- rq->rt.overloaded)
+ has_pushable_tasks(rq) &&
+ p->rt.nr_cpus_allowed > 1)
push_rt_tasks(rq);
}
if (p->se.on_rq && (weight != p->rt.nr_cpus_allowed)) {
struct rq *rq = task_rq(p);
+ if (!task_current(rq, p)) {
+ /*
+ * Make sure we dequeue this task from the pushable list
+ * before going further. It will either remain off of
+ * the list because we are no longer pushable, or it
+ * will be requeued.
+ */
+ if (p->rt.nr_cpus_allowed > 1)
+ dequeue_pushable_task(rq, p);
+
+ /*
+ * Requeue if our weight is changing and still > 1
+ */
+ if (weight > 1)
+ enqueue_pushable_task(rq, p);
+
+ }
+
if ((p->rt.nr_cpus_allowed <= 1) && (weight > 1)) {
rq->rt.rt_nr_migratory++;
} else if ((p->rt.nr_cpus_allowed > 1) && (weight <= 1)) {
__enable_runtime(rq);
- cpupri_set(&rq->rd->cpupri, rq->cpu, rq->rt.highest_prio);
+ cpupri_set(&rq->rd->cpupri, rq->cpu, rq->rt.highest_prio.curr);
}
/* Assumes rq->lock is held */
unsigned int i;
for_each_possible_cpu(i)
- alloc_cpumask_var(&per_cpu(local_cpu_mask, i), GFP_KERNEL);
+ alloc_cpumask_var_node(&per_cpu(local_cpu_mask, i),
+ GFP_KERNEL, cpu_to_node(i));
}
#endif /* CONFIG_SMP */
* can release the rq lock and p could migrate.
* Only reschedule if p is still on the same runqueue.
*/
- if (p->prio > rq->rt.highest_prio && rq->curr == p)
+ if (p->prio > rq->rt.highest_prio.curr && rq->curr == p)
resched_task(p);
#else
/* For UP simply resched on drop of prio */
struct task_struct *p = rq->curr;
p->se.exec_start = rq->clock;
+
+ /* The running task is never eligible for pushing */
+ dequeue_pushable_task(rq, p);
}
static const struct sched_class rt_sched_class = {
.rq_online = rq_online_rt,
.rq_offline = rq_offline_rt,
.pre_schedule = pre_schedule_rt,
+ .needs_post_schedule = needs_post_schedule_rt,
.post_schedule = post_schedule_rt,
.task_wake_up = task_wake_up_rt,
.switched_from = switched_from_rt,