summaryrefslogtreecommitdiff
path: root/kernel/sched/fair.c
diff options
context:
space:
mode:
Diffstat (limited to 'kernel/sched/fair.c')
-rw-r--r--kernel/sched/fair.c224
1 files changed, 151 insertions, 73 deletions
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 940e6d17cf96..c219bf8d704c 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -2637,8 +2637,6 @@ static int select_idle_sibling(struct task_struct *p, int target)
int cpu = smp_processor_id();
int prev_cpu = task_cpu(p);
struct sched_domain *sd;
- struct sched_group *sg;
- int i;
/*
* If the task is going to be woken-up on this cpu and if it is
@@ -2655,29 +2653,17 @@ static int select_idle_sibling(struct task_struct *p, int target)
return prev_cpu;
/*
- * Otherwise, iterate the domains and find an elegible idle cpu.
+ * Otherwise, check assigned siblings to find an elegible idle cpu.
*/
sd = rcu_dereference(per_cpu(sd_llc, target));
- for_each_lower_domain(sd) {
- sg = sd->groups;
- do {
- if (!cpumask_intersects(sched_group_cpus(sg),
- tsk_cpus_allowed(p)))
- goto next;
- for_each_cpu(i, sched_group_cpus(sg)) {
- if (!idle_cpu(i))
- goto next;
- }
-
- target = cpumask_first_and(sched_group_cpus(sg),
- tsk_cpus_allowed(p));
- goto done;
-next:
- sg = sg->next;
- } while (sg != sd->groups);
+ for_each_lower_domain(sd) {
+ if (!cpumask_test_cpu(sd->idle_buddy, tsk_cpus_allowed(p)))
+ continue;
+ if (idle_cpu(sd->idle_buddy))
+ return sd->idle_buddy;
}
-done:
+
return target;
}
@@ -2703,7 +2689,7 @@ select_task_rq_fair(struct task_struct *p, int sd_flag, int wake_flags)
int want_sd = 1;
int sync = wake_flags & WF_SYNC;
- if (p->rt.nr_cpus_allowed == 1)
+ if (p->nr_cpus_allowed == 1)
return prev_cpu;
if (sd_flag & SD_BALANCE_WAKE) {
@@ -3068,18 +3054,24 @@ static unsigned long __read_mostly max_load_balance_interval = HZ/10;
#define LBF_ALL_PINNED 0x01
#define LBF_NEED_BREAK 0x02
+#define LBF_SOME_PINNED 0x04
struct lb_env {
struct sched_domain *sd;
- int src_cpu;
struct rq *src_rq;
+ int src_cpu;
int dst_cpu;
struct rq *dst_rq;
+ struct cpumask *dst_grpmask;
+ int new_dst_cpu;
enum cpu_idle_type idle;
long imbalance;
+ /* The set of CPUs under consideration for load-balancing */
+ struct cpumask *cpus;
+
unsigned int flags;
unsigned int loop;
@@ -3145,9 +3137,31 @@ int can_migrate_task(struct task_struct *p, struct lb_env *env)
* 3) are cache-hot on their current CPU.
*/
if (!cpumask_test_cpu(env->dst_cpu, tsk_cpus_allowed(p))) {
+ int new_dst_cpu;
+
schedstat_inc(p, se.statistics.nr_failed_migrations_affine);
+
+ /*
+ * Remember if this task can be migrated to any other cpu in
+ * our sched_group. We may want to revisit it if we couldn't
+ * meet load balance goals by pulling other tasks on src_cpu.
+ *
+ * Also avoid computing new_dst_cpu if we have already computed
+ * one in current iteration.
+ */
+ if (!env->dst_grpmask || (env->flags & LBF_SOME_PINNED))
+ return 0;
+
+ new_dst_cpu = cpumask_first_and(env->dst_grpmask,
+ tsk_cpus_allowed(p));
+ if (new_dst_cpu < nr_cpu_ids) {
+ env->flags |= LBF_SOME_PINNED;
+ env->new_dst_cpu = new_dst_cpu;
+ }
return 0;
}
+
+ /* Record that we found atleast one task that could run on dst_cpu */
env->flags &= ~LBF_ALL_PINNED;
if (task_running(env->src_rq, p)) {
@@ -3373,6 +3387,14 @@ static int tg_load_down(struct task_group *tg, void *data)
static void update_h_load(long cpu)
{
+ struct rq *rq = cpu_rq(cpu);
+ unsigned long now = jiffies;
+
+ if (rq->h_load_throttle == now)
+ return;
+
+ rq->h_load_throttle = now;
+
rcu_read_lock();
walk_tg_tree(tg_load_down, tg_nop, (void *)cpu);
rcu_read_unlock();
@@ -3503,15 +3525,22 @@ unsigned long __weak arch_scale_smt_power(struct sched_domain *sd, int cpu)
unsigned long scale_rt_power(int cpu)
{
struct rq *rq = cpu_rq(cpu);
- u64 total, available;
+ u64 total, available, age_stamp, avg;
+
+ /*
+ * Since we're reading these variables without serialization make sure
+ * we read them once before doing sanity checks on them.
+ */
+ age_stamp = ACCESS_ONCE(rq->age_stamp);
+ avg = ACCESS_ONCE(rq->rt_avg);
- total = sched_avg_period() + (rq->clock - rq->age_stamp);
+ total = sched_avg_period() + (rq->clock - age_stamp);
- if (unlikely(total < rq->rt_avg)) {
+ if (unlikely(total < avg)) {
/* Ensures that power won't end up being negative */
available = 0;
} else {
- available = total - rq->rt_avg;
+ available = total - avg;
}
if (unlikely((s64)total < SCHED_POWER_SCALE))
@@ -3574,13 +3603,28 @@ void update_group_power(struct sched_domain *sd, int cpu)
power = 0;
- group = child->groups;
- do {
- power += group->sgp->power;
- group = group->next;
- } while (group != child->groups);
+ if (child->flags & SD_OVERLAP) {
+ /*
+ * SD_OVERLAP domains cannot assume that child groups
+ * span the current group.
+ */
- sdg->sgp->power = power;
+ for_each_cpu(cpu, sched_group_cpus(sdg))
+ power += power_of(cpu);
+ } else {
+ /*
+ * !SD_OVERLAP domains can assume that child groups
+ * span the current group.
+ */
+
+ group = child->groups;
+ do {
+ power += group->sgp->power;
+ group = group->next;
+ } while (group != child->groups);
+ }
+
+ sdg->sgp->power_orig = sdg->sgp->power = power;
}
/*
@@ -3610,7 +3654,7 @@ fix_small_capacity(struct sched_domain *sd, struct sched_group *group)
/**
* update_sg_lb_stats - Update sched_group's statistics for load balancing.
- * @sd: The sched_domain whose statistics are to be updated.
+ * @env: The load balancing environment.
* @group: sched_group whose statistics are to be updated.
* @load_idx: Load index of sched_domain of this_cpu for load calc.
* @local_group: Does group contain this_cpu.
@@ -3620,8 +3664,7 @@ fix_small_capacity(struct sched_domain *sd, struct sched_group *group)
*/
static inline void update_sg_lb_stats(struct lb_env *env,
struct sched_group *group, int load_idx,
- int local_group, const struct cpumask *cpus,
- int *balance, struct sg_lb_stats *sgs)
+ int local_group, int *balance, struct sg_lb_stats *sgs)
{
unsigned long nr_running, max_nr_running, min_nr_running;
unsigned long load, max_cpu_load, min_cpu_load;
@@ -3630,7 +3673,7 @@ static inline void update_sg_lb_stats(struct lb_env *env,
int i;
if (local_group)
- balance_cpu = group_first_cpu(group);
+ balance_cpu = group_balance_cpu(group);
/* Tally up the load of all CPUs in the group */
max_cpu_load = 0;
@@ -3638,14 +3681,15 @@ static inline void update_sg_lb_stats(struct lb_env *env,
max_nr_running = 0;
min_nr_running = ~0UL;
- for_each_cpu_and(i, sched_group_cpus(group), cpus) {
+ for_each_cpu_and(i, sched_group_cpus(group), env->cpus) {
struct rq *rq = cpu_rq(i);
nr_running = rq->nr_running;
/* Bias balancing toward cpus of our domain */
if (local_group) {
- if (idle_cpu(i) && !first_idle_cpu) {
+ if (idle_cpu(i) && !first_idle_cpu &&
+ cpumask_test_cpu(i, sched_group_mask(group))) {
first_idle_cpu = 1;
balance_cpu = i;
}
@@ -3719,11 +3763,10 @@ static inline void update_sg_lb_stats(struct lb_env *env,
/**
* update_sd_pick_busiest - return 1 on busiest group
- * @sd: sched_domain whose statistics are to be checked
+ * @env: The load balancing environment.
* @sds: sched_domain statistics
* @sg: sched_group candidate to be checked for being the busiest
* @sgs: sched_group statistics
- * @this_cpu: the current cpu
*
* Determine if @sg is a busier group than the previously selected
* busiest group.
@@ -3761,16 +3804,13 @@ static bool update_sd_pick_busiest(struct lb_env *env,
/**
* update_sd_lb_stats - Update sched_domain's statistics for load balancing.
- * @sd: sched_domain whose statistics are to be updated.
- * @this_cpu: Cpu for which load balance is currently performed.
- * @idle: Idle status of this_cpu
+ * @env: The load balancing environment.
* @cpus: Set of cpus considered for load balancing.
* @balance: Should we balance.
* @sds: variable to hold the statistics for this sched_domain.
*/
static inline void update_sd_lb_stats(struct lb_env *env,
- const struct cpumask *cpus,
- int *balance, struct sd_lb_stats *sds)
+ int *balance, struct sd_lb_stats *sds)
{
struct sched_domain *child = env->sd->child;
struct sched_group *sg = env->sd->groups;
@@ -3787,8 +3827,7 @@ static inline void update_sd_lb_stats(struct lb_env *env,
local_group = cpumask_test_cpu(env->dst_cpu, sched_group_cpus(sg));
memset(&sgs, 0, sizeof(sgs));
- update_sg_lb_stats(env, sg, load_idx, local_group,
- cpus, balance, &sgs);
+ update_sg_lb_stats(env, sg, load_idx, local_group, balance, &sgs);
if (local_group && !(*balance))
return;
@@ -3852,10 +3891,8 @@ static inline void update_sd_lb_stats(struct lb_env *env,
* Returns 1 when packing is required and a task should be moved to
* this CPU. The amount of the imbalance is returned in *imbalance.
*
- * @sd: The sched_domain whose packing is to be checked.
+ * @env: The load balancing environment.
* @sds: Statistics of the sched_domain which is to be packed
- * @this_cpu: The cpu at whose sched_domain we're performing load-balance.
- * @imbalance: returns amount of imbalanced due to packing.
*/
static int check_asym_packing(struct lb_env *env, struct sd_lb_stats *sds)
{
@@ -3881,9 +3918,8 @@ static int check_asym_packing(struct lb_env *env, struct sd_lb_stats *sds)
* fix_small_imbalance - Calculate the minor imbalance that exists
* amongst the groups of a sched_domain, during
* load balancing.
+ * @env: The load balancing environment.
* @sds: Statistics of the sched_domain whose imbalance is to be calculated.
- * @this_cpu: The cpu at whose sched_domain we're performing load-balance.
- * @imbalance: Variable to store the imbalance.
*/
static inline
void fix_small_imbalance(struct lb_env *env, struct sd_lb_stats *sds)
@@ -4026,12 +4062,7 @@ static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *s
* Also calculates the amount of weighted load which should be moved
* to restore balance.
*
- * @sd: The sched_domain whose busiest group is to be returned.
- * @this_cpu: The cpu for which load balancing is currently being performed.
- * @imbalance: Variable which stores amount of weighted load which should
- * be moved to restore balance/put a group to idle.
- * @idle: The idle status of this_cpu.
- * @cpus: The set of CPUs under consideration for load-balancing.
+ * @env: The load balancing environment.
* @balance: Pointer to a variable indicating if this_cpu
* is the appropriate cpu to perform load balancing at this_level.
*
@@ -4041,7 +4072,7 @@ static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *s
* put to idle by rebalancing its tasks onto our group.
*/
static struct sched_group *
-find_busiest_group(struct lb_env *env, const struct cpumask *cpus, int *balance)
+find_busiest_group(struct lb_env *env, int *balance)
{
struct sd_lb_stats sds;
@@ -4051,7 +4082,7 @@ find_busiest_group(struct lb_env *env, const struct cpumask *cpus, int *balance)
* Compute the various statistics relavent for load balancing at
* this level.
*/
- update_sd_lb_stats(env, cpus, balance, &sds);
+ update_sd_lb_stats(env, balance, &sds);
/*
* this_cpu is not the appropriate cpu to perform load balancing at
@@ -4131,8 +4162,7 @@ ret:
* find_busiest_queue - find the busiest runqueue among the cpus in group.
*/
static struct rq *find_busiest_queue(struct lb_env *env,
- struct sched_group *group,
- const struct cpumask *cpus)
+ struct sched_group *group)
{
struct rq *busiest = NULL, *rq;
unsigned long max_load = 0;
@@ -4147,7 +4177,7 @@ static struct rq *find_busiest_queue(struct lb_env *env,
if (!capacity)
capacity = fix_small_capacity(env->sd, group);
- if (!cpumask_test_cpu(i, cpus))
+ if (!cpumask_test_cpu(i, env->cpus))
continue;
rq = cpu_rq(i);
@@ -4214,7 +4244,8 @@ static int load_balance(int this_cpu, struct rq *this_rq,
struct sched_domain *sd, enum cpu_idle_type idle,
int *balance)
{
- int ld_moved, active_balance = 0;
+ int ld_moved, cur_ld_moved, active_balance = 0;
+ int lb_iterations, max_lb_iterations;
struct sched_group *group;
struct rq *busiest;
unsigned long flags;
@@ -4224,16 +4255,19 @@ static int load_balance(int this_cpu, struct rq *this_rq,
.sd = sd,
.dst_cpu = this_cpu,
.dst_rq = this_rq,
+ .dst_grpmask = sched_group_cpus(sd->groups),
.idle = idle,
.loop_break = sched_nr_migrate_break,
+ .cpus = cpus,
};
cpumask_copy(cpus, cpu_active_mask);
+ max_lb_iterations = cpumask_weight(env.dst_grpmask);
schedstat_inc(sd, lb_count[idle]);
redo:
- group = find_busiest_group(&env, cpus, balance);
+ group = find_busiest_group(&env, balance);
if (*balance == 0)
goto out_balanced;
@@ -4243,7 +4277,7 @@ redo:
goto out_balanced;
}
- busiest = find_busiest_queue(&env, group, cpus);
+ busiest = find_busiest_queue(&env, group);
if (!busiest) {
schedstat_inc(sd, lb_nobusyq[idle]);
goto out_balanced;
@@ -4254,6 +4288,7 @@ redo:
schedstat_add(sd, lb_imbalance[idle], env.imbalance);
ld_moved = 0;
+ lb_iterations = 1;
if (busiest->nr_running > 1) {
/*
* Attempt to move tasks. If find_busiest_group has found
@@ -4266,12 +4301,17 @@ redo:
env.src_rq = busiest;
env.loop_max = min(sysctl_sched_nr_migrate, busiest->nr_running);
+ update_h_load(env.src_cpu);
more_balance:
local_irq_save(flags);
double_rq_lock(this_rq, busiest);
- if (!env.loop)
- update_h_load(env.src_cpu);
- ld_moved += move_tasks(&env);
+
+ /*
+ * cur_ld_moved - load moved in current iteration
+ * ld_moved - cumulative load moved across iterations
+ */
+ cur_ld_moved = move_tasks(&env);
+ ld_moved += cur_ld_moved;
double_rq_unlock(this_rq, busiest);
local_irq_restore(flags);
@@ -4283,14 +4323,52 @@ more_balance:
/*
* some other cpu did the load balance for us.
*/
- if (ld_moved && this_cpu != smp_processor_id())
- resched_cpu(this_cpu);
+ if (cur_ld_moved && env.dst_cpu != smp_processor_id())
+ resched_cpu(env.dst_cpu);
+
+ /*
+ * Revisit (affine) tasks on src_cpu that couldn't be moved to
+ * us and move them to an alternate dst_cpu in our sched_group
+ * where they can run. The upper limit on how many times we
+ * iterate on same src_cpu is dependent on number of cpus in our
+ * sched_group.
+ *
+ * This changes load balance semantics a bit on who can move
+ * load to a given_cpu. In addition to the given_cpu itself
+ * (or a ilb_cpu acting on its behalf where given_cpu is
+ * nohz-idle), we now have balance_cpu in a position to move
+ * load to given_cpu. In rare situations, this may cause
+ * conflicts (balance_cpu and given_cpu/ilb_cpu deciding
+ * _independently_ and at _same_ time to move some load to
+ * given_cpu) causing exceess load to be moved to given_cpu.
+ * This however should not happen so much in practice and
+ * moreover subsequent load balance cycles should correct the
+ * excess load moved.
+ */
+ if ((env.flags & LBF_SOME_PINNED) && env.imbalance > 0 &&
+ lb_iterations++ < max_lb_iterations) {
+
+ this_rq = cpu_rq(env.new_dst_cpu);
+ env.dst_rq = this_rq;
+ env.dst_cpu = env.new_dst_cpu;
+ env.flags &= ~LBF_SOME_PINNED;
+ env.loop = 0;
+ env.loop_break = sched_nr_migrate_break;
+ /*
+ * Go back to "more_balance" rather than "redo" since we
+ * need to continue with same src_cpu.
+ */
+ goto more_balance;
+ }
/* All tasks on this runqueue were pinned by CPU affinity */
if (unlikely(env.flags & LBF_ALL_PINNED)) {
cpumask_clear_cpu(cpu_of(busiest), cpus);
- if (!cpumask_empty(cpus))
+ if (!cpumask_empty(cpus)) {
+ env.loop = 0;
+ env.loop_break = sched_nr_migrate_break;
goto redo;
+ }
goto out_balanced;
}
}
generated by cgit v1.2.3 (git 2.51.0) at 2025-09-25 09:03:56 +0000