aboutsummaryrefslogtreecommitdiff
path: root/kernel
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@woody.linux-foundation.org>2007-08-09 08:23:31 -0700
committerLinus Torvalds <torvalds@woody.linux-foundation.org>2007-08-09 08:23:31 -0700
commitbe12014dd7750648fde33e1e45cac24dc9a8be6d (patch)
treecaf9715d2c37f3c08c25e51c9f416c2bbf956236 /kernel
parente3bcf5e2785aa49f75f36a8d27d601891a7ff12b (diff)
parent7cff8cf61cac15fa29a1ca802826d2bcbca66152 (diff)
Merge git://git.kernel.org/pub/scm/linux/kernel/git/mingo/linux-2.6-sched
* git://git.kernel.org/pub/scm/linux/kernel/git/mingo/linux-2.6-sched: (61 commits) sched: refine negative nice level granularity sched: fix update_stats_enqueue() reniced codepath sched: round a bit better sched: make the multiplication table more accurate sched: optimize update_rq_clock() calls in the load-balancer sched: optimize activate_task() sched: clean up set_curr_task_fair() sched: remove __update_rq_clock() call from entity_tick() sched: move the __update_rq_clock() call to scheduler_tick() sched debug: remove the 'u64 now' parameter from print_task()/_rq() sched: remove the 'u64 now' local variables sched: remove the 'u64 now' parameter from deactivate_task() sched: remove the 'u64 now' parameter from dequeue_task() sched: remove the 'u64 now' parameter from enqueue_task() sched: remove the 'u64 now' parameter from dec_nr_running() sched: remove the 'u64 now' parameter from inc_nr_running() sched: remove the 'u64 now' parameter from dec_load() sched: remove the 'u64 now' parameter from inc_load() sched: remove the 'u64 now' parameter from update_curr_load() sched: remove the 'u64 now' parameter from ->task_new() ...
Diffstat (limited to 'kernel')
-rw-r--r--kernel/sched.c339
-rw-r--r--kernel/sched_debug.c16
-rw-r--r--kernel/sched_fair.c212
-rw-r--r--kernel/sched_idletask.c10
-rw-r--r--kernel/sched_rt.c48
5 files changed, 303 insertions, 322 deletions
diff --git a/kernel/sched.c b/kernel/sched.c
index 72bb9483d94..b0afd8db139 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -318,15 +318,19 @@ static inline int cpu_of(struct rq *rq)
}
/*
- * Per-runqueue clock, as finegrained as the platform can give us:
+ * Update the per-runqueue clock, as finegrained as the platform can give
+ * us, but without assuming monotonicity, etc.:
*/
-static unsigned long long __rq_clock(struct rq *rq)
+static void __update_rq_clock(struct rq *rq)
{
u64 prev_raw = rq->prev_clock_raw;
u64 now = sched_clock();
s64 delta = now - prev_raw;
u64 clock = rq->clock;
+#ifdef CONFIG_SCHED_DEBUG
+ WARN_ON_ONCE(cpu_of(rq) != smp_processor_id());
+#endif
/*
* Protect against sched_clock() occasionally going backwards:
*/
@@ -349,18 +353,12 @@ static unsigned long long __rq_clock(struct rq *rq)
rq->prev_clock_raw = now;
rq->clock = clock;
-
- return clock;
}
-static inline unsigned long long rq_clock(struct rq *rq)
+static void update_rq_clock(struct rq *rq)
{
- int this_cpu = smp_processor_id();
-
- if (this_cpu == cpu_of(rq))
- return __rq_clock(rq);
-
- return rq->clock;
+ if (likely(smp_processor_id() == cpu_of(rq)))
+ __update_rq_clock(rq);
}
/*
@@ -386,9 +384,12 @@ unsigned long long cpu_clock(int cpu)
{
unsigned long long now;
unsigned long flags;
+ struct rq *rq;
local_irq_save(flags);
- now = rq_clock(cpu_rq(cpu));
+ rq = cpu_rq(cpu);
+ update_rq_clock(rq);
+ now = rq->clock;
local_irq_restore(flags);
return now;
@@ -637,6 +638,11 @@ static u64 div64_likely32(u64 divident, unsigned long divisor)
#define WMULT_SHIFT 32
+/*
+ * Shift right and round:
+ */
+#define RSR(x, y) (((x) + (1UL << ((y) - 1))) >> (y))
+
static unsigned long
calc_delta_mine(unsigned long delta_exec, unsigned long weight,
struct load_weight *lw)
@@ -644,18 +650,17 @@ calc_delta_mine(unsigned long delta_exec, unsigned long weight,
u64 tmp;
if (unlikely(!lw->inv_weight))
- lw->inv_weight = WMULT_CONST / lw->weight;
+ lw->inv_weight = (WMULT_CONST - lw->weight/2) / lw->weight + 1;
tmp = (u64)delta_exec * weight;
/*
* Check whether we'd overflow the 64-bit multiplication:
*/
- if (unlikely(tmp > WMULT_CONST)) {
- tmp = ((tmp >> WMULT_SHIFT/2) * lw->inv_weight)
- >> (WMULT_SHIFT/2);
- } else {
- tmp = (tmp * lw->inv_weight) >> WMULT_SHIFT;
- }
+ if (unlikely(tmp > WMULT_CONST))
+ tmp = RSR(RSR(tmp, WMULT_SHIFT/2) * lw->inv_weight,
+ WMULT_SHIFT/2);
+ else
+ tmp = RSR(tmp * lw->inv_weight, WMULT_SHIFT);
return (unsigned long)min(tmp, (u64)(unsigned long)LONG_MAX);
}
@@ -703,11 +708,14 @@ static void update_load_sub(struct load_weight *lw, unsigned long dec)
* the relative distance between them is ~25%.)
*/
static const int prio_to_weight[40] = {
-/* -20 */ 88818, 71054, 56843, 45475, 36380, 29104, 23283, 18626, 14901, 11921,
-/* -10 */ 9537, 7629, 6103, 4883, 3906, 3125, 2500, 2000, 1600, 1280,
-/* 0 */ NICE_0_LOAD /* 1024 */,
-/* 1 */ 819, 655, 524, 419, 336, 268, 215, 172, 137,
-/* 10 */ 110, 87, 70, 56, 45, 36, 29, 23, 18, 15,
+ /* -20 */ 88761, 71755, 56483, 46273, 36291,
+ /* -15 */ 29154, 23254, 18705, 14949, 11916,
+ /* -10 */ 9548, 7620, 6100, 4904, 3906,
+ /* -5 */ 3121, 2501, 1991, 1586, 1277,
+ /* 0 */ 1024, 820, 655, 526, 423,
+ /* 5 */ 335, 272, 215, 172, 137,
+ /* 10 */ 110, 87, 70, 56, 45,
+ /* 15 */ 36, 29, 23, 18, 15,
};
/*
@@ -718,14 +726,14 @@ static const int prio_to_weight[40] = {
* into multiplications:
*/
static const u32 prio_to_wmult[40] = {
-/* -20 */ 48356, 60446, 75558, 94446, 118058,
-/* -15 */ 147573, 184467, 230589, 288233, 360285,
-/* -10 */ 450347, 562979, 703746, 879575, 1099582,
-/* -5 */ 1374389, 1717986, 2147483, 2684354, 3355443,
-/* 0 */ 4194304, 5244160, 6557201, 8196502, 10250518,
-/* 5 */ 12782640, 16025997, 19976592, 24970740, 31350126,
-/* 10 */ 39045157, 49367440, 61356675, 76695844, 95443717,
-/* 15 */ 119304647, 148102320, 186737708, 238609294, 286331153,
+ /* -20 */ 48388, 59856, 76040, 92818, 118348,
+ /* -15 */ 147320, 184698, 229616, 287308, 360437,
+ /* -10 */ 449829, 563644, 704093, 875809, 1099582,
+ /* -5 */ 1376151, 1717300, 2157191, 2708050, 3363326,
+ /* 0 */ 4194304, 5237765, 6557202, 8165337, 10153587,
+ /* 5 */ 12820798, 15790321, 19976592, 24970740, 31350126,
+ /* 10 */ 39045157, 49367440, 61356676, 76695844, 95443717,
+ /* 15 */ 119304647, 148102320, 186737708, 238609294, 286331153,
};
static void activate_task(struct rq *rq, struct task_struct *p, int wakeup);
@@ -745,8 +753,7 @@ static int balance_tasks(struct rq *this_rq, int this_cpu, struct rq *busiest,
unsigned long max_nr_move, unsigned long max_load_move,
struct sched_domain *sd, enum cpu_idle_type idle,
int *all_pinned, unsigned long *load_moved,
- int this_best_prio, int best_prio, int best_prio_seen,
- struct rq_iterator *iterator);
+ int *this_best_prio, struct rq_iterator *iterator);
#include "sched_stats.h"
#include "sched_rt.c"
@@ -782,14 +789,14 @@ static void __update_curr_load(struct rq *rq, struct load_stat *ls)
* This function is called /before/ updating rq->ls.load
* and when switching tasks.
*/
-static void update_curr_load(struct rq *rq, u64 now)
+static void update_curr_load(struct rq *rq)
{
struct load_stat *ls = &rq->ls;
u64 start;
start = ls->load_update_start;
- ls->load_update_start = now;
- ls->delta_stat += now - start;
+ ls->load_update_start = rq->clock;
+ ls->delta_stat += rq->clock - start;
/*
* Stagger updates to ls->delta_fair. Very frequent updates
* can be expensive.
@@ -798,30 +805,28 @@ static void update_curr_load(struct rq *rq, u64 now)
__update_curr_load(rq, ls);
}
-static inline void
-inc_load(struct rq *rq, const struct task_struct *p, u64 now)
+static inline void inc_load(struct rq *rq, const struct task_struct *p)
{
- update_curr_load(rq, now);
+ update_curr_load(rq);
update_load_add(&rq->ls.load, p->se.load.weight);
}
-static inline void
-dec_load(struct rq *rq, const struct task_struct *p, u64 now)
+static inline void dec_load(struct rq *rq, const struct task_struct *p)
{
- update_curr_load(rq, now);
+ update_curr_load(rq);
update_load_sub(&rq->ls.load, p->se.load.weight);
}
-static void inc_nr_running(struct task_struct *p, struct rq *rq, u64 now)
+static void inc_nr_running(struct task_struct *p, struct rq *rq)
{
rq->nr_running++;
- inc_load(rq, p, now);
+ inc_load(rq, p);
}
-static void dec_nr_running(struct task_struct *p, struct rq *rq, u64 now)
+static void dec_nr_running(struct task_struct *p, struct rq *rq)
{
rq->nr_running--;
- dec_load(rq, p, now);
+ dec_load(rq, p);
}
static void set_load_weight(struct task_struct *p)
@@ -848,18 +853,16 @@ static void set_load_weight(struct task_struct *p)
p->se.load.inv_weight = prio_to_wmult[p->static_prio - MAX_RT_PRIO];
}
-static void
-enqueue_task(struct rq *rq, struct task_struct *p, int wakeup, u64 now)
+static void enqueue_task(struct rq *rq, struct task_struct *p, int wakeup)
{
sched_info_queued(p);
- p->sched_class->enqueue_task(rq, p, wakeup, now);
+ p->sched_class->enqueue_task(rq, p, wakeup);
p->se.on_rq = 1;
}
-static void
-dequeue_task(struct rq *rq, struct task_struct *p, int sleep, u64 now)
+static void dequeue_task(struct rq *rq, struct task_struct *p, int sleep)
{
- p->sched_class->dequeue_task(rq, p, sleep, now);
+ p->sched_class->dequeue_task(rq, p, sleep);
p->se.on_rq = 0;
}
@@ -914,13 +917,11 @@ static int effective_prio(struct task_struct *p)
*/
static void activate_task(struct rq *rq, struct task_struct *p, int wakeup)
{
- u64 now = rq_clock(rq);
-
if (p->state == TASK_UNINTERRUPTIBLE)
rq->nr_uninterruptible--;
- enqueue_task(rq, p, wakeup, now);
- inc_nr_running(p, rq, now);
+ enqueue_task(rq, p, wakeup);
+ inc_nr_running(p, rq);
}
/*
@@ -928,13 +929,13 @@ static void activate_task(struct rq *rq, struct task_struct *p, int wakeup)
*/
static inline void activate_idle_task(struct task_struct *p, struct rq *rq)
{
- u64 now = rq_clock(rq);
+ update_rq_clock(rq);
if (p->state == TASK_UNINTERRUPTIBLE)
rq->nr_uninterruptible--;
- enqueue_task(rq, p, 0, now);
- inc_nr_running(p, rq, now);
+ enqueue_task(rq, p, 0);
+ inc_nr_running(p, rq);
}
/*
@@ -942,13 +943,11 @@ static inline void activate_idle_task(struct task_struct *p, struct rq *rq)
*/
static void deactivate_task(struct rq *rq, struct task_struct *p, int sleep)
{
- u64 now = rq_clock(rq);
-
if (p->state == TASK_UNINTERRUPTIBLE)
rq->nr_uninterruptible++;
- dequeue_task(rq, p, sleep, now);
- dec_nr_running(p, rq, now);
+ dequeue_task(rq, p, sleep);
+ dec_nr_running(p, rq);
}
/**
@@ -1516,6 +1515,7 @@ out_set_cpu:
out_activate:
#endif /* CONFIG_SMP */
+ update_rq_clock(rq);
activate_task(rq, p, 1);
/*
* Sync wakeups (i.e. those types of wakeups where the waker
@@ -1647,12 +1647,11 @@ void fastcall wake_up_new_task(struct task_struct *p, unsigned long clone_flags)
unsigned long flags;
struct rq *rq;
int this_cpu;
- u64 now;
rq = task_rq_lock(p, &flags);
BUG_ON(p->state != TASK_RUNNING);
this_cpu = smp_processor_id(); /* parent's CPU */
- now = rq_clock(rq);
+ update_rq_clock(rq);
p->prio = effective_prio(p);
@@ -1666,8 +1665,8 @@ void fastcall wake_up_new_task(struct task_struct *p, unsigned long clone_flags)
* Let the scheduling class do new task startup
* management (if any):
*/
- p->sched_class->task_new(rq, p, now);
- inc_nr_running(p, rq, now);
+ p->sched_class->task_new(rq, p);
+ inc_nr_running(p, rq);
}
check_preempt_curr(rq, p);
task_rq_unlock(rq, &flags);
@@ -1954,7 +1953,6 @@ static void update_cpu_load(struct rq *this_rq)
unsigned long total_load = this_rq->ls.load.weight;
unsigned long this_load = total_load;
struct load_stat *ls = &this_rq->ls;
- u64 now = __rq_clock(this_rq);
int i, scale;
this_rq->nr_load_updates++;
@@ -1962,7 +1960,7 @@ static void update_cpu_load(struct rq *this_rq)
goto do_avg;
/* Update delta_fair/delta_exec fields first */
- update_curr_load(this_rq, now);
+ update_curr_load(this_rq);
fair_delta64 = ls->delta_fair + 1;
ls->delta_fair = 0;
@@ -1970,8 +1968,8 @@ static void update_cpu_load(struct rq *this_rq)
exec_delta64 = ls->delta_exec + 1;
ls->delta_exec = 0;
- sample_interval64 = now - ls->load_update_last;
- ls->load_update_last = now;
+ sample_interval64 = this_rq->clock - ls->load_update_last;
+ ls->load_update_last = this_rq->clock;
if ((s64)sample_interval64 < (s64)TICK_NSEC)
sample_interval64 = TICK_NSEC;
@@ -2026,6 +2024,8 @@ static void double_rq_lock(struct rq *rq1, struct rq *rq2)
spin_lock(&rq1->lock);
}
}
+ update_rq_clock(rq1);
+ update_rq_clock(rq2);
}
/*
@@ -2166,8 +2166,7 @@ static int balance_tasks(struct rq *this_rq, int this_cpu, struct rq *busiest,
unsigned long max_nr_move, unsigned long max_load_move,
struct sched_domain *sd, enum cpu_idle_type idle,
int *all_pinned, unsigned long *load_moved,
- int this_best_prio, int best_prio, int best_prio_seen,
- struct rq_iterator *iterator)
+ int *this_best_prio, struct rq_iterator *iterator)
{
int pulled = 0, pinned = 0, skip_for_load;
struct task_struct *p;
@@ -2192,12 +2191,8 @@ next:
*/
skip_for_load = (p->se.load.weight >> 1) > rem_load_move +
SCHED_LOAD_SCALE_FUZZ;
- if (skip_for_load && p->prio < this_best_prio)
- skip_for_load = !best_prio_seen && p->prio == best_prio;
- if (skip_for_load ||
+ if ((skip_for_load && p->prio >= *this_best_prio) ||
!can_migrate_task(p, busiest, this_cpu, sd, idle, &pinned)) {
-
- best_prio_seen |= p->prio == best_prio;
p = iterator->next(iterator->arg);
goto next;
}
@@ -2211,8 +2206,8 @@ next:
* and the prescribed amount of weighted load.
*/
if (pulled < max_nr_move && rem_load_move > 0) {
- if (p->prio < this_best_prio)
- this_best_prio = p->prio;
+ if (p->prio < *this_best_prio)
+ *this_best_prio = p->prio;
p = iterator->next(iterator->arg);
goto next;
}
@@ -2231,32 +2226,52 @@ out:
}
/*
- * move_tasks tries to move up to max_nr_move tasks and max_load_move weighted
- * load from busiest to this_rq, as part of a balancing operation within
- * "domain". Returns the number of tasks moved.
+ * move_tasks tries to move up to max_load_move weighted load from busiest to
+ * this_rq, as part of a balancing operation within domain "sd".
+ * Returns 1 if successful and 0 otherwise.
*
* Called with both runqueues locked.
*/
static int move_tasks(struct rq *this_rq, int this_cpu, struct rq *busiest,
- unsigned long max_nr_move, unsigned long max_load_move,
+ unsigned long max_load_move,
struct sched_domain *sd, enum cpu_idle_type idle,
int *all_pinned)
{
struct sched_class *class = sched_class_highest;
- unsigned long load_moved, total_nr_moved = 0, nr_moved;
- long rem_load_move = max_load_move;
+ unsigned long total_load_moved = 0;
+ int this_best_prio = this_rq->curr->prio;
do {
- nr_moved = class->load_balance(this_rq, this_cpu, busiest,
- max_nr_move, (unsigned long)rem_load_move,
- sd, idle, all_pinned, &load_moved);
- total_nr_moved += nr_moved;
- max_nr_move -= nr_moved;
- rem_load_move -= load_moved;
+ total_load_moved +=
+ class->load_balance(this_rq, this_cpu, busiest,
+ ULONG_MAX, max_load_move - total_load_moved,
+ sd, idle, all_pinned, &this_best_prio);
class = class->next;
- } while (class && max_nr_move && rem_load_move > 0);
+ } while (class && max_load_move > total_load_moved);
- return total_nr_moved;
+ return total_load_moved > 0;
+}
+
+/*
+ * move_one_task tries to move exactly one task from busiest to this_rq, as
+ * part of active balancing operations within "domain".
+ * Returns 1 if successful and 0 otherwise.
+ *
+ * Called with both runqueues locked.
+ */
+static int move_one_task(struct rq *this_rq, int this_cpu, struct rq *busiest,
+ struct sched_domain *sd, enum cpu_idle_type idle)
+{
+ struct sched_class *class;
+ int this_best_prio = MAX_PRIO;
+
+ for (class = sched_class_highest; class; class = class->next)
+ if (class->load_balance(this_rq, this_cpu, busiest,
+ 1, ULONG_MAX, sd, idle, NULL,
+ &this_best_prio))
+ return 1;
+
+ return 0;
}
/*
@@ -2588,11 +2603,6 @@ find_busiest_queue(struct sched_group *group, enum cpu_idle_type idle,
*/
#define MAX_PINNED_INTERVAL 512
-static inline unsigned long minus_1_or_zero(unsigned long n)
-{
- return n > 0 ? n - 1 : 0;
-}
-
/*
* Check this_cpu to ensure it is balanced within domain. Attempt to move
* tasks if there is an imbalance.
@@ -2601,7 +2611,7 @@ static int load_balance(int this_cpu, struct rq *this_rq,
struct sched_domain *sd, enum cpu_idle_type idle,
int *balance)
{
- int nr_moved, all_pinned = 0, active_balance = 0, sd_idle = 0;
+ int ld_moved, all_pinned = 0, active_balance = 0, sd_idle = 0;
struct sched_group *group;
unsigned long imbalance;
struct rq *busiest;
@@ -2642,18 +2652,17 @@ redo:
schedstat_add(sd, lb_imbalance[idle], imbalance);
- nr_moved = 0;
+ ld_moved = 0;
if (busiest->nr_running > 1) {
/*
* Attempt to move tasks. If find_busiest_group has found
* an imbalance but busiest->nr_running <= 1, the group is
- * still unbalanced. nr_moved simply stays zero, so it is
+ * still unbalanced. ld_moved simply stays zero, so it is
* correctly treated as an imbalance.
*/
local_irq_save(flags);
double_rq_lock(this_rq, busiest);
- nr_moved = move_tasks(this_rq, this_cpu, busiest,
- minus_1_or_zero(busiest->nr_running),
+ ld_moved = move_tasks(this_rq, this_cpu, busiest,
imbalance, sd, idle, &all_pinned);
double_rq_unlock(this_rq, busiest);
local_irq_restore(flags);
@@ -2661,7 +2670,7 @@ redo:
/*
* some other cpu did the load balance for us.
*/
- if (nr_moved && this_cpu != smp_processor_id())
+ if (ld_moved && this_cpu != smp_processor_id())
resched_cpu(this_cpu);
/* All tasks on this runqueue were pinned by CPU affinity */
@@ -2673,7 +2682,7 @@ redo:
}
}
- if (!nr_moved) {
+ if (!ld_moved) {
schedstat_inc(sd, lb_failed[idle]);
sd->nr_balance_failed++;
@@ -2722,10 +2731,10 @@ redo:
sd->balance_interval *= 2;
}
- if (!nr_moved && !sd_idle && sd->flags & SD_SHARE_CPUPOWER &&
+ if (!ld_moved && !sd_idle && sd->flags & SD_SHARE_CPUPOWER &&
!test_sd_parent(sd, SD_POWERSAVINGS_BALANCE))
return -1;
- return nr_moved;
+ return ld_moved;
out_balanced:
schedstat_inc(sd, lb_balanced[idle]);
@@ -2757,7 +2766,7 @@ load_balance_newidle(int this_cpu, struct rq *this_rq, struct sched_domain *sd)
struct sched_group *group;
struct rq *busiest = NULL;
unsigned long imbalance;
- int nr_moved = 0;
+ int ld_moved = 0;
int sd_idle = 0;
int all_pinned = 0;
cpumask_t cpus = CPU_MASK_ALL;
@@ -2792,12 +2801,13 @@ redo:
schedstat_add(sd, lb_imbalance[CPU_NEWLY_IDLE], imbalance);
- nr_moved = 0;
+ ld_moved = 0;
if (busiest->nr_running > 1) {
/* Attempt to move tasks */
double_lock_balance(this_rq, busiest);
- nr_moved = move_tasks(this_rq, this_cpu, busiest,
- minus_1_or_zero(busiest->nr_running),
+ /* this_rq->clock is already updated */
+ update_rq_clock(busiest);
+ ld_moved = move_tasks(this_rq, this_cpu, busiest,
imbalance, sd, CPU_NEWLY_IDLE,
&all_pinned);
spin_unlock(&busiest->lock);
@@ -2809,7 +2819,7 @@ redo:
}
}
- if (!nr_moved) {
+ if (!ld_moved) {
schedstat_inc(sd, lb_failed[CPU_NEWLY_IDLE]);
if (!sd_idle && sd->flags & SD_SHARE_CPUPOWER &&
!test_sd_parent(sd, SD_POWERSAVINGS_BALANCE))
@@ -2817,7 +2827,7 @@ redo:
} else
sd->nr_balance_failed = 0;
- return nr_moved;
+ return ld_moved;
out_balanced:
schedstat_inc(sd, lb_balanced[CPU_NEWLY_IDLE]);
@@ -2894,6 +2904,8 @@ static void active_load_balance(struct rq *busiest_rq, int busiest_cpu)
/* move a task from busiest_rq to target_rq */
double_lock_balance(busiest_rq, target_rq);
+ update_rq_clock(busiest_rq);
+ update_rq_clock(target_rq);
/* Search for an sd spanning us and the target CPU. */
for_each_domain(target_cpu, sd) {
@@ -2905,8 +2917,8 @@ static void active_load_balance(struct rq *busiest_rq, int busiest_cpu)
if (likely(sd)) {
schedstat_inc(sd, alb_cnt);
- if (move_tasks(target_rq, target_cpu, busiest_rq, 1,
- ULONG_MAX, sd, CPU_IDLE, NULL))
+ if (move_one_task(target_rq, target_cpu, busiest_rq,
+ sd, CPU_IDLE))
schedstat_inc(sd, alb_pushed);
else
schedstat_inc(sd, alb_failed);
@@ -3175,8 +3187,7 @@ static int balance_tasks(struct rq *this_rq, int this_cpu, struct rq *busiest,
unsigned long max_nr_move, unsigned long max_load_move,
struct sched_domain *sd, enum cpu_idle_type idle,
int *all_pinned, unsigned long *load_moved,
- int this_best_prio, int best_prio, int best_prio_seen,
- struct rq_iterator *iterator)
+ int *this_best_prio, struct rq_iterator *iterator)
{
*load_moved = 0;
@@ -3202,7 +3213,8 @@ unsigned long long task_sched_runtime(struct task_struct *p)
rq = task_rq_lock(p, &flags);
ns = p->se.sum_exec_runtime;
if (rq->curr == p) {
- delta_exec = rq_clock(rq) - p->se.exec_start;
+ update_rq_clock(rq);
+ delta_exec = rq->clock - p->se.exec_start;
if ((s64)delta_exec > 0)
ns += delta_exec;
}
@@ -3298,9 +3310,10 @@ void scheduler_tick(void)
struct task_struct *curr = rq->curr;
spin_lock(&rq->lock);
+ __update_rq_clock(rq);
+ update_cpu_load(rq);
if (curr != rq->idle) /* FIXME: needed? */
curr->sched_class->task_tick(rq, curr);
- update_cpu_load(rq);
spin_unlock(&rq->lock);
#ifdef CONFIG_SMP
@@ -3382,7 +3395,7 @@ static inline void schedule_debug(struct task_struct *prev)
* Pick up the highest-prio task:
*/
static inline struct task_struct *
-pick_next_task(struct rq *rq, struct task_struct *prev, u64 now)
+pick_next_task(struct rq *rq, struct task_struct *prev)
{
struct sched_class *class;
struct task_struct *p;
@@ -3392,14 +3405,14 @@ pick_next_task(struct rq *rq, struct task_struct *prev, u64 now)
* the fair class we can call that function directly:
*/
if (likely(rq->nr_running == rq->cfs.nr_running)) {
- p = fair_sched_class.pick_next_task(rq, now);
+ p = fair_sched_class.pick_next_task(rq);
if (likely(p))
return p;
}
class = sched_class_highest;
for ( ; ; ) {
- p = class->pick_next_task(rq, now);
+ p = class->pick_next_task(rq);
if (p)
return p;
/*
@@ -3418,7 +3431,6 @@ asmlinkage void __sched schedule(void)
struct task_struct *prev, *next;
long *switch_count;
struct rq *rq;
- u64 now;
int cpu;
need_resched:
@@ -3436,6 +3448,7 @@ need_resched_nonpreemptible:
spin_lock_irq(&rq->lock);
clear_tsk_need_resched(prev);
+ __update_rq_clock(rq);
if (prev->state && !(preempt_count() & PREEMPT_ACTIVE)) {
if (unlikely((prev->state & TASK_INTERRUPTIBLE) &&
@@ -3450,9 +3463,8 @@ need_resched_nonpreemptible:
if (unlikely(!rq->nr_running))
idle_balance(cpu, rq);
- now = __rq_clock(rq);
- prev->sched_class->put_prev_task(rq, prev, now);
- next = pick_next_task(rq, prev, now);
+ prev->sched_class->put_prev_task(rq, prev);
+ next = pick_next_task(rq, prev);
sched_info_switch(prev, next);
@@ -3895,17 +3907,16 @@ void rt_mutex_setprio(struct task_struct *p, int prio)
unsigned long flags;
int oldprio, on_rq;
struct rq *rq;
- u64 now;
BUG_ON(prio < 0 || prio > MAX_PRIO);
rq = task_rq_lock(p, &flags);
- now = rq_clock(rq);
+ update_rq_clock(rq);
oldprio = p->prio;
on_rq = p->se.on_rq;
if (on_rq)
- dequeue_task(rq, p, 0, now);
+ dequeue_task(rq, p, 0);
if (rt_prio(prio))
p->sched_class = &rt_sched_class;
@@ -3915,7 +3926,7 @@ void rt_mutex_setprio(struct task_struct *p, int prio)
p->prio = prio;
if (on_rq) {
- enqueue_task(rq, p, 0, now);
+ enqueue_task(rq, p, 0);
/*
* Reschedule if we are currently running on this runqueue and
* our priority decreased, or if we are not currently running on
@@ -3938,7 +3949,6 @@ void set_user_nice(struct task_struct *p, long nice)
int old_prio, delta, on_rq;
unsigned long flags;
struct rq *rq;
- u64 now;
if (TASK_NICE(p) == nice || nice < -20 || nice > 19)
return;
@@ -3947,7 +3957,7 @@ void set_user_nice(struct task_struct *p, long nice)
* the task might be in the middle of scheduling on another CPU.
*/
rq = task_rq_lock(p, &flags);
- now = rq_clock(rq);
+ update_rq_clock(rq);
/*
* The RT priorities are set via sched_setscheduler(), but we still
* allow the 'normal' nice value to be set - but as expected
@@ -3960,8 +3970,8 @@ void set_user_nice(struct task_struct *p, long nice)
}
on_rq = p->se.on_rq;
if (on_rq) {
- dequeue_task(rq, p, 0, now);
- dec_load(rq, p, now);
+ dequeue_task(rq, p, 0);
+ dec_load(rq, p);
}
p->static_prio = NICE_TO_PRIO(nice);
@@ -3971,8 +3981,8 @@ void set_user_nice(struct task_struct *p, long nice)
delta = p->prio - old_prio;
if (on_rq) {
- enqueue_task(rq, p, 0, now);
- inc_load(rq, p, now);
+ enqueue_task(rq, p, 0);
+ inc_load(rq, p);
/*
* If the task increased its priority or is running and
* lowered its priority, then reschedule its CPU:
@@ -4208,6 +4218,7 @@ recheck:
spin_unlock_irqrestore(&p->pi_lock, flags);
goto recheck;
}
+ update_rq_clock(rq);
on_rq = p->se.on_rq;
if (on_rq)
deactivate_task(rq, p, 0);
@@ -4463,10 +4474,8 @@ long sched_getaffinity(pid_t pid, cpumask_t *mask)
out_unlock:
read_unlock(&tasklist_lock);
mutex_unlock(&sched_hotcpu_mutex);
- if (retval)
- return retval;
- return 0;
+ return retval;
}
/**
@@ -4966,6 +4975,7 @@ static int __migrate_task(struct task_struct *p, int src_cpu, int dest_cpu)
on_rq = p->se.on_rq;
if (on_rq)
deactivate_task(rq_src, p, 0);
+
set_task_cpu(p, dest_cpu);
if (on_rq) {
activate_task(rq_dest, p, 0);
@@ -5198,7 +5208,8 @@ static void migrate_dead_tasks(unsigned int dead_cpu)
for ( ; ; ) {
if (!rq->nr_running)
break;
- next = pick_next_task(rq, rq->curr, rq_clock(rq));
+ update_rq_clock(rq);
+ next = pick_next_task(rq, rq->curr);
if (!next)
break;
migrate_dead(dead_cpu, next);
@@ -5210,12 +5221,19 @@ static void migrate_dead_tasks(unsigned int dead_cpu)
#if defined(CONFIG_SCHED_DEBUG) && defined(CONFIG_SYSCTL)
static struct ctl_table sd_ctl_dir[] = {
- {CTL_UNNUMBERED, "sched_domain", NULL, 0, 0755, NULL, },
+ {
+ .procname = "sched_domain",
+ .mode = 0755,
+ },
{0,},
};
static struct ctl_table sd_ctl_root[] = {
- {CTL_UNNUMBERED, "kernel", NULL, 0, 0755, sd_ctl_dir, },
+ {
+ .procname = "kernel",
+ .mode = 0755,
+ .child = sd_ctl_dir,
+ },
{0,},
};
@@ -5231,11 +5249,10 @@ static struct ctl_table *sd_alloc_ctl_entry(int n)
}
static void
-set_table_entry(struct ctl_table *entry, int ctl_name,
+set_table_entry(struct ctl_table *entry,
const char *procname, void *data, int maxlen,
mode_t mode, proc_handler *proc_handler)
{
- entry->ctl_name = ctl_name;
entry->procname = procname;
entry->data = data;
entry->maxlen = maxlen;
@@ -5248,28 +5265,28 @@ sd_alloc_ctl_domain_table(struct sched_domain *sd)
{
struct ctl_table *table = sd_alloc_ctl_entry(14);
- set_table_entry(&table[0], 1, "min_interval", &sd->min_interval,
+ set_table_entry(&table[0], "min_interval", &sd->min_interval,
sizeof(long), 0644, proc_doulongvec_minmax);
- set_table_entry(&table[1], 2, "max_interval", &sd->max_interval,
+ set_table_entry(&table[1], "max_interval", &sd->max_interval,
sizeof(long), 0644, proc_doulongvec_minmax);
- set_table_entry(&table[2], 3, "busy_idx", &sd->busy_idx,
+ set_table_entry(&table[2], "busy_idx", &sd->busy_idx,
sizeof(int), 0644, proc_dointvec_minmax);
- set_table_entry(&table[3], 4, "idle_idx", &sd->idle_idx,
+ set_table_entry(&table[3], "idle_idx", &sd->idle_idx,
sizeof(int), 0644, proc_dointvec_minmax);
- set_table_entry(&table[4], 5, "newidle_idx", &sd->newidle_idx,
+ set_table_entry(&table[4], "newidle_idx", &sd->newidle_idx,
sizeof(int), 0644, proc_dointvec_minmax);
- set_table_entry(&table[5], 6, "wake_idx", &sd->wake_idx,
+ set_table_entry(&table[5], "wake_idx", &sd->wake_idx,
sizeof(int), 0644, proc_dointvec_minmax);
- set_table_entry(&table[6], 7, "forkexec_idx", &sd->forkexec_idx,
+ set_table_entry(&table[6], "forkexec_idx", &sd->forkexec_idx,
sizeof(int), 0644, proc_dointvec_minmax);
- set_table_entry(&table[7], 8, "busy_factor", &sd->busy_factor,
+ set_table_entry(&table[7], "busy_factor", &sd->busy_factor,
sizeof(int), 0644, proc_dointvec_minmax);
- set_table_entry(&table[8], 9, "imbalance_pct", &sd->imbalance_pct,
+ set_table_entry(&table[8], "imbalance_pct", &sd->imbalance_pct,
sizeof(int), 0644, proc_dointvec_minmax);
- set_table_entry(&table[10], 11, "cache_nice_tries",
+ set_table_entry(&table[10], "cache_nice_tries",
&sd->cache_nice_tries,
sizeof(int), 0644, proc_dointvec_minmax);
- set_table_entry(&table[12], 13, "flags", &sd->flags,
+ set_table_entry(&table[12], "flags", &sd->flags,
sizeof(int), 0644, proc_dointvec_minmax);
return table;
@@ -5289,7 +5306,6 @@ static ctl_table *sd_alloc_ctl_cpu_table(int cpu)
i = 0;
for_each_domain(cpu, sd) {
snprintf(buf, 32, "domain%d", i);
- entry->ctl_name = i + 1;
entry->procname = kstrdup(buf, GFP_KERNEL);
entry->mode = 0755;
entry->child = sd_alloc_ctl_domain_table(sd);
@@ -5310,7 +5326,6 @@ static void init_sched_domain_sysctl(void)
for (i = 0; i < cpu_num; i++, entry++) {
snprintf(buf, 32, "cpu%d", i);
- entry->ctl_name = i + 1;
entry->procname = kstrdup(buf, GFP_KERNEL);
entry->mode = 0755;
entry->child = sd_alloc_ctl_cpu_table(i);
@@ -5379,6 +5394,7 @@ migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu)
rq->migration_thread = NULL;
/* Idle task back to normal (off runqueue, low prio) */
rq = task_rq_lock(rq->idle, &flags);
+ update_rq_clock(rq);
deactivate_task(rq, rq->idle, 0);
rq->idle->static_prio = MAX_PRIO;
__setscheduler(rq, rq->idle, SCHED_NORMAL, 0);
@@ -6616,12 +6632,13 @@ void normalize_rt_tasks(void)
goto out_unlock;
#endif
+ update_rq_clock(rq);
on_rq = p->se.on_rq;
if (on_rq)
- deactivate_task(task_rq(p), p, 0);
+ deactivate_task(rq, p, 0);
__setscheduler(rq, p, SCHED_NORMAL, 0);
if (on_rq) {
- activate_task(task_rq(p), p, 0);
+ activate_task(rq, p, 0);
resched_task(rq->curr);
}
#ifdef CONFIG_SMP
diff --git a/kernel/sched_debug.c b/kernel/sched_debug.c
index 8421b9399e1..3da32156394 100644
--- a/kernel/sched_debug.c
+++ b/kernel/sched_debug.c
@@ -29,7 +29,7 @@
} while (0)
static void
-print_task(struct seq_file *m, struct rq *rq, struct task_struct *p, u64 now)
+print_task(struct seq_file *m, struct rq *rq, struct task_struct *p)
{
if (rq->curr == p)
SEQ_printf(m, "R");
@@ -56,7 +56,7 @@ print_task(struct seq_file *m, struct rq *rq, struct task_struct *p, u64 now)
#endif
}
-static void print_rq(struct seq_file *m, struct rq *rq, int rq_cpu, u64 now)
+static void print_rq(struct seq_file *m, struct rq *rq, int rq_cpu)
{
struct task_struct *g, *p;
@@ -77,7 +77,7 @@ static void print_rq(struct seq_file *m, struct rq *rq, int rq_cpu, u64 now)
if (!p->se.on_rq || task_cpu(p) != rq_cpu)
continue;
- print_task(m, rq, p, now);
+ print_task(m, rq, p);
} while_each_thread(g, p);
read_unlock_irq(&tasklist_lock);
@@ -106,7 +106,7 @@ print_cfs_rq_runtime_sum(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq)
(long long)wait_runtime_rq_sum);
}
-void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq, u64 now)
+void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq)
{
SEQ_printf(m, "\ncfs_rq %p\n", cfs_rq);
@@ -124,7 +124,7 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq, u64 now)
print_cfs_rq_runtime_sum(m, cpu, cfs_rq);
}
-static void print_cpu(struct seq_file *m, int cpu, u64 now)
+static void print_cpu(struct seq_file *m, int cpu)
{
struct rq *rq = &per_cpu(runqueues, cpu);
@@ -166,9 +166,9 @@ static void print_cpu(struct seq_file *m, int cpu, u64 now)
P(cpu_load[4]);
#undef P
- print_cfs_stats(m, cpu, now);
+ print_cfs_stats(m, cpu);
- print_rq(m, rq, cpu, now);
+ print_rq(m, rq, cpu);
}
static int sched_debug_show(struct seq_file *m, void *v)
@@ -184,7 +184,7 @@ static int sched_debug_show(struct seq_file *m, void *v)
SEQ_printf(m, "now at %Lu nsecs\n", (unsigned long long)now);
for_each_online_cpu(cpu)
- print_cpu(m, cpu, now);
+ print_cpu(m, cpu);
SEQ_printf(m, "\n");
diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index 6f579ff5a9b..e91db32cadf 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -222,21 +222,25 @@ niced_granularity(struct sched_entity *curr, unsigned long granularity)
{
u64 tmp;
+ if (likely(curr->load.weight == NICE_0_LOAD))
+ return granularity;
/*
- * Negative nice levels get the same granularity as nice-0:
+ * Positive nice levels get the same granularity as nice-0:
*/
- if (likely(curr->load.weight >= NICE_0_LOAD))
- return granularity;
+ if (likely(curr->load.weight < NICE_0_LOAD)) {
+ tmp = curr->load.weight * (u64)granularity;
+ return (long) (tmp >> NICE_0_SHIFT);
+ }
/*
- * Positive nice level tasks get linearly finer
+ * Negative nice level tasks get linearly finer
* granularity:
*/
- tmp = curr->load.weight * (u64)granularity;
+ tmp = curr->load.inv_weight * (u64)granularity;
/*
* It will always fit into 'long':
*/
- return (long) (tmp >> NICE_0_SHIFT);
+ return (long) (tmp >> WMULT_SHIFT);
}
static inline void
@@ -281,26 +285,25 @@ add_wait_runtime(struct cfs_rq *cfs_rq, struct sched_entity *se, long delta)
* are not in our scheduling class.
*/
static inline void
-__update_curr(struct cfs_rq *cfs_rq, struct sched_entity *curr, u64 now)
+__update_curr(struct cfs_rq *cfs_rq, struct sched_entity *curr)
{
- unsigned long delta, delta_exec, delta_fair;
- long delta_mine;
+ unsigned long delta, delta_exec, delta_fair, delta_mine;
struct load_weight *lw = &cfs_rq->load;
unsigned long load = lw->weight;
- if (unlikely(!load))
- return;
-
delta_exec = curr->delta_exec;
schedstat_set(curr->exec_max, max((u64)delta_exec, curr->exec_max));
curr->sum_exec_runtime += delta_exec;
cfs_rq->exec_clock += delta_exec;
+ if (unlikely(!load))
+ return;
+
delta_fair = calc_delta_fair(delta_exec, lw);
delta_mine = calc_delta_mine(delta_exec, curr->load.weight, lw);
- if (cfs_rq->sleeper_bonus > sysctl_sched_stat_granularity) {
+ if (cfs_rq->sleeper_bonus > sysctl_sched_granularity) {
delta = calc_delta_mine(cfs_rq->sleeper_bonus,
curr->load.weight, lw);
if (unlikely(delta > cfs_rq->sleeper_bonus))
@@ -321,7 +324,7 @@ __update_curr(struct cfs_rq *cfs_rq, struct sched_entity *curr, u64 now)
add_wait_runtime(cfs_rq, curr, delta_mine - delta_exec);
}
-static void update_curr(struct cfs_rq *cfs_rq, u64 now)
+static void update_curr(struct cfs_rq *cfs_rq)
{
struct sched_entity *curr = cfs_rq_curr(cfs_rq);
unsigned long delta_exec;
@@ -334,22 +337,22 @@ static void update_curr(struct cfs_rq *cfs_rq, u64 now)
* since the last time we changed load (this cannot
* overflow on 32 bits):
*/
- delta_exec = (unsigned long)(now - curr->exec_start);
+ delta_exec = (unsigned long)(rq_of(cfs_rq)->clock - curr->exec_start);
curr->delta_exec += delta_exec;
if (unlikely(curr->delta_exec > sysctl_sched_stat_granularity)) {
- __update_curr(cfs_rq, curr, now);
+ __update_curr(cfs_rq, curr);
curr->delta_exec = 0;
}
- curr->exec_start = now;
+ curr->exec_start = rq_of(cfs_rq)->clock;
}
static inline void
-update_stats_wait_start(struct cfs_rq *cfs_rq, struct sched_entity *se, u64 now)
+update_stats_wait_start(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
se->wait_start_fair = cfs_rq->fair_clock;
- schedstat_set(se->wait_start, now);
+ schedstat_set(se->wait_start, rq_of(cfs_rq)->clock);
}
/*
@@ -377,8 +380,7 @@ calc_weighted(unsigned long delta, unsigned long weight, int shift)
/*
* Task is being enqueued - update stats:
*/
-static void
-update_stats_enqueue(struct cfs_rq *cfs_rq, struct sched_entity *se, u64 now)
+static void update_stats_enqueue(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
s64 key;
@@ -387,7 +389,7 @@ update_stats_enqueue(struct cfs_rq *cfs_rq, struct sched_entity *se, u64 now)
* a dequeue/enqueue event is a NOP)
*/
if (se != cfs_rq_curr(cfs_rq))
- update_stats_wait_start(cfs_rq, se, now);
+ update_stats_wait_start(cfs_rq, se);
/*
* Update the key:
*/
@@ -407,7 +409,8 @@ update_stats_enqueue(struct cfs_rq *cfs_rq, struct sched_entity *se, u64 now)
(WMULT_SHIFT - NICE_0_SHIFT);
} else {
tmp = se->wait_runtime;
- key -= (tmp * se->load.weight) >> NICE_0_SHIFT;
+ key -= (tmp * se->load.inv_weight) >>
+ (WMULT_SHIFT - NICE_0_SHIFT);
}
}
@@ -418,11 +421,12 @@ update_stats_enqueue(struct cfs_rq *cfs_rq, struct sched_entity *se, u64 now)
* Note: must be called with a freshly updated rq->fair_clock.
*/
static inline void
-__update_stats_wait_end(struct cfs_rq *cfs_rq, struct sched_entity *se, u64 now)
+__update_stats_wait_end(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
unsigned long delta_fair = se->delta_fair_run;
- schedstat_set(se->wait_max, max(se->wait_max, now - se->wait_start));
+ schedstat_set(se->wait_max, max(se->wait_max,
+ rq_of(cfs_rq)->clock - se->wait_start));
if (unlikely(se->load.weight != NICE_0_LOAD))
delta_fair = calc_weighted(delta_fair, se->load.weight,
@@ -432,7 +436,7 @@ __update_stats_wait_end(struct cfs_rq *cfs_rq, struct sched_entity *se, u64 now)
}
static void
-update_stats_wait_end(struct cfs_rq *cfs_rq, struct sched_entity *se, u64 now)
+update_stats_wait_end(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
unsigned long delta_fair;
@@ -442,7 +446,7 @@ update_stats_wait_end(struct cfs_rq *cfs_rq, struct sched_entity *se, u64 now)
se->delta_fair_run += delta_fair;
if (unlikely(abs(se->delta_fair_run) >=
sysctl_sched_stat_granularity)) {
- __update_stats_wait_end(cfs_rq, se, now);
+ __update_stats_wait_end(cfs_rq, se);
se->delta_fair_run = 0;
}
@@ -451,34 +455,34 @@ update_stats_wait_end(struct cfs_rq *cfs_rq, struct sched_entity *se, u64 now)
}
static inline void
-update_stats_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se, u64 now)
+update_stats_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
- update_curr(cfs_rq, now);
+ update_curr(cfs_rq);
/*
* Mark the end of the wait period if dequeueing a
* waiting task:
*/
if (se != cfs_rq_curr(cfs_rq))
- update_stats_wait_end(cfs_rq, se, now);
+ update_stats_wait_end(cfs_rq, se);
}
/*
* We are picking a new current task - update its stats:
*/
static inline void
-update_stats_curr_start(struct cfs_rq *cfs_rq, struct sched_entity *se, u64 now)
+update_stats_curr_start(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
/*
* We are starting a new run period:
*/
- se->exec_start = now;
+ se->exec_start = rq_of(cfs_rq)->clock;
}
/*
* We are descheduling a task - update its stats:
*/
static inline void
-update_stats_curr_end(struct cfs_rq *cfs_rq, struct sched_entity *se, u64 now)
+update_stats_curr_end(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
se->exec_start = 0;
}
@@ -487,8 +491,7 @@ update_stats_curr_end(struct cfs_rq *cfs_rq, struct sched_entity *se, u64 now)
* Scheduling class queueing methods:
*/
-static void
-__enqueue_sleeper(struct cfs_rq *cfs_rq, struct sched_entity *se, u64 now)
+static void __enqueue_sleeper(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
unsigned long load = cfs_rq->load.weight, delta_fair;
long prev_runtime;
@@ -522,8 +525,7 @@ __enqueue_sleeper(struct cfs_rq *cfs_rq, struct sched_entity *se, u64 now)
schedstat_add(cfs_rq, wait_runtime, se->wait_runtime);
}
-static void
-enqueue_sleeper(struct cfs_rq *cfs_rq, struct sched_entity *se, u64 now)
+static void enqueue_sleeper(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
struct task_struct *tsk = task_of(se);
unsigned long delta_fair;
@@ -538,7 +540,7 @@ enqueue_sleeper(struct cfs_rq *cfs_rq, struct sched_entity *se, u64 now)
se->delta_fair_sleep += delta_fair;
if (unlikely(abs(se->delta_fair_sleep) >=
sysctl_sched_stat_granularity)) {
- __enqueue_sleeper(cfs_rq, se, now);
+ __enqueue_sleeper(cfs_rq, se);
se->delta_fair_sleep = 0;
}
@@ -546,7 +548,7 @@ enqueue_sleeper(struct cfs_rq *cfs_rq, struct sched_entity *se, u64 now)
#ifdef CONFIG_SCHEDSTATS
if (se->sleep_start) {
- u64 delta = now - se->sleep_start;
+ u64 delta = rq_of(cfs_rq)->clock - se->sleep_start;
if ((s64)delta < 0)
delta = 0;
@@ -558,7 +560,7 @@ enqueue_sleeper(struct cfs_rq *cfs_rq, struct sched_entity *se, u64 now)
se->sum_sleep_runtime += delta;
}
if (se->block_start) {
- u64 delta = now - se->block_start;
+ u64 delta = rq_of(cfs_rq)->clock - se->block_start;
if ((s64)delta < 0)
delta = 0;
@@ -573,26 +575,24 @@ enqueue_sleeper(struct cfs_rq *cfs_rq, struct sched_entity *se, u64 now)
}
static void
-enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se,
- int wakeup, u64 now)
+enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int wakeup)
{
/*
* Update the fair clock.
*/
- update_curr(cfs_rq, now);
+ update_curr(cfs_rq);
if (wakeup)
- enqueue_sleeper(cfs_rq, se, now);
+ enqueue_sleeper(cfs_rq, se);
- update_stats_enqueue(cfs_rq, se, now);
+ update_stats_enqueue(cfs_rq, se);
__enqueue_entity(cfs_rq, se);
}
static void
-dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se,
- int sleep, u64 now)
+dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int sleep)
{
- update_stats_dequeue(cfs_rq, se, now);
+ update_stats_dequeue(cfs_rq, se);
if (sleep) {
se->sleep_start_fair = cfs_rq->fair_clock;
#ifdef CONFIG_SCHEDSTATS
@@ -600,9 +600,9 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se,
struct task_struct *tsk = task_of(se);
if (tsk->state & TASK_INTERRUPTIBLE)
- se->sleep_start = now;
+ se->sleep_start = rq_of(cfs_rq)->clock;
if (tsk->state & TASK_UNINTERRUPTIBLE)
- se->block_start = now;
+ se->block_start = rq_of(cfs_rq)->clock;
}
cfs_rq->wait_runtime -= se->wait_runtime;
#endif
@@ -629,7 +629,7 @@ __check_preempt_curr_fair(struct cfs_rq *cfs_rq, struct sched_entity *se,
}
static inline void
-set_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, u64 now)
+set_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
/*
* Any task has to be enqueued before it get to execute on
@@ -638,49 +638,46 @@ set_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, u64 now)
* done a put_prev_task_fair() shortly before this, which
* updated rq->fair_clock - used by update_stats_wait_end())
*/
- update_stats_wait_end(cfs_rq, se, now);
- update_stats_curr_start(cfs_rq, se, now);
+ update_stats_wait_end(cfs_rq, se);
+ update_stats_curr_start(cfs_rq, se);
set_cfs_rq_curr(cfs_rq, se);
}
-static struct sched_entity *pick_next_entity(struct cfs_rq *cfs_rq, u64 now)
+static struct sched_entity *pick_next_entity(struct cfs_rq *cfs_rq)
{
struct sched_entity *se = __pick_next_entity(cfs_rq);
- set_next_entity(cfs_rq, se, now);
+ set_next_entity(cfs_rq, se);
return se;
}
-static void
-put_prev_entity(struct cfs_rq *cfs_rq, struct sched_entity *prev, u64 now)
+static void put_prev_entity(struct cfs_rq *cfs_rq, struct sched_entity *prev)
{
/*
* If still on the runqueue then deactivate_task()
* was not called and update_curr() has to be done:
*/
if (prev->on_rq)
- update_curr(cfs_rq, now);
+ update_curr(cfs_rq);
- update_stats_curr_end(cfs_rq, prev, now);
+ update_stats_curr_end(cfs_rq, prev);
if (prev->on_rq)
- update_stats_wait_start(cfs_rq, prev, now);
+ update_stats_wait_start(cfs_rq, prev);
set_cfs_rq_curr(cfs_rq, NULL);
}
static void entity_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr)
{
- struct rq *rq = rq_of(cfs_rq);
struct sched_entity *next;
- u64 now = __rq_clock(rq);
/*
* Dequeue and enqueue the task to update its
* position within the tree:
*/
- dequeue_entity(cfs_rq, curr, 0, now);
- enqueue_entity(cfs_rq, curr, 0, now);
+ dequeue_entity(cfs_rq, curr, 0);
+ enqueue_entity(cfs_rq, curr, 0);
/*
* Reschedule if another task tops the current one.
@@ -785,8 +782,7 @@ static inline int is_same_group(struct task_struct *curr, struct task_struct *p)
* increased. Here we update the fair scheduling stats and
* then put the task into the rbtree:
*/
-static void
-enqueue_task_fair(struct rq *rq, struct task_struct *p, int wakeup, u64 now)
+static void enqueue_task_fair(struct rq *rq, struct task_struct *p, int wakeup)
{
struct cfs_rq *cfs_rq;
struct sched_entity *se = &p->se;
@@ -795,7 +791,7 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int wakeup, u64 now)
if (se->on_rq)
break;
cfs_rq = cfs_rq_of(se);
- enqueue_entity(cfs_rq, se, wakeup, now);
+ enqueue_entity(cfs_rq, se, wakeup);
}
}
@@ -804,15 +800,14 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int wakeup, u64 now)
* decreased. We remove the task from the rbtree and
* update the fair scheduling stats:
*/
-static void
-dequeue_task_fair(struct rq *rq, struct task_struct *p, int sleep, u64 now)
+static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int sleep)
{
struct cfs_rq *cfs_rq;
struct sched_entity *se = &p->se;
for_each_sched_entity(se) {
cfs_rq = cfs_rq_of(se);
- dequeue_entity(cfs_rq, se, sleep, now);
+ dequeue_entity(cfs_rq, se, sleep);
/* Don't dequeue parent if it has other entities besides us */
if (cfs_rq->load.weight)
break;
@@ -825,14 +820,14 @@ dequeue_task_fair(struct rq *rq, struct task_struct *p, int sleep, u64 now)
static void yield_task_fair(struct rq *rq, struct task_struct *p)
{
struct cfs_rq *cfs_rq = task_cfs_rq(p);
- u64 now = __rq_clock(rq);
+ __update_rq_clock(rq);
/*
* Dequeue and enqueue the task to update its
* position within the tree:
*/
- dequeue_entity(cfs_rq, &p->se, 0, now);
- enqueue_entity(cfs_rq, &p->se, 0, now);
+ dequeue_entity(cfs_rq, &p->se, 0);
+ enqueue_entity(cfs_rq, &p->se, 0);
}
/*
@@ -845,7 +840,8 @@ static void check_preempt_curr_fair(struct rq *rq, struct task_struct *p)
unsigned long gran;
if (unlikely(rt_prio(p->prio))) {
- update_curr(cfs_rq, rq_clock(rq));
+ update_rq_clock(rq);
+ update_curr(cfs_rq);
resched_task(curr);
return;
}
@@ -861,7 +857,7 @@ static void check_preempt_curr_fair(struct rq *rq, struct task_struct *p)
__check_preempt_curr_fair(cfs_rq, &p->se, &curr->se, gran);
}
-static struct task_struct *pick_next_task_fair(struct rq *rq, u64 now)
+static struct task_struct *pick_next_task_fair(struct rq *rq)
{
struct cfs_rq *cfs_rq = &rq->cfs;
struct sched_entity *se;
@@ -870,7 +866,7 @@ static struct task_struct *pick_next_task_fair(struct rq *rq, u64 now)
return NULL;
do {
- se = pick_next_entity(cfs_rq, now);
+ se = pick_next_entity(cfs_rq);
cfs_rq = group_cfs_rq(se);
} while (cfs_rq);
@@ -880,14 +876,14 @@ static struct task_struct *pick_next_task_fair(struct rq *rq, u64 now)
/*
* Account for a descheduled task:
*/
-static void put_prev_task_fair(struct rq *rq, struct task_struct *prev, u64 now)
+static void put_prev_task_fair(struct rq *rq, struct task_struct *prev)
{
struct sched_entity *se = &prev->se;
struct cfs_rq *cfs_rq;
for_each_sched_entity(se) {
cfs_rq = cfs_rq_of(se);
- put_prev_entity(cfs_rq, se, now);
+ put_prev_entity(cfs_rq, se);
}
}
@@ -930,6 +926,7 @@ static struct task_struct *load_balance_next_fair(void *arg)
return __load_balance_iterator(cfs_rq, cfs_rq->rb_load_balance_curr);
}
+#ifdef CONFIG_FAIR_GROUP_SCHED
static int cfs_rq_best_prio(struct cfs_rq *cfs_rq)
{
struct sched_entity *curr;
@@ -943,12 +940,13 @@ static int cfs_rq_best_prio(struct cfs_rq *cfs_rq)
return p->prio;
}
+#endif
-static int
+static unsigned long
load_balance_fair(struct rq *this_rq, int this_cpu, struct rq *busiest,
- unsigned long max_nr_move, unsigned long max_load_move,
- struct sched_domain *sd, enum cpu_idle_type idle,
- int *all_pinned, unsigned long *total_load_moved)
+ unsigned long max_nr_move, unsigned long max_load_move,
+ struct sched_domain *sd, enum cpu_idle_type idle,
+ int *all_pinned, int *this_best_prio)
{
struct cfs_rq *busy_cfs_rq;
unsigned long load_moved, total_nr_moved = 0, nr_moved;
@@ -959,10 +957,10 @@ load_balance_fair(struct rq *this_rq, int this_cpu, struct rq *busiest,
cfs_rq_iterator.next = load_balance_next_fair;
for_each_leaf_cfs_rq(busiest, busy_cfs_rq) {
+#ifdef CONFIG_FAIR_GROUP_SCHED
struct cfs_rq *this_cfs_rq;
- long imbalance;
+ long imbalances;
unsigned long maxload;
- int this_best_prio, best_prio, best_prio_seen = 0;
this_cfs_rq = cpu_cfs_rq(busy_cfs_rq, this_cpu);
@@ -976,27 +974,17 @@ load_balance_fair(struct rq *this_rq, int this_cpu, struct rq *busiest,
imbalance /= 2;
maxload = min(rem_load_move, imbalance);
- this_best_prio = cfs_rq_best_prio(this_cfs_rq);
- best_prio = cfs_rq_best_prio(busy_cfs_rq);
-
- /*
- * Enable handling of the case where there is more than one task
- * with the best priority. If the current running task is one
- * of those with prio==best_prio we know it won't be moved
- * and therefore it's safe to override the skip (based on load)
- * of any task we find with that prio.
- */
- if (cfs_rq_curr(busy_cfs_rq) == &busiest->curr->se)
- best_prio_seen = 1;
-
+ *this_best_prio = cfs_rq_best_prio(this_cfs_rq);
+#else
+#define maxload rem_load_move
+#endif
/* pass busy_cfs_rq argument into
* load_balance_[start|next]_fair iterators
*/
cfs_rq_iterator.arg = busy_cfs_rq;
nr_moved = balance_tasks(this_rq, this_cpu, busiest,
max_nr_move, maxload, sd, idle, all_pinned,
- &load_moved, this_best_prio, best_prio,
- best_prio_seen, &cfs_rq_iterator);
+ &load_moved, this_best_prio, &cfs_rq_iterator);
total_nr_moved += nr_moved;
max_nr_move -= nr_moved;
@@ -1006,9 +994,7 @@ load_balance_fair(struct rq *this_rq, int this_cpu, struct rq *busiest,
break;
}
- *total_load_moved = max_load_move - rem_load_move;
-
- return total_nr_moved;
+ return max_load_move - rem_load_move;
}
/*
@@ -1032,14 +1018,14 @@ static void task_tick_fair(struct rq *rq, struct task_struct *curr)
* monopolize the CPU. Note: the parent runqueue is locked,
* the child is not running yet.
*/
-static void task_new_fair(struct rq *rq, struct task_struct *p, u64 now)
+static void task_new_fair(struct rq *rq, struct task_struct *p)
{
struct cfs_rq *cfs_rq = task_cfs_rq(p);
struct sched_entity *se = &p->se;
sched_info_queued(p);
- update_stats_enqueue(cfs_rq, se, now);
+ update_stats_enqueue(cfs_rq, se);
/*
* Child runs first: we let it run before the parent
* until it reschedules once. We set up the key so that
@@ -1072,15 +1058,10 @@ static void task_new_fair(struct rq *rq, struct task_struct *p, u64 now)
*/
static void set_curr_task_fair(struct rq *rq)
{
- struct task_struct *curr = rq->curr;
- struct sched_entity *se = &curr->se;
- u64 now = rq_clock(rq);
- struct cfs_rq *cfs_rq;
+ struct sched_entity *se = &rq->curr.se;
- for_each_sched_entity(se) {
- cfs_rq = cfs_rq_of(se);
- set_next_entity(cfs_rq, se, now);
- }
+ for_each_sched_entity(se)
+ set_next_entity(cfs_rq_of(se), se);
}
#else
static void set_curr_task_fair(struct rq *rq)
@@ -1109,12 +1090,11 @@ struct sched_class fair_sched_class __read_mostly = {
};
#ifdef CONFIG_SCHED_DEBUG
-void print_cfs_stats(struct seq_file *m, int cpu, u64 now)
+static void print_cfs_stats(struct seq_file *m, int cpu)
{
- struct rq *rq = cpu_rq(cpu);
struct cfs_rq *cfs_rq;
- for_each_leaf_cfs_rq(rq, cfs_rq)
- print_cfs_rq(m, cpu, cfs_rq, now);
+ for_each_leaf_cfs_rq(cpu_rq(cpu), cfs_rq)
+ print_cfs_rq(m, cpu, cfs_rq);
}
#endif
diff --git a/kernel/sched_idletask.c b/kernel/sched_idletask.c
index 41841e741c4..3503fb2d9f9 100644
--- a/kernel/sched_idletask.c
+++ b/kernel/sched_idletask.c
@@ -13,7 +13,7 @@ static void check_preempt_curr_idle(struct rq *rq, struct task_struct *p)
resched_task(rq->idle);
}
-static struct task_struct *pick_next_task_idle(struct rq *rq, u64 now)
+static struct task_struct *pick_next_task_idle(struct rq *rq)
{
schedstat_inc(rq, sched_goidle);
@@ -25,7 +25,7 @@ static struct task_struct *pick_next_task_idle(struct rq *rq, u64 now)
* message if some code attempts to do it:
*/
static void
-dequeue_task_idle(struct rq *rq, struct task_struct *p, int sleep, u64 now)
+dequeue_task_idle(struct rq *rq, struct task_struct *p, int sleep)
{
spin_unlock_irq(&rq->lock);
printk(KERN_ERR "bad: scheduling from the idle thread!\n");
@@ -33,15 +33,15 @@ dequeue_task_idle(struct rq *rq, struct task_struct *p, int sleep, u64 now)
spin_lock_irq(&rq->lock);
}
-static void put_prev_task_idle(struct rq *rq, struct task_struct *prev, u64 now)
+static void put_prev_task_idle(struct rq *rq, struct task_struct *prev)
{
}
-static int
+static unsigned long
load_balance_idle(struct rq *this_rq, int this_cpu, struct rq *busiest,
unsigned long max_nr_move, unsigned long max_load_move,
struct sched_domain *sd, enum cpu_idle_type idle,
- int *all_pinned, unsigned long *total_load_moved)
+ int *all_pinned, int *this_best_prio)
{
return 0;
}
diff --git a/kernel/sched_rt.c b/kernel/sched_rt.c
index 002fcf8d3f6..dcdcad632fd 100644
--- a/kernel/sched_rt.c
+++ b/kernel/sched_rt.c
@@ -7,7 +7,7 @@
* Update the current task's runtime statistics. Skip current tasks that
* are not in our scheduling class.
*/
-static inline void update_curr_rt(struct rq *rq, u64 now)
+static inline void update_curr_rt(struct rq *rq)
{
struct task_struct *curr = rq->curr;
u64 delta_exec;
@@ -15,18 +15,17 @@ static inline void update_curr_rt(struct rq *rq, u64 now)
if (!task_has_rt_policy(curr))
return;
- delta_exec = now - curr->se.exec_start;
+ delta_exec = rq->clock - curr->se.exec_start;
if (unlikely((s64)delta_exec < 0))
delta_exec = 0;
schedstat_set(curr->se.exec_max, max(curr->se.exec_max, delta_exec));
curr->se.sum_exec_runtime += delta_exec;
- curr->se.exec_start = now;
+ curr->se.exec_start = rq->clock;
}
-static void
-enqueue_task_rt(struct rq *rq, struct task_struct *p, int wakeup, u64 now)
+static void enqueue_task_rt(struct rq *rq, struct task_struct *p, int wakeup)
{
struct rt_prio_array *array = &rq->rt.active;
@@ -37,12 +36,11 @@ enqueue_task_rt(struct rq *rq, struct task_struct *p, int wakeup, u64 now)
/*
* Adding/removing a task to/from a priority array:
*/
-static void
-dequeue_task_rt(struct rq *rq, struct task_struct *p, int sleep, u64 now)
+static void dequeue_task_rt(struct rq *rq, struct task_struct *p, int sleep)
{
struct rt_prio_array *array = &rq->rt.active;
- update_curr_rt(rq, now);
+ update_curr_rt(rq);
list_del(&p->run_list);
if (list_empty(array->queue + p->prio))
@@ -75,7 +73,7 @@ static void check_preempt_curr_rt(struct rq *rq, struct task_struct *p)
resched_task(rq->curr);
}
-static struct task_struct *pick_next_task_rt(struct rq *rq, u64 now)
+static struct task_struct *pick_next_task_rt(struct rq *rq)
{
struct rt_prio_array *array = &rq->rt.active;
struct task_struct *next;
@@ -89,14 +87,14 @@ static struct task_struct *pick_next_task_rt(struct rq *rq, u64 now)
queue = array->queue + idx;
next = list_entry(queue->next, struct task_struct, run_list);
- next->se.exec_start = now;
+ next->se.exec_start = rq->clock;
return next;
}
-static void put_prev_task_rt(struct rq *rq, struct task_struct *p, u64 now)
+static void put_prev_task_rt(struct rq *rq, struct task_struct *p)
{
- update_curr_rt(rq, now);
+ update_curr_rt(rq);
p->se.exec_start = 0;
}
@@ -172,28 +170,15 @@ static struct task_struct *load_balance_next_rt(void *arg)
return p;
}
-static int
+static unsigned long
load_balance_rt(struct rq *this_rq, int this_cpu, struct rq *busiest,
unsigned long max_nr_move, unsigned long max_load_move,
struct sched_domain *sd, enum cpu_idle_type idle,
- int *all_pinned, unsigned long *load_moved)
+ int *all_pinned, int *this_best_prio)
{
- int this_best_prio, best_prio, best_prio_seen = 0;
int nr_moved;
struct rq_iterator rt_rq_iterator;
-
- best_prio = sched_find_first_bit(busiest->rt.active.bitmap);
- this_best_prio = sched_find_first_bit(this_rq->rt.active.bitmap);
-
- /*
- * Enable handling of the case where there is more than one task
- * with the best priority. If the current running task is one
- * of those with prio==best_prio we know it won't be moved
- * and therefore it's safe to override the skip (based on load)
- * of any task we find with that prio.
- */
- if (busiest->curr->prio == best_prio)
- best_prio_seen = 1;
+ unsigned long load_moved;
rt_rq_iterator.start = load_balance_start_rt;
rt_rq_iterator.next = load_balance_next_rt;
@@ -203,11 +188,10 @@ load_balance_rt(struct rq *this_rq, int this_cpu, struct rq *busiest,
rt_rq_iterator.arg = busiest;
nr_moved = balance_tasks(this_rq, this_cpu, busiest, max_nr_move,
- max_load_move, sd, idle, all_pinned, load_moved,
- this_best_prio, best_prio, best_prio_seen,
- &rt_rq_iterator);
+ max_load_move, sd, idle, all_pinned, &load_moved,
+ this_best_prio, &rt_rq_iterator);
- return nr_moved;
+ return load_moved;
}
static void task_tick_rt(struct rq *rq, struct task_struct *p)