* [GIT PULL] scheduler changes for v4.4
@ 2015-11-03 10:26 Ingo Molnar
0 siblings, 0 replies; only message in thread
From: Ingo Molnar @ 2015-11-03 10:26 UTC (permalink / raw)
To: Linus Torvalds
Cc: linux-kernel, Peter Zijlstra, Mike Galbraith, Thomas Gleixner,
Andrew Morton
Linus,
Please pull the latest sched-core-for-linus git tree from:
git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git sched-core-for-linus
# HEAD: e73e85f0593832aa583b252f9a16cf90ed6d30fa sched: Don't scan all-offline ->cpus_allowed twice if !CONFIG_CPUSETS
The main changes in this cycle were:
- sched/fair load tracking fixes and cleanups. (Byungchul Park)
- Make load tracking frequency scale invariant. (Dietmar Eggemann)
- sched/deadline updates. (Juri Lelli)
- stop machine fixes, cleanups and enhancements for bugs triggered by CPU
hotplug stress testing. (Oleg Nesterov)
- scheduler preemption code rework: remove PREEMPT_ACTIVE and related cleanups.
(Peter Zijlstra)
- Rework the sched_info::run_delay code to fix races. (Peter Zijlstra)
- Optimize per entity utilization tracking. (Peter Zijlstra)
- ... misc other fixes, cleanups and smaller updates.
Thanks,
Ingo
------------------>
Byungchul Park (5):
sched/fair: Factor out the {at,de}taching of the per entity load {to,from} the runqueue
sched/fair: Have task_move_group_fair() unconditionally add the entity load to the runqueue
sched/fair: Have task_move_group_fair() also detach entity load from the old runqueue
sched/fair: Fix switched_to_fair()'s per entity load tracking
sched/fair: Unify switched_{from,to}_fair() and task_move_group_fair()
Chuck Ebbert (1):
sched/x86: Fix typo in __switch_to() comments
Dietmar Eggemann (5):
sched/fair: Make load tracking frequency scale-invariant
sched/fair: Make utilization tracking CPU scale-invariant
sched/fair: Name utilization related data and functions consistently
sched/fair: Get rid of scaling utilization by capacity_orig
sched/fair: Defer calling scaling functions
Geliang Tang (1):
sched/core: Drop unlikely behind BUG_ON()
Henrik Austad (1):
sched/core: Make policy-testing consistent
Juergen Gross (1):
sched/core: Make 'sched_domain_topology' declaration static
Juri Lelli (3):
sched/deadline: Unify dl_time_before() usage
sched/deadline, locking/rtmutex: Fix open coded check in rt_mutex_waiter_less()
sched/rt: Make (do_)balance_runtime() return void
Kirill Tkhai (1):
sched/core: Delete PF_EXITING checks from cpu_cgroup_exit() callback
Leo Yan (2):
sched/fair: Polish comments for LOAD_AVG_MAX
sched/fair: Remove unnecessary parameter for group_classify()
Morten Rasmussen (2):
sched/fair: Convert arch_scale_cpu_capacity() from weak function to #define
sched/fair: Initialize task load and utilization before placing task on rq
Oleg Nesterov (7):
cpu/hotplug: Read_lock(tasklist_lock) doesn't need to disable irqs
stop_machine: Ensure that a queued callback will be called before cpu_stop_park()
stop_machine: Introduce __cpu_stop_queue_work() and cpu_stop_queue_two_works()
stop_machine: Change cpu_stop_queue_two_works() to rely on stopper->enabled
stop_machine: Kill smp_hotplug_thread->pre_unpark, introduce stop_machine_unpark()
stop_machine: Kill cpu_stop_threads->setup() and cpu_stop_unpark()
sched: Don't scan all-offline ->cpus_allowed twice if !CONFIG_CPUSETS
Peter Zijlstra (20):
sched/fair: Make the entity load aging on attaching tunable
sched/core: Remove unused argument from sched_class::task_move_group
sched/fair: Rename scale() to cap_scale()
sched/fair: Optimize __update_load_avg()
sched/fair: Optimize per entity utilization tracking
sched/core: Simplify INIT_PREEMPT_COUNT
sched/core: Rework TASK_DEAD preemption exception
sched/core: Create preempt_count invariant
sched/core: Add preempt argument to __schedule()
sched/core: Fix trace_sched_switch()
sched/core: Stop setting PREEMPT_ACTIVE
sched/core: Robustify preemption leak checks
sched/core: Simplify preempt_count tests
sched/core, sched/x86: Kill thread_info::saved_preempt_count
sched/core: Kill PREEMPT_ACTIVE
sched/core: More notrace annotations
sched/core: Add preempt_count invariant check
sched/core: Fix task and run queue sched_info::run_delay inconsistencies
sched: Start stopper early
sched: Move cpu_active() tests from stop_two_cpus() into migrate_swap_stop()
Rik van Riel (1):
sched/numa: Limit the amount of virtual memory scanned in task_numa_work()
Srikar Dronamraju (5):
sched/numa: Rename numabalancing_enabled to sched_numa_balancing
sched/numa: Disable sched_numa_balancing on UMA systems
sched/numa: Remove the NUMA sched_feature
sched/numa: Convert sched_numa_balancing to a static_branch
sched/numa: Fix task_tick_fair() from disabling numa_balancing
Vincent Guittot (1):
sched/fair: Fix nohz.next_balance update
xiaofeng.yan (1):
sched/core: Remove a parameter in the migrate_task_rq() function
arch/x86/include/asm/preempt.h | 5 +-
arch/x86/include/asm/thread_info.h | 2 -
arch/x86/kernel/process_32.c | 8 -
arch/x86/kernel/process_64.c | 10 +-
include/asm-generic/preempt.h | 2 +-
include/linux/preempt.h | 20 +-
include/linux/sched.h | 38 ++--
include/linux/sched/deadline.h | 5 +
include/linux/smpboot.h | 4 -
include/linux/stop_machine.h | 2 +
include/trace/events/sched.h | 22 +-
kernel/cpu.c | 10 +-
kernel/exit.c | 4 +-
kernel/locking/rtmutex.c | 3 +-
kernel/sched/core.c | 203 ++++++++++--------
kernel/sched/cpudeadline.c | 5 -
kernel/sched/cpudeadline.h | 1 +
kernel/sched/fair.c | 419 ++++++++++++++++++++-----------------
kernel/sched/features.h | 21 +-
kernel/sched/rt.c | 22 +-
kernel/sched/sched.h | 55 ++---
kernel/smpboot.c | 5 +-
kernel/stop_machine.c | 90 ++++----
kernel/trace/ftrace.c | 2 +-
kernel/trace/trace_sched_switch.c | 3 +-
kernel/trace/trace_sched_wakeup.c | 2 +-
26 files changed, 493 insertions(+), 470 deletions(-)
diff --git a/arch/x86/include/asm/preempt.h b/arch/x86/include/asm/preempt.h
index b12f81022a6b..01bcde84d3e4 100644
--- a/arch/x86/include/asm/preempt.h
+++ b/arch/x86/include/asm/preempt.h
@@ -30,12 +30,9 @@ static __always_inline void preempt_count_set(int pc)
/*
* must be macros to avoid header recursion hell
*/
-#define init_task_preempt_count(p) do { \
- task_thread_info(p)->saved_preempt_count = PREEMPT_DISABLED; \
-} while (0)
+#define init_task_preempt_count(p) do { } while (0)
#define init_idle_preempt_count(p, cpu) do { \
- task_thread_info(p)->saved_preempt_count = PREEMPT_ENABLED; \
per_cpu(__preempt_count, (cpu)) = PREEMPT_ENABLED; \
} while (0)
diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h
index 8afdc3e44247..809877e9030b 100644
--- a/arch/x86/include/asm/thread_info.h
+++ b/arch/x86/include/asm/thread_info.h
@@ -57,7 +57,6 @@ struct thread_info {
__u32 flags; /* low level flags */
__u32 status; /* thread synchronous flags */
__u32 cpu; /* current CPU */
- int saved_preempt_count;
mm_segment_t addr_limit;
void __user *sysenter_return;
unsigned int sig_on_uaccess_error:1;
@@ -69,7 +68,6 @@ struct thread_info {
.task = &tsk, \
.flags = 0, \
.cpu = 0, \
- .saved_preempt_count = INIT_PREEMPT_COUNT, \
.addr_limit = KERNEL_DS, \
}
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index 737527b40e5b..9f950917528b 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -280,14 +280,6 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
set_iopl_mask(next->iopl);
/*
- * If it were not for PREEMPT_ACTIVE we could guarantee that the
- * preempt_count of all tasks was equal here and this would not be
- * needed.
- */
- task_thread_info(prev_p)->saved_preempt_count = this_cpu_read(__preempt_count);
- this_cpu_write(__preempt_count, task_thread_info(next_p)->saved_preempt_count);
-
- /*
* Now maybe handle debug registers and/or IO bitmaps
*/
if (unlikely(task_thread_info(prev_p)->flags & _TIF_WORK_CTXSW_PREV ||
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index b35921a670b2..e835d263a33b 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -332,7 +332,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
/*
* Switch FS and GS.
*
- * These are even more complicated than FS and GS: they have
+ * These are even more complicated than DS and ES: they have
* 64-bit bases are that controlled by arch_prctl. Those bases
* only differ from the values in the GDT or LDT if the selector
* is 0.
@@ -401,14 +401,6 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
*/
this_cpu_write(current_task, next_p);
- /*
- * If it were not for PREEMPT_ACTIVE we could guarantee that the
- * preempt_count of all tasks was equal here and this would not be
- * needed.
- */
- task_thread_info(prev_p)->saved_preempt_count = this_cpu_read(__preempt_count);
- this_cpu_write(__preempt_count, task_thread_info(next_p)->saved_preempt_count);
-
/* Reload esp0 and ss1. This changes current_thread_info(). */
load_sp0(tss, next);
diff --git a/include/asm-generic/preempt.h b/include/asm-generic/preempt.h
index 0bec580a4885..5d8ffa3e6f8c 100644
--- a/include/asm-generic/preempt.h
+++ b/include/asm-generic/preempt.h
@@ -24,7 +24,7 @@ static __always_inline void preempt_count_set(int pc)
* must be macros to avoid header recursion hell
*/
#define init_task_preempt_count(p) do { \
- task_thread_info(p)->preempt_count = PREEMPT_DISABLED; \
+ task_thread_info(p)->preempt_count = FORK_PREEMPT_COUNT; \
} while (0)
#define init_idle_preempt_count(p, cpu) do { \
diff --git a/include/linux/preempt.h b/include/linux/preempt.h
index bea8dd8ff5e0..75e4e30677f1 100644
--- a/include/linux/preempt.h
+++ b/include/linux/preempt.h
@@ -26,7 +26,6 @@
* SOFTIRQ_MASK: 0x0000ff00
* HARDIRQ_MASK: 0x000f0000
* NMI_MASK: 0x00100000
- * PREEMPT_ACTIVE: 0x00200000
* PREEMPT_NEED_RESCHED: 0x80000000
*/
#define PREEMPT_BITS 8
@@ -53,10 +52,6 @@
#define SOFTIRQ_DISABLE_OFFSET (2 * SOFTIRQ_OFFSET)
-#define PREEMPT_ACTIVE_BITS 1
-#define PREEMPT_ACTIVE_SHIFT (NMI_SHIFT + NMI_BITS)
-#define PREEMPT_ACTIVE (__IRQ_MASK(PREEMPT_ACTIVE_BITS) << PREEMPT_ACTIVE_SHIFT)
-
/* We use the MSB mostly because its available */
#define PREEMPT_NEED_RESCHED 0x80000000
@@ -126,8 +121,7 @@
* Check whether we were atomic before we did preempt_disable():
* (used by the scheduler)
*/
-#define in_atomic_preempt_off() \
- ((preempt_count() & ~PREEMPT_ACTIVE) != PREEMPT_DISABLE_OFFSET)
+#define in_atomic_preempt_off() (preempt_count() != PREEMPT_DISABLE_OFFSET)
#if defined(CONFIG_DEBUG_PREEMPT) || defined(CONFIG_PREEMPT_TRACER)
extern void preempt_count_add(int val);
@@ -146,18 +140,6 @@ extern void preempt_count_sub(int val);
#define preempt_count_inc() preempt_count_add(1)
#define preempt_count_dec() preempt_count_sub(1)
-#define preempt_active_enter() \
-do { \
- preempt_count_add(PREEMPT_ACTIVE + PREEMPT_DISABLE_OFFSET); \
- barrier(); \
-} while (0)
-
-#define preempt_active_exit() \
-do { \
- barrier(); \
- preempt_count_sub(PREEMPT_ACTIVE + PREEMPT_DISABLE_OFFSET); \
-} while (0)
-
#ifdef CONFIG_PREEMPT_COUNT
#define preempt_disable() \
diff --git a/include/linux/sched.h b/include/linux/sched.h
index b7b9501b41af..23ca455d9582 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -599,26 +599,32 @@ struct task_cputime_atomic {
.sum_exec_runtime = ATOMIC64_INIT(0), \
}
-#ifdef CONFIG_PREEMPT_COUNT
-#define PREEMPT_DISABLED (1 + PREEMPT_ENABLED)
-#else
-#define PREEMPT_DISABLED PREEMPT_ENABLED
-#endif
+#define PREEMPT_DISABLED (PREEMPT_DISABLE_OFFSET + PREEMPT_ENABLED)
+
+/*
+ * Disable preemption until the scheduler is running -- use an unconditional
+ * value so that it also works on !PREEMPT_COUNT kernels.
+ *
+ * Reset by start_kernel()->sched_init()->init_idle()->init_idle_preempt_count().
+ */
+#define INIT_PREEMPT_COUNT PREEMPT_OFFSET
/*
- * Disable preemption until the scheduler is running.
- * Reset by start_kernel()->sched_init()->init_idle().
+ * Initial preempt_count value; reflects the preempt_count schedule invariant
+ * which states that during context switches:
*
- * We include PREEMPT_ACTIVE to avoid cond_resched() from working
- * before the scheduler is active -- see should_resched().
+ * preempt_count() == 2*PREEMPT_DISABLE_OFFSET
+ *
+ * Note: PREEMPT_DISABLE_OFFSET is 0 for !PREEMPT_COUNT kernels.
+ * Note: See finish_task_switch().
*/
-#define INIT_PREEMPT_COUNT (PREEMPT_DISABLED + PREEMPT_ACTIVE)
+#define FORK_PREEMPT_COUNT (2*PREEMPT_DISABLE_OFFSET + PREEMPT_ENABLED)
/**
* struct thread_group_cputimer - thread group interval timer counts
* @cputime_atomic: atomic thread group interval timers.
* @running: non-zero when there are timers running and
- * @cputime receives updates.
+ * @cputime receives updates.
*
* This structure contains the version of task_cputime, above, that is
* used for thread group CPU timer calculations.
@@ -1139,8 +1145,6 @@ struct sched_domain_topology_level {
#endif
};
-extern struct sched_domain_topology_level *sched_domain_topology;
-
extern void set_sched_topology(struct sched_domain_topology_level *tl);
extern void wake_up_if_idle(int cpu);
@@ -1189,10 +1193,10 @@ struct load_weight {
/*
* The load_avg/util_avg accumulates an infinite geometric series.
- * 1) load_avg factors the amount of time that a sched_entity is
- * runnable on a rq into its weight. For cfs_rq, it is the aggregated
- * such weights of all runnable and blocked sched_entities.
- * 2) util_avg factors frequency scaling into the amount of time
+ * 1) load_avg factors frequency scaling into the amount of time that a
+ * sched_entity is runnable on a rq into its weight. For cfs_rq, it is the
+ * aggregated such weights of all runnable and blocked sched_entities.
+ * 2) util_avg factors frequency and cpu scaling into the amount of time
* that a sched_entity is running on a CPU, in the range [0..SCHED_LOAD_SCALE].
* For cfs_rq, it is the aggregated such times of all runnable and
* blocked sched_entities.
diff --git a/include/linux/sched/deadline.h b/include/linux/sched/deadline.h
index 9d303b8847df..9089a2ae913d 100644
--- a/include/linux/sched/deadline.h
+++ b/include/linux/sched/deadline.h
@@ -21,4 +21,9 @@ static inline int dl_task(struct task_struct *p)
return dl_prio(p->prio);
}
+static inline bool dl_time_before(u64 a, u64 b)
+{
+ return (s64)(a - b) < 0;
+}
+
#endif /* _SCHED_DEADLINE_H */
diff --git a/include/linux/smpboot.h b/include/linux/smpboot.h
index e6109a6cd8f6..12910cf19869 100644
--- a/include/linux/smpboot.h
+++ b/include/linux/smpboot.h
@@ -24,9 +24,6 @@ struct smpboot_thread_data;
* parked (cpu offline)
* @unpark: Optional unpark function, called when the thread is
* unparked (cpu online)
- * @pre_unpark: Optional unpark function, called before the thread is
- * unparked (cpu online). This is not guaranteed to be
- * called on the target cpu of the thread. Careful!
* @cpumask: Internal state. To update which threads are unparked,
* call smpboot_update_cpumask_percpu_thread().
* @selfparking: Thread is not parked by the park function.
@@ -42,7 +39,6 @@ struct smp_hotplug_thread {
void (*cleanup)(unsigned int cpu, bool online);
void (*park)(unsigned int cpu);
void (*unpark)(unsigned int cpu);
- void (*pre_unpark)(unsigned int cpu);
cpumask_var_t cpumask;
bool selfparking;
const char *thread_comm;
diff --git a/include/linux/stop_machine.h b/include/linux/stop_machine.h
index 414d924318ce..0adedca24c5b 100644
--- a/include/linux/stop_machine.h
+++ b/include/linux/stop_machine.h
@@ -33,6 +33,8 @@ void stop_one_cpu_nowait(unsigned int cpu, cpu_stop_fn_t fn, void *arg,
struct cpu_stop_work *work_buf);
int stop_cpus(const struct cpumask *cpumask, cpu_stop_fn_t fn, void *arg);
int try_stop_cpus(const struct cpumask *cpumask, cpu_stop_fn_t fn, void *arg);
+void stop_machine_park(int cpu);
+void stop_machine_unpark(int cpu);
#else /* CONFIG_SMP */
diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h
index 539d6bc3216a..9b90c57517a9 100644
--- a/include/trace/events/sched.h
+++ b/include/trace/events/sched.h
@@ -104,22 +104,17 @@ DEFINE_EVENT(sched_wakeup_template, sched_wakeup_new,
TP_ARGS(p));
#ifdef CREATE_TRACE_POINTS
-static inline long __trace_sched_switch_state(struct task_struct *p)
+static inline long __trace_sched_switch_state(bool preempt, struct task_struct *p)
{
- long state = p->state;
-
-#ifdef CONFIG_PREEMPT
#ifdef CONFIG_SCHED_DEBUG
BUG_ON(p != current);
#endif /* CONFIG_SCHED_DEBUG */
+
/*
- * For all intents and purposes a preempted task is a running task.
+ * Preemption ignores task state, therefore preempted tasks are always
+ * RUNNING (we will not have dequeued if state != RUNNING).
*/
- if (preempt_count() & PREEMPT_ACTIVE)
- state = TASK_RUNNING | TASK_STATE_MAX;
-#endif /* CONFIG_PREEMPT */
-
- return state;
+ return preempt ? TASK_RUNNING | TASK_STATE_MAX : p->state;
}
#endif /* CREATE_TRACE_POINTS */
@@ -128,10 +123,11 @@ static inline long __trace_sched_switch_state(struct task_struct *p)
*/
TRACE_EVENT(sched_switch,
- TP_PROTO(struct task_struct *prev,
+ TP_PROTO(bool preempt,
+ struct task_struct *prev,
struct task_struct *next),
- TP_ARGS(prev, next),
+ TP_ARGS(preempt, prev, next),
TP_STRUCT__entry(
__array( char, prev_comm, TASK_COMM_LEN )
@@ -147,7 +143,7 @@ TRACE_EVENT(sched_switch,
memcpy(__entry->next_comm, next->comm, TASK_COMM_LEN);
__entry->prev_pid = prev->pid;
__entry->prev_prio = prev->prio;
- __entry->prev_state = __trace_sched_switch_state(prev);
+ __entry->prev_state = __trace_sched_switch_state(preempt, prev);
memcpy(__entry->prev_comm, prev->comm, TASK_COMM_LEN);
__entry->next_pid = next->pid;
__entry->next_prio = next->prio;
diff --git a/kernel/cpu.c b/kernel/cpu.c
index 82cf9dff4295..c85df2775b73 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -304,8 +304,8 @@ static inline void check_for_tasks(int dead_cpu)
{
struct task_struct *g, *p;
- read_lock_irq(&tasklist_lock);
- do_each_thread(g, p) {
+ read_lock(&tasklist_lock);
+ for_each_process_thread(g, p) {
if (!p->on_rq)
continue;
/*
@@ -320,8 +320,8 @@ static inline void check_for_tasks(int dead_cpu)
pr_warn("Task %s (pid=%d) is on cpu %d (state=%ld, flags=%x)\n",
p->comm, task_pid_nr(p), dead_cpu, p->state, p->flags);
- } while_each_thread(g, p);
- read_unlock_irq(&tasklist_lock);
+ }
+ read_unlock(&tasklist_lock);
}
struct take_cpu_down_param {
@@ -344,7 +344,7 @@ static int take_cpu_down(void *_param)
/* Give up timekeeping duties */
tick_handover_do_timer();
/* Park the stopper thread */
- kthread_park(current);
+ stop_machine_park((long)param->hcpu);
return 0;
}
diff --git a/kernel/exit.c b/kernel/exit.c
index ea95ee1b5ef7..443677c8efe6 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -706,10 +706,12 @@ void do_exit(long code)
smp_mb();
raw_spin_unlock_wait(&tsk->pi_lock);
- if (unlikely(in_atomic()))
+ if (unlikely(in_atomic())) {
pr_info("note: %s[%d] exited with preempt_count %d\n",
current->comm, task_pid_nr(current),
preempt_count());
+ preempt_count_set(PREEMPT_ENABLED);
+ }
/* sync mm's RSS info before statistics gathering */
if (tsk->mm)
diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c
index 7781d801212f..35e9bfcc6ad9 100644
--- a/kernel/locking/rtmutex.c
+++ b/kernel/locking/rtmutex.c
@@ -158,7 +158,8 @@ rt_mutex_waiter_less(struct rt_mutex_waiter *left,
* then right waiter has a dl_prio() too.
*/
if (dl_prio(left->prio))
- return (left->task->dl.deadline < right->task->dl.deadline);
+ return dl_time_before(left->task->dl.deadline,
+ right->task->dl.deadline);
return 0;
}
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 5bd7d60658d3..b4d263db52a6 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -817,7 +817,7 @@ static void set_load_weight(struct task_struct *p)
/*
* SCHED_IDLE tasks get minimal weight:
*/
- if (p->policy == SCHED_IDLE) {
+ if (idle_policy(p->policy)) {
load->weight = scale_load(WEIGHT_IDLEPRIO);
load->inv_weight = WMULT_IDLEPRIO;
return;
@@ -827,17 +827,19 @@ static void set_load_weight(struct task_struct *p)
load->inv_weight = prio_to_wmult[prio];
}
-static void enqueue_task(struct rq *rq, struct task_struct *p, int flags)
+static inline void enqueue_task(struct rq *rq, struct task_struct *p, int flags)
{
update_rq_clock(rq);
- sched_info_queued(rq, p);
+ if (!(flags & ENQUEUE_RESTORE))
+ sched_info_queued(rq, p);
p->sched_class->enqueue_task(rq, p, flags);
}
-static void dequeue_task(struct rq *rq, struct task_struct *p, int flags)
+static inline void dequeue_task(struct rq *rq, struct task_struct *p, int flags)
{
update_rq_clock(rq);
- sched_info_dequeued(rq, p);
+ if (!(flags & DEQUEUE_SAVE))
+ sched_info_dequeued(rq, p);
p->sched_class->dequeue_task(rq, p, flags);
}
@@ -1178,7 +1180,7 @@ void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask)
* holding rq->lock.
*/
lockdep_assert_held(&rq->lock);
- dequeue_task(rq, p, 0);
+ dequeue_task(rq, p, DEQUEUE_SAVE);
}
if (running)
put_prev_task(rq, p);
@@ -1188,7 +1190,7 @@ void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask)
if (running)
p->sched_class->set_curr_task(rq);
if (queued)
- enqueue_task(rq, p, 0);
+ enqueue_task(rq, p, ENQUEUE_RESTORE);
}
/*
@@ -1292,7 +1294,7 @@ void set_task_cpu(struct task_struct *p, unsigned int new_cpu)
if (task_cpu(p) != new_cpu) {
if (p->sched_class->migrate_task_rq)
- p->sched_class->migrate_task_rq(p, new_cpu);
+ p->sched_class->migrate_task_rq(p);
p->se.nr_migrations++;
perf_event_task_migrate(p);
}
@@ -1333,12 +1335,16 @@ static int migrate_swap_stop(void *data)
struct rq *src_rq, *dst_rq;
int ret = -EAGAIN;
+ if (!cpu_active(arg->src_cpu) || !cpu_active(arg->dst_cpu))
+ return -EAGAIN;
+
src_rq = cpu_rq(arg->src_cpu);
dst_rq = cpu_rq(arg->dst_cpu);
double_raw_lock(&arg->src_task->pi_lock,
&arg->dst_task->pi_lock);
double_rq_lock(src_rq, dst_rq);
+
if (task_cpu(arg->dst_task) != arg->dst_cpu)
goto unlock;
@@ -1574,13 +1580,15 @@ static int select_fallback_rq(int cpu, struct task_struct *p)
goto out;
}
+ /* No more Mr. Nice Guy. */
switch (state) {
case cpuset:
- /* No more Mr. Nice Guy. */
- cpuset_cpus_allowed_fallback(p);
- state = possible;
- break;
-
+ if (IS_ENABLED(CONFIG_CPUSETS)) {
+ cpuset_cpus_allowed_fallback(p);
+ state = possible;
+ break;
+ }
+ /* fall-through */
case possible:
do_set_cpus_allowed(p, cpu_possible_mask);
state = fail;
@@ -1692,7 +1700,7 @@ ttwu_stat(struct task_struct *p, int cpu, int wake_flags)
#endif /* CONFIG_SCHEDSTATS */
}
-static void ttwu_activate(struct rq *rq, struct task_struct *p, int en_flags)
+static inline void ttwu_activate(struct rq *rq, struct task_struct *p, int en_flags)
{
activate_task(rq, p, en_flags);
p->on_rq = TASK_ON_RQ_QUEUED;
@@ -2114,23 +2122,17 @@ static void __sched_fork(unsigned long clone_flags, struct task_struct *p)
#endif /* CONFIG_NUMA_BALANCING */
}
+DEFINE_STATIC_KEY_FALSE(sched_numa_balancing);
+
#ifdef CONFIG_NUMA_BALANCING
-#ifdef CONFIG_SCHED_DEBUG
+
void set_numabalancing_state(bool enabled)
{
if (enabled)
- sched_feat_set("NUMA");
+ static_branch_enable(&sched_numa_balancing);
else
- sched_feat_set("NO_NUMA");
+ static_branch_disable(&sched_numa_balancing);
}
-#else
-__read_mostly bool numabalancing_enabled;
-
-void set_numabalancing_state(bool enabled)
-{
- numabalancing_enabled = enabled;
-}
-#endif /* CONFIG_SCHED_DEBUG */
#ifdef CONFIG_PROC_SYSCTL
int sysctl_numa_balancing(struct ctl_table *table, int write,
@@ -2138,7 +2140,7 @@ int sysctl_numa_balancing(struct ctl_table *table, int write,
{
struct ctl_table t;
int err;
- int state = numabalancing_enabled;
+ int state = static_branch_likely(&sched_numa_balancing);
if (write && !capable(CAP_SYS_ADMIN))
return -EPERM;
@@ -2349,6 +2351,8 @@ void wake_up_new_task(struct task_struct *p)
struct rq *rq;
raw_spin_lock_irqsave(&p->pi_lock, flags);
+ /* Initialize new task's runnable average */
+ init_entity_runnable_average(&p->se);
#ifdef CONFIG_SMP
/*
* Fork balancing, do it here and not earlier because:
@@ -2358,8 +2362,6 @@ void wake_up_new_task(struct task_struct *p)
set_task_cpu(p, select_task_rq(p, task_cpu(p), SD_BALANCE_FORK, 0));
#endif
- /* Initialize new task's runnable average */
- init_entity_runnable_average(&p->se);
rq = __task_rq_lock(p);
activate_task(rq, p, 0);
p->on_rq = TASK_ON_RQ_QUEUED;
@@ -2476,7 +2478,6 @@ static inline void
prepare_task_switch(struct rq *rq, struct task_struct *prev,
struct task_struct *next)
{
- trace_sched_switch(prev, next);
sched_info_switch(rq, prev, next);
perf_event_task_sched_out(prev, next);
fire_sched_out_preempt_notifiers(prev, next);
@@ -2510,6 +2511,22 @@ static struct rq *finish_task_switch(struct task_struct *prev)
struct mm_struct *mm = rq->prev_mm;
long prev_state;
+ /*
+ * The previous task will have left us with a preempt_count of 2
+ * because it left us after:
+ *
+ * schedule()
+ * preempt_disable(); // 1
+ * __schedule()
+ * raw_spin_lock_irq(&rq->lock) // 2
+ *
+ * Also, see FORK_PREEMPT_COUNT.
+ */
+ if (WARN_ONCE(preempt_count() != 2*PREEMPT_DISABLE_OFFSET,
+ "corrupted preempt_count: %s/%d/0x%x\n",
+ current->comm, current->pid, preempt_count()))
+ preempt_count_set(FORK_PREEMPT_COUNT);
+
rq->prev_mm = NULL;
/*
@@ -2594,8 +2611,15 @@ asmlinkage __visible void schedule_tail(struct task_struct *prev)
{
struct rq *rq;
- /* finish_task_switch() drops rq->lock and enables preemtion */
- preempt_disable();
+ /*
+ * New tasks start with FORK_PREEMPT_COUNT, see there and
+ * finish_task_switch() for details.
+ *
+ * finish_task_switch() will drop rq->lock() and lower preempt_count
+ * and the preempt_enable() will end up enabling preemption (on
+ * PREEMPT_COUNT kernels).
+ */
+
rq = finish_task_switch(prev);
balance_callback(rq);
preempt_enable();
@@ -2953,15 +2977,13 @@ static noinline void __schedule_bug(struct task_struct *prev)
static inline void schedule_debug(struct task_struct *prev)
{
#ifdef CONFIG_SCHED_STACK_END_CHECK
- BUG_ON(unlikely(task_stack_end_corrupted(prev)));
+ BUG_ON(task_stack_end_corrupted(prev));
#endif
- /*
- * Test if we are atomic. Since do_exit() needs to call into
- * schedule() atomically, we ignore that path. Otherwise whine
- * if we are scheduling when we should not.
- */
- if (unlikely(in_atomic_preempt_off() && prev->state != TASK_DEAD))
+
+ if (unlikely(in_atomic_preempt_off())) {
__schedule_bug(prev);
+ preempt_count_set(PREEMPT_DISABLED);
+ }
rcu_sleep_check();
profile_hit(SCHED_PROFILING, __builtin_return_address(0));
@@ -3047,7 +3069,7 @@ pick_next_task(struct rq *rq, struct task_struct *prev)
*
* WARNING: must be called with preemption disabled!
*/
-static void __sched __schedule(void)
+static void __sched notrace __schedule(bool preempt)
{
struct task_struct *prev, *next;
unsigned long *switch_count;
@@ -3059,6 +3081,17 @@ static void __sched __schedule(void)
rcu_note_context_switch();
prev = rq->curr;
+ /*
+ * do_exit() calls schedule() with preemption disabled as an exception;
+ * however we must fix that up, otherwise the next task will see an
+ * inconsistent (higher) preempt count.
+ *
+ * It also avoids the below schedule_debug() test from complaining
+ * about this.
+ */
+ if (unlikely(prev->state == TASK_DEAD))
+ preempt_enable_no_resched_notrace();
+
schedule_debug(prev);
if (sched_feat(HRTICK))
@@ -3076,7 +3109,7 @@ static void __sched __schedule(void)
rq->clock_skip_update <<= 1; /* promote REQ to ACT */
switch_count = &prev->nivcsw;
- if (prev->state && !(preempt_count() & PREEMPT_ACTIVE)) {
+ if (!preempt && prev->state) {
if (unlikely(signal_pending_state(prev->state, prev))) {
prev->state = TASK_RUNNING;
} else {
@@ -3112,6 +3145,7 @@ static void __sched __schedule(void)
rq->curr = next;
++*switch_count;
+ trace_sched_switch(preempt, prev, next);
rq = context_switch(rq, prev, next); /* unlocks the rq */
cpu = cpu_of(rq);
} else {
@@ -3141,7 +3175,7 @@ asmlinkage __visible void __sched schedule(void)
sched_submit_work(tsk);
do {
preempt_disable();
- __schedule();
+ __schedule(false);
sched_preempt_enable_no_resched();
} while (need_resched());
}
@@ -3181,9 +3215,9 @@ void __sched schedule_preempt_disabled(void)
static void __sched notrace preempt_schedule_common(void)
{
do {
- preempt_active_enter();
- __schedule();
- preempt_active_exit();
+ preempt_disable_notrace();
+ __schedule(true);
+ preempt_enable_no_resched_notrace();
/*
* Check again in case we missed a preemption opportunity
@@ -3234,24 +3268,17 @@ asmlinkage __visible void __sched notrace preempt_schedule_notrace(void)
return;
do {
- /*
- * Use raw __prempt_count() ops that don't call function.
- * We can't call functions before disabling preemption which
- * disarm preemption tracing recursions.
- */
- __preempt_count_add(PREEMPT_ACTIVE + PREEMPT_DISABLE_OFFSET);
- barrier();
+ preempt_disable_notrace();
/*
* Needs preempt disabled in case user_exit() is traced
* and the tracer calls preempt_enable_notrace() causing
* an infinite recursion.
*/
prev_ctx = exception_enter();
- __schedule();
+ __schedule(true);
exception_exit(prev_ctx);
- barrier();
- __preempt_count_sub(PREEMPT_ACTIVE + PREEMPT_DISABLE_OFFSET);
+ preempt_enable_no_resched_notrace();
} while (need_resched());
}
EXPORT_SYMBOL_GPL(preempt_schedule_notrace);
@@ -3274,11 +3301,11 @@ asmlinkage __visible void __sched preempt_schedule_irq(void)
prev_state = exception_enter();
do {
- preempt_active_enter();
+ preempt_disable();
local_irq_enable();
- __schedule();
+ __schedule(true);
local_irq_disable();
- preempt_active_exit();
+ sched_preempt_enable_no_resched();
} while (need_resched());
exception_exit(prev_state);
@@ -3306,7 +3333,7 @@ EXPORT_SYMBOL(default_wake_function);
*/
void rt_mutex_setprio(struct task_struct *p, int prio)
{
- int oldprio, queued, running, enqueue_flag = 0;
+ int oldprio, queued, running, enqueue_flag = ENQUEUE_RESTORE;
struct rq *rq;
const struct sched_class *prev_class;
@@ -3338,7 +3365,7 @@ void rt_mutex_setprio(struct task_struct *p, int prio)
queued = task_on_rq_queued(p);
running = task_current(rq, p);
if (queued)
- dequeue_task(rq, p, 0);
+ dequeue_task(rq, p, DEQUEUE_SAVE);
if (running)
put_prev_task(rq, p);
@@ -3356,7 +3383,7 @@ void rt_mutex_setprio(struct task_struct *p, int prio)
if (!dl_prio(p->normal_prio) ||
(pi_task && dl_entity_preempt(&pi_task->dl, &p->dl))) {
p->dl.dl_boosted = 1;
- enqueue_flag = ENQUEUE_REPLENISH;
+ enqueue_flag |= ENQUEUE_REPLENISH;
} else
p->dl.dl_boosted = 0;
p->sched_class = &dl_sched_class;
@@ -3364,7 +3391,7 @@ void rt_mutex_setprio(struct task_struct *p, int prio)
if (dl_prio(oldprio))
p->dl.dl_boosted = 0;
if (oldprio < prio)
- enqueue_flag = ENQUEUE_HEAD;
+ enqueue_flag |= ENQUEUE_HEAD;
p->sched_class = &rt_sched_class;
} else {
if (dl_prio(oldprio))
@@ -3416,7 +3443,7 @@ void set_user_nice(struct task_struct *p, long nice)
}
queued = task_on_rq_queued(p);
if (queued)
- dequeue_task(rq, p, 0);
+ dequeue_task(rq, p, DEQUEUE_SAVE);
p->static_prio = NICE_TO_PRIO(nice);
set_load_weight(p);
@@ -3425,7 +3452,7 @@ void set_user_nice(struct task_struct *p, long nice)
delta = p->prio - old_prio;
if (queued) {
- enqueue_task(rq, p, 0);
+ enqueue_task(rq, p, ENQUEUE_RESTORE);
/*
* If the task increased its priority or is running and
* lowered its priority, then reschedule its CPU:
@@ -3746,10 +3773,7 @@ static int __sched_setscheduler(struct task_struct *p,
} else {
reset_on_fork = !!(attr->sched_flags & SCHED_FLAG_RESET_ON_FORK);
- if (policy != SCHED_DEADLINE &&
- policy != SCHED_FIFO && policy != SCHED_RR &&
- policy != SCHED_NORMAL && policy != SCHED_BATCH &&
- policy != SCHED_IDLE)
+ if (!valid_policy(policy))
return -EINVAL;
}
@@ -3805,7 +3829,7 @@ static int __sched_setscheduler(struct task_struct *p,
* Treat SCHED_IDLE as nice 20. Only allow a switch to
* SCHED_NORMAL if the RLIMIT_NICE would normally permit it.
*/
- if (p->policy == SCHED_IDLE && policy != SCHED_IDLE) {
+ if (idle_policy(p->policy) && !idle_policy(policy)) {
if (!can_nice(p, task_nice(p)))
return -EPERM;
}
@@ -3930,7 +3954,7 @@ static int __sched_setscheduler(struct task_struct *p,
queued = task_on_rq_queued(p);
running = task_current(rq, p);
if (queued)
- dequeue_task(rq, p, 0);
+ dequeue_task(rq, p, DEQUEUE_SAVE);
if (running)
put_prev_task(rq, p);
@@ -3940,11 +3964,15 @@ static int __sched_setscheduler(struct task_struct *p,
if (running)
p->sched_class->set_curr_task(rq);
if (queued) {
+ int enqueue_flags = ENQUEUE_RESTORE;
/*
* We enqueue to tail when the priority of a task is
* increased (user space view).
*/
- enqueue_task(rq, p, oldprio <= p->prio ? ENQUEUE_HEAD : 0);
+ if (oldprio <= p->prio)
+ enqueue_flags |= ENQUEUE_HEAD;
+
+ enqueue_task(rq, p, enqueue_flags);
}
check_class_changed(rq, p, prev_class, oldprio);
@@ -5093,7 +5121,7 @@ void sched_setnuma(struct task_struct *p, int nid)
running = task_current(rq, p);
if (queued)
- dequeue_task(rq, p, 0);
+ dequeue_task(rq, p, DEQUEUE_SAVE);
if (running)
put_prev_task(rq, p);
@@ -5102,7 +5130,7 @@ void sched_setnuma(struct task_struct *p, int nid)
if (running)
p->sched_class->set_curr_task(rq);
if (queued)
- enqueue_task(rq, p, 0);
+ enqueue_task(rq, p, ENQUEUE_RESTORE);
task_rq_unlock(rq, p, &flags);
}
#endif /* CONFIG_NUMA_BALANCING */
@@ -5523,21 +5551,27 @@ static void set_cpu_rq_start_time(void)
static int sched_cpu_active(struct notifier_block *nfb,
unsigned long action, void *hcpu)
{
+ int cpu = (long)hcpu;
+
switch (action & ~CPU_TASKS_FROZEN) {
case CPU_STARTING:
set_cpu_rq_start_time();
return NOTIFY_OK;
+
case CPU_ONLINE:
/*
* At this point a starting CPU has marked itself as online via
* set_cpu_online(). But it might not yet have marked itself
* as active, which is essential from here on.
- *
- * Thus, fall-through and help the starting CPU along.
*/
+ set_cpu_active(cpu, true);
+ stop_machine_unpark(cpu);
+ return NOTIFY_OK;
+
case CPU_DOWN_FAILED:
- set_cpu_active((long)hcpu, true);
+ set_cpu_active(cpu, true);
return NOTIFY_OK;
+
default:
return NOTIFY_DONE;
}
@@ -6469,7 +6503,8 @@ static struct sched_domain_topology_level default_topology[] = {
{ NULL, },
};
-struct sched_domain_topology_level *sched_domain_topology = default_topology;
+static struct sched_domain_topology_level *sched_domain_topology =
+ default_topology;
#define for_each_sd_topology(tl) \
for (tl = sched_domain_topology; tl->mask; tl++)
@@ -7470,7 +7505,7 @@ void __init sched_init(void)
#ifdef CONFIG_DEBUG_ATOMIC_SLEEP
static inline int preempt_count_equals(int preempt_offset)
{
- int nested = (preempt_count() & ~PREEMPT_ACTIVE) + rcu_preempt_depth();
+ int nested = preempt_count() + rcu_preempt_depth();
return (nested == preempt_offset);
}
@@ -7717,7 +7752,7 @@ void sched_move_task(struct task_struct *tsk)
queued = task_on_rq_queued(tsk);
if (queued)
- dequeue_task(rq, tsk, 0);
+ dequeue_task(rq, tsk, DEQUEUE_SAVE);
if (unlikely(running))
put_prev_task(rq, tsk);
@@ -7733,7 +7768,7 @@ void sched_move_task(struct task_struct *tsk)
#ifdef CONFIG_FAIR_GROUP_SCHED
if (tsk->sched_class->task_move_group)
- tsk->sched_class->task_move_group(tsk, queued);
+ tsk->sched_class->task_move_group(tsk);
else
#endif
set_task_rq(tsk, task_cpu(tsk));
@@ -7741,7 +7776,7 @@ void sched_move_task(struct task_struct *tsk)
if (unlikely(running))
tsk->sched_class->set_curr_task(rq);
if (queued)
- enqueue_task(rq, tsk, 0);
+ enqueue_task(rq, tsk, ENQUEUE_RESTORE);
task_rq_unlock(rq, tsk, &flags);
}
@@ -8205,14 +8240,6 @@ static void cpu_cgroup_exit(struct cgroup_subsys_state *css,
struct cgroup_subsys_state *old_css,
struct task_struct *task)
{
- /*
- * cgroup_exit() is called in the copy_process() failure path.
- * Ignore this case since the task hasn't ran yet, this avoids
- * trying to poke a half freed task state from generic code.
- */
- if (!(task->flags & PF_EXITING))
- return;
-
sched_move_task(task);
}
diff --git a/kernel/sched/cpudeadline.c b/kernel/sched/cpudeadline.c
index c6acb07466bb..5a75b08cfd85 100644
--- a/kernel/sched/cpudeadline.c
+++ b/kernel/sched/cpudeadline.c
@@ -31,11 +31,6 @@ static inline int right_child(int i)
return (i << 1) + 2;
}
-static inline int dl_time_before(u64 a, u64 b)
-{
- return (s64)(a - b) < 0;
-}
-
static void cpudl_exchange(struct cpudl *cp, int a, int b)
{
int cpu_a = cp->elements[a].cpu, cpu_b = cp->elements[b].cpu;
diff --git a/kernel/sched/cpudeadline.h b/kernel/sched/cpudeadline.h
index 1a0a6ef2fbe1..fcbdf83fed7e 100644
--- a/kernel/sched/cpudeadline.h
+++ b/kernel/sched/cpudeadline.h
@@ -2,6 +2,7 @@
#define _LINUX_CPUDL_H
#include <linux/sched.h>
+#include <linux/sched/deadline.h>
#define IDX_INVALID -1
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 9a5e60fe721a..824aa9f501a3 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -661,11 +661,12 @@ static unsigned long task_h_load(struct task_struct *p);
/*
* We choose a half-life close to 1 scheduling period.
- * Note: The tables below are dependent on this value.
+ * Note: The tables runnable_avg_yN_inv and runnable_avg_yN_sum are
+ * dependent on this value.
*/
#define LOAD_AVG_PERIOD 32
#define LOAD_AVG_MAX 47742 /* maximum possible load avg */
-#define LOAD_AVG_MAX_N 345 /* number of full periods to produce LOAD_MAX_AVG */
+#define LOAD_AVG_MAX_N 345 /* number of full periods to produce LOAD_AVG_MAX */
/* Give new sched_entity start runnable values to heavy its load in infant time */
void init_entity_runnable_average(struct sched_entity *se)
@@ -682,7 +683,7 @@ void init_entity_runnable_average(struct sched_entity *se)
sa->load_avg = scale_load_down(se->load.weight);
sa->load_sum = sa->load_avg * LOAD_AVG_MAX;
sa->util_avg = scale_load_down(SCHED_LOAD_SCALE);
- sa->util_sum = LOAD_AVG_MAX;
+ sa->util_sum = sa->util_avg * LOAD_AVG_MAX;
/* when this task enqueue'ed, it will contribute to its cfs_rq's load_avg */
}
@@ -2069,7 +2070,7 @@ void task_numa_fault(int last_cpupid, int mem_node, int pages, int flags)
int local = !!(flags & TNF_FAULT_LOCAL);
int priv;
- if (!numabalancing_enabled)
+ if (!static_branch_likely(&sched_numa_balancing))
return;
/* for example, ksmd faulting in a user's mm */
@@ -2157,7 +2158,7 @@ void task_numa_work(struct callback_head *work)
struct vm_area_struct *vma;
unsigned long start, end;
unsigned long nr_pte_updates = 0;
- long pages;
+ long pages, virtpages;
WARN_ON_ONCE(p != container_of(work, struct task_struct, numa_work));
@@ -2203,9 +2204,11 @@ void task_numa_work(struct callback_head *work)
start = mm->numa_scan_offset;
pages = sysctl_numa_balancing_scan_size;
pages <<= 20 - PAGE_SHIFT; /* MB in pages */
+ virtpages = pages * 8; /* Scan up to this much virtual space */
if (!pages)
return;
+
down_read(&mm->mmap_sem);
vma = find_vma(mm, start);
if (!vma) {
@@ -2240,18 +2243,22 @@ void task_numa_work(struct callback_head *work)
start = max(start, vma->vm_start);
end = ALIGN(start + (pages << PAGE_SHIFT), HPAGE_SIZE);
end = min(end, vma->vm_end);
- nr_pte_updates += change_prot_numa(vma, start, end);
+ nr_pte_updates = change_prot_numa(vma, start, end);
/*
- * Scan sysctl_numa_balancing_scan_size but ensure that
- * at least one PTE is updated so that unused virtual
- * address space is quickly skipped.
+ * Try to scan sysctl_numa_balancing_size worth of
+ * hpages that have at least one present PTE that
+ * is not already pte-numa. If the VMA contains
+ * areas that are unused or already full of prot_numa
+ * PTEs, scan up to virtpages, to skip through those
+ * areas faster.
*/
if (nr_pte_updates)
pages -= (end - start) >> PAGE_SHIFT;
+ virtpages -= (end - start) >> PAGE_SHIFT;
start = end;
- if (pages <= 0)
+ if (pages <= 0 || virtpages <= 0)
goto out;
cond_resched();
@@ -2515,6 +2522,12 @@ static u32 __compute_runnable_contrib(u64 n)
return contrib + runnable_avg_yN_sum[n];
}
+#if (SCHED_LOAD_SHIFT - SCHED_LOAD_RESOLUTION) != 10 || SCHED_CAPACITY_SHIFT != 10
+#error "load tracking assumes 2^10 as unit"
+#endif
+
+#define cap_scale(v, s) ((v)*(s) >> SCHED_CAPACITY_SHIFT)
+
/*
* We can represent the historical contribution to runnable average as the
* coefficients of a geometric series. To do this we sub-divide our runnable
@@ -2547,10 +2560,10 @@ static __always_inline int
__update_load_avg(u64 now, int cpu, struct sched_avg *sa,
unsigned long weight, int running, struct cfs_rq *cfs_rq)
{
- u64 delta, periods;
+ u64 delta, scaled_delta, periods;
u32 contrib;
- int delta_w, decayed = 0;
- unsigned long scale_freq = arch_scale_freq_capacity(NULL, cpu);
+ unsigned int delta_w, scaled_delta_w, decayed = 0;
+ unsigned long scale_freq, scale_cpu;
delta = now - sa->last_update_time;
/*
@@ -2571,6 +2584,9 @@ __update_load_avg(u64 now, int cpu, struct sched_avg *sa,
return 0;
sa->last_update_time = now;
+ scale_freq = arch_scale_freq_capacity(NULL, cpu);
+ scale_cpu = arch_scale_cpu_capacity(NULL, cpu);
+
/* delta_w is the amount already accumulated against our next period */
delta_w = sa->period_contrib;
if (delta + delta_w >= 1024) {
@@ -2585,13 +2601,16 @@ __update_load_avg(u64 now, int cpu, struct sched_avg *sa,
* period and accrue it.
*/
delta_w = 1024 - delta_w;
+ scaled_delta_w = cap_scale(delta_w, scale_freq);
if (weight) {
- sa->load_sum += weight * delta_w;
- if (cfs_rq)
- cfs_rq->runnable_load_sum += weight * delta_w;
+ sa->load_sum += weight * scaled_delta_w;
+ if (cfs_rq) {
+ cfs_rq->runnable_load_sum +=
+ weight * scaled_delta_w;
+ }
}
if (running)
- sa->util_sum += delta_w * scale_freq >> SCHED_CAPACITY_SHIFT;
+ sa->util_sum += scaled_delta_w * scale_cpu;
delta -= delta_w;
@@ -2608,23 +2627,25 @@ __update_load_avg(u64 now, int cpu, struct sched_avg *sa,
/* Efficiently calculate \sum (1..n_period) 1024*y^i */
contrib = __compute_runnable_contrib(periods);
+ contrib = cap_scale(contrib, scale_freq);
if (weight) {
sa->load_sum += weight * contrib;
if (cfs_rq)
cfs_rq->runnable_load_sum += weight * contrib;
}
if (running)
- sa->util_sum += contrib * scale_freq >> SCHED_CAPACITY_SHIFT;
+ sa->util_sum += contrib * scale_cpu;
}
/* Remainder of delta accrued against u_0` */
+ scaled_delta = cap_scale(delta, scale_freq);
if (weight) {
- sa->load_sum += weight * delta;
+ sa->load_sum += weight * scaled_delta;
if (cfs_rq)
- cfs_rq->runnable_load_sum += weight * delta;
+ cfs_rq->runnable_load_sum += weight * scaled_delta;
}
if (running)
- sa->util_sum += delta * scale_freq >> SCHED_CAPACITY_SHIFT;
+ sa->util_sum += scaled_delta * scale_cpu;
sa->period_contrib += delta;
@@ -2634,7 +2655,7 @@ __update_load_avg(u64 now, int cpu, struct sched_avg *sa,
cfs_rq->runnable_load_avg =
div_u64(cfs_rq->runnable_load_sum, LOAD_AVG_MAX);
}
- sa->util_avg = (sa->util_sum << SCHED_LOAD_SHIFT) / LOAD_AVG_MAX;
+ sa->util_avg = sa->util_sum / LOAD_AVG_MAX;
}
return decayed;
@@ -2677,8 +2698,7 @@ static inline int update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq)
if (atomic_long_read(&cfs_rq->removed_util_avg)) {
long r = atomic_long_xchg(&cfs_rq->removed_util_avg, 0);
sa->util_avg = max_t(long, sa->util_avg - r, 0);
- sa->util_sum = max_t(s32, sa->util_sum -
- ((r * LOAD_AVG_MAX) >> SCHED_LOAD_SHIFT), 0);
+ sa->util_sum = max_t(s32, sa->util_sum - r * LOAD_AVG_MAX, 0);
}
decayed = __update_load_avg(now, cpu_of(rq_of(cfs_rq)), sa,
@@ -2696,33 +2716,70 @@ static inline int update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq)
static inline void update_load_avg(struct sched_entity *se, int update_tg)
{
struct cfs_rq *cfs_rq = cfs_rq_of(se);
- int cpu = cpu_of(rq_of(cfs_rq));
u64 now = cfs_rq_clock_task(cfs_rq);
+ int cpu = cpu_of(rq_of(cfs_rq));
/*
* Track task load average for carrying it to new CPU after migrated, and
* track group sched_entity load average for task_h_load calc in migration
*/
__update_load_avg(now, cpu, &se->avg,
- se->on_rq * scale_load_down(se->load.weight), cfs_rq->curr == se, NULL);
+ se->on_rq * scale_load_down(se->load.weight),
+ cfs_rq->curr == se, NULL);
if (update_cfs_rq_load_avg(now, cfs_rq) && update_tg)
update_tg_load_avg(cfs_rq, 0);
}
+static void attach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se)
+{
+ if (!sched_feat(ATTACH_AGE_LOAD))
+ goto skip_aging;
+
+ /*
+ * If we got migrated (either between CPUs or between cgroups) we'll
+ * have aged the average right before clearing @last_update_time.
+ */
+ if (se->avg.last_update_time) {
+ __update_load_avg(cfs_rq->avg.last_update_time, cpu_of(rq_of(cfs_rq)),
+ &se->avg, 0, 0, NULL);
+
+ /*
+ * XXX: we could have just aged the entire load away if we've been
+ * absent from the fair class for too long.
+ */
+ }
+
+skip_aging:
+ se->avg.last_update_time = cfs_rq->avg.last_update_time;
+ cfs_rq->avg.load_avg += se->avg.load_avg;
+ cfs_rq->avg.load_sum += se->avg.load_sum;
+ cfs_rq->avg.util_avg += se->avg.util_avg;
+ cfs_rq->avg.util_sum += se->avg.util_sum;
+}
+
+static void detach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se)
+{
+ __update_load_avg(cfs_rq->avg.last_update_time, cpu_of(rq_of(cfs_rq)),
+ &se->avg, se->on_rq * scale_load_down(se->load.weight),
+ cfs_rq->curr == se, NULL);
+
+ cfs_rq->avg.load_avg = max_t(long, cfs_rq->avg.load_avg - se->avg.load_avg, 0);
+ cfs_rq->avg.load_sum = max_t(s64, cfs_rq->avg.load_sum - se->avg.load_sum, 0);
+ cfs_rq->avg.util_avg = max_t(long, cfs_rq->avg.util_avg - se->avg.util_avg, 0);
+ cfs_rq->avg.util_sum = max_t(s32, cfs_rq->avg.util_sum - se->avg.util_sum, 0);
+}
+
/* Add the load generated by se into cfs_rq's load average */
static inline void
enqueue_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
struct sched_avg *sa = &se->avg;
u64 now = cfs_rq_clock_task(cfs_rq);
- int migrated = 0, decayed;
+ int migrated, decayed;
- if (sa->last_update_time == 0) {
- sa->last_update_time = now;
- migrated = 1;
- }
- else {
+ migrated = !sa->last_update_time;
+ if (!migrated) {
__update_load_avg(now, cpu_of(rq_of(cfs_rq)), sa,
se->on_rq * scale_load_down(se->load.weight),
cfs_rq->curr == se, NULL);
@@ -2733,12 +2790,8 @@ enqueue_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se)
cfs_rq->runnable_load_avg += sa->load_avg;
cfs_rq->runnable_load_sum += sa->load_sum;
- if (migrated) {
- cfs_rq->avg.load_avg += sa->load_avg;
- cfs_rq->avg.load_sum += sa->load_sum;
- cfs_rq->avg.util_avg += sa->util_avg;
- cfs_rq->avg.util_sum += sa->util_sum;
- }
+ if (migrated)
+ attach_entity_load_avg(cfs_rq, se);
if (decayed || migrated)
update_tg_load_avg(cfs_rq, 0);
@@ -2753,7 +2806,7 @@ dequeue_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se)
cfs_rq->runnable_load_avg =
max_t(long, cfs_rq->runnable_load_avg - se->avg.load_avg, 0);
cfs_rq->runnable_load_sum =
- max_t(s64, cfs_rq->runnable_load_sum - se->avg.load_sum, 0);
+ max_t(s64, cfs_rq->runnable_load_sum - se->avg.load_sum, 0);
}
/*
@@ -2821,6 +2874,11 @@ static inline void
dequeue_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) {}
static inline void remove_entity_load_avg(struct sched_entity *se) {}
+static inline void
+attach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) {}
+static inline void
+detach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) {}
+
static inline int idle_balance(struct rq *rq)
{
return 0;
@@ -4817,32 +4875,39 @@ static int select_idle_sibling(struct task_struct *p, int target)
done:
return target;
}
+
/*
- * get_cpu_usage returns the amount of capacity of a CPU that is used by CFS
+ * cpu_util returns the amount of capacity of a CPU that is used by CFS
* tasks. The unit of the return value must be the one of capacity so we can
- * compare the usage with the capacity of the CPU that is available for CFS
- * task (ie cpu_capacity).
- * cfs.avg.util_avg is the sum of running time of runnable tasks on a
- * CPU. It represents the amount of utilization of a CPU in the range
- * [0..SCHED_LOAD_SCALE]. The usage of a CPU can't be higher than the full
- * capacity of the CPU because it's about the running time on this CPU.
- * Nevertheless, cfs.avg.util_avg can be higher than SCHED_LOAD_SCALE
- * because of unfortunate rounding in util_avg or just
- * after migrating tasks until the average stabilizes with the new running
- * time. So we need to check that the usage stays into the range
- * [0..cpu_capacity_orig] and cap if necessary.
- * Without capping the usage, a group could be seen as overloaded (CPU0 usage
- * at 121% + CPU1 usage at 80%) whereas CPU1 has 20% of available capacity
+ * compare the utilization with the capacity of the CPU that is available for
+ * CFS task (ie cpu_capacity).
+ *
+ * cfs_rq.avg.util_avg is the sum of running time of runnable tasks plus the
+ * recent utilization of currently non-runnable tasks on a CPU. It represents
+ * the amount of utilization of a CPU in the range [0..capacity_orig] where
+ * capacity_orig is the cpu_capacity available at the highest frequency
+ * (arch_scale_freq_capacity()).
+ * The utilization of a CPU converges towards a sum equal to or less than the
+ * current capacity (capacity_curr <= capacity_orig) of the CPU because it is
+ * the running time on this CPU scaled by capacity_curr.
+ *
+ * Nevertheless, cfs_rq.avg.util_avg can be higher than capacity_curr or even
+ * higher than capacity_orig because of unfortunate rounding in
+ * cfs.avg.util_avg or just after migrating tasks and new task wakeups until
+ * the average stabilizes with the new running time. We need to check that the
+ * utilization stays within the range of [0..capacity_orig] and cap it if
+ * necessary. Without utilization capping, a group could be seen as overloaded
+ * (CPU0 utilization at 121% + CPU1 utilization at 80%) whereas CPU1 has 20% of
+ * available capacity. We allow utilization to overshoot capacity_curr (but not
+ * capacity_orig) as it useful for predicting the capacity required after task
+ * migrations (scheduler-driven DVFS).
*/
-static int get_cpu_usage(int cpu)
+static int cpu_util(int cpu)
{
- unsigned long usage = cpu_rq(cpu)->cfs.avg.util_avg;
+ unsigned long util = cpu_rq(cpu)->cfs.avg.util_avg;
unsigned long capacity = capacity_orig_of(cpu);
- if (usage >= SCHED_LOAD_SCALE)
- return capacity;
-
- return (usage * capacity) >> SCHED_LOAD_SHIFT;
+ return (util >= capacity) ? capacity : util;
}
/*
@@ -4945,7 +5010,7 @@ select_task_rq_fair(struct task_struct *p, int prev_cpu, int sd_flag, int wake_f
* previous cpu. However, the caller only guarantees p->pi_lock is held; no
* other assumptions, including the state of rq->lock, should be made.
*/
-static void migrate_task_rq_fair(struct task_struct *p, int next_cpu)
+static void migrate_task_rq_fair(struct task_struct *p)
{
/*
* We are supposed to update the task to "current" time, then its up to date
@@ -5525,10 +5590,10 @@ static int migrate_degrades_locality(struct task_struct *p, struct lb_env *env)
unsigned long src_faults, dst_faults;
int src_nid, dst_nid;
- if (!p->numa_faults || !(env->sd->flags & SD_NUMA))
+ if (!static_branch_likely(&sched_numa_balancing))
return -1;
- if (!sched_feat(NUMA))
+ if (!p->numa_faults || !(env->sd->flags & SD_NUMA))
return -1;
src_nid = cpu_to_node(env->src_cpu);
@@ -5934,7 +5999,7 @@ struct sg_lb_stats {
unsigned long sum_weighted_load; /* Weighted load of group's tasks */
unsigned long load_per_task;
unsigned long group_capacity;
- unsigned long group_usage; /* Total usage of the group */
+ unsigned long group_util; /* Total utilization of the group */
unsigned int sum_nr_running; /* Nr tasks running in the group */
unsigned int idle_cpus;
unsigned int group_weight;
@@ -6010,19 +6075,6 @@ static inline int get_sd_load_idx(struct sched_domain *sd,
return load_idx;
}
-static unsigned long default_scale_cpu_capacity(struct sched_domain *sd, int cpu)
-{
- if ((sd->flags & SD_SHARE_CPUCAPACITY) && (sd->span_weight > 1))
- return sd->smt_gain / sd->span_weight;
-
- return SCHED_CAPACITY_SCALE;
-}
-
-unsigned long __weak arch_scale_cpu_capacity(struct sched_domain *sd, int cpu)
-{
- return default_scale_cpu_capacity(sd, cpu);
-}
-
static unsigned long scale_rt_capacity(int cpu)
{
struct rq *rq = cpu_rq(cpu);
@@ -6052,16 +6104,9 @@ static unsigned long scale_rt_capacity(int cpu)
static void update_cpu_capacity(struct sched_domain *sd, int cpu)
{
- unsigned long capacity = SCHED_CAPACITY_SCALE;
+ unsigned long capacity = arch_scale_cpu_capacity(sd, cpu);
struct sched_group *sdg = sd->groups;
- if (sched_feat(ARCH_CAPACITY))
- capacity *= arch_scale_cpu_capacity(sd, cpu);
- else
- capacity *= default_scale_cpu_capacity(sd, cpu);
-
- capacity >>= SCHED_CAPACITY_SHIFT;
-
cpu_rq(cpu)->cpu_capacity_orig = capacity;
capacity *= scale_rt_capacity(cpu);
@@ -6187,8 +6232,8 @@ static inline int sg_imbalanced(struct sched_group *group)
* group_has_capacity returns true if the group has spare capacity that could
* be used by some tasks.
* We consider that a group has spare capacity if the * number of task is
- * smaller than the number of CPUs or if the usage is lower than the available
- * capacity for CFS tasks.
+ * smaller than the number of CPUs or if the utilization is lower than the
+ * available capacity for CFS tasks.
* For the latter, we use a threshold to stabilize the state, to take into
* account the variance of the tasks' load and to return true if the available
* capacity in meaningful for the load balancer.
@@ -6202,7 +6247,7 @@ group_has_capacity(struct lb_env *env, struct sg_lb_stats *sgs)
return true;
if ((sgs->group_capacity * 100) >
- (sgs->group_usage * env->sd->imbalance_pct))
+ (sgs->group_util * env->sd->imbalance_pct))
return true;
return false;
@@ -6223,15 +6268,15 @@ group_is_overloaded(struct lb_env *env, struct sg_lb_stats *sgs)
return false;
if ((sgs->group_capacity * 100) <
- (sgs->group_usage * env->sd->imbalance_pct))
+ (sgs->group_util * env->sd->imbalance_pct))
return true;
return false;
}
-static enum group_type group_classify(struct lb_env *env,
- struct sched_group *group,
- struct sg_lb_stats *sgs)
+static inline enum
+group_type group_classify(struct sched_group *group,
+ struct sg_lb_stats *sgs)
{
if (sgs->group_no_capacity)
return group_overloaded;
@@ -6271,7 +6316,7 @@ static inline void update_sg_lb_stats(struct lb_env *env,
load = source_load(i, load_idx);
sgs->group_load += load;
- sgs->group_usage += get_cpu_usage(i);
+ sgs->group_util += cpu_util(i);
sgs->sum_nr_running += rq->cfs.h_nr_running;
if (rq->nr_running > 1)
@@ -6296,7 +6341,7 @@ static inline void update_sg_lb_stats(struct lb_env *env,
sgs->group_weight = group->group_weight;
sgs->group_no_capacity = group_is_overloaded(env, sgs);
- sgs->group_type = group_classify(env, group, sgs);
+ sgs->group_type = group_classify(group, sgs);
}
/**
@@ -6430,7 +6475,7 @@ static inline void update_sd_lb_stats(struct lb_env *env, struct sd_lb_stats *sd
group_has_capacity(env, &sds->local_stat) &&
(sgs->sum_nr_running > 1)) {
sgs->group_no_capacity = 1;
- sgs->group_type = group_overloaded;
+ sgs->group_type = group_classify(sg, sgs);
}
if (update_sd_pick_busiest(env, sds, sg, sgs)) {
@@ -7610,8 +7655,22 @@ static void rebalance_domains(struct rq *rq, enum cpu_idle_type idle)
* When the cpu is attached to null domain for ex, it will not be
* updated.
*/
- if (likely(update_next_balance))
+ if (likely(update_next_balance)) {
rq->next_balance = next_balance;
+
+#ifdef CONFIG_NO_HZ_COMMON
+ /*
+ * If this CPU has been elected to perform the nohz idle
+ * balance. Other idle CPUs have already rebalanced with
+ * nohz_idle_balance() and nohz.next_balance has been
+ * updated accordingly. This CPU is now running the idle load
+ * balance for itself and we need to update the
+ * nohz.next_balance accordingly.
+ */
+ if ((idle == CPU_IDLE) && time_after(nohz.next_balance, rq->next_balance))
+ nohz.next_balance = rq->next_balance;
+#endif
+ }
}
#ifdef CONFIG_NO_HZ_COMMON
@@ -7624,6 +7683,9 @@ static void nohz_idle_balance(struct rq *this_rq, enum cpu_idle_type idle)
int this_cpu = this_rq->cpu;
struct rq *rq;
int balance_cpu;
+ /* Earliest time when we have to do rebalance again */
+ unsigned long next_balance = jiffies + 60*HZ;
+ int update_next_balance = 0;
if (idle != CPU_IDLE ||
!test_bit(NOHZ_BALANCE_KICK, nohz_flags(this_cpu)))
@@ -7655,10 +7717,19 @@ static void nohz_idle_balance(struct rq *this_rq, enum cpu_idle_type idle)
rebalance_domains(rq, CPU_IDLE);
}
- if (time_after(this_rq->next_balance, rq->next_balance))
- this_rq->next_balance = rq->next_balance;
+ if (time_after(next_balance, rq->next_balance)) {
+ next_balance = rq->next_balance;
+ update_next_balance = 1;
+ }
}
- nohz.next_balance = this_rq->next_balance;
+
+ /*
+ * next_balance will be updated only when there is a need.
+ * When the CPU is attached to null domain for ex, it will not be
+ * updated.
+ */
+ if (likely(update_next_balance))
+ nohz.next_balance = next_balance;
end:
clear_bit(NOHZ_BALANCE_KICK, nohz_flags(this_cpu));
}
@@ -7811,7 +7882,7 @@ static void task_tick_fair(struct rq *rq, struct task_struct *curr, int queued)
entity_tick(cfs_rq, se, queued);
}
- if (numabalancing_enabled)
+ if (static_branch_unlikely(&sched_numa_balancing))
task_tick_numa(rq, curr);
}
@@ -7887,21 +7958,39 @@ prio_changed_fair(struct rq *rq, struct task_struct *p, int oldprio)
check_preempt_curr(rq, p, 0);
}
-static void switched_from_fair(struct rq *rq, struct task_struct *p)
+static inline bool vruntime_normalized(struct task_struct *p)
{
struct sched_entity *se = &p->se;
- struct cfs_rq *cfs_rq = cfs_rq_of(se);
/*
- * Ensure the task's vruntime is normalized, so that when it's
- * switched back to the fair class the enqueue_entity(.flags=0) will
- * do the right thing.
+ * In both the TASK_ON_RQ_QUEUED and TASK_ON_RQ_MIGRATING cases,
+ * the dequeue_entity(.flags=0) will already have normalized the
+ * vruntime.
+ */
+ if (p->on_rq)
+ return true;
+
+ /*
+ * When !on_rq, vruntime of the task has usually NOT been normalized.
+ * But there are some cases where it has already been normalized:
*
- * If it's queued, then the dequeue_entity(.flags=0) will already
- * have normalized the vruntime, if it's !queued, then only when
- * the task is sleeping will it still have non-normalized vruntime.
+ * - A forked child which is waiting for being woken up by
+ * wake_up_new_task().
+ * - A task which has been woken up by try_to_wake_up() and
+ * waiting for actually being woken up by sched_ttwu_pending().
*/
- if (!task_on_rq_queued(p) && p->state != TASK_RUNNING) {
+ if (!se->sum_exec_runtime || p->state == TASK_WAKING)
+ return true;
+
+ return false;
+}
+
+static void detach_task_cfs_rq(struct task_struct *p)
+{
+ struct sched_entity *se = &p->se;
+ struct cfs_rq *cfs_rq = cfs_rq_of(se);
+
+ if (!vruntime_normalized(p)) {
/*
* Fix up our vruntime so that the current sleep doesn't
* cause 'unlimited' sleep bonus.
@@ -7910,28 +7999,14 @@ static void switched_from_fair(struct rq *rq, struct task_struct *p)
se->vruntime -= cfs_rq->min_vruntime;
}
-#ifdef CONFIG_SMP
/* Catch up with the cfs_rq and remove our load when we leave */
- __update_load_avg(cfs_rq->avg.last_update_time, cpu_of(rq), &se->avg,
- se->on_rq * scale_load_down(se->load.weight), cfs_rq->curr == se, NULL);
-
- cfs_rq->avg.load_avg =
- max_t(long, cfs_rq->avg.load_avg - se->avg.load_avg, 0);
- cfs_rq->avg.load_sum =
- max_t(s64, cfs_rq->avg.load_sum - se->avg.load_sum, 0);
- cfs_rq->avg.util_avg =
- max_t(long, cfs_rq->avg.util_avg - se->avg.util_avg, 0);
- cfs_rq->avg.util_sum =
- max_t(s32, cfs_rq->avg.util_sum - se->avg.util_sum, 0);
-#endif
+ detach_entity_load_avg(cfs_rq, se);
}
-/*
- * We switched to the sched_fair class.
- */
-static void switched_to_fair(struct rq *rq, struct task_struct *p)
+static void attach_task_cfs_rq(struct task_struct *p)
{
struct sched_entity *se = &p->se;
+ struct cfs_rq *cfs_rq = cfs_rq_of(se);
#ifdef CONFIG_FAIR_GROUP_SCHED
/*
@@ -7941,31 +8016,33 @@ static void switched_to_fair(struct rq *rq, struct task_struct *p)
se->depth = se->parent ? se->parent->depth + 1 : 0;
#endif
- if (!task_on_rq_queued(p)) {
+ /* Synchronize task with its cfs_rq */
+ attach_entity_load_avg(cfs_rq, se);
+ if (!vruntime_normalized(p))
+ se->vruntime += cfs_rq->min_vruntime;
+}
+
+static void switched_from_fair(struct rq *rq, struct task_struct *p)
+{
+ detach_task_cfs_rq(p);
+}
+
+static void switched_to_fair(struct rq *rq, struct task_struct *p)
+{
+ attach_task_cfs_rq(p);
+
+ if (task_on_rq_queued(p)) {
/*
- * Ensure the task has a non-normalized vruntime when it is switched
- * back to the fair class with !queued, so that enqueue_entity() at
- * wake-up time will do the right thing.
- *
- * If it's queued, then the enqueue_entity(.flags=0) makes the task
- * has non-normalized vruntime, if it's !queued, then it still has
- * normalized vruntime.
+ * We were most likely switched from sched_rt, so
+ * kick off the schedule if running, otherwise just see
+ * if we can still preempt the current task.
*/
- if (p->state != TASK_RUNNING)
- se->vruntime += cfs_rq_of(se)->min_vruntime;
- return;
+ if (rq->curr == p)
+ resched_curr(rq);
+ else
+ check_preempt_curr(rq, p, 0);
}
-
- /*
- * We were most likely switched from sched_rt, so
- * kick off the schedule if running, otherwise just see
- * if we can still preempt the current task.
- */
- if (rq->curr == p)
- resched_curr(rq);
- else
- check_preempt_curr(rq, p, 0);
}
/* Account for a task changing its policy or group.
@@ -8000,56 +8077,16 @@ void init_cfs_rq(struct cfs_rq *cfs_rq)
}
#ifdef CONFIG_FAIR_GROUP_SCHED
-static void task_move_group_fair(struct task_struct *p, int queued)
+static void task_move_group_fair(struct task_struct *p)
{
- struct sched_entity *se = &p->se;
- struct cfs_rq *cfs_rq;
-
- /*
- * If the task was not on the rq at the time of this cgroup movement
- * it must have been asleep, sleeping tasks keep their ->vruntime
- * absolute on their old rq until wakeup (needed for the fair sleeper
- * bonus in place_entity()).
- *
- * If it was on the rq, we've just 'preempted' it, which does convert
- * ->vruntime to a relative base.
- *
- * Make sure both cases convert their relative position when migrating
- * to another cgroup's rq. This does somewhat interfere with the
- * fair sleeper stuff for the first placement, but who cares.
- */
- /*
- * When !queued, vruntime of the task has usually NOT been normalized.
- * But there are some cases where it has already been normalized:
- *
- * - Moving a forked child which is waiting for being woken up by
- * wake_up_new_task().
- * - Moving a task which has been woken up by try_to_wake_up() and
- * waiting for actually being woken up by sched_ttwu_pending().
- *
- * To prevent boost or penalty in the new cfs_rq caused by delta
- * min_vruntime between the two cfs_rqs, we skip vruntime adjustment.
- */
- if (!queued && (!se->sum_exec_runtime || p->state == TASK_WAKING))
- queued = 1;
-
- if (!queued)
- se->vruntime -= cfs_rq_of(se)->min_vruntime;
+ detach_task_cfs_rq(p);
set_task_rq(p, task_cpu(p));
- se->depth = se->parent ? se->parent->depth + 1 : 0;
- if (!queued) {
- cfs_rq = cfs_rq_of(se);
- se->vruntime += cfs_rq->min_vruntime;
#ifdef CONFIG_SMP
- /* Virtually synchronize task with its new cfs_rq */
- p->se.avg.last_update_time = cfs_rq->avg.last_update_time;
- cfs_rq->avg.load_avg += p->se.avg.load_avg;
- cfs_rq->avg.load_sum += p->se.avg.load_sum;
- cfs_rq->avg.util_avg += p->se.avg.util_avg;
- cfs_rq->avg.util_sum += p->se.avg.util_sum;
+ /* Tell se's cfs_rq has been changed -- migrated */
+ p->se.avg.last_update_time = 0;
#endif
- }
+ attach_task_cfs_rq(p);
}
void free_fair_sched_group(struct task_group *tg)
diff --git a/kernel/sched/features.h b/kernel/sched/features.h
index 83a50e7ca533..69631fa46c2f 100644
--- a/kernel/sched/features.h
+++ b/kernel/sched/features.h
@@ -36,11 +36,6 @@ SCHED_FEAT(CACHE_HOT_BUDDY, true)
*/
SCHED_FEAT(WAKEUP_PREEMPTION, true)
-/*
- * Use arch dependent cpu capacity functions
- */
-SCHED_FEAT(ARCH_CAPACITY, true)
-
SCHED_FEAT(HRTICK, false)
SCHED_FEAT(DOUBLE_TICK, false)
SCHED_FEAT(LB_BIAS, true)
@@ -72,19 +67,5 @@ SCHED_FEAT(RT_PUSH_IPI, true)
SCHED_FEAT(FORCE_SD_OVERLAP, false)
SCHED_FEAT(RT_RUNTIME_SHARE, true)
SCHED_FEAT(LB_MIN, false)
+SCHED_FEAT(ATTACH_AGE_LOAD, true)
-/*
- * Apply the automatic NUMA scheduling policy. Enabled automatically
- * at runtime if running on a NUMA machine. Can be controlled via
- * numa_balancing=
- */
-#ifdef CONFIG_NUMA_BALANCING
-
-/*
- * NUMA will favor moving tasks towards nodes where a higher number of
- * hinting faults are recorded during active load balancing. It will
- * resist moving tasks towards nodes where a lower number of hinting
- * faults have been recorded.
- */
-SCHED_FEAT(NUMA, true)
-#endif
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index d2ea59364a1c..e3cc16312046 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -635,11 +635,11 @@ bool sched_rt_bandwidth_account(struct rt_rq *rt_rq)
/*
* We ran out of runtime, see if we can borrow some from our neighbours.
*/
-static int do_balance_runtime(struct rt_rq *rt_rq)
+static void do_balance_runtime(struct rt_rq *rt_rq)
{
struct rt_bandwidth *rt_b = sched_rt_bandwidth(rt_rq);
struct root_domain *rd = rq_of_rt_rq(rt_rq)->rd;
- int i, weight, more = 0;
+ int i, weight;
u64 rt_period;
weight = cpumask_weight(rd->span);
@@ -673,7 +673,6 @@ static int do_balance_runtime(struct rt_rq *rt_rq)
diff = rt_period - rt_rq->rt_runtime;
iter->rt_runtime -= diff;
rt_rq->rt_runtime += diff;
- more = 1;
if (rt_rq->rt_runtime == rt_period) {
raw_spin_unlock(&iter->rt_runtime_lock);
break;
@@ -683,8 +682,6 @@ static int do_balance_runtime(struct rt_rq *rt_rq)
raw_spin_unlock(&iter->rt_runtime_lock);
}
raw_spin_unlock(&rt_b->rt_runtime_lock);
-
- return more;
}
/*
@@ -796,26 +793,19 @@ static void __enable_runtime(struct rq *rq)
}
}
-static int balance_runtime(struct rt_rq *rt_rq)
+static void balance_runtime(struct rt_rq *rt_rq)
{
- int more = 0;
-
if (!sched_feat(RT_RUNTIME_SHARE))
- return more;
+ return;
if (rt_rq->rt_time > rt_rq->rt_runtime) {
raw_spin_unlock(&rt_rq->rt_runtime_lock);
- more = do_balance_runtime(rt_rq);
+ do_balance_runtime(rt_rq);
raw_spin_lock(&rt_rq->rt_runtime_lock);
}
-
- return more;
}
#else /* !CONFIG_SMP */
-static inline int balance_runtime(struct rt_rq *rt_rq)
-{
- return 0;
-}
+static inline void balance_runtime(struct rt_rq *rt_rq) {}
#endif /* CONFIG_SMP */
static int do_sched_rt_period_timer(struct rt_bandwidth *rt_b, int overrun)
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 6d2a119c7ad9..efd3bfc7e347 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -84,6 +84,10 @@ static inline void update_cpu_load_active(struct rq *this_rq) { }
*/
#define RUNTIME_INF ((u64)~0ULL)
+static inline int idle_policy(int policy)
+{
+ return policy == SCHED_IDLE;
+}
static inline int fair_policy(int policy)
{
return policy == SCHED_NORMAL || policy == SCHED_BATCH;
@@ -98,6 +102,11 @@ static inline int dl_policy(int policy)
{
return policy == SCHED_DEADLINE;
}
+static inline bool valid_policy(int policy)
+{
+ return idle_policy(policy) || fair_policy(policy) ||
+ rt_policy(policy) || dl_policy(policy);
+}
static inline int task_has_rt_policy(struct task_struct *p)
{
@@ -109,11 +118,6 @@ static inline int task_has_dl_policy(struct task_struct *p)
return dl_policy(p->policy);
}
-static inline bool dl_time_before(u64 a, u64 b)
-{
- return (s64)(a - b) < 0;
-}
-
/*
* Tells if entity @a should preempt entity @b.
*/
@@ -1003,17 +1007,7 @@ extern struct static_key sched_feat_keys[__SCHED_FEAT_NR];
#define sched_feat(x) (sysctl_sched_features & (1UL << __SCHED_FEAT_##x))
#endif /* SCHED_DEBUG && HAVE_JUMP_LABEL */
-#ifdef CONFIG_NUMA_BALANCING
-#define sched_feat_numa(x) sched_feat(x)
-#ifdef CONFIG_SCHED_DEBUG
-#define numabalancing_enabled sched_feat_numa(NUMA)
-#else
-extern bool numabalancing_enabled;
-#endif /* CONFIG_SCHED_DEBUG */
-#else
-#define sched_feat_numa(x) (0)
-#define numabalancing_enabled (0)
-#endif /* CONFIG_NUMA_BALANCING */
+extern struct static_key_false sched_numa_balancing;
static inline u64 global_rt_period(void)
{
@@ -1157,16 +1151,18 @@ static const u32 prio_to_wmult[40] = {
/* 15 */ 119304647, 148102320, 186737708, 238609294, 286331153,
};
-#define ENQUEUE_WAKEUP 1
-#define ENQUEUE_HEAD 2
+#define ENQUEUE_WAKEUP 0x01
+#define ENQUEUE_HEAD 0x02
#ifdef CONFIG_SMP
-#define ENQUEUE_WAKING 4 /* sched_class::task_waking was called */
+#define ENQUEUE_WAKING 0x04 /* sched_class::task_waking was called */
#else
-#define ENQUEUE_WAKING 0
+#define ENQUEUE_WAKING 0x00
#endif
-#define ENQUEUE_REPLENISH 8
+#define ENQUEUE_REPLENISH 0x08
+#define ENQUEUE_RESTORE 0x10
-#define DEQUEUE_SLEEP 1
+#define DEQUEUE_SLEEP 0x01
+#define DEQUEUE_SAVE 0x02
#define RETRY_TASK ((void *)-1UL)
@@ -1194,7 +1190,7 @@ struct sched_class {
#ifdef CONFIG_SMP
int (*select_task_rq)(struct task_struct *p, int task_cpu, int sd_flag, int flags);
- void (*migrate_task_rq)(struct task_struct *p, int next_cpu);
+ void (*migrate_task_rq)(struct task_struct *p);
void (*task_waking) (struct task_struct *task);
void (*task_woken) (struct rq *this_rq, struct task_struct *task);
@@ -1227,7 +1223,7 @@ struct sched_class {
void (*update_curr) (struct rq *rq);
#ifdef CONFIG_FAIR_GROUP_SCHED
- void (*task_move_group) (struct task_struct *p, int on_rq);
+ void (*task_move_group) (struct task_struct *p);
#endif
};
@@ -1405,6 +1401,17 @@ unsigned long arch_scale_freq_capacity(struct sched_domain *sd, int cpu)
}
#endif
+#ifndef arch_scale_cpu_capacity
+static __always_inline
+unsigned long arch_scale_cpu_capacity(struct sched_domain *sd, int cpu)
+{
+ if (sd && (sd->flags & SD_SHARE_CPUCAPACITY) && (sd->span_weight > 1))
+ return sd->smt_gain / sd->span_weight;
+
+ return SCHED_CAPACITY_SCALE;
+}
+#endif
+
static inline void sched_rt_avg_update(struct rq *rq, u64 rt_delta)
{
rq->rt_avg += rt_delta * arch_scale_freq_capacity(NULL, cpu_of(rq));
diff --git a/kernel/smpboot.c b/kernel/smpboot.c
index a818cbc73e14..d264f59bff56 100644
--- a/kernel/smpboot.c
+++ b/kernel/smpboot.c
@@ -222,9 +222,8 @@ static void smpboot_unpark_thread(struct smp_hotplug_thread *ht, unsigned int cp
{
struct task_struct *tsk = *per_cpu_ptr(ht->store, cpu);
- if (ht->pre_unpark)
- ht->pre_unpark(cpu);
- kthread_unpark(tsk);
+ if (!ht->selfparking)
+ kthread_unpark(tsk);
}
void smpboot_unpark_threads(unsigned int cpu)
diff --git a/kernel/stop_machine.c b/kernel/stop_machine.c
index 12484e5d5c88..867bc20e1ef1 100644
--- a/kernel/stop_machine.c
+++ b/kernel/stop_machine.c
@@ -73,21 +73,24 @@ static void cpu_stop_signal_done(struct cpu_stop_done *done, bool executed)
}
}
+static void __cpu_stop_queue_work(struct cpu_stopper *stopper,
+ struct cpu_stop_work *work)
+{
+ list_add_tail(&work->list, &stopper->works);
+ wake_up_process(stopper->thread);
+}
+
/* queue @work to @stopper. if offline, @work is completed immediately */
static void cpu_stop_queue_work(unsigned int cpu, struct cpu_stop_work *work)
{
struct cpu_stopper *stopper = &per_cpu(cpu_stopper, cpu);
-
unsigned long flags;
spin_lock_irqsave(&stopper->lock, flags);
-
- if (stopper->enabled) {
- list_add_tail(&work->list, &stopper->works);
- wake_up_process(stopper->thread);
- } else
+ if (stopper->enabled)
+ __cpu_stop_queue_work(stopper, work);
+ else
cpu_stop_signal_done(work->done, false);
-
spin_unlock_irqrestore(&stopper->lock, flags);
}
@@ -213,6 +216,31 @@ static int multi_cpu_stop(void *data)
return err;
}
+static int cpu_stop_queue_two_works(int cpu1, struct cpu_stop_work *work1,
+ int cpu2, struct cpu_stop_work *work2)
+{
+ struct cpu_stopper *stopper1 = per_cpu_ptr(&cpu_stopper, cpu1);
+ struct cpu_stopper *stopper2 = per_cpu_ptr(&cpu_stopper, cpu2);
+ int err;
+
+ lg_double_lock(&stop_cpus_lock, cpu1, cpu2);
+ spin_lock_irq(&stopper1->lock);
+ spin_lock_nested(&stopper2->lock, SINGLE_DEPTH_NESTING);
+
+ err = -ENOENT;
+ if (!stopper1->enabled || !stopper2->enabled)
+ goto unlock;
+
+ err = 0;
+ __cpu_stop_queue_work(stopper1, work1);
+ __cpu_stop_queue_work(stopper2, work2);
+unlock:
+ spin_unlock(&stopper2->lock);
+ spin_unlock_irq(&stopper1->lock);
+ lg_double_unlock(&stop_cpus_lock, cpu1, cpu2);
+
+ return err;
+}
/**
* stop_two_cpus - stops two cpus
* @cpu1: the cpu to stop
@@ -247,24 +275,13 @@ int stop_two_cpus(unsigned int cpu1, unsigned int cpu2, cpu_stop_fn_t fn, void *
cpu_stop_init_done(&done, 2);
set_state(&msdata, MULTI_STOP_PREPARE);
- /*
- * If we observe both CPUs active we know _cpu_down() cannot yet have
- * queued its stop_machine works and therefore ours will get executed
- * first. Or its not either one of our CPUs that's getting unplugged,
- * in which case we don't care.
- *
- * This relies on the stopper workqueues to be FIFO.
- */
- if (!cpu_active(cpu1) || !cpu_active(cpu2)) {
+ if (cpu1 > cpu2)
+ swap(cpu1, cpu2);
+ if (cpu_stop_queue_two_works(cpu1, &work1, cpu2, &work2)) {
preempt_enable();
return -ENOENT;
}
- lg_double_lock(&stop_cpus_lock, cpu1, cpu2);
- cpu_stop_queue_work(cpu1, &work1);
- cpu_stop_queue_work(cpu2, &work2);
- lg_double_unlock(&stop_cpus_lock, cpu1, cpu2);
-
preempt_enable();
wait_for_completion(&done.completion);
@@ -452,6 +469,18 @@ static void cpu_stopper_thread(unsigned int cpu)
}
}
+void stop_machine_park(int cpu)
+{
+ struct cpu_stopper *stopper = &per_cpu(cpu_stopper, cpu);
+ /*
+ * Lockless. cpu_stopper_thread() will take stopper->lock and flush
+ * the pending works before it parks, until then it is fine to queue
+ * the new works.
+ */
+ stopper->enabled = false;
+ kthread_park(stopper->thread);
+}
+
extern void sched_set_stop_task(int cpu, struct task_struct *stop);
static void cpu_stop_create(unsigned int cpu)
@@ -462,26 +491,16 @@ static void cpu_stop_create(unsigned int cpu)
static void cpu_stop_park(unsigned int cpu)
{
struct cpu_stopper *stopper = &per_cpu(cpu_stopper, cpu);
- struct cpu_stop_work *work, *tmp;
- unsigned long flags;
- /* drain remaining works */
- spin_lock_irqsave(&stopper->lock, flags);
- list_for_each_entry_safe(work, tmp, &stopper->works, list) {
- list_del_init(&work->list);
- cpu_stop_signal_done(work->done, false);
- }
- stopper->enabled = false;
- spin_unlock_irqrestore(&stopper->lock, flags);
+ WARN_ON(!list_empty(&stopper->works));
}
-static void cpu_stop_unpark(unsigned int cpu)
+void stop_machine_unpark(int cpu)
{
struct cpu_stopper *stopper = &per_cpu(cpu_stopper, cpu);
- spin_lock_irq(&stopper->lock);
stopper->enabled = true;
- spin_unlock_irq(&stopper->lock);
+ kthread_unpark(stopper->thread);
}
static struct smp_hotplug_thread cpu_stop_threads = {
@@ -490,9 +509,7 @@ static struct smp_hotplug_thread cpu_stop_threads = {
.thread_fn = cpu_stopper_thread,
.thread_comm = "migration/%u",
.create = cpu_stop_create,
- .setup = cpu_stop_unpark,
.park = cpu_stop_park,
- .pre_unpark = cpu_stop_unpark,
.selfparking = true,
};
@@ -508,6 +525,7 @@ static int __init cpu_stop_init(void)
}
BUG_ON(smpboot_register_percpu_thread(&cpu_stop_threads));
+ stop_machine_unpark(raw_smp_processor_id());
stop_machine_initialized = true;
return 0;
}
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index b0623ac785a2..00611e95a8ee 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -5697,7 +5697,7 @@ static int alloc_retstack_tasklist(struct ftrace_ret_stack **ret_stack_list)
}
static void
-ftrace_graph_probe_sched_switch(void *ignore,
+ftrace_graph_probe_sched_switch(void *ignore, bool preempt,
struct task_struct *prev, struct task_struct *next)
{
unsigned long long timestamp;
diff --git a/kernel/trace/trace_sched_switch.c b/kernel/trace/trace_sched_switch.c
index f270088e9929..4c896a0101bd 100644
--- a/kernel/trace/trace_sched_switch.c
+++ b/kernel/trace/trace_sched_switch.c
@@ -16,7 +16,8 @@ static int sched_ref;
static DEFINE_MUTEX(sched_register_mutex);
static void
-probe_sched_switch(void *ignore, struct task_struct *prev, struct task_struct *next)
+probe_sched_switch(void *ignore, bool preempt,
+ struct task_struct *prev, struct task_struct *next)
{
if (unlikely(!sched_ref))
return;
diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c
index 12cbe77b4136..4bcfbac289ff 100644
--- a/kernel/trace/trace_sched_wakeup.c
+++ b/kernel/trace/trace_sched_wakeup.c
@@ -420,7 +420,7 @@ tracing_sched_wakeup_trace(struct trace_array *tr,
}
static void notrace
-probe_wakeup_sched_switch(void *ignore,
+probe_wakeup_sched_switch(void *ignore, bool preempt,
struct task_struct *prev, struct task_struct *next)
{
struct trace_array_cpu *data;
^ permalink raw reply related [flat|nested] only message in thread
only message in thread, other threads:[~2015-11-03 10:26 UTC | newest]
Thread overview: (only message) (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2015-11-03 10:26 [GIT PULL] scheduler changes for v4.4 Ingo Molnar
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.