summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2025-12-01 21:04:45 -0800
committerLinus Torvalds <torvalds@linux-foundation.org>2025-12-01 21:04:45 -0800
commit6d2c10e889db596938bb7b4d3cdd42d67208439a (patch)
treec8adec6da2f3c89e60bf30397c7ebff7ee85e288
parent6c26fbe8c9d3e932dce6afe2505b19b4b261cae9 (diff)
parentc04507ac500e2cc8048000c2a849588227554e06 (diff)
Merge tag 'sched-core-2025-12-01' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull scheduler updates from Ingo Molnar: "Scalability and load-balancing improvements: - Enable scheduler feature NEXT_BUDDY (Mel Gorman) - Reimplement NEXT_BUDDY to align with EEVDF goals (Mel Gorman) - Skip sched_balance_running cmpxchg when balance is not due (Tim Chen) - Implement generic code for architecture specific sched domain NUMA distances (Tim Chen) - Optimize the NUMA distances of the sched-domains builds of Intel Granite Rapids (GNR) and Clearwater Forest (CWF) platforms (Tim Chen) - Implement proportional newidle balance: a randomized algorithm that runs newidle balancing proportional to its success rate. (Peter Zijlstra) Scheduler infrastructure changes: - Implement the 'sched_change' scoped_guard() pattern for the entire scheduler (Peter Zijlstra) - More broadly utilize the sched_change guard (Peter Zijlstra) - Add support to pick functions to take runqueue-flags (Joel Fernandes) - Provide and use set_need_resched_current() (Peter Zijlstra) Fair scheduling enhancements: - Forfeit vruntime on yield (Fernand Sieber) - Only update stats for allowed CPUs when looking for dst group (Adam Li) CPU-core scheduling enhancements: - Optimize core cookie matching check (Fernand Sieber) Deadline scheduler fixes: - Only set free_cpus for online runqueues (Doug Berger) - Fix dl_server time accounting (Peter Zijlstra) - Fix dl_server stop condition (Peter Zijlstra) Proxy scheduling fixes: - Yield the donor task (Fernand Sieber) Fixes and cleanups: - Fix do_set_cpus_allowed() locking (Peter Zijlstra) - Fix migrate_disable_switch() locking (Peter Zijlstra) - Remove double update_rq_clock() in __set_cpus_allowed_ptr_locked() (Hao Jia) - Increase sched_tick_remote timeout (Phil Auld) - sched/deadline: Use cpumask_weight_and() in dl_bw_cpus() (Shrikanth Hegde) - sched/deadline: Clean up select_task_rq_dl() (Shrikanth Hegde)" * tag 'sched-core-2025-12-01' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (44 commits) sched: Provide and use set_need_resched_current() sched/fair: Proportional newidle balance sched/fair: Small cleanup to update_newidle_cost() sched/fair: Small cleanup to sched_balance_newidle() sched/fair: Revert max_newidle_lb_cost bump sched/fair: Reimplement NEXT_BUDDY to align with EEVDF goals sched/fair: Enable scheduler feature NEXT_BUDDY sched: Increase sched_tick_remote timeout sched/fair: Have SD_SERIALIZE affect newidle balancing sched/fair: Skip sched_balance_running cmpxchg when balance is not due sched/deadline: Minor cleanup in select_task_rq_dl() sched/deadline: Use cpumask_weight_and() in dl_bw_cpus sched/deadline: Document dl_server sched/deadline: Fix dl_server stop condition sched/deadline: Fix dl_server time accounting sched/core: Remove double update_rq_clock() in __set_cpus_allowed_ptr_locked() sched/eevdf: Fix min_vruntime vs avg_vruntime sched/core: Add comment explaining force-idle vruntime snapshots sched/core: Optimize core cookie matching check sched/proxy: Yield the donor task ...
Diffstat
-rw-r--r--arch/s390/mm/pfault.c3
-rw-r--r--arch/x86/include/asm/topology.h2
-rw-r--r--arch/x86/kernel/smpboot.c70
-rw-r--r--include/linux/cleanup.h5
-rw-r--r--include/linux/sched.h33
-rw-r--r--include/linux/sched/topology.h3
-rw-r--r--kernel/cgroup/cpuset.c2
-rw-r--r--kernel/kthread.c15
-rw-r--r--kernel/rcu/tiny.c8
-rw-r--r--kernel/rcu/tree.c14
-rw-r--r--kernel/rcu/tree_exp.h3
-rw-r--r--kernel/rcu/tree_plugin.h9
-rw-r--r--kernel/rcu/tree_stall.h3
-rw-r--r--kernel/sched/core.c400
-rw-r--r--kernel/sched/cpudeadline.c34
-rw-r--r--kernel/sched/cpudeadline.h4
-rw-r--r--kernel/sched/deadline.c336
-rw-r--r--kernel/sched/debug.c8
-rw-r--r--kernel/sched/ext.c132
-rw-r--r--kernel/sched/fair.c600
-rw-r--r--kernel/sched/features.h7
-rw-r--r--kernel/sched/idle.c29
-rw-r--r--kernel/sched/rt.c13
-rw-r--r--kernel/sched/sched.h271
-rw-r--r--kernel/sched/stats.h2
-rw-r--r--kernel/sched/stop_task.c13
-rw-r--r--kernel/sched/syscalls.c87
-rw-r--r--kernel/sched/topology.c114
28 files changed, 1417 insertions, 803 deletions
diff --git a/arch/s390/mm/pfault.c b/arch/s390/mm/pfault.c
index e6175d75e4b0..2f829448c719 100644
--- a/arch/s390/mm/pfault.c
+++ b/arch/s390/mm/pfault.c
@@ -199,8 +199,7 @@ block:
* return to userspace schedule() to block.
*/
__set_current_state(TASK_UNINTERRUPTIBLE);
- set_tsk_need_resched(tsk);
- set_preempt_need_resched();
+ set_need_resched_current();
}
}
out:
diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h
index 21041898157a..df943881f15b 100644
--- a/arch/x86/include/asm/topology.h
+++ b/arch/x86/include/asm/topology.h
@@ -325,4 +325,6 @@ static inline void freq_invariance_set_perf_ratio(u64 ratio, bool turbo_disabled
extern void arch_scale_freq_tick(void);
#define arch_scale_freq_tick arch_scale_freq_tick
+extern int arch_sched_node_distance(int from, int to);
+
#endif /* _ASM_X86_TOPOLOGY_H */
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index a4ba735842a8..c2107047dc14 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -515,6 +515,76 @@ static void __init build_sched_topology(void)
set_sched_topology(topology);
}
+#ifdef CONFIG_NUMA
+static int sched_avg_remote_distance;
+static int avg_remote_numa_distance(void)
+{
+ int i, j;
+ int distance, nr_remote, total_distance;
+
+ if (sched_avg_remote_distance > 0)
+ return sched_avg_remote_distance;
+
+ nr_remote = 0;
+ total_distance = 0;
+ for_each_node_state(i, N_CPU) {
+ for_each_node_state(j, N_CPU) {
+ distance = node_distance(i, j);
+
+ if (distance >= REMOTE_DISTANCE) {
+ nr_remote++;
+ total_distance += distance;
+ }
+ }
+ }
+ if (nr_remote)
+ sched_avg_remote_distance = total_distance / nr_remote;
+ else
+ sched_avg_remote_distance = REMOTE_DISTANCE;
+
+ return sched_avg_remote_distance;
+}
+
+int arch_sched_node_distance(int from, int to)
+{
+ int d = node_distance(from, to);
+
+ switch (boot_cpu_data.x86_vfm) {
+ case INTEL_GRANITERAPIDS_X:
+ case INTEL_ATOM_DARKMONT_X:
+
+ if (!x86_has_numa_in_package || topology_max_packages() == 1 ||
+ d < REMOTE_DISTANCE)
+ return d;
+
+ /*
+ * With SNC enabled, there could be too many levels of remote
+ * NUMA node distances, creating NUMA domain levels
+ * including local nodes and partial remote nodes.
+ *
+ * Trim finer distance tuning for NUMA nodes in remote package
+ * for the purpose of building sched domains. Group NUMA nodes
+ * in the remote package in the same sched group.
+ * Simplify NUMA domains and avoid extra NUMA levels including
+ * different remote NUMA nodes and local nodes.
+ *
+ * GNR and CWF don't expect systems with more than 2 packages
+ * and more than 2 hops between packages. Single average remote
+ * distance won't be appropriate if there are more than 2
+ * packages as average distance to different remote packages
+ * could be different.
+ */
+ WARN_ONCE(topology_max_packages() > 2,
+ "sched: Expect only up to 2 packages for GNR or CWF, "
+ "but saw %d packages when building sched domains.",
+ topology_max_packages());
+
+ d = avg_remote_numa_distance();
+ }
+ return d;
+}
+#endif /* CONFIG_NUMA */
+
void set_cpu_sibling_map(int cpu)
{
bool has_smt = __max_threads_per_core > 1;
diff --git a/include/linux/cleanup.h b/include/linux/cleanup.h
index b8bd2f15f91f..bacefa0f1512 100644
--- a/include/linux/cleanup.h
+++ b/include/linux/cleanup.h
@@ -348,6 +348,11 @@ _label: \
#define __DEFINE_CLASS_IS_CONDITIONAL(_name, _is_cond) \
static __maybe_unused const bool class_##_name##_is_conditional = _is_cond
+#define DEFINE_CLASS_IS_UNCONDITIONAL(_name) \
+ __DEFINE_CLASS_IS_CONDITIONAL(_name, false); \
+ static inline void * class_##_name##_lock_ptr(class_##_name##_t *_T) \
+ { return (void *)1; }
+
#define __GUARD_IS_ERR(_ptr) \
({ \
unsigned long _rc = (__force unsigned long)(_ptr); \
diff --git a/include/linux/sched.h b/include/linux/sched.h
index b469878de25c..e84bc5bce816 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -637,8 +637,8 @@ struct sched_rt_entity {
#endif
} __randomize_layout;
-typedef bool (*dl_server_has_tasks_f)(struct sched_dl_entity *);
-typedef struct task_struct *(*dl_server_pick_f)(struct sched_dl_entity *);
+struct rq_flags;
+typedef struct task_struct *(*dl_server_pick_f)(struct sched_dl_entity *, struct rq_flags *rf);
struct sched_dl_entity {
struct rb_node rb_node;
@@ -685,20 +685,22 @@ struct sched_dl_entity {
*
* @dl_server tells if this is a server entity.
*
- * @dl_defer tells if this is a deferred or regular server. For
- * now only defer server exists.
- *
- * @dl_defer_armed tells if the deferrable server is waiting
- * for the replenishment timer to activate it.
- *
* @dl_server_active tells if the dlserver is active(started).
* dlserver is started on first cfs enqueue on an idle runqueue
* and is stopped when a dequeue results in 0 cfs tasks on the
* runqueue. In other words, dlserver is active only when cpu's
* runqueue has atleast one cfs task.
*
+ * @dl_defer tells if this is a deferred or regular server. For
+ * now only defer server exists.
+ *
+ * @dl_defer_armed tells if the deferrable server is waiting
+ * for the replenishment timer to activate it.
+ *
* @dl_defer_running tells if the deferrable server is actually
* running, skipping the defer phase.
+ *
+ * @dl_defer_idle tracks idle state
*/
unsigned int dl_throttled : 1;
unsigned int dl_yielded : 1;
@@ -709,6 +711,7 @@ struct sched_dl_entity {
unsigned int dl_defer : 1;
unsigned int dl_defer_armed : 1;
unsigned int dl_defer_running : 1;
+ unsigned int dl_defer_idle : 1;
/*
* Bandwidth enforcement timer. Each -deadline task has its
@@ -730,9 +733,6 @@ struct sched_dl_entity {
* dl_server_update().
*
* @rq the runqueue this server is for
- *
- * @server_has_tasks() returns true if @server_pick return a
- * runnable task.
*/
struct rq *rq;
dl_server_pick_f server_pick_task;
@@ -1861,8 +1861,8 @@ extern int task_can_attach(struct task_struct *p);
extern int dl_bw_alloc(int cpu, u64 dl_bw);
extern void dl_bw_free(int cpu, u64 dl_bw);
-/* do_set_cpus_allowed() - consider using set_cpus_allowed_ptr() instead */
-extern void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask);
+/* set_cpus_allowed_force() - consider using set_cpus_allowed_ptr() instead */
+extern void set_cpus_allowed_force(struct task_struct *p, const struct cpumask *new_mask);
/**
* set_cpus_allowed_ptr - set CPU affinity mask of a task
@@ -2058,6 +2058,13 @@ static inline int test_tsk_need_resched(struct task_struct *tsk)
return unlikely(test_tsk_thread_flag(tsk,TIF_NEED_RESCHED));
}
+static inline void set_need_resched_current(void)
+{
+ lockdep_assert_irqs_disabled();
+ set_tsk_need_resched(current);
+ set_preempt_need_resched();
+}
+
/*
* cond_resched() and cond_resched_lock(): latency reduction via
* explicit rescheduling in places that are safe. The return
diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h
index bbcfdf12aa6e..45c0022b91ce 100644
--- a/include/linux/sched/topology.h
+++ b/include/linux/sched/topology.h
@@ -92,6 +92,9 @@ struct sched_domain {
unsigned int nr_balance_failed; /* initialise to 0 */
/* idle_balance() stats */
+ unsigned int newidle_call;
+ unsigned int newidle_success;
+ unsigned int newidle_ratio;
u64 max_newidle_lb_cost;
unsigned long last_decay_max_lb_cost;
diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index 52468d2c178a..185e820cd1df 100644
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -4180,7 +4180,7 @@ bool cpuset_cpus_allowed_fallback(struct task_struct *tsk)
rcu_read_lock();
cs_mask = task_cs(tsk)->cpus_allowed;
if (is_in_v2_mode() && cpumask_subset(cs_mask, possible_mask)) {
- do_set_cpus_allowed(tsk, cs_mask);
+ set_cpus_allowed_force(tsk, cs_mask);
changed = true;
}
rcu_read_unlock();
diff --git a/kernel/kthread.c b/kernel/kthread.c
index 31b072e8d427..99a3808d086f 100644
--- a/kernel/kthread.c
+++ b/kernel/kthread.c
@@ -593,18 +593,16 @@ EXPORT_SYMBOL(kthread_create_on_node);
static void __kthread_bind_mask(struct task_struct *p, const struct cpumask *mask, unsigned int state)
{
- unsigned long flags;
-
if (!wait_task_inactive(p, state)) {
WARN_ON(1);
return;
}
+ scoped_guard (raw_spinlock_irqsave, &p->pi_lock)
+ set_cpus_allowed_force(p, mask);
+
/* It's safe because the task is inactive. */
- raw_spin_lock_irqsave(&p->pi_lock, flags);
- do_set_cpus_allowed(p, mask);
p->flags |= PF_NO_SETAFFINITY;
- raw_spin_unlock_irqrestore(&p->pi_lock, flags);
}
static void __kthread_bind(struct task_struct *p, unsigned int cpu, unsigned int state)
@@ -857,7 +855,6 @@ int kthread_affine_preferred(struct task_struct *p, const struct cpumask *mask)
{
struct kthread *kthread = to_kthread(p);
cpumask_var_t affinity;
- unsigned long flags;
int ret = 0;
if (!wait_task_inactive(p, TASK_UNINTERRUPTIBLE) || kthread->started) {
@@ -882,10 +879,8 @@ int kthread_affine_preferred(struct task_struct *p, const struct cpumask *mask)
list_add_tail(&kthread->hotplug_node, &kthreads_hotplug);
kthread_fetch_affinity(kthread, affinity);
- /* It's safe because the task is inactive. */
- raw_spin_lock_irqsave(&p->pi_lock, flags);
- do_set_cpus_allowed(p, affinity);
- raw_spin_unlock_irqrestore(&p->pi_lock, flags);
+ scoped_guard (raw_spinlock_irqsave, &p->pi_lock)
+ set_cpus_allowed_force(p, affinity);
mutex_unlock(&kthreads_hotplug_lock);
out:
diff --git a/kernel/rcu/tiny.c b/kernel/rcu/tiny.c
index c1ebfd51768b..585cade21010 100644
--- a/kernel/rcu/tiny.c
+++ b/kernel/rcu/tiny.c
@@ -70,12 +70,10 @@ void rcu_qs(void)
*/
void rcu_sched_clock_irq(int user)
{
- if (user) {
+ if (user)
rcu_qs();
- } else if (rcu_ctrlblk.donetail != rcu_ctrlblk.curtail) {
- set_tsk_need_resched(current);
- set_preempt_need_resched();
- }
+ else if (rcu_ctrlblk.donetail != rcu_ctrlblk.curtail)
+ set_need_resched_current();
}
/*
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 8293bae1dec1..85b82a7007b9 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -2696,10 +2696,8 @@ void rcu_sched_clock_irq(int user)
/* The load-acquire pairs with the store-release setting to true. */
if (smp_load_acquire(this_cpu_ptr(&rcu_data.rcu_urgent_qs))) {
/* Idle and userspace execution already are quiescent states. */
- if (!rcu_is_cpu_rrupt_from_idle() && !user) {
- set_tsk_need_resched(current);
- set_preempt_need_resched();
- }
+ if (!rcu_is_cpu_rrupt_from_idle() && !user)
+ set_need_resched_current();
__this_cpu_write(rcu_data.rcu_urgent_qs, false);
}
rcu_flavor_sched_clock_irq(user);
@@ -2824,7 +2822,6 @@ static void strict_work_handler(struct work_struct *work)
/* Perform RCU core processing work for the current CPU. */
static __latent_entropy void rcu_core(void)
{
- unsigned long flags;
struct rcu_data *rdp = raw_cpu_ptr(&rcu_data);
struct rcu_node *rnp = rdp->mynode;
@@ -2837,8 +2834,8 @@ static __latent_entropy void rcu_core(void)
if (IS_ENABLED(CONFIG_PREEMPT_COUNT) && (!(preempt_count() & PREEMPT_MASK))) {
rcu_preempt_deferred_qs(current);
} else if (rcu_preempt_need_deferred_qs(current)) {
- set_tsk_need_resched(current);
- set_preempt_need_resched();
+ guard(irqsave)();
+ set_need_resched_current();
}
/* Update RCU state based on any recent quiescent states. */
@@ -2847,10 +2844,9 @@ static __latent_entropy void rcu_core(void)
/* No grace period and unregistered callbacks? */
if (!rcu_gp_in_progress() &&
rcu_segcblist_is_enabled(&rdp->cblist) && !rcu_rdp_is_offloaded(rdp)) {
- local_irq_save(flags);
+ guard(irqsave)();
if (!rcu_segcblist_restempty(&rdp->cblist, RCU_NEXT_READY_TAIL))
rcu_accelerate_cbs_unlocked(rnp, rdp);
- local_irq_restore(flags);
}
rcu_check_gp_start_stall(rnp, rdp, rcu_jiffies_till_stall_check());
diff --git a/kernel/rcu/tree_exp.h b/kernel/rcu/tree_exp.h
index 6058a734090c..96c49c56fc14 100644
--- a/kernel/rcu/tree_exp.h
+++ b/kernel/rcu/tree_exp.h
@@ -729,8 +729,7 @@ static void rcu_exp_need_qs(void)
__this_cpu_write(rcu_data.cpu_no_qs.b.exp, true);
/* Store .exp before .rcu_urgent_qs. */
smp_store_release(this_cpu_ptr(&rcu_data.rcu_urgent_qs), true);
- set_tsk_need_resched(current);
- set_preempt_need_resched();
+ set_need_resched_current();
}
#ifdef CONFIG_PREEMPT_RCU
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index d85763336b3c..dbe2d02be824 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -753,8 +753,7 @@ static void rcu_read_unlock_special(struct task_struct *t)
// Also if no expediting and no possible deboosting,
// slow is OK. Plus nohz_full CPUs eventually get
// tick enabled.
- set_tsk_need_resched(current);
- set_preempt_need_resched();
+ set_need_resched_current();
if (IS_ENABLED(CONFIG_IRQ_WORK) && irqs_were_disabled &&
needs_exp && rdp->defer_qs_iw_pending != DEFER_QS_PENDING &&
cpu_online(rdp->cpu)) {
@@ -813,10 +812,8 @@ static void rcu_flavor_sched_clock_irq(int user)
if (rcu_preempt_depth() > 0 ||
(preempt_count() & (PREEMPT_MASK | SOFTIRQ_MASK))) {
/* No QS, force context switch if deferred. */
- if (rcu_preempt_need_deferred_qs(t)) {
- set_tsk_need_resched(t);
- set_preempt_need_resched();
- }
+ if (rcu_preempt_need_deferred_qs(t))
+ set_need_resched_current();
} else if (rcu_preempt_need_deferred_qs(t)) {
rcu_preempt_deferred_qs(t); /* Report deferred QS. */
return;
diff --git a/kernel/rcu/tree_stall.h b/kernel/rcu/tree_stall.h
index d16afeb11506..b67532cb8770 100644
--- a/kernel/rcu/tree_stall.h
+++ b/kernel/rcu/tree_stall.h
@@ -763,8 +763,7 @@ static void print_cpu_stall(unsigned long gp_seq, unsigned long gps)
* progress and it could be we're stuck in kernel space without context
* switches for an entirely unreasonable amount of time.
*/
- set_tsk_need_resched(current);
- set_preempt_need_resched();
+ set_need_resched_current();
}
static bool csd_lock_suppress_rcu_stall;
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index f754a60de848..0c4ff93eeb78 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -121,6 +121,7 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(sched_update_nr_running_tp);
EXPORT_TRACEPOINT_SYMBOL_GPL(sched_compute_energy_tp);
DEFINE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues);
+DEFINE_PER_CPU(struct rnd_state, sched_rnd_state);
#ifdef CONFIG_SCHED_PROXY_EXEC
DEFINE_STATIC_KEY_TRUE(__sched_proxy_exec);
@@ -583,8 +584,8 @@ EXPORT_SYMBOL(__trace_set_current_state);
*
* p->on_rq <- { 0, 1 = TASK_ON_RQ_QUEUED, 2 = TASK_ON_RQ_MIGRATING }:
*
- * is set by activate_task() and cleared by deactivate_task(), under
- * rq->lock. Non-zero indicates the task is runnable, the special
+ * is set by activate_task() and cleared by deactivate_task()/block_task(),
+ * under rq->lock. Non-zero indicates the task is runnable, the special
* ON_RQ_MIGRATING state is used for migration without holding both
* rq->locks. It indicates task_cpu() is not stable, see task_rq_lock().
*
@@ -2089,6 +2090,7 @@ void enqueue_task(struct rq *rq, struct task_struct *p, int flags)
*/
uclamp_rq_inc(rq, p, flags);
+ rq->queue_mask |= p->sched_class->queue_mask;
p->sched_class->enqueue_task(rq, p, flags);
psi_enqueue(p, flags);
@@ -2121,6 +2123,7 @@ inline bool dequeue_task(struct rq *rq, struct task_struct *p, int flags)
* and mark the task ->sched_delayed.
*/
uclamp_rq_dec(rq, p);
+ rq->queue_mask |= p->sched_class->queue_mask;
return p->sched_class->dequeue_task(rq, p, flags);
}
@@ -2169,37 +2172,6 @@ inline int task_curr(const struct task_struct *p)
return cpu_curr(task_cpu(p)) == p;
}
-/*
- * ->switching_to() is called with the pi_lock and rq_lock held and must not
- * mess with locking.
- */
-void check_class_changing(struct rq *rq, struct task_struct *p,
- const struct sched_class *prev_class)
-{
- if (prev_class != p->sched_class && p->sched_class->switching_to)
- p->sched_class->switching_to(rq, p);
-}
-
-/*
- * switched_from, switched_to and prio_changed must _NOT_ drop rq->lock,
- * use the balance_callback list if you want balancing.
- *
- * this means any call to check_class_changed() must be followed by a call to
- * balance_callback().
- */
-void check_class_changed(struct rq *rq, struct task_struct *p,
- const struct sched_class *prev_class,
- int oldprio)
-{
- if (prev_class != p->sched_class) {
- if (prev_class->switched_from)
- prev_class->switched_from(rq, p);
-
- p->sched_class->switched_to(rq, p);
- } else if (oldprio != p->prio || dl_task(p))
- p->sched_class->prio_changed(rq, p, oldprio);
-}
-
void wakeup_preempt(struct rq *rq, struct task_struct *p, int flags)
{
struct task_struct *donor = rq->donor;
@@ -2362,7 +2334,7 @@ unsigned long wait_task_inactive(struct task_struct *p, unsigned int match_state
}
static void
-__do_set_cpus_allowed(struct task_struct *p, struct affinity_context *ctx);
+do_set_cpus_allowed(struct task_struct *p, struct affinity_context *ctx);
static void migrate_disable_switch(struct rq *rq, struct task_struct *p)
{
@@ -2377,10 +2349,8 @@ static void migrate_disable_switch(struct rq *rq, struct task_struct *p)
if (p->cpus_ptr != &p->cpus_mask)
return;
- /*
- * Violates locking rules! See comment in __do_set_cpus_allowed().
- */
- __do_set_cpus_allowed(p, &ac);
+ scoped_guard (task_rq_lock, p)
+ do_set_cpus_allowed(p, &ac);
}
void ___migrate_enable(void)
@@ -2613,7 +2583,8 @@ static int migration_cpu_stop(void *data)
*/
WARN_ON_ONCE(!pending->stop_pending);
preempt_disable();
- task_rq_unlock(rq, p, &rf);
+ rq_unlock(rq, &rf);
+ raw_spin_unlock_irqrestore(&p->pi_lock, rf.flags);
stop_one_cpu_nowait(task_cpu(p), migration_cpu_stop,
&pending->arg, &pending->stop_work);
preempt_enable();
@@ -2622,7 +2593,8 @@ static int migration_cpu_stop(void *data)
out:
if (pending)
pending->stop_pending = false;
- task_rq_unlock(rq, p, &rf);
+ rq_unlock(rq, &rf);
+ raw_spin_unlock_irqrestore(&p->pi_lock, rf.flags);
if (complete)
complete_all(&pending->done);
@@ -2693,56 +2665,19 @@ void set_cpus_allowed_common(struct task_struct *p, struct affinity_context *ctx
}
static void
-__do_set_cpus_allowed(struct task_struct *p, struct affinity_context *ctx)
+do_set_cpus_allowed(struct task_struct *p, struct affinity_context *ctx)
{
- struct rq *rq = task_rq(p);
- bool queued, running;
-
- /*
- * This here violates the locking rules for affinity, since we're only
- * supposed to change these variables while holding both rq->lock and
- * p->pi_lock.
- *
- * HOWEVER, it magically works, because ttwu() is the only code that
- * accesses these variables under p->pi_lock and only does so after
- * smp_cond_load_acquire(&p->on_cpu, !VAL), and we're in __schedule()
- * before finish_task().
- *
- * XXX do further audits, this smells like something putrid.
- */
- if (ctx->flags & SCA_MIGRATE_DISABLE)
- WARN_ON_ONCE(!p->on_cpu);
- else
- lockdep_assert_held(&p->pi_lock);
-
- queued = task_on_rq_queued(p);
- running = task_current_donor(rq, p);
-
- if (queued) {
- /*
- * Because __kthread_bind() calls this on blocked tasks without
- * holding rq->lock.
- */
- lockdep_assert_rq_held(rq);
- dequeue_task(rq, p, DEQUEUE_SAVE | DEQUEUE_NOCLOCK);
+ scoped_guard (sched_change, p, DEQUEUE_SAVE) {
+ p->sched_class->set_cpus_allowed(p, ctx);
+ mm_set_cpus_allowed(p->mm, ctx->new_mask);
}
- if (running)
- put_prev_task(rq, p);
-
- p->sched_class->set_cpus_allowed(p, ctx);
- mm_set_cpus_allowed(p->mm, ctx->new_mask);
-
- if (queued)
- enqueue_task(rq, p, ENQUEUE_RESTORE | ENQUEUE_NOCLOCK);
- if (running)
- set_next_task(rq, p);
}
/*
* Used for kthread_bind() and select_fallback_rq(), in both cases the user
* affinity (if any) should be destroyed too.
*/
-void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask)
+void set_cpus_allowed_force(struct task_struct *p, const struct cpumask *new_mask)
{
struct affinity_context ac = {
.new_mask = new_mask,
@@ -2754,7 +2689,8 @@ void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask)
struct rcu_head rcu;
};
- __do_set_cpus_allowed(p, &ac);
+ scoped_guard (__task_rq_lock, p)
+ do_set_cpus_allowed(p, &ac);
/*
* Because this is called with p->pi_lock held, it is not possible
@@ -2792,7 +2728,7 @@ int dup_user_cpus_ptr(struct task_struct *dst, struct task_struct *src,
* Use pi_lock to protect content of user_cpus_ptr
*
* Though unlikely, user_cpus_ptr can be reset to NULL by a concurrent
- * do_set_cpus_allowed().
+ * set_cpus_allowed_force().
*/
raw_spin_lock_irqsave(&src->pi_lock, flags);
if (src->user_cpus_ptr) {
@@ -3064,8 +3000,6 @@ static int __set_cpus_allowed_ptr_locked(struct task_struct *p,
unsigned int dest_cpu;
int ret = 0;
- update_rq_clock(rq);
-
if (kthread || is_migration_disabled(p)) {
/*
* Kernel threads are allowed on online && !active CPUs,
@@ -3120,7 +3054,7 @@ static int __set_cpus_allowed_ptr_locked(struct task_struct *p,
goto out;
}
- __do_set_cpus_allowed(p, ctx);
+ do_set_cpus_allowed(p, ctx);
return affine_move_task(rq, p, rf, dest_cpu, ctx->flags);
@@ -3529,13 +3463,7 @@ static int select_fallback_rq(int cpu, struct task_struct *p)
}
fallthrough;
case possible:
- /*
- * XXX When called from select_task_rq() we only
- * hold p->pi_lock and again violate locking order.
- *
- * More yuck to audit.
- */
- do_set_cpus_allowed(p, task_cpu_fallback_mask(p));
+ set_cpus_allowed_force(p, task_cpu_fallback_mask(p));
state = fail;
break;
case fail:
@@ -3777,7 +3705,7 @@ static int ttwu_runnable(struct task_struct *p, int wake_flags)
ttwu_do_wakeup(p);
ret = 1;
}
- __task_rq_unlock(rq, &rf);
+ __task_rq_unlock(rq, p, &rf);
return ret;
}
@@ -4231,7 +4159,7 @@ int try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
* __schedule(). See the comment for smp_mb__after_spinlock().
*
* Form a control-dep-acquire with p->on_rq == 0 above, to ensure
- * schedule()'s deactivate_task() has 'happened' and p will no longer
+ * schedule()'s block_task() has 'happened' and p will no longer
* care about it's own p->state. See the comment in __schedule().
*/
smp_acquire__after_ctrl_dep();
@@ -4370,7 +4298,7 @@ int task_call_func(struct task_struct *p, task_call_f func, void *arg)
ret = func(p, arg);
if (rq)
- rq_unlock(rq, &rf);
+ __task_rq_unlock(rq, p, &rf);
raw_spin_unlock_irqrestore(&p->pi_lock, rf.flags);
return ret;
@@ -5692,7 +5620,7 @@ static void sched_tick_remote(struct work_struct *work)
* reasonable amount of time.
*/
u64 delta = rq_clock_task(rq) - curr->se.exec_start;
- WARN_ON_ONCE(delta > (u64)NSEC_PER_SEC * 3);
+ WARN_ON_ONCE(delta > (u64)NSEC_PER_SEC * 30);
}
curr->sched_class->task_tick(rq, curr, 0);
@@ -5916,19 +5844,6 @@ static void prev_balance(struct rq *rq, struct task_struct *prev,
const struct sched_class *start_class = prev->sched_class;
const struct sched_class *class;
-#ifdef CONFIG_SCHED_CLASS_EXT
- /*
- * SCX requires a balance() call before every pick_task() including when
- * waking up from SCHED_IDLE. If @start_class is below SCX, start from
- * SCX instead. Also, set a flag to detect missing balance() call.
- */
- if (scx_enabled()) {
- rq->scx.flags |= SCX_RQ_BAL_PENDING;
- if (sched_class_above(&ext_sched_class, start_class))
- start_class = &ext_sched_class;
- }
-#endif
-
/*
* We must do the balancing pass before put_prev_task(), such
* that when we release the rq->lock the task is in the same
@@ -5972,7 +5887,7 @@ __pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
/* Assume the next prioritized class is idle_sched_class */
if (!p) {
- p = pick_task_idle(rq);
+ p = pick_task_idle(rq, rf);
put_prev_set_next_task(rq, prev, p);
}
@@ -5984,11 +5899,15 @@ restart:
for_each_active_class(class) {
if (class->pick_next_task) {
- p = class->pick_next_task(rq, prev);
+ p = class->pick_next_task(rq, prev, rf);
+ if (unlikely(p == RETRY_TASK))
+ goto restart;
if (p)
return p;
} else {
- p = class->pick_task(rq);
+ p = class->pick_task(rq, rf);
+ if (unlikely(p == RETRY_TASK))
+ goto restart;
if (p) {
put_prev_set_next_task(rq, prev, p);
return p;
@@ -6018,7 +5937,11 @@ static inline bool cookie_match(struct task_struct *a, struct task_struct *b)
return a->core_cookie == b->core_cookie;
}
-static inline struct task_struct *pick_task(struct rq *rq)
+/*
+ * Careful; this can return RETRY_TASK, it does not include the retry-loop
+ * itself due to the whole SMT pick retry thing below.
+ */
+static inline struct task_struct *pick_task(struct rq *rq, struct rq_flags *rf)
{
const struct sched_class *class;
struct task_struct *p;
@@ -6026,7 +5949,7 @@ static inline struct task_struct *pick_task(struct rq *rq)
rq->dl_server = NULL;
for_each_active_class(class) {
- p = class->pick_task(rq);
+ p = class->pick_task(rq, rf);
if (p)
return p;
}
@@ -6041,7 +5964,7 @@ static void queue_core_balance(struct rq *rq);
static struct task_struct *
pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
{
- struct task_struct *next, *p, *max = NULL;
+ struct task_struct *next, *p, *max;
const struct cpumask *smt_mask;
bool fi_before = false;
bool core_clock_updated = (rq == rq->core);
@@ -6126,7 +6049,10 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
* and there are no cookied tasks running on siblings.
*/
if (!need_sync) {
- next = pick_task(rq);
+restart_single:
+ next = pick_task(rq, rf);
+ if (unlikely(next == RETRY_TASK))
+ goto restart_single;
if (!next->core_cookie) {
rq->core_pick = NULL;
rq->core_dl_server = NULL;
@@ -6146,6 +6072,8 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
*
* Tie-break prio towards the current CPU
*/
+restart_multi:
+ max = NULL;
for_each_cpu_wrap(i, smt_mask, cpu) {
rq_i = cpu_rq(i);
@@ -6157,7 +6085,11 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
if (i != cpu && (rq_i != rq->core || !core_clock_updated))
update_rq_clock(rq_i);
- rq_i->core_pick = p = pick_task(rq_i);
+ p = pick_task(rq_i, rf);
+ if (unlikely(p == RETRY_TASK))
+ goto restart_multi;
+
+ rq_i->core_pick = p;
rq_i->core_dl_server = rq_i->dl_server;
if (!max || prio_less(max, p, fi_before))
@@ -6179,7 +6111,7 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
if (cookie)
p = sched_core_find(rq_i, cookie);
if (!p)
- p = idle_sched_class.pick_task(rq_i);
+ p = idle_sched_class.pick_task(rq_i, rf);
}
rq_i->core_pick = p;
@@ -6812,6 +6744,7 @@ static void __sched notrace __schedule(int sched_mode)
local_irq_disable();
rcu_note_context_switch(preempt);
+ migrate_disable_switch(rq, prev);
/*
* Make sure that signal_pending_state()->signal_pending() below
@@ -6918,7 +6851,6 @@ keep_resched:
*/
++*switch_count;
- migrate_disable_switch(rq, prev);
psi_account_irqtime(rq, prev, next);
psi_sched_switch(prev, next, !task_on_rq_queued(prev) ||
prev->se.sched_delayed);
@@ -7326,7 +7258,7 @@ void rt_mutex_post_schedule(void)
*/
void rt_mutex_setprio(struct task_struct *p, struct task_struct *pi_task)
{
- int prio, oldprio, queued, running, queue_flag =
+ int prio, oldprio, queue_flag =
DEQUEUE_SAVE | DEQUEUE_MOVE | DEQUEUE_NOCLOCK;
const struct sched_class *prev_class, *next_class;
struct rq_flags rf;
@@ -7388,64 +7320,51 @@ void rt_mutex_setprio(struct task_struct *p, struct task_struct *pi_task)
prev_class = p->sched_class;
next_class = __setscheduler_class(p->policy, prio);
- if (prev_class != next_class && p->se.sched_delayed)
- dequeue_task(rq, p, DEQUEUE_SLEEP | DEQUEUE_DELAYED | DEQUEUE_NOCLOCK);
-
- queued = task_on_rq_queued(p);
- running = task_current_donor(rq, p);
- if (queued)
- dequeue_task(rq, p, queue_flag);
- if (running)
- put_prev_task(rq, p);
+ if (prev_class != next_class)
+ queue_flag |= DEQUEUE_CLASS;
- /*
- * Boosting condition are:
- * 1. -rt task is running and holds mutex A
- * --> -dl task blocks on mutex A
- *
- * 2. -dl task is running and holds mutex A
- * --> -dl task blocks on mutex A and could preempt the
- * running task
- */
- if (dl_prio(prio)) {
- if (!dl_prio(p->normal_prio) ||
- (pi_task && dl_prio(pi_task->prio) &&
- dl_entity_preempt(&pi_task->dl, &p->dl))) {
- p->dl.pi_se = pi_task->dl.pi_se;
- queue_flag |= ENQUEUE_REPLENISH;
+ scoped_guard (sched_change, p, queue_flag) {
+ /*
+ * Boosting condition are:
+ * 1. -rt task is running and holds mutex A
+ * --> -dl task blocks on mutex A
+ *
+ * 2. -dl task is running and holds mutex A
+ * --> -dl task blocks on mutex A and could preempt the
+ * running task
+ */
+ if (dl_prio(prio)) {
+ if (!dl_prio(p->normal_prio) ||
+ (pi_task && dl_prio(pi_task->prio) &&
+ dl_entity_preempt(&pi_task->dl, &p->dl))) {
+ p->dl.pi_se = pi_task->dl.pi_se;
+ scope->flags |= ENQUEUE_REPLENISH;
+ } else {
+ p->dl.pi_se = &p->dl;
+ }
+ } else if (rt_prio(prio)) {
+ if (dl_prio(oldprio))
+ p->dl.pi_se = &p->dl;
+ if (oldprio < prio)
+ scope->flags |= ENQUEUE_HEAD;
} else {
- p->dl.pi_se = &p->dl;
+ if (dl_prio(oldprio))
+ p->dl.pi_se = &p->dl;
+ if (rt_prio(oldprio))
+ p->rt.timeout = 0;
}
- } else if (rt_prio(prio)) {
- if (dl_prio(oldprio))
- p->dl.pi_se = &p->dl;
- if (oldprio < prio)
- queue_flag |= ENQUEUE_HEAD;
- } else {
- if (dl_prio(oldprio))
- p->dl.pi_se = &p->dl;
- if (rt_prio(oldprio))
- p->rt.timeout = 0;
- }
- p->sched_class = next_class;
- p->prio = prio;
-
- check_class_changing(rq, p, prev_class);
-
- if (queued)
- enqueue_task(rq, p, queue_flag);
- if (running)
- set_next_task(rq, p);
-
- check_class_changed(rq, p, prev_class, oldprio);
+ p->sched_class = next_class;
+ p->prio = prio;
+ }
out_unlock:
/* Avoid rq from going away on us: */
preempt_disable();
rq_unpin_lock(rq, &rf);
__balance_callbacks(rq);
- raw_spin_rq_unlock(rq);
+ rq_repin_lock(rq, &rf);
+ __task_rq_unlock(rq, p, &rf);
preempt_enable();
}
@@ -8084,26 +8003,9 @@ int migrate_task_to(struct task_struct *p, int target_cpu)
*/
void sched_setnuma(struct task_struct *p, int nid)
{
- bool queued, running;
- struct rq_flags rf;
- struct rq *rq;
-
- rq = task_rq_lock(p, &rf);
- queued = task_on_rq_queued(p);
- running = task_current_donor(rq, p);
-
- if (queued)
- dequeue_task(rq, p, DEQUEUE_SAVE);
- if (running)
- put_prev_task(rq, p);
-
- p->numa_preferred_nid = nid;
-
- if (queued)
- enqueue_task(rq, p, ENQUEUE_RESTORE | ENQUEUE_NOCLOCK);
- if (running)
- set_next_task(rq, p);
- task_rq_unlock(rq, p, &rf);
+ guard(task_rq_lock)(p);
+ scoped_guard (sched_change, p, DEQUEUE_SAVE)
+ p->numa_preferred_nid = nid;
}
#endif /* CONFIG_NUMA_BALANCING */
@@ -8141,18 +8043,15 @@ static int __balance_push_cpu_stop(void *arg)
struct rq_flags rf;
int cpu;
- raw_spin_lock_irq(&p->pi_lock);
- rq_lock(rq, &rf);
-
- update_rq_clock(rq);
-
- if (task_rq(p) == rq && task_on_rq_queued(p)) {
+ scoped_guard (raw_spinlock_irq, &p->pi_lock) {
cpu = select_fallback_rq(rq->cpu, p);
- rq = __migrate_task(rq, &rf, p, cpu);
- }
- rq_unlock(rq, &rf);
- raw_spin_unlock_irq(&p->pi_lock);
+ rq_lock(rq, &rf);
+ update_rq_clock(rq);
+ if (task_rq(p) == rq && task_on_rq_queued(p))
+ rq = __migrate_task(rq, &rf, p, cpu);
+ rq_unlock(rq, &rf);
+ }
put_task_struct(p);
@@ -8591,6 +8490,8 @@ void __init sched_init_smp(void)
{
sched_init_numa(NUMA_NO_NODE);
+ prandom_init_once(&sched_rnd_state);
+
/*
* There's no userspace yet to cause hotplug operations; hence all the
* CPU masks are stable and all blatant races in the below code cannot
@@ -9207,38 +9108,23 @@ static void sched_change_group(struct task_struct *tsk)
*/
void sched_move_task(struct task_struct *tsk, bool for_autogroup)
{
- int queued, running, queue_flags =
- DEQUEUE_SAVE | DEQUEUE_MOVE | DEQUEUE_NOCLOCK;
+ unsigned int queue_flags = DEQUEUE_SAVE | DEQUEUE_MOVE;
+ bool resched = false;
struct rq *rq;
CLASS(task_rq_lock, rq_guard)(tsk);
rq = rq_guard.rq;
- update_rq_clock(rq);
-
- running = task_current_donor(rq, tsk);
- queued = task_on_rq_queued(tsk);
-
- if (queued)
- dequeue_task(rq, tsk, queue_flags);
- if (running)
- put_prev_task(rq, tsk);
-
- sched_change_group(tsk);
- if (!for_autogroup)
- scx_cgroup_move_task(tsk);
+ scoped_guard (sched_change, tsk, queue_flags) {
+ sched_change_group(tsk);
+ if (!for_autogroup)
+ scx_cgroup_move_task(tsk);
+ if (scope->running)
+ resched = true;
+ }
- if (queued)
- enqueue_task(rq, tsk, queue_flags);
- if (running) {
- set_next_task(rq, tsk);
- /*
- * After changing group, the running task may have joined a
- * throttled one but it's still the running task. Trigger a
- * resched to make sure that task can still run.
- */
+ if (resched)
resched_curr(rq);
- }
}
static struct cgroup_subsys_state *
@@ -10894,37 +10780,75 @@ void sched_mm_cid_fork(struct task_struct *t)
}
#endif /* CONFIG_SCHED_MM_CID */
-#ifdef CONFIG_SCHED_CLASS_EXT
-void sched_deq_and_put_task(struct task_struct *p, int queue_flags,
- struct sched_enq_and_set_ctx *ctx)
+static DEFINE_PER_CPU(struct sched_change_ctx, sched_change_ctx);
+
+struct sched_change_ctx *sched_change_begin(struct task_struct *p, unsigned int flags)
{
+ struct sched_change_ctx *ctx = this_cpu_ptr(&sched_change_ctx);
struct rq *rq = task_rq(p);
+ /*
+ * Must exclusively use matched flags since this is both dequeue and
+ * enqueue.
+ */
+ WARN_ON_ONCE(flags & 0xFFFF0000);
+
lockdep_assert_rq_held(rq);
- *ctx = (struct sched_enq_and_set_ctx){
+ if (!(flags & DEQUEUE_NOCLOCK)) {
+ update_rq_clock(rq);
+ flags |= DEQUEUE_NOCLOCK;
+ }
+
+ if (flags & DEQUEUE_CLASS) {
+ if (p->sched_class->switching_from)
+ p->sched_class->switching_from(rq, p);
+ }
+
+ *ctx = (struct sched_change_ctx){
.p = p,
- .queue_flags = queue_flags,
+ .flags = flags,
.queued = task_on_rq_queued(p),
- .running = task_current(rq, p),
+ .running = task_current_donor(rq, p),
};
- update_rq_clock(rq);
+ if (!(flags & DEQUEUE_CLASS)) {
+ if (p->sched_class->get_prio)
+ ctx->prio = p->sched_class->get_prio(rq, p);
+ else
+ ctx->prio = p->prio;
+ }
+
if (ctx->queued)
- dequeue_task(rq, p, queue_flags | DEQUEUE_NOCLOCK);
+ dequeue_task(rq, p, flags);
if (ctx->running)
put_prev_task(rq, p);
+
+ if ((flags & DEQUEUE_CLASS) && p->sched_class->switched_from)
+ p->sched_class->switched_from(rq, p);
+
+ return ctx;
}
-void sched_enq_and_set_task(struct sched_enq_and_set_ctx *ctx)
+void sched_change_end(struct sched_change_ctx *ctx)
{
- struct rq *rq = task_rq(ctx->p);
+ struct task_struct *p = ctx->p;
+ struct rq *rq = task_rq(p);
lockdep_assert_rq_held(rq);
+ if ((ctx->flags & ENQUEUE_CLASS) && p->sched_class->switching_to)
+ p->sched_class->switching_to(rq, p);
+
if (ctx->queued)
- enqueue_task(rq, ctx->p, ctx->queue_flags | ENQUEUE_NOCLOCK);
+ enqueue_task(rq, p, ctx->flags);
if (ctx->running)
- set_next_task(rq, ctx->p);
+ set_next_task(rq, p);
+
+ if (ctx->flags & ENQUEUE_CLASS) {
+ if (p->sched_class->switched_to)
+ p->sched_class->switched_to(rq, p);
+ } else {
+ p->sched_class->prio_changed(rq, p, ctx->prio);
+ }
}
-#endif /* CONFIG_SCHED_CLASS_EXT */
diff --git a/kernel/sched/cpudeadline.c b/kernel/sched/cpudeadline.c
index cdd740b3f774..37b572cc8aca 100644
--- a/kernel/sched/cpudeadline.c
+++ b/kernel/sched/cpudeadline.c
@@ -166,12 +166,13 @@ int cpudl_find(struct cpudl *cp, struct task_struct *p,
* cpudl_clear - remove a CPU from the cpudl max-heap
* @cp: the cpudl max-heap context
* @cpu: the target CPU
+ * @online: the online state of the deadline runqueue
*
* Notes: assumes cpu_rq(cpu)->lock is locked
*
* Returns: (void)
*/
-void cpudl_clear(struct cpudl *cp, int cpu)
+void cpudl_clear(struct cpudl *cp, int cpu, bool online)
{
int old_idx, new_cpu;
unsigned long flags;
@@ -184,7 +185,7 @@ void cpudl_clear(struct cpudl *cp, int cpu)
if (old_idx == IDX_INVALID) {
/*
* Nothing to remove if old_idx was invalid.
- * This could happen if a rq_offline_dl is
+ * This could happen if rq_online_dl or rq_offline_dl is
* called for a CPU without -dl tasks running.
*/
} else {
@@ -195,9 +196,12 @@ void cpudl_clear(struct cpudl *cp, int cpu)
cp->elements[new_cpu].idx = old_idx;
cp->elements[cpu].idx = IDX_INVALID;
cpudl_heapify(cp, old_idx);
-
- cpumask_set_cpu(cpu, cp->free_cpus);
}
+ if (likely(online))
+ __cpumask_set_cpu(cpu, cp->free_cpus);
+ else
+ __cpumask_clear_cpu(cpu, cp->free_cpus);
+
raw_spin_unlock_irqrestore(&cp->lock, flags);
}
@@ -228,7 +232,7 @@ void cpudl_set(struct cpudl *cp, int cpu, u64 dl)
cp->elements[new_idx].cpu = cpu;
cp->elements[cpu].idx = new_idx;
cpudl_heapify_up(cp, new_idx);
- cpumask_clear_cpu(cpu, cp->free_cpus);
+ __cpumask_clear_cpu(cpu, cp->free_cpus);
} else {
cp->elements[old_idx].dl = dl;
cpudl_heapify(cp, old_idx);
@@ -238,26 +242,6 @@ void cpudl_set(struct cpudl *cp, int cpu, u64 dl)
}
/*
- * cpudl_set_freecpu - Set the cpudl.free_cpus
- * @cp: the cpudl max-heap context
- * @cpu: rd attached CPU
- */
-void cpudl_set_freecpu(struct cpudl *cp, int cpu)
-{
- cpumask_set_cpu(cpu, cp->free_cpus);
-}
-
-/*
- * cpudl_clear_freecpu - Clear the cpudl.free_cpus
- * @cp: the cpudl max-heap context
- * @cpu: rd attached CPU
- */
-void cpudl_clear_freecpu(struct cpudl *cp, int cpu)
-{
- cpumask_clear_cpu(cpu, cp->free_cpus);
-}
-
-/*
* cpudl_init - initialize the cpudl structure
* @cp: the cpudl max-heap context
*/
diff --git a/kernel/sched/cpudeadline.h b/kernel/sched/cpudeadline.h
index 11c0f1faa7e1..d7699468eedd 100644
--- a/kernel/sched/cpudeadline.h
+++ b/kernel/sched/cpudeadline.h
@@ -19,8 +19,6 @@ struct cpudl {
int cpudl_find(struct cpudl *cp, struct task_struct *p, struct cpumask *later_mask);
void cpudl_set(struct cpudl *cp, int cpu, u64 dl);
-void cpudl_clear(struct cpudl *cp, int cpu);
+void cpudl_clear(struct cpudl *cp, int cpu, bool online);
int cpudl_init(struct cpudl *cp);
-void cpudl_set_freecpu(struct cpudl *cp, int cpu);
-void cpudl_clear_freecpu(struct cpudl *cp, int cpu);
void cpudl_cleanup(struct cpudl *cp);
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 7b7671060bf9..67f540c23717 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -125,20 +125,11 @@ static inline struct dl_bw *dl_bw_of(int i)
static inline int dl_bw_cpus(int i)
{
struct root_domain *rd = cpu_rq(i)->rd;
- int cpus;
RCU_LOCKDEP_WARN(!rcu_read_lock_sched_held(),
"sched RCU must be held");
- if (cpumask_subset(rd->span, cpu_active_mask))
- return cpumask_weight(rd->span);
-
- cpus = 0;
-
- for_each_cpu_and(i, rd->span, cpu_active_mask)
- cpus++;
-
- return cpus;
+ return cpumask_weight_and(rd->span, cpu_active_mask);
}
static inline unsigned long __dl_bw_capacity(const struct cpumask *mask)
@@ -405,7 +396,7 @@ static void __dl_clear_params(struct sched_dl_entity *dl_se);
* up, and checks if the task is still in the "ACTIVE non contending"
* state or not (in the second case, it updates running_bw).
*/
-static void task_non_contending(struct sched_dl_entity *dl_se)
+static void task_non_contending(struct sched_dl_entity *dl_se, bool dl_task)
{
struct hrtimer *timer = &dl_se->inactive_timer;
struct rq *rq = rq_of_dl_se(dl_se);
@@ -444,10 +435,10 @@ static void task_non_contending(struct sched_dl_entity *dl_se)
} else {
struct task_struct *p = dl_task_of(dl_se);
- if (dl_task(p))
+ if (dl_task)
sub_running_bw(dl_se, dl_rq);
- if (!dl_task(p) || READ_ONCE(p->__state) == TASK_DEAD) {
+ if (!dl_task || READ_ONCE(p->__state) == TASK_DEAD) {
struct dl_bw *dl_b = dl_bw_of(task_cpu(p));
if (READ_ONCE(p->__state) == TASK_DEAD)
@@ -1166,8 +1157,17 @@ static enum hrtimer_restart dl_server_timer(struct hrtimer *timer, struct sched_
sched_clock_tick();
update_rq_clock(rq);
- if (!dl_se->dl_runtime)
+ /*
+ * Make sure current has propagated its pending runtime into
+ * any relevant server through calling dl_server_update() and
+ * friends.
+ */
+ rq->donor->sched_class->update_curr(rq);
+
+ if (dl_se->dl_defer_idle) {
+ dl_server_stop(dl_se);
return HRTIMER_NORESTART;
+ }
if (dl_se->dl_defer_armed) {
/*
@@ -1416,10 +1416,11 @@ s64 dl_scaled_delta_exec(struct rq *rq, struct sched_dl_entity *dl_se, s64 delta
}
static inline void
-update_stats_dequeue_dl(struct dl_rq *dl_rq, struct sched_dl_entity *dl_se,
- int flags);
+update_stats_dequeue_dl(struct dl_rq *dl_rq, struct sched_dl_entity *dl_se, int flags);
+
static void update_curr_dl_se(struct rq *rq, struct sched_dl_entity *dl_se, s64 delta_exec)
{
+ bool idle = rq->curr == rq->idle;
s64 scaled_delta_exec;
if (unlikely(delta_exec <= 0)) {
@@ -1440,6 +1441,9 @@ static void update_curr_dl_se(struct rq *rq, struct sched_dl_entity *dl_se, s64
dl_se->runtime -= scaled_delta_exec;
+ if (dl_se->dl_defer_idle && !idle)
+ dl_se->dl_defer_idle = 0;
+
/*
* The fair server can consume its runtime while throttled (not queued/
* running as regular CFS).
@@ -1450,6 +1454,29 @@ static void update_curr_dl_se(struct rq *rq, struct sched_dl_entity *dl_se, s64
*/
if (dl_se->dl_defer && dl_se->dl_throttled && dl_runtime_exceeded(dl_se)) {
/*
+ * Non-servers would never get time accounted while throttled.
+ */
+ WARN_ON_ONCE(!dl_server(dl_se));
+
+ /*
+ * While the server is marked idle, do not push out the
+ * activation further, instead wait for the period timer
+ * to lapse and stop the server.
+ */
+ if (dl_se->dl_defer_idle && idle) {
+ /*
+ * The timer is at the zero-laxity point, this means
+ * dl_server_stop() / dl_server_start() can happen
+ * while now < deadline. This means update_dl_entity()
+ * will not replenish. Additionally start_dl_timer()
+ * will be set for 'deadline - runtime'. Negative
+ * runtime will not do.
+ */
+ dl_se->runtime = 0;
+ return;
+ }
+
+ /*
* If the server was previously activated - the starving condition
* took place, it this point it went away because the fair scheduler
* was able to get runtime in background. So return to the initial
@@ -1461,6 +1488,9 @@ static void update_curr_dl_se(struct rq *rq, struct sched_dl_entity *dl_se, s64
replenish_dl_new_period(dl_se, dl_se->rq);
+ if (idle)
+ dl_se->dl_defer_idle = 1;
+
/*
* Not being able to start the timer seems problematic. If it could not
* be started for whatever reason, we need to "unthrottle" the DL server
@@ -1543,38 +1573,213 @@ throttle:
* as time available for the fair server, avoiding a penalty for the
* rt scheduler that did not consumed that time.
*/
-void dl_server_update_idle_time(struct rq *rq, struct task_struct *p)
+void dl_server_update_idle(struct sched_dl_entity *dl_se, s64 delta_exec)
{
- s64 delta_exec;
-
- if (!rq->fair_server.dl_defer)
- return;
-
- /* no need to discount more */
- if (rq->fair_server.runtime < 0)
- return;
-
- delta_exec = rq_clock_task(rq) - p->se.exec_start;
- if (delta_exec < 0)
- return;
-
- rq->fair_server.runtime -= delta_exec;
-
- if (rq->fair_server.runtime < 0) {
- rq->fair_server.dl_defer_running = 0;
- rq->fair_server.runtime = 0;
- }
-
- p->se.exec_start = rq_clock_task(rq);
+ if (dl_se->dl_server_active && dl_se->dl_runtime && dl_se->dl_defer)
+ update_curr_dl_se(dl_se->rq, dl_se, delta_exec);
}
void dl_server_update(struct sched_dl_entity *dl_se, s64 delta_exec)
{
/* 0 runtime = fair server disabled */
- if (dl_se->dl_runtime)
+ if (dl_se->dl_server_active && dl_se->dl_runtime)
update_curr_dl_se(dl_se->rq, dl_se, delta_exec);
}
+/*
+ * dl_server && dl_defer:
+ *
+ * 6
+ * +--------------------+
+ * v |
+ * +-------------+ 4 +-----------+ 5 +------------------+
+ * +-> | A:init | <--- | D:running | -----> | E:replenish-wait |
+ * | +-------------+ +-----------+ +------------------+
+ * | | | 1 ^ ^ |
+ * | | 1 +----------+ | 3 |
+ * | v | |
+ * | +--------------------------------+ 2 |
+ * | | | ----+ |
+ * | 8 | B:zero_laxity-wait | | |
+ * | | | <---+ |
+ * | +--------------------------------+ |
+ * | | ^ ^ 2 |
+ * | | 7 | 2 +--------------------+
+ * | v |
+ * | +-------------+ |
+ * +-- | C:idle-wait | -+
+ * +-------------+
+ * ^ 7 |
+ * +---------+
+ *
+ *
+ * [A] - init
+ * dl_server_active = 0
+ * dl_throttled = 0
+ * dl_defer_armed = 0
+ * dl_defer_running = 0/1
+ * dl_defer_idle = 0
+ *
+ * [B] - zero_laxity-wait
+ * dl_server_active = 1
+ * dl_throttled = 1
+ * dl_defer_armed = 1
+ * dl_defer_running = 0
+ * dl_defer_idle = 0
+ *
+ * [C] - idle-wait
+ * dl_server_active = 1
+ * dl_throttled = 1
+ * dl_defer_armed = 1
+ * dl_defer_running = 0
+ * dl_defer_idle = 1
+ *
+ * [D] - running
+ * dl_server_active = 1
+ * dl_throttled = 0
+ * dl_defer_armed = 0
+ * dl_defer_running = 1
+ * dl_defer_idle = 0
+ *
+ * [E] - replenish-wait
+ * dl_server_active = 1
+ * dl_throttled = 1
+ * dl_defer_armed = 0
+ * dl_defer_running = 1
+ * dl_defer_idle = 0
+ *
+ *
+ * [1] A->B, A->D
+ * dl_server_start()
+ * dl_server_active = 1;
+ * enqueue_dl_entity()
+ * update_dl_entity(WAKEUP)
+ * if (!dl_defer_running)
+ * dl_defer_armed = 1;
+ * dl_throttled = 1;
+ * if (dl_throttled && start_dl_timer())
+ * return; // [B]
+ * __enqueue_dl_entity();
+ * // [D]
+ *
+ * // deplete server runtime from client-class
+ * [2] B->B, C->B, E->B
+ * dl_server_update()
+ * update_curr_dl_se() // idle = false
+ * if (dl_defer_idle)
+ * dl_defer_idle = 0;
+ * if (dl_defer && dl_throttled && dl_runtime_exceeded())
+ * dl_defer_running = 0;
+ * hrtimer_try_to_cancel(); // stop timer
+ * replenish_dl_new_period()
+ * // fwd period
+ * dl_throttled = 1;
+ * dl_defer_armed = 1;
+ * start_dl_timer(); // restart timer
+ * // [B]
+ *
+ * // timer actually fires means we have runtime
+ * [3] B->D
+ * dl_server_timer()
+ * if (dl_defer_armed)
+ * dl_defer_running = 1;
+ * enqueue_dl_entity(REPLENISH)
+ * replenish_dl_entity()
+ * // fwd period
+ * if (dl_throttled)
+ * dl_throttled = 0;
+ * if (dl_defer_armed)
+ * dl_defer_armed = 0;
+ * __enqueue_dl_entity();
+ * // [D]
+ *
+ * // schedule server
+ * [4] D->A
+ * pick_task_dl()
+ * p = server_pick_task();
+ * if (!p)
+ * dl_server_stop()
+ * dequeue_dl_entity();
+ * hrtimer_try_to_cancel();
+ * dl_defer_armed = 0;
+ * dl_throttled = 0;
+ * dl_server_active = 0;
+ * // [A]
+ * return p;
+ *
+ * // server running
+ * [5] D->E
+ * update_curr_dl_se()
+ * if (dl_runtime_exceeded())
+ * dl_throttled = 1;
+ * dequeue_dl_entity();
+ * start_dl_timer();
+ * // [E]
+ *
+ * // server replenished
+ * [6] E->D
+ * dl_server_timer()
+ * enqueue_dl_entity(REPLENISH)
+ * replenish_dl_entity()
+ * fwd-period
+ * if (dl_throttled)
+ * dl_throttled = 0;
+ * __enqueue_dl_entity();
+ * // [D]
+ *
+ * // deplete server runtime from idle
+ * [7] B->C, C->C
+ * dl_server_update_idle()
+ * update_curr_dl_se() // idle = true
+ * if (dl_defer && dl_throttled && dl_runtime_exceeded())
+ * if (dl_defer_idle)
+ * return;
+ * dl_defer_running = 0;
+ * hrtimer_try_to_cancel();
+ * replenish_dl_new_period()
+ * // fwd period
+ * dl_throttled = 1;
+ * dl_defer_armed = 1;
+ * dl_defer_idle = 1;
+ * start_dl_timer(); // restart timer
+ * // [C]
+ *
+ * // stop idle server
+ * [8] C->A
+ * dl_server_timer()
+ * if (dl_defer_idle)
+ * dl_server_stop();
+ * // [A]
+ *
+ *
+ * digraph dl_server {
+ * "A:init" -> "B:zero_laxity-wait" [label="1:dl_server_start"]
+ * "A:init" -> "D:running" [label="1:dl_server_start"]
+ * "B:zero_laxity-wait" -> "B:zero_laxity-wait" [label="2:dl_server_update"]
+ * "B:zero_laxity-wait" -> "C:idle-wait" [label="7:dl_server_update_idle"]
+ * "B:zero_laxity-wait" -> "D:running" [label="3:dl_server_timer"]
+ * "C:idle-wait" -> "A:init" [label="8:dl_server_timer"]
+ * "C:idle-wait" -> "B:zero_laxity-wait" [label="2:dl_server_update"]
+ * "C:idle-wait" -> "C:idle-wait" [label="7:dl_server_update_idle"]
+ * "D:running" -> "A:init" [label="4:pick_task_dl"]
+ * "D:running" -> "E:replenish-wait" [label="5:update_curr_dl_se"]
+ * "E:replenish-wait" -> "B:zero_laxity-wait" [label="2:dl_server_update"]
+ * "E:replenish-wait" -> "D:running" [label="6:dl_server_timer"]
+ * }
+ *
+ *
+ * Notes:
+ *
+ * - When there are fair tasks running the most likely loop is [2]->[2].
+ * the dl_server never actually runs, the timer never fires.
+ *
+ * - When there is actual fair starvation; the timer fires and starts the
+ * dl_server. This will then throttle and replenish like a normal DL
+ * task. Notably it will not 'defer' again.
+ *
+ * - When idle it will push the actication forward once, and then wait
+ * for the timer to hit or a non-idle update to restart things.
+ */
void dl_server_start(struct sched_dl_entity *dl_se)
{
struct rq *rq = dl_se->rq;
@@ -1582,6 +1787,11 @@ void dl_server_start(struct sched_dl_entity *dl_se)
if (!dl_server(dl_se) || dl_se->dl_server_active)
return;
+ /*
+ * Update the current task to 'now'.
+ */
+ rq->donor->sched_class->update_curr(rq);
+
if (WARN_ON_ONCE(!cpu_online(cpu_of(rq))))
return;
@@ -1600,6 +1810,7 @@ void dl_server_stop(struct sched_dl_entity *dl_se)
hrtimer_try_to_cancel(&dl_se->dl_timer);
dl_se->dl_defer_armed = 0;
dl_se->dl_throttled = 0;
+ dl_se->dl_defer_idle = 0;
dl_se->dl_server_active = 0;
}
@@ -1811,7 +2022,7 @@ static void dec_dl_deadline(struct dl_rq *dl_rq, u64 deadline)
if (!dl_rq->dl_nr_running) {
dl_rq->earliest_dl.curr = 0;
dl_rq->earliest_dl.next = 0;
- cpudl_clear(&rq->rd->cpudl, rq->cpu);
+ cpudl_clear(&rq->rd->cpudl, rq->cpu, rq->online);
cpupri_set(&rq->rd->cpupri, rq->cpu, rq->rt.highest_prio.curr);
} else {
struct rb_node *leftmost = rb_first_cached(&dl_rq->root);
@@ -2048,7 +2259,7 @@ static void dequeue_dl_entity(struct sched_dl_entity *dl_se, int flags)
* or "inactive")
*/
if (flags & DEQUEUE_SLEEP)
- task_non_contending(dl_se);
+ task_non_contending(dl_se, true);
}
static void enqueue_task_dl(struct rq *rq, struct task_struct *p, int flags)
@@ -2143,7 +2354,7 @@ static void yield_task_dl(struct rq *rq)
* it and the bandwidth timer will wake it up and will give it
* new scheduling parameters (thanks to dl_yielded=1).
*/
- rq->curr->dl.dl_yielded = 1;
+ rq->donor->dl.dl_yielded = 1;
update_rq_clock(rq);
update_curr_dl(rq);
@@ -2173,7 +2384,7 @@ select_task_rq_dl(struct task_struct *p, int cpu, int flags)
struct rq *rq;
if (!(flags & WF_TTWU))
- goto out;
+ return cpu;
rq = cpu_rq(cpu);
@@ -2211,7 +2422,6 @@ select_task_rq_dl(struct task_struct *p, int cpu, int flags)
}
rcu_read_unlock();
-out:
return cpu;
}
@@ -2355,7 +2565,7 @@ static struct sched_dl_entity *pick_next_dl_entity(struct dl_rq *dl_rq)
* __pick_next_task_dl - Helper to pick the next -deadline task to run.
* @rq: The runqueue to pick the next task from.
*/
-static struct task_struct *__pick_task_dl(struct rq *rq)
+static struct task_struct *__pick_task_dl(struct rq *rq, struct rq_flags *rf)
{
struct sched_dl_entity *dl_se;
struct dl_rq *dl_rq = &rq->dl;
@@ -2369,7 +2579,7 @@ again:
WARN_ON_ONCE(!dl_se);
if (dl_server(dl_se)) {
- p = dl_se->server_pick_task(dl_se);
+ p = dl_se->server_pick_task(dl_se, rf);
if (!p) {
dl_server_stop(dl_se);
goto again;
@@ -2382,9 +2592,9 @@ again:
return p;
}
-static struct task_struct *pick_task_dl(struct rq *rq)
+static struct task_struct *pick_task_dl(struct rq *rq, struct rq_flags *rf)
{
- return __pick_task_dl(rq);
+ return __pick_task_dl(rq, rf);
}
static void put_prev_task_dl(struct rq *rq, struct task_struct *p, struct task_struct *next)
@@ -2883,9 +3093,10 @@ static void rq_online_dl(struct rq *rq)
if (rq->dl.overloaded)
dl_set_overload(rq);
- cpudl_set_freecpu(&rq->rd->cpudl, rq->cpu);
if (rq->dl.dl_nr_running > 0)
cpudl_set(&rq->rd->cpudl, rq->cpu, rq->dl.earliest_dl.curr);
+ else
+ cpudl_clear(&rq->rd->cpudl, rq->cpu, true);
}
/* Assumes rq->lock is held */
@@ -2894,8 +3105,7 @@ static void rq_offline_dl(struct rq *rq)
if (rq->dl.overloaded)
dl_clear_overload(rq);
- cpudl_clear(&rq->rd->cpudl, rq->cpu);
- cpudl_clear_freecpu(&rq->rd->cpudl, rq->cpu);
+ cpudl_clear(&rq->rd->cpudl, rq->cpu, false);
}
void __init init_sched_dl_class(void)
@@ -2973,7 +3183,7 @@ static void switched_from_dl(struct rq *rq, struct task_struct *p)
* will reset the task parameters.
*/
if (task_on_rq_queued(p) && p->dl.dl_runtime)
- task_non_contending(&p->dl);
+ task_non_contending(&p->dl, false);
/*
* In case a task is setscheduled out from SCHED_DEADLINE we need to
@@ -3045,23 +3255,24 @@ static void switched_to_dl(struct rq *rq, struct task_struct *p)
}
}
+static u64 get_prio_dl(struct rq *rq, struct task_struct *p)
+{
+ return p->dl.deadline;
+}
+
/*
* If the scheduling parameters of a -deadline task changed,
* a push or pull operation might be needed.
*/
-static void prio_changed_dl(struct rq *rq, struct task_struct *p,
- int oldprio)
+static void prio_changed_dl(struct rq *rq, struct task_struct *p, u64 old_deadline)
{
if (!task_on_rq_queued(p))
return;
- /*
- * This might be too much, but unfortunately
- * we don't have the old deadline value, and
- * we can't argue if the task is increasing
- * or lowering its prio, so...
- */
- if (!rq->dl.overloaded)
+ if (p->dl.deadline == old_deadline)
+ return;
+
+ if (dl_time_before(old_deadline, p->dl.deadline))
deadline_queue_pull_task(rq);
if (task_current_donor(rq, p)) {
@@ -3094,6 +3305,8 @@ static int task_is_throttled_dl(struct task_struct *p, int cpu)
DEFINE_SCHED_CLASS(dl) = {
+ .queue_mask = 8,
+
.enqueue_task = enqueue_task_dl,
.dequeue_task = dequeue_task_dl,
.yield_task = yield_task_dl,
@@ -3116,6 +3329,7 @@ DEFINE_SCHED_CLASS(dl) = {
.task_tick = task_tick_dl,
.task_fork = task_fork_dl,
+ .get_prio = get_prio_dl,
.prio_changed = prio_changed_dl,
.switched_from = switched_from_dl,
.switched_to = switched_to_dl,
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index 02e16b70a790..41caa22e0680 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -796,7 +796,7 @@ static void print_rq(struct seq_file *m, struct rq *rq, int rq_cpu)
void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq)
{
- s64 left_vruntime = -1, min_vruntime, right_vruntime = -1, left_deadline = -1, spread;
+ s64 left_vruntime = -1, zero_vruntime, right_vruntime = -1, left_deadline = -1, spread;
struct sched_entity *last, *first, *root;
struct rq *rq = cpu_rq(cpu);
unsigned long flags;
@@ -819,15 +819,15 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq)
last = __pick_last_entity(cfs_rq);
if (last)
right_vruntime = last->vruntime;
- min_vruntime = cfs_rq->min_vruntime;
+ zero_vruntime = cfs_rq->zero_vruntime;
raw_spin_rq_unlock_irqrestore(rq, flags);
SEQ_printf(m, " .%-30s: %Ld.%06ld\n", "left_deadline",
SPLIT_NS(left_deadline));
SEQ_printf(m, " .%-30s: %Ld.%06ld\n", "left_vruntime",
SPLIT_NS(left_vruntime));
- SEQ_printf(m, " .%-30s: %Ld.%06ld\n", "min_vruntime",
- SPLIT_NS(min_vruntime));
+ SEQ_printf(m, " .%-30s: %Ld.%06ld\n", "zero_vruntime",
+ SPLIT_NS(zero_vruntime));
SEQ_printf(m, " .%-30s: %Ld.%06ld\n", "avg_vruntime",
SPLIT_NS(avg_vruntime(cfs_rq)));
SEQ_printf(m, " .%-30s: %Ld.%06ld\n", "right_vruntime",
diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c
index 979484dab2d3..6827689a0966 100644
--- a/kernel/sched/ext.c
+++ b/kernel/sched/ext.c
@@ -1474,7 +1474,7 @@ static bool dequeue_task_scx(struct rq *rq, struct task_struct *p, int deq_flags
static void yield_task_scx(struct rq *rq)
{
struct scx_sched *sch = scx_root;
- struct task_struct *p = rq->curr;
+ struct task_struct *p = rq->donor;
if (SCX_HAS_OP(sch, yield))
SCX_CALL_OP_2TASKS_RET(sch, SCX_KF_REST, yield, rq, p, NULL);
@@ -1485,7 +1485,7 @@ static void yield_task_scx(struct rq *rq)
static bool yield_to_task_scx(struct rq *rq, struct task_struct *to)
{
struct scx_sched *sch = scx_root;
- struct task_struct *from = rq->curr;
+ struct task_struct *from = rq->donor;
if (SCX_HAS_OP(sch, yield))
return SCX_CALL_OP_2TASKS_RET(sch, SCX_KF_REST, yield, rq,
@@ -2047,7 +2047,7 @@ static int balance_one(struct rq *rq, struct task_struct *prev)
lockdep_assert_rq_held(rq);
rq->scx.flags |= SCX_RQ_IN_BALANCE;
- rq->scx.flags &= ~(SCX_RQ_BAL_PENDING | SCX_RQ_BAL_KEEP);
+ rq->scx.flags &= ~SCX_RQ_BAL_KEEP;
if ((sch->ops.flags & SCX_OPS_HAS_CPU_PREEMPT) &&
unlikely(rq->scx.cpu_released)) {
@@ -2153,42 +2153,6 @@ has_tasks:
return true;
}
-static int balance_scx(struct rq *rq, struct task_struct *prev,
- struct rq_flags *rf)
-{
- int ret;
-
- rq_unpin_lock(rq, rf);
-
- ret = balance_one(rq, prev);
-
-#ifdef CONFIG_SCHED_SMT
- /*
- * When core-sched is enabled, this ops.balance() call will be followed
- * by pick_task_scx() on this CPU and the SMT siblings. Balance the
- * siblings too.
- */
- if (sched_core_enabled(rq)) {
- const struct cpumask *smt_mask = cpu_smt_mask(cpu_of(rq));
- int scpu;
-
- for_each_cpu_andnot(scpu, smt_mask, cpumask_of(cpu_of(rq))) {
- struct rq *srq = cpu_rq(scpu);
- struct task_struct *sprev = srq->curr;
-
- WARN_ON_ONCE(__rq_lockp(rq) != __rq_lockp(srq));
- update_rq_clock(srq);
- balance_one(srq, sprev);
- }
- }
-#endif
- rq_repin_lock(rq, rf);
-
- maybe_queue_balance_callback(rq);
-
- return ret;
-}
-
static void process_ddsp_deferred_locals(struct rq *rq)
{
struct task_struct *p;
@@ -2368,41 +2332,23 @@ static struct task_struct *first_local_task(struct rq *rq)
struct task_struct, scx.dsq_list.node);
}
-static struct task_struct *pick_task_scx(struct rq *rq)
+static struct task_struct *pick_task_scx(struct rq *rq, struct rq_flags *rf)
{
struct task_struct *prev = rq->curr;
+ bool keep_prev, kick_idle = false;
struct task_struct *p;
- bool keep_prev = rq->scx.flags & SCX_RQ_BAL_KEEP;
- bool kick_idle = false;
- /*
- * WORKAROUND:
- *
- * %SCX_RQ_BAL_KEEP should be set iff $prev is on SCX as it must just
- * have gone through balance_scx(). Unfortunately, there currently is a
- * bug where fair could say yes on balance() but no on pick_task(),
- * which then ends up calling pick_task_scx() without preceding
- * balance_scx().
- *
- * Keep running @prev if possible and avoid stalling from entering idle
- * without balancing.
- *
- * Once fair is fixed, remove the workaround and trigger WARN_ON_ONCE()
- * if pick_task_scx() is called without preceding balance_scx().
- */
- if (unlikely(rq->scx.flags & SCX_RQ_BAL_PENDING)) {
- if (prev->scx.flags & SCX_TASK_QUEUED) {
- keep_prev = true;
- } else {
- keep_prev = false;
- kick_idle = true;
- }
- } else if (unlikely(keep_prev &&
- prev->sched_class != &ext_sched_class)) {
- /*
- * Can happen while enabling as SCX_RQ_BAL_PENDING assertion is
- * conditional on scx_enabled() and may have been skipped.
- */
+ rq_modified_clear(rq);
+ rq_unpin_lock(rq, rf);
+ balance_one(rq, prev);
+ rq_repin_lock(rq, rf);
+ maybe_queue_balance_callback(rq);
+ if (rq_modified_above(rq, &ext_sched_class))
+ return RETRY_TASK;
+
+ keep_prev = rq->scx.flags & SCX_RQ_BAL_KEEP;
+ if (unlikely(keep_prev &&
+ prev->sched_class != &ext_sched_class)) {
WARN_ON_ONCE(scx_enable_state() == SCX_ENABLED);
keep_prev = false;
}
@@ -2997,7 +2943,7 @@ static void reweight_task_scx(struct rq *rq, struct task_struct *p,
p, p->scx.weight);
}
-static void prio_changed_scx(struct rq *rq, struct task_struct *p, int oldprio)
+static void prio_changed_scx(struct rq *rq, struct task_struct *p, u64 oldprio)
{
}
@@ -3270,6 +3216,8 @@ static void scx_cgroup_unlock(void) {}
* their current sched_class. Call them directly from sched core instead.
*/
DEFINE_SCHED_CLASS(ext) = {
+ .queue_mask = 1,
+
.enqueue_task = enqueue_task_scx,
.dequeue_task = dequeue_task_scx,
.yield_task = yield_task_scx,
@@ -3277,7 +3225,6 @@ DEFINE_SCHED_CLASS(ext) = {
.wakeup_preempt = wakeup_preempt_scx,
- .balance = balance_scx,
.pick_task = pick_task_scx,
.put_prev_task = put_prev_task_scx,
@@ -3818,11 +3765,10 @@ static void scx_bypass(bool bypass)
*/
list_for_each_entry_safe_reverse(p, n, &rq->scx.runnable_list,
scx.runnable_node) {
- struct sched_enq_and_set_ctx ctx;
-
/* cycling deq/enq is enough, see the function comment */
- sched_deq_and_put_task(p, DEQUEUE_SAVE | DEQUEUE_MOVE, &ctx);
- sched_enq_and_set_task(&ctx);
+ scoped_guard (sched_change, p, DEQUEUE_SAVE | DEQUEUE_MOVE) {
+ /* nothing */ ;
+ }
}
/* resched to restore ticks and idle state */
@@ -3972,22 +3918,20 @@ static void scx_disable_workfn(struct kthread_work *work)
scx_task_iter_start(&sti);
while ((p = scx_task_iter_next_locked(&sti))) {
+ unsigned int queue_flags = DEQUEUE_SAVE | DEQUEUE_MOVE | DEQUEUE_NOCLOCK;
const struct sched_class *old_class = p->sched_class;
const struct sched_class *new_class =
__setscheduler_class(p->policy, p->prio);
- struct sched_enq_and_set_ctx ctx;
- if (old_class != new_class && p->se.sched_delayed)
- dequeue_task(task_rq(p), p, DEQUEUE_SLEEP | DEQUEUE_DELAYED);
+ update_rq_clock(task_rq(p));
- sched_deq_and_put_task(p, DEQUEUE_SAVE | DEQUEUE_MOVE, &ctx);
+ if (old_class != new_class)
+ queue_flags |= DEQUEUE_CLASS;
- p->sched_class = new_class;
- check_class_changing(task_rq(p), p, old_class);
-
- sched_enq_and_set_task(&ctx);
+ scoped_guard (sched_change, p, queue_flags) {
+ p->sched_class = new_class;
+ }
- check_class_changed(task_rq(p), p, old_class, p->prio);
scx_exit_task(p);
}
scx_task_iter_stop(&sti);
@@ -4751,26 +4695,22 @@ static int scx_enable(struct sched_ext_ops *ops, struct bpf_link *link)
percpu_down_write(&scx_fork_rwsem);
scx_task_iter_start(&sti);
while ((p = scx_task_iter_next_locked(&sti))) {
+ unsigned int queue_flags = DEQUEUE_SAVE | DEQUEUE_MOVE;
const struct sched_class *old_class = p->sched_class;
const struct sched_class *new_class =
__setscheduler_class(p->policy, p->prio);
- struct sched_enq_and_set_ctx ctx;
if (!tryget_task_struct(p))
continue;
- if (old_class != new_class && p->se.sched_delayed)
- dequeue_task(task_rq(p), p, DEQUEUE_SLEEP | DEQUEUE_DELAYED);
-
- sched_deq_and_put_task(p, DEQUEUE_SAVE | DEQUEUE_MOVE, &ctx);
+ if (old_class != new_class)
+ queue_flags |= DEQUEUE_CLASS;
- p->scx.slice = SCX_SLICE_DFL;
- p->sched_class = new_class;
- check_class_changing(task_rq(p), p, old_class);
-
- sched_enq_and_set_task(&ctx);
+ scoped_guard (sched_change, p, queue_flags) {
+ p->scx.slice = SCX_SLICE_DFL;
+ p->sched_class = new_class;
+ }
- check_class_changed(task_rq(p), p, old_class, p->prio);
put_task_struct(p);
}
scx_task_iter_stop(&sti);
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 5b752324270b..769d7b7990df 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -554,7 +554,7 @@ static inline bool entity_before(const struct sched_entity *a,
static inline s64 entity_key(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
- return (s64)(se->vruntime - cfs_rq->min_vruntime);
+ return (s64)(se->vruntime - cfs_rq->zero_vruntime);
}
#define __node_2_se(node) \
@@ -606,13 +606,13 @@ static inline s64 entity_key(struct cfs_rq *cfs_rq, struct sched_entity *se)
*
* Which we track using:
*
- * v0 := cfs_rq->min_vruntime
+ * v0 := cfs_rq->zero_vruntime
* \Sum (v_i - v0) * w_i := cfs_rq->avg_vruntime
* \Sum w_i := cfs_rq->avg_load
*
- * Since min_vruntime is a monotonic increasing variable that closely tracks
- * the per-task service, these deltas: (v_i - v), will be in the order of the
- * maximal (virtual) lag induced in the system due to quantisation.
+ * Since zero_vruntime closely tracks the per-task service, these
+ * deltas: (v_i - v), will be in the order of the maximal (virtual) lag
+ * induced in the system due to quantisation.
*
* Also, we use scale_load_down() to reduce the size.
*
@@ -671,7 +671,7 @@ u64 avg_vruntime(struct cfs_rq *cfs_rq)
avg = div_s64(avg, load);
}
- return cfs_rq->min_vruntime + avg;
+ return cfs_rq->zero_vruntime + avg;
}
/*
@@ -732,7 +732,7 @@ static int vruntime_eligible(struct cfs_rq *cfs_rq, u64 vruntime)
load += weight;
}
- return avg >= (s64)(vruntime - cfs_rq->min_vruntime) * load;
+ return avg >= (s64)(vruntime - cfs_rq->zero_vruntime) * load;
}
int entity_eligible(struct cfs_rq *cfs_rq, struct sched_entity *se)
@@ -740,42 +740,14 @@ int entity_eligible(struct cfs_rq *cfs_rq, struct sched_entity *se)
return vruntime_eligible(cfs_rq, se->vruntime);
}
-static u64 __update_min_vruntime(struct cfs_rq *cfs_rq, u64 vruntime)
+static void update_zero_vruntime(struct cfs_rq *cfs_rq)
{
- u64 min_vruntime = cfs_rq->min_vruntime;
- /*
- * open coded max_vruntime() to allow updating avg_vruntime
- */
- s64 delta = (s64)(vruntime - min_vruntime);
- if (delta > 0) {
- avg_vruntime_update(cfs_rq, delta);
- min_vruntime = vruntime;
- }
- return min_vruntime;
-}
+ u64 vruntime = avg_vruntime(cfs_rq);
+ s64 delta = (s64)(vruntime - cfs_rq->zero_vruntime);
-static void update_min_vruntime(struct cfs_rq *cfs_rq)
-{
- struct sched_entity *se = __pick_root_entity(cfs_rq);
- struct sched_entity *curr = cfs_rq->curr;
- u64 vruntime = cfs_rq->min_vruntime;
-
- if (curr) {
- if (curr->on_rq)
- vruntime = curr->vruntime;
- else
- curr = NULL;
- }
-
- if (se) {
- if (!curr)
- vruntime = se->min_vruntime;
- else
- vruntime = min_vruntime(vruntime, se->min_vruntime);
- }
+ avg_vruntime_update(cfs_rq, delta);
- /* ensure we never gain time by being placed backwards. */
- cfs_rq->min_vruntime = __update_min_vruntime(cfs_rq, vruntime);
+ cfs_rq->zero_vruntime = vruntime;
}
static inline u64 cfs_rq_min_slice(struct cfs_rq *cfs_rq)
@@ -848,6 +820,7 @@ RB_DECLARE_CALLBACKS(static, min_vruntime_cb, struct sched_entity,
static void __enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
avg_vruntime_add(cfs_rq, se);
+ update_zero_vruntime(cfs_rq);
se->min_vruntime = se->vruntime;
se->min_slice = se->slice;
rb_add_augmented_cached(&se->run_node, &cfs_rq->tasks_timeline,
@@ -859,6 +832,7 @@ static void __dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
rb_erase_augmented_cached(&se->run_node, &cfs_rq->tasks_timeline,
&min_vruntime_cb);
avg_vruntime_sub(cfs_rq, se);
+ update_zero_vruntime(cfs_rq);
}
struct sched_entity *__pick_root_entity(struct cfs_rq *cfs_rq)
@@ -955,6 +929,16 @@ static struct sched_entity *__pick_eevdf(struct cfs_rq *cfs_rq, bool protect)
if (cfs_rq->nr_queued == 1)
return curr && curr->on_rq ? curr : se;
+ /*
+ * Picking the ->next buddy will affect latency but not fairness.
+ */
+ if (sched_feat(PICK_BUDDY) &&
+ cfs_rq->next && entity_eligible(cfs_rq, cfs_rq->next)) {
+ /* ->next will never be delayed */
+ WARN_ON_ONCE(cfs_rq->next->sched_delayed);
+ return cfs_rq->next;
+ }
+
if (curr && (!curr->on_rq || !entity_eligible(cfs_rq, curr)))
curr = NULL;
@@ -1193,6 +1177,8 @@ static s64 update_se(struct rq *rq, struct sched_entity *se)
return delta_exec;
}
+static void set_next_buddy(struct sched_entity *se);
+
/*
* Used by other classes to account runtime.
*/
@@ -1226,7 +1212,6 @@ static void update_curr(struct cfs_rq *cfs_rq)
curr->vruntime += calc_delta_fair(delta_exec, curr);
resched = update_deadline(cfs_rq, curr);
- update_min_vruntime(cfs_rq);
if (entity_is_task(curr)) {
/*
@@ -1239,8 +1224,7 @@ static void update_curr(struct cfs_rq *cfs_rq)
* against fair_server such that it can account for this time
* and possibly avoid running this period.
*/
- if (dl_server_active(&rq->fair_server))
- dl_server_update(&rq->fair_server, delta_exec);
+ dl_server_update(&rq->fair_server, delta_exec);
}
account_cfs_rq_runtime(cfs_rq, delta_exec);
@@ -3808,15 +3792,6 @@ static void reweight_entity(struct cfs_rq *cfs_rq, struct sched_entity *se,
if (!curr)
__enqueue_entity(cfs_rq, se);
cfs_rq->nr_queued++;
-
- /*
- * The entity's vruntime has been adjusted, so let's check
- * whether the rq-wide min_vruntime needs updated too. Since
- * the calculations above require stable min_vruntime rather
- * than up-to-date one, we do the update at the end of the
- * reweight process.
- */
- update_min_vruntime(cfs_rq);
}
}
@@ -5429,15 +5404,6 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
update_cfs_group(se);
- /*
- * Now advance min_vruntime if @se was the entity holding it back,
- * except when: DEQUEUE_SAVE && !DEQUEUE_MOVE, in this case we'll be
- * put back on, and if we advance min_vruntime, we'll be placed back
- * further than we started -- i.e. we'll be penalized.
- */
- if ((flags & (DEQUEUE_SAVE | DEQUEUE_MOVE)) != DEQUEUE_SAVE)
- update_min_vruntime(cfs_rq);
-
if (flags & DEQUEUE_DELAYED)
finish_delayed_dequeue_entity(se);
@@ -5512,16 +5478,6 @@ pick_next_entity(struct rq *rq, struct cfs_rq *cfs_rq)
{
struct sched_entity *se;
- /*
- * Picking the ->next buddy will affect latency but not fairness.
- */
- if (sched_feat(PICK_BUDDY) &&
- cfs_rq->next && entity_eligible(cfs_rq, cfs_rq->next)) {
- /* ->next will never be delayed */
- WARN_ON_ONCE(cfs_rq->next->sched_delayed);
- return cfs_rq->next;
- }
-
se = pick_eevdf(cfs_rq);
if (se->sched_delayed) {
dequeue_entities(rq, se, DEQUEUE_SLEEP | DEQUEUE_DELAYED);
@@ -7003,12 +6959,8 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
h_nr_idle = 1;
}
- if (!rq_h_nr_queued && rq->cfs.h_nr_queued) {
- /* Account for idle runtime */
- if (!rq->nr_running)
- dl_server_update_idle_time(rq, rq->curr);
+ if (!rq_h_nr_queued && rq->cfs.h_nr_queued)
dl_server_start(&rq->fair_server);
- }
/* At this point se is NULL and we are at root level*/
add_nr_running(rq, 1);
@@ -7035,8 +6987,6 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
hrtick_update(rq);
}
-static void set_next_buddy(struct sched_entity *se);
-
/*
* Basically dequeue_task_fair(), except it can deal with dequeue_entity()
* failing half-way through and resume the dequeue later.
@@ -8712,15 +8662,6 @@ static void set_cpus_allowed_fair(struct task_struct *p, struct affinity_context
set_task_max_allowed_capacity(p);
}
-static int
-balance_fair(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
-{
- if (sched_fair_runnable(rq))
- return 1;
-
- return sched_balance_newidle(rq, rf) != 0;
-}
-
static void set_next_buddy(struct sched_entity *se)
{
for_each_sched_entity(se) {
@@ -8732,16 +8673,81 @@ static void set_next_buddy(struct sched_entity *se)
}
}
+enum preempt_wakeup_action {
+ PREEMPT_WAKEUP_NONE, /* No preemption. */
+ PREEMPT_WAKEUP_SHORT, /* Ignore slice protection. */
+ PREEMPT_WAKEUP_PICK, /* Let __pick_eevdf() decide. */
+ PREEMPT_WAKEUP_RESCHED, /* Force reschedule. */
+};
+
+static inline bool
+set_preempt_buddy(struct cfs_rq *cfs_rq, int wake_flags,
+ struct sched_entity *pse, struct sched_entity *se)
+{
+ /*
+ * Keep existing buddy if the deadline is sooner than pse.
+ * The older buddy may be cache cold and completely unrelated
+ * to the current wakeup but that is unpredictable where as
+ * obeying the deadline is more in line with EEVDF objectives.
+ */
+ if (cfs_rq->next && entity_before(cfs_rq->next, pse))
+ return false;
+
+ set_next_buddy(pse);
+ return true;
+}
+
+/*
+ * WF_SYNC|WF_TTWU indicates the waker expects to sleep but it is not
+ * strictly enforced because the hint is either misunderstood or
+ * multiple tasks must be woken up.
+ */
+static inline enum preempt_wakeup_action
+preempt_sync(struct rq *rq, int wake_flags,
+ struct sched_entity *pse, struct sched_entity *se)
+{
+ u64 threshold, delta;
+
+ /*
+ * WF_SYNC without WF_TTWU is not expected so warn if it happens even
+ * though it is likely harmless.
+ */
+ WARN_ON_ONCE(!(wake_flags & WF_TTWU));
+
+ threshold = sysctl_sched_migration_cost;
+ delta = rq_clock_task(rq) - se->exec_start;
+ if ((s64)delta < 0)
+ delta = 0;
+
+ /*
+ * WF_RQ_SELECTED implies the tasks are stacking on a CPU when they
+ * could run on other CPUs. Reduce the threshold before preemption is
+ * allowed to an arbitrary lower value as it is more likely (but not
+ * guaranteed) the waker requires the wakee to finish.
+ */
+ if (wake_flags & WF_RQ_SELECTED)
+ threshold >>= 2;
+
+ /*
+ * As WF_SYNC is not strictly obeyed, allow some runtime for batch
+ * wakeups to be issued.
+ */
+ if (entity_before(pse, se) && delta >= threshold)
+ return PREEMPT_WAKEUP_RESCHED;
+
+ return PREEMPT_WAKEUP_NONE;
+}
+
/*
* Preempt the current task with a newly woken task if needed:
*/
static void check_preempt_wakeup_fair(struct rq *rq, struct task_struct *p, int wake_flags)
{
+ enum preempt_wakeup_action preempt_action = PREEMPT_WAKEUP_PICK;
struct task_struct *donor = rq->donor;
struct sched_entity *se = &donor->se, *pse = &p->se;
struct cfs_rq *cfs_rq = task_cfs_rq(donor);
int cse_is_idle, pse_is_idle;
- bool do_preempt_short = false;
if (unlikely(se == pse))
return;
@@ -8755,10 +8761,6 @@ static void check_preempt_wakeup_fair(struct rq *rq, struct task_struct *p, int
if (task_is_throttled(p))
return;
- if (sched_feat(NEXT_BUDDY) && !(wake_flags & WF_FORK) && !pse->sched_delayed) {
- set_next_buddy(pse);
- }
-
/*
* We can come here with TIF_NEED_RESCHED already set from new task
* wake up path.
@@ -8790,7 +8792,7 @@ static void check_preempt_wakeup_fair(struct rq *rq, struct task_struct *p, int
* When non-idle entity preempt an idle entity,
* don't give idle entity slice protection.
*/
- do_preempt_short = true;
+ preempt_action = PREEMPT_WAKEUP_SHORT;
goto preempt;
}
@@ -8809,27 +8811,74 @@ static void check_preempt_wakeup_fair(struct rq *rq, struct task_struct *p, int
* If @p has a shorter slice than current and @p is eligible, override
* current's slice protection in order to allow preemption.
*/
- do_preempt_short = sched_feat(PREEMPT_SHORT) && (pse->slice < se->slice);
+ if (sched_feat(PREEMPT_SHORT) && (pse->slice < se->slice)) {
+ preempt_action = PREEMPT_WAKEUP_SHORT;
+ goto pick;
+ }
/*
+ * Ignore wakee preemption on WF_FORK as it is less likely that
+ * there is shared data as exec often follow fork. Do not
+ * preempt for tasks that are sched_delayed as it would violate
+ * EEVDF to forcibly queue an ineligible task.
+ */
+ if ((wake_flags & WF_FORK) || pse->sched_delayed)
+ return;
+
+ /*
+ * If @p potentially is completing work required by current then
+ * consider preemption.
+ *
+ * Reschedule if waker is no longer eligible. */
+ if (in_task() && !entity_eligible(cfs_rq, se)) {
+ preempt_action = PREEMPT_WAKEUP_RESCHED;
+ goto preempt;
+ }
+
+ /* Prefer picking wakee soon if appropriate. */
+ if (sched_feat(NEXT_BUDDY) &&
+ set_preempt_buddy(cfs_rq, wake_flags, pse, se)) {
+
+ /*
+ * Decide whether to obey WF_SYNC hint for a new buddy. Old
+ * buddies are ignored as they may not be relevant to the
+ * waker and less likely to be cache hot.
+ */
+ if (wake_flags & WF_SYNC)
+ preempt_action = preempt_sync(rq, wake_flags, pse, se);
+ }
+
+ switch (preempt_action) {
+ case PREEMPT_WAKEUP_NONE:
+ return;
+ case PREEMPT_WAKEUP_RESCHED:
+ goto preempt;
+ case PREEMPT_WAKEUP_SHORT:
+ fallthrough;
+ case PREEMPT_WAKEUP_PICK:
+ break;
+ }
+
+pick:
+ /*
* If @p has become the most eligible task, force preemption.
*/
- if (__pick_eevdf(cfs_rq, !do_preempt_short) == pse)
+ if (__pick_eevdf(cfs_rq, preempt_action != PREEMPT_WAKEUP_SHORT) == pse)
goto preempt;
- if (sched_feat(RUN_TO_PARITY) && do_preempt_short)
+ if (sched_feat(RUN_TO_PARITY))
update_protect_slice(cfs_rq, se);
return;
preempt:
- if (do_preempt_short)
+ if (preempt_action == PREEMPT_WAKEUP_SHORT)
cancel_protect_slice(se);
resched_curr_lazy(rq);
}
-static struct task_struct *pick_task_fair(struct rq *rq)
+static struct task_struct *pick_task_fair(struct rq *rq, struct rq_flags *rf)
{
struct sched_entity *se;
struct cfs_rq *cfs_rq;
@@ -8873,7 +8922,7 @@ pick_next_task_fair(struct rq *rq, struct task_struct *prev, struct rq_flags *rf
int new_tasks;
again:
- p = pick_task_fair(rq);
+ p = pick_task_fair(rq, rf);
if (!p)
goto idle;
se = &p->se;
@@ -8952,14 +9001,10 @@ idle:
return NULL;
}
-static struct task_struct *__pick_next_task_fair(struct rq *rq, struct task_struct *prev)
+static struct task_struct *
+fair_server_pick_task(struct sched_dl_entity *dl_se, struct rq_flags *rf)
{
- return pick_next_task_fair(rq, prev, NULL);
-}
-
-static struct task_struct *fair_server_pick_task(struct sched_dl_entity *dl_se)
-{
- return pick_task_fair(dl_se->rq);
+ return pick_task_fair(dl_se->rq, rf);
}
void fair_server_init(struct rq *rq)
@@ -8990,7 +9035,7 @@ static void put_prev_task_fair(struct rq *rq, struct task_struct *prev, struct t
*/
static void yield_task_fair(struct rq *rq)
{
- struct task_struct *curr = rq->curr;
+ struct task_struct *curr = rq->donor;
struct cfs_rq *cfs_rq = task_cfs_rq(curr);
struct sched_entity *se = &curr->se;
@@ -9014,7 +9059,18 @@ static void yield_task_fair(struct rq *rq)
*/
rq_clock_skip_update(rq);
- se->deadline += calc_delta_fair(se->slice, se);
+ /*
+ * Forfeit the remaining vruntime, only if the entity is eligible. This
+ * condition is necessary because in core scheduling we prefer to run
+ * ineligible tasks rather than force idling. If this happens we may
+ * end up in a loop where the core scheduler picks the yielding task,
+ * which yields immediately again; without the condition the vruntime
+ * ends up quickly running away.
+ */
+ if (entity_eligible(cfs_rq, se)) {
+ se->vruntime = se->deadline;
+ se->deadline += calc_delta_fair(se->slice, se);
+ }
}
static bool yield_to_task_fair(struct rq *rq, struct task_struct *p)
@@ -10678,7 +10734,7 @@ static inline void update_sg_wakeup_stats(struct sched_domain *sd,
if (sd->flags & SD_ASYM_CPUCAPACITY)
sgs->group_misfit_task_load = 1;
- for_each_cpu(i, sched_group_span(group)) {
+ for_each_cpu_and(i, sched_group_span(group), p->cpus_ptr) {
struct rq *rq = cpu_rq(i);
unsigned int local;
@@ -11730,6 +11786,21 @@ static void update_lb_imbalance_stat(struct lb_env *env, struct sched_domain *sd
}
/*
+ * This flag serializes load-balancing passes over large domains
+ * (above the NODE topology level) - only one load-balancing instance
+ * may run at a time, to reduce overhead on very large systems with
+ * lots of CPUs and large NUMA distances.
+ *
+ * - Note that load-balancing passes triggered while another one
+ * is executing are skipped and not re-tried.
+ *
+ * - Also note that this does not serialize rebalance_domains()
+ * execution, as non-SD_SERIALIZE domains will still be
+ * load-balanced in parallel.
+ */
+static atomic_t sched_balance_running = ATOMIC_INIT(0);
+
+/*
* Check this_cpu to ensure it is balanced within domain. Attempt to move
* tasks if there is an imbalance.
*/
@@ -11754,6 +11825,7 @@ static int sched_balance_rq(int this_cpu, struct rq *this_rq,
.fbq_type = all,
.tasks = LIST_HEAD_INIT(env.tasks),
};
+ bool need_unlock = false;
cpumask_and(cpus, sched_domain_span(sd), cpu_active_mask);
@@ -11765,6 +11837,14 @@ redo:
goto out_balanced;
}
+ if (!need_unlock && (sd->flags & SD_SERIALIZE)) {
+ int zero = 0;
+ if (!atomic_try_cmpxchg_acquire(&sched_balance_running, &zero, 1))
+ goto out_balanced;
+
+ need_unlock = true;
+ }
+
group = sched_balance_find_src_group(&env);
if (!group) {
schedstat_inc(sd->lb_nobusyg[idle]);
@@ -12005,6 +12085,9 @@ out_one_pinned:
sd->balance_interval < sd->max_interval)
sd->balance_interval *= 2;
out:
+ if (need_unlock)
+ atomic_set_release(&sched_balance_running, 0);
+
return ld_moved;
}
@@ -12130,21 +12213,6 @@ out_unlock:
}
/*
- * This flag serializes load-balancing passes over large domains
- * (above the NODE topology level) - only one load-balancing instance
- * may run at a time, to reduce overhead on very large systems with
- * lots of CPUs and large NUMA distances.
- *
- * - Note that load-balancing passes triggered while another one
- * is executing are skipped and not re-tried.
- *
- * - Also note that this does not serialize rebalance_domains()
- * execution, as non-SD_SERIALIZE domains will still be
- * load-balanced in parallel.
- */
-static atomic_t sched_balance_running = ATOMIC_INIT(0);
-
-/*
* Scale the max sched_balance_rq interval with the number of CPUs in the system.
* This trades load-balance latency on larger machines for less cross talk.
*/
@@ -12153,30 +12221,43 @@ void update_max_interval(void)
max_load_balance_interval = HZ*num_online_cpus()/10;
}
-static inline bool update_newidle_cost(struct sched_domain *sd, u64 cost)
+static inline void update_newidle_stats(struct sched_domain *sd, unsigned int success)
{
+ sd->newidle_call++;
+ sd->newidle_success += success;
+
+ if (sd->newidle_call >= 1024) {
+ sd->newidle_ratio = sd->newidle_success;
+ sd->newidle_call /= 2;
+ sd->newidle_success /= 2;
+ }
+}
+
+static inline bool
+update_newidle_cost(struct sched_domain *sd, u64 cost, unsigned int success)
+{
+ unsigned long next_decay = sd->last_decay_max_lb_cost + HZ;
+ unsigned long now = jiffies;
+
+ if (cost)
+ update_newidle_stats(sd, success);
+
if (cost > sd->max_newidle_lb_cost) {
/*
* Track max cost of a domain to make sure to not delay the
* next wakeup on the CPU.
- *
- * sched_balance_newidle() bumps the cost whenever newidle
- * balance fails, and we don't want things to grow out of
- * control. Use the sysctl_sched_migration_cost as the upper
- * limit, plus a litle extra to avoid off by ones.
*/
- sd->max_newidle_lb_cost =
- min(cost, sysctl_sched_migration_cost + 200);
- sd->last_decay_max_lb_cost = jiffies;
- } else if (time_after(jiffies, sd->last_decay_max_lb_cost + HZ)) {
+ sd->max_newidle_lb_cost = cost;
+ sd->last_decay_max_lb_cost = now;
+
+ } else if (time_after(now, next_decay)) {
/*
* Decay the newidle max times by ~1% per second to ensure that
* it is not outdated and the current max cost is actually
* shorter.
*/
sd->max_newidle_lb_cost = (sd->max_newidle_lb_cost * 253) / 256;
- sd->last_decay_max_lb_cost = jiffies;
-
+ sd->last_decay_max_lb_cost = now;
return true;
}
@@ -12199,7 +12280,7 @@ static void sched_balance_domains(struct rq *rq, enum cpu_idle_type idle)
/* Earliest time when we have to do rebalance again */
unsigned long next_balance = jiffies + 60*HZ;
int update_next_balance = 0;
- int need_serialize, need_decay = 0;
+ int need_decay = 0;
u64 max_cost = 0;
rcu_read_lock();
@@ -12208,7 +12289,7 @@ static void sched_balance_domains(struct rq *rq, enum cpu_idle_type idle)
* Decay the newidle max times here because this is a regular
* visit to all the domains.
*/
- need_decay = update_newidle_cost(sd, 0);
+ need_decay = update_newidle_cost(sd, 0, 0);
max_cost += sd->max_newidle_lb_cost;
/*
@@ -12223,13 +12304,6 @@ static void sched_balance_domains(struct rq *rq, enum cpu_idle_type idle)
}
interval = get_sd_balance_interval(sd, busy);
-
- need_serialize = sd->flags & SD_SERIALIZE;
- if (need_serialize) {
- if (atomic_cmpxchg_acquire(&sched_balance_running, 0, 1))
- goto out;
- }
-
if (time_after_eq(jiffies, sd->last_balance + interval)) {
if (sched_balance_rq(cpu, rq, sd, idle, &continue_balancing)) {
/*
@@ -12243,9 +12317,6 @@ static void sched_balance_domains(struct rq *rq, enum cpu_idle_type idle)
sd->last_balance = jiffies;
interval = get_sd_balance_interval(sd, busy);
}
- if (need_serialize)
- atomic_set_release(&sched_balance_running, 0);
-out:
if (time_after(next_balance, sd->last_balance + interval)) {
next_balance = sd->last_balance + interval;
update_next_balance = 1;
@@ -12824,18 +12895,21 @@ static int sched_balance_newidle(struct rq *this_rq, struct rq_flags *rf)
rcu_read_lock();
sd = rcu_dereference_check_sched_domain(this_rq->sd);
+ if (!sd) {
+ rcu_read_unlock();
+ goto out;
+ }
if (!get_rd_overloaded(this_rq->rd) ||
- (sd && this_rq->avg_idle < sd->max_newidle_lb_cost)) {
+ this_rq->avg_idle < sd->max_newidle_lb_cost) {
- if (sd)
- update_next_balance(sd, &next_balance);
+ update_next_balance(sd, &next_balance);
rcu_read_unlock();
-
goto out;
}
rcu_read_unlock();
+ rq_modified_clear(this_rq);
raw_spin_rq_unlock(this_rq);
t0 = sched_clock_cpu(this_cpu);
@@ -12851,6 +12925,22 @@ static int sched_balance_newidle(struct rq *this_rq, struct rq_flags *rf)
break;
if (sd->flags & SD_BALANCE_NEWIDLE) {
+ unsigned int weight = 1;
+
+ if (sched_feat(NI_RANDOM)) {
+ /*
+ * Throw a 1k sided dice; and only run
+ * newidle_balance according to the success
+ * rate.
+ */
+ u32 d1k = sched_rng() % 1024;
+ weight = 1 + sd->newidle_ratio;
+ if (d1k > weight) {
+ update_newidle_stats(sd, 0);
+ continue;
+ }
+ weight = (1024 + weight/2) / weight;
+ }
pulled_task = sched_balance_rq(this_cpu, this_rq,
sd, CPU_NEWLY_IDLE,
@@ -12862,13 +12952,10 @@ static int sched_balance_newidle(struct rq *this_rq, struct rq_flags *rf)
t0 = t1;
/*
- * Failing newidle means it is not effective;
- * bump the cost so we end up doing less of it.
+ * Track max cost of a domain to make sure to not delay the
+ * next wakeup on the CPU.
*/
- if (!pulled_task)
- domain_cost = (3 * sd->max_newidle_lb_cost) / 2;
-
- update_newidle_cost(sd, domain_cost);
+ update_newidle_cost(sd, domain_cost, weight * !!pulled_task);
}
/*
@@ -12893,8 +12980,8 @@ static int sched_balance_newidle(struct rq *this_rq, struct rq_flags *rf)
if (this_rq->cfs.h_nr_queued && !pulled_task)
pulled_task = 1;
- /* Is there a task of a high priority class? */
- if (this_rq->nr_running != this_rq->cfs.h_nr_queued)
+ /* If a higher prio class was modified, restart the pick */
+ if (rq_modified_above(this_rq, &fair_sched_class))
pulled_task = -1;
out:
@@ -13012,7 +13099,170 @@ static inline void task_tick_core(struct rq *rq, struct task_struct *curr)
}
/*
- * se_fi_update - Update the cfs_rq->min_vruntime_fi in a CFS hierarchy if needed.
+ * Consider any infeasible weight scenario. Take for instance two tasks,
+ * each bound to their respective sibling, one with weight 1 and one with
+ * weight 2. Then the lower weight task will run ahead of the higher weight
+ * task without bound.
+ *
+ * This utterly destroys the concept of a shared time base.
+ *
+ * Remember; all this is about a proportionally fair scheduling, where each
+ * tasks receives:
+ *
+ * w_i
+ * dt_i = ---------- dt (1)
+ * \Sum_j w_j
+ *
+ * which we do by tracking a virtual time, s_i:
+ *
+ * 1
+ * s_i = --- d[t]_i (2)
+ * w_i
+ *
+ * Where d[t] is a delta of discrete time, while dt is an infinitesimal.
+ * The immediate corollary is that the ideal schedule S, where (2) to use
+ * an infinitesimal delta, is:
+ *
+ * 1
+ * S = ---------- dt (3)
+ * \Sum_i w_i
+ *
+ * From which we can define the lag, or deviation from the ideal, as:
+ *
+ * lag(i) = S - s_i (4)
+ *
+ * And since the one and only purpose is to approximate S, we get that:
+ *
+ * \Sum_i w_i lag(i) := 0 (5)
+ *
+ * If this were not so, we no longer converge to S, and we can no longer
+ * claim our scheduler has any of the properties we derive from S. This is
+ * exactly what you did above, you broke it!
+ *
+ *
+ * Let's continue for a while though; to see if there is anything useful to
+ * be learned. We can combine (1)-(3) or (4)-(5) and express S in s_i:
+ *
+ * \Sum_i w_i s_i
+ * S = -------------- (6)
+ * \Sum_i w_i
+ *
+ * Which gives us a way to compute S, given our s_i. Now, if you've read
+ * our code, you know that we do not in fact do this, the reason for this
+ * is two-fold. Firstly, computing S in that way requires a 64bit division
+ * for every time we'd use it (see 12), and secondly, this only describes
+ * the steady-state, it doesn't handle dynamics.
+ *
+ * Anyway, in (6): s_i -> x + (s_i - x), to get:
+ *
+ * \Sum_i w_i (s_i - x)
+ * S - x = -------------------- (7)
+ * \Sum_i w_i
+ *
+ * Which shows that S and s_i transform alike (which makes perfect sense
+ * given that S is basically the (weighted) average of s_i).
+ *
+ * So the thing to remember is that the above is strictly UP. It is
+ * possible to generalize to multiple runqueues -- however it gets really
+ * yuck when you have to add affinity support, as illustrated by our very
+ * first counter-example.
+ *
+ * Luckily I think we can avoid needing a full multi-queue variant for
+ * core-scheduling (or load-balancing). The crucial observation is that we
+ * only actually need this comparison in the presence of forced-idle; only
+ * then do we need to tell if the stalled rq has higher priority over the
+ * other.
+ *
+ * [XXX assumes SMT2; better consider the more general case, I suspect
+ * it'll work out because our comparison is always between 2 rqs and the
+ * answer is only interesting if one of them is forced-idle]
+ *
+ * And (under assumption of SMT2) when there is forced-idle, there is only
+ * a single queue, so everything works like normal.
+ *
+ * Let, for our runqueue 'k':
+ *
+ * T_k = \Sum_i w_i s_i
+ * W_k = \Sum_i w_i ; for all i of k (8)
+ *
+ * Then we can write (6) like:
+ *
+ * T_k
+ * S_k = --- (9)
+ * W_k
+ *
+ * From which immediately follows that:
+ *
+ * T_k + T_l
+ * S_k+l = --------- (10)
+ * W_k + W_l
+ *
+ * On which we can define a combined lag:
+ *
+ * lag_k+l(i) := S_k+l - s_i (11)
+ *
+ * And that gives us the tools to compare tasks across a combined runqueue.
+ *
+ *
+ * Combined this gives the following:
+ *
+ * a) when a runqueue enters force-idle, sync it against it's sibling rq(s)
+ * using (7); this only requires storing single 'time'-stamps.
+ *
+ * b) when comparing tasks between 2 runqueues of which one is forced-idle,
+ * compare the combined lag, per (11).
+ *
+ * Now, of course cgroups (I so hate them) make this more interesting in
+ * that a) seems to suggest we need to iterate all cgroup on a CPU at such
+ * boundaries, but I think we can avoid that. The force-idle is for the
+ * whole CPU, all it's rqs. So we can mark it in the root and lazily
+ * propagate downward on demand.
+ */
+
+/*
+ * So this sync is basically a relative reset of S to 0.
+ *
+ * So with 2 queues, when one goes idle, we drop them both to 0 and one
+ * then increases due to not being idle, and the idle one builds up lag to
+ * get re-elected. So far so simple, right?
+ *
+ * When there's 3, we can have the situation where 2 run and one is idle,
+ * we sync to 0 and let the idle one build up lag to get re-election. Now
+ * suppose another one also drops idle. At this point dropping all to 0
+ * again would destroy the built-up lag from the queue that was already
+ * idle, not good.
+ *
+ * So instead of syncing everything, we can:
+ *
+ * less := !((s64)(s_a - s_b) <= 0)
+ *
+ * (v_a - S_a) - (v_b - S_b) == v_a - v_b - S_a + S_b
+ * == v_a - (v_b - S_a + S_b)
+ *
+ * IOW, we can recast the (lag) comparison to a one-sided difference.
+ * So if then, instead of syncing the whole queue, sync the idle queue
+ * against the active queue with S_a + S_b at the point where we sync.
+ *
+ * (XXX consider the implication of living in a cyclic group: N / 2^n N)
+ *
+ * This gives us means of syncing single queues against the active queue,
+ * and for already idle queues to preserve their build-up lag.
+ *
+ * Of course, then we get the situation where there's 2 active and one
+ * going idle, who do we pick to sync against? Theory would have us sync
+ * against the combined S, but as we've already demonstrated, there is no
+ * such thing in infeasible weight scenarios.
+ *
+ * One thing I've considered; and this is where that core_active rudiment
+ * came from, is having active queues sync up between themselves after
+ * every tick. This limits the observed divergence due to the work
+ * conservancy.
+ *
+ * On top of that, we can improve upon things by employing (10) here.
+ */
+
+/*
+ * se_fi_update - Update the cfs_rq->zero_vruntime_fi in a CFS hierarchy if needed.
*/
static void se_fi_update(const struct sched_entity *se, unsigned int fi_seq,
bool forceidle)
@@ -13026,7 +13276,7 @@ static void se_fi_update(const struct sched_entity *se, unsigned int fi_seq,
cfs_rq->forceidle_seq = fi_seq;
}
- cfs_rq->min_vruntime_fi = cfs_rq->min_vruntime;
+ cfs_rq->zero_vruntime_fi = cfs_rq->zero_vruntime;
}
}
@@ -13079,11 +13329,11 @@ bool cfs_prio_less(const struct task_struct *a, const struct task_struct *b,
/*
* Find delta after normalizing se's vruntime with its cfs_rq's
- * min_vruntime_fi, which would have been updated in prior calls
+ * zero_vruntime_fi, which would have been updated in prior calls
* to se_fi_update().
*/
delta = (s64)(sea->vruntime - seb->vruntime) +
- (s64)(cfs_rqb->min_vruntime_fi - cfs_rqa->min_vruntime_fi);
+ (s64)(cfs_rqb->zero_vruntime_fi - cfs_rqa->zero_vruntime_fi);
return delta > 0;
}
@@ -13145,11 +13395,14 @@ static void task_fork_fair(struct task_struct *p)
* the current task.
*/
static void
-prio_changed_fair(struct rq *rq, struct task_struct *p, int oldprio)
+prio_changed_fair(struct rq *rq, struct task_struct *p, u64 oldprio)
{
if (!task_on_rq_queued(p))
return;
+ if (p->prio == oldprio)
+ return;
+
if (rq->cfs.nr_queued == 1)
return;
@@ -13161,8 +13414,9 @@ prio_changed_fair(struct rq *rq, struct task_struct *p, int oldprio)
if (task_current_donor(rq, p)) {
if (p->prio > oldprio)
resched_curr(rq);
- } else
+ } else {
wakeup_preempt(rq, p, 0);
+ }
}
#ifdef CONFIG_FAIR_GROUP_SCHED
@@ -13246,6 +13500,12 @@ static void attach_task_cfs_rq(struct task_struct *p)
attach_entity_cfs_rq(se);
}
+static void switching_from_fair(struct rq *rq, struct task_struct *p)
+{
+ if (p->se.sched_delayed)
+ dequeue_task(rq, p, DEQUEUE_SLEEP | DEQUEUE_DELAYED | DEQUEUE_NOCLOCK);
+}
+
static void switched_from_fair(struct rq *rq, struct task_struct *p)
{
detach_task_cfs_rq(p);
@@ -13319,7 +13579,7 @@ static void set_next_task_fair(struct rq *rq, struct task_struct *p, bool first)
void init_cfs_rq(struct cfs_rq *cfs_rq)
{
cfs_rq->tasks_timeline = RB_ROOT_CACHED;
- cfs_rq->min_vruntime = (u64)(-(1LL << 20));
+ cfs_rq->zero_vruntime = (u64)(-(1LL << 20));
raw_spin_lock_init(&cfs_rq->removed.lock);
}
@@ -13620,6 +13880,8 @@ static unsigned int get_rr_interval_fair(struct rq *rq, struct task_struct *task
*/
DEFINE_SCHED_CLASS(fair) = {
+ .queue_mask = 2,
+
.enqueue_task = enqueue_task_fair,
.dequeue_task = dequeue_task_fair,
.yield_task = yield_task_fair,
@@ -13628,11 +13890,10 @@ DEFINE_SCHED_CLASS(fair) = {
.wakeup_preempt = check_preempt_wakeup_fair,
.pick_task = pick_task_fair,
- .pick_next_task = __pick_next_task_fair,
+ .pick_next_task = pick_next_task_fair,
.put_prev_task = put_prev_task_fair,
.set_next_task = set_next_task_fair,
- .balance = balance_fair,
.select_task_rq = select_task_rq_fair,
.migrate_task_rq = migrate_task_rq_fair,
@@ -13647,6 +13908,7 @@ DEFINE_SCHED_CLASS(fair) = {
.reweight_task = reweight_task_fair,
.prio_changed = prio_changed_fair,
+ .switching_from = switching_from_fair,
.switched_from = switched_from_fair,
.switched_to = switched_to_fair,
diff --git a/kernel/sched/features.h b/kernel/sched/features.h
index 3c12d9f93331..980d92bab8ab 100644
--- a/kernel/sched/features.h
+++ b/kernel/sched/features.h
@@ -29,7 +29,7 @@ SCHED_FEAT(PREEMPT_SHORT, true)
* wakeup-preemption), since its likely going to consume data we
* touched, increases cache locality.
*/
-SCHED_FEAT(NEXT_BUDDY, false)
+SCHED_FEAT(NEXT_BUDDY, true)
/*
* Allow completely ignoring cfs_rq->next; which can be set from various
@@ -121,3 +121,8 @@ SCHED_FEAT(WA_BIAS, true)
SCHED_FEAT(UTIL_EST, true)
SCHED_FEAT(LATENCY_WARN, false)
+
+/*
+ * Do newidle balancing proportional to its success rate using randomization.
+ */
+SCHED_FEAT(NI_RANDOM, true)
diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c
index c39b089d4f09..1cb7a3d70e65 100644
--- a/kernel/sched/idle.c
+++ b/kernel/sched/idle.c
@@ -452,9 +452,11 @@ static void wakeup_preempt_idle(struct rq *rq, struct task_struct *p, int flags)
resched_curr(rq);
}
+static void update_curr_idle(struct rq *rq);
+
static void put_prev_task_idle(struct rq *rq, struct task_struct *prev, struct task_struct *next)
{
- dl_server_update_idle_time(rq, prev);
+ update_curr_idle(rq);
scx_update_idle(rq, false, true);
}
@@ -466,7 +468,7 @@ static void set_next_task_idle(struct rq *rq, struct task_struct *next, bool fir
next->se.exec_start = rq_clock_task(rq);
}
-struct task_struct *pick_task_idle(struct rq *rq)
+struct task_struct *pick_task_idle(struct rq *rq, struct rq_flags *rf)
{
scx_update_idle(rq, true, false);
return rq->idle;
@@ -496,21 +498,36 @@ dequeue_task_idle(struct rq *rq, struct task_struct *p, int flags)
*/
static void task_tick_idle(struct rq *rq, struct task_struct *curr, int queued)
{
+ update_curr_idle(rq);
}
-static void switched_to_idle(struct rq *rq, struct task_struct *p)
+static void switching_to_idle(struct rq *rq, struct task_struct *p)
{
BUG();
}
static void
-prio_changed_idle(struct rq *rq, struct task_struct *p, int oldprio)
+prio_changed_idle(struct rq *rq, struct task_struct *p, u64 oldprio)
{
+ if (p->prio == oldprio)
+ return;
+
BUG();
}
static void update_curr_idle(struct rq *rq)
{
+ struct sched_entity *se = &rq->idle->se;
+ u64 now = rq_clock_task(rq);
+ s64 delta_exec;
+
+ delta_exec = now - se->exec_start;
+ if (unlikely(delta_exec <= 0))
+ return;
+
+ se->exec_start = now;
+
+ dl_server_update_idle(&rq->fair_server, delta_exec);
}
/*
@@ -518,6 +535,8 @@ static void update_curr_idle(struct rq *rq)
*/
DEFINE_SCHED_CLASS(idle) = {
+ .queue_mask = 0,
+
/* no enqueue/yield_task for idle tasks */
/* dequeue is not valid, we print a debug message there: */
@@ -536,6 +555,6 @@ DEFINE_SCHED_CLASS(idle) = {
.task_tick = task_tick_idle,
.prio_changed = prio_changed_idle,
- .switched_to = switched_to_idle,
+ .switching_to = switching_to_idle,
.update_curr = update_curr_idle,
};
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index 7936d4333731..f1867fe8e5c5 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -1490,7 +1490,7 @@ static void requeue_task_rt(struct rq *rq, struct task_struct *p, int head)
static void yield_task_rt(struct rq *rq)
{
- requeue_task_rt(rq, rq->curr, 0);
+ requeue_task_rt(rq, rq->donor, 0);
}
static int find_lowest_rq(struct task_struct *task);
@@ -1695,7 +1695,7 @@ static struct task_struct *_pick_next_task_rt(struct rq *rq)
return rt_task_of(rt_se);
}
-static struct task_struct *pick_task_rt(struct rq *rq)
+static struct task_struct *pick_task_rt(struct rq *rq, struct rq_flags *rf)
{
struct task_struct *p;
@@ -2437,11 +2437,14 @@ static void switched_to_rt(struct rq *rq, struct task_struct *p)
* us to initiate a push or pull.
*/
static void
-prio_changed_rt(struct rq *rq, struct task_struct *p, int oldprio)
+prio_changed_rt(struct rq *rq, struct task_struct *p, u64 oldprio)
{
if (!task_on_rq_queued(p))
return;
+ if (p->prio == oldprio)
+ return;
+
if (task_current_donor(rq, p)) {
/*
* If our priority decreases while running, we
@@ -2566,6 +2569,8 @@ static int task_is_throttled_rt(struct task_struct *p, int cpu)
DEFINE_SCHED_CLASS(rt) = {
+ .queue_mask = 4,
+
.enqueue_task = enqueue_task_rt,
.dequeue_task = dequeue_task_rt,
.yield_task = yield_task_rt,
@@ -2589,8 +2594,8 @@ DEFINE_SCHED_CLASS(rt) = {
.get_rr_interval = get_rr_interval_rt,
- .prio_changed = prio_changed_rt,
.switched_to = switched_to_rt,
+ .prio_changed = prio_changed_rt,
.update_curr = update_curr_rt,
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index adfb6e3409d7..b419a4d98461 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -5,6 +5,7 @@
#ifndef _KERNEL_SCHED_SCHED_H
#define _KERNEL_SCHED_SCHED_H
+#include <linux/prandom.h>
#include <linux/sched/affinity.h>
#include <linux/sched/autogroup.h>
#include <linux/sched/cpufreq.h>
@@ -20,7 +21,6 @@
#include <linux/sched/task_flags.h>
#include <linux/sched/task.h>
#include <linux/sched/topology.h>
-
#include <linux/atomic.h>
#include <linux/bitmap.h>
#include <linux/bug.h>
@@ -405,6 +405,7 @@ extern s64 dl_scaled_delta_exec(struct rq *rq, struct sched_dl_entity *dl_se, s6
* naturally thottled to once per period, avoiding high context switch
* workloads from spamming the hrtimer program/cancel paths.
*/
+extern void dl_server_update_idle(struct sched_dl_entity *dl_se, s64 delta_exec);
extern void dl_server_update(struct sched_dl_entity *dl_se, s64 delta_exec);
extern void dl_server_start(struct sched_dl_entity *dl_se);
extern void dl_server_stop(struct sched_dl_entity *dl_se);
@@ -412,8 +413,6 @@ extern void dl_server_init(struct sched_dl_entity *dl_se, struct rq *rq,
dl_server_pick_f pick_task);
extern void sched_init_dl_servers(void);
-extern void dl_server_update_idle_time(struct rq *rq,
- struct task_struct *p);
extern void fair_server_init(struct rq *rq);
extern void __dl_server_attach_root(struct sched_dl_entity *dl_se, struct rq *rq);
extern int dl_server_apply_params(struct sched_dl_entity *dl_se,
@@ -682,10 +681,10 @@ struct cfs_rq {
s64 avg_vruntime;
u64 avg_load;
- u64 min_vruntime;
+ u64 zero_vruntime;
#ifdef CONFIG_SCHED_CORE
unsigned int forceidle_seq;
- u64 min_vruntime_fi;
+ u64 zero_vruntime_fi;
#endif
struct rb_root_cached tasks_timeline;
@@ -780,7 +779,6 @@ enum scx_rq_flags {
*/
SCX_RQ_ONLINE = 1 << 0,
SCX_RQ_CAN_STOP_TICK = 1 << 1,
- SCX_RQ_BAL_PENDING = 1 << 2, /* balance hasn't run yet */
SCX_RQ_BAL_KEEP = 1 << 3, /* balance decided to keep current */
SCX_RQ_BYPASSING = 1 << 4,
SCX_RQ_CLK_VALID = 1 << 5, /* RQ clock is fresh and valid */
@@ -1120,6 +1118,8 @@ struct rq {
/* runqueue lock: */
raw_spinlock_t __lock;
+ /* Per class runqueue modification mask; bits in class order. */
+ unsigned int queue_mask;
unsigned int nr_running;
#ifdef CONFIG_NUMA_BALANCING
unsigned int nr_numa_running;
@@ -1349,6 +1349,12 @@ static inline bool is_migration_disabled(struct task_struct *p)
}
DECLARE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues);
+DECLARE_PER_CPU(struct rnd_state, sched_rnd_state);
+
+static inline u32 sched_rng(void)
+{
+ return prandom_u32_state(this_cpu_ptr(&sched_rnd_state));
+}
#define cpu_rq(cpu) (&per_cpu(runqueues, (cpu)))
#define this_rq() this_cpu_ptr(&runqueues)
@@ -1432,6 +1438,9 @@ static inline bool sched_core_cookie_match(struct rq *rq, struct task_struct *p)
if (!sched_core_enabled(rq))
return true;
+ if (rq->core->core_cookie == p->core_cookie)
+ return true;
+
for_each_cpu(cpu, cpu_smt_mask(cpu_of(rq))) {
if (!available_idle_cpu(cpu)) {
idle_core = false;
@@ -1443,7 +1452,7 @@ static inline bool sched_core_cookie_match(struct rq *rq, struct task_struct *p)
* A CPU in an idle core is always the best choice for tasks with
* cookies.
*/
- return idle_core || rq->core->core_cookie == p->core_cookie;
+ return idle_core;
}
static inline bool sched_group_cookie_match(struct rq *rq,
@@ -1827,7 +1836,8 @@ struct rq *task_rq_lock(struct task_struct *p, struct rq_flags *rf)
__acquires(p->pi_lock)
__acquires(rq->lock);
-static inline void __task_rq_unlock(struct rq *rq, struct rq_flags *rf)
+static inline void
+__task_rq_unlock(struct rq *rq, struct task_struct *p, struct rq_flags *rf)
__releases(rq->lock)
{
rq_unpin_lock(rq, rf);
@@ -1839,8 +1849,7 @@ task_rq_unlock(struct rq *rq, struct task_struct *p, struct rq_flags *rf)
__releases(rq->lock)
__releases(p->pi_lock)
{
- rq_unpin_lock(rq, rf);
- raw_spin_rq_unlock(rq);
+ __task_rq_unlock(rq, p, rf);
raw_spin_unlock_irqrestore(&p->pi_lock, rf->flags);
}
@@ -1849,6 +1858,11 @@ DEFINE_LOCK_GUARD_1(task_rq_lock, struct task_struct,
task_rq_unlock(_T->rq, _T->lock, &_T->rf),
struct rq *rq; struct rq_flags rf)
+DEFINE_LOCK_GUARD_1(__task_rq_lock, struct task_struct,
+ _T->rq = __task_rq_lock(_T->lock, &_T->rf),
+ __task_rq_unlock(_T->rq, _T->lock, &_T->rf),
+ struct rq *rq; struct rq_flags rf)
+
static inline void rq_lock_irqsave(struct rq *rq, struct rq_flags *rf)
__acquires(rq->lock)
{
@@ -2342,8 +2356,7 @@ extern const u32 sched_prio_to_wmult[40];
/*
* {de,en}queue flags:
*
- * DEQUEUE_SLEEP - task is no longer runnable
- * ENQUEUE_WAKEUP - task just became runnable
+ * SLEEP/WAKEUP - task is no-longer/just-became runnable
*
* SAVE/RESTORE - an otherwise spurious dequeue/enqueue, done to ensure tasks
* are in a known state which allows modification. Such pairs
@@ -2356,34 +2369,46 @@ extern const u32 sched_prio_to_wmult[40];
*
* MIGRATION - p->on_rq == TASK_ON_RQ_MIGRATING (used for DEADLINE)
*
+ * DELAYED - de/re-queue a sched_delayed task
+ *
+ * CLASS - going to update p->sched_class; makes sched_change call the
+ * various switch methods.
+ *
* ENQUEUE_HEAD - place at front of runqueue (tail if not specified)
* ENQUEUE_REPLENISH - CBS (replenish runtime and postpone deadline)
* ENQUEUE_MIGRATED - the task was migrated during wakeup
* ENQUEUE_RQ_SELECTED - ->select_task_rq() was called
*
+ * XXX SAVE/RESTORE in combination with CLASS doesn't really make sense, but
+ * SCHED_DEADLINE seems to rely on this for now.
*/
-#define DEQUEUE_SLEEP 0x01 /* Matches ENQUEUE_WAKEUP */
-#define DEQUEUE_SAVE 0x02 /* Matches ENQUEUE_RESTORE */
-#define DEQUEUE_MOVE 0x04 /* Matches ENQUEUE_MOVE */
-#define DEQUEUE_NOCLOCK 0x08 /* Matches ENQUEUE_NOCLOCK */
-#define DEQUEUE_SPECIAL 0x10
-#define DEQUEUE_MIGRATING 0x100 /* Matches ENQUEUE_MIGRATING */
-#define DEQUEUE_DELAYED 0x200 /* Matches ENQUEUE_DELAYED */
-#define DEQUEUE_THROTTLE 0x800
-
-#define ENQUEUE_WAKEUP 0x01
-#define ENQUEUE_RESTORE 0x02
-#define ENQUEUE_MOVE 0x04
-#define ENQUEUE_NOCLOCK 0x08
-
-#define ENQUEUE_HEAD 0x10
-#define ENQUEUE_REPLENISH 0x20
-#define ENQUEUE_MIGRATED 0x40
-#define ENQUEUE_INITIAL 0x80
-#define ENQUEUE_MIGRATING 0x100
-#define ENQUEUE_DELAYED 0x200
-#define ENQUEUE_RQ_SELECTED 0x400
+#define DEQUEUE_SLEEP 0x0001 /* Matches ENQUEUE_WAKEUP */
+#define DEQUEUE_SAVE 0x0002 /* Matches ENQUEUE_RESTORE */
+#define DEQUEUE_MOVE 0x0004 /* Matches ENQUEUE_MOVE */
+#define DEQUEUE_NOCLOCK 0x0008 /* Matches ENQUEUE_NOCLOCK */
+
+#define DEQUEUE_MIGRATING 0x0010 /* Matches ENQUEUE_MIGRATING */
+#define DEQUEUE_DELAYED 0x0020 /* Matches ENQUEUE_DELAYED */
+#define DEQUEUE_CLASS 0x0040 /* Matches ENQUEUE_CLASS */
+
+#define DEQUEUE_SPECIAL 0x00010000
+#define DEQUEUE_THROTTLE 0x00020000
+
+#define ENQUEUE_WAKEUP 0x0001
+#define ENQUEUE_RESTORE 0x0002
+#define ENQUEUE_MOVE 0x0004
+#define ENQUEUE_NOCLOCK 0x0008
+
+#define ENQUEUE_MIGRATING 0x0010
+#define ENQUEUE_DELAYED 0x0020
+#define ENQUEUE_CLASS 0x0040
+
+#define ENQUEUE_HEAD 0x00010000
+#define ENQUEUE_REPLENISH 0x00020000
+#define ENQUEUE_MIGRATED 0x00040000
+#define ENQUEUE_INITIAL 0x00080000
+#define ENQUEUE_RQ_SELECTED 0x00100000
#define RETRY_TASK ((void *)-1UL)
@@ -2400,16 +2425,61 @@ struct sched_class {
#ifdef CONFIG_UCLAMP_TASK
int uclamp_enabled;
#endif
+ /*
+ * idle: 0
+ * ext: 1
+ * fair: 2
+ * rt: 4
+ * dl: 8
+ * stop: 16
+ */
+ unsigned int queue_mask;
+ /*
+ * move_queued_task/activate_task/enqueue_task: rq->lock
+ * ttwu_do_activate/activate_task/enqueue_task: rq->lock
+ * wake_up_new_task/activate_task/enqueue_task: task_rq_lock
+ * ttwu_runnable/enqueue_task: task_rq_lock
+ * proxy_task_current: rq->lock
+ * sched_change_end
+ */
void (*enqueue_task) (struct rq *rq, struct task_struct *p, int flags);
+ /*
+ * move_queued_task/deactivate_task/dequeue_task: rq->lock
+ * __schedule/block_task/dequeue_task: rq->lock
+ * proxy_task_current: rq->lock
+ * wait_task_inactive: task_rq_lock
+ * sched_change_begin
+ */
bool (*dequeue_task) (struct rq *rq, struct task_struct *p, int flags);
+
+ /*
+ * do_sched_yield: rq->lock
+ */
void (*yield_task) (struct rq *rq);
+ /*
+ * yield_to: rq->lock (double)
+ */
bool (*yield_to_task)(struct rq *rq, struct task_struct *p);
+ /*
+ * move_queued_task: rq->lock
+ * __migrate_swap_task: rq->lock
+ * ttwu_do_activate: rq->lock
+ * ttwu_runnable: task_rq_lock
+ * wake_up_new_task: task_rq_lock
+ */
void (*wakeup_preempt)(struct rq *rq, struct task_struct *p, int flags);
+ /*
+ * schedule/pick_next_task/prev_balance: rq->lock
+ */
int (*balance)(struct rq *rq, struct task_struct *prev, struct rq_flags *rf);
- struct task_struct *(*pick_task)(struct rq *rq);
+
+ /*
+ * schedule/pick_next_task: rq->lock
+ */
+ struct task_struct *(*pick_task)(struct rq *rq, struct rq_flags *rf);
/*
* Optional! When implemented pick_next_task() should be equivalent to:
*
@@ -2419,55 +2489,123 @@ struct sched_class {
* set_next_task_first(next);
* }
*/
- struct task_struct *(*pick_next_task)(struct rq *rq, struct task_struct *prev);
+ struct task_struct *(*pick_next_task)(struct rq *rq, struct task_struct *prev,
+ struct rq_flags *rf);
+ /*
+ * sched_change:
+ * __schedule: rq->lock
+ */
void (*put_prev_task)(struct rq *rq, struct task_struct *p, struct task_struct *next);
void (*set_next_task)(struct rq *rq, struct task_struct *p, bool first);
+ /*
+ * select_task_rq: p->pi_lock
+ * sched_exec: p->pi_lock
+ */
int (*select_task_rq)(struct task_struct *p, int task_cpu, int flags);
+ /*
+ * set_task_cpu: p->pi_lock || rq->lock (ttwu like)
+ */
void (*migrate_task_rq)(struct task_struct *p, int new_cpu);
+ /*
+ * ttwu_do_activate: rq->lock
+ * wake_up_new_task: task_rq_lock
+ */
void (*task_woken)(struct rq *this_rq, struct task_struct *task);
+ /*
+ * do_set_cpus_allowed: task_rq_lock + sched_change
+ */
void (*set_cpus_allowed)(struct task_struct *p, struct affinity_context *ctx);
+ /*
+ * sched_set_rq_{on,off}line: rq->lock
+ */
void (*rq_online)(struct rq *rq);
void (*rq_offline)(struct rq *rq);
+ /*
+ * push_cpu_stop: p->pi_lock && rq->lock
+ */
struct rq *(*find_lock_rq)(struct task_struct *p, struct rq *rq);
+ /*
+ * hrtick: rq->lock
+ * sched_tick: rq->lock
+ * sched_tick_remote: rq->lock
+ */
void (*task_tick)(struct rq *rq, struct task_struct *p, int queued);
+ /*
+ * sched_cgroup_fork: p->pi_lock
+ */
void (*task_fork)(struct task_struct *p);
+ /*
+ * finish_task_switch: no locks
+ */
void (*task_dead)(struct task_struct *p);
/*
- * The switched_from() call is allowed to drop rq->lock, therefore we
- * cannot assume the switched_from/switched_to pair is serialized by
- * rq->lock. They are however serialized by p->pi_lock.
+ * sched_change
+ */
+ void (*switching_from)(struct rq *this_rq, struct task_struct *task);
+ void (*switched_from) (struct rq *this_rq, struct task_struct *task);
+ void (*switching_to) (struct rq *this_rq, struct task_struct *task);
+ void (*switched_to) (struct rq *this_rq, struct task_struct *task);
+ u64 (*get_prio) (struct rq *this_rq, struct task_struct *task);
+ void (*prio_changed) (struct rq *this_rq, struct task_struct *task,
+ u64 oldprio);
+
+ /*
+ * set_load_weight: task_rq_lock + sched_change
+ * __setscheduler_parms: task_rq_lock + sched_change
*/
- void (*switching_to) (struct rq *this_rq, struct task_struct *task);
- void (*switched_from)(struct rq *this_rq, struct task_struct *task);
- void (*switched_to) (struct rq *this_rq, struct task_struct *task);
void (*reweight_task)(struct rq *this_rq, struct task_struct *task,
const struct load_weight *lw);
- void (*prio_changed) (struct rq *this_rq, struct task_struct *task,
- int oldprio);
+ /*
+ * sched_rr_get_interval: task_rq_lock
+ */
unsigned int (*get_rr_interval)(struct rq *rq,
struct task_struct *task);
+ /*
+ * task_sched_runtime: task_rq_lock
+ */
void (*update_curr)(struct rq *rq);
#ifdef CONFIG_FAIR_GROUP_SCHED
+ /*
+ * sched_change_group: task_rq_lock + sched_change
+ */
void (*task_change_group)(struct task_struct *p);
#endif
#ifdef CONFIG_SCHED_CORE
+ /*
+ * pick_next_task: rq->lock
+ * try_steal_cookie: rq->lock (double)
+ */
int (*task_is_throttled)(struct task_struct *p, int cpu);
#endif
};
+/*
+ * Does not nest; only used around sched_class::pick_task() rq-lock-breaks.
+ */
+static inline void rq_modified_clear(struct rq *rq)
+{
+ rq->queue_mask = 0;
+}
+
+static inline bool rq_modified_above(struct rq *rq, const struct sched_class * class)
+{
+ unsigned int mask = class->queue_mask;
+ return rq->queue_mask & ~((mask << 1) - 1);
+}
+
static inline void put_prev_task(struct rq *rq, struct task_struct *prev)
{
WARN_ON_ONCE(rq->donor != prev);
@@ -2579,8 +2717,9 @@ static inline bool sched_fair_runnable(struct rq *rq)
return rq->cfs.nr_queued > 0;
}
-extern struct task_struct *pick_next_task_fair(struct rq *rq, struct task_struct *prev, struct rq_flags *rf);
-extern struct task_struct *pick_task_idle(struct rq *rq);
+extern struct task_struct *pick_next_task_fair(struct rq *rq, struct task_struct *prev,
+ struct rq_flags *rf);
+extern struct task_struct *pick_task_idle(struct rq *rq, struct rq_flags *rf);
#define SCA_CHECK 0x01
#define SCA_MIGRATE_DISABLE 0x02
@@ -2610,7 +2749,7 @@ static inline bool task_allowed_on_cpu(struct task_struct *p, int cpu)
static inline cpumask_t *alloc_user_cpus_ptr(int node)
{
/*
- * See do_set_cpus_allowed() above for the rcu_head usage.
+ * See set_cpus_allowed_force() above for the rcu_head usage.
*/
int size = max_t(int, cpumask_size(), sizeof(struct rcu_head));
@@ -3875,32 +4014,42 @@ extern void set_load_weight(struct task_struct *p, bool update_load);
extern void enqueue_task(struct rq *rq, struct task_struct *p, int flags);
extern bool dequeue_task(struct rq *rq, struct task_struct *p, int flags);
-extern void check_class_changing(struct rq *rq, struct task_struct *p,
- const struct sched_class *prev_class);
-extern void check_class_changed(struct rq *rq, struct task_struct *p,
- const struct sched_class *prev_class,
- int oldprio);
-
extern struct balance_callback *splice_balance_callbacks(struct rq *rq);
extern void balance_callbacks(struct rq *rq, struct balance_callback *head);
-#ifdef CONFIG_SCHED_CLASS_EXT
/*
- * Used by SCX in the enable/disable paths to move tasks between sched_classes
- * and establish invariants.
+ * The 'sched_change' pattern is the safe, easy and slow way of changing a
+ * task's scheduling properties. It dequeues a task, such that the scheduler
+ * is fully unaware of it; at which point its properties can be modified;
+ * after which it is enqueued again.
+ *
+ * Typically this must be called while holding task_rq_lock, since most/all
+ * properties are serialized under those locks. There is currently one
+ * exception to this rule in sched/ext which only holds rq->lock.
+ */
+
+/*
+ * This structure is a temporary, used to preserve/convey the queueing state
+ * of the task between sched_change_begin() and sched_change_end(). Ensuring
+ * the task's queueing state is idempotent across the operation.
*/
-struct sched_enq_and_set_ctx {
+struct sched_change_ctx {
+ u64 prio;
struct task_struct *p;
- int queue_flags;
+ int flags;
bool queued;
bool running;
};
-void sched_deq_and_put_task(struct task_struct *p, int queue_flags,
- struct sched_enq_and_set_ctx *ctx);
-void sched_enq_and_set_task(struct sched_enq_and_set_ctx *ctx);
+struct sched_change_ctx *sched_change_begin(struct task_struct *p, unsigned int flags);
+void sched_change_end(struct sched_change_ctx *ctx);
-#endif /* CONFIG_SCHED_CLASS_EXT */
+DEFINE_CLASS(sched_change, struct sched_change_ctx *,
+ sched_change_end(_T),
+ sched_change_begin(p, flags),
+ struct task_struct *p, unsigned int flags)
+
+DEFINE_CLASS_IS_UNCONDITIONAL(sched_change)
#include "ext.h"
diff --git a/kernel/sched/stats.h b/kernel/sched/stats.h
index 26f3fd4d34ce..cbf7206b3f9d 100644
--- a/kernel/sched/stats.h
+++ b/kernel/sched/stats.h
@@ -206,7 +206,7 @@ static inline void psi_ttwu_dequeue(struct task_struct *p)
rq = __task_rq_lock(p, &rf);
psi_task_change(p, p->psi_flags, 0);
- __task_rq_unlock(rq, &rf);
+ __task_rq_unlock(rq, p, &rf);
}
}
diff --git a/kernel/sched/stop_task.c b/kernel/sched/stop_task.c
index 2d4e279f05ee..4f9192be4b5b 100644
--- a/kernel/sched/stop_task.c
+++ b/kernel/sched/stop_task.c
@@ -32,7 +32,7 @@ static void set_next_task_stop(struct rq *rq, struct task_struct *stop, bool fir
stop->se.exec_start = rq_clock_task(rq);
}
-static struct task_struct *pick_task_stop(struct rq *rq)
+static struct task_struct *pick_task_stop(struct rq *rq, struct rq_flags *rf)
{
if (!sched_stop_runnable(rq))
return NULL;
@@ -75,14 +75,17 @@ static void task_tick_stop(struct rq *rq, struct task_struct *curr, int queued)
{
}
-static void switched_to_stop(struct rq *rq, struct task_struct *p)
+static void switching_to_stop(struct rq *rq, struct task_struct *p)
{
BUG(); /* its impossible to change to this class */
}
static void
-prio_changed_stop(struct rq *rq, struct task_struct *p, int oldprio)
+prio_changed_stop(struct rq *rq, struct task_struct *p, u64 oldprio)
{
+ if (p->prio == oldprio)
+ return;
+
BUG(); /* how!?, what priority? */
}
@@ -95,6 +98,8 @@ static void update_curr_stop(struct rq *rq)
*/
DEFINE_SCHED_CLASS(stop) = {
+ .queue_mask = 16,
+
.enqueue_task = enqueue_task_stop,
.dequeue_task = dequeue_task_stop,
.yield_task = yield_task_stop,
@@ -112,6 +117,6 @@ DEFINE_SCHED_CLASS(stop) = {
.task_tick = task_tick_stop,
.prio_changed = prio_changed_stop,
- .switched_to = switched_to_stop,
+ .switching_to = switching_to_stop,
.update_curr = update_curr_stop,
};
diff --git a/kernel/sched/syscalls.c b/kernel/sched/syscalls.c
index 77ae87f36e84..807879131add 100644
--- a/kernel/sched/syscalls.c
+++ b/kernel/sched/syscalls.c
@@ -64,8 +64,6 @@ static int effective_prio(struct task_struct *p)
void set_user_nice(struct task_struct *p, long nice)
{
- bool queued, running;
- struct rq *rq;
int old_prio;
if (task_nice(p) == nice || nice < MIN_NICE || nice > MAX_NICE)
@@ -74,10 +72,7 @@ void set_user_nice(struct task_struct *p, long nice)
* We have to be careful, if called from sys_setpriority(),
* the task might be in the middle of scheduling on another CPU.
*/
- CLASS(task_rq_lock, rq_guard)(p);
- rq = rq_guard.rq;
-
- update_rq_clock(rq);
+ guard(task_rq_lock)(p);
/*
* The RT priorities are set via sched_setscheduler(), but we still
@@ -90,28 +85,12 @@ void set_user_nice(struct task_struct *p, long nice)
return;
}
- queued = task_on_rq_queued(p);
- running = task_current_donor(rq, p);
- if (queued)
- dequeue_task(rq, p, DEQUEUE_SAVE | DEQUEUE_NOCLOCK);
- if (running)
- put_prev_task(rq, p);
-
- p->static_prio = NICE_TO_PRIO(nice);
- set_load_weight(p, true);
- old_prio = p->prio;
- p->prio = effective_prio(p);
-
- if (queued)
- enqueue_task(rq, p, ENQUEUE_RESTORE | ENQUEUE_NOCLOCK);
- if (running)
- set_next_task(rq, p);
-
- /*
- * If the task increased its priority or is running and
- * lowered its priority, then reschedule its CPU:
- */
- p->sched_class->prio_changed(rq, p, old_prio);
+ scoped_guard (sched_change, p, DEQUEUE_SAVE) {
+ p->static_prio = NICE_TO_PRIO(nice);
+ set_load_weight(p, true);
+ old_prio = p->prio;
+ p->prio = effective_prio(p);
+ }
}
EXPORT_SYMBOL(set_user_nice);
@@ -515,7 +494,7 @@ int __sched_setscheduler(struct task_struct *p,
bool user, bool pi)
{
int oldpolicy = -1, policy = attr->sched_policy;
- int retval, oldprio, newprio, queued, running;
+ int retval, oldprio, newprio;
const struct sched_class *prev_class, *next_class;
struct balance_callback *head;
struct rq_flags rf;
@@ -695,38 +674,27 @@ change:
prev_class = p->sched_class;
next_class = __setscheduler_class(policy, newprio);
- if (prev_class != next_class && p->se.sched_delayed)
- dequeue_task(rq, p, DEQUEUE_SLEEP | DEQUEUE_DELAYED | DEQUEUE_NOCLOCK);
-
- queued = task_on_rq_queued(p);
- running = task_current_donor(rq, p);
- if (queued)
- dequeue_task(rq, p, queue_flags);
- if (running)
- put_prev_task(rq, p);
+ if (prev_class != next_class)
+ queue_flags |= DEQUEUE_CLASS;
- if (!(attr->sched_flags & SCHED_FLAG_KEEP_PARAMS)) {
- __setscheduler_params(p, attr);
- p->sched_class = next_class;
- p->prio = newprio;
- }
- __setscheduler_uclamp(p, attr);
- check_class_changing(rq, p, prev_class);
+ scoped_guard (sched_change, p, queue_flags) {
- if (queued) {
- /*
- * We enqueue to tail when the priority of a task is
- * increased (user space view).
- */
- if (oldprio < p->prio)
- queue_flags |= ENQUEUE_HEAD;
+ if (!(attr->sched_flags & SCHED_FLAG_KEEP_PARAMS)) {
+ __setscheduler_params(p, attr);
+ p->sched_class = next_class;
+ p->prio = newprio;
+ }
+ __setscheduler_uclamp(p, attr);
- enqueue_task(rq, p, queue_flags);
+ if (scope->queued) {
+ /*
+ * We enqueue to tail when the priority of a task is
+ * increased (user space view).
+ */
+ if (oldprio < p->prio)
+ scope->flags |= ENQUEUE_HEAD;
+ }
}
- if (running)
- set_next_task(rq, p);
-
- check_class_changed(rq, p, prev_class, oldprio);
/* Avoid rq from going away on us: */
preempt_disable();
@@ -1351,7 +1319,7 @@ static void do_sched_yield(void)
rq = this_rq_lock_irq(&rf);
schedstat_inc(rq->yld_count);
- current->sched_class->yield_task(rq);
+ rq->donor->sched_class->yield_task(rq);
preempt_disable();
rq_unlock_irq(rq, &rf);
@@ -1420,12 +1388,13 @@ EXPORT_SYMBOL(yield);
*/
int __sched yield_to(struct task_struct *p, bool preempt)
{
- struct task_struct *curr = current;
+ struct task_struct *curr;
struct rq *rq, *p_rq;
int yielded = 0;
scoped_guard (raw_spinlock_irqsave, &p->pi_lock) {
rq = this_rq();
+ curr = rq->donor;
again:
p_rq = task_rq(p);
diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c
index 444bdfdab731..cf643a5ddedd 100644
--- a/kernel/sched/topology.c
+++ b/kernel/sched/topology.c
@@ -1590,10 +1590,17 @@ static void claim_allocations(int cpu, struct sched_domain *sd)
#ifdef CONFIG_NUMA
enum numa_topology_type sched_numa_topology_type;
+/*
+ * sched_domains_numa_distance is derived from sched_numa_node_distance
+ * and provides a simplified view of NUMA distances used specifically
+ * for building NUMA scheduling domains.
+ */
static int sched_domains_numa_levels;
+static int sched_numa_node_levels;
int sched_max_numa_distance;
static int *sched_domains_numa_distance;
+static int *sched_numa_node_distance;
static struct cpumask ***sched_domains_numa_masks;
#endif /* CONFIG_NUMA */
@@ -1662,6 +1669,12 @@ sd_init(struct sched_domain_topology_level *tl,
.last_balance = jiffies,
.balance_interval = sd_weight,
+
+ /* 50% success rate */
+ .newidle_call = 512,
+ .newidle_success = 256,
+ .newidle_ratio = 512,
+
.max_newidle_lb_cost = 0,
.last_decay_max_lb_cost = jiffies,
.child = child,
@@ -1845,10 +1858,10 @@ bool find_numa_distance(int distance)
return true;
rcu_read_lock();
- distances = rcu_dereference(sched_domains_numa_distance);
+ distances = rcu_dereference(sched_numa_node_distance);
if (!distances)
goto unlock;
- for (i = 0; i < sched_domains_numa_levels; i++) {
+ for (i = 0; i < sched_numa_node_levels; i++) {
if (distances[i] == distance) {
found = true;
break;
@@ -1924,14 +1937,34 @@ static void init_numa_topology_type(int offline_node)
#define NR_DISTANCE_VALUES (1 << DISTANCE_BITS)
-void sched_init_numa(int offline_node)
+/*
+ * An architecture could modify its NUMA distance, to change
+ * grouping of NUMA nodes and number of NUMA levels when creating
+ * NUMA level sched domains.
+ *
+ * A NUMA level is created for each unique
+ * arch_sched_node_distance.
+ */
+static int numa_node_dist(int i, int j)
{
- struct sched_domain_topology_level *tl;
- unsigned long *distance_map;
+ return node_distance(i, j);
+}
+
+int arch_sched_node_distance(int from, int to)
+ __weak __alias(numa_node_dist);
+
+static bool modified_sched_node_distance(void)
+{
+ return numa_node_dist != arch_sched_node_distance;
+}
+
+static int sched_record_numa_dist(int offline_node, int (*n_dist)(int, int),
+ int **dist, int *levels)
+{
+ unsigned long *distance_map __free(bitmap) = NULL;
int nr_levels = 0;
int i, j;
int *distances;
- struct cpumask ***masks;
/*
* O(nr_nodes^2) de-duplicating selection sort -- in order to find the
@@ -1939,17 +1972,16 @@ void sched_init_numa(int offline_node)
*/
distance_map = bitmap_alloc(NR_DISTANCE_VALUES, GFP_KERNEL);
if (!distance_map)
- return;
+ return -ENOMEM;
bitmap_zero(distance_map, NR_DISTANCE_VALUES);
for_each_cpu_node_but(i, offline_node) {
for_each_cpu_node_but(j, offline_node) {
- int distance = node_distance(i, j);
+ int distance = n_dist(i, j);
if (distance < LOCAL_DISTANCE || distance >= NR_DISTANCE_VALUES) {
sched_numa_warn("Invalid distance value range");
- bitmap_free(distance_map);
- return;
+ return -EINVAL;
}
bitmap_set(distance_map, distance, 1);
@@ -1962,18 +1994,46 @@ void sched_init_numa(int offline_node)
nr_levels = bitmap_weight(distance_map, NR_DISTANCE_VALUES);
distances = kcalloc(nr_levels, sizeof(int), GFP_KERNEL);
- if (!distances) {
- bitmap_free(distance_map);
- return;
- }
+ if (!distances)
+ return -ENOMEM;
for (i = 0, j = 0; i < nr_levels; i++, j++) {
j = find_next_bit(distance_map, NR_DISTANCE_VALUES, j);
distances[i] = j;
}
- rcu_assign_pointer(sched_domains_numa_distance, distances);
+ *dist = distances;
+ *levels = nr_levels;
- bitmap_free(distance_map);
+ return 0;
+}
+
+void sched_init_numa(int offline_node)
+{
+ struct sched_domain_topology_level *tl;
+ int nr_levels, nr_node_levels;
+ int i, j;
+ int *distances, *domain_distances;
+ struct cpumask ***masks;
+
+ /* Record the NUMA distances from SLIT table */
+ if (sched_record_numa_dist(offline_node, numa_node_dist, &distances,
+ &nr_node_levels))
+ return;
+
+ /* Record modified NUMA distances for building sched domains */
+ if (modified_sched_node_distance()) {
+ if (sched_record_numa_dist(offline_node, arch_sched_node_distance,
+ &domain_distances, &nr_levels)) {
+ kfree(distances);
+ return;
+ }
+ } else {
+ domain_distances = distances;
+ nr_levels = nr_node_levels;
+ }
+ rcu_assign_pointer(sched_numa_node_distance, distances);
+ WRITE_ONCE(sched_max_numa_distance, distances[nr_node_levels - 1]);
+ WRITE_ONCE(sched_numa_node_levels, nr_node_levels);
/*
* 'nr_levels' contains the number of unique distances
@@ -1991,6 +2051,8 @@ void sched_init_numa(int offline_node)
*
* We reset it to 'nr_levels' at the end of this function.
*/
+ rcu_assign_pointer(sched_domains_numa_distance, domain_distances);
+
sched_domains_numa_levels = 0;
masks = kzalloc(sizeof(void *) * nr_levels, GFP_KERNEL);
@@ -2016,10 +2078,13 @@ void sched_init_numa(int offline_node)
masks[i][j] = mask;
for_each_cpu_node_but(k, offline_node) {
- if (sched_debug() && (node_distance(j, k) != node_distance(k, j)))
+ if (sched_debug() &&
+ (arch_sched_node_distance(j, k) !=
+ arch_sched_node_distance(k, j)))
sched_numa_warn("Node-distance not symmetric");
- if (node_distance(j, k) > sched_domains_numa_distance[i])
+ if (arch_sched_node_distance(j, k) >
+ sched_domains_numa_distance[i])
continue;
cpumask_or(mask, mask, cpumask_of_node(k));
@@ -2059,7 +2124,6 @@ void sched_init_numa(int offline_node)
sched_domain_topology = tl;
sched_domains_numa_levels = nr_levels;
- WRITE_ONCE(sched_max_numa_distance, sched_domains_numa_distance[nr_levels - 1]);
init_numa_topology_type(offline_node);
}
@@ -2067,14 +2131,18 @@ void sched_init_numa(int offline_node)
static void sched_reset_numa(void)
{
- int nr_levels, *distances;
+ int nr_levels, *distances, *dom_distances = NULL;
struct cpumask ***masks;
nr_levels = sched_domains_numa_levels;
+ sched_numa_node_levels = 0;
sched_domains_numa_levels = 0;
sched_max_numa_distance = 0;
sched_numa_topology_type = NUMA_DIRECT;
- distances = sched_domains_numa_distance;
+ distances = sched_numa_node_distance;
+ if (sched_numa_node_distance != sched_domains_numa_distance)
+ dom_distances = sched_domains_numa_distance;
+ rcu_assign_pointer(sched_numa_node_distance, NULL);
rcu_assign_pointer(sched_domains_numa_distance, NULL);
masks = sched_domains_numa_masks;
rcu_assign_pointer(sched_domains_numa_masks, NULL);
@@ -2083,6 +2151,7 @@ static void sched_reset_numa(void)
synchronize_rcu();
kfree(distances);
+ kfree(dom_distances);
for (i = 0; i < nr_levels && masks; i++) {
if (!masks[i])
continue;
@@ -2129,7 +2198,8 @@ void sched_domains_numa_masks_set(unsigned int cpu)
continue;
/* Set ourselves in the remote node's masks */
- if (node_distance(j, node) <= sched_domains_numa_distance[i])
+ if (arch_sched_node_distance(j, node) <=
+ sched_domains_numa_distance[i])
cpumask_set_cpu(cpu, sched_domains_numa_masks[i][j]);
}
}
generated by cgit (git 2.34.1) at 2025-12-05 03:44:37 +0000