[PATCH v5 10/19] sched: Split scheduler execution context

From: John Stultz
Date: Sat Aug 19 2023 - 02:10:47 EST

From: Peter Zijlstra <peterz@xxxxxxxxxxxxx>

Lets define the scheduling context as all the scheduler state in
task_struct and the execution context as all state required to run
the task.

Currently both are intertwined in task_struct. We want to logically
split these such that we can run the execution context of one task
with the scheduling context of another.

To this purpose introduce rq_selected() macro to point to the
task_struct used for scheduler state and preserve rq->curr to
denote the execution context.

NOTE: Peter previously mentioned he didn't like the name
"rq_selected()", but I've not come up with a better alternative.
I'm very open to other name proposals.

Question for Peter: Dietmar suggested you'd prefer I drop the
conditionalization of the scheduler context pointer on the rq
(so rq_selected() would be open coded as rq->curr_sched or
whatever we agree on for a name), but I'd think in the
!CONFIG_PROXY_EXEC case we'd want to avoid the wasted pointer
and its use (since it curr_sched would always be == curr)?
If I'm wrong I'm fine switching this, but would appreciate
clarification.

Cc: Joel Fernandes <joelaf@xxxxxxxxxx>
Cc: Qais Yousef <qyousef@xxxxxxxxxx>
Cc: Ingo Molnar <mingo@xxxxxxxxxx>
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Cc: Juri Lelli <juri.lelli@xxxxxxxxxx>
Cc: Vincent Guittot <vincent.guittot@xxxxxxxxxx>
Cc: Dietmar Eggemann <dietmar.eggemann@xxxxxxx>
Cc: Valentin Schneider <vschneid@xxxxxxxxxx>
Cc: Steven Rostedt <rostedt@xxxxxxxxxxx>
Cc: Ben Segall <bsegall@xxxxxxxxxx>
Cc: Zimuzo Ezeozue <zezeozue@xxxxxxxxxx>
Cc: Youssef Esmat <youssefesmat@xxxxxxxxxx>
Cc: Mel Gorman <mgorman@xxxxxxx>
Cc: Daniel Bristot de Oliveira <bristot@xxxxxxxxxx>
Cc: Will Deacon <will@xxxxxxxxxx>
Cc: Waiman Long <longman@xxxxxxxxxx>
Cc: Boqun Feng <boqun.feng@xxxxxxxxx>
Cc: "Paul E . McKenney" <paulmck@xxxxxxxxxx>
Cc: kernel-team@xxxxxxxxxxx
Signed-off-by: Peter Zijlstra (Intel) <peterz@xxxxxxxxxxxxx>
Signed-off-by: Juri Lelli <juri.lelli@xxxxxxxxxx>
Signed-off-by: Peter Zijlstra (Intel) <peterz@xxxxxxxxxxxxx>
Link: https://lkml.kernel.org/r/20181009092434.26221-5-juri.lelli@xxxxxxxxxx
[add additional comments and update more sched_class code to use
rq::proxy]
Signed-off-by: Connor O'Brien <connoro@xxxxxxxxxx>
[jstultz: Rebased and resolved minor collisions, reworked to use
accessors, tweaked update_curr_common to use rq_proxy fixing rt
scheduling issues]
Signed-off-by: John Stultz <jstultz@xxxxxxxxxx>
---
v2:
* Reworked to use accessors
* Fixed update_curr_common to use proxy instead of curr
v3:
* Tweaked wrapper names
* Swapped proxy for selected for clarity
v4:
* Minor variable name tweaks for readability
* Use a macro instead of a inline function and drop
other helper functions as suggested by Peter.
* Remove verbose comments/questions to avoid review
distractions, as suggested by Dietmar
v5:
* Add CONFIG_PROXY_EXEC option to this patch so the
new logic can be tested with this change
* Minor fix to grab rq_selected when holding the rq lock
---
init/Kconfig | 7 +++++++
kernel/sched/core.c | 39 ++++++++++++++++++++++++++-------------
kernel/sched/deadline.c | 35 ++++++++++++++++++-----------------
kernel/sched/fair.c | 18 +++++++++---------
kernel/sched/rt.c | 40 ++++++++++++++++++++--------------------
kernel/sched/sched.h | 37 +++++++++++++++++++++++++++++++++++--
6 files changed, 115 insertions(+), 61 deletions(-)

diff --git a/init/Kconfig b/init/Kconfig
index f7f65af4ee12..a6c83931a9a9 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -907,6 +907,13 @@ config NUMA_BALANCING_DEFAULT_ENABLED
If set, automatic NUMA balancing will be enabled if running on a NUMA
machine.

+config PROXY_EXEC
+ bool "Proxy Execution"
+ default n
+ help
+ This option enables proxy execution, a mechanism for mutex owning
+ tasks to inherit the scheduling context of higher priority waiters.
+
menuconfig CGROUPS
bool "Control Group support"
select KERNFS
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index c52c2eba7c73..ea0a7fb144fd 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -793,7 +793,7 @@ static enum hrtimer_restart hrtick(struct hrtimer *timer)

rq_lock(rq, &rf);
update_rq_clock(rq);
- rq->curr->sched_class->task_tick(rq, rq->curr, 1);
+ rq_selected(rq)->sched_class->task_tick(rq, rq_selected(rq), 1);
rq_unlock(rq, &rf);

return HRTIMER_NORESTART;
@@ -2200,16 +2200,18 @@ static inline void check_class_changed(struct rq *rq, struct task_struct *p,

void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags)
{
- if (p->sched_class == rq->curr->sched_class)
- rq->curr->sched_class->check_preempt_curr(rq, p, flags);
- else if (sched_class_above(p->sched_class, rq->curr->sched_class))
+ struct task_struct *curr = rq_selected(rq);
+
+ if (p->sched_class == curr->sched_class)
+ curr->sched_class->check_preempt_curr(rq, p, flags);
+ else if (sched_class_above(p->sched_class, curr->sched_class))
resched_curr(rq);

/*
* A queue event has occurred, and we're going to schedule. In
* this case, we can save a useless back to back clock update.
*/
- if (task_on_rq_queued(rq->curr) && test_tsk_need_resched(rq->curr))
+ if (task_on_rq_queued(curr) && test_tsk_need_resched(rq->curr))
rq_clock_skip_update(rq);
}

@@ -2748,7 +2750,7 @@ __do_set_cpus_allowed(struct task_struct *p, struct affinity_context *ctx)
lockdep_assert_held(&p->pi_lock);

queued = task_on_rq_queued(p);
- running = task_current(rq, p);
+ running = task_current_selected(rq, p);

if (queued) {
/*
@@ -5573,7 +5575,7 @@ unsigned long long task_sched_runtime(struct task_struct *p)
* project cycles that may never be accounted to this
* thread, breaking clock_gettime().
*/
- if (task_current(rq, p) && task_on_rq_queued(p)) {
+ if (task_current_selected(rq, p) && task_on_rq_queued(p)) {
prefetch_curr_exec_start(p);
update_rq_clock(rq);
p->sched_class->update_curr(rq);
@@ -5641,7 +5643,8 @@ void scheduler_tick(void)
{
int cpu = smp_processor_id();
struct rq *rq = cpu_rq(cpu);
- struct task_struct *curr = rq->curr;
+ /* accounting goes to the selected task */
+ struct task_struct *curr;
struct rq_flags rf;
unsigned long thermal_pressure;
u64 resched_latency;
@@ -5652,6 +5655,7 @@ void scheduler_tick(void)
sched_clock_tick();

rq_lock(rq, &rf);
+ curr = rq_selected(rq);

update_rq_clock(rq);
thermal_pressure = arch_scale_thermal_pressure(cpu_of(rq));
@@ -5742,6 +5746,13 @@ static void sched_tick_remote(struct work_struct *work)
if (cpu_is_offline(cpu))
goto out_unlock;

+ /*
+ * Since this is a remote tick for full dynticks mode, we are
+ * always sure that there is no proxy (only a single task is
+ * running).
+ */
+ SCHED_WARN_ON(rq->curr != rq_selected(rq));
+
update_rq_clock(rq);

if (!is_idle_task(curr)) {
@@ -6672,6 +6683,7 @@ static void __sched notrace __schedule(unsigned int sched_mode)
}

next = pick_next_task(rq, prev, &rf);
+ rq_set_selected(rq, next);
clear_tsk_need_resched(prev);
clear_preempt_need_resched();
#ifdef CONFIG_SCHED_DEBUG
@@ -7138,7 +7150,7 @@ void rt_mutex_setprio(struct task_struct *p, struct task_struct *pi_task)

prev_class = p->sched_class;
queued = task_on_rq_queued(p);
- running = task_current(rq, p);
+ running = task_current_selected(rq, p);
if (queued)
dequeue_task(rq, p, queue_flag);
if (running)
@@ -7226,7 +7238,7 @@ void set_user_nice(struct task_struct *p, long nice)
goto out_unlock;
}
queued = task_on_rq_queued(p);
- running = task_current(rq, p);
+ running = task_current_selected(rq, p);
if (queued)
dequeue_task(rq, p, DEQUEUE_SAVE | DEQUEUE_NOCLOCK);
if (running)
@@ -7797,7 +7809,7 @@ static int __sched_setscheduler(struct task_struct *p,
}

queued = task_on_rq_queued(p);
- running = task_current(rq, p);
+ running = task_current_selected(rq, p);
if (queued)
dequeue_task(rq, p, queue_flags);
if (running)
@@ -9298,6 +9310,7 @@ void __init init_idle(struct task_struct *idle, int cpu)
rcu_read_unlock();

rq->idle = idle;
+ rq_set_selected(rq, idle);
rcu_assign_pointer(rq->curr, idle);
idle->on_rq = TASK_ON_RQ_QUEUED;
#ifdef CONFIG_SMP
@@ -9387,7 +9400,7 @@ void sched_setnuma(struct task_struct *p, int nid)

rq = task_rq_lock(p, &rf);
queued = task_on_rq_queued(p);
- running = task_current(rq, p);
+ running = task_current_selected(rq, p);

if (queued)
dequeue_task(rq, p, DEQUEUE_SAVE);
@@ -10514,7 +10527,7 @@ void sched_move_task(struct task_struct *tsk)

update_rq_clock(rq);

- running = task_current(rq, tsk);
+ running = task_current_selected(rq, tsk);
queued = task_on_rq_queued(tsk);

if (queued)
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 9522e6607754..e8bca6b8da6f 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -1174,7 +1174,7 @@ static enum hrtimer_restart dl_task_timer(struct hrtimer *timer)
#endif

enqueue_task_dl(rq, p, ENQUEUE_REPLENISH);
- if (dl_task(rq->curr))
+ if (dl_task(rq_selected(rq)))
check_preempt_curr_dl(rq, p, 0);
else
resched_curr(rq);
@@ -1297,7 +1297,7 @@ static u64 grub_reclaim(u64 delta, struct rq *rq, struct sched_dl_entity *dl_se)
*/
static void update_curr_dl(struct rq *rq)
{
- struct task_struct *curr = rq->curr;
+ struct task_struct *curr = rq_selected(rq);
struct sched_dl_entity *dl_se = &curr->dl;
s64 delta_exec, scaled_delta_exec;
int cpu = cpu_of(rq);
@@ -1810,7 +1810,7 @@ static int find_later_rq(struct task_struct *task);
static int
select_task_rq_dl(struct task_struct *p, int cpu, int flags)
{
- struct task_struct *curr;
+ struct task_struct *curr, *selected;
bool select_rq;
struct rq *rq;

@@ -1821,6 +1821,7 @@ select_task_rq_dl(struct task_struct *p, int cpu, int flags)

rcu_read_lock();
curr = READ_ONCE(rq->curr); /* unlocked access */
+ selected = READ_ONCE(rq_selected(rq));

/*
* If we are dealing with a -deadline task, we must
@@ -1831,9 +1832,9 @@ select_task_rq_dl(struct task_struct *p, int cpu, int flags)
* other hand, if it has a shorter deadline, we
* try to make it stay here, it might be important.
*/
- select_rq = unlikely(dl_task(curr)) &&
+ select_rq = unlikely(dl_task(selected)) &&
(curr->nr_cpus_allowed < 2 ||
- !dl_entity_preempt(&p->dl, &curr->dl)) &&
+ !dl_entity_preempt(&p->dl, &selected->dl)) &&
p->nr_cpus_allowed > 1;

/*
@@ -1896,7 +1897,7 @@ static void check_preempt_equal_dl(struct rq *rq, struct task_struct *p)
* let's hope p can move out.
*/
if (rq->curr->nr_cpus_allowed == 1 ||
- !cpudl_find(&rq->rd->cpudl, rq->curr, NULL))
+ !cpudl_find(&rq->rd->cpudl, rq_selected(rq), NULL))
return;

/*
@@ -1935,7 +1936,7 @@ static int balance_dl(struct rq *rq, struct task_struct *p, struct rq_flags *rf)
static void check_preempt_curr_dl(struct rq *rq, struct task_struct *p,
int flags)
{
- if (dl_entity_preempt(&p->dl, &rq->curr->dl)) {
+ if (dl_entity_preempt(&p->dl, &rq_selected(rq)->dl)) {
resched_curr(rq);
return;
}
@@ -1945,7 +1946,7 @@ static void check_preempt_curr_dl(struct rq *rq, struct task_struct *p,
* In the unlikely case current and p have the same deadline
* let us try to decide what's the best thing to do...
*/
- if ((p->dl.deadline == rq->curr->dl.deadline) &&
+ if ((p->dl.deadline == rq_selected(rq)->dl.deadline) &&
!test_tsk_need_resched(rq->curr))
check_preempt_equal_dl(rq, p);
#endif /* CONFIG_SMP */
@@ -1980,7 +1981,7 @@ static void set_next_task_dl(struct rq *rq, struct task_struct *p, bool first)
if (hrtick_enabled_dl(rq))
start_hrtick_dl(rq, p);

- if (rq->curr->sched_class != &dl_sched_class)
+ if (rq_selected(rq)->sched_class != &dl_sched_class)
update_dl_rq_load_avg(rq_clock_pelt(rq), rq, 0);

deadline_queue_push_tasks(rq);
@@ -2297,8 +2298,8 @@ static int push_dl_task(struct rq *rq)
* can move away, it makes sense to just reschedule
* without going further in pushing next_task.
*/
- if (dl_task(rq->curr) &&
- dl_time_before(next_task->dl.deadline, rq->curr->dl.deadline) &&
+ if (dl_task(rq_selected(rq)) &&
+ dl_time_before(next_task->dl.deadline, rq_selected(rq)->dl.deadline) &&
rq->curr->nr_cpus_allowed > 1) {
resched_curr(rq);
return 0;
@@ -2423,7 +2424,7 @@ static void pull_dl_task(struct rq *this_rq)
* deadline than the current task of its runqueue.
*/
if (dl_time_before(p->dl.deadline,
- src_rq->curr->dl.deadline))
+ rq_selected(src_rq)->dl.deadline))
goto skip;

if (is_migration_disabled(p)) {
@@ -2462,9 +2463,9 @@ static void task_woken_dl(struct rq *rq, struct task_struct *p)
if (!task_on_cpu(rq, p) &&
!test_tsk_need_resched(rq->curr) &&
p->nr_cpus_allowed > 1 &&
- dl_task(rq->curr) &&
+ dl_task(rq_selected(rq)) &&
(rq->curr->nr_cpus_allowed < 2 ||
- !dl_entity_preempt(&p->dl, &rq->curr->dl))) {
+ !dl_entity_preempt(&p->dl, &rq_selected(rq)->dl))) {
push_dl_tasks(rq);
}
}
@@ -2639,12 +2640,12 @@ static void switched_to_dl(struct rq *rq, struct task_struct *p)
return;
}

- if (rq->curr != p) {
+ if (rq_selected(rq) != p) {
#ifdef CONFIG_SMP
if (p->nr_cpus_allowed > 1 && rq->dl.overloaded)
deadline_queue_push_tasks(rq);
#endif
- if (dl_task(rq->curr))
+ if (dl_task(rq_selected(rq)))
check_preempt_curr_dl(rq, p, 0);
else
resched_curr(rq);
@@ -2673,7 +2674,7 @@ static void prio_changed_dl(struct rq *rq, struct task_struct *p,
if (!rq->dl.overloaded)
deadline_queue_pull_task(rq);

- if (task_current(rq, p)) {
+ if (task_current_selected(rq, p)) {
/*
* If we now have a earlier deadline task than p,
* then reschedule, provided p is still on this
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 80f74ec20fb8..808a91ba6a5e 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -919,7 +919,7 @@ static s64 update_curr_se(struct rq *rq, struct sched_entity *curr)
*/
s64 update_curr_common(struct rq *rq)
{
- struct task_struct *curr = rq->curr;
+ struct task_struct *curr = rq_selected(rq);
s64 delta_exec;

delta_exec = update_curr_se(rq, &curr->se);
@@ -964,7 +964,7 @@ static void update_curr(struct cfs_rq *cfs_rq)

static void update_curr_fair(struct rq *rq)
{
- update_curr(cfs_rq_of(&rq->curr->se));
+ update_curr(cfs_rq_of(&rq_selected(rq)->se));
}

static inline void
@@ -6248,7 +6248,7 @@ static void hrtick_start_fair(struct rq *rq, struct task_struct *p)
s64 delta = slice - ran;

if (delta < 0) {
- if (task_current(rq, p))
+ if (task_current_selected(rq, p))
resched_curr(rq);
return;
}
@@ -6263,7 +6263,7 @@ static void hrtick_start_fair(struct rq *rq, struct task_struct *p)
*/
static void hrtick_update(struct rq *rq)
{
- struct task_struct *curr = rq->curr;
+ struct task_struct *curr = rq_selected(rq);

if (!hrtick_enabled_fair(rq) || curr->sched_class != &fair_sched_class)
return;
@@ -7957,7 +7957,7 @@ static void set_skip_buddy(struct sched_entity *se)
*/
static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int wake_flags)
{
- struct task_struct *curr = rq->curr;
+ struct task_struct *curr = rq_selected(rq);
struct sched_entity *se = &curr->se, *pse = &p->se;
struct cfs_rq *cfs_rq = task_cfs_rq(curr);
int scale = cfs_rq->nr_running >= sched_nr_latency;
@@ -7991,7 +7991,7 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int wake_
* prevents us from potentially nominating it as a false LAST_BUDDY
* below.
*/
- if (test_tsk_need_resched(curr))
+ if (test_tsk_need_resched(rq->curr))
return;

/* Idle tasks are by definition preempted by non-idle tasks. */
@@ -8990,7 +8990,7 @@ static bool __update_blocked_others(struct rq *rq, bool *done)
* update_load_avg() can call cpufreq_update_util(). Make sure that RT,
* DL and IRQ signals have been updated before updating CFS.
*/
- curr_class = rq->curr->sched_class;
+ curr_class = rq_selected(rq)->sched_class;

thermal_pressure = arch_scale_thermal_pressure(cpu_of(rq));

@@ -12239,7 +12239,7 @@ prio_changed_fair(struct rq *rq, struct task_struct *p, int oldprio)
* our priority decreased, or if we are not currently running on
* this runqueue and our priority is higher than the current's
*/
- if (task_current(rq, p)) {
+ if (task_current_selected(rq, p)) {
if (p->prio > oldprio)
resched_curr(rq);
} else
@@ -12384,7 +12384,7 @@ static void switched_to_fair(struct rq *rq, struct task_struct *p)
* kick off the schedule if running, otherwise just see
* if we can still preempt the current task.
*/
- if (task_current(rq, p))
+ if (task_current_selected(rq, p))
resched_curr(rq);
else
check_preempt_curr(rq, p, 0);
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index 0d0b276c447d..6d9036547c1d 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -574,7 +574,7 @@ static void dequeue_rt_entity(struct sched_rt_entity *rt_se, unsigned int flags)

static void sched_rt_rq_enqueue(struct rt_rq *rt_rq)
{
- struct task_struct *curr = rq_of_rt_rq(rt_rq)->curr;
+ struct task_struct *curr = rq_selected(rq_of_rt_rq(rt_rq));
struct rq *rq = rq_of_rt_rq(rt_rq);
struct sched_rt_entity *rt_se;

@@ -1044,7 +1044,7 @@ static int sched_rt_runtime_exceeded(struct rt_rq *rt_rq)
*/
static void update_curr_rt(struct rq *rq)
{
- struct task_struct *curr = rq->curr;
+ struct task_struct *curr = rq_selected(rq);
struct sched_rt_entity *rt_se = &curr->rt;
s64 delta_exec;

@@ -1591,7 +1591,7 @@ static int find_lowest_rq(struct task_struct *task);
static int
select_task_rq_rt(struct task_struct *p, int cpu, int flags)
{
- struct task_struct *curr;
+ struct task_struct *curr, *selected;
struct rq *rq;
bool test;

@@ -1603,6 +1603,7 @@ select_task_rq_rt(struct task_struct *p, int cpu, int flags)

rcu_read_lock();
curr = READ_ONCE(rq->curr); /* unlocked access */
+ selected = READ_ONCE(rq_selected(rq));

/*
* If the current task on @p's runqueue is an RT task, then
@@ -1631,8 +1632,8 @@ select_task_rq_rt(struct task_struct *p, int cpu, int flags)
* systems like big.LITTLE.
*/
test = curr &&
- unlikely(rt_task(curr)) &&
- (curr->nr_cpus_allowed < 2 || curr->prio <= p->prio);
+ unlikely(rt_task(selected)) &&
+ (curr->nr_cpus_allowed < 2 || selected->prio <= p->prio);

if (test || !rt_task_fits_capacity(p, cpu)) {
int target = find_lowest_rq(p);
@@ -1662,12 +1663,8 @@ select_task_rq_rt(struct task_struct *p, int cpu, int flags)

static void check_preempt_equal_prio(struct rq *rq, struct task_struct *p)
{
- /*
- * Current can't be migrated, useless to reschedule,
- * let's hope p can move out.
- */
if (rq->curr->nr_cpus_allowed == 1 ||
- !cpupri_find(&rq->rd->cpupri, rq->curr, NULL))
+ !cpupri_find(&rq->rd->cpupri, rq_selected(rq), NULL))
return;

/*
@@ -1710,7 +1707,9 @@ static int balance_rt(struct rq *rq, struct task_struct *p, struct rq_flags *rf)
*/
static void check_preempt_curr_rt(struct rq *rq, struct task_struct *p, int flags)
{
- if (p->prio < rq->curr->prio) {
+ struct task_struct *curr = rq_selected(rq);
+
+ if (p->prio < curr->prio) {
resched_curr(rq);
return;
}
@@ -1728,7 +1727,7 @@ static void check_preempt_curr_rt(struct rq *rq, struct task_struct *p, int flag
* to move current somewhere else, making room for our non-migratable
* task.
*/
- if (p->prio == rq->curr->prio && !test_tsk_need_resched(rq->curr))
+ if (p->prio == curr->prio && !test_tsk_need_resched(rq->curr))
check_preempt_equal_prio(rq, p);
#endif
}
@@ -1753,7 +1752,7 @@ static inline void set_next_task_rt(struct rq *rq, struct task_struct *p, bool f
* utilization. We only care of the case where we start to schedule a
* rt task
*/
- if (rq->curr->sched_class != &rt_sched_class)
+ if (rq_selected(rq)->sched_class != &rt_sched_class)
update_rt_rq_load_avg(rq_clock_pelt(rq), rq, 0);

rt_queue_push_tasks(rq);
@@ -2034,6 +2033,7 @@ static struct task_struct *pick_next_pushable_task(struct rq *rq)

BUG_ON(rq->cpu != task_cpu(p));
BUG_ON(task_current(rq, p));
+ BUG_ON(task_current_selected(rq, p));
BUG_ON(p->nr_cpus_allowed <= 1);

BUG_ON(!task_on_rq_queued(p));
@@ -2066,7 +2066,7 @@ static int push_rt_task(struct rq *rq, bool pull)
* higher priority than current. If that's the case
* just reschedule current.
*/
- if (unlikely(next_task->prio < rq->curr->prio)) {
+ if (unlikely(next_task->prio < rq_selected(rq)->prio)) {
resched_curr(rq);
return 0;
}
@@ -2419,7 +2419,7 @@ static void pull_rt_task(struct rq *this_rq)
* p if it is lower in priority than the
* current task on the run queue
*/
- if (p->prio < src_rq->curr->prio)
+ if (p->prio < rq_selected(src_rq)->prio)
goto skip;

if (is_migration_disabled(p)) {
@@ -2461,9 +2461,9 @@ static void task_woken_rt(struct rq *rq, struct task_struct *p)
bool need_to_push = !task_on_cpu(rq, p) &&
!test_tsk_need_resched(rq->curr) &&
p->nr_cpus_allowed > 1 &&
- (dl_task(rq->curr) || rt_task(rq->curr)) &&
+ (dl_task(rq_selected(rq)) || rt_task(rq_selected(rq))) &&
(rq->curr->nr_cpus_allowed < 2 ||
- rq->curr->prio <= p->prio);
+ rq_selected(rq)->prio <= p->prio);

if (need_to_push)
push_rt_tasks(rq);
@@ -2547,7 +2547,7 @@ static void switched_to_rt(struct rq *rq, struct task_struct *p)
if (p->nr_cpus_allowed > 1 && rq->rt.overloaded)
rt_queue_push_tasks(rq);
#endif /* CONFIG_SMP */
- if (p->prio < rq->curr->prio && cpu_online(cpu_of(rq)))
+ if (p->prio < rq_selected(rq)->prio && cpu_online(cpu_of(rq)))
resched_curr(rq);
}
}
@@ -2562,7 +2562,7 @@ prio_changed_rt(struct rq *rq, struct task_struct *p, int oldprio)
if (!task_on_rq_queued(p))
return;

- if (task_current(rq, p)) {
+ if (task_current_selected(rq, p)) {
#ifdef CONFIG_SMP
/*
* If our priority decreases while running, we
@@ -2588,7 +2588,7 @@ prio_changed_rt(struct rq *rq, struct task_struct *p, int oldprio)
* greater than the current running task
* then reschedule.
*/
- if (p->prio < rq->curr->prio)
+ if (p->prio < rq_selected(rq)->prio)
resched_curr(rq);
}
}
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 95900ccaaf82..71d92e75cee0 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1008,7 +1008,10 @@ struct rq {
*/
unsigned int nr_uninterruptible;

- struct task_struct __rcu *curr;
+ struct task_struct __rcu *curr; /* Execution context */
+#ifdef CONFIG_PROXY_EXEC
+ struct task_struct __rcu *curr_sched; /* Scheduling context (policy) */
+#endif
struct task_struct *idle;
struct task_struct *stop;
unsigned long next_balance;
@@ -1207,6 +1210,22 @@ DECLARE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues);
#define cpu_curr(cpu) (cpu_rq(cpu)->curr)
#define raw_rq() raw_cpu_ptr(&runqueues)

+#ifdef CONFIG_PROXY_EXEC
+#define rq_selected(rq) ((rq)->curr_sched)
+#define cpu_curr_selected(cpu) (cpu_rq(cpu)->curr_sched)
+static inline void rq_set_selected(struct rq *rq, struct task_struct *t)
+{
+ rcu_assign_pointer(rq->curr_sched, t);
+}
+#else
+#define rq_selected(rq) ((rq)->curr)
+#define cpu_curr_selected(cpu) (cpu_rq(cpu)->curr)
+static inline void rq_set_selected(struct rq *rq, struct task_struct *t)
+{
+ /* Do nothing */
+}
+#endif
+
struct sched_group;
#ifdef CONFIG_SCHED_CORE
static inline struct cpumask *sched_group_span(struct sched_group *sg);
@@ -2106,11 +2125,25 @@ static inline u64 global_rt_runtime(void)
return (u64)sysctl_sched_rt_runtime * NSEC_PER_USEC;
}

+/*
+ * Is p the current execution context?
+ */
static inline int task_current(struct rq *rq, struct task_struct *p)
{
return rq->curr == p;
}

+/*
+ * Is p the current scheduling context?
+ *
+ * Note that it might be the current execution context at the same time if
+ * rq->curr == rq_selected() == p.
+ */
+static inline int task_current_selected(struct rq *rq, struct task_struct *p)
+{
+ return rq_selected(rq) == p;
+}
+
#ifdef CONFIG_PROXY_EXEC
static inline bool task_is_blocked(struct task_struct *p)
{
@@ -2284,7 +2317,7 @@ struct sched_class {

static inline void put_prev_task(struct rq *rq, struct task_struct *prev)
{
- WARN_ON_ONCE(rq->curr != prev);
+ WARN_ON_ONCE(rq_selected(rq) != prev);
prev->sched_class->put_prev_task(rq, prev);
}

--
2.42.0.rc1.204.g551eb34607-goog