[PATCH 25/31] sched_ext: Implement SCX_KICK_WAIT

From: Tejun Heo
Date: Wed Nov 30 2022 - 03:27:14 EST


From: David Vernet <dvernet@xxxxxxxx>

If set when calling scx_bpf_kick_cpu(), the invoking CPU will busy wait for
the kicked cpu to enter the scheduler. This will be used to improve the
exclusion guarantees in scx_example_pair.

Signed-off-by: David Vernet <dvernet@xxxxxxxx>
Reviewed-by: Tejun Heo <tj@xxxxxxxxxx>
Signed-off-by: Tejun Heo <tj@xxxxxxxxxx>
Acked-by: Josh Don <joshdon@xxxxxxxxxx>
Acked-by: Hao Luo <haoluo@xxxxxxxxxx>
Acked-by: Barret Rhoden <brho@xxxxxxxxxx>
---
kernel/sched/core.c | 4 +++-
kernel/sched/ext.c | 36 ++++++++++++++++++++++++++++++++++--
kernel/sched/ext.h | 20 ++++++++++++++++++++
kernel/sched/sched.h | 2 ++
4 files changed, 59 insertions(+), 3 deletions(-)

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 79560641a61f..ea4f6edfcf32 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -5886,8 +5886,10 @@ __pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)

for_each_active_class(class) {
p = class->pick_next_task(rq);
- if (p)
+ if (p) {
+ scx_notify_pick_next_task(rq, p, class);
return p;
+ }
}

BUG(); /* The idle class should always have a runnable task. */
diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c
index bd03b55fbcf5..aeaad3d8b05a 100644
--- a/kernel/sched/ext.c
+++ b/kernel/sched/ext.c
@@ -109,8 +109,9 @@ unsigned long last_timeout_check = INITIAL_JIFFIES;

static struct delayed_work check_timeout_work;

-/* idle tracking */
#ifdef CONFIG_SMP
+
+/* idle tracking */
#ifdef CONFIG_CPUMASK_OFFSTACK
#define CL_ALIGNED_IF_ONSTACK
#else
@@ -123,7 +124,11 @@ static struct {
} idle_masks CL_ALIGNED_IF_ONSTACK;

static bool __cacheline_aligned_in_smp has_idle_cpus;
-#endif
+
+/* for %SCX_KICK_WAIT */
+static u64 __percpu *kick_cpus_pnt_seqs;
+
+#endif /* CONFIG_SMP */

/*
* Direct dispatch marker.
@@ -2959,6 +2964,7 @@ static const struct sysrq_key_op sysrq_sched_ext_reset_op = {
static void kick_cpus_irq_workfn(struct irq_work *irq_work)
{
struct rq *this_rq = this_rq();
+ u64 *pseqs = this_cpu_ptr(kick_cpus_pnt_seqs);
int this_cpu = cpu_of(this_rq);
int cpu;

@@ -2972,14 +2978,32 @@ static void kick_cpus_irq_workfn(struct irq_work *irq_work)
if (cpumask_test_cpu(cpu, this_rq->scx.cpus_to_preempt) &&
rq->curr->sched_class == &ext_sched_class)
rq->curr->scx.slice = 0;
+ pseqs[cpu] = rq->scx.pnt_seq;
resched_curr(rq);
+ } else {
+ cpumask_clear_cpu(cpu, this_rq->scx.cpus_to_wait);
}

raw_spin_rq_unlock_irqrestore(rq, flags);
}

+ for_each_cpu_andnot(cpu, this_rq->scx.cpus_to_wait,
+ cpumask_of(this_cpu)) {
+ /*
+ * Pairs with smp_store_release() issued by this CPU in
+ * scx_notify_pick_next_task() on the resched path.
+ *
+ * We busy-wait here to guarantee that no other task can be
+ * scheduled on our core before the target CPU has entered the
+ * resched path.
+ */
+ while (smp_load_acquire(&cpu_rq(cpu)->scx.pnt_seq) == pseqs[cpu])
+ cpu_relax();
+ }
+
cpumask_clear(this_rq->scx.cpus_to_kick);
cpumask_clear(this_rq->scx.cpus_to_preempt);
+ cpumask_clear(this_rq->scx.cpus_to_wait);
}
#endif

@@ -2999,6 +3023,11 @@ void __init init_sched_ext_class(void)
#ifdef CONFIG_SMP
BUG_ON(!alloc_cpumask_var(&idle_masks.cpu, GFP_KERNEL));
BUG_ON(!alloc_cpumask_var(&idle_masks.smt, GFP_KERNEL));
+
+ kick_cpus_pnt_seqs = __alloc_percpu(sizeof(kick_cpus_pnt_seqs[0]) *
+ num_possible_cpus(),
+ __alignof__(kick_cpus_pnt_seqs[0]));
+ BUG_ON(!kick_cpus_pnt_seqs);
#endif
for_each_possible_cpu(cpu) {
struct rq *rq = cpu_rq(cpu);
@@ -3009,6 +3038,7 @@ void __init init_sched_ext_class(void)
#ifdef CONFIG_SMP
BUG_ON(!zalloc_cpumask_var(&rq->scx.cpus_to_kick, GFP_KERNEL));
BUG_ON(!zalloc_cpumask_var(&rq->scx.cpus_to_preempt, GFP_KERNEL));
+ BUG_ON(!zalloc_cpumask_var(&rq->scx.cpus_to_wait, GFP_KERNEL));
init_irq_work(&rq->scx.kick_cpus_irq_work, kick_cpus_irq_workfn);
#endif
}
@@ -3228,6 +3258,8 @@ void scx_bpf_kick_cpu(s32 cpu, u64 flags)
cpumask_set_cpu(cpu, rq->scx.cpus_to_kick);
if (flags & SCX_KICK_PREEMPT)
cpumask_set_cpu(cpu, rq->scx.cpus_to_preempt);
+ if (flags & SCX_KICK_WAIT)
+ cpumask_set_cpu(cpu, rq->scx.cpus_to_wait);

irq_work_queue(&rq->scx.kick_cpus_irq_work);
preempt_enable();
diff --git a/kernel/sched/ext.h b/kernel/sched/ext.h
index 470b2224cdfa..8ae717c5e850 100644
--- a/kernel/sched/ext.h
+++ b/kernel/sched/ext.h
@@ -66,6 +66,7 @@ enum scx_tg_flags {

enum scx_kick_flags {
SCX_KICK_PREEMPT = 1LLU << 0, /* force scheduling on the CPU */
+ SCX_KICK_WAIT = 1LLU << 1, /* wait for the CPU to be rescheduled */
};

#ifdef CONFIG_SCHED_CLASS_EXT
@@ -107,6 +108,22 @@ __printf(2, 3) void scx_ops_error_type(enum scx_exit_type type,
#define scx_ops_error(fmt, args...) \
scx_ops_error_type(SCX_EXIT_ERROR, fmt, ##args)

+static inline void scx_notify_pick_next_task(struct rq *rq,
+ const struct task_struct *p,
+ const struct sched_class *active)
+{
+#ifdef CONFIG_SMP
+ if (!scx_enabled())
+ return;
+ /*
+ * Pairs with the smp_load_acquire() issued by a CPU in
+ * kick_cpus_irq_workfn() who is waiting for this CPU to perform a
+ * resched.
+ */
+ smp_store_release(&rq->scx.pnt_seq, rq->scx.pnt_seq + 1);
+#endif
+}
+
static inline void scx_notify_sched_tick(void)
{
unsigned long last_check, timeout;
@@ -164,6 +181,9 @@ static inline int scx_check_setscheduler(struct task_struct *p,
int policy) { return 0; }
static inline bool scx_can_stop_tick(struct rq *rq) { return true; }
static inline void init_sched_ext_class(void) {}
+static inline void scx_notify_pick_next_task(struct rq *rq,
+ const struct task_struct *p,
+ const struct sched_class *active) {}
static inline void scx_notify_sched_tick(void) {}

#define for_each_active_class for_each_class
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index a2ffa94ede02..5af758cc1e38 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -714,6 +714,8 @@ struct scx_rq {
#ifdef CONFIG_SMP
cpumask_var_t cpus_to_kick;
cpumask_var_t cpus_to_preempt;
+ cpumask_var_t cpus_to_wait;
+ u64 pnt_seq;
struct irq_work kick_cpus_irq_work;
#endif
};
--
2.38.1