[PATCH 5/6] sched/deadline: Create DL BW alloc, free & check overflow interface

From: Qais Yousef
Date: Sun Aug 20 2023 - 11:25:36 EST


From: Dietmar Eggemann <dietmar.eggemann@xxxxxxx>

commit 85989106feb734437e2d598b639991b9185a43a6 upstream.

While moving a set of tasks between exclusive cpusets,
cpuset_can_attach() -> task_can_attach() calls dl_cpu_busy(..., p) for
DL BW overflow checking and per-task DL BW allocation on the destination
root_domain for the DL tasks in this set.

This approach has the issue of not freeing already allocated DL BW in
the following error cases:

(1) The set of tasks includes multiple DL tasks and DL BW overflow
checking fails for one of the subsequent DL tasks.

(2) Another controller next to the cpuset controller which is attached
to the same cgroup fails in its can_attach().

To address this problem rework dl_cpu_busy():

(1) Split it into dl_bw_check_overflow() & dl_bw_alloc() and add a
dedicated dl_bw_free().

(2) dl_bw_alloc() & dl_bw_free() take a `u64 dl_bw` parameter instead of
a `struct task_struct *p` used in dl_cpu_busy(). This allows to
allocate DL BW for a set of tasks too rather than only for a single
task.

Signed-off-by: Dietmar Eggemann <dietmar.eggemann@xxxxxxx>
Signed-off-by: Juri Lelli <juri.lelli@xxxxxxxxxx>
Signed-off-by: Tejun Heo <tj@xxxxxxxxxx>
(cherry picked from commit 85989106feb734437e2d598b639991b9185a43a6)
Signed-off-by: Qais Yousef (Google) <qyousef@xxxxxxxxxxx>
---
include/linux/sched.h | 2 ++
kernel/sched/core.c | 4 ++--
kernel/sched/deadline.c | 53 +++++++++++++++++++++++++++++++----------
kernel/sched/sched.h | 2 +-
4 files changed, 45 insertions(+), 16 deletions(-)

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 5da4b3c89f63..f4b3640dadb8 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1658,6 +1658,8 @@ current_restore_flags(unsigned long orig_flags, unsigned long flags)

extern int cpuset_cpumask_can_shrink(const struct cpumask *cur, const struct cpumask *trial);
extern int task_can_attach(struct task_struct *p, const struct cpumask *cs_effective_cpus);
+extern int dl_bw_alloc(int cpu, u64 dl_bw);
+extern void dl_bw_free(int cpu, u64 dl_bw);
#ifdef CONFIG_SMP
extern void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask);
extern int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask);
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 906289d2ed68..3cfcd2059a66 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -6625,7 +6625,7 @@ int task_can_attach(struct task_struct *p,

if (unlikely(cpu >= nr_cpu_ids))
return -EINVAL;
- ret = dl_cpu_busy(cpu, p);
+ ret = dl_bw_alloc(cpu, p->dl.dl_bw);
}

out:
@@ -6885,7 +6885,7 @@ static void cpuset_cpu_active(void)
static int cpuset_cpu_inactive(unsigned int cpu)
{
if (!cpuhp_tasks_frozen) {
- int ret = dl_cpu_busy(cpu, NULL);
+ int ret = dl_bw_check_overflow(cpu);

if (ret)
return ret;
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 7d66c31db46c..d91295d3059f 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -2858,26 +2858,38 @@ int dl_cpuset_cpumask_can_shrink(const struct cpumask *cur,
return ret;
}

-int dl_cpu_busy(int cpu, struct task_struct *p)
+enum dl_bw_request {
+ dl_bw_req_check_overflow = 0,
+ dl_bw_req_alloc,
+ dl_bw_req_free
+};
+
+static int dl_bw_manage(enum dl_bw_request req, int cpu, u64 dl_bw)
{
- unsigned long flags, cap;
+ unsigned long flags;
struct dl_bw *dl_b;
- bool overflow;
+ bool overflow = 0;

rcu_read_lock_sched();
dl_b = dl_bw_of(cpu);
raw_spin_lock_irqsave(&dl_b->lock, flags);
- cap = dl_bw_capacity(cpu);
- overflow = __dl_overflow(dl_b, cap, 0, p ? p->dl.dl_bw : 0);

- if (!overflow && p) {
- /*
- * We reserve space for this task in the destination
- * root_domain, as we can't fail after this point.
- * We will free resources in the source root_domain
- * later on (see set_cpus_allowed_dl()).
- */
- __dl_add(dl_b, p->dl.dl_bw, dl_bw_cpus(cpu));
+ if (req == dl_bw_req_free) {
+ __dl_sub(dl_b, dl_bw, dl_bw_cpus(cpu));
+ } else {
+ unsigned long cap = dl_bw_capacity(cpu);
+
+ overflow = __dl_overflow(dl_b, cap, 0, dl_bw);
+
+ if (req == dl_bw_req_alloc && !overflow) {
+ /*
+ * We reserve space in the destination
+ * root_domain, as we can't fail after this point.
+ * We will free resources in the source root_domain
+ * later on (see set_cpus_allowed_dl()).
+ */
+ __dl_add(dl_b, dl_bw, dl_bw_cpus(cpu));
+ }
}

raw_spin_unlock_irqrestore(&dl_b->lock, flags);
@@ -2885,6 +2897,21 @@ int dl_cpu_busy(int cpu, struct task_struct *p)

return overflow ? -EBUSY : 0;
}
+
+int dl_bw_check_overflow(int cpu)
+{
+ return dl_bw_manage(dl_bw_req_check_overflow, cpu, 0);
+}
+
+int dl_bw_alloc(int cpu, u64 dl_bw)
+{
+ return dl_bw_manage(dl_bw_req_alloc, cpu, dl_bw);
+}
+
+void dl_bw_free(int cpu, u64 dl_bw)
+{
+ dl_bw_manage(dl_bw_req_free, cpu, dl_bw);
+}
#endif

#ifdef CONFIG_SCHED_DEBUG
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 852e856eed48..8de07aba8bdd 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -348,7 +348,7 @@ extern void __getparam_dl(struct task_struct *p, struct sched_attr *attr);
extern bool __checkparam_dl(const struct sched_attr *attr);
extern bool dl_param_changed(struct task_struct *p, const struct sched_attr *attr);
extern int dl_cpuset_cpumask_can_shrink(const struct cpumask *cur, const struct cpumask *trial);
-extern int dl_cpu_busy(int cpu, struct task_struct *p);
+extern int dl_bw_check_overflow(int cpu);

#ifdef CONFIG_CGROUP_SCHED

--
2.34.1