On 04/05/2023 10:15, Juri Lelli wrote:
> On 04/05/23 08:23, Peter Zijlstra wrote:
>> On Wed, May 03, 2023 at 09:22:27AM +0200, Juri Lelli wrote:
>>> From: Dietmar Eggemann <dietmar.eggemann@xxxxxxx>
>>>
>>> Rework the existing dl_cpu_busy() interface which offers DL BW overflow
>>> checking and per-task DL BW allocation.
>>>
>>> Add dl_bw_free() as an interface to be able to free DL BW.
>>> It will be used to allow freeing of the DL BW request done during
>>> cpuset_can_attach() in case multiple controllers are attached to the
>>> cgroup next to the cpuset controller and one of the non-cpuset
>>> can_attach() fails.
>>>
>>> dl_bw_alloc() (and dl_bw_free()) now take a `u64 dl_bw` parameter
>>> instead of `struct task_struct *p` used in dl_cpu_busy(). This allows
>>> to allocate DL BW for a set of tasks too rater than only for a single
>>> task.
>>>
>>
>> Changlog fails the 'why' test.
>>
>
> Dietmar, if you could please add (or rework) the 'why' as a reply to
> this email, I can fold in v3.
>
> Thanks!
>
-->8--
>From 4ce3556723728a606b527bef8813b0fce3ad6e22 Mon Sep 17 00:00:00 2001
From: Dietmar Eggemann <dietmar.eggemann@xxxxxxx>
Date: Wed, 3 May 2023 09:22:27 +0200
Subject: [PATCH] sched/deadline: Create DL BW alloc, free & check overflow
interface
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>
---
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 eed5d65b8d1f..0bee06542450 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1853,6 +1853,8 @@ 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 d826bec1c522..df659892d7d5 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -9319,7 +9319,7 @@ 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:
@@ -9604,7 +9604,7 @@ 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 e11de074a6fd..166c3e6eae61 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -3058,26 +3058,38 @@ 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);
@@ -3085,6 +3097,21 @@ 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 ec7b3e0a2b20..0ad712811e35 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -330,7 +330,7 @@ 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
--
2.25.1
