From: Juri Lelli <juri.lelli@redhat.com>
To: Peter Zijlstra <peterz@infradead.org>,
Ingo Molnar <mingo@kernel.org>, Qais Yousef <qyousef@layalina.io>,
Waiman Long <longman@redhat.com>, Tejun Heo <tj@kernel.org>,
Zefan Li <lizefan.x@bytedance.com>,
Johannes Weiner <hannes@cmpxchg.org>, Hao Luo <haoluo@google.com>
Cc: Dietmar Eggemann <dietmar.eggemann@arm.com>,
Steven Rostedt <rostedt@goodmis.org>,
linux-kernel@vger.kernel.org, luca.abeni@santannapisa.it,
claudio@evidence.eu.com, tommaso.cucinotta@santannapisa.it,
bristot@redhat.com, mathieu.poirier@linaro.org,
cgroups@vger.kernel.org,
Vincent Guittot <vincent.guittot@linaro.org>,
Wei Wang <wvw@google.com>, Rick Yiu <rickyiu@google.com>,
Quentin Perret <qperret@google.com>,
Heiko Carstens <hca@linux.ibm.com>,
Vasily Gorbik <gor@linux.ibm.com>,
Alexander Gordeev <agordeev@linux.ibm.com>,
Sudeep Holla <sudeep.holla@arm.com>,
Juri Lelli <juri.lelli@redhat.com>
Subject: [PATCH v2 5/6] sched/deadline: Create DL BW alloc, free & check overflow interface
Date: Wed, 3 May 2023 09:22:27 +0200 [thread overview]
Message-ID: <20230503072228.115707-6-juri.lelli@redhat.com> (raw)
In-Reply-To: <20230503072228.115707-1-juri.lelli@redhat.com>
From: Dietmar Eggemann <dietmar.eggemann@arm.com>
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.
Signed-off-by: Dietmar Eggemann <dietmar.eggemann@arm.com>
Signed-off-by: Juri Lelli <juri.lelli@redhat.com>
---
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
--
2.40.1
next prev parent reply other threads:[~2023-05-03 7:25 UTC|newest]
Thread overview: 24+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-05-03 7:22 [PATCH v2 0/6] sched/deadline: cpuset: Rework DEADLINE bandwidth restoration Juri Lelli
2023-05-03 7:22 ` [PATCH v2 1/6] cgroup/cpuset: Rename functions dealing with DEADLINE accounting Juri Lelli
2023-05-03 17:54 ` Waiman Long
2023-05-03 7:22 ` [PATCH v2 2/6] sched/cpuset: Bring back cpuset_mutex Juri Lelli
2023-05-03 17:55 ` Waiman Long
2023-05-04 6:18 ` Peter Zijlstra
2023-05-04 8:13 ` Juri Lelli
2023-05-04 6:21 ` Peter Zijlstra
2023-05-04 8:13 ` Juri Lelli
2023-05-03 7:22 ` [PATCH v2 3/6] sched/cpuset: Keep track of SCHED_DEADLINE task in cpusets Juri Lelli
2023-05-03 17:56 ` Waiman Long
2023-05-03 7:22 ` [PATCH v2 4/6] cgroup/cpuset: Iterate only if DEADLINE tasks are present Juri Lelli
2023-05-03 17:56 ` Waiman Long
2023-05-03 7:22 ` Juri Lelli [this message]
2023-05-03 17:45 ` [PATCH v2 5/6] sched/deadline: Create DL BW alloc, free & check overflow interface Waiman Long
2023-05-04 6:23 ` Peter Zijlstra
2023-05-04 8:15 ` Juri Lelli
2023-05-04 17:21 ` Dietmar Eggemann
2023-05-03 7:22 ` [PATCH v2 6/6] cgroup/cpuset: Free DL BW in case can_attach() fails Juri Lelli
2023-05-03 18:02 ` Waiman Long
2023-05-04 6:25 ` [PATCH v2 0/6] sched/deadline: cpuset: Rework DEADLINE bandwidth restoration Peter Zijlstra
2023-05-04 8:17 ` Juri Lelli
2023-05-05 19:31 ` Tejun Heo
2023-05-08 8:02 ` Juri Lelli
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20230503072228.115707-6-juri.lelli@redhat.com \
--to=juri.lelli@redhat.com \
--cc=agordeev@linux.ibm.com \
--cc=bristot@redhat.com \
--cc=cgroups@vger.kernel.org \
--cc=claudio@evidence.eu.com \
--cc=dietmar.eggemann@arm.com \
--cc=gor@linux.ibm.com \
--cc=hannes@cmpxchg.org \
--cc=haoluo@google.com \
--cc=hca@linux.ibm.com \
--cc=linux-kernel@vger.kernel.org \
--cc=lizefan.x@bytedance.com \
--cc=longman@redhat.com \
--cc=luca.abeni@santannapisa.it \
--cc=mathieu.poirier@linaro.org \
--cc=mingo@kernel.org \
--cc=peterz@infradead.org \
--cc=qperret@google.com \
--cc=qyousef@layalina.io \
--cc=rickyiu@google.com \
--cc=rostedt@goodmis.org \
--cc=sudeep.holla@arm.com \
--cc=tj@kernel.org \
--cc=tommaso.cucinotta@santannapisa.it \
--cc=vincent.guittot@linaro.org \
--cc=wvw@google.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).