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 6/6] cgroup/cpuset: Free DL BW in case can_attach() fails
Date: Wed, 3 May 2023 09:22:28 +0200 [thread overview]
Message-ID: <20230503072228.115707-7-juri.lelli@redhat.com> (raw)
In-Reply-To: <20230503072228.115707-1-juri.lelli@redhat.com>
From: Dietmar Eggemann <dietmar.eggemann@arm.com>
cpuset_can_attach() can fail. Postpone DL BW allocation until all tasks
have been checked. DL BW is not allocated per-task but as a sum over
all DL tasks migrating.
If multiple controllers are attached to the cgroup next to the cpuset
controller a non-cpuset can_attach() can fail. In this case free DL BW
in cpuset_cancel_attach().
Finally, update cpuset DL task count (nr_deadline_tasks) only in
cpuset_attach().
Suggested-by: Waiman Long <longman@redhat.com>
Signed-off-by: Dietmar Eggemann <dietmar.eggemann@arm.com>
Signed-off-by: Juri Lelli <juri.lelli@redhat.com>
---
include/linux/sched.h | 2 +-
kernel/cgroup/cpuset.c | 53 ++++++++++++++++++++++++++++++++++++++----
kernel/sched/core.c | 17 ++------------
3 files changed, 51 insertions(+), 21 deletions(-)
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 0bee06542450..2553918f0b61 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1852,7 +1852,7 @@ 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 task_can_attach(struct task_struct *p);
extern int dl_bw_alloc(int cpu, u64 dl_bw);
extern void dl_bw_free(int cpu, u64 dl_bw);
#ifdef CONFIG_SMP
diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index 6587df42cb61..d1073603c96c 100644
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -198,6 +198,8 @@ struct cpuset {
* know when to rebuild associated root domain bandwidth information.
*/
int nr_deadline_tasks;
+ int nr_migrate_dl_tasks;
+ u64 sum_migrate_dl_bw;
/* Invalid partition error code, not lock protected */
enum prs_errcode prs_err;
@@ -2494,16 +2496,23 @@ static int cpuset_can_attach_check(struct cpuset *cs)
return 0;
}
+static void reset_migrate_dl_data(struct cpuset *cs)
+{
+ cs->nr_migrate_dl_tasks = 0;
+ cs->sum_migrate_dl_bw = 0;
+}
+
/* Called by cgroups to determine if a cpuset is usable; cpuset_mutex held */
static int cpuset_can_attach(struct cgroup_taskset *tset)
{
struct cgroup_subsys_state *css;
- struct cpuset *cs;
+ struct cpuset *cs, *oldcs;
struct task_struct *task;
int ret;
/* used later by cpuset_attach() */
cpuset_attach_old_cs = task_cs(cgroup_taskset_first(tset, &css));
+ oldcs = cpuset_attach_old_cs;
cs = css_cs(css);
mutex_lock(&cpuset_mutex);
@@ -2514,7 +2523,7 @@ static int cpuset_can_attach(struct cgroup_taskset *tset)
goto out_unlock;
cgroup_taskset_for_each(task, css, tset) {
- ret = task_can_attach(task, cs->effective_cpus);
+ ret = task_can_attach(task);
if (ret)
goto out_unlock;
ret = security_task_setscheduler(task);
@@ -2522,11 +2531,31 @@ static int cpuset_can_attach(struct cgroup_taskset *tset)
goto out_unlock;
if (dl_task(task)) {
- cs->nr_deadline_tasks++;
- cpuset_attach_old_cs->nr_deadline_tasks--;
+ cs->nr_migrate_dl_tasks++;
+ cs->sum_migrate_dl_bw += task->dl.dl_bw;
}
}
+ if (!cs->nr_migrate_dl_tasks)
+ goto out_success;
+
+ if (!cpumask_intersects(oldcs->effective_cpus, cs->effective_cpus)) {
+ int cpu = cpumask_any_and(cpu_active_mask, cs->effective_cpus);
+
+ if (unlikely(cpu >= nr_cpu_ids)) {
+ reset_migrate_dl_data(cs);
+ ret = -EINVAL;
+ goto out_unlock;
+ }
+
+ ret = dl_bw_alloc(cpu, cs->sum_migrate_dl_bw);
+ if (ret) {
+ reset_migrate_dl_data(cs);
+ goto out_unlock;
+ }
+ }
+
+out_success:
/*
* Mark attach is in progress. This makes validate_change() fail
* changes which zero cpus/mems_allowed.
@@ -2549,6 +2578,14 @@ static void cpuset_cancel_attach(struct cgroup_taskset *tset)
cs->attach_in_progress--;
if (!cs->attach_in_progress)
wake_up(&cpuset_attach_wq);
+
+ if (cs->nr_migrate_dl_tasks) {
+ int cpu = cpumask_any(cs->effective_cpus);
+
+ dl_bw_free(cpu, cs->sum_migrate_dl_bw);
+ reset_migrate_dl_data(cs);
+ }
+
mutex_unlock(&cpuset_mutex);
}
@@ -2649,6 +2686,12 @@ static void cpuset_attach(struct cgroup_taskset *tset)
out:
cs->old_mems_allowed = cpuset_attach_nodemask_to;
+ if (cs->nr_migrate_dl_tasks) {
+ cs->nr_deadline_tasks += cs->nr_migrate_dl_tasks;
+ oldcs->nr_deadline_tasks -= cs->nr_migrate_dl_tasks;
+ reset_migrate_dl_data(cs);
+ }
+
cs->attach_in_progress--;
if (!cs->attach_in_progress)
wake_up(&cpuset_attach_wq);
@@ -3328,7 +3371,7 @@ static int cpuset_can_fork(struct task_struct *task, struct css_set *cset)
if (ret)
goto out_unlock;
- ret = task_can_attach(task, cs->effective_cpus);
+ ret = task_can_attach(task);
if (ret)
goto out_unlock;
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index df659892d7d5..ed0d7381b2ec 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -9294,8 +9294,7 @@ int cpuset_cpumask_can_shrink(const struct cpumask *cur,
return ret;
}
-int task_can_attach(struct task_struct *p,
- const struct cpumask *cs_effective_cpus)
+int task_can_attach(struct task_struct *p)
{
int ret = 0;
@@ -9308,21 +9307,9 @@ int task_can_attach(struct task_struct *p,
* success of set_cpus_allowed_ptr() on all attached tasks
* before cpus_mask may be changed.
*/
- if (p->flags & PF_NO_SETAFFINITY) {
+ if (p->flags & PF_NO_SETAFFINITY)
ret = -EINVAL;
- goto out;
- }
-
- if (dl_task(p) && !cpumask_intersects(task_rq(p)->rd->span,
- cs_effective_cpus)) {
- int cpu = cpumask_any_and(cpu_active_mask, cs_effective_cpus);
- if (unlikely(cpu >= nr_cpu_ids))
- return -EINVAL;
- ret = dl_bw_alloc(cpu, p->dl.dl_bw);
- }
-
-out:
return ret;
}
--
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 ` [PATCH v2 5/6] sched/deadline: Create DL BW alloc, free & check overflow interface Juri Lelli
2023-05-03 17:45 ` 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 ` Juri Lelli [this message]
2023-05-03 18:02 ` [PATCH v2 6/6] cgroup/cpuset: Free DL BW in case can_attach() fails 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=20230503072228.115707-7-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).