From: Dietmar Eggemann dietmar.eggemann@arm.com
commit 2ef269ef1ac006acf974793d975539244d77b28f upstream.
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 Reviewed-by: Waiman Long longman@redhat.com Signed-off-by: Tejun Heo tj@kernel.org (cherry picked from commit 2ef269ef1ac006acf974793d975539244d77b28f) [Conflict in kernel/cgroup/cpuset.c due to pulling extra neighboring functions that are not applicable on this branch.] Signed-off-by: Qais Yousef (Google) qyousef@layalina.io --- include/linux/sched.h | 2 +- kernel/cgroup/cpuset.c | 51 ++++++++++++++++++++++++++++++++++++++---- kernel/sched/core.c | 17 ++------------ 3 files changed, 50 insertions(+), 20 deletions(-)
diff --git a/include/linux/sched.h b/include/linux/sched.h index 91fe1d6418e7..7bfc2b45cd99 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1797,7 +1797,7 @@ 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 63c8939503cb..6905079c15c2 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -167,6 +167,8 @@ 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;
/* Handle for cpuset.cpus.partition */ struct cgroup_file partition_file; @@ -2206,16 +2208,23 @@ static int fmeter_getrate(struct fmeter *fmp)
static struct cpuset *cpuset_attach_old_cs;
+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); @@ -2227,7 +2236,7 @@ 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); @@ -2235,11 +2244,31 @@ 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. @@ -2263,6 +2292,14 @@ 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); }
@@ -2335,6 +2372,12 @@ static void cpuset_attach(struct cgroup_taskset *tset)
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); diff --git a/kernel/sched/core.c b/kernel/sched/core.c index da2a2906a826..2324b7055260 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -8789,8 +8789,7 @@ 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;
@@ -8803,21 +8802,9 @@ 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; }