From 85989106feb734437e2d598b639991b9185a43a6 Mon Sep 17 00:00:00 2001 From: Dietmar Eggemann Date: Mon, 8 May 2023 09:58:53 +0200 Subject: 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 Signed-off-by: Juri Lelli Signed-off-by: Tejun Heo --- include/linux/sched.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux/sched.h') 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); -- cgit v1.2.3 From 2ef269ef1ac006acf974793d975539244d77b28f Mon Sep 17 00:00:00 2001 From: Dietmar Eggemann Date: Mon, 8 May 2023 09:58:54 +0200 Subject: cgroup/cpuset: Free DL BW in case can_attach() fails 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 Signed-off-by: Dietmar Eggemann Signed-off-by: Juri Lelli Reviewed-by: Waiman Long Signed-off-by: Tejun Heo --- include/linux/sched.h | 2 +- kernel/cgroup/cpuset.c | 53 +++++++++++++++++++++++++++++++++++++++++++++----- kernel/sched/core.c | 17 ++-------------- 3 files changed, 51 insertions(+), 21 deletions(-) (limited to 'include/linux/sched.h') 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 b7168970fff2..2c76fcd9f0bc 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; @@ -2496,16 +2498,23 @@ 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); @@ -2516,7 +2525,7 @@ 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); @@ -2524,11 +2533,31 @@ 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. @@ -2551,6 +2580,14 @@ 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); } @@ -2651,6 +2688,12 @@ 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); @@ -3330,7 +3373,7 @@ 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; } -- cgit v1.2.3