From f080d93e1d419099a99d7473ed532289ca8dc717 Mon Sep 17 00:00:00 2001 From: Xie XiuQi Date: Tue, 14 Apr 2020 20:57:21 +0800 Subject: sched/debug: Fix trival print_task() format Ensure leave one space between state and task name. w/o patch: runnable tasks: S task PID tree-key switches prio wait Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20200414125721.195801-1-xiexiuqi@huawei.com --- kernel/sched/debug.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'kernel/sched/debug.c') diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c index a562df57a86e..b3ac1c10b032 100644 --- a/kernel/sched/debug.c +++ b/kernel/sched/debug.c @@ -437,7 +437,7 @@ print_task(struct seq_file *m, struct rq *rq, struct task_struct *p) else SEQ_printf(m, " %c", task_state_to_char(p)); - SEQ_printf(m, "%15s %5d %9Ld.%06ld %9Ld %5d ", + SEQ_printf(m, " %15s %5d %9Ld.%06ld %9Ld %5d ", p->comm, task_pid_nr(p), SPLIT_NS(p->se.vruntime), (long long)(p->nvcsw + p->nivcsw), @@ -464,10 +464,10 @@ static void print_rq(struct seq_file *m, struct rq *rq, int rq_cpu) SEQ_printf(m, "\n"); SEQ_printf(m, "runnable tasks:\n"); - SEQ_printf(m, " S task PID tree-key switches prio" + SEQ_printf(m, " S task PID tree-key switches prio" " wait-time sum-exec sum-sleep\n"); SEQ_printf(m, "-------------------------------------------------------" - "----------------------------------------------------\n"); + "------------------------------------------------------\n"); rcu_read_lock(); for_each_process_thread(g, p) { -- cgit v1.2.3-70-g09d2 From 9818427c6270a9ce8c52c8621026fe9cebae0f92 Mon Sep 17 00:00:00 2001 From: Valentin Schneider Date: Wed, 15 Apr 2020 22:05:05 +0100 Subject: sched/debug: Make sd->flags sysctl read-only Writing to the sysctl of a sched_domain->flags directly updates the value of the field, and goes nowhere near update_top_cache_domain(). This means that the cached domain pointers can end up containing stale data (e.g. the domain pointed to doesn't have the relevant flag set anymore). Explicit domain walks that check for flags will be affected by the write, but this won't be in sync with the cached pointers which will still point to the domains that were cached at the last sched_domain build. In other words, writing to this interface is playing a dangerous game. It could be made to trigger an update of the cached sched_domain pointers when written to, but this does not seem to be worth the trouble. Make it read-only. Signed-off-by: Valentin Schneider Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20200415210512.805-3-valentin.schneider@arm.com --- kernel/sched/debug.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel/sched/debug.c') diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c index b3ac1c10b032..c6cc02a6aad0 100644 --- a/kernel/sched/debug.c +++ b/kernel/sched/debug.c @@ -258,7 +258,7 @@ sd_alloc_ctl_domain_table(struct sched_domain *sd) set_table_entry(&table[2], "busy_factor", &sd->busy_factor, sizeof(int), 0644, proc_dointvec_minmax); set_table_entry(&table[3], "imbalance_pct", &sd->imbalance_pct, sizeof(int), 0644, proc_dointvec_minmax); set_table_entry(&table[4], "cache_nice_tries", &sd->cache_nice_tries, sizeof(int), 0644, proc_dointvec_minmax); - set_table_entry(&table[5], "flags", &sd->flags, sizeof(int), 0644, proc_dointvec_minmax); + set_table_entry(&table[5], "flags", &sd->flags, sizeof(int), 0444, proc_dointvec_minmax); set_table_entry(&table[6], "max_newidle_lb_cost", &sd->max_newidle_lb_cost, sizeof(long), 0644, proc_doulongvec_minmax); set_table_entry(&table[7], "name", sd->name, CORENAME_MAX_SIZE, 0444, proc_dostring); /* &table[8] is terminator */ -- cgit v1.2.3-70-g09d2 From ad32bb41fca67936c0c1d6d0bdd6d3e2e9c5432f Mon Sep 17 00:00:00 2001 From: Pavankumar Kondeti Date: Sun, 10 May 2020 18:26:41 +0530 Subject: sched/debug: Fix requested task uclamp values shown in procfs The intention of commit 96e74ebf8d59 ("sched/debug: Add task uclamp values to SCHED_DEBUG procfs") was to print requested and effective task uclamp values. The requested values printed are read from p->uclamp, which holds the last effective values. Fix this by printing the values from p->uclamp_req. Fixes: 96e74ebf8d59 ("sched/debug: Add task uclamp values to SCHED_DEBUG procfs") Signed-off-by: Pavankumar Kondeti Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Valentin Schneider Tested-by: Valentin Schneider Link: https://lkml.kernel.org/r/1589115401-26391-1-git-send-email-pkondeti@codeaurora.org --- kernel/sched/debug.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'kernel/sched/debug.c') diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c index a562df57a86e..239970b991c0 100644 --- a/kernel/sched/debug.c +++ b/kernel/sched/debug.c @@ -948,8 +948,8 @@ void proc_sched_show_task(struct task_struct *p, struct pid_namespace *ns, P(se.avg.util_est.enqueued); #endif #ifdef CONFIG_UCLAMP_TASK - __PS("uclamp.min", p->uclamp[UCLAMP_MIN].value); - __PS("uclamp.max", p->uclamp[UCLAMP_MAX].value); + __PS("uclamp.min", p->uclamp_req[UCLAMP_MIN].value); + __PS("uclamp.max", p->uclamp_req[UCLAMP_MAX].value); __PS("effective uclamp.min", uclamp_eff_value(p, UCLAMP_MIN)); __PS("effective uclamp.max", uclamp_eff_value(p, UCLAMP_MAX)); #endif -- cgit v1.2.3-70-g09d2 From 126c2092e5c8b28623cb890cd2930aa292410676 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 26 May 2020 18:11:03 +0200 Subject: sched: Add rq::ttwu_pending In preparation of removing rq->wake_list, replace the !list_empty(rq->wake_list) with rq->ttwu_pending. This is not fully equivalent as this new variable is racy. Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Ingo Molnar Link: https://lore.kernel.org/r/20200526161908.070399698@infradead.org --- kernel/sched/core.c | 13 +++++++++++-- kernel/sched/debug.c | 1 - kernel/sched/fair.c | 2 +- kernel/sched/sched.h | 4 +++- 4 files changed, 15 insertions(+), 5 deletions(-) (limited to 'kernel/sched/debug.c') diff --git a/kernel/sched/core.c b/kernel/sched/core.c index fa0d4990618e..b71ed5ee97fd 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -2275,13 +2275,21 @@ static int ttwu_remote(struct task_struct *p, int wake_flags) void sched_ttwu_pending(void) { struct rq *rq = this_rq(); - struct llist_node *llist = llist_del_all(&rq->wake_list); + struct llist_node *llist; struct task_struct *p, *t; struct rq_flags rf; + llist = llist_del_all(&rq->wake_list); if (!llist) return; + /* + * rq::ttwu_pending racy indication of out-standing wakeups. + * Races such that false-negatives are possible, since they + * are shorter lived that false-positives would be. + */ + WRITE_ONCE(rq->ttwu_pending, 0); + rq_lock_irqsave(rq, &rf); update_rq_clock(rq); @@ -2318,6 +2326,7 @@ static void __ttwu_queue_wakelist(struct task_struct *p, int cpu, int wake_flags p->sched_remote_wakeup = !!(wake_flags & WF_MIGRATED); + WRITE_ONCE(rq->ttwu_pending, 1); if (llist_add(&p->wake_entry, &rq->wake_list)) { if (!set_nr_if_polling(rq->idle)) smp_call_function_single_async(cpu, &rq->wake_csd); @@ -4705,7 +4714,7 @@ int idle_cpu(int cpu) return 0; #ifdef CONFIG_SMP - if (!llist_empty(&rq->wake_list)) + if (rq->ttwu_pending) return 0; #endif diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c index 1c24a6bbdae2..36c54265bb2b 100644 --- a/kernel/sched/debug.c +++ b/kernel/sched/debug.c @@ -638,7 +638,6 @@ do { \ P(nr_running); P(nr_switches); - P(nr_load_updates); P(nr_uninterruptible); PN(next_balance); SEQ_printf(m, " .%-30s: %ld\n", "curr->pid", (long)(task_pid_nr(rq->curr))); diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 2890bd54a088..0ed04d2a8959 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -8590,7 +8590,7 @@ static int idle_cpu_without(int cpu, struct task_struct *p) */ #ifdef CONFIG_SMP - if (!llist_empty(&rq->wake_list)) + if (rq->ttwu_pending) return 0; #endif diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 75b062999c43..c86fc94c54e5 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -895,7 +895,9 @@ struct rq { atomic_t nohz_flags; #endif /* CONFIG_NO_HZ_COMMON */ - unsigned long nr_load_updates; +#ifdef CONFIG_SMP + unsigned int ttwu_pending; +#endif u64 nr_switches; #ifdef CONFIG_UCLAMP_TASK -- cgit v1.2.3-70-g09d2