From db7ee3cb620b2cec5a5f44767ab93cb4eb80d961 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Fri, 27 Sep 2024 00:49:05 +0200 Subject: rcu: Use kthread preferred affinity for RCU boost Now that kthreads have an infrastructure to handle preferred affinity against CPU hotplug and housekeeping cpumask, convert RCU boost to use it instead of handling all the constraints by itself. Acked-by: Paul E. McKenney Signed-off-by: Frederic Weisbecker --- kernel/rcu/tree.c | 27 +++++++++++++++++++-------- 1 file changed, 19 insertions(+), 8 deletions(-) (limited to 'kernel/rcu/tree.c') diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index ff98233d4aa5..4a4c49821058 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -149,7 +149,6 @@ static int rcu_scheduler_fully_active __read_mostly; static void rcu_report_qs_rnp(unsigned long mask, struct rcu_node *rnp, unsigned long gps, unsigned long flags); -static struct task_struct *rcu_boost_task(struct rcu_node *rnp); static void invoke_rcu_core(void); static void rcu_report_exp_rdp(struct rcu_data *rdp); static void sync_sched_exp_online_cleanup(int cpu); @@ -5011,6 +5010,22 @@ int rcutree_prepare_cpu(unsigned int cpu) return 0; } +static void rcu_thread_affine_rnp(struct task_struct *t, struct rcu_node *rnp) +{ + cpumask_var_t affinity; + int cpu; + + if (!zalloc_cpumask_var(&affinity, GFP_KERNEL)) + return; + + for_each_leaf_node_possible_cpu(rnp, cpu) + cpumask_set_cpu(cpu, affinity); + + kthread_affine_preferred(t, affinity); + + free_cpumask_var(affinity); +} + /* * Update kthreads affinity during CPU-hotplug changes. * @@ -5030,19 +5045,18 @@ static void rcutree_affinity_setting(unsigned int cpu, int outgoingcpu) unsigned long mask; struct rcu_data *rdp; struct rcu_node *rnp; - struct task_struct *task_boost, *task_exp; + struct task_struct *task_exp; rdp = per_cpu_ptr(&rcu_data, cpu); rnp = rdp->mynode; - task_boost = rcu_boost_task(rnp); task_exp = rcu_exp_par_gp_task(rnp); /* - * If CPU is the boot one, those tasks are created later from early + * If CPU is the boot one, this task is created later from early * initcall since kthreadd must be created first. */ - if (!task_boost && !task_exp) + if (!task_exp) return; if (!zalloc_cpumask_var(&cm, GFP_KERNEL)) @@ -5064,9 +5078,6 @@ static void rcutree_affinity_setting(unsigned int cpu, int outgoingcpu) if (task_exp) set_cpus_allowed_ptr(task_exp, cm); - if (task_boost) - set_cpus_allowed_ptr(task_boost, cm); - mutex_unlock(&rnp->kthread_mutex); free_cpumask_var(cm); -- cgit v1.2.3 From b04e317b522630b46f78ee62ecbdc5734e8d43de Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Fri, 27 Sep 2024 00:49:07 +0200 Subject: treewide: Introduce kthread_run_worker[_on_cpu]() kthread_create() creates a kthread without running it yet. kthread_run() creates a kthread and runs it. On the other hand, kthread_create_worker() creates a kthread worker and runs it. This difference in behaviours is confusing. Also there is no way to create a kthread worker and affine it using kthread_bind_mask() or kthread_affine_preferred() before starting it. Consolidate the behaviours and introduce kthread_run_worker[_on_cpu]() that behaves just like kthread_run(). kthread_create_worker[_on_cpu]() will now only create a kthread worker without starting it. Signed-off-by: Frederic Weisbecker Signed-off-by: Dan Carpenter --- kernel/rcu/tree.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'kernel/rcu/tree.c') diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index 4a4c49821058..d4b8e87a473b 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -4906,7 +4906,7 @@ static void rcu_spawn_exp_par_gp_kworker(struct rcu_node *rnp) if (rnp->exp_kworker) return; - kworker = kthread_create_worker(0, name, rnp_index); + kworker = kthread_run_worker(0, name, rnp_index); if (IS_ERR_OR_NULL(kworker)) { pr_err("Failed to create par gp kworker on %d/%d\n", rnp->grplo, rnp->grphi); @@ -4933,7 +4933,7 @@ static void __init rcu_start_exp_gp_kworker(void) const char *name = "rcu_exp_gp_kthread_worker"; struct sched_param param = { .sched_priority = kthread_prio }; - rcu_exp_gp_kworker = kthread_create_worker(0, name); + rcu_exp_gp_kworker = kthread_run_worker(0, name); if (IS_ERR_OR_NULL(rcu_exp_gp_kworker)) { pr_err("Failed to create %s!\n", name); rcu_exp_gp_kworker = NULL; -- cgit v1.2.3 From 8044c589767456af2061ca03468aa6a295da1925 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Fri, 27 Sep 2024 00:49:08 +0200 Subject: rcu: Use kthread preferred affinity for RCU exp kworkers Now that kthreads have an infrastructure to handle preferred affinity against CPU hotplug and housekeeping cpumask, convert RCU exp workers to use it instead of handling all the constraints by itself. Acked-by: Paul E. McKenney Signed-off-by: Frederic Weisbecker --- kernel/rcu/tree.c | 105 ++++++++++-------------------------------------------- 1 file changed, 19 insertions(+), 86 deletions(-) (limited to 'kernel/rcu/tree.c') diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index d4b8e87a473b..c160e05dfb7c 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -4894,6 +4894,22 @@ rcu_boot_init_percpu_data(int cpu) rcu_boot_init_nocb_percpu_data(rdp); } +static void rcu_thread_affine_rnp(struct task_struct *t, struct rcu_node *rnp) +{ + cpumask_var_t affinity; + int cpu; + + if (!zalloc_cpumask_var(&affinity, GFP_KERNEL)) + return; + + for_each_leaf_node_possible_cpu(rnp, cpu) + cpumask_set_cpu(cpu, affinity); + + kthread_affine_preferred(t, affinity); + + free_cpumask_var(affinity); +} + struct kthread_worker *rcu_exp_gp_kworker; static void rcu_spawn_exp_par_gp_kworker(struct rcu_node *rnp) @@ -4906,7 +4922,7 @@ static void rcu_spawn_exp_par_gp_kworker(struct rcu_node *rnp) if (rnp->exp_kworker) return; - kworker = kthread_run_worker(0, name, rnp_index); + kworker = kthread_create_worker(0, name, rnp_index); if (IS_ERR_OR_NULL(kworker)) { pr_err("Failed to create par gp kworker on %d/%d\n", rnp->grplo, rnp->grphi); @@ -4916,16 +4932,9 @@ static void rcu_spawn_exp_par_gp_kworker(struct rcu_node *rnp) if (IS_ENABLED(CONFIG_RCU_EXP_KTHREAD)) sched_setscheduler_nocheck(kworker->task, SCHED_FIFO, ¶m); -} -static struct task_struct *rcu_exp_par_gp_task(struct rcu_node *rnp) -{ - struct kthread_worker *kworker = READ_ONCE(rnp->exp_kworker); - - if (!kworker) - return NULL; - - return kworker->task; + rcu_thread_affine_rnp(kworker->task, rnp); + wake_up_process(kworker->task); } static void __init rcu_start_exp_gp_kworker(void) @@ -5010,79 +5019,6 @@ int rcutree_prepare_cpu(unsigned int cpu) return 0; } -static void rcu_thread_affine_rnp(struct task_struct *t, struct rcu_node *rnp) -{ - cpumask_var_t affinity; - int cpu; - - if (!zalloc_cpumask_var(&affinity, GFP_KERNEL)) - return; - - for_each_leaf_node_possible_cpu(rnp, cpu) - cpumask_set_cpu(cpu, affinity); - - kthread_affine_preferred(t, affinity); - - free_cpumask_var(affinity); -} - -/* - * Update kthreads affinity during CPU-hotplug changes. - * - * Set the per-rcu_node kthread's affinity to cover all CPUs that are - * served by the rcu_node in question. The CPU hotplug lock is still - * held, so the value of rnp->qsmaskinit will be stable. - * - * We don't include outgoingcpu in the affinity set, use -1 if there is - * no outgoing CPU. If there are no CPUs left in the affinity set, - * this function allows the kthread to execute on any CPU. - * - * Any future concurrent calls are serialized via ->kthread_mutex. - */ -static void rcutree_affinity_setting(unsigned int cpu, int outgoingcpu) -{ - cpumask_var_t cm; - unsigned long mask; - struct rcu_data *rdp; - struct rcu_node *rnp; - struct task_struct *task_exp; - - rdp = per_cpu_ptr(&rcu_data, cpu); - rnp = rdp->mynode; - - task_exp = rcu_exp_par_gp_task(rnp); - - /* - * If CPU is the boot one, this task is created later from early - * initcall since kthreadd must be created first. - */ - if (!task_exp) - return; - - if (!zalloc_cpumask_var(&cm, GFP_KERNEL)) - return; - - mutex_lock(&rnp->kthread_mutex); - mask = rcu_rnp_online_cpus(rnp); - for_each_leaf_node_possible_cpu(rnp, cpu) - if ((mask & leaf_node_cpu_bit(rnp, cpu)) && - cpu != outgoingcpu) - cpumask_set_cpu(cpu, cm); - cpumask_and(cm, cm, housekeeping_cpumask(HK_TYPE_RCU)); - if (cpumask_empty(cm)) { - cpumask_copy(cm, housekeeping_cpumask(HK_TYPE_RCU)); - if (outgoingcpu >= 0) - cpumask_clear_cpu(outgoingcpu, cm); - } - - if (task_exp) - set_cpus_allowed_ptr(task_exp, cm); - - mutex_unlock(&rnp->kthread_mutex); - - free_cpumask_var(cm); -} - /* * Has the specified (known valid) CPU ever been fully online? */ @@ -5111,7 +5047,6 @@ int rcutree_online_cpu(unsigned int cpu) if (rcu_scheduler_active == RCU_SCHEDULER_INACTIVE) return 0; /* Too early in boot for scheduler work. */ sync_sched_exp_online_cleanup(cpu); - rcutree_affinity_setting(cpu, -1); // Stop-machine done, so allow nohz_full to disable tick. tick_dep_clear(TICK_DEP_BIT_RCU); @@ -5328,8 +5263,6 @@ int rcutree_offline_cpu(unsigned int cpu) rnp->ffmask &= ~rdp->grpmask; raw_spin_unlock_irqrestore_rcu_node(rnp, flags); - rcutree_affinity_setting(cpu, cpu); - // nohz_full CPUs need the tick for stop-machine to work quickly tick_dep_set(TICK_DEP_BIT_RCU); return 0; -- cgit v1.2.3