We can maintain the ordering of the scheduler cpu hotplug functionality nicely in one notifer. Get rid of the maze.
Signed-off-by: Thomas Gleixner <t...@linutronix.de> --- include/linux/cpu.h | 12 +-- kernel/sched/core.c | 174 ++++++++++++++++++++-------------------------------- 2 files changed, 73 insertions(+), 113 deletions(-) --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -61,19 +61,15 @@ struct notifier_block; enum { /* * SCHED_ACTIVE marks a cpu which is coming up active during - * CPU_ONLINE and CPU_DOWN_FAILED and must be the first - * notifier. CPUSET_ACTIVE adjusts cpuset according to - * cpu_active mask right after SCHED_ACTIVE. During - * CPU_DOWN_PREPARE, SCHED_INACTIVE and CPUSET_INACTIVE are - * ordered in the similar way. + * CPU_ONLINE and CPU_DOWN_FAILED and must be the first notifier. Is + * also cpuset according to cpu_active mask right after activating the + * cpu. During CPU_DOWN_PREPARE, SCHED_INACTIVE reversed the operation. * * This ordering guarantees consistent cpu_active mask and * migration behavior to all cpu notifiers. */ CPU_PRI_SCHED_ACTIVE = INT_MAX, - CPU_PRI_CPUSET_ACTIVE = INT_MAX - 1, - CPU_PRI_SCHED_INACTIVE = INT_MIN + 1, - CPU_PRI_CPUSET_INACTIVE = INT_MIN, + CPU_PRI_SCHED_INACTIVE = INT_MIN, /* migration should happen before other stuff but after perf */ CPU_PRI_PERF = 20, --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -5720,39 +5720,6 @@ static void set_cpu_rq_start_time(unsign rq->age_stamp = sched_clock_cpu(cpu); } -static int sched_cpu_active(struct notifier_block *nfb, - unsigned long action, void *hcpu) -{ - int cpu = (long)hcpu; - - switch (action & ~CPU_TASKS_FROZEN) { - case CPU_DOWN_FAILED: - set_cpu_active(cpu, true); - return NOTIFY_OK; - - default: - return NOTIFY_DONE; - } -} - -static int sched_cpu_inactive(struct notifier_block *nfb, - unsigned long action, void *hcpu) -{ - switch (action & ~CPU_TASKS_FROZEN) { - case CPU_DOWN_PREPARE: - set_cpu_active((long)hcpu, false); - return NOTIFY_OK; - default: - return NOTIFY_DONE; - } -} - -int sched_cpu_starting(unsigned int cpu) -{ - set_cpu_rq_start_time(cpu); - return 0; -} - static cpumask_var_t sched_domains_tmpmask; /* sched_domains_mutex */ #ifdef CONFIG_SCHED_DEBUG @@ -6895,10 +6862,13 @@ static void sched_init_numa(void) init_numa_topology_type(); } -static void sched_domains_numa_masks_set(int cpu) +static void sched_domains_numa_masks_set(unsigned int cpu) { - int i, j; int node = cpu_to_node(cpu); + int i, j; + + if (!sched_smp_initialized) + return; for (i = 0; i < sched_domains_numa_levels; i++) { for (j = 0; j < nr_node_ids; j++) { @@ -6908,54 +6878,23 @@ static void sched_domains_numa_masks_set } } -static void sched_domains_numa_masks_clear(int cpu) +static void sched_domains_numa_masks_clear(unsigned int cpu) { int i, j; + + if (!sched_smp_initialized) + return; + for (i = 0; i < sched_domains_numa_levels; i++) { for (j = 0; j < nr_node_ids; j++) cpumask_clear_cpu(cpu, sched_domains_numa_masks[i][j]); } } -/* - * Update sched_domains_numa_masks[level][node] array when new cpus - * are onlined. - */ -static int sched_domains_numa_masks_update(struct notifier_block *nfb, - unsigned long action, - void *hcpu) -{ - int cpu = (long)hcpu; - - if (!sched_smp_initialized) - return NOTIFY_DONE; - - switch (action & ~CPU_TASKS_FROZEN) { - case CPU_ONLINE: - sched_domains_numa_masks_set(cpu); - break; - - case CPU_DEAD: - sched_domains_numa_masks_clear(cpu); - break; - - default: - return NOTIFY_DONE; - } - - return NOTIFY_OK; -} #else -static inline void sched_init_numa(void) -{ -} - -static int sched_domains_numa_masks_update(struct notifier_block *nfb, - unsigned long action, - void *hcpu) -{ - return 0; -} +static inline void sched_init_numa(void) { } +static void sched_domains_numa_masks_set(unsigned int cpu) { } +static void sched_domains_numa_masks_clear(unsigned int cpu) { } #endif /* CONFIG_NUMA */ static int __sdt_alloc(const struct cpumask *cpu_map) @@ -7345,16 +7284,12 @@ static int num_cpus_frozen; /* used to m * If we come here as part of a suspend/resume, don't touch cpusets because we * want to restore it back to its original state upon resume anyway. */ -static int cpuset_cpu_active(struct notifier_block *nfb, unsigned long action, - void *hcpu) +static void cpuset_cpu_active(bool frozen) { if (!sched_smp_initialized) - return NOTIFY_DONE; - - switch (action) { - case CPU_ONLINE_FROZEN: - case CPU_DOWN_FAILED_FROZEN: + return; + if (frozen) { /* * num_cpus_frozen tracks how many CPUs are involved in suspend * resume sequence. As long as this is not the last online @@ -7364,38 +7299,28 @@ static int cpuset_cpu_active(struct noti num_cpus_frozen--; if (likely(num_cpus_frozen)) { partition_sched_domains(1, NULL, NULL); - break; + return; } - /* * This is the last CPU online operation. So fall through and * restore the original sched domains by considering the * cpuset configurations. */ - - case CPU_ONLINE: - cpuset_update_active_cpus(true); - break; - default: - return NOTIFY_DONE; } - return NOTIFY_OK; + cpuset_update_active_cpus(true); } -static int cpuset_cpu_inactive(struct notifier_block *nfb, unsigned long action, - void *hcpu) +static int cpuset_cpu_inactive(unsigned int cpu, bool frozen) { unsigned long flags; - long cpu = (long)hcpu; struct dl_bw *dl_b; bool overflow; int cpus; if (!sched_smp_initialized) - return NOTIFY_DONE; + return 0; - switch (action) { - case CPU_DOWN_PREPARE: + if (!frozen) { rcu_read_lock_sched(); dl_b = dl_bw_of(cpu); @@ -7407,17 +7332,60 @@ static int cpuset_cpu_inactive(struct no rcu_read_unlock_sched(); if (overflow) - return notifier_from_errno(-EBUSY); + return -EBUSY; cpuset_update_active_cpus(false); - break; - case CPU_DOWN_PREPARE_FROZEN: + } else { num_cpus_frozen++; partition_sched_domains(1, NULL, NULL); - break; + } + return 0; +} + +static int sched_cpu_active(struct notifier_block *nfb, unsigned long action, + void *hcpu) +{ + unsigned int cpu = (unsigned long)hcpu; + + switch (action & ~CPU_TASKS_FROZEN) { + case CPU_DOWN_FAILED: + case CPU_ONLINE: + set_cpu_active(cpu, true); + sched_domains_numa_masks_set(cpu); + cpuset_cpu_active(action & CPU_TASKS_FROZEN); + return NOTIFY_OK; default: return NOTIFY_DONE; } - return NOTIFY_OK; +} + +static int sched_cpu_inactive(struct notifier_block *nfb, + unsigned long action, void *hcpu) +{ + unsigned int cpu = (unsigned long)hcpu; + int ret; + + switch (action & ~CPU_TASKS_FROZEN) { + case CPU_DOWN_PREPARE: + set_cpu_active(cpu, false); + ret = cpuset_cpu_inactive(cpu, action & CPU_TASKS_FROZEN); + if (ret) { + set_cpu_active(cpu, true); + return notifier_from_errno(ret); + } + return NOTIFY_OK; + + case CPU_DEAD: + sched_domains_numa_masks_clear(cpu); + return NOTIFY_OK; + default: + return NOTIFY_DONE; + } +} + +int sched_cpu_starting(unsigned int cpu) +{ + set_cpu_rq_start_time(cpu); + return 0; } void __init sched_init_smp(void) @@ -7469,10 +7437,6 @@ static int __init migration_init(void) cpu_notifier(sched_cpu_active, CPU_PRI_SCHED_ACTIVE); cpu_notifier(sched_cpu_inactive, CPU_PRI_SCHED_INACTIVE); - hotcpu_notifier(sched_domains_numa_masks_update, CPU_PRI_SCHED_ACTIVE); - hotcpu_notifier(cpuset_cpu_active, CPU_PRI_CPUSET_ACTIVE); - hotcpu_notifier(cpuset_cpu_inactive, CPU_PRI_CPUSET_INACTIVE); - return 0; } early_initcall(migration_init);