diff --git a/arch/alpha/include/asm/thread_info.h b/arch/alpha/include/asm/thread_info.h index 3d6ce6d56fc9..48bbea6898b3 100644 --- a/arch/alpha/include/asm/thread_info.h +++ b/arch/alpha/include/asm/thread_info.h @@ -73,12 +73,14 @@ register struct thread_info *__current_thread_info __asm__("$8"); #define TIF_SYSCALL_AUDIT 4 /* syscall audit active */ #define TIF_DIE_IF_KERNEL 9 /* dik recursion lock */ #define TIF_MEMDIE 13 /* is terminating due to OOM killer */ +#define TIF_POLLING_NRFLAG 14 /* idle is polling for TIF_NEED_RESCHED */ #define _TIF_SYSCALL_TRACE (1< #endif /* _ASM_S390_TOPOLOGY_H */ diff --git a/arch/s390/kernel/topology.c b/arch/s390/kernel/topology.c index fa3b8cdaadac..355a16c55702 100644 --- a/arch/s390/kernel/topology.c +++ b/arch/s390/kernel/topology.c @@ -445,6 +445,23 @@ int topology_cpu_init(struct cpu *cpu) return sysfs_create_group(&cpu->dev.kobj, &topology_cpu_attr_group); } +const struct cpumask *cpu_coregroup_mask(int cpu) +{ + return &cpu_topology[cpu].core_mask; +} + +static const struct cpumask *cpu_book_mask(int cpu) +{ + return &cpu_topology[cpu].book_mask; +} + +static struct sched_domain_topology_level s390_topology[] = { + { cpu_coregroup_mask, cpu_core_flags, SD_INIT_NAME(MC) }, + { cpu_book_mask, SD_INIT_NAME(BOOK) }, + { cpu_cpu_mask, SD_INIT_NAME(DIE) }, + { NULL, }, +}; + static int __init topology_init(void) { if (!MACHINE_HAS_TOPOLOGY) { @@ -453,6 +470,9 @@ static int __init topology_init(void) } set_topology_timer(); out: + + set_sched_topology(s390_topology); + return device_create_file(cpu_subsys.dev_root, &dev_attr_dispatching); } device_initcall(topology_init); diff --git a/arch/tile/include/asm/thread_info.h b/arch/tile/include/asm/thread_info.h index 729aa107f64e..d767ff9f59b9 100644 --- a/arch/tile/include/asm/thread_info.h +++ b/arch/tile/include/asm/thread_info.h @@ -129,6 +129,7 @@ extern void _cpu_idle(void); #define TIF_MEMDIE 7 /* OOM killer at work */ #define TIF_NOTIFY_RESUME 8 /* callback before returning to user */ #define TIF_SYSCALL_TRACEPOINT 9 /* syscall tracepoint instrumentation */ +#define TIF_POLLING_NRFLAG 10 /* idle is polling for TIF_NEED_RESCHED */ #define _TIF_SIGPENDING (1<status & TS_POLLING); - if (polling) { - current_thread_info()->status &= ~TS_POLLING; - /* - * TS_POLLING-cleared state must be visible before we - * test NEED_RESCHED: - */ - smp_mb(); - } if (!need_resched()) { idled = 1; ret = apm_bios_call_simple(APM_FUNC_IDLE, 0, 0, &eax, &err); } - if (polling) - current_thread_info()->status |= TS_POLLING; if (!idled) return 0; diff --git a/drivers/block/loop.c b/drivers/block/loop.c index f70a230a2945..6cb1beb47c25 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -548,7 +548,7 @@ static int loop_thread(void *data) struct loop_device *lo = data; struct bio *bio; - set_user_nice(current, -20); + set_user_nice(current, MIN_NICE); while (!kthread_should_stop() || !bio_list_empty(&lo->lo_bio_list)) { diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c index 3a70ea2f7cd6..56a027d6115e 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -533,7 +533,7 @@ static int nbd_thread(void *data) struct nbd_device *nbd = data; struct request *req; - set_user_nice(current, -20); + set_user_nice(current, MIN_NICE); while (!kthread_should_stop() || !list_empty(&nbd->waiting_queue)) { /* wait for something to do */ wait_event_interruptible(nbd->waiting_wq, diff --git a/drivers/block/pktcdvd.c b/drivers/block/pktcdvd.c index a2af73db187b..ef166ad2dbad 100644 --- a/drivers/block/pktcdvd.c +++ b/drivers/block/pktcdvd.c @@ -1463,7 +1463,7 @@ static int kcdrwd(void *foobar) struct packet_data *pkt; long min_sleep_time, residue; - set_user_nice(current, -20); + set_user_nice(current, MIN_NICE); set_freezable(); for (;;) { diff --git a/drivers/char/ipmi/ipmi_si_intf.c b/drivers/char/ipmi/ipmi_si_intf.c index 1c4bb4f6ce93..5d665680ae33 100644 --- a/drivers/char/ipmi/ipmi_si_intf.c +++ b/drivers/char/ipmi/ipmi_si_intf.c @@ -1007,7 +1007,7 @@ static int ipmi_thread(void *data) struct timespec busy_until; ipmi_si_set_not_busy(&busy_until); - set_user_nice(current, 19); + set_user_nice(current, MAX_NICE); while (!kthread_should_stop()) { int busy_wait; diff --git a/drivers/cpuidle/cpuidle.c b/drivers/cpuidle/cpuidle.c index 8236746e46bb..cb7019977c50 100644 --- a/drivers/cpuidle/cpuidle.c +++ b/drivers/cpuidle/cpuidle.c @@ -32,6 +32,7 @@ LIST_HEAD(cpuidle_detected_devices); static int enabled_devices; static int off __read_mostly; static int initialized __read_mostly; +static bool use_deepest_state __read_mostly; int cpuidle_disabled(void) { @@ -65,23 +66,42 @@ int cpuidle_play_dead(void) } /** - * cpuidle_enabled - check if the cpuidle framework is ready - * @dev: cpuidle device for this cpu - * @drv: cpuidle driver for this cpu + * cpuidle_use_deepest_state - Enable/disable the "deepest idle" mode. + * @enable: Whether enable or disable the feature. * - * Return 0 on success, otherwise: - * -NODEV : the cpuidle framework is not available - * -EBUSY : the cpuidle framework is not initialized + * If the "deepest idle" mode is enabled, cpuidle will ignore the governor and + * always use the state with the greatest exit latency (out of the states that + * are not disabled). + * + * This function can only be called after cpuidle_pause() to avoid races. */ -int cpuidle_enabled(struct cpuidle_driver *drv, struct cpuidle_device *dev) +void cpuidle_use_deepest_state(bool enable) { - if (off || !initialized) - return -ENODEV; + use_deepest_state = enable; +} - if (!drv || !dev || !dev->enabled) - return -EBUSY; +/** + * cpuidle_find_deepest_state - Find the state of the greatest exit latency. + * @drv: cpuidle driver for a given CPU. + * @dev: cpuidle device for a given CPU. + */ +static int cpuidle_find_deepest_state(struct cpuidle_driver *drv, + struct cpuidle_device *dev) +{ + unsigned int latency_req = 0; + int i, ret = CPUIDLE_DRIVER_STATE_START - 1; - return 0; + for (i = CPUIDLE_DRIVER_STATE_START; i < drv->state_count; i++) { + struct cpuidle_state *s = &drv->states[i]; + struct cpuidle_state_usage *su = &dev->states_usage[i]; + + if (s->disabled || su->disable || s->exit_latency <= latency_req) + continue; + + latency_req = s->exit_latency; + ret = i; + } + return ret; } /** @@ -138,6 +158,15 @@ int cpuidle_enter_state(struct cpuidle_device *dev, struct cpuidle_driver *drv, */ int cpuidle_select(struct cpuidle_driver *drv, struct cpuidle_device *dev) { + if (off || !initialized) + return -ENODEV; + + if (!drv || !dev || !dev->enabled) + return -EBUSY; + + if (unlikely(use_deepest_state)) + return cpuidle_find_deepest_state(drv, dev); + return cpuidle_curr_governor->select(drv, dev); } @@ -169,7 +198,7 @@ int cpuidle_enter(struct cpuidle_driver *drv, struct cpuidle_device *dev, */ void cpuidle_reflect(struct cpuidle_device *dev, int index) { - if (cpuidle_curr_governor->reflect) + if (cpuidle_curr_governor->reflect && !unlikely(use_deepest_state)) cpuidle_curr_governor->reflect(dev, index); } diff --git a/drivers/cpuidle/governors/menu.c b/drivers/cpuidle/governors/menu.c index 71b523293354..c4f80c15a48d 100644 --- a/drivers/cpuidle/governors/menu.c +++ b/drivers/cpuidle/governors/menu.c @@ -296,7 +296,7 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev) data->needs_update = 0; } - data->last_state_idx = 0; + data->last_state_idx = CPUIDLE_DRIVER_STATE_START - 1; /* Special case when user has set very strict latency requirement */ if (unlikely(latency_req == 0)) @@ -310,13 +310,6 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev) data->bucket = which_bucket(data->next_timer_us); - /* - * if the correction factor is 0 (eg first time init or cpu hotplug - * etc), we actually want to start out with a unity factor. - */ - if (data->correction_factor[data->bucket] == 0) - data->correction_factor[data->bucket] = RESOLUTION * DECAY; - /* * Force the result of multiplication to be 64 bits even if both * operands are 32 bits. @@ -466,9 +459,17 @@ static int menu_enable_device(struct cpuidle_driver *drv, struct cpuidle_device *dev) { struct menu_device *data = &per_cpu(menu_devices, dev->cpu); + int i; memset(data, 0, sizeof(struct menu_device)); + /* + * if the correction factor is 0 (eg first time init or cpu hotplug + * etc), we actually want to start out with a unity factor. + */ + for(i = 0; i < BUCKETS; i++) + data->correction_factor[i] = RESOLUTION * DECAY; + return 0; } diff --git a/drivers/s390/crypto/ap_bus.c b/drivers/s390/crypto/ap_bus.c index ab3baa7f9508..8eec1653c9cc 100644 --- a/drivers/s390/crypto/ap_bus.c +++ b/drivers/s390/crypto/ap_bus.c @@ -1803,7 +1803,7 @@ static int ap_poll_thread(void *data) int requests; struct ap_device *ap_dev; - set_user_nice(current, 19); + set_user_nice(current, MAX_NICE); while (1) { if (ap_suspend_flag) return 0; diff --git a/drivers/scsi/bnx2fc/bnx2fc_fcoe.c b/drivers/scsi/bnx2fc/bnx2fc_fcoe.c index 1d41f4b9114f..f54843023466 100644 --- a/drivers/scsi/bnx2fc/bnx2fc_fcoe.c +++ b/drivers/scsi/bnx2fc/bnx2fc_fcoe.c @@ -464,7 +464,7 @@ static int bnx2fc_l2_rcv_thread(void *arg) struct fcoe_percpu_s *bg = arg; struct sk_buff *skb; - set_user_nice(current, -20); + set_user_nice(current, MIN_NICE); set_current_state(TASK_INTERRUPTIBLE); while (!kthread_should_stop()) { schedule(); @@ -602,7 +602,7 @@ int bnx2fc_percpu_io_thread(void *arg) struct bnx2fc_work *work, *tmp; LIST_HEAD(work_list); - set_user_nice(current, -20); + set_user_nice(current, MIN_NICE); set_current_state(TASK_INTERRUPTIBLE); while (!kthread_should_stop()) { schedule(); diff --git a/drivers/scsi/bnx2i/bnx2i_hwi.c b/drivers/scsi/bnx2i/bnx2i_hwi.c index b5ffd280a1ae..d6d491c2f004 100644 --- a/drivers/scsi/bnx2i/bnx2i_hwi.c +++ b/drivers/scsi/bnx2i/bnx2i_hwi.c @@ -1870,7 +1870,7 @@ int bnx2i_percpu_io_thread(void *arg) struct bnx2i_work *work, *tmp; LIST_HEAD(work_list); - set_user_nice(current, -20); + set_user_nice(current, MIN_NICE); while (!kthread_should_stop()) { spin_lock_bh(&p->p_work_lock); diff --git a/drivers/scsi/fcoe/fcoe.c b/drivers/scsi/fcoe/fcoe.c index d5e105b173f0..00ee0ed642aa 100644 --- a/drivers/scsi/fcoe/fcoe.c +++ b/drivers/scsi/fcoe/fcoe.c @@ -1872,7 +1872,7 @@ static int fcoe_percpu_receive_thread(void *arg) skb_queue_head_init(&tmp); - set_user_nice(current, -20); + set_user_nice(current, MIN_NICE); retry: while (!kthread_should_stop()) { diff --git a/drivers/scsi/ibmvscsi/ibmvfc.c b/drivers/scsi/ibmvscsi/ibmvfc.c index 23f5ba5e6472..8dd47689d584 100644 --- a/drivers/scsi/ibmvscsi/ibmvfc.c +++ b/drivers/scsi/ibmvscsi/ibmvfc.c @@ -4515,7 +4515,7 @@ static int ibmvfc_work(void *data) struct ibmvfc_host *vhost = data; int rc; - set_user_nice(current, -20); + set_user_nice(current, MIN_NICE); while (1) { rc = wait_event_interruptible(vhost->work_wait_q, diff --git a/drivers/scsi/ibmvscsi/ibmvscsi.c b/drivers/scsi/ibmvscsi/ibmvscsi.c index fa764406df68..2ebfb2bb0f42 100644 --- a/drivers/scsi/ibmvscsi/ibmvscsi.c +++ b/drivers/scsi/ibmvscsi/ibmvscsi.c @@ -2213,7 +2213,7 @@ static int ibmvscsi_work(void *data) struct ibmvscsi_host_data *hostdata = data; int rc; - set_user_nice(current, -20); + set_user_nice(current, MIN_NICE); while (1) { rc = wait_event_interruptible(hostdata->work_wait_q, diff --git a/drivers/scsi/lpfc/lpfc_hbadisc.c b/drivers/scsi/lpfc/lpfc_hbadisc.c index 59b51c529ba0..294c072e9083 100644 --- a/drivers/scsi/lpfc/lpfc_hbadisc.c +++ b/drivers/scsi/lpfc/lpfc_hbadisc.c @@ -731,7 +731,7 @@ lpfc_do_work(void *p) struct lpfc_hba *phba = p; int rc; - set_user_nice(current, -20); + set_user_nice(current, MIN_NICE); current->flags |= PF_NOFREEZE; phba->data_flags = 0; diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c index 19e99cc33724..afc84814e9bb 100644 --- a/drivers/scsi/qla2xxx/qla_os.c +++ b/drivers/scsi/qla2xxx/qla_os.c @@ -4828,7 +4828,7 @@ qla2x00_do_dpc(void *data) ha = (struct qla_hw_data *)data; base_vha = pci_get_drvdata(ha->pdev); - set_user_nice(current, -20); + set_user_nice(current, MIN_NICE); set_current_state(TASK_INTERRUPTIBLE); while (!kthread_should_stop()) { diff --git a/drivers/staging/android/binder.c b/drivers/staging/android/binder.c index 989f809f323f..a741da77828a 100644 --- a/drivers/staging/android/binder.c +++ b/drivers/staging/android/binder.c @@ -439,12 +439,12 @@ static void binder_set_nice(long nice) set_user_nice(current, nice); return; } - min_nice = 20 - current->signal->rlim[RLIMIT_NICE].rlim_cur; + min_nice = rlimit_to_nice(current->signal->rlim[RLIMIT_NICE].rlim_cur); binder_debug(BINDER_DEBUG_PRIORITY_CAP, "%d: nice value %ld not allowed use %ld instead\n", current->pid, nice, min_nice); set_user_nice(current, min_nice); - if (min_nice < 20) + if (min_nice <= MAX_NICE) return; binder_user_error("%d RLIMIT_NICE not set\n", current->pid); } diff --git a/drivers/staging/lustre/lustre/llite/lloop.c b/drivers/staging/lustre/lustre/llite/lloop.c index b9694b8cb5dd..0ff8c3362a8d 100644 --- a/drivers/staging/lustre/lustre/llite/lloop.c +++ b/drivers/staging/lustre/lustre/llite/lloop.c @@ -404,7 +404,7 @@ static int loop_thread(void *data) int refcheck; int ret = 0; - set_user_nice(current, -20); + set_user_nice(current, MIN_NICE); lo->lo_state = LLOOP_BOUND; diff --git a/fs/ocfs2/cluster/heartbeat.c b/fs/ocfs2/cluster/heartbeat.c index bf482dfed14f..73039295d0d1 100644 --- a/fs/ocfs2/cluster/heartbeat.c +++ b/fs/ocfs2/cluster/heartbeat.c @@ -1107,7 +1107,7 @@ static int o2hb_thread(void *data) mlog(ML_HEARTBEAT|ML_KTHREAD, "hb thread running\n"); - set_user_nice(current, -20); + set_user_nice(current, MIN_NICE); /* Pin node */ o2nm_depend_this_node(); diff --git a/include/linux/cpuidle.h b/include/linux/cpuidle.h index b0238cba440b..c51a436135c4 100644 --- a/include/linux/cpuidle.h +++ b/include/linux/cpuidle.h @@ -120,8 +120,6 @@ struct cpuidle_driver { #ifdef CONFIG_CPU_IDLE extern void disable_cpuidle(void); -extern int cpuidle_enabled(struct cpuidle_driver *drv, - struct cpuidle_device *dev); extern int cpuidle_select(struct cpuidle_driver *drv, struct cpuidle_device *dev); extern int cpuidle_enter(struct cpuidle_driver *drv, @@ -145,13 +143,11 @@ extern void cpuidle_resume(void); extern int cpuidle_enable_device(struct cpuidle_device *dev); extern void cpuidle_disable_device(struct cpuidle_device *dev); extern int cpuidle_play_dead(void); +extern void cpuidle_use_deepest_state(bool enable); extern struct cpuidle_driver *cpuidle_get_cpu_driver(struct cpuidle_device *dev); #else static inline void disable_cpuidle(void) { } -static inline int cpuidle_enabled(struct cpuidle_driver *drv, - struct cpuidle_device *dev) -{return -ENODEV; } static inline int cpuidle_select(struct cpuidle_driver *drv, struct cpuidle_device *dev) {return -ENODEV; } @@ -180,6 +176,7 @@ static inline int cpuidle_enable_device(struct cpuidle_device *dev) {return -ENODEV; } static inline void cpuidle_disable_device(struct cpuidle_device *dev) { } static inline int cpuidle_play_dead(void) {return -ENODEV; } +static inline void cpuidle_use_deepest_state(bool enable) {} static inline struct cpuidle_driver *cpuidle_get_cpu_driver( struct cpuidle_device *dev) {return NULL; } #endif diff --git a/include/linux/sched.h b/include/linux/sched.h index 4dce5d844b74..70f67e4e6156 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -870,6 +870,7 @@ enum cpu_idle_type { #define SD_BALANCE_WAKE 0x0010 /* Balance on wakeup */ #define SD_WAKE_AFFINE 0x0020 /* Wake task to waking CPU */ #define SD_SHARE_CPUPOWER 0x0080 /* Domain members share cpu power */ +#define SD_SHARE_POWERDOMAIN 0x0100 /* Domain members share power domain */ #define SD_SHARE_PKG_RESOURCES 0x0200 /* Domain members share cpu pkg resources */ #define SD_SERIALIZE 0x0400 /* Only a single load balancing instance */ #define SD_ASYM_PACKING 0x0800 /* Place busy groups earlier in the domain */ @@ -877,7 +878,26 @@ enum cpu_idle_type { #define SD_OVERLAP 0x2000 /* sched_domains of this level overlap */ #define SD_NUMA 0x4000 /* cross-node balancing */ -extern int __weak arch_sd_sibiling_asym_packing(void); +#ifdef CONFIG_SCHED_SMT +static inline const int cpu_smt_flags(void) +{ + return SD_SHARE_CPUPOWER | SD_SHARE_PKG_RESOURCES; +} +#endif + +#ifdef CONFIG_SCHED_MC +static inline const int cpu_core_flags(void) +{ + return SD_SHARE_PKG_RESOURCES; +} +#endif + +#ifdef CONFIG_NUMA +static inline const int cpu_numa_flags(void) +{ + return SD_NUMA; +} +#endif struct sched_domain_attr { int relax_domain_level; @@ -985,6 +1005,38 @@ void free_sched_domains(cpumask_var_t doms[], unsigned int ndoms); bool cpus_share_cache(int this_cpu, int that_cpu); +typedef const struct cpumask *(*sched_domain_mask_f)(int cpu); +typedef const int (*sched_domain_flags_f)(void); + +#define SDTL_OVERLAP 0x01 + +struct sd_data { + struct sched_domain **__percpu sd; + struct sched_group **__percpu sg; + struct sched_group_power **__percpu sgp; +}; + +struct sched_domain_topology_level { + sched_domain_mask_f mask; + sched_domain_flags_f sd_flags; + int flags; + int numa_level; + struct sd_data data; +#ifdef CONFIG_SCHED_DEBUG + char *name; +#endif +}; + +extern struct sched_domain_topology_level *sched_domain_topology; + +extern void set_sched_topology(struct sched_domain_topology_level *tl); + +#ifdef CONFIG_SCHED_DEBUG +# define SD_INIT_NAME(type) .name = #type +#else +# define SD_INIT_NAME(type) +#endif + #else /* CONFIG_SMP */ struct sched_domain_attr; @@ -1123,8 +1175,8 @@ struct sched_dl_entity { /* * Original scheduling parameters. Copied here from sched_attr - * during sched_setscheduler2(), they will remain the same until - * the next sched_setscheduler2(). + * during sched_setattr(), they will remain the same until + * the next sched_setattr(). */ u64 dl_runtime; /* maximum runtime for each instance */ u64 dl_deadline; /* relative deadline of each instance */ @@ -2723,51 +2775,9 @@ static inline int spin_needbreak(spinlock_t *lock) /* * Idle thread specific functions to determine the need_resched - * polling state. We have two versions, one based on TS_POLLING in - * thread_info.status and one based on TIF_POLLING_NRFLAG in - * thread_info.flags + * polling state. */ -#ifdef TS_POLLING -static inline int tsk_is_polling(struct task_struct *p) -{ - return task_thread_info(p)->status & TS_POLLING; -} -static inline void __current_set_polling(void) -{ - current_thread_info()->status |= TS_POLLING; -} - -static inline bool __must_check current_set_polling_and_test(void) -{ - __current_set_polling(); - - /* - * Polling state must be visible before we test NEED_RESCHED, - * paired by resched_task() - */ - smp_mb(); - - return unlikely(tif_need_resched()); -} - -static inline void __current_clr_polling(void) -{ - current_thread_info()->status &= ~TS_POLLING; -} - -static inline bool __must_check current_clr_polling_and_test(void) -{ - __current_clr_polling(); - - /* - * Polling state must be visible before we test NEED_RESCHED, - * paired by resched_task() - */ - smp_mb(); - - return unlikely(tif_need_resched()); -} -#elif defined(TIF_POLLING_NRFLAG) +#ifdef TIF_POLLING_NRFLAG static inline int tsk_is_polling(struct task_struct *p) { return test_tsk_thread_flag(p, TIF_POLLING_NRFLAG); diff --git a/include/linux/sched/prio.h b/include/linux/sched/prio.h index ac322583c820..d9cf5a5762d9 100644 --- a/include/linux/sched/prio.h +++ b/include/linux/sched/prio.h @@ -41,4 +41,20 @@ #define TASK_USER_PRIO(p) USER_PRIO((p)->static_prio) #define MAX_USER_PRIO (USER_PRIO(MAX_PRIO)) +/* + * Convert nice value [19,-20] to rlimit style value [1,40]. + */ +static inline long nice_to_rlimit(long nice) +{ + return (MAX_NICE - nice + 1); +} + +/* + * Convert rlimit style value [1,40] to nice value [-20, 19]. + */ +static inline long rlimit_to_nice(long prio) +{ + return (MAX_NICE - prio + 1); +} + #endif /* _SCHED_PRIO_H */ diff --git a/include/linux/thread_info.h b/include/linux/thread_info.h index fddbe2023a5d..cb0cec94fda3 100644 --- a/include/linux/thread_info.h +++ b/include/linux/thread_info.h @@ -104,20 +104,6 @@ static inline int test_ti_thread_flag(struct thread_info *ti, int flag) #define test_thread_flag(flag) \ test_ti_thread_flag(current_thread_info(), flag) -static inline __deprecated void set_need_resched(void) -{ - /* - * Use of this function in deprecated. - * - * As of this writing there are only a few users in the DRM tree left - * all of which are wrong and can be removed without causing too much - * grief. - * - * The DRM people are aware and are working on removing the last few - * instances. - */ -} - #define tif_need_resched() test_thread_flag(TIF_NEED_RESCHED) #if defined TIF_RESTORE_SIGMASK && !defined HAVE_SET_RESTORE_SIGMASK diff --git a/include/linux/topology.h b/include/linux/topology.h index 7062330a1329..973671ff9e7d 100644 --- a/include/linux/topology.h +++ b/include/linux/topology.h @@ -66,121 +66,6 @@ int arch_update_cpu_topology(void); #define PENALTY_FOR_NODE_WITH_CPUS (1) #endif -/* - * Below are the 3 major initializers used in building sched_domains: - * SD_SIBLING_INIT, for SMT domains - * SD_CPU_INIT, for SMP domains - * - * Any architecture that cares to do any tuning to these values should do so - * by defining their own arch-specific initializer in include/asm/topology.h. - * A definition there will automagically override these default initializers - * and allow arch-specific performance tuning of sched_domains. - * (Only non-zero and non-null fields need be specified.) - */ - -#ifdef CONFIG_SCHED_SMT -/* MCD - Do we really need this? It is always on if CONFIG_SCHED_SMT is, - * so can't we drop this in favor of CONFIG_SCHED_SMT? - */ -#define ARCH_HAS_SCHED_WAKE_IDLE -/* Common values for SMT siblings */ -#ifndef SD_SIBLING_INIT -#define SD_SIBLING_INIT (struct sched_domain) { \ - .min_interval = 1, \ - .max_interval = 2, \ - .busy_factor = 64, \ - .imbalance_pct = 110, \ - \ - .flags = 1*SD_LOAD_BALANCE \ - | 1*SD_BALANCE_NEWIDLE \ - | 1*SD_BALANCE_EXEC \ - | 1*SD_BALANCE_FORK \ - | 0*SD_BALANCE_WAKE \ - | 1*SD_WAKE_AFFINE \ - | 1*SD_SHARE_CPUPOWER \ - | 1*SD_SHARE_PKG_RESOURCES \ - | 0*SD_SERIALIZE \ - | 0*SD_PREFER_SIBLING \ - | arch_sd_sibling_asym_packing() \ - , \ - .last_balance = jiffies, \ - .balance_interval = 1, \ - .smt_gain = 1178, /* 15% */ \ - .max_newidle_lb_cost = 0, \ - .next_decay_max_lb_cost = jiffies, \ -} -#endif -#endif /* CONFIG_SCHED_SMT */ - -#ifdef CONFIG_SCHED_MC -/* Common values for MC siblings. for now mostly derived from SD_CPU_INIT */ -#ifndef SD_MC_INIT -#define SD_MC_INIT (struct sched_domain) { \ - .min_interval = 1, \ - .max_interval = 4, \ - .busy_factor = 64, \ - .imbalance_pct = 125, \ - .cache_nice_tries = 1, \ - .busy_idx = 2, \ - .wake_idx = 0, \ - .forkexec_idx = 0, \ - \ - .flags = 1*SD_LOAD_BALANCE \ - | 1*SD_BALANCE_NEWIDLE \ - | 1*SD_BALANCE_EXEC \ - | 1*SD_BALANCE_FORK \ - | 0*SD_BALANCE_WAKE \ - | 1*SD_WAKE_AFFINE \ - | 0*SD_SHARE_CPUPOWER \ - | 1*SD_SHARE_PKG_RESOURCES \ - | 0*SD_SERIALIZE \ - , \ - .last_balance = jiffies, \ - .balance_interval = 1, \ - .max_newidle_lb_cost = 0, \ - .next_decay_max_lb_cost = jiffies, \ -} -#endif -#endif /* CONFIG_SCHED_MC */ - -/* Common values for CPUs */ -#ifndef SD_CPU_INIT -#define SD_CPU_INIT (struct sched_domain) { \ - .min_interval = 1, \ - .max_interval = 4, \ - .busy_factor = 64, \ - .imbalance_pct = 125, \ - .cache_nice_tries = 1, \ - .busy_idx = 2, \ - .idle_idx = 1, \ - .newidle_idx = 0, \ - .wake_idx = 0, \ - .forkexec_idx = 0, \ - \ - .flags = 1*SD_LOAD_BALANCE \ - | 1*SD_BALANCE_NEWIDLE \ - | 1*SD_BALANCE_EXEC \ - | 1*SD_BALANCE_FORK \ - | 0*SD_BALANCE_WAKE \ - | 1*SD_WAKE_AFFINE \ - | 0*SD_SHARE_CPUPOWER \ - | 0*SD_SHARE_PKG_RESOURCES \ - | 0*SD_SERIALIZE \ - | 1*SD_PREFER_SIBLING \ - , \ - .last_balance = jiffies, \ - .balance_interval = 1, \ - .max_newidle_lb_cost = 0, \ - .next_decay_max_lb_cost = jiffies, \ -} -#endif - -#ifdef CONFIG_SCHED_BOOK -#ifndef SD_BOOK_INIT -#error Please define an appropriate SD_BOOK_INIT in include/asm/topology.h!!! -#endif -#endif /* CONFIG_SCHED_BOOK */ - #ifdef CONFIG_USE_PERCPU_NUMA_NODE_ID DECLARE_PER_CPU(int, numa_node); @@ -295,4 +180,17 @@ static inline int cpu_to_mem(int cpu) #define topology_core_cpumask(cpu) cpumask_of(cpu) #endif +#ifdef CONFIG_SCHED_SMT +static inline const struct cpumask *cpu_smt_mask(int cpu) +{ + return topology_thread_cpumask(cpu); +} +#endif + +static inline const struct cpumask *cpu_cpu_mask(int cpu) +{ + return cpumask_of_node(cpu_to_node(cpu)); +} + + #endif /* _LINUX_TOPOLOGY_H */ diff --git a/kernel/locking/locktorture.c b/kernel/locking/locktorture.c index dbafeac18e4d..0955b885d0dc 100644 --- a/kernel/locking/locktorture.c +++ b/kernel/locking/locktorture.c @@ -216,7 +216,7 @@ static int lock_torture_writer(void *arg) static DEFINE_TORTURE_RANDOM(rand); VERBOSE_TOROUT_STRING("lock_torture_writer task started"); - set_user_nice(current, 19); + set_user_nice(current, MAX_NICE); do { if ((torture_random(&rand) & 0xfffff) == 0) diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c index 8233cd4047d7..155721f7f909 100644 --- a/kernel/power/suspend.c +++ b/kernel/power/suspend.c @@ -54,9 +54,11 @@ static void freeze_begin(void) static void freeze_enter(void) { + cpuidle_use_deepest_state(true); cpuidle_resume(); wait_event(suspend_freeze_wait_head, suspend_freeze_wake); cpuidle_pause(); + cpuidle_use_deepest_state(false); } void freeze_wake(void) diff --git a/kernel/sched/core.c b/kernel/sched/core.c index a62a7dec3986..913c6d6cc2c1 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -521,6 +521,39 @@ static inline void init_hrtick(void) } #endif /* CONFIG_SCHED_HRTICK */ +/* + * cmpxchg based fetch_or, macro so it works for different integer types + */ +#define fetch_or(ptr, val) \ +({ typeof(*(ptr)) __old, __val = *(ptr); \ + for (;;) { \ + __old = cmpxchg((ptr), __val, __val | (val)); \ + if (__old == __val) \ + break; \ + __val = __old; \ + } \ + __old; \ +}) + +#ifdef TIF_POLLING_NRFLAG +/* + * Atomically set TIF_NEED_RESCHED and test for TIF_POLLING_NRFLAG, + * this avoids any races wrt polling state changes and thereby avoids + * spurious IPIs. + */ +static bool set_nr_and_not_polling(struct task_struct *p) +{ + struct thread_info *ti = task_thread_info(p); + return !(fetch_or(&ti->flags, _TIF_NEED_RESCHED) & _TIF_POLLING_NRFLAG); +} +#else +static bool set_nr_and_not_polling(struct task_struct *p) +{ + set_tsk_need_resched(p); + return true; +} +#endif + /* * resched_task - mark a task 'to be rescheduled now'. * @@ -537,17 +570,15 @@ void resched_task(struct task_struct *p) if (test_tsk_need_resched(p)) return; - set_tsk_need_resched(p); - cpu = task_cpu(p); + if (cpu == smp_processor_id()) { + set_tsk_need_resched(p); set_preempt_need_resched(); return; } - /* NEED_RESCHED must be visible before we test polling */ - smp_mb(); - if (!tsk_is_polling(p)) + if (set_nr_and_not_polling(p)) smp_send_reschedule(cpu); } @@ -3018,7 +3049,7 @@ EXPORT_SYMBOL(set_user_nice); int can_nice(const struct task_struct *p, const int nice) { /* convert nice value [19,-20] to rlimit style value [1,40] */ - int nice_rlim = 20 - nice; + int nice_rlim = nice_to_rlimit(nice); return (nice_rlim <= task_rlimit(p, RLIMIT_NICE) || capable(CAP_SYS_NICE)); @@ -3042,17 +3073,10 @@ SYSCALL_DEFINE1(nice, int, increment) * We don't have to worry. Conceptually one call occurs first * and we have a single winner. */ - if (increment < -40) - increment = -40; - if (increment > 40) - increment = 40; - + increment = clamp(increment, -NICE_WIDTH, NICE_WIDTH); nice = task_nice(current) + increment; - if (nice < MIN_NICE) - nice = MIN_NICE; - if (nice > MAX_NICE) - nice = MAX_NICE; + nice = clamp_val(nice, MIN_NICE, MAX_NICE); if (increment < 0 && !can_nice(current, nice)) return -EPERM; @@ -3642,13 +3666,11 @@ static int sched_copy_attr(struct sched_attr __user *uattr, */ attr->sched_nice = clamp(attr->sched_nice, MIN_NICE, MAX_NICE); -out: - return ret; + return 0; err_size: put_user(sizeof(*attr), &uattr->size); - ret = -E2BIG; - goto out; + return -E2BIG; } /** @@ -3808,7 +3830,7 @@ static int sched_read_attr(struct sched_attr __user *uattr, for (; addr < end; addr++) { if (*addr) - goto err_size; + return -EFBIG; } attr->size = usize; @@ -3818,12 +3840,7 @@ static int sched_read_attr(struct sched_attr __user *uattr, if (ret) return -EFAULT; -out: - return ret; - -err_size: - ret = -E2BIG; - goto out; + return 0; } /** @@ -5093,10 +5110,20 @@ static struct notifier_block migration_notifier = { .priority = CPU_PRI_MIGRATION, }; +static void __cpuinit set_cpu_rq_start_time(void) +{ + int cpu = smp_processor_id(); + struct rq *rq = cpu_rq(cpu); + rq->age_stamp = sched_clock_cpu(cpu); +} + static int sched_cpu_active(struct notifier_block *nfb, unsigned long action, void *hcpu) { switch (action & ~CPU_TASKS_FROZEN) { + case CPU_STARTING: + set_cpu_rq_start_time(); + return NOTIFY_OK; case CPU_DOWN_FAILED: set_cpu_active((long)hcpu, true); return NOTIFY_OK; @@ -5305,7 +5332,8 @@ static int sd_degenerate(struct sched_domain *sd) SD_BALANCE_FORK | SD_BALANCE_EXEC | SD_SHARE_CPUPOWER | - SD_SHARE_PKG_RESOURCES)) { + SD_SHARE_PKG_RESOURCES | + SD_SHARE_POWERDOMAIN)) { if (sd->groups != sd->groups->next) return 0; } @@ -5336,7 +5364,8 @@ sd_parent_degenerate(struct sched_domain *sd, struct sched_domain *parent) SD_BALANCE_EXEC | SD_SHARE_CPUPOWER | SD_SHARE_PKG_RESOURCES | - SD_PREFER_SIBLING); + SD_PREFER_SIBLING | + SD_SHARE_POWERDOMAIN); if (nr_node_ids == 1) pflags &= ~SD_SERIALIZE; } @@ -5610,17 +5639,6 @@ static int __init isolated_cpu_setup(char *str) __setup("isolcpus=", isolated_cpu_setup); -static const struct cpumask *cpu_cpu_mask(int cpu) -{ - return cpumask_of_node(cpu_to_node(cpu)); -} - -struct sd_data { - struct sched_domain **__percpu sd; - struct sched_group **__percpu sg; - struct sched_group_power **__percpu sgp; -}; - struct s_data { struct sched_domain ** __percpu sd; struct root_domain *rd; @@ -5633,21 +5651,6 @@ enum s_alloc { sa_none, }; -struct sched_domain_topology_level; - -typedef struct sched_domain *(*sched_domain_init_f)(struct sched_domain_topology_level *tl, int cpu); -typedef const struct cpumask *(*sched_domain_mask_f)(int cpu); - -#define SDTL_OVERLAP 0x01 - -struct sched_domain_topology_level { - sched_domain_init_f init; - sched_domain_mask_f mask; - int flags; - int numa_level; - struct sd_data data; -}; - /* * Build an iteration mask that can exclude certain CPUs from the upwards * domain traversal. @@ -5815,8 +5818,6 @@ build_sched_groups(struct sched_domain *sd, int cpu) continue; group = get_group(i, sdd, &sg); - cpumask_clear(sched_group_cpus(sg)); - sg->sgp->power = 0; cpumask_setall(sched_group_mask(sg)); for_each_cpu(j, span) { @@ -5866,44 +5867,11 @@ static void init_sched_groups_power(int cpu, struct sched_domain *sd) atomic_set(&sg->sgp->nr_busy_cpus, sg->group_weight); } -int __weak arch_sd_sibling_asym_packing(void) -{ - return 0*SD_ASYM_PACKING; -} - /* * Initializers for schedule domains * Non-inlined to reduce accumulated stack pressure in build_sched_domains() */ -#ifdef CONFIG_SCHED_DEBUG -# define SD_INIT_NAME(sd, type) sd->name = #type -#else -# define SD_INIT_NAME(sd, type) do { } while (0) -#endif - -#define SD_INIT_FUNC(type) \ -static noinline struct sched_domain * \ -sd_init_##type(struct sched_domain_topology_level *tl, int cpu) \ -{ \ - struct sched_domain *sd = *per_cpu_ptr(tl->data.sd, cpu); \ - *sd = SD_##type##_INIT; \ - SD_INIT_NAME(sd, type); \ - sd->private = &tl->data; \ - return sd; \ -} - -SD_INIT_FUNC(CPU) -#ifdef CONFIG_SCHED_SMT - SD_INIT_FUNC(SIBLING) -#endif -#ifdef CONFIG_SCHED_MC - SD_INIT_FUNC(MC) -#endif -#ifdef CONFIG_SCHED_BOOK - SD_INIT_FUNC(BOOK) -#endif - static int default_relax_domain_level = -1; int sched_domain_level_max; @@ -5991,99 +5959,154 @@ static void claim_allocations(int cpu, struct sched_domain *sd) *per_cpu_ptr(sdd->sgp, cpu) = NULL; } -#ifdef CONFIG_SCHED_SMT -static const struct cpumask *cpu_smt_mask(int cpu) -{ - return topology_thread_cpumask(cpu); -} -#endif - -/* - * Topology list, bottom-up. - */ -static struct sched_domain_topology_level default_topology[] = { -#ifdef CONFIG_SCHED_SMT - { sd_init_SIBLING, cpu_smt_mask, }, -#endif -#ifdef CONFIG_SCHED_MC - { sd_init_MC, cpu_coregroup_mask, }, -#endif -#ifdef CONFIG_SCHED_BOOK - { sd_init_BOOK, cpu_book_mask, }, -#endif - { sd_init_CPU, cpu_cpu_mask, }, - { NULL, }, -}; - -static struct sched_domain_topology_level *sched_domain_topology = default_topology; - -#define for_each_sd_topology(tl) \ - for (tl = sched_domain_topology; tl->init; tl++) - #ifdef CONFIG_NUMA - static int sched_domains_numa_levels; static int *sched_domains_numa_distance; static struct cpumask ***sched_domains_numa_masks; static int sched_domains_curr_level; +#endif -static inline int sd_local_flags(int level) -{ - if (sched_domains_numa_distance[level] > RECLAIM_DISTANCE) - return 0; - - return SD_BALANCE_EXEC | SD_BALANCE_FORK | SD_WAKE_AFFINE; -} +/* + * SD_flags allowed in topology descriptions. + * + * SD_SHARE_CPUPOWER - describes SMT topologies + * SD_SHARE_PKG_RESOURCES - describes shared caches + * SD_NUMA - describes NUMA topologies + * SD_SHARE_POWERDOMAIN - describes shared power domain + * + * Odd one out: + * SD_ASYM_PACKING - describes SMT quirks + */ +#define TOPOLOGY_SD_FLAGS \ + (SD_SHARE_CPUPOWER | \ + SD_SHARE_PKG_RESOURCES | \ + SD_NUMA | \ + SD_ASYM_PACKING | \ + SD_SHARE_POWERDOMAIN) static struct sched_domain * -sd_numa_init(struct sched_domain_topology_level *tl, int cpu) +sd_init(struct sched_domain_topology_level *tl, int cpu) { struct sched_domain *sd = *per_cpu_ptr(tl->data.sd, cpu); - int level = tl->numa_level; - int sd_weight = cpumask_weight( - sched_domains_numa_masks[level][cpu_to_node(cpu)]); + int sd_weight, sd_flags = 0; + +#ifdef CONFIG_NUMA + /* + * Ugly hack to pass state to sd_numa_mask()... + */ + sched_domains_curr_level = tl->numa_level; +#endif + + sd_weight = cpumask_weight(tl->mask(cpu)); + + if (tl->sd_flags) + sd_flags = (*tl->sd_flags)(); + if (WARN_ONCE(sd_flags & ~TOPOLOGY_SD_FLAGS, + "wrong sd_flags in topology description\n")) + sd_flags &= ~TOPOLOGY_SD_FLAGS; *sd = (struct sched_domain){ .min_interval = sd_weight, .max_interval = 2*sd_weight, .busy_factor = 32, .imbalance_pct = 125, - .cache_nice_tries = 2, - .busy_idx = 3, - .idle_idx = 2, + + .cache_nice_tries = 0, + .busy_idx = 0, + .idle_idx = 0, .newidle_idx = 0, .wake_idx = 0, .forkexec_idx = 0, .flags = 1*SD_LOAD_BALANCE | 1*SD_BALANCE_NEWIDLE - | 0*SD_BALANCE_EXEC - | 0*SD_BALANCE_FORK + | 1*SD_BALANCE_EXEC + | 1*SD_BALANCE_FORK | 0*SD_BALANCE_WAKE - | 0*SD_WAKE_AFFINE + | 1*SD_WAKE_AFFINE | 0*SD_SHARE_CPUPOWER | 0*SD_SHARE_PKG_RESOURCES - | 1*SD_SERIALIZE + | 0*SD_SERIALIZE | 0*SD_PREFER_SIBLING - | 1*SD_NUMA - | sd_local_flags(level) + | 0*SD_NUMA + | sd_flags , + .last_balance = jiffies, .balance_interval = sd_weight, + .smt_gain = 0, .max_newidle_lb_cost = 0, .next_decay_max_lb_cost = jiffies, +#ifdef CONFIG_SCHED_DEBUG + .name = tl->name, +#endif }; - SD_INIT_NAME(sd, NUMA); - sd->private = &tl->data; /* - * Ugly hack to pass state to sd_numa_mask()... + * Convert topological properties into behaviour. */ - sched_domains_curr_level = tl->numa_level; + + if (sd->flags & SD_SHARE_CPUPOWER) { + sd->imbalance_pct = 110; + sd->smt_gain = 1178; /* ~15% */ + + } else if (sd->flags & SD_SHARE_PKG_RESOURCES) { + sd->imbalance_pct = 117; + sd->cache_nice_tries = 1; + sd->busy_idx = 2; + +#ifdef CONFIG_NUMA + } else if (sd->flags & SD_NUMA) { + sd->cache_nice_tries = 2; + sd->busy_idx = 3; + sd->idle_idx = 2; + + sd->flags |= SD_SERIALIZE; + if (sched_domains_numa_distance[tl->numa_level] > RECLAIM_DISTANCE) { + sd->flags &= ~(SD_BALANCE_EXEC | + SD_BALANCE_FORK | + SD_WAKE_AFFINE); + } + +#endif + } else { + sd->flags |= SD_PREFER_SIBLING; + sd->cache_nice_tries = 1; + sd->busy_idx = 2; + sd->idle_idx = 1; + } + + sd->private = &tl->data; return sd; } +/* + * Topology list, bottom-up. + */ +static struct sched_domain_topology_level default_topology[] = { +#ifdef CONFIG_SCHED_SMT + { cpu_smt_mask, cpu_smt_flags, SD_INIT_NAME(SMT) }, +#endif +#ifdef CONFIG_SCHED_MC + { cpu_coregroup_mask, cpu_core_flags, SD_INIT_NAME(MC) }, +#endif + { cpu_cpu_mask, SD_INIT_NAME(DIE) }, + { NULL, }, +}; + +struct sched_domain_topology_level *sched_domain_topology = default_topology; + +#define for_each_sd_topology(tl) \ + for (tl = sched_domain_topology; tl->mask; tl++) + +void set_sched_topology(struct sched_domain_topology_level *tl) +{ + sched_domain_topology = tl; +} + +#ifdef CONFIG_NUMA + static const struct cpumask *sd_numa_mask(int cpu) { return sched_domains_numa_masks[sched_domains_curr_level][cpu_to_node(cpu)]; @@ -6227,7 +6250,10 @@ static void sched_init_numa(void) } } - tl = kzalloc((ARRAY_SIZE(default_topology) + level) * + /* Compute default topology size */ + for (i = 0; sched_domain_topology[i].mask; i++); + + tl = kzalloc((i + level + 1) * sizeof(struct sched_domain_topology_level), GFP_KERNEL); if (!tl) return; @@ -6235,18 +6261,19 @@ static void sched_init_numa(void) /* * Copy the default topology bits.. */ - for (i = 0; default_topology[i].init; i++) - tl[i] = default_topology[i]; + for (i = 0; sched_domain_topology[i].mask; i++) + tl[i] = sched_domain_topology[i]; /* * .. and append 'j' levels of NUMA goodness. */ for (j = 0; j < level; i++, j++) { tl[i] = (struct sched_domain_topology_level){ - .init = sd_numa_init, .mask = sd_numa_mask, + .sd_flags = cpu_numa_flags, .flags = SDTL_OVERLAP, .numa_level = j, + SD_INIT_NAME(NUMA) }; } @@ -6404,7 +6431,7 @@ struct sched_domain *build_sched_domain(struct sched_domain_topology_level *tl, const struct cpumask *cpu_map, struct sched_domain_attr *attr, struct sched_domain *child, int cpu) { - struct sched_domain *sd = tl->init(tl, cpu); + struct sched_domain *sd = sd_init(tl, cpu); if (!sd) return child; @@ -6974,6 +7001,7 @@ void __init sched_init(void) if (cpu_isolated_map == NULL) zalloc_cpumask_var(&cpu_isolated_map, GFP_NOWAIT); idle_thread_set_boot_cpu(); + set_cpu_rq_start_time(); #endif init_sched_fair_class(); diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index 800e99b99075..f9ca7d19781a 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -520,7 +520,7 @@ static enum hrtimer_restart dl_task_timer(struct hrtimer *timer) * We need to take care of a possible races here. In fact, the * task might have changed its scheduling policy to something * different from SCHED_DEADLINE or changed its reservation - * parameters (through sched_setscheduler()). + * parameters (through sched_setattr()). */ if (!dl_task(p) || dl_se->dl_new) goto unlock; @@ -741,7 +741,7 @@ void inc_dl_tasks(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq) WARN_ON(!dl_prio(prio)); dl_rq->dl_nr_running++; - inc_nr_running(rq_of_dl_rq(dl_rq)); + add_nr_running(rq_of_dl_rq(dl_rq), 1); inc_dl_deadline(dl_rq, deadline); inc_dl_migration(dl_se, dl_rq); @@ -755,7 +755,7 @@ void dec_dl_tasks(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq) WARN_ON(!dl_prio(prio)); WARN_ON(!dl_rq->dl_nr_running); dl_rq->dl_nr_running--; - dec_nr_running(rq_of_dl_rq(dl_rq)); + sub_nr_running(rq_of_dl_rq(dl_rq), 1); dec_dl_deadline(dl_rq, dl_se->deadline); dec_dl_migration(dl_se, dl_rq); diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 0fdb96de81a5..c9617b73bcc0 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -1095,6 +1095,34 @@ static void task_numa_assign(struct task_numa_env *env, env->best_cpu = env->dst_cpu; } +static bool load_too_imbalanced(long orig_src_load, long orig_dst_load, + long src_load, long dst_load, + struct task_numa_env *env) +{ + long imb, old_imb; + + /* We care about the slope of the imbalance, not the direction. */ + if (dst_load < src_load) + swap(dst_load, src_load); + + /* Is the difference below the threshold? */ + imb = dst_load * 100 - src_load * env->imbalance_pct; + if (imb <= 0) + return false; + + /* + * The imbalance is above the allowed threshold. + * Compare it with the old imbalance. + */ + if (orig_dst_load < orig_src_load) + swap(orig_dst_load, orig_src_load); + + old_imb = orig_dst_load * 100 - orig_src_load * env->imbalance_pct; + + /* Would this change make things worse? */ + return (old_imb > imb); +} + /* * This checks if the overall compute and NUMA accesses of the system would * be improved if the source tasks was migrated to the target dst_cpu taking @@ -1107,7 +1135,8 @@ static void task_numa_compare(struct task_numa_env *env, struct rq *src_rq = cpu_rq(env->src_cpu); struct rq *dst_rq = cpu_rq(env->dst_cpu); struct task_struct *cur; - long dst_load, src_load; + long orig_src_load, src_load; + long orig_dst_load, dst_load; long load; long imp = (groupimp > 0) ? groupimp : taskimp; @@ -1181,13 +1210,13 @@ static void task_numa_compare(struct task_numa_env *env, * In the overloaded case, try and keep the load balanced. */ balance: - dst_load = env->dst_stats.load; - src_load = env->src_stats.load; + orig_dst_load = env->dst_stats.load; + orig_src_load = env->src_stats.load; /* XXX missing power terms */ load = task_h_load(env->p); - dst_load += load; - src_load -= load; + dst_load = orig_dst_load + load; + src_load = orig_src_load - load; if (cur) { load = task_h_load(cur); @@ -1195,11 +1224,8 @@ balance: src_load += load; } - /* make src_load the smaller */ - if (dst_load < src_load) - swap(dst_load, src_load); - - if (src_load * env->imbalance_pct < dst_load * 100) + if (load_too_imbalanced(orig_src_load, orig_dst_load, + src_load, dst_load, env)) goto unlock; assign: @@ -1301,7 +1327,16 @@ static int task_numa_migrate(struct task_struct *p) if (env.best_cpu == -1) return -EAGAIN; - sched_setnuma(p, env.dst_nid); + /* + * If the task is part of a workload that spans multiple NUMA nodes, + * and is migrating into one of the workload's active nodes, remember + * this node as the task's preferred numa node, so the workload can + * settle down. + * A task that migrated to a second choice node will be better off + * trying for a better one later. Do not set the preferred node here. + */ + if (p->numa_group && node_isset(env.dst_nid, p->numa_group->active_nodes)) + sched_setnuma(p, env.dst_nid); /* * Reset the scan period if the task is being rescheduled on an @@ -1326,12 +1361,15 @@ static int task_numa_migrate(struct task_struct *p) /* Attempt to migrate a task to a CPU on the preferred node. */ static void numa_migrate_preferred(struct task_struct *p) { + unsigned long interval = HZ; + /* This task has no NUMA fault statistics yet */ if (unlikely(p->numa_preferred_nid == -1 || !p->numa_faults_memory)) return; /* Periodically retry migrating the task to the preferred node */ - p->numa_migrate_retry = jiffies + HZ; + interval = min(interval, msecs_to_jiffies(p->numa_scan_period) / 16); + p->numa_migrate_retry = jiffies + interval; /* Success if task is already running on preferred CPU */ if (task_node(p) == p->numa_preferred_nid) @@ -1738,6 +1776,7 @@ void task_numa_fault(int last_cpupid, int mem_node, int pages, int flags) struct task_struct *p = current; bool migrated = flags & TNF_MIGRATED; int cpu_node = task_node(current); + int local = !!(flags & TNF_FAULT_LOCAL); int priv; if (!numabalancing_enabled) @@ -1786,6 +1825,17 @@ void task_numa_fault(int last_cpupid, int mem_node, int pages, int flags) task_numa_group(p, last_cpupid, flags, &priv); } + /* + * If a workload spans multiple NUMA nodes, a shared fault that + * occurs wholly within the set of nodes that the workload is + * actively using should be counted as local. This allows the + * scan rate to slow down when a workload has settled down. + */ + if (!priv && !local && p->numa_group && + node_isset(cpu_node, p->numa_group->active_nodes) && + node_isset(mem_node, p->numa_group->active_nodes)) + local = 1; + task_numa_placement(p); /* @@ -1800,7 +1850,7 @@ void task_numa_fault(int last_cpupid, int mem_node, int pages, int flags) p->numa_faults_buffer_memory[task_faults_idx(mem_node, priv)] += pages; p->numa_faults_buffer_cpu[task_faults_idx(cpu_node, priv)] += pages; - p->numa_faults_locality[!!(flags & TNF_FAULT_LOCAL)] += pages; + p->numa_faults_locality[local] += pages; } static void reset_ptenuma_scan(struct task_struct *p) @@ -3301,7 +3351,7 @@ static void throttle_cfs_rq(struct cfs_rq *cfs_rq) } if (!se) - rq->nr_running -= task_delta; + sub_nr_running(rq, task_delta); cfs_rq->throttled = 1; cfs_rq->throttled_clock = rq_clock(rq); @@ -3352,7 +3402,7 @@ void unthrottle_cfs_rq(struct cfs_rq *cfs_rq) } if (!se) - rq->nr_running += task_delta; + add_nr_running(rq, task_delta); /* determine whether we need to wake up potentially idle cpu */ if (rq->curr == rq->idle && rq->cfs.nr_running) @@ -3884,7 +3934,7 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags) if (!se) { update_rq_runnable_avg(rq, rq->nr_running); - inc_nr_running(rq); + add_nr_running(rq, 1); } hrtick_update(rq); } @@ -3944,7 +3994,7 @@ static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags) } if (!se) { - dec_nr_running(rq); + sub_nr_running(rq, 1); update_rq_runnable_avg(rq, 1); } hrtick_update(rq); @@ -4015,7 +4065,7 @@ static void record_wakee(struct task_struct *p) * about the loss. */ if (jiffies > current->wakee_flip_decay_ts + HZ) { - current->wakee_flips = 0; + current->wakee_flips >>= 1; current->wakee_flip_decay_ts = jiffies; } @@ -4449,10 +4499,10 @@ select_task_rq_fair(struct task_struct *p, int prev_cpu, int sd_flag, int wake_f sd = tmp; } - if (affine_sd) { - if (cpu != prev_cpu && wake_affine(affine_sd, p, sync)) - prev_cpu = cpu; + if (affine_sd && cpu != prev_cpu && wake_affine(affine_sd, p, sync)) + prev_cpu = cpu; + if (sd_flag & SD_BALANCE_WAKE) { new_cpu = select_idle_sibling(p, prev_cpu); goto unlock; } @@ -4520,6 +4570,9 @@ migrate_task_rq_fair(struct task_struct *p, int next_cpu) atomic_long_add(se->avg.load_avg_contrib, &cfs_rq->removed_load); } + + /* We have migrated, no longer consider this task hot */ + se->exec_start = 0; } #endif /* CONFIG_SMP */ @@ -5070,6 +5123,7 @@ task_hot(struct task_struct *p, u64 now) /* Returns true if the destination node has incurred more faults */ static bool migrate_improves_locality(struct task_struct *p, struct lb_env *env) { + struct numa_group *numa_group = rcu_dereference(p->numa_group); int src_nid, dst_nid; if (!sched_feat(NUMA_FAVOUR_HIGHER) || !p->numa_faults_memory || @@ -5083,21 +5137,29 @@ static bool migrate_improves_locality(struct task_struct *p, struct lb_env *env) if (src_nid == dst_nid) return false; - /* Always encourage migration to the preferred node. */ + if (numa_group) { + /* Task is already in the group's interleave set. */ + if (node_isset(src_nid, numa_group->active_nodes)) + return false; + + /* Task is moving into the group's interleave set. */ + if (node_isset(dst_nid, numa_group->active_nodes)) + return true; + + return group_faults(p, dst_nid) > group_faults(p, src_nid); + } + + /* Encourage migration to the preferred node. */ if (dst_nid == p->numa_preferred_nid) return true; - /* If both task and group weight improve, this move is a winner. */ - if (task_weight(p, dst_nid) > task_weight(p, src_nid) && - group_weight(p, dst_nid) > group_weight(p, src_nid)) - return true; - - return false; + return task_faults(p, dst_nid) > task_faults(p, src_nid); } static bool migrate_degrades_locality(struct task_struct *p, struct lb_env *env) { + struct numa_group *numa_group = rcu_dereference(p->numa_group); int src_nid, dst_nid; if (!sched_feat(NUMA) || !sched_feat(NUMA_RESIST_LOWER)) @@ -5112,16 +5174,23 @@ static bool migrate_degrades_locality(struct task_struct *p, struct lb_env *env) if (src_nid == dst_nid) return false; + if (numa_group) { + /* Task is moving within/into the group's interleave set. */ + if (node_isset(dst_nid, numa_group->active_nodes)) + return false; + + /* Task is moving out of the group's interleave set. */ + if (node_isset(src_nid, numa_group->active_nodes)) + return true; + + return group_faults(p, dst_nid) < group_faults(p, src_nid); + } + /* Migrating away from the preferred node is always bad. */ if (src_nid == p->numa_preferred_nid) return true; - /* If either task or group weight get worse, don't do it. */ - if (task_weight(p, dst_nid) < task_weight(p, src_nid) || - group_weight(p, dst_nid) < group_weight(p, src_nid)) - return true; - - return false; + return task_faults(p, dst_nid) < task_faults(p, src_nid); } #else @@ -5564,6 +5633,7 @@ static unsigned long scale_rt_power(int cpu) { struct rq *rq = cpu_rq(cpu); u64 total, available, age_stamp, avg; + s64 delta; /* * Since we're reading these variables without serialization make sure @@ -5572,7 +5642,11 @@ static unsigned long scale_rt_power(int cpu) age_stamp = ACCESS_ONCE(rq->age_stamp); avg = ACCESS_ONCE(rq->rt_avg); - total = sched_avg_period() + (rq_clock(rq) - age_stamp); + delta = rq_clock(rq) - age_stamp; + if (unlikely(delta < 0)) + delta = 0; + + total = sched_avg_period() + delta; if (unlikely(total < avg)) { /* Ensures that power won't end up being negative */ @@ -6640,17 +6714,44 @@ out: return ld_moved; } +static inline unsigned long +get_sd_balance_interval(struct sched_domain *sd, int cpu_busy) +{ + unsigned long interval = sd->balance_interval; + + if (cpu_busy) + interval *= sd->busy_factor; + + /* scale ms to jiffies */ + interval = msecs_to_jiffies(interval); + interval = clamp(interval, 1UL, max_load_balance_interval); + + return interval; +} + +static inline void +update_next_balance(struct sched_domain *sd, int cpu_busy, unsigned long *next_balance) +{ + unsigned long interval, next; + + interval = get_sd_balance_interval(sd, cpu_busy); + next = sd->last_balance + interval; + + if (time_after(*next_balance, next)) + *next_balance = next; +} + /* * idle_balance is called by schedule() if this_cpu is about to become * idle. Attempts to pull tasks from other CPUs. */ static int idle_balance(struct rq *this_rq) { + unsigned long next_balance = jiffies + HZ; + int this_cpu = this_rq->cpu; struct sched_domain *sd; int pulled_task = 0; - unsigned long next_balance = jiffies + HZ; u64 curr_cost = 0; - int this_cpu = this_rq->cpu; idle_enter_fair(this_rq); @@ -6660,8 +6761,15 @@ static int idle_balance(struct rq *this_rq) */ this_rq->idle_stamp = rq_clock(this_rq); - if (this_rq->avg_idle < sysctl_sched_migration_cost) + if (this_rq->avg_idle < sysctl_sched_migration_cost) { + rcu_read_lock(); + sd = rcu_dereference_check_sched_domain(this_rq->sd); + if (sd) + update_next_balance(sd, 0, &next_balance); + rcu_read_unlock(); + goto out; + } /* * Drop the rq->lock, but keep IRQ/preempt disabled. @@ -6671,20 +6779,20 @@ static int idle_balance(struct rq *this_rq) update_blocked_averages(this_cpu); rcu_read_lock(); for_each_domain(this_cpu, sd) { - unsigned long interval; int continue_balancing = 1; u64 t0, domain_cost; if (!(sd->flags & SD_LOAD_BALANCE)) continue; - if (this_rq->avg_idle < curr_cost + sd->max_newidle_lb_cost) + if (this_rq->avg_idle < curr_cost + sd->max_newidle_lb_cost) { + update_next_balance(sd, 0, &next_balance); break; + } if (sd->flags & SD_BALANCE_NEWIDLE) { t0 = sched_clock_cpu(this_cpu); - /* If we've pulled tasks over stop searching: */ pulled_task = load_balance(this_cpu, this_rq, sd, CPU_NEWLY_IDLE, &continue_balancing); @@ -6696,10 +6804,13 @@ static int idle_balance(struct rq *this_rq) curr_cost += domain_cost; } - interval = msecs_to_jiffies(sd->balance_interval); - if (time_after(next_balance, sd->last_balance + interval)) - next_balance = sd->last_balance + interval; - if (pulled_task) + update_next_balance(sd, 0, &next_balance); + + /* + * Stop searching for tasks to pull if there are + * now runnable tasks on this rq. + */ + if (pulled_task || this_rq->nr_running > 0) break; } rcu_read_unlock(); @@ -6717,20 +6828,13 @@ static int idle_balance(struct rq *this_rq) if (this_rq->cfs.h_nr_running && !pulled_task) pulled_task = 1; - if (pulled_task || time_after(jiffies, this_rq->next_balance)) { - /* - * We are going idle. next_balance may be set based on - * a busy processor. So reset next_balance. - */ - this_rq->next_balance = next_balance; - } - out: + /* Move the next balance forward */ + if (time_after(this_rq->next_balance, next_balance)) + this_rq->next_balance = next_balance; + /* Is there a task of a high priority class? */ - if (this_rq->nr_running != this_rq->cfs.h_nr_running && - ((this_rq->stop && this_rq->stop->on_rq) || - this_rq->dl.dl_nr_running || - (this_rq->rt.rt_nr_running && !rt_rq_throttled(&this_rq->rt)))) + if (this_rq->nr_running != this_rq->cfs.h_nr_running) pulled_task = -1; if (pulled_task) { @@ -7011,16 +7115,9 @@ static void rebalance_domains(struct rq *rq, enum cpu_idle_type idle) break; } - interval = sd->balance_interval; - if (idle != CPU_IDLE) - interval *= sd->busy_factor; - - /* scale ms to jiffies */ - interval = msecs_to_jiffies(interval); - interval = clamp(interval, 1UL, max_load_balance_interval); + interval = get_sd_balance_interval(sd, idle != CPU_IDLE); need_serialize = sd->flags & SD_SERIALIZE; - if (need_serialize) { if (!spin_trylock(&balancing)) goto out; @@ -7036,6 +7133,7 @@ static void rebalance_domains(struct rq *rq, enum cpu_idle_type idle) idle = idle_cpu(cpu) ? CPU_IDLE : CPU_NOT_IDLE; } sd->last_balance = jiffies; + interval = get_sd_balance_interval(sd, idle != CPU_IDLE); } if (need_serialize) spin_unlock(&balancing); diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c index 8f4390a079c7..25b9423abce9 100644 --- a/kernel/sched/idle.c +++ b/kernel/sched/idle.c @@ -67,24 +67,21 @@ void __weak arch_cpu_idle(void) * cpuidle_idle_call - the main idle function * * NOTE: no locks or semaphores should be used here - * return non-zero on failure */ -static int cpuidle_idle_call(void) +static void cpuidle_idle_call(void) { struct cpuidle_device *dev = __this_cpu_read(cpuidle_devices); struct cpuidle_driver *drv = cpuidle_get_cpu_driver(dev); - int next_state, entered_state, ret; + int next_state, entered_state; bool broadcast; /* * Check if the idle task must be rescheduled. If it is the - * case, exit the function after re-enabling the local irq and - * set again the polling flag + * case, exit the function after re-enabling the local irq. */ - if (current_clr_polling_and_test()) { + if (need_resched()) { local_irq_enable(); - __current_set_polling(); - return 0; + return; } /* @@ -101,96 +98,79 @@ static int cpuidle_idle_call(void) rcu_idle_enter(); /* - * Check if the cpuidle framework is ready, otherwise fallback - * to the default arch specific idle method + * Ask the cpuidle framework to choose a convenient idle state. + * Fall back to the default arch idle method on errors. */ - ret = cpuidle_enabled(drv, dev); - - if (!ret) { + next_state = cpuidle_select(drv, dev); + if (next_state < 0) { +use_default: /* - * Ask the governor to choose an idle state it thinks - * it is convenient to go to. There is *always* a - * convenient idle state + * We can't use the cpuidle framework, let's use the default + * idle routine. */ - next_state = cpuidle_select(drv, dev); - - /* - * The idle task must be scheduled, it is pointless to - * go to idle, just update no idle residency and get - * out of this function - */ - if (current_clr_polling_and_test()) { - dev->last_residency = 0; - entered_state = next_state; + if (current_clr_polling_and_test()) local_irq_enable(); - } else { - broadcast = !!(drv->states[next_state].flags & - CPUIDLE_FLAG_TIMER_STOP); + else + arch_cpu_idle(); - if (broadcast) - /* - * Tell the time framework to switch - * to a broadcast timer because our - * local timer will be shutdown. If a - * local timer is used from another - * cpu as a broadcast timer, this call - * may fail if it is not available - */ - ret = clockevents_notify( - CLOCK_EVT_NOTIFY_BROADCAST_ENTER, - &dev->cpu); - - if (!ret) { - trace_cpu_idle_rcuidle(next_state, dev->cpu); - - /* - * Enter the idle state previously - * returned by the governor - * decision. This function will block - * until an interrupt occurs and will - * take care of re-enabling the local - * interrupts - */ - entered_state = cpuidle_enter(drv, dev, - next_state); - - trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, - dev->cpu); - - if (broadcast) - clockevents_notify( - CLOCK_EVT_NOTIFY_BROADCAST_EXIT, - &dev->cpu); - - /* - * Give the governor an opportunity to reflect on the - * outcome - */ - cpuidle_reflect(dev, entered_state); - } - } + goto exit_idle; } - /* - * We can't use the cpuidle framework, let's use the default - * idle routine - */ - if (ret) - arch_cpu_idle(); + /* + * The idle task must be scheduled, it is pointless to + * go to idle, just update no idle residency and get + * out of this function + */ + if (current_clr_polling_and_test()) { + dev->last_residency = 0; + entered_state = next_state; + local_irq_enable(); + goto exit_idle; + } + + broadcast = !!(drv->states[next_state].flags & CPUIDLE_FLAG_TIMER_STOP); + + /* + * Tell the time framework to switch to a broadcast timer + * because our local timer will be shutdown. If a local timer + * is used from another cpu as a broadcast timer, this call may + * fail if it is not available + */ + if (broadcast && + clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_ENTER, &dev->cpu)) + goto use_default; + + trace_cpu_idle_rcuidle(next_state, dev->cpu); + + /* + * Enter the idle state previously returned by the governor decision. + * This function will block until an interrupt occurs and will take + * care of re-enabling the local interrupts + */ + entered_state = cpuidle_enter(drv, dev, next_state); + + trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, dev->cpu); + + if (broadcast) + clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_EXIT, &dev->cpu); + + /* + * Give the governor an opportunity to reflect on the outcome + */ + cpuidle_reflect(dev, entered_state); + +exit_idle: __current_set_polling(); /* - * It is up to the idle functions to enable back the local - * interrupt + * It is up to the idle functions to reenable local interrupts */ if (WARN_ON_ONCE(irqs_disabled())) local_irq_enable(); rcu_idle_exit(); start_critical_timings(); - - return 0; } /* diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c index bd2267ad404f..0ebfd7a29472 100644 --- a/kernel/sched/rt.c +++ b/kernel/sched/rt.c @@ -79,6 +79,8 @@ void init_rt_rq(struct rt_rq *rt_rq, struct rq *rq) rt_rq->overloaded = 0; plist_head_init(&rt_rq->pushable_tasks); #endif + /* We start is dequeued state, because no RT tasks are queued */ + rt_rq->rt_queued = 0; rt_rq->rt_time = 0; rt_rq->rt_throttled = 0; @@ -112,6 +114,13 @@ static inline struct rt_rq *rt_rq_of_se(struct sched_rt_entity *rt_se) return rt_se->rt_rq; } +static inline struct rq *rq_of_rt_se(struct sched_rt_entity *rt_se) +{ + struct rt_rq *rt_rq = rt_se->rt_rq; + + return rt_rq->rq; +} + void free_rt_sched_group(struct task_group *tg) { int i; @@ -211,10 +220,16 @@ static inline struct rq *rq_of_rt_rq(struct rt_rq *rt_rq) return container_of(rt_rq, struct rq, rt); } -static inline struct rt_rq *rt_rq_of_se(struct sched_rt_entity *rt_se) +static inline struct rq *rq_of_rt_se(struct sched_rt_entity *rt_se) { struct task_struct *p = rt_task_of(rt_se); - struct rq *rq = task_rq(p); + + return task_rq(p); +} + +static inline struct rt_rq *rt_rq_of_se(struct sched_rt_entity *rt_se) +{ + struct rq *rq = rq_of_rt_se(rt_se); return &rq->rt; } @@ -391,6 +406,9 @@ static inline void set_post_schedule(struct rq *rq) } #endif /* CONFIG_SMP */ +static void enqueue_top_rt_rq(struct rt_rq *rt_rq); +static void dequeue_top_rt_rq(struct rt_rq *rt_rq); + static inline int on_rt_rq(struct sched_rt_entity *rt_se) { return !list_empty(&rt_se->run_list); @@ -452,8 +470,11 @@ static void sched_rt_rq_enqueue(struct rt_rq *rt_rq) rt_se = rt_rq->tg->rt_se[cpu]; if (rt_rq->rt_nr_running) { - if (rt_se && !on_rt_rq(rt_se)) + if (!rt_se) + enqueue_top_rt_rq(rt_rq); + else if (!on_rt_rq(rt_se)) enqueue_rt_entity(rt_se, false); + if (rt_rq->highest_prio.curr < curr->prio) resched_task(curr); } @@ -466,10 +487,17 @@ static void sched_rt_rq_dequeue(struct rt_rq *rt_rq) rt_se = rt_rq->tg->rt_se[cpu]; - if (rt_se && on_rt_rq(rt_se)) + if (!rt_se) + dequeue_top_rt_rq(rt_rq); + else if (on_rt_rq(rt_se)) dequeue_rt_entity(rt_se); } +static inline int rt_rq_throttled(struct rt_rq *rt_rq) +{ + return rt_rq->rt_throttled && !rt_rq->rt_nr_boosted; +} + static int rt_se_boosted(struct sched_rt_entity *rt_se) { struct rt_rq *rt_rq = group_rt_rq(rt_se); @@ -532,12 +560,23 @@ static inline struct rt_rq *group_rt_rq(struct sched_rt_entity *rt_se) static inline void sched_rt_rq_enqueue(struct rt_rq *rt_rq) { - if (rt_rq->rt_nr_running) - resched_task(rq_of_rt_rq(rt_rq)->curr); + struct rq *rq = rq_of_rt_rq(rt_rq); + + if (!rt_rq->rt_nr_running) + return; + + enqueue_top_rt_rq(rt_rq); + resched_task(rq->curr); } static inline void sched_rt_rq_dequeue(struct rt_rq *rt_rq) { + dequeue_top_rt_rq(rt_rq); +} + +static inline int rt_rq_throttled(struct rt_rq *rt_rq) +{ + return rt_rq->rt_throttled; } static inline const struct cpumask *sched_rt_period_mask(void) @@ -922,6 +961,38 @@ static void update_curr_rt(struct rq *rq) } } +static void +dequeue_top_rt_rq(struct rt_rq *rt_rq) +{ + struct rq *rq = rq_of_rt_rq(rt_rq); + + BUG_ON(&rq->rt != rt_rq); + + if (!rt_rq->rt_queued) + return; + + BUG_ON(!rq->nr_running); + + sub_nr_running(rq, rt_rq->rt_nr_running); + rt_rq->rt_queued = 0; +} + +static void +enqueue_top_rt_rq(struct rt_rq *rt_rq) +{ + struct rq *rq = rq_of_rt_rq(rt_rq); + + BUG_ON(&rq->rt != rt_rq); + + if (rt_rq->rt_queued) + return; + if (rt_rq_throttled(rt_rq) || !rt_rq->rt_nr_running) + return; + + add_nr_running(rq, rt_rq->rt_nr_running); + rt_rq->rt_queued = 1; +} + #if defined CONFIG_SMP static void @@ -1044,13 +1115,24 @@ void dec_rt_group(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq) {} #endif /* CONFIG_RT_GROUP_SCHED */ +static inline +unsigned int rt_se_nr_running(struct sched_rt_entity *rt_se) +{ + struct rt_rq *group_rq = group_rt_rq(rt_se); + + if (group_rq) + return group_rq->rt_nr_running; + else + return 1; +} + static inline void inc_rt_tasks(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq) { int prio = rt_se_prio(rt_se); WARN_ON(!rt_prio(prio)); - rt_rq->rt_nr_running++; + rt_rq->rt_nr_running += rt_se_nr_running(rt_se); inc_rt_prio(rt_rq, prio); inc_rt_migration(rt_se, rt_rq); @@ -1062,7 +1144,7 @@ void dec_rt_tasks(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq) { WARN_ON(!rt_prio(rt_se_prio(rt_se))); WARN_ON(!rt_rq->rt_nr_running); - rt_rq->rt_nr_running--; + rt_rq->rt_nr_running -= rt_se_nr_running(rt_se); dec_rt_prio(rt_rq, rt_se_prio(rt_se)); dec_rt_migration(rt_se, rt_rq); @@ -1119,6 +1201,8 @@ static void dequeue_rt_stack(struct sched_rt_entity *rt_se) back = rt_se; } + dequeue_top_rt_rq(rt_rq_of_se(back)); + for (rt_se = back; rt_se; rt_se = rt_se->back) { if (on_rt_rq(rt_se)) __dequeue_rt_entity(rt_se); @@ -1127,13 +1211,18 @@ static void dequeue_rt_stack(struct sched_rt_entity *rt_se) static void enqueue_rt_entity(struct sched_rt_entity *rt_se, bool head) { + struct rq *rq = rq_of_rt_se(rt_se); + dequeue_rt_stack(rt_se); for_each_sched_rt_entity(rt_se) __enqueue_rt_entity(rt_se, head); + enqueue_top_rt_rq(&rq->rt); } static void dequeue_rt_entity(struct sched_rt_entity *rt_se) { + struct rq *rq = rq_of_rt_se(rt_se); + dequeue_rt_stack(rt_se); for_each_sched_rt_entity(rt_se) { @@ -1142,6 +1231,7 @@ static void dequeue_rt_entity(struct sched_rt_entity *rt_se) if (rt_rq && rt_rq->rt_nr_running) __enqueue_rt_entity(rt_se, false); } + enqueue_top_rt_rq(&rq->rt); } /* @@ -1159,8 +1249,6 @@ enqueue_task_rt(struct rq *rq, struct task_struct *p, int flags) if (!task_current(rq, p) && p->nr_cpus_allowed > 1) enqueue_pushable_task(rq, p); - - inc_nr_running(rq); } static void dequeue_task_rt(struct rq *rq, struct task_struct *p, int flags) @@ -1171,8 +1259,6 @@ static void dequeue_task_rt(struct rq *rq, struct task_struct *p, int flags) dequeue_rt_entity(rt_se); dequeue_pushable_task(rq, p); - - dec_nr_running(rq); } /* @@ -1377,10 +1463,7 @@ pick_next_task_rt(struct rq *rq, struct task_struct *prev) if (prev->sched_class == &rt_sched_class) update_curr_rt(rq); - if (!rt_rq->rt_nr_running) - return NULL; - - if (rt_rq_throttled(rt_rq)) + if (!rt_rq->rt_queued) return NULL; put_prev_task(rq, prev); @@ -1892,9 +1975,9 @@ static void switched_to_rt(struct rq *rq, struct task_struct *p) */ if (p->on_rq && rq->curr != p) { #ifdef CONFIG_SMP - if (rq->rt.overloaded && push_rt_task(rq) && + if (p->nr_cpus_allowed > 1 && rq->rt.overloaded && /* Don't resched if we changed runqueues */ - rq != task_rq(p)) + push_rt_task(rq) && rq != task_rq(p)) check_resched = 0; #endif /* CONFIG_SMP */ if (check_resched && p->prio < rq->curr->prio) diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 456e492a3dca..600e2291a75c 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -409,6 +409,8 @@ struct rt_rq { int overloaded; struct plist_head pushable_tasks; #endif + int rt_queued; + int rt_throttled; u64 rt_time; u64 rt_runtime; @@ -423,18 +425,6 @@ struct rt_rq { #endif }; -#ifdef CONFIG_RT_GROUP_SCHED -static inline int rt_rq_throttled(struct rt_rq *rt_rq) -{ - return rt_rq->rt_throttled && !rt_rq->rt_nr_boosted; -} -#else -static inline int rt_rq_throttled(struct rt_rq *rt_rq) -{ - return rt_rq->rt_throttled; -} -#endif - /* Deadline class' related fields in a runqueue */ struct dl_rq { /* runqueue is an rbtree, ordered by deadline */ @@ -1216,12 +1206,14 @@ extern void update_idle_cpu_load(struct rq *this_rq); extern void init_task_runnable_average(struct task_struct *p); -static inline void inc_nr_running(struct rq *rq) +static inline void add_nr_running(struct rq *rq, unsigned count) { - rq->nr_running++; + unsigned prev_nr = rq->nr_running; + + rq->nr_running = prev_nr + count; #ifdef CONFIG_NO_HZ_FULL - if (rq->nr_running == 2) { + if (prev_nr < 2 && rq->nr_running >= 2) { if (tick_nohz_full_cpu(rq->cpu)) { /* Order rq->nr_running write against the IPI */ smp_wmb(); @@ -1231,9 +1223,9 @@ static inline void inc_nr_running(struct rq *rq) #endif } -static inline void dec_nr_running(struct rq *rq) +static inline void sub_nr_running(struct rq *rq, unsigned count) { - rq->nr_running--; + rq->nr_running -= count; } static inline void rq_last_tick_reset(struct rq *rq) diff --git a/kernel/sched/stop_task.c b/kernel/sched/stop_task.c index d6ce65dde541..bfe0edadbfbb 100644 --- a/kernel/sched/stop_task.c +++ b/kernel/sched/stop_task.c @@ -41,13 +41,13 @@ pick_next_task_stop(struct rq *rq, struct task_struct *prev) static void enqueue_task_stop(struct rq *rq, struct task_struct *p, int flags) { - inc_nr_running(rq); + add_nr_running(rq, 1); } static void dequeue_task_stop(struct rq *rq, struct task_struct *p, int flags) { - dec_nr_running(rq); + sub_nr_running(rq, 1); } static void yield_task_stop(struct rq *rq) diff --git a/kernel/sys.c b/kernel/sys.c index fba0f29401ea..66a751ebf9d9 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -250,7 +250,7 @@ SYSCALL_DEFINE2(getpriority, int, which, int, who) else p = current; if (p) { - niceval = 20 - task_nice(p); + niceval = nice_to_rlimit(task_nice(p)); if (niceval > retval) retval = niceval; } @@ -261,7 +261,7 @@ SYSCALL_DEFINE2(getpriority, int, which, int, who) else pgrp = task_pgrp(current); do_each_pid_thread(pgrp, PIDTYPE_PGID, p) { - niceval = 20 - task_nice(p); + niceval = nice_to_rlimit(task_nice(p)); if (niceval > retval) retval = niceval; } while_each_pid_thread(pgrp, PIDTYPE_PGID, p); @@ -277,7 +277,7 @@ SYSCALL_DEFINE2(getpriority, int, which, int, who) do_each_thread(g, p) { if (uid_eq(task_uid(p), uid)) { - niceval = 20 - task_nice(p); + niceval = nice_to_rlimit(task_nice(p)); if (niceval > retval) retval = niceval; } diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 8edc87185427..a4bab46cd38e 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -100,10 +100,10 @@ enum { /* * Rescue workers are used only on emergencies and shared by - * all cpus. Give -20. + * all cpus. Give MIN_NICE. */ - RESCUER_NICE_LEVEL = -20, - HIGHPRI_NICE_LEVEL = -20, + RESCUER_NICE_LEVEL = MIN_NICE, + HIGHPRI_NICE_LEVEL = MIN_NICE, WQ_NAME_LEN = 24, }; diff --git a/mm/huge_memory.c b/mm/huge_memory.c index b4b1feba6472..d199d2d91946 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -2740,7 +2740,7 @@ static int khugepaged(void *none) struct mm_slot *mm_slot; set_freezable(); - set_user_nice(current, 19); + set_user_nice(current, MAX_NICE); while (!kthread_should_stop()) { khugepaged_do_scan(); diff --git a/mm/memory.c b/mm/memory.c index 037b812a9531..e302ae1dcce0 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -3920,9 +3920,6 @@ static int __handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma, } } - /* THP should already have been handled */ - BUG_ON(pmd_numa(*pmd)); - /* * Use __pte_alloc instead of pte_alloc_map, because we can't * run pte_offset_map on the pmd, if an huge pmd could