diff options
| -rw-r--r-- | arch/x86/include/asm/topology.h | 47 | ||||
| -rw-r--r-- | fs/dcache.c | 1 | ||||
| -rw-r--r-- | fs/locks.c | 2 | ||||
| -rw-r--r-- | include/linux/hardirq.h | 6 | ||||
| -rw-r--r-- | include/linux/kernel.h | 5 | ||||
| -rw-r--r-- | include/linux/sched.h | 94 | ||||
| -rw-r--r-- | include/linux/topology.h | 168 | ||||
| -rw-r--r-- | include/trace/events/sched.h | 95 | ||||
| -rw-r--r-- | init/main.c | 2 | ||||
| -rw-r--r-- | kernel/kthread.c | 4 | ||||
| -rw-r--r-- | kernel/sched.c | 1099 | ||||
| -rw-r--r-- | kernel/sched_cpupri.c | 30 | ||||
| -rw-r--r-- | kernel/sched_debug.c | 4 | ||||
| -rw-r--r-- | kernel/sched_fair.c | 84 | ||||
| -rw-r--r-- | kernel/sched_features.h | 2 | ||||
| -rw-r--r-- | kernel/sched_rt.c | 62 | ||||
| -rw-r--r-- | kernel/sysctl.c | 24 | ||||
| -rw-r--r-- | kernel/workqueue.c | 2 |
18 files changed, 1117 insertions, 614 deletions
diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h index 066ef590d7e..26d06e052a1 100644 --- a/arch/x86/include/asm/topology.h +++ b/arch/x86/include/asm/topology.h @@ -129,25 +129,34 @@ extern unsigned long node_remap_size[]; #endif /* sched_domains SD_NODE_INIT for NUMA machines */ -#define SD_NODE_INIT (struct sched_domain) { \ - .min_interval = 8, \ - .max_interval = 32, \ - .busy_factor = 32, \ - .imbalance_pct = 125, \ - .cache_nice_tries = SD_CACHE_NICE_TRIES, \ - .busy_idx = 3, \ - .idle_idx = SD_IDLE_IDX, \ - .newidle_idx = SD_NEWIDLE_IDX, \ - .wake_idx = 1, \ - .forkexec_idx = SD_FORKEXEC_IDX, \ - .flags = SD_LOAD_BALANCE \ - | SD_BALANCE_EXEC \ - | SD_BALANCE_FORK \ - | SD_WAKE_AFFINE \ - | SD_WAKE_BALANCE \ - | SD_SERIALIZE, \ - .last_balance = jiffies, \ - .balance_interval = 1, \ +#define SD_NODE_INIT (struct sched_domain) { \ + .min_interval = 8, \ + .max_interval = 32, \ + .busy_factor = 32, \ + .imbalance_pct = 125, \ + .cache_nice_tries = SD_CACHE_NICE_TRIES, \ + .busy_idx = 3, \ + .idle_idx = SD_IDLE_IDX, \ + .newidle_idx = SD_NEWIDLE_IDX, \ + .wake_idx = 1, \ + .forkexec_idx = SD_FORKEXEC_IDX, \ + \ + .flags = 1*SD_LOAD_BALANCE \ + | 1*SD_BALANCE_NEWIDLE \ + | 1*SD_BALANCE_EXEC \ + | 1*SD_BALANCE_FORK \ + | 0*SD_WAKE_IDLE \ + | 1*SD_WAKE_AFFINE \ + | 1*SD_WAKE_BALANCE \ + | 0*SD_SHARE_CPUPOWER \ + | 0*SD_POWERSAVINGS_BALANCE \ + | 0*SD_SHARE_PKG_RESOURCES \ + | 1*SD_SERIALIZE \ + | 1*SD_WAKE_IDLE_FAR \ + | 0*SD_PREFER_SIBLING \ + , \ + .last_balance = jiffies, \ + .balance_interval = 1, \ } #ifdef CONFIG_X86_64_ACPI_NUMA diff --git a/fs/dcache.c b/fs/dcache.c index 9e5cd3c3a6b..a100fa35a48 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -32,6 +32,7 @@ #include <linux/swap.h> #include <linux/bootmem.h> #include <linux/fs_struct.h> +#include <linux/hardirq.h> #include "internal.h" int sysctl_vfs_cache_pressure __read_mostly = 100; diff --git a/fs/locks.c b/fs/locks.c index 52366e877d7..19ee18a6829 100644 --- a/fs/locks.c +++ b/fs/locks.c @@ -768,7 +768,7 @@ static int flock_lock_file(struct file *filp, struct file_lock *request) * give it the opportunity to lock the file. */ if (found) - cond_resched_bkl(); + cond_resched(); find_conflict: for_each_lock(inode, before) { diff --git a/include/linux/hardirq.h b/include/linux/hardirq.h index 330cb31bb49..6d527ee82b2 100644 --- a/include/linux/hardirq.h +++ b/include/linux/hardirq.h @@ -64,6 +64,12 @@ #define HARDIRQ_OFFSET (1UL << HARDIRQ_SHIFT) #define NMI_OFFSET (1UL << NMI_SHIFT) +#ifndef PREEMPT_ACTIVE +#define PREEMPT_ACTIVE_BITS 1 +#define PREEMPT_ACTIVE_SHIFT (NMI_SHIFT + NMI_BITS) +#define PREEMPT_ACTIVE (__IRQ_MASK(PREEMPT_ACTIVE_BITS) << PREEMPT_ACTIVE_SHIFT) +#endif + #if PREEMPT_ACTIVE < (1 << (NMI_SHIFT + NMI_BITS)) #error PREEMPT_ACTIVE is too low! #endif diff --git a/include/linux/kernel.h b/include/linux/kernel.h index d6320a3e8de..2b5b1e0899a 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -125,7 +125,7 @@ extern int _cond_resched(void); #endif #ifdef CONFIG_DEBUG_SPINLOCK_SLEEP - void __might_sleep(char *file, int line); + void __might_sleep(char *file, int line, int preempt_offset); /** * might_sleep - annotation for functions that can sleep * @@ -137,8 +137,9 @@ extern int _cond_resched(void); * supposed to. */ # define might_sleep() \ - do { __might_sleep(__FILE__, __LINE__); might_resched(); } while (0) + do { __might_sleep(__FILE__, __LINE__, 0); might_resched(); } while (0) #else + static inline void __might_sleep(char *file, int line, int preempt_offset) { } # define might_sleep() do { might_resched(); } while (0) #endif diff --git a/include/linux/sched.h b/include/linux/sched.h index 379531c0897..f3d74bd04d1 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -38,6 +38,8 @@ #define SCHED_BATCH 3 /* SCHED_ISO: reserved but not implemented yet */ #define SCHED_IDLE 5 +/* Can be ORed in to make sure the process is reverted back to SCHED_NORMAL on fork */ +#define SCHED_RESET_ON_FORK 0x40000000 #ifdef __KERNEL__ @@ -796,18 +798,19 @@ enum cpu_idle_type { #define SCHED_LOAD_SCALE_FUZZ SCHED_LOAD_SCALE #ifdef CONFIG_SMP -#define SD_LOAD_BALANCE 1 /* Do load balancing on this domain. */ -#define SD_BALANCE_NEWIDLE 2 /* Balance when about to become idle */ -#define SD_BALANCE_EXEC 4 /* Balance on exec */ -#define SD_BALANCE_FORK 8 /* Balance on fork, clone */ -#define SD_WAKE_IDLE 16 /* Wake to idle CPU on task wakeup */ -#define SD_WAKE_AFFINE 32 /* Wake task to waking CPU */ -#define SD_WAKE_BALANCE 64 /* Perform balancing at task wakeup */ -#define SD_SHARE_CPUPOWER 128 /* Domain members share cpu power */ -#define SD_POWERSAVINGS_BALANCE 256 /* Balance for power savings */ -#define SD_SHARE_PKG_RESOURCES 512 /* Domain members share cpu pkg resources */ -#define SD_SERIALIZE 1024 /* Only a single load balancing instance */ -#define SD_WAKE_IDLE_FAR 2048 /* Gain latency sacrificing cache hit */ +#define SD_LOAD_BALANCE 0x0001 /* Do load balancing on this domain. */ +#define SD_BALANCE_NEWIDLE 0x0002 /* Balance when about to become idle */ +#define SD_BALANCE_EXEC 0x0004 /* Balance on exec */ +#define SD_BALANCE_FORK 0x0008 /* Balance on fork, clone */ +#define SD_WAKE_IDLE 0x0010 /* Wake to idle CPU on task wakeup */ +#define SD_WAKE_AFFINE 0x0020 /* Wake task to waking CPU */ +#define SD_WAKE_BALANCE 0x0040 /* Perform balancing at task wakeup */ +#define SD_SHARE_CPUPOWER 0x0080 /* Domain members share cpu power */ +#define SD_POWERSAVINGS_BALANCE 0x0100 /* Balance for power savings */ +#define SD_SHARE_PKG_RESOURCES 0x0200 /* Domain members share cpu pkg resources */ +#define SD_SERIALIZE 0x0400 /* Only a single load balancing instance */ +#define SD_WAKE_IDLE_FAR 0x0800 /* Gain latency sacrificing cache hit */ +#define SD_PREFER_SIBLING 0x1000 /* Prefer to place tasks in a sibling domain */ enum powersavings_balance_level { POWERSAVINGS_BALANCE_NONE = 0, /* No power saving load balance */ @@ -827,7 +830,7 @@ static inline int sd_balance_for_mc_power(void) if (sched_smt_power_savings) return SD_POWERSAVINGS_BALANCE; - return 0; + return SD_PREFER_SIBLING; } static inline int sd_balance_for_package_power(void) @@ -835,7 +838,7 @@ static inline int sd_balance_for_package_power(void) if (sched_mc_power_savings | sched_smt_power_savings) return SD_POWERSAVINGS_BALANCE; - return 0; + return SD_PREFER_SIBLING; } /* @@ -857,15 +860,9 @@ struct sched_group { /* * CPU power of this group, SCHED_LOAD_SCALE being max power for a - * single CPU. This is read only (except for setup, hotplug CPU). - * Note : Never change cpu_power without recompute its reciprocal - */ - unsigned int __cpu_power; - /* - * reciprocal value of cpu_power to avoid expensive divides - * (see include/linux/reciprocal_div.h) + * single CPU. */ - u32 reciprocal_cpu_power; + unsigned int cpu_power; /* * The CPUs this group covers. @@ -918,6 +915,7 @@ struct sched_domain { unsigned int newidle_idx; unsigned int wake_idx; unsigned int forkexec_idx; + unsigned int smt_gain; int flags; /* See SD_* */ enum sched_domain_level level; @@ -1045,7 +1043,6 @@ struct sched_class { struct rq *busiest, struct sched_domain *sd, enum cpu_idle_type idle); void (*pre_schedule) (struct rq *this_rq, struct task_struct *task); - int (*needs_post_schedule) (struct rq *this_rq); void (*post_schedule) (struct rq *this_rq); void (*task_wake_up) (struct rq *this_rq, struct task_struct *task); @@ -1110,6 +1107,8 @@ struct sched_entity { u64 wait_max; u64 wait_count; u64 wait_sum; + u64 iowait_count; + u64 iowait_sum; u64 sleep_start; u64 sleep_max; @@ -1234,11 +1233,19 @@ struct task_struct { unsigned did_exec:1; unsigned in_execve:1; /* Tell the LSMs that the process is doing an * execve */ + unsigned in_iowait:1; + + + /* Revert to default priority/policy when forking */ + unsigned sched_reset_on_fork:1; + pid_t pid; pid_t tgid; +#ifdef CONFIG_CC_STACKPROTECTOR /* Canary value for the -fstack-protector gcc feature */ unsigned long stack_canary; +#endif /* * pointers to (original) parent process, youngest child, younger sibling, @@ -1840,11 +1847,12 @@ extern unsigned int sysctl_sched_min_granularity; extern unsigned int sysctl_sched_wakeup_granularity; extern unsigned int sysctl_sched_shares_ratelimit; extern unsigned int sysctl_sched_shares_thresh; -#ifdef CONFIG_SCHED_DEBUG extern unsigned int sysctl_sched_child_runs_first; +#ifdef CONFIG_SCHED_DEBUG extern unsigned int sysctl_sched_features; extern unsigned int sysctl_sched_migration_cost; extern unsigned int sysctl_sched_nr_migrate; +extern unsigned int sysctl_sched_time_avg; extern unsigned int sysctl_timer_migration; int sched_nr_latency_handler(struct ctl_table *table, int write, @@ -2308,23 +2316,31 @@ static inline int need_resched(void) * cond_resched_softirq() will enable bhs before scheduling. */ extern int _cond_resched(void); -#ifdef CONFIG_PREEMPT_BKL -static inline int cond_resched(void) -{ - return 0; -} + +#define cond_resched() ({ \ + __might_sleep(__FILE__, __LINE__, 0); \ + _cond_resched(); \ +}) + +extern int __cond_resched_lock(spinlock_t *lock); + +#ifdef CONFIG_PREEMPT +#define PREEMPT_LOCK_OFFSET PREEMPT_OFFSET #else -static inline int cond_resched(void) -{ - return _cond_resched(); -} +#define PREEMPT_LOCK_OFFSET 0 #endif -extern int cond_resched_lock(spinlock_t * lock); -extern int cond_resched_softirq(void); -static inline int cond_resched_bkl(void) -{ - return _cond_resched(); -} + +#define cond_resched_lock(lock) ({ \ + __might_sleep(__FILE__, __LINE__, PREEMPT_LOCK_OFFSET); \ + __cond_resched_lock(lock); \ +}) + +extern int __cond_resched_softirq(void); + +#define cond_resched_softirq() ({ \ + __might_sleep(__FILE__, __LINE__, SOFTIRQ_OFFSET); \ + __cond_resched_softirq(); \ +}) /* * Does a critical section need to be broken due to another diff --git a/include/linux/topology.h b/include/linux/topology.h index 7402c1a27c4..85e8cf7d393 100644 --- a/include/linux/topology.h +++ b/include/linux/topology.h @@ -85,20 +85,29 @@ int arch_update_cpu_topology(void); #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 = SD_LOAD_BALANCE \ - | SD_BALANCE_NEWIDLE \ - | SD_BALANCE_FORK \ - | SD_BALANCE_EXEC \ - | SD_WAKE_AFFINE \ - | SD_WAKE_BALANCE \ - | SD_SHARE_CPUPOWER, \ - .last_balance = jiffies, \ - .balance_interval = 1, \ +#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_WAKE_IDLE \ + | 1*SD_WAKE_AFFINE \ + | 1*SD_WAKE_BALANCE \ + | 1*SD_SHARE_CPUPOWER \ + | 0*SD_POWERSAVINGS_BALANCE \ + | 0*SD_SHARE_PKG_RESOURCES \ + | 0*SD_SERIALIZE \ + | 0*SD_WAKE_IDLE_FAR \ + | 0*SD_PREFER_SIBLING \ + , \ + .last_balance = jiffies, \ + .balance_interval = 1, \ + .smt_gain = 1178, /* 15% */ \ } #endif #endif /* CONFIG_SCHED_SMT */ @@ -106,69 +115,94 @@ int arch_update_cpu_topology(void); #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 = 1, \ - .forkexec_idx = 1, \ - .flags = SD_LOAD_BALANCE \ - | SD_BALANCE_FORK \ - | SD_BALANCE_EXEC \ - | SD_WAKE_AFFINE \ - | SD_WAKE_BALANCE \ - | SD_SHARE_PKG_RESOURCES\ - | sd_balance_for_mc_power()\ - | sd_power_saving_flags(),\ - .last_balance = jiffies, \ - .balance_interval = 1, \ +#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 = 1, \ + .forkexec_idx = 1, \ + \ + .flags = 1*SD_LOAD_BALANCE \ + | 1*SD_BALANCE_NEWIDLE \ + | 1*SD_BALANCE_EXEC \ + | 1*SD_BALANCE_FORK \ + | 1*SD_WAKE_IDLE \ + | 1*SD_WAKE_AFFINE \ + | 1*SD_WAKE_BALANCE \ + | 0*SD_SHARE_CPUPOWER \ + | 1*SD_SHARE_PKG_RESOURCES \ + | 0*SD_SERIALIZE \ + | 0*SD_WAKE_IDLE_FAR \ + | sd_balance_for_mc_power() \ + | sd_power_saving_flags() \ + , \ + .last_balance = jiffies, \ + .balance_interval = 1, \ } #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 = 2, \ - .wake_idx = 1, \ - .forkexec_idx = 1, \ - .flags = SD_LOAD_BALANCE \ - | SD_BALANCE_EXEC \ - | SD_BALANCE_FORK \ - | SD_WAKE_AFFINE \ - | SD_WAKE_BALANCE \ - | sd_balance_for_package_power()\ - | sd_power_saving_flags(),\ - .last_balance = jiffies, \ - .balance_interval = 1, \ +#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 = 2, \ + .wake_idx = 1, \ + .forkexec_idx = 1, \ + \ + .flags = 1*SD_LOAD_BALANCE \ + | 1*SD_BALANCE_NEWIDLE \ + | 1*SD_BALANCE_EXEC \ + | 1*SD_BALANCE_FORK \ + | 1*SD_WAKE_IDLE \ + | 0*SD_WAKE_AFFINE \ + | 1*SD_WAKE_BALANCE \ + | 0*SD_SHARE_CPUPOWER \ + | 0*SD_SHARE_PKG_RESOURCES \ + | 0*SD_SERIALIZE \ + | 0*SD_WAKE_IDLE_FAR \ + | sd_balance_for_package_power() \ + | sd_power_saving_flags() \ + , \ + .last_balance = jiffies, \ + .balance_interval = 1, \ } #endif /* sched_domains SD_ALLNODES_INIT for NUMA machines */ -#define SD_ALLNODES_INIT (struct sched_domain) { \ - .min_interval = 64, \ - .max_interval = 64*num_online_cpus(), \ - .busy_factor = 128, \ - .imbalance_pct = 133, \ - .cache_nice_tries = 1, \ - .busy_idx = 3, \ - .idle_idx = 3, \ - .flags = SD_LOAD_BALANCE \ - | SD_BALANCE_NEWIDLE \ - | SD_WAKE_AFFINE \ - | SD_SERIALIZE, \ - .last_balance = jiffies, \ - .balance_interval = 64, \ +#define SD_ALLNODES_INIT (struct sched_domain) { \ + .min_interval = 64, \ + .max_interval = 64*num_online_cpus(), \ + .busy_factor = 128, \ + .imbalance_pct = 133, \ + .cache_nice_tries = 1, \ + .busy_idx = 3, \ + .idle_idx = 3, \ + .flags = 1*SD_LOAD_BALANCE \ + | 1*SD_BALANCE_NEWIDLE \ + | 0*SD_BALANCE_EXEC \ + | 0*SD_BALANCE_FORK \ + | 0*SD_WAKE_IDLE \ + | 1*SD_WAKE_AFFINE \ + | 0*SD_WAKE_BALANCE \ + | 0*SD_SHARE_CPUPOWER \ + | 0*SD_POWERSAVINGS_BALANCE \ + | 0*SD_SHARE_PKG_RESOURCES \ + | 1*SD_SERIALIZE \ + | 1*SD_WAKE_IDLE_FAR \ + | 0*SD_PREFER_SIBLING \ + , \ + .last_balance = jiffies, \ + .balance_interval = 64, \ } #ifdef CONFIG_NUMA diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h index 8949bb7eb08..a4c369ec328 100644 --- a/include/trace/events/sched.h +++ b/include/trace/events/sched.h @@ -340,6 +340,101 @@ TRACE_EVENT(sched_signal_send, __entry->sig, __entry->comm, __entry->pid) ); +/* + * XXX the below sched_stat tracepoints only apply to SCHED_OTHER/BATCH/IDLE + * adding sched_stat support to SCHED_FIFO/RR would be welcome. + */ + +/* + * Tracepoint for accounting wait time (time the task is runnable + * but not actually running due to scheduler contention). + */ +TRACE_EVENT(sched_stat_wait, + + TP_PROTO(struct task_struct *tsk, u64 delay), + + TP_ARGS(tsk, delay), + + TP_STRUCT__entry( + __array( char, comm, TASK_COMM_LEN ) + __field( pid_t, pid ) + __field( u64, delay ) + ), + + TP_fast_assign( + memcpy(__entry->comm, tsk->comm, TASK_COMM_LEN); + __entry->pid = tsk->pid; + __entry->delay = delay; + ) + TP_perf_assign( + __perf_count(delay); + ), + + TP_printk("task: %s:%d wait: %Lu [ns]", + __entry->comm, __entry->pid, + (unsigned long long)__entry->delay) +); + +/* + * Tracepoint for accounting sleep time (time the task is not runnable, + * including iowait, see below). + */ +TRACE_EVENT(sched_stat_sleep, + + TP_PROTO(struct task_struct *tsk, u64 delay), + + TP_ARGS(tsk, delay), + + TP_STRUCT__entry( + __array( char, comm, TASK_COMM_LEN ) + __field( pid_t, pid ) + __field( u64, delay ) + ), + + TP_fast_assign( + memcpy(__entry->comm, tsk->comm, TASK_COMM_LEN); + __entry->pid = tsk->pid; + __entry->delay = delay; + ) + TP_perf_assign( + __perf_count(delay); + ), + + TP_printk("task: %s:%d sleep: %Lu [ns]", + __entry->comm, __entry->pid, + (unsigned long long)__entry->delay) +); + +/* + * Tracepoint for accounting iowait time (time the task is not runnable + * due to waiting on IO to complete). + */ +TRACE_EVENT(sched_stat_iowait, + + TP_PROTO(struct task_struct *tsk, u64 delay), + + TP_ARGS(tsk, delay), + + TP_STRUCT__entry( + __array( char, comm, TASK_COMM_LEN ) + __field( pid_t, pid ) + __field( u64, delay ) + ), + + TP_fast_assign( + memcpy(__entry->comm, tsk->comm, TASK_COMM_LEN); + __entry->pid = tsk->pid; + __entry->delay = delay; + ) + TP_perf_assign( + __perf_count(delay); + ), + + TP_printk("task: %s:%d iowait: %Lu [ns]", + __entry->comm, __entry->pid, + (unsigned long long)__entry->delay) +); + #endif /* _TRACE_SCHED_H */ /* This part must be outside protection */ diff --git a/init/main.c b/init/main.c index 525f6fb2bd2..b34fd8e5ede 100644 --- a/init/main.c +++ b/init/main.c @@ -631,7 +631,6 @@ asmlinkage void __init start_kernel(void) softirq_init(); timekeeping_init(); time_init(); - sched_clock_init(); profile_init(); if (!irqs_disabled()) printk(KERN_CRIT "start_kernel(): bug: interrupts were " @@ -682,6 +681,7 @@ asmlinkage void __init start_kernel(void) numa_policy_init(); if (late_time_init) late_time_init(); + sched_clock_init(); calibrate_delay(); pidmap_init(); anon_vma_init(); diff --git a/kernel/kthread.c b/kernel/kthread.c index eb8751aa041..5fe709982ca 100644 --- a/kernel/kthread.c +++ b/kernel/kthread.c @@ -16,8 +16,6 @@ #include <linux/mutex.h> #include <trace/events/sched.h> -#define KTHREAD_NICE_LEVEL (-5) - static DEFINE_SPINLOCK(kthread_create_lock); static LIST_HEAD(kthread_create_list); struct task_struct *kthreadd_task; @@ -145,7 +143,6 @@ struct task_struct *kthread_create(int (*threadfn)(void *data), * The kernel thread should not inherit these properties. */ sched_setscheduler_nocheck(create.result, SCHED_NORMAL, ¶m); - set_user_nice(create.result, KTHREAD_NICE_LEVEL); set_cpus_allowed_ptr(create.result, cpu_all_mask); } return create.result; @@ -221,7 +218,6 @@ int kthreadd(void *unused) /* Setup a clean context for our children to inherit. */ set_task_comm(tsk, "kthreadd"); ignore_signals(tsk); - set_user_nice(tsk, KTHREAD_NICE_LEVEL); set_cpus_allowed_ptr(tsk, cpu_all_mask); set_mems_allowed(node_possible_map); diff --git a/kernel/sched.c b/kernel/sched.c index 4066241ae9f..e27a53685ed 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -64,7 +64,6 @@ #include <linux/tsacct_kern.h> #include <linux/kprobes.h> #include <linux/delayacct.h> -#include <linux/reciprocal_div.h> #include <linux/unistd.h> #include <linux/pagemap.h> #include <linux/hrtimer.h> @@ -120,30 +119,8 @@ */ #define RUNTIME_INF ((u64)~0ULL) -#ifdef CONFIG_SMP - static void double_rq_lock(struct rq *rq1, struct rq *rq2); -/* - * Divide a load by a sched group cpu_power : (load / sg->__cpu_power) - * Since cpu_power is a 'constant', we can use a reciprocal divide. - */ -static inline u32 sg_div_cpu_power(const struct sched_group *sg, u32 load) -{ - return reciprocal_divide(load, sg->reciprocal_cpu_power); -} - -/* - * Each time a sched group cpu_power is changed, - * we must compute its reciprocal value - */ -static inline void sg_inc_cpu_power(struct sched_group *sg, u32 val) -{ - sg->__cpu_power += val; - sg->reciprocal_cpu_power = reciprocal_value(sg->__cpu_power); -} -#endif - static inline int rt_policy(int policy) { if (unlikely(policy == SCHED_FIFO || policy == SCHED_RR)) @@ -309,8 +286,8 @@ void set_tg_uid(struct user_struct *user) /* * Root task group. - * Every UID task group (including init_task_group aka UID-0) will - * be a child to this group. + * Every UID task group (including init_task_group aka UID-0) will + * be a child to this group. */ struct task_group root_task_group; @@ -318,7 +295,7 @@ struct task_group root_task_group; /* Default task group's sched entity on each cpu */ static DEFINE_PER_CPU(struct sched_entity, init_sched_entity); /* Default task group's cfs_rq on each cpu */ -static DEFINE_PER_CPU(struct cfs_rq, init_cfs_rq) ____cacheline_aligned_in_smp; +static DEFINE_PER_CPU(struct cfs_rq, init_tg_cfs_rq) ____cacheline_aligned_in_smp; #endif /* CONFIG_FAIR_GROUP_SCHED */ #ifdef CONFIG_RT_GROUP_SCHED @@ -616,6 +593,7 @@ struct rq { unsigned char idle_at_tick; /* For active balancing */ + int post_schedule; int active_balance; int push_cpu; /* cpu of this runqueue: */ @@ -626,6 +604,9 @@ struct rq { struct task_struct *migration_thread; struct list_head migration_queue; + + u64 rt_avg; + u64 age_stamp; #endif /* calc_load related fields */ @@ -693,6 +674,7 @@ static inline int cpu_of(struct rq *rq) #define this_rq() (&__get_cpu_var(runqueues)) #define task_rq(p) cpu_rq(task_cpu(p)) #define cpu_curr(cpu) (cpu_rq(cpu)->curr) +#define raw_rq() (&__raw_get_cpu_var(runqueues)) inline void update_rq_clock(struct rq *rq) { @@ -861,6 +843,14 @@ unsigned int sysctl_sched_shares_ratelimit = 250000; unsigned int sysctl_sched_shares_thresh = 4; /* + * period over which we average the RT time consumption, measured + * in ms. + * + * default: 1s + */ +const_debug unsigned int sysctl_sched_time_avg = MSEC_PER_SEC; + +/* * period over which we measure -rt task cpu usage in us. * default: 1s */ @@ -1278,12 +1268,37 @@ void wake_up_idle_cpu(int cpu) } #endif /* CONFIG_NO_HZ */ +static u64 sched_avg_period(void) +{ + return (u64)sysctl_sched_time_avg * NSEC_PER_MSEC / 2; +} + +static void sched_avg_update(struct rq *rq) +{ + s64 period = sched_avg_period(); + + while ((s64)(rq->clock - rq->age_stamp) > period) { + rq->age_stamp += period; + rq->rt_avg /= 2; + } +} + +static void sched_rt_avg_update(struct rq *rq, u64 rt_delta) +{ + rq->rt_avg += rt_delta; + sched_avg_update(rq); +} + #else /* !CONFIG_SMP */ static void resched_task(struct task_struct *p) { assert_spin_locked(&task_rq(p)->lock); set_tsk_need_resched(p); } + +static void sched_rt_avg_update(struct rq *rq, u64 rt_delta) +{ +} #endif /* CONFIG_SMP */ #if BITS_PER_LONG == 32 @@ -1513,28 +1528,35 @@ static unsigned long cpu_avg_load_per_task(int cpu) #ifdef CONFIG_FAIR_GROUP_SCHED +struct update_shares_data { + unsigned long rq_weight[NR_CPUS]; +}; + +static DEFINE_PER_CPU(struct update_shares_data, update_shares_data); + static void __set_se_shares(struct sched_entity *se, unsigned long shares); /* * Calculate and set the cpu's group shares. */ -static void -update_group_shares_cpu(struct task_group *tg, int cpu, - unsigned long sd_shares, unsigned long sd_rq_weight) +static void update_group_shares_cpu(struct task_group *tg, int cpu, + unsigned long sd_shares, + unsigned long sd_rq_weight, + struct update_shares_data *usd) { - unsigned long shares; - unsigned long rq_weight; + unsigned long shares, rq_weight; + int boost = 0; - if (!tg->se[cpu]) - return; - - rq_weight = tg->cfs_rq[cpu]->rq_weight; + rq_weight = usd->rq_weight[cpu]; + if (!rq_weight) { + boost = 1; + rq_weight = NICE_0_LOAD; + } /* - * \Sum shares * rq_weight - * shares = ----------------------- - * \Sum rq_weight - * + * \Sum_j shares_j * rq_weight_i + * shares_i = ----------------------------- + * \Sum_j rq_weight_j */ shares = (sd_shares * rq_weight) / sd_rq_weight; shares = clamp_t(unsigned long, shares, MIN_SHARES, MAX_SHARES); @@ -1545,8 +1567,8 @@ update_group_shares_cpu(struct task_group *tg, int cpu, unsigned long flags; spin_lock_irqsave(&rq->lock, flags); - tg->cfs_rq[cpu]->shares = shares; - + tg->cfs_rq[cpu]->rq_weight = boost ? 0 : rq_weight; + tg->cfs_rq[cpu]->shares = boost ? 0 : shares; __set_se_shares(tg->se[cpu], shares); spin_unlock_irqrestore(&rq->lock, flags); } @@ -1559,22 +1581,30 @@ update_group_shares_cpu(struct task_group *tg, int cpu, */ static int tg_shares_up(struct task_group *tg, void *data) { - unsigned long weight, rq_weight = 0; - unsigned long shares = 0; + unsigned long weight, rq_weight = 0, shares = 0; + struct update_shares_data *usd; struct sched_domain *sd = data; + unsigned long flags; int i; + if (!tg->se[0]) + return 0; + + local_irq_save(flags); + usd = &__get_cpu_var(update_shares_data); + for_each_cpu(i, sched_domain_span(sd)) { + weight = tg->cfs_rq[i]->load.weight; + usd->rq_weight[i] = weight; + /* * If there are currently no tasks on the cpu pretend there * is one of average load so that when a new task gets to * run here it will not get delayed by group starvation. */ - weight = tg->cfs_rq[i]->load.weight; if (!weight) weight = NICE_0_LOAD; - tg->cfs_rq[i]->rq_weight = weight; rq_weight += weight; shares += tg->cfs_rq[i]->shares; } @@ -1586,7 +1616,9 @@ static int tg_shares_up(struct task_group *tg, void *data) shares = tg->shares; for_each_cpu(i, sched_domain_span(sd)) - update_group_shares_cpu(tg, i, shares, rq_weight); + update_group_shares_cpu(tg, i, shares, rq_weight, usd); + + local_irq_restore(flags); return 0; } @@ -1616,8 +1648,14 @@ static int tg_load_down(struct task_group *tg, void *data) static void update_shares(struct sched_domain *sd) { - u64 now = cpu_clock(raw_smp_processor_id()); - s64 elapsed = now - sd->last_update; + s64 elapsed; + u64 now; + + if (root_task_group_empty()) + return; + + now = cpu_clock(raw_smp_processor_id()); + elapsed = now - sd->last_update; if (elapsed >= (s64)(u64)sysctl_sched_shares_ratelimit) { sd->last_update = now; @@ -1627,6 +1665,9 @@ static void update_shares(struct sched_domain *sd) static void update_shares_locked(struct rq *rq, struct sched_domain *sd) { + if (root_task_group_empty()) + return; + spin_unlock(&rq->lock); update_shares(sd); spin_lock(&rq->lock); @@ -1634,6 +1675,9 @@ static void update_shares_locked(struct rq *rq, struct sched_domain *sd) static void update_h_load(long cpu) { + if (root_task_group_empty()) + return; + walk_tg_tree(tg_load_down, tg_nop, (void *)cpu); } @@ -2268,8 +2312,7 @@ find_idlest_group(struct sched_domain *sd, struct task_struct *p, int this_cpu) } /* Adjust by relative CPU power of the group */ - avg_load = sg_div_cpu_power(group, - avg_load * SCHED_LOAD_SCALE); + avg_load = (avg_load * SCHED_LOAD_SCALE) / group->cpu_power; if (local_group) { this_load = avg_load; @@ -2637,9 +2680,32 @@ void sched_fork(struct task_struct *p, int clone_flags) set_task_cpu(p, cpu); /* - * Make sure we do not leak PI boosting priority to the child: + * Make sure we do not leak PI boosting priority to the child. */ p->prio = current->normal_prio; + + /* + * Revert to default priority/policy on fork if requested. + */ + if (unlikely(p->sched_reset_on_fork)) { + if (p->policy == SCHED_FIFO || p->policy == SCHED_RR) + p->policy = SCHED_NORMAL; + + if (p->normal_prio < DEFAULT_PRIO) + p->prio = DEFAULT_PRIO; + + if (PRIO_TO_NICE(p->static_prio) < 0) { + p->static_prio = NICE_TO_PRIO(0); + set_load_weight(p); + } + + /* + * We don't need the reset flag anymore after the fork. It has + * fulfilled its duty: + */ + p->sched_reset_on_fork = 0; + } + if (!rt_prio(p->prio)) p->sched_class = &fair_sched_class; @@ -2796,12 +2862,6 @@ static void finish_task_switch(struct rq *rq, struct task_struct *prev) { struct mm_struct *mm = rq->prev_mm; long prev_state; -#ifdef CONFIG_SMP - int post_schedule = 0; - - if (current->sched_class->needs_post_schedule) - post_schedule = current->sched_class->needs_post_schedule(rq); -#endif rq->prev_mm = NULL; @@ -2820,10 +2880,6 @@ static void finish_task_switch(struct rq *rq, struct task_struct *prev) finish_arch_switch(prev); perf_counter_task_sched_in(current, cpu_of(rq)); finish_lock_switch(rq, prev); -#ifdef CONFIG_SMP - if (post_schedule) - current->sched_class->post_schedule(rq); -# |