CFS patch, v2.6.23.8, v24 --- Documentation/sched-design-CFS.txt | 67 + Makefile | 2 arch/i386/Kconfig | 11 drivers/kvm/kvm.h | 10 fs/pipe.c | 9 fs/proc/array.c | 21 fs/proc/base.c | 2 fs/proc/proc_misc.c | 15 include/linux/cgroup.h | 12 include/linux/cpuset.h | 5 include/linux/kernel.h | 7 include/linux/kernel_stat.h | 3 include/linux/nodemask.h | 94 + include/linux/sched.h | 163 +- include/linux/taskstats.h | 7 include/linux/topology.h | 5 init/Kconfig | 26 init/main.c | 3 kernel/delayacct.c | 8 kernel/exit.c | 6 kernel/fork.c | 5 kernel/ksysfs.c | 8 kernel/sched.c | 2377 ++++++++++++++++++++++++------------- kernel/sched_debug.c | 287 +++- kernel/sched_fair.c | 969 ++++++--------- kernel/sched_idletask.c | 26 kernel/sched_rt.c | 53 kernel/sched_stats.h | 39 kernel/sysctl.c | 54 kernel/timer.c | 7 kernel/tsacct.c | 4 kernel/user.c | 249 +++ mm/memory_hotplug.c | 7 mm/page_alloc.c | 50 mm/vmscan.c | 4 net/unix/af_unix.c | 4 36 files changed, 3026 insertions(+), 1593 deletions(-) Index: linux-cfs-2.6.23.8.q/Documentation/sched-design-CFS.txt =================================================================== --- linux-cfs-2.6.23.8.q.orig/Documentation/sched-design-CFS.txt +++ linux-cfs-2.6.23.8.q/Documentation/sched-design-CFS.txt @@ -117,3 +117,70 @@ Some implementation details: iterators of the scheduling modules are used. The balancing code got quite a bit simpler as a result. + +Group scheduler extension to CFS +================================ + +Normally the scheduler operates on individual tasks and strives to provide +fair CPU time to each task. Sometimes, it may be desirable to group tasks +and provide fair CPU time to each such task group. For example, it may +be desirable to first provide fair CPU time to each user on the system +and then to each task belonging to a user. + +CONFIG_FAIR_GROUP_SCHED strives to achieve exactly that. It lets +SCHED_NORMAL/BATCH tasks be be grouped and divides CPU time fairly among such +groups. At present, there are two (mutually exclusive) mechanisms to group +tasks for CPU bandwidth control purpose: + + - Based on user id (CONFIG_FAIR_USER_SCHED) + In this option, tasks are grouped according to their user id. + - Based on "cgroup" pseudo filesystem (CONFIG_FAIR_CGROUP_SCHED) + This options lets the administrator create arbitrary groups + of tasks, using the "cgroup" pseudo filesystem. See + Documentation/cgroups.txt for more information about this + filesystem. + +Only one of these options to group tasks can be chosen and not both. + +Group scheduler tunables: + +When CONFIG_FAIR_USER_SCHED is defined, a directory is created in sysfs for +each new user and a "cpu_share" file is added in that directory. + + # cd /sys/kernel/uids + # cat 512/cpu_share # Display user 512's CPU share + 1024 + # echo 2048 > 512/cpu_share # Modify user 512's CPU share + # cat 512/cpu_share # Display user 512's CPU share + 2048 + # + +CPU bandwidth between two users are divided in the ratio of their CPU shares. +For ex: if you would like user "root" to get twice the bandwidth of user +"guest", then set the cpu_share for both the users such that "root"'s +cpu_share is twice "guest"'s cpu_share + + +When CONFIG_FAIR_CGROUP_SCHED is defined, a "cpu.shares" file is created +for each group created using the pseudo filesystem. See example steps +below to create task groups and modify their CPU share using the "cgroups" +pseudo filesystem + + # mkdir /dev/cpuctl + # mount -t cgroup -ocpu none /dev/cpuctl + # cd /dev/cpuctl + + # mkdir multimedia # create "multimedia" group of tasks + # mkdir browser # create "browser" group of tasks + + # #Configure the multimedia group to receive twice the CPU bandwidth + # #that of browser group + + # echo 2048 > multimedia/cpu.shares + # echo 1024 > browser/cpu.shares + + # firefox & # Launch firefox and move it to "browser" group + # echo > browser/tasks + + # #Launch gmplayer (or your favourite movie player) + # echo > multimedia/tasks Index: linux-cfs-2.6.23.8.q/arch/i386/Kconfig =================================================================== --- linux-cfs-2.6.23.8.q.orig/arch/i386/Kconfig +++ linux-cfs-2.6.23.8.q/arch/i386/Kconfig @@ -214,6 +214,17 @@ config X86_ES7000 endchoice +config SCHED_NO_NO_OMIT_FRAME_POINTER + bool "Single-depth WCHAN output" + default y + help + Calculate simpler /proc//wchan values. If this option + is disabled then wchan values will recurse back to the + caller function. This provides more accurate wchan values, + at the expense of slightly more scheduling overhead. + + If in doubt, say "Y". + config PARAVIRT bool "Paravirtualization support (EXPERIMENTAL)" depends on EXPERIMENTAL Index: linux-cfs-2.6.23.8.q/drivers/kvm/kvm.h =================================================================== --- linux-cfs-2.6.23.8.q.orig/drivers/kvm/kvm.h +++ linux-cfs-2.6.23.8.q/drivers/kvm/kvm.h @@ -625,6 +625,16 @@ void kvm_mmu_unload(struct kvm_vcpu *vcp int kvm_hypercall(struct kvm_vcpu *vcpu, struct kvm_run *run); +static inline void kvm_guest_enter(void) +{ + current->flags |= PF_VCPU; +} + +static inline void kvm_guest_exit(void) +{ + current->flags &= ~PF_VCPU; +} + static inline int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t gva, u32 error_code) { Index: linux-cfs-2.6.23.8.q/fs/pipe.c =================================================================== --- linux-cfs-2.6.23.8.q.orig/fs/pipe.c +++ linux-cfs-2.6.23.8.q/fs/pipe.c @@ -45,8 +45,7 @@ void pipe_wait(struct pipe_inode_info *p * Pipes are system-local resources, so sleeping on them * is considered a noninteractive wait: */ - prepare_to_wait(&pipe->wait, &wait, - TASK_INTERRUPTIBLE | TASK_NONINTERACTIVE); + prepare_to_wait(&pipe->wait, &wait, TASK_INTERRUPTIBLE); if (pipe->inode) mutex_unlock(&pipe->inode->i_mutex); schedule(); @@ -383,7 +382,7 @@ redo: /* Signal writers asynchronously that there is more room. */ if (do_wakeup) { - wake_up_interruptible(&pipe->wait); + wake_up_interruptible_sync(&pipe->wait); kill_fasync(&pipe->fasync_writers, SIGIO, POLL_OUT); } if (ret > 0) @@ -556,7 +555,7 @@ redo2: out: mutex_unlock(&inode->i_mutex); if (do_wakeup) { - wake_up_interruptible(&pipe->wait); + wake_up_interruptible_sync(&pipe->wait); kill_fasync(&pipe->fasync_readers, SIGIO, POLL_IN); } if (ret > 0) @@ -650,7 +649,7 @@ pipe_release(struct inode *inode, int de if (!pipe->readers && !pipe->writers) { free_pipe_info(inode); } else { - wake_up_interruptible(&pipe->wait); + wake_up_interruptible_sync(&pipe->wait); kill_fasync(&pipe->fasync_readers, SIGIO, POLL_IN); kill_fasync(&pipe->fasync_writers, SIGIO, POLL_OUT); } Index: linux-cfs-2.6.23.8.q/fs/proc/array.c =================================================================== --- linux-cfs-2.6.23.8.q.orig/fs/proc/array.c +++ linux-cfs-2.6.23.8.q/fs/proc/array.c @@ -367,11 +367,18 @@ static cputime_t task_stime(struct task_ stime = nsec_to_clock_t(p->se.sum_exec_runtime) - cputime_to_clock_t(task_utime(p)); - p->prev_stime = max(p->prev_stime, clock_t_to_cputime(stime)); + if (stime >= 0) + p->prev_stime = max(p->prev_stime, clock_t_to_cputime(stime)); + return p->prev_stime; } #endif +static cputime_t task_gtime(struct task_struct *p) +{ + return p->gtime; +} + static int do_task_stat(struct task_struct *task, char *buffer, int whole) { unsigned long vsize, eip, esp, wchan = ~0UL; @@ -387,6 +394,7 @@ static int do_task_stat(struct task_stru unsigned long cmin_flt = 0, cmaj_flt = 0; unsigned long min_flt = 0, maj_flt = 0; cputime_t cutime, cstime, utime, stime; + cputime_t cgtime, gtime; unsigned long rsslim = 0; char tcomm[sizeof(task->comm)]; unsigned long flags; @@ -405,6 +413,7 @@ static int do_task_stat(struct task_stru sigemptyset(&sigign); sigemptyset(&sigcatch); cutime = cstime = utime = stime = cputime_zero; + cgtime = gtime = cputime_zero; rcu_read_lock(); if (lock_task_sighand(task, &flags)) { @@ -422,6 +431,7 @@ static int do_task_stat(struct task_stru cmaj_flt = sig->cmaj_flt; cutime = sig->cutime; cstime = sig->cstime; + cgtime = sig->cgtime; rsslim = sig->rlim[RLIMIT_RSS].rlim_cur; /* add up live thread stats at the group level */ @@ -432,6 +442,7 @@ static int do_task_stat(struct task_stru maj_flt += t->maj_flt; utime = cputime_add(utime, task_utime(t)); stime = cputime_add(stime, task_stime(t)); + gtime = cputime_add(gtime, task_gtime(t)); t = next_thread(t); } while (t != task); @@ -439,6 +450,7 @@ static int do_task_stat(struct task_stru maj_flt += sig->maj_flt; utime = cputime_add(utime, sig->utime); stime = cputime_add(stime, sig->stime); + gtime = cputime_add(gtime, sig->gtime); } sid = signal_session(sig); @@ -456,6 +468,7 @@ static int do_task_stat(struct task_stru maj_flt = task->maj_flt; utime = task_utime(task); stime = task_stime(task); + gtime = task_gtime(task); } /* scale priority and nice values from timeslices to -20..20 */ @@ -473,7 +486,7 @@ static int do_task_stat(struct task_stru res = sprintf(buffer, "%d (%s) %c %d %d %d %d %d %u %lu \ %lu %lu %lu %lu %lu %ld %ld %ld %ld %d 0 %llu %lu %ld %lu %lu %lu %lu %lu \ -%lu %lu %lu %lu %lu %lu %lu %lu %d %d %u %u %llu\n", +%lu %lu %lu %lu %lu %lu %lu %lu %d %d %u %u %llu %lu %ld\n", task->pid, tcomm, state, @@ -518,7 +531,9 @@ static int do_task_stat(struct task_stru task_cpu(task), task->rt_priority, task->policy, - (unsigned long long)delayacct_blkio_ticks(task)); + (unsigned long long)delayacct_blkio_ticks(task), + cputime_to_clock_t(gtime), + cputime_to_clock_t(cgtime)); if (mm) mmput(mm); return res; Index: linux-cfs-2.6.23.8.q/fs/proc/base.c =================================================================== --- linux-cfs-2.6.23.8.q.orig/fs/proc/base.c +++ linux-cfs-2.6.23.8.q/fs/proc/base.c @@ -304,7 +304,7 @@ static int proc_pid_schedstat(struct tas return sprintf(buffer, "%llu %llu %lu\n", task->sched_info.cpu_time, task->sched_info.run_delay, - task->sched_info.pcnt); + task->sched_info.pcount); } #endif Index: linux-cfs-2.6.23.8.q/fs/proc/proc_misc.c =================================================================== --- linux-cfs-2.6.23.8.q.orig/fs/proc/proc_misc.c +++ linux-cfs-2.6.23.8.q/fs/proc/proc_misc.c @@ -443,6 +443,7 @@ static int show_stat(struct seq_file *p, int i; unsigned long jif; cputime64_t user, nice, system, idle, iowait, irq, softirq, steal; + cputime64_t guest; u64 sum = 0; struct timespec boottime; unsigned int *per_irq_sum; @@ -453,6 +454,7 @@ static int show_stat(struct seq_file *p, user = nice = system = idle = iowait = irq = softirq = steal = cputime64_zero; + guest = cputime64_zero; getboottime(&boottime); jif = boottime.tv_sec; @@ -467,6 +469,7 @@ static int show_stat(struct seq_file *p, irq = cputime64_add(irq, kstat_cpu(i).cpustat.irq); softirq = cputime64_add(softirq, kstat_cpu(i).cpustat.softirq); steal = cputime64_add(steal, kstat_cpu(i).cpustat.steal); + guest = cputime64_add(guest, kstat_cpu(i).cpustat.guest); for (j = 0; j < NR_IRQS; j++) { unsigned int temp = kstat_cpu(i).irqs[j]; sum += temp; @@ -474,7 +477,7 @@ static int show_stat(struct seq_file *p, } } - seq_printf(p, "cpu %llu %llu %llu %llu %llu %llu %llu %llu\n", + seq_printf(p, "cpu %llu %llu %llu %llu %llu %llu %llu %llu %llu\n", (unsigned long long)cputime64_to_clock_t(user), (unsigned long long)cputime64_to_clock_t(nice), (unsigned long long)cputime64_to_clock_t(system), @@ -482,7 +485,8 @@ static int show_stat(struct seq_file *p, (unsigned long long)cputime64_to_clock_t(iowait), (unsigned long long)cputime64_to_clock_t(irq), (unsigned long long)cputime64_to_clock_t(softirq), - (unsigned long long)cputime64_to_clock_t(steal)); + (unsigned long long)cputime64_to_clock_t(steal), + (unsigned long long)cputime64_to_clock_t(guest)); for_each_online_cpu(i) { /* Copy values here to work around gcc-2.95.3, gcc-2.96 */ @@ -494,7 +498,9 @@ static int show_stat(struct seq_file *p, irq = kstat_cpu(i).cpustat.irq; softirq = kstat_cpu(i).cpustat.softirq; steal = kstat_cpu(i).cpustat.steal; - seq_printf(p, "cpu%d %llu %llu %llu %llu %llu %llu %llu %llu\n", + guest = kstat_cpu(i).cpustat.guest; + seq_printf(p, + "cpu%d %llu %llu %llu %llu %llu %llu %llu %llu %llu\n", i, (unsigned long long)cputime64_to_clock_t(user), (unsigned long long)cputime64_to_clock_t(nice), @@ -503,7 +509,8 @@ static int show_stat(struct seq_file *p, (unsigned long long)cputime64_to_clock_t(iowait), (unsigned long long)cputime64_to_clock_t(irq), (unsigned long long)cputime64_to_clock_t(softirq), - (unsigned long long)cputime64_to_clock_t(steal)); + (unsigned long long)cputime64_to_clock_t(steal), + (unsigned long long)cputime64_to_clock_t(guest)); } seq_printf(p, "intr %llu", (unsigned long long)sum); Index: linux-cfs-2.6.23.8.q/include/linux/cgroup.h =================================================================== --- /dev/null +++ linux-cfs-2.6.23.8.q/include/linux/cgroup.h @@ -0,0 +1,12 @@ +#ifndef _LINUX_CGROUP_H +#define _LINUX_CGROUP_H + +/* + * Control groups are not backported - we use a few compatibility + * defines to be able to use the upstream sched.c as-is: + */ +#define task_pid_nr(task) (task)->pid +#define task_pid_vnr(task) (task)->pid +#define find_task_by_vpid(pid) find_task_by_pid(pid) + +#endif Index: linux-cfs-2.6.23.8.q/include/linux/cpuset.h =================================================================== --- linux-cfs-2.6.23.8.q.orig/include/linux/cpuset.h +++ linux-cfs-2.6.23.8.q/include/linux/cpuset.h @@ -146,6 +146,11 @@ static inline int cpuset_do_slab_mem_spr static inline void cpuset_track_online_nodes(void) {} +static inline cpumask_t cpuset_cpus_allowed_locked(struct task_struct *p) +{ + return cpu_possible_map; +} + #endif /* !CONFIG_CPUSETS */ #endif /* _LINUX_CPUSET_H */ Index: linux-cfs-2.6.23.8.q/include/linux/kernel.h =================================================================== --- linux-cfs-2.6.23.8.q.orig/include/linux/kernel.h +++ linux-cfs-2.6.23.8.q/include/linux/kernel.h @@ -61,6 +61,13 @@ extern const char linux_proc_banner[]; #define KERN_INFO "<6>" /* informational */ #define KERN_DEBUG "<7>" /* debug-level messages */ +/* + * Annotation for a "continued" line of log printout (only done after a + * line that had no enclosing \n). Only to be used by core/arch code + * during early bootup (a continued line is not SMP-safe otherwise). + */ +#define KERN_CONT "" + extern int console_printk[]; #define console_loglevel (console_printk[0]) Index: linux-cfs-2.6.23.8.q/include/linux/kernel_stat.h =================================================================== --- linux-cfs-2.6.23.8.q.orig/include/linux/kernel_stat.h +++ linux-cfs-2.6.23.8.q/include/linux/kernel_stat.h @@ -23,6 +23,7 @@ struct cpu_usage_stat { cputime64_t idle; cputime64_t iowait; cputime64_t steal; + cputime64_t guest; }; struct kernel_stat { @@ -52,7 +53,9 @@ static inline int kstat_irqs(int irq) } extern void account_user_time(struct task_struct *, cputime_t); +extern void account_user_time_scaled(struct task_struct *, cputime_t); extern void account_system_time(struct task_struct *, int, cputime_t); +extern void account_system_time_scaled(struct task_struct *, cputime_t); extern void account_steal_time(struct task_struct *, cputime_t); #endif /* _LINUX_KERNEL_STAT_H */ Index: linux-cfs-2.6.23.8.q/include/linux/nodemask.h =================================================================== --- linux-cfs-2.6.23.8.q.orig/include/linux/nodemask.h +++ linux-cfs-2.6.23.8.q/include/linux/nodemask.h @@ -338,31 +338,88 @@ static inline void __nodes_remap(nodemas #endif /* MAX_NUMNODES */ /* + * Bitmasks that are kept for all the nodes. + */ +enum node_states { + N_POSSIBLE, /* The node could become online at some point */ + N_ONLINE, /* The node is online */ + N_NORMAL_MEMORY, /* The node has regular memory */ +#ifdef CONFIG_HIGHMEM + N_HIGH_MEMORY, /* The node has regular or high memory */ +#else + N_HIGH_MEMORY = N_NORMAL_MEMORY, +#endif + N_CPU, /* The node has one or more cpus */ + NR_NODE_STATES +}; + +/* * The following particular system nodemasks and operations * on them manage all possible and online nodes. */ -extern nodemask_t node_online_map; -extern nodemask_t node_possible_map; +extern nodemask_t node_states[NR_NODE_STATES]; #if MAX_NUMNODES > 1 -#define num_online_nodes() nodes_weight(node_online_map) -#define num_possible_nodes() nodes_weight(node_possible_map) -#define node_online(node) node_isset((node), node_online_map) -#define node_possible(node) node_isset((node), node_possible_map) -#define first_online_node first_node(node_online_map) -#define next_online_node(nid) next_node((nid), node_online_map) +static inline int node_state(int node, enum node_states state) +{ + return node_isset(node, node_states[state]); +} + +static inline void node_set_state(int node, enum node_states state) +{ + __node_set(node, &node_states[state]); +} + +static inline void node_clear_state(int node, enum node_states state) +{ + __node_clear(node, &node_states[state]); +} + +static inline int num_node_state(enum node_states state) +{ + return nodes_weight(node_states[state]); +} + +#define for_each_node_state(__node, __state) \ + for_each_node_mask((__node), node_states[__state]) + +#define first_online_node first_node(node_states[N_ONLINE]) +#define next_online_node(nid) next_node((nid), node_states[N_ONLINE]) + extern int nr_node_ids; #else -#define num_online_nodes() 1 -#define num_possible_nodes() 1 -#define node_online(node) ((node) == 0) -#define node_possible(node) ((node) == 0) + +static inline int node_state(int node, enum node_states state) +{ + return node == 0; +} + +static inline void node_set_state(int node, enum node_states state) +{ +} + +static inline void node_clear_state(int node, enum node_states state) +{ +} + +static inline int num_node_state(enum node_states state) +{ + return 1; +} + +#define for_each_node_state(node, __state) \ + for ( (node) = 0; (node) == 0; (node) = 1) + #define first_online_node 0 #define next_online_node(nid) (MAX_NUMNODES) #define nr_node_ids 1 + #endif +#define node_online_map node_states[N_ONLINE] +#define node_possible_map node_states[N_POSSIBLE] + #define any_online_node(mask) \ ({ \ int node; \ @@ -372,10 +429,15 @@ extern int nr_node_ids; node; \ }) -#define node_set_online(node) set_bit((node), node_online_map.bits) -#define node_set_offline(node) clear_bit((node), node_online_map.bits) +#define num_online_nodes() num_node_state(N_ONLINE) +#define num_possible_nodes() num_node_state(N_POSSIBLE) +#define node_online(node) node_state((node), N_ONLINE) +#define node_possible(node) node_state((node), N_POSSIBLE) + +#define node_set_online(node) node_set_state((node), N_ONLINE) +#define node_set_offline(node) node_clear_state((node), N_ONLINE) -#define for_each_node(node) for_each_node_mask((node), node_possible_map) -#define for_each_online_node(node) for_each_node_mask((node), node_online_map) +#define for_each_node(node) for_each_node_state(node, N_POSSIBLE) +#define for_each_online_node(node) for_each_node_state(node, N_ONLINE) #endif /* __LINUX_NODEMASK_H */ Index: linux-cfs-2.6.23.8.q/include/linux/sched.h =================================================================== --- linux-cfs-2.6.23.8.q.orig/include/linux/sched.h +++ linux-cfs-2.6.23.8.q/include/linux/sched.h @@ -2,6 +2,10 @@ #define _LINUX_SCHED_H #include /* For AT_VECTOR_SIZE */ +#include /* CFS backport details */ + +/* backporting helper macro: */ +#define cpu_sibling_map(cpu) cpu_sibling_map[cpu] /* * cloning flags: @@ -86,6 +90,7 @@ struct sched_param { #include #include #include +#include #include @@ -135,6 +140,7 @@ extern unsigned long weighted_cpuload(co struct seq_file; struct cfs_rq; +struct task_group; #ifdef CONFIG_SCHED_DEBUG extern void proc_sched_show_task(struct task_struct *p, struct seq_file *m); extern void proc_sched_set_task(struct task_struct *p); @@ -173,8 +179,7 @@ print_cfs_rq(struct seq_file *m, int cpu #define EXIT_ZOMBIE 16 #define EXIT_DEAD 32 /* in tsk->state again */ -#define TASK_NONINTERACTIVE 64 -#define TASK_DEAD 128 +#define TASK_DEAD 64 #define __set_task_state(tsk, state_value) \ do { (tsk)->state = (state_value); } while (0) @@ -515,6 +520,8 @@ struct signal_struct { * in __exit_signal, except for the group leader. */ cputime_t utime, stime, cutime, cstime; + cputime_t gtime; + cputime_t cgtime; unsigned long nvcsw, nivcsw, cnvcsw, cnivcsw; unsigned long min_flt, maj_flt, cmin_flt, cmaj_flt; unsigned long inblock, oublock, cinblock, coublock; @@ -595,8 +602,23 @@ struct user_struct { /* Hash table maintenance information */ struct hlist_node uidhash_node; uid_t uid; + +#ifdef CONFIG_FAIR_USER_SCHED + struct task_group *tg; +#ifdef CONFIG_SYSFS + struct kset kset; + struct subsys_attribute user_attr; + struct work_struct work; +#endif +#endif }; +#ifdef CONFIG_FAIR_USER_SCHED +extern int uids_kobject_init(void); +#else +static inline int uids_kobject_init(void) { return 0; } +#endif + extern struct user_struct *find_user(uid_t); extern struct user_struct root_user; @@ -608,13 +630,17 @@ struct reclaim_state; #if defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT) struct sched_info { /* cumulative counters */ - unsigned long pcnt; /* # of times run on this cpu */ + unsigned long pcount; /* # of times run on this cpu */ unsigned long long cpu_time, /* time spent on the cpu */ run_delay; /* time spent waiting on a runqueue */ /* timestamps */ unsigned long long last_arrival,/* when we last ran on a cpu */ last_queued; /* when we were last queued to run */ +#ifdef CONFIG_SCHEDSTATS + /* BKL stats */ + unsigned int bkl_count; +#endif }; #endif /* defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT) */ @@ -749,39 +775,38 @@ struct sched_domain { #ifdef CONFIG_SCHEDSTATS /* load_balance() stats */ - unsigned long lb_cnt[CPU_MAX_IDLE_TYPES]; - unsigned long lb_failed[CPU_MAX_IDLE_TYPES]; - unsigned long lb_balanced[CPU_MAX_IDLE_TYPES]; - unsigned long lb_imbalance[CPU_MAX_IDLE_TYPES]; - unsigned long lb_gained[CPU_MAX_IDLE_TYPES]; - unsigned long lb_hot_gained[CPU_MAX_IDLE_TYPES]; - unsigned long lb_nobusyg[CPU_MAX_IDLE_TYPES]; - unsigned long lb_nobusyq[CPU_MAX_IDLE_TYPES]; + unsigned int lb_count[CPU_MAX_IDLE_TYPES]; + unsigned int lb_failed[CPU_MAX_IDLE_TYPES]; + unsigned int lb_balanced[CPU_MAX_IDLE_TYPES]; + unsigned int lb_imbalance[CPU_MAX_IDLE_TYPES]; + unsigned int lb_gained[CPU_MAX_IDLE_TYPES]; + unsigned int lb_hot_gained[CPU_MAX_IDLE_TYPES]; + unsigned int lb_nobusyg[CPU_MAX_IDLE_TYPES]; + unsigned int lb_nobusyq[CPU_MAX_IDLE_TYPES]; /* Active load balancing */ - unsigned long alb_cnt; - unsigned long alb_failed; - unsigned long alb_pushed; + unsigned int alb_count; + unsigned int alb_failed; + unsigned int alb_pushed; /* SD_BALANCE_EXEC stats */ - unsigned long sbe_cnt; - unsigned long sbe_balanced; - unsigned long sbe_pushed; + unsigned int sbe_count; + unsigned int sbe_balanced; + unsigned int sbe_pushed; /* SD_BALANCE_FORK stats */ - unsigned long sbf_cnt; - unsigned long sbf_balanced; - unsigned long sbf_pushed; + unsigned int sbf_count; + unsigned int sbf_balanced; + unsigned int sbf_pushed; /* try_to_wake_up() stats */ - unsigned long ttwu_wake_remote; - unsigned long ttwu_move_affine; - unsigned long ttwu_move_balance; + unsigned int ttwu_wake_remote; + unsigned int ttwu_move_affine; + unsigned int ttwu_move_balance; #endif }; -extern int partition_sched_domains(cpumask_t *partition1, - cpumask_t *partition2); +extern void partition_sched_domains(int ndoms_new, cpumask_t *doms_new); #endif /* CONFIG_SMP */ @@ -853,23 +878,28 @@ struct rq; struct sched_domain; struct sched_class { - struct sched_class *next; + const struct sched_class *next; void (*enqueue_task) (struct rq *rq, struct task_struct *p, int wakeup); void (*dequeue_task) (struct rq *rq, struct task_struct *p, int sleep); - void (*yield_task) (struct rq *rq, struct task_struct *p); + void (*yield_task) (struct rq *rq); void (*check_preempt_curr) (struct rq *rq, struct task_struct *p); struct task_struct * (*pick_next_task) (struct rq *rq); void (*put_prev_task) (struct rq *rq, struct task_struct *p); +#ifdef CONFIG_SMP unsigned long (*load_balance) (struct rq *this_rq, int this_cpu, - struct rq *busiest, - unsigned long max_nr_move, unsigned long max_load_move, + struct rq *busiest, unsigned long max_load_move, struct sched_domain *sd, enum cpu_idle_type idle, int *all_pinned, int *this_best_prio); + int (*move_one_task) (struct rq *this_rq, int this_cpu, + struct rq *busiest, struct sched_domain *sd, + enum cpu_idle_type idle); +#endif + void (*set_curr_task) (struct rq *rq); void (*task_tick) (struct rq *rq, struct task_struct *p); void (*task_new) (struct rq *rq, struct task_struct *p); @@ -887,31 +917,21 @@ struct load_weight { * 4 se->block_start * 4 se->run_node * 4 se->sleep_start - * 4 se->sleep_start_fair * 6 se->load.weight - * 7 se->delta_fair - * 15 se->wait_runtime */ struct sched_entity { - long wait_runtime; - unsigned long delta_fair_run; - unsigned long delta_fair_sleep; - unsigned long delta_exec; - s64 fair_key; struct load_weight load; /* for load-balancing */ struct rb_node run_node; unsigned int on_rq; u64 exec_start; u64 sum_exec_runtime; + u64 vruntime; u64 prev_sum_exec_runtime; - u64 wait_start_fair; - u64 sleep_start_fair; #ifdef CONFIG_SCHEDSTATS u64 wait_start; u64 wait_max; - s64 sum_wait_runtime; u64 sleep_start; u64 sleep_max; @@ -920,9 +940,25 @@ struct sched_entity { u64 block_start; u64 block_max; u64 exec_max; + u64 slice_max; - unsigned long wait_runtime_overruns; - unsigned long wait_runtime_underruns; + u64 nr_migrations; + u64 nr_migrations_cold; + u64 nr_failed_migrations_affine; + u64 nr_failed_migrations_running; + u64 nr_failed_migrations_hot; + u64 nr_forced_migrations; + u64 nr_forced2_migrations; + + u64 nr_wakeups; + u64 nr_wakeups_sync; + u64 nr_wakeups_migrate; + u64 nr_wakeups_local; + u64 nr_wakeups_remote; + u64 nr_wakeups_affine; + u64 nr_wakeups_affine_attempts; + u64 nr_wakeups_passive; + u64 nr_wakeups_idle; #endif #ifdef CONFIG_FAIR_GROUP_SCHED @@ -951,7 +987,7 @@ struct task_struct { int prio, static_prio, normal_prio; struct list_head run_list; - struct sched_class *sched_class; + const struct sched_class *sched_class; struct sched_entity se; #ifdef CONFIG_PREEMPT_NOTIFIERS @@ -1021,7 +1057,8 @@ struct task_struct { int __user *clear_child_tid; /* CLONE_CHILD_CLEARTID */ unsigned int rt_priority; - cputime_t utime, stime; + cputime_t utime, stime, utimescaled, stimescaled; + cputime_t gtime; cputime_t prev_utime, prev_stime; unsigned long nvcsw, nivcsw; /* context switch counts */ struct timespec start_time; /* monotonic time */ @@ -1314,6 +1351,7 @@ static inline void put_task_struct(struc #define PF_STARTING 0x00000002 /* being created */ #define PF_EXITING 0x00000004 /* getting shut down */ #define PF_EXITPIDONE 0x00000008 /* pi exit done on shut down */ +#define PF_VCPU 0x00000010 /* I'm a virtual CPU */ #define PF_FORKNOEXEC 0x00000040 /* forked but didn't exec */ #define PF_SUPERPRIV 0x00000100 /* used super-user privileges */ #define PF_DUMPCORE 0x00000200 /* dumped core */ @@ -1401,15 +1439,26 @@ static inline void idle_task_exit(void) extern void sched_idle_next(void); +#ifdef CONFIG_SCHED_DEBUG extern unsigned int sysctl_sched_latency; extern unsigned int sysctl_sched_min_granularity; extern unsigned int sysctl_sched_wakeup_granularity; extern unsigned int sysctl_sched_batch_wakeup_granularity; -extern unsigned int sysctl_sched_stat_granularity; -extern unsigned int sysctl_sched_runtime_limit; -extern unsigned int sysctl_sched_compat_yield; extern unsigned int sysctl_sched_child_runs_first; extern unsigned int sysctl_sched_features; +extern unsigned int sysctl_sched_migration_cost; +extern unsigned int sysctl_sched_nr_migrate; +#ifdef CONFIG_FAIR_GROUP_SCHED +extern unsigned int sysctl_sched_min_bal_int_shares; +extern unsigned int sysctl_sched_max_bal_int_shares; +#endif + +int sched_nr_latency_handler(struct ctl_table *table, int write, + struct file *file, void __user *buffer, size_t *length, + loff_t *ppos); +#endif + +extern unsigned int sysctl_sched_compat_yield; #ifdef CONFIG_RT_MUTEXES extern int rt_mutex_getprio(struct task_struct *p); @@ -1843,6 +1892,18 @@ extern int sched_mc_power_savings, sched extern void normalize_rt_tasks(void); +#ifdef CONFIG_FAIR_GROUP_SCHED + +extern struct task_group init_task_group; + +extern struct task_group *sched_create_group(void); +extern void sched_destroy_group(struct task_group *tg); +extern void sched_move_task(struct task_struct *tsk); +extern int sched_group_set_shares(struct task_group *tg, unsigned long shares); +extern unsigned long sched_group_shares(struct task_group *tg); + +#endif + #ifdef CONFIG_TASK_XACCT static inline void add_rchar(struct task_struct *tsk, ssize_t amt) { @@ -1881,6 +1942,14 @@ static inline void inc_syscw(struct task } #endif +#ifdef CONFIG_SMP +void migration_init(void); +#else +static inline void migration_init(void) +{ +} +#endif + #endif /* __KERNEL__ */ #endif Index: linux-cfs-2.6.23.8.q/include/linux/taskstats.h =================================================================== --- linux-cfs-2.6.23.8.q.orig/include/linux/taskstats.h +++ linux-cfs-2.6.23.8.q/include/linux/taskstats.h @@ -31,7 +31,7 @@ */ -#define TASKSTATS_VERSION 5 +#define TASKSTATS_VERSION 6 #define TS_COMM_LEN 32 /* should be >= TASK_COMM_LEN * in linux/sched.h */ @@ -152,6 +152,11 @@ struct taskstats { __u64 nvcsw; /* voluntary_ctxt_switches */ __u64 nivcsw; /* nonvoluntary_ctxt_switches */ + + /* time accounting for SMT machines */ + __u64 ac_utimescaled; /* utime scaled on frequency etc */ + __u64 ac_stimescaled; /* stime scaled on frequency etc */ + __u64 cpu_scaled_run_real_total; /* scaled cpu_run_real_total */ }; Index: linux-cfs-2.6.23.8.q/include/linux/topology.h =================================================================== --- linux-cfs-2.6.23.8.q.orig/include/linux/topology.h +++ linux-cfs-2.6.23.8.q/include/linux/topology.h @@ -159,15 +159,14 @@ .imbalance_pct = 125, \ .cache_nice_tries = 1, \ .busy_idx = 2, \ - .idle_idx = 0, \ - .newidle_idx = 0, \ + .idle_idx = 1, \ + .newidle_idx = 2, \ .wake_idx = 1, \ .forkexec_idx = 1, \ .flags = SD_LOAD_BALANCE \ | SD_BALANCE_NEWIDLE \ | SD_BALANCE_EXEC \ | SD_WAKE_AFFINE \ - | SD_WAKE_IDLE \ | BALANCE_FOR_PKG_POWER,\ .last_balance = jiffies, \ .balance_interval = 1, \ Index: linux-cfs-2.6.23.8.q/init/Kconfig =================================================================== --- linux-cfs-2.6.23.8.q.orig/init/Kconfig +++ linux-cfs-2.6.23.8.q/init/Kconfig @@ -273,6 +273,11 @@ config LOG_BUF_SHIFT config CPUSETS bool "Cpuset support" depends on SMP + # + # disabled for now - depends on control groups, which + # are hard to backport: + # + depends on 0 help This option will let you create and manage CPUSETs which allow dynamically partitioning a system into sets of CPUs and @@ -281,6 +286,27 @@ config CPUSETS Say N if unsure. +config FAIR_GROUP_SCHED + bool "Fair group CPU scheduler" + default y + depends on EXPERIMENTAL + help + This feature lets CPU scheduler recognize task groups and control CPU + bandwidth allocation to such task groups. + +choice + depends on FAIR_GROUP_SCHED + prompt "Basis for grouping tasks" + default FAIR_USER_SCHED + +config FAIR_USER_SCHED + bool "user id" + help + This option will choose userid as the basis for grouping + tasks, thus providing equal CPU bandwidth to each user. + +endchoice + config SYSFS_DEPRECATED bool "Create deprecated sysfs files" default y Index: linux-cfs-2.6.23.8.q/init/main.c =================================================================== --- linux-cfs-2.6.23.8.q.orig/init/main.c +++ linux-cfs-2.6.23.8.q/init/main.c @@ -752,11 +752,8 @@ __setup("nosoftlockup", nosoftlockup_set static void __init do_pre_smp_initcalls(void) { extern int spawn_ksoftirqd(void); -#ifdef CONFIG_SMP - extern int migration_init(void); migration_init(); -#endif spawn_ksoftirqd(); if (!nosoftlockup) spawn_softlockup_task(); Index: linux-cfs-2.6.23.8.q/kernel/delayacct.c =================================================================== --- linux-cfs-2.6.23.8.q.orig/kernel/delayacct.c +++ linux-cfs-2.6.23.8.q/kernel/delayacct.c @@ -115,11 +115,17 @@ int __delayacct_add_tsk(struct taskstats tmp += timespec_to_ns(&ts); d->cpu_run_real_total = (tmp < (s64)d->cpu_run_real_total) ? 0 : tmp; + tmp = (s64)d->cpu_scaled_run_real_total; + cputime_to_timespec(tsk->utimescaled + tsk->stimescaled, &ts); + tmp += timespec_to_ns(&ts); + d->cpu_scaled_run_real_total = + (tmp < (s64)d->cpu_scaled_run_real_total) ? 0 : tmp; + /* * No locking available for sched_info (and too expensive to add one) * Mitigate by taking snapshot of values */ - t1 = tsk->sched_info.pcnt; + t1 = tsk->sched_info.pcount; t2 = tsk->sched_info.run_delay; t3 = tsk->sched_info.cpu_time; Index: linux-cfs-2.6.23.8.q/kernel/exit.c =================================================================== --- linux-cfs-2.6.23.8.q.orig/kernel/exit.c +++ linux-cfs-2.6.23.8.q/kernel/exit.c @@ -111,6 +111,7 @@ static void __exit_signal(struct task_st */ sig->utime = cputime_add(sig->utime, tsk->utime); sig->stime = cputime_add(sig->stime, tsk->stime); + sig->gtime = cputime_add(sig->gtime, tsk->gtime); sig->min_flt += tsk->min_flt; sig->maj_flt += tsk->maj_flt; sig->nvcsw += tsk->nvcsw; @@ -1242,6 +1243,11 @@ static int wait_task_zombie(struct task_ cputime_add(p->stime, cputime_add(sig->stime, sig->cstime))); + psig->cgtime = + cputime_add(psig->cgtime, + cputime_add(p->gtime, + cputime_add(sig->gtime, + sig->cgtime))); psig->cmin_flt += p->min_flt + sig->min_flt + sig->cmin_flt; psig->cmaj_flt += Index: linux-cfs-2.6.23.8.q/kernel/fork.c =================================================================== --- linux-cfs-2.6.23.8.q.orig/kernel/fork.c +++ linux-cfs-2.6.23.8.q/kernel/fork.c @@ -877,6 +877,8 @@ static inline int copy_signal(unsigned l sig->tty_old_pgrp = NULL; sig->utime = sig->stime = sig->cutime = sig->cstime = cputime_zero; + sig->gtime = cputime_zero; + sig->cgtime = cputime_zero; sig->nvcsw = sig->nivcsw = sig->cnvcsw = sig->cnivcsw = 0; sig->min_flt = sig->maj_flt = sig->cmin_flt = sig->cmaj_flt = 0; sig->inblock = sig->oublock = sig->cinblock = sig->coublock = 0; @@ -1047,6 +1049,9 @@ static struct task_struct *copy_process( p->stime = cputime_zero; p->prev_utime = cputime_zero; p->prev_stime = cputime_zero; + p->gtime = cputime_zero; + p->utimescaled = cputime_zero; + p->stimescaled = cputime_zero; #ifdef CONFIG_TASK_XACCT p->rchar = 0; /* I/O counter: bytes read */ Index: linux-cfs-2.6.23.8.q/kernel/ksysfs.c =================================================================== --- linux-cfs-2.6.23.8.q.orig/kernel/ksysfs.c +++ linux-cfs-2.6.23.8.q/kernel/ksysfs.c @@ -14,6 +14,7 @@ #include #include #include +#include #define KERNEL_ATTR_RO(_name) \ static struct subsys_attribute _name##_attr = __ATTR_RO(_name) @@ -116,6 +117,13 @@ static int __init ksysfs_init(void) ¬es_attr); } + /* + * Create "/sys/kernel/uids" directory and corresponding root user's + * directory under it. + */ + if (!error) + error = uids_kobject_init(); + return error; } Index: linux-cfs-2.6.23.8.q/kernel/sched.c =================================================================== --- linux-cfs-2.6.23.8.q.orig/kernel/sched.c +++ linux-cfs-2.6.23.8.q/kernel/sched.c @@ -44,6 +44,7 @@ #include #include #include +#include #include #include #include @@ -61,8 +62,10 @@ #include #include #include +#include #include +#include /* * Scheduler clock - returns current time in nanosec units. @@ -71,7 +74,7 @@ */ unsigned long long __attribute__((weak)) sched_clock(void) { - return (unsigned long long)jiffies * (1000000000 / HZ); + return (unsigned long long)jiffies * (NSEC_PER_SEC / HZ); } /* @@ -95,8 +98,8 @@ unsigned long long __attribute__((weak)) /* * Some helpers for converting nanosecond timing to jiffy resolution */ -#define NS_TO_JIFFIES(TIME) ((TIME) / (1000000000 / HZ)) -#define JIFFIES_TO_NS(TIME) ((TIME) * (1000000000 / HZ)) +#define NS_TO_JIFFIES(TIME) ((unsigned long)(TIME) / (NSEC_PER_SEC / HZ)) +#define JIFFIES_TO_NS(TIME) ((TIME) * (NSEC_PER_SEC / HZ)) #define NICE_0_LOAD SCHED_LOAD_SCALE #define NICE_0_SHIFT SCHED_LOAD_SHIFT @@ -104,11 +107,9 @@ unsigned long long __attribute__((weak)) /* * These are the 'tuning knobs' of the scheduler: * - * Minimum timeslice is 5 msecs (or 1 jiffy, whichever is larger), - * default timeslice is 100 msecs, maximum timeslice is 800 msecs. + * default timeslice is 100 msecs (used only for SCHED_RR tasks). * Timeslices get refilled after they expire. */ -#define MIN_TIMESLICE max(5 * HZ / 1000, 1) #define DEF_TIMESLICE (100 * HZ / 1000) #ifdef CONFIG_SMP @@ -132,24 +133,6 @@ static inline void sg_inc_cpu_power(stru } #endif -#define SCALE_PRIO(x, prio) \ - max(x * (MAX_PRIO - prio) / (MAX_USER_PRIO / 2), MIN_TIMESLICE) - -/* - * static_prio_timeslice() scales user-nice values [ -20 ... 0 ... 19 ] - * to time slice values: [800ms ... 100ms ... 5ms] - */ -static unsigned int static_prio_timeslice(int static_prio) -{ - if (static_prio == NICE_TO_PRIO(19)) - return 1; - - if (static_prio < NICE_TO_PRIO(0)) - return SCALE_PRIO(DEF_TIMESLICE * 4, static_prio); - else - return SCALE_PRIO(DEF_TIMESLICE, static_prio); -} - static inline int rt_policy(int policy) { if (unlikely(policy == SCHED_FIFO) || unlikely(policy == SCHED_RR)) @@ -170,31 +153,162 @@ struct rt_prio_array { struct list_head queue[MAX_RT_PRIO]; }; -struct load_stat { - struct load_weight load; - u64 load_update_start, load_update_last; - unsigned long delta_fair, delta_exec, delta_stat; +#ifdef CONFIG_FAIR_GROUP_SCHED + +#include + +struct cfs_rq; + +/* task group related information */ +struct task_group { +#ifdef CONFIG_FAIR_CGROUP_SCHED + struct cgroup_subsys_state css; +#endif + /* schedulable entities of this group on each cpu */ + struct sched_entity **se; + /* runqueue "owned" by this group on each cpu */ + struct cfs_rq **cfs_rq; + + /* shares assigned to a task group governs how much of cpu bandwidth + * is allocated to the group. The more shares a group has, the more is + * the cpu bandwidth allocated to it. + * + * For ex, lets say that there are three task groups, A, B and C which + * have been assigned shares 1000, 2000 and 3000 respectively. Then, + * cpu bandwidth allocated by the scheduler to task groups A, B and C + * should be: + * + * Bw(A) = 1000/(1000+2000+3000) * 100 = 16.66% + * Bw(B) = 2000/(1000+2000+3000) * 100 = 33.33% + * Bw(C) = 3000/(1000+2000+3000) * 100 = 50% + * + * The weight assigned to a task group's schedulable entities on every + * cpu (task_group.se[a_cpu]->load.weight) is derived from the task + * group's shares. For ex: lets say that task group A has been + * assigned shares of 1000 and there are two CPUs in a system. Then, + * + * tg_A->se[0]->load.weight = tg_A->se[1]->load.weight = 1000; + * + * Note: It's not necessary that each of a task's group schedulable + * entity have the same weight on all CPUs. If the group + * has 2 of its tasks on CPU0 and 1 task on CPU1, then a + * better distribution of weight could be: + * + * tg_A->se[0]->load.weight = 2/3 * 2000 = 1333 + * tg_A->se[1]->load.weight = 1/2 * 2000 = 667 + * + * rebalance_shares() is responsible for distributing the shares of a + * task groups like this among the group's schedulable entities across + * cpus. + * + */ + unsigned long shares; + + /* lock to serialize modification to shares */ + struct mutex lock; + + unsigned long last_total_load; + struct rcu_head rcu; +}; + +/* 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 struct sched_entity *init_sched_entity_p[NR_CPUS]; +static struct cfs_rq *init_cfs_rq_p[NR_CPUS]; + +static DEFINE_MUTEX(doms_cur_mutex); /* serialize access to doms_curr[] array */ + +#ifdef CONFIG_SMP +/* kernel thread that runs rebalance_shares() periodically */ +static struct task_struct *lb_monitor_task; + +static int load_balance_monitor(void *unused); +#endif + +static void set_se_shares(struct sched_entity *se, unsigned long shares); + +/* Default task group. + * Every task in system belong to this group at bootup. + */ +struct task_group init_task_group = { + .se = init_sched_entity_p, + .cfs_rq = init_cfs_rq_p, }; +#ifdef CONFIG_FAIR_USER_SCHED +# define INIT_TASK_GROUP_LOAD 2*NICE_0_LOAD /* root user's cpu share */ +#else +# define INIT_TASK_GROUP_LOAD NICE_0_LOAD +#endif + +#define MIN_GROUP_SHARES 100 + +static int init_task_group_load = INIT_TASK_GROUP_LOAD; + +/* return group to which a task belongs */ +static inline struct task_group *task_group(struct task_struct *p) +{ + struct task_group *tg; + +#ifdef CONFIG_FAIR_USER_SCHED + tg = p->user->tg; +#elif defined(CONFIG_FAIR_CGROUP_SCHED) + tg = container_of(task_subsys_state(p, cpu_cgroup_subsys_id), + struct task_group, css); +#else + tg = &init_task_group; +#endif + + return tg; +} + +/* Change a task's cfs_rq and parent entity if it moves across CPUs/groups */ +static inline void set_task_cfs_rq(struct task_struct *p, unsigned int cpu) +{ + p->se.cfs_rq = task_group(p)->cfs_rq[cpu]; + p->se.parent = task_group(p)->se[cpu]; +} + +static inline void lock_doms_cur(void) +{ + mutex_lock(&doms_cur_mutex); +} + +static inline void unlock_doms_cur(void) +{ + mutex_unlock(&doms_cur_mutex); +} + +#else + +static inline void set_task_cfs_rq(struct task_struct *p, unsigned int cpu) { } +static inline void lock_doms_cur(void) { } +static inline void unlock_doms_cur(void) { } + +#endif /* CONFIG_FAIR_GROUP_SCHED */ + /* CFS-related fields in a runqueue */ struct cfs_rq { struct load_weight load; unsigned long nr_running; - s64 fair_clock; u64 exec_clock; - s64 wait_runtime; - u64 sleeper_bonus; - unsigned long wait_runtime_overruns, wait_runtime_underruns; + u64 min_vruntime; struct rb_root tasks_timeline; struct rb_node *rb_leftmost; struct rb_node *rb_load_balance_curr; -#ifdef CONFIG_FAIR_GROUP_SCHED /* 'curr' points to currently running entity on this cfs_rq. * It is set to NULL otherwise (i.e when none are currently running). */ struct sched_entity *curr; + + unsigned long nr_spread_over; + +#ifdef CONFIG_FAIR_GROUP_SCHED struct rq *rq; /* cpu runqueue to which this cfs_rq is attached */ /* leaf cfs_rqs are those that hold tasks (lowest schedulable entity in @@ -205,6 +319,7 @@ struct cfs_rq { * list is used during load balance. */ struct list_head leaf_cfs_rq_list; /* Better name : task_cfs_rq_list? */ + struct task_group *tg; /* group that "owns" this runqueue */ #endif }; @@ -223,7 +338,8 @@ struct rt_rq { * acquire operations must be ordered by ascending &runqueue. */ struct rq { - spinlock_t lock; /* runqueue lock */ + /* runqueue lock: */ + spinlock_t lock; /* * nr_running and cpu_load should be in the same cacheline because @@ -236,13 +352,15 @@ struct rq { #ifdef CONFIG_NO_HZ unsigned char in_nohz_recently; #endif - struct load_stat ls; /* capture load from *all* tasks on this cpu */ + /* capture load from *all* tasks on this cpu: */ + struct load_weight load; unsigned long nr_load_updates; u64 nr_switches; struct cfs_rq cfs; #ifdef CONFIG_FAIR_GROUP_SCHED - struct list_head leaf_cfs_rq_list; /* list of leaf cfs_rq on this cpu */ + /* list of leaf cfs_rq on this cpu: */ + struct list_head leaf_cfs_rq_list; #endif struct rt_rq rt; @@ -274,7 +392,8 @@ struct rq { /* For active balancing */ int active_balance; int push_cpu; - int cpu; /* cpu of this runqueue */ + /* cpu of this runqueue: */ + int cpu; struct task_struct *migration_thread; struct list_head migration_queue; @@ -285,19 +404,22 @@ struct rq { struct sched_info rq_sched_info; /* sys_sched_yield() stats */ - unsigned long yld_exp_empty; - unsigned long yld_act_empty; - unsigned long yld_both_empty; - unsigned long yld_cnt; + unsigned int yld_exp_empty; + unsigned int yld_act_empty; + unsigned int yld_both_empty; + unsigned int yld_count; /* schedule() stats */ - unsigned long sched_switch; - unsigned long sched_cnt; - unsigned long sched_goidle; + unsigned int sched_switch; + unsigned int sched_count; + unsigned int sched_goidle; /* try_to_wake_up() stats */ - unsigned long ttwu_cnt; - unsigned long ttwu_local; + unsigned int ttwu_count; + unsigned int ttwu_local; + + /* BKL stats */ + unsigned int bkl_count; #endif struct lock_class_key rq_lock_key; }; @@ -382,6 +504,41 @@ static void update_rq_clock(struct rq *r #define cpu_curr(cpu) (cpu_rq(cpu)->curr) /* + * Tunables that become constants when CONFIG_SCHED_DEBUG is off: + */ +#ifdef CONFIG_SCHED_DEBUG +# define const_debug __read_mostly +#else +# define const_debug static const +#endif + +/* + * Debugging: various feature bits + */ +enum { + SCHED_FEAT_NEW_FAIR_SLEEPERS = 1, + SCHED_FEAT_WAKEUP_PREEMPT = 2, + SCHED_FEAT_START_DEBIT = 4, + SCHED_FEAT_TREE_AVG = 8, + SCHED_FEAT_APPROX_AVG = 16, +}; + +const_debug unsigned int sysctl_sched_features = + SCHED_FEAT_NEW_FAIR_SLEEPERS * 1 | + SCHED_FEAT_WAKEUP_PREEMPT * 1 | + SCHED_FEAT_START_DEBIT * 1 | + SCHED_FEAT_TREE_AVG * 0 | + SCHED_FEAT_APPROX_AVG * 0; + +#define sched_feat(x) (sysctl_sched_features & SCHED_FEAT_##x) + +/* + * Number of tasks to iterate in a single balance run. + * Limited because this is done with IRQs disabled. + */ +const_debug unsigned int sysctl_sched_nr_migrate = 32; + +/* * For kernel-internal use: high-speed (but slightly incorrect) per-cpu * clock constructed from sched_clock(): */ @@ -399,18 +556,7 @@ unsigned long long cpu_clock(int cpu) return now; } - -#ifdef CONFIG_FAIR_GROUP_SCHED -/* Change a task's ->cfs_rq if it moves across CPUs */ -static inline void set_task_cfs_rq(struct task_struct *p) -{ - p->se.cfs_rq = &task_rq(p)->cfs; -} -#else -static inline void set_task_cfs_rq(struct task_struct *p) -{ -} -#endif +EXPORT_SYMBOL_GPL(cpu_clock); #ifndef prepare_arch_switch # define prepare_arch_switch(next) do { } while (0) @@ -496,16 +642,13 @@ static inline void finish_lock_switch(st static inline struct rq *__task_rq_lock(struct task_struct *p) __acquires(rq->lock) { - struct rq *rq; - -repeat_lock_task: - rq = task_rq(p); - spin_lock(&rq->lock); - if (unlikely(rq != task_rq(p))) { + for (;;) { + struct rq *rq = task_rq(p); + spin_lock(&rq->lock); + if (likely(rq == task_rq(p))) + return rq; spin_unlock(&rq->lock); - goto repeat_lock_task; } - return rq; } /* @@ -518,18 +661,17 @@ static struct rq *task_rq_lock(struct ta { struct rq *rq; -repeat_lock_task: - local_irq_save(*flags); - rq = task_rq(p); - spin_lock(&rq->lock); - if (unlikely(rq != task_rq(p))) { + for (;;) { + local_irq_save(*flags); + rq = task_rq(p); + spin_lock(&rq->lock); + if (likely(rq == task_rq(p))) + return rq; spin_unlock_irqrestore(&rq->lock, *flags); - goto repeat_lock_task; } - return rq; } -static inline void __task_rq_unlock(struct rq *rq) +static void __task_rq_unlock(struct rq *rq) __releases(rq->lock) { spin_unlock(&rq->lock); @@ -544,7 +686,7 @@ static inline void task_rq_unlock(struct /* * this_rq_lock - lock this runqueue and disable interrupts. */ -static inline struct rq *this_rq_lock(void) +static struct rq *this_rq_lock(void) __acquires(rq->lock) { struct rq *rq; @@ -644,19 +786,6 @@ static inline void resched_task(struct t } #endif -static u64 div64_likely32(u64 divident, unsigned long divisor) -{ -#if BITS_PER_LONG == 32 - if (likely(divident <= 0xffffffffULL)) - return (u32)divident / divisor; - do_div(divident, divisor); - - return divident; -#else - return divident / divisor; -#endif -} - #if BITS_PER_LONG == 32 # define WMULT_CONST (~0UL) #else @@ -698,16 +827,14 @@ calc_delta_fair(unsigned long delta_exec return calc_delta_mine(delta_exec, NICE_0_LOAD, lw); } -static void update_load_add(struct load_weight *lw, unsigned long inc) +static inline void update_load_add(struct load_weight *lw, unsigned long inc) { lw->weight += inc; - lw->inv_weight = 0; } -static void update_load_sub(struct load_weight *lw, unsigned long dec) +static inline void update_load_sub(struct load_weight *lw, unsigned long dec) { lw->weight -= dec; - lw->inv_weight = 0; } /* @@ -776,90 +903,51 @@ struct rq_iterator { struct task_struct *(*next)(void *); }; -static int balance_tasks(struct rq *this_rq, int this_cpu, struct rq *busiest, - unsigned long max_nr_move, unsigned long max_load_move, - struct sched_domain *sd, enum cpu_idle_type idle, - int *all_pinned, unsigned long *load_moved, - int *this_best_prio, struct rq_iterator *iterator); +#ifdef CONFIG_SMP +static unsigned long +balance_tasks(struct rq *this_rq, int this_cpu, struct rq *busiest, + unsigned long max_load_move, struct sched_domain *sd, + enum cpu_idle_type idle, int *all_pinned, + int *this_best_prio, struct rq_iterator *iterator); -#include "sched_stats.h" -#include "sched_rt.c" -#include "sched_fair.c" -#include "sched_idletask.c" -#ifdef CONFIG_SCHED_DEBUG -# include "sched_debug.c" +static int +iter_move_one_task(struct rq *this_rq, int this_cpu, struct rq *busiest, + struct sched_domain *sd, enum cpu_idle_type idle, + struct rq_iterator *iterator); #endif -#define sched_class_highest (&rt_sched_class) - -static void __update_curr_load(struct rq *rq, struct load_stat *ls) +static inline void inc_load(struct rq *rq, unsigned long load) { - if (rq->curr != rq->idle && ls->load.weight) { - ls->delta_exec += ls->delta_stat; - ls->delta_fair += calc_delta_fair(ls->delta_stat, &ls->load); - ls->delta_stat = 0; - } + update_load_add(&rq->load, load); } -/* - * Update delta_exec, delta_fair fields for rq. - * - * delta_fair clock advances at a rate inversely proportional to - * total load (rq->ls.load.weight) on the runqueue, while - * delta_exec advances at the same rate as wall-clock (provided - * cpu is not idle). - * - * delta_exec / delta_fair is a measure of the (smoothened) load on this - * runqueue over any given interval. This (smoothened) load is used - * during load balance. - * - * This function is called /before/ updating rq->ls.load - * and when switching tasks. - */ -static void update_curr_load(struct rq *rq) +static inline void dec_load(struct rq *rq, unsigned long load) { - struct load_stat *ls = &rq->ls; - u64 start; - - start = ls->load_update_start; - ls->load_update_start = rq->clock; - ls->delta_stat += rq->clock - start; - /* - * Stagger updates to ls->delta_fair. Very frequent updates - * can be expensive. - */ - if (ls->delta_stat >= sysctl_sched_stat_granularity) - __update_curr_load(rq, ls); + update_load_sub(&rq->load, load); } -static inline void inc_load(struct rq *rq, const struct task_struct *p) -{ - update_curr_load(rq); - update_load_add(&rq->ls.load, p->se.load.weight); -} +#include "sched_stats.h" +#include "sched_idletask.c" +#include "sched_fair.c" +#include "sched_rt.c" +#ifdef CONFIG_SCHED_DEBUG +# include "sched_debug.c" +#endif -static inline void dec_load(struct rq *rq, const struct task_struct *p) -{ - update_curr_load(rq); - update_load_sub(&rq->ls.load, p->se.load.weight); -} +#define sched_class_highest (&rt_sched_class) static void inc_nr_running(struct task_struct *p, struct rq *rq) { rq->nr_running++; - inc_load(rq, p); } static void dec_nr_running(struct task_struct *p, struct rq *rq) { rq->nr_running--; - dec_load(rq, p); } static void set_load_weight(struct task_struct *p) { - p->se.wait_runtime = 0; - if (task_has_rt_policy(p)) { p->se.load.weight = prio_to_weight[0] * 2; p->se.load.inv_weight = prio_to_wmult[0] >> 1; @@ -951,20 +1039,6 @@ static void activate_task(struct rq *rq, } /* - * activate_idle_task - move idle task to the _front_ of runqueue. - */ -static inline void activate_idle_task(struct task_struct *p, struct rq *rq) -{ - update_rq_clock(rq); - - if (p->state == TASK_UNINTERRUPTIBLE) - rq->nr_uninterruptible--; - - enqueue_task(rq, p, 0); - inc_nr_running(p, rq); -} - -/* * deactivate_task - remove a task from the runqueue. */ static void deactivate_task(struct rq *rq, struct task_struct *p, int sleep) @@ -988,32 +1062,56 @@ inline int task_curr(const struct task_s /* Used instead of source_load when we know the type == 0 */ unsigned long weighted_cpuload(const int cpu) { - return cpu_rq(cpu)->ls.load.weight; + return cpu_rq(cpu)->load.weight; } static inline void __set_task_cpu(struct task_struct *p, unsigned int cpu) { + set_task_cfs_rq(p, cpu); #ifdef CONFIG_SMP + /* + * After ->cpu is set up to a new value, task_rq_lock(p, ...) can be + * successfuly executed on another CPU. We must ensure that updates of + * per-task data have been completed by this moment. + */ + smp_wmb(); task_thread_info(p)->cpu = cpu; - set_task_cfs_rq(p); #endif } #ifdef CONFIG_SMP +/* + * Is this task likely cache-hot: + */ +static inline int +task_hot(struct task_struct *p, u64 now, struct sched_domain *sd) +{ + s64 delta; + + if (p->sched_class != &fair_sched_class) + return 0; + + if (sysctl_sched_migration_cost == -1) + return 1; + if (sysctl_sched_migration_cost == 0) + return 0; + + delta = now - p->se.exec_start; + + return delta < (s64)sysctl_sched_migration_cost; +} + + void set_task_cpu(struct task_struct *p, unsigned int new_cpu) { int old_cpu = task_cpu(p); struct rq *old_rq = cpu_rq(old_cpu), *new_rq = cpu_rq(new_cpu); - u64 clock_offset, fair_clock_offset; + struct cfs_rq *old_cfsrq = task_cfs_rq(p), + *new_cfsrq = cpu_cfs_rq(old_cfsrq, new_cpu); + u64 clock_offset; clock_offset = old_rq->clock - new_rq->clock; - fair_clock_offset = old_rq->cfs.fair_clock - new_rq->cfs.fair_clock; - - if (p->se.wait_start_fair) - p->se.wait_start_fair -= fair_clock_offset; - if (p->se.sleep_start_fair) - p->se.sleep_start_fair -= fair_clock_offset; #ifdef CONFIG_SCHEDSTATS if (p->se.wait_start) @@ -1022,7 +1120,14 @@ void set_task_cpu(struct task_struct *p, p->se.sleep_start -= clock_offset; if (p->se.block_start) p->se.block_start -= clock_offset; + if (old_cpu != new_cpu) { + schedstat_inc(p, se.nr_migrations); + if (task_hot(p, old_rq->clock, NULL)) + schedstat_inc(p, se.nr_forced2_migrations); + } #endif + p->se.vruntime -= old_cfsrq->min_vruntime - + new_cfsrq->min_vruntime; __set_task_cpu(p, new_cpu); } @@ -1077,69 +1182,71 @@ void wait_task_inactive(struct task_stru int running, on_rq; struct rq *rq; -repeat: - /* - * We do the initial early heuristics without holding - * any task-queue locks at all. We'll only try to get - * the runqueue lock when things look like they will - * work out! - */ - rq = task_rq(p); + for (;;) { + /* + * We do the initial early heuristics without holding + * any task-queue locks at all. We'll only try to get + * the runqueue lock when things look like they will + * work out! + */ + rq = task_rq(p); - /* - * If the task is actively running on another CPU - * still, just relax and busy-wait without holding - * any locks. - * - * NOTE! Since we don't hold any locks, it's not - * even sure that "rq" stays as the right runqueue! - * But we don't care, since "task_running()" will - * return false if the runqueue has changed and p - * is actually now running somewhere else! - */ - while (task_running(rq, p)) - cpu_relax(); + /* + * If the task is actively running on another CPU + * still, just relax and busy-wait without holding + * any locks. + * + * NOTE! Since we don't hold any locks, it's not + * even sure that "rq" stays as the right runqueue! + * But we don't care, since "task_running()" will + * return false if the runqueue has changed and p + * is actually now running somewhere else! + */ + while (task_running(rq, p)) + cpu_relax(); - /* - * Ok, time to look more closely! We need the rq - * lock now, to be *sure*. If we're wrong, we'll - * just go back and repeat. - */ - rq = task_rq_lock(p, &flags); - running = task_running(rq, p); - on_rq = p->se.on_rq; - task_rq_unlock(rq, &flags); + /* + * Ok, time to look more closely! We need the rq + * lock now, to be *sure*. If we're wrong, we'll + * just go back and repeat. + */ + rq = task_rq_lock(p, &flags); + running = task_running(rq, p); + on_rq = p->se.on_rq; + task_rq_unlock(rq, &flags); - /* - * Was it really running after all now that we - * checked with the proper locks actually held? - * - * Oops. Go back and try again.. - */ - if (unlikely(running)) { - cpu_relax(); - goto repeat; - } + /* + * Was it really running after all now that we + * checked with the proper locks actually held? + * + * Oops. Go back and try again.. + */ + if (unlikely(running)) { + cpu_relax(); + continue; + } - /* - * It's not enough that it's not actively running, - * it must be off the runqueue _entirely_, and not - * preempted! - * - * So if it wa still runnable (but just not actively - * running right now), it's preempted, and we should - * yield - it could be a while. - */ - if (unlikely(on_rq)) { - yield(); - goto repeat; - } + /* + * It's not enough that it's not actively running, + * it must be off the runqueue _entirely_, and not + * preempted! + * + * So if it wa still runnable (but just not actively + * running right now), it's preempted, and we should + * yield - it could be a while. + */ + if (unlikely(on_rq)) { + schedule_timeout_uninterruptible(1); + continue; + } - /* - * Ahh, all good. It wasn't running, and it wasn't - * runnable, which means that it will never become - * running in the future either. We're all done! - */ + /* + * Ahh, all good. It wasn't running, and it wasn't + * runnable, which means that it will never become + * running in the future either. We're all done! + */ + break; + } } /*** @@ -1173,7 +1280,7 @@ void kick_process(struct task_struct *p) * We want to under-estimate the load of migration sources, to * balance conservatively. */ -static inline unsigned long source_load(int cpu, int type) +static unsigned long source_load(int cpu, int type) { struct rq *rq = cpu_rq(cpu); unsigned long total = weighted_cpuload(cpu); @@ -1188,7 +1295,7 @@ static inline unsigned long source_load( * Return a high guess at the load of a migration-target cpu weighted * according to the scheduling class and "nice" value. */ -static inline unsigned long target_load(int cpu, int type) +static unsigned long target_load(int cpu, int type) { struct rq *rq = cpu_rq(cpu); unsigned long total = weighted_cpuload(cpu); @@ -1230,7 +1337,7 @@ find_idlest_group(struct sched_domain *s /* Skip over this group if it has no CPUs allowed */ if (!cpus_intersects(group->cpumask, p->cpus_allowed)) - goto nextgroup; + continue; local_group = cpu_isset(this_cpu, group->cpumask); @@ -1258,9 +1365,7 @@ find_idlest_group(struct sched_domain *s min_load = avg_load; idlest = group; } -nextgroup: - group = group->next; - } while (group != sd->groups); + } while (group = group->next, group != sd->groups); if (!idlest || 100*this_load < imbalance*min_load) return NULL; @@ -1392,8 +1497,13 @@ static int wake_idle(int cpu, struct tas if (sd->flags & SD_WAKE_IDLE) { cpus_and(tmp, sd->span, p->cpus_allowed); for_each_cpu_mask(i, tmp) { - if (idle_cpu(i)) + if (idle_cpu(i)) { + if (i != task_cpu(p)) { + schedstat_inc(p, + se.nr_wakeups_idle); + } return i; + } } } else { break; @@ -1424,7 +1534,7 @@ static inline int wake_idle(int cpu, str */ static int try_to_wake_up(struct task_struct *p, unsigned int state, int sync) { - int cpu, this_cpu, success = 0; + int cpu, orig_cpu, this_cpu, success = 0; unsigned long flags; long old_state; struct rq *rq; @@ -1443,6 +1553,7 @@ static int try_to_wake_up(struct task_st goto out_running; cpu = task_cpu(p); + orig_cpu = cpu; this_cpu = smp_processor_id(); #ifdef CONFIG_SMP @@ -1451,7 +1562,7 @@ static int try_to_wake_up(struct task_st new_cpu = cpu; - schedstat_inc(rq, ttwu_cnt); + schedstat_inc(rq, ttwu_count); if (cpu == this_cpu) { schedstat_inc(rq, ttwu_local); goto out_set_cpu; @@ -1486,6 +1597,13 @@ static int try_to_wake_up(struct task_st unsigned long tl = this_load; unsigned long tl_per_task; + /* + * Attract cache-cold tasks on sync wakeups: + */ + if (sync && !task_hot(p, rq->clock, this_sd)) + goto out_set_cpu; + + schedstat_inc(p, se.nr_wakeups_affine_attempts); tl_per_task = cpu_avg_load_per_task(this_cpu); /* @@ -1505,6 +1623,7 @@ static int try_to_wake_up(struct task_st * there is no bad imbalance. */ schedstat_inc(this_sd, ttwu_move_affine); + schedstat_inc(p, se.nr_wakeups_affine); goto out_set_cpu; } } @@ -1516,6 +1635,7 @@ static int try_to_wake_up(struct task_st if (this_sd->flags & SD_WAKE_BALANCE) { if (imbalance*this_load <= 100*load) { schedstat_inc(this_sd, ttwu_move_balance); + schedstat_inc(p, se.nr_wakeups_passive); goto out_set_cpu; } } @@ -1541,18 +1661,18 @@ out_set_cpu: out_activate: #endif /* CONFIG_SMP */ + schedstat_inc(p, se.nr_wakeups); + if (sync) + schedstat_inc(p, se.nr_wakeups_sync); + if (orig_cpu != cpu) + schedstat_inc(p, se.nr_wakeups_migrate); + if (cpu == this_cpu) + schedstat_inc(p, se.nr_wakeups_local); + else + schedstat_inc(p, se.nr_wakeups_remote); update_rq_clock(rq); activate_task(rq, p, 1); - /* - * Sync wakeups (i.e. those types of wakeups where the waker - * has indicated that it will leave the CPU in short order) - * don't trigger a preemption, if the woken up task will run on - * this cpu. (in this case the 'I will reschedule' promise of - * the waker guarantees that the freshly woken up task is going - * to be considered on this CPU.) - */ - if (!sync || cpu != this_cpu) - check_preempt_curr(rq, p); + check_preempt_curr(rq, p); success = 1; out_running: @@ -1583,28 +1703,20 @@ int fastcall wake_up_state(struct task_s */ static void __sched_fork(struct task_struct *p) { - p->se.wait_start_fair = 0; p->se.exec_start = 0; p->se.sum_exec_runtime = 0; p->se.prev_sum_exec_runtime = 0; - p->se.delta_exec = 0; - p->se.delta_fair_run = 0; - p->se.delta_fair_sleep = 0; - p->se.wait_runtime = 0; - p->se.sleep_start_fair = 0; #ifdef CONFIG_SCHEDSTATS p->se.wait_start = 0; - p->se.sum_wait_runtime = 0; p->se.sum_sleep_runtime = 0; p->se.sleep_start = 0; p->se.block_start = 0; p->se.sleep_max = 0; p->se.block_max = 0; p->se.exec_max = 0; + p->se.slice_max = 0; p->se.wait_max = 0; - p->se.wait_runtime_overruns = 0; - p->se.wait_runtime_underruns = 0; #endif INIT_LIST_HEAD(&p->run_list); @@ -1635,12 +1747,14 @@ void sched_fork(struct task_struct *p, i #ifdef CONFIG_SMP cpu = sched_balance_self(cpu, SD_BALANCE_FORK); #endif - __set_task_cpu(p, cpu); + set_task_cpu(p, cpu); /* * Make sure we do not leak PI boosting priority to the child: */ p->prio = current->normal_prio; + if (!rt_prio(p->prio)) + p->sched_class = &fair_sched_class; #if defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT) if (likely(sched_info_on())) @@ -1657,12 +1771,6 @@ void sched_fork(struct task_struct *p, i } /* - * After fork, child runs first. (default) If set to 0 then - * parent will (try to) run first. - */ -unsigned int __read_mostly sysctl_sched_child_runs_first = 1; - -/* * wake_up_new_task - wake up a newly created task for the first time. * * This function will do some initial scheduler statistics housekeeping @@ -1673,24 +1781,14 @@ void fastcall wake_up_new_task(struct ta { unsigned long flags; struct rq *rq; - int this_cpu; rq = task_rq_lock(p, &flags); BUG_ON(p->state != TASK_RUNNING); - this_cpu = smp_processor_id(); /* parent's CPU */ update_rq_clock(rq); p->prio = effective_prio(p); - if (rt_prio(p->prio)) - p->sched_class = &rt_sched_class; - else - p->sched_class = &fair_sched_class; - - if (!p->sched_class->task_new || !sysctl_sched_child_runs_first || - (clone_flags & CLONE_VM) || task_cpu(p) != this_cpu || - !current->se.on_rq) { - + if (!p->sched_class->task_new || !current->se.on_rq) { activate_task(rq, p, 0); } else { /* @@ -1799,7 +1897,7 @@ prepare_task_switch(struct rq *rq, struc * with the lock held can cause deadlocks; see schedule() for * details.) */ -static inline void finish_task_switch(struct rq *rq, struct task_struct *prev) +static void finish_task_switch(struct rq *rq, struct task_struct *prev) __releases(rq->lock) { struct mm_struct *mm = rq->prev_mm; @@ -1849,7 +1947,7 @@ asmlinkage void schedule_tail(struct tas preempt_enable(); #endif if (current->set_child_tid) - put_user(current->pid, current->set_child_tid); + put_user(task_pid_vnr(current), current->set_child_tid); } /* @@ -1981,42 +2079,10 @@ unsigned long nr_active(void) */ static void update_cpu_load(struct rq *this_rq) { - u64 fair_delta64, exec_delta64, idle_delta64, sample_interval64, tmp64; - unsigned long total_load = this_rq->ls.load.weight; - unsigned long this_load = total_load; - struct load_stat *ls = &this_rq->ls; + unsigned long this_load = this_rq->load.weight; int i, scale; this_rq->nr_load_updates++; - if (unlikely(!(sysctl_sched_features & SCHED_FEAT_PRECISE_CPU_LOAD))) - goto do_avg; - - /* Update delta_fair/delta_exec fields first */ - update_curr_load(this_rq); - - fair_delta64 = ls->delta_fair + 1; - ls->delta_fair = 0; - - exec_delta64 = ls->delta_exec + 1; - ls->delta_exec = 0; - - sample_interval64 = this_rq->clock - ls->load_update_last; - ls->load_update_last = this_rq->clock; - - if ((s64)sample_interval64 < (s64)TICK_NSEC) - sample_interval64 = TICK_NSEC; - - if (exec_delta64 > sample_interval64) - exec_delta64 = sample_interval64; - - idle_delta64 = sample_interval64 - exec_delta64; - - tmp64 = div64_64(SCHED_LOAD_SCALE * exec_delta64, fair_delta64); - tmp64 = div64_64(tmp64 * exec_delta64, sample_interval64); - - this_load = (unsigned long)tmp64; - -do_avg: /* Update our load: */ for (i = 0, scale = 1; i < CPU_LOAD_IDX_MAX; i++, scale += scale) { @@ -2026,7 +2092,13 @@ do_avg: old_load = this_rq->cpu_load[i]; new_load = this_load; - + /* + * Round up the averaging division if load is increasing. This + * prevents us from getting stuck on 9 if the load is 10, for + * example. + */ + if (new_load > old_load) + new_load += scale-1; this_rq->cpu_load[i] = (old_load*(scale-1) + new_load) >> i; } } @@ -2178,27 +2250,52 @@ int can_migrate_task(struct task_struct * 2) cannot be migrated to this CPU due to cpus_allowed, or * 3) are cache-hot on their current CPU. */ - if (!cpu_isset(this_cpu, p->cpus_allowed)) + if (!cpu_isset(this_cpu, p->cpus_allowed)) { + schedstat_inc(p, se.nr_failed_migrations_affine); return 0; + } *all_pinned = 0; - if (task_running(rq, p)) + if (task_running(rq, p)) { + schedstat_inc(p, se.nr_failed_migrations_running); return 0; + } + + /* + * Aggressive migration if: + * 1) task is cache cold, or + * 2) too many balance attempts have failed. + */ + + if (!task_hot(p, rq->clock, sd) || + sd->nr_balance_failed > sd->cache_nice_tries) { +#ifdef CONFIG_SCHEDSTATS + if (task_hot(p, rq->clock, sd)) { + schedstat_inc(sd, lb_hot_gained[idle]); + schedstat_inc(p, se.nr_forced_migrations); + } +#endif + return 1; + } + if (task_hot(p, rq->clock, sd)) { + schedstat_inc(p, se.nr_failed_migrations_hot); + return 0; + } return 1; } -static int balance_tasks(struct rq *this_rq, int this_cpu, struct rq *busiest, - unsigned long max_nr_move, unsigned long max_load_move, - struct sched_domain *sd, enum cpu_idle_type idle, - int *all_pinned, unsigned long *load_moved, - int *this_best_prio, struct rq_iterator *iterator) +static unsigned long +balance_tasks(struct rq *this_rq, int this_cpu, struct rq *busiest, + unsigned long max_load_move, struct sched_domain *sd, + enum cpu_idle_type idle, int *all_pinned, + int *this_best_prio, struct rq_iterator *iterator) { - int pulled = 0, pinned = 0, skip_for_load; + int loops = 0, pulled = 0, pinned = 0, skip_for_load; struct task_struct *p; long rem_load_move = max_load_move; - if (max_nr_move == 0 || max_load_move == 0) + if (max_load_move == 0) goto out; pinned = 1; @@ -2208,10 +2305,10 @@ static int balance_tasks(struct rq *this */ p = iterator->start(iterator->arg); next: - if (!p) + if (!p || loops++ > sysctl_sched_nr_migrate) goto out; /* - * To help distribute high priority tasks accross CPUs we don't + * To help distribute high priority tasks across CPUs we don't * skip a task if it will be the highest priority task (i.e. smallest * prio value) on its new queue regardless of its load weight */ @@ -2228,10 +2325,9 @@ next: rem_load_move -= p->se.load.weight; /* - * We only want to steal up to the prescribed number of tasks - * and the prescribed amount of weighted load. + * We only want to steal up to the prescribed amount of weighted load. */ - if (pulled < max_nr_move && rem_load_move > 0) { + if (rem_load_move > 0) { if (p->prio < *this_best_prio) *this_best_prio = p->prio; p = iterator->next(iterator->arg); @@ -2239,7 +2335,7 @@ next: } out: /* - * Right now, this is the only place pull_task() is called, + * Right now, this is one of only two places pull_task() is called, * so we can safely collect pull_task() stats here rather than * inside pull_task(). */ @@ -2247,8 +2343,8 @@ out: if (all_pinned) *all_pinned = pinned; - *load_moved = max_load_move - rem_load_move; - return pulled; + + return max_load_move - rem_load_move; } /* @@ -2263,14 +2359,14 @@ static int move_tasks(struct rq *this_rq struct sched_domain *sd, enum cpu_idle_type idle, int *all_pinned) { - struct sched_class *class = sched_class_highest; + const struct sched_class *class = sched_class_highest; unsigned long total_load_moved = 0; int this_best_prio = this_rq->curr->prio; do { total_load_moved += class->load_balance(this_rq, this_cpu, busiest, - ULONG_MAX, max_load_move - total_load_moved, + max_load_move - total_load_moved, sd, idle, all_pinned, &this_best_prio); class = class->next; } while (class && max_load_move > total_load_moved); @@ -2278,6 +2374,32 @@ static int move_tasks(struct rq *this_rq return total_load_moved > 0; } +static int +iter_move_one_task(struct rq *this_rq, int this_cpu, struct rq *busiest, + struct sched_domain *sd, enum cpu_idle_type idle, + struct rq_iterator *iterator) +{ + struct task_struct *p = iterator->start(iterator->arg); + int pinned = 0; + + while (p) { + if (can_migrate_task(p, busiest, this_cpu, sd, idle, &pinned)) { + pull_task(busiest, p, this_rq, this_cpu); + /* + * Right now, this is only the second place pull_task() + * is called, so we can safely collect pull_task() + * stats here rather than inside pull_task(). + */ + schedstat_inc(sd, lb_gained[idle]); + + return 1; + } + p = iterator->next(iterator->arg); + } + + return 0; +} + /* * move_one_task tries to move exactly one task from busiest to this_rq, as * part of active balancing operations within "domain". @@ -2288,13 +2410,10 @@ static int move_tasks(struct rq *this_rq static int move_one_task(struct rq *this_rq, int this_cpu, struct rq *busiest, struct sched_domain *sd, enum cpu_idle_type idle) { - struct sched_class *class; - int this_best_prio = MAX_PRIO; + const struct sched_class *class; for (class = sched_class_highest; class; class = class->next) - if (class->load_balance(this_rq, this_cpu, busiest, - 1, ULONG_MAX, sd, idle, NULL, - &this_best_prio)) + if (class->move_one_task(this_rq, this_cpu, busiest, sd, idle)) return 1; return 0; @@ -2315,7 +2434,7 @@ find_busiest_group(struct sched_domain * unsigned long max_pull; unsigned long busiest_load_per_task, busiest_nr_running; unsigned long this_load_per_task, this_nr_running; - int load_idx; + int load_idx, group_imb = 0; #if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT) int power_savings_balance = 1; unsigned long leader_nr_running = 0, min_load_per_task = 0; @@ -2334,9 +2453,10 @@ find_busiest_group(struct sched_domain * load_idx = sd->idle_idx; do { - unsigned long load, group_capacity; + unsigned long load, group_capacity, max_cpu_load, min_cpu_load; int local_group; int i; + int __group_imb = 0; unsigned int balance_cpu = -1, first_idle_cpu = 0; unsigned long sum_nr_running, sum_weighted_load; @@ -2347,6 +2467,8 @@ find_busiest_group(struct sched_domain * /* Tally up the load of all CPUs in the group */ sum_weighted_load = sum_nr_running = avg_load = 0; + max_cpu_load = 0; + min_cpu_load = ~0UL; for_each_cpu_mask(i, group->cpumask) { struct rq *rq; @@ -2367,8 +2489,13 @@ find_busiest_group(struct sched_domain * } load = target_load(i, load_idx); - } else + } else { load = source_load(i, load_idx); + if (load > max_cpu_load) + max_cpu_load = load; + if (min_cpu_load > load) + min_cpu_load = load; + } avg_load += load; sum_nr_running += rq->nr_running; @@ -2394,6 +2521,9 @@ find_busiest_group(struct sched_domain * avg_load = sg_div_cpu_power(group, avg_load * SCHED_LOAD_SCALE); + if ((max_cpu_load - min_cpu_load) > SCHED_LOAD_SCALE) + __group_imb = 1; + group_capacity = group->__cpu_power / SCHED_LOAD_SCALE; if (local_group) { @@ -2402,11 +2532,12 @@ find_busiest_group(struct sched_domain * this_nr_running = sum_nr_running; this_load_per_task = sum_weighted_load; } else if (avg_load > max_load && - sum_nr_running > group_capacity) { + (sum_nr_running > group_capacity || __group_imb)) { max_load = avg_load; busiest = group; busiest_nr_running = sum_nr_running; busiest_load_per_task = sum_weighted_load; + group_imb = __group_imb; } #if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT) @@ -2478,6 +2609,9 @@ group_next: goto out_balanced; busiest_load_per_task /= busiest_nr_running; + if (group_imb) + busiest_load_per_task = min(busiest_load_per_task, avg_load); + /* * We're trying to get all the cpus to the average_load, so we don't * want to push ourselves above the average load, nor do we wish to @@ -2652,7 +2786,7 @@ static int load_balance(int this_cpu, st !test_sd_parent(sd, SD_POWERSAVINGS_BALANCE)) sd_idle = 1; - schedstat_inc(sd, lb_cnt[idle]); + schedstat_inc(sd, lb_count[idle]); redo: group = find_busiest_group(sd, this_cpu, &imbalance, idle, &sd_idle, @@ -2805,7 +2939,7 @@ load_balance_newidle(int this_cpu, struc !test_sd_parent(sd, SD_POWERSAVINGS_BALANCE)) sd_idle = 1; - schedstat_inc(sd, lb_cnt[CPU_NEWLY_IDLE]); + schedstat_inc(sd, lb_count[CPU_NEWLY_IDLE]); redo: group = find_busiest_group(sd, this_cpu, &imbalance, CPU_NEWLY_IDLE, &sd_idle, &cpus, NULL); @@ -2939,7 +3073,7 @@ static void active_load_balance(struct r } if (likely(sd)) { - schedstat_inc(sd, alb_cnt); + schedstat_inc(sd, alb_count); if (move_one_task(target_rq, target_cpu, busiest_rq, sd, CPU_IDLE)) @@ -3032,7 +3166,7 @@ static DEFINE_SPINLOCK(balancing); * * Balancing parameters are set up in arch_init_sched_domains. */ -static inline void rebalance_domains(int cpu, enum cpu_idle_type idle) +static void rebalance_domains(int cpu, enum cpu_idle_type idle) { int balance = 1; struct rq *rq = cpu_rq(cpu); @@ -3216,18 +3350,6 @@ static inline void idle_balance(int cpu, { } -/* Avoid "used but not defined" warning on UP */ -static int balance_tasks(struct rq *this_rq, int this_cpu, struct rq *busiest, - unsigned long max_nr_move, unsigned long max_load_move, - struct sched_domain *sd, enum cpu_idle_type idle, - int *all_pinned, unsigned long *load_moved, - int *this_best_prio, struct rq_iterator *iterator) -{ - *load_moved = 0; - - return 0; -} - #endif DEFINE_PER_CPU(struct kernel_stat, kstat); @@ -3260,7 +3382,6 @@ unsigned long long task_sched_runtime(st /* * Account user cpu time to a process. * @p: the process that the cpu time gets accounted to - * @hardirq_offset: the offset to subtract from hardirq_count() * @cputime: the cpu time spent in user space since the last update */ void account_user_time(struct task_struct *p, cputime_t cputime) @@ -3279,6 +3400,35 @@ void account_user_time(struct task_struc } /* + * Account guest cpu time to a process. + * @p: the process that the cpu time gets accounted to + * @cputime: the cpu time spent in virtual machine since the last update + */ +static void account_guest_time(struct task_struct *p, cputime_t cputime) +{ + cputime64_t tmp; + struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat; + + tmp = cputime_to_cputime64(cputime); + + p->utime = cputime_add(p->utime, cputime); + p->gtime = cputime_add(p->gtime, cputime); + + cpustat->user = cputime64_add(cpustat->user, tmp); + cpustat->guest = cputime64_add(cpustat->guest, tmp); +} + +/* + * Account scaled user cpu time to a process. + * @p: the process that the cpu time gets accounted to + * @cputime: the cpu time spent in user space since the last update + */ +void account_user_time_scaled(struct task_struct *p, cputime_t cputime) +{ + p->utimescaled = cputime_add(p->utimescaled, cputime); +} + +/* * Account system cpu time to a process. * @p: the process that the cpu time gets accounted to * @hardirq_offset: the offset to subtract from hardirq_count() @@ -3291,6 +3441,9 @@ void account_system_time(struct task_str struct rq *rq = this_rq(); cputime64_t tmp; + if ((p->flags & PF_VCPU) && (irq_count() - hardirq_offset == 0)) + return account_guest_time(p, cputime); + p->stime = cputime_add(p->stime, cputime); /* Add system time to cpustat. */ @@ -3310,6 +3463,17 @@ void account_system_time(struct task_str } /* + * Account scaled system cpu time to a process. + * @p: the process that the cpu time gets accounted to + * @hardirq_offset: the offset to subtract from hardirq_count() + * @cputime: the cpu time spent in kernel space since the last update + */ +void account_system_time_scaled(struct task_struct *p, cputime_t cputime) +{ + p->stimescaled = cputime_add(p->stimescaled, cputime); +} + +/* * Account for involuntary wait time. * @p: the process from which the cpu time has been stolen * @steal: the cpu time spent in involuntary wait @@ -3406,12 +3570,19 @@ EXPORT_SYMBOL(sub_preempt_count); */ static noinline void __schedule_bug(struct task_struct *prev) { - printk(KERN_ERR "BUG: scheduling while atomic: %s/0x%08x/%d\n", - prev->comm, preempt_count(), prev->pid); + struct pt_regs *regs = get_irq_regs(); + + printk(KERN_ERR "BUG: scheduling while atomic: %s/%d/0x%08x\n", + prev->comm, prev->pid, preempt_count()); + debug_show_held_locks(prev); if (irqs_disabled()) print_irqtrace_events(prev); - dump_stack(); + + if (regs) + show_regs(regs); + else + dump_stack(); } /* @@ -3429,7 +3600,13 @@ static inline void schedule_debug(struct profile_hit(SCHED_PROFILING, __builtin_return_address(0)); - schedstat_inc(this_rq(), sched_cnt); + schedstat_inc(this_rq(), sched_count); +#ifdef CONFIG_SCHEDSTATS + if (unlikely(prev->lock_depth >= 0)) { + schedstat_inc(this_rq(), bkl_count); + schedstat_inc(prev, sched_info.bkl_count); + } +#endif } /* @@ -3438,7 +3615,7 @@ static inline void schedule_debug(struct static inline struct task_struct * pick_next_task(struct rq *rq, struct task_struct *prev) { - struct sched_class *class; + const struct sched_class *class; struct task_struct *p; /* @@ -3487,9 +3664,13 @@ need_resched_nonpreemptible: schedule_debug(prev); - spin_lock_irq(&rq->lock); - clear_tsk_need_resched(prev); + /* + * Do the rq-clock update outside the rq lock: + */ + local_irq_disable(); __update_rq_clock(rq); + spin_lock(&rq->lock); + clear_tsk_need_resched(prev); if (prev->state && !(preempt_count() & PREEMPT_ACTIVE)) { if (unlikely((prev->state & TASK_INTERRUPTIBLE) && @@ -3549,27 +3730,30 @@ asmlinkage void __sched preempt_schedule if (likely(ti->preempt_count || irqs_disabled())) return; -need_resched: - add_preempt_count(PREEMPT_ACTIVE); - /* - * We keep the big kernel semaphore locked, but we - * clear ->lock_depth so that schedule() doesnt - * auto-release the semaphore: - */ + do { + add_preempt_count(PREEMPT_ACTIVE); + + /* + * We keep the big kernel semaphore locked, but we + * clear ->lock_depth so that schedule() doesnt + * auto-release the semaphore: + */ #ifdef CONFIG_PREEMPT_BKL - saved_lock_depth = task->lock_depth; - task->lock_depth = -1; + saved_lock_depth = task->lock_depth; + task->lock_depth = -1; #endif - schedule(); + schedule(); #ifdef CONFIG_PREEMPT_BKL - task->lock_depth = saved_lock_depth; + task->lock_depth = saved_lock_depth; #endif - sub_preempt_count(PREEMPT_ACTIVE); + sub_preempt_count(PREEMPT_ACTIVE); - /* we could miss a preemption opportunity between schedule and now */ - barrier(); - if (unlikely(test_thread_flag(TIF_NEED_RESCHED))) - goto need_resched; + /* + * Check again in case we missed a preemption opportunity + * between schedule and now. + */ + barrier(); + } while (unlikely(test_thread_flag(TIF_NEED_RESCHED))); } EXPORT_SYMBOL(preempt_schedule); @@ -3589,29 +3773,32 @@ asmlinkage void __sched preempt_schedule /* Catch callers which need to be fixed */ BUG_ON(ti->preempt_count || !irqs_disabled()); -need_resched: - add_preempt_count(PREEMPT_ACTIVE); - /* - * We keep the big kernel semaphore locked, but we - * clear ->lock_depth so that schedule() doesnt - * auto-release the semaphore: - */ + do { + add_preempt_count(PREEMPT_ACTIVE); + + /* + * We keep the big kernel semaphore locked, but we + * clear ->lock_depth so that schedule() doesnt + * auto-release the semaphore: + */ #ifdef CONFIG_PREEMPT_BKL - saved_lock_depth = task->lock_depth; - task->lock_depth = -1; + saved_lock_depth = task->lock_depth; + task->lock_depth = -1; #endif - local_irq_enable(); - schedule(); - local_irq_disable(); + local_irq_enable(); + schedule(); + local_irq_disable(); #ifdef CONFIG_PREEMPT_BKL - task->lock_depth = saved_lock_depth; + task->lock_depth = saved_lock_depth; #endif - sub_preempt_count(PREEMPT_ACTIVE); + sub_preempt_count(PREEMPT_ACTIVE); - /* we could miss a preemption opportunity between schedule and now */ - barrier(); - if (unlikely(test_thread_flag(TIF_NEED_RESCHED))) - goto need_resched; + /* + * Check again in case we missed a preemption opportunity + * between schedule and now. + */ + barrier(); + } while (unlikely(test_thread_flag(TIF_NEED_RESCHED))); } #endif /* CONFIG_PREEMPT */ @@ -3635,10 +3822,9 @@ EXPORT_SYMBOL(default_wake_function); static void __wake_up_common(wait_queue_head_t *q, unsigned int mode, int nr_exclusive, int sync, void *key) { - struct list_head *tmp, *next; + wait_queue_t *curr, *next; - list_for_each_safe(tmp, next, &q->task_list) { - wait_queue_t *curr = list_entry(tmp, wait_queue_t, task_list); + list_for_each_entry_safe(curr, next, &q->task_list, task_list) { unsigned flags = curr->flags; if (curr->func(curr, mode, sync, key) && @@ -3704,7 +3890,7 @@ __wake_up_sync(wait_queue_head_t *q, uns } EXPORT_SYMBOL_GPL(__wake_up_sync); /* For internal use only */ -void fastcall complete(struct completion *x) +void complete(struct completion *x) { unsigned long flags; @@ -3716,7 +3902,7 @@ void fastcall complete(struct completion } EXPORT_SYMBOL(complete); -void fastcall complete_all(struct completion *x) +void complete_all(struct completion *x) { unsigned long flags; @@ -3728,206 +3914,119 @@ void fastcall complete_all(struct comple } EXPORT_SYMBOL(complete_all); -void fastcall __sched wait_for_completion(struct completion *x) -{ - might_sleep(); - - spin_lock_irq(&x->wait.lock); - if (!x->done) { - DECLARE_WAITQUEUE(wait, current); - - wait.flags |= WQ_FLAG_EXCLUSIVE; - __add_wait_queue_tail(&x->wait, &wait); - do { - __set_current_state(TASK_UNINTERRUPTIBLE); - spin_unlock_irq(&x->wait.lock); - schedule(); - spin_lock_irq(&x->wait.lock); - } while (!x->done); - __remove_wait_queue(&x->wait, &wait); - } - x->done--; - spin_unlock_irq(&x->wait.lock); -} -EXPORT_SYMBOL(wait_for_completion); - -unsigned long fastcall __sched -wait_for_completion_timeout(struct completion *x, unsigned long timeout) +static inline long __sched +do_wait_for_common(struct completion *x, long timeout, int state) { - might_sleep(); - - spin_lock_irq(&x->wait.lock); if (!x->done) { DECLARE_WAITQUEUE(wait, current); wait.flags |= WQ_FLAG_EXCLUSIVE; __add_wait_queue_tail(&x->wait, &wait); do { - __set_current_state(TASK_UNINTERRUPTIBLE); + if (state == TASK_INTERRUPTIBLE && + signal_pending(current)) { + __remove_wait_queue(&x->wait, &wait); + return -ERESTARTSYS; + } + __set_current_state(state); spin_unlock_irq(&x->wait.lock); timeout = schedule_timeout(timeout); spin_lock_irq(&x->wait.lock); if (!timeout) { __remove_wait_queue(&x->wait, &wait); - goto out; + return timeout; } } while (!x->done); __remove_wait_queue(&x->wait, &wait); } x->done--; -out: - spin_unlock_irq(&x->wait.lock); return timeout; } -EXPORT_SYMBOL(wait_for_completion_timeout); -int fastcall __sched wait_for_completion_interruptible(struct completion *x) +static long __sched +wait_for_common(struct completion *x, long timeout, int state) { - int ret = 0; - might_sleep(); spin_lock_irq(&x->wait.lock); - if (!x->done) { - DECLARE_WAITQUEUE(wait, current); - - wait.flags |= WQ_FLAG_EXCLUSIVE; - __add_wait_queue_tail(&x->wait, &wait); - do { - if (signal_pending(current)) { - ret = -ERESTARTSYS; - __remove_wait_queue(&x->wait, &wait); - goto out; - } - __set_current_state(TASK_INTERRUPTIBLE); - spin_unlock_irq(&x->wait.lock); - schedule(); - spin_lock_irq(&x->wait.lock); - } while (!x->done); - __remove_wait_queue(&x->wait, &wait); - } - x->done--; -out: + timeout = do_wait_for_common(x, timeout, state); spin_unlock_irq(&x->wait.lock); - - return ret; + return timeout; } -EXPORT_SYMBOL(wait_for_completion_interruptible); -unsigned long fastcall __sched -wait_for_completion_interruptible_timeout(struct completion *x, - unsigned long timeout) +void __sched wait_for_completion(struct completion *x) { - might_sleep(); - - spin_lock_irq(&x->wait.lock); - if (!x->done) { - DECLARE_WAITQUEUE(wait, current); + wait_for_common(x, MAX_SCHEDULE_TIMEOUT, TASK_UNINTERRUPTIBLE); +} +EXPORT_SYMBOL(wait_for_completion); - wait.flags |= WQ_FLAG_EXCLUSIVE; - __add_wait_queue_tail(&x->wait, &wait); - do { - if (signal_pending(current)) { - timeout = -ERESTARTSYS; - __remove_wait_queue(&x->wait, &wait); - goto out; - } - __set_current_state(TASK_INTERRUPTIBLE); - spin_unlock_irq(&x->wait.lock); - timeout = schedule_timeout(timeout); - spin_lock_irq(&x->wait.lock); - if (!timeout) { - __remove_wait_queue(&x->wait, &wait); - goto out; - } - } while (!x->done); - __remove_wait_queue(&x->wait, &wait); - } - x->done--; -out: - spin_unlock_irq(&x->wait.lock); - return timeout; +unsigned long __sched +wait_for_completion_timeout(struct completion *x, unsigned long timeout) +{ + return wait_for_common(x, timeout, TASK_UNINTERRUPTIBLE); } -EXPORT_SYMBOL(wait_for_completion_interruptible_timeout); +EXPORT_SYMBOL(wait_for_completion_timeout); -static inline void -sleep_on_head(wait_queue_head_t *q, wait_queue_t *wait, unsigned long *flags) +int __sched wait_for_completion_interruptible(struct completion *x) { - spin_lock_irqsave(&q->lock, *flags); - __add_wait_queue(q, wait); - spin_unlock(&q->lock); + long t = wait_for_common(x, MAX_SCHEDULE_TIMEOUT, TASK_INTERRUPTIBLE); + if (t == -ERESTARTSYS) + return t; + return 0; } +EXPORT_SYMBOL(wait_for_completion_interruptible); -static inline void -sleep_on_tail(wait_queue_head_t *q, wait_queue_t *wait, unsigned long *flags) +unsigned long __sched +wait_for_completion_interruptible_timeout(struct completion *x, + unsigned long timeout) { - spin_lock_irq(&q->lock); - __remove_wait_queue(q, wait); - spin_unlock_irqrestore(&q->lock, *flags); + return wait_for_common(x, timeout, TASK_INTERRUPTIBLE); } +EXPORT_SYMBOL(wait_for_completion_interruptible_timeout); -void __sched interruptible_sleep_on(wait_queue_head_t *q) +static long __sched +sleep_on_common(wait_queue_head_t *q, int state, long timeout) { unsigned long flags; wait_queue_t wait; init_waitqueue_entry(&wait, current); - current->state = TASK_INTERRUPTIBLE; + __set_current_state(state); - sleep_on_head(q, &wait, &flags); - schedule(); - sleep_on_tail(q, &wait, &flags); + spin_lock_irqsave(&q->lock, flags); + __add_wait_queue(q, &wait); + spin_unlock(&q->lock); + timeout = schedule_timeout(timeout); + spin_lock_irq(&q->lock); + __remove_wait_queue(q, &wait); + spin_unlock_irqrestore(&q->lock, flags); + + return timeout; +} + +void __sched interruptible_sleep_on(wait_queue_head_t *q) +{ + sleep_on_common(q, TASK_INTERRUPTIBLE, MAX_SCHEDULE_TIMEOUT); } EXPORT_SYMBOL(interruptible_sleep_on); long __sched interruptible_sleep_on_timeout(wait_queue_head_t *q, long timeout) { - unsigned long flags; - wait_queue_t wait; - - init_waitqueue_entry(&wait, current); - - current->state = TASK_INTERRUPTIBLE; - - sleep_on_head(q, &wait, &flags); - timeout = schedule_timeout(timeout); - sleep_on_tail(q, &wait, &flags); - - return timeout; + return sleep_on_common(q, TASK_INTERRUPTIBLE, timeout); } EXPORT_SYMBOL(interruptible_sleep_on_timeout); void __sched sleep_on(wait_queue_head_t *q) { - unsigned long flags; - wait_queue_t wait; - - init_waitqueue_entry(&wait, current); - - current->state = TASK_UNINTERRUPTIBLE; - - sleep_on_head(q, &wait, &flags); - schedule(); - sleep_on_tail(q, &wait, &flags); + sleep_on_common(q, TASK_UNINTERRUPTIBLE, MAX_SCHEDULE_TIMEOUT); } EXPORT_SYMBOL(sleep_on); long __sched sleep_on_timeout(wait_queue_head_t *q, long timeout) { - unsigned long flags; - wait_queue_t wait; - - init_waitqueue_entry(&wait, current); - - current->state = TASK_UNINTERRUPTIBLE; - - sleep_on_head(q, &wait, &flags); - timeout = schedule_timeout(timeout); - sleep_on_tail(q, &wait, &flags); - - return timeout; + return sleep_on_common(q, TASK_UNINTERRUPTIBLE, timeout); } EXPORT_SYMBOL(sleep_on_timeout); @@ -3946,7 +4045,7 @@ EXPORT_SYMBOL(sleep_on_timeout); void rt_mutex_setprio(struct task_struct *p, int prio) { unsigned long flags; - int oldprio, on_rq; + int oldprio, on_rq, running; struct rq *rq; BUG_ON(prio < 0 || prio > MAX_PRIO); @@ -3956,8 +4055,12 @@ void rt_mutex_setprio(struct task_struct oldprio = p->prio; on_rq = p->se.on_rq; - if (on_rq) + running = task_running(rq, p); + if (on_rq) { dequeue_task(rq, p, 0); + if (running) + p->sched_class->put_prev_task(rq, p); + } if (rt_prio(prio)) p->sched_class = &rt_sched_class; @@ -3967,13 +4070,15 @@ void rt_mutex_setprio(struct task_struct p->prio = prio; if (on_rq) { + if (running) + p->sched_class->set_curr_task(rq); enqueue_task(rq, p, 0); /* * Reschedule if we are currently running on this runqueue and * our priority decreased, or if we are not currently running on * this runqueue and our priority is higher than the current's */ - if (task_running(rq, p)) { + if (running) { if (p->prio > oldprio) resched_task(rq->curr); } else { @@ -4010,10 +4115,8 @@ void set_user_nice(struct task_struct *p goto out_unlock; } on_rq = p->se.on_rq; - if (on_rq) { + if (on_rq) dequeue_task(rq, p, 0); - dec_load(rq, p); - } p->static_prio = NICE_TO_PRIO(nice); set_load_weight(p); @@ -4023,7 +4126,6 @@ void set_user_nice(struct task_struct *p if (on_rq) { enqueue_task(rq, p, 0); - inc_load(rq, p); /* * If the task increased its priority or is running and * lowered its priority, then reschedule its CPU: @@ -4137,9 +4239,9 @@ struct task_struct *idle_task(int cpu) * find_process_by_pid - find a process with a matching PID value. * @pid: the pid in question. */ -static inline struct task_struct *find_process_by_pid(pid_t pid) +static struct task_struct *find_process_by_pid(pid_t pid) { - return pid ? find_task_by_pid(pid) : current; + return pid ? find_task_by_vpid(pid) : current; } /* Actually do priority change: must hold rq lock. */ @@ -4179,7 +4281,7 @@ __setscheduler(struct rq *rq, struct tas int sched_setscheduler(struct task_struct *p, int policy, struct sched_param *param) { - int retval, oldprio, oldpolicy = -1, on_rq; + int retval, oldprio, oldpolicy = -1, on_rq, running; unsigned long flags; struct rq *rq; @@ -4261,18 +4363,26 @@ recheck: } update_rq_clock(rq); on_rq = p->se.on_rq; - if (on_rq) + running = task_running(rq, p); + if (on_rq) { deactivate_task(rq, p, 0); + if (running) + p->sched_class->put_prev_task(rq, p); + } + oldprio = p->prio; __setscheduler(rq, p, policy, param->sched_priority); + if (on_rq) { + if (running) + p->sched_class->set_curr_task(rq); activate_task(rq, p, 0); /* * Reschedule if we are currently running on this runqueue and * our priority decreased, or if we are not currently running on * this runqueue and our priority is higher than the current's */ - if (task_running(rq, p)) { + if (running) { if (p->prio > oldprio) resched_task(rq->curr); } else { @@ -4343,10 +4453,10 @@ asmlinkage long sys_sched_setparam(pid_t asmlinkage long sys_sched_getscheduler(pid_t pid) { struct task_struct *p; - int retval = -EINVAL; + int retval; if (pid < 0) - goto out_nounlock; + return -EINVAL; retval = -ESRCH; read_lock(&tasklist_lock); @@ -4357,8 +4467,6 @@ asmlinkage long sys_sched_getscheduler(p retval = p->policy; } read_unlock(&tasklist_lock); - -out_nounlock: return retval; } @@ -4371,10 +4479,10 @@ asmlinkage long sys_sched_getparam(pid_t { struct sched_param lp; struct task_struct *p; - int retval = -EINVAL; + int retval; if (!param || pid < 0) - goto out_nounlock; + return -EINVAL; read_lock(&tasklist_lock); p = find_process_by_pid(pid); @@ -4394,7 +4502,6 @@ asmlinkage long sys_sched_getparam(pid_t */ retval = copy_to_user(param, &lp, sizeof(*param)) ? -EFAULT : 0; -out_nounlock: return retval; out_unlock: @@ -4437,8 +4544,21 @@ long sched_setaffinity(pid_t pid, cpumas cpus_allowed = cpuset_cpus_allowed(p); cpus_and(new_mask, new_mask, cpus_allowed); + again: retval = set_cpus_allowed(p, new_mask); + if (!retval) { + cpus_allowed = cpuset_cpus_allowed(p); + if (!cpus_subset(new_mask, cpus_allowed)) { + /* + * We must have raced with a concurrent cpuset + * update. Just reset the cpus_allowed to the + * cpuset's cpus_allowed + */ + new_mask = cpus_allowed; + goto again; + } + } out_unlock: put_task_struct(p); mutex_unlock(&sched_hotcpu_mutex); @@ -4554,8 +4674,8 @@ asmlinkage long sys_sched_yield(void) { struct rq *rq = this_rq_lock(); - schedstat_inc(rq, yld_cnt); - current->sched_class->yield_task(rq, current); + schedstat_inc(rq, yld_count); + current->sched_class->yield_task(rq); /* * Since we are going to call schedule() anyway, there's @@ -4749,11 +4869,12 @@ asmlinkage long sys_sched_rr_get_interval(pid_t pid, struct timespec __user *interval) { struct task_struct *p; - int retval = -EINVAL; + unsigned int time_slice; + int retval; struct timespec t; if (pid < 0) - goto out_nounlock; + return -EINVAL; retval = -ESRCH; read_lock(&tasklist_lock); @@ -4765,12 +4886,24 @@ long sys_sched_rr_get_interval(pid_t pid if (retval) goto out_unlock; - jiffies_to_timespec(p->policy == SCHED_FIFO ? - 0 : static_prio_timeslice(p->static_prio), &t); + if (p->policy == SCHED_FIFO) + time_slice = 0; + else if (p->policy == SCHED_RR) + time_slice = DEF_TIMESLICE; + else { + struct sched_entity *se = &p->se; + unsigned long flags; + struct rq *rq; + + rq = task_rq_lock(p, &flags); + time_slice = NS_TO_JIFFIES(sched_slice(cfs_rq_of(se), se)); + task_rq_unlock(rq, &flags); + } read_unlock(&tasklist_lock); + jiffies_to_timespec(time_slice, &t); retval = copy_to_user(interval, &t, sizeof(t)) ? -EFAULT : 0; -out_nounlock: return retval; + out_unlock: read_unlock(&tasklist_lock); return retval; @@ -4784,18 +4917,18 @@ static void show_task(struct task_struct unsigned state; state = p->state ? __ffs(p->state) + 1 : 0; - printk("%-13.13s %c", p->comm, + printk(KERN_INFO "%-13.13s %c", p->comm, state < sizeof(stat_nam) - 1 ? stat_nam[state] : '?'); #if BITS_PER_LONG == 32 if (state == TASK_RUNNING) - printk(" running "); + printk(KERN_CONT " running "); else - printk(" %08lx ", thread_saved_pc(p)); + printk(KERN_CONT " %08lx ", thread_saved_pc(p)); #else if (state == TASK_RUNNING) - printk(" running task "); + printk(KERN_CONT " running task "); else - printk(" %016lx ", thread_saved_pc(p)); + printk(KERN_CONT " %016lx ", thread_saved_pc(p)); #endif #ifdef CONFIG_DEBUG_STACK_USAGE { @@ -4805,7 +4938,8 @@ static void show_task(struct task_struct free = (unsigned long)n - (unsigned long)end_of_stack(p); } #endif - printk("%5lu %5d %6d\n", free, p->pid, p->parent->pid); + printk(KERN_CONT "%5lu %5d %6d\n", free, + task_pid_nr(p), task_pid_nr(p->parent)); if (state != TASK_RUNNING) show_stack(p, NULL); @@ -4911,7 +5045,7 @@ cpumask_t nohz_cpu_mask = CPU_MASK_NONE; static inline void sched_init_granularity(void) { unsigned int factor = 1 + ilog2(num_online_cpus()); - const unsigned long limit = 100000000; + const unsigned long limit = 200000000; sysctl_sched_min_granularity *= factor; if (sysctl_sched_min_granularity > limit) @@ -4921,8 +5055,8 @@ static inline void sched_init_granularit if (sysctl_sched_latency > limit) sysctl_sched_latency = limit; - sysctl_sched_runtime_limit = sysctl_sched_latency; - sysctl_sched_wakeup_granularity = sysctl_sched_min_granularity / 2; + sysctl_sched_wakeup_granularity *= factor; + sysctl_sched_batch_wakeup_granularity *= factor; } #ifdef CONFIG_SMP @@ -5047,6 +5181,8 @@ static int migration_thread(void *data) struct migration_req *req; struct list_head *head; + try_to_freeze(); + spin_lock_irq(&rq->lock); if (cpu_is_offline(cpu)) { @@ -5091,8 +5227,19 @@ wait_to_die: } #ifdef CONFIG_HOTPLUG_CPU + +static int __migrate_task_irq(struct task_struct *p, int src_cpu, int dest_cpu) +{ + int ret; + + local_irq_disable(); + ret = __migrate_task(p, src_cpu, dest_cpu); + local_irq_enable(); + return ret; +} + /* - * Figure out where task on dead CPU should go, use force if neccessary. + * Figure out where task on dead CPU should go, use force if necessary. * NOTE: interrupts should be disabled by the caller */ static void move_task_off_dead_cpu(int dead_cpu, struct task_struct *p) @@ -5102,35 +5249,42 @@ static void move_task_off_dead_cpu(int d struct rq *rq; int dest_cpu; -restart: - /* On same node? */ - mask = node_to_cpumask(cpu_to_node(dead_cpu)); - cpus_and(mask, mask, p->cpus_allowed); - dest_cpu = any_online_cpu(mask); - - /* On any allowed CPU? */ - if (dest_cpu == NR_CPUS) - dest_cpu = any_online_cpu(p->cpus_allowed); - - /* No more Mr. Nice Guy. */ - if (dest_cpu == NR_CPUS) { - rq = task_rq_lock(p, &flags); - cpus_setall(p->cpus_allowed); - dest_cpu = any_online_cpu(p->cpus_allowed); - task_rq_unlock(rq, &flags); + do { + /* On same node? */ + mask = node_to_cpumask(cpu_to_node(dead_cpu)); + cpus_and(mask, mask, p->cpus_allowed); + dest_cpu = any_online_cpu(mask); + + /* On any allowed CPU? */ + if (dest_cpu == NR_CPUS) + dest_cpu = any_online_cpu(p->cpus_allowed); + + /* No more Mr. Nice Guy. */ + if (dest_cpu == NR_CPUS) { + cpumask_t cpus_allowed = cpuset_cpus_allowed_locked(p); + /* + * Try to stay on the same cpuset, where the + * current cpuset may be a subset of all cpus. + * The cpuset_cpus_allowed_locked() variant of + * cpuset_cpus_allowed() will not block. It must be + * called within calls to cpuset_lock/cpuset_unlock. + */ + rq = task_rq_lock(p, &flags); + p->cpus_allowed = cpus_allowed; + dest_cpu = any_online_cpu(p->cpus_allowed); + task_rq_unlock(rq, &flags); - /* - * Don't tell them about moving exiting tasks or - * kernel threads (both mm NULL), since they never - * leave kernel. - */ - if (p->mm && printk_ratelimit()) - printk(KERN_INFO "process %d (%s) no " - "longer affine to cpu%d\n", - p->pid, p->comm, dead_cpu); - } - if (!__migrate_task(p, dead_cpu, dest_cpu)) - goto restart; + /* + * Don't tell them about moving exiting tasks or + * kernel threads (both mm NULL), since they never + * leave kernel. + */ + if (p->mm && printk_ratelimit()) + printk(KERN_INFO "process %d (%s) no " + "longer affine to cpu%d\n", + task_pid_nr(p), p->comm, dead_cpu); + } + } while (!__migrate_task_irq(p, dead_cpu, dest_cpu)); } /* @@ -5158,7 +5312,7 @@ static void migrate_live_tasks(int src_c { struct task_struct *p, *t; - write_lock_irq(&tasklist_lock); + read_lock(&tasklist_lock); do_each_thread(t, p) { if (p == current) @@ -5168,13 +5322,13 @@ static void migrate_live_tasks(int src_c move_task_off_dead_cpu(src_cpu, p); } while_each_thread(t, p); - write_unlock_irq(&tasklist_lock); + read_unlock(&tasklist_lock); } /* * Schedules idle task to be the next runnable task on current CPU. - * It does so by boosting its priority to highest possible and adding it to - * the _front_ of the runqueue. Used by CPU offline code. + * It does so by boosting its priority to highest possible. + * Used by CPU offline code. */ void sched_idle_next(void) { @@ -5194,8 +5348,8 @@ void sched_idle_next(void) __setscheduler(rq, p, SCHED_FIFO, MAX_RT_PRIO-1); - /* Add idle task to the _front_ of its priority queue: */ - activate_idle_task(p, rq); + update_rq_clock(rq); + activate_task(rq, p, 0); spin_unlock_irqrestore(&rq->lock, flags); } @@ -5221,7 +5375,7 @@ static void migrate_dead(unsigned int de struct rq *rq = cpu_rq(dead_cpu); /* Must be exiting, otherwise would be on tasklist. */ - BUG_ON(p->exit_state != EXIT_ZOMBIE && p->exit_state != EXIT_DEAD); + BUG_ON(!p->exit_state); /* Cannot have done final schedule yet: would have vanished. */ BUG_ON(p->state == TASK_DEAD); @@ -5232,11 +5386,10 @@ static void migrate_dead(unsigned int de * Drop lock around migration; if someone else moves it, * that's OK. No task can be added to this CPU, so iteration is * fine. - * NOTE: interrupts should be left disabled --dev@ */ - spin_unlock(&rq->lock); + spin_unlock_irq(&rq->lock); move_task_off_dead_cpu(dead_cpu, p); - spin_lock(&rq->lock); + spin_lock_irq(&rq->lock); put_task_struct(p); } @@ -5267,7 +5420,7 @@ static struct ctl_table sd_ctl_dir[] = { .procname = "sched_domain", .mode = 0555, }, - {0,}, + {0, }, }; static struct ctl_table sd_ctl_root[] = { @@ -5277,20 +5430,38 @@ static struct ctl_table sd_ctl_root[] = .mode = 0555, .child = sd_ctl_dir, }, - {0,}, + {0, }, }; static struct ctl_table *sd_alloc_ctl_entry(int n) { struct ctl_table *entry = - kmalloc(n * sizeof(struct ctl_table), GFP_KERNEL); - - BUG_ON(!entry); - memset(entry, 0, n * sizeof(struct ctl_table)); + kcalloc(n, sizeof(struct ctl_table), GFP_KERNEL); return entry; } +static void sd_free_ctl_entry(struct ctl_table **tablep) +{ + struct ctl_table *entry; + + /* + * In the intermediate directories, both the child directory and + * procname are dynamically allocated and could fail but the mode + * will always be set. In the lowest directory the names are + * static strings and all have proc handlers. + */ + for (entry = *tablep; entry->mode; entry++) { + if (entry->child) + sd_free_ctl_entry(&entry->child); + if (entry->proc_handler == NULL) + kfree(entry->procname); + } + + kfree(*tablep); + *tablep = NULL; +} + static void set_table_entry(struct ctl_table *entry, const char *procname, void *data, int maxlen, @@ -5306,7 +5477,10 @@ set_table_entry(struct ctl_table *entry, static struct ctl_table * sd_alloc_ctl_domain_table(struct sched_domain *sd) { - struct ctl_table *table = sd_alloc_ctl_entry(14); + struct ctl_table *table = sd_alloc_ctl_entry(12); + + if (table == NULL) + return NULL; set_table_entry(&table[0], "min_interval", &sd->min_interval, sizeof(long), 0644, proc_doulongvec_minmax); @@ -5326,16 +5500,17 @@ sd_alloc_ctl_domain_table(struct sched_d sizeof(int), 0644, proc_dointvec_minmax); set_table_entry(&table[8], "imbalance_pct", &sd->imbalance_pct, sizeof(int), 0644, proc_dointvec_minmax); - set_table_entry(&table[10], "cache_nice_tries", + set_table_entry(&table[9], "cache_nice_tries", &sd->cache_nice_tries, sizeof(int), 0644, proc_dointvec_minmax); - set_table_entry(&table[12], "flags", &sd->flags, + set_table_entry(&table[10], "flags", &sd->flags, sizeof(int), 0644, proc_dointvec_minmax); + /* &table[11] is terminator */ return table; } -static ctl_table *sd_alloc_ctl_cpu_table(int cpu) +static ctl_table * sd_alloc_ctl_cpu_table(int cpu) { struct ctl_table *entry, *table; struct sched_domain *sd; @@ -5345,6 +5520,8 @@ static ctl_table *sd_alloc_ctl_cpu_table for_each_domain(cpu, sd) domain_num++; entry = table = sd_alloc_ctl_entry(domain_num + 1); + if (table == NULL) + return NULL; i = 0; for_each_domain(cpu, sd) { @@ -5359,24 +5536,44 @@ static ctl_table *sd_alloc_ctl_cpu_table } static struct ctl_table_header *sd_sysctl_header; -static void init_sched_domain_sysctl(void) +static void register_sched_domain_sysctl(void) { int i, cpu_num = num_online_cpus(); struct ctl_table *entry = sd_alloc_ctl_entry(cpu_num + 1); char buf[32]; + WARN_ON(sd_ctl_dir[0].child); sd_ctl_dir[0].child = entry; - for (i = 0; i < cpu_num; i++, entry++) { + if (entry == NULL) + return; + + for_each_online_cpu(i) { snprintf(buf, 32, "cpu%d", i); entry->procname = kstrdup(buf, GFP_KERNEL); entry->mode = 0555; entry->child = sd_alloc_ctl_cpu_table(i); + entry++; } + + WARN_ON(sd_sysctl_header); sd_sysctl_header = register_sysctl_table(sd_ctl_root); } + +/* may be called multiple times per register */ +static void unregister_sched_domain_sysctl(void) +{ + if (sd_sysctl_header) + unregister_sysctl_table(sd_sysctl_header); + sd_sysctl_header = NULL; + if (sd_ctl_dir[0].child) + sd_free_ctl_entry(&sd_ctl_dir[0].child); +} #else -static void init_sched_domain_sysctl(void) +static void register_sched_domain_sysctl(void) +{ +} +static void unregister_sched_domain_sysctl(void) { } #endif @@ -5403,6 +5600,7 @@ migration_call(struct notifier_block *nf p = kthread_create(migration_thread, hcpu, "migration/%d", cpu); if (IS_ERR(p)) return NOTIFY_BAD; + p->flags |= PF_NOFREEZE; kthread_bind(p, cpu); /* Must be high prio: stop_machine expects to yield to it. */ rq = task_rq_lock(p, &flags); @@ -5413,7 +5611,7 @@ migration_call(struct notifier_block *nf case CPU_ONLINE: case CPU_ONLINE_FROZEN: - /* Strictly unneccessary, as first user will wake it. */ + /* Strictly unnecessary, as first user will wake it. */ wake_up_process(cpu_rq(cpu)->migration_thread); break; @@ -5431,19 +5629,21 @@ migration_call(struct notifier_block *nf case CPU_DEAD: case CPU_DEAD_FROZEN: + cpuset_lock(); /* around calls to cpuset_cpus_allowed_lock() */ migrate_live_tasks(cpu); rq = cpu_rq(cpu); kthread_stop(rq->migration_thread); rq->migration_thread = NULL; /* Idle task back to normal (off runqueue, low prio) */ - rq = task_rq_lock(rq->idle, &flags); + spin_lock_irq(&rq->lock); update_rq_clock(rq); deactivate_task(rq, rq->idle, 0); rq->idle->static_prio = MAX_PRIO; __setscheduler(rq, rq->idle, SCHED_NORMAL, 0); rq->idle->sched_class = &idle_sched_class; migrate_dead_tasks(cpu); - task_rq_unlock(rq, &flags); + spin_unlock_irq(&rq->lock); + cpuset_unlock(); migrate_nr_uninterruptible(rq); BUG_ON(rq->nr_running != 0); @@ -5477,7 +5677,7 @@ static struct notifier_block __cpuinitda .priority = 10 }; -int __init migration_init(void) +void __init migration_init(void) { void *cpu = (void *)(long)smp_processor_id(); int err; @@ -5487,8 +5687,6 @@ int __init migration_init(void) BUG_ON(err == NOTIFY_BAD); migration_call(&migration_notifier, CPU_ONLINE, cpu); register_cpu_notifier(&migration_notifier); - - return 0; } #endif @@ -5498,100 +5696,102 @@ int __init migration_init(void) int nr_cpu_ids __read_mostly = NR_CPUS; EXPORT_SYMBOL(nr_cpu_ids); -#undef SCHED_DOMAIN_DEBUG -#ifdef SCHED_DOMAIN_DEBUG -static void sched_domain_debug(struct sched_domain *sd, int cpu) -{ - int level = 0; +#ifdef CONFIG_SCHED_DEBUG - if (!sd) { - printk(KERN_DEBUG "CPU%d attaching NULL sched-domain.\n", cpu); - return; +static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level) +{ + struct sched_group *group = sd->groups; + cpumask_t groupmask; + char str[NR_CPUS]; + + cpumask_scnprintf(str, NR_CPUS, sd->span); + cpus_clear(groupmask); + + printk(KERN_DEBUG "%*s domain %d: ", level, "", level); + + if (!(sd->flags & SD_LOAD_BALANCE)) { + printk("does not load-balance\n"); + if (sd->parent) + printk(KERN_ERR "ERROR: !SD_LOAD_BALANCE domain" + " has parent"); + return -1; } - printk(KERN_DEBUG "CPU%d attaching sched-domain:\n", cpu); + printk(KERN_CONT "span %s\n", str); + if (!cpu_isset(cpu, sd->span)) { + printk(KERN_ERR "ERROR: domain->span does not contain " + "CPU%d\n", cpu); + } + if (!cpu_isset(cpu, group->cpumask)) { + printk(KERN_ERR "ERROR: domain->groups does not contain" + " CPU%d\n", cpu); + } + + printk(KERN_DEBUG "%*s groups:", level + 1, ""); do { - int i; - char str[NR_CPUS]; - struct sched_group *group = sd->groups; - cpumask_t groupmask; - - cpumask_scnprintf(str, NR_CPUS, sd->span); - cpus_clear(groupmask); - - printk(KERN_DEBUG); - for (i = 0; i < level + 1; i++) - printk(" "); - printk("domain %d: ", level); - - if (!(sd->flags & SD_LOAD_BALANCE)) { - printk("does not load-balance\n"); - if (sd->parent) - printk(KERN_ERR "ERROR: !SD_LOAD_BALANCE domain" - " has parent"); + if (!group) { + printk("\n"); + printk(KERN_ERR "ERROR: group is NULL\n"); break; } - printk("span %s\n", str); + if (!group->__cpu_power) { + printk(KERN_CONT "\n"); + printk(KERN_ERR "ERROR: domain->cpu_power not " + "set\n"); + break; + } - if (!cpu_isset(cpu, sd->span)) - printk(KERN_ERR "ERROR: domain->span does not contain " - "CPU%d\n", cpu); - if (!cpu_isset(cpu, group->cpumask)) - printk(KERN_ERR "ERROR: domain->groups does not contain" - " CPU%d\n", cpu); - - printk(KERN_DEBUG); - for (i = 0; i < level + 2; i++) - printk(" "); - printk("groups:"); - do { - if (!group) { - printk("\n"); - printk(KERN_ERR "ERROR: group is NULL\n"); - break; - } + if (!cpus_weight(group->cpumask)) { + printk(KERN_CONT "\n"); + printk(KERN_ERR "ERROR: empty group\n"); + break; + } - if (!group->__cpu_power) { - printk("\n"); - printk(KERN_ERR "ERROR: domain->cpu_power not " - "set\n"); - } + if (cpus_intersects(groupmask, group->cpumask)) { + printk(KERN_CONT "\n"); + printk(KERN_ERR "ERROR: repeated CPUs\n"); + break; + } - if (!cpus_weight(group->cpumask)) { - printk("\n"); - printk(KERN_ERR "ERROR: empty group\n"); - } + cpus_or(groupmask, groupmask, group->cpumask); - if (cpus_intersects(groupmask, group->cpumask)) { - printk("\n"); - printk(KERN_ERR "ERROR: repeated CPUs\n"); - } + cpumask_scnprintf(str, NR_CPUS, group->cpumask); + printk(KERN_CONT " %s", str); + + group = group->next; + } while (group != sd->groups); + printk(KERN_CONT "\n"); - cpus_or(groupmask, groupmask, group->cpumask); + if (!cpus_equal(sd->span, groupmask)) + printk(KERN_ERR "ERROR: groups don't span domain->span\n"); - cpumask_scnprintf(str, NR_CPUS, group->cpumask); - printk(" %s", str); + if (sd->parent && !cpus_subset(groupmask, sd->parent->span)) + printk(KERN_ERR "ERROR: parent span is not a superset " + "of domain->span\n"); + return 0; +} - group = group->next; - } while (group != sd->groups); - printk("\n"); - - if (!cpus_equal(sd->span, groupmask)) - printk(KERN_ERR "ERROR: groups don't span " - "domain->span\n"); +static void sched_domain_debug(struct sched_domain *sd, int cpu) +{ + int level = 0; + if (!sd) { + printk(KERN_DEBUG "CPU%d attaching NULL sched-domain.\n", cpu); + return; + } + + printk(KERN_DEBUG "CPU%d attaching sched-domain:\n", cpu); + + for (;;) { + if (sched_domain_debug_one(sd, cpu, level)) + break; level++; sd = sd->parent; if (!sd) - continue; - - if (!cpus_subset(groupmask, sd->span)) - printk(KERN_ERR "ERROR: parent span is not a superset " - "of domain->span\n"); - - } while (sd); + break; + } } #else # define sched_domain_debug(sd, cpu) do { } while (0) @@ -5700,7 +5900,7 @@ static int __init isolated_cpu_setup(cha return 1; } -__setup ("isolcpus=", isolated_cpu_setup); +__setup("isolcpus=", isolated_cpu_setup); /* * init_sched_build_groups takes the cpumask we wish to span, and a pointer @@ -5856,7 +6056,7 @@ static int cpu_to_core_group(int cpu, co struct sched_group **sg) { int group; - cpumask_t mask = cpu_sibling_map[cpu]; + cpumask_t mask = cpu_sibling_map(cpu); cpus_and(mask, mask, *cpu_map); group = first_cpu(mask); if (sg) @@ -5885,7 +6085,7 @@ static int cpu_to_phys_group(int cpu, co cpus_and(mask, mask, *cpu_map); group = first_cpu(mask); #elif defined(CONFIG_SCHED_SMT) - cpumask_t mask = cpu_sibling_map[cpu]; + cpumask_t mask = cpu_sibling_map(cpu); cpus_and(mask, mask, *cpu_map); group = first_cpu(mask); #else @@ -5929,24 +6129,23 @@ static void init_numa_sched_groups_power if (!sg) return; -next_sg: - for_each_cpu_mask(j, sg->cpumask) { - struct sched_domain *sd; + do { + for_each_cpu_mask(j, sg->cpumask) { + struct sched_domain *sd; - sd = &per_cpu(phys_domains, j); - if (j != first_cpu(sd->groups->cpumask)) { - /* - * Only add "power" once for each - * physical package. - */ - continue; - } + sd = &per_cpu(phys_domains, j); + if (j != first_cpu(sd->groups->cpumask)) { + /* + * Only add "power" once for each + * physical package. + */ + continue; + } - sg_inc_cpu_power(sg, sd->groups->__cpu_power); - } - sg = sg->next; - if (sg != group_head) - goto next_sg; + sg_inc_cpu_power(sg, sd->groups->__cpu_power); + } + sg = sg->next; + } while (sg != group_head); } #endif @@ -6057,7 +6256,7 @@ static int build_sched_domains(const cpu /* * Allocate the per-node list of sched groups */ - sched_group_nodes = kzalloc(sizeof(struct sched_group *)*MAX_NUMNODES, + sched_group_nodes = kcalloc(MAX_NUMNODES, sizeof(struct sched_group *), GFP_KERNEL); if (!sched_group_nodes) { printk(KERN_WARNING "Can not alloc sched group node list\n"); @@ -6120,7 +6319,7 @@ static int build_sched_domains(const cpu p = sd; sd = &per_cpu(cpu_domains, i); *sd = SD_SIBLING_INIT; - sd->span = cpu_sibling_map[i]; + sd->span = cpu_sibling_map(i); cpus_and(sd->span, sd->span, *cpu_map); sd->parent = p; p->child = sd; @@ -6131,7 +6330,7 @@ static int build_sched_domains(const cpu #ifdef CONFIG_SCHED_SMT /* Set up CPU (sibling) groups */ for_each_cpu_mask(i, *cpu_map) { - cpumask_t this_sibling_map = cpu_sibling_map[i]; + cpumask_t this_sibling_map = cpu_sibling_map(i); cpus_and(this_sibling_map, this_sibling_map, *cpu_map); if (i != first_cpu(this_sibling_map)) continue; @@ -6293,22 +6492,33 @@ error: return -ENOMEM; #endif } + +static cpumask_t *doms_cur; /* current sched domains */ +static int ndoms_cur; /* number of sched domains in 'doms_cur' */ + +/* + * Special case: If a kmalloc of a doms_cur partition (array of + * cpumask_t) fails, then fallback to a single sched domain, + * as determined by the single cpumask_t fallback_doms. + */ +static cpumask_t fallback_doms; + /* * Set up scheduler domains and groups. Callers must hold the hotplug lock. + * For now this just excludes isolated cpus, but could be used to + * exclude other special cases in the future. */ static int arch_init_sched_domains(const cpumask_t *cpu_map) { - cpumask_t cpu_default_map; int err; - /* - * Setup mask for cpus without special case scheduling requirements. - * For now this just excludes isolated cpus, but could be used to - * exclude other special cases in the future. - */ - cpus_andnot(cpu_default_map, *cpu_map, cpu_isolated_map); - - err = build_sched_domains(&cpu_default_map); + ndoms_cur = 1; + doms_cur = kmalloc(sizeof(cpumask_t), GFP_KERNEL); + if (!doms_cur) + doms_cur = &fallback_doms; + cpus_andnot(*doms_cur, *cpu_map, cpu_isolated_map); + err = build_sched_domains(doms_cur); + register_sched_domain_sysctl(); return err; } @@ -6326,6 +6536,8 @@ static void detach_destroy_domains(const { int i; + unregister_sched_domain_sysctl(); + for_each_cpu_mask(i, *cpu_map) cpu_attach_domain(NULL, i); synchronize_sched(); @@ -6333,30 +6545,74 @@ static void detach_destroy_domains(const } /* - * Partition sched domains as specified by the cpumasks below. - * This attaches all cpus from the cpumasks to the NULL domain, - * waits for a RCU quiescent period, recalculates sched - * domain information and then attaches them back to the - * correct sched domains + * Partition sched domains as specified by the 'ndoms_new' + * cpumasks in the array doms_new[] of cpumasks. This compares + * doms_new[] to the current sched domain partitioning, doms_cur[]. + * It destroys each deleted domain and builds each new domain. + * + * 'doms_new' is an array of cpumask_t's of length 'ndoms_new'. + * The masks don't intersect (don't overlap.) We should setup one + * sched domain for each mask. CPUs not in any of the cpumasks will + * not be load balanced. If the same cpumask appears both in the + * current 'doms_cur' domains and in the new 'doms_new', we can leave + * it as it is. + * + * The passed in 'doms_new' should be kmalloc'd. This routine takes + * ownership of it and will kfree it when done with it. If the caller + * failed the kmalloc call, then it can pass in doms_new == NULL, + * and partition_sched_domains() will fallback to the single partition + * 'fallback_doms'. + * * Call with hotplug lock held */ -int partition_sched_domains(cpumask_t *partition1, cpumask_t *partition2) +void partition_sched_domains(int ndoms_new, cpumask_t *doms_new) { - cpumask_t change_map; - int err = 0; + int i, j; - cpus_and(*partition1, *partition1, cpu_online_map); - cpus_and(*partition2, *partition2, cpu_online_map); - cpus_or(change_map, *partition1, *partition2); - - /* Detach sched domains from all of the affected cpus */ - detach_destroy_domains(&change_map); - if (!cpus_empty(*partition1)) - err = build_sched_domains(partition1); - if (!err && !cpus_empty(*partition2)) - err = build_sched_domains(partition2); + lock_doms_cur(); - return err; + /* always unregister in case we don't destroy any domains */ + unregister_sched_domain_sysctl(); + + if (doms_new == NULL) { + ndoms_new = 1; + doms_new = &fallback_doms; + cpus_andnot(doms_new[0], cpu_online_map, cpu_isolated_map); + } + + /* Destroy deleted domains */ + for (i = 0; i < ndoms_cur; i++) { + for (j = 0; j < ndoms_new; j++) { + if (cpus_equal(doms_cur[i], doms_new[j])) + goto match1; + } + /* no match - a current sched domain not in new doms_new[] */ + detach_destroy_domains(doms_cur + i); +match1: + ; + } + + /* Build new domains */ + for (i = 0; i < ndoms_new; i++) { + for (j = 0; j < ndoms_cur; j++) { + if (cpus_equal(doms_new[i], doms_cur[j])) + goto match2; + } + /* no match - add a new doms_new */ + build_sched_domains(doms_new + i); +match2: + ; + } + + /* Remember the new sched domains */ + if (doms_cur != &fallback_doms) + kfree(doms_cur); + doms_cur = doms_new; + ndoms_cur = ndoms_new; + + register_sched_domain_sysctl(); + + unlock_doms_cur(); } #if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT) @@ -6487,12 +6743,22 @@ void __init sched_init_smp(void) /* XXX: Theoretical race here - CPU may be hotplugged now */ hotcpu_notifier(update_sched_domains, 0); - init_sched_domain_sysctl(); - /* Move init over to a non-isolated CPU */ if (set_cpus_allowed(current, non_isolated_cpus) < 0) BUG(); sched_init_granularity(); + +#if defined(CONFIG_FAIR_GROUP_SCHED) && defined(CONFIG_SMP) + lb_monitor_task = kthread_create(load_balance_monitor, NULL, + "load_balance_monitor"); + if (!IS_ERR(lb_monitor_task)) { + lb_monitor_task->flags |= PF_NOFREEZE; + wake_up_process(lb_monitor_task); + } else { + printk("Could not create load balance monitor thread" + "(error = %ld) \n", PTR_ERR(lb_monitor_task)); + } +#endif } #else void __init sched_init_smp(void) @@ -6511,28 +6777,20 @@ int in_sched_functions(unsigned long add && addr < (unsigned long)__sched_text_end); } -static inline void init_cfs_rq(struct cfs_rq *cfs_rq, struct rq *rq) +static void init_cfs_rq(struct cfs_rq *cfs_rq, struct rq *rq) { cfs_rq->tasks_timeline = RB_ROOT; - cfs_rq->fair_clock = 1; #ifdef CONFIG_FAIR_GROUP_SCHED cfs_rq->rq = rq; #endif + cfs_rq->min_vruntime = (u64)(-(1LL << 20)); } void __init sched_init(void) { - u64 now = sched_clock(); int highest_cpu = 0; int i, j; - /* - * Link up the scheduling class hierarchy: - */ - rt_sched_class.next = &fair_sched_class; - fair_sched_class.next = &idle_sched_class; - idle_sched_class.next = NULL; - for_each_possible_cpu(i) { struct rt_prio_array *array; struct rq *rq; @@ -6545,10 +6803,28 @@ void __init sched_init(void) init_cfs_rq(&rq->cfs, rq); #ifdef CONFIG_FAIR_GROUP_SCHED INIT_LIST_HEAD(&rq->leaf_cfs_rq_list); - list_add(&rq->cfs.leaf_cfs_rq_list, &rq->leaf_cfs_rq_list); + { + struct cfs_rq *cfs_rq = &per_cpu(init_cfs_rq, i); + struct sched_entity *se = + &per_cpu(init_sched_entity, i); + + init_cfs_rq_p[i] = cfs_rq; + init_cfs_rq(cfs_rq, rq); + cfs_rq->tg = &init_task_group; + list_add(&cfs_rq->leaf_cfs_rq_list, + &rq->leaf_cfs_rq_list); + + init_sched_entity_p[i] = se; + se->cfs_rq = &rq->cfs; + se->my_q = cfs_rq; + se->load.weight = init_task_group_load; + se->load.inv_weight = + div64_64(1ULL<<32, init_task_group_load); + se->parent = NULL; + } + init_task_group.shares = init_task_group_load; + mutex_init(&init_task_group.lock); #endif - rq->ls.load_update_last = now; - rq->ls.load_update_start = now; for (j = 0; j < CPU_LOAD_IDX_MAX; j++) rq->cpu_load[j] = 0; @@ -6633,26 +6909,40 @@ EXPORT_SYMBOL(__might_sleep); #endif #ifdef CONFIG_MAGIC_SYSRQ +static void normalize_task(struct rq *rq, struct task_struct *p) +{ + int on_rq; + update_rq_clock(rq); + on_rq = p->se.on_rq; + if (on_rq) + deactivate_task(rq, p, 0); + __setscheduler(rq, p, SCHED_NORMAL, 0); + if (on_rq) { + activate_task(rq, p, 0); + resched_task(rq->curr); + } +} + void normalize_rt_tasks(void) { struct task_struct *g, *p; unsigned long flags; struct rq *rq; - int on_rq; read_lock_irq(&tasklist_lock); do_each_thread(g, p) { - p->se.fair_key = 0; - p->se.wait_runtime = 0; + /* + * Only normalize user tasks: + */ + if (!p->mm) + continue; + p->se.exec_start = 0; - p->se.wait_start_fair = 0; - p->se.sleep_start_fair = 0; #ifdef CONFIG_SCHEDSTATS p->se.wait_start = 0; p->se.sleep_start = 0; p->se.block_start = 0; #endif - task_rq(p)->cfs.fair_clock = 0; task_rq(p)->clock = 0; if (!rt_task(p)) { @@ -6667,26 +6957,9 @@ void normalize_rt_tasks(void) spin_lock_irqsave(&p->pi_lock, flags); rq = __task_rq_lock(p); -#ifdef CONFIG_SMP - /* - * Do not touch the migration thread: - */ - if (p == rq->migration_thread) - goto out_unlock; -#endif - update_rq_clock(rq); - on_rq = p->se.on_rq; - if (on_rq) - deactivate_task(rq, p, 0); - __setscheduler(rq, p, SCHED_NORMAL, 0); - if (on_rq) { - activate_task(rq, p, 0); - resched_task(rq->curr); - } -#ifdef CONFIG_SMP - out_unlock: -#endif + normalize_task(rq, p); + __task_rq_unlock(rq); spin_unlock_irqrestore(&p->pi_lock, flags); } while_each_thread(g, p); @@ -6739,3 +7012,497 @@ void set_curr_task(int cpu, struct task_ } #endif + +#if defined(CONFIG_FAIR_GROUP_SCHED) && defined(CONFIG_SMP) + +/* distribute shares of all task groups among their schedulable entities, + * to reflect load distrbution across cpus. + */ +static int rebalance_shares(struct sched_domain *sd, int this_cpu) +{ + struct cfs_rq *cfs_rq; + struct rq *rq = cpu_rq(this_cpu); + cpumask_t sdspan = sd->span; + int balanced = 1; + + /* Walk thr' all the task groups that we have */ + for_each_leaf_cfs_rq(rq, cfs_rq) { + int i; + unsigned long total_load = 0, total_shares; + struct task_group *tg = cfs_rq->tg; + + /* Gather total task load of this group across cpus */ + for_each_cpu_mask(i, sdspan) + total_load += tg->cfs_rq[i]->load.weight; + + /* Nothing to do if this group has no load or if it's load + * hasn't changed since the last time we checked. + */ + if (!total_load || total_load == tg->last_total_load) + continue; + + tg->last_total_load = total_load; + + /* tg->shares represents the number of cpu shares the task group + * is eligible to hold on a single cpu. On N cpus, it is + * eligible to hold (N * tg->shares) number of cpu shares. + */ + total_shares = tg->shares * cpus_weight(sdspan); + + /* redistribute total_shares across cpus as per the task load + * distribution. + */ + for_each_cpu_mask(i, sdspan) { + unsigned long local_load, local_shares, irqflags; + + local_load = tg->cfs_rq[i]->load.weight; + local_shares = (local_load * total_shares) / total_load; + if (!local_shares) + local_shares = MIN_GROUP_SHARES; + if (local_shares == tg->se[i]->load.weight) + continue; + + spin_lock_irqsave(&cpu_rq(i)->lock, irqflags); + set_se_shares(tg->se[i], local_shares); + spin_unlock_irqrestore(&cpu_rq(i)->lock, irqflags); + balanced = 0; + } + } + + return balanced; +} + +/* + * How frequently should we rebalance_shares() across cpus? + * + * The more frequently we rebalance shares, the more accurate is the fairness + * of cpu bandwidth distribution between task groups. However higher frequency + * also implies increased scheduling overhead. + * + * sysctl_sched_min_bal_int_shares represents the minimum interval between + * consecutive calls to rebalance_shares() in the same sched domain. + * + * sysctl_sched_max_bal_int_shares represents the maximum interval between + * consecutive calls to rebalance_shares() in the same sched domain. + * + * These settings allows for the appropriate tradeoff between accuracy of + * fairness and the associated overhead. + * + */ + +/* default: 8ms, units: milliseconds */ +const_debug unsigned int sysctl_sched_min_bal_int_shares = 8; + +/* default: 128ms, units: milliseconds */ +const_debug unsigned int sysctl_sched_max_bal_int_shares = 128; + +static int load_balance_monitor(void *unused) +{ + unsigned int timeout = sysctl_sched_min_bal_int_shares; + + while (!kthread_should_stop()) { + int i, cpu, balanced = 1; + + lock_cpu_hotplug(); /* Prevent cpus going down or coming up */ + lock_doms_cur(); /* lockout changes to doms_cur[] array */ + + rcu_read_lock(); /* to walk rq->sd chain on various cpus */ + + for (i=0; i < ndoms_cur; i++) { + cpu