diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2017-02-20 12:52:55 -0800 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2017-02-20 12:52:55 -0800 |
commit | 828cad8ea05d194d8a9452e0793261c2024c23a2 (patch) | |
tree | 0ad7c7e044cdcfe75d78da0b52eb2358d4686e02 /kernel/sched/autogroup.c | |
parent | 60c906bab124a0627fba04c9ca5e61bba4747c0c (diff) | |
parent | bb3bac2ca9a3a5b7fa601781adf70167a0449d75 (diff) |
Merge branch 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull scheduler updates from Ingo Molnar:
"The main changes in this (fairly busy) cycle were:
- There was a class of scheduler bugs related to forgetting to update
the rq-clock timestamp which can cause weird and hard to debug
problems, so there's a new debug facility for this: which uncovered
a whole lot of bugs which convinced us that we want to keep the
debug facility.
(Peter Zijlstra, Matt Fleming)
- Various cputime related updates: eliminate cputime and use u64
nanoseconds directly, simplify and improve the arch interfaces,
implement delayed accounting more widely, etc. - (Frederic
Weisbecker)
- Move code around for better structure plus cleanups (Ingo Molnar)
- Move IO schedule accounting deeper into the scheduler plus related
changes to improve the situation (Tejun Heo)
- ... plus a round of sched/rt and sched/deadline fixes, plus other
fixes, updats and cleanups"
* 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (85 commits)
sched/core: Remove unlikely() annotation from sched_move_task()
sched/autogroup: Rename auto_group.[ch] to autogroup.[ch]
sched/topology: Split out scheduler topology code from core.c into topology.c
sched/core: Remove unnecessary #include headers
sched/rq_clock: Consolidate the ordering of the rq_clock methods
delayacct: Include <uapi/linux/taskstats.h>
sched/core: Clean up comments
sched/rt: Show the 'sched_rr_timeslice' SCHED_RR timeslice tuning knob in milliseconds
sched/clock: Add dummy clear_sched_clock_stable() stub function
sched/cputime: Remove generic asm headers
sched/cputime: Remove unused nsec_to_cputime()
s390, sched/cputime: Remove unused cputime definitions
powerpc, sched/cputime: Remove unused cputime definitions
s390, sched/cputime: Make arch_cpu_idle_time() to return nsecs
ia64, sched/cputime: Remove unused cputime definitions
ia64: Convert vtime to use nsec units directly
ia64, sched/cputime: Move the nsecs based cputime headers to the last arch using it
sched/cputime: Remove jiffies based cputime
sched/cputime, vtime: Return nsecs instead of cputime_t to account
sched/cputime: Complete nsec conversion of tick based accounting
...
Diffstat (limited to 'kernel/sched/autogroup.c')
-rw-r--r-- | kernel/sched/autogroup.c | 271 |
1 files changed, 271 insertions, 0 deletions
diff --git a/kernel/sched/autogroup.c b/kernel/sched/autogroup.c new file mode 100644 index 000000000000..da39489d2d80 --- /dev/null +++ b/kernel/sched/autogroup.c @@ -0,0 +1,271 @@ +#include "sched.h" + +#include <linux/proc_fs.h> +#include <linux/seq_file.h> +#include <linux/kallsyms.h> +#include <linux/utsname.h> +#include <linux/security.h> +#include <linux/export.h> + +unsigned int __read_mostly sysctl_sched_autogroup_enabled = 1; +static struct autogroup autogroup_default; +static atomic_t autogroup_seq_nr; + +void __init autogroup_init(struct task_struct *init_task) +{ + autogroup_default.tg = &root_task_group; + kref_init(&autogroup_default.kref); + init_rwsem(&autogroup_default.lock); + init_task->signal->autogroup = &autogroup_default; +} + +void autogroup_free(struct task_group *tg) +{ + kfree(tg->autogroup); +} + +static inline void autogroup_destroy(struct kref *kref) +{ + struct autogroup *ag = container_of(kref, struct autogroup, kref); + +#ifdef CONFIG_RT_GROUP_SCHED + /* We've redirected RT tasks to the root task group... */ + ag->tg->rt_se = NULL; + ag->tg->rt_rq = NULL; +#endif + sched_offline_group(ag->tg); + sched_destroy_group(ag->tg); +} + +static inline void autogroup_kref_put(struct autogroup *ag) +{ + kref_put(&ag->kref, autogroup_destroy); +} + +static inline struct autogroup *autogroup_kref_get(struct autogroup *ag) +{ + kref_get(&ag->kref); + return ag; +} + +static inline struct autogroup *autogroup_task_get(struct task_struct *p) +{ + struct autogroup *ag; + unsigned long flags; + + if (!lock_task_sighand(p, &flags)) + return autogroup_kref_get(&autogroup_default); + + ag = autogroup_kref_get(p->signal->autogroup); + unlock_task_sighand(p, &flags); + + return ag; +} + +static inline struct autogroup *autogroup_create(void) +{ + struct autogroup *ag = kzalloc(sizeof(*ag), GFP_KERNEL); + struct task_group *tg; + + if (!ag) + goto out_fail; + + tg = sched_create_group(&root_task_group); + + if (IS_ERR(tg)) + goto out_free; + + kref_init(&ag->kref); + init_rwsem(&ag->lock); + ag->id = atomic_inc_return(&autogroup_seq_nr); + ag->tg = tg; +#ifdef CONFIG_RT_GROUP_SCHED + /* + * Autogroup RT tasks are redirected to the root task group + * so we don't have to move tasks around upon policy change, + * or flail around trying to allocate bandwidth on the fly. + * A bandwidth exception in __sched_setscheduler() allows + * the policy change to proceed. + */ + free_rt_sched_group(tg); + tg->rt_se = root_task_group.rt_se; + tg->rt_rq = root_task_group.rt_rq; +#endif + tg->autogroup = ag; + + sched_online_group(tg, &root_task_group); + return ag; + +out_free: + kfree(ag); +out_fail: + if (printk_ratelimit()) { + printk(KERN_WARNING "autogroup_create: %s failure.\n", + ag ? "sched_create_group()" : "kmalloc()"); + } + + return autogroup_kref_get(&autogroup_default); +} + +bool task_wants_autogroup(struct task_struct *p, struct task_group *tg) +{ + if (tg != &root_task_group) + return false; + /* + * If we race with autogroup_move_group() the caller can use the old + * value of signal->autogroup but in this case sched_move_task() will + * be called again before autogroup_kref_put(). + * + * However, there is no way sched_autogroup_exit_task() could tell us + * to avoid autogroup->tg, so we abuse PF_EXITING flag for this case. + */ + if (p->flags & PF_EXITING) + return false; + + return true; +} + +void sched_autogroup_exit_task(struct task_struct *p) +{ + /* + * We are going to call exit_notify() and autogroup_move_group() can't + * see this thread after that: we can no longer use signal->autogroup. + * See the PF_EXITING check in task_wants_autogroup(). + */ + sched_move_task(p); +} + +static void +autogroup_move_group(struct task_struct *p, struct autogroup *ag) +{ + struct autogroup *prev; + struct task_struct *t; + unsigned long flags; + + BUG_ON(!lock_task_sighand(p, &flags)); + + prev = p->signal->autogroup; + if (prev == ag) { + unlock_task_sighand(p, &flags); + return; + } + + p->signal->autogroup = autogroup_kref_get(ag); + /* + * We can't avoid sched_move_task() after we changed signal->autogroup, + * this process can already run with task_group() == prev->tg or we can + * race with cgroup code which can read autogroup = prev under rq->lock. + * In the latter case for_each_thread() can not miss a migrating thread, + * cpu_cgroup_attach() must not be possible after cgroup_exit() and it + * can't be removed from thread list, we hold ->siglock. + * + * If an exiting thread was already removed from thread list we rely on + * sched_autogroup_exit_task(). + */ + for_each_thread(p, t) + sched_move_task(t); + + unlock_task_sighand(p, &flags); + autogroup_kref_put(prev); +} + +/* Allocates GFP_KERNEL, cannot be called under any spinlock */ +void sched_autogroup_create_attach(struct task_struct *p) +{ + struct autogroup *ag = autogroup_create(); + + autogroup_move_group(p, ag); + /* drop extra reference added by autogroup_create() */ + autogroup_kref_put(ag); +} +EXPORT_SYMBOL(sched_autogroup_create_attach); + +/* Cannot be called under siglock. Currently has no users */ +void sched_autogroup_detach(struct task_struct *p) +{ + autogroup_move_group(p, &autogroup_default); +} +EXPORT_SYMBOL(sched_autogroup_detach); + +void sched_autogroup_fork(struct signal_struct *sig) +{ + sig->autogroup = autogroup_task_get(current); +} + +void sched_autogroup_exit(struct signal_struct *sig) +{ + autogroup_kref_put(sig->autogroup); +} + +static int __init setup_autogroup(char *str) +{ + sysctl_sched_autogroup_enabled = 0; + + return 1; +} + +__setup("noautogroup", setup_autogroup); + +#ifdef CONFIG_PROC_FS + +int proc_sched_autogroup_set_nice(struct task_struct *p, int nice) +{ + static unsigned long next = INITIAL_JIFFIES; + struct autogroup *ag; + unsigned long shares; + int err; + + if (nice < MIN_NICE || nice > MAX_NICE) + return -EINVAL; + + err = security_task_setnice(current, nice); + if (err) + return err; + + if (nice < 0 && !can_nice(current, nice)) + return -EPERM; + + /* this is a heavy operation taking global locks.. */ + if (!capable(CAP_SYS_ADMIN) && time_before(jiffies, next)) + return -EAGAIN; + + next = HZ / 10 + jiffies; + ag = autogroup_task_get(p); + shares = scale_load(sched_prio_to_weight[nice + 20]); + + down_write(&ag->lock); + err = sched_group_set_shares(ag->tg, shares); + if (!err) + ag->nice = nice; + up_write(&ag->lock); + + autogroup_kref_put(ag); + + return err; +} + +void proc_sched_autogroup_show_task(struct task_struct *p, struct seq_file *m) +{ + struct autogroup *ag = autogroup_task_get(p); + + if (!task_group_is_autogroup(ag->tg)) + goto out; + + down_read(&ag->lock); + seq_printf(m, "/autogroup-%ld nice %d\n", ag->id, ag->nice); + up_read(&ag->lock); + +out: + autogroup_kref_put(ag); +} +#endif /* CONFIG_PROC_FS */ + +#ifdef CONFIG_SCHED_DEBUG +int autogroup_path(struct task_group *tg, char *buf, int buflen) +{ + if (!task_group_is_autogroup(tg)) + return 0; + + return snprintf(buf, buflen, "%s-%ld", "/autogroup", tg->autogroup->id); +} +#endif /* CONFIG_SCHED_DEBUG */ |