// SPDX-License-Identifier: GPL-2.0-only/* * kernel/sched/syscalls.c * * Core kernel scheduler syscalls related code * * Copyright (C) 1991-2002 Linus Torvalds * Copyright (C) 1998-2024 Ingo Molnar, Red Hat */#include <linux/sched.h>#include <linux/cpuset.h>#include <linux/sched/debug.h> #include <uapi/linux/sched/types.h> #include "sched.h"#include "autogroup.h" static inline int __normal_prio(int policy, int rt_prio, int nice){ int prio; if (dl_policy(policy)) prio = MAX_DL_PRIO - 1; else if (rt_policy(policy)) prio = MAX_RT_PRIO - 1 - rt_prio; else prio = NICE_TO_PRIO(nice); return prio;} /* * Calculate the expected normal priority: i.e. priority * without taking RT-inheritance into account. Might be * boosted by interactivity modifiers. Changes upon fork, * setprio syscalls, and whenever the interactivity * estimator recalculates. */static inline int normal_prio(struct task_struct *p){ return __normal_prio(p->policy, p->rt_priority, PRIO_TO_NICE(p->static_prio));} /* * Calculate the current priority, i.e. the priority * taken into account by the scheduler. This value might * be boosted by RT tasks, or might be boosted by * interactivity modifiers. Will be RT if the task got * RT-boosted. If not then it returns p->normal_prio. */static int effective_prio(struct task_struct *p){ p->normal_prio = normal_prio(p); /* * If we are RT tasks or we were boosted to RT priority, * keep the priority unchanged. Otherwise, update priority * to the normal priority: */ if (!rt_or_dl_prio(p->prio)) return p->normal_prio; return p->prio;} void set_user_nice(struct task_struct *p, long nice){ int old_prio; if (task_nice(p) == nice || nice < MIN_NICE || nice > MAX_NICE) return; /* * We have to be careful, if called from sys_setpriority(), * the task might be in the middle of scheduling on another CPU. */ guard(task_rq_lock)(p); /* * The RT priorities are set via sched_setscheduler(), but we still * allow the 'normal' nice value to be set - but as expected * it won't have any effect on scheduling until the task is * SCHED_DEADLINE, SCHED_FIFO or SCHED_RR: */ if (task_has_dl_policy(p) || task_has_rt_policy(p)) { p->static_prio = NICE_TO_PRIO(nice); return; } scoped_guard (sched_change, p, DEQUEUE_SAVE) { p->static_prio = NICE_TO_PRIO(nice); set_load_weight(p, true); old_prio = p->prio; p->prio = effective_prio(p); }}EXPORT_SYMBOL(set_user_nice); /* * is_nice_reduction - check if nice value is an actual reduction * * Similar to can_nice() but does not perform a capability check. * * @p: task * @nice: nice value */static bool is_nice_reduction(const struct task_struct *p, const int nice){ /* Convert nice value [19,-20] to rlimit style value [1,40]: */ int nice_rlim = nice_to_rlimit(nice); return (nice_rlim <= task_rlimit(p, RLIMIT_NICE));} /* * can_nice - check if a task can reduce its nice value * @p: task * @nice: nice value */int can_nice(const struct task_struct *p, const int nice){ return is_nice_reduction(p, nice) || capable(CAP_SYS_NICE);} #ifdef __ARCH_WANT_SYS_NICE /* * sys_nice - change the priority of the current process. * @increment: priority increment * * sys_setpriority is a more generic, but much slower function that * does similar things. */SYSCALL_DEFINE1(nice, int, increment){ long nice, retval; /* * Setpriority might change our priority at the same moment. * We don't have to worry. Conceptually one call occurs first * and we have a single winner. */ increment = clamp(increment, -NICE_WIDTH, NICE_WIDTH); nice = task_nice(current) + increment; nice = clamp_val(nice, MIN_NICE, MAX_NICE); if (increment < 0 && !can_nice(current, nice)) return -EPERM; retval = security_task_setnice(current, nice); if (retval) return retval; set_user_nice(current, nice); return 0;} #endif /* __ARCH_WANT_SYS_NICE */ /** * task_prio - return the priority value of a given task. * @p: the task in question. * * Return: The priority value as seen by users in /proc. * * sched policy return value kernel prio user prio/nice * * normal, batch, idle [0 ... 39] [100 ... 139] 0/[-20 ... 19] * fifo, rr [-2 ... -100] [98 ... 0] [1 ... 99] * deadline -101 -1 0 */int task_prio(const struct task_struct *p){ return p->prio - MAX_RT_PRIO;} /** * idle_cpu - is a given CPU idle currently? * @cpu: the processor in question. * * Return: 1 if the CPU is currently idle. 0 otherwise. */int idle_cpu(int cpu){ return idle_rq(cpu_rq(cpu));} /** * idle_task - return the idle task for a given CPU. * @cpu: the processor in question. * * Return: The idle task for the CPU @cpu. */struct task_struct *idle_task(int cpu){ return cpu_rq(cpu)->idle;} #ifdef CONFIG_SCHED_COREint sched_core_idle_cpu(int cpu){ struct rq *rq = cpu_rq(cpu); if (sched_core_enabled(rq) && rq->curr == rq->idle) return 1; return idle_cpu(cpu);}#endif /* CONFIG_SCHED_CORE */ /** * find_process_by_pid - find a process with a matching PID value. * @pid: the pid in question. * * The task of @pid, if found. %NULL otherwise. */static struct task_struct *find_process_by_pid(pid_t pid){ return pid ? find_task_by_vpid(pid) : current;} static struct task_struct *find_get_task(pid_t pid){ struct task_struct *p; guard(rcu)(); p = find_process_by_pid(pid); if (likely(p)) get_task_struct(p); return p;} DEFINE_CLASS(find_get_task, struct task_struct *, if (_T) put_task_struct(_T), find_get_task(pid), pid_t pid) /* * sched_setparam() passes in -1 for its policy, to let the functions * it calls know not to change it. */#define SETPARAM_POLICY -1 static void __setscheduler_params(struct task_struct *p, const struct sched_attr *attr){ int policy = attr->sched_policy; if (policy == SETPARAM_POLICY) policy = p->policy; p->policy = policy; if (dl_policy(policy)) __setparam_dl(p, attr); else if (fair_policy(policy)) __setparam_fair(p, attr); /* rt-policy tasks do not have a timerslack */ if (rt_or_dl_task_policy(p)) { p->timer_slack_ns = 0; } else if (p->timer_slack_ns == 0) { /* when switching back to non-rt policy, restore timerslack */ p->timer_slack_ns = p->default_timer_slack_ns; } /* * __sched_setscheduler() ensures attr->sched_priority == 0 when * !rt_policy. Always setting this ensures that things like * getparam()/getattr() don't report silly values for !rt tasks. */ p->rt_priority = attr->sched_priority; p->normal_prio = normal_prio(p); set_load_weight(p, true);} /* * Check the target process has a UID that matches the current process's: */static bool check_same_owner(struct task_struct *p){ const struct cred *cred = current_cred(), *pcred; guard(rcu)(); pcred = __task_cred(p); return (uid_eq(cred->euid, pcred->euid) || uid_eq(cred->euid, pcred->uid));} #ifdef CONFIG_RT_MUTEXESstatic inline void __setscheduler_dl_pi(int newprio, int policy, struct task_struct *p, struct sched_change_ctx *scope){ /* * In case a DEADLINE task (either proper or boosted) gets * setscheduled to a lower priority class, check if it neeeds to * inherit parameters from a potential pi_task. In that case make * sure replenishment happens with the next enqueue. */ if (dl_prio(newprio) && !dl_policy(policy)) { struct task_struct *pi_task = rt_mutex_get_top_task(p); if (pi_task) { p->dl.pi_se = pi_task->dl.pi_se; scope->flags |= ENQUEUE_REPLENISH; } }}#else /* !CONFIG_RT_MUTEXES */static inline void __setscheduler_dl_pi(int newprio, int policy, struct task_struct *p, struct sched_change_ctx *scope){}#endif /* !CONFIG_RT_MUTEXES */ #ifdef CONFIG_UCLAMP_TASK static int uclamp_validate(struct task_struct *p, const struct sched_attr *attr){ int util_min = p->uclamp_req[UCLAMP_MIN].value; int util_max = p->uclamp_req[UCLAMP_MAX].value; if (attr->sched_flags & SCHED_FLAG_UTIL_CLAMP_MIN) { util_min = attr->sched_util_min; if (util_min + 1 > SCHED_CAPACITY_SCALE + 1) return -EINVAL; } if (attr->sched_flags & SCHED_FLAG_UTIL_CLAMP_MAX) { util_max = attr->sched_util_max; if (util_max + 1 > SCHED_CAPACITY_SCALE + 1) return -EINVAL; } if (util_min != -1 && util_max != -1 && util_min > util_max) return -EINVAL; /* * We have valid uclamp attributes; make sure uclamp is enabled. * * We need to do that here, because enabling static branches is a * blocking operation which obviously cannot be done while holding * scheduler locks. */ sched_uclamp_enable(); return 0;} static bool uclamp_reset(const struct sched_attr *attr, enum uclamp_id clamp_id, struct uclamp_se *uc_se){ /* Reset on sched class change for a non user-defined clamp value. */ if (likely(!(attr->sched_flags & SCHED_FLAG_UTIL_CLAMP)) && !uc_se->user_defined) return true; /* Reset on sched_util_{min,max} == -1. */ if (clamp_id == UCLAMP_MIN && attr->sched_flags & SCHED_FLAG_UTIL_CLAMP_MIN && attr->sched_util_min == -1) { return true; } if (clamp_id == UCLAMP_MAX && attr->sched_flags & SCHED_FLAG_UTIL_CLAMP_MAX && attr->sched_util_max == -1) { return true; } return false;} static void __setscheduler_uclamp(struct task_struct *p, const struct sched_attr *attr){ enum uclamp_id clamp_id; for_each_clamp_id(clamp_id) { struct uclamp_se *uc_se = &p->uclamp_req[clamp_id]; unsigned int value; if (!uclamp_reset(attr, clamp_id, uc_se)) continue; /* * RT by default have a 100% boost value that could be modified * at runtime. */ if (unlikely(rt_task(p) && clamp_id == UCLAMP_MIN)) value = sysctl_sched_uclamp_util_min_rt_default; else value = uclamp_none(clamp_id); uclamp_se_set(uc_se, value, false); } if (likely(!(attr->sched_flags & SCHED_FLAG_UTIL_CLAMP))) return; if (attr->sched_flags & SCHED_FLAG_UTIL_CLAMP_MIN && attr->sched_util_min != -1) { uclamp_se_set(&p->uclamp_req[UCLAMP_MIN], attr->sched_util_min, true); } if (attr->sched_flags & SCHED_FLAG_UTIL_CLAMP_MAX && attr->sched_util_max != -1) { uclamp_se_set(&p->uclamp_req[UCLAMP_MAX], attr->sched_util_max, true); }} #else /* !CONFIG_UCLAMP_TASK: */ static inline int uclamp_validate(struct task_struct *p, const struct sched_attr *attr){ return -EOPNOTSUPP;}static void __setscheduler_uclamp(struct task_struct *p, const struct sched_attr *attr) { }#endif /* !CONFIG_UCLAMP_TASK */ /* * Allow unprivileged RT tasks to decrease priority. * Only issue a capable test if needed and only once to avoid an audit * event on permitted non-privileged operations: */static int user_check_sched_setscheduler(struct task_struct *p, const struct sched_attr *attr, int policy, int reset_on_fork){ if (fair_policy(policy)) { if (attr->sched_nice < task_nice(p) && !is_nice_reduction(p, attr->sched_nice)) goto req_priv; } if (rt_policy(policy)) { unsigned long rlim_rtprio = task_rlimit(p, RLIMIT_RTPRIO); /* Can't set/change the rt policy: */ if (policy != p->policy && !rlim_rtprio) goto req_priv; /* Can't increase priority: */ if (attr->sched_priority > p->rt_priority && attr->sched_priority > rlim_rtprio) goto req_priv; } /* * Can't set/change SCHED_DEADLINE policy at all for now * (safest behavior); in the future we would like to allow * unprivileged DL tasks to increase their relative deadline * or reduce their runtime (both ways reducing utilization) */ if (dl_policy(policy)) goto req_priv; /* * Treat SCHED_IDLE as nice 20. Only allow a switch to * SCHED_NORMAL if the RLIMIT_NICE would normally permit it. */ if (task_has_idle_policy(p) && !idle_policy(policy)) { if (!is_nice_reduction(p, task_nice(p))) goto req_priv; } /* Can't change other user's priorities: */ if (!check_same_owner(p)) goto req_priv; /* Normal users shall not reset the sched_reset_on_fork flag: */ if (p->sched_reset_on_fork && !reset_on_fork) goto req_priv; return 0; req_priv: if (!capable(CAP_SYS_NICE)) return -EPERM; return 0;} int __sched_setscheduler(struct task_struct *p, const struct sched_attr *attr, bool user, bool pi){ int oldpolicy = -1, policy = attr->sched_policy; int retval, oldprio, newprio; const struct sched_class *prev_class, *next_class; struct balance_callback *head;Lines 1–500 of 1578. Load more
// SPDX-License-Identifier: GPL-2.0-only /* * kernel/sched/syscalls.c * * Core kernel scheduler syscalls related code * * Copyright (C) 1991-2002 Linus Torvalds * Copyright (C) 1998-2024 Ingo Molnar, Red Hat */ #include <linux/sched.h> #include <linux/cpuset.h> #include <linux/sched/debug.h> #include <uapi/linux/sched/types.h> #include "sched.h" #include "autogroup.h" static inline int __normal_prio(int policy, int rt_prio, int nice) { int prio; if (dl_policy(policy)) prio = MAX_DL_PRIO - 1; else if (rt_policy(policy)) prio = MAX_RT_PRIO - 1 - rt_prio; else prio = NICE_TO_PRIO(nice); return prio; } /* * Calculate the expected normal priority: i.e. priority * without taking RT-inheritance into account. Might be * boosted by interactivity modifiers. Changes upon fork, * setprio syscalls, and whenever the interactivity * estimator recalculates. */ static inline int normal_prio(struct task_struct *p) { return __normal_prio(p->policy, p->rt_priority, PRIO_TO_NICE(p->static_prio)); } /* * Calculate the current priority, i.e. the priority * taken into account by the scheduler. This value might * be boosted by RT tasks, or might be boosted by * interactivity modifiers. Will be RT if the task got * RT-boosted. If not then it returns p->normal_prio. */ static int effective_prio(struct task_struct *p) { p->normal_prio = normal_prio(p); /* * If we are RT tasks or we were boosted to RT priority, * keep the priority unchanged. Otherwise, update priority * to the normal priority: */ if (!rt_or_dl_prio(p->prio)) return p->normal_prio; return p->prio; } void set_user_nice(struct task_struct *p, long nice) { int old_prio; if (task_nice(p) == nice || nice < MIN_NICE || nice > MAX_NICE) return; /* * We have to be careful, if called from sys_setpriority(), * the task might be in the middle of scheduling on another CPU. */ guard(task_rq_lock)(p); /* * The RT priorities are set via sched_setscheduler(), but we still * allow the 'normal' nice value to be set - but as expected * it won't have any effect on scheduling until the task is * SCHED_DEADLINE, SCHED_FIFO or SCHED_RR: */ if (task_has_dl_policy(p) || task_has_rt_policy(p)) { p->static_prio = NICE_TO_PRIO(nice); return; } scoped_guard (sched_change, p, DEQUEUE_SAVE) { p->static_prio = NICE_TO_PRIO(nice); set_load_weight(p, true); old_prio = p->prio; p->prio = effective_prio(p); } } EXPORT_SYMBOL(set_user_nice); /* * is_nice_reduction - check if nice value is an actual reduction * * Similar to can_nice() but does not perform a capability check. * * @p: task * @nice: nice value */ static bool is_nice_reduction(const struct task_struct *p, const int nice) { /* Convert nice value [19,-20] to rlimit style value [1,40]: */ int nice_rlim = nice_to_rlimit(nice); return (nice_rlim <= task_rlimit(p, RLIMIT_NICE)); } /* * can_nice - check if a task can reduce its nice value * @p: task * @nice: nice value */ int can_nice(const struct task_struct *p, const int nice) { return is_nice_reduction(p, nice) || capable(CAP_SYS_NICE); } #ifdef __ARCH_WANT_SYS_NICE /* * sys_nice - change the priority of the current process. * @increment: priority increment * * sys_setpriority is a more generic, but much slower function that * does similar things. */ SYSCALL_DEFINE1(nice, int, increment) { long nice, retval; /* * Setpriority might change our priority at the same moment. * We don't have to worry. Conceptually one call occurs first * and we have a single winner. */ increment = clamp(increment, -NICE_WIDTH, NICE_WIDTH); nice = task_nice(current) + increment; nice = clamp_val(nice, MIN_NICE, MAX_NICE); if (increment < 0 && !can_nice(current, nice)) return -EPERM; retval = security_task_setnice(current, nice); if (retval) return retval; set_user_nice(current, nice); return 0; } #endif /* __ARCH_WANT_SYS_NICE */ /** * task_prio - return the priority value of a given task. * @p: the task in question. * * Return: The priority value as seen by users in /proc. * * sched policy return value kernel prio user prio/nice * * normal, batch, idle [0 ... 39] [100 ... 139] 0/[-20 ... 19] * fifo, rr [-2 ... -100] [98 ... 0] [1 ... 99] * deadline -101 -1 0 */ int task_prio(const struct task_struct *p) { return p->prio - MAX_RT_PRIO; } /** * idle_cpu - is a given CPU idle currently? * @cpu: the processor in question. * * Return: 1 if the CPU is currently idle. 0 otherwise. */ int idle_cpu(int cpu) { return idle_rq(cpu_rq(cpu)); } /** * idle_task - return the idle task for a given CPU. * @cpu: the processor in question. * * Return: The idle task for the CPU @cpu. */ struct task_struct *idle_task(int cpu) { return cpu_rq(cpu)->idle; } #ifdef CONFIG_SCHED_CORE int sched_core_idle_cpu(int cpu) { struct rq *rq = cpu_rq(cpu); if (sched_core_enabled(rq) && rq->curr == rq->idle) return 1; return idle_cpu(cpu); } #endif /* CONFIG_SCHED_CORE */ /** * find_process_by_pid - find a process with a matching PID value. * @pid: the pid in question. * * The task of @pid, if found. %NULL otherwise. */ static struct task_struct *find_process_by_pid(pid_t pid) { return pid ? find_task_by_vpid(pid) : current; } static struct task_struct *find_get_task(pid_t pid) { struct task_struct *p; guard(rcu)(); p = find_process_by_pid(pid); if (likely(p)) get_task_struct(p); return p; } DEFINE_CLASS(find_get_task, struct task_struct *, if (_T) put_task_struct(_T), find_get_task(pid), pid_t pid) /* * sched_setparam() passes in -1 for its policy, to let the functions * it calls know not to change it. */ #define SETPARAM_POLICY -1 static void __setscheduler_params(struct task_struct *p, const struct sched_attr *attr) { int policy = attr->sched_policy; if (policy == SETPARAM_POLICY) policy = p->policy; p->policy = policy; if (dl_policy(policy)) __setparam_dl(p, attr); else if (fair_policy(policy)) __setparam_fair(p, attr); /* rt-policy tasks do not have a timerslack */ if (rt_or_dl_task_policy(p)) { p->timer_slack_ns = 0; } else if (p->timer_slack_ns == 0) { /* when switching back to non-rt policy, restore timerslack */ p->timer_slack_ns = p->default_timer_slack_ns; } /* * __sched_setscheduler() ensures attr->sched_priority == 0 when * !rt_policy. Always setting this ensures that things like * getparam()/getattr() don't report silly values for !rt tasks. */ p->rt_priority = attr->sched_priority; p->normal_prio = normal_prio(p); set_load_weight(p, true); } /* * Check the target process has a UID that matches the current process's: */ static bool check_same_owner(struct task_struct *p) { const struct cred *cred = current_cred(), *pcred; guard(rcu)(); pcred = __task_cred(p); return (uid_eq(cred->euid, pcred->euid) || uid_eq(cred->euid, pcred->uid)); } #ifdef CONFIG_RT_MUTEXES static inline void __setscheduler_dl_pi(int newprio, int policy, struct task_struct *p, struct sched_change_ctx *scope) { /* * In case a DEADLINE task (either proper or boosted) gets * setscheduled to a lower priority class, check if it neeeds to * inherit parameters from a potential pi_task. In that case make * sure replenishment happens with the next enqueue. */ if (dl_prio(newprio) && !dl_policy(policy)) { struct task_struct *pi_task = rt_mutex_get_top_task(p); if (pi_task) { p->dl.pi_se = pi_task->dl.pi_se; scope->flags |= ENQUEUE_REPLENISH; } } } #else /* !CONFIG_RT_MUTEXES */ static inline void __setscheduler_dl_pi(int newprio, int policy, struct task_struct *p, struct sched_change_ctx *scope) { } #endif /* !CONFIG_RT_MUTEXES */ #ifdef CONFIG_UCLAMP_TASK static int uclamp_validate(struct task_struct *p, const struct sched_attr *attr) { int util_min = p->uclamp_req[UCLAMP_MIN].value; int util_max = p->uclamp_req[UCLAMP_MAX].value; if (attr->sched_flags & SCHED_FLAG_UTIL_CLAMP_MIN) { util_min = attr->sched_util_min; if (util_min + 1 > SCHED_CAPACITY_SCALE + 1) return -EINVAL; } if (attr->sched_flags & SCHED_FLAG_UTIL_CLAMP_MAX) { util_max = attr->sched_util_max; if (util_max + 1 > SCHED_CAPACITY_SCALE + 1) return -EINVAL; } if (util_min != -1 && util_max != -1 && util_min > util_max) return -EINVAL; /* * We have valid uclamp attributes; make sure uclamp is enabled. * * We need to do that here, because enabling static branches is a * blocking operation which obviously cannot be done while holding * scheduler locks. */ sched_uclamp_enable(); return 0; } static bool uclamp_reset(const struct sched_attr *attr, enum uclamp_id clamp_id, struct uclamp_se *uc_se) { /* Reset on sched class change for a non user-defined clamp value. */ if (likely(!(attr->sched_flags & SCHED_FLAG_UTIL_CLAMP)) && !uc_se->user_defined) return true; /* Reset on sched_util_{min,max} == -1. */ if (clamp_id == UCLAMP_MIN && attr->sched_flags & SCHED_FLAG_UTIL_CLAMP_MIN && attr->sched_util_min == -1) { return true; } if (clamp_id == UCLAMP_MAX && attr->sched_flags & SCHED_FLAG_UTIL_CLAMP_MAX && attr->sched_util_max == -1) { return true; } return false; } static void __setscheduler_uclamp(struct task_struct *p, const struct sched_attr *attr) { enum uclamp_id clamp_id; for_each_clamp_id(clamp_id) { struct uclamp_se *uc_se = &p->uclamp_req[clamp_id]; unsigned int value; if (!uclamp_reset(attr, clamp_id, uc_se)) continue; /* * RT by default have a 100% boost value that could be modified * at runtime. */ if (unlikely(rt_task(p) && clamp_id == UCLAMP_MIN)) value = sysctl_sched_uclamp_util_min_rt_default; else value = uclamp_none(clamp_id); uclamp_se_set(uc_se, value, false); } if (likely(!(attr->sched_flags & SCHED_FLAG_UTIL_CLAMP))) return; if (attr->sched_flags & SCHED_FLAG_UTIL_CLAMP_MIN && attr->sched_util_min != -1) { uclamp_se_set(&p->uclamp_req[UCLAMP_MIN], attr->sched_util_min, true); } if (attr->sched_flags & SCHED_FLAG_UTIL_CLAMP_MAX && attr->sched_util_max != -1) { uclamp_se_set(&p->uclamp_req[UCLAMP_MAX], attr->sched_util_max, true); } } #else /* !CONFIG_UCLAMP_TASK: */ static inline int uclamp_validate(struct task_struct *p, const struct sched_attr *attr) { return -EOPNOTSUPP; } static void __setscheduler_uclamp(struct task_struct *p, const struct sched_attr *attr) { } #endif /* !CONFIG_UCLAMP_TASK */ /* * Allow unprivileged RT tasks to decrease priority. * Only issue a capable test if needed and only once to avoid an audit * event on permitted non-privileged operations: */ static int user_check_sched_setscheduler(struct task_struct *p, const struct sched_attr *attr, int policy, int reset_on_fork) { if (fair_policy(policy)) { if (attr->sched_nice < task_nice(p) && !is_nice_reduction(p, attr->sched_nice)) goto req_priv; } if (rt_policy(policy)) { unsigned long rlim_rtprio = task_rlimit(p, RLIMIT_RTPRIO); /* Can't set/change the rt policy: */ if (policy != p->policy && !rlim_rtprio) goto req_priv; /* Can't increase priority: */ if (attr->sched_priority > p->rt_priority && attr->sched_priority > rlim_rtprio) goto req_priv; } /* * Can't set/change SCHED_DEADLINE policy at all for now * (safest behavior); in the future we would like to allow * unprivileged DL tasks to increase their relative deadline * or reduce their runtime (both ways reducing utilization) */ if (dl_policy(policy)) goto req_priv; /* * Treat SCHED_IDLE as nice 20. Only allow a switch to * SCHED_NORMAL if the RLIMIT_NICE would normally permit it. */ if (task_has_idle_policy(p) && !idle_policy(policy)) { if (!is_nice_reduction(p, task_nice(p))) goto req_priv; } /* Can't change other user's priorities: */ if (!check_same_owner(p)) goto req_priv; /* Normal users shall not reset the sched_reset_on_fork flag: */ if (p->sched_reset_on_fork && !reset_on_fork) goto req_priv; return 0; req_priv: if (!capable(CAP_SYS_NICE)) return -EPERM; return 0; } int __sched_setscheduler(struct task_struct *p, const struct sched_attr *attr, bool user, bool pi) { int oldpolicy = -1, policy = attr->sched_policy; int retval, oldprio, newprio; const struct sched_class *prev_class, *next_class; struct balance_callback *head;