mirror of
https://gitee.com/bianbu-linux/linux-6.6
synced 2025-04-24 14:07:52 -04:00
13685c4a08
RT tasks by default run at the highest capacity/performance level. When uclamp is selected this default behavior is retained by enforcing the requested uclamp.min (p->uclamp_req[UCLAMP_MIN]) of the RT tasks to be uclamp_none(UCLAMP_MAX), which is SCHED_CAPACITY_SCALE; the maximum value. This is also referred to as 'the default boost value of RT tasks'. See commit1a00d99997("sched/uclamp: Set default clamps for RT tasks"). On battery powered devices, it is desired to control this default (currently hardcoded) behavior at runtime to reduce energy consumed by RT tasks. For example, a mobile device manufacturer where big.LITTLE architecture is dominant, the performance of the little cores varies across SoCs, and on high end ones the big cores could be too power hungry. Given the diversity of SoCs, the new knob allows manufactures to tune the best performance/power for RT tasks for the particular hardware they run on. They could opt to further tune the value when the user selects a different power saving mode or when the device is actively charging. The runtime aspect of it further helps in creating a single kernel image that can be run on multiple devices that require different tuning. Keep in mind that a lot of RT tasks in the system are created by the kernel. On Android for instance I can see over 50 RT tasks, only a handful of which created by the Android framework. To control the default behavior globally by system admins and device integrator, introduce the new sysctl_sched_uclamp_util_min_rt_default to change the default boost value of the RT tasks. I anticipate this to be mostly in the form of modifying the init script of a particular device. To avoid polluting the fast path with unnecessary code, the approach taken is to synchronously do the update by traversing all the existing tasks in the system. This could race with a concurrent fork(), which is dealt with by introducing sched_post_fork() function which will ensure the racy fork will get the right update applied. Tested on Juno-r2 in combination with the RT capacity awareness [1]. By default an RT task will go to the highest capacity CPU and run at the maximum frequency, which is particularly energy inefficient on high end mobile devices because the biggest core[s] are 'huge' and power hungry. With this patch the RT task can be controlled to run anywhere by default, and doesn't cause the frequency to be maximum all the time. Yet any task that really needs to be boosted can easily escape this default behavior by modifying its requested uclamp.min value (p->uclamp_req[UCLAMP_MIN]) via sched_setattr() syscall. [1]804d402fb6: ("sched/rt: Make RT capacity-aware") Signed-off-by: Qais Yousef <qais.yousef@arm.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Link: https://lkml.kernel.org/r/20200716110347.19553-2-qais.yousef@arm.com
184 lines
4.9 KiB
C
184 lines
4.9 KiB
C
/* SPDX-License-Identifier: GPL-2.0 */
|
|
#ifndef _LINUX_SCHED_TASK_H
|
|
#define _LINUX_SCHED_TASK_H
|
|
|
|
/*
|
|
* Interface between the scheduler and various task lifetime (fork()/exit())
|
|
* functionality:
|
|
*/
|
|
|
|
#include <linux/sched.h>
|
|
#include <linux/uaccess.h>
|
|
|
|
struct task_struct;
|
|
struct rusage;
|
|
union thread_union;
|
|
struct css_set;
|
|
|
|
/* All the bits taken by the old clone syscall. */
|
|
#define CLONE_LEGACY_FLAGS 0xffffffffULL
|
|
|
|
struct kernel_clone_args {
|
|
u64 flags;
|
|
int __user *pidfd;
|
|
int __user *child_tid;
|
|
int __user *parent_tid;
|
|
int exit_signal;
|
|
unsigned long stack;
|
|
unsigned long stack_size;
|
|
unsigned long tls;
|
|
pid_t *set_tid;
|
|
/* Number of elements in *set_tid */
|
|
size_t set_tid_size;
|
|
int cgroup;
|
|
struct cgroup *cgrp;
|
|
struct css_set *cset;
|
|
};
|
|
|
|
/*
|
|
* This serializes "schedule()" and also protects
|
|
* the run-queue from deletions/modifications (but
|
|
* _adding_ to the beginning of the run-queue has
|
|
* a separate lock).
|
|
*/
|
|
extern rwlock_t tasklist_lock;
|
|
extern spinlock_t mmlist_lock;
|
|
|
|
extern union thread_union init_thread_union;
|
|
extern struct task_struct init_task;
|
|
|
|
#ifdef CONFIG_PROVE_RCU
|
|
extern int lockdep_tasklist_lock_is_held(void);
|
|
#endif /* #ifdef CONFIG_PROVE_RCU */
|
|
|
|
extern asmlinkage void schedule_tail(struct task_struct *prev);
|
|
extern void init_idle(struct task_struct *idle, int cpu);
|
|
|
|
extern int sched_fork(unsigned long clone_flags, struct task_struct *p);
|
|
extern void sched_post_fork(struct task_struct *p);
|
|
extern void sched_dead(struct task_struct *p);
|
|
|
|
void __noreturn do_task_dead(void);
|
|
|
|
extern void proc_caches_init(void);
|
|
|
|
extern void fork_init(void);
|
|
|
|
extern void release_task(struct task_struct * p);
|
|
|
|
#ifdef CONFIG_HAVE_COPY_THREAD_TLS
|
|
extern int copy_thread_tls(unsigned long, unsigned long, unsigned long,
|
|
struct task_struct *, unsigned long);
|
|
#else
|
|
extern int copy_thread(unsigned long, unsigned long, unsigned long,
|
|
struct task_struct *);
|
|
|
|
/* Architectures that haven't opted into copy_thread_tls get the tls argument
|
|
* via pt_regs, so ignore the tls argument passed via C. */
|
|
static inline int copy_thread_tls(
|
|
unsigned long clone_flags, unsigned long sp, unsigned long arg,
|
|
struct task_struct *p, unsigned long tls)
|
|
{
|
|
return copy_thread(clone_flags, sp, arg, p);
|
|
}
|
|
#endif
|
|
extern void flush_thread(void);
|
|
|
|
#ifdef CONFIG_HAVE_EXIT_THREAD
|
|
extern void exit_thread(struct task_struct *tsk);
|
|
#else
|
|
static inline void exit_thread(struct task_struct *tsk)
|
|
{
|
|
}
|
|
#endif
|
|
extern void do_group_exit(int);
|
|
|
|
extern void exit_files(struct task_struct *);
|
|
extern void exit_itimers(struct signal_struct *);
|
|
|
|
extern long _do_fork(struct kernel_clone_args *kargs);
|
|
extern bool legacy_clone_args_valid(const struct kernel_clone_args *kargs);
|
|
extern long do_fork(unsigned long, unsigned long, unsigned long, int __user *, int __user *);
|
|
struct task_struct *fork_idle(int);
|
|
struct mm_struct *copy_init_mm(void);
|
|
extern pid_t kernel_thread(int (*fn)(void *), void *arg, unsigned long flags);
|
|
extern long kernel_wait4(pid_t, int __user *, int, struct rusage *);
|
|
|
|
extern void free_task(struct task_struct *tsk);
|
|
|
|
/* sched_exec is called by processes performing an exec */
|
|
#ifdef CONFIG_SMP
|
|
extern void sched_exec(void);
|
|
#else
|
|
#define sched_exec() {}
|
|
#endif
|
|
|
|
static inline struct task_struct *get_task_struct(struct task_struct *t)
|
|
{
|
|
refcount_inc(&t->usage);
|
|
return t;
|
|
}
|
|
|
|
extern void __put_task_struct(struct task_struct *t);
|
|
|
|
static inline void put_task_struct(struct task_struct *t)
|
|
{
|
|
if (refcount_dec_and_test(&t->usage))
|
|
__put_task_struct(t);
|
|
}
|
|
|
|
void put_task_struct_rcu_user(struct task_struct *task);
|
|
|
|
#ifdef CONFIG_ARCH_WANTS_DYNAMIC_TASK_STRUCT
|
|
extern int arch_task_struct_size __read_mostly;
|
|
#else
|
|
# define arch_task_struct_size (sizeof(struct task_struct))
|
|
#endif
|
|
|
|
#ifndef CONFIG_HAVE_ARCH_THREAD_STRUCT_WHITELIST
|
|
/*
|
|
* If an architecture has not declared a thread_struct whitelist we
|
|
* must assume something there may need to be copied to userspace.
|
|
*/
|
|
static inline void arch_thread_struct_whitelist(unsigned long *offset,
|
|
unsigned long *size)
|
|
{
|
|
*offset = 0;
|
|
/* Handle dynamically sized thread_struct. */
|
|
*size = arch_task_struct_size - offsetof(struct task_struct, thread);
|
|
}
|
|
#endif
|
|
|
|
#ifdef CONFIG_VMAP_STACK
|
|
static inline struct vm_struct *task_stack_vm_area(const struct task_struct *t)
|
|
{
|
|
return t->stack_vm_area;
|
|
}
|
|
#else
|
|
static inline struct vm_struct *task_stack_vm_area(const struct task_struct *t)
|
|
{
|
|
return NULL;
|
|
}
|
|
#endif
|
|
|
|
/*
|
|
* Protects ->fs, ->files, ->mm, ->group_info, ->comm, keyring
|
|
* subscriptions and synchronises with wait4(). Also used in procfs. Also
|
|
* pins the final release of task.io_context. Also protects ->cpuset and
|
|
* ->cgroup.subsys[]. And ->vfork_done.
|
|
*
|
|
* Nests both inside and outside of read_lock(&tasklist_lock).
|
|
* It must not be nested with write_lock_irq(&tasklist_lock),
|
|
* neither inside nor outside.
|
|
*/
|
|
static inline void task_lock(struct task_struct *p)
|
|
{
|
|
spin_lock(&p->alloc_lock);
|
|
}
|
|
|
|
static inline void task_unlock(struct task_struct *p)
|
|
{
|
|
spin_unlock(&p->alloc_lock);
|
|
}
|
|
|
|
#endif /* _LINUX_SCHED_TASK_H */
|