diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2023-10-31 02:12:15 +0300 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2023-10-31 02:12:15 +0300 |
commit | 63ce50fff9240d66cf3b59663f458f55ba6dcfcc (patch) | |
tree | c2613289116d6f80a50f534e9c5e4afc26064574 /include/linux/sched | |
parent | 3cf3fabccb9dc821ffaec3ad6bf0cd6b278bd012 (diff) | |
parent | 984ffb6a4366752c949f7b39640aecdce222607f (diff) | |
download | linux-63ce50fff9240d66cf3b59663f458f55ba6dcfcc.tar.xz |
Merge tag 'sched-core-2023-10-28' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull scheduler updates from Ingo Molnar:
"Fair scheduler (SCHED_OTHER) improvements:
- Remove the old and now unused SIS_PROP code & option
- Scan cluster before LLC in the wake-up path
- Use candidate prev/recent_used CPU if scanning failed for cluster
wakeup
NUMA scheduling improvements:
- Improve the VMA access-PID code to better skip/scan VMAs
- Extend tracing to cover VMA-skipping decisions
- Improve/fix the recently introduced sched_numa_find_nth_cpu() code
- Generalize numa_map_to_online_node()
Energy scheduling improvements:
- Remove the EM_MAX_COMPLEXITY limit
- Add tracepoints to track energy computation
- Make the behavior of the 'sched_energy_aware' sysctl more
consistent
- Consolidate and clean up access to a CPU's max compute capacity
- Fix uclamp code corner cases
RT scheduling improvements:
- Drive dl_rq->overloaded with dl_rq->pushable_dl_tasks updates
- Drive the ->rto_mask with rt_rq->pushable_tasks updates
Scheduler scalability improvements:
- Rate-limit updates to tg->load_avg
- On x86 disable IBRS when CPU is offline to improve single-threaded
performance
- Micro-optimize in_task() and in_interrupt()
- Micro-optimize the PSI code
- Avoid updating PSI triggers and ->rtpoll_total when there are no
state changes
Core scheduler infrastructure improvements:
- Use saved_state to reduce some spurious freezer wakeups
- Bring in a handful of fast-headers improvements to scheduler
headers
- Make the scheduler UAPI headers more widely usable by user-space
- Simplify the control flow of scheduler syscalls by using lock
guards
- Fix sched_setaffinity() vs. CPU hotplug race
Scheduler debuggability improvements:
- Disallow writing invalid values to sched_rt_period_us
- Fix a race in the rq-clock debugging code triggering warnings
- Fix a warning in the bandwidth distribution code
- Micro-optimize in_atomic_preempt_off() checks
- Enforce that the tasklist_lock is held in for_each_thread()
- Print the TGID in sched_show_task()
- Remove the /proc/sys/kernel/sched_child_runs_first sysctl
... and misc cleanups & fixes"
* tag 'sched-core-2023-10-28' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (82 commits)
sched/fair: Remove SIS_PROP
sched/fair: Use candidate prev/recent_used CPU if scanning failed for cluster wakeup
sched/fair: Scan cluster before scanning LLC in wake-up path
sched: Add cpus_share_resources API
sched/core: Fix RQCF_ACT_SKIP leak
sched/fair: Remove unused 'curr' argument from pick_next_entity()
sched/nohz: Update comments about NEWILB_KICK
sched/fair: Remove duplicate #include
sched/psi: Update poll => rtpoll in relevant comments
sched: Make PELT acronym definition searchable
sched: Fix stop_one_cpu_nowait() vs hotplug
sched/psi: Bail out early from irq time accounting
sched/topology: Rename 'DIE' domain to 'PKG'
sched/psi: Delete the 'update_total' function parameter from update_triggers()
sched/psi: Avoid updating PSI triggers and ->rtpoll_total when there are no state changes
sched/headers: Remove comment referring to rq::cpu_load, since this has been removed
sched/numa: Complete scanning of inactive VMAs when there is no alternative
sched/numa: Complete scanning of partial VMAs regardless of PID activity
sched/numa: Move up the access pid reset logic
sched/numa: Trace decisions related to skipping VMAs
...
Diffstat (limited to 'include/linux/sched')
-rw-r--r-- | include/linux/sched/deadline.h | 4 | ||||
-rw-r--r-- | include/linux/sched/numa_balancing.h | 10 | ||||
-rw-r--r-- | include/linux/sched/sd_flags.h | 7 | ||||
-rw-r--r-- | include/linux/sched/signal.h | 3 | ||||
-rw-r--r-- | include/linux/sched/smt.h | 2 | ||||
-rw-r--r-- | include/linux/sched/topology.h | 10 | ||||
-rw-r--r-- | include/linux/sched/types.h | 2 | ||||
-rw-r--r-- | include/linux/sched/vhost_task.h | 7 |
8 files changed, 35 insertions, 10 deletions
diff --git a/include/linux/sched/deadline.h b/include/linux/sched/deadline.h index 7c83d4d5a971..df3aca89d4f5 100644 --- a/include/linux/sched/deadline.h +++ b/include/linux/sched/deadline.h @@ -1,4 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_SCHED_DEADLINE_H +#define _LINUX_SCHED_DEADLINE_H /* * SCHED_DEADLINE tasks has negative priorities, reflecting @@ -34,3 +36,5 @@ extern void dl_add_task_root_domain(struct task_struct *p); extern void dl_clear_root_domain(struct root_domain *rd); #endif /* CONFIG_SMP */ + +#endif /* _LINUX_SCHED_DEADLINE_H */ diff --git a/include/linux/sched/numa_balancing.h b/include/linux/sched/numa_balancing.h index 3988762efe15..b69afb8630db 100644 --- a/include/linux/sched/numa_balancing.h +++ b/include/linux/sched/numa_balancing.h @@ -15,6 +15,16 @@ #define TNF_FAULT_LOCAL 0x08 #define TNF_MIGRATE_FAIL 0x10 +enum numa_vmaskip_reason { + NUMAB_SKIP_UNSUITABLE, + NUMAB_SKIP_SHARED_RO, + NUMAB_SKIP_INACCESSIBLE, + NUMAB_SKIP_SCAN_DELAY, + NUMAB_SKIP_PID_INACTIVE, + NUMAB_SKIP_IGNORE_PID, + NUMAB_SKIP_SEQ_COMPLETED, +}; + #ifdef CONFIG_NUMA_BALANCING extern void task_numa_fault(int last_node, int node, int pages, int flags); extern pid_t task_numa_group_id(struct task_struct *p); diff --git a/include/linux/sched/sd_flags.h b/include/linux/sched/sd_flags.h index fad77b5172e2..a8b28647aafc 100644 --- a/include/linux/sched/sd_flags.h +++ b/include/linux/sched/sd_flags.h @@ -110,6 +110,13 @@ SD_FLAG(SD_ASYM_CPUCAPACITY_FULL, SDF_SHARED_PARENT | SDF_NEEDS_GROUPS) SD_FLAG(SD_SHARE_CPUCAPACITY, SDF_SHARED_CHILD | SDF_NEEDS_GROUPS) /* + * Domain members share CPU cluster (LLC tags or L2 cache) + * + * NEEDS_GROUPS: Clusters are shared between groups. + */ +SD_FLAG(SD_CLUSTER, SDF_NEEDS_GROUPS) + +/* * Domain members share CPU package resources (i.e. caches) * * SHARED_CHILD: Set from the base domain up until spanned CPUs no longer share diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h index 0014d3adaf84..9610bad018a3 100644 --- a/include/linux/sched/signal.h +++ b/include/linux/sched/signal.h @@ -656,7 +656,8 @@ extern bool current_is_single_threaded(void); while ((t = next_thread(t)) != g) #define __for_each_thread(signal, t) \ - list_for_each_entry_rcu(t, &(signal)->thread_head, thread_node) + list_for_each_entry_rcu(t, &(signal)->thread_head, thread_node, \ + lockdep_is_held(&tasklist_lock)) #define for_each_thread(p, t) \ __for_each_thread((p)->signal, t) diff --git a/include/linux/sched/smt.h b/include/linux/sched/smt.h index 59d3736c454c..fb1e295e7e63 100644 --- a/include/linux/sched/smt.h +++ b/include/linux/sched/smt.h @@ -17,4 +17,4 @@ static inline bool sched_smt_active(void) { return false; } void arch_smt_update(void); -#endif +#endif /* _LINUX_SCHED_SMT_H */ diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h index 67b573d5bf28..de545ba85218 100644 --- a/include/linux/sched/topology.h +++ b/include/linux/sched/topology.h @@ -45,7 +45,7 @@ static inline int cpu_smt_flags(void) #ifdef CONFIG_SCHED_CLUSTER static inline int cpu_cluster_flags(void) { - return SD_SHARE_PKG_RESOURCES; + return SD_CLUSTER | SD_SHARE_PKG_RESOURCES; } #endif @@ -109,8 +109,6 @@ struct sched_domain { u64 max_newidle_lb_cost; unsigned long last_decay_max_lb_cost; - u64 avg_scan_cost; /* select_idle_sibling */ - #ifdef CONFIG_SCHEDSTATS /* load_balance() stats */ unsigned int lb_count[CPU_MAX_IDLE_TYPES]; @@ -179,6 +177,7 @@ cpumask_var_t *alloc_sched_domains(unsigned int ndoms); void free_sched_domains(cpumask_var_t doms[], unsigned int ndoms); bool cpus_share_cache(int this_cpu, int that_cpu); +bool cpus_share_resources(int this_cpu, int that_cpu); typedef const struct cpumask *(*sched_domain_mask_f)(int cpu); typedef int (*sched_domain_flags_f)(void); @@ -232,6 +231,11 @@ static inline bool cpus_share_cache(int this_cpu, int that_cpu) return true; } +static inline bool cpus_share_resources(int this_cpu, int that_cpu) +{ + return true; +} + #endif /* !CONFIG_SMP */ #if defined(CONFIG_ENERGY_MODEL) && defined(CONFIG_CPU_FREQ_GOV_SCHEDUTIL) diff --git a/include/linux/sched/types.h b/include/linux/sched/types.h index 3c3e049224ae..969aaf5ef9d6 100644 --- a/include/linux/sched/types.h +++ b/include/linux/sched/types.h @@ -20,4 +20,4 @@ struct task_cputime { unsigned long long sum_exec_runtime; }; -#endif +#endif /* _LINUX_SCHED_TYPES_H */ diff --git a/include/linux/sched/vhost_task.h b/include/linux/sched/vhost_task.h index 837a23624a66..bc60243d43b3 100644 --- a/include/linux/sched/vhost_task.h +++ b/include/linux/sched/vhost_task.h @@ -1,7 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _LINUX_VHOST_TASK_H -#define _LINUX_VHOST_TASK_H - +#ifndef _LINUX_SCHED_VHOST_TASK_H +#define _LINUX_SCHED_VHOST_TASK_H struct vhost_task; @@ -11,4 +10,4 @@ void vhost_task_start(struct vhost_task *vtsk); void vhost_task_stop(struct vhost_task *vtsk); void vhost_task_wake(struct vhost_task *vtsk); -#endif +#endif /* _LINUX_SCHED_VHOST_TASK_H */ |