diff options
| author | Linus Torvalds <torvalds@linux-foundation.org> | 2019-07-08 16:39:53 -0700 |
|---|---|---|
| committer | Linus Torvalds <torvalds@linux-foundation.org> | 2019-07-08 16:39:53 -0700 |
| commit | dad1c12ed831a7a89cc01e5582cd0b81a4be7f19 (patch) | |
| tree | 7a84799d3108bd9d3f1d4b530afd3ff9300db982 | |
| parent | 090bc5a2a91499c1fd64b78d125daa6ca5531d38 (diff) | |
| parent | af24bde8df2029f067dc46aff0393c8f18ff6e2f (diff) | |
| download | linux-dad1c12ed831a7a89cc01e5582cd0b81a4be7f19.tar.bz2 | |
Merge branch 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull scheduler updates from Ingo Molnar:
- Remove the unused per rq load array and all its infrastructure, by
Dietmar Eggemann.
- Add utilization clamping support by Patrick Bellasi. This is a
refinement of the energy aware scheduling framework with support for
boosting of interactive and capping of background workloads: to make
sure critical GUI threads get maximum frequency ASAP, and to make
sure background processing doesn't unnecessarily move to cpufreq
governor to higher frequencies and less energy efficient CPU modes.
- Add the bare minimum of tracepoints required for LISA EAS regression
testing, by Qais Yousef - which allows automated testing of various
power management features, including energy aware scheduling.
- Restructure the former tsk_nr_cpus_allowed() facility that the -rt
kernel used to modify the scheduler's CPU affinity logic such as
migrate_disable() - introduce the task->cpus_ptr value instead of
taking the address of &task->cpus_allowed directly - by Sebastian
Andrzej Siewior.
- Misc optimizations, fixes, cleanups and small enhancements - see the
Git log for details.
* 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (33 commits)
sched/uclamp: Add uclamp support to energy_compute()
sched/uclamp: Add uclamp_util_with()
sched/cpufreq, sched/uclamp: Add clamps for FAIR and RT tasks
sched/uclamp: Set default clamps for RT tasks
sched/uclamp: Reset uclamp values on RESET_ON_FORK
sched/uclamp: Extend sched_setattr() to support utilization clamping
sched/core: Allow sched_setattr() to use the current policy
sched/uclamp: Add system default clamps
sched/uclamp: Enforce last task's UCLAMP_MAX
sched/uclamp: Add bucket local max tracking
sched/uclamp: Add CPU's clamp buckets refcounting
sched/fair: Rename weighted_cpuload() to cpu_runnable_load()
sched/debug: Export the newly added tracepoints
sched/debug: Add sched_overutilized tracepoint
sched/debug: Add new tracepoint to track PELT at se level
sched/debug: Add new tracepoints to track PELT at rq level
sched/debug: Add a new sched_trace_*() helper functions
sched/autogroup: Make autogroup_path() always available
sched/wait: Deduplicate code with do-while
sched/topology: Remove unused 'sd' parameter from arch_scale_cpu_capacity()
...
49 files changed, 1216 insertions, 618 deletions
diff --git a/Documentation/scheduler/sched-pelt.c b/Documentation/scheduler/sched-pelt.c index e4219139386a..7238b355919c 100644 --- a/Documentation/scheduler/sched-pelt.c +++ b/Documentation/scheduler/sched-pelt.c @@ -20,7 +20,8 @@ void calc_runnable_avg_yN_inv(void) int i; unsigned int x; - printf("static const u32 runnable_avg_yN_inv[] = {"); + /* To silence -Wunused-but-set-variable warnings. */ + printf("static const u32 runnable_avg_yN_inv[] __maybe_unused = {"); for (i = 0; i < HALFLIFE; i++) { x = ((1UL<<32)-1)*pow(y, i); diff --git a/arch/arm/kernel/topology.c b/arch/arm/kernel/topology.c index 60e375ce1ab2..d17cb1e6d679 100644 --- a/arch/arm/kernel/topology.c +++ b/arch/arm/kernel/topology.c @@ -169,7 +169,7 @@ static void update_cpu_capacity(unsigned int cpu) topology_set_cpu_scale(cpu, cpu_capacity(cpu) / middle_capacity); pr_info("CPU%u: update cpu_capacity %lu\n", - cpu, topology_get_cpu_scale(NULL, cpu)); + cpu, topology_get_cpu_scale(cpu)); } #else diff --git a/arch/ia64/kernel/mca.c b/arch/ia64/kernel/mca.c index 6a52d761854b..79190d877fa7 100644 --- a/arch/ia64/kernel/mca.c +++ b/arch/ia64/kernel/mca.c @@ -1831,7 +1831,7 @@ format_mca_init_stack(void *mca_data, unsigned long offset, ti->cpu = cpu; p->stack = ti; p->state = TASK_UNINTERRUPTIBLE; - cpumask_set_cpu(cpu, &p->cpus_allowed); + cpumask_set_cpu(cpu, &p->cpus_mask); INIT_LIST_HEAD(&p->tasks); p->parent = p->real_parent = p->group_leader = p; INIT_LIST_HEAD(&p->children); diff --git a/arch/mips/include/asm/switch_to.h b/arch/mips/include/asm/switch_to.h index 0f813bb753c6..09cbe9042828 100644 --- a/arch/mips/include/asm/switch_to.h +++ b/arch/mips/include/asm/switch_to.h @@ -42,7 +42,7 @@ extern struct task_struct *ll_task; * inline to try to keep the overhead down. If we have been forced to run on * a "CPU" with an FPU because of a previous high level of FP computation, * but did not actually use the FPU during the most recent time-slice (CU1 - * isn't set), we undo the restriction on cpus_allowed. + * isn't set), we undo the restriction on cpus_mask. * * We're not calling set_cpus_allowed() here, because we have no need to * force prompt migration - we're already switching the current CPU to a @@ -57,7 +57,7 @@ do { \ test_ti_thread_flag(__prev_ti, TIF_FPUBOUND) && \ (!(KSTK_STATUS(prev) & ST0_CU1))) { \ clear_ti_thread_flag(__prev_ti, TIF_FPUBOUND); \ - prev->cpus_allowed = prev->thread.user_cpus_allowed; \ + prev->cpus_mask = prev->thread.user_cpus_allowed; \ } \ next->thread.emulated_fp = 0; \ } while(0) diff --git a/arch/mips/kernel/mips-mt-fpaff.c b/arch/mips/kernel/mips-mt-fpaff.c index a7c0f97e4b0d..1a08428eedcf 100644 --- a/arch/mips/kernel/mips-mt-fpaff.c +++ b/arch/mips/kernel/mips-mt-fpaff.c @@ -177,7 +177,7 @@ asmlinkage long mipsmt_sys_sched_getaffinity(pid_t pid, unsigned int len, if (retval) goto out_unlock; - cpumask_or(&allowed, &p->thread.user_cpus_allowed, &p->cpus_allowed); + cpumask_or(&allowed, &p->thread.user_cpus_allowed, p->cpus_ptr); cpumask_and(&mask, &allowed, cpu_active_mask); out_unlock: diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c index c52766a5b85f..ac7159263da0 100644 --- a/arch/mips/kernel/traps.c +++ b/arch/mips/kernel/traps.c @@ -891,12 +891,12 @@ static void mt_ase_fp_affinity(void) * restricted the allowed set to exclude any CPUs with FPUs, * we'll skip the procedure. */ - if (cpumask_intersects(¤t->cpus_allowed, &mt_fpu_cpumask)) { + if (cpumask_intersects(¤t->cpus_mask, &mt_fpu_cpumask)) { cpumask_t tmask; current->thread.user_cpus_allowed - = current->cpus_allowed; - cpumask_and(&tmask, ¤t->cpus_allowed, + = current->cpus_mask; + cpumask_and(&tmask, ¤t->cpus_mask, &mt_fpu_cpumask); set_cpus_allowed_ptr(current, &tmask); set_thread_flag(TIF_FPUBOUND); diff --git a/arch/powerpc/platforms/cell/spufs/sched.c b/arch/powerpc/platforms/cell/spufs/sched.c index e56b553de27b..f18d5067cd0f 100644 --- a/arch/powerpc/platforms/cell/spufs/sched.c +++ b/arch/powerpc/platforms/cell/spufs/sched.c @@ -128,7 +128,7 @@ void __spu_update_sched_info(struct spu_context *ctx) * runqueue. The context will be rescheduled on the proper node * if it is timesliced or preempted. */ - cpumask_copy(&ctx->cpus_allowed, ¤t->cpus_allowed); + cpumask_copy(&ctx->cpus_allowed, current->cpus_ptr); /* Save the current cpu id for spu interrupt routing. */ ctx->last_ran = raw_smp_processor_id(); diff --git a/arch/x86/kernel/cpu/resctrl/pseudo_lock.c b/arch/x86/kernel/cpu/resctrl/pseudo_lock.c index 604c0e3bcc83..f68baccc69f0 100644 --- a/arch/x86/kernel/cpu/resctrl/pseudo_lock.c +++ b/arch/x86/kernel/cpu/resctrl/pseudo_lock.c @@ -1503,7 +1503,7 @@ static int pseudo_lock_dev_mmap(struct file *filp, struct vm_area_struct *vma) * may be scheduled elsewhere and invalidate entries in the * pseudo-locked region. */ - if (!cpumask_subset(¤t->cpus_allowed, &plr->d->cpu_mask)) { + if (!cpumask_subset(current->cpus_ptr, &plr->d->cpu_mask)) { mutex_unlock(&rdtgroup_mutex); return -EINVAL; } diff --git a/drivers/base/arch_topology.c b/drivers/base/arch_topology.c index 1739d7e1952a..9b09e31ae82f 100644 --- a/drivers/base/arch_topology.c +++ b/drivers/base/arch_topology.c @@ -43,7 +43,7 @@ static ssize_t cpu_capacity_show(struct device *dev, { struct cpu *cpu = container_of(dev, struct cpu, dev); - return sprintf(buf, "%lu\n", topology_get_cpu_scale(NULL, cpu->dev.id)); + return sprintf(buf, "%lu\n", topology_get_cpu_scale(cpu->dev.id)); } static void update_topology_flags_workfn(struct work_struct *work); @@ -116,7 +116,7 @@ void topology_normalize_cpu_scale(void) / capacity_scale; topology_set_cpu_scale(cpu, capacity); pr_debug("cpu_capacity: CPU%d cpu_capacity=%lu\n", - cpu, topology_get_cpu_scale(NULL, cpu)); + cpu, topology_get_cpu_scale(cpu)); } } @@ -185,7 +185,7 @@ init_cpu_capacity_callback(struct notifier_block *nb, cpumask_andnot(cpus_to_visit, cpus_to_visit, policy->related_cpus); for_each_cpu(cpu, policy->related_cpus) { - raw_capacity[cpu] = topology_get_cpu_scale(NULL, cpu) * + raw_capacity[cpu] = topology_get_cpu_scale(cpu) * policy->cpuinfo.max_freq / 1000UL; capacity_scale = max(raw_capacity[cpu], capacity_scale); } diff --git a/drivers/infiniband/hw/hfi1/affinity.c b/drivers/infiniband/hw/hfi1/affinity.c index 4fe662c3bbc1..c142b23bb401 100644 --- a/drivers/infiniband/hw/hfi1/affinity.c +++ b/drivers/infiniband/hw/hfi1/affinity.c @@ -1038,7 +1038,7 @@ int hfi1_get_proc_affinity(int node) struct hfi1_affinity_node *entry; cpumask_var_t diff, hw_thread_mask, available_mask, intrs_mask; const struct cpumask *node_mask, - *proc_mask = ¤t->cpus_allowed; + *proc_mask = current->cpus_ptr; struct hfi1_affinity_node_list *affinity = &node_affinity; struct cpu_mask_set *set = &affinity->proc; @@ -1046,7 +1046,7 @@ int hfi1_get_proc_affinity(int node) * check whether process/context affinity has already * been set */ - if (cpumask_weight(proc_mask) == 1) { + if (current->nr_cpus_allowed == 1) { hfi1_cdbg(PROC, "PID %u %s affinity set to CPU %*pbl", current->pid, current->comm, cpumask_pr_args(proc_mask)); @@ -1057,7 +1057,7 @@ int hfi1_get_proc_affinity(int node) cpu = cpumask_first(proc_mask); cpumask_set_cpu(cpu, &set->used); goto done; - } else if (cpumask_weight(proc_mask) < cpumask_weight(&set->mask)) { + } else if (current->nr_cpus_allowed < cpumask_weight(&set->mask)) { hfi1_cdbg(PROC, "PID %u %s affinity set to CPU set(s) %*pbl", current->pid, current->comm, cpumask_pr_args(proc_mask)); diff --git a/drivers/infiniband/hw/hfi1/sdma.c b/drivers/infiniband/hw/hfi1/sdma.c index 28b66bd70b74..2395fd4233a7 100644 --- a/drivers/infiniband/hw/hfi1/sdma.c +++ b/drivers/infiniband/hw/hfi1/sdma.c @@ -869,14 +869,13 @@ struct sdma_engine *sdma_select_user_engine(struct hfi1_devdata *dd, { struct sdma_rht_node *rht_node; struct sdma_engine *sde = NULL; - const struct cpumask *current_mask = ¤t->cpus_allowed; unsigned long cpu_id; /* * To ensure that always the same sdma engine(s) will be * selected make sure the process is pinned to this CPU only. */ - if (cpumask_weight(current_mask) != 1) + if (current->nr_cpus_allowed != 1) goto out; cpu_id = smp_processor_id(); diff --git a/drivers/infiniband/hw/qib/qib_file_ops.c b/drivers/infiniband/hw/qib/qib_file_ops.c index 78fa634de98a..27b6e664e59d 100644 --- a/drivers/infiniband/hw/qib/qib_file_ops.c +++ b/drivers/infiniband/hw/qib/qib_file_ops.c @@ -1142,7 +1142,7 @@ static __poll_t qib_poll(struct file *fp, struct poll_table_struct *pt) static void assign_ctxt_affinity(struct file *fp, struct qib_devdata *dd) { struct qib_filedata *fd = fp->private_data; - const unsigned int weight = cpumask_weight(¤t->cpus_allowed); + const unsigned int weight = current->nr_cpus_allowed; const struct cpumask *local_mask = cpumask_of_pcibus(dd->pcidev->bus); int local_cpu; @@ -1623,9 +1623,8 @@ static int qib_assign_ctxt(struct file *fp, const struct qib_user_info *uinfo) ret = find_free_ctxt(i_minor - 1, fp, uinfo); else { int unit; - const unsigned int cpu = cpumask_first(¤t->cpus_allowed); - const unsigned int weight = - cpumask_weight(¤t->cpus_allowed); + const unsigned int cpu = cpumask_first(current->cpus_ptr); + const unsigned int weight = current->nr_cpus_allowed; if (weight == 1 && !test_bit(cpu, qib_cpulist)) if (!find_hca(cpu, &unit) && unit >= 0) diff --git a/fs/proc/array.c b/fs/proc/array.c index 55180501b915..46dcb6f0eccf 100644 --- a/fs/proc/array.c +++ b/fs/proc/array.c @@ -381,9 +381,9 @@ static inline void task_context_switch_counts(struct seq_file *m, static void task_cpus_allowed(struct seq_file *m, struct task_struct *task) { seq_printf(m, "Cpus_allowed:\t%*pb\n", - cpumask_pr_args(&task->cpus_allowed)); + cpumask_pr_args(task->cpus_ptr)); seq_printf(m, "Cpus_allowed_list:\t%*pbl\n", - cpumask_pr_args(&task->cpus_allowed)); + cpumask_pr_args(task->cpus_ptr)); } static inline void task_core_dumping(struct seq_file *m, struct mm_struct *mm) diff --git a/include/linux/arch_topology.h b/include/linux/arch_topology.h index d9bdc1a7f4e7..1cfe05ea1d89 100644 --- a/include/linux/arch_topology.h +++ b/include/linux/arch_topology.h @@ -18,7 +18,7 @@ DECLARE_PER_CPU(unsigned long, cpu_scale); struct sched_domain; static inline -unsigned long topology_get_cpu_scale(struct sched_domain *sd, int cpu) +unsigned long topology_get_cpu_scale(int cpu) { return per_cpu(cpu_scale, cpu); } diff --git a/include/linux/energy_model.h b/include/linux/energy_model.h index aa027f7bcb3e..73f8c3cb9588 100644 --- a/include/linux/energy_model.h +++ b/include/linux/energy_model.h @@ -89,7 +89,7 @@ static inline unsigned long em_pd_energy(struct em_perf_domain *pd, * like schedutil. */ cpu = cpumask_first(to_cpumask(pd->cpus)); - scale_cpu = arch_scale_cpu_capacity(NULL, cpu); + scale_cpu = arch_scale_cpu_capacity(cpu); cs = &pd->table[pd->nr_cap_states - 1]; freq = map_util_freq(max_util, cs->frequency, scale_cpu); diff --git a/include/linux/log2.h b/include/linux/log2.h index 1aec01365ed4..83a4a3ca3e8a 100644 --- a/include/linux/log2.h +++ b/include/linux/log2.h @@ -220,4 +220,38 @@ int __order_base_2(unsigned long n) ilog2((n) - 1) + 1) : \ __order_base_2(n) \ ) + +static inline __attribute__((const)) +int __bits_per(unsigned long n) +{ + if (n < 2) + return 1; + if (is_power_of_2(n)) + return order_base_2(n) + 1; + return order_base_2(n); +} + +/** + * bits_per - calculate the number of bits required for the argument + * @n: parameter + * + * This is constant-capable and can be used for compile time + * initializations, e.g bitfields. + * + * The first few values calculated by this routine: + * bf(0) = 1 + * bf(1) = 1 + * bf(2) = 2 + * bf(3) = 2 + * bf(4) = 3 + * ... and so on. + */ +#define bits_per(n) \ +( \ + __builtin_constant_p(n) ? ( \ + ((n) == 0 || (n) == 1) \ + ? 1 : ilog2(n) + 1 \ + ) : \ + __bits_per(n) \ +) #endif /* _LINUX_LOG2_H */ diff --git a/include/linux/sched.h b/include/linux/sched.h index 76adce49b5ad..459d95e4a574 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -35,6 +35,7 @@ struct audit_context; struct backing_dev_info; struct bio_list; struct blk_plug; +struct capture_control; struct cfs_rq; struct fs_struct; struct futex_pi_state; @@ -47,8 +48,9 @@ struct pid_namespace; struct pipe_inode_info; struct rcu_node; struct reclaim_state; -struct capture_control; struct robust_list_head; +struct root_domain; +struct rq; struct sched_attr; struct sched_param; struct seq_file; @@ -281,6 +283,18 @@ struct vtime { u64 gtime; }; +/* + * Utilization clamp constraints. + * @UCLAMP_MIN: Minimum utilization + * @UCLAMP_MAX: Maximum utilization + * @UCLAMP_CNT: Utilization clamp constraints count + */ +enum uclamp_id { + UCLAMP_MIN = 0, + UCLAMP_MAX, + UCLAMP_CNT +}; + struct sched_info { #ifdef CONFIG_SCHED_INFO /* Cumulative counters: */ @@ -312,6 +326,10 @@ struct sched_info { # define SCHED_FIXEDPOINT_SHIFT 10 # define SCHED_FIXEDPOINT_SCALE (1L << SCHED_FIXEDPOINT_SHIFT) +/* Increase resolution of cpu_capacity calculations */ +# define SCHED_CAPACITY_SHIFT SCHED_FIXEDPOINT_SHIFT +# define SCHED_CAPACITY_SCALE (1L << SCHED_CAPACITY_SHIFT) + struct load_weight { unsigned long weight; u32 inv_weight; @@ -560,6 +578,41 @@ struct sched_dl_entity { struct hrtimer inactive_timer; }; +#ifdef CONFIG_UCLAMP_TASK +/* Number of utilization clamp buckets (shorter alias) */ +#define UCLAMP_BUCKETS CONFIG_UCLAMP_BUCKETS_COUNT + +/* + * Utilization clamp for a scheduling entity + * @value: clamp value "assigned" to a se + * @bucket_id: bucket index corresponding to the "assigned" value + * @active: the se is currently refcounted in a rq's bucket + * @user_defined: the requested clamp value comes from user-space + * + * The bucket_id is the index of the clamp bucket matching the clamp value + * which is pre-computed and stored to avoid expensive integer divisions from + * the fast path. + * + * The active bit is set whenever a task has got an "effective" value assigned, + * which can be different from the clamp value "requested" from user-space. + * This allows to know a task is refcounted in the rq's bucket corresponding + * to the "effective" bucket_id. + * + * The user_defined bit is set whenever a task has got a task-specific clamp + * value requested from userspace, i.e. the system defaults apply to this task + * just as a restriction. This allows to relax default clamps when a less + * restrictive task-specific value has been requested, thus allowing to + * implement a "nice" semantic. For example, a task running with a 20% + * default boost can still drop its own boosting to 0%. + */ +struct uclamp_se { + unsigned int value : bits_per(SCHED_CAPACITY_SCALE); + unsigned int bucket_id : bits_per(UCLAMP_BUCKETS); + unsigned int active : 1; + unsigned int user_defined : 1; +}; +#endif /* CONFIG_UCLAMP_TASK */ + union rcu_special { struct { u8 blocked; @@ -640,6 +693,13 @@ struct task_struct { #endif struct sched_dl_entity dl; +#ifdef CONFIG_UCLAMP_TASK + /* Clamp values requested for a scheduling entity */ + struct uclamp_se uclamp_req[UCLAMP_CNT]; + /* Effective clamp values used for a scheduling entity */ + struct uclamp_se uclamp[UCLAMP_CNT]; +#endif + #ifdef CONFIG_PREEMPT_NOTIFIERS /* List of struct preempt_notifier: */ struct hlist_head preempt_notifiers; @@ -651,7 +711,8 @@ struct task_struct { unsigned int policy; int nr_cpus_allowed; - cpumask_t cpus_allowed; + const cpumask_t *cpus_ptr; + cpumask_t cpus_mask; #ifdef CONFIG_PREEMPT_RCU int rcu_read_lock_nesting; @@ -1399,7 +1460,7 @@ extern struct pid *cad_pid; #define PF_SWAPWRITE 0x00800000 /* Allowed to write to swap */ #define PF_MEMSTALL 0x01000000 /* Stalled due to lack of memory */ #define PF_UMH 0x02000000 /* I'm an Usermodehelper process */ -#define PF_NO_SETAFFINITY 0x04000000 /* Userland is not allowed to meddle with cpus_allowed */ +#define PF_NO_SETAFFINITY 0x04000000 /* Userland is not allowed to meddle with cpus_mask */ #define PF_MCE_EARLY 0x08000000 /* Early kill for mce process policy */ #define PF_MEMALLOC_NOCMA 0x10000000 /* All allocation request will have _GFP_MOVABLE cleared */ #define PF_FREEZER_SKIP 0x40000000 /* Freezer should not count it as freezable */ @@ -1915,4 +1976,16 @@ static inline void rseq_syscall(struct pt_regs *regs) #endif +const struct sched_avg *sched_trace_cfs_rq_avg(struct cfs_rq *cfs_rq); +char *sched_trace_cfs_rq_path(struct cfs_rq *cfs_rq, char *str, int len); +int sched_trace_cfs_rq_cpu(struct cfs_rq *cfs_rq); + +const struct sched_avg *sched_trace_rq_avg_rt(struct rq *rq); +const struct sched_avg *sched_trace_rq_avg_dl(struct rq *rq); +const struct sched_avg *sched_trace_rq_avg_irq(struct rq *rq); + +int sched_trace_rq_cpu(struct rq *rq); + +const struct cpumask *sched_trace_rd_span(struct root_domain *rd); + #endif diff --git a/include/linux/sched/nohz.h b/include/linux/sched/nohz.h index b36f4cf38111..1abe91ff6e4a 100644 --- a/include/linux/sched/nohz.h +++ b/include/linux/sched/nohz.h @@ -7,14 +7,6 @@ */ #if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON) -extern void cpu_load_update_nohz_start(void); -extern void cpu_load_update_nohz_stop(void); -#else -static inline void cpu_load_update_nohz_start(void) { } -static inline void cpu_load_update_nohz_stop(void) { } -#endif - -#if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON) extern void nohz_balance_enter_idle(int cpu); extern int get_nohz_timer_target(void); #else diff --git a/include/linux/sched/sysctl.h b/include/linux/sched/sysctl.h index 99ce6d728df7..d4f6215ee03f 100644 --- a/include/linux/sched/sysctl.h +++ b/include/linux/sched/sysctl.h @@ -56,6 +56,11 @@ int sched_proc_update_handler(struct ctl_table *table, int write, extern unsigned int sysctl_sched_rt_period; extern int sysctl_sched_rt_runtime; +#ifdef CONFIG_UCLAMP_TASK +extern unsigned int sysctl_sched_uclamp_util_min; +extern unsigned int sysctl_sched_uclamp_util_max; +#endif + #ifdef CONFIG_CFS_BANDWIDTH extern unsigned int sysctl_sched_cfs_bandwidth_slice; #endif @@ -75,6 +80,12 @@ extern int sched_rt_handler(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos); +#ifdef CONFIG_UCLAMP_TASK +extern int sysctl_sched_uclamp_handler(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, + loff_t *ppos); +#endif + extern int sysctl_numa_balancing(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos); diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h index cfc0a89a7159..7863bb62d2ab 100644 --- a/include/linux/sched/topology.h +++ b/include/linux/sched/topology.h @@ -7,12 +7,6 @@ #include <linux/sched/idle.h> /* - * Increase resolution of cpu_capacity calculations - */ -#define SCHED_CAPACITY_SHIFT SCHED_FIXEDPOINT_SHIFT -#define SCHED_CAPACITY_SCALE (1L << SCHED_CAPACITY_SHIFT) - -/* * sched-domains (multiprocessor balancing) declarations: */ #ifdef CONFIG_SMP @@ -84,11 +78,6 @@ struct sched_domain { unsigned int busy_factor; /* less balancing by factor if busy */ unsigned int imbalance_pct; /* No balance until over watermark */ unsigned int cache_nice_tries; /* Leave cache hot tasks for # tries */ - unsigned int busy_idx; - unsigned int idle_idx; - unsigned int newidle_idx; - unsigned int wake_idx; - unsigned int forkexec_idx; int nohz_idle; /* NOHZ IDLE status */ int flags; /* See SD_* */ @@ -201,14 +190,6 @@ extern void set_sched_topology(struct sched_domain_topology_level *tl); # define SD_INIT_NAME(type) #endif -#ifndef arch_scale_cpu_capacity -static __always_inline -unsigned long arch_scale_cpu_capacity(struct sched_domain *sd, int cpu) -{ - return SCHED_CAPACITY_SCALE; -} -#endif - #else /* CONFIG_SMP */ struct sched_domain_attr; @@ -224,16 +205,16 @@ static inline bool cpus_share_cache(int this_cpu, int that_cpu) return true; } +#endif /* !CONFIG_SMP */ + #ifndef arch_scale_cpu_capacity static __always_inline -unsigned long arch_scale_cpu_capacity(void __always_unused *sd, int cpu) +unsigned long arch_scale_cpu_capacity(int cpu) { return SCHED_CAPACITY_SCALE; } #endif -#endif /* !CONFIG_SMP */ - static inline int task_node(const struct task_struct *p) { return cpu_to_node(task_cpu(p)); diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h index c8c7c7efb487..420e80e56e55 100644 --- a/include/trace/events/sched.h +++ b/include/trace/events/sched.h @@ -594,6 +594,37 @@ TRACE_EVENT(sched_wake_idle_without_ipi, TP_printk("cpu=%d", __entry->cpu) ); + +/* + * Following tracepoints are not exported in tracefs and provide hooking + * mechanisms only for testing and debugging purposes. + * + * Postfixed with _tp to make them easily identifiable in the code. + */ +DECLARE_TRACE(pelt_cfs_tp, + TP_PROTO(struct cfs_rq *cfs_rq), + TP_ARGS(cfs_rq)); + +DECLARE_TRACE(pelt_rt_tp, + TP_PROTO(struct rq *rq), + TP_ARGS(rq)); + +DECLARE_TRACE(pelt_dl_tp, + TP_PROTO(struct rq *rq), + TP_ARGS(rq)); + +DECLARE_TRACE(pelt_irq_tp, + TP_PROTO(struct rq *rq), + TP_ARGS(rq)); + +DECLARE_TRACE(pelt_se_tp, + TP_PROTO(struct sched_entity *se), + TP_ARGS(se)); + +DECLARE_TRACE(sched_overutilized_tp, + TP_PROTO(struct root_domain *rd, bool overutilized), + TP_ARGS(rd, overutilized)); + #endif /* _TRACE_SCHED_H */ /* This part must be outside protection */ diff --git a/include/uapi/linux/sched.h b/include/uapi/linux/sched.h index ed4ee170bee2..617bb59aa8ba 100644 --- a/include/uapi/linux/sched.h +++ b/include/uapi/linux/sched.h @@ -51,9 +51,21 @@ #define SCHED_FLAG_RESET_ON_FORK 0x01 #define SCHED_FLAG_RECLAIM 0x02 #define SCHED_FLAG_DL_OVERRUN 0x04 +#define SCHED_FLAG_KEEP_POLICY 0x08 +#define SCHED_FLAG_KEEP_PARAMS 0x10 +#define SCHED_FLAG_UTIL_CLAMP_MIN 0x20 +#define SCHED_FLAG_UTIL_CLAMP_MAX 0x40 + +#define SCHED_FLAG_KEEP_ALL (SCHED_FLAG_KEEP_POLICY | \ + SCHED_FLAG_KEEP_PARAMS) + +#define SCHED_FLAG_UTIL_CLAMP (SCHED_FLAG_UTIL_CLAMP_MIN | \ + SCHED_FLAG_UTIL_CLAMP_MAX) #define SCHED_FLAG_ALL (SCHED_FLAG_RESET_ON_FORK | \ SCHED_FLAG_RECLAIM | \ - SCHED_FLAG_DL_OVERRUN) + SCHED_FLAG_DL_OVERRUN | \ + SCHED_FLAG_KEEP_ALL | \ + SCHED_FLAG_UTIL_CLAMP) #endif /* _UAPI_LINUX_SCHED_H */ diff --git a/include/uapi/linux/sched/types.h b/include/uapi/linux/sched/types.h index 10fbb8031930..c852153ddb0d 100644 --- a/include/uapi/linux/sched/types.h +++ b/include/uapi/linux/sched/types.h @@ -9,6 +9,7 @@ struct sched_param { }; #define SCHED_ATTR_SIZE_VER0 48 /* sizeof first published struct */ +#define SCHED_ATTR_SIZE_VER1 56 /* add: util_{min,max} */ /* * Extended scheduling parameters data structure. @@ -21,8 +22,33 @@ struct sched_param { * the tasks may be useful for a wide variety of application fields, e.g., * multimedia, streaming, automation and control, and many others. * - * This variant (sched_attr) is meant at describing a so-called - * sporadic time-constrained task. In such model a task is specified by: + * This variant (sched_attr) allows to define additional attributes to + * improve the scheduler knowledge about task requirements. + * + * Scheduling Class Attributes + * =========================== + * + * A subset of sched_attr attributes specifies the + * scheduling policy and relative POSIX attributes: + * + * @size size of the structure, for fwd/bwd compat. + * + * @sched_policy task's scheduling policy + * @sched_nice task's nice value (SCHED_NORMAL/BATCH) + * @sched_priority task's static priority (SCHED_FIFO/RR) + * + * Certain more advanced scheduling features can be controlled by a + * predefined set of flags via the attribute: + * + * @sched_flags for customizing the scheduler behaviour + * + * Sporadic Time-Constrained Task Attributes + * ========================================= + * + * A subset of sched_attr attributes allows to describe a so-called + * sporadic time-constrained task. + * + * In such a model a task is specified by: * - the activation period or minimum instance inter-arrival time; * - the maximum (or average, depending on the actual scheduling * discipline) computation time of all instances, a.k.a. runtime; @@ -34,14 +60,8 @@ struct sched_param { * than the runtime and must be completed by time instant t equal to * the instance activation time + the deadline. * - * This is reflected by the actual fields of the sched_attr structure: + * This is reflected by the following fields of the sched_attr structure: * - * @size size of the structure, for fwd/bwd compat. - * - * @sched_policy task's scheduling policy - * @sched_flags for customizing the scheduler behaviour - * @sched_nice task's nice value (SCHED_NORMAL/BATCH) - * @sched_priority task's static priority (SCHED_FIFO/RR) * @sched_deadline representative of the task's deadline * @sched_runtime representative of the task's runtime * @sched_period representative of the task's period @@ -53,6 +73,29 @@ struct sched_param { * As of now, the SCHED_DEADLINE policy (sched_dl scheduling class) is the * only user of this new interface. More information about the algorithm * available in the scheduling class file or in Documentation/. + * + * Task Utilization Attributes + * =========================== + * + * A subset of sched_attr attributes allows to specify the utilization + * expected for a task. These attributes allow to inform the scheduler about + * the utilization boundaries within which it should schedule the task. These + * boundaries are valuable hints to support scheduler decisions on both task + * placement and frequency selection. + * + * @sched_util_min represents the minimum utilization + * @sched_util_max represents the maximum utilization + * + * Utilization is a value in the range [0..SCHED_CAPACITY_SCALE]. It + * represents the percentage of CPU time used by a task when running at the + * maximum frequency on the highest capacity CPU of the system. For example, a + * 20% utilization task is a task running for 2ms every 10ms at maximum + * frequency. + * + * A task with a min utilization value bigger than 0 is more likely scheduled + * on a CPU with a capacity big enough to fit the specified value. + * A task with a max utilization value smaller than 1024 is more likely + * scheduled on a CPU with no more capacity than the specified value. */ struct sched_attr { __u32 size; @@ -70,6 +113,11 @@ struct sched_attr { __u64 sched_runtime; __u64 sched_deadline; __u64 sched_period; + + /* Utilization hints */ + __u32 sched_util_min; + __u32 sched_util_max; + }; #endif /* _UAPI_LINUX_SCHED_TYPES_H */ diff --git a/init/Kconfig b/init/Kconfig index 0e2344389501..c88289c18d59 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -677,6 +677,59 @@ config HAVE_UNSTABLE_SCHED_CLOCK config GENERIC_SCHED_CLOCK bool +menu "Scheduler features" + +config UCLAMP_TASK + bool "Enable utilization clamping for RT/FAIR tasks" + depends on CPU_FREQ_GOV_SCHEDUTIL + help + This feature enables the scheduler to track the clamped utilization + of each CPU based on RUNNABLE tasks scheduled on that CPU. + + With this option, the user can specify the min and max CPU + utilization allowed for RUNNABLE tasks. The max utilization defines + the maximum frequency a task should use while the min utilization + defines the minimum frequency it should use. + + Both min and max utilization clamp values are hints to the scheduler, + aiming at improving its frequency selection policy, but they do not + enforce or grant any specific bandwidth for tasks. + + If in doubt, say N. + +config UCLAMP_BUCKETS_COUNT + int "Number of supported utilization clamp buckets" + range 5 20 + default 5 + depends on UCLAMP_TASK + help + Defines the number of clamp buckets to use. The range of each bucket + will be SCHED_CAPACITY_SCALE/UCLAMP_BUCKETS_COUNT. The higher the + number of clamp buckets the finer their granularity and the higher + the precision of clamping aggregation and tracking at run-time. + + For example, with the minimum configuration value we will have 5 + clamp buckets tracking 20% utilization each. A 25% boosted tasks will + be refcounted in the [20..39]% bucket and will set the bucket clamp + effective value to 25%. + If a second 30% boosted task should be co-scheduled on the same CPU, + that task will be refcounted in the same bucket of the first task and + it will boost the bucket clamp effective value to 30%. + The clamp effective value of a bucket is reset to its nominal value + (20% in the example above) when there are no more tasks refcounted in + that bucket. + + An additional boost/capping margin can be added to some tasks. In the + example above the 25% task will be boosted to 30% until it exits the + CPU. If that should be considered not acceptable on certain systems, + it's always possible to reduce the margin by increasing the number of + clamp buckets to trade off used memory for run-time tracking + precision. + + If in doubt, use the default value. + +endmenu + # # For architectures that want to enable the support for NUMA-affine scheduler # balancing logic: diff --git a/init/init_task.c b/init/init_task.c index afa6ad795355..7ab773b9b3cd 100644 --- a/init/init_task.c +++ b/init/init_task.c @@ -72,7 +72,8 @@ struct task_struct init_task .static_prio = MAX_PRIO - 20, .normal_prio = MAX_PRIO - 20, .policy = SCHED_NORMAL, - .cpus_allowed = CPU_MASK_ALL, + .cpus_ptr = &init_task.cpus_mask, + .cpus_mask = CPU_MASK_ALL, .nr_cpus_allowed= NR_CPUS, .mm = NULL, .active_mm = &init_mm, diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index 515525ff1cfd..a1590e244f5f 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -2829,7 +2829,7 @@ static void cpuset_fork(struct task_struct *task) if (task_css_is_root(task, cpuset_cgrp_id)) return; - set_cpus_allowed_ptr(task, ¤t->cpus_allowed); + set_cpus_allowed_ptr(task, current->cpus_ptr); task->mems_allowed = current->mems_allowed; } diff --git a/kernel/fork.c b/kernel/fork.c index d18e343d4aab..847dd147b068 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -898,6 +898,8 @@ static struct task_struct *dup_task_struct(struct task_struct *orig, int node) #ifdef CONFIG_STACKPROTECTOR tsk->stack_canary = get_random_canary(); #endif + if (orig->cpus_ptr == &orig->cpus_mask) + tsk->cpus_ptr = &tsk->cpus_mask; /* * One for us, one for whoever does the "release_task()" (usually diff --git a/kernel/power/energy_model.c b/kernel/power/energy_model.c index 7d66ee68aaaf..0a9326f5f421 100644 --- a/kernel/power/energy_model.c +++ b/kernel/power/energy_model.c @@ -223,7 +223,7 @@ int em_register_perf_domain(cpumask_t *span, unsigned int nr_states, * All CPUs of a domain must have the same micro-architecture * since they all share the same table. */ - cap = arch_scale_cpu_capacity(NULL, cpu); + cap = arch_scale_cpu_capacity(cpu); if (prev_cap && prev_cap != cap) { pr_err("CPUs of %*pbl must have the same capacity\n", cpumask_pr_args(span)); diff --git a/kernel/sched/autogroup.c b/kernel/sched/autogroup.c index 2d4ff5353ded..2067080bb235 100644 --- a/kernel/sched/autogroup.c +++ b/kernel/sched/autogroup.c @@ -259,7 +259,6 @@ out: } #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)) @@ -267,4 +266,3 @@ int autogroup_path(struct task_group *tg, char *buf, int buflen) return snprintf(buf, buflen, "%s-%ld", "/autogroup", tg->autogroup->id); } -#endif diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 874c427742a9..fa43ce3962e7 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -23,6 +23,17 @@ #define CREATE_TRACE_POINTS #include <trace/events/sched.h> +/* + * Export tracepoints that act as a bare tracehook (ie: have no trace event + * associated with them) to allow external modules to probe them. + */ +EXPORT_TRACEPOINT_SYMBOL_GPL(pelt_cfs_tp); +EXPORT_TRACEPOINT_SYMBOL_GPL(pelt_rt_tp); +EXPORT_TRACEPOINT_SYMBOL_GPL(pelt_dl_tp); +EXPORT_TRACEPOINT_SYMBOL_GPL(pelt_irq_tp); +EXPORT_TRACEPOINT_SYMBOL_GPL(pelt_se_tp); +EXPORT_TRACEPOINT_SYMBOL_GPL(sched_overutilized_tp); + DEFINE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues); #if defined(CONFIG_SCHED_DEBUG) && defined(CONFIG_JUMP_LABEL) @@ -761,6 +772,401 @@ static void set_load_weight(struct task_struct *p, bool update_load) } } +#ifdef CONFIG_UCLAMP_TASK +/* Max allowed minimum utilization */ +unsigned int sysctl_sched_uclamp_util_min = SCHED_CAPACITY_SCALE; + +/* Max allowed maximum utilization */ +unsigned int sysctl_sched_uclamp_util_max = SCHED_CAPACITY_SCALE; + +/* All clamps are required to be less or equal than these values */ +static struct uclamp_se uclamp_default[UCLAMP_CNT]; + +/* Integer rounded range for each bucket */ +#define UCLAMP_BUCKET_DELTA DIV_ROUND_CLOSEST(SCHED_CAPACITY_SCALE, UCLAMP_BUCKETS) + +#define for_each_clamp_id(clamp_id) \ + for ((clamp_id) = 0; (clamp_id) < UCLAMP_CNT; (clamp_id)++) + +static inline unsigned int uclamp_bucket_id(unsigned int clamp_value) +{ + return clamp_value / UCLAMP_BUCKET_DELTA; +} + +static inline unsigned int uclamp_bucket_base_value(unsigned int clamp_value) +{ + return UCLAMP_BUCKET_DELTA * uclamp_bucket_id(clamp_value); +} + +static inline unsigned int uclamp_none(int clamp_id) +{ + if (clamp_id == UCLAMP_MIN) + return 0; + return SCHED_CAPACITY_SCALE; +} + +static inline void uclamp_se_set(struct uclamp_se *uc_se, + unsigned int value, bool user_defined) +{ + uc_se->value = value; + uc_se->bucket_id = uclamp_bucket_id(value); + uc_se->user_defined = user_defined; +} + +static inline unsigned int +uclamp_idle_value(struct rq *rq, unsigned int clamp_id, + unsigned int clamp_value) +{ + /* + * Avoid blocked utilization pushing up the frequency when we go + * idle (which drops the max-clamp) by retaining the last known + * max-clamp. + */ + if (clamp_id == UCLAMP_MAX) { + rq->uclamp_flags |= UCLAMP_FLAG_IDLE; + return clamp_value; + } + + return uclamp_none(UCLAMP_MIN); +} + +static inline void uclamp_idle_reset(struct rq *rq, unsigned int clamp_id, + unsigned int clamp_value) +{ + /* Reset max-clamp retention only on idle exit */ + if (!(rq->uclamp_flags & UCLAMP_FLAG_IDLE)) + return; + + WRITE_ONCE(rq->uclamp[clamp_id].value, clamp_value); +} + +static inline +unsigned int uclamp_rq_max_value(struct rq *rq, unsigned int clamp_id, + unsigned int clamp_value) +{ + struct uclamp_bucket *bucket = rq->uclamp[clamp_id].bucket; + int bucket_id = UCLAMP_BUCKETS - 1; + + /* + * Since both min and max clamps are max aggregated, find the + * top most bucket with tasks in. + */ + for ( ; bucket_id >= 0; bucket_id--) { + if (!bucket[bucket_id].tasks) + continue; + return bucket[bucket_id].value; + } + + /* No tasks -- default clamp values */ + return uclamp_idle_value(rq, clamp_id, clamp_value); +} + +/* + * The effective clamp bucket index of a task depends on, by increasing + * priority: + * - the task specific clamp value, when explicitly requested from userspace + * - the system default clamp value, defined by the sysadmin + */ +static inline struct uclamp_se +uclamp_eff_get(struct task_struct *p, unsigned int clamp_id) +{ + struct uclamp_se uc_req = p->uclamp_req[clamp_id]; + struct uclamp_se uc_max = uclamp_default[clamp_id]; + + /* System default restrictions always apply */ + if (unlikely(uc_req.value > uc_max.value)) + return uc_max; + + return uc_req; +} + +unsigned int uclamp_eff_value(struct task_struct *p, unsigned int clamp_id) +{ + struct uclamp_se uc_eff; + + /* Task currently refcounted: use back-annotated (effective) value */ + if (p->uclamp[clamp_id].active) + return p->uclamp[clamp_id].value; + + uc_eff = uclamp_eff_get(p, clamp_id); + + return uc_eff.value; +} + +/* + * When a task is enqueued on a rq, the clamp bucket currently defined by the + * task's uclamp::bucket_id is refcounted on that rq. This also immediately + * updates the rq's clamp value if required. + * + * Tasks can have a task-specific value requested from user-space, track + * within each bucket the maximum value for tasks refcounted in it. + * This "local max aggregation" allows to track the exact "requested" value + * for each bucket when all its RUNNABLE tasks require the same clamp. + */ +static inline void uclamp_rq_inc_id(struct rq *rq, struct task_struct *p, + unsigned int clamp_id) +{ + struct uclamp_rq *uc_rq = &rq->uclamp[clamp_id]; + struct uclamp_se *uc_se = &p->uclamp[clamp_id]; + struct uclamp_bucket *bucket; + + lockdep_assert_held(&rq->lock); + + /* Update task effective clamp */ + p->uclamp[clamp_id] = uclamp_eff_get(p, clamp_id); + + bucket = &uc_rq->bucket[uc_se->bucket_id]; + bucket->tasks++; + uc_se->active = true; + + uclamp_idle_reset(rq, clamp_id, uc_se->value); + + /* + * Local max aggregation: rq buckets always track the max + * "requested" clamp value of its RUNNABLE tasks. + */ + if (bucket->tasks == 1 || uc_se->value > bucket->value) + bucket->value = uc_se->value; + + if (uc_se->value > READ_ONCE(uc_rq->value)) + WRITE_ONCE(uc_rq->value, uc_se->value); +} + +/* + * When a task is dequeued from a rq, the clamp bucket refcounted by the task + * is released. If this is the last task reference counting the rq's max + * active clamp value, then the rq's clamp value is updated. + * + * Both refcounted tasks and rq's cached clamp values are expected to be + * always valid. If it's detected they are not, as defensive programming, + * enforce the expected state and warn. + */ +static inline void uclamp_rq_dec_id(struct rq *rq, struct task_struct *p, + unsigned int clamp_id) +{ + struct uclamp_rq *uc_rq = &rq->uclamp[clamp_id]; + struct uclamp_se *uc_se = &p->uclamp[clamp_id]; + struct uclamp_bucket *bucket; + unsigned int bkt_clamp; + unsigned int rq_clamp; + + lockdep_assert_held(&rq->lock); + + bucket = &uc_rq->bucket[uc_se->bucket_id]; + SCHED_WARN_ON(!bucket->tasks); + if (likely(bucket->tasks)) + bucket->tasks--; + uc_se->active = false; + + /* + * Keep "local max aggregation" simple and accept to (possibly) + * overboost some RUNNABLE tasks in the same bucket. + * The rq clamp bucket value is reset to its base value whenever + * there are no more RUNNABLE tasks refcounting it. + */ + if (likely(bucket->tasks)) + return; + + rq_clamp = READ_ONCE(uc_rq->value); + /* + * Defensive programming: this should never happen. If it happens, + * e.g. due to future modification, warn and fixup the expected value. + */ + SCHED_WARN_ON(bucket->value > rq_clamp); + if (bucket->value >= rq_clamp) { + bkt_clamp = uclamp_rq_max_value(rq, clamp_id, uc_se->value); + WRITE_ONCE(uc_rq->value, bkt_clamp); + } +} + +static inline void uclamp_rq_inc(struct rq *rq, struct task_struct *p) +{ + unsigned int clamp_id; + + if (unlikely(!p->sched_class->uclamp_enabled)) + return; + + for_each_clamp_id(clamp_id) + uclamp_rq_inc_id(rq, p, clamp_id); + + /* Reset clamp idle holding when there is one RUNNABLE task */ + if (rq->uclamp_flags & UCLAMP_FLAG_IDLE) + rq->uclamp_flags &= ~UCLAMP_FLAG_IDLE; +} + +static inline void uclamp_rq_dec(struct rq *rq, struct task_struct *p) +{ + unsigned int clamp_id; + + if (unlikely(!p->sched_class->uclamp_enabled)) + return; + + for_each_clamp_id(clamp_id) + uclamp_rq_dec_id(rq, p, clamp_id); +} + +int sysctl_sched_uclamp_handler(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, + loff_t *ppos) +{ + int old_min, old_max; + static DEFINE_MUTEX(mutex); + int result; + + mutex_lock(&mutex); + old_min = sysctl_sched_uclamp_util_min; + old_max = sysctl_sched_uclamp_util_max; + + result = proc_dointvec(table, write, buffer, lenp, ppos); + if (result) + goto undo; + if (!write) + goto done; + + if (sysctl_sched_uclamp_util_min > sysctl_sched_uclamp_util_max || + sysctl_sched_uclamp_util_max > SCHED_CAPACITY_SCALE) { + result = -EINVAL; + goto undo; + } + + if (old_min != sysctl_sched_uclamp_util_min) { + uclamp_se_set(&uclamp_default[UCLAMP_MIN], + sysctl_sched_uclamp_util_min, false); + } + if (old_max != sysctl_sched_uclamp_util_max) { + uclamp_se_set(&uclamp_default[UCLAMP_MAX], + sysctl_sched_uclamp_util_max, false); + } + + /* + * Updating all the RUNNABLE task is expensive, keep it simple and do + * just a lazy update at each next enqueue time. + */ + goto done; + +undo: + sysctl_sched_uclamp_util_min = old_min; + sysctl_sched_uclamp_util_max = old_max; +done: + mutex_unlock(&mutex); + + return result; +} + +static int uclamp_validate(struct task_struct *p, + const struct sched_attr *attr) +{ + unsigned int lower_bound = p->uclamp_req[UCLAMP_MIN].value; + unsigned int upper_bound = p->uclamp_req[UCLAMP_MAX].value; + + if (attr->sched_flags & SCHED_FLAG_UTIL_CLAMP_MIN) + lower_bound = attr->sched_util_min; + if (attr->sched_flags & SCHED_FLAG_UTIL_CLAMP_MAX) + upper_bound = attr->sched_util_max; + + if (lower_bound > upper_bound) + return -EINVAL; + if (upper_bound > SCHED_CAPACITY_SCALE) + return -EINVAL; + + return 0; +} + +static void __setscheduler_uclamp(struct task_struct *p, + const struct sched_attr *attr) +{ + unsigned int clamp_id; + + /* + * On scheduling class change, reset to default clamps for tasks + * without a task-specific value. + */ + for_each_clamp_id(clamp_id) { + struct uclamp_se *uc_se = &p->uclamp_req[clamp_id]; + unsigned int clamp_value = uclamp_none(clamp_id); + + /* Keep using defined clamps across class changes */ + if (uc_se->user_defined) + continue; + + /* By default, RT tasks always get 100% boost */ + if (unlikely(rt_task(p) && clamp_id == UCLAMP_MIN)) + clamp_value = uclamp_none(UCLAMP_MAX); + + uclamp_se_set(uc_se, clamp_value, false); + } + + if (likely(!(attr->sched_flags & SCHED_FLAG_UTIL_CLAMP))) + return; + + if (attr->sched_flags & SCHED_FLAG_UTIL_CLAMP_MIN) { + uclamp_se_set(&p->uclamp_req[UCLAMP_MIN], + attr->sched_util_min, true); + } + + if (attr->sched_flags & SCHED_FLAG_UTIL_CLAMP_MAX) { + uclamp_se_set(&p->uclamp_req[UCLAMP_MAX], + attr->sched_util_max, true); + } +} + +static void uclamp_fork(struct task_struct *p) +{ + unsigned int clamp_id; + + for_each_clamp_id(clamp_id) + p->uclamp[clamp_id].active = false; + + if (likely(!p->sched_reset_on_fork)) + return; + + for_each_clamp_id(clamp_id) { + unsigned int clamp_value = uclamp_none(clamp_id); + + /* By default, RT tasks always get 100% boost */ + if (unlikely(rt_task(p) && clamp_id == UCLAMP_MIN)) + clamp_value = uclamp_none(UCLAMP_MAX); + + uclamp_se_set(&p->uclamp_req[clamp_id], clamp_value, false); + } +} + +static void __init init_uclamp(void) +{ + struct uclamp_se uc_max = {}; + unsigned int clamp_id; + int cpu; + + for_each_possible_cpu(cpu) { + memset(&cpu_rq(cpu)->uclamp, 0, sizeof(struct uclamp_rq)); + cpu_rq(cpu)->uclamp_flags = 0; + } + + for_each_clamp_id(clamp_id) { + uclamp_se_set(&init_task.uclamp_req[clamp_id], + uclamp_none(clamp_id), false); + } + + /* System defaults allow max clamp values for both indexes */ + uclamp_se_set(&uc_max, uclamp_none(UCLAMP_MAX), false); + for_each_clamp_id(clamp_id) + uclamp_default[clamp_id] = uc_max; +} + +#else /* CONFIG_UCLAMP_TASK */ +static inline void uclamp_rq_inc(struct rq *rq, struct task_struct *p) { } +static inline void uclamp_rq_dec(struct rq *rq, struct task_struct *p) { } +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) { } +static inline void uclamp_fork(struct task_struct *p) { } +static inline void init_uclamp(void) { } +#endif /* CONFIG_UCLAMP_TASK */ + static inline void enqueue_task(struct rq *rq, struct task_struct *p, int flags) { if (!(flags & ENQUEUE_NOCLOCK)) @@ -771,6 +1177,7 @@ static inline void enqueue_task(struct rq *rq, struct task_struct *p, int flags) psi_enqueue(p, flags & ENQUEUE_WAKEUP); } + uclamp_rq_inc(rq, p); p->sched_class->enqueue_task(rq, p, flags); } @@ -784,6 +1191,7 @@ static inline void dequeue_task(struct rq *rq, struct task_struct *p, int flags) psi_dequeue(p, flags & DEQUEUE_SLEEP); } + uclamp_rq_dec(rq, p); p->sched_class->dequeue_task(rq, p, flags); } @@ -930,7 +1338,7 @@ static inline bool is_per_cpu_kthread(struct task_struct *p) */ static inline bool is_cpu_allowed(struct task_struct *p, int cpu) { - if (!cpumask_test_cpu(cpu, &p->cpus_allowed)) + if (!cpumask_test_cpu(cpu, p->cpus_ptr)) return false; if (is_per_cpu_kthread(p)) @@ -1025,7 +1433,7 @@ static int migration_cpu_stop(void *data) local_irq_disable(); /* * We need to explicitly wake pending tasks before running - * __migrate_task() such that we will not miss enforcing cpus_allowed + * __migrate_task() such that we will not miss enforcing cpus_ptr * during wakeups, see set_cpus_allowed_ptr()'s TASK_WAKING test. */ sched_ttwu_pending(); @@ -1056,7 +1464,7 @@ static int migration_cpu_stop(void *data) */ void set_cpus_allowed_common(struct task_struct *p, const struct cpumask *new_mask) { - cpumask_copy(&p->cpus_allowed, new_mask); + cpumask_copy(&p->cpus_mask, new_mask); p->nr_cpus_allowed = cpumask_weight(new_mask); } @@ -1126,7 +1534,7 @@ static int __set_cpus_allowed_ptr(struct task_struct *p, goto out; } - if (cpumask_equal(&p->cpus_allowed, new_mask)) + if (cpumask_equal(p->cpus_ptr, new_mask)) goto out; if (!cpumask_intersects(new_mask, cpu_valid_mask)) { @@ -1286,10 +1694,10 @@ static int migrate_swap_stop(void *data) if (task_cpu(arg->src_task) != arg->src_cpu) goto unlock; - if (!cpumask_test_cpu(arg->dst_cpu, &arg->src_task->cpus_allowed)) + if (!cpumask_test_cpu(arg->dst_cpu, arg->src_task->cpus_ptr)) goto unlock; - if (!cpumask_test_cpu(arg->src_cpu, &arg->dst_task->cpus_allowed)) + if (!cpumask_test_cpu(arg->src_cpu, arg->dst_task->cpus_ptr)) goto unlock; __migrate_swap_task(arg->src_task, arg->dst_cpu); @@ -1331,10 +1739,10 @@ int migrate_swap(struct task_struct *cur, struct task_struct *p, if (!cpu_active(arg.src_cpu) || !cpu_active(arg.dst_cpu)) goto out; - if (!cpumask_test_cpu(arg.dst_cpu, &arg.src_task->cpus_allowed)) + if (!cpumask_test_cpu(arg.dst_cpu, arg.src_task->cpus_ptr)) goto out; - if (!cpumask_test_cpu(arg.src_cpu, &arg.dst_task->cpus_allowed)) + if (!cpumask_test_cpu(arg.src_cpu, arg.dst_task->cpus_ptr)) goto out; trace_sched_swap_numa(cur, arg.src_cpu, p, arg.dst_cpu); @@ -1479,7 +1887,7 @@ void kick_process(struct task_struct *p) EXPORT_SYMBOL_GPL(kick_process); /* - * ->cpus_allowed is protected by both rq->lock and p->pi_lock + * ->cpus_ptr is protected by both rq->lock and p->pi_lock * * A few notes on cpu_active vs cpu_online: * @@ -1519,14 +1927,14 @@ static int select_fallback_rq(int cpu, struct task_struct *p) for_each_cpu(dest_cpu, nodemask) { if (!cpu_active(dest_cpu)) continue; - if (cpumask_test_cpu(dest_cpu, &p->cpus_allowed)) + if (cpumask_test_cpu(dest_cpu, p->cpus_ptr)) return dest_cpu; } } for (;;) { /* Any allowed, online CPU? */ - for_each_cpu(dest_cpu, &p->cpus_allowed) { + for_each_cpu(dest_cpu, p->cpus_ptr) { if (!is_cpu_allowed(p, dest_cpu)) continue; @@ -1570,7 +1978,7 @@ out: } /* - * The caller (fork, wakeup) owns p->pi_lock, ->cpus_allowed is stable. + * The caller (fork, wakeup) owns p->pi_lock, ->cpus_ptr is stable. */ static inline int select_task_rq(struct task_struct *p, int cpu, int sd_flags, int wake_flags) @@ -1580,11 +1988,11 @@ int select_task_rq(struct task_struct *p, int cpu, int sd_flags, int wake_flags) if (p->nr_cpus_allowed > 1) cpu = p->sched_class->select_task_rq(p, cpu, sd_flags, wake_flags); else - cpu = cpumask_any(&p->cpus_allowed); + cpu = cpumask_any(p->cpus_ptr); /* * In order not to call set_task_cpu() on a blocking task we need - * to rely on ttwu() to place the task on a valid ->cpus_allowed + * to rely on ttwu() to place the task on a valid ->cpus_ptr * CPU. * * Since this is common to all placement strategies, this lives here. @@ -1991,6 +2399,29 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags) unsigned long flags; int cpu, success = 0; + if (p == current) { + /* + * We're waking current, this means 'p->on_rq' and 'task_cpu(p) + * == smp_processor_id()'. Together this means we can special + * case the whole 'p->on_rq && ttwu_remote()' case below + * without taking any locks. + * + * In particular: + * - we rely on Program-Order guarantees for all the ordering, + * - we're serialized against set_special_state() by virtue of + * it disabling IRQs (this allows not taking ->pi_lock). + */ + if (!(p->state & state)) + return false; + + success = 1; + cpu = task_cpu(p); + trace_sched_waking(p); + p->state = TASK_RUNNING; + trace_sched_wakeup(p); + goto out; + } + /* * If we are going to wake up a thread waiting for CONDITION we * need to ensure that CONDITION=1 done by the caller can not be @@ -2000,7 +2431,7 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags) raw_spin_lock_irqsave(&p->pi_lock, flags); smp_mb__after_spinlock(); if (!(p->state & state)) - goto out; + goto unlock; trace_sched_waking(p); @@ -2030,7 +2461,7 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags) */ smp_rmb(); if (p->on_rq && ttwu_remote(p, wake_flags)) - goto stat; + goto unlock; #ifdef CONFIG_SMP /* @@ -2090,10 +2521,11 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags) #endif /* CONFIG_SMP */ ttwu_queue(p, cpu, wake_flags); -stat: - ttwu_stat(p, cpu, wake_flags); -out: +unlock: raw_spin_unlock_irqrestore(&p->pi_lock, flags); +out: + if (success) + ttwu_stat(p, cpu, wake_flags); return success; } @@ -2300,6 +2732,8 @@ int sched_fork(unsigned long clone_flags, struct task_struct *p) */ p->prio = current->normal_prio; + uclamp_fork(p); + /* * Revert to default priority/policy on fork if requested. */ @@ -2395,7 +2829,7 @@ void wake_up_new_task(struct task_struct *p) #ifdef CONFIG_SMP /* * Fork balancing, do it here and not earlier because: - * - cpus_allowed can change in the fork path + * - cpus_ptr can change in the fork path * - any previously selected CPU might disappear through hotplug * * Use __set_task_cpu() to avoid calling sched_class::migrate_task_rq, @@ -3033,7 +3467,6 @@ void scheduler_tick(void) update_rq_clock(rq); curr->sched_class->task_tick(rq, curr, 0); - cpu_load_update_active(rq); calc_global_load_tick(rq); psi_task_tick(rq); @@ -4071,6 +4504,13 @@ static void __setscheduler_params(struct task_struct *p, static void __setscheduler(struct rq *rq, struct task_struct *p, const struct sched_attr *attr, bool keep_boost) { + /* + * If params can't change scheduling class changes aren't allowed + * either. + */ + if (attr->sched_flags & SCHED_FLAG_KEEP_PARAMS) + return; + __setscheduler_params(p, attr); /* @@ -4208,6 +4648,13 @@ recheck: return retval; } + /* Update task specific "requested" clamps */ + if (attr->sched_flags & SCHED_FLAG_UTIL_CLAMP) { + retval = uclamp_validate(p, attr); + if (retval) + return retval; + } + /* * Make sure no PI-waiters arrive (or leave) while we are * changing the priority of the task: @@ -4237,6 +4684,8 @@ recheck: goto change; if (dl_policy(policy) && dl_param_changed(p, attr)) goto change; + if (attr->sched_flags & SCHED_FLAG_UTIL_CLAMP) + goto change; p->sched_reset_on_fork = reset_on_fork; task_rq_unlock(rq, p, &rf); @@ -4267,7 +4716,7 @@ change: * the entire root_domain to become SCHED_DEADLINE. We * will also fail if there's no bandwidth available. */ - if (!cpumask_subset(span, &p->cpus_allowed) || + if (!cpumask_subset(span, p->cpus_ptr) || rq->rd->dl_bw.bw == 0) { task_rq_unlock(rq, p, &rf); return -EPERM; @@ -4317,7 +4766,9 @@ change: put_prev_task(rq, p); prev_class = p->sched_class; + __setscheduler(rq, p, attr, pi); + __setscheduler_uclamp(p, attr); if (queued) { /* @@ -4493,6 +4944,10 @@ static int sched_copy_attr(struct sched_attr __user *uattr, struct sched_attr *a if (ret) return -EFAULT; + if ((attr->sched_flags & SCHED_FLAG_UTIL_CLAMP) && + size < SCHED_ATTR_SIZE_VER1) + return -EINVAL; + /* * XXX: Do we want to be lenient like existing syscalls; or do we want * to be strict and return an error on out-of-bounds values? @@ -4556,14 +5011,21 @@ SYSCALL_DEFINE3(sched_setattr, pid_t, pid, struct sched_attr __user *, uattr, if ((int)attr.sched_policy < 0) return -EINVAL; + if (attr.sched_flags & SCHED_FLAG_KEEP_POLICY) + attr.sched_policy = SETPARAM_POLICY; rcu_read_lock(); retval = -ESRCH; p = find_process_by_pid(pid); - if (p != NULL) - retval = sched_setattr(p, &attr); + if (likely(p)) + get_task_struct(p); rcu_read_unlock(); + if (likely(p)) { + retval = sched_setattr(p, &attr); + put_task_struct(p); + } + return retval; } @@ -4714,6 +5176,11 @@ SYSCALL_DEFINE4(sched_getattr, pid_t, pid, struct sched_attr __user *, uattr, else attr.sched_nice = task_nice(p); +#ifdef CONFIG_UCLAMP_TASK + attr.sched_util_min = p->uclamp_req[UCLAMP_MIN].value; + attr.sched_util_max = p->uclamp_req[UCLAMP_MAX].value; +#endif + rcu_read_unlock(); retval = sched_read_attr(uattr, &attr, size); @@ -4866,7 +5333,7 @@ long sched_getaffinity(pid_t pid, struct cpumask *mask) goto out_unlock; raw_spin_lock_irqsave(&p->pi_lock, flags); - cpumask_and(mask, &p->cpus_allowed, cpu_active_mask); + cpumask_and(mask, &p->cpus_mask, cpu_active_mask); raw_spin_unlock_irqrestore(&p->pi_lock, flags); out_unlock: @@ -5123,7 +5590,7 @@ long __sched io_schedule_timeout(long timeout) } EXPORT_SYMBOL(io_schedule_timeout); -void io_schedule(void) +void __sched io_schedule(void) { int token; @@ -5443,7 +5910,7 @@ int task_can_attach(struct task_struct *p, * allowed nodes is unnecessary. Thus, cpusets are not * applicable for such threads. This prevents checking for * success of set_cpus_allowed_ptr() on all attached tasks - * before cpus_allowed may be changed. + * before cpus_mask may be changed. */ if (p->flags & PF_NO_SETAFFINITY) { ret = -EINVAL; @@ -5470,7 +5937,7 @@ int migrate_task_to(struct task_struct *p, int target_cpu) if (curr_cpu == target_cpu) return 0; - if (!cpumask_test_cpu(target_cpu, &p->cpus_allowed)) + if (!cpumask_test_cpu(target_cpu, p->cpus_ptr)) return -EINVAL; /* TODO: This is not properly updating schedstats */ @@ -5608,7 +6075,7 @@ static void migrate_tasks(struct rq *dead_rq, struct rq_flags *rf) put_prev_task(rq, next); /* - * Rules for changing task_struct::cpus_allowed are holding + * Rules for changing task_struct::cpus_mask are holding * both pi_lock and rq->lock, such that holding either * stabilizes the mask. * @@ -5902,8 +6369,8 @@ DECLARE_PER_CPU(cpumask_var_t, select_idle_mask); void __init sched_init(void) { - int i, j; unsigned long alloc_size = 0, ptr; + int i; wait_bit_init(); @@ -6005,10 +6472,6 @@ void __init sched_init(void) #ifdef CONFIG_RT_GROUP_SCHED init_tg_rt_entry(&root_task_group, &rq->rt, NULL, i, NULL); #endif - - for (j = 0; j < CPU_LOAD_IDX_MAX; j++) - rq->cpu_load[j] = 0; - #ifdef CONFIG_SMP rq->sd = NULL; rq->rd = NULL; @@ -6063,6 +6526,8 @@ void __init sched_init(void) psi_init(); + init_uclamp(); + scheduler_running = 1; } diff --git a/kernel/sched/cpudeadline.c b/kernel/sched/cpudeadline.c index ec4e4a9aab5f..5cc4012572ec 100644 --- a/kernel/sched/cpudeadline.c +++ b/kernel/sched/cpudeadline.c @@ -120,14 +120,14 @@ int cpudl_find(struct cpudl *cp, struct task_struct *p, const struct sched_dl_entity *dl_se = &p->dl; if (later_mask && - cpumask_and(later_mask, cp->free_cpus, &p->cpus_allowed)) { + cpumask_and(later_mask, cp->free_cpus, p->cpus_ptr)) { return 1; } else { int best_cpu = cpudl_maximum(cp); WARN_ON(best_cpu != -1 && !cpu_present(best_cpu)); - if (cpumask_test_cpu(best_cpu, &p->cpus_allowed) && + if (cpumask_test_cpu(best_cpu, p->cpus_ptr) && dl_time_before(dl_se->deadline, cp->elements[0].dl)) { if (later_mask) cpumask_set_cpu(best_cpu, later_mask); diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c index 962cf343f798..636ca6f88c8e 100644 --- a/kernel/sched/cpufreq_schedutil.c +++ b/kernel/sched/cpufreq_schedutil.c @@ -196,14 +196,17 @@ static unsigned int get_next_freq(struct sugov_policy *sg_policy, * based on the task model parameters and gives the minimal utilization * required to meet deadlines. */ -unsigned long schedutil_freq_util(int cpu, unsigned long util_cfs, - unsigned long max, enum schedutil_type type) +unsigned long schedutil_cpu_util(int cpu, unsigned long util_cfs, + unsigned long max, enum schedutil_type type, + struct task_struct *p) { unsigned long dl_util, util, irq; struct rq *rq = cpu_rq(cpu); - if (type == FREQUENCY_UTIL && rt_rq_is_runnable(&rq->rt)) + if (!IS_BUILTIN(CONFIG_UCLAMP_TASK) && + type == FREQUENCY_UTIL && rt_rq_is_runnable(&rq->rt)) { return max; + } /* * Early check to see if IRQ/steal time saturates the CPU, can be @@ -219,9 +222,16 @@ unsigned long schedutil_freq_util(int cpu, unsigned long util_cfs, * CFS tasks and we use the same metric to track the effective * utilization (PELT windows are synchronized) we can directly add them * to obtain the CPU's actual utilization. + * + * CFS and RT utilization can be boosted or capped, depending on + * utilization clamp constraints requested by currently RUNNABLE + * tasks. + * When there are no CFS RUNNABLE tasks, clamps are released and + * frequency will be gracefully reduced with the utilization decay. */ - util = util_cfs; - util += cpu_util_rt(rq); + util = util_cfs + cpu_util_rt(rq); + if (type == FREQUENCY_UTIL) + util = uclamp_util_with(rq, util, p); dl_util = cpu_util_dl(rq); @@ -276,12 +286,12 @@ static unsigned long sugov_get_util(struct sugov_cpu *sg_cpu) { struct rq *rq = cpu_rq(sg_cpu->cpu); unsigned long util = cpu_util_cfs(rq); - unsigned long max = arch_scale_cpu_capacity(NULL, sg_cpu->cpu); + unsigned long max = arch_scale_cpu_capacity(sg_cpu->cpu); sg_cpu->max = max; sg_cpu->bw_dl = cpu_bw_dl(rq); - return schedutil_freq_util(sg_cpu->cpu, util, max, FREQUENCY_UTIL); + return schedutil_cpu_util(sg_cpu->cpu, util, max, FREQUENCY_UTIL, NULL); } /** diff --git a/kernel/sched/cpupri.c b/kernel/sched/cpupri.c index 9c6480e6d62d..b7abca987d94 100644 --- a/kernel/sched/cpupri.c +++ b/kernel/sched/cpupri.c @@ -94,11 +94,11 @@ int cpupri_find(struct cpupri *cp, struct task_struct *p, if (skip) continue; - if (cpumask_any_and(&p->cpus_allowed, vec->mask) >= nr_cpu_ids) + if (cpumask_any_and(p->cpus_ptr, vec->mask) >= nr_cpu_ids) continue; if (lowest_mask) { - cpumask_and(lowest_mask, &p->cpus_allowed, vec->mask); + cpumask_and(lowest_mask, p->cpus_ptr, vec->mask); /* * We have to ensure that we have at least one bit diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index 43901fa3f269..8b5bb2ac16e2 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -538,7 +538,7 @@ static struct rq *dl_task_offline_migration(struct rq *rq, struct task_struct *p * If we cannot preempt any rq, fall back to pick any * online CPU: */ - cpu = cpumask_any_and(cpu_active_mask, &p->cpus_allowed); + cpu = cpumask_any_and(cpu_active_mask, p->cpus_ptr); if (cpu >= nr_cpu_ids) { /* * Failed to find any suitable CPU. @@ -1195,7 +1195,7 @@ static void update_curr_dl(struct rq *rq) &curr->dl); } else { unsigned long scale_freq = arch_scale_freq_capacity(cpu); - unsigned long scale_cpu = arch_scale_cpu_capacity(NULL, cpu); + unsigned long scale_cpu = arch_scale_cpu_capacity(cpu); scaled_delta_exec = cap_scale(delta_exec, scale_freq); scaled_delta_exec = cap_scale(scaled_delta_exec, scale_cpu); @@ -1824,7 +1824,7 @@ static void set_curr_task_dl(struct rq *rq) static int pick_dl_task(struct rq *rq, struct task_struct *p, int cpu) { if (!task_running(rq, p) && - cpumask_test_cpu(cpu, &p->cpus_allowed)) + cpumask_test_cpu(cpu, p->cpus_ptr)) return 1; return 0; } @@ -1974,7 +1974,7 @@ static struct rq *find_lock_later_rq(struct task_struct *task, struct rq *rq) /* Retry if something changed. */ if (double_lock_balance(rq, later_rq)) { if (unlikely(task_rq(task) != rq || - !cpumask_test_cpu(later_rq->cpu, &task->cpus_allowed) || + !cpumask_test_cpu(later_rq->cpu, task->cpus_ptr) || task_running(rq, task) || !dl_task(task) || !task_on_rq_queued(task))) { diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c index 14c6a8716ba1..f7e4579e746c 100644 --- a/kernel/sched/debug.c +++ b/kernel/sched/debug.c @@ -233,49 +233,35 @@ static void sd_free_ctl_entry(struct ctl_table **tablep) *tablep = NULL; } -static int min_load_idx = 0; -static int max_load_idx = CPU_LOAD_IDX_MAX-1; - static void set_table_entry(struct ctl_table *entry, const char *procname, void *data, int maxlen, - umode_t mode, proc_handler *proc_handler, - bool load_idx) + umode_t mode, proc_handler *proc_handler) { entry->procname = procname; entry->data = data; entry->maxlen = maxlen; entry->mode = mode; entry->proc_handler = proc_handler; - - if (load_idx) { - entry->extra1 = &min_load_idx; - entry->extra2 = &max_load_idx; - } } 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(9); if (table == NULL) return NULL; - set_table_entry(&table[0] , "min_interval", &sd->min_interval, sizeof(long), 0644, proc_doulongvec_minmax, false); - set_table_entry(&table[1] , "max_interval", &sd->max_interval, sizeof(long), 0644, proc_doulongvec_minmax, false); - set_table_entry(&table[2] , "busy_idx", &sd->busy_idx, sizeof(int) , 0644, proc_dointvec_minmax, true ); - set_table_entry(&table[3] , "idle_idx", &sd->idle_idx, sizeof(int) , 0644, proc_dointvec_minmax, true ); - set_table_entry(&table[4] , "newidle_idx", &sd->newidle_idx, sizeof(int) , 0644, proc_dointvec_minmax, true ); - set_table_entry(&table[5] , "wake_idx", &sd->wake_idx, sizeof(int) , 0644, proc_dointvec_minmax, true ); - set_table_entry(&table[6] , "forkexec_idx", &sd->forkexec_idx, sizeof(int) , 0644, proc_dointvec_minmax, true ); - set_table_entry(&table[7] , "busy_factor", &sd->busy_factor, sizeof(int) , 0644, proc_dointvec_minmax, false); - set_table_entry(&table[8] , "imbalance_pct", &sd->imbalance_pct, sizeof(int) , 0644, proc_dointvec_minmax, false); - set_table_entry(&table[9] , "cache_nice_tries", &sd->cache_nice_tries, sizeof(int) , 0644, proc_dointvec_minmax, false); - set_table_entry(&table[10], "flags", &sd->flags, sizeof(int) , 0644, proc_dointvec_minmax, false); - set_table_entry(&table[11], "max_newidle_lb_cost", &sd->max_newidle_lb_cost, sizeof(long), 0644, proc_doulongvec_minmax, false); - set_table_entry(&table[12], "name", sd->name, CORENAME_MAX_SIZE, 0444, proc_dostring, false); - /* &table[13] is terminator */ + set_table_entry(&table[0], "min_interval", &sd->min_interval, sizeof(long), 0644, proc_doulongvec_minmax); + set_table_entry(&table[1], "max_interval", &sd->max_interval, sizeof(long), 0644, proc_doulongvec_minmax); + set_table_entry(&table[2], "busy_factor", &sd->busy_factor, sizeof(int), 0644, proc_dointvec_minmax); + set_table_entry(&table[3], "imbalance_pct", &sd->imbalance_pct, sizeof(int), 0644, proc_dointvec_minmax); + set_table_entry(&table[4], "cache_nice_tries", &sd->cache_nice_tries, sizeof(int), 0644, proc_dointvec_minmax); + set_table_entry(&table[5], "flags", &sd->flags, sizeof(int), 0644, proc_dointvec_minmax); + set_table_entry(&table[6], "max_newidle_lb_cost", &sd->max_newidle_lb_cost, sizeof(long), 0644, proc_doulongvec_minmax); + set_table_entry(&table[7], "name", sd->name, CORENAME_MAX_SIZE, 0444, proc_dostring); + /* &table[8] is terminator */ return table; } @@ -653,8 +639,6 @@ do { \ SEQ_printf(m, " .%-30s: %Ld.%06ld\n", #x, SPLIT_NS(rq->x)) P(nr_running); - SEQ_printf(m, " .%-30s: %lu\n", "load", - rq->load.weight); P(nr_switches); P(nr_load_updates); P(nr_uninterruptible); @@ -662,11 +646,6 @@ do { \ SEQ_printf(m, " .%-30s: %ld\n", "curr->pid", (long)(task_pid_nr(rq->curr))); PN(clock); PN(clock_task); - P(cpu_load[0]); - P(cpu_load[1]); - P(cpu_load[2]); - P(cpu_load[3]); - P(cpu_load[4]); #undef P #undef PN diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 8591529e1753..036be95a87e9 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -275,6 +275,19 @@ static inline struct cfs_rq *group_cfs_rq(struct sched_entity *grp) return grp->my_q; } +static inline void cfs_rq_tg_path(struct cfs_rq *cfs_rq, char *path, int len) +{ + if (!path) + return; + + if (cfs_rq && task_group_is_autogroup(cfs_rq->tg)) + autogroup_path(cfs_rq->tg, path, len); + else if (cfs_rq && cfs_rq->tg->css.cgroup) + cgroup_path(cfs_rq->tg->css.cgroup, path, len); + else + strlcpy(path, "(null)", len); +} + static inline bool list_add_leaf_cfs_rq(struct cfs_rq *cfs_rq) { struct rq *rq = rq_of(cfs_rq); @@ -449,6 +462,12 @@ static inline struct cfs_rq *group_cfs_rq(struct sched_entity *grp) return NULL; } +static inline void cfs_rq_tg_path(struct cfs_rq *cfs_rq, char *path, int len) +{ + if (path) + strlcpy(path, "(null)", len); +} + static inline bool list_add_leaf_cfs_rq(struct cfs_rq *cfs_rq) { return true; @@ -764,7 +783,7 @@ void post_init_entity_util_avg(struct task_struct *p) struct sched_entity *se = &p->se; struct cfs_rq *cfs_rq = cfs_rq_of(se); struct sched_avg *sa = &se->avg; - long cpu_scale = arch_scale_cpu_capacity(NULL, cpu_of(rq_of(cfs_rq))); + long cpu_scale = arch_scale_cpu_capacity(cpu_of(rq_of(cfs_rq))); long cap = (long)(cpu_scale - cfs_rq->avg.util_avg) / 2; if (cap > 0) { @@ -1466,9 +1485,7 @@ bool should_numa_migrate_memory(struct task_struct *p, struct page * page, group_faults_cpu(ng, src_nid) * group_faults(p, dst_nid) * 4; } -static unsigned long weighted_cpuload(struct rq *rq); -static unsigned long source_load(int cpu, int type); -static unsigned long target_load(int cpu, int type); +static unsigned long cpu_runnable_load(struct rq *rq); /* Cached statistics for all CPUs within a node */ struct numa_stats { @@ -1489,7 +1506,7 @@ static void update_numa_stats(struct numa_stats *ns, int nid) for_each_cpu(cpu, cpumask_of_node(nid)) { struct rq *rq = cpu_rq(cpu); - ns->load += weighted_cpuload(rq); + ns->load += cpu_runnable_load(rq); ns->compute_capacity += capacity_of(cpu); } @@ -1621,7 +1638,7 @@ static void task_numa_compare(struct task_numa_env *env, * be incurred if the tasks were swapped. */ /* Skip this swap candidate if cannot move to the source cpu */ - if (!cpumask_test_cpu(env->src_cpu, &cur->cpus_allowed)) + if (!cpumask_test_cpu(env->src_cpu, cur->cpus_ptr)) goto unlock; /* @@ -1718,7 +1735,7 @@ static void task_numa_find_cpu(struct task_numa_env *env, for_each_cpu(cpu, cpumask_of_node(env->dst_nid)) { /* Skip this CPU if the source task cannot migrate */ - if (!cpumask_test_cpu(cpu, &env->p->cpus_allowed)) + if (!cpumask_test_cpu(cpu, env->p->cpus_ptr)) continue; env->dst_cpu = cpu; @@ -2686,8 +2703,6 @@ static void account_entity_enqueue(struct cfs_rq *cfs_rq, struct sched_entity *se) { update_load_add(&cfs_rq->load, se->load.weight); - if (!parent_entity(se)) - update_load_add(&rq_of(cfs_rq)->load, se->load.weight); #ifdef CONFIG_SMP if (entity_is_task(se)) { struct rq *rq = rq_of(cfs_rq); @@ -2703,8 +2718,6 @@ static void account_entity_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se) { update_load_sub(&cfs_rq->load, se->load.weight); - if (!parent_entity(se)) - update_load_sub(&rq_of(cfs_rq)->load, se->load.weight); #ifdef CONFIG_SMP if (entity_is_task(se)) { account_numa_dequeue(rq_of(cfs_rq), task_of(se)); @@ -3334,6 +3347,9 @@ static inline int propagate_entity_load_avg(struct sched_entity *se) update_tg_cfs_util(cfs_rq, se, gcfs_rq); update_tg_cfs_runnable(cfs_rq, se, gcfs_rq); + trace_pelt_cfs_tp(cfs_rq); + trace_pelt_se_tp(se); + return 1; } @@ -3486,6 +3502,8 @@ static void attach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *s add_tg_cfs_propagate(cfs_rq, se->avg.load_sum); cfs_rq_util_change(cfs_rq, flags); + + trace_pelt_cfs_tp(cfs_rq); } /** @@ -3505,6 +3523,8 @@ static void detach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *s add_tg_cfs_propagate(cfs_rq, -se->avg.load_sum); cfs_rq_util_change(cfs_rq, 0); + + trace_pelt_cfs_tp(cfs_rq); } /* @@ -4100,7 +4120,8 @@ set_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *se) * least twice that of our own weight (i.e. dont track it * when there are only lesser-weight tasks around): */ - if (schedstat_enabled() && rq_of(cfs_rq)->load.weight >= 2*se->load.weight) { + if (schedstat_enabled() && + rq_of(cfs_rq)->cfs.load.weight >= 2*se->load.weight) { schedstat_set(se->statistics.slice_max, max((u64)schedstat_val(se->statistics.slice_max), se->sum_exec_runtime - se->prev_sum_exec_runtime)); @@ -4734,6 +4755,11 @@ static void start_cfs_slack_bandwidth(struct cfs_bandwidth *cfs_b) if (runtime_refresh_within(cfs_b, min_left)) return; + /* don't push forwards an existing deferred unthrottle */ + if (cfs_b->slack_started) + return; + cfs_b->slack_started = true; + hrtimer_start(&cfs_b->slack_timer, ns_to_ktime(cfs_bandwidth_slack_period), HRTIMER_MODE_REL); @@ -4787,6 +4813,7 @@ static void do_sched_cfs_slack_timer(struct cfs_bandwidth *cfs_b) /* confirm we're still not at a refresh boundary */ raw_spin_lock_irqsave(&cfs_b->lock, flags); + cfs_b->slack_started = false; if (cfs_b->distribute_running) { raw_spin_unlock_irqrestore(&cfs_b->lock, flags); return; @@ -4950,6 +4977,7 @@ void init_cfs_bandwidth(struct cfs_bandwidth *cfs_b) hrtimer_init(&cfs_b->slack_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); cfs_b->slack_timer.function = sched_cfs_slack_timer; cfs_b->distribute_running = 0; + cfs_b->slack_started = false; } static void init_cfs_rq_runtime(struct cfs_rq *cfs_rq) @@ -5153,8 +5181,10 @@ static inline bool cpu_overutilized(int cpu) static inline void update_overutilized_status(struct rq *rq) { - if (!READ_ONCE(rq->rd->overutilized) && cpu_overutilized(rq->cpu)) + if (!READ_ONCE(rq->rd->overutilized) && cpu_overutilized(rq->cpu)) { WRITE_ONCE(rq->rd->overutilized, SG_OVERUTILIZED); + trace_sched_overutilized_tp(rq->rd, SG_OVERUTILIZED); + } } #else static inline void update_overutilized_status(struct rq *rq) { } @@ -5325,71 +5355,6 @@ DEFINE_PER_CPU(cpumask_var_t, load_balance_mask); DEFINE_PER_CPU(cpumask_var_t, select_idle_mask); #ifdef CONFIG_NO_HZ_COMMON -/* - * per rq 'load' arrray crap; XXX kill this. - */ - -/* - * The exact cpuload calculated at every tick would be: - * - * load' = (1 - 1/2^i) * load + (1/2^i) * cur_load - * - * If a CPU misses updates for n ticks (as it was idle) and update gets - * called on the n+1-th tick when CPU may be busy, then we have: - * - * load_n = (1 - 1/2^i)^n * load_0 - * load_n+1 = (1 - 1/2^i) * load_n + (1/2^i) * cur_load - * - * decay_load_missed() below does efficient calculation of - * - * load' = (1 - 1/2^i)^n * load - * - * Because x^(n+m) := x^n * x^m we can decompose any x^n in power-of-2 factors. - * This allows us to precompute the above in said factors, thereby allowing the - * reduction of an arbitrary n in O(log_2 n) steps. (See also - * fixed_power_int()) - * - * The calculation is approximated on a 128 point scale. - */ -#define DEGRADE_SHIFT 7 - -static const u8 degrade_zero_ticks[CPU_LOAD_IDX_MAX] = {0, 8, 32, 64, 128}; -static const u8 degrade_factor[CPU_LOAD_IDX_MAX][DEGRADE_SHIFT + 1] = { - { 0, 0, 0, 0, 0, 0, 0, 0 }, - { 64, 32, 8, 0, 0, 0, 0, 0 }, - { 96, 72, 40, 12, 1, 0, 0, 0 }, - { 112, 98, 75, 43, 15, 1, 0, 0 }, - { 120, 112, 98, 76, 45, 16, 2, 0 } -}; - -/* - * Update cpu_load for any missed ticks, due to tickless idle. The backlog - * would be when CPU is idle and so we just decay the old load without - * adding any new load. - */ -static unsigned long -decay_load_missed(unsigned long load, unsigned long missed_updates, int idx) -{ - int j = 0; - - if (!missed_updates) - return load; - - if (missed_updates >= degrade_zero_ticks[idx]) - return 0; - - if (idx == 1) - return load >> missed_updates; - - while (missed_updates) { - if (missed_updates % 2) - load = (load * degrade_factor[idx][j]) >> DEGRADE_SHIFT; - - missed_updates >>= 1; - j++; - } - return load; -} static struct { cpumask_var_t idle_cpus_mask; @@ -5401,234 +5366,11 @@ static struct { #endif /* CONFIG_NO_HZ_COMMON */ -/** - * __cpu_load_update - update the rq->cpu_load[] statistics - * @this_rq: The rq to update statistics for - * @this_load: The current load - * @pending_updates: The number of missed updates - * - * Update rq->cpu_load[] statistics. This function is usually called every - * scheduler tick (TICK_NSEC). - * - * This function computes a decaying average: - * - * load[i]' = (1 - 1/2^i) * load[i] + (1/2^i) * load - * - * Because of NOHZ it might not get called on every tick which gives need for - * the @pending_updates argument. - * - * load[i]_n = (1 - 1/2^i) * load[i]_n-1 + (1/2^i) * load_n-1 - * = A * load[i]_n-1 + B ; A := (1 - 1/2^i), B := (1/2^i) * load - * = A * (A * load[i]_n-2 + B) + B - * = A * (A * (A * load[i]_n-3 + B) + B) + B - * = A^3 * load[i]_n-3 + (A^2 + A + 1) * B - * = A^n * load[i]_0 + (A^(n-1) + A^(n-2) + ... + 1) * B - * = A^n * load[i]_0 + ((1 - A^n) / (1 - A)) * B - * = (1 - 1/2^i)^n * (load[i]_0 - load) + load - * - * In the above we've assumed load_n := load, which is true for NOHZ_FULL as - * any change in load would have resulted in the tick being turned back on. - * - * For regular NOHZ, this reduces to: - * - * load[i]_n = (1 - 1/2^i)^n * load[i]_0 - * - * see decay_load_misses(). For NOHZ_FULL we get to subtract and add the extra - * term. - */ -static void cpu_load_update(struct rq *this_rq, unsigned long this_load, - unsigned long pending_updates) -{ - unsigned long __maybe_unused tickless_load = this_rq->cpu_load[0]; - int i, scale; - - this_rq->nr_load_updates++; - - /* Update our load: */ - this_rq->cpu_load[0] = this_load; /* Fasttrack for idx 0 */ - for (i = 1, scale = 2; i < CPU_LOAD_IDX_MAX; i++, scale += scale) { - unsigned long old_load, new_load; - - /* scale is effectively 1 << i now, and >> i divides by scale */ - - old_load = this_rq->cpu_load[i]; -#ifdef CONFIG_NO_HZ_COMMON - old_load = decay_load_missed(old_load, pending_updates - 1, i); - if (tickless_load) { - old_load -= decay_load_missed(tickless_load, pending_updates - 1, i); - /* - * old_load can never be a negative value because a - * decayed tickless_load cannot be greater than the - * original tickless_load. - */ - old_load += tickless_load; - } -#endif - 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; - } -} - -/* Used instead of source_load when we know the type == 0 */ -static unsigned long weighted_cpuload(struct rq *rq) +static unsigned long cpu_runnable_load(struct rq *rq) { return cfs_rq_runnable_load_avg(&rq->cfs); } -#ifdef CONFIG_NO_HZ_COMMON -/* - * There is no sane way to deal with nohz on smp when using jiffies because the - * CPU doing the jiffies update might drift wrt the CPU doing the jiffy reading - * causing off-by-one errors in observed deltas; {0,2} instead of {1,1}. - * - * Therefore we need to avoid the delta approach from the regular tick when - * possible since that would seriously skew the load calculation. This is why we - * use cpu_load_update_periodic() for CPUs out of nohz. However we'll rely on - * jiffies deltas for updates happening while in nohz mode (idle ticks, idle - * loop exit, nohz_idle_balance, nohz full exit...) - * - * This means we might still be one tick off for nohz periods. - */ - -static void cpu_load_update_nohz(struct rq *this_rq, - unsigned long curr_jiffies, - unsigned long load) -{ - unsigned long pending_updates; - - pending_updates = curr_jiffies - this_rq->last_load_update_tick; - if (pending_updates) { - this_rq->last_load_update_tick = curr_jiffies; - /* - * In the regular NOHZ case, we were idle, this means load 0. - * In the NOHZ_FULL case, we were non-idle, we should consider - * its weighted load. - */ - cpu_load_update(this_rq, load, pending_updates); - } -} - -/* - * Called from nohz_idle_balance() to update the load ratings before doing the - * idle balance. - */ -static void cpu_load_update_idle(struct rq *this_rq) -{ - /* - * bail if there's load or we're actually up-to-date. - */ - if (weighted_cpuload(this_rq)) - return; - - cpu_load_update_nohz(this_rq, READ_ONCE(jiffies), 0); -} - -/* - * Record CPU load on nohz entry so we know the tickless load to account - * on nohz exit. cpu_load[0] happens then to be updated more frequently - * than other cpu_load[idx] but it should be fine as cpu_load readers - * shouldn't rely into synchronized cpu_load[*] updates. - */ -void cpu_load_update_nohz_start(void) -{ - struct rq *this_rq = this_rq(); - - /* - * This is all lockless but should be fine. If weighted_cpuload changes - * concurrently we'll exit nohz. And cpu_load write can race with - * cpu_load_update_idle() but both updater would be writing the same. - */ - this_rq->cpu_load[0] = weighted_cpuload(this_rq); -} - -/* - * Account the tickless load in the end of a nohz frame. - */ -void cpu_load_update_nohz_stop(void) -{ - unsigned long curr_jiffies = READ_ONCE(jiffies); - struct rq *this_rq = this_rq(); - unsigned long load; - struct rq_flags rf; - - if (curr_jiffies == this_rq->last_load_update_tick) - return; - - load = weighted_cpuload(this_rq); - rq_lock(this_rq, &rf); - update_rq_clock(this_rq); - cpu_load_update_nohz(this_rq, curr_jiffies, load); - rq_unlock(this_rq, &rf); -} -#else /* !CONFIG_NO_HZ_COMMON */ -static inline void cpu_load_update_nohz(struct rq *this_rq, - unsigned long curr_jiffies, - unsigned long load) { } -#endif /* CONFIG_NO_HZ_COMMON */ - -static void cpu_load_update_periodic(struct rq *this_rq, unsigned long load) -{ -#ifdef CONFIG_NO_HZ_COMMON - /* See the mess around cpu_load_update_nohz(). */ - this_rq->last_load_update_tick = READ_ONCE(jiffies); -#endif - cpu_load_update(this_rq, load, 1); -} - -/* - * Called from scheduler_tick() - */ -void cpu_load_update_active(struct rq *this_rq) -{ - unsigned long load = weighted_cpuload(this_rq); - - if (tick_nohz_tick_stopped()) - cpu_load_update_nohz(this_rq, READ_ONCE(jiffies), load); - else - cpu_load_update_periodic(this_rq, load); -} - -/* - * Return a low guess at the load of a migration-source CPU weighted - * according to the scheduling class and "nice" value. - * - * We want to under-estimate the load of migration sources, to - * balance conservatively. - */ -static unsigned long source_load(int cpu, int type) -{ - struct rq *rq = cpu_rq(cpu); - unsigned long total = weighted_cpuload(rq); - - if (type == 0 || !sched_feat(LB_BIAS)) - return total; - - return min(rq->cpu_load[type-1], total); -} - -/* - * Return a high guess at the load of a migration-target CPU weighted - * according to the scheduling class and "nice" value. - */ -static unsigned long target_load(int cpu, int type) -{ - struct rq *rq = cpu_rq(cpu); - unsigned long total = weighted_cpuload(rq); - - if (type == 0 || !sched_feat(LB_BIAS)) - return total; - - return max(rq->cpu_load[type-1], total); -} - static unsigned long capacity_of(int cpu) { return cpu_rq(cpu)->cpu_capacity; @@ -5638,7 +5380,7 @@ static unsigned long cpu_avg_load_per_task(int cpu) { struct rq *rq = cpu_rq(cpu); unsigned long nr_running = READ_ONCE(rq->cfs.h_nr_running); - unsigned long load_avg = weighted_cpuload(rq); + unsigned long load_avg = cpu_runnable_load(rq); if (nr_running) return load_avg / nr_running; @@ -5736,7 +5478,7 @@ wake_affine_weight(struct sched_domain *sd, struct task_struct *p, s64 this_eff_load, prev_eff_load; unsigned long task_load; - this_eff_load = target_load(this_cpu, sd->wake_idx); + this_eff_load = cpu_runnable_load(cpu_rq(this_cpu)); if (sync) { unsigned long current_load = task_h_load(current); @@ -5754,7 +5496,7 @@ wake_affine_weight(struct sched_domain *sd, struct task_struct *p, this_eff_load *= 100; this_eff_load *= capacity_of(prev_cpu); - prev_eff_load = source_load(prev_cpu, sd->wake_idx); + prev_eff_load = cpu_runnable_load(cpu_rq(prev_cpu)); prev_eff_load -= task_load; if (sched_feat(WA_BIAS)) prev_eff_load *= 100 + (sd->imbalance_pct - 100) / 2; @@ -5815,14 +5557,10 @@ find_idlest_group(struct sched_domain *sd, struct task_struct *p, unsigned long this_runnable_load = ULONG_MAX; unsigned long min_avg_load = ULONG_MAX, this_avg_load = ULONG_MAX; unsigned long most_spare = 0, this_spare = 0; - int load_idx = sd->forkexec_idx; int imbalance_scale = 100 + (sd->imbalance_pct-100)/2; unsigned long imbalance = scale_load_down(NICE_0_LOAD) * (sd->imbalance_pct-100) / 100; - if (sd_flag & SD_BALANCE_WAKE) - load_idx = sd->wake_idx; - do { unsigned long load, avg_load, runnable_load; unsigned long spare_cap, max_spare_cap; @@ -5831,7 +5569,7 @@ find_idlest_group(struct sched_domain *sd, struct task_struct *p, /* Skip over this group if it has no CPUs allowed */ if (!cpumask_intersects(sched_group_span(group), - &p->cpus_allowed)) + p->cpus_ptr)) continue; local_group = cpumask_test_cpu(this_cpu, @@ -5846,12 +5584,7 @@ find_idlest_group(struct sched_domain *sd, struct task_struct *p, max_spare_cap = 0; for_each_cpu(i, sched_group_span(group)) { - /* Bias balancing toward CPUs of our domain */ - if (local_group) - load = source_load(i, load_idx); - else - load = target_load(i, load_idx); - + load = cpu_runnable_load(cpu_rq(i)); runnable_load += load; avg_load += cfs_rq_load_avg(&cpu_rq(i)->cfs); @@ -5963,7 +5696,7 @@ find_idlest_group_cpu(struct sched_group *group, struct task_struct *p, int this return cpumask_first(sched_group_span(group)); /* Traverse only the allowed CPUs */ - for_each_cpu_and(i, sched_group_span(group), &p->cpus_allowed) { + for_each_cpu_and(i, sched_group_span(group), p->cpus_ptr) { if (available_idle_cpu(i)) { struct rq *rq = cpu_rq(i); struct cpuidle_state *idle = idle_get_state(rq); @@ -5987,7 +5720,7 @@ find_idlest_group_cpu(struct sched_group *group, struct task_struct *p, int this shallowest_idle_cpu = i; } } else if (shallowest_idle_cpu == -1) { - load = weighted_cpuload(cpu_rq(i)); + load = cpu_runnable_load(cpu_rq(i)); if (load < min_load) { min_load = load; least_loaded_cpu = i; @@ -6003,7 +5736,7 @@ static inline int find_idlest_cpu(struct sched_domain *sd, struct task_struct *p { int new_cpu = cpu; - if (!cpumask_intersects(sched_domain_span(sd), &p->cpus_allowed)) + if (!cpumask_intersects(sched_domain_span(sd), p->cpus_ptr)) return prev_cpu; /* @@ -6120,7 +5853,7 @@ static int select_idle_core(struct task_struct *p, struct sched_domain *sd, int if (!test_idle_cores(target, false)) return -1; - cpumask_and(cpus, sched_domain_span(sd), &p->cpus_allowed); + cpumask_and(cpus, sched_domain_span(sd), p->cpus_ptr); for_each_cpu_wrap(core, cpus, target) { bool idle = true; @@ -6154,7 +5887,7 @@ static int select_idle_smt(struct task_struct *p, int target) return -1; for_each_cpu(cpu, cpu_smt_mask(target)) { - if (!cpumask_test_cpu(cpu, &p->cpus_allowed)) + if (!cpumask_test_cpu(cpu, p->cpus_ptr)) continue; if (available_idle_cpu(cpu)) return cpu; @@ -6218,7 +5951,7 @@ static int select_idle_cpu(struct task_struct *p, struct sched_domain *sd, int t for_each_cpu_wrap(cpu, sched_domain_span(sd), target) { if (!--nr) return -1; - if (!cpumask_test_cpu(cpu, &p->cpus_allowed)) + if (!cpumask_test_cpu(cpu, p->cpus_ptr)) continue; if (available_idle_cpu(cpu)) break; @@ -6255,7 +5988,7 @@ static int select_idle_sibling(struct task_struct *p, int prev, int target) recent_used_cpu != target && cpus_share_cache(recent_used_cpu, target) && available_idle_cpu(recent_used_cpu) && - cpumask_test_cpu(p->recent_used_cpu, &p->cpus_allowed)) { + cpumask_test_cpu(p->recent_used_cpu, p->cpus_ptr)) { /* * Replace recent_used_cpu with prev as it is a potential * candidate for the next wake: @@ -6499,11 +6232,21 @@ static unsigned long cpu_util_next(int cpu, struct task_struct *p, int dst_cpu) static long compute_energy(struct task_struct *p, int dst_cpu, struct perf_domain *pd) { - long util, max_util, sum_util, energy = 0; + unsigned int max_util, util_cfs, cpu_util, cpu_cap; + unsigned long sum_util, energy = 0; + struct task_struct *tsk; int cpu; for (; pd; pd = pd->next) { + struct cpumask *pd_mask = perf_domain_span(pd); + + /* + * The energy model mandates all the CPUs of a performance + * domain have the same capacity. + */ + cpu_cap = arch_scale_cpu_capacity(cpumask_first(pd_mask)); max_util = sum_util = 0; + /* * The capacity state of CPUs of the current rd can be driven by * CPUs of another rd if they belong to the same performance @@ -6514,11 +6257,29 @@ compute_energy(struct task_struct *p, int dst_cpu, struct perf_domain *pd) * it will not appear in its pd list and will not be accounted * by compute_energy(). */ - for_each_cpu_and(cpu, perf_domain_span(pd), cpu_online_mask) { - util = cpu_util_next(cpu, p, dst_cpu); - util = schedutil_energy_util(cpu, util); - max_util = max(util, max_util); - sum_util += util; + for_each_cpu_and(cpu, pd_mask, cpu_online_mask) { + util_cfs = cpu_util_next(cpu, p, dst_cpu); + + /* + * Busy time computation: utilization clamping is not + * required since the ratio (sum_util / cpu_capacity) + * is already enough to scale the EM reported power + * consumption at the (eventually clamped) cpu_capacity. + */ + sum_util += schedutil_cpu_util(cpu, util_cfs, cpu_cap, + ENERGY_UTIL, NULL); + + /* + * Performance domain frequency: utilization clamping + * must be considered since it affects the selection + * of the performance domain frequency. + * NOTE: in case RT tasks are running, by default the + * FREQUENCY_UTIL's utilization can be max OPP. + */ + tsk = cpu == dst_cpu ? p : NULL; + cpu_util = schedutil_cpu_util(cpu, util_cfs, cpu_cap, + FREQUENCY_UTIL, tsk); + max_util = max(max_util, cpu_util); } energy += em_pd_energy(pd->em_pd, max_util, sum_util); @@ -6601,7 +6362,7 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu) int max_spare_cap_cpu = -1; for_each_cpu_and(cpu, perf_domain_span(pd), sched_domain_span(sd)) { - if (!cpumask_test_cpu(cpu, &p->cpus_allowed)) + if (!cpumask_test_cpu(cpu, p->cpus_ptr)) continue; /* Skip CPUs that will be overutilized. */ @@ -6690,7 +6451,7 @@ select_task_rq_fair(struct task_struct *p, int prev_cpu, int sd_flag, int wake_f } want_affine = !wake_wide(p) && !wake_cap(p, cpu, prev_cpu) && - cpumask_test_cpu(cpu, &p->cpus_allowed); + cpumask_test_cpu(cpu, p->cpus_ptr); } rcu_read_lock(); @@ -7446,14 +7207,14 @@ int can_migrate_task(struct task_struct *p, struct lb_env *env) /* * We do not migrate tasks that are: * 1) throttled_lb_pair, or - * 2) cannot be migrated to this CPU due to cpus_allowed, or + * 2) cannot be migrated to this CPU due to cpus_ptr, or * 3) running (obviously), or * 4) are cache-hot on their current CPU. */ if (throttled_lb_pair(task_group(p), env->src_cpu, env->dst_cpu)) return 0; - if (!cpumask_test_cpu(env->dst_cpu, &p->cpus_allowed)) { + if (!cpumask_test_cpu(env->dst_cpu, p->cpus_ptr)) { int cpu; schedstat_inc(p->se.statistics.nr_failed_migrations_affine); @@ -7473,7 +7234,7 @@ int can_migrate_task(struct task_struct *p, struct lb_env *env) /* Prevent to re-select dst_cpu via env's CPUs: */ for_each_cpu_and(cpu, env->dst_grpmask, env->cpus) { - if (cpumask_test_cpu(cpu, &p->cpus_allowed)) { + if (cpumask_test_cpu(cpu, p->cpus_ptr)) { env->flags |= LBF_DST_PINNED; env->new_dst_cpu = cpu; break; @@ -7559,7 +7320,7 @@ static struct task_struct *detach_one_task(struct lb_env *env) static const unsigned int sched_nr_migrate_break = 32; /* - * detach_tasks() -- tries to detach up to imbalance weighted load from + * detach_tasks() -- tries to detach up to imbalance runnable load from * busiest_rq, as part of a balancing operation within domain "sd". * * Returns number of detached tasks if successful and 0 otherwise. @@ -7627,7 +7388,7 @@ static int detach_tasks(struct lb_env *env) /* * We only want to steal up to the prescribed amount of - * weighted load. + * runnable load. */ if (env->imbalance <= 0) break; @@ -7696,6 +7457,7 @@ static void attach_tasks(struct lb_env *env) rq_unlock(env->dst_rq, &rf); } +#ifdef CONFIG_NO_HZ_COMMON static inline bool cfs_rq_has_blocked(struct cfs_rq *cfs_rq) { if (cfs_rq->avg.load_avg) @@ -7723,6 +7485,19 @@ static inline bool others_have_blocked(struct rq *rq) return false; } +static inline void update_blocked_load_status(struct rq *rq, bool has_blocked) +{ + rq->last_blocked_load_update_tick = jiffies; + + if (!has_blocked) + rq->has_blocked_load = 0; +} +#else +static inline bool cfs_rq_has_blocked(struct cfs_rq *cfs_rq) { return false; } +static inline bool others_have_blocked(struct rq *rq) { return false; } +static inline void update_blocked_load_status(struct rq *rq, bool has_blocked) {} +#endif + #ifdef CONFIG_FAIR_GROUP_SCHED static inline bool cfs_rq_is_decayed(struct cfs_rq *cfs_rq) @@ -7788,11 +7563,7 @@ static void update_blocked_averages(int cpu) if (others_have_blocked(rq)) done = false; -#ifdef CONFIG_NO_HZ_COMMON - rq->last_blocked_load_update_tick = jiffies; - if (done) - rq->has_blocked_load = 0; -#endif + update_blocked_load_status(rq, !done); rq_unlock_irqrestore(rq, &rf); } @@ -7858,11 +7629,7 @@ static inline void update_blocked_averages(int cpu) update_rt_rq_load_avg(rq_clock_pelt(rq), rq, curr_class == &rt_sched_class); update_dl_rq_load_avg(rq_clock_pelt(rq), rq, curr_class == &dl_sched_class); update_irq_load_avg(rq, 0); -#ifdef CONFIG_NO_HZ_COMMON - rq->last_blocked_load_update_tick = jiffies; - if (!cfs_rq_has_blocked(cfs_rq) && !others_have_blocked(rq)) - rq->has_blocked_load = 0; -#endif + update_blocked_load_status(rq, cfs_rq_has_blocked(cfs_rq) || others_have_blocked(rq)); rq_unlock_irqrestore(rq, &rf); } @@ -7880,7 +7647,6 @@ static unsigned long task_h_load(struct task_struct *p) struct sg_lb_stats { unsigned long avg_load; /*Avg load across the CPUs of the group */ unsigned long group_load; /* Total load over the CPUs of the group */ - unsigned long sum_weighted_load; /* Weighted load of group's tasks */ unsigned long load_per_task; unsigned long group_capacity; unsigned long group_util; /* Total utilization of the group */ @@ -7934,38 +7700,10 @@ static inline void init_sd_lb_stats(struct sd_lb_stats *sds) }; } -/** - * get_sd_load_idx - Obtain the load index for a given sched domain. - * @sd: The sched_domain whose load_idx is to be obtained. - * @idle: The idle status of the CPU for whose sd load_idx is obtained. - * - * Return: The load index. - */ -static inline int get_sd_load_idx(struct sched_domain *sd, - enum cpu_idle_type idle) -{ - int load_idx; - - switch (idle) { - case CPU_NOT_IDLE: - load_idx = sd->busy_idx; - break; - - case CPU_NEWLY_IDLE: - load_idx = sd->newidle_idx; - break; - default: - load_idx = sd->idle_idx; - break; - } - - return load_idx; -} - static unsigned long scale_rt_capacity(struct sched_domain *sd, int cpu) { struct rq *rq = cpu_rq(cpu); - unsigned long max = arch_scale_cpu_capacity(sd, cpu); + unsigned long max = arch_scale_cpu_capacity(cpu); unsigned long used, free; unsigned long irq; @@ -7990,7 +7728,7 @@ static void update_cpu_capacity(struct sched_domain *sd, int cpu) unsigned long capacity = scale_rt_capacity(sd, cpu); struct sched_group *sdg = sd->groups; - cpu_rq(cpu)->cpu_capacity_orig = arch_scale_cpu_capacity(sd, cpu); + cpu_rq(cpu)->cpu_capacity_orig = arch_scale_cpu_capacity(cpu); if (!capacity) capacity = 1; @@ -8100,7 +7838,7 @@ static inline int check_misfit_status(struct rq *rq, struct sched_domain *sd) /* * Group imbalance indicates (and tries to solve) the problem where balancing - * groups is inadequate due to ->cpus_allowed constraints. + * groups is inadequate due to ->cpus_ptr constraints. * * Imagine a situation of two groups of 4 CPUs each and 4 tasks each with a * cpumask covering 1 CPU of the first group and 3 CPUs of the second group. @@ -8250,9 +7988,6 @@ static inline void update_sg_lb_stats(struct lb_env *env, struct sg_lb_stats *sgs, int *sg_status) { - int local_group = cpumask_test_cpu(env->dst_cpu, sched_group_span(group)); - int load_idx = get_sd_load_idx(env->sd, env->idle); - unsigned long load; int i, nr_running; memset(sgs, 0, sizeof(*sgs)); @@ -8263,13 +7998,7 @@ static inline void update_sg_lb_stats(struct lb_env *env, if ((env->flags & LBF_NOHZ_STATS) && update_nohz_stats(rq, false)) env->flags |= LBF_NOHZ_AGAIN; - /* Bias balancing toward CPUs of our domain: */ - if (local_group) - load = target_load(i, load_idx); - else - load = source_load(i, load_idx); - - sgs->group_load += load; + sgs->group_load += cpu_runnable_load(rq); sgs->group_util += cpu_util(i); sgs->sum_nr_running += rq->cfs.h_nr_running; @@ -8284,7 +8013,6 @@ static inline void update_sg_lb_stats(struct lb_env *env, sgs->nr_numa_running += rq->nr_numa_running; sgs->nr_preferred_running += rq->nr_preferred_running; #endif - sgs->sum_weighted_load += weighted_cpuload(rq); /* * No need to call idle_cpu() if nr_running is not 0 */ @@ -8303,7 +8031,7 @@ static inline void update_sg_lb_stats(struct lb_env *env, sgs->avg_load = (sgs->group_load*SCHED_CAPACITY_SCALE) / sgs->group_capacity; if (sgs->sum_nr_running) - sgs->load_per_task = sgs->sum_weighted_load / sgs->sum_nr_running; + sgs->load_per_task = sgs->group_load / sgs->sum_nr_running; sgs->group_weight = group->group_weight; @@ -8517,8 +8245,12 @@ next_group: /* Update over-utilization (tipping point, U >= 0) indicator */ WRITE_ONCE(rd->overutilized, sg_status & SG_OVERUTILIZED); + trace_sched_overutilized_tp(rd, sg_status & SG_OVERUTILIZED); } else if (sg_status & SG_OVERUTILIZED) { - WRITE_ONCE(env->dst_rq->rd->overutilized, SG_OVERUTILIZED); + struct root_domain *rd = env->dst_rq->rd; + + WRITE_ONCE(rd->overutilized, SG_OVERUTILIZED); + trace_sched_overutilized_tp(rd, SG_OVERUTILIZED); } } @@ -8724,7 +8456,7 @@ static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *s * find_busiest_group - Returns the busiest group within the sched_domain * if there is an imbalance. * - * Also calculates the amount of weighted load which should be moved + * Also calculates the amount of runnable load which should be moved * to restore balance. * * @env: The load balancing environment. @@ -8769,7 +8501,7 @@ static struct sched_group *find_busiest_group(struct lb_env *env) /* * If the busiest group is imbalanced the below checks don't * work because they assume all things are equal, which typically - * isn't true due to cpus_allowed constraints and the like. + * isn't true due to cpus_ptr constraints and the like. */ if (busiest->group_type == group_imbalanced) goto force_balance; @@ -8843,7 +8575,7 @@ static struct rq *find_busiest_queue(struct lb_env *env, int i; for_each_cpu_and(i, sched_group_span(group), env->cpus) { - unsigned long capacity, wl; + unsigned long capacity, load; enum fbq_type rt; rq = cpu_rq(i); @@ -8897,30 +8629,30 @@ static struct rq *find_busiest_queue(struct lb_env *env, rq->nr_running == 1) continue; - wl = weighted_cpuload(rq); + load = cpu_runnable_load(rq); /* - * When comparing with imbalance, use weighted_cpuload() + * When comparing with imbalance, use cpu_runnable_load() * which is not scaled with the CPU capacity. */ - if (rq->nr_running == 1 && wl > env->imbalance && + if (rq->nr_running == 1 && load > env->imbalance && !check_cpu_capacity(rq, env->sd)) continue; /* * For the load comparisons with the other CPU's, consider - * the weighted_cpuload() scaled with the CPU capacity, so + * the cpu_runnable_load() scaled with the CPU capacity, so * that the load can be moved away from the CPU that is * potentially running at a lower capacity. * - * Thus we're looking for max(wl_i / capacity_i), crosswise + * Thus we're looking for max(load_i / capacity_i), crosswise * multiplication to rid ourselves of the division works out - * to: wl_i * capacity_j > wl_j * capacity_i; where j is + * to: load_i * capacity_j > load_j * capacity_i; where j is * our previous maximum. */ - if (wl * busiest_capacity > busiest_load * capacity) { - busiest_load = wl; + if (load * busiest_capacity > busiest_load * capacity) { + busiest_load = load; busiest_capacity = capacity; busiest = rq; } @@ -9211,7 +8943,7 @@ more_balance: * if the curr task on busiest CPU can't be * moved to this_cpu: */ - if (!cpumask_test_cpu(this_cpu, &busiest->curr->cpus_allowed)) { + if (!cpumask_test_cpu(this_cpu, busiest->curr->cpus_ptr)) { raw_spin_unlock_irqrestore(&busiest->lock, flags); env.flags |= LBF_ALL_PINNED; @@ -9880,7 +9612,6 @@ static bool _nohz_idle_balance(struct rq *this_rq, unsigned int flags, rq_lock_irqsave(rq, &rf); update_rq_clock(rq); - cpu_load_update_idle(rq); rq_unlock_irqrestore(rq, &rf); if (flags & NOHZ_BALANCE_KICK) @@ -10691,6 +10422,10 @@ const struct sched_class fair_sched_class = { #ifdef CONFIG_FAIR_GROUP_SCHED .task_change_group = task_change_group_fair, #endif + +#ifdef CONFIG_UCLAMP_TASK + .uclamp_enabled = 1, +#endif }; #ifdef CONFIG_SCHED_DEBUG @@ -10738,3 +10473,83 @@ __init void init_sched_fair_class(void) #endif /* SMP */ } + +/* + * Helper functions to facilitate extracting info from tracepoints. + */ + +const struct sched_avg *sched_trace_cfs_rq_avg(struct cfs_rq *cfs_rq) +{ +#ifdef CONFIG_SMP + return cfs_rq ? &cfs_rq->avg : NULL; +#else + return NULL; +#endif +} +EXPORT_SYMBOL_GPL(sched_trace_cfs_rq_avg); + +char *sched_trace_cfs_rq_path(struct cfs_rq *cfs_rq, char *str, int len) +{ + if (!cfs_rq) { + if (str) + strlcpy(str, "(null)", len); + else + return NULL; + } + + cfs_rq_tg_path(cfs_rq, str, len); + return str; +} +EXPORT_SYMBOL_GPL(sched_trace_cfs_rq_path); + +int sched_trace_cfs_rq_cpu(struct cfs_rq *cfs_rq) +{ + return cfs_rq ? cpu_of(rq_of(cfs_rq)) : -1; +} +EXPORT_SYMBOL_GPL(sched_trace_cfs_rq_cpu); + +const struct sched_avg *sched_trace_rq_avg_rt(struct rq *rq) +{ +#ifdef CONFIG_SMP + return rq ? &rq->avg_rt : NULL; +#else + return NULL; +#endif +} +EXPORT_SYMBOL_GPL(sched_trace_rq_avg_rt); + +const struct sched_avg *sched_trace_rq_avg_dl(struct rq *rq) +{ +#ifdef CONFIG_SMP + return rq ? &rq->avg_dl : NULL; +#else + return NULL; +#endif +} +EXPORT_SYMBOL_GPL(sched_trace_rq_avg_dl); + +const struct sched_avg *sched_trace_rq_avg_irq(struct rq *rq) +{ +#if defined(CONFIG_SMP) && defined(CONFIG_HAVE_SCHED_AVG_IRQ) + return rq ? &rq->avg_irq : NULL; +#else + return NULL; +#endif +} +EXPORT_SYMBOL_GPL(sched_trace_rq_avg_irq); + +int sched_trace_rq_cpu(struct rq *rq) +{ + return rq ? cpu_of(rq) : -1; +} +EXPORT_SYMBOL_GPL(sched_trace_rq_cpu); + +const struct cpumask *sched_trace_rd_span(struct root_domain *rd) +{ +#ifdef CONFIG_SMP + return rd ? rd->span : NULL; +#else + return NULL; +#endif +} +EXPORT_SYMBOL_GPL(sched_trace_rd_span); diff --git a/kernel/sched/features.h b/kernel/sched/features.h index 858589b83377..2410db5e9a35 100644 --- a/kernel/sched/features.h +++ b/kernel/sched/features.h @@ -39,7 +39,6 @@ SCHED_FEAT(WAKEUP_PREEMPTION, true) SCHED_FEAT(HRTICK, false) SCHED_FEAT(DOUBLE_TICK, false) -SCHED_FEAT(LB_BIAS, false) /* * Decrement CPU capacity based on time not spent running tasks diff --git a/kernel/sched/pelt.c b/kernel/sched/pelt.c index befce29bd882..a96db50d40e0 100644 --- a/kernel/sched/pelt.c +++ b/kernel/sched/pelt.c @@ -28,6 +28,8 @@ #include "sched.h" #include "pelt.h" +#include <trace/events/sched.h> + /* * Approximate: * val * y^n, where y^32 ~= 0.5 (~1 scheduling period) @@ -265,6 +267,7 @@ int __update_load_avg_blocked_se(u64 now, struct sched_entity *se) { if (___update_load_sum(now, &se->avg, 0, 0, 0)) { ___update_load_avg(&se->avg, se_weight(se), se_runnable(se)); + trace_pelt_se_tp(se); return 1; } @@ -278,6 +281,7 @@ int __update_load_avg_se(u64 now, struct cfs_rq *cfs_rq, struct sched_entity *se ___update_load_avg(&se->avg, se_weight(se), se_runnable(se)); cfs_se_util_change(&se->avg); + trace_pelt_se_tp(se); return 1; } @@ -292,6 +296,7 @@ int __update_load_avg_cfs_rq(u64 now, struct cfs_rq *cfs_rq) cfs_rq->curr != NULL)) { ___update_load_avg(&cfs_rq->avg, 1, 1); + trace_pelt_cfs_tp(cfs_rq); return 1; } @@ -317,6 +322,7 @@ int update_rt_rq_load_avg(u64 now, struct rq *rq, int running) running)) { ___update_load_avg(&rq->avg_rt, 1, 1); + trace_pelt_rt_tp(rq); return 1; } @@ -340,6 +346,7 @@ int update_dl_rq_load_avg(u64 now, struct rq *rq, int running) running)) { ___update_load_avg(&rq->avg_dl, 1, 1); + trace_pelt_dl_tp(rq); return 1; } @@ -366,7 +373,7 @@ int update_irq_load_avg(struct rq *rq, u64 running) * reflect the real amount of computation */ running = cap_scale(running, arch_scale_freq_capacity(cpu_of(rq))); - running = cap_scale(running, arch_scale_cpu_capacity(NULL, cpu_of(rq))); + running = cap_scale(running, arch_scale_cpu_capacity(cpu_of(rq))); /* * We know the time that has been used by interrupt since last update @@ -388,8 +395,10 @@ int update_irq_load_avg(struct rq *rq, u64 running) 1, 1); - if (ret) + if (ret) { ___update_load_avg(&rq->avg_irq, 1, 1); + trace_pelt_irq_tp(rq); + } return ret; } diff --git a/kernel/sched/pelt.h b/kernel/sched/pelt.h index 7489d5f56960..afff644da065 100644 --- a/kernel/sched/pelt.h +++ b/kernel/sched/pelt.h @@ -79,7 +79,7 @@ static inline void update_rq_clock_pelt(struct rq *rq, s64 delta) * Scale the elapsed time to reflect the real amount of * computation */ - delta = cap_scale(delta, arch_scale_cpu_capacity(NULL, cpu_of(rq))); + delta = cap_scale(delta, arch_scale_cpu_capacity(cpu_of(rq))); delta = cap_scale(delta, arch_scale_freq_capacity(cpu_of(rq))); rq->clock_pelt += delta; diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c index 1e6b909dca36..a532558a5176 100644 --- a/kernel/sched/rt.c +++ b/kernel/sched/rt.c @@ -1614,7 +1614,7 @@ static void put_prev_task_rt(struct rq *rq, struct task_struct *p) static int pick_rt_task(struct rq *rq, struct task_struct *p, int cpu) { if (!task_running(rq, p) && - cpumask_test_cpu(cpu, &p->cpus_allowed)) + cpumask_test_cpu(cpu, p->cpus_ptr)) return 1; return 0; @@ -1751,7 +1751,7 @@ static struct rq *find_lock_lowest_rq(struct task_struct *task, struct rq *rq) * Also make sure that it wasn't scheduled on its rq. */ if (unlikely(task_rq(task) != rq || - !cpumask_test_cpu(lowest_rq->cpu, &task->cpus_allowed) || + !cpumask_test_cpu(lowest_rq->cpu, task->cpus_ptr) || task_running(rq, task) || !rt_task(task) || !task_on_rq_queued(task))) { @@ -2400,6 +2400,10 @@ const struct sched_class rt_sched_class = { .switched_to = switched_to_rt, .update_curr = update_curr_rt, + +#ifdef CONFIG_UCLAMP_TASK + .uclamp_enabled = 1, +#endif }; #ifdef CONFIG_RT_GROUP_SCHED diff --git a/kernel/sched/sched-pelt.h b/kernel/sched/sched-pelt.h index a26473674fb7..c529706bed11 100644 --- a/kernel/sched/sched-pelt.h +++ b/kernel/sched/sched-pelt.h @@ -1,7 +1,7 @@ /* SPDX-License-Identifier: GPL-2.0 */ /* Generated by Documentation/scheduler/sched-pelt; do not modify. */ -static const u32 runnable_avg_yN_inv[] = { +static const u32 runnable_avg_yN_inv[] __maybe_unused = { 0xffffffff, 0xfa83b2da, 0xf5257d14, 0xefe4b99a, 0xeac0c6e6, 0xe5b906e6, 0xe0ccdeeb, 0xdbfbb796, 0xd744fcc9, 0xd2a81d91, 0xce248c14, 0xc9b9bd85, 0xc5672a10, 0xc12c4cc9, 0xbd08a39e, 0xb8fbaf46, 0xb504f333, 0xb123f581, diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index b52ed1ada0be..802b1f3405f2 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -96,12 +96,6 @@ extern atomic_long_t calc_load_tasks; extern void calc_global_load_tick(struct rq *this_rq); extern long calc_load_fold_active(struct rq *this_rq, long adjust); -#ifdef CONFIG_SMP -extern void cpu_load_update_active(struct rq *this_rq); -#else -static inline void cpu_load_update_active(struct rq *this_rq) { } -#endif - /* * Helpers for converting nanosecond timing to jiffy resolution */ @@ -344,8 +338,10 @@ struct cfs_bandwidth { u64 runtime_expires; int expires_seq; - short idle; - short period_active; + u8 idle; + u8 period_active; + u8 distribute_running; + u8 slack_started; struct hrtimer period_timer; struct hrtimer slack_timer; struct list_head throttled_cfs_rq; @@ -354,8 +350,6 @@ struct cfs_bandwidth { int nr_periods; int nr_throttled; u64 throttled_time; - - bool distribute_running; #endif }; @@ -797,6 +791,48 @@ extern void rto_push_irq_work_func(struct irq_work *work); #endif #endif /* CONFIG_SMP */ +#ifdef CONFIG_UCLAMP_TASK +/* + * struct uclamp_bucket - Utilization clamp bucket + * @value: utilization clamp value for tasks on this clamp bucket + * @tasks: number of RUNNABLE tasks on this clamp bucket + * + * Keep track of how many tasks are RUNNABLE for a given utilization + * clamp value. + */ +struct uclamp_bucket { + unsigned long value : bits_per(SCHED_CAPACITY_SCALE); + unsigned long tasks : BITS_PER_LONG - bits_per(SCHED_CAPACITY_SCALE); +}; + +/* + * struct uclamp_rq - rq's utilization clamp + * @value: currently active clamp values for a rq + * @bucket: utilization clamp buckets affecting a rq + * + * Keep track of RUNNABLE tasks on a rq to aggregate their clamp values. + * A clamp value is affecting a rq when there is at least one task RUNNABLE + * (or actually running) with that value. + * + * There are up to UCLAMP_CNT possible different clamp values, currently there + * are only two: minimum utilization and maximum utilization. + * + * All utilization clamping values are MAX aggregated, since: + * - for util_min: we want to run the CPU at least at the max of the minimum + * utilization required by its currently RUNNABLE tasks. + * - for util_max: we want to allow the CPU to run up to the max of the + * maximum utilization allowed by its currently RUNNABLE tasks. + * + * Since on each system we expect only a limited number of different + * utilization clamp values (UCLAMP_BUCKETS), use a simple array to track + * the metrics required to compute all the per-rq utilization clamp values. + */ +struct uclamp_rq { + unsigned int value; + struct uclamp_bucket bucket[UCLAMP_BUCKETS]; +}; +#endif /* CONFIG_UCLAMP_TASK */ + /* * This is the main, per-CPU runqueue data structure. * @@ -818,8 +854,6 @@ struct rq { unsigned int nr_preferred_running; unsigned int numa_migrate_on; #endif - #define CPU_LOAD_IDX_MAX 5 - unsigned long cpu_load[CPU_LOAD_IDX_MAX]; #ifdef CONFIG_NO_HZ_COMMON #ifdef CONFIG_SMP unsigned long last_load_update_tick; @@ -830,11 +864,16 @@ struct rq { atomic_t nohz_flags; #endif /* CONFIG_NO_HZ_COMMON */ - /* capture load from *all* tasks on this CPU: */ - struct load_weight load; unsigned long nr_load_updates; u64 nr_switches; +#ifdef CONFIG_UCLAMP_TASK + /* Utilization clamp values based on CPU's RUNNABLE tasks */ + struct uclamp_rq uclamp[UCLAMP_CNT] ____cacheline_aligned; + unsigned int uclamp_flags; +#define UCLAMP_FLAG_IDLE 0x01 +#endif + struct cfs_rq cfs; struct rt_rq rt; struct dl_rq dl; @@ -1649,6 +1688,10 @@ extern const u32 sched_prio_to_wmult[40]; struct sched_class { const struct sched_class *next; +#ifdef CONFIG_UCLAMP_TASK + int uclamp_enabled; +#endif + void (*enqueue_task) (struct rq *rq, struct task_struct *p, int flags); void (*dequeue_task) (struct rq *rq, struct task_struct *p, int flags); void (*yield_task) (struct rq *rq); @@ -2222,6 +2265,48 @@ static inline void cpufreq_update_util(struct rq *rq, unsigned int flags) static inline void cpufreq_update_util(struct rq *rq, unsigned int flags) {} #endif /* CONFIG_CPU_FREQ */ +#ifdef CONFIG_UCLAMP_TASK +unsigned int uclamp_eff_value(struct task_struct *p, unsigned int clamp_id); + +static __always_inline +unsigned int uclamp_util_with(struct rq *rq, unsigned int util, + struct task_struct *p) +{ + unsigned int min_util = READ_ONCE(rq->uclamp[UCLAMP_MIN].value); + unsigned int max_util = READ_ONCE(rq->uclamp[UCLAMP_MAX].value); + + if (p) { + min_util = max(min_util, uclamp_eff_value(p, UCLAMP_MIN)); + max_util = max(max_util, uclamp_eff_value(p, UCLAMP_MAX)); + } + + /* + * Since CPU's {min,max}_util clamps are MAX aggregated considering + * RUNNABLE tasks with _different_ clamps, we can end up with an + * inversion. Fix it now when the clamps are applied. + */ + if (unlikely(min_util >= max_util)) + return min_util; + + return clamp(util, min_util, max_util); +} + +static inline unsigned int uclamp_util(struct rq *rq, unsigned int util) +{ + return uclamp_util_with(rq, util, NULL); +} +#else /* CONFIG_UCLAMP_TASK */ +static inline unsigned int uclamp_util_with(struct rq *rq, unsigned int util, + struct task_struct *p) +{ + return util; +} +static inline unsigned int uclamp_util(struct rq *rq, unsigned int util) +{ + return util; +} +#endif /* CONFIG_UCLAMP_TASK */ + #ifdef arch_scale_freq_capacity # ifndef arch_scale_freq_invariant # define arch_scale_freq_invariant() true @@ -2237,7 +2322,6 @@ static inline unsigned long capacity_orig_of(int cpu) } #endif -#ifdef CONFIG_CPU_FREQ_GOV_SCHEDUTIL /** * enum schedutil_type - CPU utilization type * @FREQUENCY_UTIL: Utilization used to select frequency @@ -2253,15 +2337,11 @@ enum schedutil_type { ENERGY_UTIL, }; -unsigned long schedutil_freq_util(int cpu, unsigned long util_cfs, - unsigned long max, enum schedutil_type type); - -static inline unsigned long schedutil_energy_util(int cpu, unsigned long cfs) -{ - unsigned long max = arch_scale_cpu_capacity(NULL, cpu); +#ifdef CONFIG_CPU_FREQ_GOV_SCHEDUTIL - return schedutil_freq_util(cpu, cfs, max, ENERGY_UTIL); -} +unsigned long schedutil_cpu_util(int cpu, unsigned long util_cfs, + unsigned long max, enum schedutil_type type, + struct task_struct *p); static inline unsigned long cpu_bw_dl(struct rq *rq) { @@ -2290,11 +2370,13 @@ static inline unsigned long cpu_util_rt(struct rq *rq) return READ_ONCE(rq->avg_rt.util_avg); } #else /* CONFIG_CPU_FREQ_GOV_SCHEDUTIL */ -static inline unsigned long schedutil_energy_util(int cpu, unsigned long cfs) +static inline unsigned long schedutil_cpu_util(int cpu, unsigned long util_cfs, + unsigned long max, enum schedutil_type type, + struct task_struct *p) { - return cfs; + return 0; } -#endif +#endif /* CONFIG_CPU_FREQ_GOV_SCHEDUTIL */ #ifdef CONFIG_HAVE_SCHED_AVG_IRQ static inline unsigned long cpu_util_irq(struct rq *rq) diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c index f53f89df837d..f751ce0b783e 100644 --- a/kernel/sched/topology.c +++ b/kernel/sched/topology.c @@ -1344,11 +1344,6 @@ sd_init(struct sched_domain_topology_level *tl, .imbalance_pct = 125, .cache_nice_tries = 0, - .busy_idx = 0, - .idle_idx = 0, - .newidle_idx = 0, - .wake_idx = 0, - .forkexec_idx = 0, .flags = 1*SD_LOAD_BALANCE | 1*SD_BALANCE_NEWIDLE @@ -1400,13 +1395,10 @@ sd_init(struct sched_domain_topology_level *tl, } else if (sd->flags & SD_SHARE_PKG_RESOURCES) { sd->imbalance_pct = 117; sd->cache_nice_tries = 1; - sd->busy_idx = 2; #ifdef CONFIG_NUMA } else if (sd->flags & SD_NUMA) { sd->cache_nice_tries = 2; - sd->busy_idx = 3; - sd->idle_idx = 2; sd->flags &= ~SD_PREFER_SIBLING; sd->flags |= SD_SERIALIZE; @@ -1419,8 +1411,6 @@ sd_init(struct sched_domain_topology_level *tl, #endif } else { sd->cache_nice_tries = 1; - sd->busy_idx = 2; - sd->idle_idx = 1; } /* @@ -1884,10 +1874,10 @@ static struct sched_domain_topology_level unsigned long cap; /* Is there any asymmetry? */ - cap = arch_scale_cpu_capacity(NULL, cpumask_first(cpu_map)); + cap = arch_scale_cpu_capacity(cpumask_first(cpu_map)); for_each_cpu(i, cpu_map) { - if (arch_scale_cpu_capacity(NULL, i) != cap) { + if (arch_scale_cpu_capacity(i) != cap) { asym = true; break; } @@ -1902,7 +1892,7 @@ static struct sched_domain_topology_level * to everyone. */ for_each_cpu(i, cpu_map) { - unsigned long max_capacity = arch_scale_cpu_capacity(NULL, i); + unsigned long max_capacity = arch_scale_cpu_capacity(i); int tl_id = 0; for_each_sd_topology(tl) { @@ -1912,7 +1902,7 @@ static struct sched_domain_topology_level for_each_cpu_and(j, tl->mask(i), cpu_map) { unsigned long capacity; - capacity = arch_scale_cpu_capacity(NULL, j); + capacity = arch_scale_cpu_capacity(j); if (capacity <= max_capacity) continue; diff --git a/kernel/sched/wait.c b/kernel/sched/wait.c index fa0f9adfb752..c1e566a114ca 100644 --- a/kernel/sched/wait.c +++ b/kernel/sched/wait.c @@ -118,16 +118,12 @@ static void __wake_up_common_lock(struct wait_queue_head *wq_head, unsigned int bookmark.func = NULL; INIT_LIST_HEAD(&bookmark.entry); - spin_lock_irqsave(&wq_head->lock, flags); - nr_exclusive = __wake_up_common(wq_head, mode, nr_exclusive, wake_flags, key, &bookmark); - spin_unlock_irqrestore(&wq_head->lock, flags); - - while (bookmark.flags & WQ_FLAG_BOOKMARK) { + do { spin_lock_irqsave(&wq_head->lock, flags); nr_exclusive = __wake_up_common(wq_head, mode, nr_exclusive, wake_flags, key, &bookmark); spin_unlock_irqrestore(&wq_head->lock, flags); - } + } while (bookmark.flags & WQ_FLAG_BOOKMARK); } /** diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 1beca96fb625..1c1ad1e14f21 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -452,6 +452,22 @@ static struct ctl_table kern_table[] = { .mode = 0644, .proc_handler = sched_rr_handler, }, +#ifdef CONFIG_UCLAMP_TASK + { + .procname = "sched_util_clamp_min", + .data = &sysctl_sched_uclamp_util_min, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = sysctl_sched_uclamp_handler, + }, + { + .procname = "sched_util_clamp_max", + .data = &sysctl_sched_uclamp_util_max, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = sysctl_sched_uclamp_handler, + }, +#endif #ifdef CONFIG_SCHED_AUTOGROUP { .procname = "sched_autogroup_enabled", diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index f4ee1a3428ae..be9707f68024 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -782,7 +782,6 @@ static void tick_nohz_stop_tick(struct tick_sched *ts, int cpu) */ if (!ts->tick_stopped) { calc_load_nohz_start(); - cpu_load_update_nohz_start(); quiet_vmstat(); ts->last_tick = hrtimer_get_expires(&ts->sched_timer); @@ -829,7 +828,6 @@ static void tick_nohz_restart_sched_tick(struct tick_sched *ts, ktime_t now) { /* Update jiffies first */ tick_do_update_jiffies64(now); - cpu_load_update_nohz_stop(); /* * Clear the timer idle flag, so we avoid IPIs on remote queueing and diff --git a/kernel/trace/trace_hwlat.c b/kernel/trace/trace_hwlat.c index 1e6db9cbe4dc..fa95139445b2 100644 --- a/kernel/trace/trace_hwlat.c +++ b/kernel/trace/trace_hwlat.c @@ -277,7 +277,7 @@ static void move_to_next_cpu(void) * of this thread, than stop migrating for the duration * of the current test. */ - if (!cpumask_equal(current_mask, ¤t->cpus_allowed)) + if (!cpumask_equal(current_mask, current->cpus_ptr)) goto disable; get_online_cpus(); diff --git a/lib/smp_processor_id.c b/lib/smp_processor_id.c index 157d9e31f6c2..60ba93fc42ce 100644 --- a/lib/smp_processor_id.c +++ b/lib/smp_processor_id.c @@ -23,7 +23,7 @@ unsigned int check_preemption_disabled(const char *what1, const char *what2) * Kernel threads bound to a single CPU can safely use * smp_processor_id(): */ - if (cpumask_equal(¤t->cpus_allowed, cpumask_of(this_cpu))) + if (cpumask_equal(current->cpus_ptr, cpumask_of(this_cpu))) goto out; /* diff --git a/samples/trace_events/trace-events-sample.c b/samples/trace_events/trace-events-sample.c index 1da597aa6141..1a72b7d95cdc 100644 --- a/samples/trace_events/trace-events-sample.c +++ b/samples/trace_events/trace-events-sample.c @@ -34,7 +34,7 @@ static void simple_thread_func(int cnt) /* Silly tracepoints */ trace_foo_bar("hello", cnt, array, random_strings[len], - ¤t->cpus_allowed); + current->cpus_ptr); trace_foo_with_template_simple("HELLO", cnt); |