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()
  ...

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);
 

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

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);

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)

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:

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(&current->cpus_allowed, &mt_fpu_cpumask)) {
+		if (cpumask_intersects(&current->cpus_mask, &mt_fpu_cpumask)) {
 			cpumask_t tmask;
 
 			current->thread.user_cpus_allowed
-				= current->cpus_allowed;
-			cpumask_and(&tmask, &current->cpus_allowed,
+				= current->cpus_mask;
+			cpumask_and(&tmask, &current->cpus_mask,
 				    &mt_fpu_cpumask);
 			set_cpus_allowed_ptr(current, &tmask);
 			set_thread_flag(TIF_FPUBOUND);

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, &current->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();

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(&current->cpus_allowed, &plr->d->cpu_mask)) {
+	if (!cpumask_subset(current->cpus_ptr, &plr->d->cpu_mask)) {
 		mutex_unlock(&rdtgroup_mutex);
 		return -EINVAL;
 	}

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);
 	}

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 = &current->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));

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 = &current->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();

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(&current->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(&current->cpus_allowed);
-		const unsigned int weight =
-			cpumask_weight(&current->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)

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)

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);
 }

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);
 

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 */

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

include/linux/sched/nohz.h

@@ -6,14 +6,6 @@
  * This is the interface between the scheduler and nohz/dynticks:
  */
 
-#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);

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);

include/linux/sched/topology.h

@@ -6,12 +6,6 @@
 
 #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:
  */
@@ -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));

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 */

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 */

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 */

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:

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,

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, &current->cpus_allowed);
+	set_cpus_allowed_ptr(task, current->cpus_ptr);
 	task->mems_allowed = current->mems_allowed;
 }
 

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

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));

kernel/sched/autogroup.c

@@ -259,7 +259,6 @@ void proc_sched_autogroup_show_task(struct task_struct *p, struct seq_file *m)
 }
 #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

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);

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);
 }
 
 /**

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

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))) {

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
 

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

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;
 }

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;

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

kernel/sched/sched-pelt.h

 /* 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,

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)

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;

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);
 }
 
 /**

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",

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

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, &current->cpus_allowed))
+	if (!cpumask_equal(current_mask, current->cpus_ptr))
 		goto disable;
 
 	get_online_cpus();

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(&current->cpus_allowed, cpumask_of(this_cpu)))
+	if (cpumask_equal(current->cpus_ptr, cpumask_of(this_cpu)))
 		goto out;
 
 	/*

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],
-		      &current->cpus_allowed);
+		      current->cpus_ptr);
 
 	trace_foo_with_template_simple("HELLO", cnt);