Merge branch 'sched-core-for-linus' of git://git.kernel.org/pub/scm/l…

…inux/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

@@ -1038,15 +1038,15 @@ 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;
 
 	/*
 	 * 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