summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
-rw-r--r--Documentation/scheduler/sched-pelt.c3
-rw-r--r--arch/arm/kernel/topology.c2
-rw-r--r--arch/ia64/kernel/mca.c2
-rw-r--r--arch/mips/include/asm/switch_to.h4
-rw-r--r--arch/mips/kernel/mips-mt-fpaff.c2
-rw-r--r--arch/mips/kernel/traps.c6
-rw-r--r--arch/powerpc/platforms/cell/spufs/sched.c2
-rw-r--r--arch/x86/kernel/cpu/resctrl/pseudo_lock.c2
-rw-r--r--drivers/base/arch_topology.c6
-rw-r--r--drivers/infiniband/hw/hfi1/affinity.c6
-rw-r--r--drivers/infiniband/hw/hfi1/sdma.c3
-rw-r--r--drivers/infiniband/hw/qib/qib_file_ops.c7
-rw-r--r--fs/proc/array.c4
-rw-r--r--include/linux/arch_topology.h2
-rw-r--r--include/linux/energy_model.h2
-rw-r--r--include/linux/log2.h34
-rw-r--r--include/linux/sched.h79
-rw-r--r--include/linux/sched/nohz.h8
-rw-r--r--include/linux/sched/sysctl.h11
-rw-r--r--include/linux/sched/topology.h25
-rw-r--r--include/trace/events/sched.h31
-rw-r--r--include/uapi/linux/sched.h14
-rw-r--r--include/uapi/linux/sched/types.h66
-rw-r--r--init/Kconfig53
-rw-r--r--init/init_task.c3
-rw-r--r--kernel/cgroup/cpuset.c2
-rw-r--r--kernel/fork.c2
-rw-r--r--kernel/power/energy_model.c2
-rw-r--r--kernel/sched/autogroup.c2
-rw-r--r--kernel/sched/core.c533
-rw-r--r--kernel/sched/cpudeadline.c4
-rw-r--r--kernel/sched/cpufreq_schedutil.c24
-rw-r--r--kernel/sched/cpupri.c4
-rw-r--r--kernel/sched/deadline.c8
-rw-r--r--kernel/sched/debug.c43
-rw-r--r--kernel/sched/fair.c623
-rw-r--r--kernel/sched/features.h1
-rw-r--r--kernel/sched/pelt.c13
-rw-r--r--kernel/sched/pelt.h2
-rw-r--r--kernel/sched/rt.c8
-rw-r--r--kernel/sched/sched-pelt.h2
-rw-r--r--kernel/sched/sched.h134
-rw-r--r--kernel/sched/topology.c18
-rw-r--r--kernel/sched/wait.c8
-rw-r--r--kernel/sysctl.c16
-rw-r--r--kernel/time/tick-sched.c2
-rw-r--r--kernel/trace/trace_hwlat.c2
-rw-r--r--lib/smp_processor_id.c2
-rw-r--r--samples/trace_events/trace-events-sample.c2
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(&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);
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, &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();
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(&current->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 = &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));
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 = &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();
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(&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)
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