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:
 "The main updates in this cycle were:

   - Group balancing enhancements and cleanups (Brendan Jackman)

   - Move CPU isolation related functionality into its separate
     kernel/sched/isolation.c file, with related 'housekeeping_*()'
     namespace and nomenclature et al. (Frederic Weisbecker)

   - Improve the interactive/cpu-intense fairness calculation (Josef
     Bacik)

   - Improve the PELT code and related cleanups (Peter Zijlstra)

   - Improve the logic of pick_next_task_fair() (Uladzislau Rezki)

   - Improve the RT IPI based balancing logic (Steven Rostedt)

   - Various micro-optimizations:

   - better !CONFIG_SCHED_DEBUG optimizations (Patrick Bellasi)

   - better idle loop (Cheng Jian)

   - ... plus misc fixes, cleanups and updates"

* 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (54 commits)
  sched/core: Optimize sched_feat() for !CONFIG_SCHED_DEBUG builds
  sched/sysctl: Fix attributes of some extern declarations
  sched/isolation: Document isolcpus= boot parameter flags, mark it deprecated
  sched/isolation: Add basic isolcpus flags
  sched/isolation: Move isolcpus= handling to the housekeeping code
  sched/isolation: Handle the nohz_full= parameter
  sched/isolation: Introduce housekeeping flags
  sched/isolation: Split out new CONFIG_CPU_ISOLATION=y config from CONFIG_NO_HZ_FULL
  sched/isolation: Rename is_housekeeping_cpu() to housekeeping_cpu()
  sched/isolation: Use its own static key
  sched/isolation: Make the housekeeping cpumask private
  sched/isolation: Provide a dynamic off-case to housekeeping_any_cpu()
  sched/isolation, watchdog: Use housekeeping_cpumask() instead of ad-hoc version
  sched/isolation: Move housekeeping related code to its own file
  sched/idle: Micro-optimize the idle loop
  sched/isolcpus: Fix "isolcpus=" boot parameter handling when !CONFIG_CPUMASK_OFFSTACK
  x86/tsc: Append the 'tsc=' description for the 'tsc=unstable' boot parameter
  sched/rt: Simplify the IPI based RT balancing logic
  block/ioprio: Use a helper to check for RT prio
  sched/rt: Add a helper to test for a RT task
  ...

Documentation/admin-guide/kernel-parameters.txt

@@ -1730,20 +1730,33 @@
 	isapnp=		[ISAPNP]
 			Format: <RDP>,<reset>,<pci_scan>,<verbosity>
 
-	isolcpus=	[KNL,SMP] Isolate CPUs from the general scheduler.
-			The argument is a cpu list, as described above.
+	isolcpus=	[KNL,SMP] Isolate a given set of CPUs from disturbance.
+			[Deprecated - use cpusets instead]
+			Format: [flag-list,]<cpu-list>
+
+			Specify one or more CPUs to isolate from disturbances
+			specified in the flag list (default: domain):
+
+			nohz
+			  Disable the tick when a single task runs.
+			domain
+			  Isolate from the general SMP balancing and scheduling
+			  algorithms. Note that performing domain isolation this way
+			  is irreversible: it's not possible to bring back a CPU to
+			  the domains once isolated through isolcpus. It's strongly
+			  advised to use cpusets instead to disable scheduler load
+			  balancing through the "cpuset.sched_load_balance" file.
+			  It offers a much more flexible interface where CPUs can
+			  move in and out of an isolated set anytime.
+
+			  You can move a process onto or off an "isolated" CPU via
+			  the CPU affinity syscalls or cpuset.
+			  <cpu number> begins at 0 and the maximum value is
+			  "number of CPUs in system - 1".
+
+			The format of <cpu-list> is described above.
 
-			This option can be used to specify one or more CPUs
-			to isolate from the general SMP balancing and scheduling
-			algorithms. You can move a process onto or off an
-			"isolated" CPU via the CPU affinity syscalls or cpuset.
-			<cpu number> begins at 0 and the maximum value is
-			"number of CPUs in system - 1".
 
-			This option is the preferred way to isolate CPUs. The
-			alternative -- manually setting the CPU mask of all
-			tasks in the system -- can cause problems and
-			suboptimal load balancer performance.
 
 	iucv=		[HW,NET]
 
@@ -4209,6 +4222,9 @@
 			Used to run time disable IRQ_TIME_ACCOUNTING on any
 			platforms where RDTSC is slow and this accounting
 			can add overhead.
+			[x86] unstable: mark the TSC clocksource as unstable, this
+			marks the TSC unconditionally unstable at bootup and
+			avoids any further wobbles once the TSC watchdog notices.
 
 	turbografx.map[2|3]=	[HW,JOY]
 			TurboGraFX parallel port interface

drivers/base/cpu.c

@@ -18,6 +18,7 @@
 #include <linux/cpufeature.h>
 #include <linux/tick.h>
 #include <linux/pm_qos.h>
+#include <linux/sched/isolation.h>
 
 #include "base.h"
 
@@ -271,8 +272,16 @@ static ssize_t print_cpus_isolated(struct device *dev,
 				  struct device_attribute *attr, char *buf)
 {
 	int n = 0, len = PAGE_SIZE-2;
+	cpumask_var_t isolated;
 
-	n = scnprintf(buf, len, "%*pbl\n", cpumask_pr_args(cpu_isolated_map));
+	if (!alloc_cpumask_var(&isolated, GFP_KERNEL))
+		return -ENOMEM;
+
+	cpumask_andnot(isolated, cpu_possible_mask,
+		       housekeeping_cpumask(HK_FLAG_DOMAIN));
+	n = scnprintf(buf, len, "%*pbl\n", cpumask_pr_args(isolated));
+
+	free_cpumask_var(isolated);
 
 	return n;
 }

drivers/net/ethernet/tile/tilegx.c

@@ -40,7 +40,7 @@
 #include <linux/tcp.h>
 #include <linux/net_tstamp.h>
 #include <linux/ptp_clock_kernel.h>
-#include <linux/tick.h>
+#include <linux/sched/isolation.h>
 
 #include <asm/checksum.h>
 #include <asm/homecache.h>
@@ -2270,8 +2270,8 @@ static int __init tile_net_init_module(void)
 		tile_net_dev_init(name, mac);
 
 	if (!network_cpus_init())
-		cpumask_and(&network_cpus_map, housekeeping_cpumask(),
-			    cpu_online_mask);
+		cpumask_and(&network_cpus_map,
+			    housekeeping_cpumask(HK_FLAG_MISC), cpu_online_mask);
 
 	return 0;
 }

fs/proc/array.c

@@ -138,7 +138,7 @@ static const char * const task_state_array[] = {
 static inline const char *get_task_state(struct task_struct *tsk)
 {
 	BUILD_BUG_ON(1 + ilog2(TASK_REPORT_MAX) != ARRAY_SIZE(task_state_array));
-	return task_state_array[__get_task_state(tsk)];
+	return task_state_array[task_state_index(tsk)];
 }
 
 static inline int get_task_umask(struct task_struct *tsk)

include/linux/cpumask.h

@@ -131,6 +131,11 @@ static inline unsigned int cpumask_first(const struct cpumask *srcp)
 	return 0;
 }
 
+static inline unsigned int cpumask_last(const struct cpumask *srcp)
+{
+	return 0;
+}
+
 /* Valid inputs for n are -1 and 0. */
 static inline unsigned int cpumask_next(int n, const struct cpumask *srcp)
 {
@@ -179,6 +184,17 @@ static inline unsigned int cpumask_first(const struct cpumask *srcp)
 	return find_first_bit(cpumask_bits(srcp), nr_cpumask_bits);
 }
 
+/**
+ * cpumask_last - get the last CPU in a cpumask
+ * @srcp:	- the cpumask pointer
+ *
+ * Returns	>= nr_cpumask_bits if no CPUs set.
+ */
+static inline unsigned int cpumask_last(const struct cpumask *srcp)
+{
+	return find_last_bit(cpumask_bits(srcp), nr_cpumask_bits);
+}
+
 unsigned int cpumask_next(int n, const struct cpumask *srcp);
 
 /**

include/linux/ioprio.h

@@ -3,6 +3,7 @@
 #define IOPRIO_H
 
 #include <linux/sched.h>
+#include <linux/sched/rt.h>
 #include <linux/iocontext.h>
 
 /*
@@ -63,7 +64,7 @@ static inline int task_nice_ioclass(struct task_struct *task)
 {
 	if (task->policy == SCHED_IDLE)
 		return IOPRIO_CLASS_IDLE;
-	else if (task->policy == SCHED_FIFO || task->policy == SCHED_RR)
+	else if (task_is_realtime(task))
 		return IOPRIO_CLASS_RT;
 	else
 		return IOPRIO_CLASS_BE;

include/linux/sched.h

@@ -166,8 +166,6 @@ struct task_group;
 /* Task command name length: */
 #define TASK_COMM_LEN			16
 
-extern cpumask_var_t			cpu_isolated_map;
-
 extern void scheduler_tick(void);
 
 #define	MAX_SCHEDULE_TIMEOUT		LONG_MAX
@@ -332,9 +330,11 @@ struct load_weight {
 struct sched_avg {
 	u64				last_update_time;
 	u64				load_sum;
+	u64				runnable_load_sum;
 	u32				util_sum;
 	u32				period_contrib;
 	unsigned long			load_avg;
+	unsigned long			runnable_load_avg;
 	unsigned long			util_avg;
 };
 
@@ -377,6 +377,7 @@ struct sched_statistics {
 struct sched_entity {
 	/* For load-balancing: */
 	struct load_weight		load;
+	unsigned long			runnable_weight;
 	struct rb_node			run_node;
 	struct list_head		group_node;
 	unsigned int			on_rq;
@@ -472,10 +473,10 @@ struct sched_dl_entity {
 	 * conditions between the inactive timer handler and the wakeup
 	 * code.
 	 */
-	int				dl_throttled;
-	int				dl_boosted;
-	int				dl_yielded;
-	int				dl_non_contending;
+	int				dl_throttled      : 1;
+	int				dl_boosted        : 1;
+	int				dl_yielded        : 1;
+	int				dl_non_contending : 1;
 
 	/*
 	 * Bandwidth enforcement timer. Each -deadline task has its
@@ -1246,7 +1247,7 @@ static inline pid_t task_pgrp_nr(struct task_struct *tsk)
 #define TASK_REPORT_IDLE	(TASK_REPORT + 1)
 #define TASK_REPORT_MAX		(TASK_REPORT_IDLE << 1)
 
-static inline unsigned int __get_task_state(struct task_struct *tsk)
+static inline unsigned int task_state_index(struct task_struct *tsk)
 {
 	unsigned int tsk_state = READ_ONCE(tsk->state);
 	unsigned int state = (tsk_state | tsk->exit_state) & TASK_REPORT;
@@ -1259,7 +1260,7 @@ static inline unsigned int __get_task_state(struct task_struct *tsk)
 	return fls(state);
 }
 
-static inline char __task_state_to_char(unsigned int state)
+static inline char task_index_to_char(unsigned int state)
 {
 	static const char state_char[] = "RSDTtXZPI";
 
@@ -1270,7 +1271,7 @@ static inline char __task_state_to_char(unsigned int state)
 
 static inline char task_state_to_char(struct task_struct *tsk)
 {
-	return __task_state_to_char(__get_task_state(tsk));
+	return task_index_to_char(task_state_index(tsk));
 }
 
 /**

include/linux/sched/isolation.h

@@ -0,0 +1,51 @@
+#ifndef _LINUX_SCHED_ISOLATION_H
+#define _LINUX_SCHED_ISOLATION_H
+
+#include <linux/cpumask.h>
+#include <linux/init.h>
+#include <linux/tick.h>
+
+enum hk_flags {
+	HK_FLAG_TIMER		= 1,
+	HK_FLAG_RCU		= (1 << 1),
+	HK_FLAG_MISC		= (1 << 2),
+	HK_FLAG_SCHED		= (1 << 3),
+	HK_FLAG_TICK		= (1 << 4),
+	HK_FLAG_DOMAIN		= (1 << 5),
+};
+
+#ifdef CONFIG_CPU_ISOLATION
+DECLARE_STATIC_KEY_FALSE(housekeeping_overriden);
+extern int housekeeping_any_cpu(enum hk_flags flags);
+extern const struct cpumask *housekeeping_cpumask(enum hk_flags flags);
+extern void housekeeping_affine(struct task_struct *t, enum hk_flags flags);
+extern bool housekeeping_test_cpu(int cpu, enum hk_flags flags);
+extern void __init housekeeping_init(void);
+
+#else
+
+static inline int housekeeping_any_cpu(enum hk_flags flags)
+{
+	return smp_processor_id();
+}
+
+static inline const struct cpumask *housekeeping_cpumask(enum hk_flags flags)
+{
+	return cpu_possible_mask;
+}
+
+static inline void housekeeping_affine(struct task_struct *t,
+				       enum hk_flags flags) { }
+static inline void housekeeping_init(void) { }
+#endif /* CONFIG_CPU_ISOLATION */
+
+static inline bool housekeeping_cpu(int cpu, enum hk_flags flags)
+{
+#ifdef CONFIG_CPU_ISOLATION
+	if (static_branch_unlikely(&housekeeping_overriden))
+		return housekeeping_test_cpu(cpu, flags);
+#endif
+	return true;
+}
+
+#endif /* _LINUX_SCHED_ISOLATION_H */

include/linux/sched/rt.h

@@ -18,6 +18,17 @@ static inline int rt_task(struct task_struct *p)
 	return rt_prio(p->prio);
 }
 
+static inline bool task_is_realtime(struct task_struct *tsk)
+{
+	int policy = tsk->policy;
+
+	if (policy == SCHED_FIFO || policy == SCHED_RR)
+		return true;
+	if (policy == SCHED_DEADLINE)
+		return true;
+	return false;
+}
+
 #ifdef CONFIG_RT_MUTEXES
 /*
  * Must hold either p->pi_lock or task_rq(p)->lock.

include/linux/sched/sysctl.h

@@ -38,9 +38,9 @@ extern unsigned int sysctl_numa_balancing_scan_period_max;
 extern unsigned int sysctl_numa_balancing_scan_size;
 
 #ifdef CONFIG_SCHED_DEBUG
-extern unsigned int sysctl_sched_migration_cost;
-extern unsigned int sysctl_sched_nr_migrate;
-extern unsigned int sysctl_sched_time_avg;
+extern __read_mostly unsigned int sysctl_sched_migration_cost;
+extern __read_mostly unsigned int sysctl_sched_nr_migrate;
+extern __read_mostly unsigned int sysctl_sched_time_avg;
 
 int sched_proc_update_handler(struct ctl_table *table, int write,
 		void __user *buffer, size_t *length,

include/linux/tick.h

@@ -138,7 +138,6 @@ static inline u64 get_cpu_iowait_time_us(int cpu, u64 *unused) { return -1; }
 #ifdef CONFIG_NO_HZ_FULL
 extern bool tick_nohz_full_running;
 extern cpumask_var_t tick_nohz_full_mask;
-extern cpumask_var_t housekeeping_mask;
 
 static inline bool tick_nohz_full_enabled(void)
 {
@@ -162,11 +161,6 @@ static inline void tick_nohz_full_add_cpus_to(struct cpumask *mask)
 		cpumask_or(mask, mask, tick_nohz_full_mask);
 }
 
-static inline int housekeeping_any_cpu(void)
-{
-	return cpumask_any_and(housekeeping_mask, cpu_online_mask);
-}
-
 extern void tick_nohz_dep_set(enum tick_dep_bits bit);
 extern void tick_nohz_dep_clear(enum tick_dep_bits bit);
 extern void tick_nohz_dep_set_cpu(int cpu, enum tick_dep_bits bit);
@@ -235,11 +229,8 @@ static inline void tick_dep_clear_signal(struct signal_struct *signal,
 
 extern void tick_nohz_full_kick_cpu(int cpu);
 extern void __tick_nohz_task_switch(void);
+extern void __init tick_nohz_full_setup(cpumask_var_t cpumask);
 #else
-static inline int housekeeping_any_cpu(void)
-{
-	return smp_processor_id();
-}
 static inline bool tick_nohz_full_enabled(void) { return false; }
 static inline bool tick_nohz_full_cpu(int cpu) { return false; }
 static inline void tick_nohz_full_add_cpus_to(struct cpumask *mask) { }
@@ -259,35 +250,9 @@ static inline void tick_dep_clear_signal(struct signal_struct *signal,
 
 static inline void tick_nohz_full_kick_cpu(int cpu) { }
 static inline void __tick_nohz_task_switch(void) { }
+static inline void tick_nohz_full_setup(cpumask_var_t cpumask) { }
 #endif
 
-static inline const struct cpumask *housekeeping_cpumask(void)
-{
-#ifdef CONFIG_NO_HZ_FULL
-	if (tick_nohz_full_enabled())
-		return housekeeping_mask;
-#endif
-	return cpu_possible_mask;
-}
-
-static inline bool is_housekeeping_cpu(int cpu)
-{
-#ifdef CONFIG_NO_HZ_FULL
-	if (tick_nohz_full_enabled())
-		return cpumask_test_cpu(cpu, housekeeping_mask);
-#endif
-	return true;
-}
-
-static inline void housekeeping_affine(struct task_struct *t)
-{
-#ifdef CONFIG_NO_HZ_FULL
-	if (tick_nohz_full_enabled())
-		set_cpus_allowed_ptr(t, housekeeping_mask);
-
-#endif
-}
-
 static inline void tick_nohz_task_switch(void)
 {
 	if (tick_nohz_full_enabled())

include/trace/events/sched.h

@@ -118,7 +118,7 @@ static inline long __trace_sched_switch_state(bool preempt, struct task_struct *
 	if (preempt)
 		return TASK_STATE_MAX;
 
-	return __get_task_state(p);
+	return task_state_index(p);
 }
 #endif /* CREATE_TRACE_POINTS */