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

…inux/kernel/git/tip/tip

Pull scheduler changes from Ingo Molnar:
 "The main changes are:

   - irqtime accounting cleanups and enhancements. (Frederic Weisbecker)

   - schedstat debugging enhancements, make it more broadly runtime
     available. (Josh Poimboeuf)

   - More work on asymmetric topology/capacity scheduling. (Morten
     Rasmussen)

   - sched/wait fixes and cleanups. (Oleg Nesterov)

   - PELT (per entity load tracking) improvements. (Peter Zijlstra)

   - Rewrite and enhance select_idle_siblings(). (Peter Zijlstra)

   - sched/numa enhancements/fixes (Rik van Riel)

   - sched/cputime scalability improvements (Stanislaw Gruszka)

   - Load calculation arithmetics fixes. (Dietmar Eggemann)

   - sched/deadline enhancements (Tommaso Cucinotta)

   - Fix utilization accounting when switching to the SCHED_NORMAL
     policy. (Vincent Guittot)

   - ... plus misc cleanups and enhancements"

* 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (64 commits)
  sched/irqtime: Consolidate irqtime flushing code
  sched/irqtime: Consolidate accounting synchronization with u64_stats API
  u64_stats: Introduce IRQs disabled helpers
  sched/irqtime: Remove needless IRQs disablement on kcpustat update
  sched/irqtime: No need for preempt-safe accessors
  sched/fair: Fix min_vruntime tracking
  sched/debug: Add SCHED_WARN_ON()
  sched/core: Fix set_user_nice()
  sched/fair: Introduce set_curr_task() helper
  sched/core, ia64: Rename set_curr_task()
  sched/core: Fix incorrect utilization accounting when switching to fair class
  sched/core: Optimize SCHED_SMT
  sched/core: Rewrite and improve select_idle_siblings()
  sched/core: Replace sd_busy/nr_busy_cpus with sched_domain_shared
  sched/core: Introduce 'struct sched_domain_shared'
  sched/core: Restructure destroy_sched_domain()
  sched/core: Remove unused @cpu argument from destroy_sched_domain*()
  sched/wait: Introduce init_wait_entry()
  sched/wait: Avoid abort_exclusive_wait() in __wait_on_bit_lock()
  sched/wait: Avoid abort_exclusive_wait() in ___wait_event()
  ...

Documentation/scheduler/sched-deadline.txt

@@ -16,6 +16,7 @@ CONTENTS
    4.1 System-wide settings
    4.2 Task interface
    4.3 Default behavior
+   4.4 Behavior of sched_yield()
  5. Tasks CPU affinity
    5.1 SCHED_DEADLINE and cpusets HOWTO
  6. Future plans
@@ -426,6 +427,23 @@ CONTENTS
  Finally, notice that in order not to jeopardize the admission control a
  -deadline task cannot fork.
 
+
+4.4 Behavior of sched_yield()
+-----------------------------
+
+ When a SCHED_DEADLINE task calls sched_yield(), it gives up its
+ remaining runtime and is immediately throttled, until the next
+ period, when its runtime will be replenished (a special flag
+ dl_yielded is set and used to handle correctly throttling and runtime
+ replenishment after a call to sched_yield()).
+
+ This behavior of sched_yield() allows the task to wake-up exactly at
+ the beginning of the next period. Also, this may be useful in the
+ future with bandwidth reclaiming mechanisms, where sched_yield() will
+ make the leftoever runtime available for reclamation by other
+ SCHED_DEADLINE tasks.
+
+
 5. Tasks CPU affinity
 =====================
 

arch/ia64/kernel/mca.c

@@ -986,7 +986,7 @@ ia64_mca_modify_original_stack(struct pt_regs *regs,
 	int cpu = smp_processor_id();
 
 	previous_current = curr_task(cpu);
-	set_curr_task(cpu, current);
+	ia64_set_curr_task(cpu, current);
 	if ((p = strchr(current->comm, ' ')))
 		*p = '\0';
 
@@ -1360,14 +1360,14 @@ ia64_mca_handler(struct pt_regs *regs, struct switch_stack *sw,
 				cpumask_clear_cpu(i, &mca_cpu);	/* wake next cpu */
 				while (monarch_cpu != -1)
 					cpu_relax();	/* spin until last cpu leaves */
-				set_curr_task(cpu, previous_current);
+				ia64_set_curr_task(cpu, previous_current);
 				ia64_mc_info.imi_rendez_checkin[cpu]
 						= IA64_MCA_RENDEZ_CHECKIN_NOTDONE;
 				return;
 			}
 		}
 	}
-	set_curr_task(cpu, previous_current);
+	ia64_set_curr_task(cpu, previous_current);
 	ia64_mc_info.imi_rendez_checkin[cpu] = IA64_MCA_RENDEZ_CHECKIN_NOTDONE;
 	monarch_cpu = -1;	/* This frees the slaves and previous monarchs */
 }
@@ -1729,7 +1729,7 @@ ia64_init_handler(struct pt_regs *regs, struct switch_stack *sw,
 		NOTIFY_INIT(DIE_INIT_SLAVE_LEAVE, regs, (long)&nd, 1);
 
 		mprintk("Slave on cpu %d returning to normal service.\n", cpu);
-		set_curr_task(cpu, previous_current);
+		ia64_set_curr_task(cpu, previous_current);
 		ia64_mc_info.imi_rendez_checkin[cpu] = IA64_MCA_RENDEZ_CHECKIN_NOTDONE;
 		atomic_dec(&slaves);
 		return;
@@ -1756,7 +1756,7 @@ ia64_init_handler(struct pt_regs *regs, struct switch_stack *sw,
 
 	mprintk("\nINIT dump complete.  Monarch on cpu %d returning to normal service.\n", cpu);
 	atomic_dec(&monarchs);
-	set_curr_task(cpu, previous_current);
+	ia64_set_curr_task(cpu, previous_current);
 	monarch_cpu = -1;
 	return;
 }

arch/x86/kernel/smpboot.c

@@ -471,7 +471,7 @@ static bool match_die(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o)
 	return false;
 }
 
-static struct sched_domain_topology_level numa_inside_package_topology[] = {
+static struct sched_domain_topology_level x86_numa_in_package_topology[] = {
 #ifdef CONFIG_SCHED_SMT
 	{ cpu_smt_mask, cpu_smt_flags, SD_INIT_NAME(SMT) },
 #endif
@@ -480,22 +480,23 @@ static struct sched_domain_topology_level numa_inside_package_topology[] = {
 #endif
 	{ NULL, },
 };
+
+static struct sched_domain_topology_level x86_topology[] = {
+#ifdef CONFIG_SCHED_SMT
+	{ cpu_smt_mask, cpu_smt_flags, SD_INIT_NAME(SMT) },
+#endif
+#ifdef CONFIG_SCHED_MC
+	{ cpu_coregroup_mask, cpu_core_flags, SD_INIT_NAME(MC) },
+#endif
+	{ cpu_cpu_mask, SD_INIT_NAME(DIE) },
+	{ NULL, },
+};
+
 /*
- * set_sched_topology() sets the topology internal to a CPU.  The
- * NUMA topologies are layered on top of it to build the full
- * system topology.
- *
- * If NUMA nodes are observed to occur within a CPU package, this
- * function should be called.  It forces the sched domain code to
- * only use the SMT level for the CPU portion of the topology.
- * This essentially falls back to relying on NUMA information
- * from the SRAT table to describe the entire system topology
- * (except for hyperthreads).
+ * Set if a package/die has multiple NUMA nodes inside.
+ * AMD Magny-Cours and Intel Cluster-on-Die have this.
  */
-static void primarily_use_numa_for_topology(void)
-{
-	set_sched_topology(numa_inside_package_topology);
-}
+static bool x86_has_numa_in_package;
 
 void set_cpu_sibling_map(int cpu)
 {
@@ -558,7 +559,7 @@ void set_cpu_sibling_map(int cpu)
 				c->booted_cores = cpu_data(i).booted_cores;
 		}
 		if (match_die(c, o) && !topology_same_node(c, o))
-			primarily_use_numa_for_topology();
+			x86_has_numa_in_package = true;
 	}
 
 	threads = cpumask_weight(topology_sibling_cpumask(cpu));
@@ -1304,6 +1305,16 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus)
 		zalloc_cpumask_var(&per_cpu(cpu_core_map, i), GFP_KERNEL);
 		zalloc_cpumask_var(&per_cpu(cpu_llc_shared_map, i), GFP_KERNEL);
 	}
+
+	/*
+	 * Set 'default' x86 topology, this matches default_topology() in that
+	 * it has NUMA nodes as a topology level. See also
+	 * native_smp_cpus_done().
+	 *
+	 * Must be done before set_cpus_sibling_map() is ran.
+	 */
+	set_sched_topology(x86_topology);
+
 	set_cpu_sibling_map(0);
 
 	switch (smp_sanity_check(max_cpus)) {
@@ -1370,6 +1381,9 @@ void __init native_smp_cpus_done(unsigned int max_cpus)
 {
 	pr_debug("Boot done\n");
 
+	if (x86_has_numa_in_package)
+		set_sched_topology(x86_numa_in_package_topology);
+
 	nmi_selftest();
 	impress_friends();
 	setup_ioapic_dest();

include/linux/kernel.h

@@ -259,17 +259,14 @@ static inline void might_fault(void) { }
 extern struct atomic_notifier_head panic_notifier_list;
 extern long (*panic_blink)(int state);
 __printf(1, 2)
-void panic(const char *fmt, ...)
-	__noreturn __cold;
+void panic(const char *fmt, ...) __noreturn __cold;
 void nmi_panic(struct pt_regs *regs, const char *msg);
 extern void oops_enter(void);
 extern void oops_exit(void);
 void print_oops_end_marker(void);
 extern int oops_may_print(void);
-void do_exit(long error_code)
-	__noreturn;
-void complete_and_exit(struct completion *, long)
-	__noreturn;
+void do_exit(long error_code) __noreturn;
+void complete_and_exit(struct completion *, long) __noreturn;
 
 /* Internal, do not use. */
 int __must_check _kstrtoul(const char *s, unsigned int base, unsigned long *res);

include/linux/sched.h

@@ -448,6 +448,8 @@ static inline void io_schedule(void)
 	io_schedule_timeout(MAX_SCHEDULE_TIMEOUT);
 }
 
+void __noreturn do_task_dead(void);
+
 struct nsproxy;
 struct user_namespace;
 
@@ -1022,7 +1024,8 @@ extern void wake_up_q(struct wake_q_head *head);
 #define SD_BALANCE_FORK		0x0008	/* Balance on fork, clone */
 #define SD_BALANCE_WAKE		0x0010  /* Balance on wakeup */
 #define SD_WAKE_AFFINE		0x0020	/* Wake task to waking CPU */
-#define SD_SHARE_CPUCAPACITY	0x0080	/* Domain members share cpu power */
+#define SD_ASYM_CPUCAPACITY	0x0040  /* Groups have different max cpu capacities */
+#define SD_SHARE_CPUCAPACITY	0x0080	/* Domain members share cpu capacity */
 #define SD_SHARE_POWERDOMAIN	0x0100	/* Domain members share power domain */
 #define SD_SHARE_PKG_RESOURCES	0x0200	/* Domain members share cpu pkg resources */
 #define SD_SERIALIZE		0x0400	/* Only a single load balancing instance */
@@ -1064,6 +1067,12 @@ extern int sched_domain_level_max;
 
 struct sched_group;
 
+struct sched_domain_shared {
+	atomic_t	ref;
+	atomic_t	nr_busy_cpus;
+	int		has_idle_cores;
+};
+
 struct sched_domain {
 	/* These fields must be setup */
 	struct sched_domain *parent;	/* top domain must be null terminated */
@@ -1094,6 +1103,8 @@ struct sched_domain {
 	u64 max_newidle_lb_cost;
 	unsigned long next_decay_max_lb_cost;
 
+	u64 avg_scan_cost;		/* select_idle_sibling */
+
 #ifdef CONFIG_SCHEDSTATS
 	/* load_balance() stats */
 	unsigned int lb_count[CPU_MAX_IDLE_TYPES];
@@ -1132,6 +1143,7 @@ struct sched_domain {
 		void *private;		/* used during construction */
 		struct rcu_head rcu;	/* used during destruction */
 	};
+	struct sched_domain_shared *shared;
 
 	unsigned int span_weight;
 	/*
@@ -1165,6 +1177,7 @@ typedef int (*sched_domain_flags_f)(void);
 
 struct sd_data {
 	struct sched_domain **__percpu sd;
+	struct sched_domain_shared **__percpu sds;
 	struct sched_group **__percpu sg;
 	struct sched_group_capacity **__percpu sgc;
 };
@@ -2568,7 +2581,7 @@ static inline bool is_idle_task(const struct task_struct *p)
 	return p->pid == 0;
 }
 extern struct task_struct *curr_task(int cpu);
-extern void set_curr_task(int cpu, struct task_struct *p);
+extern void ia64_set_curr_task(int cpu, struct task_struct *p);
 
 void yield(void);
 
@@ -3206,7 +3219,11 @@ static inline int signal_pending_state(long state, struct task_struct *p)
  * cond_resched_lock() will drop the spinlock before scheduling,
  * cond_resched_softirq() will enable bhs before scheduling.
  */
+#ifndef CONFIG_PREEMPT
 extern int _cond_resched(void);
+#else
+static inline int _cond_resched(void) { return 0; }
+#endif
 
 #define cond_resched() ({			\
 	___might_sleep(__FILE__, __LINE__, 0);	\
@@ -3236,6 +3253,15 @@ static inline void cond_resched_rcu(void)
 #endif
 }
 
+static inline unsigned long get_preempt_disable_ip(struct task_struct *p)
+{
+#ifdef CONFIG_DEBUG_PREEMPT
+	return p->preempt_disable_ip;
+#else
+	return 0;
+#endif
+}
+
 /*
  * Does a critical section need to be broken due to another
  * task waiting?: (technically does not depend on CONFIG_PREEMPT,

include/linux/u64_stats_sync.h

@@ -103,31 +103,42 @@ static inline void u64_stats_update_end_raw(struct u64_stats_sync *syncp)
 #endif
 }
 
-static inline unsigned int u64_stats_fetch_begin(const struct u64_stats_sync *syncp)
+static inline unsigned int __u64_stats_fetch_begin(const struct u64_stats_sync *syncp)
 {
 #if BITS_PER_LONG==32 && defined(CONFIG_SMP)
 	return read_seqcount_begin(&syncp->seq);
 #else
-#if BITS_PER_LONG==32
-	preempt_disable();
-#endif
 	return 0;
 #endif
 }
 
-static inline bool u64_stats_fetch_retry(const struct u64_stats_sync *syncp,
+static inline unsigned int u64_stats_fetch_begin(const struct u64_stats_sync *syncp)
+{
+#if BITS_PER_LONG==32 && !defined(CONFIG_SMP)
+	preempt_disable();
+#endif
+	return __u64_stats_fetch_begin(syncp);
+}
+
+static inline bool __u64_stats_fetch_retry(const struct u64_stats_sync *syncp,
 					 unsigned int start)
 {
 #if BITS_PER_LONG==32 && defined(CONFIG_SMP)
 	return read_seqcount_retry(&syncp->seq, start);
 #else
-#if BITS_PER_LONG==32
-	preempt_enable();
-#endif
 	return false;
 #endif
 }
 
+static inline bool u64_stats_fetch_retry(const struct u64_stats_sync *syncp,
+					 unsigned int start)
+{
+#if BITS_PER_LONG==32 && !defined(CONFIG_SMP)
+	preempt_enable();
+#endif
+	return __u64_stats_fetch_retry(syncp, start);
+}
+
 /*
  * In case irq handlers can update u64 counters, readers can use following helpers
  * - SMP 32bit arches use seqcount protection, irq safe.
@@ -136,27 +147,19 @@ static inline bool u64_stats_fetch_retry(const struct u64_stats_sync *syncp,
  */
 static inline unsigned int u64_stats_fetch_begin_irq(const struct u64_stats_sync *syncp)
 {
-#if BITS_PER_LONG==32 && defined(CONFIG_SMP)
-	return read_seqcount_begin(&syncp->seq);
-#else
-#if BITS_PER_LONG==32
+#if BITS_PER_LONG==32 && !defined(CONFIG_SMP)
 	local_irq_disable();
 #endif
-	return 0;
-#endif
+	return __u64_stats_fetch_begin(syncp);
 }
 
 static inline bool u64_stats_fetch_retry_irq(const struct u64_stats_sync *syncp,
-					 unsigned int start)
+					     unsigned int start)
 {
-#if BITS_PER_LONG==32 && defined(CONFIG_SMP)
-	return read_seqcount_retry(&syncp->seq, start);
-#else
-#if BITS_PER_LONG==32
+#if BITS_PER_LONG==32 && !defined(CONFIG_SMP)
 	local_irq_enable();
 #endif
-	return false;
-#endif
+	return __u64_stats_fetch_retry(syncp, start);
 }
 
 #endif /* _LINUX_U64_STATS_SYNC_H */