[PATCH 06/89] sched/topology: Split out scheduler topology interfaces from <linux/sched.h> into <linux/sched/topology.h>

[Ingo Molnar <mingo@kernel.org>]

The vast majority of sched.h users does not require the topology types and
interfaces, so split them out into a separate header, and include them
in the .c files that require them.

This reduces the size of linux/sched.h by ~6%.

Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/arm/kernel/topology.c     |   1 +
 arch/arm64/kernel/topology.c   |   1 +
 arch/powerpc/kernel/smp.c      |   1 +
 arch/s390/kernel/topology.c    |   1 +
 arch/x86/kernel/smpboot.c      |   1 +
 block/blk-mq.c                 |   1 +
 block/blk-softirq.c            |   1 +
 include/linux/cpuset.h         |   1 +
 include/linux/sched.h          | 212 -----------------------------------------------------------
 include/linux/sched/topology.h | 217 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
 kernel/sched/fair.c            |   2 +
 kernel/sched/sched.h           |   1 +
 12 files changed, 228 insertions(+), 212 deletions(-)

diff --git a/arch/arm/kernel/topology.c b/arch/arm/kernel/topology.c
index ebf47d91b804..f8a3ab82e77f 100644
--- a/arch/arm/kernel/topology.c
+++ b/arch/arm/kernel/topology.c
@@ -21,6 +21,7 @@
 #include <linux/nodemask.h>
 #include <linux/of.h>
 #include <linux/sched.h>
+#include <linux/sched/topology.h>
 #include <linux/slab.h>
 #include <linux/string.h>
 
diff --git a/arch/arm64/kernel/topology.c b/arch/arm64/kernel/topology.c
index 655e65f38f31..3aeb7bbb1bfc 100644
--- a/arch/arm64/kernel/topology.c
+++ b/arch/arm64/kernel/topology.c
@@ -20,6 +20,7 @@
 #include <linux/nodemask.h>
 #include <linux/of.h>
 #include <linux/sched.h>
+#include <linux/sched/topology.h>
 #include <linux/slab.h>
 #include <linux/string.h>
 #include <linux/cpufreq.h>
diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index 893bd7f79be6..54903862cf57 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -20,6 +20,7 @@
 #include <linux/kernel.h>
 #include <linux/export.h>
 #include <linux/sched.h>
+#include <linux/sched/topology.h>
 #include <linux/smp.h>
 #include <linux/interrupt.h>
 #include <linux/delay.h>
diff --git a/arch/s390/kernel/topology.c b/arch/s390/kernel/topology.c
index 93dcbae1e98d..044dec44ce8d 100644
--- a/arch/s390/kernel/topology.c
+++ b/arch/s390/kernel/topology.c
@@ -13,6 +13,7 @@
 #include <linux/export.h>
 #include <linux/kernel.h>
 #include <linux/sched.h>
+#include <linux/sched/topology.h>
 #include <linux/delay.h>
 #include <linux/init.h>
 #include <linux/slab.h>
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 46732dc3b73c..0fe89249d9ac 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -45,6 +45,7 @@
 #include <linux/smp.h>
 #include <linux/export.h>
 #include <linux/sched.h>
+#include <linux/sched/topology.h>
 #include <linux/percpu.h>
 #include <linux/bootmem.h>
 #include <linux/err.h>
diff --git a/block/blk-mq.c b/block/blk-mq.c
index c3400b5444a7..92bf48dac06f 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -20,6 +20,7 @@
 #include <linux/cpu.h>
 #include <linux/cache.h>
 #include <linux/sched/sysctl.h>
+#include <linux/sched/topology.h>
 #include <linux/delay.h>
 #include <linux/crash_dump.h>
 #include <linux/prefetch.h>
diff --git a/block/blk-softirq.c b/block/blk-softirq.c
index 06cf9807f49a..87b7df4851bf 100644
--- a/block/blk-softirq.c
+++ b/block/blk-softirq.c
@@ -9,6 +9,7 @@
 #include <linux/interrupt.h>
 #include <linux/cpu.h>
 #include <linux/sched.h>
+#include <linux/sched/topology.h>
 
 #include "blk.h"
 
diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h
index bfc204e70338..c608c39cb161 100644
--- a/include/linux/cpuset.h
+++ b/include/linux/cpuset.h
@@ -9,6 +9,7 @@
  */
 
 #include <linux/sched.h>
+#include <linux/sched/topology.h>
 #include <linux/cpumask.h>
 #include <linux/nodemask.h>
 #include <linux/mm.h>
diff --git a/include/linux/sched.h b/include/linux/sched.h
index c8e519d0b4a3..b2e18537088b 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -969,12 +969,6 @@ enum cpu_idle_type {
 # 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)
-
-/*
  * Wake-queues are lists of tasks with a pending wakeup, whose
  * callers have already marked the task as woken internally,
  * and can thus carry on. A common use case is being able to
@@ -1024,214 +1018,8 @@ extern void wake_q_add(struct wake_q_head *head,
 		       struct task_struct *task);
 extern void wake_up_q(struct wake_q_head *head);
 
-/*
- * sched-domains (multiprocessor balancing) declarations:
- */
-#ifdef CONFIG_SMP
-#define SD_LOAD_BALANCE		0x0001	/* Do load balancing on this domain. */
-#define SD_BALANCE_NEWIDLE	0x0002	/* Balance when about to become idle */
-#define SD_BALANCE_EXEC		0x0004	/* Balance on exec */
-#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_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 */
-#define SD_ASYM_PACKING		0x0800  /* Place busy groups earlier in the domain */
-#define SD_PREFER_SIBLING	0x1000	/* Prefer to place tasks in a sibling domain */
-#define SD_OVERLAP		0x2000	/* sched_domains of this level overlap */
-#define SD_NUMA			0x4000	/* cross-node balancing */
-
-#ifdef CONFIG_SCHED_SMT
-static inline int cpu_smt_flags(void)
-{
-	return SD_SHARE_CPUCAPACITY | SD_SHARE_PKG_RESOURCES;
-}
-#endif
-
-#ifdef CONFIG_SCHED_MC
-static inline int cpu_core_flags(void)
-{
-	return SD_SHARE_PKG_RESOURCES;
-}
-#endif
-
-#ifdef CONFIG_NUMA
-static inline int cpu_numa_flags(void)
-{
-	return SD_NUMA;
-}
-#endif
-
-extern int arch_asym_cpu_priority(int cpu);
-
-struct sched_domain_attr {
-	int relax_domain_level;
-};
-
-#define SD_ATTR_INIT	(struct sched_domain_attr) {	\
-	.relax_domain_level = -1,			\
-}
-
-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 */
-	struct sched_domain *child;	/* bottom domain must be null terminated */
-	struct sched_group *groups;	/* the balancing groups of the domain */
-	unsigned long min_interval;	/* Minimum balance interval ms */
-	unsigned long max_interval;	/* Maximum balance interval ms */
-	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;
-	unsigned int smt_gain;
-
-	int nohz_idle;			/* NOHZ IDLE status */
-	int flags;			/* See SD_* */
-	int level;
-
-	/* Runtime fields. */
-	unsigned long last_balance;	/* init to jiffies. units in jiffies */
-	unsigned int balance_interval;	/* initialise to 1. units in ms. */
-	unsigned int nr_balance_failed; /* initialise to 0 */
-
-	/* idle_balance() stats */
-	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];
-	unsigned int lb_failed[CPU_MAX_IDLE_TYPES];
-	unsigned int lb_balanced[CPU_MAX_IDLE_TYPES];
-	unsigned int lb_imbalance[CPU_MAX_IDLE_TYPES];
-	unsigned int lb_gained[CPU_MAX_IDLE_TYPES];
-	unsigned int lb_hot_gained[CPU_MAX_IDLE_TYPES];
-	unsigned int lb_nobusyg[CPU_MAX_IDLE_TYPES];
-	unsigned int lb_nobusyq[CPU_MAX_IDLE_TYPES];
-
-	/* Active load balancing */
-	unsigned int alb_count;
-	unsigned int alb_failed;
-	unsigned int alb_pushed;
-
-	/* SD_BALANCE_EXEC stats */
-	unsigned int sbe_count;
-	unsigned int sbe_balanced;
-	unsigned int sbe_pushed;
-
-	/* SD_BALANCE_FORK stats */
-	unsigned int sbf_count;
-	unsigned int sbf_balanced;
-	unsigned int sbf_pushed;
-
-	/* try_to_wake_up() stats */
-	unsigned int ttwu_wake_remote;
-	unsigned int ttwu_move_affine;
-	unsigned int ttwu_move_balance;
-#endif
-#ifdef CONFIG_SCHED_DEBUG
-	char *name;
-#endif
-	union {
-		void *private;		/* used during construction */
-		struct rcu_head rcu;	/* used during destruction */
-	};
-	struct sched_domain_shared *shared;
-
-	unsigned int span_weight;
-	/*
-	 * Span of all CPUs in this domain.
-	 *
-	 * NOTE: this field is variable length. (Allocated dynamically
-	 * by attaching extra space to the end of the structure,
-	 * depending on how many CPUs the kernel has booted up with)
-	 */
-	unsigned long span[0];
-};
-
-static inline struct cpumask *sched_domain_span(struct sched_domain *sd)
-{
-	return to_cpumask(sd->span);
-}
-
-extern void partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[],
-				    struct sched_domain_attr *dattr_new);
-
-/* Allocate an array of sched domains, for partition_sched_domains(). */
-cpumask_var_t *alloc_sched_domains(unsigned int ndoms);
-void free_sched_domains(cpumask_var_t doms[], unsigned int ndoms);
-
-bool cpus_share_cache(int this_cpu, int that_cpu);
-
-typedef const struct cpumask *(*sched_domain_mask_f)(int cpu);
-typedef int (*sched_domain_flags_f)(void);
-
-#define SDTL_OVERLAP	0x01
-
-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;
-};
-
-struct sched_domain_topology_level {
-	sched_domain_mask_f mask;
-	sched_domain_flags_f sd_flags;
-	int		    flags;
-	int		    numa_level;
-	struct sd_data      data;
-#ifdef CONFIG_SCHED_DEBUG
-	char                *name;
-#endif
-};
-
-extern void set_sched_topology(struct sched_domain_topology_level *tl);
 extern void wake_up_if_idle(int cpu);
 
-#ifdef CONFIG_SCHED_DEBUG
-# define SD_INIT_NAME(type)		.name = #type
-#else
-# define SD_INIT_NAME(type)
-#endif
-
-#else /* CONFIG_SMP */
-
-struct sched_domain_attr;
-
-static inline void
-partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[],
-			struct sched_domain_attr *dattr_new)
-{
-}
-
-static inline bool cpus_share_cache(int this_cpu, int that_cpu)
-{
-	return true;
-}
-
-#endif	/* !CONFIG_SMP */
-
-
 struct io_context;			/* See blkdev.h */
 
 
diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h
new file mode 100644
index 000000000000..ae2cb8f9c431
--- /dev/null
+++ b/include/linux/sched/topology.h
@@ -0,0 +1,217 @@
+#ifndef _LINUX_SCHED_TOPOLOGY_H
+#define _LINUX_SCHED_TOPOLOGY_H
+
+/*
+ * sched-domains (multiprocessor balancing) declarations:
+ */
+#ifdef CONFIG_SMP
+
+#define SD_LOAD_BALANCE		0x0001	/* Do load balancing on this domain. */
+#define SD_BALANCE_NEWIDLE	0x0002	/* Balance when about to become idle */
+#define SD_BALANCE_EXEC		0x0004	/* Balance on exec */
+#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_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 */
+#define SD_ASYM_PACKING		0x0800  /* Place busy groups earlier in the domain */
+#define SD_PREFER_SIBLING	0x1000	/* Prefer to place tasks in a sibling domain */
+#define SD_OVERLAP		0x2000	/* sched_domains of this level overlap */
+#define SD_NUMA			0x4000	/* cross-node balancing */
+
+/*
+ * Increase resolution of cpu_capacity calculations
+ */
+#define SCHED_CAPACITY_SHIFT	SCHED_FIXEDPOINT_SHIFT
+#define SCHED_CAPACITY_SCALE	(1L << SCHED_CAPACITY_SHIFT)
+
+#ifdef CONFIG_SCHED_SMT
+static inline int cpu_smt_flags(void)
+{
+	return SD_SHARE_CPUCAPACITY | SD_SHARE_PKG_RESOURCES;
+}
+#endif
+
+#ifdef CONFIG_SCHED_MC
+static inline int cpu_core_flags(void)
+{
+	return SD_SHARE_PKG_RESOURCES;
+}
+#endif
+
+#ifdef CONFIG_NUMA
+static inline int cpu_numa_flags(void)
+{
+	return SD_NUMA;
+}
+#endif
+
+extern int arch_asym_cpu_priority(int cpu);
+
+struct sched_domain_attr {
+	int relax_domain_level;
+};
+
+#define SD_ATTR_INIT	(struct sched_domain_attr) {	\
+	.relax_domain_level = -1,			\
+}
+
+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 */
+	struct sched_domain *child;	/* bottom domain must be null terminated */
+	struct sched_group *groups;	/* the balancing groups of the domain */
+	unsigned long min_interval;	/* Minimum balance interval ms */
+	unsigned long max_interval;	/* Maximum balance interval ms */
+	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;
+	unsigned int smt_gain;
+
+	int nohz_idle;			/* NOHZ IDLE status */
+	int flags;			/* See SD_* */
+	int level;
+
+	/* Runtime fields. */
+	unsigned long last_balance;	/* init to jiffies. units in jiffies */
+	unsigned int balance_interval;	/* initialise to 1. units in ms. */
+	unsigned int nr_balance_failed; /* initialise to 0 */
+
+	/* idle_balance() stats */
+	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];
+	unsigned int lb_failed[CPU_MAX_IDLE_TYPES];
+	unsigned int lb_balanced[CPU_MAX_IDLE_TYPES];
+	unsigned int lb_imbalance[CPU_MAX_IDLE_TYPES];
+	unsigned int lb_gained[CPU_MAX_IDLE_TYPES];
+	unsigned int lb_hot_gained[CPU_MAX_IDLE_TYPES];
+	unsigned int lb_nobusyg[CPU_MAX_IDLE_TYPES];
+	unsigned int lb_nobusyq[CPU_MAX_IDLE_TYPES];
+
+	/* Active load balancing */
+	unsigned int alb_count;
+	unsigned int alb_failed;
+	unsigned int alb_pushed;
+
+	/* SD_BALANCE_EXEC stats */
+	unsigned int sbe_count;
+	unsigned int sbe_balanced;
+	unsigned int sbe_pushed;
+
+	/* SD_BALANCE_FORK stats */
+	unsigned int sbf_count;
+	unsigned int sbf_balanced;
+	unsigned int sbf_pushed;
+
+	/* try_to_wake_up() stats */
+	unsigned int ttwu_wake_remote;
+	unsigned int ttwu_move_affine;
+	unsigned int ttwu_move_balance;
+#endif
+#ifdef CONFIG_SCHED_DEBUG
+	char *name;
+#endif
+	union {
+		void *private;		/* used during construction */
+		struct rcu_head rcu;	/* used during destruction */
+	};
+	struct sched_domain_shared *shared;
+
+	unsigned int span_weight;
+	/*
+	 * Span of all CPUs in this domain.
+	 *
+	 * NOTE: this field is variable length. (Allocated dynamically
+	 * by attaching extra space to the end of the structure,
+	 * depending on how many CPUs the kernel has booted up with)
+	 */
+	unsigned long span[0];
+};
+
+static inline struct cpumask *sched_domain_span(struct sched_domain *sd)
+{
+	return to_cpumask(sd->span);
+}
+
+extern void partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[],
+				    struct sched_domain_attr *dattr_new);
+
+/* Allocate an array of sched domains, for partition_sched_domains(). */
+cpumask_var_t *alloc_sched_domains(unsigned int ndoms);
+void free_sched_domains(cpumask_var_t doms[], unsigned int ndoms);
+
+bool cpus_share_cache(int this_cpu, int that_cpu);
+
+typedef const struct cpumask *(*sched_domain_mask_f)(int cpu);
+typedef int (*sched_domain_flags_f)(void);
+
+#define SDTL_OVERLAP	0x01
+
+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;
+};
+
+struct sched_domain_topology_level {
+	sched_domain_mask_f mask;
+	sched_domain_flags_f sd_flags;
+	int		    flags;
+	int		    numa_level;
+	struct sd_data      data;
+#ifdef CONFIG_SCHED_DEBUG
+	char                *name;
+#endif
+};
+
+extern void set_sched_topology(struct sched_domain_topology_level *tl);
+
+#ifdef CONFIG_SCHED_DEBUG
+# define SD_INIT_NAME(type)		.name = #type
+#else
+# define SD_INIT_NAME(type)
+#endif
+
+#else /* CONFIG_SMP */
+
+struct sched_domain_attr;
+
+static inline void
+partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[],
+			struct sched_domain_attr *dattr_new)
+{
+}
+
+static inline bool cpus_share_cache(int this_cpu, int that_cpu)
+{
+	return true;
+}
+
+#endif	/* !CONFIG_SMP */
+
+#endif /* _LINUX_SCHED_TOPOLOGY_H */
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 274c747a01ce..fcd520db8e32 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -21,6 +21,8 @@
  */
 
 #include <linux/sched.h>
+#include <linux/sched/topology.h>
+
 #include <linux/latencytop.h>
 #include <linux/cpumask.h>
 #include <linux/cpuidle.h>
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 17ed94b9b413..319fcf80930c 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1,6 +1,7 @@
 
 #include <linux/sched.h>
 #include <linux/sched/sysctl.h>
+#include <linux/sched/topology.h>
 #include <linux/sched/rt.h>
 #include <linux/u64_stats_sync.h>
 #include <linux/sched/deadline.h>
-- 
2.7.4