summaryrefslogtreecommitdiff
path: root/include/linux/sched/topology.h
blob: d7b6dab956ec4a130cd835d255b3a93bab764e54 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
#ifndef _LINUX_SCHED_TOPOLOGY_H
#define _LINUX_SCHED_TOPOLOGY_H

#include <linux/topology.h>

#include <linux/sched/idle.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;

	/*
	 * Some variables from the most recent sd_lb_stats for this domain,
	 * used by wake_affine().
	 */
	unsigned long	nr_running;
	unsigned long	load;
	unsigned long	capacity;
};

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 */

static inline int task_node(const struct task_struct *p)
{
	return cpu_to_node(task_cpu(p));
}

#endif /* _LINUX_SCHED_TOPOLOGY_H */