aboutsummaryrefslogtreecommitdiff
path: root/kernel/sched_cpupri.c
blob: 52154fefab7eef9c8302a7da96741bf59d13c6b6 (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
/*
 *  kernel/sched_cpupri.c
 *
 *  CPU priority management
 *
 *  Copyright (C) 2007-2008 Novell
 *
 *  Author: Gregory Haskins <ghaskins@novell.com>
 *
 *  This code tracks the priority of each CPU so that global migration
 *  decisions are easy to calculate.  Each CPU can be in a state as follows:
 *
 *                 (INVALID), IDLE, NORMAL, RT1, ... RT99
 *
 *  going from the lowest priority to the highest.  CPUs in the INVALID state
 *  are not eligible for routing.  The system maintains this state with
 *  a 2 dimensional bitmap (the first for priority class, the second for cpus
 *  in that class).  Therefore a typical application without affinity
 *  restrictions can find a suitable CPU with O(1) complexity (e.g. two bit
 *  searches).  For tasks with affinity restrictions, the algorithm has a
 *  worst case complexity of O(min(102, nr_domcpus)), though the scenario that
 *  yields the worst case search is fairly contrived.
 *
 *  This program is free software; you can redistribute it and/or
 *  modify it under the terms of the GNU General Public License
 *  as published by the Free Software Foundation; version 2
 *  of the License.
 */

#include "sched_cpupri.h"

/* Convert between a 140 based task->prio, and our 102 based cpupri */
static int convert_prio(int prio)
{
	int cpupri;

	if (prio == CPUPRI_INVALID)
		cpupri = CPUPRI_INVALID;
	else if (prio == MAX_PRIO)
		cpupri = CPUPRI_IDLE;
	else if (prio >= MAX_RT_PRIO)
		cpupri = CPUPRI_NORMAL;
	else
		cpupri = MAX_RT_PRIO - prio + 1;

	return cpupri;
}

#define for_each_cpupri_active(array, idx)                    \
  for (idx = find_first_bit(array, CPUPRI_NR_PRIORITIES);     \
       idx < CPUPRI_NR_PRIORITIES;                            \
       idx = find_next_bit(array, CPUPRI_NR_PRIORITIES, idx+1))

/**
 * cpupri_find - find the best (lowest-pri) CPU in the system
 * @cp: The cpupri context
 * @p: The task
 * @lowest_mask: A mask to fill in with selected CPUs
 *
 * Note: This function returns the recommended CPUs as calculated during the
 * current invokation.  By the time the call returns, the CPUs may have in
 * fact changed priorities any number of times.  While not ideal, it is not
 * an issue of correctness since the normal rebalancer logic will correct
 * any discrepancies created by racing against the uncertainty of the current
 * priority configuration.
 *
 * Returns: (int)bool - CPUs were found
 */
int cpupri_find(struct cpupri *cp, struct task_struct *p,
		cpumask_t *lowest_mask)
{
	int                  idx      = 0;
	int                  task_pri = convert_prio(p->prio);

	for_each_cpupri_active(cp->pri_active, idx) {
		struct cpupri_vec *vec  = &cp->pri_to_cpu[idx];
		cpumask_t mask;

		if (idx >= task_pri)
			break;

		cpus_and(mask, p->cpus_allowed, vec->mask);

		if (cpus_empty(mask))
			continue;

		*lowest_mask = mask;
		return 1;
	}

	return 0;
}

/**
 * cpupri_set - update the cpu priority setting
 * @cp: The cpupri context
 * @cpu: The target cpu
 * @pri: The priority (INVALID-RT99) to assign to this CPU
 *
 * Note: Assumes cpu_rq(cpu)->lock is locked
 *
 * Returns: (void)
 */
void cpupri_set(struct cpupri *cp, int cpu, int newpri)
{
	int                 *currpri = &cp->cpu_to_pri[cpu];
	int                  oldpri  = *currpri;
	unsigned long        flags;

	newpri = convert_prio(newpri);

	BUG_ON(newpri >= CPUPRI_NR_PRIORITIES);

	if (newpri == oldpri)
		return;

	/*
	 * If the cpu was currently mapped to a different value, we
	 * first need to unmap the old value
	 */
	if (likely(oldpri != CPUPRI_INVALID)) {
		struct cpupri_vec *vec  = &cp->pri_to_cpu[oldpri];

		spin_lock_irqsave(&vec->lock, flags);

		vec->count--;
		if (!vec->count)
			clear_bit(oldpri, cp->pri_active);
		cpu_clear(cpu, vec->mask);

		spin_unlock_irqrestore(&vec->lock, flags);
	}

	if (likely(newpri != CPUPRI_INVALID)) {
		struct cpupri_vec *vec = &cp->pri_to_cpu[newpri];

		spin_lock_irqsave(&vec->lock, flags);

		cpu_set(cpu, vec->mask);
		vec->count++;
		if (vec->count == 1)
			set_bit(newpri, cp->pri_active);

		spin_unlock_irqrestore(&vec->lock, flags);
	}

	*currpri = newpri;
}

/**
 * cpupri_init - initialize the cpupri structure
 * @cp: The cpupri context
 *
 * Returns: (void)
 */
void cpupri_init(struct cpupri *cp)
{
	int i;

	memset(cp, 0, sizeof(*cp));

	for (i = 0; i < CPUPRI_NR_PRIORITIES; i++) {
		struct cpupri_vec *vec = &cp->pri_to_cpu[i];

		spin_lock_init(&vec->lock);
		vec->count = 0;
		cpus_clear(vec->mask);
	}

	for_each_possible_cpu(i)
		cp->cpu_to_pri[i] = CPUPRI_INVALID;
}