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
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
|
// SPDX-License-Identifier: GPL-2.0-only
/*
* 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.
*/
#include "sched.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;
}
static inline int __cpupri_find(struct cpupri *cp, struct task_struct *p,
struct cpumask *lowest_mask, int idx)
{
struct cpupri_vec *vec = &cp->pri_to_cpu[idx];
int skip = 0;
if (!atomic_read(&(vec)->count))
skip = 1;
/*
* When looking at the vector, we need to read the counter,
* do a memory barrier, then read the mask.
*
* Note: This is still all racey, but we can deal with it.
* Ideally, we only want to look at masks that are set.
*
* If a mask is not set, then the only thing wrong is that we
* did a little more work than necessary.
*
* If we read a zero count but the mask is set, because of the
* memory barriers, that can only happen when the highest prio
* task for a run queue has left the run queue, in which case,
* it will be followed by a pull. If the task we are processing
* fails to find a proper place to go, that pull request will
* pull this task if the run queue is running at a lower
* priority.
*/
smp_rmb();
/* Need to do the rmb for every iteration */
if (skip)
return 0;
if (cpumask_any_and(p->cpus_ptr, vec->mask) >= nr_cpu_ids)
return 0;
if (lowest_mask) {
cpumask_and(lowest_mask, p->cpus_ptr, vec->mask);
/*
* We have to ensure that we have at least one bit
* still set in the array, since the map could have
* been concurrently emptied between the first and
* second reads of vec->mask. If we hit this
* condition, simply act as though we never hit this
* priority level and continue on.
*/
if (cpumask_empty(lowest_mask))
return 0;
}
return 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 (or NULL)
* @fitness_fn: A pointer to a function to do custom checks whether the CPU
* fits a specific criteria so that we only return those CPUs.
*
* Note: This function returns the recommended CPUs as calculated during the
* current invocation. 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.
*
* Return: (int)bool - CPUs were found
*/
int cpupri_find(struct cpupri *cp, struct task_struct *p,
struct cpumask *lowest_mask,
bool (*fitness_fn)(struct task_struct *p, int cpu))
{
int task_pri = convert_prio(p->prio);
int best_unfit_idx = -1;
int idx = 0, cpu;
BUG_ON(task_pri >= CPUPRI_NR_PRIORITIES);
for (idx = 0; idx < task_pri; idx++) {
if (!__cpupri_find(cp, p, lowest_mask, idx))
continue;
if (!lowest_mask || !fitness_fn)
return 1;
/* Ensure the capacity of the CPUs fit the task */
for_each_cpu(cpu, lowest_mask) {
if (!fitness_fn(p, cpu))
cpumask_clear_cpu(cpu, lowest_mask);
}
/*
* If no CPU at the current priority can fit the task
* continue looking
*/
if (cpumask_empty(lowest_mask)) {
/*
* Store our fallback priority in case we
* didn't find a fitting CPU
*/
if (best_unfit_idx == -1)
best_unfit_idx = idx;
continue;
}
return 1;
}
/*
* If we failed to find a fitting lowest_mask, make sure we fall back
* to the last known unfitting lowest_mask.
*
* Note that the map of the recorded idx might have changed since then,
* so we must ensure to do the full dance to make sure that level still
* holds a valid lowest_mask.
*
* As per above, the map could have been concurrently emptied while we
* were busy searching for a fitting lowest_mask at the other priority
* levels.
*
* This rule favours honouring priority over fitting the task in the
* correct CPU (Capacity Awareness being the only user now).
* The idea is that if a higher priority task can run, then it should
* run even if this ends up being on unfitting CPU.
*
* The cost of this trade-off is not entirely clear and will probably
* be good for some workloads and bad for others.
*
* The main idea here is that if some CPUs were overcommitted, we try
* to spread which is what the scheduler traditionally did. Sys admins
* must do proper RT planning to avoid overloading the system if they
* really care.
*/
if (best_unfit_idx != -1)
return __cpupri_find(cp, p, lowest_mask, best_unfit_idx);
return 0;
}
/**
* cpupri_set - update the CPU priority setting
* @cp: The cpupri context
* @cpu: The target CPU
* @newpri: 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;
int do_mb = 0;
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
* need to map it to the new value then remove the old value.
* Note, we must add the new value first, otherwise we risk the
* cpu being missed by the priority loop in cpupri_find.
*/
if (likely(newpri != CPUPRI_INVALID)) {
struct cpupri_vec *vec = &cp->pri_to_cpu[newpri];
cpumask_set_cpu(cpu, vec->mask);
/*
* When adding a new vector, we update the mask first,
* do a write memory barrier, and then update the count, to
* make sure the vector is visible when count is set.
*/
smp_mb__before_atomic();
atomic_inc(&(vec)->count);
do_mb = 1;
}
if (likely(oldpri != CPUPRI_INVALID)) {
struct cpupri_vec *vec = &cp->pri_to_cpu[oldpri];
/*
* Because the order of modification of the vec->count
* is important, we must make sure that the update
* of the new prio is seen before we decrement the
* old prio. This makes sure that the loop sees
* one or the other when we raise the priority of
* the run queue. We don't care about when we lower the
* priority, as that will trigger an rt pull anyway.
*
* We only need to do a memory barrier if we updated
* the new priority vec.
*/
if (do_mb)
smp_mb__after_atomic();
/*
* When removing from the vector, we decrement the counter first
* do a memory barrier and then clear the mask.
*/
atomic_dec(&(vec)->count);
smp_mb__after_atomic();
cpumask_clear_cpu(cpu, vec->mask);
}
*currpri = newpri;
}
/**
* cpupri_init - initialize the cpupri structure
* @cp: The cpupri context
*
* Return: -ENOMEM on memory allocation failure.
*/
int cpupri_init(struct cpupri *cp)
{
int i;
for (i = 0; i < CPUPRI_NR_PRIORITIES; i++) {
struct cpupri_vec *vec = &cp->pri_to_cpu[i];
atomic_set(&vec->count, 0);
if (!zalloc_cpumask_var(&vec->mask, GFP_KERNEL))
goto cleanup;
}
cp->cpu_to_pri = kcalloc(nr_cpu_ids, sizeof(int), GFP_KERNEL);
if (!cp->cpu_to_pri)
goto cleanup;
for_each_possible_cpu(i)
cp->cpu_to_pri[i] = CPUPRI_INVALID;
return 0;
cleanup:
for (i--; i >= 0; i--)
free_cpumask_var(cp->pri_to_cpu[i].mask);
return -ENOMEM;
}
/**
* cpupri_cleanup - clean up the cpupri structure
* @cp: The cpupri context
*/
void cpupri_cleanup(struct cpupri *cp)
{
int i;
kfree(cp->cpu_to_pri);
for (i = 0; i < CPUPRI_NR_PRIORITIES; i++)
free_cpumask_var(cp->pri_to_cpu[i].mask);
}
|