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
|
From ef79ed54f47d3ce342809e4914f4d9cf400f1ae0 Mon Sep 17 00:00:00 2001
From: Valentin Schneider <valentin.schneider@arm.com>
Date: Fri, 23 Oct 2020 12:12:17 +0200
Subject: [PATCH 020/323] sched: Comment affine_move_task()
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/5.10/older/patches-5.10.204-rt100.tar.xz
Signed-off-by: Valentin Schneider <valentin.schneider@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20201013140116.26651-2-valentin.schneider@arm.com
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
---
kernel/sched/core.c | 81 +++++++++++++++++++++++++++++++++++++++++++--
1 file changed, 79 insertions(+), 2 deletions(-)
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 3b7bb01eecc0..565d8011c832 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -2094,7 +2094,75 @@ void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask)
}
/*
- * This function is wildly self concurrent, consider at least 3 times.
+ * This function is wildly self concurrent; here be dragons.
+ *
+ *
+ * When given a valid mask, __set_cpus_allowed_ptr() must block until the
+ * designated task is enqueued on an allowed CPU. If that task is currently
+ * running, we have to kick it out using the CPU stopper.
+ *
+ * Migrate-Disable comes along and tramples all over our nice sandcastle.
+ * Consider:
+ *
+ * Initial conditions: P0->cpus_mask = [0, 1]
+ *
+ * P0@CPU0 P1
+ *
+ * migrate_disable();
+ * <preempted>
+ * set_cpus_allowed_ptr(P0, [1]);
+ *
+ * P1 *cannot* return from this set_cpus_allowed_ptr() call until P0 executes
+ * its outermost migrate_enable() (i.e. it exits its Migrate-Disable region).
+ * This means we need the following scheme:
+ *
+ * P0@CPU0 P1
+ *
+ * migrate_disable();
+ * <preempted>
+ * set_cpus_allowed_ptr(P0, [1]);
+ * <blocks>
+ * <resumes>
+ * migrate_enable();
+ * __set_cpus_allowed_ptr();
+ * <wakes local stopper>
+ * `--> <woken on migration completion>
+ *
+ * Now the fun stuff: there may be several P1-like tasks, i.e. multiple
+ * concurrent set_cpus_allowed_ptr(P0, [*]) calls. CPU affinity changes of any
+ * task p are serialized by p->pi_lock, which we can leverage: the one that
+ * should come into effect at the end of the Migrate-Disable region is the last
+ * one. This means we only need to track a single cpumask (i.e. p->cpus_mask),
+ * but we still need to properly signal those waiting tasks at the appropriate
+ * moment.
+ *
+ * This is implemented using struct set_affinity_pending. The first
+ * __set_cpus_allowed_ptr() caller within a given Migrate-Disable region will
+ * setup an instance of that struct and install it on the targeted task_struct.
+ * Any and all further callers will reuse that instance. Those then wait for
+ * a completion signaled at the tail of the CPU stopper callback (1), triggered
+ * on the end of the Migrate-Disable region (i.e. outermost migrate_enable()).
+ *
+ *
+ * (1) In the cases covered above. There is one more where the completion is
+ * signaled within affine_move_task() itself: when a subsequent affinity request
+ * cancels the need for an active migration. Consider:
+ *
+ * Initial conditions: P0->cpus_mask = [0, 1]
+ *
+ * P0@CPU0 P1 P2
+ *
+ * migrate_disable();
+ * <preempted>
+ * set_cpus_allowed_ptr(P0, [1]);
+ * <blocks>
+ * set_cpus_allowed_ptr(P0, [0, 1]);
+ * <signal completion>
+ * <awakes>
+ *
+ * Note that the above is safe vs a concurrent migrate_enable(), as any
+ * pending affinity completion is preceded an uninstallion of
+ * p->migration_pending done with p->pi_lock held.
*/
static int affine_move_task(struct rq *rq, struct task_struct *p, struct rq_flags *rf,
int dest_cpu, unsigned int flags)
@@ -2138,6 +2206,7 @@ static int affine_move_task(struct rq *rq, struct task_struct *p, struct rq_flag
if (!(flags & SCA_MIGRATE_ENABLE)) {
/* serialized by p->pi_lock */
if (!p->migration_pending) {
+ /* Install the request */
refcount_set(&my_pending.refs, 1);
init_completion(&my_pending.done);
p->migration_pending = &my_pending;
@@ -2181,7 +2250,11 @@ static int affine_move_task(struct rq *rq, struct task_struct *p, struct rq_flag
}
if (task_running(rq, p) || p->state == TASK_WAKING) {
-
+ /*
+ * Lessen races (and headaches) by delegating
+ * is_migration_disabled(p) checks to the stopper, which will
+ * run on the same CPU as said p.
+ */
task_rq_unlock(rq, p, rf);
stop_one_cpu(cpu_of(rq), migration_cpu_stop, &arg);
@@ -2206,6 +2279,10 @@ static int affine_move_task(struct rq *rq, struct task_struct *p, struct rq_flag
if (refcount_dec_and_test(&pending->refs))
wake_up_var(&pending->refs);
+ /*
+ * Block the original owner of &pending until all subsequent callers
+ * have seen the completion and decremented the refcount
+ */
wait_var_event(&my_pending.refs, !refcount_read(&my_pending.refs));
return 0;
--
2.43.0
|
