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
|
From: John Stultz <johnstul@us.ibm.com>
Date: Fri, 3 Jul 2009 08:29:58 -0500
Subject: [PATCH 104/353] posix-timers: Thread posix-cpu-timers on -rt
Origin: https://git.kernel.org/cgit/linux/kernel/git/rt/linux-stable-rt.git/commit?id=93d6691678e3b2f624878e8ba031fbbb16094def
posix-cpu-timer code takes non -rt safe locks in hard irq
context. Move it to a thread.
[ 3.0 fixes from Peter Zijlstra <peterz@infradead.org> ]
Signed-off-by: John Stultz <johnstul@us.ibm.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
include/linux/sched.h | 3 +
init/init_task.c | 7 ++
kernel/fork.c | 3 +
kernel/time/posix-cpu-timers.c | 154 ++++++++++++++++++++++++++++++++-
4 files changed, 164 insertions(+), 3 deletions(-)
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 96b1e60d2444..92faffe9ecf0 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -836,6 +836,9 @@ struct task_struct {
#ifdef CONFIG_POSIX_TIMERS
struct task_cputime cputime_expires;
struct list_head cpu_timers[3];
+#ifdef CONFIG_PREEMPT_RT_BASE
+ struct task_struct *posix_timer_list;
+#endif
#endif
/* Process credentials: */
diff --git a/init/init_task.c b/init/init_task.c
index d71054b95528..634becebd713 100644
--- a/init/init_task.c
+++ b/init/init_task.c
@@ -50,6 +50,12 @@ static struct sighand_struct init_sighand = {
.signalfd_wqh = __WAIT_QUEUE_HEAD_INITIALIZER(init_sighand.signalfd_wqh),
};
+#if defined(CONFIG_POSIX_TIMERS) && defined(CONFIG_PREEMPT_RT_BASE)
+# define INIT_TIMER_LIST .posix_timer_list = NULL,
+#else
+# define INIT_TIMER_LIST
+#endif
+
/*
* Set up the first task table, touch at your own risk!. Base=0,
* limit=0x1fffff (=2MB)
@@ -119,6 +125,7 @@ struct task_struct init_task
INIT_CPU_TIMERS(init_task)
.pi_lock = __RAW_SPIN_LOCK_UNLOCKED(init_task.pi_lock),
.timer_slack_ns = 50000, /* 50 usec default slack */
+ INIT_TIMER_LIST
.thread_pid = &init_struct_pid,
.thread_group = LIST_HEAD_INIT(init_task.thread_group),
.thread_node = LIST_HEAD_INIT(init_signals.thread_head),
diff --git a/kernel/fork.c b/kernel/fork.c
index a18d695259af..c27c196fd70e 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1587,6 +1587,9 @@ static void rt_mutex_init_task(struct task_struct *p)
*/
static void posix_cpu_timers_init(struct task_struct *tsk)
{
+#ifdef CONFIG_PREEMPT_RT_BASE
+ tsk->posix_timer_list = NULL;
+#endif
tsk->cputime_expires.prof_exp = 0;
tsk->cputime_expires.virt_exp = 0;
tsk->cputime_expires.sched_exp = 0;
diff --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c
index bfaa44a80c03..2d29b269dc83 100644
--- a/kernel/time/posix-cpu-timers.c
+++ b/kernel/time/posix-cpu-timers.c
@@ -3,8 +3,10 @@
* Implement CPU time clocks for the POSIX clock interface.
*/
+#include <uapi/linux/sched/types.h>
#include <linux/sched/signal.h>
#include <linux/sched/cputime.h>
+#include <linux/sched/rt.h>
#include <linux/posix-timers.h>
#include <linux/errno.h>
#include <linux/math64.h>
@@ -15,6 +17,7 @@
#include <linux/workqueue.h>
#include <linux/compat.h>
#include <linux/sched/deadline.h>
+#include <linux/smpboot.h>
#include "posix-timers.h"
@@ -1140,14 +1143,12 @@ static inline int fastpath_timer_check(struct task_struct *tsk)
* already updated our counts. We need to check if any timers fire now.
* Interrupts are disabled.
*/
-void run_posix_cpu_timers(struct task_struct *tsk)
+static void __run_posix_cpu_timers(struct task_struct *tsk)
{
LIST_HEAD(firing);
struct k_itimer *timer, *next;
unsigned long flags;
- lockdep_assert_irqs_disabled();
-
/*
* The fast path checks that there are no expired thread or thread
* group timers. If that's so, just return.
@@ -1200,6 +1201,153 @@ void run_posix_cpu_timers(struct task_struct *tsk)
}
}
+#ifdef CONFIG_PREEMPT_RT_BASE
+#include <linux/kthread.h>
+#include <linux/cpu.h>
+DEFINE_PER_CPU(struct task_struct *, posix_timer_task);
+DEFINE_PER_CPU(struct task_struct *, posix_timer_tasklist);
+DEFINE_PER_CPU(bool, posix_timer_th_active);
+
+static void posix_cpu_kthread_fn(unsigned int cpu)
+{
+ struct task_struct *tsk = NULL;
+ struct task_struct *next = NULL;
+
+ BUG_ON(per_cpu(posix_timer_task, cpu) != current);
+
+ /* grab task list */
+ raw_local_irq_disable();
+ tsk = per_cpu(posix_timer_tasklist, cpu);
+ per_cpu(posix_timer_tasklist, cpu) = NULL;
+ raw_local_irq_enable();
+
+ /* its possible the list is empty, just return */
+ if (!tsk)
+ return;
+
+ /* Process task list */
+ while (1) {
+ /* save next */
+ next = tsk->posix_timer_list;
+
+ /* run the task timers, clear its ptr and
+ * unreference it
+ */
+ __run_posix_cpu_timers(tsk);
+ tsk->posix_timer_list = NULL;
+ put_task_struct(tsk);
+
+ /* check if this is the last on the list */
+ if (next == tsk)
+ break;
+ tsk = next;
+ }
+}
+
+static inline int __fastpath_timer_check(struct task_struct *tsk)
+{
+ /* tsk == current, ensure it is safe to use ->signal/sighand */
+ if (unlikely(tsk->exit_state))
+ return 0;
+
+ if (!task_cputime_zero(&tsk->cputime_expires))
+ return 1;
+
+ if (!task_cputime_zero(&tsk->signal->cputime_expires))
+ return 1;
+
+ return 0;
+}
+
+void run_posix_cpu_timers(struct task_struct *tsk)
+{
+ unsigned int cpu = smp_processor_id();
+ struct task_struct *tasklist;
+
+ BUG_ON(!irqs_disabled());
+
+ if (per_cpu(posix_timer_th_active, cpu) != true)
+ return;
+
+ /* get per-cpu references */
+ tasklist = per_cpu(posix_timer_tasklist, cpu);
+
+ /* check to see if we're already queued */
+ if (!tsk->posix_timer_list && __fastpath_timer_check(tsk)) {
+ get_task_struct(tsk);
+ if (tasklist) {
+ tsk->posix_timer_list = tasklist;
+ } else {
+ /*
+ * The list is terminated by a self-pointing
+ * task_struct
+ */
+ tsk->posix_timer_list = tsk;
+ }
+ per_cpu(posix_timer_tasklist, cpu) = tsk;
+
+ wake_up_process(per_cpu(posix_timer_task, cpu));
+ }
+}
+
+static int posix_cpu_kthread_should_run(unsigned int cpu)
+{
+ return __this_cpu_read(posix_timer_tasklist) != NULL;
+}
+
+static void posix_cpu_kthread_park(unsigned int cpu)
+{
+ this_cpu_write(posix_timer_th_active, false);
+}
+
+static void posix_cpu_kthread_unpark(unsigned int cpu)
+{
+ this_cpu_write(posix_timer_th_active, true);
+}
+
+static void posix_cpu_kthread_setup(unsigned int cpu)
+{
+ struct sched_param sp;
+
+ sp.sched_priority = MAX_RT_PRIO - 1;
+ sched_setscheduler_nocheck(current, SCHED_FIFO, &sp);
+ posix_cpu_kthread_unpark(cpu);
+}
+
+static struct smp_hotplug_thread posix_cpu_thread = {
+ .store = &posix_timer_task,
+ .thread_should_run = posix_cpu_kthread_should_run,
+ .thread_fn = posix_cpu_kthread_fn,
+ .thread_comm = "posixcputmr/%u",
+ .setup = posix_cpu_kthread_setup,
+ .park = posix_cpu_kthread_park,
+ .unpark = posix_cpu_kthread_unpark,
+};
+
+static int __init posix_cpu_thread_init(void)
+{
+ /* Start one for boot CPU. */
+ unsigned long cpu;
+ int ret;
+
+ /* init the per-cpu posix_timer_tasklets */
+ for_each_possible_cpu(cpu)
+ per_cpu(posix_timer_tasklist, cpu) = NULL;
+
+ ret = smpboot_register_percpu_thread(&posix_cpu_thread);
+ WARN_ON(ret);
+
+ return 0;
+}
+early_initcall(posix_cpu_thread_init);
+#else /* CONFIG_PREEMPT_RT_BASE */
+void run_posix_cpu_timers(struct task_struct *tsk)
+{
+ lockdep_assert_irqs_disabled();
+ __run_posix_cpu_timers(tsk);
+}
+#endif /* CONFIG_PREEMPT_RT_BASE */
+
/*
* Set one of the process-wide special case CPU timers or RLIMIT_CPU.
* The tsk->sighand->siglock must be held by the caller.
|
