summaryrefslogtreecommitdiffstats
path: root/debian/patches-rt/hrtimers-prepare-full-preemption.patch
blob: 15015993489acd2d48f4806635e07770f2bc0c2c (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
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
From: Ingo Molnar <mingo@elte.hu>
Date: Fri, 3 Jul 2009 08:29:34 -0500
Subject: hrtimers: Prepare full preemption
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.13-rt10.tar.xz

Make cancellation of a running callback in softirq context safe
against preemption.

Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

---
 fs/timerfd.c                 |    5 ++++-
 include/linux/hrtimer.h      |   13 ++++++++++++-
 include/linux/posix-timers.h |    2 +-
 kernel/time/alarmtimer.c     |    2 +-
 kernel/time/hrtimer.c        |   33 ++++++++++++++++++++++++++++++++-
 kernel/time/itimer.c         |    1 +
 kernel/time/posix-timers.c   |   39 +++++++++++++++++++++++++++++++++++++--
 7 files changed, 88 insertions(+), 7 deletions(-)

--- a/fs/timerfd.c
+++ b/fs/timerfd.c
@@ -471,7 +471,10 @@ static int do_timerfd_settime(int ufd, i
 				break;
 		}
 		spin_unlock_irq(&ctx->wqh.lock);
-		cpu_relax();
+		if (isalarm(ctx))
+			hrtimer_wait_for_timer(&ctx->t.alarm.timer);
+		else
+			hrtimer_wait_for_timer(&ctx->t.tmr);
 	}
 
 	/*
--- a/include/linux/hrtimer.h
+++ b/include/linux/hrtimer.h
@@ -22,6 +22,7 @@
 #include <linux/percpu.h>
 #include <linux/timer.h>
 #include <linux/timerqueue.h>
+#include <linux/wait.h>
 
 struct hrtimer_clock_base;
 struct hrtimer_cpu_base;
@@ -216,6 +217,9 @@ struct hrtimer_cpu_base {
 	ktime_t				expires_next;
 	struct hrtimer			*next_timer;
 	ktime_t				softirq_expires_next;
+#ifdef CONFIG_PREEMPT_RT_BASE
+	wait_queue_head_t		wait;
+#endif
 	struct hrtimer			*softirq_next_timer;
 	struct hrtimer_clock_base	clock_base[HRTIMER_MAX_CLOCK_BASES];
 } ____cacheline_aligned;
@@ -433,6 +437,13 @@ static inline void hrtimer_restart(struc
 	hrtimer_start_expires(timer, HRTIMER_MODE_ABS);
 }
 
+/* Softirq preemption could deadlock timer removal */
+#ifdef CONFIG_PREEMPT_RT_BASE
+  extern void hrtimer_wait_for_timer(const struct hrtimer *timer);
+#else
+# define hrtimer_wait_for_timer(timer)	do { cpu_relax(); } while (0)
+#endif
+
 /* Query timers: */
 extern ktime_t __hrtimer_get_remaining(const struct hrtimer *timer, bool adjust);
 
@@ -458,7 +469,7 @@ static inline int hrtimer_is_queued(stru
  * Helper function to check, whether the timer is running the callback
  * function
  */
-static inline int hrtimer_callback_running(struct hrtimer *timer)
+static inline int hrtimer_callback_running(const struct hrtimer *timer)
 {
 	return timer->base->running == timer;
 }
--- a/include/linux/posix-timers.h
+++ b/include/linux/posix-timers.h
@@ -114,8 +114,8 @@ struct k_itimer {
 		struct {
 			struct alarm	alarmtimer;
 		} alarm;
-		struct rcu_head		rcu;
 	} it;
+	struct rcu_head		rcu;
 };
 
 void run_posix_cpu_timers(struct task_struct *task);
--- a/kernel/time/alarmtimer.c
+++ b/kernel/time/alarmtimer.c
@@ -436,7 +436,7 @@ int alarm_cancel(struct alarm *alarm)
 		int ret = alarm_try_to_cancel(alarm);
 		if (ret >= 0)
 			return ret;
-		cpu_relax();
+		hrtimer_wait_for_timer(&alarm->timer);
 	}
 }
 EXPORT_SYMBOL_GPL(alarm_cancel);
--- a/kernel/time/hrtimer.c
+++ b/kernel/time/hrtimer.c
@@ -939,6 +939,33 @@ u64 hrtimer_forward(struct hrtimer *time
 }
 EXPORT_SYMBOL_GPL(hrtimer_forward);
 
+#ifdef CONFIG_PREEMPT_RT_BASE
+# define wake_up_timer_waiters(b)	wake_up(&(b)->wait)
+
+/**
+ * hrtimer_wait_for_timer - Wait for a running timer
+ *
+ * @timer:	timer to wait for
+ *
+ * The function waits in case the timers callback function is
+ * currently executed on the waitqueue of the timer base. The
+ * waitqueue is woken up after the timer callback function has
+ * finished execution.
+ */
+void hrtimer_wait_for_timer(const struct hrtimer *timer)
+{
+	struct hrtimer_clock_base *base = timer->base;
+
+	if (base && base->cpu_base &&
+	    base->index >= HRTIMER_BASE_MONOTONIC_SOFT)
+		wait_event(base->cpu_base->wait,
+				!(hrtimer_callback_running(timer)));
+}
+
+#else
+# define wake_up_timer_waiters(b)	do { } while (0)
+#endif
+
 /*
  * enqueue_hrtimer - internal function to (re)start a timer
  *
@@ -1171,7 +1198,7 @@ int hrtimer_cancel(struct hrtimer *timer
 
 		if (ret >= 0)
 			return ret;
-		cpu_relax();
+		hrtimer_wait_for_timer(timer);
 	}
 }
 EXPORT_SYMBOL_GPL(hrtimer_cancel);
@@ -1477,6 +1504,7 @@ static __latent_entropy void hrtimer_run
 	hrtimer_update_softirq_timer(cpu_base, true);
 
 	raw_spin_unlock_irqrestore(&cpu_base->lock, flags);
+	wake_up_timer_waiters(cpu_base);
 }
 
 #ifdef CONFIG_HIGH_RES_TIMERS
@@ -1846,6 +1874,9 @@ int hrtimers_prepare_cpu(unsigned int cp
 	cpu_base->softirq_next_timer = NULL;
 	cpu_base->expires_next = KTIME_MAX;
 	cpu_base->softirq_expires_next = KTIME_MAX;
+#ifdef CONFIG_PREEMPT_RT_BASE
+	init_waitqueue_head(&cpu_base->wait);
+#endif
 	return 0;
 }
 
--- a/kernel/time/itimer.c
+++ b/kernel/time/itimer.c
@@ -215,6 +215,7 @@ int do_setitimer(int which, struct itime
 		/* We are sharing ->siglock with it_real_fn() */
 		if (hrtimer_try_to_cancel(timer) < 0) {
 			spin_unlock_irq(&tsk->sighand->siglock);
+			hrtimer_wait_for_timer(&tsk->signal->real_timer);
 			goto again;
 		}
 		expires = timeval_to_ktime(value->it_value);
--- a/kernel/time/posix-timers.c
+++ b/kernel/time/posix-timers.c
@@ -463,7 +463,7 @@ static struct k_itimer * alloc_posix_tim
 
 static void k_itimer_rcu_free(struct rcu_head *head)
 {
-	struct k_itimer *tmr = container_of(head, struct k_itimer, it.rcu);
+	struct k_itimer *tmr = container_of(head, struct k_itimer, rcu);
 
 	kmem_cache_free(posix_timers_cache, tmr);
 }
@@ -480,7 +480,7 @@ static void release_posix_timer(struct k
 	}
 	put_pid(tmr->it_pid);
 	sigqueue_free(tmr->sigq);
-	call_rcu(&tmr->it.rcu, k_itimer_rcu_free);
+	call_rcu(&tmr->rcu, k_itimer_rcu_free);
 }
 
 static int common_timer_create(struct k_itimer *new_timer)
@@ -821,6 +821,22 @@ static void common_hrtimer_arm(struct k_
 		hrtimer_start_expires(timer, HRTIMER_MODE_ABS);
 }
 
+/*
+ * Protected by RCU!
+ */
+static void timer_wait_for_callback(const struct k_clock *kc, struct k_itimer *timr)
+{
+#ifdef CONFIG_PREEMPT_RT_FULL
+	if (kc->timer_arm == common_hrtimer_arm)
+		hrtimer_wait_for_timer(&timr->it.real.timer);
+	else if (kc == &alarm_clock)
+		hrtimer_wait_for_timer(&timr->it.alarm.alarmtimer.timer);
+	else
+		/* FIXME: Whacky hack for posix-cpu-timers */
+		schedule_timeout(1);
+#endif
+}
+
 static int common_hrtimer_try_to_cancel(struct k_itimer *timr)
 {
 	return hrtimer_try_to_cancel(&timr->it.real.timer);
@@ -885,6 +901,7 @@ static int do_timer_settime(timer_t time
 	if (!timr)
 		return -EINVAL;
 
+	rcu_read_lock();
 	kc = timr->kclock;
 	if (WARN_ON_ONCE(!kc || !kc->timer_set))
 		error = -EINVAL;
@@ -893,9 +910,12 @@ static int do_timer_settime(timer_t time
 
 	unlock_timer(timr, flag);
 	if (error == TIMER_RETRY) {
+		timer_wait_for_callback(kc, timr);
 		old_spec64 = NULL;	// We already got the old time...
+		rcu_read_unlock();
 		goto retry;
 	}
+	rcu_read_unlock();
 
 	return error;
 }
@@ -977,10 +997,15 @@ SYSCALL_DEFINE1(timer_delete, timer_t, t
 	if (!timer)
 		return -EINVAL;
 
+	rcu_read_lock();
 	if (timer_delete_hook(timer) == TIMER_RETRY) {
 		unlock_timer(timer, flags);
+		timer_wait_for_callback(clockid_to_kclock(timer->it_clock),
+					timer);
+		rcu_read_unlock();
 		goto retry_delete;
 	}
+	rcu_read_unlock();
 
 	spin_lock(&current->sighand->siglock);
 	list_del(&timer->list);
@@ -1006,8 +1031,18 @@ static void itimer_delete(struct k_itime
 retry_delete:
 	spin_lock_irqsave(&timer->it_lock, flags);
 
+	/* On RT we can race with a deletion */
+	if (!timer->it_signal) {
+		unlock_timer(timer, flags);
+		return;
+	}
+
 	if (timer_delete_hook(timer) == TIMER_RETRY) {
+		rcu_read_lock();
 		unlock_timer(timer, flags);
+		timer_wait_for_callback(clockid_to_kclock(timer->it_clock),
+					timer);
+		rcu_read_unlock();
 		goto retry_delete;
 	}
 	list_del(&timer->list);