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
|
Subject: rt: Introduce cpu_chill()
From: Thomas Gleixner <tglx@linutronix.de>
Date: Wed Mar 7 20:51:03 2012 +0100
From: Thomas Gleixner <tglx@linutronix.de>
Retry loops on RT might loop forever when the modifying side was
preempted. Add cpu_chill() to replace cpu_relax(). cpu_chill()
defaults to cpu_relax() for non RT. On RT it puts the looping task to
sleep for a tick so the preempted task can make progress.
Steven Rostedt changed it to use a hrtimer instead of msleep():
|
|Ulrich Obergfell pointed out that cpu_chill() calls msleep() which is woken
|up by the ksoftirqd running the TIMER softirq. But as the cpu_chill() is
|called from softirq context, it may block the ksoftirqd() from running, in
|which case, it may never wake up the msleep() causing the deadlock.
+ bigeasy later changed to schedule_hrtimeout()
|If a task calls cpu_chill() and gets woken up by a regular or spurious
|wakeup and has a signal pending, then it exits the sleep loop in
|do_nanosleep() and sets up the restart block. If restart->nanosleep.type is
|not TI_NONE then this results in accessing a stale user pointer from a
|previously interrupted syscall and a copy to user based on the stale
|pointer or a BUG() when 'type' is not supported in nanosleep_copyout().
+ bigeasy: add PF_NOFREEZE:
| [....] Waiting for /dev to be fully populated...
| =====================================
| [ BUG: udevd/229 still has locks held! ]
| 3.12.11-rt17 #23 Not tainted
| -------------------------------------
| 1 lock held by udevd/229:
| #0: (&type->i_mutex_dir_key#2){+.+.+.}, at: lookup_slow+0x28/0x98
|
| stack backtrace:
| CPU: 0 PID: 229 Comm: udevd Not tainted 3.12.11-rt17 #23
| (unwind_backtrace+0x0/0xf8) from (show_stack+0x10/0x14)
| (show_stack+0x10/0x14) from (dump_stack+0x74/0xbc)
| (dump_stack+0x74/0xbc) from (do_nanosleep+0x120/0x160)
| (do_nanosleep+0x120/0x160) from (hrtimer_nanosleep+0x90/0x110)
| (hrtimer_nanosleep+0x90/0x110) from (cpu_chill+0x30/0x38)
| (cpu_chill+0x30/0x38) from (dentry_kill+0x158/0x1ec)
| (dentry_kill+0x158/0x1ec) from (dput+0x74/0x15c)
| (dput+0x74/0x15c) from (lookup_real+0x4c/0x50)
| (lookup_real+0x4c/0x50) from (__lookup_hash+0x34/0x44)
| (__lookup_hash+0x34/0x44) from (lookup_slow+0x38/0x98)
| (lookup_slow+0x38/0x98) from (path_lookupat+0x208/0x7fc)
| (path_lookupat+0x208/0x7fc) from (filename_lookup+0x20/0x60)
| (filename_lookup+0x20/0x60) from (user_path_at_empty+0x50/0x7c)
| (user_path_at_empty+0x50/0x7c) from (user_path_at+0x14/0x1c)
| (user_path_at+0x14/0x1c) from (vfs_fstatat+0x48/0x94)
| (vfs_fstatat+0x48/0x94) from (SyS_stat64+0x14/0x30)
| (SyS_stat64+0x14/0x30) from (ret_fast_syscall+0x0/0x48)
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
include/linux/hrtimer.h | 8 ++++++++
kernel/time/hrtimer.c | 31 ++++++++++++++++++++++++++++++-
2 files changed, 38 insertions(+), 1 deletion(-)
---
--- a/include/linux/hrtimer.h
+++ b/include/linux/hrtimer.h
@@ -42,6 +42,7 @@ enum hrtimer_mode {
HRTIMER_MODE_PINNED = 0x02,
HRTIMER_MODE_SOFT = 0x04,
HRTIMER_MODE_HARD = 0x08,
+ HRTIMER_MODE_CHILL = 0x10,
HRTIMER_MODE_ABS_PINNED = HRTIMER_MODE_ABS | HRTIMER_MODE_PINNED,
HRTIMER_MODE_REL_PINNED = HRTIMER_MODE_REL | HRTIMER_MODE_PINNED,
@@ -124,6 +125,7 @@ struct hrtimer {
u8 is_rel;
u8 is_soft;
u8 is_hard;
+ u8 is_chill;
};
/**
@@ -540,4 +542,10 @@ int hrtimers_dead_cpu(unsigned int cpu);
#define hrtimers_dead_cpu NULL
#endif
+#ifdef CONFIG_PREEMPT_RT
+extern void cpu_chill(void);
+#else
+# define cpu_chill() cpu_relax()
+#endif
+
#endif
--- a/kernel/time/hrtimer.c
+++ b/kernel/time/hrtimer.c
@@ -1422,6 +1422,7 @@ static void __hrtimer_init(struct hrtime
base += hrtimer_clockid_to_base(clock_id);
timer->is_soft = softtimer;
timer->is_hard = !!(mode & HRTIMER_MODE_HARD);
+ timer->is_chill = !!(mode & HRTIMER_MODE_CHILL);
timer->base = &cpu_base->clock_base[base];
timerqueue_init(&timer->node);
}
@@ -1788,7 +1789,7 @@ static enum hrtimer_restart hrtimer_wake
t->task = NULL;
if (task)
- wake_up_process(task);
+ wake_up_state(task, timer->is_chill ? TASK_RTLOCK_WAIT : TASK_NORMAL);
return HRTIMER_NORESTART;
}
@@ -2006,6 +2007,34 @@ SYSCALL_DEFINE2(nanosleep_time32, struct
}
#endif
+#ifdef CONFIG_PREEMPT_RT
+/*
+ * Sleep for 1 ms in hope whoever holds what we want will let it go.
+ */
+void cpu_chill(void)
+{
+ unsigned int freeze_flag = current->flags & PF_NOFREEZE;
+ ktime_t chill_time;
+
+ local_irq_disable();
+ current_save_and_set_rtlock_wait_state();
+ local_irq_enable();
+
+ chill_time = ktime_set(0, NSEC_PER_MSEC);
+
+ current->flags |= PF_NOFREEZE;
+ schedule_hrtimeout(&chill_time,
+ HRTIMER_MODE_REL_HARD| HRTIMER_MODE_CHILL);
+ if (!freeze_flag)
+ current->flags &= ~PF_NOFREEZE;
+
+ local_irq_disable();
+ current_restore_rtlock_saved_state();
+ local_irq_enable();
+}
+EXPORT_SYMBOL(cpu_chill);
+#endif
+
/*
* Functions related to boot-time initialization:
*/
|
