rt: Introduce cpu_chill()

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>

include/linux/delay.h

@@ -76,4 +76,10 @@ static inline void fsleep(unsigned long usecs)
 		msleep(DIV_ROUND_UP(usecs, 1000));
 }
 
+#ifdef CONFIG_PREEMPT_RT
+extern void cpu_chill(void);
+#else
+# define cpu_chill()	cpu_relax()
+#endif
+
 #endif /* defined(_LINUX_DELAY_H) */

kernel/time/hrtimer.c

@@ -1993,6 +1993,36 @@ SYSCALL_DEFINE2(nanosleep_time32, struct old_timespec32 __user *, rqtp,
 }
 #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;
+	struct task_struct *self = current;
+	ktime_t chill_time;
+
+	raw_spin_lock_irq(&self->pi_lock);
+	self->saved_state = self->state;
+	__set_current_state_no_track(TASK_UNINTERRUPTIBLE);
+	raw_spin_unlock_irq(&self->pi_lock);
+
+	chill_time = ktime_set(0, NSEC_PER_MSEC);
+
+	current->flags |= PF_NOFREEZE;
+	schedule_hrtimeout(&chill_time, HRTIMER_MODE_REL_HARD);
+	if (!freeze_flag)
+		current->flags &= ~PF_NOFREEZE;
+
+	raw_spin_lock_irq(&self->pi_lock);
+	__set_current_state_no_track(self->saved_state);
+	self->saved_state = TASK_RUNNING;
+	raw_spin_unlock_irq(&self->pi_lock);
+}
+EXPORT_SYMBOL(cpu_chill);
+#endif
+
 /*
  * Functions related to boot-time initialization:
  */