linux/debian/patches/features/all/rt/cpu_chill-Add-a-UNINTERRUPT...

104 lines
3.9 KiB
Diff

From: Steven Rostedt <rostedt@goodmis.org>
Date: Tue, 4 Mar 2014 12:28:32 -0500
Subject: cpu_chill: Add a UNINTERRUPTIBLE hrtimer_nanosleep
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.14/older/patches-4.14.8-rt9.tar.xz
We hit another bug that was caused by switching cpu_chill() from
msleep() to hrtimer_nanosleep().
This time it is a livelock. The problem is that hrtimer_nanosleep()
calls schedule with the state == TASK_INTERRUPTIBLE. But these means
that if a signal is pending, the scheduler wont schedule, and will
simply change the current task state back to TASK_RUNNING. This
nullifies the whole point of cpu_chill() in the first place. That is,
if a task is spinning on a try_lock() and it preempted the owner of the
lock, if it has a signal pending, it will never give up the CPU to let
the owner of the lock run.
I made a static function __hrtimer_nanosleep() that takes a fifth
parameter "state", which determines the task state of that the
nanosleep() will be in. The normal hrtimer_nanosleep() will act the
same, but cpu_chill() will call the __hrtimer_nanosleep() directly with
the TASK_UNINTERRUPTIBLE state.
cpu_chill() only cares that the first sleep happens, and does not care
about the state of the restart schedule (in hrtimer_nanosleep_restart).
Reported-by: Ulrich Obergfell <uobergfe@redhat.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
---
kernel/time/hrtimer.c | 24 +++++++++++++++++-------
1 file changed, 17 insertions(+), 7 deletions(-)
--- a/kernel/time/hrtimer.c
+++ b/kernel/time/hrtimer.c
@@ -1743,12 +1743,13 @@ int nanosleep_copyout(struct restart_blo
return -ERESTART_RESTARTBLOCK;
}
-static int __sched do_nanosleep(struct hrtimer_sleeper *t, enum hrtimer_mode mode)
+static int __sched do_nanosleep(struct hrtimer_sleeper *t, enum hrtimer_mode mode,
+ unsigned long state)
{
struct restart_block *restart;
do {
- set_current_state(TASK_INTERRUPTIBLE);
+ set_current_state(state);
hrtimer_start_expires(&t->timer, mode);
if (likely(t->task))
@@ -1786,13 +1787,15 @@ static long __sched hrtimer_nanosleep_re
hrtimer_init_sleeper_on_stack(&t, restart->nanosleep.clockid,
HRTIMER_MODE_ABS, current);
hrtimer_set_expires_tv64(&t.timer, restart->nanosleep.expires);
- ret = do_nanosleep(&t, HRTIMER_MODE_ABS);
+ /* cpu_chill() does not care about restart state. */
+ ret = do_nanosleep(&t, HRTIMER_MODE_ABS, TASK_INTERRUPTIBLE);
destroy_hrtimer_on_stack(&t.timer);
return ret;
}
-long hrtimer_nanosleep(const struct timespec64 *rqtp,
- const enum hrtimer_mode mode, const clockid_t clockid)
+static long __hrtimer_nanosleep(const struct timespec64 *rqtp,
+ const enum hrtimer_mode mode, const clockid_t clockid,
+ unsigned long state)
{
struct restart_block *restart;
struct hrtimer_sleeper t;
@@ -1805,7 +1808,7 @@ long hrtimer_nanosleep(const struct time
hrtimer_init_sleeper_on_stack(&t, clockid, mode, current);
hrtimer_set_expires_range_ns(&t.timer, timespec64_to_ktime(*rqtp), slack);
- ret = do_nanosleep(&t, mode);
+ ret = do_nanosleep(&t, mode, state);
if (ret != -ERESTART_RESTARTBLOCK)
goto out;
@@ -1824,6 +1827,12 @@ long hrtimer_nanosleep(const struct time
return ret;
}
+long hrtimer_nanosleep(const struct timespec64 *rqtp,
+ const enum hrtimer_mode mode, const clockid_t clockid)
+{
+ return __hrtimer_nanosleep(rqtp, mode, clockid, TASK_INTERRUPTIBLE);
+}
+
SYSCALL_DEFINE2(nanosleep, struct timespec __user *, rqtp,
struct timespec __user *, rmtp)
{
@@ -1871,7 +1880,8 @@ void cpu_chill(void)
unsigned int freeze_flag = current->flags & PF_NOFREEZE;
current->flags |= PF_NOFREEZE;
- hrtimer_nanosleep(&tu, HRTIMER_MODE_REL_HARD, CLOCK_MONOTONIC);
+ __hrtimer_nanosleep(&tu, HRTIMER_MODE_REL_HARD, CLOCK_MONOTONIC,
+ TASK_UNINTERRUPTIBLE);
if (!freeze_flag)
current->flags &= ~PF_NOFREEZE;
}