diff mbox series

[v6,1/2] posix-timers: Prefer delivery of signals to the current thread

Message ID 20230316123028.2890338-1-elver@google.com
State New
Headers show
Series [v6,1/2] posix-timers: Prefer delivery of signals to the current thread | expand

Commit Message

Marco Elver March 16, 2023, 12:30 p.m. UTC
From: Dmitry Vyukov <dvyukov@google.com>

POSIX timers using the CLOCK_PROCESS_CPUTIME_ID clock prefer the main
thread of a thread group for signal delivery.     However, this has a
significant downside: it requires waking up a potentially idle thread.

Instead, prefer to deliver signals to the current thread (in the same
thread group) if SIGEV_THREAD_ID is not set by the user. This does not
change guaranteed semantics, since POSIX process CPU time timers have
never guaranteed that signal delivery is to a specific thread (without
SIGEV_THREAD_ID set).

The effect is that we no longer wake up potentially idle threads, and
the kernel is no longer biased towards delivering the timer signal to
any particular thread (which better distributes the timer signals esp.
when multiple timers fire concurrently).

Signed-off-by: Dmitry Vyukov <dvyukov@google.com>
Suggested-by: Oleg Nesterov <oleg@redhat.com>
Reviewed-by: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Marco Elver <elver@google.com>
---
v6:
- Split test from this patch.
- Update wording on what this patch aims to improve.

v5:
- Rebased onto v6.2.

v4:
- Restructured checks in send_sigqueue() as suggested.

v3:
- Switched to the completely different implementation (much simpler)
  based on the Oleg's idea.

RFC v2:
- Added additional Cc as Thomas asked.
---
 kernel/signal.c | 25 ++++++++++++++++++++++---
 1 file changed, 22 insertions(+), 3 deletions(-)

Comments

Marco Elver April 6, 2023, 2:12 p.m. UTC | #1
On Thu, 16 Mar 2023 at 13:31, Marco Elver <elver@google.com> wrote:
>
> From: Dmitry Vyukov <dvyukov@google.com>
>
> POSIX timers using the CLOCK_PROCESS_CPUTIME_ID clock prefer the main
> thread of a thread group for signal delivery.     However, this has a
> significant downside: it requires waking up a potentially idle thread.
>
> Instead, prefer to deliver signals to the current thread (in the same
> thread group) if SIGEV_THREAD_ID is not set by the user. This does not
> change guaranteed semantics, since POSIX process CPU time timers have
> never guaranteed that signal delivery is to a specific thread (without
> SIGEV_THREAD_ID set).
>
> The effect is that we no longer wake up potentially idle threads, and
> the kernel is no longer biased towards delivering the timer signal to
> any particular thread (which better distributes the timer signals esp.
> when multiple timers fire concurrently).
>
> Signed-off-by: Dmitry Vyukov <dvyukov@google.com>
> Suggested-by: Oleg Nesterov <oleg@redhat.com>
> Reviewed-by: Oleg Nesterov <oleg@redhat.com>
> Signed-off-by: Marco Elver <elver@google.com>
> ---
> v6:
> - Split test from this patch.
> - Update wording on what this patch aims to improve.
>
> v5:
> - Rebased onto v6.2.
>
> v4:
> - Restructured checks in send_sigqueue() as suggested.
>
> v3:
> - Switched to the completely different implementation (much simpler)
>   based on the Oleg's idea.
>
> RFC v2:
> - Added additional Cc as Thomas asked.
> ---
>  kernel/signal.c | 25 ++++++++++++++++++++++---
>  1 file changed, 22 insertions(+), 3 deletions(-)
>
> diff --git a/kernel/signal.c b/kernel/signal.c
> index 8cb28f1df294..605445fa27d4 100644
> --- a/kernel/signal.c
> +++ b/kernel/signal.c
> @@ -1003,8 +1003,7 @@ static void complete_signal(int sig, struct task_struct *p, enum pid_type type)
>         /*
>          * Now find a thread we can wake up to take the signal off the queue.
>          *
> -        * If the main thread wants the signal, it gets first crack.
> -        * Probably the least surprising to the average bear.
> +        * Try the suggested task first (may or may not be the main thread).
>          */
>         if (wants_signal(sig, p))
>                 t = p;
> @@ -1970,8 +1969,23 @@ int send_sigqueue(struct sigqueue *q, struct pid *pid, enum pid_type type)
>
>         ret = -1;
>         rcu_read_lock();
> +       /*
> +        * This function is used by POSIX timers to deliver a timer signal.
> +        * Where type is PIDTYPE_PID (such as for timers with SIGEV_THREAD_ID
> +        * set), the signal must be delivered to the specific thread (queues
> +        * into t->pending).
> +        *
> +        * Where type is not PIDTYPE_PID, signals must just be delivered to the
> +        * current process. In this case, prefer to deliver to current if it is
> +        * in the same thread group as the target, as it avoids unnecessarily
> +        * waking up a potentially idle task.
> +        */
>         t = pid_task(pid, type);
> -       if (!t || !likely(lock_task_sighand(t, &flags)))
> +       if (!t)
> +               goto ret;
> +       if (type != PIDTYPE_PID && same_thread_group(t, current))
> +               t = current;
> +       if (!likely(lock_task_sighand(t, &flags)))
>                 goto ret;
>
>         ret = 1; /* the signal is ignored */
> @@ -1993,6 +2007,11 @@ int send_sigqueue(struct sigqueue *q, struct pid *pid, enum pid_type type)
>         q->info.si_overrun = 0;
>
>         signalfd_notify(t, sig);
> +       /*
> +        * If the type is not PIDTYPE_PID, we just use shared_pending, which
> +        * won't guarantee that the specified task will receive the signal, but
> +        * is sufficient if t==current in the common case.
> +        */
>         pending = (type != PIDTYPE_PID) ? &t->signal->shared_pending : &t->pending;
>         list_add_tail(&q->list, &pending->list);
>         sigaddset(&pending->signal, sig);
> --

One last semi-gentle ping. ;-)

1. We're seeing that in some applications that use POSIX timers
heavily, but where the main thread is mostly idle, the main thread
receives a disproportional amount of the signals along with being
woken up constantly. This is bad, because the main thread usually
waits with the help of a futex or really long sleeps. Now the main
thread will steal time (to go back to sleep) from another thread that
could have instead just proceeded with whatever it was doing.

2. Delivering signals to random threads is currently way too
expensive. We need to resort to this crazy algorithm: 1) receive timer
signal, 2) check if main thread, 3) if main thread (which is likely),
pick a random thread and do tgkill. To find a random thread, iterate
/proc/self/task, but that's just abysmal for various reasons. Other
alternatives, like inherited task clock perf events are too expensive
as soon as we need to enable/disable the timers (does IPIs), and
maintaining O(#threads) timers is just as horrible.

This patch solves both the above issues.

We acknowledge the unfortunate situation of attributing this patch to
one clear subsystem and owner: it straddles into signal delivery and
POSIX timers territory, and perhaps some scheduling. The patch itself
only touches kernel/signal.c.

If anyone has serious objections, please shout (soon'ish). Given the
patch has been reviewed by Oleg, and scrutinized by Dmitry and myself,
presumably we need to find a tree that currently takes kernel/signal.c
patches?

Thanks!

-- Marco
Peter Zijlstra April 6, 2023, 8:22 p.m. UTC | #2
On Thu, Mar 16, 2023 at 01:30:27PM +0100, Marco Elver wrote:
> From: Dmitry Vyukov <dvyukov@google.com>
> 
> POSIX timers using the CLOCK_PROCESS_CPUTIME_ID clock prefer the main
> thread of a thread group for signal delivery.     However, this has a
> significant downside: it requires waking up a potentially idle thread.
> 
> Instead, prefer to deliver signals to the current thread (in the same
> thread group) if SIGEV_THREAD_ID is not set by the user. This does not
> change guaranteed semantics, since POSIX process CPU time timers have
> never guaranteed that signal delivery is to a specific thread (without
> SIGEV_THREAD_ID set).
> 
> The effect is that we no longer wake up potentially idle threads, and
> the kernel is no longer biased towards delivering the timer signal to
> any particular thread (which better distributes the timer signals esp.
> when multiple timers fire concurrently).
> 
> Signed-off-by: Dmitry Vyukov <dvyukov@google.com>
> Suggested-by: Oleg Nesterov <oleg@redhat.com>
> Reviewed-by: Oleg Nesterov <oleg@redhat.com>
> Signed-off-by: Marco Elver <elver@google.com>

Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>

> ---
>  kernel/signal.c | 25 ++++++++++++++++++++++---
>  1 file changed, 22 insertions(+), 3 deletions(-)
> 
> diff --git a/kernel/signal.c b/kernel/signal.c
> index 8cb28f1df294..605445fa27d4 100644
> --- a/kernel/signal.c
> +++ b/kernel/signal.c
> @@ -1003,8 +1003,7 @@ static void complete_signal(int sig, struct task_struct *p, enum pid_type type)
>  	/*
>  	 * Now find a thread we can wake up to take the signal off the queue.
>  	 *
> -	 * If the main thread wants the signal, it gets first crack.
> -	 * Probably the least surprising to the average bear.
> +	 * Try the suggested task first (may or may not be the main thread).
>  	 */
>  	if (wants_signal(sig, p))
>  		t = p;
> @@ -1970,8 +1969,23 @@ int send_sigqueue(struct sigqueue *q, struct pid *pid, enum pid_type type)
>  
>  	ret = -1;
>  	rcu_read_lock();
> +	/*
> +	 * This function is used by POSIX timers to deliver a timer signal.
> +	 * Where type is PIDTYPE_PID (such as for timers with SIGEV_THREAD_ID
> +	 * set), the signal must be delivered to the specific thread (queues
> +	 * into t->pending).
> +	 *
> +	 * Where type is not PIDTYPE_PID, signals must just be delivered to the
> +	 * current process. In this case, prefer to deliver to current if it is
> +	 * in the same thread group as the target, as it avoids unnecessarily
> +	 * waking up a potentially idle task.
> +	 */
>  	t = pid_task(pid, type);
> -	if (!t || !likely(lock_task_sighand(t, &flags)))
> +	if (!t)
> +		goto ret;
> +	if (type != PIDTYPE_PID && same_thread_group(t, current))
> +		t = current;
> +	if (!likely(lock_task_sighand(t, &flags)))
>  		goto ret;
>  
>  	ret = 1; /* the signal is ignored */
> @@ -1993,6 +2007,11 @@ int send_sigqueue(struct sigqueue *q, struct pid *pid, enum pid_type type)
>  	q->info.si_overrun = 0;
>  
>  	signalfd_notify(t, sig);
> +	/*
> +	 * If the type is not PIDTYPE_PID, we just use shared_pending, which
> +	 * won't guarantee that the specified task will receive the signal, but
> +	 * is sufficient if t==current in the common case.
> +	 */
>  	pending = (type != PIDTYPE_PID) ? &t->signal->shared_pending : &t->pending;
>  	list_add_tail(&q->list, &pending->list);
>  	sigaddset(&pending->signal, sig);
> -- 
> 2.40.0.rc1.284.g88254d51c5-goog
>
John Stultz April 1, 2024, 8:17 p.m. UTC | #3
On Thu, Mar 16, 2023 at 5:30 AM Marco Elver <elver@google.com> wrote:
>
> From: Dmitry Vyukov <dvyukov@google.com>
>
> POSIX timers using the CLOCK_PROCESS_CPUTIME_ID clock prefer the main
> thread of a thread group for signal delivery.     However, this has a
> significant downside: it requires waking up a potentially idle thread.
>
> Instead, prefer to deliver signals to the current thread (in the same
> thread group) if SIGEV_THREAD_ID is not set by the user. This does not
> change guaranteed semantics, since POSIX process CPU time timers have
> never guaranteed that signal delivery is to a specific thread (without
> SIGEV_THREAD_ID set).
>
> The effect is that we no longer wake up potentially idle threads, and
> the kernel is no longer biased towards delivering the timer signal to
> any particular thread (which better distributes the timer signals esp.
> when multiple timers fire concurrently).
>
> Signed-off-by: Dmitry Vyukov <dvyukov@google.com>
> Suggested-by: Oleg Nesterov <oleg@redhat.com>
> Reviewed-by: Oleg Nesterov <oleg@redhat.com>
> Signed-off-by: Marco Elver <elver@google.com>

Apologies for drudging up this old thread.

I wanted to ask if anyone had objections to including this in the -stable trees?

After this and the follow-on patch e797203fb3ba
("selftests/timers/posix_timers: Test delivery of signals across
threads") landed, folks testing older kernels with the latest
selftests started to see the new test checking for this behavior to
stall.  Thomas did submit an adjustment to the test here to avoid the
stall: https://lore.kernel.org/lkml/20230606142031.071059989@linutronix.de/,
but it didn't seem to land, however that would just result in the test
failing instead of hanging.

This change does seem to cherry-pick cleanly back to at least
stable/linux-5.10.y cleanly, so it looks simple to pull this change
back. But I wanted to make sure there wasn't anything subtle I was
missing before sending patches.

thanks
-john
Dmitry Vyukov April 2, 2024, 9:07 a.m. UTC | #4
On Mon, 1 Apr 2024 at 22:17, John Stultz <jstultz@google.com> wrote:
>
> On Thu, Mar 16, 2023 at 5:30 AM Marco Elver <elver@google.com> wrote:
> >
> > From: Dmitry Vyukov <dvyukov@google.com>
> >
> > POSIX timers using the CLOCK_PROCESS_CPUTIME_ID clock prefer the main
> > thread of a thread group for signal delivery.     However, this has a
> > significant downside: it requires waking up a potentially idle thread.
> >
> > Instead, prefer to deliver signals to the current thread (in the same
> > thread group) if SIGEV_THREAD_ID is not set by the user. This does not
> > change guaranteed semantics, since POSIX process CPU time timers have
> > never guaranteed that signal delivery is to a specific thread (without
> > SIGEV_THREAD_ID set).
> >
> > The effect is that we no longer wake up potentially idle threads, and
> > the kernel is no longer biased towards delivering the timer signal to
> > any particular thread (which better distributes the timer signals esp.
> > when multiple timers fire concurrently).
> >
> > Signed-off-by: Dmitry Vyukov <dvyukov@google.com>
> > Suggested-by: Oleg Nesterov <oleg@redhat.com>
> > Reviewed-by: Oleg Nesterov <oleg@redhat.com>
> > Signed-off-by: Marco Elver <elver@google.com>
>
> Apologies for drudging up this old thread.
>
> I wanted to ask if anyone had objections to including this in the -stable trees?
>
> After this and the follow-on patch e797203fb3ba
> ("selftests/timers/posix_timers: Test delivery of signals across
> threads") landed, folks testing older kernels with the latest
> selftests started to see the new test checking for this behavior to
> stall.  Thomas did submit an adjustment to the test here to avoid the
> stall: https://lore.kernel.org/lkml/20230606142031.071059989@linutronix.de/,
> but it didn't seem to land, however that would just result in the test
> failing instead of hanging.
>
> This change does seem to cherry-pick cleanly back to at least
> stable/linux-5.10.y cleanly, so it looks simple to pull this change
> back. But I wanted to make sure there wasn't anything subtle I was
> missing before sending patches.

I don't have objections per se. But I wonder how other tests deal with
such situations. It should happen for any test for new functionality.
Can we do the same other tests are doing?
Thomas Gleixner April 2, 2024, 2:57 p.m. UTC | #5
On Mon, Apr 01 2024 at 13:17, John Stultz wrote:
> Apologies for drudging up this old thread.
> I wanted to ask if anyone had objections to including this in the -stable trees?
>
> After this and the follow-on patch e797203fb3ba
> ("selftests/timers/posix_timers: Test delivery of signals across
> threads") landed, folks testing older kernels with the latest
> selftests started to see the new test checking for this behavior to
> stall.  Thomas did submit an adjustment to the test here to avoid the
> stall: https://lore.kernel.org/lkml/20230606142031.071059989@linutronix.de/,
> but it didn't seem to land, however that would just result in the test
> failing instead of hanging.

Thanks for reminding me about this series. I completely forgot about it.

> This change does seem to cherry-pick cleanly back to at least
> stable/linux-5.10.y cleanly, so it looks simple to pull this change
> back. But I wanted to make sure there wasn't anything subtle I was
> missing before sending patches.

This test in particular exercises new functionality/behaviour, which
really has no business to be backported into stable just to make the
relevant test usable on older kernels.

Why would testing with latest tests against an older kernel be valid per
se?

Thanks,

        tglx
John Stultz April 2, 2024, 5:23 p.m. UTC | #6
On Tue, Apr 2, 2024 at 7:57 AM Thomas Gleixner <tglx@linutronix.de> wrote:
> On Mon, Apr 01 2024 at 13:17, John Stultz wrote:
> > This change does seem to cherry-pick cleanly back to at least
> > stable/linux-5.10.y cleanly, so it looks simple to pull this change
> > back. But I wanted to make sure there wasn't anything subtle I was
> > missing before sending patches.
>
> This test in particular exercises new functionality/behaviour, which
> really has no business to be backported into stable just to make the
> relevant test usable on older kernels.

That's fair. I didn't have all the context around what motivated the
change and the follow-on test, which is why I'm asking here.

> Why would testing with latest tests against an older kernel be valid per
> se?

So yeah, it definitely can get fuzzy trying to split hairs between
when a change in behavior is a "new feature" or a "fix".

Greg could probably articulate it better, but my understanding is the
main point for running newer tests on older kernels is that newer
tests will have more coverage of what is expected of the kernel. For
features that older kernels don't support, ideally the tests will
check for that functionality like userland applications would, and
skip that portion of the test if it's unsupported. This way, we're
able to find issues (important enough to warrant tests having been
created) that have not yet been patched in the -stable trees.

In this case, there is a behavioral change combined with a compliance
test, which makes it look a bit more like a fix, rather than a feature
(additionally the lack of a way for userland to probe for this new
"feature" makes it seem fix-like).  But the intended result of this is
just spurring this discussion to see if it makes sense to backport or
not.  Disabling/ignoring the test (maybe after Thomas' fix to avoid it
from hanging :) is a fine solution too, but not one I'd want folks to
do until they've synced with maintainers and had full context.

thanks
-john
Oleg Nesterov April 3, 2024, 3:03 p.m. UTC | #7
On 04/03, Thomas Gleixner wrote:
>
> The test if fragile as hell as there is absolutely no guarantee that the
> signal target distribution is as expected. The expectation is based on a
> statistical assumption which does not really hold.

Agreed. I too never liked this test-case.

I forgot everything about this patch and test-case, I can't really read
your patch right now (sorry), so I am sure I missed something, but

>  static void *distribution_thread(void *arg)
>  {
> -	while (__atomic_load_n(&remain, __ATOMIC_RELAXED));
> -	return NULL;
> +	while (__atomic_load_n(&remain, __ATOMIC_RELAXED) && !done) {
> +		if (got_signal)
> +			usleep(10);
> +	}
> +
> +	return (void *)got_signal;
>  }

Why distribution_thread() can't simply exit if got_signal != 0 ?

See https://lore.kernel.org/all/20230128195641.GA14906@redhat.com/

Oleg.
Thomas Gleixner April 3, 2024, 3:43 p.m. UTC | #8
On Wed, Apr 03 2024 at 17:03, Oleg Nesterov wrote:
> On 04/03, Thomas Gleixner wrote:
>> The test if fragile as hell as there is absolutely no guarantee that the
>> signal target distribution is as expected. The expectation is based on a
>> statistical assumption which does not really hold.
>
> Agreed. I too never liked this test-case.
>
> I forgot everything about this patch and test-case, I can't really read
> your patch right now (sorry), so I am sure I missed something, but
>
>>  static void *distribution_thread(void *arg)
>>  {
>> -	while (__atomic_load_n(&remain, __ATOMIC_RELAXED));
>> -	return NULL;
>> +	while (__atomic_load_n(&remain, __ATOMIC_RELAXED) && !done) {
>> +		if (got_signal)
>> +			usleep(10);
>> +	}
>> +
>> +	return (void *)got_signal;
>>  }
>
> Why distribution_thread() can't simply exit if got_signal != 0 ?
>
> See https://lore.kernel.org/all/20230128195641.GA14906@redhat.com/

Indeed. It's too obvious :)
Oleg Nesterov April 4, 2024, 1:43 p.m. UTC | #9
Perhaps I am totally confused, but.

On 04/04, Dmitry Vyukov wrote:
>
> On Wed, 3 Apr 2024 at 17:43, Thomas Gleixner <tglx@linutronix.de> wrote:
> >
> > > Why distribution_thread() can't simply exit if got_signal != 0 ?
> > >
> > > See https://lore.kernel.org/all/20230128195641.GA14906@redhat.com/
> >
> > Indeed. It's too obvious :)
>
> This test models the intended use-case that was the motivation for the change:
> We want to sample execution of a running multi-threaded program, it
> has multiple active threads (that don't exit), since all threads are
> running and consuming CPU,

Yes,

> they all should get a signal eventually.

Well, yes and no.

No, in a sense that the motivation was not to ensure that all threads
get a signal, the motivation was to ensure that cpu_timer_fire() paths
will use the current task as the default target for signal_wake_up/etc.
This is just optimization.

But yes, all should get a signal eventually. And this will happen with
or without the commit bcb7ee79029dca ("posix-timers: Prefer delivery of
signals to the current thread"). Any thread can dequeue a shared signal,
say, on return from interrupt.

Just without that commit this "eventually" means A_LOT_OF_TIME statistically.

> If threads will exit once they get a signal,

just in case, the main thread should not exit ...

> then the test will pass
> even if signal delivery is biased towards a single running thread all
> the time (the previous kernel impl).

See above.

But yes, I agree, if thread exits once it get a signal, then A_LOT_OF_TIME
will be significantly decreased. But again, this is just statistical issue,
I do not see how can we test the commit bcb7ee79029dca reliably.

OTOH. If the threads do not exit after they get signal, then _in theory_
nothing can guarantee that this test-case will ever complete even with
that commit. It is possible that one of the threads will "never" have a
chance to run cpu_timer_fire().

In short, I leave this to you and Thomas. I have no idea how to write a
"good" test for that commit.

Well... perhaps the main thread should just sleep in pause(), and
distribution_handler() should check that gettid() != getpid() ?
Something like this maybe... We need to ensure that the main thread
enters pause before timer_settime().

Oleg.
Thomas Gleixner April 4, 2024, 3:10 p.m. UTC | #10
On Thu, Apr 04 2024 at 15:43, Oleg Nesterov wrote:
> On 04/04, Dmitry Vyukov wrote:
>> they all should get a signal eventually.
>
> Well, yes and no.
>
> No, in a sense that the motivation was not to ensure that all threads
> get a signal, the motivation was to ensure that cpu_timer_fire() paths
> will use the current task as the default target for signal_wake_up/etc.
> This is just optimization.
>
> But yes, all should get a signal eventually. And this will happen with
> or without the commit bcb7ee79029dca ("posix-timers: Prefer delivery of
> signals to the current thread"). Any thread can dequeue a shared signal,
> say, on return from interrupt.
>
> Just without that commit this "eventually" means A_LOT_OF_TIME
> statistically.

bcb7ee79029dca only directs the wakeup to current, but the signal is
still queued in the process wide shared pending list. So the thread
which sees sigpending() first will grab and deliver it to itself.

> But yes, I agree, if thread exits once it get a signal, then A_LOT_OF_TIME
> will be significantly decreased. But again, this is just statistical issue,
> I do not see how can we test the commit bcb7ee79029dca reliably.

We can't.

What we can actually test is the avoidance of waking up the main thread
by doing the following in the main thread:

     start_threads();
     barrier_wait();
     nanosleep(2 seconds);
     done = 1;
     stop_threads();

and in the first thread which is started:

first_thread()
     barrier_wait();
     start_timer();
     loop()
     
On a pre 6.3 kernel nanosleep() will return early because the main
thread is woken up and will eventually win the race to deliver the
signal.

On a 6.3 and later kernel nanosleep() will not return early because the
main thread is not woken up as the wake up is directed at current,
i.e. a worker thread, which is running anyway and will consume the
signal.

> OTOH. If the threads do not exit after they get signal, then _in theory_
> nothing can guarantee that this test-case will ever complete even with
> that commit. It is possible that one of the threads will "never" have a
> chance to run cpu_timer_fire().

Even with the exit I managed to make one out of 100 runs run into the
timeout because the main thread always won the race.

> In short, I leave this to you and Thomas. I have no idea how to write a
> "good" test for that commit.
>
> Well... perhaps the main thread should just sleep in pause(), and
> distribution_handler() should check that gettid() != getpid() ?
> Something like this maybe... We need to ensure that the main thread
> enters pause before timer_settime().

I'm testing a modification which implements something like the above and
the success condition is that the main thread does not return early from
nanosleep() and has no signal accounted. It survived 2000 iterations by
now.

Let me polish it up.

Thanks,

        tglx
Oleg Nesterov April 6, 2024, 3:10 p.m. UTC | #11
Dmitry, Thomas,

To simplify the review I've attached the code with this patch applied below.

Yes, this changes the "semantics" of check_timer_distribution(), perhaps it
should be renamed.

But I do not see a better approach, and in fact I think that

	Test that all running threads _eventually_ receive CLOCK_PROCESS_CPUTIME_ID

is the wrong goal.

Do you agree?

Oleg.
-------------------------------------------------------------------------------

static pthread_t ctd_thread;
static volatile int ctd_count, ctd_failed;

static void ctd_sighandler(int sig)
{
	if (pthread_self() != ctd_thread)
		ctd_failed = 1;
	ctd_count--;
}

static void *ctd_thread_func(void *arg)
{
	struct itimerspec val = {
		.it_value.tv_sec = 0,
		.it_value.tv_nsec = 1000 * 1000,
		.it_interval.tv_sec = 0,
		.it_interval.tv_nsec = 1000 * 1000,
	};
	timer_t id;

	/* 1/10 seconds to ensure the leader sleeps */
	usleep(10000);

	ctd_count = 100;
	if (timer_create(CLOCK_PROCESS_CPUTIME_ID, NULL, &id))
		return "Can't create timer";
	if (timer_settime(id, 0, &val, NULL))
		return "Can't set timer";

	while (ctd_count > 0 && !ctd_failed)
		;

	if (timer_delete(id))
		return "Can't delete timer";

	return NULL;
}

/*
 * Test that only the running thread receives the timer signal.
 */
static int check_timer_distribution(void)
{
	const char *errmsg;

	signal(SIGALRM, ctd_sighandler);

	errmsg = "Can't create thread";
	if (pthread_create(&ctd_thread, NULL, ctd_thread_func, NULL))
		goto err;

	errmsg = "Can't join thread";
	if (pthread_join(ctd_thread, (void **)&errmsg) || errmsg)
		goto err;

	if (ctd_failed)
		ksft_test_result_skip("No signal distribution. Assuming old kernel\n");
	else
		ksft_test_result_pass("check signal distribution\n");

	return 0;
err:
	ksft_print_msg(errmsg);
	return -1;
}
Thomas Gleixner April 6, 2024, 10 p.m. UTC | #12
On Sat, Apr 06 2024 at 17:10, Oleg Nesterov wrote:
> Yes, this changes the "semantics" of check_timer_distribution(), perhaps it
> should be renamed.

Definitely.

> But I do not see a better approach, and in fact I think that
>
> 	Test that all running threads _eventually_ receive CLOCK_PROCESS_CPUTIME_ID
>
> is the wrong goal.
>
> Do you agree?

No argument from my side. All we can test is that the leader is not
woken up.

Thanks,

        tglx
Oleg Nesterov April 8, 2024, 6:49 p.m. UTC | #13
On 04/08, Oleg Nesterov wrote:
>
> On 04/08, Dmitry Vyukov wrote:
> >
> > >
> > >         if (ctd_failed)
> > >                 ksft_test_result_skip("No signal distribution. Assuming old kernel\n");
> >
> > Shouldn't the test fail here? The goal of a test is to fail when
> > things don't work.
>
> I've copied this from the previous patch from Thomas, I am fine
> either way.
>
> > I don't see any other ksft_test_result_fail() calls, and it does not
> > look that the test will hang on incorrect distribution.
>
> Yes, it should never hang.

Forgot to say...

To me this test should simply do

	ksft_test_result(!ctd_failed, "check signal distribution\n");
	return 0;

but I am not familiar with tools/testing/selftests/ and I am not sure
I understand the last email from Thomas.

I agree with whatever you and Thomas decide.

Oleg.
Thomas Gleixner April 8, 2024, 10:17 p.m. UTC | #14
On Mon, Apr 08 2024 at 20:49, Oleg Nesterov wrote:
> To me this test should simply do
>
> 	ksft_test_result(!ctd_failed, "check signal distribution\n");
> 	return 0;

Right.

> but I am not familiar with tools/testing/selftests/ and I am not sure
> I understand the last email from Thomas.

The discussion started about running new tests on older kernels. As this
is a feature and not a bug fix that obviously fails on older kernels.

So something like the uncompiled below should work.

Thanks,

        tglx
---
--- a/tools/testing/selftests/timers/posix_timers.c
+++ b/tools/testing/selftests/timers/posix_timers.c
@@ -184,80 +184,83 @@ static int check_timer_create(int which)
 	return 0;
 }
 
-int remain;
-__thread int got_signal;
+static pthread_t ctd_thread;
+static volatile int ctd_count, ctd_failed;
 
-static void *distribution_thread(void *arg)
+static void ctd_sighandler(int sig)
 {
-	while (__atomic_load_n(&remain, __ATOMIC_RELAXED));
-	return NULL;
-}
-
-static void distribution_handler(int nr)
-{
-	if (!__atomic_exchange_n(&got_signal, 1, __ATOMIC_RELAXED))
-		__atomic_fetch_sub(&remain, 1, __ATOMIC_RELAXED);
+	if (pthread_self() != ctd_thread)
+		ctd_failed = 1;
+	ctd_count--;
 }
 
-/*
- * Test that all running threads _eventually_ receive CLOCK_PROCESS_CPUTIME_ID
- * timer signals. This primarily tests that the kernel does not favour any one.
- */
-static int check_timer_distribution(void)
+static void *ctd_thread_func(void *arg)
 {
-	int err, i;
-	timer_t id;
-	const int nthreads = 10;
-	pthread_t threads[nthreads];
 	struct itimerspec val = {
 		.it_value.tv_sec = 0,
 		.it_value.tv_nsec = 1000 * 1000,
 		.it_interval.tv_sec = 0,
 		.it_interval.tv_nsec = 1000 * 1000,
 	};
+	timer_t id;
 
-	remain = nthreads + 1;  /* worker threads + this thread */
-	signal(SIGALRM, distribution_handler);
-	err = timer_create(CLOCK_PROCESS_CPUTIME_ID, NULL, &id);
-	if (err < 0) {
-		ksft_perror("Can't create timer");
-		return -1;
-	}
-	err = timer_settime(id, 0, &val, NULL);
-	if (err < 0) {
-		ksft_perror("Can't set timer");
-		return -1;
-	}
+	/* 1/10 seconds to ensure the leader sleeps */
+	usleep(10000);
 
-	for (i = 0; i < nthreads; i++) {
-		err = pthread_create(&threads[i], NULL, distribution_thread,
-				     NULL);
-		if (err) {
-			ksft_print_msg("Can't create thread: %s (%d)\n",
-				       strerror(errno), errno);
-			return -1;
-		}
-	}
+	ctd_count = 100;
+	if (timer_create(CLOCK_PROCESS_CPUTIME_ID, NULL, &id))
+		return "Can't create timer";
+	if (timer_settime(id, 0, &val, NULL))
+		return "Can't set timer";
 
-	/* Wait for all threads to receive the signal. */
-	while (__atomic_load_n(&remain, __ATOMIC_RELAXED));
+	while (ctd_count > 0 && !ctd_failed)
+		;
 
-	for (i = 0; i < nthreads; i++) {
-		err = pthread_join(threads[i], NULL);
-		if (err) {
-			ksft_print_msg("Can't join thread: %s (%d)\n",
-				       strerror(errno), errno);
-			return -1;
-		}
-	}
+	if (timer_delete(id))
+		return "Can't delete timer";
 
-	if (timer_delete(id)) {
-		ksft_perror("Can't delete timer");
+	return NULL;
+}
+
+static bool check_kernel_version(unsigned int min_major, unsigned int min_minor)
+{
+	unsigned int major, minor;
+	struct utsname info;
+
+	uname(&info);
+	if (sscanf(info.release, "%u.%u.", &major, &minor) != 2)
+		ksft_exit_fail();
+	return major > min_major || (major == min_major && minor >= min_minor);
+}
+
+/*
+ * Test that only the running thread receives the timer signal.
+ */
+static int check_timer_distribution(void)
+{
+	const char *errmsg;
+
+	if (!check_kernel_version(6, 3)) {
+		ksft_test_result_skip("check signal distribution (old kernel)\n");
 		return 0;
 	}
 
-	ksft_test_result_pass("check_timer_distribution\n");
+	signal(SIGALRM, ctd_sighandler);
+
+	errmsg = "Can't create thread";
+	if (pthread_create(&ctd_thread, NULL, ctd_thread_func, NULL))
+		goto err;
+
+	errmsg = "Can't join thread";
+	if (pthread_join(ctd_thread, (void **)&errmsg) || errmsg)
+		goto err;
+
+	ksft_test_result(!ctd_failed, "check signal distribution\n");
 	return 0;
+
+err:
+	ksft_print_msg(errmsg);
+	return -1;
 }
 
 int main(int argc, char **argv)
Oleg Nesterov April 9, 2024, 11:10 a.m. UTC | #15
On 04/09, Thomas Gleixner wrote:
>
> The discussion started about running new tests on older kernels. As this
> is a feature and not a bug fix that obviously fails on older kernels.

OK, I see... please see below.

> So something like the uncompiled below should work.

Hmm... this patch doesn't apply to Linus's tree...

It seems that this is because in your tree check_timer_distribution() does

	if (timer_delete(id)) {
		ksft_perror("Can't delete timer");
		return 0;
	}

while in Linus's tree it returns -1 if timer_delete() fails. Nevermind.

Thomas, I am almost shy to continue this discussion and waste your time ;)
But ...

> +static bool check_kernel_version(unsigned int min_major, unsigned int min_minor)
> +{
> +	unsigned int major, minor;
> +	struct utsname info;
> +
> +	uname(&info);
> +	if (sscanf(info.release, "%u.%u.", &major, &minor) != 2)
> +		ksft_exit_fail();
> +	return major > min_major || (major == min_major && minor >= min_minor);
> +}

this looks useful regardless. Perhaps it should be moved into
tools/testing/selftests/kselftest.h as ksft_ck_kernel_version() ?

> +static int check_timer_distribution(void)
> +{
> +	const char *errmsg;
> +
> +	if (!check_kernel_version(6, 3)) {
> +		ksft_test_result_skip("check signal distribution (old kernel)\n");
>  		return 0;

...

> +	ksft_test_result(!ctd_failed, "check signal distribution\n");

Perhaps

	if (!ctd_failed)
		ksft_test_result_pass("check signal distribution\n");
	else if (check_kernel_version(6, 3))
		ksft_test_result_fail("check signal distribution\n");
	else
		ksft_test_result_skip("check signal distribution (old kernel)\n");

makes more sense?

This way it can be used on the older kernels with bcb7ee79029d backported.

Oleg.
Thomas Gleixner April 9, 2024, 12:02 p.m. UTC | #16
On Tue, Apr 09 2024 at 13:10, Oleg Nesterov wrote:
> On 04/09, Thomas Gleixner wrote:
> It seems that this is because in your tree check_timer_distribution() does
>
> 	if (timer_delete(id)) {
> 		ksft_perror("Can't delete timer");
> 		return 0;
> 	}
>
> while in Linus's tree it returns -1 if timer_delete()
> fails. Nevermind.

Ooops.

>> +static bool check_kernel_version(unsigned int min_major, unsigned int min_minor)
>> +{
>> +	unsigned int major, minor;
>> +	struct utsname info;
>> +
>> +	uname(&info);
>> +	if (sscanf(info.release, "%u.%u.", &major, &minor) != 2)
>> +		ksft_exit_fail();
>> +	return major > min_major || (major == min_major && minor >= min_minor);
>> +}
>
> this looks useful regardless. Perhaps it should be moved into
> tools/testing/selftests/kselftest.h as ksft_ck_kernel_version() ?

Makes sense.

>> +static int check_timer_distribution(void)
>> +{
>> +	const char *errmsg;
>> +
>> +	if (!check_kernel_version(6, 3)) {
>> +		ksft_test_result_skip("check signal distribution (old kernel)\n");
>>  		return 0;
>
> ..
>
>> +	ksft_test_result(!ctd_failed, "check signal distribution\n");
>
> Perhaps
>
> 	if (!ctd_failed)
> 		ksft_test_result_pass("check signal distribution\n");
> 	else if (check_kernel_version(6, 3))
> 		ksft_test_result_fail("check signal distribution\n");
> 	else
> 		ksft_test_result_skip("check signal distribution (old kernel)\n");
>
> makes more sense?
>
> This way it can be used on the older kernels with bcb7ee79029d backported.

Indeed.
Mark Brown April 11, 2024, 12:41 p.m. UTC | #17
On Sat, Apr 06, 2024 at 05:09:51PM +0200, Oleg Nesterov wrote:
> Thomas says:
> 
> 	The signal distribution test has a tendency to hang for a long
> 	time as the signal delivery is not really evenly distributed. In
> 	fact it might never be distributed across all threads ever in
> 	the way it is written.
> 
> To me even the
> 
> 	This primarily tests that the kernel does not favour any one.
> 
> comment doesn't look right. The kernel does favour a thread which hits
> the timer interrupt when CLOCK_PROCESS_CPUTIME_ID expires.
> 
> The new version simply checks that the group leader sleeping in join()
> never receives SIGALRM, cpu_timer_fire() should always send the signal
> to the thread which burns cpu.
> 
> Without the commit bcb7ee79029d ("posix-timers: Prefer delivery of signals
> to the current thread") the test-case fails immediately, the very 1st tick
> wakes the leader up. Otherwise it quickly succeeds after 100 ticks.

This has landed in -next and is causing warning spam throughout
kselftest when built with clang:

/home/broonie/git/bisect/tools/testing/selftests/kselftest.h:435:6: warning: variable 'major' is used uninitialized whenever '||' condition is true [-Wsometimes-uninitialized]
        if (uname(&info) || sscanf(info.release, "%u.%u.", &major, &minor) != 2)
            ^~~~~~~~~~~~
/home/broonie/git/bisect/tools/testing/selftests/kselftest.h:438:9: note: uninitialized use occurs here
        return major > min_major || (major == min_major && minor >= min_minor);
               ^~~~~
/home/broonie/git/bisect/tools/testing/selftests/kselftest.h:435:6: note: remove the '||' if its condition is always false
        if (uname(&info) || sscanf(info.release, "%u.%u.", &major, &minor) != 2)
            ^~~~~~~~~~~~~~~
/home/broonie/git/bisect/tools/testing/selftests/kselftest.h:432:20: note: initialize the variable 'major' to silence this warning
        unsigned int major, minor;
                          ^
                           = 0
John Stultz April 11, 2024, 3:33 p.m. UTC | #18
On Thu, Apr 11, 2024 at 5:42 AM Mark Brown <broonie@kernel.org> wrote:
> On Sat, Apr 06, 2024 at 05:09:51PM +0200, Oleg Nesterov wrote:
> > Without the commit bcb7ee79029d ("posix-timers: Prefer delivery of signals
> > to the current thread") the test-case fails immediately, the very 1st tick
> > wakes the leader up. Otherwise it quickly succeeds after 100 ticks.
>
> This has landed in -next and is causing warning spam throughout
> kselftest when built with clang:
>
> /home/broonie/git/bisect/tools/testing/selftests/kselftest.h:435:6: warning: variable 'major' is used uninitialized whenever '||' condition is true [-Wsometimes-uninitialized]
>         if (uname(&info) || sscanf(info.release, "%u.%u.", &major, &minor) != 2)
>             ^~~~~~~~~~~~
> /home/broonie/git/bisect/tools/testing/selftests/kselftest.h:438:9: note: uninitialized use occurs here
>         return major > min_major || (major == min_major && minor >= min_minor);
>                ^~~~~
> /home/broonie/git/bisect/tools/testing/selftests/kselftest.h:435:6: note: remove the '||' if its condition is always false
>         if (uname(&info) || sscanf(info.release, "%u.%u.", &major, &minor) != 2)
>             ^~~~~~~~~~~~~~~
> /home/broonie/git/bisect/tools/testing/selftests/kselftest.h:432:20: note: initialize the variable 'major' to silence this warning
>         unsigned int major, minor;
>                           ^
>                            = 0

I hit this one too yesterday and included a fix for it here:
  https://lore.kernel.org/lkml/20240410232637.4135564-2-jstultz@google.com/

thanks
-john
diff mbox series

Patch

diff --git a/kernel/signal.c b/kernel/signal.c
index 8cb28f1df294..605445fa27d4 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -1003,8 +1003,7 @@  static void complete_signal(int sig, struct task_struct *p, enum pid_type type)
 	/*
 	 * Now find a thread we can wake up to take the signal off the queue.
 	 *
-	 * If the main thread wants the signal, it gets first crack.
-	 * Probably the least surprising to the average bear.
+	 * Try the suggested task first (may or may not be the main thread).
 	 */
 	if (wants_signal(sig, p))
 		t = p;
@@ -1970,8 +1969,23 @@  int send_sigqueue(struct sigqueue *q, struct pid *pid, enum pid_type type)
 
 	ret = -1;
 	rcu_read_lock();
+	/*
+	 * This function is used by POSIX timers to deliver a timer signal.
+	 * Where type is PIDTYPE_PID (such as for timers with SIGEV_THREAD_ID
+	 * set), the signal must be delivered to the specific thread (queues
+	 * into t->pending).
+	 *
+	 * Where type is not PIDTYPE_PID, signals must just be delivered to the
+	 * current process. In this case, prefer to deliver to current if it is
+	 * in the same thread group as the target, as it avoids unnecessarily
+	 * waking up a potentially idle task.
+	 */
 	t = pid_task(pid, type);
-	if (!t || !likely(lock_task_sighand(t, &flags)))
+	if (!t)
+		goto ret;
+	if (type != PIDTYPE_PID && same_thread_group(t, current))
+		t = current;
+	if (!likely(lock_task_sighand(t, &flags)))
 		goto ret;
 
 	ret = 1; /* the signal is ignored */
@@ -1993,6 +2007,11 @@  int send_sigqueue(struct sigqueue *q, struct pid *pid, enum pid_type type)
 	q->info.si_overrun = 0;
 
 	signalfd_notify(t, sig);
+	/*
+	 * If the type is not PIDTYPE_PID, we just use shared_pending, which
+	 * won't guarantee that the specified task will receive the signal, but
+	 * is sufficient if t==current in the common case.
+	 */
 	pending = (type != PIDTYPE_PID) ? &t->signal->shared_pending : &t->pending;
 	list_add_tail(&q->list, &pending->list);
 	sigaddset(&pending->signal, sig);