linux-toradex.git/kernel/sched, branch v4.4.106 Linux kernel for Apalis and Colibri modules sched/rt: Simplify the IPI based RT balancing logic 2017-11-30T08:37:25+00:00 Steven Rostedt (Red Hat) rostedt@goodmis.org 2017-10-06T18:05:04+00:00 cb1831a83e54cd3269a2420fce81c4fd8ae6f667 commit 4bdced5c9a2922521e325896a7bbbf0132c94e56 upstream. When a CPU lowers its priority (schedules out a high priority task for a lower priority one), a check is made to see if any other CPU has overloaded RT tasks (more than one). It checks the rto_mask to determine this and if so it will request to pull one of those tasks to itself if the non running RT task is of higher priority than the new priority of the next task to run on the current CPU. When we deal with large number of CPUs, the original pull logic suffered from large lock contention on a single CPU run queue, which caused a huge latency across all CPUs. This was caused by only having one CPU having overloaded RT tasks and a bunch of other CPUs lowering their priority. To solve this issue, commit: b6366f048e0c ("sched/rt: Use IPI to trigger RT task push migration instead of pulling") changed the way to request a pull. Instead of grabbing the lock of the overloaded CPU's runqueue, it simply sent an IPI to that CPU to do the work. Although the IPI logic worked very well in removing the large latency build up, it still could suffer from a large number of IPIs being sent to a single CPU. On a 80 CPU box, I measured over 200us of processing IPIs. Worse yet, when I tested this on a 120 CPU box, with a stress test that had lots of RT tasks scheduling on all CPUs, it actually triggered the hard lockup detector! One CPU had so many IPIs sent to it, and due to the restart mechanism that is triggered when the source run queue has a priority status change, the CPU spent minutes! processing the IPIs. Thinking about this further, I realized there's no reason for each run queue to send its own IPI. As all CPUs with overloaded tasks must be scanned regardless if there's one or many CPUs lowering their priority, because there's no current way to find the CPU with the highest priority task that can schedule to one of these CPUs, there really only needs to be one IPI being sent around at a time. This greatly simplifies the code! The new approach is to have each root domain have its own irq work, as the rto_mask is per root domain. The root domain has the following fields attached to it: rto_push_work - the irq work to process each CPU set in rto_mask rto_lock - the lock to protect some of the other rto fields rto_loop_start - an atomic that keeps contention down on rto_lock the first CPU scheduling in a lower priority task is the one to kick off the process. rto_loop_next - an atomic that gets incremented for each CPU that schedules in a lower priority task. rto_loop - a variable protected by rto_lock that is used to compare against rto_loop_next rto_cpu - The cpu to send the next IPI to, also protected by the rto_lock. When a CPU schedules in a lower priority task and wants to make sure overloaded CPUs know about it. It increments the rto_loop_next. Then it atomically sets rto_loop_start with a cmpxchg. If the old value is not "0", then it is done, as another CPU is kicking off the IPI loop. If the old value is "0", then it will take the rto_lock to synchronize with a possible IPI being sent around to the overloaded CPUs. If rto_cpu is greater than or equal to nr_cpu_ids, then there's either no IPI being sent around, or one is about to finish. Then rto_cpu is set to the first CPU in rto_mask and an IPI is sent to that CPU. If there's no CPUs set in rto_mask, then there's nothing to be done. When the CPU receives the IPI, it will first try to push any RT tasks that is queued on the CPU but can't run because a higher priority RT task is currently running on that CPU. Then it takes the rto_lock and looks for the next CPU in the rto_mask. If it finds one, it simply sends an IPI to that CPU and the process continues. If there's no more CPUs in the rto_mask, then rto_loop is compared with rto_loop_next. If they match, everything is done and the process is over. If they do not match, then a CPU scheduled in a lower priority task as the IPI was being passed around, and the process needs to start again. The first CPU in rto_mask is sent the IPI. This change removes this duplication of work in the IPI logic, and greatly lowers the latency caused by the IPIs. This removed the lockup happening on the 120 CPU machine. It also simplifies the code tremendously. What else could anyone ask for? Thanks to Peter Zijlstra for simplifying the rto_loop_start atomic logic and supplying me with the rto_start_trylock() and rto_start_unlock() helper functions. Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Clark Williams <williams@redhat.com> Cc: Daniel Bristot de Oliveira <bristot@redhat.com> Cc: John Kacur <jkacur@redhat.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Scott Wood <swood@redhat.com> Cc: Thomas Gleixner <tglx@linutronix.de> Link: http://lkml.kernel.org/r/20170424114732.1aac6dc4@gandalf.local.home Signed-off-by: Ingo Molnar <mingo@kernel.org> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> 
commit 4bdced5c9a2922521e325896a7bbbf0132c94e56 upstream.

When a CPU lowers its priority (schedules out a high priority task for a
lower priority one), a check is made to see if any other CPU has overloaded
RT tasks (more than one). It checks the rto_mask to determine this and if so
it will request to pull one of those tasks to itself if the non running RT
task is of higher priority than the new priority of the next task to run on
the current CPU.

When we deal with large number of CPUs, the original pull logic suffered
from large lock contention on a single CPU run queue, which caused a huge
latency across all CPUs. This was caused by only having one CPU having
overloaded RT tasks and a bunch of other CPUs lowering their priority. To
solve this issue, commit:

  b6366f048e0c ("sched/rt: Use IPI to trigger RT task push migration instead of pulling")

changed the way to request a pull. Instead of grabbing the lock of the
overloaded CPU's runqueue, it simply sent an IPI to that CPU to do the work.

Although the IPI logic worked very well in removing the large latency build
up, it still could suffer from a large number of IPIs being sent to a single
CPU. On a 80 CPU box, I measured over 200us of processing IPIs. Worse yet,
when I tested this on a 120 CPU box, with a stress test that had lots of
RT tasks scheduling on all CPUs, it actually triggered the hard lockup
detector! One CPU had so many IPIs sent to it, and due to the restart
mechanism that is triggered when the source run queue has a priority status
change, the CPU spent minutes! processing the IPIs.

Thinking about this further, I realized there's no reason for each run queue
to send its own IPI. As all CPUs with overloaded tasks must be scanned
regardless if there's one or many CPUs lowering their priority, because
there's no current way to find the CPU with the highest priority task that
can schedule to one of these CPUs, there really only needs to be one IPI
being sent around at a time.

This greatly simplifies the code!

The new approach is to have each root domain have its own irq work, as the
rto_mask is per root domain. The root domain has the following fields
attached to it:

  rto_push_work	 - the irq work to process each CPU set in rto_mask
  rto_lock	 - the lock to protect some of the other rto fields
  rto_loop_start - an atomic that keeps contention down on rto_lock
		    the first CPU scheduling in a lower priority task
		    is the one to kick off the process.
  rto_loop_next	 - an atomic that gets incremented for each CPU that
		    schedules in a lower priority task.
  rto_loop	 - a variable protected by rto_lock that is used to
		    compare against rto_loop_next
  rto_cpu	 - The cpu to send the next IPI to, also protected by
		    the rto_lock.

When a CPU schedules in a lower priority task and wants to make sure
overloaded CPUs know about it. It increments the rto_loop_next. Then it
atomically sets rto_loop_start with a cmpxchg. If the old value is not "0",
then it is done, as another CPU is kicking off the IPI loop. If the old
value is "0", then it will take the rto_lock to synchronize with a possible
IPI being sent around to the overloaded CPUs.

If rto_cpu is greater than or equal to nr_cpu_ids, then there's either no
IPI being sent around, or one is about to finish. Then rto_cpu is set to the
first CPU in rto_mask and an IPI is sent to that CPU. If there's no CPUs set
in rto_mask, then there's nothing to be done.

When the CPU receives the IPI, it will first try to push any RT tasks that is
queued on the CPU but can't run because a higher priority RT task is
currently running on that CPU.

Then it takes the rto_lock and looks for the next CPU in the rto_mask. If it
finds one, it simply sends an IPI to that CPU and the process continues.

If there's no more CPUs in the rto_mask, then rto_loop is compared with
rto_loop_next. If they match, everything is done and the process is over. If
they do not match, then a CPU scheduled in a lower priority task as the IPI
was being passed around, and the process needs to start again. The first CPU
in rto_mask is sent the IPI.

This change removes this duplication of work in the IPI logic, and greatly
lowers the latency caused by the IPIs. This removed the lockup happening on
the 120 CPU machine. It also simplifies the code tremendously. What else
could anyone ask for?

Thanks to Peter Zijlstra for simplifying the rto_loop_start atomic logic and
supplying me with the rto_start_trylock() and rto_start_unlock() helper
functions.

Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Clark Williams <williams@redhat.com>
Cc: Daniel Bristot de Oliveira <bristot@redhat.com>
Cc: John Kacur <jkacur@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Scott Wood <swood@redhat.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/20170424114732.1aac6dc4@gandalf.local.home
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
sched: Make resched_cpu() unconditional 2017-11-30T08:37:19+00:00 Paul E. McKenney paulmck@linux.vnet.ibm.com 2017-09-18T15:54:40+00:00 8ff3471878f3f8161bff92f73b3ecb35d6c397dc commit 7c2102e56a3f7d85b5d8f33efbd7aecc1f36fdd8 upstream. The current implementation of synchronize_sched_expedited() incorrectly assumes that resched_cpu() is unconditional, which it is not. This means that synchronize_sched_expedited() can hang when resched_cpu()'s trylock fails as follows (analysis by Neeraj Upadhyay): o CPU1 is waiting for expedited wait to complete: sync_rcu_exp_select_cpus rdp->exp_dynticks_snap & 0x1 // returns 1 for CPU5 IPI sent to CPU5 synchronize_sched_expedited_wait ret = swait_event_timeout(rsp->expedited_wq, sync_rcu_preempt_exp_done(rnp_root), jiffies_stall); expmask = 0x20, CPU 5 in idle path (in cpuidle_enter()) o CPU5 handles IPI and fails to acquire rq lock. Handles IPI sync_sched_exp_handler resched_cpu returns while failing to try lock acquire rq->lock need_resched is not set o CPU5 calls rcu_idle_enter() and as need_resched is not set, goes to idle (schedule() is not called). o CPU 1 reports RCU stall. Given that resched_cpu() is now used only by RCU, this commit fixes the assumption by making resched_cpu() unconditional. Reported-by: Neeraj Upadhyay <neeraju@codeaurora.org> Suggested-by: Neeraj Upadhyay <neeraju@codeaurora.org> Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Acked-by: Steven Rostedt (VMware) <rostedt@goodmis.org> Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> 
commit 7c2102e56a3f7d85b5d8f33efbd7aecc1f36fdd8 upstream.

The current implementation of synchronize_sched_expedited() incorrectly
assumes that resched_cpu() is unconditional, which it is not.  This means
that synchronize_sched_expedited() can hang when resched_cpu()'s trylock
fails as follows (analysis by Neeraj Upadhyay):

o	CPU1 is waiting for expedited wait to complete:

	sync_rcu_exp_select_cpus
	     rdp->exp_dynticks_snap & 0x1   // returns 1 for CPU5
	     IPI sent to CPU5

	synchronize_sched_expedited_wait
		 ret = swait_event_timeout(rsp->expedited_wq,
					   sync_rcu_preempt_exp_done(rnp_root),
					   jiffies_stall);

	expmask = 0x20, CPU 5 in idle path (in cpuidle_enter())

o	CPU5 handles IPI and fails to acquire rq lock.

	Handles IPI
	     sync_sched_exp_handler
		 resched_cpu
		     returns while failing to try lock acquire rq->lock
		 need_resched is not set

o	CPU5 calls  rcu_idle_enter() and as need_resched is not set, goes to
	idle (schedule() is not called).

o	CPU 1 reports RCU stall.

Given that resched_cpu() is now used only by RCU, this commit fixes the
assumption by making resched_cpu() unconditional.

Reported-by: Neeraj Upadhyay <neeraju@codeaurora.org>
Suggested-by: Neeraj Upadhyay <neeraju@codeaurora.org>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Acked-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
sched/autogroup: Fix autogroup_move_group() to never skip sched_move_task() 2017-10-27T08:23:17+00:00 Oleg Nesterov oleg@redhat.com 2016-11-14T18:46:09+00:00 0f85c0954be46bbd36960191daa447ad86b98f0b commit 18f649ef344127ef6de23a5a4272dbe2fdb73dde upstream. The PF_EXITING check in task_wants_autogroup() is no longer needed. Remove it, but see the next patch. However the comment is correct in that autogroup_move_group() must always change task_group() for every thread so the sysctl_ check is very wrong; we can race with cgroups and even sys_setsid() is not safe because a task running with task_group() == ag->tg must participate in refcounting: int main(void) { int sctl = open("/proc/sys/kernel/sched_autogroup_enabled", O_WRONLY); assert(sctl > 0); if (fork()) { wait(NULL); // destroy the child's ag/tg pause(); } assert(pwrite(sctl, "1\n", 2, 0) == 2); assert(setsid() > 0); if (fork()) pause(); kill(getppid(), SIGKILL); sleep(1); // The child has gone, the grandchild runs with kref == 1 assert(pwrite(sctl, "0\n", 2, 0) == 2); assert(setsid() > 0); // runs with the freed ag/tg for (;;) sleep(1); return 0; } crashes the kernel. It doesn't really need sleep(1), it doesn't matter if autogroup_move_group() actually frees the task_group or this happens later. Reported-by: Vern Lovejoy <vlovejoy@redhat.com> Signed-off-by: Oleg Nesterov <oleg@redhat.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: hartsjc@redhat.com Cc: vbendel@redhat.com Link: http://lkml.kernel.org/r/20161114184609.GA15965@redhat.com Signed-off-by: Ingo Molnar <mingo@kernel.org> Signed-off-by: Sumit Semwal <sumit.semwal@linaro.org> [sumits: submit to 4.4 LTS, post testing on Hikey] Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> 
commit 18f649ef344127ef6de23a5a4272dbe2fdb73dde upstream.

The PF_EXITING check in task_wants_autogroup() is no longer needed. Remove
it, but see the next patch.

However the comment is correct in that autogroup_move_group() must always
change task_group() for every thread so the sysctl_ check is very wrong;
we can race with cgroups and even sys_setsid() is not safe because a task
running with task_group() == ag->tg must participate in refcounting:

	int main(void)
	{
		int sctl = open("/proc/sys/kernel/sched_autogroup_enabled", O_WRONLY);

		assert(sctl > 0);
		if (fork()) {
			wait(NULL); // destroy the child's ag/tg
			pause();
		}

		assert(pwrite(sctl, "1\n", 2, 0) == 2);
		assert(setsid() > 0);
		if (fork())
			pause();

		kill(getppid(), SIGKILL);
		sleep(1);

		// The child has gone, the grandchild runs with kref == 1
		assert(pwrite(sctl, "0\n", 2, 0) == 2);
		assert(setsid() > 0);

		// runs with the freed ag/tg
		for (;;)
			sleep(1);

		return 0;
	}

crashes the kernel. It doesn't really need sleep(1), it doesn't matter if
autogroup_move_group() actually frees the task_group or this happens later.

Reported-by: Vern Lovejoy <vlovejoy@redhat.com>
Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: hartsjc@redhat.com
Cc: vbendel@redhat.com
Link: http://lkml.kernel.org/r/20161114184609.GA15965@redhat.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Sumit Semwal <sumit.semwal@linaro.org>
 [sumits: submit to 4.4 LTS, post testing on Hikey]
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
sched/cpuset/pm: Fix cpuset vs. suspend-resume bugs 2017-10-12T09:27:35+00:00 Peter Zijlstra peterz@infradead.org 2017-09-07T09:13:38+00:00 90fd6738731b6d105fc8f04832ae17a9ac82c05c commit 50e76632339d4655859523a39249dd95ee5e93e7 upstream. Cpusets vs. suspend-resume is _completely_ broken. And it got noticed because it now resulted in non-cpuset usage breaking too. On suspend cpuset_cpu_inactive() doesn't call into cpuset_update_active_cpus() because it doesn't want to move tasks about, there is no need, all tasks are frozen and won't run again until after we've resumed everything. But this means that when we finally do call into cpuset_update_active_cpus() after resuming the last frozen cpu in cpuset_cpu_active(), the top_cpuset will not have any difference with the cpu_active_mask and this it will not in fact do _anything_. So the cpuset configuration will not be restored. This was largely hidden because we would unconditionally create identity domains and mobile users would not in fact use cpusets much. And servers what do use cpusets tend to not suspend-resume much. An addition problem is that we'd not in fact wait for the cpuset work to finish before resuming the tasks, allowing spurious migrations outside of the specified domains. Fix the rebuild by introducing cpuset_force_rebuild() and fix the ordering with cpuset_wait_for_hotplug(). Reported-by: Andy Lutomirski <luto@kernel.org> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: <stable@vger.kernel.org> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Rafael J. Wysocki <rjw@rjwysocki.net> Cc: Tejun Heo <tj@kernel.org> Cc: Thomas Gleixner <tglx@linutronix.de> Fixes: deb7aa308ea2 ("cpuset: reorganize CPU / memory hotplug handling") Link: http://lkml.kernel.org/r/20170907091338.orwxrqkbfkki3c24@hirez.programming.kicks-ass.net Signed-off-by: Ingo Molnar <mingo@kernel.org> Signed-off-by: Mike Galbraith <efault@gmx.de> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> 
commit 50e76632339d4655859523a39249dd95ee5e93e7 upstream.

Cpusets vs. suspend-resume is _completely_ broken. And it got noticed
because it now resulted in non-cpuset usage breaking too.

On suspend cpuset_cpu_inactive() doesn't call into
cpuset_update_active_cpus() because it doesn't want to move tasks about,
there is no need, all tasks are frozen and won't run again until after
we've resumed everything.

But this means that when we finally do call into
cpuset_update_active_cpus() after resuming the last frozen cpu in
cpuset_cpu_active(), the top_cpuset will not have any difference with
the cpu_active_mask and this it will not in fact do _anything_.

So the cpuset configuration will not be restored. This was largely
hidden because we would unconditionally create identity domains and
mobile users would not in fact use cpusets much. And servers what do use
cpusets tend to not suspend-resume much.

An addition problem is that we'd not in fact wait for the cpuset work to
finish before resuming the tasks, allowing spurious migrations outside
of the specified domains.

Fix the rebuild by introducing cpuset_force_rebuild() and fix the
ordering with cpuset_wait_for_hotplug().

Reported-by: Andy Lutomirski <luto@kernel.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: <stable@vger.kernel.org>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rafael J. Wysocki <rjw@rjwysocki.net>
Cc: Tejun Heo <tj@kernel.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Fixes: deb7aa308ea2 ("cpuset: reorganize CPU / memory hotplug handling")
Link: http://lkml.kernel.org/r/20170907091338.orwxrqkbfkki3c24@hirez.programming.kicks-ass.net
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Mike Galbraith <efault@gmx.de>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
sched/cputime: Fix prev steal time accouting during CPU hotplug 2017-08-07T02:19:43+00:00 Wanpeng Li wanpeng.li@hotmail.com 2016-06-13T10:32:45+00:00 62208707b466cc3c6ce951a7c4b7b4bb9b9192f6 commit 3d89e5478bf550a50c99e93adf659369798263b0 upstream. Commit: e9532e69b8d1 ("sched/cputime: Fix steal time accounting vs. CPU hotplug") ... set rq->prev_* to 0 after a CPU hotplug comes back, in order to fix the case where (after CPU hotplug) steal time is smaller than rq->prev_steal_time. However, this should never happen. Steal time was only smaller because of the KVM-specific bug fixed by the previous patch. Worse, the previous patch triggers a bug on CPU hot-unplug/plug operation: because rq->prev_steal_time is cleared, all of the CPU's past steal time will be accounted again on hot-plug. Since the root cause has been fixed, we can just revert commit e9532e69b8d1. Signed-off-by: Wanpeng Li <wanpeng.li@hotmail.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Acked-by: Paolo Bonzini <pbonzini@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Radim Krčmář <rkrcmar@redhat.com> Cc: Rik van Riel <riel@redhat.com> Cc: Thomas Gleixner <tglx@linutronix.de> Fixes: 'commit e9532e69b8d1 ("sched/cputime: Fix steal time accounting vs. CPU hotplug")' Link: http://lkml.kernel.org/r/1465813966-3116-3-git-send-email-wanpeng.li@hotmail.com Signed-off-by: Ingo Molnar <mingo@kernel.org> Signed-off-by: Andres Oportus <andresoportus@google.com> Acked-by: Paolo Bonzini <pbonzini@redhat.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> 
commit 3d89e5478bf550a50c99e93adf659369798263b0 upstream.

Commit:

  e9532e69b8d1 ("sched/cputime: Fix steal time accounting vs. CPU hotplug")

... set rq->prev_* to 0 after a CPU hotplug comes back, in order to
fix the case where (after CPU hotplug) steal time is smaller than
rq->prev_steal_time.

However, this should never happen. Steal time was only smaller because of the
KVM-specific bug fixed by the previous patch.  Worse, the previous patch
triggers a bug on CPU hot-unplug/plug operation: because
rq->prev_steal_time is cleared, all of the CPU's past steal time will be
accounted again on hot-plug.

Since the root cause has been fixed, we can just revert commit e9532e69b8d1.

Signed-off-by: Wanpeng Li <wanpeng.li@hotmail.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Paolo Bonzini <pbonzini@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Radim Krčmář <rkrcmar@redhat.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Fixes: 'commit e9532e69b8d1 ("sched/cputime: Fix steal time accounting vs. CPU hotplug")'
Link: http://lkml.kernel.org/r/1465813966-3116-3-git-send-email-wanpeng.li@hotmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Andres Oportus <andresoportus@google.com>
Acked-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
sched/cgroup: Move sched_online_group() back into css_online() to fix crash 2017-08-07T02:19:42+00:00 Konstantin Khlebnikov khlebnikov@yandex-team.ru 2017-02-08T11:27:27+00:00 0e0967e26241147e43723be660f64a291c2f5f27 commit 96b777452d8881480fd5be50112f791c17db4b6b upstream. Commit: 2f5177f0fd7e ("sched/cgroup: Fix/cleanup cgroup teardown/init") .. moved sched_online_group() from css_online() to css_alloc(). It exposes half-baked task group into global lists before initializing generic cgroup stuff. LTP testcase (third in cgroup_regression_test) written for testing similar race in kernels 2.6.26-2.6.28 easily triggers this oops: BUG: unable to handle kernel NULL pointer dereference at 0000000000000008 IP: kernfs_path_from_node_locked+0x260/0x320 CPU: 1 PID: 30346 Comm: cat Not tainted 4.10.0-rc5-test #4 Call Trace: ? kernfs_path_from_node+0x4f/0x60 kernfs_path_from_node+0x3e/0x60 print_rt_rq+0x44/0x2b0 print_rt_stats+0x7a/0xd0 print_cpu+0x2fc/0xe80 ? __might_sleep+0x4a/0x80 sched_debug_show+0x17/0x30 seq_read+0xf2/0x3b0 proc_reg_read+0x42/0x70 __vfs_read+0x28/0x130 ? security_file_permission+0x9b/0xc0 ? rw_verify_area+0x4e/0xb0 vfs_read+0xa5/0x170 SyS_read+0x46/0xa0 entry_SYSCALL_64_fastpath+0x1e/0xad Here the task group is already linked into the global RCU-protected 'task_groups' list, but the css->cgroup pointer is still NULL. This patch reverts this chunk and moves online back to css_online(). Signed-off-by: Konstantin Khlebnikov <khlebnikov@yandex-team.ru> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Tejun Heo <tj@kernel.org> Cc: Thomas Gleixner <tglx@linutronix.de> Fixes: 2f5177f0fd7e ("sched/cgroup: Fix/cleanup cgroup teardown/init") Link: http://lkml.kernel.org/r/148655324740.424917.5302984537258726349.stgit@buzz Signed-off-by: Ingo Molnar <mingo@kernel.org> Signed-off-by: Matt Fleming <matt@codeblueprint.co.uk> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> 
commit 96b777452d8881480fd5be50112f791c17db4b6b upstream.

Commit:

  2f5177f0fd7e ("sched/cgroup: Fix/cleanup cgroup teardown/init")

.. moved sched_online_group() from css_online() to css_alloc().
It exposes half-baked task group into global lists before initializing
generic cgroup stuff.

LTP testcase (third in cgroup_regression_test) written for testing
similar race in kernels 2.6.26-2.6.28 easily triggers this oops:

  BUG: unable to handle kernel NULL pointer dereference at 0000000000000008
  IP: kernfs_path_from_node_locked+0x260/0x320
  CPU: 1 PID: 30346 Comm: cat Not tainted 4.10.0-rc5-test #4
  Call Trace:
  ? kernfs_path_from_node+0x4f/0x60
  kernfs_path_from_node+0x3e/0x60
  print_rt_rq+0x44/0x2b0
  print_rt_stats+0x7a/0xd0
  print_cpu+0x2fc/0xe80
  ? __might_sleep+0x4a/0x80
  sched_debug_show+0x17/0x30
  seq_read+0xf2/0x3b0
  proc_reg_read+0x42/0x70
  __vfs_read+0x28/0x130
  ? security_file_permission+0x9b/0xc0
  ? rw_verify_area+0x4e/0xb0
  vfs_read+0xa5/0x170
  SyS_read+0x46/0xa0
  entry_SYSCALL_64_fastpath+0x1e/0xad

Here the task group is already linked into the global RCU-protected 'task_groups'
list, but the css->cgroup pointer is still NULL.

This patch reverts this chunk and moves online back to css_online().

Signed-off-by: Konstantin Khlebnikov <khlebnikov@yandex-team.ru>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Tejun Heo <tj@kernel.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Fixes: 2f5177f0fd7e ("sched/cgroup: Fix/cleanup cgroup teardown/init")
Link: http://lkml.kernel.org/r/148655324740.424917.5302984537258726349.stgit@buzz
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Matt Fleming <matt@codeblueprint.co.uk>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
sched/topology: Optimize build_group_mask() 2017-07-21T05:44:59+00:00 Lauro Ramos Venancio lvenanci@redhat.com 2017-04-20T19:51:40+00:00 988067ec9606e3d7bd7e1125118e77e06c2eda4a commit f32d782e31bf079f600dcec126ed117b0577e85c upstream. The group mask is always used in intersection with the group CPUs. So, when building the group mask, we don't have to care about CPUs that are not part of the group. Signed-off-by: Lauro Ramos Venancio <lvenanci@redhat.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: lwang@redhat.com Cc: riel@redhat.com Link: http://lkml.kernel.org/r/1492717903-5195-2-git-send-email-lvenanci@redhat.com Signed-off-by: Ingo Molnar <mingo@kernel.org> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> 
commit f32d782e31bf079f600dcec126ed117b0577e85c upstream.

The group mask is always used in intersection with the group CPUs. So,
when building the group mask, we don't have to care about CPUs that are
not part of the group.

Signed-off-by: Lauro Ramos Venancio <lvenanci@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: lwang@redhat.com
Cc: riel@redhat.com
Link: http://lkml.kernel.org/r/1492717903-5195-2-git-send-email-lvenanci@redhat.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
sched/topology: Fix overlapping sched_group_mask 2017-07-21T05:44:59+00:00 Peter Zijlstra peterz@infradead.org 2017-04-25T12:00:49+00:00 5c34f49776b8d556bb83d31945cfdb5340792bf2 commit 73bb059f9b8a00c5e1bf2f7ca83138c05d05e600 upstream. The point of sched_group_mask is to select those CPUs from sched_group_cpus that can actually arrive at this balance domain. The current code gets it wrong, as can be readily demonstrated with a topology like: node 0 1 2 3 0: 10 20 30 20 1: 20 10 20 30 2: 30 20 10 20 3: 20 30 20 10 Where (for example) domain 1 on CPU1 ends up with a mask that includes CPU0: [] CPU1 attaching sched-domain: [] domain 0: span 0-2 level NUMA [] groups: 1 (mask: 1), 2, 0 [] domain 1: span 0-3 level NUMA [] groups: 0-2 (mask: 0-2) (cpu_capacity: 3072), 0,2-3 (cpu_capacity: 3072) This causes sched_balance_cpu() to compute the wrong CPU and consequently should_we_balance() will terminate early resulting in missed load-balance opportunities. The fixed topology looks like: [] CPU1 attaching sched-domain: [] domain 0: span 0-2 level NUMA [] groups: 1 (mask: 1), 2, 0 [] domain 1: span 0-3 level NUMA [] groups: 0-2 (mask: 1) (cpu_capacity: 3072), 0,2-3 (cpu_capacity: 3072) (note: this relies on OVERLAP domains to always have children, this is true because the regular topology domains are still here -- this is before degenerate trimming) Debugged-by: Lauro Ramos Venancio <lvenanci@redhat.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: linux-kernel@vger.kernel.org Fixes: e3589f6c81e4 ("sched: Allow for overlapping sched_domain spans") Signed-off-by: Ingo Molnar <mingo@kernel.org> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> 
commit 73bb059f9b8a00c5e1bf2f7ca83138c05d05e600 upstream.

The point of sched_group_mask is to select those CPUs from
sched_group_cpus that can actually arrive at this balance domain.

The current code gets it wrong, as can be readily demonstrated with a
topology like:

  node   0   1   2   3
    0:  10  20  30  20
    1:  20  10  20  30
    2:  30  20  10  20
    3:  20  30  20  10

Where (for example) domain 1 on CPU1 ends up with a mask that includes
CPU0:

  [] CPU1 attaching sched-domain:
  []  domain 0: span 0-2 level NUMA
  []   groups: 1 (mask: 1), 2, 0
  []   domain 1: span 0-3 level NUMA
  []    groups: 0-2 (mask: 0-2) (cpu_capacity: 3072), 0,2-3 (cpu_capacity: 3072)

This causes sched_balance_cpu() to compute the wrong CPU and
consequently should_we_balance() will terminate early resulting in
missed load-balance opportunities.

The fixed topology looks like:

  [] CPU1 attaching sched-domain:
  []  domain 0: span 0-2 level NUMA
  []   groups: 1 (mask: 1), 2, 0
  []   domain 1: span 0-3 level NUMA
  []    groups: 0-2 (mask: 1) (cpu_capacity: 3072), 0,2-3 (cpu_capacity: 3072)

(note: this relies on OVERLAP domains to always have children, this is
 true because the regular topology domains are still here -- this is
 before degenerate trimming)

Debugged-by: Lauro Ramos Venancio <lvenanci@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Fixes: e3589f6c81e4 ("sched: Allow for overlapping sched_domain spans")
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
sched/loadavg: Avoid loadavg spikes caused by delayed NO_HZ accounting 2017-07-05T12:37:21+00:00 Matt Fleming matt@codeblueprint.co.uk 2017-02-17T12:07:30+00:00 6ca11db55f62ea484c4ecf28b1fa9da14536f31e commit 6e5f32f7a43f45ee55c401c0b9585eb01f9629a8 upstream. If we crossed a sample window while in NO_HZ we will add LOAD_FREQ to the pending sample window time on exit, setting the next update not one window into the future, but two. This situation on exiting NO_HZ is described by: this_rq->calc_load_update < jiffies < calc_load_update In this scenario, what we should be doing is: this_rq->calc_load_update = calc_load_update [ next window ] But what we actually do is: this_rq->calc_load_update = calc_load_update + LOAD_FREQ [ next+1 window ] This has the effect of delaying load average updates for potentially up to ~9seconds. This can result in huge spikes in the load average values due to per-cpu uninterruptible task counts being out of sync when accumulated across all CPUs. It's safe to update the per-cpu active count if we wake between sample windows because any load that we left in 'calc_load_idle' will have been zero'd when the idle load was folded in calc_global_load(). This issue is easy to reproduce before, commit 9d89c257dfb9 ("sched/fair: Rewrite runnable load and utilization average tracking") just by forking short-lived process pipelines built from ps(1) and grep(1) in a loop. I'm unable to reproduce the spikes after that commit, but the bug still seems to be present from code review. Signed-off-by: Matt Fleming <matt@codeblueprint.co.uk> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Mike Galbraith <umgwanakikbuti@gmail.com> Cc: Morten Rasmussen <morten.rasmussen@arm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Vincent Guittot <vincent.guittot@linaro.org> Fixes: commit 5167e8d ("sched/nohz: Rewrite and fix load-avg computation -- again") Link: http://lkml.kernel.org/r/20170217120731.11868-2-matt@codeblueprint.co.uk Signed-off-by: Ingo Molnar <mingo@kernel.org> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> 
commit 6e5f32f7a43f45ee55c401c0b9585eb01f9629a8 upstream.

If we crossed a sample window while in NO_HZ we will add LOAD_FREQ to
the pending sample window time on exit, setting the next update not
one window into the future, but two.

This situation on exiting NO_HZ is described by:

  this_rq->calc_load_update < jiffies < calc_load_update

In this scenario, what we should be doing is:

  this_rq->calc_load_update = calc_load_update		     [ next window ]

But what we actually do is:

  this_rq->calc_load_update = calc_load_update + LOAD_FREQ   [ next+1 window ]

This has the effect of delaying load average updates for potentially
up to ~9seconds.

This can result in huge spikes in the load average values due to
per-cpu uninterruptible task counts being out of sync when accumulated
across all CPUs.

It's safe to update the per-cpu active count if we wake between sample
windows because any load that we left in 'calc_load_idle' will have
been zero'd when the idle load was folded in calc_global_load().

This issue is easy to reproduce before,

  commit 9d89c257dfb9 ("sched/fair: Rewrite runnable load and utilization average tracking")

just by forking short-lived process pipelines built from ps(1) and
grep(1) in a loop. I'm unable to reproduce the spikes after that
commit, but the bug still seems to be present from code review.

Signed-off-by: Matt Fleming <matt@codeblueprint.co.uk>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Mike Galbraith <umgwanakikbuti@gmail.com>
Cc: Morten Rasmussen <morten.rasmussen@arm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vincent Guittot <vincent.guittot@linaro.org>
Fixes: commit 5167e8d ("sched/nohz: Rewrite and fix load-avg computation -- again")
Link: http://lkml.kernel.org/r/20170217120731.11868-2-matt@codeblueprint.co.uk
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
sched/fair: Initialize throttle_count for new task-groups lazily 2017-05-25T12:30:12+00:00 Konstantin Khlebnikov khlebnikov@yandex-team.ru 2016-06-16T12:57:01+00:00 ada79b5ecda79ec7b53053d9955a5ee04c8dd633 commit 094f469172e00d6ab0a3130b0e01c83b3cf3a98d upstream. Cgroup created inside throttled group must inherit current throttle_count. Broken throttle_count allows to nominate throttled entries as a next buddy, later this leads to null pointer dereference in pick_next_task_fair(). This patch initialize cfs_rq->throttle_count at first enqueue: laziness allows to skip locking all rq at group creation. Lazy approach also allows to skip full sub-tree scan at throttling hierarchy (not in this patch). Signed-off-by: Konstantin Khlebnikov <khlebnikov@yandex-team.ru> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: bsegall@google.com Link: http://lkml.kernel.org/r/146608182119.21870.8439834428248129633.stgit@buzz Signed-off-by: Ingo Molnar <mingo@kernel.org> Cc: Ben Pineau <benjamin.pineau@mirakl.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> 
commit 094f469172e00d6ab0a3130b0e01c83b3cf3a98d upstream.

Cgroup created inside throttled group must inherit current throttle_count.
Broken throttle_count allows to nominate throttled entries as a next buddy,
later this leads to null pointer dereference in pick_next_task_fair().

This patch initialize cfs_rq->throttle_count at first enqueue: laziness
allows to skip locking all rq at group creation. Lazy approach also allows
to skip full sub-tree scan at throttling hierarchy (not in this patch).

Signed-off-by: Konstantin Khlebnikov <khlebnikov@yandex-team.ru>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: bsegall@google.com
Link: http://lkml.kernel.org/r/146608182119.21870.8439834428248129633.stgit@buzz
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: Ben Pineau <benjamin.pineau@mirakl.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>