Message-ID: <4F7F4EF0.70305@linux.vnet.ibm.com>
Date:	Sat, 07 Apr 2012 01:45:44 +0530
From:	"Srivatsa S. Bhat" <srivatsa.bhat@...ux.vnet.ibm.com>
To:	paulmck@...ux.vnet.ibm.com
CC:	Peter Zijlstra <a.p.zijlstra@...llo.nl>,
	Arjan van de Ven <arjan@...radead.org>,
	Steven Rostedt <rostedt@...dmis.org>,
	"rusty@...tcorp.com.au" <rusty@...tcorp.com.au>,
	"Rafael J. Wysocki" <rjw@...k.pl>,
	Srivatsa Vaddagiri <vatsa@...ux.vnet.ibm.com>,
	"akpm@...ux-foundation.org" <akpm@...ux-foundation.org>,
	Paul Gortmaker <paul.gortmaker@...driver.com>,
	Milton Miller <miltonm@....com>,
	"mingo@...e.hu" <mingo@...e.hu>, Tejun Heo <tj@...nel.org>,
	KOSAKI Motohiro <kosaki.motohiro@...il.com>,
	linux-kernel <linux-kernel@...r.kernel.org>,
	Linux PM mailing list <linux-pm@...r.kernel.org>,
	nikunj@...ux.vnet.ibm.com
Subject: Re: CPU Hotplug rework

On 04/06/2012 04:36 AM, Paul E. McKenney wrote:

> Hello,
> 
> Here is my attempt at a summary of the discussion.
> 


Thanks for the summary, it is really helpful :-)

> Srivatsa, I left out the preempt_disable() pieces, but would be happy
> to add them in when you let me know what you are thinking to do for
> de-stop_machine()ing CPU hotplug.
>


Ok..

 
> 							Thanx, Paul
> 
> ------------------------------------------------------------------------
> 
> CPU-hotplug work breakout:
> 
> 1.	Read and understand the current generic code.
> 	Srivatsa Bhat has done this, as have Paul E. McKenney and
> 	Peter Zijlstra to a lesser extent.


	"lesser extent"?? Hell no! :-) ;-)

> 
> 2.	Read and understand the architecture-specific code, looking
> 	for opportunities to consolidate additional function into
> 	core code.
> 
> 	a.	Carry out any indicated consolidation.
> 
> 	b.	Convert all architectures to make use of the
> 		consolidated implementation.
> 
> 	Not started.  Low priority from a big.LITTLE perspective.


Recently this unexpectedly assumed high priority due to some scheduler
changes and things got fixed up temporarily. And in that context,
Peter Zijlstra gave some more technical pointers on what is wrong and needs
to be done right. Link: https://lkml.org/lkml/2012/3/22/149

Nikunj (in CC) has offered to work with me on this consolidation.

> 
> 3.	Address the current kthread creation/teardown/migration
> 	performance issues.  (More details below.)
> 
> 	Highest priority from a big.LITTLE perspective.
> 
> 4.	Wean CPU-hotplug offlining from stop_machine().
> 	(More details below.)
> 
> 	Moderate priority from a big.LITTLE perspective.
> 
> 
> ADDRESSING KTHREAD CREATION/TEARDOWN/MIGRATION PERFORMANCE ISSUES
> 
> 1.	Evaluate approaches.  Approaches currently under
> 	consideration include:
> 
> 	a.	Park the kthreads rather than tearing them down or
> 		migrating them.  RCU currently takes this sort of
> 		approach.  Note that RCU currently relies on both
> 		preempt_disable() and local_bh_disable() blocking the
> 		current CPU from going offline.
> 
> 	b.	Allow in-kernel kthreads to avoid the delay
> 		required to work around a bug in old versions of
> 		bash.  (This bug is a failure to expect receiving
> 		a SIGCHILD signal corresponding to a child
> 		created by a fork() system call that has not yet
> 		returned.)
> 
> 		This might be implemented using an additional
> 		CLONE_ flag.  This should allow kthreads to
> 		be created and torn down much more quickly.
> 
> 	c.	Have some other TBD way to "freeze" a kthread.
> 		(As in "your clever idea here".)
> 
> 2.	Implement the chosen approach or approaches.  (Different
> 	kernel subsystems might have different constraints, possibly
> 	requiring different kthread handling.)
> 
> 
> WEAN CPU-HOTPLUG OFFLINING FROM stop_machine()
> 
> 
> 1.	CPU_DYING notifier fixes needed as of 3.2:
> 
> 	o	vfp_hotplug():  I believe that this works as-is.
> 	o	s390_nohz_notify():  I believe that this works as-is.
> 	o	x86_pmu_notifier():  I believe that this works as-is.
> 	o	perf_ibs_cpu_notifier():  I don't know enough about
> 		APIC to say.
> 	o	tboot_cpu_callback():  I believe that this works as-is,
> 		but this one returns NOTIFY_BAD to a CPU_DYING notifier,
> 		which is badness.  But it looks like that case is a
> 		"cannot happen" case.  Still needs to be fixed.
> 	o	clockevents_notify():  This one acquires a global lock,
> 		so it should be safe as-is.
> 	o	console_cpu_notify():  This one takes the same action
> 		for CPU_ONLINE, CPU_DEAD, CPU_DOWN_FAILED, and
> 		CPU_UP_CANCELLED that it does for CPU_DYING, so it
> 		should be OK.
> 	*	rcu_cpu_notify():  This one needs adjustment as noted
> 		above, but nothing major.  Patch has been posted,
> 		probably needs a bit of debugging.
> 	o	migration_call():  I defer to Peter on this one.
> 		It looks to me like it is written to handle other
> 		CPUs, but...
> 	*	workqueue_cpu_callback(): Might need help, does a
> 		non-atomic OR.
> 	o	kvm_cpu_hotplug(): Uses a global spinlock, so should
> 		be OK as-is.
> 
> 2.	Evaluate designs for stop_machine()-free CPU hotplug.
> 	Implement the chosen design.  An outline for a particular
> 	design is shown below, but the actual design might be
> 	quite different.
> 
> 3.	Fix issues with CPU Hotplug callback registration. Currently
> 	there is no totally-race-free way to register callbacks and do
> 	setup for already online cpus.
> 
> 	Srivatsa had posted an incomplete patchset some time ago
> 	regarding this, which gives an idea of the direction he had
> 	in mind.
> 	http://thread.gmane.org/gmane.linux.kernel/1258880/focus=15826
> 


Gah, this has been "incomplete" for quite some time now.. I'll try to speed up
things a bit :-)

> 4.	There is a mismatch between the code and the documentation around
> 	the difference between [un/register]_hotcpu_notifier and
> 	[un/register]_cpu_notifier. And I remember seeing several places
> 	in the code that uses them inconsistently. Not terribly important,
> 	but good to fix it up while we are at it.
> 
> 5.	There was another thread where stuff related to CPU hotplug had
> 	been discussed. It had exposed some new challenges to CPU hotplug,
> 	if we were to support asynchronous smp booting.
> 
> 	http://thread.gmane.org/gmane.linux.kernel/1246209/focus=48535
> 	http://thread.gmane.org/gmane.linux.kernel/1246209/focus=48542
> 	http://thread.gmane.org/gmane.linux.kernel/1246209/focus=1253241
> 	http://thread.gmane.org/gmane.linux.kernel/1246209/focus=1253267
> 
> 6.	If preempt_disable() no longer blocks CPU offlining, then
> 	uses of preempt_disable() in the kernel need to be inspected
> 	to see which are relying on blocking offlining, and any
> 	identified will need adjustment.
> 
> 
> DRAFT REQUIREMENTS FOR stop_machine()-FREE CPU HOTPLUG
> 
> 1.	preempt_disable() or something similarly lightweight and
> 	unconditional must block removal of any CPU that was
> 	in cpu_online_map at the start of the "critical section".
> 	(I will identify these as hotplug read-side critical sections.)
> 
> 	I don't believe that there is any prohibition against a CPU
> 	appearing suddenly, but some auditing would be required to
> 	confirm this.  But see below.
> 
> 2.	A subsystem not involved in the CPU-hotplug process must be able
> 	to test if a CPU is online and be guaranteed that this test
> 	remains valid (the CPU remains fully functional) for the duration
> 	of the hotplug read-side critical section.
> 
> 3.	If a subsystem needs to operate on all currently online CPUs,
> 	then it must participate in the CPU-hotplug process.  My
> 	belief is that if some code needs to test whether a CPU is
> 	present, and needs an "offline" indication to persist, then
> 	that code's subsystem must participate in CPU-hotplug operations.
> 
> 4.	There must be a way to register/unregister for CPU-hotplug events.
> 	This is currently cpu_notifier(), register_cpu_notifier(),
> 	and unregister_cpu_notifier().
> 
> n-1.	CPU-hotplug operations should be reasonably fast.  A few
> 	milliseconds is OK, multiple seconds not so much.
> 
> n.	(Your additional constraints here.)
> 
> 
> STRAWMAN DESIGN FOR stop_machine()-FREE CPU HOTPLUG
> 
> a.	Maintain the cpu_online_map, as currently, but the meaning
> 	of a set bit is that the CPU is fully functional.  If there
> 	is any service that the CPU no longer offers, its bit is
> 	cleared.
> 
> b.	Continue to use preempt_enable()/preempt_disable() to mark
> 	hotplug read-side critical sections.
> 
> c.	Instead of using __stop_machine(), use a per-CPU variable that
> 	is checked in the idle loop.  Possibly another TIF_ bit.
> 
> d.	The CPU notifiers are like today, except that CPU_DYING() is
> 	invoked by the CPU after it sees that its per-CPU variable
> 	telling it to go offline.  As today, the CPU_DYING notifiers
> 	are invoked with interrupts disabled, but other CPUs are still
> 	running.  Of course, the CPU_DYING notifiers need to be audited
> 	and repaired.  There are fewer than 20 of them, so not so bad.
> 	RCU's is an easy fix:  Just re-introduce locking and the global
> 	RCU callback orphanage.  My guesses for the others at the end.
> 
> e.	Getting rid of __stop_machine() means that the final step of the
> 	CPU going offline will no longer be seen as atomic by other CPUs.
> 	This will require more careful tracking of dependencies among
> 	different subsystems.  The required tracking can be reduced
> 	by invoking notifiers in registration order for CPU-online
> 	operations and invoking them in the reverse of registration
> 	order for CPU-offline operations.
> 
> 	For example, the scheduler uses RCU.  If notifiers are invoked in
> 	the same order for all CPU-hotplug operations, then on CPU-offline
> 	operations, during the time between when RCU's notifier is invoked
> 	and when the scheduler's notifier is invoked, the scheduler must
> 	deal with a CPU on which RCU isn't working.  (RCU currently
> 	works around this by allowing a one-jiffy time period after
> 	notification when it still pays attention to the CPU.)
> 
> 	In contrast, if notifiers are invoked in reverse-registration
> 	order for CPU-offline operations, then any time the scheduler
> 	sees a CPU as online, RCU also is treating it as online.
> 
> f.	There will be some circular dependencies.  For example, the
> 	scheduler uses RCU, but in some configurations, RCU also uses
> 	kthreads.  These dependencies must be handled on a case-by-case
> 	basis.	For example, the scheduler could invoke an RCU API
> 	to tell RCU when to shut down its per-CPU kthreads and when
> 	to start them up.  Or RCU could deal with its kthreads in the
> 	CPU_DOWN_PREPARE and CPU_ONLINE notifiers.  Either way, RCU
> 	needs to correctly handle the interval when it cannot use
> 	kthreads on a given CPU that it is still handling, for example,
> 	by switching to running the RCU core code in softirq context.
> 
> g.	Most subsystems participating in CPU-hotplug operations will need
> 	to keep their own copy of CPU online/offline state.  For example,
> 	RCU uses the ->qsmaskinit fields in the rcu_node structure for
> 	this purpose.
> 
> h.	So CPU-offline handling looks something like the following:
> 
> 	i.	Acquire the hotplug mutex.
> 	
> 	ii.	Invoke the CPU_DOWN_PREPARE notifiers.  If there
> 		are objections, invoke the CPU_DOWN_FAILED notifiers
> 		and return an error.
> 
> 	iii.	Clear the CPU's bit in cpu_online_map.
> 	
> 	iv.	Invoke synchronize_sched() to ensure that all future hotplug
> 		read-side critical sections ignore the outgoing CPU.
> 
> 	v.	Set a per-CPU variable telling the CPU to take itself
> 		offline.  There would need to be something here to
> 		help the CPU get to idle quickly, possibly requiring
> 		another round of notifiers.  CPU_DOWN?
> 
> 	vi.	When the dying CPU gets to the idle loop, it invokes the
> 		CPU_DYING notifiers and updates its per-CPU variable to
> 		indicate that it is ready to die.  It then spins in a
> 		tight loop (or does some other architecture-specified
> 		operation to wait to be turned off).
> 
> 		Note that there is no need for RCU to guess how long the
> 		CPU might be executing RCU read-side critical sections.
> 
> 	vii.	When the task doing the offline operation sees the
> 		updated per-CPU variable, it calls __cpu_die().
> 
> 	viii.	The CPU_DEAD notifiers are invoked.
> 
> 	ix.	Theeck_for_tasks() function is invoked.
> 
> 	x.	Release the hotplug mutex.
> 
> 	xi.	Invoke the CPU_POST_DEAD notifiers.
> 
> i.	I do not believe that the CPU-offline handling needs to change
> 	much.


Regards,
Srivatsa S. Bhat

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/

Powered by blists - more mailing lists