Changeset a43455a1 ("sched/numa: Ensure task_numa_migrate() checks
the preferred node") fixes an issue where workloads would never
converge on a fully loaded (or overloaded) system.

However, it introduces a regression on less than fully loaded systems,
where workloads converge on a few NUMA nodes, instead of properly
staying spread out across the whole system. This leads to a reduction
in available memory bandwidth, and usable CPU cache, with predictable
performance problems.

The root cause appears to be an interaction between the load balancer
and NUMA balancing, where the short term load represented by the load
balancer differs from the long term load the NUMA balancing code would
like to base its decisions on.

Simply reverting a43455a1 would re-introduce the non-convergence
of workloads on fully loaded systems, so that is not a good option. As
an aside, the check done before a43455a1 only applied to a task's
preferred node, not to other candidate nodes in the system, so the
converge-on-too-few-nodes problem still happens, just to a lesser
degree.

Instead, try to compensate for the impedance mismatch between the load
balancer and NUMA balancing by only ever considering a lesser loaded
node as a destination for NUMA balancing, regardless of whether the
task is trying to move to the preferred node, or to another node.

This patch also addresses the issue that a system with a single
runnable thread would never migrate that thread to near its memory,
introduced by 095bebf6 ("sched/numa: Do not move past the balance
point if unbalanced").

A test where the main thread creates a large memory area, and spawns a
worker thread to iterate over the memory (placed on another node by
select_task_rq_fair), after which the main thread goes to sleep and
waits for the worker thread to loop over all the memory now sees the
worker thread migrated to where the memory is, instead of having all
the memory migrated over like before.

Jirka has run a number of performance tests on several systems: single
instance SpecJBB 2005 performance is 7-15% higher on a 4 node system,
with higher gains on systems with more cores per socket.
Multi-instance SpecJBB 2005 (one per node), linpack, and stream see
little or no changes with the revert of 095bebf6 and this patch.
Reported-by: NArtem Bityutski <dedekind1@gmail.com>
Reported-by: NJirka Hladky <jhladky@redhat.com>
Tested-by: NJirka Hladky <jhladky@redhat.com>
Tested-by: NArtem Bityutskiy <dedekind1@gmail.com>
Signed-off-by: NRik van Riel <riel@redhat.com>
Signed-off-by: NPeter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: NMel Gorman <mgorman@suse.de>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/20150528095249.3083ade0@annuminas.surriel.comSigned-off-by: NIngo Molnar <mingo@kernel.org>

Commit 095bebf6 ("sched/numa: Do not move past the balance point
if unbalanced") broke convergence of workloads with just one runnable
thread, by making it impossible for the one runnable thread on the
system to move from one NUMA node to another.

Instead, the thread would remain where it was, and pull all the memory
across to its location, which is much slower than just migrating the
thread to where the memory is.

The next patch has a better fix for the issue that 095bebf6 tried
to address.
Reported-by: NJirka Hladky <jhladky@redhat.com>
Signed-off-by: NRik van Riel <riel@redhat.com>
Signed-off-by: NPeter Zijlstra (Intel) <peterz@infradead.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: dedekind1@gmail.com
Cc: mgorman@suse.de
Link: http://lkml.kernel.org/r/1432753468-7785-2-git-send-email-riel@redhat.comSigned-off-by: NIngo Molnar <mingo@kernel.org>

The optimized task selection logic optimistically selects a new task
to run without first doing a full put_prev_task(). This is so that we
can avoid a put/set on the common ancestors of the old and new task.

Similarly, we should only call check_cfs_rq_runtime() to throttle
eligible groups if they're part of the common ancestry, otherwise it
is possible to end up with no eligible task in the simple task
selection.

Imagine:
		/root
	/prev		/next
	/A		/B

If our optimistic selection ends up throttling /next, we goto simple
and our put_prev_task() ends up throttling /prev, after which we're
going to bug out in set_next_entity() because there aren't any tasks
left.

Avoid this scenario by only throttling common ancestors.
Reported-by: NMohammed Naser <mnaser@vexxhost.com>
Reported-by: NKonstantin Khlebnikov <khlebnikov@yandex-team.ru>
Signed-off-by: NBen Segall <bsegall@google.com>
[ munged Changelog ]
Signed-off-by: NPeter Zijlstra (Intel) <peterz@infradead.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Roman Gushchin <klamm@yandex-team.ru>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: pjt@google.com
Fixes: 678d5718 ("sched/fair: Optimize cgroup pick_next_task_fair()")
Link: http://lkml.kernel.org/r/xm26wq1oswoq.fsf@sword-of-the-dawn.mtv.corp.google.comSigned-off-by: NIngo Molnar <mingo@kernel.org>

preempt_schedule_context() is a tracing safe preemption point but it's
only used when CONFIG_CONTEXT_TRACKING=y. Other configs have tracing
recursion issues since commit:

  b30f0e3f ("sched/preempt: Optimize preemption operations on __schedule() callers")

introduced function based preemp_count_*() ops.

Lets make it available on all configs and give it a more appropriate
name for its new position.
Reported-by: NFengguang Wu <fengguang.wu@intel.com>
Signed-off-by: NFrederic Weisbecker <fweisbec@gmail.com>
Signed-off-by: NPeter Zijlstra (Intel) <peterz@infradead.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/1433432349-1021-3-git-send-email-fweisbec@gmail.comSigned-off-by: NIngo Molnar <mingo@kernel.org>

Since function tracing disables preemption, it needs a safe preemption
point to use when preemption is re-enabled without worrying about tracing
recursion. Ie: to avoid tracing recursion, that preemption point can't
be traced (use of notrace qualifier) and it can't call any traceable
function before that preemption point disables preemption itself, which
disarms the recursion.

preempt_schedule() was fine until commit:

  b30f0e3f ("sched/preempt: Optimize preemption operations on __schedule() callers")

because PREEMPT_ACTIVE (which has the property to disable preemption
and this disarm tracing preemption recursion) was set before calling
any further function.

But that commit introduced the use of preempt_count_add/sub() functions
to set PREEMPT_ACTIVE and because these functions are called before
preemption gets a chance to be disabled, we have a tracing recursion.

preempt_schedule_context() is one of the possible preemption functions
used by tracing. Its special purpose is to avoid tracing recursion
against context tracking. Lets enhance this function to become more
generally tracing safe by disabling preemption with raw accessors, such
that no function is called before preemption gets disabled and disarm
the tracing recursion.

This function is going to become the specific tracing-safe preemption
point in further commit.
Reported-by: NFengguang Wu <fengguang.wu@intel.com>
Signed-off-by: NFrederic Weisbecker <fweisbec@gmail.com>
Signed-off-by: NPeter Zijlstra (Intel) <peterz@infradead.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/1433432349-1021-2-git-send-email-fweisbec@gmail.comSigned-off-by: NIngo Molnar <mingo@kernel.org>

It is possible for fbq_classify_rq() to indicate that a CPU has tasks that
should be moved to another NUMA node, but for migrate_improves_locality
and migrate_degrades_locality to not identify those tasks.

This patch always gives preference to preferred node evaluations, and
only checks the number of faults when evaluating moves between two
non-preferred nodes on a larger NUMA system.

On a two node system, the number of faults is never evaluated. Either
a task is about to be pulled off its preferred node, or migrated onto
it.
Signed-off-by: NRik van Riel <riel@redhat.com>
Signed-off-by: NPeter 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: mgorman@suse.de
Link: http://lkml.kernel.org/r/20150514225936.35b91717@annuminas.surriel.comSigned-off-by: NIngo Molnar <mingo@kernel.org>

__schedule() disables preemption and some of its callers
(the preempt_schedule*() family) also set PREEMPT_ACTIVE.

So we have two preempt_count() modifications that could be performed
at once.

Lets remove the preemption disablement from __schedule() and pull
this responsibility to its callers in order to optimize preempt_count()
operations in a single place.
Suggested-by: NLinus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: NFrederic Weisbecker <fweisbec@gmail.com>
Signed-off-by: NPeter Zijlstra (Intel) <peterz@infradead.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/1431441711-29753-5-git-send-email-fweisbec@gmail.comSigned-off-by: NIngo Molnar <mingo@kernel.org>

block plug callback could sleep, so we introduce a parameter
'from_schedule' and corresponding drivers can use it to destinguish a
schedule plug flush or a plug finish. Unfortunately io_schedule_out
still uses blk_flush_plug(). This causes below output (Note, I added a
might_sleep() in raid1_unplug to make it trigger faster, but the whole
thing doesn't matter if I add might_sleep). In raid1/10, this can cause
deadlock.

This patch makes io_schedule_out always uses blk_schedule_flush_plug.
This should only impact drivers (as far as I know, raid 1/10) which are
sensitive to the 'from_schedule' parameter.

[  370.817949] ------------[ cut here ]------------
[  370.817960] WARNING: CPU: 7 PID: 145 at ../kernel/sched/core.c:7306 __might_sleep+0x7f/0x90()
[  370.817969] do not call blocking ops when !TASK_RUNNING; state=2 set at [<ffffffff81092fcf>] prepare_to_wait+0x2f/0x90
[  370.817971] Modules linked in: raid1
[  370.817976] CPU: 7 PID: 145 Comm: kworker/u16:9 Tainted: G        W       4.0.0+ #361
[  370.817977] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.7.5-20140709_153802- 04/01/2014
[  370.817983] Workqueue: writeback bdi_writeback_workfn (flush-9:1)
[  370.817985]  ffffffff81cd83be ffff8800ba8cb298 ffffffff819dd7af 0000000000000001
[  370.817988]  ffff8800ba8cb2e8 ffff8800ba8cb2d8 ffffffff81051afc ffff8800ba8cb2c8
[  370.817990]  ffffffffa00061a8 000000000000041e 0000000000000000 ffff8800ba8cba28
[  370.817993] Call Trace:
[  370.817999]  [<ffffffff819dd7af>] dump_stack+0x4f/0x7b
[  370.818002]  [<ffffffff81051afc>] warn_slowpath_common+0x8c/0xd0
[  370.818004]  [<ffffffff81051b86>] warn_slowpath_fmt+0x46/0x50
[  370.818006]  [<ffffffff81092fcf>] ? prepare_to_wait+0x2f/0x90
[  370.818008]  [<ffffffff81092fcf>] ? prepare_to_wait+0x2f/0x90
[  370.818010]  [<ffffffff810776ef>] __might_sleep+0x7f/0x90
[  370.818014]  [<ffffffffa0000c03>] raid1_unplug+0xd3/0x170 [raid1]
[  370.818024]  [<ffffffff81421d9a>] blk_flush_plug_list+0x8a/0x1e0
[  370.818028]  [<ffffffff819e3550>] ? bit_wait+0x50/0x50
[  370.818031]  [<ffffffff819e21b0>] io_schedule_timeout+0x130/0x140
[  370.818033]  [<ffffffff819e3586>] bit_wait_io+0x36/0x50
[  370.818034]  [<ffffffff819e31b5>] __wait_on_bit+0x65/0x90
[  370.818041]  [<ffffffff8125b67c>] ? ext4_read_block_bitmap_nowait+0xbc/0x630
[  370.818043]  [<ffffffff819e3550>] ? bit_wait+0x50/0x50
[  370.818045]  [<ffffffff819e3302>] out_of_line_wait_on_bit+0x72/0x80
[  370.818047]  [<ffffffff810935e0>] ? autoremove_wake_function+0x40/0x40
[  370.818050]  [<ffffffff811de744>] __wait_on_buffer+0x44/0x50
[  370.818053]  [<ffffffff8125ae80>] ext4_wait_block_bitmap+0xe0/0xf0
[  370.818058]  [<ffffffff812975d6>] ext4_mb_init_cache+0x206/0x790
[  370.818062]  [<ffffffff8114bc6c>] ? lru_cache_add+0x1c/0x50
[  370.818064]  [<ffffffff81297c7e>] ext4_mb_init_group+0x11e/0x200
[  370.818066]  [<ffffffff81298231>] ext4_mb_load_buddy+0x341/0x360
[  370.818068]  [<ffffffff8129a1a3>] ext4_mb_find_by_goal+0x93/0x2f0
[  370.818070]  [<ffffffff81295b54>] ? ext4_mb_normalize_request+0x1e4/0x5b0
[  370.818072]  [<ffffffff8129ab67>] ext4_mb_regular_allocator+0x67/0x460
[  370.818074]  [<ffffffff81295b54>] ? ext4_mb_normalize_request+0x1e4/0x5b0
[  370.818076]  [<ffffffff8129ca4b>] ext4_mb_new_blocks+0x4cb/0x620
[  370.818079]  [<ffffffff81290956>] ext4_ext_map_blocks+0x4c6/0x14d0
[  370.818081]  [<ffffffff812a4d4e>] ? ext4_es_lookup_extent+0x4e/0x290
[  370.818085]  [<ffffffff8126399d>] ext4_map_blocks+0x14d/0x4f0
[  370.818088]  [<ffffffff81266fbd>] ext4_writepages+0x76d/0xe50
[  370.818094]  [<ffffffff81149691>] do_writepages+0x21/0x50
[  370.818097]  [<ffffffff811d5c00>] __writeback_single_inode+0x60/0x490
[  370.818099]  [<ffffffff811d630a>] writeback_sb_inodes+0x2da/0x590
[  370.818103]  [<ffffffff811abf4b>] ? trylock_super+0x1b/0x50
[  370.818105]  [<ffffffff811abf4b>] ? trylock_super+0x1b/0x50
[  370.818107]  [<ffffffff811d665f>] __writeback_inodes_wb+0x9f/0xd0
[  370.818109]  [<ffffffff811d69db>] wb_writeback+0x34b/0x3c0
[  370.818111]  [<ffffffff811d70df>] bdi_writeback_workfn+0x23f/0x550
[  370.818116]  [<ffffffff8106bbd8>] process_one_work+0x1c8/0x570
[  370.818117]  [<ffffffff8106bb5b>] ? process_one_work+0x14b/0x570
[  370.818119]  [<ffffffff8106c09b>] worker_thread+0x11b/0x470
[  370.818121]  [<ffffffff8106bf80>] ? process_one_work+0x570/0x570
[  370.818124]  [<ffffffff81071868>] kthread+0xf8/0x110
[  370.818126]  [<ffffffff81071770>] ? kthread_create_on_node+0x210/0x210
[  370.818129]  [<ffffffff819e9322>] ret_from_fork+0x42/0x70
[  370.818131]  [<ffffffff81071770>] ? kthread_create_on_node+0x210/0x210
[  370.818132] ---[ end trace 7b4deb71e68b6605 ]---

V2: don't change ->in_iowait

Cc: NeilBrown <neilb@suse.de>
Signed-off-by: NShaohua Li <shli@fb.com>
Reviewed-by: NJeff Moyer <jmoyer@redhat.com>
Signed-off-by: NJens Axboe <axboe@fb.com>

In the below two commits (see Fixes) we have periodic timers that can
stop themselves when they're no longer required, but need to be
(re)-started when their idle condition changes.

Further complications is that we want the timer handler to always do
the forward such that it will always correctly deal with the overruns,
and we do not want to race such that the handler has already decided
to stop, but the (external) restart sees the timer still active and we
end up with a 'lost' timer.

The problem with the current code is that the re-start can come before
the callback does the forward, at which point the forward from the
callback will WARN about forwarding an enqueued timer.

Now, conceptually its easy to detect if you're before or after the fwd
by comparing the expiration time against the current time. Of course,
that's expensive (and racy) because we don't have the current time.

Alternatively one could cache this state inside the timer, but then
everybody pays the overhead of maintaining this extra state, and that
is undesired.

The only other option that I could see is the external timer_active
variable, which I tried to kill before. I would love a nicer interface
for this seemingly simple 'problem' but alas.

Fixes: 272325c4 ("perf: Fix mux_interval hrtimer wreckage")
Fixes: 77a4d1a1 ("sched: Cleanup bandwidth timers")
Cc: pjt@google.com
Cc: tglx@linutronix.de
Cc: klamm@yandex-team.ru
Cc: mingo@kernel.org
Cc: bsegall@google.com
Cc: hpa@zytor.com
Cc: Sasha Levin <sasha.levin@oracle.com>
Signed-off-by: NPeter Zijlstra (Intel) <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20150514102311.GX21418@twins.programming.kicks-ass.net

static code checking was unhappy with:

  ./kernel/sched/fair.c:162 WARNING: return of wrong type
                int != unsigned int

get_update_sysctl_factor() is declared to return int but is
currently  returning an unsigned int. The first few preprocessed
lines are:

 static int get_update_sysctl_factor(void)
 {
 unsigned int cpus = ({ int __min1 = (cpumask_weight(cpu_online_mask));
 int __min2 = (8); __min1 < __min2 ? __min1: __min2; });
 unsigned int factor;

The type used by min_t() should be 'unsigned int' and the return type
of get_update_sysctl_factor() should also be 'unsigned int' as its
call-site update_sysctl() is expecting 'unsigned int' and the values
utilizing:

  'factor'
  'sysctl_sched_min_granularity'
  'sched_nr_latency'
  'sysctl_sched_wakeup_granularity'

... are also all 'unsigned int', plus cpumask_weight() is also
returning 'unsigned int'.

So the natural type to use around here is 'unsigned int'.

( Patch was compile tested with x86_64_defconfig +
  CONFIG_SCHED_DEBUG=y and the changed sections in
  kernel/sched/fair.i were reviewed. )
Signed-off-by: NNicholas Mc Guire <hofrat@osadl.org>
[ Improved the changelog a bit. ]
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/1431716742-11077-1-git-send-email-hofrat@osadl.orgSigned-off-by: NIngo Molnar <mingo@kernel.org>

This is useful for locking primitives that can effect multiple
wakeups per operation and want to avoid lock internal lock contention
by delaying the wakeups until we've released the lock internal locks.

Alternatively it can be used to avoid issuing multiple wakeups, and
thus save a few cycles, in packet processing. Queue all target tasks
and wakeup once you've processed all packets. That way you avoid
waking the target task multiple times if there were multiple packets
for the same task.

Properties of a wake_q are:
- Lockless, as queue head must reside on the stack.
- Being a queue, maintains wakeup order passed by the callers. This can
  be important for otherwise, in scenarios where highly contended locks
  could affect any reliance on lock fairness.
- A queued task cannot be added again until it is woken up.

This patch adds the needed infrastructure into the scheduler code
and uses the new wake_list to delay the futex wakeups until
after we've released the hash bucket locks.
Signed-off-by: NPeter Zijlstra (Intel) <peterz@infradead.org>
[tweaks, adjustments, comments, etc.]
Signed-off-by: NDavidlohr Bueso <dbueso@suse.de>
Signed-off-by: NPeter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: NThomas Gleixner <tglx@linutronix.de>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Chris Mason <clm@fb.com>
Cc: Davidlohr Bueso <dave@stgolabs.net>
Cc: George Spelvin <linux@horizon.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Manfred Spraul <manfred@colorfullife.com>
Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Cc: Steven Rostedt <rostedt@goodmis.org>
Link: http://lkml.kernel.org/r/1430494072-30283-2-git-send-email-dave@stgolabs.netSigned-off-by: NIngo Molnar <mingo@kernel.org>

Recent optimizations were made to thread_group_cputimer to improve its
scalability by keeping track of cputime stats without a lock. However,
the values were open coded to the structure, causing them to be at
a different abstraction level from the regular task_cputime structure.
Furthermore, any subsequent similar optimizations would not be able to
share the new code, since they are specific to thread_group_cputimer.

This patch adds the new task_cputime_atomic data structure (introduced in
the previous patch in the series) to thread_group_cputimer for keeping
track of the cputime atomically, which also helps generalize the code.
Suggested-by: NIngo Molnar <mingo@kernel.org>
Signed-off-by: NJason Low <jason.low2@hp.com>
Signed-off-by: NPeter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: NThomas Gleixner <tglx@linutronix.de>
Acked-by: NRik van Riel <riel@redhat.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Aswin Chandramouleeswaran <aswin@hp.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Davidlohr Bueso <dave@stgolabs.net>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Mike Galbraith <umgwanakikbuti@gmail.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Preeti U Murthy <preeti@linux.vnet.ibm.com>
Cc: Scott J Norton <scott.norton@hp.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Waiman Long <Waiman.Long@hp.com>
Link: http://lkml.kernel.org/r/1430251224-5764-6-git-send-email-jason.low2@hp.comSigned-off-by: NIngo Molnar <mingo@kernel.org>

While running a database workload, we found a scalability issue with itimers.

Much of the problem was caused by the thread_group_cputimer spinlock.
Each time we account for group system/user time, we need to obtain a
thread_group_cputimer's spinlock to update the timers. On larger systems
(such as a 16 socket machine), this caused more than 30% of total time
spent trying to obtain this kernel lock to update these group timer stats.

This patch converts the timers to 64-bit atomic variables and use
atomic add to update them without a lock. With this patch, the percent
of total time spent updating thread group cputimer timers was reduced
from 30% down to less than 1%.

Note: On 32-bit systems using the generic 64-bit atomics, this causes
sample_group_cputimer() to take locks 3 times instead of just 1 time.
However, we tested this patch on a 32-bit system ARM system using the
generic atomics and did not find the overhead to be much of an issue.
An explanation for why this isn't an issue is that 32-bit systems usually
have small numbers of CPUs, and cacheline contention from extra spinlocks
called periodically is not really apparent on smaller systems.
Signed-off-by: NJason Low <jason.low2@hp.com>
Signed-off-by: NPeter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: NThomas Gleixner <tglx@linutronix.de>
Acked-by: NRik van Riel <riel@redhat.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Aswin Chandramouleeswaran <aswin@hp.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Davidlohr Bueso <dave@stgolabs.net>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Mike Galbraith <umgwanakikbuti@gmail.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Preeti U Murthy <preeti@linux.vnet.ibm.com>
Cc: Scott J Norton <scott.norton@hp.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Waiman Long <Waiman.Long@hp.com>
Link: http://lkml.kernel.org/r/1430251224-5764-4-git-send-email-jason.low2@hp.comSigned-off-by: NIngo Molnar <mingo@kernel.org>

The p->mm->numa_scan_seq is accessed using READ_ONCE/WRITE_ONCE
and modified without exclusive access. It is not clear why it is
accessed this way. This patch provides some documentation on that.
Suggested-by: NIngo Molnar <mingo@kernel.org>
Signed-off-by: NJason Low <jason.low2@hp.com>
Signed-off-by: NPeter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: NThomas Gleixner <tglx@linutronix.de>
Acked-by: NRik van Riel <riel@redhat.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Aswin Chandramouleeswaran <aswin@hp.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Davidlohr Bueso <dave@stgolabs.net>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Mike Galbraith <umgwanakikbuti@gmail.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Preeti U Murthy <preeti@linux.vnet.ibm.com>
Cc: Scott J Norton <scott.norton@hp.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Waiman Long <waiman.long@hp.com>
Link: http://lkml.kernel.org/r/1430440094.2475.61.camel@j-VirtualBoxSigned-off-by: NIngo Molnar <mingo@kernel.org>

ACCESS_ONCE doesn't work reliably on non-scalar types. This patch removes
the rest of the existing usages of ACCESS_ONCE() in the scheduler, and use
the new READ_ONCE() and WRITE_ONCE() APIs as appropriate.
Signed-off-by: NJason Low <jason.low2@hp.com>
Signed-off-by: NPeter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: NThomas Gleixner <tglx@linutronix.de>
Acked-by: NRik van Riel <riel@redhat.com>
Acked-by: NWaiman Long <Waiman.Long@hp.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Aswin Chandramouleeswaran <aswin@hp.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Davidlohr Bueso <dave@stgolabs.net>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Mike Galbraith <umgwanakikbuti@gmail.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Preeti U Murthy <preeti@linux.vnet.ibm.com>
Cc: Scott J Norton <scott.norton@hp.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Link: http://lkml.kernel.org/r/1430251224-5764-2-git-send-email-jason.low2@hp.comSigned-off-by: NIngo Molnar <mingo@kernel.org>

'rt_period_us' is automatically type converted from u64 to long and then cast
back to u64 - this down/up conversion is unnecessary and can be removed to
improve readability.

This will also help us not truncate 'rt_period_us' to 32 bits on 32-bit kernels,
should we ever have so large values. (unlikely, not the least due to procfs.)
Signed-off-by: NNicholas Mc Guire <hofrat@osadl.org>
Signed-off-by: NPeter Zijlstra (Intel) <peterz@infradead.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/1430643116-24049-1-git-send-email-hofrat@osadl.orgSigned-off-by: NIngo Molnar <mingo@kernel.org>

I could not find the loadavg code.. turns out it was hidden in a file
called proc.c. It further got mingled up with the cruft per rq load
indexes (which we really want to get rid of).

Move the per rq load indexes into the fair.c load-balance code (that's
the only thing that uses them) and rename proc.c to loadavg.c so we
can find it again.
Signed-off-by: NPeter Zijlstra (Intel) <peterz@infradead.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Paul Gortmaker <paul.gortmaker@windriver.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
[ Did minor cleanups to the code. ]
Signed-off-by: NIngo Molnar <mingo@kernel.org>

We removed __cpuinit support (leaving no-op stubs) quite some time
ago.  However this one crept back in as of commit a803f026
("sched: Initialize rq->age_stamp on processor start")

Since we want to clobber the stubs too, get this removed now.
Signed-off-by: NPaul Gortmaker <paul.gortmaker@windriver.com>
Signed-off-by: NPeter Zijlstra (Intel) <peterz@infradead.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Corey Minyard <cminyard@mvista.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/1430174880-27958-2-git-send-email-paul.gortmaker@windriver.comSigned-off-by: NIngo Molnar <mingo@kernel.org>

Commit 3c18d447 ("sched/core: Check for available DL bandwidth in
cpuset_cpu_inactive()"), a SCHED_DEADLINE bugfix, had a logic error that
caused a regression in setting a CPU inactive during suspend. I ran into
this when a program was failing pthread_setaffinity_np() with EINVAL after
a suspend+wake up.

A simple reproducer:

	$ ./a.out
	sched_setaffinity: Success
	$ systemctl suspend
	$ ./a.out
	sched_setaffinity: Invalid argument

... where ./a.out is:

	#define _GNU_SOURCE
	#include <errno.h>
	#include <sched.h>
	#include <stdio.h>
	#include <stdlib.h>
	#include <string.h>
	#include <unistd.h>

	int main(void)
	{
		long num_cores;
		cpu_set_t cpu_set;
		int ret;

		num_cores = sysconf(_SC_NPROCESSORS_ONLN);
		CPU_ZERO(&cpu_set);
		CPU_SET(num_cores - 1, &cpu_set);
		errno = 0;
		ret = sched_setaffinity(getpid(), sizeof(cpu_set), &cpu_set);
		perror("sched_setaffinity");
		return ret ? EXIT_FAILURE : EXIT_SUCCESS;
	}

The mistake is that suspend is handled in the action ==
CPU_DOWN_PREPARE_FROZEN case of the switch statement in
cpuset_cpu_inactive().

However, the commit in question masked out CPU_TASKS_FROZEN
from the action, making this case dead.

The fix is straightforward.
Signed-off-by: NOmar Sandoval <osandov@osandov.com>
Signed-off-by: NPeter Zijlstra (Intel) <peterz@infradead.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Juri Lelli <juri.lelli@arm.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Fixes: 3c18d447 ("sched/core: Check for available DL bandwidth in cpuset_cpu_inactive()")
Link: http://lkml.kernel.org/r/1cb5ecb3d6543c38cce5790387f336f54ec8e2bc.1430733960.git.osandov@osandov.comSigned-off-by: NIngo Molnar <mingo@kernel.org>

Ronny reported that the following scenario is not handled correctly:

	T1 (prio = 10)
	   lock(rtmutex);

	T2 (prio = 20)
	   lock(rtmutex)
	      boost T1

	T1 (prio = 20)
	   sys_set_scheduler(prio = 30)
	   T1 prio = 30
	   ....
	   sys_set_scheduler(prio = 10)
	   T1 prio = 30

The last step is wrong as T1 should now be back at prio 20.

Commit c365c292 ("sched: Consider pi boosting in setscheduler()")
only handles the case where a boosted tasks tries to lower its
priority.

Fix it by taking the new effective priority into account for the
decision whether a change of the priority is required.
Reported-by: NRonny Meeus <ronny.meeus@gmail.com>
Tested-by: NSteven Rostedt <rostedt@goodmis.org>
Signed-off-by: NThomas Gleixner <tglx@linutronix.de>
Signed-off-by: NPeter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: NSteven Rostedt <rostedt@goodmis.org>
Cc: <stable@vger.kernel.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Mike Galbraith <umgwanakikbuti@gmail.com>
Fixes: c365c292 ("sched: Consider pi boosting in setscheduler()")
Link: http://lkml.kernel.org/r/alpine.DEB.2.11.1505051806060.4225@nanosSigned-off-by: NIngo Molnar <mingo@kernel.org>

Commit 335f4919 (sched/idle: Use explicit broadcast oneshot
control function) replaced clockevents_notify() invocations in
cpuidle_idle_call() with direct calls to tick_broadcast_enter()
and tick_broadcast_exit(), but it overlooked the fact that
interrupts were already enabled before calling the latter which
led to functional breakage on systems using idle states with the
CPUIDLE_FLAG_TIMER_STOP flag set.

Fix that by moving the invocations of tick_broadcast_enter()
and tick_broadcast_exit() down into cpuidle_enter_state() where
interrupts are still disabled when tick_broadcast_exit() is
called.  Also ensure that interrupts will be disabled before
running tick_broadcast_exit() even if they have been enabled by
the idle state's ->enter callback.  Trigger a WARN_ON_ONCE() in
that case, as we generally don't want that to happen for states
with CPUIDLE_FLAG_TIMER_STOP set.

Fixes: 335f4919 (sched/idle: Use explicit broadcast oneshot control function)
Reported-and-tested-by: NLinus Walleij <linus.walleij@linaro.org>
Acked-by: NPeter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: NDaniel Lezcano <daniel.lezcano@linaro.org>
Reported-and-tested-by: NSudeep Holla <sudeep.holla@arm.com>
Signed-off-by: NRafael J. Wysocki <rafael.j.wysocki@intel.com>

This reverts commits 0a4e6be9
and 80f7fdb1.

The task migration notifier was originally introduced in order to support
the pvclock vsyscall with non-synchronized TSC, but KVM only supports it
with synchronized TSC.  Hence, on KVM the race condition is only needed
due to a bad implementation on the host side, and even then it's so rare
that it's mostly theoretical.

As far as KVM is concerned it's possible to fix the host, avoiding the
additional complexity in the vDSO and the (re)introduction of the task
migration notifier.

Xen, on the other hand, hasn't yet implemented vsyscall support at
all, so we do not care about its plans for non-synchronized TSC.
Reported-by: NPeter Zijlstra <peterz@infradead.org>
Suggested-by: NMarcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: NPaolo Bonzini <pbonzini@redhat.com>

The struct member is gone.

Reported-by: fengguang.wu@intel.com>
Signed-off-by: NThomas Gleixner <tglx@linutronix.de>
Cc: Peter Zijlstra <peterz@infradead.org>

Roman reported a 3 cpu lockup scenario involving __start_cfs_bandwidth().

The more I look at that code the more I'm convinced its crack, that
entire __start_cfs_bandwidth() thing is brain melting, we don't need to
cancel a timer before starting it, *hrtimer_start*() will happily remove
the timer for you if its still enqueued.

Removing that, removes a big part of the problem, no more ugly cancel
loop to get stuck in.

So now, if I understand things right, the entire reason you have this
cfs_b->lock guarded ->timer_active nonsense is to make sure we don't
accidentally lose the timer.

It appears to me that it should be possible to guarantee that same by
unconditionally (re)starting the timer when !queued. Because regardless
what hrtimer::function will return, if we beat it to (re)enqueue the
timer, it doesn't matter.

Now, because hrtimers don't come with any serialization guarantees we
must ensure both handler and (re)start loop serialize their access to
the hrtimer to avoid both trying to forward the timer at the same
time.

Update the rt bandwidth timer to match.

This effectively reverts: 09dc4ab0 ("sched/fair: Fix
tg_set_cfs_bandwidth() deadlock on rq->lock").
Reported-by: NRoman Gushchin <klamm@yandex-team.ru>
Signed-off-by: NPeter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: NBen Segall <bsegall@google.com>
Cc: Paul Turner <pjt@google.com>
Link: http://lkml.kernel.org/r/20150415095011.804589208@infradead.orgSigned-off-by: NThomas Gleixner <tglx@linutronix.de>

hrtimer_start() does not longer defer already expired timers to the
softirq. Get rid of the __hrtimer_start_range_ns() invocation.
Signed-off-by: NThomas Gleixner <tglx@linutronix.de>
Acked-by: NPeter Zijlstra <peterz@infradead.org>
Cc: Preeti U Murthy <preeti@linux.vnet.ibm.com>
Cc: Viresh Kumar <viresh.kumar@linaro.org>
Cc: Marcelo Tosatti <mtosatti@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Link: http://lkml.kernel.org/r/20150414203502.627353666@linutronix.deSigned-off-by: NThomas Gleixner <tglx@linutronix.de>

hrtimer_start() now enforces a timer interrupt when an already expired
timer is enqueued.

Get rid of the __hrtimer_start_range_ns() invocations and the loops
around it.
Signed-off-by: NThomas Gleixner <tglx@linutronix.de>
Acked-by: NPeter Zijlstra <peterz@infradead.org>
Cc: Preeti U Murthy <preeti@linux.vnet.ibm.com>
Cc: Viresh Kumar <viresh.kumar@linaro.org>
Cc: Marcelo Tosatti <mtosatti@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Link: http://lkml.kernel.org/r/20150414203502.531131739@linutronix.deSigned-off-by: NThomas Gleixner <tglx@linutronix.de>

Since commit:

  029632fb ("sched: Make separate sched*.c translation units")

autogroup is a separate translation unit built from the Makefile and
thus no longer needs its content wrapped with #ifdef CONFIG_SCHED_AUTOGROUP.
Signed-off-by: NTobias Klauser <tklauser@distanz.ch>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1429116678-17000-1-git-send-email-tklauser@distanz.chSigned-off-by: NIngo Molnar <mingo@kernel.org>

Currently when a process accesses a hugetlb range protected with
PROTNONE, unexpected COWs are triggered, which finally puts the hugetlb
subsystem into a broken/uncontrollable state, where for example
h->resv_huge_pages is subtracted too much and wraps around to a very
large number, and the free hugepage pool is no longer maintainable.

This patch simply stops changing protection for vma(VM_HUGETLB) to fix
the problem.  And this also allows us to avoid useless overhead of minor
faults.
Signed-off-by: NNaoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Suggested-by: NMel Gorman <mgorman@suse.de>
Cc: Hugh Dickins <hughd@google.com>
Cc: "Kirill A. Shutemov" <kirill@shutemov.name>
Cc: David Rientjes <rientjes@google.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Ingo Molnar <mingo@elte.hu>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Commit:

  3c18d447 ("sched/core: Check for available DL bandwidth in cpuset_cpu_inactive()")

forgot a trace_printk() debugging piece in and Steve's banner screamed
in dmesg. Remove it.
Signed-off-by: NBorislav Petkov <bp@suse.de>
Cc: Juri Lelli <juri.lelli@arm.com>
Cc: Juri Lelli <juri.lelli@gmail.com>
Cc: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Link: http://lkml.kernel.org/r/1428050570-21041-1-git-send-email-bp@alien8.deSigned-off-by: NIngo Molnar <mingo@kernel.org>

Replace the clockevents_notify() call with an explicit function call.
Signed-off-by: NThomas Gleixner <tglx@linutronix.de>
Signed-off-by: NRafael J. Wysocki <rafael.j.wysocki@intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/6422336.RMm7oUHcXh@vostro.rjw.lanSigned-off-by: NIngo Molnar <mingo@kernel.org>

I observed that DL tasks can't be migrated to other CPUs during CPU
hotplug, in addition, task may/may not be running again if CPU is
added back.

The root cause which I found is that DL tasks will be throtted and
removed from the DL rq after comsuming all their budget, which
leads to the situation that stop task can't pick them up from the
DL rq and migrate them to other CPUs during hotplug.

The method to reproduce:

  schedtool -E -t 50000:100000 -e ./test

Actually './test' is just a simple for loop. Then observe which CPU the
test task is on and offline it:

  echo 0 > /sys/devices/system/cpu/cpuN/online

This patch adds the DL task migration during CPU hotplug by finding a
most suitable later deadline rq after DL timer fires if current rq is
offline.

If it fails to find a suitable later deadline rq then it falls back to
any eligible online CPU in so that the deadline task will come back
to us, and the push/pull mechanism should then move it around properly.
Suggested-and-Acked-by: NJuri Lelli <juri.lelli@arm.com>
Signed-off-by: NWanpeng Li <wanpeng.li@linux.intel.com>
Signed-off-by: NPeter Zijlstra (Intel) <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1427411315-4298-1-git-send-email-wanpeng.li@linux.intel.comSigned-off-by: NIngo Molnar <mingo@kernel.org>

Hotplug operations are destructive w.r.t. cpusets. In case such an
operation is performed on a CPU belonging to an exlusive cpuset, the
DL bandwidth information associated with the corresponding root
domain is gone even if the operation fails (in sched_cpu_inactive()).

For this reason we need to move the check we currently have in
sched_cpu_inactive() to cpuset_cpu_inactive() to prevent useless
cpusets reconfiguration in the CPU_DOWN_FAILED path.
Signed-off-by: NJuri Lelli <juri.lelli@arm.com>
Signed-off-by: NPeter Zijlstra (Intel) <peterz@infradead.org>
Cc: Juri Lelli <juri.lelli@gmail.com>
Link: http://lkml.kernel.org/r/1427792017-7356-2-git-send-email-juri.lelli@arm.comSigned-off-by: NIngo Molnar <mingo@kernel.org>

dl_task_timer() may fire on a different rq from where a task was removed
after throttling. Since the call path is:

  dl_task_timer() ->
    enqueue_task_dl() ->
      enqueue_dl_entity() ->
        replenish_dl_entity()

and replenish_dl_entity() uses dl_se's rq, we can't use current's rq
in dl_task_timer(), but we need to lock the task's previous one.
Tested-by: NWanpeng Li <wanpeng.li@linux.intel.com>
Signed-off-by: NJuri Lelli <juri.lelli@arm.com>
Signed-off-by: NPeter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: NKirill Tkhai <ktkhai@parallels.com>
Cc: Juri Lelli <juri.lelli@gmail.com>
Fixes: 3960c8c0 ("sched: Make dl_task_time() use task_rq_lock()")
Link: http://lkml.kernel.org/r/1427792017-7356-1-git-send-email-juri.lelli@arm.comSigned-off-by: NIngo Molnar <mingo@kernel.org>

Obviously, 'rq' is not used in these two functions, therefore,
there is no reason for it to be passed as an argument.
Signed-off-by: NAbel Vesa <abelvesa@gmail.com>
Signed-off-by: NPeter Zijlstra (Intel) <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1425383427-26244-1-git-send-email-abelvesa@gmail.comSigned-off-by: NIngo Molnar <mingo@kernel.org>

One version of sched_rt_global_constaints() (the !rt-cgroup one)
changes state, therefore if we fail the later sched_dl_global_constraints()
call the state is left in an inconsistent state.

Fix this by changing the order of the calls.
Signed-off-by: NWanpeng Li <wanpeng.li@linux.intel.com>
[ Improved the changelog. ]
Signed-off-by: NPeter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: NJuri Lelli <juri.lelli@arm.com>
Link: http://lkml.kernel.org/r/1426590931-4639-2-git-send-email-wanpeng.li@linux.intel.comSigned-off-by: NIngo Molnar <mingo@kernel.org>

Since commit 40767b0d ("sched/deadline: Fix deadline parameter
modification handling") we clear the thottled state when switching
from a dl task, therefore we should never find it set in switching to
a dl task.
Signed-off-by: NWanpeng Li <wanpeng.li@linux.intel.com>
[ Improved the changelog. ]
Signed-off-by: NPeter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: NJuri Lelli <juri.lelli@arm.com>
Link: http://lkml.kernel.org/r/1426590931-4639-1-git-send-email-wanpeng.li@linux.intel.comSigned-off-by: NIngo Molnar <mingo@kernel.org>

When a CPU is kicked to do nohz idle balancing, it wakes up to do load
balancing on itself, followed by load balancing on behalf of idle CPUs.
But it may end up with load after the load balancing attempt on itself.
This aborts nohz idle balancing. As a result several idle CPUs are left
without tasks till such a time that an ILB CPU finds it unfavorable to
pull tasks upon itself. This delays spreading of load across idle CPUs
and worse, clutters only a few CPUs with tasks.

The effect of the above problem was observed on an SMT8 POWER server
with 2 levels of numa domains. Busy loops equal to number of cores were
spawned. Since load balancing on fork/exec is discouraged across numa
domains, all busy loops would start on one of the numa domains. However
it was expected that eventually one busy loop would run per core across
all domains due to nohz idle load balancing. But it was observed that it
took as long as 10 seconds to spread the load across numa domains.

Further investigation showed that this was a consequence of the
following:

 1. An ILB CPU was chosen from the first numa domain to trigger nohz idle
    load balancing [Given the experiment, upto 6 CPUs per core could be
    potentially idle in this domain.]

 2. However the ILB CPU would call load_balance() on itself before
    initiating nohz idle load balancing.

 3. Given cores are SMT8, the ILB CPU had enough opportunities to pull
    tasks from its sibling cores to even out load.

 4. Now that the ILB CPU was no longer idle, it would abort nohz idle
    load balancing

As a result the opportunities to spread load across numa domains were
lost until such a time that the cores within the first numa domain had
equal number of tasks among themselves.  This is a pretty bad scenario,
since the cores within the first numa domain would have as many as 4
tasks each, while cores in the neighbouring numa domains would all
remain idle.

Fix this, by checking if a CPU was woken up to do nohz idle load
balancing, before it does load balancing upon itself. This way we allow
idle CPUs across the system to do load balancing which results in
quicker spread of load, instead of performing load balancing within the
local sched domain hierarchy of the ILB CPU alone under circumstances
such as above.
Signed-off-by: NPreeti U Murthy <preeti@linux.vnet.ibm.com>
Signed-off-by: NPeter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: NJason Low <jason.low2@hp.com>
Cc: benh@kernel.crashing.org
Cc: daniel.lezcano@linaro.org
Cc: efault@gmx.de
Cc: iamjoonsoo.kim@lge.com
Cc: morten.rasmussen@arm.com
Cc: pjt@google.com
Cc: riel@redhat.com
Cc: srikar@linux.vnet.ibm.com
Cc: svaidy@linux.vnet.ibm.com
Cc: tim.c.chen@linux.intel.com
Cc: vincent.guittot@linaro.org
Link: http://lkml.kernel.org/r/20150326130014.21532.17158.stgit@preeti.in.ibm.comSigned-off-by: NIngo Molnar <mingo@kernel.org>

Currently the freq invariant accounting (in
__update_entity_runnable_avg() and sched_rt_avg_update()) get the
scale factor from a weak function call, this means that even for archs
that default on their implementation the compiler cannot see into this
function and optimize the extra scaling math away.

This is sad, esp. since its a 64-bit multiplication which can be quite
costly on some platforms.

So replace the weak function with #ifdef and __always_inline goo. This
is not quite as nice from an arch support PoV but should at least
result in compile time errors if done wrong.
Signed-off-by: NPeter Zijlstra (Intel) <peterz@infradead.org>
Cc: Ben Segall <bsegall@google.com>
Cc: Morten.Rasmussen@arm.com
Cc: Paul Turner <pjt@google.com>
Cc: Vincent Guittot <vincent.guittot@linaro.org>
Cc: dietmar.eggemann@arm.com
Cc: efault@gmx.de
Cc: kamalesh@linux.vnet.ibm.com
Cc: nicolas.pitre@linaro.org
Cc: preeti@linux.vnet.ibm.com
Cc: riel@redhat.com
Link: http://lkml.kernel.org/r/20150323131905.GF23123@twins.programming.kicks-ass.netSigned-off-by: NIngo Molnar <mingo@kernel.org>

When a CPU is used to handle a lot of IRQs or some RT tasks, the remaining
capacity for CFS tasks can be significantly reduced. Once we detect such
situation by comparing cpu_capacity_orig and cpu_capacity, we trig an idle
load balance to check if it's worth moving its tasks on an idle CPU.

It's worth trying to move the task before the CPU is fully utilized to
minimize the preemption by irq or RT tasks.

Once the idle load_balance has selected the busiest CPU, it will look for an
active load balance for only two cases:

  - There is only 1 task on the busiest CPU.

  - We haven't been able to move a task of the busiest rq.

A CPU with a reduced capacity is included in the 1st case, and it's worth to
actively migrate its task if the idle CPU has got more available capacity for
CFS tasks. This test has been added in need_active_balance.

As a sidenote, this will not generate more spurious ilb because we already
trig an ilb if there is more than 1 busy cpu. If this cpu is the only one that
has a task, we will trig the ilb once for migrating the task.

The nohz_kick_needed function has been cleaned up a bit while adding the new
test

env.src_cpu and env.src_rq must be set unconditionnally because they are used
in need_active_balance which is called even if busiest->nr_running equals 1
Signed-off-by: NVincent Guittot <vincent.guittot@linaro.org>
Signed-off-by: NPeter Zijlstra (Intel) <peterz@infradead.org>
Cc: Morten.Rasmussen@arm.com
Cc: dietmar.eggemann@arm.com
Cc: efault@gmx.de
Cc: kamalesh@linux.vnet.ibm.com
Cc: linaro-kernel@lists.linaro.org
Cc: nicolas.pitre@linaro.org
Cc: preeti@linux.vnet.ibm.com
Cc: riel@redhat.com
Link: http://lkml.kernel.org/r/1425052454-25797-12-git-send-email-vincent.guittot@linaro.orgSigned-off-by: NIngo Molnar <mingo@kernel.org>

Add the SD_PREFER_SIBLING flag for SMT level in order to ensure that
the scheduler will place at least one task per core.
Signed-off-by: NVincent Guittot <vincent.guittot@linaro.org>
Signed-off-by: NPeter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: NPreeti U. Murthy <preeti@linux.vnet.ibm.com>
Cc: Morten.Rasmussen@arm.com
Cc: dietmar.eggemann@arm.com
Cc: efault@gmx.de
Cc: kamalesh@linux.vnet.ibm.com
Cc: linaro-kernel@lists.linaro.org
Cc: nicolas.pitre@linaro.org
Cc: riel@redhat.com
Link: http://lkml.kernel.org/r/1425052454-25797-11-git-send-email-vincent.guittot@linaro.orgSigned-off-by: NIngo Molnar <mingo@kernel.org>