If the cpufreq driver hasn't set the CPUFREQ_HAVE_GOVERNOR_PER_POLICY
flag, then the kernel will crash on accessing sysfs files for the sched
governor.
CPUFreq governors we can have the governor specific sysfs files in two
places:
A. /sys/devices/system/cpu/cpuX/cpufreq/<governor>
B. /sys/devices/system/cpu/cpufreq/<governor>
The case A. is for governor per policy case, where we can control the
governor tunables for each policy separately. The case B. is for system
wide tunable values.
The schedfreq governor only implements the case A. and not B. The sysfs
files in case B will still be present in
/sys/devices/system/cpu/cpufreq/<governor>, but accessing them will
crash kernel as the governor doesn't support that.
Moreover the sched governor is pretty new and will be used only for the
ARM platforms and there is no need to support the case B at all.
Hence use policy->kobj instead of get_governor_parent_kobj(), so that we
always create the sysfs files in path A.
Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
The implementation is utterly broken, resulting in all processes being
allows to move tasks between sets (as long as they have access to the
"tasks" attribute), and upstream is heading towards checking only
capability anyway, so let's get rid of this code.
BUG=b:31790445,chromium:647994
TEST=Boot android container, examine logcat
Change-Id: I2f780a5992c34e52a8f2d0b3557fc9d490da2779
Signed-off-by: Dmitry Torokhov <dtor@chromium.org>
Reviewed-on: https://chromium-review.googlesource.com/394967
Reviewed-by: Ricky Zhou <rickyz@chromium.org>
Reviewed-by: John Stultz <john.stultz@linaro.org>
The ENERGY_AWARE sched feature flag cannot be set unless
CONFIG_SCHED_DEBUG is enabled.
So this patch allows the flag to default to true at build time
if the config is set.
Change-Id: I8835a571fdb7a8f8ee6a54af1e11a69f3b5ce8e6
Signed-off-by: John Stultz <john.stultz@linaro.org>
It will cause deadlock and while(1) if call printk while schedule is in
progress. The block state like as below:
cpu0(hold the console sem):
printk->console_unlock->up_sem->spin_lock(&sem->lock)->wake_up_process(cpu1)
->try_to_wake_up(cpu1)->while(p->on_cpu).
cpu1(request console sem):
console_lock->down_sem->schedule->idle_banlance->update_cpu_capacity->
printk->console_trylock->spin_lock(&sem->lock).
p->on_cpu will be 1 forever, because the task is still running on cpu1,
so cpu0 is blocked in while(p->on_cpu), but cpu1 could not get
spin_lock(&sem->lock), it is blocked too, it means the task will running
on cpu1 forever.
Signed-off-by: Caesar Wang <wxt@rock-chips.com>
On at least one platform, occasionally the timer providing the wallclock
was able to be reset/go backwards for at least some time after wakeup.
Accept that this might happen and warn the first time, but otherwise just
carry on.
Change-Id: Id3164477ba79049561af7f0889cbeebc199ead4e
Signed-off-by: Chris Redpath <chris.redpath@arm.com>
commit 135e8c9250dd5c8c9aae5984fde6f230d0cbfeaf upstream.
The origin of the issue I've seen is related to
a missing memory barrier between check for task->state and
the check for task->on_rq.
The task being woken up is already awake from a schedule()
and is doing the following:
do {
schedule()
set_current_state(TASK_(UN)INTERRUPTIBLE);
} while (!cond);
The waker, actually gets stuck doing the following in
try_to_wake_up():
while (p->on_cpu)
cpu_relax();
Analysis:
The instance I've seen involves the following race:
CPU1 CPU2
while () {
if (cond)
break;
do {
schedule();
set_current_state(TASK_UN..)
} while (!cond);
wakeup_routine()
spin_lock_irqsave(wait_lock)
raw_spin_lock_irqsave(wait_lock) wake_up_process()
} try_to_wake_up()
set_current_state(TASK_RUNNING); ..
list_del(&waiter.list);
CPU2 wakes up CPU1, but before it can get the wait_lock and set
current state to TASK_RUNNING the following occurs:
CPU3
wakeup_routine()
raw_spin_lock_irqsave(wait_lock)
if (!list_empty)
wake_up_process()
try_to_wake_up()
raw_spin_lock_irqsave(p->pi_lock)
..
if (p->on_rq && ttwu_wakeup())
..
while (p->on_cpu)
cpu_relax()
..
CPU3 tries to wake up the task on CPU1 again since it finds
it on the wait_queue, CPU1 is spinning on wait_lock, but immediately
after CPU2, CPU3 got it.
CPU3 checks the state of p on CPU1, it is TASK_UNINTERRUPTIBLE and
the task is spinning on the wait_lock. Interestingly since p->on_rq
is checked under pi_lock, I've noticed that try_to_wake_up() finds
p->on_rq to be 0. This was the most confusing bit of the analysis,
but p->on_rq is changed under runqueue lock, rq_lock, the p->on_rq
check is not reliable without this fix IMHO. The race is visible
(based on the analysis) only when ttwu_queue() does a remote wakeup
via ttwu_queue_remote. In which case the p->on_rq change is not
done uder the pi_lock.
The result is that after a while the entire system locks up on
the raw_spin_irqlock_save(wait_lock) and the holder spins infintely
Reproduction of the issue:
The issue can be reproduced after a long run on my system with 80
threads and having to tweak available memory to very low and running
memory stress-ng mmapfork test. It usually takes a long time to
reproduce. I am trying to work on a test case that can reproduce
the issue faster, but thats work in progress. I am still testing the
changes on my still in a loop and the tests seem OK thus far.
Big thanks to Benjamin and Nick for helping debug this as well.
Ben helped catch the missing barrier, Nick caught every missing
bit in my theory.
Signed-off-by: Balbir Singh <bsingharora@gmail.com>
[ Updated comment to clarify matching barriers. Many
architectures do not have a full barrier in switch_to()
so that cannot be relied upon. ]
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Alexey Kardashevskiy <aik@ozlabs.ru>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Nicholas Piggin <nicholas.piggin@gmail.com>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/e02cce7b-d9ca-1ad0-7a61-ea97c7582b37@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Conflicts:
in fs/proc/task_mmu.c:
looks like vma_get_anon_name() want have a name for anonymous
vma when there is no name used in vma. commit: 586278d78b
The name show is after any other names, so it maybe covered.
but anyway, it just a show here.
[ Upstream commit 1dff76b92f69051e579bdc131e01500da9fa2a91 ]
The following message can be observed on the Ubuntu v3.13.0-65 with KASan
backported:
==================================================================
BUG: KASan: use after free in task_numa_find_cpu+0x64c/0x890 at addr ffff880dd393ecd8
Read of size 8 by task qemu-system-x86/3998900
=============================================================================
BUG kmalloc-128 (Tainted: G B ): kasan: bad access detected
-----------------------------------------------------------------------------
INFO: Allocated in task_numa_fault+0xc1b/0xed0 age=41980 cpu=18 pid=3998890
__slab_alloc+0x4f8/0x560
__kmalloc+0x1eb/0x280
task_numa_fault+0xc1b/0xed0
do_numa_page+0x192/0x200
handle_mm_fault+0x808/0x1160
__do_page_fault+0x218/0x750
do_page_fault+0x1a/0x70
page_fault+0x28/0x30
SyS_poll+0x66/0x1a0
system_call_fastpath+0x1a/0x1f
INFO: Freed in task_numa_free+0x1d2/0x200 age=62 cpu=18 pid=0
__slab_free+0x2ab/0x3f0
kfree+0x161/0x170
task_numa_free+0x1d2/0x200
finish_task_switch+0x1d2/0x210
__schedule+0x5d4/0xc60
schedule_preempt_disabled+0x40/0xc0
cpu_startup_entry+0x2da/0x340
start_secondary+0x28f/0x360
Call Trace:
[<ffffffff81a6ce35>] dump_stack+0x45/0x56
[<ffffffff81244aed>] print_trailer+0xfd/0x170
[<ffffffff8124ac36>] object_err+0x36/0x40
[<ffffffff8124cbf9>] kasan_report_error+0x1e9/0x3a0
[<ffffffff8124d260>] kasan_report+0x40/0x50
[<ffffffff810dda7c>] ? task_numa_find_cpu+0x64c/0x890
[<ffffffff8124bee9>] __asan_load8+0x69/0xa0
[<ffffffff814f5c38>] ? find_next_bit+0xd8/0x120
[<ffffffff810dda7c>] task_numa_find_cpu+0x64c/0x890
[<ffffffff810de16c>] task_numa_migrate+0x4ac/0x7b0
[<ffffffff810de523>] numa_migrate_preferred+0xb3/0xc0
[<ffffffff810e0b88>] task_numa_fault+0xb88/0xed0
[<ffffffff8120ef02>] do_numa_page+0x192/0x200
[<ffffffff81211038>] handle_mm_fault+0x808/0x1160
[<ffffffff810d7dbd>] ? sched_clock_cpu+0x10d/0x160
[<ffffffff81068c52>] ? native_load_tls+0x82/0xa0
[<ffffffff81a7bd68>] __do_page_fault+0x218/0x750
[<ffffffff810c2186>] ? hrtimer_try_to_cancel+0x76/0x160
[<ffffffff81a6f5e7>] ? schedule_hrtimeout_range_clock.part.24+0xf7/0x1c0
[<ffffffff81a7c2ba>] do_page_fault+0x1a/0x70
[<ffffffff81a772e8>] page_fault+0x28/0x30
[<ffffffff8128cbd4>] ? do_sys_poll+0x1c4/0x6d0
[<ffffffff810e64f6>] ? enqueue_task_fair+0x4b6/0xaa0
[<ffffffff810233c9>] ? sched_clock+0x9/0x10
[<ffffffff810cf70a>] ? resched_task+0x7a/0xc0
[<ffffffff810d0663>] ? check_preempt_curr+0xb3/0x130
[<ffffffff8128b5c0>] ? poll_select_copy_remaining+0x170/0x170
[<ffffffff810d3bc0>] ? wake_up_state+0x10/0x20
[<ffffffff8112a28f>] ? drop_futex_key_refs.isra.14+0x1f/0x90
[<ffffffff8112d40e>] ? futex_requeue+0x3de/0xba0
[<ffffffff8112e49e>] ? do_futex+0xbe/0x8f0
[<ffffffff81022c89>] ? read_tsc+0x9/0x20
[<ffffffff8111bd9d>] ? ktime_get_ts+0x12d/0x170
[<ffffffff8108f699>] ? timespec_add_safe+0x59/0xe0
[<ffffffff8128d1f6>] SyS_poll+0x66/0x1a0
[<ffffffff81a830dd>] system_call_fastpath+0x1a/0x1f
As commit 1effd9f193 ("sched/numa: Fix unsafe get_task_struct() in
task_numa_assign()") points out, the rcu_read_lock() cannot protect the
task_struct from being freed in the finish_task_switch(). And the bug
happens in the process of calculation of imp which requires the access of
p->numa_faults being freed in the following path:
do_exit()
current->flags |= PF_EXITING;
release_task()
~~delayed_put_task_struct()~~
schedule()
...
...
rq->curr = next;
context_switch()
finish_task_switch()
put_task_struct()
__put_task_struct()
task_numa_free()
The fix here to get_task_struct() early before end of dst_rq->lock to
protect the calculation process and also put_task_struct() in the
corresponding point if finally the dst_rq->curr somehow cannot be
assigned.
Additional credit to Liang Chen who helped fix the error logic and add the
put_task_struct() to the place it missed.
Signed-off-by: Gavin Guo <gavin.guo@canonical.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Hugh Dickins <hughd@google.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rik van Riel <riel@redhat.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: jay.vosburgh@canonical.com
Cc: liang.chen@canonical.com
Link: http://lkml.kernel.org/r/1453264618-17645-1-git-send-email-gavin.guo@canonical.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Sasha Levin <alexander.levin@verizon.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
The SchedTune tasks accounting is used to identify how many tasks are in
a boostgroup and thus to bias the selection of an OPP based on the
maximum boost value of the active boostgroups.
The current implementation however update the accounting after CPU
capacity has been update. This has two effects:
a) when we enqueue a boosted task, we do not immediately boost its CPU
b) when we dequeue a boosted task, we can keep a CPU boosted even if not
required
This patch change the order of the SchedTune accounting and SchedFreq
updated to ensure to have always an updated representation of which
boosted tasks are runnable on a CPU before updating its capacity.
Reported-by: Leo Yan <leo.yan@linaro.org>
Signed-off-by: Patrick Bellasi <patrick.bellasi@arm.com>
The previous patch:
e7ce26f - FIXUP: sched/tune: fix accounting for runnable tasks
squashed together patches of a series to fix SchedTune's accounting
issues. However, in the consolidation and cleanup of the series to merge
in the Android Common Kernel, we somehow missed a couple of important
changes:
1) the schedtune_exit function is not more required, because e7ce26f
fixes accounting of exiting tasks in a different way
2) the schedtune_initialized flag was not set at the end of
scheddtune_init_cgroup() thus failing to enabled SchedTune at boot.
This patch thus is to be considered an integration of e7ce26f.
Signed-off-by: Patrick Bellasi <patrick.bellasi@arm.com>
[jstultz: Cherry-picked from android-3.18. It should be noted that
some of this patch was already applied in the 4.4 patches (schedtune_exit
doesn't exist for example), but this patch just ensures things are totally
synced up]
Signed-off-by: John Stultz <john.stultz@linaro.org>
Use do_div() instead of "/" operator to fix undefined references to
"__aeabi_uldivmod" build error for ARCH=arm.
Also in TP_fast_assign(), along with do_div() usage, replace "," with
";" which would have resulted in a syntax error (!), because
'#define TP_fast_assign(args...) args' would have stripped off the ","
and left white space between these two assignments after CPP phase.
Signed-off-by: Amit Pundir <amit.pundir@linaro.org>
[jstultz: Cherry-picked from common/android-3.18]
Signed-off-by: John Stultz <john.stultz@linaro.org>
Include clocksource/arm_arch_timer.h to fix implicit function
declaration of ‘arch_timer_read_counter’ build error for ARCH=arm.
Signed-off-by: Amit Pundir <amit.pundir@linaro.org>
[jstultz: Cherry-picked from common/android-3.18]
Signed-off-by: John Stultz <john.stultz@linaro.org>
Part of the responsibility of the update_sg_lb_stats() function is to
update the idle_cpus statistical counter in struct sg_lb_stats. This
check is done by calling idle_cpu(). The idle_cpu() function, in
turn, checks a number of fields within the run queue structure such
as rq->curr and rq->nr_running.
With the current layout of the run queue structure, rq->curr and
rq->nr_running are in separate cachelines. The rq->curr variable is
checked first followed by nr_running. As nr_running is also accessed
by update_sg_lb_stats() earlier, it makes no sense to load another
cacheline when nr_running is not 0 as idle_cpu() will always return
false in this case.
This patch eliminates this redundant cacheline load by checking the
cached nr_running before calling idle_cpu().
Signed-off-by: Waiman Long <Waiman.Long@hpe.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Douglas Hatch <doug.hatch@hpe.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Scott J Norton <scott.norton@hpe.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/1448478580-26467-2-git-send-email-Waiman.Long@hpe.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
(cherry picked from commit a426f99c91d1036767a7819aaaba6bd3191b7f06)
Signed-off-by: Javi Merino <javi.merino@arm.com>
Two fixups that have been reported on LKML. The next version of
scheduler-driver cpu frequency selection patch set should include
these fixes and we can drop this patch then.
Signed-off-by: Ricky Liang <jcliang@chromium.org>
Change-Id: Ia2f8b5c0dd5dac06580256eeb4b259929688af68
This may be useful for detecting and debugging RT throttling issues.
Change-Id: I5807a897d11997d76421c1fcaa2918aad988c6c9
Signed-off-by: Matt Wagantall <mattw@codeaurora.org>
[rameezmustafa@codeaurora.org]: Port to msm-3.18]
Signed-off-by: Syed Rameez Mustafa <rameezmustafa@codeaurora.org>
[jstultz: forwardported to 4.4]
Signed-off-by: John Stultz <john.stultz@linaro.org>
Existing debug prints do not provide any clues about which tasks
may have triggered RT throttling. Print the names and PIDs of
all tasks on the throttled rt_rq to help narrow down the source
of the problem.
Change-Id: I180534c8a647254ed38e89d0c981a8f8bccd741c
Signed-off-by: Matt Wagantall <mattw@codeaurora.org>
[rameezmustafa@codeaurora.org]: Port to msm-3.18]
Signed-off-by: Syed Rameez Mustafa <rameezmustafa@codeaurora.org>
Because sched_setscheduler() checks p->flags & PF_NO_SETAFFINITY
without locks, a caller might observe an old value and race with the
set_cpus_allowed_ptr() call from __kthread_bind() and effectively undo
it:
__kthread_bind()
do_set_cpus_allowed()
<SYSCALL>
sched_setaffinity()
if (p->flags & PF_NO_SETAFFINITIY)
set_cpus_allowed_ptr()
p->flags |= PF_NO_SETAFFINITY
Fix the bug by putting everything under the regular scheduler locks.
This also closes a hole in the serialization of task_struct::{nr_,}cpus_allowed.
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Tejun Heo <tj@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: dedekind1@gmail.com
Cc: juri.lelli@arm.com
Cc: mgorman@suse.de
Cc: riel@redhat.com
Cc: rostedt@goodmis.org
Link: http://lkml.kernel.org/r/20150515154833.545640346@infradead.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
(cherry picked from commit 25834c73f9)
Signed-off-by: Punit Agrawal <punit.agrawal@arm.com>
BUG=chrome-os-partner:44828
TEST=Boot kernel on Oak.
TEST=smaug-release and strago-release trybots.
Change-Id: Id3c898c5ee1a22ed704e83f2ecf5f78199280d38
Reviewed-on: https://chromium-review.googlesource.com/321264
Commit-Ready: Ricky Liang <jcliang@chromium.org>
Tested-by: Ricky Liang <jcliang@chromium.org>
Reviewed-by: Ricky Liang <jcliang@chromium.org>
Conflicts:
kernel/sched/core.c
This CL separates the notion of boost and prefer_idle schedtune
attributes in cpu selection. Today only top-app
tasks are boosted. The CPU selection is slightly tweaked such that
higher order cpus are preferred only for boosted tasks (top-app) and the
rest would be skewed towards lower order cpus.
This avoids starvation issues for fg tasks when interacting with high
priority top-app tasks (a problem often seen in the case of system_server).
bug: 30245369
bug: 30292998
Change-Id: I0377e00893b9f6586eec55632a265518fd2fa8a1
Conflicts:
kernel/sched/fair.c
Currently the vmstat updater is not deferrable as a result of commit
ba4877b9ca ("vmstat: do not use deferrable delayed work for
vmstat_update"). This in turn can cause multiple interruptions of the
applications because the vmstat updater may run at
Make vmstate_update deferrable again and provide a function that folds
the differentials when the processor is going to idle mode thus
addressing the issue of the above commit in a clean way.
Note that the shepherd thread will continue scanning the differentials
from another processor and will reenable the vmstat workers if it
detects any changes.
Change-Id: Idf256cfacb40b4dc8dbb6795cf06b34e8fec7a06
Fixes: ba4877b9ca ("vmstat: do not use deferrable delayed work for vmstat_update")
Signed-off-by: Christoph Lameter <cl@linux.com>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Tetsuo Handa <penguin-kernel@i-love.sakura.ne.jp>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Git-repo: git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
Git-commit: 0eb77e9880321915322d42913c3b53241739c8aa
[shashim@codeaurora.org: resolve minor merge conflicts]
Signed-off-by: Shiraz Hashim <shashim@codeaurora.org>
[jstultz: fwdport to 4.4]
Signed-off-by: John Stultz <john.stultz@linaro.org>
When a task leaves a rq because it is migrated away it carries its
utilization with him. In this case and OPP update on the src rq might be
needed. The corresponding update at dst rq will happen at enqueue time.
Change-Id: I22754a43760fc8d22a488fe15044af93787ea7a8
sched/fair: Fix uninitialised variable in idle_balance
compiler warned, looks legit.
Signed-off-by: Chris Redpath <chris.redpath@arm.com>
cpufreq_sched_limits (called when CPUFREQ_GOV_LIMITS event happens)
bails out if policy->rwsem is already locked. However, that rwsem is
always guaranteed to be locked when we get here after a thermal
throttling event happens:
th_throttling ->
cpufreq_update_policy()
...
down_write(&policy->rwsem);
...
cpufreq_set_policy() ->
...
__cpufreq_governor(policy, CPUFREQ_GOV_LIMITS); ->
cpufreq_sched_limits()
...
if (!down_write_trylock(&policy->rwsem))
return; <-- BAIL OUT!
So, we don't currently react immediately to thermal capping event (even
if reaction is still quick in practice, ~1ms, as lots of events are likely
to trigger a frequency selection on a high loaded system).
Fix this bug by removing the bail out condition.
While we are at it we also slightly change handling of the new limits by
clamping the last requested_freq between policy's max and min. Doing so
gives us the oppurtunity to correctly restore the last requested
frequency as soon as a thermal unthrottling event happens.
bug: 30481949
Change-Id: I3c13e818f238c1ffa66b34e419e8b87314b57427
Suggested-by: Javi Merino <javi.merino@arm.com>
Signed-off-by: Juri Lelli <juri.lelli@arm.com>
Signed-off-by: Srinath Sridharan <srinathsr@google.com>
[jstultz: fwdported to 4.4]
Signed-off-by: John Stultz <john.stultz@linaro.org>
When idle cpus cannot be found for Top-app/FG tasks, the cpu selection
algorithm picks a cpu with lowest OPP amongst the busy cpus as a second
choice.
Mitigates the "runnable" time for ui and render threads.
bug: 30481949
bug: 30342017
bug: 30508678
Change-Id: I5a97e31d33284895c0fa6f6942102713ee576d77
SchedTune needs to walk the scheduling domains to compute the energy
normalization constants used for PE space filtering. To build such
constants we need the energy model data for each CPU in the system.
However, by walking the SDs as a late initcall stage, the userspace has
been already initialized and it could happen that some CPUs are
hotplugged out.
For example, this could happen if a user-space thermal manager daemon
detects that CPUs are to much hot during the boot process.
To avoid such a race condition we can anticipate the SchedTune
initialization code to be a postcore_initicall. This allows to keep the
SchedTune initialization code as simple as an initcall while still safely
relaying on SDs provided data.
Such calls are executed before user-space is initialized and thus, apart
from the case of unlucky early-init kernel space generated hotplugs,
this solution should be safe enough to get all the data we need.
Signed-off-by: Patrick Bellasi <patrick.bellasi@arm.com>
[jstultz: fwdported to 4.4]
Signed-off-by: John Stultz <john.stultz@linaro.org>
Hint to enable biasing of tasks towards idle cpus, even when a given
task is negatively boosted. The mechanism allows upto 20% reduction in
camera power without hurting performance.
bug: 28312446
Change-Id: I97ea5671aa1e6bcb165408b41e17bc82e41c2c9e
If cpus are busy, the cpu selection algorithm was favoring
cpus with lower capacity. This can result in uneven packing
since there will be a bias toward the same cpu until there
is a capacity change. Instead use the utilization so there
is immediate feedback as tasks are assigned
BUG: 30115868
Change-Id: I0ac7ae3ab5d8f2f5a5838c29bb6da2c3e8ef44e8
Bug: 29000863
Signed-off-by: albert.zl_huang <albert.zl_huang@htc.com>
Change-Id: I2b5a28b0a9edb31bdaa1ca2310397dd2f36f6c23
Updated to use arch_timer_read_counter() as arch_counter_get_cntvct
doesn't exist in this kernel.
Signed-off-by: Chris Redpath <chris.redpath@arm.com>
The current kernel allows to use either PELT or WALT to track CPUs utilizations.
One of the main differences between the two approaches is that PELT
tracks only utilization of SCHED_OTHER classes while WALT tracks all tasks
with a single signal.
The current sched_freq_tick does not make this distinction and, when WALT
is in use, we end up adding multiple time the contribution related to
the RT and DL classes. This patch fixes this issue by:
1. providing two different code paths for PELT and WALT, thus granting that
when we switch to PELT we get the original behaviour based on the assumption
that class aggregations is done underneath by SchedFreq.
2. avoiding the double accounting of DL and RT workloads, when WALT is in use,
by just adding a margin to the original WALT signal when we need to check
if the CFS capacity has to be increased.
Change-Id: I7326fd50e868e97fb5e12351917e9d2969bfdae7
Signed-off-by: Patrick Bellasi <patrick.bellasi@arm.com>
During scheduler tick handling, the frequency was being set to
max-freq if the current frequency is less than the current
utilization. Change to just request "right" frequency instead
of max.
BUG: 29871410
Change-Id: I6fe65b14413da44b1520ba116f72320083eb92f8
The CPU utilization reported when WALT is in use already tracks the
contributions due to RT and DL workloads. However, SchedFreq exposes
different capacity update functions, one for each class, and does classes
utilization internally at update_cpu_capacity_request() call time.
This patch ensures that when WALT is in use, the:
cpu_sched_capacity_reqs::cfs
value is tracking just the load generated by SCHED_OTHER tasks.
Change-Id: Ibd9c9a10874a1d91f62477034548f7664e57cd6a
Signed-off-by: Patrick Bellasi <patrick.bellasi@arm.com>
use a window based view of time in order to track task
demand and CPU utilization in the scheduler.
Window Assisted Load Tracking (WALT) implementation credits:
Srivatsa Vaddagiri, Steve Muckle, Syed Rameez Mustafa, Joonwoo Park,
Pavan Kumar Kondeti, Olav Haugan
2016-03-06: Integration with EAS/refactoring by Vikram Mulukutla
and Todd Kjos
Change-Id: I21408236836625d4e7d7de1843d20ed5ff36c708
Includes fixes for issues:
eas/walt: Use walt_ktime_clock() instead of ktime_get_ns() to avoid a
race resulting in watchdog resets
BUG: 29353986
Change-Id: Ic1820e22a136f7c7ebd6f42e15f14d470f6bbbdb
Handle walt accounting anomoly during resume
During resume, there is a corner case where on wakeup, a task's
prev_runnable_sum can go negative. This is a workaround that
fixes the condition and warns (instead of crashing).
BUG: 29464099
Change-Id: I173e7874324b31a3584435530281708145773508
Signed-off-by: Todd Kjos <tkjos@google.com>
Signed-off-by: Srinath Sridharan <srinathsr@google.com>
Signed-off-by: Juri Lelli <juri.lelli@arm.com>
[jstultz: fwdported to 4.4]
Signed-off-by: John Stultz <john.stultz@linaro.org>
The current definition of the Performance Boost (PB) and Performance Constraint
(PC) regions is has two main issues:
1) in the computation of the boost index we overflow the thresholds_gains
table for boost=100
2) the two cuts had _NOT_ the same ratio
The last point means that when boost=0 we do _not_ have a "standard" EAS
behaviour, i.e. accepting all candidate which decrease energy regardless
of their impact on performances. Instead, we accept only schedule candidate
which are in the Optimal region, i.e. decrease energy while increasing
performances.
This behaviour can have a negative impact also on CPU selection policies
which tries to spread tasks to reduce latencies. Indeed, for example
we could end up rejecting a schedule candidate which want to move a task
from a congested CPU to an idle one while, specifically in the case where
the target CPU will be running on a lower OPP.
This patch fixes these two issues by properly clamping the boost value
in the appropriate range to compute the threshold indexes as well as
by using the same threshold index for both cuts.
Signed-off-by: Patrick Bellasi <patrick.bellasi@arm.com>
Signed-off-by: Srinath Sridharan <srinathsr@google.com>
sched/tune: fix update of threshold index for boost groups
When SchedTune is configured to work with CGroup mode, each time we update
the boost value of a group we do not update the threshed indexes for the
definition of the Performance Boost (PC) and Performance Constraint (PC)
region. This means that while the OPP boosting and CPU biasing selection
is working as expected, the __schedtune_accept_deltas function is always
using the initial values for these cuts.
This patch ensure that each time a new boost value is configured for a
boost group, the cuts for the PB and PC region are properly updated too.
Signed-off-by: Patrick Bellasi <patrick.bellasi@arm.com>
Signed-off-by: Srinath Sridharan <srinathsr@google.com>
sched/tune: update PC and PB cuts definition
The current definition of Performance Boost (PB) and Performance
Constraint (PC) cuts defines two "dead regions":
- up to 20% boost: we are in energy-reduction only mode, i.e.
accept all candidate which reduce energy
- over 70% boost: we are in performance-increase only mode, i.e.
accept only sched candidate which do not reduce performances
This patch uses a more fine grained configuration where these two "dead
regions" are reduced to: up to 10% and over 90%.
This should allow to have some boosting benefits starting from 10% boost
values as well as not being to much permissive starting from boost values
of 80%.
Suggested-by: Leo Yan <leo.yan@linaro.org>
Signed-off-by: Patrick Bellasi <patrick.bellasi@arm.com>
Signed-off-by: Srinath Sridharan <srinathsr@google.com>
bug: 28312446
Change-Id: Ia326c66521e38c98e7a7eddbbb7c437875efa1ba
Signed-off-by: Patrick Bellasi <patrick.bellasi@arm.com>
find_best_target CPU selection is biased towards lower CPU IDs. Bias
towards higher CPUs for boosted tasks. For boosted tasks unconditionally
use the idle CPU returned by find_best_target.
BUG: 29512132
Change-Id: I3d650051752163fcf3dc7909751d1fde3f9d17c0
Conflicts:
kernel/sched/fair.c
Contains:
sched/tune: fix accounting for runnable tasks (1/5)
The accounting for tasks into boost groups of different CPUs is currently
broken mainly because:
a) we do not properly track the change of boost group of a RUNNABLE task
b) there are race conditions between migration code and accounting code
This patch provides a fixes to ensure enqueue/dequeue
accounting also for throttled tasks.
Without this patch is can happen that a task is enqueued into a throttled
RQ thus not being accounted for the boosting of the corresponding RQ.
We could argue that a throttled task should not boost a CPU, however:
a) properly implementing CPU boosting considering throttled tasks will
increase a lot the complexity of the solution
b) it's not easy to quantify the benefits introduced by such a more
complex solution
Since task throttling requires the usage of the CFS bandwidth controller,
which is not widely used on mobile systems (at least not by Android kernels
so far), for the time being we go for the simple solution and boost also
for throttled RQs.
sched/tune: fix accounting for runnable tasks (2/5)
This patch provides the code required to enforce proper locking.
A per boost group spinlock has been added to grant atomic
accounting of tasks as well as to serialise enqueue/dequeue operations,
triggered by tasks migrations, with cgroups's attach/detach operations.
sched/tune: fix accounting for runnable tasks (3/5)
This patch adds cgroups {allow,can,cancel}_attach callbacks.
Since a task can be migrated between boost groups while it's running,
the CGroups's attach callbacks have been added to properly migrate
boost contributions of RUNNABLE tasks.
The RQ's lock is used to serialise enqueue/dequeue operations, triggered
by tasks migrations, with cgroups's attach/detach operations. While the
SchedTune's CPU lock is used to grant atrocity of the accounting within
the CPU.
NOTE: the current implementation does not allows a concurrent CPU migration
and CGroups change.
sched/tune: fix accounting for runnable tasks (4/5)
This fixes accounting for exiting tasks by adding a dedicated call early
in the do_exit() syscall, which disables SchedTune accounting as soon as a
task is flagged PF_EXITING.
This flag is set before the multiple dequeue/enqueue dance triggered
by cgroup_exit() which is useful only to inject useless tasks movements
thus increasing possibilities for race conditions with the migration code.
The schedtune_exit_task() call does the last dequeue of a task from its
current boost group. This is a solution more aligned with what happens in
mainline kernels (>v4.4) where the exit_cgroup does not move anymore a dying
task to the root control group.
sched/tune: fix accounting for runnable tasks (5/5)
To avoid accounting issues at startup, this patch disable the SchedTune
accounting until the required data structures have been properly
initialized.
Signed-off-by: Patrick Bellasi <patrick.bellasi@arm.com>
[jstultz: fwdported to 4.4]
Signed-off-by: John Stultz <john.stultz@linaro.org>
With the introduction of initialization function required to compute the
energy normalization constants from DTB at boot time, we have now a
late_initcall which is already used by SchedTune.
This patch consolidate within that function the other initialization
bits which was previously deferred to the first CGroup creation.
Signed-off-by: Patrick Bellasi <patrick.bellasi@arm.com>
[jstultz: fwdported to 4.4]
Signed-off-by: John Stultz <john.stultz@linaro.org>
The usage of conditional compiled code is discouraged in fair.c.
This patch clean up a bit fair.c by moving schedtune_{cpu.task}_boost
definitions into tune.h.
Signed-off-by: Patrick Bellasi <patrick.bellasi@arm.com>
The definition of the acceptance regions as well as the translation of
these regions into a payoff value was both wrong which turned out in:
a) a wrong definition of payoff for the performance boost region
b) a correct "by chance" definition of the payoff for the performance
constraint region (i.e. two sign errors together fixing the formula)
This patch provides a better description of the cut regions as well as
a fixed version of the payoff computations, which are now reduced to a
single formula usable for both cases.
Reported-by: Leo Yan <leo.yan@linaro.org>
Reviewed-by: Leo Yan <leo.yan@linaro.org>
Signed-off-by: Leo Yan <leo.yan@linaro.org>
Signed-off-by: Patrick Bellasi <patrick.bellasi@arm.com>
Change-Id: I164ee04ba98c3a776605f18cb65ee61b3e917939
Contains also:
eas/stune: schedtune cpu boost_max must be non-negative.
This is to avoid under-accounting cpu capacity which may
cause task stacking and frequency spikes.
Change-Id: Ie1c1cbd52a6edb77b4c15a830030aa748dff6f29
The energy normalization function is required to get the proper values
for the P-E space filtering function to work.
That normalization is part of the hot wakeup path and currently implemented
with a function call.
Moving the normalization function into fair.c allows the compiler to
further optimize that code by reducing overheads in the wakeup hot path.
Signed-off-by: Patrick Bellasi <patrick.bellasi@arm.com>
[jstultz: fwdported to 4.4]
Signed-off-by: John Stultz <john.stultz@linaro.org>
A boosted task needs to be scheduled on a CPU which can grant a minimum
capacity which is higher than its utilization.
However, a task can be allocated on a CPU which already provides an utilization
which is higher than the task boosted utilization itself.
Moreover, with the previous approach a task 100% boosted is not fitting any
CPU.
This patch makes use of the boosted task utilization just as a threashold
which defines the minimum capacity should be available on a CPU to host that
task.
Signed-off-by: Patrick Bellasi <patrick.bellasi@arm.com>
The choice of initial task load upon fork has a large influence
on CPU and OPP selection when scheduler-driven DVFS is in use.
Make this tuneable by adding a new sysctl "sched_initial_task_util".
If the sched governor is not used, the default remains at SCHED_LOAD_SCALE
Otherwise, the value from the sysctl is used. This defaults to 0.
Signed-off-by: "Todd Kjos <tkjos@google.com>"
EAS assumes that clusters with smaller capacity cores are more
energy-efficient. This may not be true on non-big-little devices,
so EAS can make incorrect cluster selections when finding a CPU
to wake. The "sched_is_big_little" hint can be used to cause a
cpu-based selection instead of cluster-based selection.
This change incorporates the addition of the sync hint enable patch
EAS did not honour synchronous wakeup hints, a new sysctl is
created to ask EAS to use this information when selecting a CPU.
The control is called "sched_sync_hint_enable".
Also contains:
EAS: sched/fair: for SMP bias toward idle core with capacity
For SMP devices, on wakeup bias towards idle cores that have capacity
vs busy devices that need a higher OPP
eas: favor idle cpus for boosted tasks
BUG: 29533997
BUG: 29512132
Change-Id: I0cc9a1b1b88fb52916f18bf2d25715bdc3634f9c
Signed-off-by: Juri Lelli <juri.lelli@arm.com>
Signed-off-by: Srinath Sridharan <srinathsr@google.com>
eas/sched/fair: Favoring busy cpus with low OPPs
BUG: 29533997
BUG: 29512132
Change-Id: I9305b3239698d64278db715a2e277ea0bb4ece79
Signed-off-by: Juri Lelli <juri.lelli@arm.com>
