Since commit '8a99b6833c88(sched: Move SCHED_DEBUG sysctl to debugfs)',
SCHED_DEBUG sysctls are moved to debugfs, so these extern sysctls in
include/linux/sched/sysctl.h are no longer needed for sysctl.c, even
some are no longer needed.
So move those extern sysctls that needed by kernel/sched/debug.c to
kernel/sched/sched.h, and remove others that are no longer needed.
Signed-off-by: Hailong Liu <liu.hailong6@zte.com.cn>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20210606115451.26745-1-liuhailongg6@163.com
Since CPU capacity asymmetry can stem purely from maximum frequency
differences (e.g. Pixel 1), a rebuild of the scheduler topology can be
issued upon loading cpufreq, see:
arch_topology.c::init_cpu_capacity_callback()
Turns out that if this rebuild happens *before* sched_debug_init() is
run (which is a late initcall), we end up messing up the sched_domain debug
directory: passing a NULL parent to debugfs_create_dir() ends up creating
the directory at the debugfs root, which in this case creates
/sys/kernel/debug/domains (instead of /sys/kernel/debug/sched/domains).
This currently doesn't happen on asymmetric systems which use cpufreq-scpi
or cpufreq-dt drivers, as those are loaded via
deferred_probe_initcall() (it is also a late initcall, but appears to be
ordered *after* sched_debug_init()).
Ionela has been working on detecting maximum frequency asymmetry via ACPI,
and that actually happens via a *device* initcall, thus before
sched_debug_init(), and causes the aforementionned debugfs mayhem.
One option would be to punt sched_debug_init() down to
fs_initcall_sync(). Preventing update_sched_domain_debugfs() from running
before sched_debug_init() appears to be the safer option.
Fixes: 3b87f136f8 ("sched,debug: Convert sysctl sched_domains to debugfs")
Signed-off-by: Valentin Schneider <valentin.schneider@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: http://lore.kernel.org/r/20210514095339.12979-1-ionela.voinescu@arm.com
The _sum and _avg values are in general sync together with the PELT
divider. They are however not always completely in perfect sync,
resulting in situations where _sum gets to zero while _avg stays
positive. Such situations are undesirable.
This comes from the fact that PELT will increase period_contrib, also
increasing the PELT divider, without updating _sum and _avg values to
stay in perfect sync where (_sum == _avg * divider). However, such PELT
change will never lower _sum, making it impossible to end up in a
situation where _sum is zero and _avg is not.
Therefore, we need to ensure that when subtracting load outside PELT,
that when _sum is zero, _avg is also set to zero. This occurs when
(_sum < _avg * divider), and the subtracted (_avg * divider) is bigger
or equal to the current _sum, while the subtracted _avg is smaller than
the current _avg.
Reported-by: Sachin Sant <sachinp@linux.vnet.ibm.com>
Reported-by: Naresh Kamboju <naresh.kamboju@linaro.org>
Signed-off-by: Odin Ugedal <odin@uged.al>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Vincent Guittot <vincent.guittot@linaro.org>
Tested-by: Sachin Sant <sachinp@linux.vnet.ibm.com>
Link: https://lore.kernel.org/r/20210624111815.57937-1-odin@uged.al
Currently the CPU capacity asymmetry detection, performed through
asym_cpu_capacity_level, tries to identify the lowest topology level
at which the highest CPU capacity is being observed, not necessarily
finding the level at which all possible capacity values are visible
to all CPUs, which might be bit problematic for some possible/valid
asymmetric topologies i.e.:
DIE [ ]
MC [ ][ ]
CPU [0] [1] [2] [3] [4] [5] [6] [7]
Capacity |.....| |.....| |.....| |.....|
L M B B
Where:
arch_scale_cpu_capacity(L) = 512
arch_scale_cpu_capacity(M) = 871
arch_scale_cpu_capacity(B) = 1024
In this particular case, the asymmetric topology level will point
at MC, as all possible CPU masks for that level do cover the CPU
with the highest capacity. It will work just fine for the first
cluster, not so much for the second one though (consider the
find_energy_efficient_cpu which might end up attempting the energy
aware wake-up for a domain that does not see any asymmetry at all)
Rework the way the capacity asymmetry levels are being detected,
allowing to point to the lowest topology level (for a given CPU), where
full set of available CPU capacities is visible to all CPUs within given
domain. As a result, the per-cpu sd_asym_cpucapacity might differ across
the domains. This will have an impact on EAS wake-up placement in a way
that it might see different range of CPUs to be considered, depending on
the given current and target CPUs.
Additionally, those levels, where any range of asymmetry (not
necessarily full) is being detected will get identified as well.
The selected asymmetric topology level will be denoted by
SD_ASYM_CPUCAPACITY_FULL sched domain flag whereas the 'sub-levels'
would receive the already used SD_ASYM_CPUCAPACITY flag. This allows
maintaining the current behaviour for asymmetric topologies, with
misfit migration operating correctly on lower levels, if applicable,
as any asymmetry is enough to trigger the misfit migration.
The logic there relies on the SD_ASYM_CPUCAPACITY flag and does not
relate to the full asymmetry level denoted by the sd_asym_cpucapacity
pointer.
Detecting the CPU capacity asymmetry is being based on a set of
available CPU capacities for all possible CPUs. This data is being
generated upon init and updated once CPU topology changes are being
detected (through arch_update_cpu_topology). As such, any changes
to identified CPU capacities (like initializing cpufreq) need to be
explicitly advertised by corresponding archs to trigger rebuilding
the data.
Additional -dflags- parameter, used when building sched domains, has
been removed as well, as the asymmetry flags are now being set directly
in sd_init.
Suggested-by: Peter Zijlstra <peterz@infradead.org>
Suggested-by: Valentin Schneider <valentin.schneider@arm.com>
Signed-off-by: Beata Michalska <beata.michalska@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Valentin Schneider <valentin.schneider@arm.com>
Reviewed-by: Dietmar Eggemann <dietmar.eggemann@arm.com>
Tested-by: Valentin Schneider <valentin.schneider@arm.com>
Link: https://lore.kernel.org/r/20210603140627.8409-3-beata.michalska@arm.com
Race detected between psi_trigger_destroy/create as shown below, which
cause panic by accessing invalid psi_system->poll_wait->wait_queue_entry
and psi_system->poll_timer->entry->next. Under this modification, the
race window is removed by initialising poll_wait and poll_timer in
group_init which are executed only once at beginning.
psi_trigger_destroy() psi_trigger_create()
mutex_lock(trigger_lock);
rcu_assign_pointer(poll_task, NULL);
mutex_unlock(trigger_lock);
mutex_lock(trigger_lock);
if (!rcu_access_pointer(group->poll_task)) {
timer_setup(poll_timer, poll_timer_fn, 0);
rcu_assign_pointer(poll_task, task);
}
mutex_unlock(trigger_lock);
synchronize_rcu();
del_timer_sync(poll_timer); <-- poll_timer has been reinitialized by
psi_trigger_create()
So, trigger_lock/RCU correctly protects destruction of
group->poll_task but misses this race affecting poll_timer and
poll_wait.
Fixes: 461daba06b ("psi: eliminate kthread_worker from psi trigger scheduling mechanism")
Co-developed-by: ziwei.dai <ziwei.dai@unisoc.com>
Signed-off-by: ziwei.dai <ziwei.dai@unisoc.com>
Co-developed-by: ke.wang <ke.wang@unisoc.com>
Signed-off-by: ke.wang <ke.wang@unisoc.com>
Signed-off-by: Zhaoyang Huang <zhaoyang.huang@unisoc.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Suren Baghdasaryan <surenb@google.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Link: https://lkml.kernel.org/r/1623371374-15664-1-git-send-email-huangzhaoyang@gmail.com
The CFS bandwidth controller limits CPU requests of a task group to
quota during each period. However, parallel workloads might be bursty
so that they get throttled even when their average utilization is under
quota. And they are latency sensitive at the same time so that
throttling them is undesired.
We borrow time now against our future underrun, at the cost of increased
interference against the other system users. All nicely bounded.
Traditional (UP-EDF) bandwidth control is something like:
(U = \Sum u_i) <= 1
This guaranteeds both that every deadline is met and that the system is
stable. After all, if U were > 1, then for every second of walltime,
we'd have to run more than a second of program time, and obviously miss
our deadline, but the next deadline will be further out still, there is
never time to catch up, unbounded fail.
This work observes that a workload doesn't always executes the full
quota; this enables one to describe u_i as a statistical distribution.
For example, have u_i = {x,e}_i, where x is the p(95) and x+e p(100)
(the traditional WCET). This effectively allows u to be smaller,
increasing the efficiency (we can pack more tasks in the system), but at
the cost of missing deadlines when all the odds line up. However, it
does maintain stability, since every overrun must be paired with an
underrun as long as our x is above the average.
That is, suppose we have 2 tasks, both specify a p(95) value, then we
have a p(95)*p(95) = 90.25% chance both tasks are within their quota and
everything is good. At the same time we have a p(5)p(5) = 0.25% chance
both tasks will exceed their quota at the same time (guaranteed deadline
fail). Somewhere in between there's a threshold where one exceeds and
the other doesn't underrun enough to compensate; this depends on the
specific CDFs.
At the same time, we can say that the worst case deadline miss, will be
\Sum e_i; that is, there is a bounded tardiness (under the assumption
that x+e is indeed WCET).
The benefit of burst is seen when testing with schbench. Default value of
kernel.sched_cfs_bandwidth_slice_us(5ms) and CONFIG_HZ(1000) is used.
mkdir /sys/fs/cgroup/cpu/test
echo $$ > /sys/fs/cgroup/cpu/test/cgroup.procs
echo 100000 > /sys/fs/cgroup/cpu/test/cpu.cfs_quota_us
echo 100000 > /sys/fs/cgroup/cpu/test/cpu.cfs_burst_us
./schbench -m 1 -t 3 -r 20 -c 80000 -R 10
The average CPU usage is at 80%. I run this for 10 times, and got long tail
latency for 6 times and got throttled for 8 times.
Tail latencies are shown below, and it wasn't the worst case.
Latency percentiles (usec)
50.0000th: 19872
75.0000th: 21344
90.0000th: 22176
95.0000th: 22496
*99.0000th: 22752
99.5000th: 22752
99.9000th: 22752
min=0, max=22727
rps: 9.90 p95 (usec) 22496 p99 (usec) 22752 p95/cputime 28.12% p99/cputime 28.44%
The interferenece when using burst is valued by the possibilities for
missing the deadline and the average WCET. Test results showed that when
there many cgroups or CPU is under utilized, the interference is
limited. More details are shown in:
https://lore.kernel.org/lkml/5371BD36-55AE-4F71-B9D7-B86DC32E3D2B@linux.alibaba.com/
Co-developed-by: Shanpei Chen <shanpeic@linux.alibaba.com>
Signed-off-by: Shanpei Chen <shanpeic@linux.alibaba.com>
Co-developed-by: Tianchen Ding <dtcccc@linux.alibaba.com>
Signed-off-by: Tianchen Ding <dtcccc@linux.alibaba.com>
Signed-off-by: Huaixin Chang <changhuaixin@linux.alibaba.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Ben Segall <bsegall@google.com>
Acked-by: Tejun Heo <tj@kernel.org>
Link: https://lore.kernel.org/r/20210621092800.23714-2-changhuaixin@linux.alibaba.com
Now cpu.uclamp.min acts as a protection, we need to make sure that the
uclamp request of the task is within the allowed range of the cgroup,
that is it is clamp()'ed correctly by tg->uclamp[UCLAMP_MIN] and
tg->uclamp[UCLAMP_MAX].
As reported by Xuewen [1] we can have some corner cases where there's
inversion between uclamp requested by task (p) and the uclamp values of
the taskgroup it's attached to (tg). Following table demonstrates
2 corner cases:
| p | tg | effective
-----------+-----+------+-----------
CASE 1
-----------+-----+------+-----------
uclamp_min | 60% | 0% | 60%
-----------+-----+------+-----------
uclamp_max | 80% | 50% | 50%
-----------+-----+------+-----------
CASE 2
-----------+-----+------+-----------
uclamp_min | 0% | 30% | 30%
-----------+-----+------+-----------
uclamp_max | 20% | 50% | 20%
-----------+-----+------+-----------
With this fix we get:
| p | tg | effective
-----------+-----+------+-----------
CASE 1
-----------+-----+------+-----------
uclamp_min | 60% | 0% | 50%
-----------+-----+------+-----------
uclamp_max | 80% | 50% | 50%
-----------+-----+------+-----------
CASE 2
-----------+-----+------+-----------
uclamp_min | 0% | 30% | 30%
-----------+-----+------+-----------
uclamp_max | 20% | 50% | 30%
-----------+-----+------+-----------
Additionally uclamp_update_active_tasks() must now unconditionally
update both UCLAMP_MIN/MAX because changing the tg's UCLAMP_MAX for
instance could have an impact on the effective UCLAMP_MIN of the tasks.
| p | tg | effective
-----------+-----+------+-----------
old
-----------+-----+------+-----------
uclamp_min | 60% | 0% | 50%
-----------+-----+------+-----------
uclamp_max | 80% | 50% | 50%
-----------+-----+------+-----------
*new*
-----------+-----+------+-----------
uclamp_min | 60% | 0% | *60%*
-----------+-----+------+-----------
uclamp_max | 80% |*70%* | *70%*
-----------+-----+------+-----------
[1] https://lore.kernel.org/lkml/CAB8ipk_a6VFNjiEnHRHkUMBKbA+qzPQvhtNjJ_YNzQhqV_o8Zw@mail.gmail.com/
Fixes: 0c18f2ecfc ("sched/uclamp: Fix wrong implementation of cpu.uclamp.min")
Reported-by: Xuewen Yan <xuewen.yan94@gmail.com>
Signed-off-by: Qais Yousef <qais.yousef@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20210617165155.3774110-1-qais.yousef@arm.com
DL keeps track of the utilization on a per-rq basis with the structure
avg_dl. This utilization is updated during task_tick_dl(),
put_prev_task_dl() and set_next_task_dl(). However, when the current
running task changes its policy, set_next_task_dl() which would usually
take care of updating the utilization when the rq starts running DL
tasks, will not see a such change, leaving the avg_dl structure outdated.
When that very same task will be dequeued later, put_prev_task_dl() will
then update the utilization, based on a wrong last_update_time, leading to
a huge spike in the DL utilization signal.
The signal would eventually recover from this issue after few ms. Even
if no DL tasks are run, avg_dl is also updated in
__update_blocked_others(). But as the CPU capacity depends partly on the
avg_dl, this issue has nonetheless a significant impact on the scheduler.
Fix this issue by ensuring a load update when a running task changes
its policy to DL.
Fixes: 3727e0e ("sched/dl: Add dl_rq utilization tracking")
Signed-off-by: Vincent Donnefort <vincent.donnefort@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Vincent Guittot <vincent.guittot@linaro.org>
Link: https://lore.kernel.org/r/1624271872-211872-3-git-send-email-vincent.donnefort@arm.com
RT keeps track of the utilization on a per-rq basis with the structure
avg_rt. This utilization is updated during task_tick_rt(),
put_prev_task_rt() and set_next_task_rt(). However, when the current
running task changes its policy, set_next_task_rt() which would usually
take care of updating the utilization when the rq starts running RT tasks,
will not see a such change, leaving the avg_rt structure outdated. When
that very same task will be dequeued later, put_prev_task_rt() will then
update the utilization, based on a wrong last_update_time, leading to a
huge spike in the RT utilization signal.
The signal would eventually recover from this issue after few ms. Even if
no RT tasks are run, avg_rt is also updated in __update_blocked_others().
But as the CPU capacity depends partly on the avg_rt, this issue has
nonetheless a significant impact on the scheduler.
Fix this issue by ensuring a load update when a running task changes
its policy to RT.
Fixes: 371bf427 ("sched/rt: Add rt_rq utilization tracking")
Signed-off-by: Vincent Donnefort <vincent.donnefort@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Vincent Guittot <vincent.guittot@linaro.org>
Link: https://lore.kernel.org/r/1624271872-211872-2-git-send-email-vincent.donnefort@arm.com
Change the type and name of task_struct::state. Drop the volatile and
shrink it to an 'unsigned int'. Rename it in order to find all uses
such that we can use READ_ONCE/WRITE_ONCE as appropriate.
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Daniel Bristot de Oliveira <bristot@redhat.com>
Acked-by: Will Deacon <will@kernel.org>
Acked-by: Daniel Thompson <daniel.thompson@linaro.org>
Link: https://lore.kernel.org/r/20210611082838.550736351@infradead.org
Replace a bunch of 'p->state == TASK_RUNNING' with a new helper:
task_is_running(p).
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Davidlohr Bueso <dave@stgolabs.net>
Acked-by: Geert Uytterhoeven <geert@linux-m68k.org>
Acked-by: Will Deacon <will@kernel.org>
Link: https://lore.kernel.org/r/20210611082838.222401495@infradead.org
This commit in sched/urgent moved the cfs_rq_is_decayed() function:
a7b359fc6a: ("sched/fair: Correctly insert cfs_rq's to list on unthrottle")
and this fresh commit in sched/core modified it in the old location:
9e077b52d8: ("sched/pelt: Check that *_avg are null when *_sum are")
Merge the two variants.
Conflicts:
kernel/sched/fair.c
Signed-off-by: Ingo Molnar <mingo@kernel.org>
This is a partial forward-port of Peter Ziljstra's work first posted
at:
https://lore.kernel.org/lkml/20180530142236.667774973@infradead.org/
Currently select_idle_cpu()'s proportional scheme uses the average idle
time *for when we are idle*, that is temporally challenged. When a CPU
is not at all idle, we'll happily continue using whatever value we did
see when the CPU goes idle. To fix this, introduce a separate average
idle and age it (the existing value still makes sense for things like
new-idle balancing, which happens when we do go idle).
The overall goal is to not spend more time scanning for idle CPUs than
we're idle for. Otherwise we're inhibiting work. This means that we need to
consider the cost over all the wake-ups between consecutive idle periods.
To track this, the scan cost is subtracted from the estimated average
idle time.
The impact of this patch is related to workloads that have domains that
are fully busy or overloaded. Without the patch, the scan depth may be
too high because a CPU is not reaching idle.
Due to the nature of the patch, this is a regression magnet. It
potentially wins when domains are almost fully busy or overloaded --
at that point searches are likely to fail but idle is not being aged
as CPUs are active so search depth is too large and useless. It will
potentially show regressions when there are idle CPUs and a deep search is
beneficial. This tbench result on a 2-socket broadwell machine partially
illustates the problem
5.13.0-rc2 5.13.0-rc2
vanilla sched-avgidle-v1r5
Hmean 1 445.02 ( 0.00%) 451.36 * 1.42%*
Hmean 2 830.69 ( 0.00%) 846.03 * 1.85%*
Hmean 4 1350.80 ( 0.00%) 1505.56 * 11.46%*
Hmean 8 2888.88 ( 0.00%) 2586.40 * -10.47%*
Hmean 16 5248.18 ( 0.00%) 5305.26 * 1.09%*
Hmean 32 8914.03 ( 0.00%) 9191.35 * 3.11%*
Hmean 64 10663.10 ( 0.00%) 10192.65 * -4.41%*
Hmean 128 18043.89 ( 0.00%) 18478.92 * 2.41%*
Hmean 256 16530.89 ( 0.00%) 17637.16 * 6.69%*
Hmean 320 16451.13 ( 0.00%) 17270.97 * 4.98%*
Note that 8 was a regression point where a deeper search would have helped
but it gains for high thread counts when searches are useless. Hackbench
is a more extreme example although not perfect as the tasks idle rapidly
hackbench-process-pipes
5.13.0-rc2 5.13.0-rc2
vanilla sched-avgidle-v1r5
Amean 1 0.3950 ( 0.00%) 0.3887 ( 1.60%)
Amean 4 0.9450 ( 0.00%) 0.9677 ( -2.40%)
Amean 7 1.4737 ( 0.00%) 1.4890 ( -1.04%)
Amean 12 2.3507 ( 0.00%) 2.3360 * 0.62%*
Amean 21 4.0807 ( 0.00%) 4.0993 * -0.46%*
Amean 30 5.6820 ( 0.00%) 5.7510 * -1.21%*
Amean 48 8.7913 ( 0.00%) 8.7383 ( 0.60%)
Amean 79 14.3880 ( 0.00%) 13.9343 * 3.15%*
Amean 110 21.2233 ( 0.00%) 19.4263 * 8.47%*
Amean 141 28.2930 ( 0.00%) 25.1003 * 11.28%*
Amean 172 34.7570 ( 0.00%) 30.7527 * 11.52%*
Amean 203 41.0083 ( 0.00%) 36.4267 * 11.17%*
Amean 234 47.7133 ( 0.00%) 42.0623 * 11.84%*
Amean 265 53.0353 ( 0.00%) 47.7720 * 9.92%*
Amean 296 60.0170 ( 0.00%) 53.4273 * 10.98%*
Stddev 1 0.0052 ( 0.00%) 0.0025 ( 51.57%)
Stddev 4 0.0357 ( 0.00%) 0.0370 ( -3.75%)
Stddev 7 0.0190 ( 0.00%) 0.0298 ( -56.64%)
Stddev 12 0.0064 ( 0.00%) 0.0095 ( -48.38%)
Stddev 21 0.0065 ( 0.00%) 0.0097 ( -49.28%)
Stddev 30 0.0185 ( 0.00%) 0.0295 ( -59.54%)
Stddev 48 0.0559 ( 0.00%) 0.0168 ( 69.92%)
Stddev 79 0.1559 ( 0.00%) 0.0278 ( 82.17%)
Stddev 110 1.1728 ( 0.00%) 0.0532 ( 95.47%)
Stddev 141 0.7867 ( 0.00%) 0.0968 ( 87.69%)
Stddev 172 1.0255 ( 0.00%) 0.0420 ( 95.91%)
Stddev 203 0.8106 ( 0.00%) 0.1384 ( 82.92%)
Stddev 234 1.1949 ( 0.00%) 0.1328 ( 88.89%)
Stddev 265 0.9231 ( 0.00%) 0.0820 ( 91.11%)
Stddev 296 1.0456 ( 0.00%) 0.1327 ( 87.31%)
Again, higher thread counts benefit and the standard deviation
shows that results are also a lot more stable when the idle
time is aged.
The patch potentially matters when a socket was multiple LLCs as the
maximum search depth is lower. However, some of the test results were
suspiciously good (e.g. specjbb2005 gaining 50% on a Zen1 machine) and
other results were not dramatically different to other mcahines.
Given the nature of the patch, Peter's full series is not being forward
ported as each part should stand on its own. Preferably they would be
merged at different times to reduce the risk of false bisections.
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Mel Gorman <mgorman@techsingularity.net>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20210615111611.GH30378@techsingularity.net
Energy Aware Scheduling (EAS) needs to predict the decisions made by
SchedUtil. The map_util_freq() exists to do that.
There are corner cases where the max allowed frequency might be reduced
(due to thermal). SchedUtil as a CPUFreq governor, is aware of that
but EAS is not. This patch aims to address it.
SchedUtil stores the maximum allowed frequency in
'sugov_policy::next_freq' field. EAS has to predict that value, which is
the real used frequency. That value is made after a call to
cpufreq_driver_resolve_freq() which clamps to the CPUFreq policy limits.
In the existing code EAS is not able to predict that real frequency.
This leads to energy estimation errors.
To avoid wrong energy estimation in EAS (due to frequency miss prediction)
make sure that the step which calculates Performance Domain frequency,
is also aware of the allowed CPU capacity.
Furthermore, modify map_util_freq() to not extend the frequency value.
Instead, use map_util_perf() to extend the util value in both places:
SchedUtil and EAS, but for EAS clamp it to max allowed CPU capacity.
In the end, we achieve the same desirable behavior for both subsystems
and alignment in regards to the real CPU frequency.
Signed-off-by: Lukasz Luba <lukasz.luba@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com> (For the schedutil part)
Link: https://lore.kernel.org/r/20210614191238.23224-1-lukasz.luba@arm.com
Energy Aware Scheduling (EAS) needs to be able to predict the frequency
requests made by the SchedUtil governor to properly estimate energy used
in the future. It has to take into account CPUs utilization and forecast
Performance Domain (PD) frequency. There is a corner case when the max
allowed frequency might be reduced due to thermal. SchedUtil is aware of
that reduced frequency, so it should be taken into account also in EAS
estimations.
SchedUtil, as a CPUFreq governor, knows the maximum allowed frequency of
a CPU, thanks to cpufreq_driver_resolve_freq() and internal clamping
to 'policy::max'. SchedUtil is responsible to respect that upper limit
while setting the frequency through CPUFreq drivers. This effective
frequency is stored internally in 'sugov_policy::next_freq' and EAS has
to predict that value.
In the existing code the raw value of arch_scale_cpu_capacity() is used
for clamping the returned CPU utilization from effective_cpu_util().
This patch fixes issue with too big single CPU utilization, by introducing
clamping to the allowed CPU capacity. The allowed CPU capacity is a CPU
capacity reduced by thermal pressure raw value.
Thanks to knowledge about allowed CPU capacity, we don't get too big value
for a single CPU utilization, which is then added to the util sum. The
util sum is used as a source of information for estimating whole PD energy.
To avoid wrong energy estimation in EAS (due to capped frequency), make
sure that the calculation of util sum is aware of allowed CPU capacity.
This thermal pressure might be visible in scenarios where the CPUs are not
heavily loaded, but some other component (like GPU) drastically reduced
available power budget and increased the SoC temperature. Thus, we still
use EAS for task placement and CPUs are not over-utilized.
Signed-off-by: Lukasz Luba <lukasz.luba@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Vincent Guittot <vincent.guittot@linaro.org>
Reviewed-by: Dietmar Eggemann <dietmar.eggemann@arm.com>
Link: https://lore.kernel.org/r/20210614191128.22735-1-lukasz.luba@arm.com
In case the _avg delta is 0 there is no need to update se's _avg
(level n) nor cfs_rq's _avg (level n-1). These values stay the same.
Since cfs_rq's _avg isn't changed, i.e. no load is propagated down,
cfs_rq's _sum should stay the same as well.
So bail out after se's _sum has been updated.
Signed-off-by: Dietmar Eggemann <dietmar.eggemann@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Vincent Guittot <vincent.guittot@linaro.org>
Link: https://lore.kernel.org/r/20210601083616.804229-1-dietmar.eggemann@arm.com
Check that we never break the rule that pelt's avg values are null if
pelt's sum are.
Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Dietmar Eggemann <dietmar.eggemann@arm.com>
Acked-by: Odin Ugedal <odin@uged.al>
Link: https://lore.kernel.org/r/20210601155328.19487-1-vincent.guittot@linaro.org
Fix an issue where fairness is decreased since cfs_rq's can end up not
being decayed properly. For two sibling control groups with the same
priority, this can often lead to a load ratio of 99/1 (!!).
This happens because when a cfs_rq is throttled, all the descendant
cfs_rq's will be removed from the leaf list. When they initial cfs_rq
is unthrottled, it will currently only re add descendant cfs_rq's if
they have one or more entities enqueued. This is not a perfect
heuristic.
Instead, we insert all cfs_rq's that contain one or more enqueued
entities, or it its load is not completely decayed.
Can often lead to situations like this for equally weighted control
groups:
$ ps u -C stress
USER PID %CPU %MEM VSZ RSS TTY STAT START TIME COMMAND
root 10009 88.8 0.0 3676 100 pts/1 R+ 11:04 0:13 stress --cpu 1
root 10023 3.0 0.0 3676 104 pts/1 R+ 11:04 0:00 stress --cpu 1
Fixes: 31bc6aeaab ("sched/fair: Optimize update_blocked_averages()")
[vingo: !SMP build fix]
Signed-off-by: Odin Ugedal <odin@uged.al>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Vincent Guittot <vincent.guittot@linaro.org>
Link: https://lore.kernel.org/r/20210612112815.61678-1-odin@uged.al
Revert commit 4698f88c06 ("sched/debug: Fix 'schedstats=enable'
cmdline option").
After commit 6041186a32 ("init: initialize jump labels before
command line option parsing") we can rely on jump label infra being
ready for use when setup_schedstats() is called.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Kees Cook <keescook@chromium.org>
Acked-by: Josh Poimboeuf <jpoimboe@redhat.com>
Link: https://lkml.kernel.org/r/20210602112108.1709635-1-eric.dumazet@gmail.com
The util_est internal UTIL_AVG_UNCHANGED flag which is used to prevent
unnecessary util_est updates uses the LSB of util_est.enqueued. It is
exposed via _task_util_est() (and task_util_est()).
Commit 92a801e5d5 ("sched/fair: Mask UTIL_AVG_UNCHANGED usages")
mentions that the LSB is lost for util_est resolution but
find_energy_efficient_cpu() checks if task_util_est() returns 0 to
return prev_cpu early.
_task_util_est() returns the max value of util_est.ewma and
util_est.enqueued or'ed w/ UTIL_AVG_UNCHANGED.
So task_util_est() returning the max of task_util() and
_task_util_est() will never return 0 under the default
SCHED_FEAT(UTIL_EST, true).
To fix this use the MSB of util_est.enqueued instead and keep the flag
util_est internal, i.e. don't export it via _task_util_est().
The maximal possible util_avg value for a task is 1024 so the MSB of
'unsigned int util_est.enqueued' isn't used to store a util value.
As a caveat the code behind the util_est_se trace point has to filter
UTIL_AVG_UNCHANGED to see the real util_est.enqueued value which should
be easy to do.
This also fixes an issue report by Xuewen Yan that util_est_update()
only used UTIL_AVG_UNCHANGED for the subtrahend of the equation:
last_enqueued_diff = ue.enqueued - (task_util() | UTIL_AVG_UNCHANGED)
Fixes: b89997aa88 sched/pelt: Fix task util_est update filtering
Signed-off-by: Dietmar Eggemann <dietmar.eggemann@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Xuewen Yan <xuewen.yan@unisoc.com>
Reviewed-by: Vincent Donnefort <vincent.donnefort@arm.com>
Reviewed-by: Vincent Guittot <vincent.guittot@linaro.org>
Link: https://lore.kernel.org/r/20210602145808.1562603-1-dietmar.eggemann@arm.com
Rounding in PELT calculation happening when entities are attached/detached
of a cfs_rq can result into situations where util/runnable_avg is not null
but util/runnable_sum is. This is normally not possible so we need to
ensure that util/runnable_sum stays synced with util/runnable_avg.
detach_entity_load_avg() is the last place where we don't sync
util/runnable_sum with util/runnbale_avg when moving some sched_entities
Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20210601085832.12626-1-vincent.guittot@linaro.org
Will reported that the 'XXX __migrate_task() can fail' in migration_cpu_stop()
can happen, and it *is* sort of a big deal. Looking at it some more, one
will note there is a glaring hole in the deferred CPU selection:
(w/ CONFIG_CPUSET=n, so that the affinity mask passed via taskset doesn't
get AND'd with cpu_online_mask)
$ taskset -pc 0-2 $PID
# offline CPUs 3-4
$ taskset -pc 3-5 $PID
`\
$PID may stay on 0-2 due to the cpumask_any_distribute() picking an
offline CPU and __migrate_task() refusing to do anything due to
cpu_is_allowed().
set_cpus_allowed_ptr() goes to some length to pick a dest_cpu that matches
the right constraints vs affinity and the online/active state of the
CPUs. Reuse that instead of discarding it in the affine_move_task() case.
Fixes: 6d337eab04 ("sched: Fix migrate_disable() vs set_cpus_allowed_ptr()")
Reported-by: Will Deacon <will@kernel.org>
Signed-off-by: Valentin Schneider <valentin.schneider@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20210526205751.842360-2-valentin.schneider@arm.com
When using something other than 8 spaces per tab, this ascii art
makes not sense, and the reader might end up wondering what this
advanced equation "is".
Signed-off-by: Odin Ugedal <odin@uged.al>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Vincent Guittot <vincent.guittot@linaro.org>
Link: https://lkml.kernel.org/r/20210518125202.78658-4-odin@uged.al
Extend 8fb12156b8 ("init: Pin init task to the boot CPU, initially")
to cover the new PF_NO_SETAFFINITY requirement.
While there, move wait_for_completion(&kthreadd_done) into kernel_init()
to make it absolutely clear it is the very first thing done by the init
thread.
Fixes: 570a752b7a ("lib/smp_processor_id: Use is_percpu_thread() instead of nr_cpus_allowed")
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Valentin Schneider <valentin.schneider@arm.com>
Tested-by: Valentin Schneider <valentin.schneider@arm.com>
Tested-by: Borislav Petkov <bp@alien8.de>
Link: https://lkml.kernel.org/r/YLS4mbKUrA3Gnb4t@hirez.programming.kicks-ass.net
During the update of fair blocked load (__update_blocked_fair()), we
update the contribution of the cfs in tg->load_avg if cfs_rq's pelt
has decayed. Nevertheless, the pelt values of a cfs_rq could have
been recently updated while propagating the change of a child. In this
case, cfs_rq's pelt will not decayed because it has already been
updated and we don't update tg->load_avg.
__update_blocked_fair
...
for_each_leaf_cfs_rq_safe: child cfs_rq
update cfs_rq_load_avg() for child cfs_rq
...
update_load_avg(cfs_rq_of(se), se, 0)
...
update cfs_rq_load_avg() for parent cfs_rq
-propagation of child's load makes parent cfs_rq->load_sum
becoming null
-UPDATE_TG is not set so it doesn't update parent
cfs_rq->tg_load_avg_contrib
..
for_each_leaf_cfs_rq_safe: parent cfs_rq
update cfs_rq_load_avg() for parent cfs_rq
- nothing to do because parent cfs_rq has already been updated
recently so cfs_rq->tg_load_avg_contrib is not updated
...
parent cfs_rq is decayed
list_del_leaf_cfs_rq parent cfs_rq
- but it still contibutes to tg->load_avg
we must set UPDATE_TG flags when propagting pending load to the parent
Fixes: 039ae8bcf7 ("sched/fair: Fix O(nr_cgroups) in the load balancing path")
Reported-by: Odin Ugedal <odin@uged.al>
Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Odin Ugedal <odin@uged.al>
Link: https://lkml.kernel.org/r/20210527122916.27683-3-vincent.guittot@linaro.org
when removing a cfs_rq from the list we only check _sum value so we must
ensure that _avg and _sum stay synced so load_sum can't be null whereas
load_avg is not after propagating load in the cgroup hierarchy.
Use load_avg to compute load_sum similarly to what is done for util_sum
and runnable_sum.
Fixes: 0e2d2aaaae ("sched/fair: Rewrite PELT migration propagation")
Reported-by: Odin Ugedal <odin@uged.al>
Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Odin Ugedal <odin@uged.al>
Link: https://lkml.kernel.org/r/20210527122916.27683-2-vincent.guittot@linaro.org
fair_sched_class->next no longer exists since commit:
a87e749e8f ("sched: Remove struct sched_class::next field").
Now the sched_class order is specified by the linker script.
Rewrite the comment in a more generic way.
Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20210519063709.323162-1-masahiroy@kernel.org
cpu_cgroup_css_online() calls cpu_util_update_eff() without holding the
uclamp_mutex or rcu_read_lock() like other call sites, which is
a mistake.
The uclamp_mutex is required to protect against concurrent reads and
writes that could update the cgroup hierarchy.
The rcu_read_lock() is required to traverse the cgroup data structures
in cpu_util_update_eff().
Surround the caller with the required locks and add some asserts to
better document the dependency in cpu_util_update_eff().
Fixes: 7226017ad3 ("sched/uclamp: Fix a bug in propagating uclamp value in new cgroups")
Reported-by: Quentin Perret <qperret@google.com>
Signed-off-by: Qais Yousef <qais.yousef@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20210510145032.1934078-3-qais.yousef@arm.com
cpu.uclamp.min is a protection as described in cgroup-v2 Resource
Distribution Model
Documentation/admin-guide/cgroup-v2.rst
which means we try our best to preserve the minimum performance point of
tasks in this group. See full description of cpu.uclamp.min in the
cgroup-v2.rst.
But the current implementation makes it a limit, which is not what was
intended.
For example:
tg->cpu.uclamp.min = 20%
p0->uclamp[UCLAMP_MIN] = 0
p1->uclamp[UCLAMP_MIN] = 50%
Previous Behavior (limit):
p0->effective_uclamp = 0
p1->effective_uclamp = 20%
New Behavior (Protection):
p0->effective_uclamp = 20%
p1->effective_uclamp = 50%
Which is inline with how protections should work.
With this change the cgroup and per-task behaviors are the same, as
expected.
Additionally, we remove the confusing relationship between cgroup and
!user_defined flag.
We don't want for example RT tasks that are boosted by default to max to
change their boost value when they attach to a cgroup. If a cgroup wants
to limit the max performance point of tasks attached to it, then
cpu.uclamp.max must be set accordingly.
Or if they want to set different boost value based on cgroup, then
sysctl_sched_util_clamp_min_rt_default must be used to NOT boost to max
and set the right cpu.uclamp.min for each group to let the RT tasks
obtain the desired boost value when attached to that group.
As it stands the dependency on !user_defined flag adds an extra layer of
complexity that is not required now cpu.uclamp.min behaves properly as
a protection.
The propagation model of effective cpu.uclamp.min in child cgroups as
implemented by cpu_util_update_eff() is still correct. The parent
protection sets an upper limit of what the child cgroups will
effectively get.
Fixes: 3eac870a32 (sched/uclamp: Use TG's clamps to restrict TASK's clamps)
Signed-off-by: Qais Yousef <qais.yousef@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20210510145032.1934078-2-qais.yousef@arm.com
For all intents and purposes, the idle task is a per-CPU kthread. It isn't
created via the same route as other pcpu kthreads however, and as a result
it is missing a few bells and whistles: it fails kthread_is_per_cpu() and
it doesn't have PF_NO_SETAFFINITY set.
Fix the former by giving the idle task a kthread struct along with the
KTHREAD_IS_PER_CPU flag. This requires some extra iffery as init_idle()
call be called more than once on the same idle task.
Signed-off-by: Valentin Schneider <valentin.schneider@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20210510151024.2448573-2-valentin.schneider@arm.com
We have a mismatch between RCU and isolation -- in relation to what is
considered the maximum valid CPU number.
This matters because nohz_full= and rcu_nocbs= are joined at the hip; in
fact the former will enforce the latter. So we don't want a CPU mask to
be valid for one and denied for the other.
The difference 1st appeared as of v4.15; further details are below.
As it is confusing to anyone who isn't looking at the code regularly, a
reminder is in order; three values exist here:
CONFIG_NR_CPUS - compiled in maximum cap on number of CPUs supported.
nr_cpu_ids - possible # of CPUs (typically reflects what ACPI says)
cpus_present - actual number of present/detected/installed CPUs.
For this example, I'll refer to NR_CPUS=64 from "make defconfig" and
nr_cpu_ids=6 for ACPI reporting on a board that could run a six core,
and present=4 for a quad that is physically in the socket. From dmesg:
smpboot: Allowing 6 CPUs, 2 hotplug CPUs
setup_percpu: NR_CPUS:64 nr_cpumask_bits:64 nr_cpu_ids:6 nr_node_ids:1
rcu: RCU restricting CPUs from NR_CPUS=64 to nr_cpu_ids=6.
smp: Brought up 1 node, 4 CPUs
And from userspace, see:
paul@trash:/sys/devices/system/cpu$ cat present
0-3
paul@trash:/sys/devices/system/cpu$ cat possible
0-5
paul@trash:/sys/devices/system/cpu$ cat kernel_max
63
Everything is fine if we boot 5x5 for rcu/nohz:
Command line: BOOT_IMAGE=/boot/bzImage nohz_full=2-5 rcu_nocbs=2-5 root=/dev/sda1 ro
NO_HZ: Full dynticks CPUs: 2-5.
rcu: Offload RCU callbacks from CPUs: 2-5.
..even though there is no CPU 4 or 5. Both RCU and nohz_full are OK.
Now we push that > 6 but less than NR_CPU and with 15x15 we get:
Command line: BOOT_IMAGE=/boot/bzImage rcu_nocbs=2-15 nohz_full=2-15 root=/dev/sda1 ro
rcu: Note: kernel parameter 'rcu_nocbs=', 'nohz_full', or 'isolcpus=' contains nonexistent CPUs.
rcu: Offload RCU callbacks from CPUs: 2-5.
These are both functionally equivalent, as we are only changing flags on
phantom CPUs that don't exist, but note the kernel interpretation changes.
And worse, it only changes for one of the two - which is the problem.
RCU doesn't care if you want to restrict the flags on phantom CPUs but
clearly nohz_full does after this change from v4.15.
edb9382175: ("sched/isolation: Move isolcpus= handling to the housekeeping code")
- if (cpulist_parse(str, non_housekeeping_mask) < 0) {
- pr_warn("Housekeeping: Incorrect nohz_full cpumask\n");
+ err = cpulist_parse(str, non_housekeeping_mask);
+ if (err < 0 || cpumask_last(non_housekeeping_mask) >= nr_cpu_ids) {
+ pr_warn("Housekeeping: nohz_full= or isolcpus= incorrect CPU range\n");
To be clear, the sanity check on "possible" (nr_cpu_ids) is new here.
The goal was reasonable ; not wanting housekeeping to land on a
not-possible CPU, but note two things:
1) this is an exclusion list, not an inclusion list; we are tracking
non_housekeeping CPUs; not ones who are explicitly assigned housekeeping
2) we went one further in 9219565aa8 ("sched/isolation: Require a present CPU in housekeeping mask")
- ensuring that housekeeping was sanity checking against present and not just possible CPUs.
To be clear, this means the check added in v4.15 is doubly redundant.
And more importantly, overly strict/restrictive.
We care now, because the bitmap boot arg parsing now knows that a value
of "N" is NR_CPUS; the size of the bitmap, but the bitmap code doesn't
know anything about the subtleties of our max/possible/present CPU
specifics as outlined above.
So drop the check added in v4.15 (edb9382175) and make RCU and
nohz_full both in alignment again on NR_CPUS so "N" works for both,
and then they can fall back to nr_cpu_ids internally just as before.
Command line: BOOT_IMAGE=/boot/bzImage nohz_full=2-N rcu_nocbs=2-N root=/dev/sda1 ro
NO_HZ: Full dynticks CPUs: 2-5.
rcu: Offload RCU callbacks from CPUs: 2-5.
As shown above, with this change, RCU and nohz_full are in sync, even
with the use of the "N" placeholder. Same result is achieved with "15".
Signed-off-by: Paul Gortmaker <paul.gortmaker@windriver.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Acked-by: Paul E. McKenney <paulmck@kernel.org>
Link: https://lore.kernel.org/r/20210419042659.1134916-1-paul.gortmaker@windriver.com
Make:
struct dl_rq::dl_nr_migratory
struct dl_rq::dl_nr_running
struct rt_rq::rt_nr_boosted
struct rt_rq::rt_nr_migratory
struct rt_rq::rt_nr_total
struct rq::nr_uninterruptible
32-bit.
If total number of tasks can't exceed 2**32 (and less due to futex pid
limits), then per-runqueue counters can't as well.
This patchset has been sponsored by REX Prefix Eradication Society.
Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20210422200228.1423391-4-adobriyan@gmail.com
Creating 2**32 tasks to wait in D-state is impossible and wasteful.
Return "unsigned int" and save on REX prefixes.
Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20210422200228.1423391-2-adobriyan@gmail.com
Creating 2**32 tasks is impossible due to futex pid limits and wasteful
anyway. Nobody has done it.
Bring nr_running() into 32-bit world to save on REX prefixes.
Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20210422200228.1423391-1-adobriyan@gmail.com
As pointed out by commit
de9b8f5dcb ("sched: Fix crash trying to dequeue/enqueue the idle thread")
init_idle() can and will be invoked more than once on the same idle
task. At boot time, it is invoked for the boot CPU thread by
sched_init(). Then smp_init() creates the threads for all the secondary
CPUs and invokes init_idle() on them.
As the hotplug machinery brings the secondaries to life, it will issue
calls to idle_thread_get(), which itself invokes init_idle() yet again.
In this case it's invoked twice more per secondary: at _cpu_up(), and at
bringup_cpu().
Given smp_init() already initializes the idle tasks for all *possible*
CPUs, no further initialization should be required. Now, removing
init_idle() from idle_thread_get() exposes some interesting expectations
with regards to the idle task's preempt_count: the secondary startup always
issues a preempt_disable(), requiring some reset of the preempt count to 0
between hot-unplug and hotplug, which is currently served by
idle_thread_get() -> idle_init().
Given the idle task is supposed to have preemption disabled once and never
see it re-enabled, it seems that what we actually want is to initialize its
preempt_count to PREEMPT_DISABLED and leave it there. Do that, and remove
init_idle() from idle_thread_get().
Secondary startups were patched via coccinelle:
@begone@
@@
-preempt_disable();
...
cpu_startup_entry(CPUHP_AP_ONLINE_IDLE);
Signed-off-by: Valentin Schneider <valentin.schneider@arm.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Acked-by: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20210512094636.2958515-1-valentin.schneider@arm.com
This patch provides support for setting and copying core scheduling
'task cookies' between threads (PID), processes (TGID), and process
groups (PGID).
The value of core scheduling isn't that tasks don't share a core,
'nosmt' can do that. The value lies in exploiting all the sharing
opportunities that exist to recover possible lost performance and that
requires a degree of flexibility in the API.
From a security perspective (and there are others), the thread,
process and process group distinction is an existent hierarchal
categorization of tasks that reflects many of the security concerns
about 'data sharing'. For example, protecting against cache-snooping
by a thread that can just read the memory directly isn't all that
useful.
With this in mind, subcommands to CREATE/SHARE (TO/FROM) provide a
mechanism to create and share cookies. CREATE/SHARE_TO specify a
target pid with enum pidtype used to specify the scope of the targeted
tasks. For example, PIDTYPE_TGID will share the cookie with the
process and all of it's threads as typically desired in a security
scenario.
API:
prctl(PR_SCHED_CORE, PR_SCHED_CORE_GET, tgtpid, pidtype, &cookie)
prctl(PR_SCHED_CORE, PR_SCHED_CORE_CREATE, tgtpid, pidtype, NULL)
prctl(PR_SCHED_CORE, PR_SCHED_CORE_SHARE_TO, tgtpid, pidtype, NULL)
prctl(PR_SCHED_CORE, PR_SCHED_CORE_SHARE_FROM, srcpid, pidtype, NULL)
where 'tgtpid/srcpid == 0' implies the current process and pidtype is
kernel enum pid_type {PIDTYPE_PID, PIDTYPE_TGID, PIDTYPE_PGID, ...}.
For return values, EINVAL, ENOMEM are what they say. ESRCH means the
tgtpid/srcpid was not found. EPERM indicates lack of PTRACE permission
access to tgtpid/srcpid. ENODEV indicates your machines lacks SMT.
[peterz: complete rewrite]
Signed-off-by: Chris Hyser <chris.hyser@oracle.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Tested-by: Don Hiatt <dhiatt@digitalocean.com>
Tested-by: Hongyu Ning <hongyu.ning@linux.intel.com>
Tested-by: Vincent Guittot <vincent.guittot@linaro.org>
Link: https://lkml.kernel.org/r/20210422123309.039845339@infradead.org
Note that sched_core_fork() is called from under tasklist_lock, and
not from sched_fork() earlier. This avoids a few races later.
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Tested-by: Don Hiatt <dhiatt@digitalocean.com>
Tested-by: Hongyu Ning <hongyu.ning@linux.intel.com>
Tested-by: Vincent Guittot <vincent.guittot@linaro.org>
Link: https://lkml.kernel.org/r/20210422123308.980003687@infradead.org
In order to not have to use pid_struct, create a new, smaller,
structure to manage task cookies for core scheduling.
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Tested-by: Don Hiatt <dhiatt@digitalocean.com>
Tested-by: Hongyu Ning <hongyu.ning@linux.intel.com>
Tested-by: Vincent Guittot <vincent.guittot@linaro.org>
Link: https://lkml.kernel.org/r/20210422123308.919768100@infradead.org
- Don't migrate if there is a cookie mismatch
Load balance tries to move task from busiest CPU to the
destination CPU. When core scheduling is enabled, if the
task's cookie does not match with the destination CPU's
core cookie, this task may be skipped by this CPU. This
mitigates the forced idle time on the destination CPU.
- Select cookie matched idle CPU
In the fast path of task wakeup, select the first cookie matched
idle CPU instead of the first idle CPU.
- Find cookie matched idlest CPU
In the slow path of task wakeup, find the idlest CPU whose core
cookie matches with task's cookie
Signed-off-by: Aubrey Li <aubrey.li@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Tested-by: Don Hiatt <dhiatt@digitalocean.com>
Tested-by: Hongyu Ning <hongyu.ning@linux.intel.com>
Tested-by: Vincent Guittot <vincent.guittot@linaro.org>
Link: https://lkml.kernel.org/r/20210422123308.860083871@infradead.org
When a sibling is forced-idle to match the core-cookie; search for
matching tasks to fill the core.
rcu_read_unlock() can incur an infrequent deadlock in
sched_core_balance(). Fix this by using the RCU-sched flavor instead.
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Tested-by: Don Hiatt <dhiatt@digitalocean.com>
Tested-by: Hongyu Ning <hongyu.ning@linux.intel.com>
Tested-by: Vincent Guittot <vincent.guittot@linaro.org>
Link: https://lkml.kernel.org/r/20210422123308.800048269@infradead.org
During force-idle, we end up doing cross-cpu comparison of vruntimes
during pick_next_task. If we simply compare (vruntime-min_vruntime)
across CPUs, and if the CPUs only have 1 task each, we will always
end up comparing 0 with 0 and pick just one of the tasks all the time.
This starves the task that was not picked. To fix this, take a snapshot
of the min_vruntime when entering force idle and use it for comparison.
This min_vruntime snapshot will only be used for cross-CPU vruntime
comparison, and nothing else.
A note about the min_vruntime snapshot and force idling:
During selection:
When we're not fi, we need to update snapshot.
when we're fi and we were not fi, we must update snapshot.
When we're fi and we were already fi, we must not update snapshot.
Which gives:
fib fi update
0 0 1
0 1 1
1 0 1
1 1 0
Where:
fi: force-idled now
fib: force-idled before
So the min_vruntime snapshot needs to be updated when: !(fib && fi).
Also, the cfs_prio_less() function needs to be aware of whether the
core is in force idle or not, since it will be use this information to
know whether to advance a cfs_rq's min_vruntime_fi in the hierarchy.
So pass this information along via pick_task() -> prio_less().
Suggested-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Joel Fernandes (Google) <joel@joelfernandes.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Tested-by: Don Hiatt <dhiatt@digitalocean.com>
Tested-by: Hongyu Ning <hongyu.ning@linux.intel.com>
Tested-by: Vincent Guittot <vincent.guittot@linaro.org>
Link: https://lkml.kernel.org/r/20210422123308.738542617@infradead.org
The rationale is as follows. In the core-wide pick logic, even if
need_sync == false, we need to go look at other CPUs (non-local CPUs)
to see if they could be running RT.
Say the RQs in a particular core look like this:
Let CFS1 and CFS2 be 2 tagged CFS tags.
Let RT1 be an untagged RT task.
rq0 rq1
CFS1 (tagged) RT1 (no tag)
CFS2 (tagged)
Say schedule() runs on rq0. Now, it will enter the above loop and
pick_task(RT) will return NULL for 'p'. It will enter the above if()
block and see that need_sync == false and will skip RT entirely.
The end result of the selection will be (say prio(CFS1) > prio(CFS2)):
rq0 rq1
CFS1 IDLE
When it should have selected:
rq0 rq1
IDLE RT
Suggested-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Joel Fernandes (Google) <joel@joelfernandes.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Tested-by: Don Hiatt <dhiatt@digitalocean.com>
Tested-by: Hongyu Ning <hongyu.ning@linux.intel.com>
Tested-by: Vincent Guittot <vincent.guittot@linaro.org>
Link: https://lkml.kernel.org/r/20210422123308.678425748@infradead.org
If there is only one long running local task and the sibling is
forced idle, it might not get a chance to run until a schedule
event happens on any cpu in the core.
So we check for this condition during a tick to see if a sibling
is starved and then give it a chance to schedule.
Signed-off-by: Vineeth Pillai <viremana@linux.microsoft.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Tested-by: Don Hiatt <dhiatt@digitalocean.com>
Tested-by: Hongyu Ning <hongyu.ning@linux.intel.com>
Tested-by: Vincent Guittot <vincent.guittot@linaro.org>
Link: https://lkml.kernel.org/r/20210422123308.617407840@infradead.org
Instead of only selecting a local task, select a task for all SMT
siblings for every reschedule on the core (irrespective which logical
CPU does the reschedule).
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Tested-by: Don Hiatt <dhiatt@digitalocean.com>
Tested-by: Hongyu Ning <hongyu.ning@linux.intel.com>
Tested-by: Vincent Guittot <vincent.guittot@linaro.org>
Link: https://lkml.kernel.org/r/20210422123308.557559654@infradead.org
Introduce task_struct::core_cookie as an opaque identifier for core
scheduling. When enabled; core scheduling will only allow matching
task to be on the core; where idle matches everything.
When task_struct::core_cookie is set (and core scheduling is enabled)
these tasks are indexed in a second RB-tree, first on cookie value
then on scheduling function, such that matching task selection always
finds the most elegible match.
NOTE: *shudder* at the overhead...
NOTE: *sigh*, a 3rd copy of the scheduling function; the alternative
is per class tracking of cookies and that just duplicates a lot of
stuff for no raisin (the 2nd copy lives in the rt-mutex PI code).
[Joel: folded fixes]
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Joel Fernandes (Google) <joel@joelfernandes.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Tested-by: Don Hiatt <dhiatt@digitalocean.com>
Tested-by: Hongyu Ning <hongyu.ning@linux.intel.com>
Tested-by: Vincent Guittot <vincent.guittot@linaro.org>
Link: https://lkml.kernel.org/r/20210422123308.496975854@infradead.org
