IF YOU WOULD LIKE TO GET AN ACCOUNT, please write an
email to Administrator. User accounts are meant only to access repo
and report issues and/or generate pull requests.
This is a purpose-specific Git hosting for
BaseALT
projects. Thank you for your understanding!
Только зарегистрированные пользователи имеют доступ к сервису!
Для получения аккаунта, обратитесь к администратору.
hrtimer_force_reprogram() and hrtimer_interrupt() invokes
__hrtimer_get_next_event() to find the earliest expiry time of hrtimer
bases. __hrtimer_get_next_event() does not update
cpu_base::[softirq_]_expires_next to preserve reprogramming logic. That
needs to be done at the callsites.
hrtimer_force_reprogram() updates cpu_base::softirq_expires_next only when
the first expiring timer is a softirq timer and the soft interrupt is not
activated. That's wrong because cpu_base::softirq_expires_next is left
stale when the first expiring timer of all bases is a timer which expires
in hard interrupt context. hrtimer_interrupt() does never update
cpu_base::softirq_expires_next which is wrong too.
That becomes a problem when clock_settime() sets CLOCK_REALTIME forward and
the first soft expiring timer is in the CLOCK_REALTIME_SOFT base. Setting
CLOCK_REALTIME forward moves the clock MONOTONIC based expiry time of that
timer before the stale cpu_base::softirq_expires_next.
cpu_base::softirq_expires_next is cached to make the check for raising the
soft interrupt fast. In the above case the soft interrupt won't be raised
until clock monotonic reaches the stale cpu_base::softirq_expires_next
value. That's incorrect, but what's worse it that if the softirq timer
becomes the first expiring timer of all clock bases after the hard expiry
timer has been handled the reprogramming of the clockevent from
hrtimer_interrupt() will result in an interrupt storm. That happens because
the reprogramming does not use cpu_base::softirq_expires_next, it uses
__hrtimer_get_next_event() which returns the actual expiry time. Once clock
MONOTONIC reaches cpu_base::softirq_expires_next the soft interrupt is
raised and the storm subsides.
Change the logic in hrtimer_force_reprogram() to evaluate the soft and hard
bases seperately, update softirq_expires_next and handle the case when a
soft expiring timer is the first of all bases by comparing the expiry times
and updating the required cpu base fields. Split this functionality into a
separate function to be able to use it in hrtimer_interrupt() as well
without copy paste.
Fixes: 5da70160462e ("hrtimer: Implement support for softirq based hrtimers")
Reported-by: Mikael Beckius <mikael.beckius@windriver.com>
Suggested-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Mikael Beckius <mikael.beckius@windriver.com>
Signed-off-by: Anna-Maria Behnsen <anna-maria@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20210223160240.27518-1-anna-maria@linutronix.de
There's a non-trivial conflict between the parallel TLB flush
framework and the IPI flush debugging code - merge them
manually.
Conflicts:
kernel/smp.c
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Call the generic send_call_function_single_ipi() function, which
will avoid the IPI when @last_cpu is idle.
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Simplify the code and avoid having an additional function on the stack
by inlining on_each_cpu_cond() and on_each_cpu().
Suggested-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Nadav Amit <namit@vmware.com>
[ Minor edits. ]
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20210220231712.2475218-10-namit@vmware.com
Currently, on_each_cpu() and similar functions do not exploit the
potential of concurrency: the function is first executed remotely and
only then it is executed locally. Functions such as TLB flush can take
considerable time, so this provides an opportunity for performance
optimization.
To do so, modify smp_call_function_many_cond(), to allows the callers to
provide a function that should be executed (remotely/locally), and run
them concurrently. Keep other smp_call_function_many() semantic as it is
today for backward compatibility: the called function is not executed in
this case locally.
smp_call_function_many_cond() does not use the optimized version for a
single remote target that smp_call_function_single() implements. For
synchronous function call, smp_call_function_single() keeps a
call_single_data (which is used for synchronization) on the stack.
Interestingly, it seems that not using this optimization provides
greater performance improvements (greater speedup with a single remote
target than with multiple ones). Presumably, holding data structures
that are intended for synchronization on the stack can introduce
overheads due to TLB misses and false-sharing when the stack is used for
other purposes.
Signed-off-by: Nadav Amit <namit@vmware.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Dave Hansen <dave.hansen@linux.intel.com>
Link: https://lore.kernel.org/r/20210220231712.2475218-2-namit@vmware.com
Sometimes the PMU internal buffers have to be flushed for per-CPU events
during a context switch, e.g., large PEBS. Otherwise, the perf tool may
report samples in locations that do not belong to the process where the
samples are processed in, because PEBS does not tag samples with PID/TID.
The current code only flush the buffers for a per-task event. It doesn't
check a per-CPU event.
Add a new event state flag, PERF_ATTACH_SCHED_CB, to indicate that the
PMU internal buffers have to be flushed for this event during a context
switch.
Add sched_cb_entry and perf_sched_cb_usages back to track the PMU/cpuctx
which is required to be flushed.
Only need to invoke the sched_task() for per-CPU events in this patch.
The per-task events have been handled in perf_event_context_sched_in/out
already.
Fixes: 9c964efa4330 ("perf/x86/intel: Drain the PEBS buffer during context switches")
Reported-by: Gabriel Marin <gmx@google.com>
Originally-by: Namhyung Kim <namhyung@kernel.org>
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lkml.kernel.org/r/20201130193842.10569-1-kan.liang@linux.intel.com
Adds defines for lock state returns from lock_is_held_type() based on
Johannes Berg's suggestions as it make it easier to read and maintain
the lock states. These are defines and a enum to avoid changes to
lock_is_held_type() and lockdep_is_held() return types.
Updates to lock_is_held_type() and __lock_is_held() to use the new
defines.
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/linux-wireless/871rdmu9z9.fsf@codeaurora.org/
Some kernel functions must be called without holding a specific lock.
Add lockdep_assert_not_held() to be used in these functions to detect
incorrect calls while holding a lock.
lockdep_assert_not_held() provides the opposite functionality of
lockdep_assert_held() which is used to assert calls that require
holding a specific lock.
Incorporates suggestions from Peter Zijlstra to avoid misfires when
lockdep_off() is employed.
The need for lockdep_assert_not_held() came up in a discussion on
ath10k patch. ath10k_drain_tx() and i915_vma_pin_ww() are examples
of functions that can use lockdep_assert_not_held().
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/linux-wireless/871rdmu9z9.fsf@codeaurora.org/
In order to help identifying problems with IPI handling and remote
function execution add some more data to IPI debugging code.
There have been multiple reports of CPUs looping long times (many
seconds) in smp_call_function_many() waiting for another CPU executing
a function like tlb flushing. Most of these reports have been for
cases where the kernel was running as a guest on top of KVM or Xen
(there are rumours of that happening under VMWare, too, and even on
bare metal).
Finding the root cause hasn't been successful yet, even after more than
2 years of chasing this bug by different developers.
Commit:
35feb60474bf4f7 ("kernel/smp: Provide CSD lock timeout diagnostics")
tried to address this by adding some debug code and by issuing another
IPI when a hang was detected. This helped mitigating the problem
(the repeated IPI unlocks the hang), but the root cause is still unknown.
Current available data suggests that either an IPI wasn't sent when it
should have been, or that the IPI didn't result in the target CPU
executing the queued function (due to the IPI not reaching the CPU,
the IPI handler not being called, or the handler not seeing the queued
request).
Try to add more diagnostic data by introducing a global atomic counter
which is being incremented when doing critical operations (before and
after queueing a new request, when sending an IPI, and when dequeueing
a request). The counter value is stored in percpu variables which can
be printed out when a hang is detected.
The data of the last event (consisting of sequence counter, source
CPU, target CPU, and event type) is stored in a global variable. When
a new event is to be traced, the data of the last event is stored in
the event related percpu location and the global data is updated with
the new event's data. This allows to track two events in one data
location: one by the value of the event data (the event before the
current one), and one by the location itself (the current event).
A typical printout with a detected hang will look like this:
csd: Detected non-responsive CSD lock (#1) on CPU#1, waiting 5000000003 ns for CPU#06 scf_handler_1+0x0/0x50(0xffffa2a881bb1410).
csd: CSD lock (#1) handling prior scf_handler_1+0x0/0x50(0xffffa2a8813823c0) request.
csd: cnt(00008cc): ffff->0000 dequeue (src cpu 0 == empty)
csd: cnt(00008cd): ffff->0006 idle
csd: cnt(0003668): 0001->0006 queue
csd: cnt(0003669): 0001->0006 ipi
csd: cnt(0003e0f): 0007->000a queue
csd: cnt(0003e10): 0001->ffff ping
csd: cnt(0003e71): 0003->0000 ping
csd: cnt(0003e72): ffff->0006 gotipi
csd: cnt(0003e73): ffff->0006 handle
csd: cnt(0003e74): ffff->0006 dequeue (src cpu 0 == empty)
csd: cnt(0003e7f): 0004->0006 ping
csd: cnt(0003e80): 0001->ffff pinged
csd: cnt(0003eb2): 0005->0001 noipi
csd: cnt(0003eb3): 0001->0006 queue
csd: cnt(0003eb4): 0001->0006 noipi
csd: cnt now: 0003f00
The idea is to print only relevant entries. Those are all events which
are associated with the hang (so sender side events for the source CPU
of the hanging request, and receiver side events for the target CPU),
and the related events just before those (for adding data needed to
identify a possible race). Printing all available data would be
possible, but this would add large amounts of data printed on larger
configurations.
Signed-off-by: Juergen Gross <jgross@suse.com>
[ Minor readability edits. Breaks col80 but is far more readable. ]
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Tested-by: Paul E. McKenney <paulmck@kernel.org>
Link: https://lore.kernel.org/r/20210301101336.7797-4-jgross@suse.com
In order to be able to easily add more CSD lock debugging data to
struct call_function_data->csd move the call_single_data_t element
into a sub-structure.
Signed-off-by: Juergen Gross <jgross@suse.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20210301101336.7797-3-jgross@suse.com
Currently CSD lock debugging can be switched on and off via a kernel
config option only. Unfortunately there is at least one problem with
CSD lock handling pending for about 2 years now, which has been seen
in different environments (mostly when running virtualized under KVM
or Xen, at least once on bare metal). Multiple attempts to catch this
issue have finally led to introduction of CSD lock debug code, but
this code is not in use in most distros as it has some impact on
performance.
In order to be able to ship kernels with CONFIG_CSD_LOCK_WAIT_DEBUG
enabled even for production use, add a boot parameter for switching
the debug functionality on. This will reduce any performance impact
of the debug coding to a bare minimum when not being used.
Signed-off-by: Juergen Gross <jgross@suse.com>
[ Minor edits. ]
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20210301101336.7797-2-jgross@suse.com
Provided the target address of a R_X86_64_PC32 relocation is aligned,
the low two bits should be invariant between the relative and absolute
value.
Turns out the address is not aligned and things go sideways, ensure we
transfer the bits in the absolute form when fixing up the key address.
Fixes: 73f44fe19d35 ("static_call: Allow module use without exposing static_call_key")
Reported-by: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Tested-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Link: https://lkml.kernel.org/r/20210225220351.GE4746@worktop.programming.kicks-ass.net
Many drivers don't want interrupts enabled automatically via request_irq().
So they are handling this issue by either way of the below two:
(1)
irq_set_status_flags(irq, IRQ_NOAUTOEN);
request_irq(dev, irq...);
(2)
request_irq(dev, irq...);
disable_irq(irq);
The code in the second way is silly and unsafe. In the small time gap
between request_irq() and disable_irq(), interrupts can still come.
The code in the first way is safe though it's subobtimal.
Add a new IRQF_NO_AUTOEN flag which can be handed in by drivers to
request_irq() and request_nmi(). It prevents the automatic enabling of the
requested interrupt/nmi in the same safe way as #1 above. With that the
various usage sites of #1 and #2 above can be simplified and corrected.
Signed-off-by: Barry Song <song.bao.hua@hisilicon.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: dmitry.torokhov@gmail.com
Link: https://lore.kernel.org/r/20210302224916.13980-2-song.bao.hua@hisilicon.com
The commit 36b238d57172 ("psi: Optimize switching tasks inside shared
cgroups") only update cgroups whose state actually changes during a
task switch only in task preempt case, not in task sleep case.
We actually don't need to clear and set TSK_ONCPU state for common cgroups
of next and prev task in sleep case, that can save many psi_group_change
especially when most activity comes from one leaf cgroup.
sleep before:
psi_dequeue()
while ((group = iterate_groups(prev))) # all ancestors
psi_group_change(prev, .clear=TSK_RUNNING|TSK_ONCPU)
psi_task_switch()
while ((group = iterate_groups(next))) # all ancestors
psi_group_change(next, .set=TSK_ONCPU)
sleep after:
psi_dequeue()
nop
psi_task_switch()
while ((group = iterate_groups(next))) # until (prev & next)
psi_group_change(next, .set=TSK_ONCPU)
while ((group = iterate_groups(prev))) # all ancestors
psi_group_change(prev, .clear=common?TSK_RUNNING:TSK_RUNNING|TSK_ONCPU)
When a voluntary sleep switches to another task, we remove one call of
psi_group_change() for every common cgroup ancestor of the two tasks.
Co-developed-by: Muchun Song <songmuchun@bytedance.com>
Signed-off-by: Muchun Song <songmuchun@bytedance.com>
Signed-off-by: Chengming Zhou <zhouchengming@bytedance.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Link: https://lkml.kernel.org/r/20210303034659.91735-5-zhouchengming@bytedance.com
Move the unlikely branches out of line. This eliminates undesirable
jumps during wakeup and sleeps for workloads that aren't under any
sort of resource pressure.
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Signed-off-by: Chengming Zhou <zhouchengming@bytedance.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lkml.kernel.org/r/20210303034659.91735-4-zhouchengming@bytedance.com
Move the reclaim detection from the timer tick to the task state
tracking machinery using the recently added ONCPU state. And we
also add task psi_flags changes checking in the psi_task_switch()
optimization to update the parents properly.
In terms of performance and cost, this ONCPU task state tracking
is not cheaper than previous timer tick in aggregate. But the code is
simpler and shorter this way, so it's a maintainability win. And
Johannes did some testing with perf bench, the performace and cost
changes would be acceptable for real workloads.
Thanks to Johannes Weiner for pointing out the psi_task_switch()
optimization things and the clearer changelog.
Co-developed-by: Muchun Song <songmuchun@bytedance.com>
Signed-off-by: Muchun Song <songmuchun@bytedance.com>
Signed-off-by: Chengming Zhou <zhouchengming@bytedance.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Link: https://lkml.kernel.org/r/20210303034659.91735-3-zhouchengming@bytedance.com
The FULL state doesn't exist for the CPU resource at the system level,
but exist at the cgroup level, means all non-idle tasks in a cgroup are
delayed on the CPU resource which used by others outside of the cgroup
or throttled by the cgroup cpu.max configuration.
Co-developed-by: Muchun Song <songmuchun@bytedance.com>
Signed-off-by: Muchun Song <songmuchun@bytedance.com>
Signed-off-by: Chengming Zhou <zhouchengming@bytedance.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Link: https://lkml.kernel.org/r/20210303034659.91735-2-zhouchengming@bytedance.com
Factorizing and unifying cpuhp callback range invocations, especially for
the hotunplug path, where two different ways of decrementing were used. The
first one, decrements before the callback is called:
cpuhp_thread_fun()
state = st->state;
st->state--;
cpuhp_invoke_callback(state);
The second one, after:
take_down_cpu()|cpuhp_down_callbacks()
cpuhp_invoke_callback(st->state);
st->state--;
This is problematic for rolling back the steps in case of error, as
depending on the decrement, the rollback will start from N or N-1. It also
makes tracing inconsistent, between steps run in the cpuhp thread and
the others.
Additionally, avoid useless cpuhp_thread_fun() loops by skipping empty
steps.
Signed-off-by: Vincent Donnefort <vincent.donnefort@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lkml.kernel.org/r/20210216103506.416286-4-vincent.donnefort@arm.com
The atomic states (between CPUHP_AP_IDLE_DEAD and CPUHP_AP_ONLINE) are
triggered by the CPUHP_BRINGUP_CPU step. If the latter fails, no atomic
state can be rolled back.
DEAD callbacks too can't fail and disallow recovery. As a consequence,
during hotunplug, the fail injection interface should prohibit all states
from CPUHP_BRINGUP_CPU to CPUHP_ONLINE.
Signed-off-by: Vincent Donnefort <vincent.donnefort@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lkml.kernel.org/r/20210216103506.416286-3-vincent.donnefort@arm.com
Currently, the only way of resetting the fail injection is to trigger a
hotplug, hotunplug or both. This is rather annoying for testing
and, as the default value for this file is -1, it seems pretty natural to
let a user write it.
Signed-off-by: Vincent Donnefort <vincent.donnefort@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lkml.kernel.org/r/20210216103506.416286-2-vincent.donnefort@arm.com
Being called for each dequeue, util_est reduces the number of its updates
by filtering out when the EWMA signal is different from the task util_avg
by less than 1%. It is a problem for a sudden util_avg ramp-up. Due to the
decay from a previous high util_avg, EWMA might now be close enough to
the new util_avg. No update would then happen while it would leave
ue.enqueued with an out-of-date value.
Taking into consideration the two util_est members, EWMA and enqueued for
the filtering, ensures, for both, an up-to-date value.
This is for now an issue only for the trace probe that might return the
stale value. Functional-wise, it isn't a problem, as the value is always
accessed through max(enqueued, ewma).
This problem has been observed using LISA's UtilConvergence:test_means on
the sd845c board.
No regression observed with Hackbench on sd845c and Perf-bench sched pipe
on hikey/hikey960.
Signed-off-by: Vincent Donnefort <vincent.donnefort@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Dietmar Eggemann <dietmar.eggemann@arm.com>
Reviewed-by: Vincent Guittot <vincent.guittot@linaro.org>
Link: https://lkml.kernel.org/r/20210225165820.1377125-1-vincent.donnefort@arm.com
Syzbot reported a handful of occurrences where an sd->nr_balance_failed can
grow to much higher values than one would expect.
A successful load_balance() resets it to 0; a failed one increments
it. Once it gets to sd->cache_nice_tries + 3, this *should* trigger an
active balance, which will either set it to sd->cache_nice_tries+1 or reset
it to 0. However, in case the to-be-active-balanced task is not allowed to
run on env->dst_cpu, then the increment is done without any further
modification.
This could then be repeated ad nauseam, and would explain the absurdly high
values reported by syzbot (86, 149). VincentG noted there is value in
letting sd->cache_nice_tries grow, so the shift itself should be
fixed. That means preventing:
"""
If the value of the right operand is negative or is greater than or equal
to the width of the promoted left operand, the behavior is undefined.
"""
Thus we need to cap the shift exponent to
BITS_PER_TYPE(typeof(lefthand)) - 1.
I had a look around for other similar cases via coccinelle:
@expr@
position pos;
expression E1;
expression E2;
@@
(
E1 >> E2@pos
|
E1 >> E2@pos
)
@cst depends on expr@
position pos;
expression expr.E1;
constant cst;
@@
(
E1 >> cst@pos
|
E1 << cst@pos
)
@script:python depends on !cst@
pos << expr.pos;
exp << expr.E2;
@@
# Dirty hack to ignore constexpr
if exp.upper() != exp:
coccilib.report.print_report(pos[0], "Possible UB shift here")
The only other match in kernel/sched is rq_clock_thermal() which employs
sched_thermal_decay_shift, and that exponent is already capped to 10, so
that one is fine.
Fixes: 5a7f55590467 ("sched/fair: Relax constraint on task's load during load balance")
Reported-by: syzbot+d7581744d5fd27c9fbe1@syzkaller.appspotmail.com
Signed-off-by: Valentin Schneider <valentin.schneider@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: http://lore.kernel.org/r/000000000000ffac1205b9a2112f@google.com
The sub_positive local version is saving an explicit load-store and is
enough for the cpu_util_next() usage.
Signed-off-by: Vincent Donnefort <vincent.donnefort@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Quentin Perret <qperret@google.com>
Reviewed-by: Dietmar Eggemann <dietmar.eggemann@arm.com>
Link: https://lkml.kernel.org/r/20210225083612.1113823-3-vincent.donnefort@arm.com
find_energy_efficient_cpu() (feec()) computes for each perf_domain (pd) an
energy delta as follows:
feec(task)
for_each_pd
base_energy = compute_energy(task, -1, pd)
-> for_each_cpu(pd)
-> cpu_util_next(cpu, task, -1)
energy_delta = compute_energy(task, dst_cpu, pd)
-> for_each_cpu(pd)
-> cpu_util_next(cpu, task, dst_cpu)
energy_delta -= base_energy
Then it picks the best CPU as being the one that minimizes energy_delta.
cpu_util_next() estimates the CPU utilization that would happen if the
task was placed on dst_cpu as follows:
max(cpu_util + task_util, cpu_util_est + _task_util_est)
The task contribution to the energy delta can then be either:
(1) _task_util_est, on a mostly idle CPU, where cpu_util is close to 0
and _task_util_est > cpu_util.
(2) task_util, on a mostly busy CPU, where cpu_util > _task_util_est.
(cpu_util_est doesn't appear here. It is 0 when a CPU is idle and
otherwise must be small enough so that feec() takes the CPU as a
potential target for the task placement)
This is problematic for feec(), as cpu_util_next() might give an unfair
advantage to a CPU which is mostly busy (2) compared to one which is
mostly idle (1). _task_util_est being always bigger than task_util in
feec() (as the task is waking up), the task contribution to the energy
might look smaller on certain CPUs (2) and this breaks the energy
comparison.
This issue is, moreover, not sporadic. By starving idle CPUs, it keeps
their cpu_util < _task_util_est (1) while others will maintain cpu_util >
_task_util_est (2).
Fix this problem by always using max(task_util, _task_util_est) as a task
contribution to the energy (ENERGY_UTIL). The new estimated CPU
utilization for the energy would then be:
max(cpu_util, cpu_util_est) + max(task_util, _task_util_est)
compute_energy() still needs to know which OPP would be selected if the
task would be migrated in the perf_domain (FREQUENCY_UTIL). Hence,
cpu_util_next() is still used to estimate the maximum util within the pd.
Signed-off-by: Vincent Donnefort <vincent.donnefort@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Quentin Perret <qperret@google.com>
Reviewed-by: Dietmar Eggemann <dietmar.eggemann@arm.com>
Link: https://lkml.kernel.org/r/20210225083612.1113823-2-vincent.donnefort@arm.com
Start to update last_blocked_load_update_tick to reduce the possibility
of another cpu starting the update one more time
Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Valentin Schneider <valentin.schneider@arm.com>
Link: https://lkml.kernel.org/r/20210224133007.28644-8-vincent.guittot@linaro.org
Instead of waking up a random and already idle CPU, we can take advantage
of this_cpu being about to enter idle to run the ILB and update the
blocked load.
Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Valentin Schneider <valentin.schneider@arm.com>
Link: https://lkml.kernel.org/r/20210224133007.28644-7-vincent.guittot@linaro.org
The function sync_runqueues_membarrier_state() should copy the
membarrier state from the @mm received as parameter to each runqueue
currently running tasks using that mm.
However, the use of smp_call_function_many() skips the current runqueue,
which is unintended. Replace by a call to on_each_cpu_mask().
Fixes: 227a4aadc75b ("sched/membarrier: Fix p->mm->membarrier_state racy load")
Reported-by: Nadav Amit <nadav.amit@gmail.com>
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: stable@vger.kernel.org # 5.4.x+
Link: https://lore.kernel.org/r/74F1E842-4A84-47BF-B6C2-5407DFDD4A4A@gmail.com
Reorder the tests and skip useless ones when no load balance has been
performed and rq lock has not been released.
Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Valentin Schneider <valentin.schneider@arm.com>
Link: https://lkml.kernel.org/r/20210224133007.28644-6-vincent.guittot@linaro.org
Now that we have set_affinity_pending::stop_pending to indicate if a
stopper is in progress, and we have the guarantee that if that stopper
exists, it will (eventually) complete our @pending we can simplify the
refcount scheme by no longer counting the stopper thread.
Fixes: 6d337eab041d ("sched: Fix migrate_disable() vs set_cpus_allowed_ptr()")
Cc: stable@kernel.org
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Valentin Schneider <valentin.schneider@arm.com>
Link: https://lkml.kernel.org/r/20210224131355.724130207@infradead.org
Remove the specific case for handling this_cpu outside for_each_cpu() loop
when running ILB. Instead we use for_each_cpu_wrap() and start with the
next cpu after this_cpu so we will continue to finish with this_cpu.
update_nohz_stats() is now used for this_cpu too and will prevents
unnecessary update. We don't need a special case for handling the update of
nohz.next_balance for this_cpu anymore because it is now handled by the
loop like others.
Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Valentin Schneider <valentin.schneider@arm.com>
Link: https://lkml.kernel.org/r/20210224133007.28644-5-vincent.guittot@linaro.org
Consider:
sched_setaffinity(p, X); sched_setaffinity(p, Y);
Then the first will install p->migration_pending = &my_pending; and
issue stop_one_cpu_nowait(pending); and the second one will read
p->migration_pending and _also_ issue: stop_one_cpu_nowait(pending),
the _SAME_ @pending.
This causes stopper list corruption.
Add set_affinity_pending::stop_pending, to indicate if a stopper is in
progress.
Fixes: 6d337eab041d ("sched: Fix migrate_disable() vs set_cpus_allowed_ptr()")
Cc: stable@kernel.org
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Valentin Schneider <valentin.schneider@arm.com>
Link: https://lkml.kernel.org/r/20210224131355.649146419@infradead.org
idle load balance is the only user of update_nohz_stats and doesn't use
force parameter. Remove it
Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Valentin Schneider <valentin.schneider@arm.com>
Link: https://lkml.kernel.org/r/20210224133007.28644-4-vincent.guittot@linaro.org
When the purpose of migration_cpu_stop() is to migrate the task to
'any' valid CPU, don't migrate the task when it's already running on a
valid CPU.
Fixes: 6d337eab041d ("sched: Fix migrate_disable() vs set_cpus_allowed_ptr()")
Cc: stable@kernel.org
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Valentin Schneider <valentin.schneider@arm.com>
Link: https://lkml.kernel.org/r/20210224131355.569238629@infradead.org
The return of _nohz_idle_balance() is not used anymore so we can remove
it
Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Valentin Schneider <valentin.schneider@arm.com>
Link: https://lkml.kernel.org/r/20210224133007.28644-3-vincent.guittot@linaro.org
The SCA_MIGRATE_ENABLE and task_running() cases are almost identical,
collapse them to avoid further duplication.
Fixes: 6d337eab041d ("sched: Fix migrate_disable() vs set_cpus_allowed_ptr()")
Cc: stable@kernel.org
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Valentin Schneider <valentin.schneider@arm.com>
Link: https://lkml.kernel.org/r/20210224131355.500108964@infradead.org
newidle_balance runs with both preempt and irq disabled which prevent
local irq to run during this period. The duration for updating the
blocked load of CPUs varies according to the number of CPU cgroups
with non-decayed load and extends this critical period to an uncontrolled
level.
Remove the update from newidle_balance and trigger a normal ILB that
will take care of the update instead.
This reduces the IRQ latency from O(nr_cgroups * nr_nohz_cpus) to
O(nr_cgroups).
Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Valentin Schneider <valentin.schneider@arm.com>
Link: https://lkml.kernel.org/r/20210224133007.28644-2-vincent.guittot@linaro.org
Since, when ->stop_pending, only the stopper can uninstall
p->migration_pending. This could simplify a few ifs, because:
(pending != NULL) => (pending == p->migration_pending)
Also, the fatty comment above affine_move_task() probably needs a bit
of gardening.
Signed-off-by: Valentin Schneider <valentin.schneider@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
When affine_move_task() issues a migration_cpu_stop(), the purpose of
that function is to complete that @pending, not any random other
p->migration_pending that might have gotten installed since.
This realization much simplifies migration_cpu_stop() and allows
further necessary steps to fix all this as it provides the guarantee
that @pending's stopper will complete @pending (and not some random
other @pending).
Fixes: 6d337eab041d ("sched: Fix migrate_disable() vs set_cpus_allowed_ptr()")
Cc: stable@kernel.org
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Valentin Schneider <valentin.schneider@arm.com>
Link: https://lkml.kernel.org/r/20210224131355.430014682@infradead.org
When affine_move_task(p) is called on a running task @p, which is not
otherwise already changing affinity, we'll first set
p->migration_pending and then do:
stop_one_cpu(cpu_of_rq(rq), migration_cpu_stop, &arg);
This then gets us to migration_cpu_stop() running on the CPU that was
previously running our victim task @p.
If we find that our task is no longer on that runqueue (this can
happen because of a concurrent migration due to load-balance etc.),
then we'll end up at the:
} else if (dest_cpu < 1 || pending) {
branch. Which we'll take because we set pending earlier. Here we first
check if the task @p has already satisfied the affinity constraints,
if so we bail early [A]. Otherwise we'll reissue migration_cpu_stop()
onto the CPU that is now hosting our task @p:
stop_one_cpu_nowait(cpu_of(rq), migration_cpu_stop,
&pending->arg, &pending->stop_work);
Except, we've never initialized pending->arg, which will be all 0s.
This then results in running migration_cpu_stop() on the next CPU with
arg->p == NULL, which gives the by now obvious result of fireworks.
The cure is to change affine_move_task() to always use pending->arg,
furthermore we can use the exact same pattern as the
SCA_MIGRATE_ENABLE case, since we'll block on the pending->done
completion anyway, no point in adding yet another completion in
stop_one_cpu().
This then gives a clear distinction between the two
migration_cpu_stop() use cases:
- sched_exec() / migrate_task_to() : arg->pending == NULL
- affine_move_task() : arg->pending != NULL;
And we can have it ignore p->migration_pending when !arg->pending. Any
stop work from sched_exec() / migrate_task_to() is in addition to stop
works from affine_move_task(), which will be sufficient to issue the
completion.
Fixes: 6d337eab041d ("sched: Fix migrate_disable() vs set_cpus_allowed_ptr()")
Cc: stable@kernel.org
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Valentin Schneider <valentin.schneider@arm.com>
Link: https://lkml.kernel.org/r/20210224131355.357743989@infradead.org
-----BEGIN PGP SIGNATURE-----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=w0Sf
-----END PGP SIGNATURE-----
Merge tag 'io_uring-5.12-2021-03-05' of git://git.kernel.dk/linux-block
Pull io_uring fixes from Jens Axboe:
"A bit of a mix between fallout from the worker change, cleanups and
reductions now possible from that change, and fixes in general. In
detail:
- Fully serialize manager and worker creation, fixing races due to
that.
- Clean up some naming that had gone stale.
- SQPOLL fixes.
- Fix race condition around task_work rework that went into this
merge window.
- Implement unshare. Used for when the original task does unshare(2)
or setuid/seteuid and friends, drops the original workers and forks
new ones.
- Drop the only remaining piece of state shuffling we had left, which
was cred. Move it into issue instead, and we can drop all of that
code too.
- Kill f_op->flush() usage. That was such a nasty hack that we had
out of necessity, we no longer need it.
- Following from ->flush() removal, we can also drop various bits of
ctx state related to SQPOLL and cancelations.
- Fix an issue with IOPOLL retry, which originally was fallout from a
filemap change (removing iov_iter_revert()), but uncovered an issue
with iovec re-import too late.
- Fix an issue with system suspend.
- Use xchg() for fallback work, instead of cmpxchg().
- Properly destroy io-wq on exec.
- Add create_io_thread() core helper, and use that in io-wq and
io_uring. This allows us to remove various silly completion events
related to thread setup.
- A few error handling fixes.
This should be the grunt of fixes necessary for the new workers, next
week should be quieter. We've got a pending series from Pavel on
cancelations, and how tasks and rings are indexed. Outside of that,
should just be minor fixes. Even with these fixes, we're still killing
a net ~80 lines"
* tag 'io_uring-5.12-2021-03-05' of git://git.kernel.dk/linux-block: (41 commits)
io_uring: don't restrict issue_flags for io_openat
io_uring: make SQPOLL thread parking saner
io-wq: kill hashed waitqueue before manager exits
io_uring: clear IOCB_WAITQ for non -EIOCBQUEUED return
io_uring: don't keep looping for more events if we can't flush overflow
io_uring: move to using create_io_thread()
kernel: provide create_io_thread() helper
io_uring: reliably cancel linked timeouts
io_uring: cancel-match based on flags
io-wq: ensure all pending work is canceled on exit
io_uring: ensure that threads freeze on suspend
io_uring: remove extra in_idle wake up
io_uring: inline __io_queue_async_work()
io_uring: inline io_req_clean_work()
io_uring: choose right tctx->io_wq for try cancel
io_uring: fix -EAGAIN retry with IOPOLL
io-wq: fix error path leak of buffered write hash map
io_uring: remove sqo_task
io_uring: kill sqo_dead and sqo submission halting
io_uring: ignore double poll add on the same waitqueue head
...
As pointed out by Ilya and explained in the new comment, there's a
discrepancy between x86 and BPF CMPXCHG semantics: BPF always loads
the value from memory into r0, while x86 only does so when r0 and the
value in memory are different. The same issue affects s390.
At first this might sound like pure semantics, but it makes a real
difference when the comparison is 32-bit, since the load will
zero-extend r0/rax.
The fix is to explicitly zero-extend rax after doing such a
CMPXCHG. Since this problem affects multiple archs, this is done in
the verifier by patching in a BPF_ZEXT_REG instruction after every
32-bit cmpxchg. Any archs that don't need such manual zero-extension
can do a look-ahead with insn_is_zext to skip the unnecessary mov.
Note this still goes on top of Ilya's patch:
https://lore.kernel.org/bpf/20210301154019.129110-1-iii@linux.ibm.com/T/#u
Differences v5->v6[1]:
- Moved is_cmpxchg_insn and ensured it can be safely re-used. Also renamed it
and removed 'inline' to match the style of the is_*_function helpers.
- Fixed up comments in verifier test (thanks for the careful review, Martin!)
Differences v4->v5[1]:
- Moved the logic entirely into opt_subreg_zext_lo32_rnd_hi32, thanks to Martin
for suggesting this.
Differences v3->v4[1]:
- Moved the optimization against pointless zext into the correct place:
opt_subreg_zext_lo32_rnd_hi32 is called _after_ fixup_bpf_calls.
Differences v2->v3[1]:
- Moved patching into fixup_bpf_calls (patch incoming to rename this function)
- Added extra commentary on bpf_jit_needs_zext
- Added check to avoid adding a pointless zext(r0) if there's already one there.
Difference v1->v2[1]: Now solved centrally in the verifier instead of
specifically for the x86 JIT. Thanks to Ilya and Daniel for the suggestions!
[1] v5: https://lore.kernel.org/bpf/CA+i-1C3ytZz6FjcPmUg5s4L51pMQDxWcZNvM86w4RHZ_o2khwg@mail.gmail.com/T/#t
v4: https://lore.kernel.org/bpf/CA+i-1C3ytZz6FjcPmUg5s4L51pMQDxWcZNvM86w4RHZ_o2khwg@mail.gmail.com/T/#t
v3: https://lore.kernel.org/bpf/08669818-c99d-0d30-e1db-53160c063611@iogearbox.net/T/#t
v2: https://lore.kernel.org/bpf/08669818-c99d-0d30-e1db-53160c063611@iogearbox.net/T/#t
v1: https://lore.kernel.org/bpf/d7ebaefb-bfd6-a441-3ff2-2fdfe699b1d2@iogearbox.net/T/#t
Reported-by: Ilya Leoshkevich <iii@linux.ibm.com>
Fixes: 5ffa25502b5a ("bpf: Add instructions for atomic_[cmp]xchg")
Signed-off-by: Brendan Jackman <jackmanb@google.com>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Acked-by: Ilya Leoshkevich <iii@linux.ibm.com>
Tested-by: Ilya Leoshkevich <iii@linux.ibm.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
On the kernel side, introduce a new btf_kind_operations. It is
similar to that of BTF_KIND_INT, however, it does not need to
handle encodings and bit offsets. Do not implement printing, since
the kernel does not know how to format floating-point values.
Signed-off-by: Ilya Leoshkevich <iii@linux.ibm.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Yonghong Song <yhs@fb.com>
Link: https://lore.kernel.org/bpf/20210226202256.116518-7-iii@linux.ibm.com
Provide a generic helper for setting up an io_uring worker. Returns a
task_struct so that the caller can do whatever setup is needed, then call
wake_up_new_task() to kick it into gear.
Add a kernel_clone_args member, io_thread, which tells copy_process() to
mark the task with PF_IO_WORKER.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
insn_has_def32() returns false for 32-bit BPF_FETCH insns. This makes
adjust_insn_aux_data() incorrectly set zext_dst, as can be seen in [1].
This happens because insn_no_def() does not know about the BPF_FETCH
variants of BPF_STX.
Fix in two steps.
First, replace insn_no_def() with insn_def_regno(), which returns the
register an insn defines. Normally insn_no_def() calls are followed by
insn->dst_reg uses; replace those with the insn_def_regno() return
value.
Second, adjust the BPF_STX special case in is_reg64() to deal with
queries made from opt_subreg_zext_lo32_rnd_hi32(), where the state
information is no longer available. Add a comment, since the purpose
of this special case is not clear at first glance.
[1] https://lore.kernel.org/bpf/20210223150845.1857620-1-jackmanb@google.com/
Fixes: 5ffa25502b5a ("bpf: Add instructions for atomic_[cmp]xchg")
Signed-off-by: Ilya Leoshkevich <iii@linux.ibm.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Acked-by: Brendan Jackman <jackmanb@google.com>
Link: https://lore.kernel.org/bpf/20210301154019.129110-1-iii@linux.ibm.com
If tracing is disabled for some reason (traceoff_on_warning, command line,
etc), the ftrace selftests are guaranteed to fail, as their results are
defined by trace data in the ring buffers. If the ring buffers are turned
off, the tests will fail, due to lack of data.
Because tracing being disabled is for a specific reason (warning, user
decided to, etc), it does not make sense to enable tracing to run the self
tests, as the test output may corrupt the reason for the tracing to be
disabled.
Instead, simply skip the self tests and report that they are being skipped
due to tracing being disabled.
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
When the CONFIG_RING_BUFFER_VALIDATE_TIME_DELTAS is enabled, and the time
stamps are detected as not being valid, it reports information about the
write stamp, but does not show the before_stamp which is still useful
information. Also, it should give a warning once, such that tests detect
this happening.
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Part of the logic of the new time stamp code depends on the before_stamp and
the write_stamp to be different if the write_stamp does not match the last
event on the buffer, as it will be used to calculate the delta of the next
event written on the buffer.
The discard logic depends on this, as the next event to come in needs to
inject a full timestamp as it can not rely on the last event timestamp in
the buffer because it is unknown due to events after it being discarded. But
by changing the write_stamp back to the time before it, it forces the next
event to use a full time stamp, instead of relying on it.
The issue came when a full time stamp was used for the event, and
rb_time_delta() returns zero in that case. The update to the write_stamp
(which subtracts delta) made it not change. Then when the event is removed
from the buffer, because the before_stamp and write_stamp still match, the
next event written would calculate its delta from the write_stamp, but that
would be wrong as the write_stamp is of the time of the event that was
discarded.
In the case that the delta change being made to write_stamp is zero, set the
before_stamp to zero as well, and this will force the next event to inject a
full timestamp and not use the current write_stamp.
Cc: stable@vger.kernel.org
Fixes: a389d86f7fd09 ("ring-buffer: Have nested events still record running time stamp")
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
