| Age | Commit message (Collapse) | Author | Files | Lines |
|---|
|
With delayed dequeued feature, a sleeping sched_entity remains queued
in the rq until its lag has elapsed but can't run.
Rename h_nr_running into h_nr_queued to reflect this new behavior.
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>
Link: https://lore.kernel.org/r/20241202174606.4074512-4-vincent.guittot@linaro.org
|
|
Vincent and Dietmar noted that while
commit fc1892becd56 ("sched/eevdf: Fixup PELT vs DELAYED_DEQUEUE") fixes
the entity runnable stats, it does not adjust the cfs_rq runnable stats,
which are based off of h_nr_running.
Track h_nr_delayed such that we can discount those and adjust the
signal.
Fixes: fc1892becd56 ("sched/eevdf: Fixup PELT vs DELAYED_DEQUEUE")
Closes: https://lore.kernel.org/lkml/a9a45193-d0c6-4ba2-a822-464ad30b550e@arm.com/
Closes: https://lore.kernel.org/lkml/CAKfTPtCNUvWE_GX5LyvTF-WdxUT=ZgvZZv-4t=eWntg5uOFqiQ@mail.gmail.com/
[ Fixes checkpatch warnings and rebased ]
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reported-by: Dietmar Eggemann <dietmar.eggemann@arm.com>
Reported-by: Vincent Guittot <vincent.guittot@linaro.org>
Signed-off-by: "Peter Zijlstra (Intel)" <peterz@infradead.org>
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>
Tested-by: K Prateek Nayak <kprateek.nayak@amd.com>
Link: https://lore.kernel.org/r/20241202174606.4074512-3-vincent.guittot@linaro.org
|
|
We can't stop the tick of a rq if there are at least 2 tasks enqueued in
the whole hierarchy and not only at the root cfs rq.
rq->cfs.nr_running tracks the number of sched_entity at one level
whereas rq->cfs.h_nr_running tracks all queued tasks in the
hierarchy.
Fixes: 11cc374f4643b ("sched_ext: Simplify scx_can_stop_tick() invocation in sched_can_stop_tick()")
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>
Link: https://lore.kernel.org/r/20241202174606.4074512-2-vincent.guittot@linaro.org
|
|
Adam reports that enabling NEXT_BUDDY insta triggers a WARN in
pick_next_entity().
Moving clear_buddies() up before the delayed dequeue bits ensures
no ->next buddy becomes delayed. Further ensure no new ->next buddy
ever starts as delayed.
Fixes: 152e11f6df29 ("sched/fair: Implement delayed dequeue")
Reported-by: Adam Li <adamli@os.amperecomputing.com>
Signed-off-by: K Prateek Nayak <kprateek.nayak@amd.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Tested-by: Adam Li <adamli@os.amperecomputing.com>
Link: https://lkml.kernel.org/r/670a0d54-e398-4b1f-8a6e-90784e2fdf89@amd.com
|
|
As all the non-domain and non-managed_irq housekeeping types have been
unified to HK_TYPE_KERNEL_NOISE, replace all these references in the
scheduler to use HK_TYPE_KERNEL_NOISE.
Signed-off-by: Waiman Long <longman@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Frederic Weisbecker <frederic@kernel.org>
Link: https://lore.kernel.org/r/20241030175253.125248-5-longman@redhat.com
|
|
The housekeeping cpumasks are only set by two boot commandline
parameters: "nohz_full" and "isolcpus". When there is more than one of
"nohz_full" or "isolcpus", the extra ones must have the same CPU list
or the setup will fail partially.
The HK_TYPE_DOMAIN and HK_TYPE_MANAGED_IRQ types are settable by
"isolcpus" only and their settings can be independent of the other
types. The other housekeeping types are all set by "nohz_full" or
"isolcpus=nohz" without a way to set them individually. So they all
have identical cpumasks.
There is actually no point in having different cpumasks for these
"nohz_full" only housekeeping types. Consolidate these types to use the
same cpumask by aliasing them to the same value. If there is a need to
set any of them independently in the future, we can break them out to
their own cpumasks again.
With this change, the number of cpumasks in the housekeeping structure
drops from 9 to 3. Other than that, there should be no other functional
change.
Signed-off-by: Waiman Long <longman@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Frederic Weisbecker <frederic@kernel.org>
Link: https://lore.kernel.org/r/20241030175253.125248-4-longman@redhat.com
|
|
The "isolcpus=nohz" boot parameter and flag were used to disable tick
when running a single task. Nowsdays, this "nohz" flag is seldomly used
as it is included as part of the "nohz_full" parameter. Extend this
flag to cover other kernel noises disabled by the "nohz_full" parameter
to make them equivalent. This also eliminates the need to use both the
"isolcpus" and the "nohz_full" parameters to fully isolated a given
set of CPUs.
Suggested-by: Frederic Weisbecker <frederic@kernel.org>
Signed-off-by: Waiman Long <longman@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Frederic Weisbecker <frederic@kernel.org>
Link: https://lore.kernel.org/r/20241030175253.125248-3-longman@redhat.com
|
|
The HK_TYPE_SCHED housekeeping type is defined but not set anywhere. So
any code that try to use HK_TYPE_SCHED are essentially dead code. So
remove HK_TYPE_SCHED and any code that use it.
Signed-off-by: Waiman Long <longman@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Frederic Weisbecker <frederic@kernel.org>
Link: https://lore.kernel.org/r/20241030175253.125248-2-longman@redhat.com
|
|
Andy reported that clang gets upset with CONFIG_CFS_BANDWIDTH=n:
kernel/sched/fair.c:6580:20: error: unused function 'cfs_bandwidth_used' [-Werror,-Wunused-function]
6580 | static inline bool cfs_bandwidth_used(void)
| ^~~~~~~~~~~~~~~~~~
Indeed, cfs_bandwidth_used() is only used within functions defined under
CONFIG_CFS_BANDWIDTH=y. Remove its CONFIG_CFS_BANDWIDTH=n declaration &
definition.
Reported-by: Andy Shevchenko <andy.shevchenko@gmail.com>
Signed-off-by: Valentin Schneider <vschneid@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Andy Shevchenko <andy.shevchenko@gmail.com>
Link: https://lore.kernel.org/r/20241127165501.160004-1-vschneid@redhat.com
|
|
After commit b58652db66c9 ("sched/deadline: Fix task_struct reference
leak"), I identified additional calls to hrtimer_try_to_cancel that
might also require a dl_server check. It remains unclear whether this
omission was intentional or accidental in those contexts.
This patch consolidates the timer cancellation logic into dedicated
functions, ensuring consistent behavior across all calls.
Additionally, it reduces code duplication and improves overall code
cleanliness.
Note the use of the __always_inline keyword. In some instances, we
have a task_struct pointer, dereference the dl member, and then use
the container_of macro to retrieve the task_struct pointer again. By
inlining the code, the compiler can potentially optimize out this
redundant round trip.
Signed-off-by: Wander Lairson Costa <wander@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Juri Lelli <juri.lelli@redhat.com>
Link: https://lore.kernel.org/r/20240724142253.27145-3-wander@redhat.com
|
|
Currently we check for bandwidth overflow potentially due to hotplug
operations at the end of sched_cpu_deactivate(), after the cpu going
offline has already been removed from scheduling, active_mask, etc.
This can create issues for DEADLINE tasks, as there is a substantial
race window between the start of sched_cpu_deactivate() and the moment
we possibly decide to roll-back the operation if dl_bw_deactivate()
returns failure in cpuset_cpu_inactive(). An example is a throttled
task that sees its replenishment timer firing while the cpu it was
previously running on is considered offline, but before
dl_bw_deactivate() had a chance to say no and roll-back happened.
Fix this by directly calling dl_bw_deactivate() first thing in
sched_cpu_deactivate() and do the required calculation in the former
function considering the cpu passed as an argument as offline already.
By doing so we also simplify sched_cpu_deactivate(), as there is no need
anymore for any kind of roll-back if we fail early.
Signed-off-by: Juri Lelli <juri.lelli@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Phil Auld <pauld@redhat.com>
Tested-by: Waiman Long <longman@redhat.com>
Link: https://lore.kernel.org/r/Zzc1DfPhbvqDDIJR@jlelli-thinkpadt14gen4.remote.csb
|
|
For hotplug operations, DEADLINE needs to check that there is still enough
bandwidth left after removing the CPU that is going offline. We however
fail to do so currently.
Restore the correct behavior by restructuring dl_bw_manage() a bit, so
that overflow conditions (not enough bandwidth left) are properly
checked. Also account for dl_server bandwidth, i.e. discount such
bandwidth in the calculation since NORMAL tasks will be anyway moved
away from the CPU as a result of the hotplug operation.
Signed-off-by: Juri Lelli <juri.lelli@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Phil Auld <pauld@redhat.com>
Tested-by: Waiman Long <longman@redhat.com>
Link: https://lore.kernel.org/r/20241114142810.794657-3-juri.lelli@redhat.com
|
|
When root domain non-destructive changes (e.g., only modifying one of
the existing root domains while the rest is not touched) happen we still
need to clear DEADLINE bandwidth accounting so that it's then properly
restored, taking into account DEADLINE tasks associated to each cpuset
(associated to each root domain). After the introduction of dl_servers,
we fail to restore such servers contribution after non-destructive
changes (as they are only considered on destructive changes when
runqueues are attached to the new domains).
Fix this by making sure we iterate over the dl_servers attached to
domains that have not been destroyed and add their bandwidth
contribution back correctly.
Signed-off-by: Juri Lelli <juri.lelli@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Phil Auld <pauld@redhat.com>
Tested-by: Waiman Long <longman@redhat.com>
Link: https://lore.kernel.org/r/20241114142810.794657-2-juri.lelli@redhat.com
|
|
task_on_rq_queued read p->on_rq without READ_ONCE, though p->on_rq is
set with WRITE_ONCE in {activate|deactivate}_task and smp_store_release
in __block_task, and also read with READ_ONCE in task_on_rq_migrating.
Make all of these accesses pair together by adding READ_ONCE in the
task_on_rq_queued.
Signed-off-by: Harshit Agarwal <harshit@nutanix.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Phil Auld <pauld@redhat.com>
Link: https://lkml.kernel.org/r/20241114210812.1836587-1-jon@nutanix.com
|
|
When steal time exceeds the measured delta when updating clock_task, we
currently try to catch up the excess in future updates.
However, this results in inaccurate run times for the future things using
clock_task, in some situations, as they end up getting additional steal
time that did not actually happen.
This is because there is a window between reading the elapsed time in
update_rq_clock() and sampling the steal time in update_rq_clock_task().
If the VCPU gets preempted between those two points, any additional
steal time is accounted to the outgoing task even though the calculated
delta did not actually contain any of that "stolen" time.
When this race happens, we can end up with steal time that exceeds the
calculated delta, and the previous code would try to catch up that excess
steal time in future clock updates, which is given to the next,
incoming task, even though it did not actually have any time stolen.
This behavior is particularly bad when steal time can be very long,
which we've seen when trying to extend steal time to contain the duration
that the host was suspended [0]. When this happens, clock_task stays
frozen, during which the running task stays running for the whole
duration, since its run time doesn't increase.
However the race can happen even under normal operation.
Ideally we would read the elapsed cpu time and the steal time atomically,
to prevent this race from happening in the first place, but doing so
is non-trivial.
Since the time between those two points isn't otherwise accounted anywhere,
neither to the outgoing task nor the incoming task (because the "end of
outgoing task" and "start of incoming task" timestamps are the same),
I would argue that the right thing to do is to simply drop any excess steal
time, in order to prevent these issues.
[0] https://lore.kernel.org/kvm/20240820043543.837914-1-suleiman@google.com/
Signed-off-by: Suleiman Souhlal <suleiman@google.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/20241118043745.1857272-1-suleiman@google.com
|
|
Anders had bisected a crash using PREEMPT_RT with linux-next and
isolated it down to commit 894d1b3db41c ("locking/mutex: Remove
wakeups from under mutex::wait_lock"), where it seemed the
wake_q structure was somehow getting corrupted causing a null
pointer traversal.
I was able to easily repoduce this with PREEMPT_RT and managed
to isolate down that through various call stacks we were
actually calling wake_up_q() twice on the same wake_q.
I found that in the problematic commit, I had added the
wake_up_q() call in task_blocks_on_rt_mutex() around
__ww_mutex_add_waiter(), following a similar pattern in
__mutex_lock_common().
However, its just wrong. We haven't dropped the lock->wait_lock,
so its contrary to the point of the original patch. And it
didn't match the __mutex_lock_common() logic of re-initializing
the wake_q after calling it midway in the stack.
Looking at it now, the wake_up_q() call is incorrect and should
just be removed. So drop the erronious logic I had added.
Fixes: 894d1b3db41c ("locking/mutex: Remove wakeups from under mutex::wait_lock")
Closes: https://lore.kernel.org/lkml/6afb936f-17c7-43fa-90e0-b9e780866097@app.fastmail.com/
Reported-by: Anders Roxell <anders.roxell@linaro.org>
Reported-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: John Stultz <jstultz@google.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Juri Lelli <juri.lelli@redhat.com>
Tested-by: Anders Roxell <anders.roxell@linaro.org>
Tested-by: K Prateek Nayak <kprateek.nayak@amd.com>
Link: https://lore.kernel.org/r/20241114190051.552665-1-jstultz@google.com
|
|
When running the following command:
while true; do
stress-ng --cyclic 30 --timeout 30s --minimize --quiet
done
a warning is eventually triggered:
WARNING: CPU: 43 PID: 2848 at kernel/sched/deadline.c:794
setup_new_dl_entity+0x13e/0x180
...
Call Trace:
<TASK>
? show_trace_log_lvl+0x1c4/0x2df
? enqueue_dl_entity+0x631/0x6e0
? setup_new_dl_entity+0x13e/0x180
? __warn+0x7e/0xd0
? report_bug+0x11a/0x1a0
? handle_bug+0x3c/0x70
? exc_invalid_op+0x14/0x70
? asm_exc_invalid_op+0x16/0x20
enqueue_dl_entity+0x631/0x6e0
enqueue_task_dl+0x7d/0x120
__do_set_cpus_allowed+0xe3/0x280
__set_cpus_allowed_ptr_locked+0x140/0x1d0
__set_cpus_allowed_ptr+0x54/0xa0
migrate_enable+0x7e/0x150
rt_spin_unlock+0x1c/0x90
group_send_sig_info+0xf7/0x1a0
? kill_pid_info+0x1f/0x1d0
kill_pid_info+0x78/0x1d0
kill_proc_info+0x5b/0x110
__x64_sys_kill+0x93/0xc0
do_syscall_64+0x5c/0xf0
entry_SYSCALL_64_after_hwframe+0x6e/0x76
RIP: 0033:0x7f0dab31f92b
This warning occurs because set_cpus_allowed dequeues and enqueues tasks
with the ENQUEUE_RESTORE flag set. If the task is boosted, the warning
is triggered. A boosted task already had its parameters set by
rt_mutex_setprio, and a new call to setup_new_dl_entity is unnecessary,
hence the WARN_ON call.
Check if we are requeueing a boosted task and avoid calling
setup_new_dl_entity if that's the case.
Fixes: 295d6d5e3736 ("sched/deadline: Fix switching to -deadline")
Signed-off-by: Wander Lairson Costa <wander@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Juri Lelli <juri.lelli@redhat.com>
Link: https://lore.kernel.org/r/20240724142253.27145-2-wander@redhat.com
|
|
Update the documentation for the `preempt=' parameter which now also
accepts `lazy'.
Fixes: 7c70cb94d29cd ("sched: Add Lazy preemption model")
Reported-by: Shrikanth Hegde <sshegde@linux.ibm.com>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Shrikanth Hegde <sshegde@linux.ibm.com>
Link: https://lore.kernel.org/r/20241122173557.MYOtT95Q@linutronix.de
|
|
Scheduler raises a SCHED_SOFTIRQ to trigger a load balancing event on
from the IPI handler on the idle CPU. If the SMP function is invoked
from an idle CPU via flush_smp_call_function_queue() then the HARD-IRQ
flag is not set and raise_softirq_irqoff() needlessly wakes ksoftirqd
because soft interrupts are handled before ksoftirqd get on the CPU.
Adding a trace_printk() in nohz_csd_func() at the spot of raising
SCHED_SOFTIRQ and enabling trace events for sched_switch, sched_wakeup,
and softirq_entry (for SCHED_SOFTIRQ vector alone) helps observing the
current behavior:
<idle>-0 [000] dN.1.: nohz_csd_func: Raising SCHED_SOFTIRQ from nohz_csd_func
<idle>-0 [000] dN.4.: sched_wakeup: comm=ksoftirqd/0 pid=16 prio=120 target_cpu=000
<idle>-0 [000] .Ns1.: softirq_entry: vec=7 [action=SCHED]
<idle>-0 [000] .Ns1.: softirq_exit: vec=7 [action=SCHED]
<idle>-0 [000] d..2.: sched_switch: prev_comm=swapper/0 prev_pid=0 prev_prio=120 prev_state=R ==> next_comm=ksoftirqd/0 next_pid=16 next_prio=120
ksoftirqd/0-16 [000] d..2.: sched_switch: prev_comm=ksoftirqd/0 prev_pid=16 prev_prio=120 prev_state=S ==> next_comm=swapper/0 next_pid=0 next_prio=120
...
Use __raise_softirq_irqoff() to raise the softirq. The SMP function call
is always invoked on the requested CPU in an interrupt handler. It is
guaranteed that soft interrupts are handled at the end.
Following are the observations with the changes when enabling the same
set of events:
<idle>-0 [000] dN.1.: nohz_csd_func: Raising SCHED_SOFTIRQ for nohz_idle_balance
<idle>-0 [000] dN.1.: softirq_raise: vec=7 [action=SCHED]
<idle>-0 [000] .Ns1.: softirq_entry: vec=7 [action=SCHED]
No unnecessary ksoftirqd wakeups are seen from idle task's context to
service the softirq.
Fixes: b2a02fc43a1f ("smp: Optimize send_call_function_single_ipi()")
Closes: https://lore.kernel.org/lkml/fcf823f-195e-6c9a-eac3-25f870cb35ac@inria.fr/ [1]
Reported-by: Julia Lawall <julia.lawall@inria.fr>
Suggested-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: K Prateek Nayak <kprateek.nayak@amd.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Link: https://lore.kernel.org/r/20241119054432.6405-5-kprateek.nayak@amd.com
|
|
Commit b2a02fc43a1f ("smp: Optimize send_call_function_single_ipi()")
optimizes IPIs to idle CPUs in TIF_POLLING_NRFLAG mode by setting the
TIF_NEED_RESCHED flag in idle task's thread info and relying on
flush_smp_call_function_queue() in idle exit path to run the
call-function. A softirq raised by the call-function is handled shortly
after in do_softirq_post_smp_call_flush() but the TIF_NEED_RESCHED flag
remains set and is only cleared later when schedule_idle() calls
__schedule().
need_resched() check in _nohz_idle_balance() exists to bail out of load
balancing if another task has woken up on the CPU currently in-charge of
idle load balancing which is being processed in SCHED_SOFTIRQ context.
Since the optimization mentioned above overloads the interpretation of
TIF_NEED_RESCHED, check for idle_cpu() before going with the existing
need_resched() check which can catch a genuine task wakeup on an idle
CPU processing SCHED_SOFTIRQ from do_softirq_post_smp_call_flush(), as
well as the case where ksoftirqd needs to be preempted as a result of
new task wakeup or slice expiry.
In case of PREEMPT_RT or threadirqs, although the idle load balancing
may be inhibited in some cases on the ilb CPU, the fact that ksoftirqd
is the only fair task going back to sleep will trigger a newidle balance
on the CPU which will alleviate some imbalance if it exists if idle
balance fails to do so.
Fixes: b2a02fc43a1f ("smp: Optimize send_call_function_single_ipi()")
Signed-off-by: K Prateek Nayak <kprateek.nayak@amd.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/20241119054432.6405-4-kprateek.nayak@amd.com
|
|
The need_resched() check currently in nohz_csd_func() can be tracked
to have been added in scheduler_ipi() back in 2011 via commit
ca38062e57e9 ("sched: Use resched IPI to kick off the nohz idle balance")
Since then, it has travelled quite a bit but it seems like an idle_cpu()
check currently is sufficient to detect the need to bail out from an
idle load balancing. To justify this removal, consider all the following
case where an idle load balancing could race with a task wakeup:
o Since commit f3dd3f674555b ("sched: Remove the limitation of WF_ON_CPU
on wakelist if wakee cpu is idle") a target perceived to be idle
(target_rq->nr_running == 0) will return true for
ttwu_queue_cond(target) which will offload the task wakeup to the idle
target via an IPI.
In all such cases target_rq->ttwu_pending will be set to 1 before
queuing the wake function.
If an idle load balance races here, following scenarios are possible:
- The CPU is not in TIF_POLLING_NRFLAG mode in which case an actual
IPI is sent to the CPU to wake it out of idle. If the
nohz_csd_func() queues before sched_ttwu_pending(), the idle load
balance will bail out since idle_cpu(target) returns 0 since
target_rq->ttwu_pending is 1. If the nohz_csd_func() is queued after
sched_ttwu_pending() it should see rq->nr_running to be non-zero and
bail out of idle load balancing.
- The CPU is in TIF_POLLING_NRFLAG mode and instead of an actual IPI,
the sender will simply set TIF_NEED_RESCHED for the target to put it
out of idle and flush_smp_call_function_queue() in do_idle() will
execute the call function. Depending on the ordering of the queuing
of nohz_csd_func() and sched_ttwu_pending(), the idle_cpu() check in
nohz_csd_func() should either see target_rq->ttwu_pending = 1 or
target_rq->nr_running to be non-zero if there is a genuine task
wakeup racing with the idle load balance kick.
o The waker CPU perceives the target CPU to be busy
(targer_rq->nr_running != 0) but the CPU is in fact going idle and due
to a series of unfortunate events, the system reaches a case where the
waker CPU decides to perform the wakeup by itself in ttwu_queue() on
the target CPU but target is concurrently selected for idle load
balance (XXX: Can this happen? I'm not sure, but we'll consider the
mother of all coincidences to estimate the worst case scenario).
ttwu_do_activate() calls enqueue_task() which would increment
"rq->nr_running" post which it calls wakeup_preempt() which is
responsible for setting TIF_NEED_RESCHED (via a resched IPI or by
setting TIF_NEED_RESCHED on a TIF_POLLING_NRFLAG idle CPU) The key
thing to note in this case is that rq->nr_running is already non-zero
in case of a wakeup before TIF_NEED_RESCHED is set which would
lead to idle_cpu() check returning false.
In all cases, it seems that need_resched() check is unnecessary when
checking for idle_cpu() first since an impending wakeup racing with idle
load balancer will either set the "rq->ttwu_pending" or indicate a newly
woken task via "rq->nr_running".
Chasing the reason why this check might have existed in the first place,
I came across Peter's suggestion on the fist iteration of Suresh's
patch from 2011 [1] where the condition to raise the SCHED_SOFTIRQ was:
sched_ttwu_do_pending(list);
if (unlikely((rq->idle == current) &&
rq->nohz_balance_kick &&
!need_resched()))
raise_softirq_irqoff(SCHED_SOFTIRQ);
Since the condition to raise the SCHED_SOFIRQ was preceded by
sched_ttwu_do_pending() (which is equivalent of sched_ttwu_pending()) in
the current upstream kernel, the need_resched() check was necessary to
catch a newly queued task. Peter suggested modifying it to:
if (idle_cpu() && rq->nohz_balance_kick && !need_resched())
raise_softirq_irqoff(SCHED_SOFTIRQ);
where idle_cpu() seems to have replaced "rq->idle == current" check.
Even back then, the idle_cpu() check would have been sufficient to catch
a new task being enqueued. Since commit b2a02fc43a1f ("smp: Optimize
send_call_function_single_ipi()") overloads the interpretation of
TIF_NEED_RESCHED for TIF_POLLING_NRFLAG idling, remove the
need_resched() check in nohz_csd_func() to raise SCHED_SOFTIRQ based
on Peter's suggestion.
Fixes: b2a02fc43a1f ("smp: Optimize send_call_function_single_ipi()")
Suggested-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: K Prateek Nayak <kprateek.nayak@amd.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/20241119054432.6405-3-kprateek.nayak@amd.com
|
|
do_softirq_post_smp_call_flush() on PREEMPT_RT kernels carries a
WARN_ON_ONCE() for any SOFTIRQ being raised from an SMP-call-function.
Since do_softirq_post_smp_call_flush() is called with preempt disabled,
raising a SOFTIRQ during flush_smp_call_function_queue() can lead to
longer preempt disabled sections.
Since commit b2a02fc43a1f ("smp: Optimize
send_call_function_single_ipi()") IPIs to an idle CPU in
TIF_POLLING_NRFLAG mode can be optimized out by instead setting
TIF_NEED_RESCHED bit in idle task's thread_info and relying on the
flush_smp_call_function_queue() in the idle-exit path to run the
SMP-call-function.
To trigger an idle load balancing, the scheduler queues
nohz_csd_function() responsible for triggering an idle load balancing on
a target nohz idle CPU and sends an IPI. Only now, this IPI is optimized
out and the SMP-call-function is executed from
flush_smp_call_function_queue() in do_idle() which can raise a
SCHED_SOFTIRQ to trigger the balancing.
So far, this went undetected since, the need_resched() check in
nohz_csd_function() would make it bail out of idle load balancing early
as the idle thread does not clear TIF_POLLING_NRFLAG before calling
flush_smp_call_function_queue(). The need_resched() check was added with
the intent to catch a new task wakeup, however, it has recently
discovered to be unnecessary and will be removed in the subsequent
commit after which nohz_csd_function() can raise a SCHED_SOFTIRQ from
flush_smp_call_function_queue() to trigger an idle load balance on an
idle target in TIF_POLLING_NRFLAG mode.
nohz_csd_function() bails out early if "idle_cpu()" check for the
target CPU, and does not lock the target CPU's rq until the very end,
once it has found tasks to run on the CPU and will not inhibit the
wakeup of, or running of a newly woken up higher priority task. Account
for this and prevent a WARN_ON_ONCE() when SCHED_SOFTIRQ is raised from
flush_smp_call_function_queue().
Signed-off-by: K Prateek Nayak <kprateek.nayak@amd.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/20241119054432.6405-2-kprateek.nayak@amd.com
|
|
Commit 8f9ea86fdf99b added some logic to sched_setaffinity that included
a WARN when a per-task affinity assignment races with a cpuset update.
Specifically, we can have a race where a cpuset update results in the
task affinity no longer being a subset of the cpuset. That's fine; we
have a fallback to instead use the cpuset mask. However, we have a WARN
set up that will trigger if the cpuset mask has no overlap at all with
the requested task affinity. This shouldn't be a warning condition; its
trivial to create this condition.
Reproduced the warning by the following setup:
- $PID inside a cpuset cgroup
- another thread repeatedly switching the cpuset cpus from 1-2 to just 1
- another thread repeatedly setting the $PID affinity (via taskset) to 2
Fixes: 8f9ea86fdf99b ("sched: Always preserve the user requested cpumask")
Signed-off-by: Josh Don <joshdon@google.com>
Acked-and-tested-by: Vincent Guittot <vincent.guittot@linaro.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Waiman Long <longman@redhat.com>
Tested-by: Madadi Vineeth Reddy <vineethr@linux.ibm.com>
Link: https://lkml.kernel.org/r/20241111182738.1832953-1-joshdon@google.com
|
|
The condition in replenish_dl_new_period() that checks if a reservation
(dl_server) is deferred and is not handling a starvation case is
obviously wrong.
Fix it.
Fixes: a110a81c52a9 ("sched/deadline: Deferrable dl server")
Signed-off-by: Juri Lelli <juri.lelli@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: stable@vger.kernel.org
Link: https://lkml.kernel.org/r/20241127063740.8278-1-juri.lelli@redhat.com
|
|
|
|
The point behind strscpy() was to once and for all avoid all the
problems with 'strncpy()' and later broken "fixed" versions like
strlcpy() that just made things worse.
So strscpy not only guarantees NUL-termination (unlike strncpy), it also
doesn't do unnecessary padding at the destination. But at the same time
also avoids byte-at-a-time reads and writes by _allowing_ some extra NUL
writes - within the size, of course - so that the whole copy can be done
with word operations.
It is also stable in the face of a mutable source string: it explicitly
does not read the source buffer multiple times (so an implementation
using "strnlen()+memcpy()" would be wrong), and does not read the source
buffer past the size (like the mis-design that is strlcpy does).
Finally, the return value is designed to be simple and unambiguous: if
the string cannot be copied fully, it returns an actual negative error,
making error handling clearer and simpler (and the caller already knows
the size of the buffer). Otherwise it returns the string length of the
result.
However, there was one final stability issue that can be important to
callers: the stability of the destination buffer.
In particular, the same way we shouldn't read the source buffer more
than once, we should avoid doing multiple writes to the destination
buffer: first writing a potentially non-terminated string, and then
terminating it with NUL at the end does not result in a stable result
buffer.
Yes, it gives the right result in the end, but if the rule for the
destination buffer was that it is _always_ NUL-terminated even when
accessed concurrently with updates, the final byte of the buffer needs
to always _stay_ as a NUL byte.
[ Note that "final byte is NUL" here is literally about the final byte
in the destination array, not the terminating NUL at the end of the
string itself. There is no attempt to try to make concurrent reads and
writes give any kind of consistent string length or contents, but we
do want to guarantee that there is always at least that final
terminating NUL character at the end of the destination array if it
existed before ]
This is relevant in the kernel for the tsk->comm[] array, for example.
Even without locking (for either readers or writers), we want to know
that while the buffer contents may be garbled, it is always a valid C
string and always has a NUL character at 'comm[TASK_COMM_LEN-1]' (and
never has any "out of thin air" data).
So avoid any "copy possibly non-terminated string, and terminate later"
behavior, and write the destination buffer only once.
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
|
|
bprintf() is unused. Remove it. It was added in the commit 4370aa4aa753
("vsprintf: add binary printf") but as far as I can see was never used,
unlike the other two functions in that patch.
Link: https://lore.kernel.org/20241002173147.210107-1-linux@treblig.org
Reviewed-by: Andy Shevchenko <andy@kernel.org>
Acked-by: Petr Mladek <pmladek@suse.com>
Signed-off-by: Dr. David Alan Gilbert <linux@treblig.org>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
|
|
since 2024.07.26:
assorted minor bug fixes
assorted platform specific tweaks
initial RAPL PSYS (SysWatt) support
Signed-off-by: Len Brown <len.brown@intel.com>
|
|
Introduce the counter as a part of global, platform counters structure.
We open the counter for only one cpu, but otherwise treat it as an
ordinary RAPL counter, allowing for grouped perf read.
The counter is disabled by default, because it's interpretation may
require additional, platform specific information, making it unsuitable
for general use.
Signed-off-by: Patryk Wlazlyn <patryk.wlazlyn@linux.intel.com>
Signed-off-by: Len Brown <len.brown@intel.com>
|
|
Add '+' to optstring when early scanning for --no-msr and --no-perf.
It causes option processing to stop as soon as a nonoption argument is
encountered, effectively skipping child's arguments.
Fixes: 3e4048466c39 ("tools/power turbostat: Add --no-msr option")
Signed-off-by: Patryk Wlazlyn <patryk.wlazlyn@linux.intel.com>
Signed-off-by: Len Brown <len.brown@intel.com>
|
|
Force the --no-perf early to prevent using it as a source. User asks for
raw values, but perf returns them relative to the opening of the file
descriptor.
Signed-off-by: Patryk Wlazlyn <patryk.wlazlyn@linux.intel.com>
Signed-off-by: Len Brown <len.brown@intel.com>
|
|
On some machines, the graphics device is enumerated as
/sys/class/drm/card1 instead of /sys/class/drm/card0. The current
implementation does not handle this scenario, resulting in the loss of
graphics C6 residency and frequency information.
Add support for /sys/class/drm/card1, ensuring that turbostat can
retrieve and display the graphics columns for these platforms.
Signed-off-by: Zhang Rui <rui.zhang@intel.com>
Signed-off-by: Len Brown <len.brown@intel.com>
|
|
Snapshots of the graphics sysfs knobs are taken based on file
descriptors. To optimize this process, open the files and cache the file
descriptors during the graphics probe phase. As a result, the previously
cached pathnames become redundant and are removed.
This change aims to streamline the code without altering its functionality.
No functional change intended.
Signed-off-by: Zhang Rui <rui.zhang@intel.com>
Signed-off-by: Len Brown <len.brown@intel.com>
|
|
Currently, there is an inconsistency in how graphics sysfs knobs are
accessed: graphics residency sysfs knobs are opened and closed for each
read, while graphics frequency sysfs knobs are opened once and remain
open until turbostat exits. This inconsistency is confusing and adds
unnecessary code complexity.
Consolidate the access method by opening the sysfs files once and
reusing the file pointers for subsequent accesses. This approach
simplifies the code and ensures a consistent method for accessing
graphics sysfs knobs.
Signed-off-by: Zhang Rui <rui.zhang@intel.com>
Signed-off-by: Len Brown <len.brown@intel.com>
|
|
The graphics sysfs knobs are read-only, making the use of fflush()
before reading them redundant.
Remove the unnecessary fflush() call.
Signed-off-by: Zhang Rui <rui.zhang@intel.com>
Signed-off-by: Len Brown <len.brown@intel.com>
|
|
In various generations, platforms often share a majority of features,
diverging only in a few specific aspects. The current approach of using
hardcoded values in 'platform_features' structure fails to effectively
represent these divergences.
To improve the description of platform divergence:
1. Each newly introduced 'platform_features' structure must have a base,
typically derived from the previous generation.
2. Platform feature values should be inherited from the base structure
rather than being hardcoded.
This approach ensures a more accurate and maintainable representation of
platform-specific features across different generations.
Converts `adl_features` and `lnl_features` to follow this new scheme.
No functional change.
Signed-off-by: Zhang Rui <rui.zhang@intel.com>
Signed-off-by: Len Brown <len.brown@intel.com>
|
|
Add initial support for GraniteRapids-D. It shares the same features
with SapphireRapids.
Signed-off-by: Zhang Rui <rui.zhang@intel.com>
Signed-off-by: Len Brown <len.brown@intel.com>
|
|
Lunarlake supports CC1/CC6/CC7/PC2/PC6/PC10.
Remove PC3 support on Lunarlake.
Signed-off-by: Zhang Rui <rui.zhang@intel.com>
Signed-off-by: Len Brown <len.brown@intel.com>
|
|
As ARL shares the same features with ADL/RPL/MTL, now 'arl_features' is
used by Lunarlake platform only.
Rename 'arl_features' to 'lnl_features'.
No functional change.
Signed-off-by: Zhang Rui <rui.zhang@intel.com>
Signed-off-by: Len Brown <len.brown@intel.com>
|
|
Similar to ADL/RPL/MTL, ARL supports CC1/CC6/CC7/PC2/PC3/PC6/PC8/PC10.
Add back PC8 support on Arrowlake.
Signed-off-by: Zhang Rui <rui.zhang@intel.com>
Signed-off-by: Len Brown <len.brown@intel.com>
|
|
Similar to ADL/RPL, MTL support CC1/CC6/CC7/PC2/PC3/PC6/PC8/CP10.
Remove PC7/PC9 support on MTL.
Signed-off-by: Zhang Rui <rui.zhang@intel.com>
Signed-off-by: Len Brown <len.brown@intel.com>
|
|
Honor --show CPU and --show Core when "topo.num_cpus == 1".
Previously turbostat assumed that on a 1-CPU system, these
columns should never appear.
Honoring these flags makes it easier for several programs
that parse turbostat output.
Signed-off-by: Patryk Wlazlyn <patryk.wlazlyn@linux.intel.com>
Signed-off-by: Len Brown <len.brown@intel.com>
|
|
parse_cpu_string() parses the string input either from command line or
from /sys/fs/cgroup/cpuset.cpus.effective to get a list of CPUs that
turbostat can run with.
The cpu string returned by /sys/fs/cgroup/cpuset.cpus.effective contains
a trailing '\n', but strtoul() fails to treat this as an error.
That says, for the code below
val = ("\n", NULL, 10);
val returns 0, and errno is also not set.
As a result, CPU0 is erroneously considered as allowed CPU and this
causes failures when turbostat tries to run on CPU0.
get_counters: Could not migrate to CPU 0
...
turbostat: re-initialized with num_cpus 8, allowed_cpus 5
get_counters: Could not migrate to CPU 0
Add a check to return immediately if '\n' or '\0' is detected.
Fixes: 8c3dd2c9e542 ("tools/power/turbostat: Abstrct function for parsing cpu string")
Signed-off-by: Zhang Rui <rui.zhang@intel.com>
Signed-off-by: Len Brown <len.brown@intel.com>
|
|
Intel hybrid platforms expose different perf devices for P and E cores.
Instead of one, "/sys/bus/event_source/devices/cpu" device, there are
"/sys/bus/event_source/devices/{cpu_core,cpu_atom}".
This, however makes it more complicated for the user,
because most of the counters are available on both and had to be
handled manually.
This patch allows users to use "virtual" cpu device that is seemingly
translated to cpu_core and cpu_atom perf devices, depending on the type
of a CPU we are opening the counter for.
Signed-off-by: Patryk Wlazlyn <patryk.wlazlyn@linux.intel.com>
Signed-off-by: Len Brown <len.brown@intel.com>
|
|
If the very first printed column was for a PMT counter of type xtal_time
we would misalign the column header, because we were always printing the
delimiter.
Signed-off-by: Patryk Wlazlyn <patryk.wlazlyn@linux.intel.com>
Signed-off-by: Len Brown <len.brown@intel.com>
|
|
Fix build regression seen when using old gcc-9 compiler.
Signed-off-by: Todd Brandt <todd.e.brandt@intel.com>
Reviewed-by: Chen Yu <yu.c.chen@intel.com>
Signed-off-by: Len Brown <len.brown@intel.com>
|
|
If a PCI device has an associated device_node with power supplies,
pci_bus_add_device() creates platform devices for use by pwrctrl. When the
PCI device is removed, pci_stop_dev() uses of_find_device_by_node() to
locate the related platform device, then unregisters it.
But when we remove a PCI device with no associated device node,
dev_of_node(dev) is NULL, and of_find_device_by_node(NULL) returns the
first device with "dev->of_node == NULL". The result is that we (a)
mistakenly unregister a completely unrelated platform device, leading to
issues like the first trace below, and (b) dereference the NULL pointer
from dev_of_node() when clearing OF_POPULATED, as in the second trace.
Unregister a platform device only if there is one associated with this PCI
device. This resolves issues seen when doing:
# echo 1 > /sys/bus/pci/devices/.../remove
Sample issue from unregistering the wrong platform device:
WARNING: CPU: 0 PID: 5095 at drivers/regulator/core.c:5885 regulator_unregister+0x140/0x160
Call trace:
regulator_unregister+0x140/0x160
devm_rdev_release+0x1c/0x30
release_nodes+0x68/0x100
devres_release_all+0x98/0xf8
device_unbind_cleanup+0x20/0x70
device_release_driver_internal+0x1f4/0x240
device_release_driver+0x20/0x40
bus_remove_device+0xd8/0x170
device_del+0x154/0x380
device_unregister+0x28/0x88
of_device_unregister+0x1c/0x30
pci_stop_bus_device+0x154/0x1b0
pci_stop_and_remove_bus_device_locked+0x28/0x48
remove_store+0xa0/0xb8
dev_attr_store+0x20/0x40
sysfs_kf_write+0x4c/0x68
Later NULL pointer dereference for of_node_clear_flag(NULL, OF_POPULATED):
Unable to handle kernel NULL pointer dereference at virtual address 00000000000000c0
Call trace:
pci_stop_bus_device+0x190/0x1b0
pci_stop_and_remove_bus_device_locked+0x28/0x48
remove_store+0xa0/0xb8
dev_attr_store+0x20/0x40
sysfs_kf_write+0x4c/0x68
Link: https://lore.kernel.org/r/20241126210443.4052876-1-briannorris@chromium.org
Fixes: 681725afb6b9 ("PCI/pwrctl: Remove pwrctl device without iterating over all children of pwrctl parent")
Reported-by: Saurabh Sengar <ssengar@linux.microsoft.com>
Closes: https://lore.kernel.org/r/1732890621-19656-1-git-send-email-ssengar@linux.microsoft.com
Signed-off-by: Brian Norris <briannorris@chromium.org>
[bhelgaas: commit log]
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
|
|
This reverts commit 3791ea69a4858b81e0277f695ca40f5aae40f312.
It was reported to cause boot-time issues, so revert it for now.
Reported-by: Geert Uytterhoeven <geert@linux-m68k.org>
Fixes: 3791ea69a485 ("serial: sh-sci: Clean sci_ports[0] after at earlycon exit")
Cc: stable <stable@kernel.org>
Cc: Claudiu Beznea <claudiu.beznea.uj@bp.renesas.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
In the error handling for this function, d is freed without ever
removing it from intc_list which would lead to a use after free.
To fix this, let's only add it to the list after everything has
succeeded.
Fixes: 2dcec7a988a1 ("sh: intc: set_irq_wake() support")
Signed-off-by: Dan Carpenter <dan.carpenter@linaro.org>
Reviewed-by: John Paul Adrian Glaubitz <glaubitz@physik.fu-berlin.de>
Signed-off-by: John Paul Adrian Glaubitz <glaubitz@physik.fu-berlin.de>
|
|
When CONFIG_CPUMASK_OFFSTACK and CONFIG_DEBUG_PER_CPU_MAPS are selected,
cpu_max_bits_warn() generates a runtime warning similar as below when
showing /proc/cpuinfo. Fix this by using nr_cpu_ids (the runtime limit)
instead of NR_CPUS to iterate CPUs.
[ 3.052463] ------------[ cut here ]------------
[ 3.059679] WARNING: CPU: 3 PID: 1 at include/linux/cpumask.h:108 show_cpuinfo+0x5e8/0x5f0
[ 3.070072] Modules linked in: efivarfs autofs4
[ 3.076257] CPU: 0 PID: 1 Comm: systemd Not tainted 5.19-rc5+ #1052
[ 3.099465] Stack : 9000000100157b08 9000000000f18530 9000000000cf846c 9000000100154000
[ 3.109127] 9000000100157a50 0000000000000000 9000000100157a58 9000000000ef7430
[ 3.118774] 90000001001578e8 0000000000000040 0000000000000020 ffffffffffffffff
[ 3.128412] 0000000000aaaaaa 1ab25f00eec96a37 900000010021de80 900000000101c890
[ 3.138056] 0000000000000000 0000000000000000 0000000000000000 0000000000aaaaaa
[ 3.147711] ffff8000339dc220 0000000000000001 0000000006ab4000 0000000000000000
[ 3.157364] 900000000101c998 0000000000000004 9000000000ef7430 0000000000000000
[ 3.167012] 0000000000000009 000000000000006c 0000000000000000 0000000000000000
[ 3.176641] 9000000000d3de08 9000000001639390 90000000002086d8 00007ffff0080286
[ 3.186260] 00000000000000b0 0000000000000004 0000000000000000 0000000000071c1c
[ 3.195868] ...
[ 3.199917] Call Trace:
[ 3.203941] [<90000000002086d8>] show_stack+0x38/0x14c
[ 3.210666] [<9000000000cf846c>] dump_stack_lvl+0x60/0x88
[ 3.217625] [<900000000023d268>] __warn+0xd0/0x100
[ 3.223958] [<9000000000cf3c90>] warn_slowpath_fmt+0x7c/0xcc
[ 3.231150] [<9000000000210220>] show_cpuinfo+0x5e8/0x5f0
[ 3.238080] [<90000000004f578c>] seq_read_iter+0x354/0x4b4
[ 3.245098] [<90000000004c2e90>] new_sync_read+0x17c/0x1c4
[ 3.252114] [<90000000004c5174>] vfs_read+0x138/0x1d0
[ 3.258694] [<90000000004c55f8>] ksys_read+0x70/0x100
[ 3.265265] [<9000000000cfde9c>] do_syscall+0x7c/0x94
[ 3.271820] [<9000000000202fe4>] handle_syscall+0xc4/0x160
[ 3.281824] ---[ end trace 8b484262b4b8c24c ]---
Cc: stable@vger.kernel.org
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
Reviewed-by: John Paul Adrian Glaubitz <glaubitz@physik.fu-berlin.de>
Tested-by: John Paul Adrian Glaubitz <glaubitz@physik.fu-berlin.de>
Signed-off-by: John Paul Adrian Glaubitz <glaubitz@physik.fu-berlin.de>
|
Vincent Guittot
Peter Zijlstra
K Prateek Nayak
Waiman Long
Valentin Schneider
Wander Lairson Costa
Juri Lelli
Harshit Agarwal
Suleiman Souhlal
John Stultz
Sebastian Andrzej Siewior
Josh Don
Linus Torvalds
Dr. David Alan Gilbert
Len Brown
Patryk Wlazlyn
Zhang Rui
Todd Brandt
Brian Norris
Greg Kroah-Hartman
Dan Carpenter
Huacai Chen