- Make sure the run-queue balance callback is invoked only on the outgoing CPU
-----BEGIN PGP SIGNATURE-----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=ExIs
-----END PGP SIGNATURE-----
Merge tag 'sched_urgent_for_v5.15_rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull scheduler fixes from Borislav Petkov:
- Make sure the idle timer expires in hardirq context, on PREEMPT_RT
- Make sure the run-queue balance callback is invoked only on the
outgoing CPU
* tag 'sched_urgent_for_v5.15_rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
sched: Prevent balance_push() on remote runqueues
sched/idle: Make the idle timer expire in hard interrupt context
sched_setscheduler() and rt_mutex_setprio() invoke the run-queue balance
callback after changing priorities or the scheduling class of a task. The
run-queue for which the callback is invoked can be local or remote.
That's not a problem for the regular rq::push_work which is serialized with
a busy flag in the run-queue struct, but for the balance_push() work which
is only valid to be invoked on the outgoing CPU that's wrong. It not only
triggers the debug warning, but also leaves the per CPU variable push_work
unprotected, which can result in double enqueues on the stop machine list.
Remove the warning and validate that the function is invoked on the
outgoing CPU.
Fixes: ae79270232 ("sched: Optimize finish_lock_switch()")
Reported-by: Sebastian Siewior <bigeasy@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: stable@vger.kernel.org
Link: https://lkml.kernel.org/r/87zgt1hdw7.ffs@tglx
The regular pile:
- A few improvements to the mutex code
- Documentation updates for atomics to clarify the difference between
cmpxchg() and try_cmpxchg() and to explain the forward progress
expectations.
- Simplification of the atomics fallback generator
- The addition of arch_atomic_long*() variants and generic arch_*()
bitops based on them.
- Add the missing might_sleep() invocations to the down*() operations of
semaphores.
The PREEMPT_RT locking core:
- Scheduler updates to support the state preserving mechanism for
'sleeping' spin- and rwlocks on RT. This mechanism is carefully
preserving the state of the task when blocking on a 'sleeping' spin- or
rwlock and takes regular wake-ups targeted at the same task into
account. The preserved or updated (via a regular wakeup) state is
restored when the lock has been acquired.
- Restructuring of the rtmutex code so it can be utilized and extended
for the RT specific lock variants.
- Restructuring of the ww_mutex code to allow sharing of the ww_mutex
specific functionality for rtmutex based ww_mutexes.
- Header file disentangling to allow substitution of the regular lock
implementations with the PREEMPT_RT variants without creating an
unmaintainable #ifdef mess.
- Shared base code for the PREEMPT_RT specific rw_semaphore and rwlock
implementations. Contrary to the regular rw_semaphores and rwlocks the
PREEMPT_RT implementation is writer unfair because it is infeasible to
do priority inheritance on multiple readers. Experience over the years
has shown that real-time workloads are not the typical workloads which
are sensitive to writer starvation. The alternative solution would be
to allow only a single reader which has been tried and discarded as it
is a major bottleneck especially for mmap_sem. Aside of that many of
the writer starvation critical usage sites have been converted to a
writer side mutex/spinlock and RCU read side protections in the past
decade so that the issue is less prominent than it used to be.
- The actual rtmutex based lock substitutions for PREEMPT_RT enabled
kernels which affect mutex, ww_mutex, rw_semaphore, spinlock_t and
rwlock_t. The spin/rw_lock*() functions disable migration across the
critical section to preserve the existing semantics vs. per CPU
variables.
- Rework of the futex REQUEUE_PI mechanism to handle the case of early
wake-ups which interleave with a re-queue operation to prevent the
situation that a task would be blocked on both the rtmutex associated
to the outer futex and the rtmutex based hash bucket spinlock.
While this situation cannot happen on !RT enabled kernels the changes
make the underlying concurrency problems easier to understand in
general. As a result the difference between !RT and RT kernels is
reduced to the handling of waiting for the critical section. !RT
kernels simply spin-wait as before and RT kernels utilize rcu_wait().
- The substitution of local_lock for PREEMPT_RT with a spinlock which
protects the critical section while staying preemptible. The CPU
locality is established by disabling migration.
The underlying concepts of this code have been in use in PREEMPT_RT for
way more than a decade. The code has been refactored several times over
the years and this final incarnation has been optimized once again to be
as non-intrusive as possible, i.e. the RT specific parts are mostly
isolated.
It has been extensively tested in the 5.14-rt patch series and it has
been verified that !RT kernels are not affected by these changes.
-----BEGIN PGP SIGNATURE-----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=IEqE
-----END PGP SIGNATURE-----
Merge tag 'locking-core-2021-08-30' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull locking and atomics updates from Thomas Gleixner:
"The regular pile:
- A few improvements to the mutex code
- Documentation updates for atomics to clarify the difference between
cmpxchg() and try_cmpxchg() and to explain the forward progress
expectations.
- Simplification of the atomics fallback generator
- The addition of arch_atomic_long*() variants and generic arch_*()
bitops based on them.
- Add the missing might_sleep() invocations to the down*() operations
of semaphores.
The PREEMPT_RT locking core:
- Scheduler updates to support the state preserving mechanism for
'sleeping' spin- and rwlocks on RT.
This mechanism is carefully preserving the state of the task when
blocking on a 'sleeping' spin- or rwlock and takes regular wake-ups
targeted at the same task into account. The preserved or updated
(via a regular wakeup) state is restored when the lock has been
acquired.
- Restructuring of the rtmutex code so it can be utilized and
extended for the RT specific lock variants.
- Restructuring of the ww_mutex code to allow sharing of the ww_mutex
specific functionality for rtmutex based ww_mutexes.
- Header file disentangling to allow substitution of the regular lock
implementations with the PREEMPT_RT variants without creating an
unmaintainable #ifdef mess.
- Shared base code for the PREEMPT_RT specific rw_semaphore and
rwlock implementations.
Contrary to the regular rw_semaphores and rwlocks the PREEMPT_RT
implementation is writer unfair because it is infeasible to do
priority inheritance on multiple readers. Experience over the years
has shown that real-time workloads are not the typical workloads
which are sensitive to writer starvation.
The alternative solution would be to allow only a single reader
which has been tried and discarded as it is a major bottleneck
especially for mmap_sem. Aside of that many of the writer
starvation critical usage sites have been converted to a writer
side mutex/spinlock and RCU read side protections in the past
decade so that the issue is less prominent than it used to be.
- The actual rtmutex based lock substitutions for PREEMPT_RT enabled
kernels which affect mutex, ww_mutex, rw_semaphore, spinlock_t and
rwlock_t. The spin/rw_lock*() functions disable migration across
the critical section to preserve the existing semantics vs per-CPU
variables.
- Rework of the futex REQUEUE_PI mechanism to handle the case of
early wake-ups which interleave with a re-queue operation to
prevent the situation that a task would be blocked on both the
rtmutex associated to the outer futex and the rtmutex based hash
bucket spinlock.
While this situation cannot happen on !RT enabled kernels the
changes make the underlying concurrency problems easier to
understand in general. As a result the difference between !RT and
RT kernels is reduced to the handling of waiting for the critical
section. !RT kernels simply spin-wait as before and RT kernels
utilize rcu_wait().
- The substitution of local_lock for PREEMPT_RT with a spinlock which
protects the critical section while staying preemptible. The CPU
locality is established by disabling migration.
The underlying concepts of this code have been in use in PREEMPT_RT for
way more than a decade. The code has been refactored several times over
the years and this final incarnation has been optimized once again to be
as non-intrusive as possible, i.e. the RT specific parts are mostly
isolated.
It has been extensively tested in the 5.14-rt patch series and it has
been verified that !RT kernels are not affected by these changes"
* tag 'locking-core-2021-08-30' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (92 commits)
locking/rtmutex: Return success on deadlock for ww_mutex waiters
locking/rtmutex: Prevent spurious EDEADLK return caused by ww_mutexes
locking/rtmutex: Dequeue waiter on ww_mutex deadlock
locking/rtmutex: Dont dereference waiter lockless
locking/semaphore: Add might_sleep() to down_*() family
locking/ww_mutex: Initialize waiter.ww_ctx properly
static_call: Update API documentation
locking/local_lock: Add PREEMPT_RT support
locking/spinlock/rt: Prepare for RT local_lock
locking/rtmutex: Add adaptive spinwait mechanism
locking/rtmutex: Implement equal priority lock stealing
preempt: Adjust PREEMPT_LOCK_OFFSET for RT
locking/rtmutex: Prevent lockdep false positive with PI futexes
futex: Prevent requeue_pi() lock nesting issue on RT
futex: Simplify handle_early_requeue_pi_wakeup()
futex: Reorder sanity checks in futex_requeue()
futex: Clarify comment in futex_requeue()
futex: Restructure futex_requeue()
futex: Correct the number of requeued waiters for PI
futex: Remove bogus condition for requeue PI
...
- The biggest change in this cycle is scheduler support for asymmetric
scheduling affinity, to support the execution of legacy 32-bit tasks on
AArch32 systems that also have 64-bit-only CPUs.
Architectures can fill in this functionality by defining their
own task_cpu_possible_mask(p). When this is done, the scheduler will
make sure the task will only be scheduled on CPUs that support it.
(The actual arm64 specific changes are not part of this tree.)
For other architectures there will be no change in functionality.
- Add cgroup SCHED_IDLE support
- Increase node-distance flexibility & delay determining it until a CPU
is brought online. (This enables platforms where node distance isn't
final until the CPU is only.)
- Deadline scheduler enhancements & fixes
- Misc fixes & cleanups.
Signed-off-by: Ingo Molnar <mingo@kernel.org>
-----BEGIN PGP SIGNATURE-----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=VdGE
-----END PGP SIGNATURE-----
Merge tag 'sched-core-2021-08-30' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull scheduler updates from Ingo Molnar:
- The biggest change in this cycle is scheduler support for asymmetric
scheduling affinity, to support the execution of legacy 32-bit tasks
on AArch32 systems that also have 64-bit-only CPUs.
Architectures can fill in this functionality by defining their own
task_cpu_possible_mask(p). When this is done, the scheduler will make
sure the task will only be scheduled on CPUs that support it.
(The actual arm64 specific changes are not part of this tree.)
For other architectures there will be no change in functionality.
- Add cgroup SCHED_IDLE support
- Increase node-distance flexibility & delay determining it until a CPU
is brought online. (This enables platforms where node distance isn't
final until the CPU is only.)
- Deadline scheduler enhancements & fixes
- Misc fixes & cleanups.
* tag 'sched-core-2021-08-30' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (27 commits)
eventfd: Make signal recursion protection a task bit
sched/fair: Mark tg_is_idle() an inline in the !CONFIG_FAIR_GROUP_SCHED case
sched: Introduce dl_task_check_affinity() to check proposed affinity
sched: Allow task CPU affinity to be restricted on asymmetric systems
sched: Split the guts of sched_setaffinity() into a helper function
sched: Introduce task_struct::user_cpus_ptr to track requested affinity
sched: Reject CPU affinity changes based on task_cpu_possible_mask()
cpuset: Cleanup cpuset_cpus_allowed_fallback() use in select_fallback_rq()
cpuset: Honour task_cpu_possible_mask() in guarantee_online_cpus()
cpuset: Don't use the cpu_possible_mask as a last resort for cgroup v1
sched: Introduce task_cpu_possible_mask() to limit fallback rq selection
sched: Cgroup SCHED_IDLE support
sched/topology: Skip updating masks for non-online nodes
sched: Replace deprecated CPU-hotplug functions.
sched: Skip priority checks with SCHED_FLAG_KEEP_PARAMS
sched: Fix UCLAMP_FLAG_IDLE setting
sched/deadline: Fix missing clock update in migrate_task_rq_dl()
sched/fair: Avoid a second scan of target in select_idle_cpu
sched/fair: Use prev instead of new target as recent_used_cpu
sched: Don't report SCHED_FLAG_SUGOV in sched_getattr()
...
Pull RCU updates from Paul McKenney:
"RCU changes for this cycle were:
- Documentation updates
- Miscellaneous fixes
- Offloaded-callbacks updates
- Updates to the nolibc library
- Tasks-RCU updates
- In-kernel torture-test updates
- Torture-test scripting, perhaps most notably the pinning of
torture-test guest OSes so as to force differences in memory
latency. For example, in a two-socket system, a four-CPU guest OS
will have one pair of its CPUs pinned to threads in a single core
on one socket and the other pair pinned to threads in a single core
on the other socket. This approach proved able to force race
conditions that earlier testing missed. Some of these race
conditions are still being tracked down"
* 'core-rcu.2021.08.28a' of git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu: (61 commits)
torture: Replace deprecated CPU-hotplug functions.
rcu: Replace deprecated CPU-hotplug functions
rcu: Print human-readable message for schedule() in RCU reader
rcu: Explain why rcu_all_qs() is a stub in preemptible TREE RCU
rcu: Use per_cpu_ptr to get the pointer of per_cpu variable
rcu: Remove useless "ret" update in rcu_gp_fqs_loop()
rcu: Mark accesses in tree_stall.h
rcu: Make rcu_gp_init() and rcu_gp_fqs_loop noinline to conserve stack
rcu: Mark lockless ->qsmask read in rcu_check_boost_fail()
srcutiny: Mark read-side data races
rcu: Start timing stall repetitions after warning complete
rcu: Do not disable GP stall detection in rcu_cpu_stall_reset()
rcu/tree: Handle VM stoppage in stall detection
rculist: Unify documentation about missing list_empty_rcu()
rcu: Mark accesses to ->rcu_read_lock_nesting
rcu: Weaken ->dynticks accesses and updates
rcu: Remove special bit at the bottom of the ->dynticks counter
rcu: Fix stall-warning deadlock due to non-release of rcu_node ->lock
rcu: Fix to include first blocked task in stall warning
torture: Make kvm-test-1-run-qemu.sh check for reboot loops
...
In preparation for restricting the affinity of a task during execve()
on arm64, introduce a new dl_task_check_affinity() helper function to
give an indication as to whether the restricted mask is admissible for
a deadline task.
Signed-off-by: Will Deacon <will@kernel.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Daniel Bristot de Oliveira <bristot@redhat.com>
Link: https://lore.kernel.org/r/20210730112443.23245-10-will@kernel.org
Asymmetric systems may not offer the same level of userspace ISA support
across all CPUs, meaning that some applications cannot be executed by
some CPUs. As a concrete example, upcoming arm64 big.LITTLE designs do
not feature support for 32-bit applications on both clusters.
Although userspace can carefully manage the affinity masks for such
tasks, one place where it is particularly problematic is execve()
because the CPU on which the execve() is occurring may be incompatible
with the new application image. In such a situation, it is desirable to
restrict the affinity mask of the task and ensure that the new image is
entered on a compatible CPU. From userspace's point of view, this looks
the same as if the incompatible CPUs have been hotplugged off in the
task's affinity mask. Similarly, if a subsequent execve() reverts to
a compatible image, then the old affinity is restored if it is still
valid.
In preparation for restricting the affinity mask for compat tasks on
arm64 systems without uniform support for 32-bit applications, introduce
{force,relax}_compatible_cpus_allowed_ptr(), which respectively restrict
and restore the affinity mask for a task based on the compatible CPUs.
Signed-off-by: Will Deacon <will@kernel.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Valentin Schneider <valentin.schneider@arm.com>
Reviewed-by: Quentin Perret <qperret@google.com>
Link: https://lore.kernel.org/r/20210730112443.23245-9-will@kernel.org
In preparation for replaying user affinity requests using a saved mask,
split sched_setaffinity() up so that the initial task lookup and
security checks are only performed when the request is coming directly
from userspace.
Signed-off-by: Will Deacon <will@kernel.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Valentin Schneider <Valentin.Schneider@arm.com>
Link: https://lore.kernel.org/r/20210730112443.23245-8-will@kernel.org
In preparation for saving and restoring the user-requested CPU affinity
mask of a task, add a new cpumask_t pointer to 'struct task_struct'.
If the pointer is non-NULL, then the mask is copied across fork() and
freed on task exit.
Signed-off-by: Will Deacon <will@kernel.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Valentin Schneider <Valentin.Schneider@arm.com>
Link: https://lore.kernel.org/r/20210730112443.23245-7-will@kernel.org
Reject explicit requests to change the affinity mask of a task via
set_cpus_allowed_ptr() if the requested mask is not a subset of the
mask returned by task_cpu_possible_mask(). This ensures that the
'cpus_mask' for a given task cannot contain CPUs which are incapable of
executing it, except in cases where the affinity is forced.
Signed-off-by: Will Deacon <will@kernel.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Valentin Schneider <Valentin.Schneider@arm.com>
Reviewed-by: Quentin Perret <qperret@google.com>
Link: https://lore.kernel.org/r/20210730112443.23245-6-will@kernel.org
select_fallback_rq() only needs to recheck for an allowed CPU if the
affinity mask of the task has changed since the last check.
Return a 'bool' from cpuset_cpus_allowed_fallback() to indicate whether
the affinity mask was updated, and use this to elide the allowed check
when the mask has been left alone.
No functional change.
Suggested-by: Valentin Schneider <valentin.schneider@arm.com>
Signed-off-by: Will Deacon <will@kernel.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Valentin Schneider <valentin.schneider@arm.com>
Link: https://lore.kernel.org/r/20210730112443.23245-5-will@kernel.org
Asymmetric systems may not offer the same level of userspace ISA support
across all CPUs, meaning that some applications cannot be executed by
some CPUs. As a concrete example, upcoming arm64 big.LITTLE designs do
not feature support for 32-bit applications on both clusters.
On such a system, we must take care not to migrate a task to an
unsupported CPU when forcefully moving tasks in select_fallback_rq()
in response to a CPU hot-unplug operation.
Introduce a task_cpu_possible_mask() hook which, given a task argument,
allows an architecture to return a cpumask of CPUs that are capable of
executing that task. The default implementation returns the
cpu_possible_mask, since sane machines do not suffer from per-cpu ISA
limitations that affect scheduling. The new mask is used when selecting
the fallback runqueue as a last resort before forcing a migration to the
first active CPU.
Signed-off-by: Will Deacon <will@kernel.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Valentin Schneider <Valentin.Schneider@arm.com>
Reviewed-by: Quentin Perret <qperret@google.com>
Link: https://lore.kernel.org/r/20210730112443.23245-2-will@kernel.org
This extends SCHED_IDLE to cgroups.
Interface: cgroup/cpu.idle.
0: default behavior
1: SCHED_IDLE
Extending SCHED_IDLE to cgroups means that we incorporate the existing
aspects of SCHED_IDLE; a SCHED_IDLE cgroup will count all of its
descendant threads towards the idle_h_nr_running count of all of its
ancestor cgroups. Thus, sched_idle_rq() will work properly.
Additionally, SCHED_IDLE cgroups are configured with minimum weight.
There are two key differences between the per-task and per-cgroup
SCHED_IDLE interface:
- The cgroup interface allows tasks within a SCHED_IDLE hierarchy to
maintain their relative weights. The entity that is "idle" is the
cgroup, not the tasks themselves.
- Since the idle entity is the cgroup, our SCHED_IDLE wakeup preemption
decision is not made by comparing the current task with the woken
task, but rather by comparing their matching sched_entity.
A typical use-case for this is a user that creates an idle and a
non-idle subtree. The non-idle subtree will dominate competition vs
the idle subtree, but the idle subtree will still be high priority vs
other users on the system. The latter is accomplished via comparing
matching sched_entity in the waken preemption path (this could also be
improved by making the sched_idle_rq() decision dependent on the
perspective of a specific task).
For now, we maintain the existing SCHED_IDLE semantics. Future patches
may make improvements that extend how we treat SCHED_IDLE entities.
The per-task_group idle field is an integer that currently only holds
either a 0 or a 1. This is explicitly typed as an integer to allow for
further extensions to this API. For example, a negative value may
indicate a highly latency-sensitive cgroup that should be preferred
for preemption/placement/etc.
Signed-off-by: Josh Don <joshdon@google.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Vincent Guittot <vincent.guittot@linaro.org>
Link: https://lore.kernel.org/r/20210730020019.1487127-2-joshdon@google.com
Eugene tripped over the case where rq_lock(), as called in a
for_each_possible_cpu() loop came apart because rq->core hadn't been
setup yet.
This is a somewhat unusual, but valid case.
Rework things such that rq->core is initialized to point at itself. IOW
initialize each CPU as a single threaded Core. CPU online will then join
the new CPU (thread) to an existing Core where needed.
For completeness sake, have CPU offline fully undo the state so as to
not presume the topology will match the next time it comes online.
Fixes: 9edeaea1bc ("sched: Core-wide rq->lock")
Reported-by: Eugene Syromiatnikov <esyr@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Josh Don <joshdon@google.com>
Tested-by: Eugene Syromiatnikov <esyr@redhat.com>
Link: https://lkml.kernel.org/r/YR473ZGeKqMs6kw+@hirez.programming.kicks-ass.net
RT enabled kernels substitute spin/rwlocks with 'sleeping' variants based
on rtmutexes. Blocking on such a lock is similar to preemption versus:
- I/O scheduling and worker handling, because these functions might block
on another substituted lock, or come from a lock contention within these
functions.
- RCU considers this like a preemption, because the task might be in a read
side critical section.
Add a separate scheduling point for this, and hand a new scheduling mode
argument to __schedule() which allows, along with separate mode masks, to
handle this gracefully from within the scheduler, without proliferating that
to other subsystems like RCU.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20210815211302.372319055@linutronix.de
PREEMPT_RT needs to hand a special state into __schedule() when a task
blocks on a 'sleeping' spin/rwlock. This is required to handle
rcu_note_context_switch() correctly without having special casing in the
RCU code. From an RCU point of view the blocking on the sleeping spinlock
is equivalent to preemption, because the task might be in a read side
critical section.
schedule_debug() also has a check which would trigger with the !preempt
case, but that could be handled differently.
To avoid adding another argument and extra checks which cannot be optimized
out by the compiler, the following solution has been chosen:
- Replace the boolean 'preempt' argument with an unsigned integer
'sched_mode' argument and define constants to hand in:
(0 == no preemption, 1 = preemption).
- Add two masks to apply on that mode: one for the debug/rcu invocations,
and one for the actual scheduling decision.
For a non RT kernel these masks are UINT_MAX, i.e. all bits are set,
which allows the compiler to optimize the AND operation out, because it is
not masking out anything. IOW, it's not different from the boolean.
RT enabled kernels will define these masks separately.
No functional change.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20210815211302.315473019@linutronix.de
Waiting for spinlocks and rwlocks on non RT enabled kernels is task::state
preserving. Any wakeup which matches the state is valid.
RT enabled kernels substitutes them with 'sleeping' spinlocks. This creates
an issue vs. task::__state.
In order to block on the lock, the task has to overwrite task::__state and a
consecutive wakeup issued by the unlocker sets the state back to
TASK_RUNNING. As a consequence the task loses the state which was set
before the lock acquire and also any regular wakeup targeted at the task
while it is blocked on the lock.
To handle this gracefully, add a 'saved_state' member to task_struct which
is used in the following way:
1) When a task blocks on a 'sleeping' spinlock, the current state is saved
in task::saved_state before it is set to TASK_RTLOCK_WAIT.
2) When the task unblocks and after acquiring the lock, it restores the saved
state.
3) When a regular wakeup happens for a task while it is blocked then the
state change of that wakeup is redirected to operate on task::saved_state.
This is also required when the task state is running because the task
might have been woken up from the lock wait and has not yet restored
the saved state.
To make it complete, provide the necessary helpers to save and restore the
saved state along with the necessary documentation how the RT lock blocking
is supposed to work.
For non-RT kernels there is no functional change.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20210815211302.258751046@linutronix.de
RT kernels have a slightly more complicated handling of wakeups due to
'sleeping' spin/rwlocks. If a task is blocked on such a lock then the
original state of the task is preserved over the blocking period, and
any regular (non lock related) wakeup has to be targeted at the
saved state to ensure that these wakeups are not lost.
Once the task acquires the lock it restores the task state from the saved state.
To avoid cluttering try_to_wake_up() with that logic, split the wakeup
state check out into an inline helper and use it at both places where
task::__state is checked against the state argument of try_to_wake_up().
No functional change.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20210815211302.088945085@linutronix.de
The functions get_online_cpus() and put_online_cpus() have been
deprecated during the CPU hotplug rework. They map directly to
cpus_read_lock() and cpus_read_unlock().
Replace deprecated CPU-hotplug functions with the official version.
The behavior remains unchanged.
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/r/20210803141621.780504-33-bigeasy@linutronix.de
The cond_resched() function reports an RCU quiescent state only in
non-preemptible TREE RCU implementation. This commit therefore adds a
comment explaining why cond_resched() does nothing in preemptible kernels.
Signed-off-by: Frederic Weisbecker <frederic@kernel.org>
Cc: Neeraj Upadhyay <neeraju@codeaurora.org>
Cc: Joel Fernandes <joel@joelfernandes.org>
Cc: Uladzislau Rezki <urezki@gmail.com>
Cc: Boqun Feng <boqun.feng@gmail.com>
Cc: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
SCHED_FLAG_KEEP_PARAMS can be passed to sched_setattr to specify that
the call must not touch scheduling parameters (nice or priority). This
is particularly handy for uclamp when used in conjunction with
SCHED_FLAG_KEEP_POLICY as that allows to issue a syscall that only
impacts uclamp values.
However, sched_setattr always checks whether the priorities and nice
values passed in sched_attr are valid first, even if those never get
used down the line. This is useless at best since userspace can
trivially bypass this check to set the uclamp values by specifying low
priorities. However, it is cumbersome to do so as there is no single
expression of this that skips both RT and CFS checks at once. As such,
userspace needs to query the task policy first with e.g. sched_getattr
and then set sched_attr.sched_priority accordingly. This is racy and
slower than a single call.
As the priority and nice checks are useless when SCHED_FLAG_KEEP_PARAMS
is specified, simply inherit them in this case to match the policy
inheritance of SCHED_FLAG_KEEP_POLICY.
Reported-by: Wei Wang <wvw@google.com>
Signed-off-by: Quentin Perret <qperret@google.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Dietmar Eggemann <dietmar.eggemann@arm.com>
Reviewed-by: Qais Yousef <qais.yousef@arm.com>
Link: https://lore.kernel.org/r/20210805102154.590709-3-qperret@google.com
The UCLAMP_FLAG_IDLE flag is set on a runqueue when dequeueing the last
uclamp active task (that is, when buckets.tasks reaches 0 for all
buckets) to maintain the last uclamp.max and prevent blocked util from
suddenly becoming visible.
However, there is an asymmetry in how the flag is set and cleared which
can lead to having the flag set whilst there are active tasks on the rq.
Specifically, the flag is cleared in the uclamp_rq_inc() path, which is
called at enqueue time, but set in uclamp_rq_dec_id() which is called
both when dequeueing a task _and_ in the update_uclamp_active() path. As
a result, when both uclamp_rq_{dec,ind}_id() are called from
update_uclamp_active(), the flag ends up being set but not cleared,
hence leaving the runqueue in a broken state.
Fix this by clearing the flag in update_uclamp_active() as well.
Fixes: e496187da7 ("sched/uclamp: Enforce last task's UCLAMP_MAX")
Reported-by: Rick Yiu <rickyiu@google.com>
Signed-off-by: Quentin Perret <qperret@google.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Qais Yousef <qais.yousef@arm.com>
Tested-by: Dietmar Eggemann <dietmar.eggemann@arm.com>
Link: https://lore.kernel.org/r/20210805102154.590709-2-qperret@google.com
SCHED_FLAG_SUGOV is supposed to be a kernel-only flag that userspace
cannot interact with. However, sched_getattr() currently reports it
in sched_flags if called on a sugov worker even though it is not
actually defined in a UAPI header. To avoid this, make sure to
clean-up the sched_flags field in sched_getattr() before returning to
userspace.
Signed-off-by: Quentin Perret <qperret@google.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/20210727101103.2729607-3-qperret@google.com
Double enqueues in rt runqueues (list) have been reported while running
a simple test that spawns a number of threads doing a short sleep/run
pattern while being concurrently setscheduled between rt and fair class.
WARNING: CPU: 3 PID: 2825 at kernel/sched/rt.c:1294 enqueue_task_rt+0x355/0x360
CPU: 3 PID: 2825 Comm: setsched__13
RIP: 0010:enqueue_task_rt+0x355/0x360
Call Trace:
__sched_setscheduler+0x581/0x9d0
_sched_setscheduler+0x63/0xa0
do_sched_setscheduler+0xa0/0x150
__x64_sys_sched_setscheduler+0x1a/0x30
do_syscall_64+0x33/0x40
entry_SYSCALL_64_after_hwframe+0x44/0xae
list_add double add: new=ffff9867cb629b40, prev=ffff9867cb629b40,
next=ffff98679fc67ca0.
kernel BUG at lib/list_debug.c:31!
invalid opcode: 0000 [#1] PREEMPT_RT SMP PTI
CPU: 3 PID: 2825 Comm: setsched__13
RIP: 0010:__list_add_valid+0x41/0x50
Call Trace:
enqueue_task_rt+0x291/0x360
__sched_setscheduler+0x581/0x9d0
_sched_setscheduler+0x63/0xa0
do_sched_setscheduler+0xa0/0x150
__x64_sys_sched_setscheduler+0x1a/0x30
do_syscall_64+0x33/0x40
entry_SYSCALL_64_after_hwframe+0x44/0xae
__sched_setscheduler() uses rt_effective_prio() to handle proper queuing
of priority boosted tasks that are setscheduled while being boosted.
rt_effective_prio() is however called twice per each
__sched_setscheduler() call: first directly by __sched_setscheduler()
before dequeuing the task and then by __setscheduler() to actually do
the priority change. If the priority of the pi_top_task is concurrently
being changed however, it might happen that the two calls return
different results. If, for example, the first call returned the same rt
priority the task was running at and the second one a fair priority, the
task won't be removed by the rt list (on_list still set) and then
enqueued in the fair runqueue. When eventually setscheduled back to rt
it will be seen as enqueued already and the WARNING/BUG be issued.
Fix this by calling rt_effective_prio() only once and then reusing the
return value. While at it refactor code as well for clarity. Concurrent
priority inheritance handling is still safe and will eventually converge
to a new state by following the inheritance chain(s).
Fixes: 0782e63bc6 ("sched: Handle priority boosted tasks proper in setscheduler()")
[squashed Peterz changes; added changelog]
Reported-by: Mark Simmons <msimmons@redhat.com>
Signed-off-by: Juri Lelli <juri.lelli@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20210803104501.38333-1-juri.lelli@redhat.com
The Frequency Invariance Engine (FIE) is providing a frequency scaling
correction factor that helps achieve more accurate load-tracking.
Normally, this scaling factor can be obtained directly with the help of
the cpufreq drivers as they know the exact frequency the hardware is
running at. But that isn't the case for CPPC cpufreq driver.
Another way of obtaining that is using the arch specific counter
support, which is already present in kernel, but that hardware is
optional for platforms.
This patch updates the CPPC driver to register itself with the topology
core to provide its own implementation (cppc_scale_freq_tick()) of
topology_scale_freq_tick() which gets called by the scheduler on every
tick. Note that the arch specific counters have higher priority than
CPPC counters, if available, though the CPPC driver doesn't need to have
any special handling for that.
On an invocation of cppc_scale_freq_tick(), we schedule an irq work
(since we reach here from hard-irq context), which then schedules a
normal work item and cppc_scale_freq_workfn() updates the per_cpu
arch_freq_scale variable based on the counter updates since the last
tick.
To allow platforms to disable this CPPC counter-based frequency
invariance support, this is all done under CONFIG_ACPI_CPPC_CPUFREQ_FIE,
which is enabled by default.
This also exports sched_setattr_nocheck() as the CPPC driver can be
built as a module.
Cc: linux-acpi@vger.kernel.org
Tested-by: Vincent Guittot <vincent.guittot@linaro.org>
Reviewed-by: Ionela Voinescu <ionela.voinescu@arm.com>
Tested-by: Qian Cai <quic_qiancai@quicinc.com>
Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
- Micro-optimize tick_nohz_full_cpu()
- Optimize idle exit tick restarts to be less eager
- Optimize tick_nohz_dep_set_task() to only wake up
a single CPU. This reduces IPIs and interruptions
on nohz_full CPUs.
- Optimize tick_nohz_dep_set_signal() in a similar
fashion.
- Skip IPIs in tick_nohz_kick_task() when trying
to kick a non-running task.
- Micro-optimize tick_nohz_task_switch() IRQ flags
handling to reduce context switching costs.
- Misc cleanups and fixes
Signed-off-by: Ingo Molnar <mingo@kernel.org>
-----BEGIN PGP SIGNATURE-----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=18pN
-----END PGP SIGNATURE-----
Merge tag 'timers-nohz-2021-06-28' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull timers/nohz updates from Ingo Molnar:
- Micro-optimize tick_nohz_full_cpu()
- Optimize idle exit tick restarts to be less eager
- Optimize tick_nohz_dep_set_task() to only wake up a single CPU.
This reduces IPIs and interruptions on nohz_full CPUs.
- Optimize tick_nohz_dep_set_signal() in a similar fashion.
- Skip IPIs in tick_nohz_kick_task() when trying to kick a
non-running task.
- Micro-optimize tick_nohz_task_switch() IRQ flags handling to
reduce context switching costs.
- Misc cleanups and fixes
* tag 'timers-nohz-2021-06-28' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
MAINTAINERS: Add myself as context tracking maintainer
tick/nohz: Call tick_nohz_task_switch() with interrupts disabled
tick/nohz: Kick only _queued_ task whose tick dependency is updated
tick/nohz: Change signal tick dependency to wake up CPUs of member tasks
tick/nohz: Only wake up a single target cpu when kicking a task
tick/nohz: Update nohz_full Kconfig help
tick/nohz: Update idle_exittime on actual idle exit
tick/nohz: Remove superflous check for CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
tick/nohz: Conditionally restart tick on idle exit
tick/nohz: Evaluate the CPU expression after the static key
- Changes to core scheduling facilities:
- Add "Core Scheduling" via CONFIG_SCHED_CORE=y, which enables
coordinated scheduling across SMT siblings. This is a much
requested feature for cloud computing platforms, to allow
the flexible utilization of SMT siblings, without exposing
untrusted domains to information leaks & side channels, plus
to ensure more deterministic computing performance on SMT
systems used by heterogenous workloads.
There's new prctls to set core scheduling groups, which
allows more flexible management of workloads that can share
siblings.
- Fix task->state access anti-patterns that may result in missed
wakeups and rename it to ->__state in the process to catch new
abuses.
- Load-balancing changes:
- Tweak newidle_balance for fair-sched, to improve
'memcache'-like workloads.
- "Age" (decay) average idle time, to better track & improve workloads
such as 'tbench'.
- Fix & improve energy-aware (EAS) balancing logic & metrics.
- Fix & improve the uclamp metrics.
- Fix task migration (taskset) corner case on !CONFIG_CPUSET.
- Fix RT and deadline utilization tracking across policy changes
- Introduce a "burstable" CFS controller via cgroups, which allows
bursty CPU-bound workloads to borrow a bit against their future
quota to improve overall latencies & batching. Can be tweaked
via /sys/fs/cgroup/cpu/<X>/cpu.cfs_burst_us.
- Rework assymetric topology/capacity detection & handling.
- Scheduler statistics & tooling:
- Disable delayacct by default, but add a sysctl to enable
it at runtime if tooling needs it. Use static keys and
other optimizations to make it more palatable.
- Use sched_clock() in delayacct, instead of ktime_get_ns().
- Misc cleanups and fixes.
Signed-off-by: Ingo Molnar <mingo@kernel.org>
-----BEGIN PGP SIGNATURE-----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=3VDr
-----END PGP SIGNATURE-----
Merge tag 'sched-core-2021-06-28' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull scheduler udpates from Ingo Molnar:
- Changes to core scheduling facilities:
- Add "Core Scheduling" via CONFIG_SCHED_CORE=y, which enables
coordinated scheduling across SMT siblings. This is a much
requested feature for cloud computing platforms, to allow the
flexible utilization of SMT siblings, without exposing untrusted
domains to information leaks & side channels, plus to ensure more
deterministic computing performance on SMT systems used by
heterogenous workloads.
There are new prctls to set core scheduling groups, which allows
more flexible management of workloads that can share siblings.
- Fix task->state access anti-patterns that may result in missed
wakeups and rename it to ->__state in the process to catch new
abuses.
- Load-balancing changes:
- Tweak newidle_balance for fair-sched, to improve 'memcache'-like
workloads.
- "Age" (decay) average idle time, to better track & improve
workloads such as 'tbench'.
- Fix & improve energy-aware (EAS) balancing logic & metrics.
- Fix & improve the uclamp metrics.
- Fix task migration (taskset) corner case on !CONFIG_CPUSET.
- Fix RT and deadline utilization tracking across policy changes
- Introduce a "burstable" CFS controller via cgroups, which allows
bursty CPU-bound workloads to borrow a bit against their future
quota to improve overall latencies & batching. Can be tweaked via
/sys/fs/cgroup/cpu/<X>/cpu.cfs_burst_us.
- Rework assymetric topology/capacity detection & handling.
- Scheduler statistics & tooling:
- Disable delayacct by default, but add a sysctl to enable it at
runtime if tooling needs it. Use static keys and other
optimizations to make it more palatable.
- Use sched_clock() in delayacct, instead of ktime_get_ns().
- Misc cleanups and fixes.
* tag 'sched-core-2021-06-28' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (72 commits)
sched/doc: Update the CPU capacity asymmetry bits
sched/topology: Rework CPU capacity asymmetry detection
sched/core: Introduce SD_ASYM_CPUCAPACITY_FULL sched_domain flag
psi: Fix race between psi_trigger_create/destroy
sched/fair: Introduce the burstable CFS controller
sched/uclamp: Fix uclamp_tg_restrict()
sched/rt: Fix Deadline utilization tracking during policy change
sched/rt: Fix RT utilization tracking during policy change
sched: Change task_struct::state
sched,arch: Remove unused TASK_STATE offsets
sched,timer: Use __set_current_state()
sched: Add get_current_state()
sched,perf,kvm: Fix preemption condition
sched: Introduce task_is_running()
sched: Unbreak wakeups
sched/fair: Age the average idle time
sched/cpufreq: Consider reduced CPU capacity in energy calculation
sched/fair: Take thermal pressure into account while estimating energy
thermal/cpufreq_cooling: Update offline CPUs per-cpu thermal_pressure
sched/fair: Return early from update_tg_cfs_load() if delta == 0
...
On a 128 cores AMD machine, there are 8 cores in nohz_full mode, and
the others are used for housekeeping. When many housekeeping cpus are
in idle state, we can observe huge time burn in the loop for searching
nearest busy housekeeper cpu by ftrace.
9) | get_nohz_timer_target() {
9) | housekeeping_test_cpu() {
9) 0.390 us | housekeeping_get_mask.part.1();
9) 0.561 us | }
9) 0.090 us | __rcu_read_lock();
9) 0.090 us | housekeeping_cpumask();
9) 0.521 us | housekeeping_cpumask();
9) 0.140 us | housekeeping_cpumask();
...
9) 0.500 us | housekeeping_cpumask();
9) | housekeeping_any_cpu() {
9) 0.090 us | housekeeping_get_mask.part.1();
9) 0.100 us | sched_numa_find_closest();
9) 0.491 us | }
9) 0.100 us | __rcu_read_unlock();
9) + 76.163 us | }
for_each_cpu_and() is a micro function, so in get_nohz_timer_target()
function the
for_each_cpu_and(i, sched_domain_span(sd),
housekeeping_cpumask(HK_FLAG_TIMER))
equals to below:
for (i = -1; i = cpumask_next_and(i, sched_domain_span(sd),
housekeeping_cpumask(HK_FLAG_TIMER)), i < nr_cpu_ids;)
That will cause that housekeeping_cpumask() will be invoked many times.
The housekeeping_cpumask() function returns a const value, so it is
unnecessary to invoke it every time. This patch can minimize the worst
searching time from ~76us to ~16us in my testing.
Similarly, the find_new_ilb() function has the same problem.
Co-developed-by: Li RongQing <lirongqing@baidu.com>
Signed-off-by: Li RongQing <lirongqing@baidu.com>
Signed-off-by: Yuan ZhaoXiong <yuanzhaoxiong@baidu.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/1622985115-51007-1-git-send-email-yuanzhaoxiong@baidu.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
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 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
This reverts commit 4c38f2df71.
There are few races in the frequency invariance support for CPPC driver,
namely the driver doesn't stop the kthread_work and irq_work on policy
exit during suspend/resume or CPU hotplug.
A proper fix won't be possible for the 5.13-rc, as it requires a lot of
changes. Lets revert the patch instead for now.
Fixes: 4c38f2df71 ("cpufreq: CPPC: Add support for frequency invariance")
Reported-by: Qian Cai <quic_qiancai@quicinc.com>
Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
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
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
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
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
Call tick_nohz_task_switch() slightly earlier after the context switch
to benefit from disabled IRQs. This way the function doesn't need to
disable them once more.
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Frederic Weisbecker <frederic@kernel.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20210512232924.150322-10-frederic@kernel.org
When the tick dependency of a task is updated, we want it to aknowledge
the new state and restart the tick if needed. If the task is not
running, we don't need to kick it because it will observe the new
dependency upon scheduling in. But if the task is running, we may need
to send an IPI to it so that it gets notified.
Unfortunately we don't have the means to check if a task is running
in a race free way. Checking p->on_cpu in a synchronized way against
p->tick_dep_mask would imply adding a full barrier between
prepare_task_switch() and tick_nohz_task_switch(), which we want to
avoid in this fast-path.
Therefore we blindly fire an IPI to the task's CPU.
Meanwhile we can check if the task is queued on the CPU rq because
p->on_rq is always set to TASK_ON_RQ_QUEUED _before_ schedule() and its
full barrier that precedes tick_nohz_task_switch(). And if the task is
queued on a nohz_full CPU, it also has fair chances to be running as the
isolation constraints prescribe running single tasks on full dynticks
CPUs.
So use this as a trick to check if we can spare an IPI toward a
non-running task.
NOTE: For the ordering to be correct, it is assumed that we never
deactivate a task while it is running, the only exception being the task
deactivating itself while scheduling out.
Suggested-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: Frederic Weisbecker <frederic@kernel.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Acked-by: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20210512232924.150322-9-frederic@kernel.org
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
