The expiry cache is an array indexed by clock ids. The new sample functions
allow to retrieve a corresponding array of samples.
Convert the fastpath expiry checks to make use of the new sample functions
and do the comparisons on the sample and the expiry array.
Make the check for the expiry array being zero array based as well.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Frederic Weisbecker <frederic@kernel.org>
Link: https://lkml.kernel.org/r/20190821192921.695481430@linutronix.de
Using struct task_cputime for the expiry cache is a pretty odd choice and
comes with magic defines to rename the fields for usage in the expiry
cache.
struct task_cputime is basically a u64 array with 3 members, but it has
distinct members.
The expiry cache content is different than the content of task_cputime
because
expiry[PROF] = task_cputime.stime + task_cputime.utime
expiry[VIRT] = task_cputime.utime
expiry[SCHED] = task_cputime.sum_exec_runtime
So there is no direct mapping between task_cputime and the expiry cache and
the #define based remapping is just a horrible hack.
Having the expiry cache array based allows further simplification of the
expiry code.
To avoid an all in one cleanup which is hard to review add a temporary
anonymous union into struct task_cputime which allows array based access to
it. That requires to reorder the members. Add a build time sanity check to
validate that the members are at the same place.
The union and the build time checks will be removed after conversion.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Frederic Weisbecker <frederic@kernel.org>
Link: https://lkml.kernel.org/r/20190821192921.105793824@linutronix.de
Per task/process data of posix CPU timers is all over the place which
makes the code hard to follow and requires ifdeffery.
Create a container to hold all this information in one place, so data is
consolidated and the ifdeffery can be confined to the posix timer header
file and removed from places like fork.
As a first step, move the cpu_timers list head array into the new struct
and clean up the initializers and simplify fork. The remaining #ifdef in
fork will be removed later.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Frederic Weisbecker <frederic@kernel.org>
Link: https://lkml.kernel.org/r/20190821192920.819418976@linutronix.de
cpu_clock_sample_group() and cpu_timer_sample_group() are almost the
same. Before the rename one called thread_group_cputimer() and the other
thread_group_cputime(). Really intuitive function names.
Consolidate the functions and also avoid the thread traversal when
the thread group's accounting is already active.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Frederic Weisbecker <frederic@kernel.org>
Link: https://lkml.kernel.org/r/20190821192919.960966884@linutronix.de
thread_group_cputimer() is a complete misnomer. The function does two things:
- For arming process wide timers it makes sure that the atomic time
storage is up to date. If no cpu timer is armed yet, then the atomic
time storage is not updated by the scheduler for performance reasons.
In that case a full summing up of all threads needs to be done and the
update needs to be enabled.
- Samples the current time into the caller supplied storage.
Rename it to thread_group_start_cputime(), make it static and fixup the
callsite.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Frederic Weisbecker <frederic@kernel.org>
Link: https://lkml.kernel.org/r/20190821192919.869350319@linutronix.de
get_itimer() locks sighand lock and checks whether the timer is already
expired. If it is not expired then the thread group cputime accounting is
already enabled. Use the sampling function not the one which is meant for
starting a timer.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Frederic Weisbecker <frederic@kernel.org>
Link: https://lkml.kernel.org/r/20190821192919.689713638@linutronix.de
get_itimer() needs a sample of the current thread group cputime. It invokes
thread_group_cputimer() - which is a misnomer. That function also starts
eventually the group cputime accouting which is bogus because the
accounting is already active when a timer is armed.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Frederic Weisbecker <frederic@kernel.org>
Link: https://lkml.kernel.org/r/20190821192919.599658199@linutronix.de
The code contains three slightly different copies of validating whether a
given clock resolves to a valid task and whether the current caller has
permissions to access it.
Create central functions. Replace check_clock() as a first step and rename
it to something sensible.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lkml.kernel.org/r/20190821192919.326097175@linutronix.de
The VDSO update for CLOCK_BOOTTIME has a overflow issue as it shifts the
nanoseconds based boot time offset left by the clocksource shift. That
overflows once the boot time offset becomes large enough. As a consequence
CLOCK_BOOTTIME in the VDSO becomes a random number causing applications to
misbehave.
Fix it by storing a timespec64 representation of the offset when boot time
is adjusted and add that to the MONOTONIC base time value in the vdso data
page. Using the timespec64 representation avoids a 64bit division in the
update code.
Fixes: 44f57d788e ("timekeeping: Provide a generic update_vsyscall() implementation")
Reported-by: Chris Clayton <chris2553@googlemail.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Chris Clayton <chris2553@googlemail.com>
Tested-by: Vincenzo Frascino <vincenzo.frascino@arm.com>
Link: https://lkml.kernel.org/r/alpine.DEB.2.21.1908221257580.1983@nanos.tec.linutronix.de
Warning when p == NULL and then proceeding and dereferencing p does not
make any sense as the kernel will crash with a NULL pointer dereference
right away.
Bailing out when p == NULL and returning an error code does not cure the
underlying problem which caused p to be NULL. Though it might allow to
do proper debugging.
Same applies to the clock id check in set_process_cpu_timer().
Clean them up and make them return without trying to do further damage.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Frederic Weisbecker <frederic@kernel.org>
Link: https://lkml.kernel.org/r/20190819143801.846497772@linutronix.de
migration_base is used as a placeholder when an hrtimer is migrated to a
different CPU. In the case that hrtimer_cancel_wait_running() hits a timer
which is currently migrated it would pointlessly acquire the expiry lock of
the migration base, which is even not initialized.
Surely it could be initialized, but there is absolutely no point in
acquiring this lock because the timer is guaranteed not to run it's
callback for which the caller waits to finish on that base. So it would
just do the inc/lock/dec/unlock dance for nothing.
As the base switch is short and non-preemptible, there is no issue when the
wait function returns immediately.
The timer base and base->cpu_base cannot be NULL in the code path which is
invoking that, so just replace those checks with a check whether base is
migration base.
[ tglx: Updated from RT patch. Massaged changelog. Added comment. ]
Signed-off-by: Julien Grall <julien.grall@arm.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lkml.kernel.org/r/20190821092409.13225-4-julien.grall@arm.com
The update to timer->base is protected by the base->cpu_base->lock().
However, hrtimer_cancel_wait_running() does access it lockless. So the
compiler is allowed to refetch timer->base which can cause havoc when the
timer base is changed concurrently.
Use READ_ONCE() to prevent this.
[ tglx: Adapted from a RT patch ]
Signed-off-by: Julien Grall <julien.grall@arm.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lkml.kernel.org/r/20190821092409.13225-2-julien.grall@arm.com
The handling of a priority inversion between timer cancelling and a a not
well defined possible preemption of softirq kthread is not very clear.
Especially in the posix timers side it's unclear why there is a specific RT
wait callback.
All the nice explanations can be found in the initial changelog of
f61eff83ce (hrtimer: Prepare support for PREEMPT_RT").
Extract the detailed informations from there and put it into comments.
Signed-off-by: Frederic Weisbecker <frederic@kernel.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lkml.kernel.org/r/20190820132656.GC2093@lenoir
Posix timer delete retry loops are affected by the same priority inversion
and live lock issues as the other timers.
Provide a RT specific synchronization function which keeps a reference to
the timer by holding rcu read lock to prevent the timer from being freed,
dropping the timer lock and invoking the timer specific wait function via a
new callback.
This does not yet cover posix CPU timers because they need more special
treatment on PREEMPT_RT.
[ This is folded into the original attempt which did not use a callback. ]
Originally-by: Anna-Maria Gleixenr <anna-maria@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Frederic Weisbecker <frederic@kernel.org>
Link: https://lkml.kernel.org/r/20190819143801.656864506@linutronix.de
Timer deletion on PREEMPT_RT is prone to priority inversion and live
locks. The hrtimer code has a synchronization mechanism for this. Posix CPU
timers will grow one.
But that mechanism cannot be invoked while holding the k_itimer lock
because that can deadlock against the running timer callback. So the lock
must be dropped which allows the timer to be freed.
The timer free can be prevented by taking RCU readlock before dropping the
lock, but because the rcu_head is part of the 'it' union a concurrent free
will overwrite the hrtimer on which the task is trying to synchronize.
Move the rcu_head out of the union to prevent this.
[ tglx: Fixed up kernel-doc. Rewrote changelog ]
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20190730223828.965541887@linutronix.de
When PREEMPT_RT is enabled, the soft interrupt thread can be preempted. If
the soft interrupt thread is preempted in the middle of a timer callback,
then calling del_timer_sync() can lead to two issues:
- If the caller is on a remote CPU then it has to spin wait for the timer
handler to complete. This can result in unbound priority inversion.
- If the caller originates from the task which preempted the timer
handler on the same CPU, then spin waiting for the timer handler to
complete is never going to end.
To avoid these issues, add a new lock to the timer base which is held
around the execution of the timer callbacks. If del_timer_sync() detects
that the timer callback is currently running, it blocks on the expiry
lock. When the callback is finished, the expiry lock is dropped by the
softirq thread which wakes up the waiter and the system makes progress.
This addresses both the priority inversion and the life lock issues.
This mechanism is not used for timers which are marked IRQSAFE as for those
preemption is disabled accross the callback and therefore this situation
cannot happen. The callbacks for such timers need to be individually
audited for RT compliance.
The same issue can happen in virtual machines when the vCPU which runs a
timer callback is scheduled out. If a second vCPU of the same guest calls
del_timer_sync() it will spin wait for the other vCPU to be scheduled back
in. The expiry lock mechanism would avoid that. It'd be trivial to enable
this when paravirt spinlocks are enabled in a guest, but it's not clear
whether this is an actual problem in the wild, so for now it's an RT only
mechanism.
As the softirq thread can be preempted with PREEMPT_RT=y, the SMP variant
of del_timer_sync() needs to be used on UP as well.
[ tglx: Refactored it for mainline ]
Signed-off-by: Anna-Maria Gleixner <anna-maria@linutronix.de>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20190726185753.832418500@linutronix.de
When PREEMPT_RT is enabled, the soft interrupt thread can be preempted. If
the soft interrupt thread is preempted in the middle of a timer callback,
then calling hrtimer_cancel() can lead to two issues:
- If the caller is on a remote CPU then it has to spin wait for the timer
handler to complete. This can result in unbound priority inversion.
- If the caller originates from the task which preempted the timer
handler on the same CPU, then spin waiting for the timer handler to
complete is never going to end.
To avoid these issues, add a new lock to the timer base which is held
around the execution of the timer callbacks. If hrtimer_cancel() detects
that the timer callback is currently running, it blocks on the expiry
lock. When the callback is finished, the expiry lock is dropped by the
softirq thread which wakes up the waiter and the system makes progress.
This addresses both the priority inversion and the life lock issues.
The same issue can happen in virtual machines when the vCPU which runs a
timer callback is scheduled out. If a second vCPU of the same guest calls
hrtimer_cancel() it will spin wait for the other vCPU to be scheduled back
in. The expiry lock mechanism would avoid that. It'd be trivial to enable
this when paravirt spinlocks are enabled in a guest, but it's not clear
whether this is an actual problem in the wild, so for now it's an RT only
mechanism.
[ tglx: Refactored it for mainline ]
Signed-off-by: Anna-Maria Gleixner <anna-maria@linutronix.de>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20190726185753.737767218@linutronix.de
On PREEMPT_RT enabled kernels hrtimers which are not explicitely marked for
hard interrupt expiry mode are moved into soft interrupt context either for
latency reasons or because the hrtimer callback takes regular spinlocks or
invokes other functions which are not suitable for hard interrupt context
on PREEMPT_RT.
The hrtimer_sleeper callback is RT compatible in hard interrupt context,
but there is a latency concern: Untrusted userspace can spawn many threads
which arm timers for the same expiry time on the same CPU. On expiry that
causes a latency spike due to the wakeup of a gazillion threads.
OTOH, priviledged real-time user space applications rely on the low latency
of hard interrupt wakeups. These syscall related wakeups are all based on
hrtimer sleepers.
If the current task is in a real-time scheduling class, mark the mode for
hard interrupt expiry.
[ tglx: Split out of a larger combo patch. Added changelog ]
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20190726185753.645792403@linutronix.de
On PREEMPT_RT not all hrtimers can be expired in hard interrupt context
even if that is perfectly fine on a PREEMPT_RT=n kernel, e.g. because they
take regular spinlocks. Also for latency reasons PREEMPT_RT tries to defer
most hrtimers' expiry into softirq context.
hrtimers marked with HRTIMER_MODE_HARD must be kept in hard interrupt
context expiry mode. Add the required logic.
No functional change for PREEMPT_RT=n kernels.
[ tglx: Split out of a larger combo patch. Added changelog ]
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20190726185753.551967692@linutronix.de
The tick related hrtimers, which drive the scheduler tick and hrtimer based
broadcasting are required to expire in hard interrupt context for obvious
reasons.
Mark them so PREEMPT_RT kernels wont move them to soft interrupt expiry.
Make the horribly formatted RCU_NONIDLE bracket maze readable while at it.
No functional change,
[ tglx: Split out from larger combo patch. Add changelog ]
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20190726185753.459144407@linutronix.de
hrtimer_start_range_ns() has a WARN_ONCE() which verifies that a timer
which is marker for softirq expiry is not queued in the hard interrupt base
and vice versa.
When PREEMPT_RT is enabled, timers which are not explicitely marked to
expire in hard interrupt context are deferrred to the soft interrupt. So
the regular check would trigger.
Change the check, so when PREEMPT_RT is enabled, it is verified that the
timers marked for hard interrupt expiry are not tried to be queued for soft
interrupt expiry or any of the unmarked and softirq marked is tried to be
expired in hard interrupt context.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
hrtimer_sleepers will gain a scheduling class dependent treatment on
PREEMPT_RT. Create a wrapper around hrtimer_start_expires() to make that
possible.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
hrtimer_init_sleeper() calls require prior initialisation of the hrtimer
object which is embedded into the hrtimer_sleeper.
Combine the initialization and spare a function call. Fixup all call sites.
This is also a preparatory change for PREEMPT_RT to do hrtimer sleeper
specific initializations of the embedded hrtimer without modifying any of
the call sites.
No functional change.
[ anna-maria: Minor cleanups ]
[ tglx: Adopted to the removal of the task argument of
hrtimer_init_sleeper() and trivial polishing.
Folded a fix from Stephen Rothwell for the vsoc code ]
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Anna-Maria Gleixner <anna-maria@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20190726185752.887468908@linutronix.de
On 32-bit x86 when building with clang-9, the 'division' loop gets turned
back into an inefficient division that causes a link error:
kernel/time/vsyscall.o: In function `update_vsyscall':
vsyscall.c:(.text+0xe3): undefined reference to `__udivdi3'
Use the existing __iter_div_u64_rem() function which is used to address the
same issue in other places.
Fixes: 44f57d788e ("timekeeping: Provide a generic update_vsyscall() implementation")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Nathan Chancellor <natechancellor@gmail.com>
Tested-by: Nathan Chancellor <natechancellor@gmail.com>
Link: https://lkml.kernel.org/r/20190710130206.1670830-1-arnd@arndb.de
Pull scheduler updates from Ingo Molnar:
- Remove the unused per rq load array and all its infrastructure, by
Dietmar Eggemann.
- Add utilization clamping support by Patrick Bellasi. This is a
refinement of the energy aware scheduling framework with support for
boosting of interactive and capping of background workloads: to make
sure critical GUI threads get maximum frequency ASAP, and to make
sure background processing doesn't unnecessarily move to cpufreq
governor to higher frequencies and less energy efficient CPU modes.
- Add the bare minimum of tracepoints required for LISA EAS regression
testing, by Qais Yousef - which allows automated testing of various
power management features, including energy aware scheduling.
- Restructure the former tsk_nr_cpus_allowed() facility that the -rt
kernel used to modify the scheduler's CPU affinity logic such as
migrate_disable() - introduce the task->cpus_ptr value instead of
taking the address of &task->cpus_allowed directly - by Sebastian
Andrzej Siewior.
- Misc optimizations, fixes, cleanups and small enhancements - see the
Git log for details.
* 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (33 commits)
sched/uclamp: Add uclamp support to energy_compute()
sched/uclamp: Add uclamp_util_with()
sched/cpufreq, sched/uclamp: Add clamps for FAIR and RT tasks
sched/uclamp: Set default clamps for RT tasks
sched/uclamp: Reset uclamp values on RESET_ON_FORK
sched/uclamp: Extend sched_setattr() to support utilization clamping
sched/core: Allow sched_setattr() to use the current policy
sched/uclamp: Add system default clamps
sched/uclamp: Enforce last task's UCLAMP_MAX
sched/uclamp: Add bucket local max tracking
sched/uclamp: Add CPU's clamp buckets refcounting
sched/fair: Rename weighted_cpuload() to cpu_runnable_load()
sched/debug: Export the newly added tracepoints
sched/debug: Add sched_overutilized tracepoint
sched/debug: Add new tracepoint to track PELT at se level
sched/debug: Add new tracepoints to track PELT at rq level
sched/debug: Add a new sched_trace_*() helper functions
sched/autogroup: Make autogroup_path() always available
sched/wait: Deduplicate code with do-while
sched/topology: Remove unused 'sd' parameter from arch_scale_cpu_capacity()
...
