preempt_schedule_common() is marked notrace, but it does not use
_notrace() preempt_count functions and __schedule() is also not marked
notrace, which means that its perfectly possible to end up in the
tracer from preempt_schedule_common().
Steve says:
| Yep, there's some history to this. This was originally the issue that
| caused function tracing to go into infinite recursion. But now we have
| preempt_schedule_notrace(), which is used by the function tracer, and
| that function must not be traced till preemption is disabled.
|
| Now if function tracing is running and we take an interrupt when
| NEED_RESCHED is set, it calls
|
| preempt_schedule_common() (not traced)
|
| But then that calls preempt_disable() (traced)
|
| function tracer calls preempt_disable_notrace() followed by
| preempt_enable_notrace() which will see NEED_RESCHED set, and it will
| call preempt_schedule_notrace(), which stops the recursion, but
| still calls __schedule() here, and that means when we return, we call
| the __schedule() from preempt_schedule_common().
|
| That said, I prefer this patch. Preemption is disabled before calling
| __schedule(), and we get rid of a one round recursion with the
| scheduler.
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Steven Rostedt <rostedt@goodmis.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
When we warn about a preempt_count leak; reset the preempt_count to
the known good value such that the problem does not ripple forward.
This is most important on x86 which has a per cpu preempt_count that is
not saved/restored (after this series). So if you schedule with an
invalid (!2*PREEMPT_DISABLE_OFFSET) preempt_count the next task is
messed up too.
Enforcing this invariant limits the borkage to just the one task.
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Frederic Weisbecker <fweisbec@gmail.com>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Steven Rostedt <rostedt@goodmis.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Assuming units of PREEMPT_DISABLE_OFFSET for preempt_count() numbers.
Now that TASK_DEAD no longer results in preempt_count() == 3 during
scheduling, we will always call context_switch() with preempt_count()
== 2.
However, we don't always end up with preempt_count() == 2 in
finish_task_switch() because new tasks get created with
preempt_count() == 1.
Create FORK_PREEMPT_COUNT and set it to 2 and use that in the right
places. Note that we cannot use INIT_PREEMPT_COUNT as that serves
another purpose (boot).
After this, preempt_count() is invariant across the context switch,
with exception of PREEMPT_ACTIVE.
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
TASK_DEAD is special in that the final schedule call from do_exit()
must be done with preemption disabled.
This means we end up scheduling with a preempt_count() higher than
usual (3 instead of the 'expected' 2).
Since future patches will want to rely on an invariant
preempt_count() value during schedule, fix this up.
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Frederic Weisbecker <fweisbec@gmail.com>
Reviewed-by: Steven Rostedt <rostedt@goodmis.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
So the problem this patch is trying to address is as follows:
CPU0 CPU1
context_switch(A, B)
ttwu(A)
LOCK A->pi_lock
A->on_cpu == 0
finish_task_switch(A)
prev_state = A->state <-.
WMB |
A->on_cpu = 0; |
UNLOCK rq0->lock |
| context_switch(C, A)
`-- A->state = TASK_DEAD
prev_state == TASK_DEAD
put_task_struct(A)
context_switch(A, C)
finish_task_switch(A)
A->state == TASK_DEAD
put_task_struct(A)
The argument being that the WMB will allow the load of A->state on CPU0
to cross over and observe CPU1's store of A->state, which will then
result in a double-drop and use-after-free.
Now the comment states (and this was true once upon a long time ago)
that we need to observe A->state while holding rq->lock because that
will order us against the wakeup; however the wakeup will not in fact
acquire (that) rq->lock; it takes A->pi_lock these days.
We can obviously fix this by upgrading the WMB to an MB, but that is
expensive, so we'd rather avoid that.
The alternative this patch takes is: smp_store_release(&A->on_cpu, 0),
which avoids the MB on some archs, but not important ones like ARM.
Reported-by: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: <stable@vger.kernel.org> # v3.1+
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Cc: manfred@colorfullife.com
Cc: will.deacon@arm.com
Fixes: e4a52bcb9a ("sched: Remove rq->lock from the first half of ttwu()")
Link: http://lkml.kernel.org/r/20150929124509.GG3816@twins.programming.kicks-ass.net
Signed-off-by: Ingo Molnar <mingo@kernel.org>
HV_X64_MSR_VP_RUNTIME msr used by guest to get
"the time the virtual processor consumes running guest code,
and the time the associated logical processor spends running
hypervisor code on behalf of that guest."
Calculation of this time is performed by task_cputime_adjusted()
for vcpu task.
Necessary to support loading of winhv.sys in guest, which in turn is
required to support Windows VMBus.
Signed-off-by: Andrey Smetanin <asmetanin@virtuozzo.com>
Reviewed-by: Roman Kagan <rkagan@virtuozzo.com>
Signed-off-by: Denis V. Lunev <den@openvz.org>
CC: Paolo Bonzini <pbonzini@redhat.com>
CC: Gleb Natapov <gleb@kernel.org>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Pull scheduler fix from Thomas Gleixner:
"A single bug fix for the scheduler to prevent dequeueing of the idle
task when setting the cpus allowed mask"
* 'sched-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
sched: Fix crash trying to dequeue/enqueue the idle thread
This reverts commit 51360155ec and adapts
fs/userfaultfd.c to use the old version of that function.
It didn't look robust to call __wake_up_common with "nr == 1" when we
absolutely require wakeall semantics, but we've full control of what we
insert in the two waitqueue heads of the blocked userfaults. No
exclusive waitqueue risks to be inserted into those two waitqueue heads
so we can as well stick to "nr == 1" of the old code and we can rely
purely on the fact no waitqueue inserted in one of the two waitqueue
heads we must enforce as wakeall, has wait->flags WQ_FLAG_EXCLUSIVE set.
Signed-off-by: Andrea Arcangeli <aarcange@redhat.com>
Cc: Dr. David Alan Gilbert <dgilbert@redhat.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Shuah Khan <shuahkh@osg.samsung.com>
Cc: Thierry Reding <treding@nvidia.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Pull KVM fixes from Paolo Bonzini:
"Mostly stable material, a lot of ARM fixes"
* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (22 commits)
sched: access local runqueue directly in single_task_running
arm/arm64: KVM: Remove 'config KVM_ARM_MAX_VCPUS'
arm64: KVM: Remove all traces of the ThumbEE registers
arm: KVM: Disable virtual timer even if the guest is not using it
arm64: KVM: Disable virtual timer even if the guest is not using it
arm/arm64: KVM: vgic: Check for !irqchip_in_kernel() when mapping resources
KVM: s390: Replace incorrect atomic_or with atomic_andnot
arm: KVM: Fix incorrect device to IPA mapping
arm64: KVM: Fix user access for debug registers
KVM: vmx: fix VPID is 0000H in non-root operation
KVM: add halt_attempted_poll to VCPU stats
kvm: fix zero length mmio searching
kvm: fix double free for fast mmio eventfd
kvm: factor out core eventfd assign/deassign logic
kvm: don't try to register to KVM_FAST_MMIO_BUS for non mmio eventfd
KVM: make the declaration of functions within 80 characters
KVM: arm64: add workaround for Cortex-A57 erratum #852523
KVM: fix polling for guest halt continued even if disable it
arm/arm64: KVM: Fix PSCI affinity info return value for non valid cores
arm64: KVM: set {v,}TCR_EL2 RES1 bits
...
Commit 2ee507c472 ("sched: Add function single_task_running to let a task
check if it is the only task running on a cpu") referenced the current
runqueue with the smp_processor_id. When CONFIG_DEBUG_PREEMPT is enabled,
that is only allowed if preemption is disabled or the currrent task is
bound to the local cpu (e.g. kernel worker).
With commit f781951299 ("kvm: add halt_poll_ns module parameter") KVM
calls single_task_running. If CONFIG_DEBUG_PREEMPT is enabled that
generates a lot of kernel messages.
To avoid adding preemption in that cases, as it would limit the usefulness,
we change single_task_running to access directly the cpu local runqueue.
Cc: Tim Chen <tim.c.chen@linux.intel.com>
Suggested-by: Peter Zijlstra <peterz@infradead.org>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: <stable@vger.kernel.org>
Fixes: 2ee507c472
Signed-off-by: Dominik Dingel <dingel@linux.vnet.ibm.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Currently task_numa_work() scans up to numa_balancing_scan_size_mb worth
of memory per invocation, but only counts memory areas that have at
least one PTE that is still present and not marked for numa hint faulting.
It will skip over arbitarily large amounts of memory that are either
unused, full of swap ptes, or full of PTEs that were already marked
for NUMA hint faults but have not been faulted on yet.
This can cause excessive amounts of CPU use, due to there being
essentially no upper limit on the scan rate of very large processes
that are not yet in a phase where they are actively accessing old
memory pages (eg. they are still initializing their data).
Avoid that problem by placing an upper limit on the amount of virtual
memory that task_numa_work() scans in each invocation. This can be a
higher limit than "pages", to ensure the task still skips over unused
areas fairly quickly.
While we are here, also fix the "nr_pte_updates" logic, so it only
counts page ranges with ptes in them.
Reported-by: Andrea Arcangeli <aarcange@redhat.com>
Reported-by: Jan Stancek <jstancek@redhat.com>
Signed-off-by: Rik van Riel <riel@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Mel Gorman <mgorman@suse.de>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/20150911090027.4a7987bd@annuminas.surriel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Sasha reports that his virtual machine tries to schedule the idle
thread since commit 6c37067e27 ("sched: Change the
sched_class::set_cpus_allowed() calling context").
Hit trace shows this happening from idle_thread_get()->init_idle(),
which is the _second_ init_idle() invocation on that task_struct, the
first being done through idle_init()->fork_idle(). (this code is
insane...)
Because we call init_idle() twice in a row, its ->sched_class ==
&idle_sched_class and ->on_rq = TASK_ON_RQ_QUEUED. This means
do_set_cpus_allowed() think we're queued and will call dequeue_task(),
which is implemented with BUG() for the idle class, seeing how
dequeueing the idle task is a daft thing.
Aside of the whole insanity of calling init_idle() _twice_, change the
code to call set_cpus_allowed_common() instead as this is 'obviously'
before the idle task gets ran etc..
Reported-by: Sasha Levin <sasha.levin@oracle.com>
Tested-by: Sasha Levin <sasha.levin@oracle.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Fixes: 6c37067e27 ("sched: Change the sched_class::set_cpus_allowed() calling context")
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Pull scheduler fixes from Ingo Molnar:
"A migrate_tasks() locking fix, and a late-coming nohz change plus a
nohz debug check"
* 'sched-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
sched: 'Annotate' migrate_tasks()
nohz: Assert existing housekeepers when nohz full enabled
nohz: Affine unpinned timers to housekeepers
Currently the load_{sum,avg} and util_{sum,avg} tracking is asymmetric
in that load tracking gets a 2^10 unit from the weight, but util gets
no such factor.
This results in more lost bits for util scaling and asymmetric scaling
rules.
Fix this by removing shifts, such that we gain the 2^10 factor from
scaling. There is no risk of overflowing the u32 as the max value is
now LOAD_AVG_MAX << 10, which is still well below UINT_MAX.
This further entangles the assumption that both LOAD and CAPACITY
shifts are the same (and 10) so put in an assertion for that.
This fixes the math for the LOAD_RESOLUTION != 0 case.
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Prior to this patch; the line:
scaled_delta_w = (delta_w * 1024) >> 10;
which is the result of the default arch_scale_freq_capacity()
function, turns into:
1b03: 49 89 d1 mov %rdx,%r9
1b06: 49 c1 e1 0a shl $0xa,%r9
1b0a: 49 c1 e9 0a shr $0xa,%r9
Which is silly; when made unsigned int, GCC recognises this as
pointless ops and fails to emit them (confirmed on 4.9.3 and 5.1.1).
Furthermore, afaict unsigned is actually the correct type for these
fields anyway, as we've explicitly ruled out negative delta's earlier
in this function.
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Besides the existing frequency scale-invariance correction factor, apply
CPU scale-invariance correction factor to utilization tracking to
compensate for any differences in compute capacity. This could be due to
micro-architectural differences (i.e. instructions per seconds) between
cpus in HMP systems (e.g. big.LITTLE), and/or differences in the current
maximum frequency supported by individual cpus in SMP systems. In the
existing implementation utilization isn't comparable between cpus as it
is relative to the capacity of each individual CPU.
Each segment of the sched_avg.util_sum geometric series is now scaled
by the CPU performance factor too so the sched_avg.util_avg of each
sched entity will be invariant from the particular CPU of the HMP/SMP
system on which the sched entity is scheduled.
With this patch, the utilization of a CPU stays relative to the max CPU
performance of the fastest CPU in the system.
In contrast to utilization (sched_avg.util_sum), load
(sched_avg.load_sum) should not be scaled by compute capacity. The
utilization metric is based on running time which only makes sense when
cpus are _not_ fully utilized (utilization cannot go beyond 100% even if
more tasks are added), where load is runnable time which isn't limited
by the capacity of the CPU and therefore is a better metric for
overloaded scenarios. If we run two nice-0 busy loops on two cpus with
different compute capacity their load should be similar since their
compute demands are the same. We have to assume that the compute demand
of any task running on a fully utilized CPU (no spare cycles = 100%
utilization) is high and the same no matter of the compute capacity of
its current CPU, hence we shouldn't scale load by CPU capacity.
Signed-off-by: Dietmar Eggemann <dietmar.eggemann@arm.com>
Signed-off-by: Morten Rasmussen <morten.rasmussen@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/55CE7409.1000700@arm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Since commit:
d4573c3e1c ("sched: Improve load balancing in the presence of idle CPUs")
the ILB CPU starts with the idle load balancing of other idle CPUs and
finishes with itself in order to speed up the spread of tasks in all
idle CPUs.
The this_rq->next_balance is still used in nohz_idle_balance() as an
intermediate step to gather the shortest next balance before updating
nohz.next_balance. But the former has not been updated yet and is likely to
be set with the current jiffies. As a result, the nohz.next_balance will be
set with current jiffies instead of the real next balance date. This
generates spurious kicks of nohz ilde balance.
nohz_idle_balance() must set the nohz.next_balance without taking into
account this_rq->next_balance which is not updated yet. Then, this_rq will
update nohz.next_update with its next_balance once updated and if necessary.
Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Jason Low <jason.low2@hp.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: preeti@linux.vnet.ibm.com
Link: http://lkml.kernel.org/r/1438595750-20455-1-git-send-email-vincent.guittot@linaro.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
By observing that switched_from_fair() detaches from a runqueue, and
switched_to_fair() attaches to a runqueue, we can see that
task_move_group_fair() is one followed by the other with flipping the
runqueue in between.
Therefore extract all the common bits and implement all three
functions in terms of them.
This should fix a few corner cases wrt. vruntime normalization; where,
when we take a task off of a runqueue we convert to an approximation
of lag by subtracting min_vruntime, and when placing a task on the a
runqueue to the reverse.
Suggested-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Byungchul Park <byungchul.park@lge.com>
[peterz: Changelog]
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: yuyang.du@intel.com
Link: http://lkml.kernel.org/r/1440069720-27038-6-git-send-email-byungchul.park@lge.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Where switched_from_fair() will remove the entity's load from the
runqueue, switched_to_fair() does not currently add it back. This
means that when a task leaves the fair class for a short duration; say
because of PI; we loose its load contribution.
This can ripple forward and disturb the load tracking because other
operations (enqueue, dequeue) assume its factored in. Only once the
runqueue empties will the load tracking recover.
When we add it back in, age the per entity average to match up with
the runqueue age. This has the obvious problem that if the task leaves
the fair class for a significant time, the load will age to 0.
Employ the normal migration rule for inter-runqueue moves in
task_move_group_fair(). Again, there is the obvious problem of the
task migrating while not in the fair class.
The alternative solution would be to to omit the chunk in
attach_entity_load_avg(), which would effectively reset the timestamp
and use whatever avg there was.
Signed-off-by: Byungchul Park <byungchul.park@lge.com>
[ Rewrote the changelog and comments. ]
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: yuyang.du@intel.com
Link: http://lkml.kernel.org/r/1440069720-27038-5-git-send-email-byungchul.park@lge.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
