Currently the freq invariant accounting (in
__update_entity_runnable_avg() and sched_rt_avg_update()) get the
scale factor from a weak function call, this means that even for archs
that default on their implementation the compiler cannot see into this
function and optimize the extra scaling math away.
This is sad, esp. since its a 64-bit multiplication which can be quite
costly on some platforms.
So replace the weak function with #ifdef and __always_inline goo. This
is not quite as nice from an arch support PoV but should at least
result in compile time errors if done wrong.
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Ben Segall <bsegall@google.com>
Cc: Morten.Rasmussen@arm.com
Cc: Paul Turner <pjt@google.com>
Cc: Vincent Guittot <vincent.guittot@linaro.org>
Cc: dietmar.eggemann@arm.com
Cc: efault@gmx.de
Cc: kamalesh@linux.vnet.ibm.com
Cc: nicolas.pitre@linaro.org
Cc: preeti@linux.vnet.ibm.com
Cc: riel@redhat.com
Link: http://lkml.kernel.org/r/20150323131905.GF23123@twins.programming.kicks-ass.net
Signed-off-by: Ingo Molnar <mingo@kernel.org>
When a CPU is used to handle a lot of IRQs or some RT tasks, the remaining
capacity for CFS tasks can be significantly reduced. Once we detect such
situation by comparing cpu_capacity_orig and cpu_capacity, we trig an idle
load balance to check if it's worth moving its tasks on an idle CPU.
It's worth trying to move the task before the CPU is fully utilized to
minimize the preemption by irq or RT tasks.
Once the idle load_balance has selected the busiest CPU, it will look for an
active load balance for only two cases:
- There is only 1 task on the busiest CPU.
- We haven't been able to move a task of the busiest rq.
A CPU with a reduced capacity is included in the 1st case, and it's worth to
actively migrate its task if the idle CPU has got more available capacity for
CFS tasks. This test has been added in need_active_balance.
As a sidenote, this will not generate more spurious ilb because we already
trig an ilb if there is more than 1 busy cpu. If this cpu is the only one that
has a task, we will trig the ilb once for migrating the task.
The nohz_kick_needed function has been cleaned up a bit while adding the new
test
env.src_cpu and env.src_rq must be set unconditionnally because they are used
in need_active_balance which is called even if busiest->nr_running equals 1
Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Morten.Rasmussen@arm.com
Cc: dietmar.eggemann@arm.com
Cc: efault@gmx.de
Cc: kamalesh@linux.vnet.ibm.com
Cc: linaro-kernel@lists.linaro.org
Cc: nicolas.pitre@linaro.org
Cc: preeti@linux.vnet.ibm.com
Cc: riel@redhat.com
Link: http://lkml.kernel.org/r/1425052454-25797-12-git-send-email-vincent.guittot@linaro.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
The scheduler tries to compute how many tasks a group of CPUs can handle by
assuming that a task's load is SCHED_LOAD_SCALE and a CPU's capacity is
SCHED_CAPACITY_SCALE.
'struct sg_lb_stats:group_capacity_factor' divides the capacity of the group
by SCHED_LOAD_SCALE to estimate how many task can run in the group. Then, it
compares this value with the sum of nr_running to decide if the group is
overloaded or not.
But the 'group_capacity_factor' concept is hardly working for SMT systems, it
sometimes works for big cores but fails to do the right thing for little cores.
Below are two examples to illustrate the problem that this patch solves:
1- If the original capacity of a CPU is less than SCHED_CAPACITY_SCALE
(640 as an example), a group of 3 CPUS will have a max capacity_factor of 2
(div_round_closest(3x640/1024) = 2) which means that it will be seen as
overloaded even if we have only one task per CPU.
2 - If the original capacity of a CPU is greater than SCHED_CAPACITY_SCALE
(1512 as an example), a group of 4 CPUs will have a capacity_factor of 4
(at max and thanks to the fix [0] for SMT system that prevent the apparition
of ghost CPUs) but if one CPU is fully used by rt tasks (and its capacity is
reduced to nearly nothing), the capacity factor of the group will still be 4
(div_round_closest(3*1512/1024) = 5 which is cap to 4 with [0]).
So, this patch tries to solve this issue by removing capacity_factor and
replacing it with the 2 following metrics:
- The available CPU's capacity for CFS tasks which is already used by
load_balance().
- The usage of the CPU by the CFS tasks. For the latter, utilization_avg_contrib
has been re-introduced to compute the usage of a CPU by CFS tasks.
'group_capacity_factor' and 'group_has_free_capacity' has been removed and replaced
by 'group_no_capacity'. We compare the number of task with the number of CPUs and
we evaluate the level of utilization of the CPUs to define if a group is
overloaded or if a group has capacity to handle more tasks.
For SD_PREFER_SIBLING, a group is tagged overloaded if it has more than 1 task
so it will be selected in priority (among the overloaded groups). Since [1],
SD_PREFER_SIBLING is no more concerned by the computation of 'load_above_capacity'
because local is not overloaded.
[1] 9a5d9ba6a3 ("sched/fair: Allow calculate_imbalance() to move idle cpus")
Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Morten.Rasmussen@arm.com
Cc: dietmar.eggemann@arm.com
Cc: efault@gmx.de
Cc: kamalesh@linux.vnet.ibm.com
Cc: linaro-kernel@lists.linaro.org
Cc: nicolas.pitre@linaro.org
Cc: preeti@linux.vnet.ibm.com
Cc: riel@redhat.com
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: http://lkml.kernel.org/r/1425052454-25797-9-git-send-email-vincent.guittot@linaro.org
[ Tidied up the changelog. ]
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Monitor the usage level of each group of each sched_domain level. The usage is
the portion of cpu_capacity_orig that is currently used on a CPU or group of
CPUs. We use the utilization_load_avg to evaluate the usage level of each
group.
The utilization_load_avg only takes into account the running time of the CFS
tasks on a CPU with a maximum value of SCHED_LOAD_SCALE when the CPU is fully
utilized. Nevertheless, we must cap utilization_load_avg which can be
temporally greater than SCHED_LOAD_SCALE after the migration of a task on this
CPU and until the metrics are stabilized.
The utilization_load_avg is in the range [0..SCHED_LOAD_SCALE] to reflect the
running load on the CPU whereas the available capacity for the CFS task is in
the range [0..cpu_capacity_orig]. In order to test if a CPU is fully utilized
by CFS tasks, we have to scale the utilization in the cpu_capacity_orig range
of the CPU to get the usage of the latter. The usage can then be compared with
the available capacity (ie cpu_capacity) to deduct the usage level of a CPU.
The frequency scaling invariance of the usage is not taken into account in this
patch, it will be solved in another patch which will deal with frequency
scaling invariance on the utilization_load_avg.
Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Morten Rasmussen <morten.rasmussen@arm.com>
Cc: Morten.Rasmussen@arm.com
Cc: dietmar.eggemann@arm.com
Cc: efault@gmx.de
Cc: kamalesh@linux.vnet.ibm.com
Cc: linaro-kernel@lists.linaro.org
Cc: nicolas.pitre@linaro.org
Cc: preeti@linux.vnet.ibm.com
Cc: riel@redhat.com
Link: http://lkml.kernel.org/r/1425455327-13508-1-git-send-email-vincent.guittot@linaro.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
This new field 'cpu_capacity_orig' reflects the original capacity of a CPU
before being altered by rt tasks and/or IRQ
The cpu_capacity_orig will be used:
- to detect when the capacity of a CPU has been noticeably reduced so we can
trig load balance to look for a CPU with better capacity. As an example, we
can detect when a CPU handles a significant amount of irq
(with CONFIG_IRQ_TIME_ACCOUNTING) but this CPU is seen as an idle CPU by
scheduler whereas CPUs, which are really idle, are available.
- evaluate the available capacity for CFS tasks
Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Kamalesh Babulal <kamalesh@linux.vnet.ibm.com>
Acked-by: Morten Rasmussen <morten.rasmussen@arm.com>
Cc: Morten.Rasmussen@arm.com
Cc: dietmar.eggemann@arm.com
Cc: efault@gmx.de
Cc: linaro-kernel@lists.linaro.org
Cc: nicolas.pitre@linaro.org
Cc: preeti@linux.vnet.ibm.com
Cc: riel@redhat.com
Link: http://lkml.kernel.org/r/1425052454-25797-7-git-send-email-vincent.guittot@linaro.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
The average running time of RT tasks is used to estimate the remaining compute
capacity for CFS tasks. This remaining capacity is the original capacity scaled
down by a factor (aka scale_rt_capacity). This estimation of available capacity
must also be invariant with frequency scaling.
A frequency scaling factor is applied on the running time of the RT tasks for
computing scale_rt_capacity.
In sched_rt_avg_update(), we now scale the RT execution time like below:
rq->rt_avg += rt_delta * arch_scale_freq_capacity() >> SCHED_CAPACITY_SHIFT
Then, scale_rt_capacity can be summarized by:
scale_rt_capacity = SCHED_CAPACITY_SCALE * available / total
with available = total - rq->rt_avg
This has been been optimized in current code by:
scale_rt_capacity = available / (total >> SCHED_CAPACITY_SHIFT)
But we can also developed the equation like below:
scale_rt_capacity = SCHED_CAPACITY_SCALE - ((rq->rt_avg << SCHED_CAPACITY_SHIFT) / total)
and we can optimize the equation by removing SCHED_CAPACITY_SHIFT shift in
the computation of rq->rt_avg and scale_rt_capacity().
so rq->rt_avg += rt_delta * arch_scale_freq_capacity()
and
scale_rt_capacity = SCHED_CAPACITY_SCALE - (rq->rt_avg / total)
arch_scale_frequency_capacity() will be called in the hot path of the scheduler
which implies to have a short and efficient function.
As an example, arch_scale_frequency_capacity() should return a cached value that
is updated periodically outside of the hot path.
Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Morten Rasmussen <morten.rasmussen@arm.com>
Cc: Morten.Rasmussen@arm.com
Cc: dietmar.eggemann@arm.com
Cc: efault@gmx.de
Cc: kamalesh@linux.vnet.ibm.com
Cc: linaro-kernel@lists.linaro.org
Cc: nicolas.pitre@linaro.org
Cc: preeti@linux.vnet.ibm.com
Cc: riel@redhat.com
Link: http://lkml.kernel.org/r/1425052454-25797-6-git-send-email-vincent.guittot@linaro.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Apply frequency scale-invariance correction factor to usage tracking.
Each segment of the running_avg_sum geometric series is now scaled by the
current frequency so the utilization_avg_contrib of each entity will be
invariant with frequency scaling.
As a result, utilization_load_avg which is the sum of utilization_avg_contrib,
becomes invariant too. So the usage level that is returned by get_cpu_usage(),
stays relative to the max frequency as the cpu_capacity which is is compared against.
Then, we want the keep the load tracking values in a 32-bit type, which implies
that the max value of {runnable|running}_avg_sum must be lower than
2^32/88761=48388 (88761 is the max weigth of a task). As LOAD_AVG_MAX = 47742,
arch_scale_freq_capacity() must return a value less than
(48388/47742) << SCHED_CAPACITY_SHIFT = 1037 (SCHED_SCALE_CAPACITY = 1024).
So we define the range to [0..SCHED_SCALE_CAPACITY] in order to avoid overflow.
Signed-off-by: Morten Rasmussen <morten.rasmussen@arm.com>
Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Paul Turner <pjt@google.com>
Cc: Ben Segall <bsegall@google.com>
Cc: Ben Segall <bsegall@google.com>
Cc: Morten.Rasmussen@arm.com
Cc: Paul Turner <pjt@google.com>
Cc: dietmar.eggemann@arm.com
Cc: efault@gmx.de
Cc: kamalesh@linux.vnet.ibm.com
Cc: linaro-kernel@lists.linaro.org
Cc: nicolas.pitre@linaro.org
Cc: preeti@linux.vnet.ibm.com
Cc: riel@redhat.com
Link: http://lkml.kernel.org/r/1425455186-13451-1-git-send-email-vincent.guittot@linaro.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Add usage contribution tracking for group entities. Unlike
se->avg.load_avg_contrib, se->avg.utilization_avg_contrib for group
entities is the sum of se->avg.utilization_avg_contrib for all entities on the
group runqueue.
It is _not_ influenced in any way by the task group h_load. Hence it is
representing the actual cpu usage of the group, not its intended load
contribution which may differ significantly from the utilization on
lightly utilized systems.
Signed-off-by: Morten Rasmussen <morten.rasmussen@arm.com>
Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Paul Turner <pjt@google.com>
Cc: Ben Segall <bsegall@google.com>
Cc: Ben Segall <bsegall@google.com>
Cc: Morten.Rasmussen@arm.com
Cc: Paul Turner <pjt@google.com>
Cc: dietmar.eggemann@arm.com
Cc: efault@gmx.de
Cc: kamalesh@linux.vnet.ibm.com
Cc: linaro-kernel@lists.linaro.org
Cc: nicolas.pitre@linaro.org
Cc: preeti@linux.vnet.ibm.com
Cc: riel@redhat.com
Link: http://lkml.kernel.org/r/1425052454-25797-3-git-send-email-vincent.guittot@linaro.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Add new statistics which reflect the average time a task is running on the CPU
and the sum of these running time of the tasks on a runqueue. The latter is
named utilization_load_avg.
This patch is based on the usage metric that was proposed in the 1st
versions of the per-entity load tracking patchset by Paul Turner
<pjt@google.com> but that has be removed afterwards. This version differs from
the original one in the sense that it's not linked to task_group.
The rq's utilization_load_avg will be used to check if a rq is overloaded or
not instead of trying to compute how many tasks a group of CPUs can handle.
Rename runnable_avg_period into avg_period as it is now used with both
runnable_avg_sum and running_avg_sum.
Add some descriptions of the variables to explain their differences.
Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Morten Rasmussen <morten.rasmussen@arm.com>
Cc: Paul Turner <pjt@google.com>
Cc: Ben Segall <bsegall@google.com>
Cc: Ben Segall <bsegall@google.com>
Cc: Morten.Rasmussen@arm.com
Cc: Paul Turner <pjt@google.com>
Cc: dietmar.eggemann@arm.com
Cc: efault@gmx.de
Cc: kamalesh@linux.vnet.ibm.com
Cc: linaro-kernel@lists.linaro.org
Cc: nicolas.pitre@linaro.org
Cc: preeti@linux.vnet.ibm.com
Cc: riel@redhat.com
Link: http://lkml.kernel.org/r/1425052454-25797-2-git-send-email-vincent.guittot@linaro.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Dave Chinner reported the following on https://lkml.org/lkml/2015/3/1/226
Across the board the 4.0-rc1 numbers are much slower, and the degradation
is far worse when using the large memory footprint configs. Perf points
straight at the cause - this is from 4.0-rc1 on the "-o bhash=101073" config:
- 56.07% 56.07% [kernel] [k] default_send_IPI_mask_sequence_phys
- default_send_IPI_mask_sequence_phys
- 99.99% physflat_send_IPI_mask
- 99.37% native_send_call_func_ipi
smp_call_function_many
- native_flush_tlb_others
- 99.85% flush_tlb_page
ptep_clear_flush
try_to_unmap_one
rmap_walk
try_to_unmap
migrate_pages
migrate_misplaced_page
- handle_mm_fault
- 99.73% __do_page_fault
trace_do_page_fault
do_async_page_fault
+ async_page_fault
0.63% native_send_call_func_single_ipi
generic_exec_single
smp_call_function_single
This is showing excessive migration activity even though excessive
migrations are meant to get throttled. Normally, the scan rate is tuned
on a per-task basis depending on the locality of faults. However, if
migrations fail for any reason then the PTE scanner may scan faster if
the faults continue to be remote. This means there is higher system CPU
overhead and fault trapping at exactly the time we know that migrations
cannot happen. This patch tracks when migration failures occur and
slows the PTE scanner.
Signed-off-by: Mel Gorman <mgorman@suse.de>
Reported-by: Dave Chinner <david@fromorbit.com>
Tested-by: Dave Chinner <david@fromorbit.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Aneesh Kumar <aneesh.kumar@linux.vnet.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
The following point:
2. per-CPU pvclock time info is updated if the
underlying CPU changes.
Is not true anymore since "KVM: x86: update pvclock area conditionally,
on cpu migration".
Add task migration notification back.
Problem noticed by Andy Lutomirski.
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
CC: stable@kernel.org # 3.11+
When debugging the latencies on a 40 core box, where we hit 300 to
500 microsecond latencies, I found there was a huge contention on the
runqueue locks.
Investigating it further, running ftrace, I found that it was due to
the pulling of RT tasks.
The test that was run was the following:
cyclictest --numa -p95 -m -d0 -i100
This created a thread on each CPU, that would set its wakeup in iterations
of 100 microseconds. The -d0 means that all the threads had the same
interval (100us). Each thread sleeps for 100us and wakes up and measures
its latencies.
cyclictest is maintained at:
git://git.kernel.org/pub/scm/linux/kernel/git/clrkwllms/rt-tests.git
What happened was another RT task would be scheduled on one of the CPUs
that was running our test, when the other CPU tests went to sleep and
scheduled idle. This caused the "pull" operation to execute on all
these CPUs. Each one of these saw the RT task that was overloaded on
the CPU of the test that was still running, and each one tried
to grab that task in a thundering herd way.
To grab the task, each thread would do a double rq lock grab, grabbing
its own lock as well as the rq of the overloaded CPU. As the sched
domains on this box was rather flat for its size, I saw up to 12 CPUs
block on this lock at once. This caused a ripple affect with the
rq locks especially since the taking was done via a double rq lock, which
means that several of the CPUs had their own rq locks held while trying
to take this rq lock. As these locks were blocked, any wakeups or load
balanceing on these CPUs would also block on these locks, and the wait
time escalated.
I've tried various methods to lessen the load, but things like an
atomic counter to only let one CPU grab the task wont work, because
the task may have a limited affinity, and we may pick the wrong
CPU to take that lock and do the pull, to only find out that the
CPU we picked isn't in the task's affinity.
Instead of doing the PULL, I now have the CPUs that want the pull to
send over an IPI to the overloaded CPU, and let that CPU pick what
CPU to push the task to. No more need to grab the rq lock, and the
push/pull algorithm still works fine.
With this patch, the latency dropped to just 150us over a 20 hour run.
Without the patch, the huge latencies would trigger in seconds.
I've created a new sched feature called RT_PUSH_IPI, which is enabled
by default.
When RT_PUSH_IPI is not enabled, the old method of grabbing the rq locks
and having the pulling CPU do the work is implemented. When RT_PUSH_IPI
is enabled, the IPI is sent to the overloaded CPU to do a push.
To enabled or disable this at run time:
# mount -t debugfs nodev /sys/kernel/debug
# echo RT_PUSH_IPI > /sys/kernel/debug/sched_features
or
# echo NO_RT_PUSH_IPI > /sys/kernel/debug/sched_features
Update: This original patch would send an IPI to all CPUs in the RT overload
list. But that could theoretically cause the reverse issue. That is, there
could be lots of overloaded RT queues and one CPU lowers its priority. It would
then send an IPI to all the overloaded RT queues and they could then all try
to grab the rq lock of the CPU lowering its priority, and then we have the
same problem.
The latest design sends out only one IPI to the first overloaded CPU. It tries to
push any tasks that it can, and then looks for the next overloaded CPU that can
push to the source CPU. The IPIs stop when all overloaded CPUs that have pushable
tasks that have priorities greater than the source CPU are covered. In case the
source CPU lowers its priority again, a flag is set to tell the IPI traversal to
restart with the first RT overloaded CPU after the source CPU.
Parts-suggested-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Joern Engel <joern@purestorage.com>
Cc: Clark Williams <williams@redhat.com>
Cc: Mike Galbraith <umgwanakikbuti@gmail.com>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/20150318144946.2f3cc982@gandalf.local.home
Signed-off-by: Ingo Molnar <mingo@kernel.org>
When non-realtime tasks get priority-inheritance boosted to a realtime
scheduling class, RLIMIT_RTTIME starts to apply to them. However, the
counter used for checking this (the same one used for SCHED_RR
timeslices) was not getting reset. This meant that tasks running with a
non-realtime scheduling class which are repeatedly boosted to a realtime
one, but never block while they are running realtime, eventually hit the
timeout without ever running for a time over the limit. This patch
resets the realtime timeslice counter when un-PI-boosting from an RT to
a non-RT scheduling class.
I have some test code with two threads and a shared PTHREAD_PRIO_INHERIT
mutex which induces priority boosting and spins while boosted that gets
killed by a SIGXCPU on non-fixed kernels but doesn't with this patch
applied. It happens much faster with a CONFIG_PREEMPT_RT kernel, and
does happen eventually with PREEMPT_VOLUNTARY kernels.
Signed-off-by: Brian Silverman <brian@peloton-tech.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: austin@peloton-tech.com
Cc: <stable@vger.kernel.org>
Link: http://lkml.kernel.org/r/1424305436-6716-1-git-send-email-brian@peloton-tech.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Needed by the next patch. Also makes cpu_isolated_map present
when compiled without SMP and/or with CONFIG_NR_CPUS=1, like
the other cpu masks.
At some point we may want to clean things up so cpumasks do
not exist in UP kernels. Maybe something for the CONFIG_TINY
crowd.
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Clark Williams <williams@redhat.com>
Cc: Li Zefan <lizefan@huawei.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Luiz Capitulino <lcapitulino@redhat.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Mike Galbraith <umgwanakikbuti@gmail.com>
Cc: cgroups@vger.kernel.org
Signed-off-by: Rik van Riel <riel@redhat.com>
Acked-by: Zefan Li <lizefan@huawei.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
This commit informs RCU of an outgoing CPU just before that CPU invokes
arch_cpu_idle_dead() during its last pass through the idle loop (via a
new CPU_DYING_IDLE notifier value). This change means that RCU need not
deal with outgoing CPUs passing through the scheduler after informing
RCU that they are no longer online. Note that removing the CPU from
the rcu_node ->qsmaskinit bit masks is done at CPU_DYING_IDLE time,
and orphaning callbacks is still done at CPU_DEAD time, the reason being
that at CPU_DEAD time we have another CPU that can adopt them.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
This commit uses a per-CPU variable to make the CPU-offline code path
through the idle loop more precise, so that the outgoing CPU is
guaranteed to make it into the idle loop before it is powered off.
This commit is in preparation for putting the RCU offline-handling
code on this code path, which will eliminate the magic one-jiffy
wait that RCU uses as the maximum time for an outgoing CPU to get
all the way through the scheduler.
The magic one-jiffy wait for incoming CPUs remains a separate issue.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
This patch adds rq->clock update skip for SCHED_DEADLINE task yield,
to tell update_rq_clock() that we've just updated the clock, so that
we don't do a microscopic update in schedule() and double the
fastpath cost.
Signed-off-by: Wanpeng Li <wanpeng.li@linux.intel.com>
Cc: Juri Lelli <juri.lelli@arm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1425961200-3809-1-git-send-email-wanpeng.li@linux.intel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Current context tracking symbols are designed to express living state.
As such they are prefixed with "IN_": IN_USER, IN_KERNEL.
Now we are going to use these symbols to also express state transitions
such as context_tracking_enter(IN_USER) or context_tracking_exit(IN_USER).
But while the "IN_" prefix works well to express entering a context, it's
confusing to depict a context exit: context_tracking_exit(IN_USER)
could mean two things:
1) We are exiting the current context to enter user context.
2) We are exiting the user context
We want 2) but the reviewer may be confused and understand 1)
So lets disambiguate these symbols and rename them to CONTEXT_USER and
CONTEXT_KERNEL.
Acked-by: Rik van Riel <riel@redhat.com>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Will deacon <will.deacon@arm.com>
Cc: Marcelo Tosatti <mtosatti@redhat.com>
Cc: Christian Borntraeger <borntraeger@de.ibm.com>
Cc: Luiz Capitulino <lcapitulino@redhat.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Commit 3810631332 (PM / sleep: Re-implement suspend-to-idle handling)
overlooked the fact that entering some sufficiently deep idle states
by CPUs may cause their local timers to stop and in those cases it
is necessary to switch over to a broadcast timer prior to entering
the idle state. If the cpuidle driver in use does not provide
the new ->enter_freeze callback for any of the idle states, that
problem affects suspend-to-idle too, but it is not taken into account
after the changes made by commit 3810631332.
Fix that by changing the definition of cpuidle_enter_freeze() and
re-arranging of the code in cpuidle_idle_call(), so the former does
not call cpuidle_enter() any more and the fallback case is handled
by cpuidle_idle_call() directly.
Fixes: 3810631332 (PM / sleep: Re-implement suspend-to-idle handling)
Reported-and-tested-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Move the fallback code path in cpuidle_idle_call() to the end of the
function to avoid jumping to a label in an if () branch.
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Disabling interrupts at the end of cpuidle_enter_freeze() is not
useful, because its caller, cpuidle_idle_call(), re-enables them
right away after invoking it.
To avoid that unnecessary back and forth dance with interrupts,
make cpuidle_enter_freeze() enable interrupts after calling
enter_freeze_proper() and drop the local_irq_disable() at its
end, so that all of the code paths in it end up with interrupts
enabled. Then, cpuidle_idle_call() will not need to re-enable
interrupts after calling cpuidle_enter_freeze() any more, because
the latter will return with interrupts enabled, in analogy with
cpuidle_enter().
Reported-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Pull scheduler fixes from Ingo Molnar:
"Thiscontains misc fixes: preempt_schedule_common() and io_schedule()
recursion fixes, sched/dl fixes, a completion_done() revert, two
sched/rt fixes and a comment update patch"
* 'sched-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
sched/rt: Avoid obvious configuration fail
sched/autogroup: Fix failure to set cpu.rt_runtime_us
sched/dl: Do update_rq_clock() in yield_task_dl()
sched: Prevent recursion in io_schedule()
sched/completion: Serialize completion_done() with complete()
sched: Fix preempt_schedule_common() triggering tracing recursion
sched/dl: Prevent enqueue of a sleeping task in dl_task_timer()
sched: Make dl_task_time() use task_rq_lock()
sched: Clarify ordering between task_rq_lock() and move_queued_task()
If the CPU is running a realtime task that does not round-robin
with another realtime task of equal priority, there is no point
in keeping the scheduler tick going. After all, whenever the
scheduler tick runs, the kernel will just decide not to
reschedule.
Extend sched_can_stop_tick() to recognize these situations, and
inform the rest of the kernel that the scheduler tick can be
stopped.
Tested-by: Luiz Capitulino <lcapitulino@redhat.com>
Signed-off-by: Rik van Riel <riel@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: fweisbec@redhat.com
Cc: mtosatti@redhat.com
Link: http://lkml.kernel.org/r/20150216152349.6a8ed824@annuminas.surriel.com
[ Small cleanliness tweak. ]
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Commit 81907478c4 ("sched/fair: Avoid using uninitialized variable
in preferred_group_nid()") unconditionally initializes max_group with
NODE_MASK_NONE, this means that when !max_faults (max_group didn't get
set), we'll now continue the iteration with an empty mask.
Which in turn makes the actual body of the loop go away, so we'll just
iterate until completion; short circuit this by breaking out of the
loop as soon as this would happen.
Signed-off-by: Jan Beulich <jbeulich@suse.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: http://lkml.kernel.org/r/20150209113727.GS5029@twins.programming.kicks-ass.net
Signed-off-by: Ingo Molnar <mingo@kernel.org>
There is a subtle interaction between the logic introduced in commit
e63da03639 ("sched/numa: Allow task switch if load imbalance improves"),
the way the load balancer counts the load on each NUMA node, and the way
NUMA hinting faults are done.
Specifically, the load balancer only counts currently running tasks
in the load, while NUMA hinting faults may cause tasks to stop, if
the page is locked by another task.
This could cause all of the threads of a large single instance workload,
like SPECjbb2005, to migrate to the same NUMA node. This was possible
because occasionally they all fault on the same few pages, and only one
of the threads remains runnable. That thread can move to the process's
preferred NUMA node without making the imbalance worse, because nothing
else is running at that time.
The fix is to check the direction of the net moving of load, and to
refuse a NUMA move if it would cause the system to move past the point
of balance. In an unbalanced state, only moves that bring us closer
to the balance point are allowed.
Signed-off-by: Rik van Riel <riel@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: mgorman@suse.de
Link: http://lkml.kernel.org/r/20150203165648.0e9ac692@annuminas.surriel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Setting the root group's cpu.rt_runtime_us to 0 is a bad thing; it
would disallow the kernel creating RT tasks.
One can of course still set it to 1, which will (likely) still wreck
your kernel, but at least make it clear that setting it to 0 is not
good.
Collect both sanity checks into the one place while we're there.
Suggested-by: Zefan Li <lizefan@huawei.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: http://lkml.kernel.org/r/20150209112715.GO24151@twins.programming.kicks-ass.net
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Because task_group() uses a cache of autogroup_task_group(), whose
output depends on sched_class, switching classes can generate
problems.
In particular, when started as fair, the cache points to the
autogroup, so when switching to RT the tg_rt_schedulable() test fails
for every cpu.rt_{runtime,period}_us change because now the autogroup
has tasks and no runtime.
Furthermore, going back to the previous semantics of varying
task_group() with sched_class has the down-side that the sched_debug
output varies as well, even though the task really is in the
autogroup.
Therefore add an autogroup exception to tg_has_rt_tasks() -- such that
both (all) task_group() usages in sched/core now have one. And remove
all the remnants of the variable task_group() output.
Reported-by: Zefan Li <lizefan@huawei.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <umgwanakikbuti@gmail.com>
Cc: Stefan Bader <stefan.bader@canonical.com>
Fixes: 8323f26ce3 ("sched: Fix race in task_group()")
Link: http://lkml.kernel.org/r/20150209112237.GR5029@twins.programming.kicks-ass.net
Signed-off-by: Ingo Molnar <mingo@kernel.org>
io_schedule() calls blk_flush_plug() which, depending on the
contents of current->plug, can initiate arbitrary blk-io requests.
Note that this contrasts with blk_schedule_flush_plug() which requires
all non-trivial work to be handed off to a separate thread.
This makes it possible for io_schedule() to recurse, and initiating
block requests could possibly call mempool_alloc() which, in times of
memory pressure, uses io_schedule().
Apart from any stack usage issues, io_schedule() will not behave
correctly when called recursively as delayacct_blkio_start() does
not allow for repeated calls.
So:
- use ->in_iowait to detect recursion. Set it earlier, and restore
it to the old value.
- move the call to "raw_rq" after the call to blk_flush_plug().
As this is some sort of per-cpu thing, we want some chance that
we are on the right CPU
- When io_schedule() is called recurively, use blk_schedule_flush_plug()
which cannot further recurse.
- as this makes io_schedule() a lot more complex and as io_schedule()
must match io_schedule_timeout(), but all the changes in io_schedule_timeout()
and make io_schedule a simple wrapper for that.
Signed-off-by: NeilBrown <neilb@suse.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
[ Moved the now rudimentary io_schedule() into sched.h. ]
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Tony Battersby <tonyb@cybernetics.com>
Link: http://lkml.kernel.org/r/20150213162600.059fffb2@notabene.brown
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Commit de30ec4730 "Remove unnecessary ->wait.lock serialization when
reading completion state" was not correct, without lock/unlock the code
like stop_machine_from_inactive_cpu()
while (!completion_done())
cpu_relax();
can return before complete() finishes its spin_unlock() which writes to
this memory. And spin_unlock_wait().
While at it, change try_wait_for_completion() to use READ_ONCE().
Reported-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Reported-by: Davidlohr Bueso <dave@stgolabs.net>
Tested-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
[ Added a comment with the barrier. ]
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Nicholas Mc Guire <der.herr@hofr.at>
Cc: raghavendra.kt@linux.vnet.ibm.com
Cc: waiman.long@hp.com
Fixes: de30ec4730 ("sched/completion: Remove unnecessary ->wait.lock serialization when reading completion state")
Link: http://lkml.kernel.org/r/20150212195913.GA30430@redhat.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Since the function graph tracer needs to disable preemption, it might
call preempt_schedule() after reenabling it if something triggered the
need for rescheduling in between.
Therefore we can't trace preempt_schedule() itself because we would
face a function tracing recursion otherwise as the tracer is always
called before PREEMPT_ACTIVE gets set to prevent that recursion. This is
why preempt_schedule() is tagged as "notrace".
But the same issue applies to every function called by preempt_schedule()
before PREEMPT_ACTIVE is actually set. And preempt_schedule_common() is
one such example. Unfortunately we forgot to tag it as notrace as well
and as a result we are encountering tracing recursion since it got
introduced by:
a18b5d0181 ("sched: Fix missing preemption opportunity")
Let's fix that by applying the appropriate function tag to
preempt_schedule_common().
Reported-by: Huang Ying <ying.huang@intel.com>
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Steven Rostedt <rostedt@goodmis.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: http://lkml.kernel.org/r/1424110807-15057-1-git-send-email-fweisbec@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
A deadline task may be throttled and dequeued at the same time.
This happens, when it becomes throttled in schedule(), which
is called to go to sleep:
current->state = TASK_INTERRUPTIBLE;
schedule()
deactivate_task()
dequeue_task_dl()
update_curr_dl()
start_dl_timer()
__dequeue_task_dl()
prev->on_rq = 0;
Later the timer fires, but the task is still dequeued:
dl_task_timer()
enqueue_task_dl() /* queues on dl_rq; on_rq remains 0 */
Someone wakes it up:
try_to_wake_up()
enqueue_dl_entity()
BUG_ON(on_dl_rq())
Patch fixes this problem, it prevents queueing !on_rq tasks
on dl_rq.
Reported-by: Fengguang Wu <fengguang.wu@intel.com>
Signed-off-by: Kirill Tkhai <ktkhai@parallels.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
[ Wrote comment. ]
Cc: Juri Lelli <juri.lelli@arm.com>
Fixes: 1019a359d3 ("sched/deadline: Fix stale yield state")
Link: http://lkml.kernel.org/r/1374601424090314@web4j.yandex.ru
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Kirill reported that a dl task can be throttled and dequeued at the
same time. This happens, when it becomes throttled in schedule(),
which is called to go to sleep:
current->state = TASK_INTERRUPTIBLE;
schedule()
deactivate_task()
dequeue_task_dl()
update_curr_dl()
start_dl_timer()
__dequeue_task_dl()
prev->on_rq = 0;
This invalidates the assumption from commit 0f397f2c90 ("sched/dl:
Fix race in dl_task_timer()"):
"The only reason we don't strictly need ->pi_lock now is because
we're guaranteed to have p->state == TASK_RUNNING here and are
thus free of ttwu races".
And therefore we have to use the full task_rq_lock() here.
This further amends the fact that we forgot to update the rq lock loop
for TASK_ON_RQ_MIGRATE, from commit cca26e8009 ("sched: Teach
scheduler to understand TASK_ON_RQ_MIGRATING state").
Reported-by: Kirill Tkhai <ktkhai@parallels.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Juri Lelli <juri.lelli@arm.com>
Link: http://lkml.kernel.org/r/20150217123139.GN5029@twins.programming.kicks-ass.net
Signed-off-by: Ingo Molnar <mingo@kernel.org>
There was a wee bit of confusion around the exact ordering here;
clarify things.
Reported-by: Kirill Tkhai <ktkhai@parallels.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Link: http://lkml.kernel.org/r/20150217121258.GM5029@twins.programming.kicks-ass.net
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Till now suspend-to-idle has not been able to save much more energy
than runtime PM because of timer interrupts that periodically bring
CPUs out of idle while they are waiting for a wakeup interrupt. Of
course, the timer interrupts are not wakeup ones, so the handling of
them can be deferred until a real wakeup interrupt happens, but at
the same time we don't want to mass-expire timers at that point.
The solution is to suspend the entire timekeeping when the last CPU
is entering an idle state and resume it when the first CPU goes out
of idle. That has to be done with care, though, so as to avoid
accessing suspended clocksources etc. end we need extra support
from idle drivers for that.
This series of commits adds support for quiescing timers during
suspend-to-idle and adds the requisite callbacks to intel_idle
and the ACPI cpuidle driver.
/
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v2.0.22 (GNU/Linux)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=55Jb
-----END PGP SIGNATURE-----
Merge tag 'suspend-to-idle-3.20-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm
Pull suspend-to-idle updates from Rafael Wysocki:
"Suspend-to-idle timer quiescing support for v3.20-rc1
Until now suspend-to-idle has not been able to save much more energy
than runtime PM because of timer interrupts that periodically bring
CPUs out of idle while they are waiting for a wakeup interrupt. Of
course, the timer interrupts are not wakeup ones, so the handling of
them can be deferred until a real wakeup interrupt happens, but at the
same time we don't want to mass-expire timers at that point.
The solution is to suspend the entire timekeeping when the last CPU is
entering an idle state and resume it when the first CPU goes out of
idle. That has to be done with care, though, so as to avoid accessing
suspended clocksources etc. end we need extra support from idle
drivers for that.
This series of commits adds support for quiescing timers during
suspend-to-idle and adds the requisite callbacks to intel_idle and the
ACPI cpuidle driver"
* tag 'suspend-to-idle-3.20-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm:
ACPI / idle: Implement ->enter_freeze callback routine
intel_idle: Add ->enter_freeze callbacks
PM / sleep: Make it possible to quiesce timers during suspend-to-idle
timekeeping: Make it safe to use the fast timekeeper while suspended
timekeeping: Pass readout base to update_fast_timekeeper()
PM / sleep: Re-implement suspend-to-idle handling
printk and friends can now format bitmaps using '%*pb[l]'. cpumask
and nodemask also provide cpumask_pr_args() and nodemask_pr_args()
respectively which can be used to generate the two printf arguments
necessary to format the specified cpu/nodemask.
Signed-off-by: Tejun Heo <tj@kernel.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
In preparation for adding support for quiescing timers in the final
stage of suspend-to-idle transitions, rework the freeze_enter()
function making the system wait on a wakeup event, the freeze_wake()
function terminating the suspend-to-idle loop and the mechanism by
which deep idle states are entered during suspend-to-idle.
First of all, introduce a simple state machine for suspend-to-idle
and make the code in question use it.
Second, prevent freeze_enter() from losing wakeup events due to race
conditions and ensure that the number of online CPUs won't change
while it is being executed. In addition to that, make it force
all of the CPUs re-enter the idle loop in case they are in idle
states already (so they can enter deeper idle states if possible).
Next, drop cpuidle_use_deepest_state() and replace use_deepest_state
checks in cpuidle_select() and cpuidle_reflect() with a single
suspend-to-idle state check in cpuidle_idle_call().
Finally, introduce cpuidle_enter_freeze() that will simply find the
deepest idle state available to the given CPU and enter it using
cpuidle_enter().
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
When the hypervisor pauses a virtualised kernel the kernel will observe a
jump in timebase, this can cause spurious messages from the softlockup
detector.
Whilst these messages are harmless, they are accompanied with a stack
trace which causes undue concern and more problematically the stack trace
in the guest has nothing to do with the observed problem and can only be
misleading.
Futhermore, on POWER8 this is completely avoidable with the introduction
of the Virtual Time Base (VTB) register.
This patch (of 2):
This permits the use of arch specific clocks for which virtualised kernels
can use their notion of 'running' time, not the elpased wall time which
will include host execution time.
Signed-off-by: Cyril Bur <cyrilbur@gmail.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Andrew Jones <drjones@redhat.com>
Acked-by: Don Zickus <dzickus@redhat.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Ulrich Obergfell <uobergfe@redhat.com>
Cc: chai wen <chaiw.fnst@cn.fujitsu.com>
Cc: Fabian Frederick <fabf@skynet.be>
Cc: Aaron Tomlin <atomlin@redhat.com>
Cc: Ben Zhang <benzh@chromium.org>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: John Stultz <john.stultz@linaro.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Pull s390 updates from Martin Schwidefsky:
- The remaining patches for the z13 machine support: kernel build
option for z13, the cache synonym avoidance, SMT support,
compare-and-delay for spinloops and the CES5S crypto adapater.
- The ftrace support for function tracing with the gcc hotpatch option.
This touches common code Makefiles, Steven is ok with the changes.
- The hypfs file system gets an extension to access diagnose 0x0c data
in user space for performance analysis for Linux running under z/VM.
- The iucv hvc console gets wildcard spport for the user id filtering.
- The cacheinfo code is converted to use the generic infrastructure.
- Cleanup and bug fixes.
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/s390/linux: (42 commits)
s390/process: free vx save area when releasing tasks
s390/hypfs: Eliminate hypfs interval
s390/hypfs: Add diagnose 0c support
s390/cacheinfo: don't use smp_processor_id() in preemptible context
s390/zcrypt: fixed domain scanning problem (again)
s390/smp: increase maximum value of NR_CPUS to 512
s390/jump label: use different nop instruction
s390/jump label: add sanity checks
s390/mm: correct missing space when reporting user process faults
s390/dasd: cleanup profiling
s390/dasd: add locking for global_profile access
s390/ftrace: hotpatch support for function tracing
ftrace: let notrace function attribute disable hotpatching if necessary
ftrace: allow architectures to specify ftrace compile options
s390: reintroduce diag 44 calls for cpu_relax()
s390/zcrypt: Add support for new crypto express (CEX5S) adapter.
s390/zcrypt: Number of supported ap domains is not retrievable.
s390/spinlock: add compare-and-delay to lock wait loops
s390/tape: remove redundant if statement
s390/hvc_iucv: add simple wildcard matches to the iucv allow filter
...
Pull scheduler updates from Ingo Molnar:
"The main scheduler changes in this cycle were:
- various sched/deadline fixes and enhancements
- rescheduling latency fixes/cleanups
- rework the rq->clock code to be more consistent and more robust.
- minor micro-optimizations
- ->avg.decay_count fixes
- add a stack overflow check to might_sleep()
- idle-poll handler fix, possibly resulting in power savings
- misc smaller updates and fixes"
* 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
sched/Documentation: Remove unneeded word
sched/wait: Introduce wait_on_bit_timeout()
sched: Pull resched loop to __schedule() callers
sched/deadline: Remove cpu_active_mask from cpudl_find()
sched: Fix hrtick_start() on UP
sched/deadline: Avoid pointless __setscheduler()
sched/deadline: Fix stale yield state
sched/deadline: Fix hrtick for a non-leftmost task
sched/deadline: Modify cpudl::free_cpus to reflect rd->online
sched/idle: Add missing checks to the exit condition of cpu_idle_poll()
sched: Fix missing preemption opportunity
sched/rt: Reduce rq lock contention by eliminating locking of non-feasible target
sched/debug: Print rq->clock_task
sched/core: Rework rq->clock update skips
sched/core: Validate rq_clock*() serialization
sched/core: Remove check of p->sched_class
sched/fair: Fix sched_entity::avg::decay_count initialization
sched/debug: Fix potential call to __ffs(0) in sched_show_task()
sched/debug: Check for stack overflow in ___might_sleep()
sched/fair: Fix the dealing with decay_count in __synchronize_entity_decay()
Pull perf updates from Ingo Molnar:
"Kernel side changes:
- AMD range breakpoints support:
Extend breakpoint tools and core to support address range through
perf event with initial backend support for AMD extended
breakpoints.
The syntax is:
perf record -e mem:addr/len:type
For example set write breakpoint from 0x1000 to 0x1200 (0x1000 + 512)
perf record -e mem:0x1000/512:w
- event throttling/rotating fixes
- various event group handling fixes, cleanups and general paranoia
code to be more robust against bugs in the future.
- kernel stack overhead fixes
User-visible tooling side changes:
- Show precise number of samples in at the end of a 'record' session,
if processing build ids, since we will then traverse the whole
perf.data file and see all the PERF_RECORD_SAMPLE records,
otherwise stop showing the previous off-base heuristicly counted
number of "samples" (Namhyung Kim).
- Support to read compressed module from build-id cache (Namhyung
Kim)
- Enable sampling loads and stores simultaneously in 'perf mem'
(Stephane Eranian)
- 'perf diff' output improvements (Namhyung Kim)
- Fix error reporting for evsel pgfault constructor (Arnaldo Carvalho
de Melo)
Tooling side infrastructure changes:
- Cache eh/debug frame offset for dwarf unwind (Namhyung Kim)
- Support parsing parameterized events (Cody P Schafer)
- Add support for IP address formats in libtraceevent (David Ahern)
Plus other misc fixes"
* 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (48 commits)
perf: Decouple unthrottling and rotating
perf: Drop module reference on event init failure
perf: Use POLLIN instead of POLL_IN for perf poll data in flag
perf: Fix put_event() ctx lock
perf: Fix move_group() order
perf: Fix event->ctx locking
perf: Add a bit of paranoia
perf symbols: Convert lseek + read to pread
perf tools: Use perf_data_file__fd() consistently
perf symbols: Support to read compressed module from build-id cache
perf evsel: Set attr.task bit for a tracking event
perf header: Set header version correctly
perf record: Show precise number of samples
perf tools: Do not use __perf_session__process_events() directly
perf callchain: Cache eh/debug frame offset for dwarf unwind
perf tools: Provide stub for missing pthread_attr_setaffinity_np
perf evsel: Don't rely on malloc working for sz 0
tools lib traceevent: Add support for IP address formats
perf ui/tui: Show fatal error message only if exists
perf tests: Fix typo in sample-parsing.c
...
Pull core locking updates from Ingo Molnar:
"The main changes are:
- mutex, completions and rtmutex micro-optimizations
- lock debugging fix
- various cleanups in the MCS and the futex code"
* 'locking-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
locking/rtmutex: Optimize setting task running after being blocked
locking/rwsem: Use task->state helpers
sched/completion: Add lock-free checking of the blocking case
sched/completion: Remove unnecessary ->wait.lock serialization when reading completion state
locking/mutex: Explicitly mark task as running after wakeup
futex: Fix argument handling in futex_lock_pi() calls
doc: Fix misnamed FUTEX_CMP_REQUEUE_PI op constants
locking/Documentation: Update code path
softirq/preempt: Add missing current->preempt_disable_ip update
locking/osq: No need for load/acquire when acquire-polling
locking/mcs: Better differentiate between MCS variants
locking/mutex: Introduce ww_mutex_set_context_slowpath()
locking/mutex: Move MCS related comments to proper location
locking/mutex: Checking the stamp is WW only
Pull scheduler fixes from Ingo Molnar:
"Misc fixes"
* 'sched-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
sched/deadline: Fix deadline parameter modification handling
sched/wait: Remove might_sleep() from wait_event_cmd()
sched: Fix crash if cpuset_cpumask_can_shrink() is passed an empty cpumask
sched/fair: Avoid using uninitialized variable in preferred_group_nid()
The "thread would block" case can be checked without grabbing ->wait.lock.
[ If the check does not return early then grab the lock and recheck.
A memory barrier is not needed as complete() and complete_all() imply
a barrier.
The ACCESS_ONCE() is needed for calls in a loop that, if inlined, could
optimize out the re-fetching of x->done. ]
Signed-off-by: Nicholas Mc Guire <der.herr@hofr.at>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: http://lkml.kernel.org/r/1422013307-13200-1-git-send-email-der.herr@hofr.at
Signed-off-by: Ingo Molnar <mingo@kernel.org>
__schedule() disables preemption during its job and re-enables it
afterward without doing a preemption check to avoid recursion.
But if an event happens after the context switch which requires
rescheduling, we need to check again if a task of a higher priority
needs the CPU. A preempt irq can raise such a situation. To handle that,
__schedule() loops on need_resched().
But preempt_schedule_*() functions, which call __schedule(), also loop
on need_resched() to handle missed preempt irqs. Hence we end up with
the same loop happening twice.
Lets simplify that by attributing the need_resched() loop responsibility
to all __schedule() callers.
There is a risk that the outer loop now handles reschedules that used
to be handled by the inner loop with the added overhead of caller details
(inc/dec of PREEMPT_ACTIVE, irq save/restore) but assuming those inner
rescheduling loop weren't too frequent, this shouldn't matter. Especially
since the whole preemption path is now losing one loop in any case.
Suggested-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Link: http://lkml.kernel.org/r/1422404652-29067-2-git-send-email-fweisbec@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
cpu_active_mask is rarely changed (only on hotplug), so remove this
operation to gain a little performance.
If there is a change in cpu_active_mask, rq_online_dl() and
rq_offline_dl() should take care of it normally, so cpudl::free_cpus
carries enough information for us.
For the rare case when a task is put onto a dying cpu (which
rq_offline_dl() can't handle in a timely fashion), it will be
handled through _cpu_down()->...->multi_cpu_stop()->migration_call()
->migrate_tasks(), preventing the task from hanging on the
dead cpu.
Cc: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Xunlei Pang <pang.xunlei@linaro.org>
[peterz: changelog]
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1421642980-10045-2-git-send-email-pang.xunlei@linaro.org
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
The commit 177ef2a631 ("sched/deadline: Fix a precision problem in
the microseconds range") forgot to change the UP version of
hrtick_start(), do so now.
Signed-off-by: Wanpeng Li <wanpeng.li@linux.intel.com>
Fixes: 177ef2a631 ("sched/deadline: Fix a precision problem in the microseconds range")
[ Fixed the changelog. ]
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Juri Lelli <juri.lelli@arm.com>
Cc: Kirill Tkhai <ktkhai@parallels.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: http://lkml.kernel.org/r/1416962647-76792-7-git-send-email-wanpeng.li@linux.intel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
There is no need to dequeue/enqueue and push/pull if there are
no scheduling parameters changed for the DL class.
Both fair and RT classes already check if parameters changed for
them to avoid unnecessary overhead. This patch add the parameters
changed test for the DL class in order to reduce overhead.
Signed-off-by: Wanpeng Li <wanpeng.li@linux.intel.com>
[ Fixed up the changelog. ]
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Juri Lelli <juri.lelli@arm.com>
Cc: Kirill Tkhai <ktkhai@parallels.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: http://lkml.kernel.org/r/1416962647-76792-5-git-send-email-wanpeng.li@linux.intel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
When we fail to start the deadline timer in update_curr_dl(), we
forget to clear ->dl_yielded, resulting in wrecked time keeping.
Since the natural place to clear both ->dl_yielded and ->dl_throttled
is in replenish_dl_entity(); both are after all waiting for that event;
make it so.
Luckily since 67dfa1b756 ("sched/deadline: Implement
cancel_dl_timer() to use in switched_from_dl()") the
task_on_rq_queued() condition in dl_task_timer() must be true, and can
therefore call enqueue_task_dl() unconditionally.
Reported-by: Wanpeng Li <wanpeng.li@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Kirill Tkhai <ktkhai@parallels.com>
Cc: Juri Lelli <juri.lelli@arm.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: http://lkml.kernel.org/r/1416962647-76792-4-git-send-email-wanpeng.li@linux.intel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
After update_curr_dl() the current task might not be the leftmost task
anymore. In that case do not start a new hrtick for it.
In this case NEED_RESCHED will be set and the next schedule will start
the hrtick for the new task if and when appropriate.
Signed-off-by: Wanpeng Li <wanpeng.li@linux.intel.com>
Acked-by: Juri Lelli <juri.lelli@arm.com>
[ Rewrote the changelog and comment. ]
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Kirill Tkhai <ktkhai@parallels.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: http://lkml.kernel.org/r/1416962647-76792-2-git-send-email-wanpeng.li@linux.intel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Commit 67dfa1b756 ("sched/deadline: Implement cancel_dl_timer() to
use in switched_from_dl()") removed the hrtimer_try_cancel() function
call out from init_dl_task_timer(), which gets called from
__setparam_dl().
The result is that we can now re-init the timer while its active --
this is bad and corrupts timer state.
Furthermore; changing the parameters of an active deadline task is
tricky in that you want to maintain guarantees, while immediately
effective change would allow one to circumvent the CBS guarantees --
this too is bad, as one (bad) task should not be able to affect the
others.
Rework things to avoid both problems. We only need to initialize the
timer once, so move that to __sched_fork() for new tasks.
Then make sure __setparam_dl() doesn't affect the current running
state but only updates the parameters used to calculate the next
scheduling period -- this guarantees the CBS functions as expected
(albeit slightly pessimistic).
This however means we need to make sure __dl_clear_params() needs to
reset the active state otherwise new (and tasks flipping between
classes) will not properly (re)compute their first instance.
Todo: close class flipping CBS hole.
Todo: implement delayed BW release.
Reported-by: Luca Abeni <luca.abeni@unitn.it>
Acked-by: Juri Lelli <juri.lelli@arm.com>
Tested-by: Luca Abeni <luca.abeni@unitn.it>
Fixes: 67dfa1b756 ("sched/deadline: Implement cancel_dl_timer() to use in switched_from_dl()")
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: <stable@vger.kernel.org>
Cc: Kirill Tkhai <tkhai@yandex.ru>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: http://lkml.kernel.org/r/20150128140803.GF23038@twins.programming.kicks-ass.net
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Commit 8eb23b9f35 ("sched: Debug nested sleeps") added code to report
on nested sleep conditions, which we generally want to avoid because the
inner sleeping operation can re-set the thread state to TASK_RUNNING,
but that will then cause the outer sleep loop not actually sleep when it
calls schedule.
However, that's actually valid traditional behavior, with the inner
sleep being some fairly rare case (like taking a sleeping lock that
normally doesn't actually need to sleep).
And the debug code would actually change the state of the task to
TASK_RUNNING internally, which makes that kind of traditional and
working code not work at all, because now the nested sleep doesn't just
sometimes cause the outer one to not block, but will cause it to happen
every time.
In particular, it will cause the cardbus kernel daemon (pccardd) to
basically busy-loop doing scheduling, converting a laptop into a heater,
as reported by Bruno Prémont. But there may be other legacy uses of
that nested sleep model in other drivers that are also likely to never
get converted to the new model.
This fixes both cases:
- don't set TASK_RUNNING when the nested condition happens (note: even
if WARN_ONCE() only _warns_ once, the return value isn't whether the
warning happened, but whether the condition for the warning was true.
So despite the warning only happening once, the "if (WARN_ON(..))"
would trigger for every nested sleep.
- in the cases where we knowingly disable the warning by using
"sched_annotate_sleep()", don't change the task state (that is used
for all core scheduling decisions), instead use '->task_state_change'
that is used for the debugging decision itself.
(Credit for the second part of the fix goes to Oleg Nesterov: "Can't we
avoid this subtle change in behaviour DEBUG_ATOMIC_SLEEP adds?" with the
suggested change to use 'task_state_change' as part of the test)
Reported-and-bisected-by: Bruno Prémont <bonbons@linux-vserver.org>
Tested-by: Rafael J Wysocki <rjw@rjwysocki.net>
Acked-by: Oleg Nesterov <oleg@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>,
Cc: Ilya Dryomov <ilya.dryomov@inktank.com>,
Cc: Mike Galbraith <umgwanakikbuti@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Peter Hurley <peter@hurleysoftware.com>,
Cc: Davidlohr Bueso <dave@stgolabs.net>,
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Currently, cpudl::free_cpus contains all CPUs during init, see
cpudl_init(). When calling cpudl_find(), we have to add rd->span
to avoid selecting the cpu outside the current root domain, because
cpus_allowed cannot be depended on when performing clustered
scheduling using the cpuset, see find_later_rq().
This patch adds cpudl_set_freecpu() and cpudl_clear_freecpu() for
changing cpudl::free_cpus when doing rq_online_dl()/rq_offline_dl(),
so we can avoid the rd->span operation when calling cpudl_find()
in find_later_rq().
Signed-off-by: Xunlei Pang <pang.xunlei@linaro.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Juri Lelli <juri.lelli@gmail.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: http://lkml.kernel.org/r/1421642980-10045-1-git-send-email-pang.xunlei@linaro.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
cpu_idle_poll() is entered into when either the cpu_idle_force_poll is set or
tick_check_broadcast_expired() returns true. The exit condition from
cpu_idle_poll() is tif_need_resched().
However this does not take into account scenarios where cpu_idle_force_poll
changes or tick_check_broadcast_expired() returns false, without setting
the resched flag. So a cpu will be caught in cpu_idle_poll() needlessly,
thereby wasting power. Add an explicit check on cpu_idle_force_poll and
tick_check_broadcast_expired() to the exit condition of cpu_idle_poll()
to avoid this.
Signed-off-by: Preeti U Murthy <preeti@linux.vnet.ibm.com>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: linuxppc-dev@lists.ozlabs.org
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: http://lkml.kernel.org/r/20150121105655.15279.59626.stgit@preeti.in.ibm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
If an interrupt fires in cond_resched(), between the call to __schedule()
and the PREEMPT_ACTIVE count decrementation, and that interrupt sets
TIF_NEED_RESCHED, the call to preempt_schedule_irq() will be ignored
due to the PREEMPT_ACTIVE count. This kind of scenario, with irq preemption
being delayed because it's interrupting a preempt-disabled area, is
usually fixed up after preemption is re-enabled back with an explicit
call to preempt_schedule().
This is what preempt_enable() does but a raw preempt count decrement as
performed by __preempt_count_sub(PREEMPT_ACTIVE) doesn't handle delayed
preemption check. Therefore when such a race happens, the rescheduling
is going to be delayed until the next scheduler or preemption entrypoint.
This can be a problem for scheduler latency sensitive workloads.
Lets fix that by consolidating cond_resched() with preempt_schedule()
internals.
Reported-by: Linus Torvalds <torvalds@linux-foundation.org>
Reported-by: Ingo Molnar <mingo@kernel.org>
Original-patch-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1421946484-9298-1-git-send-email-fweisbec@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
This patch adds checks that prevens futile attempts to move rt tasks
to a CPU with active tasks of equal or higher priority.
This reduces run queue lock contention and improves the performance of
a well known OLTP benchmark by 0.7%.
Signed-off-by: Tim Chen <tim.c.chen@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Shawn Bohrer <sbohrer@rgmadvisors.com>
Cc: Suruchi Kadu <suruchi.a.kadu@intel.com>
Cc: Doug Nelson<doug.nelson@intel.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: http://lkml.kernel.org/r/1421430374.2399.27.camel@schen9-desk2.jf.intel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
If the kernel is compiled with function tracer support the -pg compile option
is passed to gcc to generate extra code into the prologue of each function.
This patch replaces the "open-coded" -pg compile flag with a CC_FLAGS_FTRACE
makefile variable which architectures can override if a different option
should be used for code generation.
Acked-by: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
At least some gcc versions - validly afaict - warn about potentially
using max_group uninitialized: There's no way the compiler can prove
that the body of the conditional where it and max_faults get set/
updated gets executed; in fact, without knowing all the details of
other scheduler code, I can't prove this either.
Generally the necessary change would appear to be to clear max_group
prior to entering the inner loop, and break out of the outer loop when
it ends up being all clear after the inner one. This, however, seems
inefficient, and afaict the same effect can be achieved by exiting the
outer loop when max_faults is still zero after the inner loop.
[ mingo: changed the solution to zero initialization: uninitialized_var()
needs to die, as it's an actively dangerous construct: if in the future
a known-proven-good piece of code is changed to have a true, buggy
uninitialized variable, the compiler warning is then supressed...
The better long term solution is to clean up the code flow, so that
even simple minded compilers (and humans!) are able to read it without
getting a headache. ]
Signed-off-by: Jan Beulich <jbeulich@suse.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Rik van Riel <riel@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: http://lkml.kernel.org/r/54C2139202000078000588F7@mail.emea.novell.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Both Linus (most recent) and Steve (a while ago) reported that perf
related callbacks have massive stack bloat.
The problem is that software events need a pt_regs in order to
properly report the event location and unwind stack. And because we
could not assume one was present we allocated one on stack and filled
it with minimal bits required for operation.
Now, pt_regs is quite large, so this is undesirable. Furthermore it
turns out that most sites actually have a pt_regs pointer available,
making this even more onerous, as the stack space is pointless waste.
This patch addresses the problem by observing that software events
have well defined nesting semantics, therefore we can use static
per-cpu storage instead of on-stack.
Linus made the further observation that all but the scheduler callers
of perf_sw_event() have a pt_regs available, so we change the regular
perf_sw_event() to require a valid pt_regs (where it used to be
optional) and add perf_sw_event_sched() for the scheduler.
We have a scheduler specific call instead of a more generic _noregs()
like construct because we can assume non-recursion from the scheduler
and thereby simplify the code further (_noregs would have to put the
recursion context call inline in order to assertain which __perf_regs
element to use).
One last note on the implementation of perf_trace_buf_prepare(); we
allow .regs = NULL for those cases where we already have a pt_regs
pointer available and do not need another.
Reported-by: Linus Torvalds <torvalds@linux-foundation.org>
Reported-by: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Javi Merino <javi.merino@arm.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Petr Mladek <pmladek@suse.cz>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Tom Zanussi <tom.zanussi@linux.intel.com>
Cc: Vaibhav Nagarnaik <vnagarnaik@google.com>
Link: http://lkml.kernel.org/r/20141216115041.GW3337@twins.programming.kicks-ass.net
Signed-off-by: Ingo Molnar <mingo@kernel.org>
The original purpose of rq::skip_clock_update was to avoid 'costly' clock
updates for back to back wakeup-preempt pairs. The big problem with it
has always been that the rq variable is unaware of the context and
causes indiscrimiate clock skips.
Rework the entire thing and create a sense of context by only allowing
schedule() to skip clock updates. (XXX can we measure the cost of the
added store?)
By ensuring only schedule can ever skip an update, we guarantee we're
never more than 1 tick behind on the update.
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: umgwanakikbuti@gmail.com
Link: http://lkml.kernel.org/r/20150105103554.432381549@infradead.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
rq->clock{,_task} are serialized by rq->lock, verify this.
One immediate fail is the usage in scale_rt_capability, so 'annotate'
that for now, there's more 'funny' there. Maybe change rq->lock into a
raw_seqlock_t?
(Only 32-bit is affected)
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20150105103554.361872747@infradead.org
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: umgwanakikbuti@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Search all usage of p->sched_class in sched/core.c, no one check it
before use, so it seems that every task must belong to one sched_class.
Signed-off-by: Yao Dongdong <yaodongdong@huawei.com>
[ Moved the early class assignment to make it boot. ]
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: http://lkml.kernel.org/r/1419835303-28958-1-git-send-email-yaodongdong@huawei.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Child has the same decay_count as parent. If it's not zero,
we add it to parent's cfs_rq->removed_load:
wake_up_new_task()->set_task_cpu()->migrate_task_rq_fair().
Child's load is a just garbade after copying of parent,
it hasn't been on cfs_rq yet, and it must not be added to
cfs_rq::removed_load in migrate_task_rq_fair().
The patch moves sched_entity::avg::decay_count intialization
in sched_fork(). So, migrate_task_rq_fair() does not change
removed_load.
Signed-off-by: Kirill Tkhai <ktkhai@parallels.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Ben Segall <bsegall@google.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: http://lkml.kernel.org/r/1418644618.6074.13.camel@tkhai
Signed-off-by: Ingo Molnar <mingo@kernel.org>
"struct task_struct"->state is "volatile long" and __ffs() warns that
"Undefined if no bit exists, so code should check against 0 first."
Therefore, at expression
state = p->state ? __ffs(p->state) + 1 : 0;
in sched_show_task(), CPU might see "p->state" before "?" as "non-zero"
but "p->state" after "?" as "zero", which could result in
"state >= sizeof(stat_nam)" being true and bogus '?' is printed.
This patch changes "state" from "unsigned int" to "unsigned long" and
save "p->state" before calling __ffs(), in order to avoid potential call
to __ffs(0).
Signed-off-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: http://lkml.kernel.org/r/201412052131.GCE35924.FVHFOtLOJOMQFS@I-love.SAKURA.ne.jp
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Sometimes a "BUG: sleeping function called from invalid context"
message is not indicative of locking problems, but is the result
of a stack overflow corrupting the thread info.
Witness http://oss.sgi.com/archives/xfs/2014-02/msg00325.html
for example, which took a few go-rounds to sort out.
If we're printing the warning, things are wonky already, and
it'd be informative to check for the stack end corruption at this
point, too.
Signed-off-by: Eric Sandeen <sandeen@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: http://lkml.kernel.org/r/5490B158.4060005@redhat.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
In __synchronize_entity_decay(), if "decays" happens to be zero,
se->avg.decay_count will not be zeroed, holding the positive value
assigned when dequeued last time.
This is problematic in the following case:
If this runnable task is CFS-balanced to other CPUs soon afterwards,
migrate_task_rq_fair() will treat it as a blocked task due to its
non-zero decay_count, thereby adding its load to cfs_rq->removed_load
wrongly.
Thus, we must zero se->avg.decay_count in this case as well.
Signed-off-by: Xunlei Pang <pang.xunlei@linaro.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Ben Segall <bsegall@google.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: http://lkml.kernel.org/r/1418745509-2609-1-git-send-email-pang.xunlei@linaro.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
The dl_runtime_exceeded() function is supposed to ckeck if
a SCHED_DEADLINE task must be throttled, by checking if its
current runtime is <= 0. However, it also checks if the
scheduling deadline has been missed (the current time is
larger than the current scheduling deadline), further
decreasing the runtime if this happens.
This "double accounting" is wrong:
- In case of partitioned scheduling (or single CPU), this
happens if task_tick_dl() has been called later than expected
(due to small HZ values). In this case, the current runtime is
also negative, and replenish_dl_entity() can take care of the
deadline miss by recharging the current runtime to a value smaller
than dl_runtime
- In case of global scheduling on multiple CPUs, scheduling
deadlines can be missed even if the task did not consume more
runtime than expected, hence penalizing the task is wrong
This patch fix this problem by throttling a SCHED_DEADLINE task
only when its runtime becomes negative, and not modifying the runtime
Signed-off-by: Luca Abeni <luca.abeni@unitn.it>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Juri Lelli <juri.lelli@gmail.com>
Cc: <stable@vger.kernel.org>
Cc: Dario Faggioli <raistlin@linux.it>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: http://lkml.kernel.org/r/1418813432-20797-3-git-send-email-luca.abeni@unitn.it
Signed-off-by: Ingo Molnar <mingo@kernel.org>
According to global EDF, tasks should be migrated between runqueues
without checking if their scheduling deadlines and runtimes are valid.
However, SCHED_DEADLINE currently performs such a check:
a migration happens doing:
deactivate_task(rq, next_task, 0);
set_task_cpu(next_task, later_rq->cpu);
activate_task(later_rq, next_task, 0);
which ends up calling dequeue_task_dl(), setting the new CPU, and then
calling enqueue_task_dl().
enqueue_task_dl() then calls enqueue_dl_entity(), which calls
update_dl_entity(), which can modify scheduling deadline and runtime,
breaking global EDF scheduling.
As a result, some of the properties of global EDF are not respected:
for example, a taskset {(30, 80), (40, 80), (120, 170)} scheduled on
two cores can have unbounded response times for the third task even
if 30/80+40/80+120/170 = 1.5809 < 2
This can be fixed by invoking update_dl_entity() only in case of
wakeup, or if this is a new SCHED_DEADLINE task.
Signed-off-by: Luca Abeni <luca.abeni@unitn.it>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Juri Lelli <juri.lelli@gmail.com>
Cc: <stable@vger.kernel.org>
Cc: Dario Faggioli <raistlin@linux.it>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: http://lkml.kernel.org/r/1418813432-20797-2-git-send-email-luca.abeni@unitn.it
Signed-off-by: Ingo Molnar <mingo@kernel.org>
In effective_load, we have (long w * unsigned long tg->shares) / long W,
when w is negative, it is cast to unsigned long and hence the product is
insanely large. Fix this by casting tg->shares to long.
Reported-by: Sasha Levin <sasha.levin@oracle.com>
Signed-off-by: Yuyang Du <yuyang.du@intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Dave Jones <davej@redhat.com>
Cc: Andrey Ryabinin <a.ryabinin@samsung.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: http://lkml.kernel.org/r/20141219002956.GA25405@intel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
When allocating space for load_balance_mask, in sched_init, when
CPUMASK_OFFSTACK is set, we've managed to spill over
KMALLOC_MAX_SIZE on our 6144 core machine. The patch below
breaks up the allocations so that they don't overflow the max
alloc size. It also allocates the masks on the the node from
which they'll most commonly be accessed, to minimize remote
accesses on NUMA machines.
Suggested-by: George Beshers <gbeshers@sgi.com>
Signed-off-by: Alex Thorlton <athorlton@sgi.com>
Cc: George Beshers <gbeshers@sgi.com>
Cc: Russ Anderson <rja@sgi.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: http://lkml.kernel.org/r/1418928270-148543-1-git-send-email-athorlton@sgi.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
rcu_read_lock() can not protect p->real_parent if release_task(p) was
already called, change sched_show_task() to check pis_alive() like other
users do.
Note: we need some helpers to cleanup the code like this. And it seems
that that the usage of cpu_curr(cpu) in dump_cpu_task() is not safe too.
Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Cc: Aaron Tomlin <atomlin@redhat.com>
Cc: Alexey Dobriyan <adobriyan@gmail.com>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>,
Cc: Sterling Alexander <stalexan@redhat.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Roland McGrath <roland@hack.frob.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Pull scheduler updates from Ingo Molnar:
"The main changes in this cycle are:
- 'Nested Sleep Debugging', activated when CONFIG_DEBUG_ATOMIC_SLEEP=y.
This instruments might_sleep() checks to catch places that nest
blocking primitives - such as mutex usage in a wait loop. Such
bugs can result in hard to debug races/hangs.
Another category of invalid nesting that this facility will detect
is the calling of blocking functions from within schedule() ->
sched_submit_work() -> blk_schedule_flush_plug().
There's some potential for false positives (if secondary blocking
primitives themselves are not ready yet for this facility), but the
kernel will warn once about such bugs per bootup, so the warning
isn't much of a nuisance.
This feature comes with a number of fixes, for problems uncovered
with it, so no messages are expected normally.
- Another round of sched/numa optimizations and refinements, for
CONFIG_NUMA_BALANCING=y.
- Another round of sched/dl fixes and refinements.
Plus various smaller fixes and cleanups"
* 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (54 commits)
sched: Add missing rcu protection to wake_up_all_idle_cpus
sched/deadline: Introduce start_hrtick_dl() for !CONFIG_SCHED_HRTICK
sched/numa: Init numa balancing fields of init_task
sched/deadline: Remove unnecessary definitions in cpudeadline.h
sched/cpupri: Remove unnecessary definitions in cpupri.h
sched/deadline: Fix rq->dl.pushable_tasks bug in push_dl_task()
sched/fair: Fix stale overloaded status in the busiest group finding logic
sched: Move p->nr_cpus_allowed check to select_task_rq()
sched/completion: Document when to use wait_for_completion_io_*()
sched: Update comments about CLONE_NEWUTS and CLONE_NEWIPC
sched/fair: Kill task_struct::numa_entry and numa_group::task_list
sched: Refactor task_struct to use numa_faults instead of numa_* pointers
sched/deadline: Don't check CONFIG_SMP in switched_from_dl()
sched/deadline: Reschedule from switched_from_dl() after a successful pull
sched/deadline: Push task away if the deadline is equal to curr during wakeup
sched/deadline: Add deadline rq status print
sched/deadline: Fix artificial overrun introduced by yield_task_dl()
sched/rt: Clean up check_preempt_equal_prio()
sched/core: Use dl_bw_of() under rcu_read_lock_sched()
sched: Check if we got a shallowest_idle_cpu before searching for least_loaded_cpu
...
Pull RCU updates from Ingo Molnar:
"These are the main changes in this cycle:
- Streamline RCU's use of per-CPU variables, shifting from "cpu"
arguments to functions to "this_"-style per-CPU variable
accessors.
- signal-handling RCU updates.
- real-time updates.
- torture-test updates.
- miscellaneous fixes.
- documentation updates"
* 'core-rcu-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (34 commits)
rcu: Fix FIXME in rcu_tasks_kthread()
rcu: More info about potential deadlocks with rcu_read_unlock()
rcu: Optimize cond_resched_rcu_qs()
rcu: Add sparse check for RCU_INIT_POINTER()
documentation: memory-barriers.txt: Correct example for reorderings
documentation: Add atomic_long_t to atomic_ops.txt
documentation: Additional restriction for control dependencies
documentation: Document RCU self test boot params
rcutorture: Fix rcu_torture_cbflood() memory leak
rcutorture: Remove obsolete kversion param in kvm.sh
rcutorture: Remove stale test configurations
rcutorture: Enable RCU self test in configs
rcutorture: Add early boot self tests
torture: Run Linux-kernel binary out of results directory
cpu: Avoid puts_pending overflow
rcu: Remove "cpu" argument to rcu_cleanup_after_idle()
rcu: Remove "cpu" argument to rcu_prepare_for_idle()
rcu: Remove "cpu" argument to rcu_needs_cpu()
rcu: Remove "cpu" argument to rcu_note_context_switch()
rcu: Remove "cpu" argument to rcu_preempt_check_callbacks()
...
Locklessly doing is_idle_task(rq->curr) is only okay because of
RCU protection. The older variant of the broken code checked
rq->curr == rq->idle instead and therefore didn't need RCU.
Fixes: f6be8af1c9 ("sched: Add new API wake_up_if_idle() to wake up the idle cpu")
Signed-off-by: Andy Lutomirski <luto@amacapital.net>
Reviewed-by: Chuansheng Liu <chuansheng.liu@intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/729365dddca178506dfd0a9451006344cd6808bc.1417277372.git.luto@amacapital.net
Signed-off-by: Ingo Molnar <mingo@kernel.org>
It appears that some SCHEDULE_USER (asm for schedule_user) callers
in arch/x86/kernel/entry_64.S are called from RCU kernel context,
and schedule_user will return in RCU user context. This causes RCU
warnings and possible failures.
This is intended to be a minimal fix suitable for 3.18.
Reported-and-tested-by: Dave Jones <davej@redhat.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Frédéric Weisbecker <fweisbec@gmail.com>
Acked-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Signed-off-by: Andy Lutomirski <luto@amacapital.net>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Chris bisected a NULL pointer deference in task_sched_runtime() to
commit 6e998916df 'sched/cputime: Fix clock_nanosleep()/clock_gettime()
inconsistency'.
Chris observed crashes in atop or other /proc walking programs when he
started fork bombs on his machine. He assumed that this is a new exit
race, but that does not make any sense when looking at that commit.
What's interesting is that, the commit provides update_curr callbacks
for all scheduling classes except stop_task and idle_task.
While nothing can ever hit that via the clock_nanosleep() and
clock_gettime() interfaces, which have been the target of the commit in
question, the author obviously forgot that there are other code paths
which invoke task_sched_runtime()
do_task_stat(()
thread_group_cputime_adjusted()
thread_group_cputime()
task_cputime()
task_sched_runtime()
if (task_current(rq, p) && task_on_rq_queued(p)) {
update_rq_clock(rq);
up->sched_class->update_curr(rq);
}
If the stats are read for a stomp machine task, aka 'migration/N' and
that task is current on its cpu, this will happily call the NULL pointer
of stop_task->update_curr. Ooops.
Chris observation that this happens faster when he runs the fork bomb
makes sense as the fork bomb will kick migration threads more often so
the probability to hit the issue will increase.
Add the missing update_curr callbacks to the scheduler classes stop_task
and idle_task. While idle tasks cannot be monitored via /proc we have
other means to hit the idle case.
Fixes: 6e998916df 'sched/cputime: Fix clock_nanosleep()/clock_gettime() inconsistency'
Reported-by: Chris Mason <clm@fb.com>
Reported-and-tested-by: Borislav Petkov <bp@alien8.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Stanislaw Gruszka <sgruszka@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Actually, cpudl_set() and cpudl_init() can never be used without
CONFIG_SMP.
Signed-off-by: pang.xunlei <pang.xunlei@linaro.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Juri Lelli <juri.lelli@gmail.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: http://lkml.kernel.org/r/1415260327-30465-4-git-send-email-pang.xunlei@linaro.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Actually, cpupri_set() and cpupri_init() can never be used without
CONFIG_SMP.
Signed-off-by: pang.xunlei <pang.xunlei@linaro.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Juri Lelli <juri.lelli@gmail.com>
Cc: "pang.xunlei" <pang.xunlei@linaro.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: http://lkml.kernel.org/r/1415260327-30465-1-git-send-email-pang.xunlei@linaro.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Do not call dequeue_pushable_dl_task() when failing to push an eligible
task, as it remains pushable, merely not at this particular moment.
Actually the patch is the same behavior as commit 311e800e16 ("sched,
rt: Fix rq->rt.pushable_tasks bug in push_rt_task()" in -rt side.
Signed-off-by: Wanpeng Li <wanpeng.li@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Juri Lelli <juri.lelli@arm.com>
Cc: Kirill Tkhai <ktkhai@parallels.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: http://lkml.kernel.org/r/1415258564-8573-1-git-send-email-wanpeng.li@linux.intel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Commit caeb178c60 ("sched/fair: Make update_sd_pick_busiest() return
'true' on a busier sd") changes groups to be ranked in the order of
overloaded > imbalance > other, and busiest group is picked according
to this order.
sgs->group_capacity_factor is used to check if the group is overloaded.
When the child domain prefers tasks to go to siblings first, the
sgs->group_capacity_factor will be set lower than one in order to
move all the excess tasks away.
However, group overloaded status is not updated when
sgs->group_capacity_factor is set to lower than one, which leads to us
missing to find the busiest group.
This patch fixes it by updating group overloaded status when sg capacity
factor is set to one, in order to find the busiest group accurately.
Signed-off-by: Wanpeng Li <wanpeng.li@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Rik van Riel <riel@redhat.com>
Cc: Vincent Guittot <vincent.guittot@linaro.org>
Cc: Kirill Tkhai <ktkhai@parallels.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: http://lkml.kernel.org/r/1415144690-25196-1-git-send-email-wanpeng.li@linux.intel.com
[ Fixed the changelog. ]
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Move the p->nr_cpus_allowed check into kernel/sched/core.c: select_task_rq().
This change will make fair.c, rt.c, and deadline.c all start with the
same logic.
Suggested-and-Acked-by: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Wanpeng Li <wanpeng.li@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: "pang.xunlei" <pang.xunlei@linaro.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: http://lkml.kernel.org/r/1415150077-59053-1-git-send-email-wanpeng.li@linux.intel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
As discussed in [1], accounting IO is meant for blkio only. Document that
so driver authors won't use them for device io.
[1] http://thread.gmane.org/gmane.linux.drivers.i2c/20470
Signed-off-by: Wolfram Sang <wsa@the-dreams.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: One Thousand Gnomes <gnomes@lxorguk.ukuu.org.uk>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: http://lkml.kernel.org/r/1415098901-2768-1-git-send-email-wsa@the-dreams.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Commit d670ec1317 "posix-cpu-timers: Cure SMP wobbles" fixes one glibc
test case in cost of breaking another one. After that commit, calling
clock_nanosleep(TIMER_ABSTIME, X) and then clock_gettime(&Y) can result
of Y time being smaller than X time.
Reproducer/tester can be found further below, it can be compiled and ran by:
gcc -o tst-cpuclock2 tst-cpuclock2.c -pthread
while ./tst-cpuclock2 ; do : ; done
This reproducer, when running on a buggy kernel, will complain
about "clock_gettime difference too small".
Issue happens because on start in thread_group_cputimer() we initialize
sum_exec_runtime of cputimer with threads runtime not yet accounted and
then add the threads runtime to running cputimer again on scheduler
tick, making it's sum_exec_runtime bigger than actual threads runtime.
KOSAKI Motohiro posted a fix for this problem, but that patch was never
applied: https://lkml.org/lkml/2013/5/26/191 .
This patch takes different approach to cure the problem. It calls
update_curr() when cputimer starts, that assure we will have updated
stats of running threads and on the next schedule tick we will account
only the runtime that elapsed from cputimer start. That also assure we
have consistent state between cpu times of individual threads and cpu
time of the process consisted by those threads.
Full reproducer (tst-cpuclock2.c):
#define _GNU_SOURCE
#include <unistd.h>
#include <sys/syscall.h>
#include <stdio.h>
#include <time.h>
#include <pthread.h>
#include <stdint.h>
#include <inttypes.h>
/* Parameters for the Linux kernel ABI for CPU clocks. */
#define CPUCLOCK_SCHED 2
#define MAKE_PROCESS_CPUCLOCK(pid, clock) \
((~(clockid_t) (pid) << 3) | (clockid_t) (clock))
static pthread_barrier_t barrier;
/* Help advance the clock. */
static void *chew_cpu(void *arg)
{
pthread_barrier_wait(&barrier);
while (1) ;
return NULL;
}
/* Don't use the glibc wrapper. */
static int do_nanosleep(int flags, const struct timespec *req)
{
clockid_t clock_id = MAKE_PROCESS_CPUCLOCK(0, CPUCLOCK_SCHED);
return syscall(SYS_clock_nanosleep, clock_id, flags, req, NULL);
}
static int64_t tsdiff(const struct timespec *before, const struct timespec *after)
{
int64_t before_i = before->tv_sec * 1000000000ULL + before->tv_nsec;
int64_t after_i = after->tv_sec * 1000000000ULL + after->tv_nsec;
return after_i - before_i;
}
int main(void)
{
int result = 0;
pthread_t th;
pthread_barrier_init(&barrier, NULL, 2);
if (pthread_create(&th, NULL, chew_cpu, NULL) != 0) {
perror("pthread_create");
return 1;
}
pthread_barrier_wait(&barrier);
/* The test. */
struct timespec before, after, sleeptimeabs;
int64_t sleepdiff, diffabs;
const struct timespec sleeptime = {.tv_sec = 0,.tv_nsec = 100000000 };
/* The relative nanosleep. Not sure why this is needed, but its presence
seems to make it easier to reproduce the problem. */
if (do_nanosleep(0, &sleeptime) != 0) {
perror("clock_nanosleep");
return 1;
}
/* Get the current time. */
if (clock_gettime(CLOCK_PROCESS_CPUTIME_ID, &before) < 0) {
perror("clock_gettime[2]");
return 1;
}
/* Compute the absolute sleep time based on the current time. */
uint64_t nsec = before.tv_nsec + sleeptime.tv_nsec;
sleeptimeabs.tv_sec = before.tv_sec + nsec / 1000000000;
sleeptimeabs.tv_nsec = nsec % 1000000000;
/* Sleep for the computed time. */
if (do_nanosleep(TIMER_ABSTIME, &sleeptimeabs) != 0) {
perror("absolute clock_nanosleep");
return 1;
}
/* Get the time after the sleep. */
if (clock_gettime(CLOCK_PROCESS_CPUTIME_ID, &after) < 0) {
perror("clock_gettime[3]");
return 1;
}
/* The time after sleep should always be equal to or after the absolute sleep
time passed to clock_nanosleep. */
sleepdiff = tsdiff(&sleeptimeabs, &after);
if (sleepdiff < 0) {
printf("absolute clock_nanosleep woke too early: %" PRId64 "\n", sleepdiff);
result = 1;
printf("Before %llu.%09llu\n", before.tv_sec, before.tv_nsec);
printf("After %llu.%09llu\n", after.tv_sec, after.tv_nsec);
printf("Sleep %llu.%09llu\n", sleeptimeabs.tv_sec, sleeptimeabs.tv_nsec);
}
/* The difference between the timestamps taken before and after the
clock_nanosleep call should be equal to or more than the duration of the
sleep. */
diffabs = tsdiff(&before, &after);
if (diffabs < sleeptime.tv_nsec) {
printf("clock_gettime difference too small: %" PRId64 "\n", diffabs);
result = 1;
}
pthread_cancel(th);
return result;
}
Signed-off-by: Stanislaw Gruszka <sgruszka@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Rik van Riel <riel@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: http://lkml.kernel.org/r/20141112155843.GA24803@redhat.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
While looking over the cpu-timer code I found that we appear to add
the delta for the calling task twice, through:
cpu_timer_sample_group()
thread_group_cputimer()
thread_group_cputime()
times->sum_exec_runtime += task_sched_runtime();
*sample = cputime.sum_exec_runtime + task_delta_exec();
Which would make the sample run ahead, making the sleep short.
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Stanislaw Gruszka <sgruszka@redhat.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Rik van Riel <riel@redhat.com>
Cc: Tejun Heo <tj@kernel.org>
Link: http://lkml.kernel.org/r/20141112113737.GI10476@twins.programming.kicks-ass.net
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Because the whole numa task selection stuff runs with preemption
enabled (its long and expensive) we can end up migrating and selecting
oneself as a swap target. This doesn't really work out well -- we end
up trying to acquire the same lock twice for the swap migrate -- so
avoid this.
Reported-and-Tested-by: Sasha Levin <sasha.levin@oracle.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: http://lkml.kernel.org/r/20141110100328.GF29390@twins.programming.kicks-ass.net
Signed-off-by: Ingo Molnar <mingo@kernel.org>
On latest mm + KASan patchset I've got this:
==================================================================
BUG: AddressSanitizer: out of bounds access in sched_init_smp+0x3ba/0x62c at addr ffff88006d4bee6c
=============================================================================
BUG kmalloc-8 (Not tainted): kasan error
-----------------------------------------------------------------------------
Disabling lock debugging due to kernel taint
INFO: Allocated in alloc_vfsmnt+0xb0/0x2c0 age=75 cpu=0 pid=0
__slab_alloc+0x4b4/0x4f0
__kmalloc_track_caller+0x15f/0x1e0
kstrdup+0x44/0x90
alloc_vfsmnt+0xb0/0x2c0
vfs_kern_mount+0x35/0x190
kern_mount_data+0x25/0x50
pid_ns_prepare_proc+0x19/0x50
alloc_pid+0x5e2/0x630
copy_process.part.41+0xdf5/0x2aa0
do_fork+0xf5/0x460
kernel_thread+0x21/0x30
rest_init+0x1e/0x90
start_kernel+0x522/0x531
x86_64_start_reservations+0x2a/0x2c
x86_64_start_kernel+0x15b/0x16a
INFO: Slab 0xffffea0001b52f80 objects=24 used=22 fp=0xffff88006d4befc0 flags=0x100000000004080
INFO: Object 0xffff88006d4bed20 @offset=3360 fp=0xffff88006d4bee70
Bytes b4 ffff88006d4bed10: 00 00 00 00 00 00 00 00 5a 5a 5a 5a 5a 5a 5a 5a ........ZZZZZZZZ
Object ffff88006d4bed20: 70 72 6f 63 00 6b 6b a5 proc.kk.
Redzone ffff88006d4bed28: cc cc cc cc cc cc cc cc ........
Padding ffff88006d4bee68: 5a 5a 5a 5a 5a 5a 5a 5a ZZZZZZZZ
CPU: 0 PID: 1 Comm: swapper/0 Tainted: G B 3.18.0-rc3-mm1+ #108
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.7.5-0-ge51488c-20140602_164612-nilsson.home.kraxel.org 04/01/2014
ffff88006d4be000 0000000000000000 ffff88006d4bed20 ffff88006c86fd18
ffffffff81cd0a59 0000000000000058 ffff88006d404240 ffff88006c86fd48
ffffffff811fa3a8 ffff88006d404240 ffffea0001b52f80 ffff88006d4bed20
Call Trace:
dump_stack (lib/dump_stack.c:52)
print_trailer (mm/slub.c:645)
object_err (mm/slub.c:652)
? sched_init_smp (kernel/sched/core.c:6552 kernel/sched/core.c:7063)
kasan_report_error (mm/kasan/report.c:102 mm/kasan/report.c:178)
? kasan_poison_shadow (mm/kasan/kasan.c:48)
? kasan_unpoison_shadow (mm/kasan/kasan.c:54)
? kasan_poison_shadow (mm/kasan/kasan.c:48)
? kasan_kmalloc (mm/kasan/kasan.c:311)
__asan_load4 (mm/kasan/kasan.c:371)
? sched_init_smp (kernel/sched/core.c:6552 kernel/sched/core.c:7063)
sched_init_smp (kernel/sched/core.c:6552 kernel/sched/core.c:7063)
kernel_init_freeable (init/main.c:869 init/main.c:997)
? finish_task_switch (kernel/sched/sched.h:1036 kernel/sched/core.c:2248)
? rest_init (init/main.c:924)
kernel_init (init/main.c:929)
? rest_init (init/main.c:924)
ret_from_fork (arch/x86/kernel/entry_64.S:348)
? rest_init (init/main.c:924)
Read of size 4 by task swapper/0:
Memory state around the buggy address:
ffff88006d4beb80: fc fc fc fc fc fc fc fc fc fc 00 fc fc fc fc fc
ffff88006d4bec00: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc
ffff88006d4bec80: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc
ffff88006d4bed00: fc fc fc fc 00 fc fc fc fc fc fc fc fc fc fc fc
ffff88006d4bed80: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc
>ffff88006d4bee00: fc fc fc fc fc fc fc fc fc fc fc fc fc fc 04 fc
^
ffff88006d4bee80: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc
ffff88006d4bef00: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc
ffff88006d4bef80: fc fc fc fc fc fc fc fc fb fb fb fb fb fb fb fb
ffff88006d4bf000: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
ffff88006d4bf080: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
==================================================================
Zero 'level' (e.g. on non-NUMA system) causing out of bounds
access in this line:
sched_max_numa_distance = sched_domains_numa_distance[level - 1];
Fix this by exiting from sched_init_numa() earlier.
Signed-off-by: Andrey Ryabinin <a.ryabinin@samsung.com>
Reviewed-by: Rik van Riel <riel@redhat.com>
Fixes: 9942f79ba ("sched/numa: Export info needed for NUMA balancing on complex topologies")
Cc: peterz@infradead.org
Link: http://lkml.kernel.org/r/1415372020-1871-1-git-send-email-a.ryabinin@samsung.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
This patch simplifies task_struct by removing the four numa_* pointers
in the same array and replacing them with the array pointer. By doing this,
on x86_64, the size of task_struct is reduced by 3 ulong pointers (24 bytes on
x86_64).
A new parameter is added to the task_faults_idx function so that it can return
an index to the correct offset, corresponding with the old precalculated
pointers.
All of the code in sched/ that depended on task_faults_idx and numa_* was
changed in order to match the new logic.
Signed-off-by: Iulia Manda <iulia.manda21@gmail.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: mgorman@suse.de
Cc: dave@stgolabs.net
Cc: riel@redhat.com
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: http://lkml.kernel.org/r/20141031001331.GA30662@winterfell
Signed-off-by: Ingo Molnar <mingo@kernel.org>
There are both UP and SMP version of pull_dl_task(), so don't need
to check CONFIG_SMP in switched_from_dl();
Signed-off-by: Wanpeng Li <wanpeng.li@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Juri Lelli <juri.lelli@arm.com>
Cc: Kirill Tkhai <ktkhai@parallels.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: http://lkml.kernel.org/r/1414708776-124078-6-git-send-email-wanpeng.li@linux.intel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
In switched_from_dl() we have to issue a resched if we successfully
pulled some task from other cpus. This patch also aligns the behavior
with -rt.
Suggested-by: Juri Lelli <juri.lelli@arm.com>
Signed-off-by: Wanpeng Li <wanpeng.li@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Kirill Tkhai <ktkhai@parallels.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: http://lkml.kernel.org/r/1414708776-124078-5-git-send-email-wanpeng.li@linux.intel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
This patch pushes task away if the dealine of the task is equal
to current during wake up. The same behavior as rt class.
Signed-off-by: Wanpeng Li <wanpeng.li@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Juri Lelli <juri.lelli@arm.com>
Cc: Kirill Tkhai <ktkhai@parallels.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: http://lkml.kernel.org/r/1414708776-124078-4-git-send-email-wanpeng.li@linux.intel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
The yield semantic of deadline class is to reduce remaining runtime to
zero, and then update_curr_dl() will stop it. However, comsumed bandwidth
is reduced from the budget of yield task again even if it has already been
set to zero which leads to artificial overrun. This patch fix it by make
sure we don't steal some more time from the task that yielded in update_curr_dl().
Suggested-by: Juri Lelli <juri.lelli@arm.com>
Signed-off-by: Wanpeng Li <wanpeng.li@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Kirill Tkhai <ktkhai@parallels.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: http://lkml.kernel.org/r/1414708776-124078-2-git-send-email-wanpeng.li@linux.intel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
This patch checks if current can be pushed/pulled somewhere else
in advance to make logic clear, the same behavior as dl class.
- If current can't be migrated, useless to reschedule, let's hope
task can move out.
- If task is migratable, so let's not schedule it and see if it
can be pushed or pulled somewhere else.
Signed-off-by: Wanpeng Li <wanpeng.li@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Juri Lelli <juri.lelli@arm.com>
Cc: Kirill Tkhai <ktkhai@parallels.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: http://lkml.kernel.org/r/1414708776-124078-1-git-send-email-wanpeng.li@linux.intel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
As per commit f10e00f4bf ("sched/dl: Use dl_bw_of() under
rcu_read_lock_sched()"), dl_bw_of() has to be protected by
rcu_read_lock_sched().
Signed-off-by: Juri Lelli <juri.lelli@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: http://lkml.kernel.org/r/1414497286-28824-1-git-send-email-juri.lelli@arm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Idle cpu is idler than non-idle cpu, so we needn't search for least_loaded_cpu
after we have found an idle cpu.
Signed-off-by: Yao Dongdong <yaodongdong@huawei.com>
Reviewed-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: http://lkml.kernel.org/r/1414469286-6023-1-git-send-email-yaodongdong@huawei.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Currently used hrtimer_try_to_cancel() is racy:
raw_spin_lock(&rq->lock)
... dl_task_timer raw_spin_lock(&rq->lock)
... raw_spin_lock(&rq->lock) ...
switched_from_dl() ... ...
hrtimer_try_to_cancel() ... ...
switched_to_fair() ... ...
... ... ...
... ... ...
raw_spin_unlock(&rq->lock) ... (asquired)
... ... ...
... ... ...
do_exit() ... ...
schedule() ... ...
raw_spin_lock(&rq->lock) ... raw_spin_unlock(&rq->lock)
... ... ...
raw_spin_unlock(&rq->lock) ... raw_spin_lock(&rq->lock)
... ... (asquired)
put_task_struct() ... ...
free_task_struct() ... ...
... ... raw_spin_unlock(&rq->lock)
... (asquired) ...
... ... ...
... (use after free) ...
So, let's implement 100% guaranteed way to cancel the timer and let's
be sure we are safe even in very unlikely situations.
rq unlocking does not limit the area of switched_from_dl() use, because
this has already been possible in pull_dl_task() below.
Let's consider the safety of of this unlocking. New code in the patch
is working when hrtimer_try_to_cancel() fails. This means the callback
is running. In this case hrtimer_cancel() is just waiting till the
callback is finished. Two
1) Since we are in switched_from_dl(), new class is not dl_sched_class and
new prio is not less MAX_DL_PRIO. So, the callback returns early; it's
right after !dl_task() check. After that hrtimer_cancel() returns back too.
The above is:
raw_spin_lock(rq->lock); ...
... dl_task_timer()
... raw_spin_lock(rq->lock);
switched_from_dl() ...
hrtimer_try_to_cancel() ...
raw_spin_unlock(rq->lock); ...
hrtimer_cancel() ...
... raw_spin_unlock(rq->lock);
... return HRTIMER_NORESTART;
... ...
raw_spin_lock(rq->lock); ...
2) But the below is also possible:
dl_task_timer()
raw_spin_lock(rq->lock);
...
raw_spin_unlock(rq->lock);
raw_spin_lock(rq->lock); ...
switched_from_dl() ...
hrtimer_try_to_cancel() ...
... return HRTIMER_NORESTART;
raw_spin_unlock(rq->lock); ...
hrtimer_cancel(); ...
raw_spin_lock(rq->lock); ...
In this case hrtimer_cancel() returns immediately. Very unlikely case,
just to mention.
Nobody can manipulate the task, because check_class_changed() is
always called with pi_lock locked. Nobody can force the task to
participate in (concurrent) priority inheritance schemes (the same reason).
All concurrent task operations require pi_lock, which is held by us.
No deadlocks with dl_task_timer() are possible, because it returns
right after !dl_task() check (it does nothing).
If we receive a new dl_task during the time of unlocked rq, we just
don't have to do pull_dl_task() in switched_from_dl() further.
Signed-off-by: Kirill Tkhai <ktkhai@parallels.com>
[ Added comments]
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Juri Lelli <juri.lelli@arm.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: http://lkml.kernel.org/r/1414420852.19914.186.camel@tkhai
Signed-off-by: Ingo Molnar <mingo@kernel.org>
In some cases this can trigger a true flood of output.
Requested-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
There is a race between kthread_stop() and the new wait_woken() that
can result in a lack of progress.
CPU 0 | CPU 1
|
rfcomm_run() | kthread_stop()
... |
if (!test_bit(KTHREAD_SHOULD_STOP)) |
| set_bit(KTHREAD_SHOULD_STOP)
| wake_up_process()
wait_woken() | wait_for_completion()
set_current_state(INTERRUPTIBLE) |
if (!WQ_FLAG_WOKEN) |
schedule_timeout() |
|
After which both tasks will wait.. forever.
Fix this by having wait_woken() check for kthread_should_stop() but
only for kthreads (obviously).
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Peter Hurley <peter@hurleysoftware.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
sched_move_task() is the only interface to change sched_task_group:
cpu_cgrp_subsys methods and autogroup_move_group() use it.
Everything is synchronized by task_rq_lock(), so cpu_cgroup_attach()
is ordered with other users of sched_move_task(). This means we do no
need RCU here: if we've dereferenced a tg here, the .attach method
hasn't been called for it yet.
Thus, we should pass "true" to task_css_check() to silence lockdep
warnings.
Fixes: eeb61e53ea ("sched: Fix race between task_group and sched_task_group")
Reported-by: Oleg Nesterov <oleg@redhat.com>
Reported-by: Fengguang Wu <fengguang.wu@intel.com>
Signed-off-by: Kirill Tkhai <ktkhai@parallels.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: http://lkml.kernel.org/r/1414473874.8574.2.camel@tkhai
Signed-off-by: Ingo Molnar <mingo@kernel.org>
The "cpu" argument to rcu_note_context_switch() is always the current
CPU, so drop it. This in turn allows the "cpu" argument to
rcu_preempt_note_context_switch() to be removed, which allows the sole
use of "cpu" in both functions to be replaced with a this_cpu_ptr().
Again, the anticipated cross-CPU uses of these functions has been
replaced by NO_HZ_FULL.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Reviewed-by: Pranith Kumar <bobby.prani@gmail.com>
cond_resched() is a preemption point, not strictly a blocking
primitive, so exclude it from the ->state test.
In particular, preemption preserves task_struct::state.
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: tglx@linutronix.de
Cc: ilya.dryomov@inktank.com
Cc: umgwanakikbuti@gmail.com
Cc: oleg@redhat.com
Cc: Alex Elder <alex.elder@linaro.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Axel Lin <axel.lin@ingics.com>
Cc: Daniel Borkmann <dborkman@redhat.com>
Cc: Dave Jones <davej@redhat.com>
Cc: Jason Baron <jbaron@akamai.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Rusty Russell <rusty@rustcorp.com.au>
Cc: Steven Rostedt <rostedt@goodmis.org>
Link: http://lkml.kernel.org/r/20140924082242.656559952@infradead.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Validate we call might_sleep() with TASK_RUNNING, which catches places
where we nest blocking primitives, eg. mutex usage in a wait loop.
Since all blocking is arranged through task_struct::state, nesting
this will cause the inner primitive to set TASK_RUNNING and the outer
will thus not block.
Another observed problem is calling a blocking function from
schedule()->sched_submit_work()->blk_schedule_flush_plug() which will
then destroy the task state for the actual __schedule() call that
comes after it.
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: tglx@linutronix.de
Cc: ilya.dryomov@inktank.com
Cc: umgwanakikbuti@gmail.com
Cc: oleg@redhat.com
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: http://lkml.kernel.org/r/20140924082242.591637616@infradead.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
There are a few places that call blocking primitives from wait loops,
provide infrastructure to support this without the typical
task_struct::state collision.
We record the wakeup in wait_queue_t::flags which leaves
task_struct::state free to be used by others.
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Oleg Nesterov <oleg@redhat.com>
Cc: tglx@linutronix.de
Cc: ilya.dryomov@inktank.com
Cc: umgwanakikbuti@gmail.com
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: http://lkml.kernel.org/r/20140924082242.051202318@infradead.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Use nr_cpus_allowed to bail from select_task_rq() when only one cpu
can be used, and saves some cycles for pinned tasks.
Signed-off-by: Wanpeng Li <wanpeng.li@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: http://lkml.kernel.org/r/1413253360-5318-2-git-send-email-wanpeng.li@linux.intel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
There is no need to do balance during fork since SCHED_DEADLINE
tasks can't fork. This patch avoid the SD_BALANCE_FORK check.
Signed-off-by: Wanpeng Li <wanpeng.li@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1413253360-5318-1-git-send-email-wanpeng.li@linux.intel.com
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
How we deal with updates to exclusive cpusets is currently broken.
As an example, suppose we have an exclusive cpuset composed of
two cpus: A[cpu0,cpu1]. We can assign SCHED_DEADLINE task to it
up to the allowed bandwidth. If we want now to modify cpusetA's
cpumask, we have to check that removing a cpu's amount of
bandwidth doesn't break AC guarantees. This thing isn't checked
in the current code.
This patch fixes the problem above, denying an update if the
new cpumask won't have enough bandwidth for SCHED_DEADLINE tasks
that are currently active.
Signed-off-by: Juri Lelli <juri.lelli@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Li Zefan <lizefan@huawei.com>
Cc: cgroups@vger.kernel.org
Link: http://lkml.kernel.org/r/5433E6AF.5080105@arm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Exclusive cpusets are the only way users can restrict SCHED_DEADLINE tasks
affinity (performing what is commonly called clustered scheduling).
Unfortunately, such thing is currently broken for two reasons:
- No check is performed when the user tries to attach a task to
an exlusive cpuset (recall that exclusive cpusets have an
associated maximum allowed bandwidth).
- Bandwidths of source and destination cpusets are not correctly
updated after a task is migrated between them.
This patch fixes both things at once, as they are opposite faces
of the same coin.
The check is performed in cpuset_can_attach(), as there aren't any
points of failure after that function. The updated is split in two
halves. We first reserve bandwidth in the destination cpuset, after
we pass the check in cpuset_can_attach(). And we then release
bandwidth from the source cpuset when the task's affinity is
actually changed. Even if there can be time windows when sched_setattr()
may erroneously fail in the source cpuset, we are fine with it, as
we can't perfom an atomic update of both cpusets at once.
Reported-by: Daniel Wagner <daniel.wagner@bmw-carit.de>
Reported-by: Vincent Legout <vincent@legout.info>
Signed-off-by: Juri Lelli <juri.lelli@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Dario Faggioli <raistlin@linux.it>
Cc: Michael Trimarchi <michael@amarulasolutions.com>
Cc: Fabio Checconi <fchecconi@gmail.com>
Cc: michael@amarulasolutions.com
Cc: luca.abeni@unitn.it
Cc: Li Zefan <lizefan@huawei.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: cgroups@vger.kernel.org
Link: http://lkml.kernel.org/r/1411118561-26323-3-git-send-email-juri.lelli@arm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
As Kirill mentioned (https://lkml.org/lkml/2013/1/29/118):
| If rq has already had 2 or more pushable tasks and we try to add a
| pinned task then call of push_rt_task will just waste a time.
Just switched pinned task is not able to be pushed. If the rq has had
several dl tasks before they have already been considered as candidates
to be pushed (or pulled). This patch implements the same behavior as rt
class which introduced by commit 1044791755 ("sched/rt: Do not try to
push tasks if pinned task switches to RT").
Suggested-by: Kirill V Tkhai <tkhai@yandex.ru>
Acked-by: Juri Lelli <juri.lelli@arm.com>
Signed-off-by: Wanpeng Li <wanpeng.li@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: http://lkml.kernel.org/r/1413938203-224610-1-git-send-email-wanpeng.li@linux.intel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
task_preempt_count() is pointless if preemption counter is per-cpu,
currently this is x86 only. It is only valid if the task is not
running, and even in this case the only info it can provide is the
state of PREEMPT_ACTIVE bit.
Change its single caller to check p->on_rq instead, this should be
the same if p->state != TASK_RUNNING, and kill this helper.
Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Kirill Tkhai <tkhai@yandex.ru>
Cc: Alexander Graf <agraf@suse.de>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Christoph Lameter <cl@linux.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: linux-arch@vger.kernel.org
Link: http://lkml.kernel.org/r/20141008183348.GC17495@redhat.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Both callers of finish_task_switch() need to recalculate this_rq()
and pass it as an argument, plus __schedule() does this again after
context_switch().
It would be simpler to call this_rq() once in finish_task_switch()
and return the this rq to the callers.
Note: probably "int cpu" in __schedule() should die; it is not used
and both rcu_note_context_switch() and wq_worker_sleeping() do not
really need this argument.
Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Kirill Tkhai <tkhai@yandex.ru>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: http://lkml.kernel.org/r/20141009193232.GB5408@redhat.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
finish_task_switch() enables preemption, so post_schedule(rq) can be
called on the wrong (and even dead) CPU. Afaics, nothing really bad
can happen, but in this case we can wrongly clear rq->post_schedule
on that CPU. And this simply looks wrong in any case.
Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Kirill Tkhai <tkhai@yandex.ru>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: http://lkml.kernel.org/r/20141008193644.GA32055@redhat.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
In pseudo-interleaved numa_groups, all tasks try to relocate to
the group's preferred_nid. When a group is spread across multiple
NUMA nodes, this can lead to tasks swapping their location with
other tasks inside the same group, instead of swapping location with
tasks from other NUMA groups. This can keep NUMA groups from converging.
Examining all nodes, when dealing with a task in a pseudo-interleaved
NUMA group, avoids this problem. Note that only CPUs in nodes that
improve the task or group score are examined, so the loop isn't too
bad.
Tested-by: Vinod Chegu <chegu_vinod@hp.com>
Signed-off-by: Rik van Riel <riel@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: "Vinod Chegu" <chegu_vinod@hp.com>
Cc: mgorman@suse.de
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: http://lkml.kernel.org/r/20141009172747.0d97c38c@annuminas.surriel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
On systems with complex NUMA topologies, the node scoring is adjusted
to allow workloads to converge on nodes that are near each other.
The way a task group's preferred nid is determined needs to be adjusted,
in order for the preferred_nid to be consistent with group_weight scoring.
This ensures that we actually try to converge workloads on adjacent nodes.
Signed-off-by: Rik van Riel <riel@redhat.com>
Tested-by: Chegu Vinod <chegu_vinod@hp.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: mgorman@suse.de
Cc: chegu_vinod@hp.com
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: http://lkml.kernel.org/r/1413530994-9732-6-git-send-email-riel@redhat.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
In order to do task placement on systems with complex NUMA topologies,
it is necessary to count the faults on nodes nearby the node that is
being examined for a potential move.
In case of a system with a backplane interconnect, we are dealing with
groups of NUMA nodes; each of the nodes within a group is the same number
of hops away from nodes in other groups in the system. Optimal placement
on this topology is achieved by counting all nearby nodes equally. When
comparing nodes A and B at distance N, nearby nodes are those at distances
smaller than N from nodes A or B.
Placement strategy on a system with a glueless mesh NUMA topology needs
to be different, because there are no natural groups of nodes determined
by the hardware. Instead, when dealing with two nodes A and B at distance
N, N >= 2, there will be intermediate nodes at distance < N from both nodes
A and B. Good placement can be achieved by right shifting the faults on
nearby nodes by the number of hops from the node being scored. In this
context, a nearby node is any node less than the maximum distance in the
system away from the node. Those nodes are skipped for efficiency reasons,
there is no real policy reason to do so.
Placement policy on directly connected NUMA systems is not affected.
Signed-off-by: Rik van Riel <riel@redhat.com>
Tested-by: Chegu Vinod <chegu_vinod@hp.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: mgorman@suse.de
Cc: chegu_vinod@hp.com
Link: http://lkml.kernel.org/r/1413530994-9732-5-git-send-email-riel@redhat.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Preparatory patch for adding NUMA placement on systems with
complex NUMA topology. Also fix a potential divide by zero
in group_weight()
Signed-off-by: Rik van Riel <riel@redhat.com>
Tested-by: Chegu Vinod <chegu_vinod@hp.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: mgorman@suse.de
Cc: chegu_vinod@hp.com
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: http://lkml.kernel.org/r/1413530994-9732-4-git-send-email-riel@redhat.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Smaller NUMA systems tend to have all NUMA nodes directly connected
to each other. This includes the degenerate case of a system with just
one node, ie. a non-NUMA system.
Larger systems can have two kinds of NUMA topology, which affects how
tasks and memory should be placed on the system.
On glueless mesh systems, nodes that are not directly connected to
each other will bounce traffic through intermediary nodes. Task groups
can be run closer to each other by moving tasks from a node to an
intermediary node between it and the task's preferred node.
On NUMA systems with backplane controllers, the intermediary hops
are incapable of running programs. This creates "islands" of nodes
that are at an equal distance to anywhere else in the system.
Each kind of topology requires a slightly different placement
algorithm; this patch provides the mechanism to detect the kind
of NUMA topology of a system.
Signed-off-by: Rik van Riel <riel@redhat.com>
Tested-by: Chegu Vinod <chegu_vinod@hp.com>
[ Changed to use kernel/sched/sched.h ]
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: mgorman@suse.de
Cc: chegu_vinod@hp.com
Link: http://lkml.kernel.org/r/1413530994-9732-3-git-send-email-riel@redhat.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Export some information that is necessary to do placement of
tasks on systems with multi-level NUMA topologies.
Signed-off-by: Rik van Riel <riel@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: mgorman@suse.de
Cc: chegu_vinod@hp.com
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: http://lkml.kernel.org/r/1413530994-9732-2-git-send-email-riel@redhat.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
1) switched_to_dl() check is wrong. We reschedule only
if rq->curr is deadline task, and we do not reschedule
if it's a lower priority task. But we must always
preempt a task of other classes.
2) dl_task_timer():
Policy does not change in case of priority inheritance.
rt_mutex_setprio() changes prio, while policy remains old.
So we lose some balancing logic in dl_task_timer() and
switched_to_dl() when we check policy instead of priority. Boosted
task may be rq->curr.
(I didn't change switched_from_dl() because no check is necessary
there at all).
I've looked at this place(switched_to_dl) several times and even fixed
this function, but found just now... I suppose some performance tests
may work better after this.
Signed-off-by: Kirill Tkhai <ktkhai@parallels.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Juri Lelli <juri.lelli@gmail.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: http://lkml.kernel.org/r/1413909356.19914.128.camel@tkhai
Signed-off-by: Ingo Molnar <mingo@kernel.org>
preempt_schedule_context() does preempt_enable_notrace() at the end
and this can call the same function again; exception_exit() is heavy
and it is quite possible that need-resched is true again.
1. Change this code to dec preempt_count() and check need_resched()
by hand.
2. As Linus suggested, we can use the PREEMPT_ACTIVE bit and avoid
the enable/disable dance around __schedule(). But in this case
we need to move into sched/core.c.
3. Cosmetic, but x86 forgets to declare this function. This doesn't
really matter because it is only called by asm helpers, still it
make sense to add the declaration into asm/preempt.h to match
preempt_schedule().
Reported-by: Sasha Levin <sasha.levin@oracle.com>
Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Alexander Graf <agraf@suse.de>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Christoph Lameter <cl@linux.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Peter Anvin <hpa@zytor.com>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: Chuck Ebbert <cebbert.lkml@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Link: http://lkml.kernel.org/r/20141005202322.GB27962@redhat.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
While offling node by hot removing memory, the following divide error
occurs:
divide error: 0000 [#1] SMP
[...]
Call Trace:
[...] handle_mm_fault
[...] ? try_to_wake_up
[...] ? wake_up_state
[...] __do_page_fault
[...] ? do_futex
[...] ? put_prev_entity
[...] ? __switch_to
[...] do_page_fault
[...] page_fault
[...]
RIP [<ffffffff810a7081>] task_numa_fault
RSP <ffff88084eb2bcb0>
The issue occurs as follows:
1. When page fault occurs and page is allocated from node 1,
task_struct->numa_faults_buffer_memory[] of node 1 is
incremented and p->numa_faults_locality[] is also incremented
as follows:
o numa_faults_buffer_memory[] o numa_faults_locality[]
NR_NUMA_HINT_FAULT_TYPES
| 0 | 1 |
---------------------------------- ----------------------
node 0 | 0 | 0 | remote | 0 |
node 1 | 0 | 1 | locale | 1 |
---------------------------------- ----------------------
2. node 1 is offlined by hot removing memory.
3. When page fault occurs, fault_types[] is calculated by using
p->numa_faults_buffer_memory[] of all online nodes in
task_numa_placement(). But node 1 was offline by step 2. So
the fault_types[] is calculated by using only
p->numa_faults_buffer_memory[] of node 0. So both of fault_types[]
are set to 0.
4. The values(0) of fault_types[] pass to update_task_scan_period().
5. numa_faults_locality[1] is set to 1. So the following division is
calculated.
static void update_task_scan_period(struct task_struct *p,
unsigned long shared, unsigned long private){
...
ratio = DIV_ROUND_UP(private * NUMA_PERIOD_SLOTS, (private + shared));
}
6. But both of private and shared are set to 0. So divide error
occurs here.
The divide error is rare case because the trigger is node offline.
This patch always increments denominator for avoiding divide error.
Signed-off-by: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: http://lkml.kernel.org/r/54475703.8000505@jp.fujitsu.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Unlocked access to dst_rq->curr in task_numa_compare() is racy.
If curr task is exiting this may be a reason of use-after-free:
task_numa_compare() do_exit()
... current->flags |= PF_EXITING;
... release_task()
... ~~delayed_put_task_struct()~~
... schedule()
rcu_read_lock() ...
cur = ACCESS_ONCE(dst_rq->curr) ...
... rq->curr = next;
... context_switch()
... finish_task_switch()
... put_task_struct()
... __put_task_struct()
... free_task_struct()
task_numa_assign() ...
get_task_struct() ...
As noted by Oleg:
<<The lockless get_task_struct(tsk) is only safe if tsk == current
and didn't pass exit_notify(), or if this tsk was found on a rcu
protected list (say, for_each_process() or find_task_by_vpid()).
IOW, it is only safe if release_task() was not called before we
take rcu_read_lock(), in this case we can rely on the fact that
delayed_put_pid() can not drop the (potentially) last reference
until rcu_read_unlock().
And as Kirill pointed out task_numa_compare()->task_numa_assign()
path does get_task_struct(dst_rq->curr) and this is not safe. The
task_struct itself can't go away, but rcu_read_lock() can't save
us from the final put_task_struct() in finish_task_switch(); this
reference goes away without rcu gp>>
The patch provides simple check of PF_EXITING flag. If it's not set,
this guarantees that call_rcu() of delayed_put_task_struct() callback
hasn't happened yet, so we can safely do get_task_struct() in
task_numa_assign().
Locked dst_rq->lock protects from concurrency with the last schedule().
Reusing or unmapping of cur's memory may happen without it.
Suggested-by: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Kirill Tkhai <ktkhai@parallels.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: http://lkml.kernel.org/r/1413962231.19914.130.camel@tkhai
Signed-off-by: Ingo Molnar <mingo@kernel.org>
dl_task_timer() is racy against several paths. Daniel noticed that
the replenishment timer may experience a race condition against an
enqueue_dl_entity() called from rt_mutex_setprio(). With his own
words:
rt_mutex_setprio() resets p->dl.dl_throttled. So the pattern is:
start_dl_timer() throttled = 1, rt_mutex_setprio() throlled = 0,
sched_switch() -> enqueue_task(), dl_task_timer-> enqueue_task()
throttled is 0
=> BUG_ON(on_dl_rq(dl_se)) fires as the scheduling entity is already
enqueued on the -deadline runqueue.
As we do for the other races, we just bail out in the replenishment
timer code.
Reported-by: Daniel Wagner <daniel.wagner@bmw-carit.de>
Tested-by: Daniel Wagner <daniel.wagner@bmw-carit.de>
Signed-off-by: Juri Lelli <juri.lelli@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: vincent@legout.info
Cc: Dario Faggioli <raistlin@linux.it>
Cc: Michael Trimarchi <michael@amarulasolutions.com>
Cc: Fabio Checconi <fchecconi@gmail.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: http://lkml.kernel.org/r/1414142198-18552-5-git-send-email-juri.lelli@arm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
In the deboost path, right after the dl_boosted flag has been
reset, we can currently end up replenishing using -deadline
parameters of a !SCHED_DEADLINE entity. This of course causes
a bug, as those parameters are empty.
In the case depicted above it is safe to simply bail out, as
the deboosted task is going to be back to its original scheduling
class anyway.
Reported-by: Daniel Wagner <daniel.wagner@bmw-carit.de>
Tested-by: Daniel Wagner <daniel.wagner@bmw-carit.de>
Signed-off-by: Juri Lelli <juri.lelli@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: vincent@legout.info
Cc: Dario Faggioli <raistlin@linux.it>
Cc: Michael Trimarchi <michael@amarulasolutions.com>
Cc: Fabio Checconi <fchecconi@gmail.com>
Link: http://lkml.kernel.org/r/1414142198-18552-4-git-send-email-juri.lelli@arm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
The race may happen when somebody is changing task_group of a forking task.
Child's cgroup is the same as parent's after dup_task_struct() (there just
memory copying). Also, cfs_rq and rt_rq are the same as parent's.
But if parent changes its task_group before it's called cgroup_post_fork(),
we do not reflect this situation on child. Child's cfs_rq and rt_rq remain
the same, while child's task_group changes in cgroup_post_fork().
To fix this we introduce fork() method, which calls sched_move_task() directly.
This function changes sched_task_group on appropriate (also its logic has
no problem with freshly created tasks, so we shouldn't introduce something
special; we are able just to use it).
Possibly, this decides the Burke Libbey's problem: https://lkml.org/lkml/2014/10/24/456
Signed-off-by: Kirill Tkhai <ktkhai@parallels.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: http://lkml.kernel.org/r/1414405105.19914.169.camel@tkhai
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Pull percpu consistent-ops changes from Tejun Heo:
"Way back, before the current percpu allocator was implemented, static
and dynamic percpu memory areas were allocated and handled separately
and had their own accessors. The distinction has been gone for many
years now; however, the now duplicate two sets of accessors remained
with the pointer based ones - this_cpu_*() - evolving various other
operations over time. During the process, we also accumulated other
inconsistent operations.
This pull request contains Christoph's patches to clean up the
duplicate accessor situation. __get_cpu_var() uses are replaced with
with this_cpu_ptr() and __this_cpu_ptr() with raw_cpu_ptr().
Unfortunately, the former sometimes is tricky thanks to C being a bit
messy with the distinction between lvalues and pointers, which led to
a rather ugly solution for cpumask_var_t involving the introduction of
this_cpu_cpumask_var_ptr().
This converts most of the uses but not all. Christoph will follow up
with the remaining conversions in this merge window and hopefully
remove the obsolete accessors"
* 'for-3.18-consistent-ops' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/percpu: (38 commits)
irqchip: Properly fetch the per cpu offset
percpu: Resolve ambiguities in __get_cpu_var/cpumask_var_t -fix
ia64: sn_nodepda cannot be assigned to after this_cpu conversion. Use __this_cpu_write.
percpu: Resolve ambiguities in __get_cpu_var/cpumask_var_t
Revert "powerpc: Replace __get_cpu_var uses"
percpu: Remove __this_cpu_ptr
clocksource: Replace __this_cpu_ptr with raw_cpu_ptr
sparc: Replace __get_cpu_var uses
avr32: Replace __get_cpu_var with __this_cpu_write
blackfin: Replace __get_cpu_var uses
tile: Use this_cpu_ptr() for hardware counters
tile: Replace __get_cpu_var uses
powerpc: Replace __get_cpu_var uses
alpha: Replace __get_cpu_var
ia64: Replace __get_cpu_var uses
s390: cio driver &__get_cpu_var replacements
s390: Replace __get_cpu_var uses
mips: Replace __get_cpu_var uses
MIPS: Replace __get_cpu_var uses in FPU emulator.
arm: Replace __this_cpu_ptr with raw_cpu_ptr
...
Pull scheduler updates from Ingo Molnar:
"The main changes in this cycle were:
- Optimized support for Intel "Cluster-on-Die" (CoD) topologies (Dave
Hansen)
- Various sched/idle refinements for better idle handling (Nicolas
Pitre, Daniel Lezcano, Chuansheng Liu, Vincent Guittot)
- sched/numa updates and optimizations (Rik van Riel)
- sysbench speedup (Vincent Guittot)
- capacity calculation cleanups/refactoring (Vincent Guittot)
- Various cleanups to thread group iteration (Oleg Nesterov)
- Double-rq-lock removal optimization and various refactorings
(Kirill Tkhai)
- various sched/deadline fixes
... and lots of other changes"
* 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (72 commits)
sched/dl: Use dl_bw_of() under rcu_read_lock_sched()
sched/fair: Delete resched_cpu() from idle_balance()
sched, time: Fix build error with 64 bit cputime_t on 32 bit systems
sched: Improve sysbench performance by fixing spurious active migration
sched/x86: Fix up typo in topology detection
x86, sched: Add new topology for multi-NUMA-node CPUs
sched/rt: Use resched_curr() in task_tick_rt()
sched: Use rq->rd in sched_setaffinity() under RCU read lock
sched: cleanup: Rename 'out_unlock' to 'out_free_new_mask'
sched: Use dl_bw_of() under RCU read lock
sched/fair: Remove duplicate code from can_migrate_task()
sched, mips, ia64: Remove __ARCH_WANT_UNLOCKED_CTXSW
sched: print_rq(): Don't use tasklist_lock
sched: normalize_rt_tasks(): Don't use _irqsave for tasklist_lock, use task_rq_lock()
sched: Fix the task-group check in tg_has_rt_tasks()
sched/fair: Leverage the idle state info when choosing the "idlest" cpu
sched: Let the scheduler see CPU idle states
sched/deadline: Fix inter- exclusive cpusets migrations
sched/deadline: Clear dl_entity params when setscheduling to different class
sched/numa: Kill the wrong/dead TASK_DEAD check in task_numa_fault()
...
Pull core locking updates from Ingo Molnar:
"The main updates in this cycle were:
- mutex MCS refactoring finishing touches: improve comments, refactor
and clean up code, reduce debug data structure footprint, etc.
- qrwlock finishing touches: remove old code, self-test updates.
- small rwsem optimization
- various smaller fixes/cleanups"
* 'locking-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
locking/lockdep: Revert qrwlock recusive stuff
locking/rwsem: Avoid double checking before try acquiring write lock
locking/rwsem: Move EXPORT_SYMBOL() lines to follow function definition
locking/rwlock, x86: Delete unused asm/rwlock.h and rwlock.S
locking/rwlock, x86: Clean up asm/spinlock*.h to remove old rwlock code
locking/semaphore: Resolve some shadow warnings
locking/selftest: Support queued rwlock
locking/lockdep: Restrict the use of recursive read_lock() with qrwlock
locking/spinlocks: Always evaluate the second argument of spin_lock_nested()
locking/Documentation: Update locking/mutex-design.txt disadvantages
locking/Documentation: Move locking related docs into Documentation/locking/
locking/mutexes: Use MUTEX_SPIN_ON_OWNER when appropriate
locking/mutexes: Refactor optimistic spinning code
locking/mcs: Remove obsolete comment
locking/mutexes: Document quick lock release when unlocking
locking/mutexes: Standardize arguments in lock/unlock slowpaths
locking: Remove deprecated smp_mb__() barriers
1. vma_policy_mof(task) is simply not safe unless task == current,
it can race with do_exit()->mpol_put(). Remove this arg and update
its single caller.
2. vma can not be NULL, remove this check and simplify the code.
Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: David Rientjes <rientjes@google.com>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Cyrill Gorcunov <gorcunov@openvz.org>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>
Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Hugh Dickins <hughd@google.com>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Highlights include:
Stable fixes:
- fix an NFSv4.1 state renewal regression
- fix open/lock state recovery error handling
- fix lock recovery when CREATE_SESSION/SETCLIENTID_CONFIRM fails
- fix statd when reconnection fails
- Don't wake tasks during connection abort
- Don't start reboot recovery if lease check fails
- fix duplicate proc entries
Features:
- pNFS block driver fixes and clean ups from Christoph
- More code cleanups from Anna
- Improve mmap() writeback performance
- Replace use of PF_TRANS with a more generic mechanism for avoiding
deadlocks in nfs_release_page
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1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=/OQi
-----END PGP SIGNATURE-----
Merge tag 'nfs-for-3.18-1' of git://git.linux-nfs.org/projects/trondmy/linux-nfs
Pull NFS client updates from Trond Myklebust:
"Highlights include:
Stable fixes:
- fix an NFSv4.1 state renewal regression
- fix open/lock state recovery error handling
- fix lock recovery when CREATE_SESSION/SETCLIENTID_CONFIRM fails
- fix statd when reconnection fails
- don't wake tasks during connection abort
- don't start reboot recovery if lease check fails
- fix duplicate proc entries
Features:
- pNFS block driver fixes and clean ups from Christoph
- More code cleanups from Anna
- Improve mmap() writeback performance
- Replace use of PF_TRANS with a more generic mechanism for avoiding
deadlocks in nfs_release_page"
* tag 'nfs-for-3.18-1' of git://git.linux-nfs.org/projects/trondmy/linux-nfs: (66 commits)
NFSv4.1: Fix an NFSv4.1 state renewal regression
NFSv4: fix open/lock state recovery error handling
NFSv4: Fix lock recovery when CREATE_SESSION/SETCLIENTID_CONFIRM fails
NFS: Fabricate fscache server index key correctly
SUNRPC: Add missing support for RPC_CLNT_CREATE_NO_RETRANS_TIMEOUT
NFSv3: Fix missing includes of nfs3_fs.h
NFS/SUNRPC: Remove other deadlock-avoidance mechanisms in nfs_release_page()
NFS: avoid waiting at all in nfs_release_page when congested.
NFS: avoid deadlocks with loop-back mounted NFS filesystems.
MM: export page_wakeup functions
SCHED: add some "wait..on_bit...timeout()" interfaces.
NFS: don't use STABLE writes during writeback.
NFSv4: use exponential retry on NFS4ERR_DELAY for async requests.
rpc: Add -EPERM processing for xs_udp_send_request()
rpc: return sent and err from xs_sendpages()
lockd: Try to reconnect if statd has moved
SUNRPC: Don't wake tasks during connection abort
Fixing lease renewal
nfs: fix duplicate proc entries
pnfs/blocklayout: Fix a 64-bit division/remainder issue in bl_map_stripe
...
rq->rd is freed using call_rcu_sched(), so rcu_read_lock() to access it
is not enough. We should use either rcu_read_lock_sched() or preempt_disable().
Reported-by: Sasha Levin <sasha.levin@oracle.com>
Suggested-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Kirill Tkhai <ktkhai@parallels.com
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Fixes: 66339c31bc "sched: Use dl_bw_of() under RCU read lock"
Link: http://lkml.kernel.org/r/1412065417.20287.24.camel@tkhai
Signed-off-by: Ingo Molnar <mingo@kernel.org>
We already reschedule env.dst_cpu in attach_tasks()->check_preempt_curr()
if this is necessary.
Furthermore, a higher priority class task may be current on dest rq,
we shouldn't disturb it.
Signed-off-by: Kirill Tkhai <ktkhai@parallels.com>
Cc: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20140930210441.5258.55054.stgit@localhost
Signed-off-by: Ingo Molnar <mingo@kernel.org>
On 32 bit systems cmpxchg cannot handle 64 bit values, so
some additional magic is required to allow a 32 bit system
with CONFIG_VIRT_CPU_ACCOUNTING_GEN=y enabled to build.
Make sure the correct cmpxchg function is used when doing
an atomic swap of a cputime_t.
Reported-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Rik van Riel <riel@redhat.com>
Acked-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: umgwanakikbuti@gmail.com
Cc: fweisbec@gmail.com
Cc: srao@redhat.com
Cc: lwoodman@redhat.com
Cc: atheurer@redhat.com
Cc: oleg@redhat.com
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Paul Mackerras <paulus@samba.org>
Cc: linux390@de.ibm.com
Cc: linux-arch@vger.kernel.org
Cc: linuxppc-dev@lists.ozlabs.org
Cc: linux-s390@vger.kernel.org
Link: http://lkml.kernel.org/r/20140930155947.070cdb1f@annuminas.surriel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Since commit caeb178c60 ("sched/fair: Make update_sd_pick_busiest() ...")
sd_pick_busiest returns a group that can be neither imbalanced nor overloaded
but is only more loaded than others. This change has been introduced to ensure
a better load balance in system that are not overloaded but as a side effect,
it can also generate useless active migration between groups.
Let take the example of 3 tasks on a quad cores system. We will always have an
idle core so the load balance will find a busiest group (core) whenever an ILB
is triggered and it will force an active migration (once above
nr_balance_failed threshold) so the idle core becomes busy but another core
will become idle. With the next ILB, the freshly idle core will try to pull the
task of a busy CPU.
The number of spurious active migration is not so huge in quad core system
because the ILB is not triggered so much. But it becomes significant as soon as
you have more than one sched_domain level like on a dual cluster of quad cores
where the ILB is triggered every tick when you have more than 1 busy_cpu
We need to ensure that the migration generate a real improveùent and will not
only move the avg_load imbalance on another CPU.
Before caeb178c60, the filtering of such use
case was ensured by the following test in f_b_g:
if ((local->idle_cpus < busiest->idle_cpus) &&
busiest->sum_nr_running <= busiest->group_weight)
This patch modified the condition to take into account situation where busiest
group is not overloaded: If the diff between the number of idle cpus in 2
groups is less than or equal to 1 and the busiest group is not overloaded,
moving a task will not improve the load balance but just move it.
A test with sysbench on a dual clusters of quad cores gives the following
results:
command: sysbench --test=cpu --num-threads=5 --max-time=5 run
The HZ is 200 which means that 1000 ticks has fired during the test.
With Mainline, perf gives the following figures:
Samples: 727 of event 'sched:sched_migrate_task'
Event count (approx.): 727
Overhead Command Shared Object Symbol
........ ............... ............. ..............
12.52% migration/1 [unknown] [.] 00000000
12.52% migration/5 [unknown] [.] 00000000
12.52% migration/7 [unknown] [.] 00000000
12.10% migration/6 [unknown] [.] 00000000
11.83% migration/0 [unknown] [.] 00000000
11.83% migration/3 [unknown] [.] 00000000
11.14% migration/4 [unknown] [.] 00000000
10.87% migration/2 [unknown] [.] 00000000
2.75% sysbench [unknown] [.] 00000000
0.83% swapper [unknown] [.] 00000000
0.55% ktps65090charge [unknown] [.] 00000000
0.41% mmcqd/1 [unknown] [.] 00000000
0.14% perf [unknown] [.] 00000000
With this patch, perf gives the following figures
Samples: 20 of event 'sched:sched_migrate_task'
Event count (approx.): 20
Overhead Command Shared Object Symbol
........ ............... ............. ..............
80.00% sysbench [unknown] [.] 00000000
10.00% swapper [unknown] [.] 00000000
5.00% ktps65090charge [unknown] [.] 00000000
5.00% migration/1 [unknown] [.] 00000000
Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org>
Reviewed-by: Rik van Riel <riel@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: http://lkml.kernel.org/r/1412170735-5356-1-git-send-email-vincent.guittot@linaro.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
In commit c1221321b7
sched: Allow wait_on_bit_action() functions to support a timeout
I suggested that a "wait_on_bit_timeout()" interface would not meet my
need. This isn't true - I was just over-engineering.
Including a 'private' field in wait_bit_key instead of a focused
"timeout" field was just premature generalization. If some other
use is ever found, it can be generalized or added later.
So this patch renames "private" to "timeout" with a meaning "stop
waiting when "jiffies" reaches or passes "timeout",
and adds two of the many possible wait..bit..timeout() interfaces:
wait_on_page_bit_killable_timeout(), which is the one I want to use,
and out_of_line_wait_on_bit_timeout() which is a reasonably general
example. Others can be added as needed.
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: NeilBrown <neilb@suse.de>
Acked-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
Peter Zijlstra