The efficiency of suspend-to-idle depends on being able to keep CPUs
in the deepest available idle states for as much time as possible.
Ideally, they should only be brought out of idle by system wakeup
interrupts.
However, timer interrupts occurring periodically prevent that from
happening and it is not practical to chase all of the "misbehaving"
timers in a whack-a-mole fashion. A much more effective approach is
to suspend the local ticks for all CPUs and the entire timekeeping
along the lines of what is done during full suspend, which also
helps to keep suspend-to-idle and full suspend reasonably similar.
The idea is to suspend the local tick on each CPU executing
cpuidle_enter_freeze() and to make the last of them suspend the
entire timekeeping. That should prevent timer interrupts from
triggering until an IO interrupt wakes up one of the CPUs. It
needs to be done with interrupts disabled on all of the CPUs,
though, because otherwise the suspended clocksource might be
accessed by an interrupt handler which might lead to fatal
consequences.
Unfortunately, the existing ->enter callbacks provided by cpuidle
drivers generally cannot be used for implementing that, because some
of them re-enable interrupts temporarily and some idle entry methods
cause interrupts to be re-enabled automatically on exit. Also some
of these callbacks manipulate local clock event devices of the CPUs
which really shouldn't be done after suspending their ticks.
To overcome that difficulty, introduce a new cpuidle state callback,
->enter_freeze, that will be guaranteed (1) to keep interrupts
disabled all the time (and return with interrupts disabled) and (2)
not to touch the CPU timer devices. Modify cpuidle_enter_freeze() to
look for the deepest available idle state with ->enter_freeze present
and to make the CPU execute that callback with suspended tick (and the
last of the online CPUs to execute it with suspended timekeeping).
Suggested-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Pull s390 updates from Martin Schwidefsky:
"This patch set contains the main portion of the changes for 3.18 in
regard to the s390 architecture. It is a bit bigger than usual,
mainly because of a new driver and the vector extension patches.
The interesting bits are:
- Quite a bit of work on the tracing front. Uprobes is enabled and
the ftrace code is reworked to get some of the lost performance
back if CONFIG_FTRACE is enabled.
- To improve boot time with CONFIG_DEBIG_PAGEALLOC, support for the
IPTE range facility is added.
- The rwlock code is re-factored to improve writer fairness and to be
able to use the interlocked-access instructions.
- The kernel part for the support of the vector extension is added.
- The device driver to access the CD/DVD on the HMC is added, this
will hopefully come in handy to improve the installation process.
- Add support for control-unit initiated reconfiguration.
- The crypto device driver is enhanced to enable the additional AP
domains and to allow the new crypto hardware to be used.
- Bug fixes"
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/s390/linux: (39 commits)
s390/ftrace: simplify enabling/disabling of ftrace_graph_caller
s390/ftrace: remove 31 bit ftrace support
s390/kdump: add support for vector extension
s390/disassembler: add vector instructions
s390: add support for vector extension
s390/zcrypt: Toleration of new crypto hardware
s390/idle: consolidate idle functions and definitions
s390/nohz: use a per-cpu flag for arch_needs_cpu
s390/vtime: do not reset idle data on CPU hotplug
s390/dasd: add support for control unit initiated reconfiguration
s390/dasd: fix infinite loop during format
s390/mm: make use of ipte range facility
s390/setup: correct 4-level kernel page table detection
s390/topology: call set_sched_topology early
s390/uprobes: architecture backend for uprobes
s390/uprobes: common library for kprobes and uprobes
s390/rwlock: use the interlocked-access facility 1 instructions
s390/rwlock: improve writer fairness
s390/rwlock: remove interrupt-enabling rwlock variant.
s390/mm: remove change bit override support
...
Move the nohz_delay bit from the s390_idle data structure to the
per-cpu flags. Clear the nohz delay flag in __cpu_disable and
remove the cpu hotplug notifier that used to do this.
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
This way we unbloat a bit main.c and more importantly we initialize
nohz full after init_IRQ(). This dependency will be needed in further
patches because nohz full needs irq work to raise its own IRQ.
Information about the support for this ability on ARM64 is obtained on
init_IRQ() which initialize the pointer to __smp_call_function.
Since tick_init() is called right after init_IRQ(), this is a good place
to call tick_nohz_init() and prepare for that dependency.
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
The local nohz kick is currently used by perf which needs it to be
NMI-safe. Recent commit though (7d1311b93e)
changed its implementation to fire the local kick using the remote kick
API. It was convenient to make the code more generic but the remote kick
isn't NMI-safe.
As a result:
WARNING: CPU: 3 PID: 18062 at kernel/irq_work.c:72 irq_work_queue_on+0x11e/0x140()
CPU: 3 PID: 18062 Comm: trinity-subchil Not tainted 3.16.0+ #34
0000000000000009 00000000903774d1 ffff880244e06c00 ffffffff9a7f1e37
0000000000000000 ffff880244e06c38 ffffffff9a0791dd ffff880244fce180
0000000000000003 ffff880244e06d58 ffff880244e06ef8 0000000000000000
Call Trace:
<NMI> [<ffffffff9a7f1e37>] dump_stack+0x4e/0x7a
[<ffffffff9a0791dd>] warn_slowpath_common+0x7d/0xa0
[<ffffffff9a07930a>] warn_slowpath_null+0x1a/0x20
[<ffffffff9a17ca1e>] irq_work_queue_on+0x11e/0x140
[<ffffffff9a10a2c7>] tick_nohz_full_kick_cpu+0x57/0x90
[<ffffffff9a186cd5>] __perf_event_overflow+0x275/0x350
[<ffffffff9a184f80>] ? perf_event_task_disable+0xa0/0xa0
[<ffffffff9a01a4cf>] ? x86_perf_event_set_period+0xbf/0x150
[<ffffffff9a187934>] perf_event_overflow+0x14/0x20
[<ffffffff9a020386>] intel_pmu_handle_irq+0x206/0x410
[<ffffffff9a0b54d3>] ? arch_vtime_task_switch+0x63/0x130
[<ffffffff9a01937b>] perf_event_nmi_handler+0x2b/0x50
[<ffffffff9a007b72>] nmi_handle+0xd2/0x390
[<ffffffff9a007aa5>] ? nmi_handle+0x5/0x390
[<ffffffff9a0d131b>] ? lock_release+0xab/0x330
[<ffffffff9a008062>] default_do_nmi+0x72/0x1c0
[<ffffffff9a0c925f>] ? cpuacct_account_field+0xcf/0x200
[<ffffffff9a008268>] do_nmi+0xb8/0x100
Lets fix this by restoring the use of local irq work for the nohz local
kick.
Reported-by: Catalin Iacob <iacobcatalin@gmail.com>
Reported-and-tested-by: Dave Jones <davej@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Pull scheduler updates from Ingo Molnar:
- Move the nohz kick code out of the scheduler tick to a dedicated IPI,
from Frederic Weisbecker.
This necessiated quite some background infrastructure rework,
including:
* Clean up some irq-work internals
* Implement remote irq-work
* Implement nohz kick on top of remote irq-work
* Move full dynticks timer enqueue notification to new kick
* Move multi-task notification to new kick
* Remove unecessary barriers on multi-task notification
- Remove proliferation of wait_on_bit() action functions and allow
wait_on_bit_action() functions to support a timeout. (Neil Brown)
- Another round of sched/numa improvements, cleanups and fixes. (Rik
van Riel)
- Implement fast idling of CPUs when the system is partially loaded,
for better scalability. (Tim Chen)
- Restructure and fix the CPU hotplug handling code that may leave
cfs_rq and rt_rq's throttled when tasks are migrated away from a dead
cpu. (Kirill Tkhai)
- Robustify the sched topology setup code. (Peterz Zijlstra)
- Improve sched_feat() handling wrt. static_keys (Jason Baron)
- Misc fixes.
* 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (37 commits)
sched/fair: Fix 'make xmldocs' warning caused by missing description
sched: Use macro for magic number of -1 for setparam
sched: Robustify topology setup
sched: Fix sched_setparam() policy == -1 logic
sched: Allow wait_on_bit_action() functions to support a timeout
sched: Remove proliferation of wait_on_bit() action functions
sched/numa: Revert "Use effective_load() to balance NUMA loads"
sched: Fix static_key race with sched_feat()
sched: Remove extra static_key*() function indirection
sched/rt: Fix replenish_dl_entity() comments to match the current upstream code
sched: Transform resched_task() into resched_curr()
sched/deadline: Kill task_struct->pi_top_task
sched: Rework check_for_tasks()
sched/rt: Enqueue just unthrottled rt_rq back on the stack in __disable_runtime()
sched/fair: Disable runtime_enabled on dying rq
sched/numa: Change scan period code to match intent
sched/numa: Rework best node setting in task_numa_migrate()
sched/numa: Examine a task move when examining a task swap
sched/numa: Simplify task_numa_compare()
sched/numa: Use effective_load() to balance NUMA loads
...
Binding the grace-period kthreads to the timekeeping CPU resulted in
significant performance decreases for some workloads. For more detail,
see:
https://lkml.org/lkml/2014/6/3/395 for benchmark numbers
https://lkml.org/lkml/2014/6/4/218 for CPU statistics
It turns out that it is necessary to bind the grace-period kthreads
to the timekeeping CPU only when all but CPU 0 is a nohz_full CPU
on the one hand or if CONFIG_NO_HZ_FULL_SYSIDLE=y on the other.
In other cases, it suffices to bind the grace-period kthreads to the
set of non-nohz_full CPUs.
This commit therefore creates a tick_nohz_not_full_mask that is the
complement of tick_nohz_full_mask, and then binds the grace-period
kthread to the set of CPUs indicated by this new mask, which covers
the CONFIG_NO_HZ_FULL_SYSIDLE=n case. The CONFIG_NO_HZ_FULL_SYSIDLE=y
case still binds the grace-period kthreads to the timekeeping CPU.
This commit also includes the tick_nohz_full_enabled() check suggested
by Frederic Weisbecker.
Reported-by: Jet Chen <jet.chen@intel.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
[ paulmck: Created housekeeping_affine() and housekeeping_mask per
fweisbec feedback. ]
Remotely kicking a full nohz CPU in order to make it re-evaluate its
next tick is currently implemented using the scheduler IPI.
However this bloats a scheduler fast path with an off-topic feature.
The scheduler tick was abused here for its cool "callable
anywhere/anytime" properties.
But now that the irq work subsystem can queue remote callbacks, it's
a perfect fit to safely queue IPIs when interrupts are disabled
without worrying about concurrent callers.
So lets implement remote kick on top of irq work. This is going to
be used when a new event requires the next tick to be recalculated:
more than 1 task competing on the CPU, timer armed, ...
Acked-by: Peter Zijlstra <peterz@infradead.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Kevin Hilman <khilman@linaro.org>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Viresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
A few functions use remote per CPU access APIs when they
deal with local values.
Just do the right conversion to improve performance, code
readability and debug checks.
While at it, lets extend some of these function names with *_this_cpu()
suffix in order to display their purpose more clearly.
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Pull nohz improvements from Frederic Weisbecker:
" It mostly contains fixes and full dynticks off-case optimizations. I believe that
distros want to enable this feature so it seems important to optimize the case
where the "nohz_full=" parameter is empty. ie: I'm trying to remove any performance
regression that comes with NO_HZ_FULL=y when the feature is not used.
This patchset improves the current situation a lot (off-case appears to be around 11% faster
with hackbench, although I guess it may vary depending on the configuration but it should be
significantly faster in any case) now there is still some work to do: I can still observe a
remaining loss of 1.6% throughput seen with hackbench compared to CONFIG_NO_HZ_FULL=n. "
Signed-off-by: Ingo Molnar <mingo@kernel.org>
We are planning to convert the dynticks Kconfig options layout
into a choice menu. The user must be able to easily pick
any of the following implementations: constant periodic tick,
idle dynticks, full dynticks.
As this implies a mutual exclusion, the two dynticks implementions
need to converge on the selection of a common Kconfig option in order
to ease the sharing of a common infrastructure.
It would thus seem pretty natural to reuse CONFIG_NO_HZ to
that end. It already implements all the idle dynticks code
and the full dynticks depends on all that code for now.
So ideally the choice menu would propose CONFIG_NO_HZ_IDLE and
CONFIG_NO_HZ_EXTENDED then both would select CONFIG_NO_HZ.
On the other hand we want to stay backward compatible: if
CONFIG_NO_HZ is set in an older config file, we want to
enable CONFIG_NO_HZ_IDLE by default.
But we can't afford both at the same time or we run into
a circular dependency:
1) CONFIG_NO_HZ_IDLE and CONFIG_NO_HZ_EXTENDED both select
CONFIG_NO_HZ
2) If CONFIG_NO_HZ is set, we default to CONFIG_NO_HZ_IDLE
We might be able to support that from Kconfig/Kbuild but it
may not be wise to introduce such a confusing behaviour.
So to solve this, create a new CONFIG_NO_HZ_COMMON option
which gathers the common code between idle and full dynticks
(that common code for now is simply the idle dynticks code)
and select it from their referring Kconfig.
Then we'll later create CONFIG_NO_HZ_IDLE and map CONFIG_NO_HZ
to it for backward compatibility.
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Chris Metcalf <cmetcalf@tilera.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: Geoff Levand <geoff@infradead.org>
Cc: Gilad Ben Yossef <gilad@benyossef.com>
Cc: Hakan Akkan <hakanakkan@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Kevin Hilman <khilman@linaro.org>
Cc: Li Zhong <zhong@linux.vnet.ibm.com>
Cc: Namhyung Kim <namhyung.kim@lge.com>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Paul Gortmaker <paul.gortmaker@windriver.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
For extreme usecases such as Real Time or HPC, having
the ability to shutdown the tick when a single task runs
on a CPU is a desired feature:
* Reducing the amount of interrupts improves throughput
for CPU-bound tasks. The CPU is less distracted from its
real job, from an execution time and from the cache point
of views.
* This also improve latency response as we have less critical
sections.
Start with introducing a very simple interface to define
full dynticks CPU: use a boot time option defined cpumask
through the "nohz_extended=" kernel parameter. CPUs that
are part of this range will have their tick shutdown
whenever possible: provided they run a single task and
they don't do kernel activity that require the periodic
tick. These details will be later documented in
Documentation/*
An online CPU must be kept outside this range to handle the
timekeeping.
Suggested-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Chris Metcalf <cmetcalf@tilera.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: Geoff Levand <geoff@infradead.org>
Cc: Gilad Ben Yossef <gilad@benyossef.com>
Cc: Hakan Akkan <hakanakkan@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Kevin Hilman <khilman@linaro.org>
Cc: Li Zhong <zhong@linux.vnet.ibm.com>
Cc: Namhyung Kim <namhyung.kim@lge.com>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Paul Gortmaker <paul.gortmaker@windriver.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Conflicts:
kernel/irq_work.c
Add support for printk in full dynticks CPU.
* Don't stop tick with irq works pending. This
fix is generally useful and concerns archs that
can't raise self IPIs.
* Flush irq works before CPU offlining.
* Introduce "lazy" irq works that can wait for the
next tick to be executed, unless it's stopped.
* Implement klogd wake up using irq work. This
removes the ad-hoc printk_tick()/printk_needs_cpu()
hooks and make it working even in dynticks mode.
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
