linux-toradex.git/include/linux/cpu.h, branch v3.2-rt10

workqueue: Fix cpuhotplug trainwreck

2012-01-16T19:00:32+00:00

The current workqueue code does crazy stuff on cpu unplug, it relies on
forced affine breakage, thereby violating per-cpu expectations. Worse,
it tries to re-attach to a cpu if the thing comes up again before all
previously queued works are finished. This breaks (admittedly bonkers)
cpu-hotplug use that relies on a down-up cycle to push all usage away.

Introduce a new WQ_NON_AFFINE flag that indicates a per-cpu workqueue
will not respect cpu affinity and use this to migrate all its pending
works to whatever cpu is doing cpu-down.

This also adds a warning for queue_on_cpu() users which warns when its
used on WQ_NON_AFFINE workqueues for the API implies you care about
what cpu things are ran on when such workqueues cannot guarantee this.

For the rest, simply flush all per-cpu works and don't mess about.
This also means that currently all workqueues that are manually
flushing things on cpu-down in order to provide the per-cpu guarantee
no longer need to do so.

In short, we tell the WQ what we want it to do, provide validation for
this and loose ~250 lines of code.

Signed-off-by: Peter Zijlstra 
Signed-off-by: Thomas Gleixner

hotplug: Lightweight get online cpus

2012-01-16T19:00:24+00:00

get_online_cpus() is a heavy weight function which involves a global
mutex. migrate_disable() wants a simpler construct which prevents only
a CPU from going doing while a task is in a migrate disabled section.

Implement a per cpu lockless mechanism, which serializes only in the
real unplug case on a global mutex. That serialization affects only
tasks on the cpu which should be brought down.

Signed-off-by: Thomas Gleixner

PM / Sleep: Remove unused symbol 'suspend_cpu_hotplug'

2011-11-04T21:28:09+00:00

Remove the suspend_cpu_hotplug declaration, which doesn't correspond
to an existing variable.

[rjw: Added the changelog.]

Signed-off-by: Srivatsa S. Bhat 
Signed-off-by: Rafael J. Wysocki

notifiers: cpu: move cpu notifiers into cpu.h

2011-07-26T03:57:14+00:00

We presently define all kinds of notifiers in notifier.h.  This is not
necessary at all, since different subsystems use different notifiers, they
are almost non-related with each other.

This can also save much build time.  Suppose I add a new netdevice event,
really I don't have to recompile all the source, just network related.
Without this patch, all the source will be recompiled.

I move the notify events near to their subsystem notifier registers, so
that they can be found more easily.

This patch:

It is not necessary to share the same notifier.h.

Signed-off-by: WANG Cong 
Cc: David Miller 
Cc: "Rafael J. Wysocki" 
Cc: Greg KH 
Signed-off-by: Andrew Morton 
Signed-off-by: Linus Torvalds

driver core: prune docs about device_interface

2010-11-11T00:57:11+00:00

drivers/base/intf.c was removed before the beginning of (git) time but
its Documentation stuck around.  Remove it.

Signed-off-by: Brandon Philips 
Signed-off-by: Greg Kroah-Hartman

workqueue: reimplement CPU hotplugging support using trustee

2010-06-29T08:07:12+00:00

Reimplement CPU hotplugging support using trustee thread.  On CPU
down, a trustee thread is created and each step of CPU down is
executed by the trustee and workqueue_cpu_callback() simply drives and
waits for trustee state transitions.

CPU down operation no longer waits for works to be drained but trustee
sticks around till all pending works have been completed.  If CPU is
brought back up while works are still draining,
workqueue_cpu_callback() tells trustee to step down and tell workers
to rebind to the cpu.

As it's difficult to tell whether cwqs are empty if it's freezing or
frozen, trustee doesn't consider draining to be complete while a gcwq
is freezing or frozen (tracked by new GCWQ_FREEZING flag).  Also,
workers which get unbound from their cpu are marked with WORKER_ROGUE.

Trustee based implementation doesn't bring any new feature at this
point but it will be used to manage worker pool when dynamic shared
worker pool is implemented.

Signed-off-by: Tejun Heo

sched: adjust when cpu_active and cpuset configurations are updated during cpu on/offlining

2010-06-08T19:40:36+00:00

Currently, when a cpu goes down, cpu_active is cleared before
CPU_DOWN_PREPARE starts and cpuset configuration is updated from a
default priority cpu notifier.  When a cpu is coming up, it's set
before CPU_ONLINE but cpuset configuration again is updated from the
same cpu notifier.

For cpu notifiers, this presents an inconsistent state.  Threads which
a CPU_DOWN_PREPARE notifier expects to be bound to the CPU can be
migrated to other cpus because the cpu is no more inactive.

Fix it by updating cpu_active in the highest priority cpu notifier and
cpuset configuration in the second highest when a cpu is coming up.
Down path is updated similarly.  This guarantees that all other cpu
notifiers see consistent cpu_active and cpuset configuration.

cpuset_track_online_cpus() notifier is converted to
cpuset_update_active_cpus() which just updates the configuration and
now called from cpuset_cpu_[in]active() notifiers registered from
sched_init_smp().  If cpuset is disabled, cpuset_update_active_cpus()
degenerates into partition_sched_domains() making separate notifier
for !CONFIG_CPUSETS unnecessary.

This problem is triggered by cmwq.  During CPU_DOWN_PREPARE, hotplug
callback creates a kthread and kthread_bind()s it to the target cpu,
and the thread is expected to run on that cpu.

* Ingo's test discovered __cpuinit/exit markups were incorrect.
  Fixed.

Signed-off-by: Tejun Heo 
Acked-by: Peter Zijlstra 
Cc: Rusty Russell 
Cc: Ingo Molnar 
Cc: Paul Menage

sched: define and use CPU_PRI_* enums for cpu notifier priorities

2010-06-08T19:40:36+00:00

Instead of hardcoding priority 10 and 20 in sched and perf, collect
them into CPU_PRI_* enums.

Signed-off-by: Tejun Heo 
Acked-by: Peter Zijlstra 
Cc: Rusty Russell 
Cc: Paul Mackerras 
Cc: Ingo Molnar 
Cc: Arnaldo Carvalho de Melo

powerpc/pseries: Serialize cpu hotplug operations during deactivate Vs deallocate

2009-12-09T06:09:36+00:00

Currently the cpu-allocation/deallocation process comprises of two steps:
- Set the indicators and to update the device tree with DLPAR node
  information.

- Online/offline the allocated/deallocated CPU.

This is achieved by writing to the sysfs tunables "probe" during allocation
and "release" during deallocation.

At the sametime, the userspace can independently online/offline the CPUs of
the system using the sysfs tunable "online".

It is quite possible that when a userspace tool offlines a CPU
for the purpose of deallocation and is in the process of updating the device
tree, some other userspace tool could bring the CPU back online by writing to
the "online" sysfs tunable thereby causing the deallocate process to fail.

The solution to this is to serialize writes to the "probe/release" sysfs
tunable with the writes to the "online" sysfs tunable.

This patch employs a mutex to provide this serialization, which is a no-op on
all architectures except PPC_PSERIES

Signed-off-by: Gautham R Shenoy 
Acked-by: Vaidyanathan Srinivasan 
Signed-off-by: Benjamin Herrenschmidt

sysfs/cpu: Add probe/release files

2009-12-09T06:09:33+00:00

Version 3 of this patch is updated with documentation added to
Documentation/ABI.  There are no changes to any of the C code from v2
of the patch.

In order to support kernel DLPAR of CPU resources we need to provide an
interface to add (probe) and remove (release) the resource from the system.
This patch Creates new generic probe and release sysfs files to facilitate
cpu probe/release.  The probe/release interface provides for allowing each
arch to supply their own routines for implementing the backend of adding
and removing cpus to/from the system.

This also creates the powerpc specific stubs to handle the arch callouts
from writes to the sysfs files.

The creation and use of these files is regulated by the
CONFIG_ARCH_CPU_PROBE_RELEASE option so that only architectures that need the
capability will have the files created.

Signed-off-by: Nathan Fontenot 
Signed-off-by: Benjamin Herrenschmidt