add Documentation/sched-design-CFS.txt
Signed-off-by: Ingo Molnar <mingo@elte.hu>

enable CONFIG_SCHED_DEBUG in lib/Kconfig.debug.

the runtime overhead of this option is very small.
Signed-off-by: Ingo Molnar <mingo@elte.hu>

scheduler debugging core: implement /proc/sched_debug and
/proc/<PID>/sched files for scheduler debugging.
Signed-off-by: Ingo Molnar <mingo@elte.hu>

add CFS debug sysctls: only tweakable if SCHED_DEBUG is enabled.
This allows for faster debugging of scheduler problems.
Signed-off-by: Ingo Molnar <mingo@elte.hu>

remove the old cpu-accounting field from signal_struct, now
that the code is using CFS's stats.
Signed-off-by: Ingo Molnar <mingo@elte.hu>

remove unused rq types from sched.c, now that we switched
over to CFS.
Signed-off-by: Ingo Molnar <mingo@elte.hu>

batch_task() in sched.h is now unused - remove it.
Signed-off-by: Ingo Molnar <mingo@elte.hu>

remove now-unused types/fields used by the old scheduler.
Signed-off-by: Ingo Molnar <mingo@elte.hu>

remove now unused interactivity-heuristics related defined and
types of the old scheduler.
Signed-off-by: Ingo Molnar <mingo@elte.hu>

clean up include files in sched.c, they were still old-style <asm/>.
Signed-off-by: Ingo Molnar <mingo@elte.hu>

sched_fork()/sched_exit() does not need to specify fastcall anymore,
as the x86 kernel defaults to regparm3, and no assembly code calls
these functions.
Signed-off-by: Ingo Molnar <mingo@elte.hu>

update delay-accounting to use CFS's precise stats.
Signed-off-by: Ingo Molnar <mingo@elte.hu>

make use of CFS's precise accounting to drive /proc/<pid>/stat statistics.

this code was co-authored by:

 Balbir Singh <balbir@linux.vnet.ibm.com>
 Dmitry Adamushko <dmitry.adamushko@gmail.com>
 Ingo Molnar <mingo@elte.hu>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Dmitry Adamushko <dmitry.adamushko@gmail.com>

make use of sched-clock-unstable events.
Signed-off-by: Ingo Molnar <mingo@elte.hu>

track TSC-unstable events and propagate it to the scheduler code.
Also allow sched_clock() to be used when the TSC is unstable,
the rq_clock() wrapper creates a reliable clock out of it.
Signed-off-by: Ingo Molnar <mingo@elte.hu>

apply the CFS core code.

this change switches over the scheduler core to CFS's modular
design and makes use of kernel/sched_fair/rt/idletask.c to implement
Linux's scheduling policies.

thanks to Andrew Morton and Thomas Gleixner for lots of detailed review
feedback and for fixlets.
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Mike Galbraith <efault@gmx.de>
Signed-off-by: Dmitry Adamushko <dmitry.adamushko@gmail.com>
Signed-off-by: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com>

remove the sleep-bonus interactivity code from the core scheduler.

scheduling policy is implemented in the policy modules, and CFS does
not need such type of heuristics.
Signed-off-by: Ingo Molnar <mingo@elte.hu>

remove the expired_starving() heuristics from the core scheduler.

CFS does not need it, and this did not really work well in practice
anyway, due to the rq->nr_running multiplier to STARVATION_LIMIT.
Signed-off-by: Ingo Molnar <mingo@elte.hu>

remove the sleep_type heuristics from the core scheduler - scheduling
policy is implemented in the scheduling-policy modules. (and CFS does
not use this type of sleep-type heuristics)
Signed-off-by: Ingo Molnar <mingo@elte.hu>

add the new load-calculation methods of CFS.
Signed-off-by: Ingo Molnar <mingo@elte.hu>

clean up: move __normal_prio() in head of normal_prio().

no code changed.
Signed-off-by: Ingo Molnar <mingo@elte.hu>

cleanup: move dequeue/enqueue_task() to a more logical place, to
not split up __normal_prio()/normal_prio().
Signed-off-by: Ingo Molnar <mingo@elte.hu>

move resched_task()/resched_cpu() into the 'public interfaces'
section of sched.c, for use by kernel/sched_fair/rt/idletask.c
Signed-off-by: Ingo Molnar <mingo@elte.hu>

remove the SleepAVG field from /proc/<pid>/status, as
with the removal of the sleep-average code this value
no longer makes sense.
Signed-off-by: Ingo Molnar <mingo@elte.hu>

clean up the rt priority macros, pointed out by Andrew Morton.
Signed-off-by: Ingo Molnar <mingo@elte.hu>

add the set_task_cfs_rq() abstraction needed by CONFIG_FAIR_GROUP_SCHED.

(not activated yet)
Signed-off-by: Ingo Molnar <mingo@elte.hu>

update the posix-cpu-timers code to use CFS's CPU accounting information.
Signed-off-by: Ingo Molnar <mingo@elte.hu>

add rq_clock()/__rq_clock(), a robust wrapper around sched_clock(),
used by CFS. It protects against common type of sched_clock() problems
(caused by hardware): time warps forwards and backwards.
Signed-off-by: Ingo Molnar <mingo@elte.hu>

add the CFS rq data types to sched.c.

(the old scheduler fields are still intact, they are removed
 by a later patch)
Signed-off-by: Ingo Molnar <mingo@elte.hu>

add the CFS data types to sched.h.

(the old scheduler is still fully intact.)
Signed-off-by: Ingo Molnar <mingo@elte.hu>

add kernel/sched_idletask.c - which implements the idle thread
scheduling class. This further simplifies sched.c (under CFS),
for example a number of 'if (p == rq->idle)' type of special-cases
can be removed from sched.c, and schedule() gets simpler too.
Signed-off-by: Ingo Molnar <mingo@elte.hu>

add kernel/sched_rt.c: SCHED_FIFO/SCHED_RR support. The behavior
and semantics of SCHED_FIFO/SCHED_RR tasks is unchanged.
Signed-off-by: Ingo Molnar <mingo@elte.hu>

add kernel/sched_fair.c - which implements the bulk of CFS's
behavioral changes for SCHED_OTHER tasks.

see Documentation/sched-design-CFS.txt about details.

Authors:

 Ingo Molnar <mingo@elte.hu>
 Dmitry Adamushko <dmitry.adamushko@gmail.com>
 Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com>
 Mike Galbraith <efault@gmx.de>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Mike Galbraith <efault@gmx.de>
Signed-off-by: Dmitry Adamushko <dmitry.adamushko@gmail.com>
Signed-off-by: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com>

increase SMP-nice's resolution. This is needed by CFS to
implement SCHED_IDLE and cleaned up nice level support.

no behavioral changes.
Signed-off-by: Ingo Molnar <mingo@elte.hu>

create sched_stats.h and move sched.c schedstats code into it.
This cleans up sched.c a bit.

no code changes are caused by this patch.
Signed-off-by: Ingo Molnar <mingo@elte.hu>

add the init_idle_bootup_task() callback to the bootup thread,
unused at the moment. (CFS will use it to switch the scheduling
class of the boot thread to the idle class)
Signed-off-by: Ingo Molnar <mingo@elte.hu>

add in_atomic_preempt_off() - debugging helper that will
simplify schedule().
Signed-off-by: Ingo Molnar <mingo@elte.hu>

remove sched_exit(): the elaborate dance of us trying to recover
timeslices given to child tasks never really worked.

CFS does not need it either.
Signed-off-by: Ingo Molnar <mingo@elte.hu>

uninline set_task_cpu(): CFS will add more code to it.
Signed-off-by: Ingo Molnar <mingo@elte.hu>

the SMP load-balancer uses the boot-time migration-cost estimation
code to attempt to improve the quality of balancing. The reason for
this code is that the discrete priority queues do not preserve
the order of scheduling accurately, so the load-balancer skips
tasks that were running on a CPU 'recently'.

this code is fundamental fragile: the boot-time migration cost detector
doesnt really work on systems that had large L3 caches, it caused boot
delays on large systems and the whole cache-hot concept made the
balancing code pretty undeterministic as well.

(and hey, i wrote most of it, so i can say it out loud that it sucks ;-)

under CFS the same purpose of cache affinity can be achieved without
any special cache-hot special-case: tasks are sorted in the 'timeline'
tree and the SMP balancer picks tasks from the left side of the
tree, thus the most cache-cold task is balanced automatically.
Signed-off-by: Ingo Molnar <mingo@elte.hu>