linux/kernel
Tejun Heo 969c79215a sched: replace migration_thread with cpu_stop
Currently migration_thread is serving three purposes - migration
pusher, context to execute active_load_balance() and forced context
switcher for expedited RCU synchronize_sched.  All three roles are
hardcoded into migration_thread() and determining which job is
scheduled is slightly messy.

This patch kills migration_thread and replaces all three uses with
cpu_stop.  The three different roles of migration_thread() are
splitted into three separate cpu_stop callbacks -
migration_cpu_stop(), active_load_balance_cpu_stop() and
synchronize_sched_expedited_cpu_stop() - and each use case now simply
asks cpu_stop to execute the callback as necessary.

synchronize_sched_expedited() was implemented with private
preallocated resources and custom multi-cpu queueing and waiting
logic, both of which are provided by cpu_stop.
synchronize_sched_expedited_count is made atomic and all other shared
resources along with the mutex are dropped.

synchronize_sched_expedited() also implemented a check to detect cases
where not all the callback got executed on their assigned cpus and
fall back to synchronize_sched().  If called with cpu hotplug blocked,
cpu_stop already guarantees that and the condition cannot happen;
otherwise, stop_machine() would break.  However, this patch preserves
the paranoid check using a cpumask to record on which cpus the stopper
ran so that it can serve as a bisection point if something actually
goes wrong theree.

Because the internal execution state is no longer visible,
rcu_expedited_torture_stats() is removed.

This patch also renames cpu_stop threads to from "stopper/%d" to
"migration/%d".  The names of these threads ultimately don't matter
and there's no reason to make unnecessary userland visible changes.

With this patch applied, stop_machine() and sched now share the same
resources.  stop_machine() is faster without wasting any resources and
sched migration users are much cleaner.

Signed-off-by: Tejun Heo <tj@kernel.org>
Acked-by: Peter Zijlstra <peterz@infradead.org>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Dipankar Sarma <dipankar@in.ibm.com>
Cc: Josh Triplett <josh@freedesktop.org>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Dimitri Sivanich <sivanich@sgi.com>
2010-05-06 18:49:21 +02:00
..
gcov
irq Merge branch 'irq-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip 2010-04-06 13:03:22 -07:00
power PM / Hibernate: user.c, fix SNAPSHOT_SET_SWAP_AREA handling 2010-04-10 22:28:56 +02:00
time Merge branch 'linus' into sched/core 2010-04-15 09:36:16 +02:00
trace Merge branch 'master' into export-slabh 2010-04-05 11:37:28 +09:00
.gitignore
acct.c copy_signal() cleanup: kill taskstats_tgid_init() and acct_init_pacct() 2010-03-12 15:52:39 -08:00
async.c include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h 2010-03-30 22:02:32 +09:00
audit_tree.c include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h 2010-03-30 22:02:32 +09:00
audit_watch.c include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h 2010-03-30 22:02:32 +09:00
audit.c include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h 2010-03-30 22:02:32 +09:00
audit.h
auditfilter.c include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h 2010-03-30 22:02:32 +09:00
auditsc.c audit: preface audit printk with audit 2010-04-05 13:19:45 -07:00
backtracetest.c
bounds.c
capability.c sched: Remove remaining USER_SCHED code 2010-04-02 20:12:00 +02:00
cgroup_freezer.c Merge branch 'master' into export-slabh 2010-04-05 11:37:28 +09:00
cgroup.c cgroups: remove duplicate include 2010-03-24 16:31:19 -07:00
compat.c include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h 2010-03-30 22:02:32 +09:00
configs.c
cpu.c stop_machine: reimplement using cpu_stop 2010-05-06 18:49:20 +02:00
cpuset.c sched: Make select_fallback_rq() cpuset friendly 2010-04-02 20:12:03 +02:00
cred.c Merge branch 'linus' into sched/core 2010-04-15 09:36:16 +02:00
delayacct.c
dma.c
early_res.c x86: Do not free zero sized per cpu areas 2010-03-29 18:55:40 +02:00
elfcore.c elf coredump: add extended numbering support 2010-03-06 11:26:46 -08:00
exec_domain.c
exit.c Merge branch 'linus' into sched/core 2010-04-15 09:36:16 +02:00
extable.c
fork.c mm: avoid null-pointer deref in sync_mm_rss() 2010-04-07 08:38:02 -07:00
freezer.c
futex_compat.c
futex.c
groups.c
hrtimer.c
hung_task.c
hw_breakpoint.c Merge branch 'perf/core' into perf/urgent 2010-03-04 11:47:52 +01:00
itimer.c
kallsyms.c include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h 2010-03-30 22:02:32 +09:00
Kconfig.freezer
Kconfig.hz
Kconfig.locks
Kconfig.preempt
kexec.c percpu: add __percpu sparse annotations to core kernel subsystems 2010-02-17 11:17:38 +09:00
kfifo.c kfifo: Don't use integer as NULL pointer 2010-02-16 15:11:08 -08:00
kgdb.c kgdb: Turn off tracing while in the debugger 2010-04-02 14:58:19 -05:00
kmod.c
kprobes.c kprobes: Calculate the index correctly when freeing the out-of-line execution slot 2010-03-11 14:06:16 +01:00
ksysfs.c Merge branch 'for-next' into for-linus 2010-03-08 16:55:37 +01:00
kthread.c cpuset: fix the problem that cpuset_mem_spread_node() returns an offline node 2010-03-24 16:31:21 -07:00
latencytop.c include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h 2010-03-30 22:02:32 +09:00
lockdep_internals.h
lockdep_proc.c
lockdep_states.h
lockdep.c Merge branch 'slabh' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/misc 2010-04-05 09:39:11 -07:00
Makefile elf coredump: replace ELF_CORE_EXTRA_* macros by functions 2010-03-06 11:26:45 -08:00
module.c stop_machine: reimplement using cpu_stop 2010-05-06 18:49:20 +02:00
mutex-debug.c
mutex-debug.h
mutex.c
mutex.h
notifier.c sched: Use lockdep-based checking on rcu_dereference() 2010-02-25 10:34:26 +01:00
ns_cgroup.c
nsproxy.c include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h 2010-03-30 22:02:32 +09:00
padata.c include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h 2010-03-30 22:02:32 +09:00
panic.c panic: fix panic_timeout accuracy when running on a hypervisor 2010-03-06 11:26:33 -08:00
params.c Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/jikos/trivial 2010-03-12 16:04:50 -08:00
perf_event.c Merge branch 'master' into export-slabh 2010-04-05 11:37:28 +09:00
pid_namespace.c include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h 2010-03-30 22:02:32 +09:00
pid.c Merge branch 'core-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip 2010-03-13 14:43:01 -08:00
pm_qos_params.c
posix-cpu-timers.c Merge branch 'timers-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip 2010-03-26 15:10:38 -07:00
posix-timers.c
printk.c printk: avoid warning when CONFIG_PRINTK is disabled 2010-03-06 11:26:33 -08:00
profile.c
ptrace.c ptrace: Fix ptrace_regset() comments and diagnose errors specifically 2010-02-23 13:45:26 -08:00
range.c
rcupdate.c rcu: Make rcu_read_lock_bh_held() allow for disabled BH 2010-03-16 09:57:49 +01:00
rcutiny.c
rcutorture.c sched: replace migration_thread with cpu_stop 2010-05-06 18:49:21 +02:00
rcutree_plugin.h rcu: Fix holdoff for accelerated GPs for last non-dynticked CPU 2010-02-28 09:17:42 +01:00
rcutree_trace.c rcu: Stop overflowing signed integers 2010-02-25 10:34:57 +01:00
rcutree.c rcu: Fix accelerated grace periods for last non-dynticked CPU 2010-02-27 09:53:52 +01:00
rcutree.h rcu: Increase RCU CPU stall timeouts if PROVE_RCU 2010-03-11 13:38:01 +01:00
relay.c splice: comparing unsigned int < 0 2010-03-06 11:26:32 -08:00
res_counter.c include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h 2010-03-30 22:02:32 +09:00
resource.c resources: add interfaces that return conflict information 2010-03-23 13:33:50 -07:00
rtmutex_common.h
rtmutex-debug.c
rtmutex-debug.h
rtmutex-tester.c
rtmutex.c
rtmutex.h
rwsem.c
sched_clock.c
sched_cpupri.c include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h 2010-03-30 22:02:32 +09:00
sched_cpupri.h
sched_debug.c Merge branch 'linus' into sched/core 2010-04-15 09:36:16 +02:00
sched_fair.c sched: replace migration_thread with cpu_stop 2010-05-06 18:49:21 +02:00
sched_features.h sched: Remove ASYM_GRAN feature 2010-03-11 18:32:53 +01:00
sched_idletask.c sched: Cure load average vs NO_HZ woes 2010-04-23 11:02:02 +02:00
sched_rt.c sched: Add enqueue/dequeue flags 2010-04-02 20:12:05 +02:00
sched_stats.h
sched.c sched: replace migration_thread with cpu_stop 2010-05-06 18:49:21 +02:00
seccomp.c
semaphore.c
signal.c kernel core: use helpers for rlimits 2010-03-06 11:26:33 -08:00
slow-work-debugfs.c
slow-work.c slow-work: use get_ref wrapper instead of directly calling get_ref 2010-03-29 09:13:30 -07:00
slow-work.h SLOW_WORK: CONFIG_SLOW_WORK_PROC should be CONFIG_SLOW_WORK_DEBUG 2010-03-29 09:14:47 -07:00
smp.c include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h 2010-03-30 22:02:32 +09:00
softirq.c
softlockup.c softlockup: Stop spurious softlockup messages due to overflow 2010-03-21 19:30:13 +01:00
spinlock.c
srcu.c include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h 2010-03-30 22:02:32 +09:00
stacktrace.c
stop_machine.c sched: replace migration_thread with cpu_stop 2010-05-06 18:49:21 +02:00
sys_ni.c Add generic sys_ipc wrapper 2010-03-12 15:52:32 -08:00
sys.c include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h 2010-03-30 22:02:32 +09:00
sysctl_binary.c include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h 2010-03-30 22:02:32 +09:00
sysctl_check.c
sysctl.c sysctl extern cleanup: lockdep 2010-03-12 15:53:10 -08:00
taskstats.c include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h 2010-03-30 22:02:32 +09:00
test_kprobes.c
time.c include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h 2010-03-30 22:02:32 +09:00
timeconst.pl
timer.c include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h 2010-03-30 22:02:32 +09:00
tracepoint.c
tsacct.c mm: clean up mm_counter 2010-03-06 11:26:23 -08:00
uid16.c
up.c
user_namespace.c
user-return-notifier.c
user.c sched: Remove remaining USER_SCHED code 2010-04-02 20:12:00 +02:00
utsname_sysctl.c
utsname.c
wait.c
workqueue.c