kernel_optimize_test/kernel
Oleg Nesterov 5dee1707df move the related code from exit_notify() to exit_signals()
The previous bugfix was not optimal, we shouldn't care about group stop
when we are the only thread or the group stop is in progress.  In that case
nothing special is needed, just set PF_EXITING and return.

Also, take the related "TIF_SIGPENDING re-targeting" code from exit_notify().

So, from the performance POV the only difference is that we don't trust
!signal_pending() until we take ->siglock.  But this in fact fixes another
___pure___ theoretical minor race.  __group_complete_signal() finds the
task without PF_EXITING and chooses it as the target for signal_wake_up().
But nothing prevents this task from exiting in between without noticing the
pending signal and thus unpredictably delaying the actual delivery.

Signed-off-by: Oleg Nesterov <oleg@tv-sign.ru>
Cc: Davide Libenzi <davidel@xmailserver.org>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Roland McGrath <roland@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-08 09:22:27 -08:00
..
irq genirq: stackdump after the "Trying to free already-free IRQ" message 2008-01-30 13:33:24 +01:00
power PM: documentation cleanups 2008-02-07 01:27:17 -05:00
time time: fix sysfs_show_{available,current}_clocksources() buffer overflow problem 2008-02-06 10:41:03 -08:00
.gitignore
acct.c
audit_tree.c
audit.c [AUDIT] ratelimit printk messages audit 2008-02-01 14:25:04 -05:00
audit.h
auditfilter.c [AUDIT] make audit=0 really stop audit messages 2008-02-01 14:24:33 -05:00
auditsc.c [AUDIT] create context if auditing was ever enabled 2008-02-01 14:24:45 -05:00
backtracetest.c x86: add a simple backtrace test module 2008-01-30 13:33:08 +01:00
capability.c Add 64-bit capability support to the kernel 2008-02-05 09:44:20 -08:00
cgroup_debug.c
cgroup.c Handle pid namespaces in cgroups code 2008-02-07 08:42:22 -08:00
compat.c
configs.c
cpu.c
cpuset.c proc: seqfile convert proc_pid_status to properly handle pid namespaces 2008-02-08 09:22:24 -08:00
delayacct.c
dma.c
exec_domain.c
exit.c move the related code from exit_notify() to exit_signals() 2008-02-08 09:22:27 -08:00
extable.c module: Don't report discarded init pages as kernel text. 2008-01-29 17:13:18 +11:00
fork.c Memory controller: accounting setup 2008-02-07 08:42:18 -08:00
futex_compat.c futex: Add bitset conditional wait/wakeup functionality 2008-02-01 17:45:14 +01:00
futex.c futex: Add bitset conditional wait/wakeup functionality 2008-02-01 17:45:14 +01:00
hrtimer.c timerfd: new timerfd API 2008-02-05 09:44:07 -08:00
itimer.c
kallsyms.c remove support for un-needed _extratext section 2008-02-06 10:41:01 -08:00
Kconfig.hz sched: high-res preemption tick 2008-01-25 21:08:29 +01:00
Kconfig.preempt sched: remove the !PREEMPT_BKL code 2008-01-25 21:08:33 +01:00
kexec.c vmcoreinfo: add "VMCOREINFO_" to all the call for vmcoreinfo_append_str() 2008-02-07 08:42:25 -08:00
kfifo.c
kmod.c
kprobes.c kprobes: kretprobe user entry-handler 2008-02-06 10:41:11 -08:00
ksysfs.c
kthread.c sched: fix, always create kernel threads with normal priority 2008-01-25 21:08:33 +01:00
latencytop.c sched: latencytop support 2008-01-25 21:08:34 +01:00
lockdep_internals.h
lockdep_proc.c
lockdep.c
Makefile namespaces: cleanup the code managed with PID_NS option 2008-02-08 09:22:23 -08:00
marker.c
module.c fix "modules: make module_address_lookup() safe" 2008-02-08 09:22:24 -08:00
mutex-debug.c
mutex-debug.h
mutex.c
mutex.h
notifier.c kernel/notifier.c should #include <linux/reboot.h> 2008-02-06 10:41:02 -08:00
ns_cgroup.c
nsproxy.c namespaces: move the IPC namespace under IPC_NS option 2008-02-08 09:22:23 -08:00
panic.c ACPI: Taint kernel on ACPI table override (format corrected) 2008-02-06 22:07:51 -05:00
params.c kernel/params.c: remove sparse-warning (different signedness) 2008-02-06 10:41:08 -08:00
pid_namespace.c namespaces: cleanup the code managed with PID_NS option 2008-02-08 09:22:23 -08:00
pid.c namespaces: cleanup the code managed with PID_NS option 2008-02-08 09:22:23 -08:00
pm_qos_params.c pm qos infrastructure and interface 2008-02-05 09:44:22 -08:00
posix-cpu-timers.c sched: rt-watchdog: fix .rlim_max = RLIM_INFINITY 2008-01-25 21:08:32 +01:00
posix-timers.c timerfd: new timerfd API 2008-02-05 09:44:07 -08:00
printk.c printk.c: use unsigned ints instead of longs for logbuf index 2008-02-06 10:41:04 -08:00
profile.c debug: clean up kernel/profile.c 2008-01-25 21:08:33 +01:00
ptrace.c ptrace_check_attach: remove unneeded ->signal != NULL check 2008-02-08 09:22:26 -08:00
rcuclassic.c Preempt-RCU: implementation 2008-01-25 21:08:24 +01:00
rcupdate.c Preempt-RCU: fix rcu_barrier for preemptive environment. 2008-01-25 21:08:24 +01:00
rcupreempt_trace.c Preempt-RCU: implementation 2008-01-25 21:08:24 +01:00
rcupreempt.c Preempt-RCU: CPU Hotplug handling 2008-01-25 21:08:25 +01:00
rcutorture.c
relay.c relay: nopage 2008-02-06 10:41:07 -08:00
res_counter.c Memory controller improve user interface 2008-02-07 08:42:18 -08:00
resource.c
rtmutex_common.h
rtmutex-debug.c
rtmutex-debug.h
rtmutex-tester.c
rtmutex.c
rtmutex.h
rwsem.c
sched_debug.c sched: keep total / count stats in addition to the max for 2008-01-25 21:08:35 +01:00
sched_fair.c sched: let +nice tasks have smaller impact 2008-01-31 22:45:22 +01:00
sched_idletask.c sched: high-res preemption tick 2008-01-25 21:08:29 +01:00
sched_rt.c sched: fix goto retry in pick_next_task_rt() 2008-01-25 21:08:34 +01:00
sched_stats.h
sched.c Merge branch 'task_killable' of git://git.kernel.org/pub/scm/linux/kernel/git/willy/misc 2008-02-01 11:45:47 +11:00
seccomp.c
signal.c move the related code from exit_notify() to exit_signals() 2008-02-08 09:22:27 -08:00
softirq.c time: track accurate idle time with tick_sched.idle_sleeptime 2008-01-30 13:30:04 +01:00
softlockup.c debug: softlockup looping fix 2008-02-02 14:27:45 +11:00
spinlock.c spinlock: lockbreak cleanup 2008-01-30 13:31:20 +01:00
srcu.c make srcu_readers_active() static 2008-02-06 10:41:02 -08:00
stacktrace.c
stop_machine.c stopmachine: semaphore to mutex 2008-02-06 10:41:08 -08:00
sys_ni.c timerfd: new timerfd API 2008-02-05 09:44:07 -08:00
sys.c sys_setsid: remove now unneeded session != 1 check 2008-02-08 09:22:27 -08:00
sysctl_check.c capabilities: introduce per-process capability bounding set 2008-02-05 09:44:20 -08:00
sysctl.c hugetlb: add locking for overcommit sysctl 2008-02-08 09:22:23 -08:00
taskstats.c
test_kprobes.c kprobes: kretprobe user entry-handler 2008-02-06 10:41:11 -08:00
time.c speed up jiffies conversion functions if HZ==USER_HZ 2008-02-06 10:41:10 -08:00
timer.c taskstats scaled time cleanup 2008-02-06 10:41:00 -08:00
tsacct.c
uid16.c
user_namespace.c namespaces: cleanup the code managed with the USER_NS option 2008-02-08 09:22:23 -08:00
user.c namespaces: cleanup the code managed with the USER_NS option 2008-02-08 09:22:23 -08:00
utsname_sysctl.c
utsname.c
wait.c
workqueue.c