The patch titled
make kthread_stop() scalable
has been added to the -mm tree. Its filename is
make-kthread_stop-scalable.patch
*** Remember to use Documentation/SubmitChecklist when testing your code ***
See http://www.zip.com.au/~akpm/linux/patches/stuff/added-to-mm.txt to find
out what to do about this
------------------------------------------------------
Subject: make kthread_stop() scalable
From: Oleg Nesterov <oleg@xxxxxxxxxx>
It's a shame kthread_stop() (may take a while!) runs with a global
semaphore held. With this patch kthread() allocates all neccesary data
(struct kthread) on its own stack, globals kthread_stop_xxx are deleted.
HACKS:
- re-use task_struct->set_child_tid to point to "struct kthread"
- use do_exit() directly to preserve "struct kthread" on stack
Signed-off-by: Oleg Nesterov <oleg@xxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
kernel/kthread.c | 98 ++++++++++++++++++++++++---------------------
1 files changed, 54 insertions(+), 44 deletions(-)
diff -puN kernel/kthread.c~make-kthread_stop-scalable kernel/kthread.c
--- a/kernel/kthread.c~make-kthread_stop-scalable
+++ a/kernel/kthread.c
@@ -17,7 +17,25 @@
static DEFINE_SPINLOCK(kthread_create_lock);
static LIST_HEAD(kthread_create_list);
-struct task_struct *kthreadd_task;
+struct task_struct *kthreadd_task __read_mostly;
+
+struct kthread {
+ int should_stop;
+ struct task_struct *task;
+
+ struct completion exited;
+ int err;
+};
+
+static inline struct kthread *to_kthread(struct task_struct *t)
+{
+ return (void*)t->set_child_tid;
+}
+
+static inline void set_kthread(struct kthread *self)
+{
+ current->set_child_tid = (void __user*)self;
+}
struct kthread_create_info
{
@@ -27,24 +45,12 @@ struct kthread_create_info
struct completion created;
struct completion started;
- /* Result passed back to kthread_create() from kthreadd. */
- pid_t result;
+ /* Result passed back to kthread_create() from kthread. */
+ struct kthread *result;
struct list_head list;
};
-struct kthread_stop_info
-{
- struct task_struct *k;
- int err;
- struct completion done;
-};
-
-/* Thread stopping is done by setthing this var: lock serializes
- * multiple kthread_stop calls. */
-static DEFINE_MUTEX(kthread_stop_lock);
-static struct kthread_stop_info kthread_stop_info;
-
/**
* kthread_should_stop - should this kthread return now?
*
@@ -54,20 +60,28 @@ static struct kthread_stop_info kthread_
*/
int kthread_should_stop(void)
{
- return (kthread_stop_info.k == current);
+ return to_kthread(current)->should_stop;
}
EXPORT_SYMBOL(kthread_should_stop);
static int kthread(void *_create)
{
- struct kthread_create_info *create = _create;
- int (*threadfn)(void *data);
- void *data;
- int ret = -EINTR;
+ struct kthread self = {
+ .task = current,
+ .err = -EINTR,
+ };
/* Copy data: it's on kthread's stack */
- threadfn = create->threadfn;
- data = create->data;
+ struct kthread_create_info *create = _create;
+ int (*threadfn)(void *data) = create->threadfn;
+ void *data = create->data;
+
+ /*
+ * This should be enough to assure that self is still on
+ * stack when we enter do_exit()
+ */
+ set_kthread(&self);
+ create->result = &self;
/* OK, tell user we're spawned, wait for stop or wakeup */
__set_current_state(TASK_UNINTERRUPTIBLE);
@@ -75,13 +89,13 @@ static int kthread(void *_create)
schedule();
if (!kthread_should_stop())
- ret = threadfn(data);
+ self.err = threadfn(data);
- /* It might have exited on its own, w/o kthread_stop. Check. */
- if (kthread_should_stop()) {
- kthread_stop_info.err = ret;
- complete(&kthread_stop_info.done);
- }
+ /* It might have exited on its own, w/o kthread_stop. Check. */
+ if (kthread_should_stop())
+ complete(&self.exited);
+
+ do_exit(0);
return 0;
}
@@ -91,7 +105,7 @@ static void create_kthread(struct kthrea
/* We want our own signal handler (we take no signals by default). */
pid = kernel_thread(kthread, create, CLONE_FS | CLONE_FILES | SIGCHLD);
- create->result = pid;
+ create->result = ERR_PTR(pid);
complete(&create->created);
}
@@ -135,11 +149,11 @@ struct task_struct *kthread_create(int (
wake_up_process(kthreadd_task);
wait_for_completion(&create.created);
- if (create.result < 0)
- return ERR_PTR(create.result);
+ if (IS_ERR(create.result))
+ return (void*)create.result;
wait_for_completion(&create.started);
- ret = find_task_by_pid(create.result);
+ ret = create.result->task;
va_start(args, namefmt);
vsnprintf(ret->comm, sizeof(ret->comm), namefmt, args);
@@ -183,27 +197,23 @@ EXPORT_SYMBOL(kthread_bind);
*/
int kthread_stop(struct task_struct *k)
{
+ struct kthread *kthread;
int ret;
- mutex_lock(&kthread_stop_lock);
-
/* It could exit after stop_info.k set, but before wake_up_process. */
get_task_struct(k);
+ kthread = to_kthread(k);
- /* Must init completion *before* thread sees kthread_stop_info.k */
- init_completion(&kthread_stop_info.done);
+ /* Must init completion *before* thread sees ->should_stop */
+ init_completion(&kthread->exited);
smp_wmb();
-
- /* Now set kthread_should_stop() to true, and wake it up. */
- kthread_stop_info.k = k;
+ kthread->should_stop = 1;
wake_up_process(k);
- put_task_struct(k);
/* Once it dies, reset stop ptr, gather result and we're done. */
- wait_for_completion(&kthread_stop_info.done);
- kthread_stop_info.k = NULL;
- ret = kthread_stop_info.err;
- mutex_unlock(&kthread_stop_lock);
+ wait_for_completion(&kthread->exited);
+ ret = kthread->err;
+ put_task_struct(k);
return ret;
}
_
Patches currently in -mm which might be from oleg@xxxxxxxxxx are
kernel-doc-fix-plisth-comments.patch
git-dvb.patch
smaps-add-clear_refs-file-to-clear-reference-fix.patch
fix-refrigerator-vs-thaw_process-race.patch
doc-atomic_add_unless-doesnt-imply-mb-on-failure.patch
clone-flag-clone_parent_tidptr-leaves-invalid-results-in-memory.patch
allow-access-to-proc-pid-fd-after-setuid.patch
freezer-task-exit_state-should-be-treated-as-bolean.patch
softlockup-trivial-s-99-max_rt_prio.patch
fix-race-between-proc_get_inode-and-remove_proc_entry.patch
getrusage-fill-ru_inblock-and-ru_oublock-fields-if-possible.patch
futex-restartable-futex_wait.patch
futex-restartable-futex_wait-fix.patch
add-support-for-deferrable-timers-respun.patch
add-support-for-deferrable-timers-respun-tidy.patch
add-support-for-deferrable-timers-respun-fix.patch
add-a-new-deferrable-delayed-work-init.patch
reimplement-flush_workqueue.patch
implement-flush_work.patch
implement-flush_work-sanity.patch
implement-flush_work_keventd.patch
flush_workqueue-use-preempt_disable-to-hold-off-cpu-hotplug.patch
flush_cpu_workqueue-dont-flush-an-empty-worklist.patch
aio-use-flush_work.patch
kblockd-use-flush_work.patch
relayfs-use-flush_keventd_work.patch
tg3-use-flush_keventd_work.patch
e1000-use-flush_keventd_work.patch
libata-use-flush_work.patch
phy-use-flush_work.patch
call-cpu_chain-with-cpu_down_failed-if-cpu_down_prepare-failed.patch
slab-use-cpu_lock_.patch
workqueue-fix-freezeable-workqueues-implementation.patch
workqueue-fix-flush_workqueue-vs-cpu_dead-race.patch
workqueue-dont-clear-cwq-thread-until-it-exits.patch
workqueue-dont-migrate-pending-works-from-the-dead-cpu.patch
workqueue-kill-run_scheduled_work.patch
workqueue-dont-save-interrupts-in-run_workqueue.patch
workqueue-make-cancel_rearming_delayed_workqueue-work-on-idle-dwork.patch
workqueue-introduce-cpu_singlethread_map.patch
workqueue-introduce-workqueue_struct-singlethread.patch
workqueue-make-init_workqueues-__init.patch
make-queue_delayed_work-friendly-to-flush_fork.patch
unify-queue_delayed_work-and-queue_delayed_work_on.patch
workqueue-introduce-wq_per_cpu-helper.patch
make-cancel_rearming_delayed_work-work-on-any-workqueue-not-just-keventd_wq.patch
ipvs-flush-defense_work-before-module-unload.patch
workqueue-kill-noautorel-works.patch
worker_thread-dont-play-with-signals.patch
worker_thread-fix-racy-try_to_freeze-usage.patch
zap_other_threads-remove-unneeded-exit_signal-change.patch
slab-shutdown-cache_reaper-when-cpu-goes-down.patch
unify-flush_work-flush_work_keventd-and-rename-it-to-cancel_work_sync.patch
____call_usermodehelper-dont-flush_signals.patch
freezer-read-pf_borrowed_mm-in-a-nonracy-way.patch
freezer-close-theoretical-race-between-refrigerator-and-thaw_tasks.patch
freezer-remove-pf_nofreeze-from-rcutorture-thread.patch
freezer-remove-pf_nofreeze-from-bluetooth-threads.patch
freezer-add-try_to_freeze-calls-to-all-kernel-threads.patch
freezer-fix-vfork-problem.patch
freezer-take-kernel_execve-into-consideration.patch
kthread-dont-depend-on-work-queues-take-2.patch
kthread-dont-depend-on-work-queues-take-2-fix.patch
change-reparent_to_init-to-reparent_to_kthreadd.patch
nlmclnt_recovery-dont-use-clone_sighand.patch
usbatm_heavy_init-dont-use-clone_sighand.patch
pnpbios_thread_init-dont-use-clone_sighand.patch
wait_for_helper-remove-unneeded-do_sigaction.patch
worker_thread-dont-play-with-sigchld-and-numa-policy.patch
change-kernel-threads-to-ignore-signals-instead-of-blocking-them.patch
fix-kthread_create-vs-freezer-theoretical-race.patch
make-kthread_create-more-scalable.patch
make-kthread_stop-scalable.patch
dont-init-pgrp-and-__session-in-init_signals.patch
-
To unsubscribe from this list: send the line "unsubscribe mm-commits" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
