The patch titled
workqueues: make get_online_cpus() useable for work->func()
has been added to the -mm tree. Its filename is
workqueues-make-get_online_cpus-useable-for-work-func.patch
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** 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
The current -mm tree may be found at http://userweb.kernel.org/~akpm/mmotm/
------------------------------------------------------
Subject: workqueues: make get_online_cpus() useable for work->func()
From: Oleg Nesterov <oleg@xxxxxxxxxx>
workqueue_cpu_callback(CPU_DEAD) flushes cwq->thread under
cpu_maps_update_begin(). This means that the multithreaded workqueues
can't use get_online_cpus() due to the possible deadlock, very bad and
very old problem.
Introduce the new state, CPU_POST_DEAD, which is called after
cpu_hotplug_done() but before cpu_maps_update_done().
Change workqueue_cpu_callback() to use CPU_POST_DEAD instead of CPU_DEAD.
This means that create/destroy functions can't rely on get_online_cpus()
any longer and should take cpu_add_remove_lock instead.
Signed-off-by: Oleg Nesterov <oleg@xxxxxxxxxx>
Cc: Gautham R Shenoy <ego@xxxxxxxxxx>
Cc: Heiko Carstens <heiko.carstens@xxxxxxxxxx>
Cc: Max Krasnyansky <maxk@xxxxxxxxxxxx>
Cc: Paul Jackson <pj@xxxxxxx>
Cc: Paul Menage <menage@xxxxxxxxxx>
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Cc: Vegard Nossum <vegard.nossum@xxxxxxxxx>
Cc: Martin Schwidefsky <schwidefsky@xxxxxxxxxx>
Cc: Ingo Molnar <mingo@xxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
include/linux/notifier.h | 2 ++
kernel/cpu.c | 5 +++++
kernel/workqueue.c | 18 +++++++++---------
3 files changed, 16 insertions(+), 9 deletions(-)
diff -puN include/linux/notifier.h~workqueues-make-get_online_cpus-useable-for-work-func include/linux/notifier.h
--- a/include/linux/notifier.h~workqueues-make-get_online_cpus-useable-for-work-func
+++ a/include/linux/notifier.h
@@ -214,6 +214,8 @@ static inline int notifier_to_errno(int
#define CPU_DEAD 0x0007 /* CPU (unsigned)v dead */
#define CPU_DYING 0x0008 /* CPU (unsigned)v not running any task,
* not handling interrupts, soon dead */
+#define CPU_POST_DEAD 0x0009 /* CPU (unsigned)v dead, cpu_hotplug
+ * lock is dropped */
/* Used for CPU hotplug events occuring while tasks are frozen due to a suspend
* operation in progress
diff -puN kernel/cpu.c~workqueues-make-get_online_cpus-useable-for-work-func kernel/cpu.c
--- a/kernel/cpu.c~workqueues-make-get_online_cpus-useable-for-work-func
+++ a/kernel/cpu.c
@@ -277,6 +277,11 @@ out_allowed:
set_cpus_allowed_ptr(current, &old_allowed);
out_release:
cpu_hotplug_done();
+ if (!err) {
+ if (raw_notifier_call_chain(&cpu_chain, CPU_POST_DEAD | mod,
+ hcpu) == NOTIFY_BAD)
+ BUG();
+ }
return err;
}
diff -puN kernel/workqueue.c~workqueues-make-get_online_cpus-useable-for-work-func kernel/workqueue.c
--- a/kernel/workqueue.c~workqueues-make-get_online_cpus-useable-for-work-func
+++ a/kernel/workqueue.c
@@ -791,7 +791,7 @@ struct workqueue_struct *__create_workqu
err = create_workqueue_thread(cwq, singlethread_cpu);
start_workqueue_thread(cwq, -1);
} else {
- get_online_cpus();
+ cpu_maps_update_begin();
spin_lock(&workqueue_lock);
list_add(&wq->list, &workqueues);
spin_unlock(&workqueue_lock);
@@ -803,7 +803,7 @@ struct workqueue_struct *__create_workqu
err = create_workqueue_thread(cwq, cpu);
start_workqueue_thread(cwq, cpu);
}
- put_online_cpus();
+ cpu_maps_update_done();
}
if (err) {
@@ -817,8 +817,8 @@ EXPORT_SYMBOL_GPL(__create_workqueue_key
static void cleanup_workqueue_thread(struct cpu_workqueue_struct *cwq)
{
/*
- * Our caller is either destroy_workqueue() or CPU_DEAD,
- * get_online_cpus() protects cwq->thread.
+ * Our caller is either destroy_workqueue() or CPU_POST_DEAD,
+ * cpu_add_remove_lock protects cwq->thread.
*/
if (cwq->thread == NULL)
return;
@@ -828,7 +828,7 @@ static void cleanup_workqueue_thread(str
flush_cpu_workqueue(cwq);
/*
- * If the caller is CPU_DEAD and cwq->worklist was not empty,
+ * If the caller is CPU_POST_DEAD and cwq->worklist was not empty,
* a concurrent flush_workqueue() can insert a barrier after us.
* However, in that case run_workqueue() won't return and check
* kthread_should_stop() until it flushes all work_struct's.
@@ -852,14 +852,14 @@ void destroy_workqueue(struct workqueue_
const cpumask_t *cpu_map = wq_cpu_map(wq);
int cpu;
- get_online_cpus();
+ cpu_maps_update_begin();
spin_lock(&workqueue_lock);
list_del(&wq->list);
spin_unlock(&workqueue_lock);
for_each_cpu_mask_nr(cpu, *cpu_map)
cleanup_workqueue_thread(per_cpu_ptr(wq->cpu_wq, cpu));
- put_online_cpus();
+ cpu_maps_update_done();
free_percpu(wq->cpu_wq);
kfree(wq);
@@ -898,7 +898,7 @@ static int __devinit workqueue_cpu_callb
case CPU_UP_CANCELED:
start_workqueue_thread(cwq, -1);
- case CPU_DEAD:
+ case CPU_POST_DEAD:
cleanup_workqueue_thread(cwq);
break;
}
@@ -906,7 +906,7 @@ static int __devinit workqueue_cpu_callb
switch (action) {
case CPU_UP_CANCELED:
- case CPU_DEAD:
+ case CPU_POST_DEAD:
cpu_clear(cpu, cpu_populated_map);
}
_
Patches currently in -mm which might be from oleg@xxxxxxxxxx are
get_user_pages-fix-possible-page-leak-on-oom.patch
migrate_timers-add-comment-use-spinlock_irq.patch
posix-timers-timer_delete-remove-the-bogus-it_process-=-null-check.patch
posix-timers-release_posix_timer-kill-the-bogus-put_task_struct-it_process.patch
signals-collect_signal-remove-the-unneeded-sigismember-check.patch
signals-collect_signal-simplify-the-still_pending-logic.patch
signals-change-collect_signal-to-return-void.patch
__exit_signal-dont-take-rcu-lock.patch
signals-dequeue_signal-dont-check-signal_group_exit-when-setting-signal_stop_dequeued.patch
signals-do_signal_stop-kill-the-signal_unkillable-check.patch
coredump-zap_threads-comments-use-while_each_thread.patch
signals-make-siginfo_t-si_utime-si_sstime-report-times-in-user_hz-not-hz.patch
kernel-signalc-change-vars-pid-and-tgid-types-to-pid_t.patch
include-asm-ptraceh-userspace-headers-cleanup.patch
ptrace-give-more-respect-to-sigkill.patch
ptrace-never-sleep-in-task_traced-if-sigkilled.patch
ptrace-kill-may_ptrace_stop.patch
introduce-pf_kthread-flag.patch
kill-pf_borrowed_mm-in-favour-of-pf_kthread.patch
coredump-zap_threads-must-skip-kernel-threads.patch
coredump-elf_core_dump-skip-kernel-threads.patch
workqueues-insert_work-use-list_head-instead-of-int-tail.patch
workqueues-implement-flush_work.patch
workqueues-schedule_on_each_cpu-use-flush_work.patch
workqueues-make-get_online_cpus-useable-for-work-func.patch
s390-topology-dont-use-kthread-for-arch_reinit_sched_domains.patch
pidns-remove-now-unused-kill_proc-function.patch
pidns-remove-now-unused-find_pid-function.patch
pidns-remove-find_task_by_pid-unused-for-a-long-time.patch
distinct-tgid-tid-i-o-statistics.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
