user/sven/linux.git/kernel/smpboot.c, branch v4.10.3

kthread/smpboot: do not park in kthread_create_on_cpu()

2016-10-11T22:06:33Z

kthread_create_on_cpu() was added by the commit 2a1d446019f9a5983e ("kthread: Implement park/unpark facility"). It is currently used only when enabling new CPU. For this purpose, the newly created kthread has to be parked. The CPU binding is a bit tricky. The kthread is parked when the CPU has not been allowed yet. And the CPU is bound when the kthread is unparked. The function would be useful for more per-CPU kthreads, e.g. bnx2fc_thread, fcoethread. For this purpose, the newly created kthread should stay in the uninterruptible state. This patch moves the parking into smpboot. It binds the thread already when created. Then the function might be used universally. Also the behavior is consistent with kthread_create() and kthread_create_on_node(). Link: http://lkml.kernel.org/r/1470754545-17632-4-git-send-email-pmladek@suse.com Signed-off-by: Petr Mladek Reviewed-by: Thomas Gleixner Cc: Oleg Nesterov Cc: Tejun Heo Cc: Ingo Molnar Cc: Peter Zijlstra Cc: Steven Rostedt Cc: "Paul E. McKenney" Cc: Josh Triplett Cc: Jiri Kosina Cc: Borislav Petkov Cc: Michal Hocko Cc: Vlastimil Babka Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds

Revert "sched/core: Do not use smp_processor_id() with preempt enabled in smpboot_thread_fn()"

2016-10-04T07:55:57Z

This reverts commit 4fa5cd5245b627db88c9ca08ae442373b02596b4. The original change widens a preempt-off section, to avoid a seemingly unsafe smp_processor_id() use. During review I overlooked two facts: - The code to calls a non-trivial function callback: ht->park(td->cpu); ... which might (and does occasionally) sleep, triggering the warning. - More importantly, as pointed out by Peter Zijlstra, using smp_processor_id() in that context is safe, if it's done from a kernel thread that is pinned to a single CPU - which is the case here. So revert to the original code that enables preemption sooner. Reported-by: kernel test robot Acked-by: Peter Zijlstra Cc: Con Kolivas Cc: Alfred Chen Link: http://lkml.kernel.org/r/20160930015102.GB20189@yexl-desktop Signed-off-by: Ingo Molnar

sched/core: Do not use smp_processor_id() with preempt enabled in smpboot_thread_fn()

2016-09-22T10:28:00Z

We should not be using smp_processor_id() with preempt enabled. Bug identified and fix provided by Alfred Chen. Reported-by: Alfred Chen Signed-off-by: Con Kolivas Cc: Alfred Chen Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/2042051.3vvUWIM0vs@hex Signed-off-by: Ingo Molnar

cpu/hotplug: Unpark smpboot threads from the state machine

2016-03-01T19:36:56Z

Handle the smpboot threads in the state machine. Signed-off-by: Thomas Gleixner Cc: linux-arch@vger.kernel.org Cc: Rik van Riel Cc: Rafael Wysocki Cc: "Srivatsa S. Bhat" Cc: Peter Zijlstra Cc: Arjan van de Ven Cc: Sebastian Siewior Cc: Rusty Russell Cc: Steven Rostedt Cc: Oleg Nesterov Cc: Tejun Heo Cc: Andrew Morton Cc: Paul McKenney Cc: Linus Torvalds Cc: Paul Turner Link: http://lkml.kernel.org/r/20160226182341.295777684@linutronix.de Signed-off-by: Thomas Gleixner

stop_machine: Kill smp_hotplug_thread->pre_unpark, introduce stop_machine_unpark()

2015-10-20T08:23:55Z

1. Change smpboot_unpark_thread() to check ->selfparking, just like smpboot_park_thread() does. 2. Introduce stop_machine_unpark() which sets ->enabled and calls kthread_unpark(). 3. Change smpboot_thread_call() and cpu_stop_init() to call stop_machine_unpark() by hand. This way: - IMO the ->selfparking logic becomes more consistent. - We can kill the smp_hotplug_thread->pre_unpark() method. - We can easily unpark the stopper thread earlier. Say, we can move stop_machine_unpark() from smpboot_thread_call() to sched_cpu_active() as Peter suggests. Signed-off-by: Oleg Nesterov Signed-off-by: Peter Zijlstra (Intel) Cc: Andrew Morton Cc: Linus Torvalds Cc: Mike Galbraith Cc: Paul E. McKenney Cc: Peter Zijlstra Cc: Rik van Riel Cc: Tejun Heo Cc: Thomas Gleixner Cc: heiko.carstens@de.ibm.com Link: http://lkml.kernel.org/r/20151009160049.GA10166@redhat.com Signed-off-by: Ingo Molnar

smpboot: allow passing the cpumask on per-cpu thread registration

2015-09-04T23:54:41Z

It makes the registration cheaper and simpler for the smpboot per-cpu kthread users that don't need to always update the cpumask after threads creation. [sfr@canb.auug.org.au: fix for allow passing the cpumask on per-cpu thread registration] Signed-off-by: Frederic Weisbecker Reviewed-by: Chris Metcalf Reviewed-by: Thomas Gleixner Cc: Chris Metcalf Cc: Don Zickus Cc: Peter Zijlstra Cc: Ulrich Obergfell Signed-off-by: Stephen Rothwell Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds

smpboot: make cleanup to mirror setup

2015-09-04T23:54:41Z

The per-cpu kthread cleanup() callback is the mirror of the setup() callback. When the per-cpu kthread is started, it first calls setup() to initialize the resources which are then released by cleanup() when the kthread exits. Now since the introduction of a per-cpu kthread cpumask, the kthreads excluded by the cpumask on boot may happen to be parked immediately after their creation without taking the setup() stage, waiting to be asked to unpark to do so. Then when smpboot_unregister_percpu_thread() is later called, the kthread is stopped without having ever called setup(). But this triggers a bug as the kthread unconditionally calls cleanup() on exit but this doesn't mirror any setup(). Thus the kernel crashes because we try to free resources that haven't been initialized, as in the watchdog case: WATCHDOG disable 0 WATCHDOG disable 1 WATCHDOG disable 2 BUG: unable to handle kernel NULL pointer dereference at (null) IP: hrtimer_active+0x26/0x60 [...] Call Trace: hrtimer_try_to_cancel+0x1c/0x280 hrtimer_cancel+0x1d/0x30 watchdog_disable+0x56/0x70 watchdog_cleanup+0xe/0x10 smpboot_thread_fn+0x23c/0x2c0 kthread+0xf8/0x110 ret_from_fork+0x3f/0x70 This bug is currently masked with explicit kthread unparking before kthread_stop() on smpboot_destroy_threads(). This forces a call to setup() and then unpark(). We could fix this by unconditionally calling setup() on kthread entry. But setup() isn't always cheap. In the case of watchdog it launches hrtimer, perf events, etc... So we may as well like to skip it if there are chances the kthread will never be used, as in a reduced cpumask value. So let's simply do a state machine check before calling cleanup() that makes sure setup() has been called before mirroring it. And remove the nasty hack workaround. Signed-off-by: Frederic Weisbecker Reviewed-by: Chris Metcalf Reviewed-by: Thomas Gleixner Cc: Chris Metcalf Cc: Don Zickus Cc: Peter Zijlstra Cc: Ulrich Obergfell Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds

smpboot: fix memory leak on error handling

2015-09-04T23:54:41Z

The cpumask is allocated before threads get created. If the latter step fails, we need to free the cpumask. Signed-off-by: Frederic Weisbecker Reviewed-by: Chris Metcalf Reviewed-by: Thomas Gleixner Cc: Chris Metcalf Cc: Don Zickus Cc: Peter Zijlstra Cc: Ulrich Obergfell Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds

watchdog: add watchdog_cpumask sysctl to assist nohz

2015-06-25T00:49:40Z

Change the default behavior of watchdog so it only runs on the housekeeping cores when nohz_full is enabled at build and boot time. Allow modifying the set of cores the watchdog is currently running on with a new kernel.watchdog_cpumask sysctl. In the current system, the watchdog subsystem runs a periodic timer that schedules the watchdog kthread to run. However, nohz_full cores are designed to allow userspace application code running on those cores to have 100% access to the CPU. So the watchdog system prevents the nohz_full application code from being able to run the way it wants to, thus the motivation to suppress the watchdog on nohz_full cores, which this patchset provides by default. However, if we disable the watchdog globally, then the housekeeping cores can't benefit from the watchdog functionality. So we allow disabling it only on some cores. See Documentation/lockup-watchdogs.txt for more information. [jhubbard@nvidia.com: fix a watchdog crash in some configurations] Signed-off-by: Chris Metcalf Acked-by: Don Zickus Cc: Ingo Molnar Cc: Ulrich Obergfell Cc: Thomas Gleixner Cc: Peter Zijlstra Cc: Frederic Weisbecker Signed-off-by: John Hubbard Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds

smpboot: allow excluding cpus from the smpboot threads

2015-06-25T00:49:40Z

This patch series allows the watchdog to run by default only on the housekeeping cores when nohz_full is in effect; this seems to be a good compromise short of turning it off completely (since the nohz_full cores can't tolerate a watchdog). To provide customizability, we add /proc/sys/kernel/watchdog_cpumask so that the set of cores running the watchdog can be tuned to different values after bootup. To implement this customizability, we add a new smpboot_update_cpumask_percpu_thread() API to the smpboot_thread subsystem that lets us park or unpark "unwanted" threads. And now that threads can be parked for long periods of time, we tweak the /proc//stat and /proc//status code so parked threads aren't reported as running, which is otherwise confusing. This patch (of 3): This change allows some cores to be excluded from running the smp_hotplug_thread tasks. The following commit to update kernel/watchdog.c to use this functionality is the motivating example, and more information on the motivation is provided there. A new smp_hotplug_thread field is introduced, "cpumask", which is cpumask field managed by the smpboot subsystem that indicates whether or not the given smp_hotplug_thread should run on that core; the cpumask is checked when deciding whether to unpark the thread. To limit the cpumask to less than cpu_possible, you must call smpboot_update_cpumask_percpu_thread() after registering. Signed-off-by: Chris Metcalf Cc: Don Zickus Cc: Ingo Molnar Cc: Ulrich Obergfell Cc: Thomas Gleixner Cc: Peter Zijlstra Cc: Frederic Weisbecker Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds