From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
To: "Srivatsa S. Bhat" <srivatsa.bhat@linux.vnet.ibm.com>
Cc: linux-doc@vger.kernel.org, peterz@infradead.org,
fweisbec@gmail.com, linux-kernel@vger.kernel.org,
mingo@kernel.org, linux-arch@vger.kernel.org,
linux@arm.linux.org.uk, xiaoguangrong@linux.vnet.ibm.com,
wangyun@linux.vnet.ibm.com, nikunj@linux.vnet.ibm.com,
linux-pm@vger.kernel.org, rusty@rustcorp.com.au,
rostedt@goodmis.org, rjw@sisk.pl, namhyung@kernel.org,
tglx@linutronix.de, linux-arm-kernel@lists.infradead.org,
netdev@vger.kernel.org, oleg@redhat.com, sbw@mit.edu,
tj@kernel.org, akpm@linux-foundation.org,
linuxppc-dev@lists.ozlabs.org
Subject: Re: [PATCH v5 09/45] smp, cpu hotplug: Fix smp_call_function_*() to prevent CPU offline properly
Date: Sun, 10 Feb 2013 11:56:39 -0800 [thread overview]
Message-ID: <20130210195639.GL2666@linux.vnet.ibm.com> (raw)
In-Reply-To: <5117F7E9.7070906@linux.vnet.ibm.com>
On Mon, Feb 11, 2013 at 01:11:29AM +0530, Srivatsa S. Bhat wrote:
> On 02/09/2013 05:37 AM, Paul E. McKenney wrote:
> > On Tue, Jan 22, 2013 at 01:05:10PM +0530, Srivatsa S. Bhat wrote:
> >> Once stop_machine() is gone from the CPU offline path, we won't be able to
> >> depend on preempt_disable() to prevent CPUs from going offline from under us.
> >>
> >> Use the get/put_online_cpus_atomic() APIs to prevent CPUs from going offline,
> >> while invoking from atomic context.
> >>
> >> Signed-off-by: Srivatsa S. Bhat <srivatsa.bhat@linux.vnet.ibm.com>
> >
> > Would it make sense for get_online_cpus_atomic() to return the current
> > CPU number?
>
> Hmm, I'm not so sure. I tried to model it after get_online_cpus(), which doesn't
> return anything (for other reasons, of course..)
>
> Moreover, a function name like *_cpu_* returning the CPU number would be intuitive.
> But a name such as *_cpus_* (plural) returning a CPU number might appear confusing..
>
> And also I don't think it'll make a huge improvement in the callers.. (We might
> be better off avoiding an smp_processor_id() if possible, since this function could
> be called in very hot paths).. So I don't see a strong case for returning the
> CPU number. But let me know if you think it'll still be worth it for some reason...
I just noted a lot of two-line code sequences in your patch that would be
one line if the CPU number was returned. But I don't feel strongly about
it, so if people are OK with the current version, no problem.
Thanx, Paul
> > Looks good otherwise.
> >
>
> Thank you very much for the detailed review, Paul!
>
> Regards,
> Srivatsa S. Bhat
>
> >
> >> ---
> >>
> >> kernel/smp.c | 40 ++++++++++++++++++++++++++--------------
> >> 1 file changed, 26 insertions(+), 14 deletions(-)
> >>
> >> diff --git a/kernel/smp.c b/kernel/smp.c
> >> index 29dd40a..f421bcc 100644
> >> --- a/kernel/smp.c
> >> +++ b/kernel/smp.c
> >> @@ -310,7 +310,8 @@ int smp_call_function_single(int cpu, smp_call_func_t func, void *info,
> >> * prevent preemption and reschedule on another processor,
> >> * as well as CPU removal
> >> */
> >> - this_cpu = get_cpu();
> >> + get_online_cpus_atomic();
> >> + this_cpu = smp_processor_id();
> >>
> >> /*
> >> * Can deadlock when called with interrupts disabled.
> >> @@ -342,7 +343,7 @@ int smp_call_function_single(int cpu, smp_call_func_t func, void *info,
> >> }
> >> }
> >>
> >> - put_cpu();
> >> + put_online_cpus_atomic();
> >>
> >> return err;
> >> }
> >> @@ -371,8 +372,10 @@ int smp_call_function_any(const struct cpumask *mask,
> >> const struct cpumask *nodemask;
> >> int ret;
> >>
> >> + get_online_cpus_atomic();
> >> /* Try for same CPU (cheapest) */
> >> - cpu = get_cpu();
> >> + cpu = smp_processor_id();
> >> +
> >> if (cpumask_test_cpu(cpu, mask))
> >> goto call;
> >>
> >> @@ -388,7 +391,7 @@ int smp_call_function_any(const struct cpumask *mask,
> >> cpu = cpumask_any_and(mask, cpu_online_mask);
> >> call:
> >> ret = smp_call_function_single(cpu, func, info, wait);
> >> - put_cpu();
> >> + put_online_cpus_atomic();
> >> return ret;
> >> }
> >> EXPORT_SYMBOL_GPL(smp_call_function_any);
> >> @@ -409,25 +412,28 @@ void __smp_call_function_single(int cpu, struct call_single_data *data,
> >> unsigned int this_cpu;
> >> unsigned long flags;
> >>
> >> - this_cpu = get_cpu();
> >> + get_online_cpus_atomic();
> >> +
> >> + this_cpu = smp_processor_id();
> >> +
> >> /*
> >> * Can deadlock when called with interrupts disabled.
> >> * We allow cpu's that are not yet online though, as no one else can
> >> * send smp call function interrupt to this cpu and as such deadlocks
> >> * can't happen.
> >> */
> >> - WARN_ON_ONCE(cpu_online(smp_processor_id()) && wait && irqs_disabled()
> >> + WARN_ON_ONCE(cpu_online(this_cpu) && wait && irqs_disabled()
> >> && !oops_in_progress);
> >>
> >> if (cpu == this_cpu) {
> >> local_irq_save(flags);
> >> data->func(data->info);
> >> local_irq_restore(flags);
> >> - } else {
> >> + } else if ((unsigned)cpu < nr_cpu_ids && cpu_online(cpu)) {
> >> csd_lock(data);
> >> generic_exec_single(cpu, data, wait);
> >> }
> >> - put_cpu();
> >> + put_online_cpus_atomic();
> >> }
> >>
> >> /**
> >> @@ -451,6 +457,8 @@ void smp_call_function_many(const struct cpumask *mask,
> >> unsigned long flags;
> >> int refs, cpu, next_cpu, this_cpu = smp_processor_id();
> >>
> >> + get_online_cpus_atomic();
> >> +
> >> /*
> >> * Can deadlock when called with interrupts disabled.
> >> * We allow cpu's that are not yet online though, as no one else can
> >> @@ -467,17 +475,18 @@ void smp_call_function_many(const struct cpumask *mask,
> >>
> >> /* No online cpus? We're done. */
> >> if (cpu >= nr_cpu_ids)
> >> - return;
> >> + goto out_unlock;
> >>
> >> /* Do we have another CPU which isn't us? */
> >> next_cpu = cpumask_next_and(cpu, mask, cpu_online_mask);
> >> if (next_cpu == this_cpu)
> >> - next_cpu = cpumask_next_and(next_cpu, mask, cpu_online_mask);
> >> + next_cpu = cpumask_next_and(next_cpu, mask,
> >> + cpu_online_mask);
> >>
> >> /* Fastpath: do that cpu by itself. */
> >> if (next_cpu >= nr_cpu_ids) {
> >> smp_call_function_single(cpu, func, info, wait);
> >> - return;
> >> + goto out_unlock;
> >> }
> >>
> >> data = &__get_cpu_var(cfd_data);
> >> @@ -523,7 +532,7 @@ void smp_call_function_many(const struct cpumask *mask,
> >> /* Some callers race with other cpus changing the passed mask */
> >> if (unlikely(!refs)) {
> >> csd_unlock(&data->csd);
> >> - return;
> >> + goto out_unlock;
> >> }
> >>
> >> raw_spin_lock_irqsave(&call_function.lock, flags);
> >> @@ -554,6 +563,9 @@ void smp_call_function_many(const struct cpumask *mask,
> >> /* Optionally wait for the CPUs to complete */
> >> if (wait)
> >> csd_lock_wait(&data->csd);
> >> +
> >> +out_unlock:
> >> + put_online_cpus_atomic();
> >> }
> >> EXPORT_SYMBOL(smp_call_function_many);
> >>
> >> @@ -574,9 +586,9 @@ EXPORT_SYMBOL(smp_call_function_many);
> >> */
> >> int smp_call_function(smp_call_func_t func, void *info, int wait)
> >> {
> >> - preempt_disable();
> >> + get_online_cpus_atomic();
> >> smp_call_function_many(cpu_online_mask, func, info, wait);
> >> - preempt_enable();
> >> + put_online_cpus_atomic();
> >>
> >> return 0;
> >> }
> >>
>
next prev parent reply other threads:[~2013-02-10 19:56 UTC|newest]
Thread overview: 122+ messages / expand[flat|nested] mbox.gz Atom feed top
2013-01-22 7:33 [PATCH v5 00/45] CPU hotplug: stop_machine()-free CPU hotplug Srivatsa S. Bhat
2013-01-22 7:33 ` [PATCH v5 01/45] percpu_rwlock: Introduce the global reader-writer lock backend Srivatsa S. Bhat
2013-01-22 18:45 ` Stephen Hemminger
2013-01-22 19:41 ` Srivatsa S. Bhat
2013-01-22 19:32 ` Steven Rostedt
2013-01-22 19:58 ` Srivatsa S. Bhat
2013-01-22 20:54 ` Steven Rostedt
2013-01-24 4:14 ` Michel Lespinasse
2013-01-24 15:58 ` Oleg Nesterov
2013-01-22 7:33 ` [PATCH v5 02/45] percpu_rwlock: Introduce per-CPU variables for the reader and the writer Srivatsa S. Bhat
2013-01-22 7:33 ` [PATCH v5 03/45] percpu_rwlock: Provide a way to define and init percpu-rwlocks at compile time Srivatsa S. Bhat
2013-01-22 7:33 ` [PATCH v5 04/45] percpu_rwlock: Implement the core design of Per-CPU Reader-Writer Locks Srivatsa S. Bhat
2013-01-23 18:55 ` Tejun Heo
2013-01-23 19:33 ` Srivatsa S. Bhat
2013-01-23 19:57 ` Tejun Heo
2013-01-24 4:30 ` Srivatsa S. Bhat
2013-01-29 11:12 ` Namhyung Kim
2013-02-08 22:47 ` Paul E. McKenney
2013-02-10 18:38 ` Srivatsa S. Bhat
2013-02-08 23:10 ` Paul E. McKenney
2013-02-10 18:06 ` Oleg Nesterov
2013-02-10 19:24 ` Srivatsa S. Bhat
2013-02-10 19:50 ` Oleg Nesterov
2013-02-10 20:09 ` Srivatsa S. Bhat
2013-02-10 22:13 ` Paul E. McKenney
2013-02-10 19:54 ` Paul E. McKenney
2013-02-12 16:15 ` Paul E. McKenney
2013-02-10 19:10 ` Srivatsa S. Bhat
2013-02-10 19:47 ` Paul E. McKenney
2013-02-10 19:57 ` Srivatsa S. Bhat
2013-02-10 20:13 ` Oleg Nesterov
2013-02-10 20:20 ` Srivatsa S. Bhat
2013-01-22 7:34 ` [PATCH v5 05/45] percpu_rwlock: Make percpu-rwlocks IRQ-safe, optimally Srivatsa S. Bhat
2013-02-08 23:44 ` Paul E. McKenney
2013-02-10 19:27 ` Srivatsa S. Bhat
2013-02-10 18:42 ` Oleg Nesterov
2013-02-10 19:30 ` Srivatsa S. Bhat
2013-01-22 7:34 ` [PATCH v5 06/45] percpu_rwlock: Allow writers to be readers, and add lockdep annotations Srivatsa S. Bhat
2013-02-08 23:47 ` Paul E. McKenney
2013-02-10 19:32 ` Srivatsa S. Bhat
2013-01-22 7:34 ` [PATCH v5 07/45] CPU hotplug: Provide APIs to prevent CPU offline from atomic context Srivatsa S. Bhat
2013-01-29 10:21 ` Namhyung Kim
2013-02-10 19:34 ` Srivatsa S. Bhat
2013-02-08 23:50 ` Paul E. McKenney
2013-01-22 7:35 ` [PATCH v5 08/45] CPU hotplug: Convert preprocessor macros to static inline functions Srivatsa S. Bhat
2013-02-08 23:51 ` Paul E. McKenney
2013-01-22 7:35 ` [PATCH v5 09/45] smp, cpu hotplug: Fix smp_call_function_*() to prevent CPU offline properly Srivatsa S. Bhat
2013-02-09 0:07 ` Paul E. McKenney
2013-02-10 19:41 ` Srivatsa S. Bhat
2013-02-10 19:56 ` Paul E. McKenney [this message]
2013-02-10 19:59 ` Srivatsa S. Bhat
2013-01-22 7:35 ` [PATCH v5 10/45] smp, cpu hotplug: Fix on_each_cpu_*() " Srivatsa S. Bhat
2013-01-22 7:35 ` [PATCH v5 11/45] sched/timer: Use get/put_online_cpus_atomic() to prevent CPU offline Srivatsa S. Bhat
2013-01-22 7:35 ` [PATCH v5 12/45] sched/migration: Use raw_spin_lock/unlock since interrupts are already disabled Srivatsa S. Bhat
2013-01-22 7:36 ` [PATCH v5 13/45] sched/rt: Use get/put_online_cpus_atomic() to prevent CPU offline Srivatsa S. Bhat
2013-01-22 7:36 ` [PATCH v5 14/45] rcu, CPU hotplug: Fix comment referring to stop_machine() Srivatsa S. Bhat
2013-02-09 0:14 ` Paul E. McKenney
2013-02-10 19:43 ` Srivatsa S. Bhat
2013-01-22 7:36 ` [PATCH v5 15/45] tick: Use get/put_online_cpus_atomic() to prevent CPU offline Srivatsa S. Bhat
2013-01-22 7:37 ` [PATCH v5 16/45] time/clocksource: " Srivatsa S. Bhat
2013-01-22 7:37 ` [PATCH v5 17/45] softirq: " Srivatsa S. Bhat
2013-01-22 7:38 ` [PATCH v5 18/45] irq: " Srivatsa S. Bhat
2013-01-22 7:38 ` [PATCH v5 19/45] net: " Srivatsa S. Bhat
2013-01-22 7:38 ` [PATCH v5 20/45] block: " Srivatsa S. Bhat
2013-01-22 7:38 ` [PATCH v5 21/45] crypto: pcrypt - Protect access to cpu_online_mask with get/put_online_cpus() Srivatsa S. Bhat
2013-01-22 7:39 ` [PATCH v5 22/45] infiniband: ehca: Use get/put_online_cpus_atomic() to prevent CPU offline Srivatsa S. Bhat
2013-01-22 7:39 ` [PATCH v5 23/45] [SCSI] fcoe: " Srivatsa S. Bhat
2013-01-22 7:39 ` [PATCH v5 24/45] staging: octeon: " Srivatsa S. Bhat
2013-01-22 7:39 ` [PATCH v5 25/45] x86: " Srivatsa S. Bhat
2013-01-22 7:39 ` [PATCH v5 26/45] perf/x86: " Srivatsa S. Bhat
2013-01-22 7:40 ` [PATCH v5 27/45] KVM: Use get/put_online_cpus_atomic() to prevent CPU offline from atomic context Srivatsa S. Bhat
2013-01-22 7:40 ` [PATCH v5 28/45] kvm/vmx: Use get/put_online_cpus_atomic() to prevent CPU offline Srivatsa S. Bhat
2013-01-22 7:40 ` [PATCH v5 29/45] x86/xen: " Srivatsa S. Bhat
2013-02-19 18:10 ` Konrad Rzeszutek Wilk
2013-02-19 18:29 ` Srivatsa S. Bhat
2013-01-22 7:41 ` [PATCH v5 30/45] alpha/smp: " Srivatsa S. Bhat
2013-01-22 7:41 ` [PATCH v5 31/45] blackfin/smp: " Srivatsa S. Bhat
2013-01-28 9:09 ` Bob Liu
2013-01-28 19:06 ` Tejun Heo
2013-01-29 1:14 ` Srivatsa S. Bhat
2013-01-22 7:41 ` [PATCH v5 32/45] cris/smp: " Srivatsa S. Bhat
2013-01-22 7:42 ` [PATCH v5 33/45] hexagon/smp: " Srivatsa S. Bhat
2013-01-22 7:42 ` [PATCH v5 34/45] ia64: " Srivatsa S. Bhat
2013-01-22 7:42 ` [PATCH v5 35/45] m32r: " Srivatsa S. Bhat
2013-01-22 7:42 ` [PATCH v5 36/45] MIPS: " Srivatsa S. Bhat
2013-01-22 7:43 ` [PATCH v5 37/45] mn10300: " Srivatsa S. Bhat
2013-01-22 7:43 ` [PATCH v5 38/45] parisc: " Srivatsa S. Bhat
2013-01-22 7:43 ` [PATCH v5 39/45] powerpc: " Srivatsa S. Bhat
2013-01-22 7:44 ` [PATCH v5 40/45] sh: " Srivatsa S. Bhat
2013-01-22 7:44 ` [PATCH v5 41/45] sparc: " Srivatsa S. Bhat
2013-01-22 7:44 ` [PATCH v5 42/45] tile: " Srivatsa S. Bhat
2013-01-22 7:44 ` [PATCH v5 43/45] cpu: No more __stop_machine() in _cpu_down() Srivatsa S. Bhat
2013-01-22 7:45 ` [PATCH v5 44/45] CPU hotplug, stop_machine: Decouple CPU hotplug from stop_machine() in Kconfig Srivatsa S. Bhat
2013-02-09 0:15 ` Paul E. McKenney
2013-02-10 19:45 ` Srivatsa S. Bhat
2013-01-22 7:45 ` [PATCH v5 45/45] Documentation/cpu-hotplug: Remove references to stop_machine() Srivatsa S. Bhat
2013-02-09 0:16 ` Paul E. McKenney
2013-02-04 13:47 ` [PATCH v5 00/45] CPU hotplug: stop_machine()-free CPU hotplug Srivatsa S. Bhat
2013-02-07 4:14 ` Rusty Russell
2013-02-07 6:11 ` Srivatsa S. Bhat
2013-02-08 15:41 ` Russell King - ARM Linux
2013-02-08 16:44 ` Srivatsa S. Bhat
2013-02-08 18:09 ` Srivatsa S. Bhat
2013-02-11 11:58 ` Vincent Guittot
2013-02-11 12:23 ` Srivatsa S. Bhat
2013-02-11 19:08 ` Paul E. McKenney
2013-02-12 3:58 ` Srivatsa S. Bhat
2013-02-15 13:28 ` Vincent Guittot
2013-02-15 19:40 ` Srivatsa S. Bhat
2013-02-18 10:24 ` Vincent Guittot
2013-02-18 10:34 ` Srivatsa S. Bhat
2013-02-18 10:51 ` Srivatsa S. Bhat
2013-02-18 10:58 ` Vincent Guittot
2013-02-18 15:30 ` Steven Rostedt
2013-02-18 16:50 ` Vincent Guittot
2013-02-18 19:53 ` Steven Rostedt
2013-02-18 19:53 ` Steven Rostedt
2013-02-19 10:33 ` Vincent Guittot
2013-02-18 10:54 ` Thomas Gleixner
2013-02-18 10:57 ` Srivatsa S. Bhat
2013-02-11 12:41 ` [PATCH v5 01/45] percpu_rwlock: Introduce the global reader-writer lock backend David Howells
2013-02-11 12:56 ` Srivatsa S. Bhat
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20130210195639.GL2666@linux.vnet.ibm.com \
--to=paulmck@linux.vnet.ibm.com \
--cc=akpm@linux-foundation.org \
--cc=fweisbec@gmail.com \
--cc=linux-arch@vger.kernel.org \
--cc=linux-arm-kernel@lists.infradead.org \
--cc=linux-doc@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-pm@vger.kernel.org \
--cc=linux@arm.linux.org.uk \
--cc=linuxppc-dev@lists.ozlabs.org \
--cc=mingo@kernel.org \
--cc=namhyung@kernel.org \
--cc=netdev@vger.kernel.org \
--cc=nikunj@linux.vnet.ibm.com \
--cc=oleg@redhat.com \
--cc=peterz@infradead.org \
--cc=rjw@sisk.pl \
--cc=rostedt@goodmis.org \
--cc=rusty@rustcorp.com.au \
--cc=sbw@mit.edu \
--cc=srivatsa.bhat@linux.vnet.ibm.com \
--cc=tglx@linutronix.de \
--cc=tj@kernel.org \
--cc=wangyun@linux.vnet.ibm.com \
--cc=xiaoguangrong@linux.vnet.ibm.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).