From: "Paul E. McKenney" <paulmck@kernel.org>
To: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Cc: "Uladzislau Rezki (Sony)" <urezki@gmail.com>,
LKML <linux-kernel@vger.kernel.org>, RCU <rcu@vger.kernel.org>,
Michael Ellerman <mpe@ellerman.id.au>,
Andrew Morton <akpm@linux-foundation.org>,
Daniel Axtens <dja@axtens.net>,
Frederic Weisbecker <frederic@kernel.org>,
Neeraj Upadhyay <neeraju@codeaurora.org>,
Joel Fernandes <joel@joelfernandes.org>,
Peter Zijlstra <peterz@infradead.org>,
Michal Hocko <mhocko@suse.com>,
Thomas Gleixner <tglx@linutronix.de>,
"Theodore Y . Ts'o" <tytso@mit.edu>,
Oleksiy Avramchenko <oleksiy.avramchenko@sonymobile.com>
Subject: Re: [PATCH 3/3] kvfree_rcu: use migrate_disable/enable()
Date: Wed, 20 Jan 2021 13:42:53 -0800 [thread overview]
Message-ID: <20210120214253.GG2743@paulmck-ThinkPad-P72> (raw)
In-Reply-To: <20210120194554.34dby47iipmyplts@linutronix.de>
On Wed, Jan 20, 2021 at 08:45:54PM +0100, Sebastian Andrzej Siewior wrote:
> On 2021-01-20 17:21:48 [+0100], Uladzislau Rezki (Sony) wrote:
> > --- a/kernel/rcu/tree.c
> > +++ b/kernel/rcu/tree.c
> > @@ -3489,10 +3489,12 @@ add_ptr_to_bulk_krc_lock(struct kfree_rcu_cpu **krcp,
> > (*krcp)->bkvhead[idx]->nr_records == KVFREE_BULK_MAX_ENTR) {
> > bnode = get_cached_bnode(*krcp);
> > if (!bnode && can_alloc) {
> > + migrate_disable();
> > krc_this_cpu_unlock(*krcp, *flags);
>
> Why is krc_this_cpu_unlock() defined as
> | static inline void
> | krc_this_cpu_unlock(struct kfree_rcu_cpu *krcp, unsigned long flags)
> | {
> | raw_spin_unlock(&krcp->lock);
> | local_irq_restore(flags);
> | }
>
> instead of raw_spin_unlock_irqrestore()?
> Should something with the locked section trigger a scheduling event by
> setting TIF_NEED_RESCHED then there will be no scheduling event on
> unlock. It will be delayed until a later "random" preempt_enable().
>
> raw_spin_unlock_irqrestore() will reschedule if the flag is set,
> local_irq_restore() will not.
Good catch, thank you! This one is already in mainline, so I queued
the following patch.
Thanx, Paul
------------------------------------------------------------------------
commit 6c1d51e012c5b474cda77d4fa644d76e041c1e05
Author: Paul E. McKenney <paulmck@kernel.org>
Date: Wed Jan 20 13:38:08 2021 -0800
kvfree_rcu: Make krc_this_cpu_unlock() use raw_spin_unlock_irqrestore()
The krc_this_cpu_unlock() function does a raw_spin_unlock() immediately
followed by a local_irq_restore(). This commit saves a line of code by
merging them into a raw_spin_unlock_irqrestore(). This transformation
also reduces scheduling latency because raw_spin_unlock_irqrestore()
responds immediately to a reschedule request. In contrast,
local_irq_restore() does a scheduling-oblivious enabling of interrupts.
Reported-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index cad3607..e7a226a 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -3201,8 +3201,7 @@ krc_this_cpu_lock(unsigned long *flags)
static inline void
krc_this_cpu_unlock(struct kfree_rcu_cpu *krcp, unsigned long flags)
{
- raw_spin_unlock(&krcp->lock);
- local_irq_restore(flags);
+ raw_spin_unlock_irqrestore(&krcp->lock, flags);
}
static inline struct kvfree_rcu_bulk_data *
next prev parent reply other threads:[~2021-01-21 0:48 UTC|newest]
Thread overview: 36+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-01-20 16:21 [PATCH 1/3] kvfree_rcu: Allocate a page for a single argument Uladzislau Rezki (Sony)
2021-01-20 16:21 ` [PATCH 2/3] kvfree_rcu: Use __GFP_NOMEMALLOC for single-argument kvfree_rcu() Uladzislau Rezki (Sony)
2021-01-28 18:06 ` Uladzislau Rezki
2021-01-20 16:21 ` [PATCH 3/3] kvfree_rcu: use migrate_disable/enable() Uladzislau Rezki (Sony)
2021-01-20 19:45 ` Sebastian Andrzej Siewior
2021-01-20 21:42 ` Paul E. McKenney [this message]
2021-01-23 9:31 ` 回复: " Zhang, Qiang
2021-01-24 21:57 ` Uladzislau Rezki
2021-01-25 1:50 ` 回复: " Zhang, Qiang
2021-01-25 2:18 ` Zhang, Qiang
2021-01-25 13:49 ` Uladzislau Rezki
2021-01-26 9:33 ` 回复: " Zhang, Qiang
2021-01-26 13:43 ` Uladzislau Rezki
2021-01-20 18:40 ` [PATCH 1/3] kvfree_rcu: Allocate a page for a single argument Paul E. McKenney
2021-01-20 19:57 ` Sebastian Andrzej Siewior
2021-01-20 21:54 ` Paul E. McKenney
2021-01-21 13:35 ` Uladzislau Rezki
2021-01-21 15:07 ` Paul E. McKenney
2021-01-21 19:17 ` Uladzislau Rezki
2021-01-22 11:17 ` Sebastian Andrzej Siewior
2021-01-22 15:28 ` Paul E. McKenney
2021-01-21 12:38 ` Uladzislau Rezki
2021-01-22 11:34 ` Sebastian Andrzej Siewior
2021-01-22 14:21 ` Uladzislau Rezki
2021-01-25 13:22 ` Michal Hocko
2021-01-25 14:31 ` Uladzislau Rezki
2021-01-25 15:39 ` Michal Hocko
2021-01-25 16:25 ` Uladzislau Rezki
2021-01-28 15:11 ` Uladzislau Rezki
2021-01-28 15:17 ` Michal Hocko
2021-01-28 15:30 ` Uladzislau Rezki
2021-01-28 18:02 ` Uladzislau Rezki
[not found] ` <YBPNvbJLg56XU8co@dhcp22.suse.cz>
2021-01-29 16:35 ` Uladzislau Rezki
2021-02-01 11:47 ` Michal Hocko
2021-02-01 14:44 ` Uladzislau Rezki
2021-02-03 19:37 ` Paul E. McKenney
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=20210120214253.GG2743@paulmck-ThinkPad-P72 \
--to=paulmck@kernel.org \
--cc=akpm@linux-foundation.org \
--cc=bigeasy@linutronix.de \
--cc=dja@axtens.net \
--cc=frederic@kernel.org \
--cc=joel@joelfernandes.org \
--cc=linux-kernel@vger.kernel.org \
--cc=mhocko@suse.com \
--cc=mpe@ellerman.id.au \
--cc=neeraju@codeaurora.org \
--cc=oleksiy.avramchenko@sonymobile.com \
--cc=peterz@infradead.org \
--cc=rcu@vger.kernel.org \
--cc=tglx@linutronix.de \
--cc=tytso@mit.edu \
--cc=urezki@gmail.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