From: "Uladzislau Rezki (Sony)" <urezki@gmail.com>
To: LKML <linux-kernel@vger.kernel.org>, RCU <rcu@vger.kernel.org>,
"Paul E . McKenney" <paulmck@kernel.org>
Cc: Andrew Morton <akpm@linux-foundation.org>,
Peter Zijlstra <peterz@infradead.org>,
Michal Hocko <mhocko@suse.com>,
Thomas Gleixner <tglx@linutronix.de>,
"Theodore Y . Ts'o" <tytso@mit.edu>,
Joel Fernandes <joel@joelfernandes.org>,
Sebastian Andrzej Siewior <bigeasy@linutronix.de>,
Uladzislau Rezki <urezki@gmail.com>,
Oleksiy Avramchenko <oleksiy.avramchenko@sonymobile.com>
Subject: [PATCH 16/16] rcu/tree: Use delayed work instead of hrtimer to refill the cache
Date: Thu, 29 Oct 2020 17:50:19 +0100 [thread overview]
Message-ID: <20201029165019.14218-16-urezki@gmail.com> (raw)
In-Reply-To: <20201029165019.14218-1-urezki@gmail.com>
A CONFIG_PREEMPT_COUNT is unconditionally enabled, thus a page
can be obtained directly from a kvfree_rcu() path. To distinguish
that and take a decision the preemptable() macro is used when it
is save to enter allocator.
It means that refilling a cache is not important from timing point
of view. Switch to a delayed work, so the actual work is queued from
the timer interrupt with 1 jiffy delay. An immediate placing a task
on a current CPU can lead to rq->lock double lock. That is why a
delayed method is in place.
Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com>
---
kernel/rcu/tree.c | 26 +++++---------------------
1 file changed, 5 insertions(+), 21 deletions(-)
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 3f9b016a44dc..9ea55f800b4b 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -3086,7 +3086,6 @@ struct kfree_rcu_cpu_work {
* per-cpu lock.
* @page_cache_work: A work to refill the cache when it is empty
* @work_in_progress: Indicates that page_cache_work is running
- * @hrtimer: A hrtimer for scheduling a page_cache_work
* @nr_bkv_objs: number of allocated objects at @bkvcache.
*
* This is a per-CPU structure. The reason that it is not included in
@@ -3104,9 +3103,8 @@ struct kfree_rcu_cpu {
bool initialized;
int count;
- struct work_struct page_cache_work;
+ struct delayed_work page_cache_work;
atomic_t work_in_progress;
- struct hrtimer hrtimer;
struct llist_head bkvcache;
int nr_bkv_objs;
@@ -3355,22 +3353,12 @@ static void kfree_rcu_monitor(struct work_struct *work)
raw_spin_unlock_irqrestore(&krcp->lock, flags);
}
-static enum hrtimer_restart
-schedule_page_work_fn(struct hrtimer *t)
-{
- struct kfree_rcu_cpu *krcp =
- container_of(t, struct kfree_rcu_cpu, hrtimer);
-
- queue_work(system_highpri_wq, &krcp->page_cache_work);
- return HRTIMER_NORESTART;
-}
-
static void fill_page_cache_func(struct work_struct *work)
{
struct kvfree_rcu_bulk_data *bnode;
struct kfree_rcu_cpu *krcp =
container_of(work, struct kfree_rcu_cpu,
- page_cache_work);
+ page_cache_work.work);
unsigned long flags;
bool pushed;
int i;
@@ -3398,12 +3386,8 @@ static void
run_page_cache_worker(struct kfree_rcu_cpu *krcp)
{
if (rcu_scheduler_active == RCU_SCHEDULER_RUNNING &&
- !atomic_xchg(&krcp->work_in_progress, 1)) {
- hrtimer_init(&krcp->hrtimer, CLOCK_MONOTONIC,
- HRTIMER_MODE_REL);
- krcp->hrtimer.function = schedule_page_work_fn;
- hrtimer_start(&krcp->hrtimer, 0, HRTIMER_MODE_REL);
- }
+ !atomic_xchg(&krcp->work_in_progress, 1))
+ schedule_delayed_work(&krcp->page_cache_work, 1);
}
// Record ptr in a page managed by krcp, with the pre-krc_this_cpu_lock()
@@ -4503,7 +4487,7 @@ static void __init kfree_rcu_batch_init(void)
}
INIT_DELAYED_WORK(&krcp->monitor_work, kfree_rcu_monitor);
- INIT_WORK(&krcp->page_cache_work, fill_page_cache_func);
+ INIT_DELAYED_WORK(&krcp->page_cache_work, fill_page_cache_func);
krcp->initialized = true;
}
if (register_shrinker(&kfree_rcu_shrinker))
--
2.20.1
next prev parent reply other threads:[~2020-10-29 16:51 UTC|newest]
Thread overview: 36+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-10-29 16:50 [PATCH 01/16] rcu/tree: Add a work to allocate pages from regular context Uladzislau Rezki (Sony)
2020-10-29 16:50 ` [PATCH 02/16] lib/debug: Remove pointless ARCH_NO_PREEMPT dependencies Uladzislau Rezki (Sony)
2020-10-29 16:50 ` [PATCH 03/16] preempt: Make preempt count unconditional Uladzislau Rezki (Sony)
2020-10-29 16:50 ` [PATCH 04/16] preempt: Cleanup PREEMPT_COUNT leftovers Uladzislau Rezki (Sony)
2020-10-29 16:50 ` [PATCH 05/16] lockdep: " Uladzislau Rezki (Sony)
2020-10-29 16:50 ` [PATCH 06/16] mm/pagemap: " Uladzislau Rezki (Sony)
2020-10-29 20:57 ` Uladzislau Rezki
2020-10-29 21:26 ` Paul E. McKenney
2020-10-29 16:50 ` [PATCH 07/16] locking/bitspinlock: " Uladzislau Rezki (Sony)
2020-10-29 16:50 ` [PATCH 08/16] uaccess: " Uladzislau Rezki (Sony)
2020-10-29 16:50 ` [PATCH 09/16] sched: " Uladzislau Rezki (Sony)
2020-10-29 16:50 ` [PATCH 10/16] ARM: " Uladzislau Rezki (Sony)
2020-10-29 16:50 ` [PATCH 11/16] xtensa: " Uladzislau Rezki (Sony)
2020-10-29 16:50 ` [PATCH 12/16] drm/i915: " Uladzislau Rezki (Sony)
2020-10-29 16:50 ` [PATCH 13/16] rcutorture: " Uladzislau Rezki (Sony)
2020-10-29 16:50 ` [PATCH 14/16] preempt: Remove PREEMPT_COUNT from Kconfig Uladzislau Rezki (Sony)
2020-10-29 16:50 ` [PATCH 15/16] rcu/tree: Allocate a page when caller is preemptible Uladzislau Rezki (Sony)
2020-11-03 18:03 ` Joel Fernandes
2020-11-04 11:39 ` Uladzislau Rezki
2020-11-04 14:36 ` Joel Fernandes
2020-10-29 16:50 ` Uladzislau Rezki (Sony) [this message]
2020-10-29 19:47 ` [PATCH 16/16] rcu/tree: Use delayed work instead of hrtimer to refill the cache Paul E. McKenney
2020-10-29 20:13 ` Uladzislau Rezki
2020-10-29 20:22 ` Uladzislau Rezki
2020-10-29 20:33 ` Paul E. McKenney
2020-10-29 21:00 ` Uladzislau Rezki
2020-11-03 15:47 ` [PATCH 01/16] rcu/tree: Add a work to allocate pages from regular context Joel Fernandes
2020-11-03 16:33 ` Uladzislau Rezki
2020-11-03 19:18 ` Paul E. McKenney
2020-11-04 12:35 ` Uladzislau Rezki
2020-11-04 14:12 ` Paul E. McKenney
2020-11-04 14:40 ` Uladzislau Rezki
2020-11-03 17:54 ` Joel Fernandes
2020-11-04 12:12 ` Uladzislau Rezki
2020-11-04 15:01 ` Joel Fernandes
2020-11-04 18:38 ` Uladzislau Rezki
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=20201029165019.14218-16-urezki@gmail.com \
--to=urezki@gmail.com \
--cc=akpm@linux-foundation.org \
--cc=bigeasy@linutronix.de \
--cc=joel@joelfernandes.org \
--cc=linux-kernel@vger.kernel.org \
--cc=mhocko@suse.com \
--cc=oleksiy.avramchenko@sonymobile.com \
--cc=paulmck@kernel.org \
--cc=peterz@infradead.org \
--cc=rcu@vger.kernel.org \
--cc=tglx@linutronix.de \
--cc=tytso@mit.edu \
/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