[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20201028111221.584884062@infradead.org>
Date: Wed, 28 Oct 2020 12:07:13 +0100
From: Peter Zijlstra <peterz@...radead.org>
To: mingo@...nel.org
Cc: linux-kernel@...r.kernel.org, will@...nel.org, paulmck@...nel.org,
hch@....de, axboe@...nel.dk, chris@...is-wilson.co.uk,
davem@...emloft.net, kuba@...nel.org, fweisbec@...il.com,
oleg@...hat.com, vincent.guittot@...aro.org, peterz@...radead.org
Subject: [RFC][PATCH v3 6/6] rcu/tree: Use irq_work_queue_remote()
AFAICT we only need/use irq_work_queue_on() on remote CPUs, since we
can directly access local state. So avoid the IRQ_WORK dependency and
use the unconditionally available irq_work_queue_remote().
This survives a number of TREE01 runs.
Signed-off-by: Peter Zijlstra (Intel) <peterz@...radead.org>
---
kernel/rcu/tree.c | 4 +---
1 file changed, 1 insertion(+), 3 deletions(-)
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -1308,14 +1308,12 @@ static int rcu_implicit_dynticks_qs(stru
resched_cpu(rdp->cpu);
WRITE_ONCE(rdp->last_fqs_resched, jiffies);
}
-#ifdef CONFIG_IRQ_WORK
if (!rdp->rcu_iw_pending && rdp->rcu_iw_gp_seq != rnp->gp_seq &&
(rnp->ffmask & rdp->grpmask)) {
rdp->rcu_iw_pending = true;
rdp->rcu_iw_gp_seq = rnp->gp_seq;
- irq_work_queue_on(&rdp->rcu_iw, rdp->cpu);
+ irq_work_queue_remote(rdp->cpu, &rdp->rcu_iw);
}
-#endif
}
return 0;
Powered by blists - more mailing lists