[<prev] [next>] [thread-next>] [day] [month] [year] [list]
Message-Id: <20231219140843.939329-1-frederic@kernel.org>
Date: Tue, 19 Dec 2023 15:08:35 +0100
From: Frederic Weisbecker <frederic@...nel.org>
To: LKML <linux-kernel@...r.kernel.org>
Cc: Frederic Weisbecker <frederic@...nel.org>,
Boqun Feng <boqun.feng@...il.com>,
Joel Fernandes <joel@...lfernandes.org>,
Neeraj Upadhyay <neeraj.upadhyay@....com>,
"Paul E . McKenney" <paulmck@...nel.org>,
Uladzislau Rezki <urezki@...il.com>,
Zqiang <qiang.zhang1211@...il.com>,
rcu <rcu@...r.kernel.org>,
Hillf Danton <hdanton@...a.com>
Subject: [PATCH 0/8 v2] rcu: Fix expedited GP deadlock (and cleanup some nocb stuff)
TREE04 can trigger a writer stall if run with memory pressure. This
is due to a circular dependency between waiting for expedited grace
period and polling on expedited grace period when workqueues go back
to mayday serialization.
Here is a proposal fix.
Changes since v1:
* Add __maybe_unused to __call_rcu_nocb_wake() declaration (reported by Paul)
* Add reviewed-by tags
* Fix nocb changelog (reported by Neeraj)
* Fixed comment (reported by Hillf)
Frederic Weisbecker (8):
rcu/nocb: Make IRQs disablement symmetric
rcu/nocb: Re-arrange call_rcu() NOCB specific code
rcu/exp: Fix RCU expedited parallel grace period kworker allocation
failure recovery
rcu/exp: Handle RCU expedited grace period kworker allocation failure
rcu: s/boost_kthread_mutex/kthread_mutex
rcu/exp: Make parallel exp gp kworker per rcu node
rcu/exp: Handle parallel exp gp kworkers affinity
rcu/exp: Remove rcu_par_gp_wq
kernel/rcu/rcu.h | 5 -
kernel/rcu/tree.c | 222 +++++++++++++++++++++++++--------------
kernel/rcu/tree.h | 18 ++--
kernel/rcu/tree_exp.h | 81 +++-----------
kernel/rcu/tree_nocb.h | 38 ++++---
kernel/rcu/tree_plugin.h | 52 ++-------
6 files changed, 194 insertions(+), 222 deletions(-)
--
2.34.1
Powered by blists - more mailing lists