linux-kernel - [PATCH 00/11] rcu: introduce percpu rcu_preempt

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite for Android: free password hash cracker in your pocket

[<prev] [next>] [thread-next>] [day] [month] [year] [list]

Message-Id: <20191031100806.1326-1-laijs@linux.alibaba.com>
Date:   Thu, 31 Oct 2019 10:07:55 +0000
From:   Lai Jiangshan <laijs@...ux.alibaba.com>
To:     linux-kernel@...r.kernel.org
Cc:     Lai Jiangshan <laijs@...ux.alibaba.com>,
        Thomas Gleixner <tglx@...utronix.de>,
        Ingo Molnar <mingo@...hat.com>,
        "H. Peter Anvin" <hpa@...or.com>, x86@...nel.org,
        "Paul E. McKenney" <paulmck@...nel.org>,
        Josh Triplett <josh@...htriplett.org>,
        Steven Rostedt <rostedt@...dmis.org>,
        Lai Jiangshan <jiangshanlai@...il.com>,
        Joel Fernandes <joel@...lfernandes.org>,
        Peter Zijlstra <peterz@...radead.org>, rcu@...r.kernel.org,
        Mathieu Desnoyers <mathieu.desnoyers@...icios.com>
Subject: [PATCH 00/11] rcu: introduce percpu rcu_preempt_depth

My mind was occupied with percpu rcu_preempt_depth for
several years since Peter introduced percu preempt_count.
But it was stopped by no good way to avoid the scheduler deadlocks.
Now we have deferred_qs to avoid the deadlocks, it is time to implement it.

During the work, I found two possible? drawbacks (fixed by patch1/2
but patch2 is reverted by patch8 which is a better way).

And my not noticing the order of handling special.b.deferred_qs
ate many debuging energy (patch7).

The percpu rcu_preempt_depth patch is the last patch, patch11.

x86 is the only beneficial arch. But other arch can put
->rcu_read_lock_nesting and ->rcu_read_unlock_special to
thread_info to avoid the function call after we have patch8/9.

CC: Thomas Gleixner <tglx@...utronix.de>
CC: Ingo Molnar <mingo@...hat.com>
CC: "H. Peter Anvin" <hpa@...or.com>
CC: x86@...nel.org
CC: "Paul E. McKenney" <paulmck@...nel.org>
CC: Josh Triplett <josh@...htriplett.org>
CC: Steven Rostedt <rostedt@...dmis.org>
CC: Lai Jiangshan <jiangshanlai@...il.com>
CC: Joel Fernandes <joel@...lfernandes.org>
CC: Peter Zijlstra <peterz@...radead.org>
CC: linux-kernel@...r.kernel.org
CC: rcu@...r.kernel.org

Lai Jiangshan (11):
  rcu: avoid leaking exp_deferred_qs into next GP
  rcu: fix bug when rcu_exp_handler() in nested interrupt
  rcu: clean up rcu_preempt_deferred_qs_irqrestore()
  rcu: cleanup rcu_preempt_deferred_qs()
  rcu: clean all rcu_read_unlock_special after report qs
  rcu: clear t->rcu_read_unlock_special in one go
  rcu: set special.b.deferred_qs before wake_up()
  rcu: don't use negative ->rcu_read_lock_nesting
  rcu: wrap usages of rcu_read_lock_nesting
  rcu: clear the special.b.need_qs in rcu_note_context_switch()
  x86,rcu: use percpu rcu_preempt_depth

 arch/x86/Kconfig                         |   2 +
 arch/x86/include/asm/rcu_preempt_depth.h |  87 +++++++++++++++
 arch/x86/kernel/cpu/common.c             |   7 ++
 arch/x86/kernel/process_32.c             |   2 +
 arch/x86/kernel/process_64.c             |   2 +
 include/linux/rcupdate.h                 |  24 +++++
 init/init_task.c                         |   2 +-
 kernel/fork.c                            |   2 +-
 kernel/rcu/Kconfig                       |   3 +
 kernel/rcu/tree_exp.h                    |  58 ++++------
 kernel/rcu/tree_plugin.h                 | 130 +++++++++++++----------
 11 files changed, 220 insertions(+), 99 deletions(-)
 create mode 100644 arch/x86/include/asm/rcu_preempt_depth.h

-- 
2.20.1