From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
To: Peter Zijlstra <peterz@infradead.org>
Cc: linux-kernel@vger.kernel.org, mingo@kernel.org,
jiangshanlai@gmail.com, dipankar@in.ibm.com,
akpm@linux-foundation.org, mathieu.desnoyers@efficios.com,
josh@joshtriplett.org, tglx@linutronix.de, rostedt@goodmis.org,
dhowells@redhat.com, edumazet@google.com, fweisbec@gmail.com,
oleg@redhat.com, joel@joelfernandes.org
Subject: Re: [PATCH tip/core/rcu 16/27] rcu: Add comment documenting how rcu_seq_snap works
Date: Tue, 26 Jun 2018 15:27:47 -0700 [thread overview]
Message-ID: <20180626222747.GP3593@linux.vnet.ibm.com> (raw)
In-Reply-To: <20180626201503.GS2494@hirez.programming.kicks-ass.net>
On Tue, Jun 26, 2018 at 10:15:03PM +0200, Peter Zijlstra wrote:
> On Tue, Jun 26, 2018 at 12:31:46PM -0700, Paul E. McKenney wrote:
> > > Then the existing comment is misleading and really needs change.
> >
> > Would it be sufficient to add something like "The memory barrier is
> > required to support the many-to-many ordering guaranteed by RCU grace
> > periods"?
>
> What would lead me to wonder why after the load and not (also) before.
The memory barriers on the other sides of these primitives are supplied
by the caller. For example, in srcu_gp_end(), there is a set of
spin_unlock_irq_rcu_node()/spin_lock_irq_rcu_node() pairs between the
rcu_seq_end() of the prior SRCU grace period and the rcu_seq_start()
of the next one.
However, these things aren't anywhere near a fastpath, so I could add
the smp_mb() calls on the other sides for readability, if that would
be useful.
Thanx, Paul
next prev parent reply other threads:[~2018-06-26 22:25 UTC|newest]
Thread overview: 46+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-06-26 0:34 [PATCH tip/core/rcu 0/27] Post-gp_seq miscellaneous fixes for v4.19 Paul E. McKenney
2018-06-26 0:34 ` [PATCH tip/core/rcu 01/27] rcu: Make rcu_read_unlock_special() static Paul E. McKenney
2018-06-26 0:34 ` [PATCH tip/core/rcu 02/27] rcu: Improve rcu_note_voluntary_context_switch() reporting Paul E. McKenney
2018-06-26 0:34 ` [PATCH tip/core/rcu 03/27] rcu: rcupdate.h: Get rid of Sphinx warnings at rcu_pointer_handoff() Paul E. McKenney
2018-06-26 0:34 ` [PATCH tip/core/rcu 04/27] rcu: Use pr_fmt to prefix "rcu: " to logging output Paul E. McKenney
2018-06-26 0:34 ` [PATCH tip/core/rcu 05/27] rcu: Improve RCU-tasks naming and comments Paul E. McKenney
2018-06-26 0:34 ` [PATCH tip/core/rcu 06/27] rcu: Mark task as .need_qs less aggressively Paul E. McKenney
2018-06-26 17:08 ` Peter Zijlstra
2018-06-26 18:03 ` Paul E. McKenney
2018-06-26 21:38 ` Paul E. McKenney
2018-06-26 0:34 ` [PATCH tip/core/rcu 07/27] rcu: Inline rcu_dynticks_momentary_idle() into its sole caller Paul E. McKenney
2018-06-26 0:34 ` [PATCH tip/core/rcu 08/27] rcu: Clarify and correct the rcu_preempt_qs() header comment Paul E. McKenney
2018-06-26 0:34 ` [PATCH tip/core/rcu 09/27] rcu: Remove unused rcu_kick_nohz_cpu() function Paul E. McKenney
2018-06-26 0:34 ` [PATCH tip/core/rcu 10/27] rcu: Remove unused local variable "cpu" Paul E. McKenney
2018-06-26 0:34 ` [PATCH tip/core/rcu 11/27] rcu: Remove "inline" from panic_on_rcu_stall() and rcu_blocking_is_gp() Paul E. McKenney
2018-06-26 0:34 ` [PATCH tip/core/rcu 12/27] rcu: Remove "inline" from rcu_torture_print_module_parms() Paul E. McKenney
2018-06-26 0:34 ` [PATCH tip/core/rcu 13/27] rcu: Remove "inline" from rcu_perf_print_module_parms() Paul E. McKenney
2018-06-26 0:35 ` [PATCH tip/core/rcu 14/27] rcu: Remove __maybe_unused from rcu_cpu_has_callbacks() Paul E. McKenney
2018-06-26 0:35 ` [PATCH tip/core/rcu 15/27] rcu: Use RCU CPU stall timeout for rcu_check_gp_start_stall() Paul E. McKenney
2018-06-26 0:35 ` [PATCH tip/core/rcu 16/27] rcu: Add comment documenting how rcu_seq_snap works Paul E. McKenney
2018-06-26 17:14 ` Peter Zijlstra
2018-06-26 18:08 ` Paul E. McKenney
2018-06-26 19:21 ` Peter Zijlstra
2018-06-26 19:31 ` Paul E. McKenney
2018-06-26 20:15 ` Peter Zijlstra
2018-06-26 22:27 ` Paul E. McKenney [this message]
2018-06-26 17:30 ` Peter Zijlstra
2018-06-26 18:10 ` Paul E. McKenney
2018-06-26 19:27 ` Peter Zijlstra
2018-06-27 4:39 ` Joel Fernandes
2018-06-27 17:54 ` Paul E. McKenney
2018-06-27 18:27 ` Joel Fernandes
2018-06-27 19:11 ` Paul E. McKenney
2018-06-28 5:10 ` Joel Fernandes
2018-06-28 17:42 ` Paul E. McKenney
2018-06-26 0:35 ` [PATCH tip/core/rcu 17/27] rcu: Speed up calling of RCU tasks callbacks Paul E. McKenney
2018-06-26 0:35 ` [PATCH tip/core/rcu 18/27] rcu: Add comment to the last sleep in the rcu tasks loop Paul E. McKenney
2018-06-26 0:35 ` [PATCH tip/core/rcu 19/27] rcu: Add diagnostics for rcutorture writer stall warning Paul E. McKenney
2018-06-26 0:35 ` [PATCH tip/core/rcu 20/27] rcu: Check the range of jiffies_till_{first,next}_fqs when setting them Paul E. McKenney
2018-06-26 0:35 ` [PATCH tip/core/rcu 21/27] doc: Update synchronize_rcu() definition in whatisRCU.txt Paul E. McKenney
2018-06-26 0:35 ` [PATCH tip/core/rcu 22/27] rcu: Make rcu_seq_diff() more exact Paul E. McKenney
2018-06-26 0:35 ` [PATCH tip/core/rcu 23/27] MAINTAINERS: Update RCU, SRCU, and TORTURE-TEST entries Paul E. McKenney
2018-06-26 0:35 ` [PATCH tip/core/rcu 24/27] rcu: Print stall-warning NMI dyntick state in hexadecimal Paul E. McKenney
2018-06-26 0:35 ` [PATCH tip/core/rcu 25/27] srcu: Add grace-period number to rcutorture statistics printout Paul E. McKenney
2018-06-26 0:35 ` [PATCH tip/core/rcu 26/27] rculist: Improve documentation for list_for_each_entry_from_rcu() Paul E. McKenney
2018-06-26 0:35 ` [PATCH tip/core/rcu 27/27] rcu: Assign higher prio to RCU threads if rcutorture is built-in 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=20180626222747.GP3593@linux.vnet.ibm.com \
--to=paulmck@linux.vnet.ibm.com \
--cc=akpm@linux-foundation.org \
--cc=dhowells@redhat.com \
--cc=dipankar@in.ibm.com \
--cc=edumazet@google.com \
--cc=fweisbec@gmail.com \
--cc=jiangshanlai@gmail.com \
--cc=joel@joelfernandes.org \
--cc=josh@joshtriplett.org \
--cc=linux-kernel@vger.kernel.org \
--cc=mathieu.desnoyers@efficios.com \
--cc=mingo@kernel.org \
--cc=oleg@redhat.com \
--cc=peterz@infradead.org \
--cc=rostedt@goodmis.org \
--cc=tglx@linutronix.de \
/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