From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
To: Josh Triplett <josh@joshtriplett.org>
Cc: linux-kernel@vger.kernel.org, mingo@elte.hu,
laijs@cn.fujitsu.com, dipankar@in.ibm.com,
akpm@linux-foundation.org, mathieu.desnoyers@polymtl.ca,
niv@us.ibm.com, tglx@linutronix.de, peterz@infradead.org,
rostedt@goodmis.org, Valdis.Kletnieks@vt.edu,
dhowells@redhat.com, eric.dumazet@gmail.com, darren@dvhart.com,
patches@linaro.org
Subject: Re: [PATCH tip/core/rcu 03/28] rcu: Streamline code produced by __rcu_read_unlock()
Date: Thu, 9 Jun 2011 07:17:14 -0700 [thread overview]
Message-ID: <20110609141714.GA2285@linux.vnet.ibm.com> (raw)
In-Reply-To: <20110609034507.GC6167@leaf>
On Wed, Jun 08, 2011 at 08:45:07PM -0700, Josh Triplett wrote:
> On Wed, Jun 08, 2011 at 12:29:42PM -0700, Paul E. McKenney wrote:
> > Given some common flag combinations, particularly -Os, gcc will inline
> > rcu_read_unlock_special() despite its being in an unlikely() clause.
> > Use noline to prohibit this misoptimization.
>
> If rcu_read_unlock_special only gets called in the one place, why does
> it hurt to inline it, as long as the inlined code stays on the cold
> path? Might as well remove the overhead of the function call.
One problem with inlining rcu_read_unlock_special() is that it
increases the icache footprint on the fast path. Because the call to
rcu_read_unlock_special() occurs only rarely (if the reader blocked
or took too long), it is better to take the overhead of the call in
the uncommon case than to take the additional cache-miss overhead
in the common case.
Or did I miss your point?
Thanx, Paul
next prev parent reply other threads:[~2011-06-09 14:17 UTC|newest]
Thread overview: 54+ messages / expand[flat|nested] mbox.gz Atom feed top
2011-06-08 19:29 [PATCH tip/core/rcu 0/28] patches queued for 3.1, first installment Paul E. McKenney
2011-06-08 19:29 ` [PATCH tip/core/rcu 01/28] rcu: Simplify curing of load woes Paul E. McKenney
2011-06-10 14:18 ` Peter Zijlstra
2011-06-10 19:53 ` Paul E. McKenney
2011-06-08 19:29 ` [PATCH tip/core/rcu 02/28] rcu: Use kthread_create_on_node() Paul E. McKenney
2011-06-08 19:29 ` [PATCH tip/core/rcu 03/28] rcu: Streamline code produced by __rcu_read_unlock() Paul E. McKenney
2011-06-08 23:17 ` Mathieu Desnoyers
[not found] ` <BLU0-SMTP16E45D0FAD13ACF913B28B96620@phx.gbl>
2011-06-08 23:58 ` Paul E. McKenney
2011-06-09 3:45 ` Josh Triplett
2011-06-09 14:17 ` Paul E. McKenney [this message]
2011-06-10 7:14 ` Lai Jiangshan
2011-06-10 19:35 ` Paul E. McKenney
2011-06-08 19:29 ` [PATCH tip/core/rcu 04/28] rcu: Restore checks for blocking in RCU read-side critical sections Paul E. McKenney
2011-06-08 23:28 ` Frederic Weisbecker
2011-06-08 23:46 ` Paul E. McKenney
2011-06-08 23:48 ` Frederic Weisbecker
2011-06-08 19:29 ` [PATCH tip/core/rcu 05/28] rcu: Move rcu_head definition to types.h Paul E. McKenney
2011-06-08 23:26 ` Mathieu Desnoyers
[not found] ` <BLU0-SMTP635E2E394E1488A2717A5B96620@phx.gbl>
2011-06-09 0:02 ` Paul E. McKenney
2011-06-09 0:11 ` Mathieu Desnoyers
[not found] ` <BLU0-SMTP796363CC311D3AB84B196996650@phx.gbl>
2011-06-09 18:38 ` Paul E. McKenney
2011-06-09 20:12 ` Mathieu Desnoyers
2011-06-08 19:29 ` [PATCH tip/core/rcu 06/28] rcu: Update rcutorture documentation Paul E. McKenney
2011-06-08 19:29 ` [PATCH tip/core/rcu 07/28] Fix mismatched variable in rcutree_trace.c Paul E. McKenney
2011-06-08 23:23 ` Mathieu Desnoyers
[not found] ` <BLU0-SMTP181D8DEE03E1353C8A106396620@phx.gbl>
2011-06-09 0:03 ` Paul E. McKenney
2011-06-08 19:29 ` [PATCH tip/core/rcu 08/28] rcu: Abstract common code for RCU grace-period-wait primitives Paul E. McKenney
2011-06-08 19:29 ` [PATCH tip/core/rcu 09/28] rcu: Catch rcutorture up to new RCU API additions Paul E. McKenney
2011-06-08 19:29 ` [PATCH tip/core/rcu 10/28] rcu: Fix RCU's NMI documentation Paul E. McKenney
2011-06-08 23:19 ` Mathieu Desnoyers
2011-06-08 19:29 ` [PATCH tip/core/rcu 11/28] audit_tree,rcu: Convert call_rcu(__put_tree) to kfree_rcu() Paul E. McKenney
2011-06-08 19:29 ` [PATCH tip/core/rcu 12/28] block,rcu: Convert call_rcu(cfq_cfqd_free) " Paul E. McKenney
2011-06-08 19:29 ` [PATCH tip/core/rcu 13/28] nfs,rcu: Convert call_rcu(nfs_free_delegation_callback) " Paul E. McKenney
2011-06-09 17:12 ` Trond Myklebust
2011-06-08 19:29 ` [PATCH tip/core/rcu 14/28] security,rcu: Convert call_rcu(whitelist_item_free) " Paul E. McKenney
2011-06-09 0:39 ` James Morris
2011-06-09 18:45 ` Paul E. McKenney
2011-06-08 19:29 ` [PATCH tip/core/rcu 15/28] scsi,rcu: Convert call_rcu(fc_rport_free_rcu) " Paul E. McKenney
2011-06-08 19:29 ` [PATCH tip/core/rcu 16/28] block,rcu: Convert call_rcu(disk_free_ptbl_rcu_cb) " Paul E. McKenney
2011-06-08 19:29 ` [PATCH tip/core/rcu 17/28] ia64,rcu: Convert call_rcu(sn_irq_info_free) " Paul E. McKenney
2011-06-08 19:29 ` [PATCH tip/core/rcu 18/28] jbd2,rcu: Convert call_rcu(free_devcache) " Paul E. McKenney
2011-06-08 19:34 ` Jan Kara
2011-06-08 19:47 ` Paul E. McKenney
2011-06-08 19:29 ` [PATCH tip/core/rcu 19/28] md,rcu: Convert call_rcu(free_conf) " Paul E. McKenney
2011-06-09 2:03 ` NeilBrown
2011-06-08 19:29 ` [PATCH tip/core/rcu 20/28] security,rcu: Convert call_rcu(sel_netnode_free) " Paul E. McKenney
2011-06-08 19:30 ` [PATCH tip/core/rcu 21/28] security,rcu: Convert call_rcu(sel_netport_free) " Paul E. McKenney
2011-06-08 19:30 ` [PATCH tip/core/rcu 22/28] ipc,rcu: Convert call_rcu(free_un) " Paul E. McKenney
2011-06-08 19:30 ` [PATCH tip/core/rcu 23/28] ipc,rcu: Convert call_rcu(ipc_immediate_free) " Paul E. McKenney
2011-06-08 19:30 ` [PATCH tip/core/rcu 24/28] vmalloc,rcu: Convert call_rcu(rcu_free_va) " Paul E. McKenney
2011-06-08 19:30 ` [PATCH tip/core/rcu 25/28] vmalloc,rcu: Convert call_rcu(rcu_free_vb) " Paul E. McKenney
2011-06-08 19:30 ` [PATCH tip/core/rcu 26/28] sysctl,rcu: Convert call_rcu(free_head) to kfree Paul E. McKenney
2011-06-08 19:30 ` [PATCH tip/core/rcu 27/28] net,rcu: Convert call_rcu(xt_rateest_free_rcu) to kfree_rcu() Paul E. McKenney
2011-06-08 19:30 ` [PATCH tip/core/rcu 28/28] net,rcu: Convert call_rcu(sk_filter_release_rcu) to kfree_rcu 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=20110609141714.GA2285@linux.vnet.ibm.com \
--to=paulmck@linux.vnet.ibm.com \
--cc=Valdis.Kletnieks@vt.edu \
--cc=akpm@linux-foundation.org \
--cc=darren@dvhart.com \
--cc=dhowells@redhat.com \
--cc=dipankar@in.ibm.com \
--cc=eric.dumazet@gmail.com \
--cc=josh@joshtriplett.org \
--cc=laijs@cn.fujitsu.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mathieu.desnoyers@polymtl.ca \
--cc=mingo@elte.hu \
--cc=niv@us.ibm.com \
--cc=patches@linaro.org \
--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