From: Gautham R Shenoy <ego@in.ibm.com>
To: Paul E McKenney <paulmck@us.ibm.com>,
Steven Rostedt <rostedt@goodmis.org>
Cc: "K. Prasad" <prasad@linux.vnet.ibm.com>,
mingo@elte.hu, linux-kernel@vger.kernel.org,
linux-rt-users@vger.kernel.org, dipankar@in.ibm.com,
Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>
Subject: __get_cpu_var() called from a preempt-unsafe context in __rcu_preempt_unboost() ?
Date: Fri, 4 Jan 2008 17:39:05 +0530 [thread overview]
Message-ID: <20080104120905.GA15640@in.ibm.com> (raw)
In-Reply-To: <20080103163055.GB27651@Krystal>
Hi Paul, Steve,
This is with reference to the preemptible rcu implementation in
2.6.24-rc5-rt1.
In __rcu_read_unlock(), we call __rcu_preempt_unboost() to unboost a
task's priority which had been bumped up when it was preempted out
while the rcu_read section.
The code path is as follows
__rcu_read_unlock()
|
|--> local_irq_restore(oldirq);
|
|--> __rcu_preempt_unboost();
|
|--> rcu_trace_boost_unboost_called(RCU_BOOST_ME)
where RCU_BOOST_ME is #defined as &__get_cpu_var(rcu_boost_data).
Is calling __get_cpu_var() safe in this context, since we've already
enabled the local interrupts and we're not in a preempt_disabled() ?
Thanks and Regards
gautham.
--
Gautham R Shenoy
Linux Technology Center
IBM India.
"Freedom comes with a price tag of responsibility, which is still a bargain,
because Freedom is priceless!"
next prev parent reply other threads:[~2008-01-04 12:09 UTC|newest]
Thread overview: 35+ messages / expand[flat|nested] mbox.gz Atom feed top
2007-12-31 6:09 [PATCH 2/2] Markers Implementation for Preempt RCU Boost Tracing K. Prasad
2007-12-31 10:20 ` Ingo Molnar
2008-01-02 3:31 ` Frank Ch. Eigler
2008-01-02 12:47 ` Ingo Molnar
2008-01-02 16:33 ` Frank Ch. Eigler
2008-01-02 17:01 ` Ingo Molnar
2008-01-02 17:56 ` Frank Ch. Eigler
2008-01-02 20:10 ` Ingo Molnar
2008-01-07 18:59 ` Mathieu Desnoyers
2008-01-13 18:07 ` Pavel Machek
2008-01-14 15:35 ` Mathieu Desnoyers
2008-01-14 16:30 ` Linus Torvalds
2008-01-14 19:36 ` Mathieu Desnoyers
2008-01-02 23:49 ` Nicholas Miell
2008-01-03 19:24 ` Mathieu Desnoyers
2008-01-03 16:30 ` Mathieu Desnoyers
2008-01-04 10:58 ` Gautham R Shenoy
2008-01-05 12:46 ` Mathieu Desnoyers
2008-01-07 19:43 ` K. Prasad
2008-01-07 19:50 ` [PATCH 0/2] Markers Implementation for RCU Tracing - Ver II K. Prasad
2008-02-18 12:21 ` Jan Kiszka
2008-02-18 12:47 ` Jan Kiszka
2008-02-18 19:48 ` Paul E. McKenney
2008-02-18 20:41 ` Mathieu Desnoyers
2008-02-19 16:27 ` Markers: multi-probe locking fun (was: Re: [PATCH 0/2] Markers Implementation for RCU Tracing - Ver II) Jan Kiszka
2008-02-19 20:33 ` Mathieu Desnoyers
2008-02-19 22:18 ` Paul E. McKenney
2008-02-19 22:32 ` Mathieu Desnoyers
2008-02-19 21:54 ` Paul E. McKenney
2008-02-19 22:03 ` Mathieu Desnoyers
2008-02-19 22:19 ` Paul E. McKenney
2008-01-07 19:55 ` [PATCH 1/2] Markers Implementation for RCU Preempt Tracing - Ver II K. Prasad
2008-01-07 19:56 ` [PATCH 2/2] Markers Implementation for Preempt RCU Boost " K. Prasad
2008-01-04 12:09 ` Gautham R Shenoy [this message]
2008-01-04 13:48 ` __get_cpu_var() called from a preempt-unsafe context in __rcu_preempt_unboost() ? Steven Rostedt
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=20080104120905.GA15640@in.ibm.com \
--to=ego@in.ibm.com \
--cc=dipankar@in.ibm.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-rt-users@vger.kernel.org \
--cc=mathieu.desnoyers@polymtl.ca \
--cc=mingo@elte.hu \
--cc=paulmck@us.ibm.com \
--cc=prasad@linux.vnet.ibm.com \
--cc=rostedt@goodmis.org \
/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