From: Thomas Gleixner <tglx@linutronix.de>
To: LKML <linux-kernel@vger.kernel.org>
Cc: Steven Rostedt <rostedt@goodmis.org>,
Peter Zijlstra <peterz@infradead.org>,
Ingo Molnar <mingo@kernel.org>
Subject: [patch V4 05/10] rtmutex: Clarify the boost/deboost part
Date: Wed, 11 Jun 2014 18:44:06 -0000 [thread overview]
Message-ID: <20140611183853.297793547@linutronix.de> (raw)
In-Reply-To: 20140611182944.108526809@linutronix.de
[-- Attachment #1: rtmutex-clarify-the-lock-chain-walk.patch --]
[-- Type: text/plain, Size: 4249 bytes --]
Add a separate local variable for the boost/deboost logic to make the
code more readable. Add comments where appropriate.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
kernel/locking/rtmutex.c | 58 ++++++++++++++++++++++++++++++++++++++---------
1 file changed, 48 insertions(+), 10 deletions(-)
Index: tip/kernel/locking/rtmutex.c
===================================================================
--- tip.orig/kernel/locking/rtmutex.c
+++ tip/kernel/locking/rtmutex.c
@@ -345,9 +345,10 @@ static int rt_mutex_adjust_prio_chain(st
struct rt_mutex_waiter *orig_waiter,
struct task_struct *top_task)
{
- struct rt_mutex *lock;
struct rt_mutex_waiter *waiter, *top_waiter = orig_waiter;
+ struct rt_mutex_waiter *prerequeue_top_waiter;
int detect_deadlock, ret = 0, depth = 0;
+ struct rt_mutex *lock;
unsigned long flags;
detect_deadlock = debug_rt_mutex_detect_deadlock(orig_waiter,
@@ -454,9 +455,14 @@ static int rt_mutex_adjust_prio_chain(st
goto out_unlock_pi;
}
- top_waiter = rt_mutex_top_waiter(lock);
+ /*
+ * Store the current top waiter before doing the requeue
+ * operation on @lock. We need it for the boost/deboost
+ * decision below.
+ */
+ prerequeue_top_waiter = rt_mutex_top_waiter(lock);
- /* Requeue the waiter */
+ /* Requeue the waiter in the lock waiter list. */
rt_mutex_dequeue(lock, waiter);
waiter->prio = task->prio;
rt_mutex_enqueue(lock, waiter);
@@ -465,35 +471,58 @@ static int rt_mutex_adjust_prio_chain(st
raw_spin_unlock_irqrestore(&task->pi_lock, flags);
put_task_struct(task);
+ /*
+ * We must abort the chain walk if there is no lock owner even
+ * in the dead lock detection case, as we have nothing to
+ * follow here. This is the end of the chain we are walking.
+ */
if (!rt_mutex_owner(lock)) {
/*
* If the requeue above changed the top waiter, then we need
* to wake the new top waiter up to try to get the lock.
*/
-
- if (top_waiter != rt_mutex_top_waiter(lock))
+ if (prerequeue_top_waiter != rt_mutex_top_waiter(lock))
wake_up_process(rt_mutex_top_waiter(lock)->task);
raw_spin_unlock(&lock->wait_lock);
return 0;
}
- /* Grab the next task */
+ /* Grab the next task, i.e. the owner of @lock */
task = rt_mutex_owner(lock);
get_task_struct(task);
raw_spin_lock_irqsave(&task->pi_lock, flags);
if (waiter == rt_mutex_top_waiter(lock)) {
- /* Boost the owner */
- rt_mutex_dequeue_pi(task, top_waiter);
+ /*
+ * The waiter became the new top (highest priority)
+ * waiter on the lock. Replace the previous top waiter
+ * in the owner tasks pi waiters list with this waiter
+ * and adjust the priority of the owner.
+ */
+ rt_mutex_dequeue_pi(task, prerequeue_top_waiter);
rt_mutex_enqueue_pi(task, waiter);
__rt_mutex_adjust_prio(task);
- } else if (top_waiter == waiter) {
- /* Deboost the owner */
+ } else if (prerequeue_top_waiter == waiter) {
+ /*
+ * The waiter was the top waiter on the lock, but is
+ * no longer the top prority waiter. Replace waiter in
+ * the owner tasks pi waiters list with the new top
+ * (highest priority) waiter and adjust the priority
+ * of the owner.
+ * The new top waiter is stored in @waiter so that
+ * @waiter == @top_waiter evaluates to true below and
+ * we continue to deboost the rest of the chain.
+ */
rt_mutex_dequeue_pi(task, waiter);
waiter = rt_mutex_top_waiter(lock);
rt_mutex_enqueue_pi(task, waiter);
__rt_mutex_adjust_prio(task);
+ } else {
+ /*
+ * Nothing changed. No need to do any priority
+ * adjustment.
+ */
}
/*
@@ -506,6 +535,10 @@ static int rt_mutex_adjust_prio_chain(st
raw_spin_unlock_irqrestore(&task->pi_lock, flags);
+ /*
+ * Store the top waiter of @lock for the end of chain walk
+ * decision below.
+ */
top_waiter = rt_mutex_top_waiter(lock);
raw_spin_unlock(&lock->wait_lock);
@@ -516,6 +549,11 @@ static int rt_mutex_adjust_prio_chain(st
if (!next_lock)
goto out_put_task;
+ /*
+ * If the current waiter is not the top waiter on the lock,
+ * then we can stop the chain walk here if we are not in full
+ * deadlock detection mode.
+ */
if (!detect_deadlock && waiter != top_waiter)
goto out_put_task;
next prev parent reply other threads:[~2014-06-11 18:47 UTC|newest]
Thread overview: 27+ messages / expand[flat|nested] mbox.gz Atom feed top
2014-06-11 18:44 [patch V4 00/10] rtmutex: Code clarification and optimization Thomas Gleixner
2014-06-11 18:44 ` [patch V4 01/10] rtmutex: Plug slow unlock race Thomas Gleixner
2014-06-13 15:41 ` Steven Rostedt
2014-06-16 8:06 ` [tip:locking/urgent] " tip-bot for Thomas Gleixner
2014-06-11 18:44 ` [patch V4 02/10] rtmutex: Simplify rtmutex_slowtrylock() Thomas Gleixner
2014-06-12 3:34 ` Lai Jiangshan
2014-06-13 15:58 ` Steven Rostedt
2014-06-11 18:44 ` [patch V4 03/10] rtmutex: Simplify and document try_to_take_rtmutex() Thomas Gleixner
2014-06-13 16:27 ` Steven Rostedt
2014-06-11 18:44 ` [patch V4 04/10] rtmutex: No need to keep task ref for lock owner check Thomas Gleixner
2014-06-13 16:30 ` Steven Rostedt
2014-06-11 18:44 ` Thomas Gleixner [this message]
2014-06-13 16:35 ` [patch V4 05/10] rtmutex: Clarify the boost/deboost part Steven Rostedt
2014-06-11 18:44 ` [patch V4 06/10] rtmutex: Document pi chain walk Thomas Gleixner
2014-06-13 16:54 ` Steven Rostedt
2014-06-11 18:44 ` [patch V4 07/10] rtmutex: Simplify remove_waiter() Thomas Gleixner
2014-06-13 16:58 ` Steven Rostedt
2014-06-11 18:44 ` [patch V4 09/10] rtmutex: Cleanup deadlock detector debug logic Thomas Gleixner
2014-06-13 17:19 ` Steven Rostedt
2014-06-13 19:43 ` Thomas Gleixner
2014-06-11 18:44 ` [patch V4 08/10] rtmutex: Confine deadlock logic to futex Thomas Gleixner
2014-06-13 17:10 ` Steven Rostedt
2014-06-11 18:44 ` [patch V4 10/10] rtmutex: Avoid pointless requeueing in the deadlock detection chain walk Thomas Gleixner
2014-06-13 17:28 ` Steven Rostedt
2014-06-13 19:46 ` Thomas Gleixner
2014-06-22 8:45 ` [patch V4 00/10] rtmutex: Code clarification and optimization Ingo Molnar
2014-06-22 9:20 ` Thomas Gleixner
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=20140611183853.297793547@linutronix.de \
--to=tglx@linutronix.de \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@kernel.org \
--cc=peterz@infradead.org \
--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