From: Kefeng Wang <wangkefeng.wang@huawei.com>
To: Peter Zijlstra <peterz@infradead.org>
Cc: Ingo Molnar <mingo@redhat.com>, Will Deacon <will@kernel.org>,
Waiman Long <longman@redhat.com>,
Boqun Feng <boqun.feng@gmail.com>,
Thomas Gleixner <tglx@linutronix.de>,
Mark Rutland <mark.rutland@arm.com>,
"Paul E. McKenney" <paulmck@kernel.org>,
<linux-kernel@vger.kernel.org>, <kasan-dev@googlegroups.com>,
Kefeng Wang <wangkefeng.wang@huawei.com>
Subject: [PATCH v2 1/2] locking: Make owner_on_cpu() into <linux/sched.h>
Date: Fri, 3 Dec 2021 15:59:34 +0800 [thread overview]
Message-ID: <20211203075935.136808-2-wangkefeng.wang@huawei.com> (raw)
In-Reply-To: <20211203075935.136808-1-wangkefeng.wang@huawei.com>
Move the owner_on_cpu() from kernel/locking/rwsem.c into
include/linux/sched.h with under CONFIG_SMP, then use it
in the mutex/rwsem/rtmutex to simplify the code.
Signed-off-by: Kefeng Wang <wangkefeng.wang@huawei.com>
---
include/linux/sched.h | 9 +++++++++
kernel/locking/mutex.c | 11 ++---------
kernel/locking/rtmutex.c | 5 ++---
kernel/locking/rwsem.c | 9 ---------
4 files changed, 13 insertions(+), 21 deletions(-)
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 78c351e35fec..ff609d9c2f21 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -2171,6 +2171,15 @@ extern long sched_getaffinity(pid_t pid, struct cpumask *mask);
#endif
#ifdef CONFIG_SMP
+static inline bool owner_on_cpu(struct task_struct *owner)
+{
+ /*
+ * As lock holder preemption issue, we both skip spinning if
+ * task is not on cpu or its cpu is preempted
+ */
+ return owner->on_cpu && !vcpu_is_preempted(task_cpu(owner));
+}
+
/* Returns effective CPU energy utilization, as seen by the scheduler */
unsigned long sched_cpu_util(int cpu, unsigned long max);
#endif /* CONFIG_SMP */
diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c
index db1913611192..5e3585950ec8 100644
--- a/kernel/locking/mutex.c
+++ b/kernel/locking/mutex.c
@@ -367,8 +367,7 @@ bool mutex_spin_on_owner(struct mutex *lock, struct task_struct *owner,
/*
* Use vcpu_is_preempted to detect lock holder preemption issue.
*/
- if (!owner->on_cpu || need_resched() ||
- vcpu_is_preempted(task_cpu(owner))) {
+ if (!owner_on_cpu(owner) || need_resched()) {
ret = false;
break;
}
@@ -403,14 +402,8 @@ static inline int mutex_can_spin_on_owner(struct mutex *lock)
* structure won't go away during the spinning period.
*/
owner = __mutex_owner(lock);
-
- /*
- * As lock holder preemption issue, we both skip spinning if task is not
- * on cpu or its cpu is preempted
- */
-
if (owner)
- retval = owner->on_cpu && !vcpu_is_preempted(task_cpu(owner));
+ retval = owner_on_cpu(owner);
/*
* If lock->owner is not set, the mutex has been released. Return true
diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c
index 0c6a48dfcecb..41152e8e799a 100644
--- a/kernel/locking/rtmutex.c
+++ b/kernel/locking/rtmutex.c
@@ -1379,9 +1379,8 @@ static bool rtmutex_spin_on_owner(struct rt_mutex_base *lock,
* for CONFIG_PREEMPT_RCU=y)
* - the VCPU on which owner runs is preempted
*/
- if (!owner->on_cpu || need_resched() ||
- rt_mutex_waiter_is_top_waiter(lock, waiter) ||
- vcpu_is_preempted(task_cpu(owner))) {
+ if (!owner_on_cpu(owner) || need_resched() ||
+ rt_mutex_waiter_is_top_waiter(lock, waiter)) {
res = false;
break;
}
diff --git a/kernel/locking/rwsem.c b/kernel/locking/rwsem.c
index 04a74d040a6d..69aba4abe104 100644
--- a/kernel/locking/rwsem.c
+++ b/kernel/locking/rwsem.c
@@ -658,15 +658,6 @@ static inline bool rwsem_try_write_lock_unqueued(struct rw_semaphore *sem)
return false;
}
-static inline bool owner_on_cpu(struct task_struct *owner)
-{
- /*
- * As lock holder preemption issue, we both skip spinning if
- * task is not on cpu or its cpu is preempted
- */
- return owner->on_cpu && !vcpu_is_preempted(task_cpu(owner));
-}
-
static inline bool rwsem_can_spin_on_owner(struct rw_semaphore *sem)
{
struct task_struct *owner;
--
2.26.2
next prev parent reply other threads:[~2021-12-03 7:48 UTC|newest]
Thread overview: 7+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-12-03 7:59 [PATCH v2 0/2] locking: Fix racy reads of owner->on_cpu Kefeng Wang
2021-12-03 7:59 ` Kefeng Wang [this message]
2021-12-06 15:15 ` [tip: locking/core] locking: Make owner_on_cpu() into <linux/sched.h> tip-bot2 for Kefeng Wang
2021-12-03 7:59 ` [PATCH v2 2/2] locking: Mark racy reads of owner->on_cpu Kefeng Wang
2021-12-06 15:15 ` [tip: locking/core] " tip-bot2 for Marco Elver
2021-12-03 8:33 ` [PATCH v2 0/2] locking: Fix " Peter Zijlstra
2021-12-03 15:49 ` Waiman Long
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=20211203075935.136808-2-wangkefeng.wang@huawei.com \
--to=wangkefeng.wang@huawei.com \
--cc=boqun.feng@gmail.com \
--cc=kasan-dev@googlegroups.com \
--cc=linux-kernel@vger.kernel.org \
--cc=longman@redhat.com \
--cc=mark.rutland@arm.com \
--cc=mingo@redhat.com \
--cc=paulmck@kernel.org \
--cc=peterz@infradead.org \
--cc=tglx@linutronix.de \
--cc=will@kernel.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
all inboxes | Powered by JetHome®