From: Peter Zijlstra <peterz@infradead.org>
To: tglx@linutronix.de
Cc: mingo@kernel.org, juri.lelli@arm.com, rostedt@goodmis.org,
xlpang@redhat.com, bigeasy@linutronix.de,
linux-kernel@vger.kernel.org, mathieu.desnoyers@efficios.com,
jdesfossez@efficios.com, bristot@redhat.com,
dvhart@infradead.org, peterz@infradead.org
Subject: [PATCH -v5 06/14] futex,rt_mutex: Provide futex specific rt_mutex API
Date: Sat, 04 Mar 2017 10:27:23 +0100 [thread overview]
Message-ID: <20170304093559.150922713@infradead.org> (raw)
In-Reply-To: 20170304092717.762954142@infradead.org
[-- Attachment #1: peterz-futex-pi-unlock-1.patch --]
[-- Type: text/plain, Size: 6619 bytes --]
Part of what makes futex_unlock_pi() intricate is that
rt_mutex_futex_unlock() -> rt_mutex_slowunlock() can drop
rt_mutex::wait_lock.
This means we cannot rely on the atomicy of wait_lock, which we would
like to do in order to not rely on hb->lock so much.
The reason rt_mutex_slowunlock() needs to drop wait_lock is because it
can race with the rt_mutex fastpath, however futexes have their own
fast path.
Since futexes already have a bunch of separate rt_mutex accessors,
complete that set and implement a rt_mutex variant without fastpath
for them.
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
---
kernel/futex.c | 30 ++++++++++-----------
kernel/locking/rtmutex.c | 55 +++++++++++++++++++++++++++++-----------
kernel/locking/rtmutex_common.h | 9 +++++-
3 files changed, 62 insertions(+), 32 deletions(-)
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -916,7 +916,7 @@ void exit_pi_state_list(struct task_stru
pi_state->owner = NULL;
raw_spin_unlock_irq(&curr->pi_lock);
- rt_mutex_unlock(&pi_state->pi_mutex);
+ rt_mutex_futex_unlock(&pi_state->pi_mutex);
spin_unlock(&hb->lock);
@@ -1364,20 +1364,18 @@ static int wake_futex_pi(u32 __user *uad
pi_state->owner = new_owner;
raw_spin_unlock(&new_owner->pi_lock);
- raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock);
-
- deboost = rt_mutex_futex_unlock(&pi_state->pi_mutex, &wake_q);
-
/*
- * First unlock HB so the waiter does not spin on it once he got woken
- * up. Second wake up the waiter before the priority is adjusted. If we
- * deboost first (and lose our higher priority), then the task might get
- * scheduled away before the wake up can take place.
+ * We've updated the uservalue, this unlock cannot fail.
*/
+ deboost = __rt_mutex_futex_unlock(&pi_state->pi_mutex, &wake_q);
+
+ raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock);
spin_unlock(&hb->lock);
- wake_up_q(&wake_q);
- if (deboost)
+
+ if (deboost) {
+ wake_up_q(&wake_q);
rt_mutex_adjust_prio(current);
+ }
return 0;
}
@@ -2253,7 +2251,7 @@ static int fixup_owner(u32 __user *uaddr
* task acquired the rt_mutex after we removed ourself from the
* rt_mutex waiters list.
*/
- if (rt_mutex_trylock(&q->pi_state->pi_mutex)) {
+ if (rt_mutex_futex_trylock(&q->pi_state->pi_mutex)) {
locked = 1;
goto out;
}
@@ -2568,7 +2566,7 @@ static int futex_lock_pi(u32 __user *uad
if (!trylock) {
ret = rt_mutex_timed_futex_lock(&q.pi_state->pi_mutex, to);
} else {
- ret = rt_mutex_trylock(&q.pi_state->pi_mutex);
+ ret = rt_mutex_futex_trylock(&q.pi_state->pi_mutex);
/* Fixup the trylock return value: */
ret = ret ? 0 : -EWOULDBLOCK;
}
@@ -2591,7 +2589,7 @@ static int futex_lock_pi(u32 __user *uad
* it and return the fault to userspace.
*/
if (ret && (rt_mutex_owner(&q.pi_state->pi_mutex) == current))
- rt_mutex_unlock(&q.pi_state->pi_mutex);
+ rt_mutex_futex_unlock(&q.pi_state->pi_mutex);
/* Unqueue and drop the lock */
unqueue_me_pi(&q);
@@ -2898,7 +2896,7 @@ static int futex_wait_requeue_pi(u32 __u
spin_lock(q.lock_ptr);
ret = fixup_pi_state_owner(uaddr2, &q, current);
if (ret && rt_mutex_owner(&q.pi_state->pi_mutex) == current)
- rt_mutex_unlock(&q.pi_state->pi_mutex);
+ rt_mutex_futex_unlock(&q.pi_state->pi_mutex);
/*
* Drop the reference to the pi state which
* the requeue_pi() code acquired for us.
@@ -2938,7 +2936,7 @@ static int futex_wait_requeue_pi(u32 __u
* userspace.
*/
if (ret && rt_mutex_owner(pi_mutex) == current)
- rt_mutex_unlock(pi_mutex);
+ rt_mutex_futex_unlock(pi_mutex);
/* Unqueue and drop the lock. */
unqueue_me_pi(&q);
--- a/kernel/locking/rtmutex.c
+++ b/kernel/locking/rtmutex.c
@@ -1488,15 +1488,23 @@ EXPORT_SYMBOL_GPL(rt_mutex_lock_interrup
/*
* Futex variant with full deadlock detection.
+ * Futex variants must not use the fast-path, see __rt_mutex_futex_unlock().
*/
-int rt_mutex_timed_futex_lock(struct rt_mutex *lock,
+int __sched rt_mutex_timed_futex_lock(struct rt_mutex *lock,
struct hrtimer_sleeper *timeout)
{
might_sleep();
- return rt_mutex_timed_fastlock(lock, TASK_INTERRUPTIBLE, timeout,
- RT_MUTEX_FULL_CHAINWALK,
- rt_mutex_slowlock);
+ return rt_mutex_slowlock(lock, TASK_INTERRUPTIBLE,
+ timeout, RT_MUTEX_FULL_CHAINWALK);
+}
+
+/*
+ * Futex variant, must not use fastpath.
+ */
+int __sched rt_mutex_futex_trylock(struct rt_mutex *lock)
+{
+ return rt_mutex_slowtrylock(lock);
}
/**
@@ -1555,19 +1563,38 @@ void __sched rt_mutex_unlock(struct rt_m
EXPORT_SYMBOL_GPL(rt_mutex_unlock);
/**
- * rt_mutex_futex_unlock - Futex variant of rt_mutex_unlock
- * @lock: the rt_mutex to be unlocked
- *
- * Returns: true/false indicating whether priority adjustment is
- * required or not.
+ * Futex variant, that since futex variants do not use the fast-path, can be
+ * simple and will not need to retry.
*/
-bool __sched rt_mutex_futex_unlock(struct rt_mutex *lock,
- struct wake_q_head *wqh)
+bool __sched __rt_mutex_futex_unlock(struct rt_mutex *lock,
+ struct wake_q_head *wake_q)
+{
+ lockdep_assert_held(&lock->wait_lock);
+
+ debug_rt_mutex_unlock(lock);
+
+ if (!rt_mutex_has_waiters(lock)) {
+ lock->owner = NULL;
+ return false; /* done */
+ }
+
+ mark_wakeup_next_waiter(wake_q, lock);
+ return true; /* deboost and wakeups */
+}
+
+void __sched rt_mutex_futex_unlock(struct rt_mutex *lock)
{
- if (likely(rt_mutex_cmpxchg_release(lock, current, NULL)))
- return false;
+ DEFINE_WAKE_Q(wake_q);
+ bool deboost;
- return rt_mutex_slowunlock(lock, wqh);
+ raw_spin_lock_irq(&lock->wait_lock);
+ deboost = __rt_mutex_futex_unlock(lock, &wake_q);
+ raw_spin_unlock_irq(&lock->wait_lock);
+
+ if (deboost) {
+ wake_up_q(&wake_q);
+ rt_mutex_adjust_prio(current);
+ }
}
/**
--- a/kernel/locking/rtmutex_common.h
+++ b/kernel/locking/rtmutex_common.h
@@ -109,9 +109,14 @@ extern int rt_mutex_start_proxy_lock(str
extern int rt_mutex_finish_proxy_lock(struct rt_mutex *lock,
struct hrtimer_sleeper *to,
struct rt_mutex_waiter *waiter);
+
extern int rt_mutex_timed_futex_lock(struct rt_mutex *l, struct hrtimer_sleeper *to);
-extern bool rt_mutex_futex_unlock(struct rt_mutex *lock,
- struct wake_q_head *wqh);
+extern int rt_mutex_futex_trylock(struct rt_mutex *l);
+
+extern void rt_mutex_futex_unlock(struct rt_mutex *lock);
+extern bool __rt_mutex_futex_unlock(struct rt_mutex *lock,
+ struct wake_q_head *wqh);
+
extern void rt_mutex_adjust_prio(struct task_struct *task);
#ifdef CONFIG_DEBUG_RT_MUTEXES
next prev parent reply other threads:[~2017-03-04 10:47 UTC|newest]
Thread overview: 36+ messages / expand[flat|nested] mbox.gz Atom feed top
2017-03-04 9:27 [PATCH -v5 00/14] the saga of FUTEX_UNLOCK_PI wobbles continues Peter Zijlstra
2017-03-04 9:27 ` [PATCH -v5 01/14] futex: Fix potential use-after-free in FUTEX_REQUEUE_PI Peter Zijlstra
2017-03-14 20:48 ` [tip:locking/urgent] " tip-bot for Peter Zijlstra
2017-03-04 9:27 ` [PATCH -v5 02/14] futex: Add missing error handling to FUTEX_REQUEUE_PI Peter Zijlstra
2017-03-14 20:49 ` [tip:locking/urgent] " tip-bot for Peter Zijlstra
2017-03-04 9:27 ` [PATCH -v5 03/14] futex: Cleanup variable names for futex_top_waiter() Peter Zijlstra
2017-03-04 9:27 ` [PATCH -v5 04/14] futex: Use smp_store_release() in mark_wake_futex() Peter Zijlstra
2017-03-04 9:27 ` [PATCH -v5 05/14] futex: Remove rt_mutex_deadlock_account_*() Peter Zijlstra
2017-03-04 9:27 ` Peter Zijlstra [this message]
2017-03-04 9:27 ` [PATCH -v5 07/14] futex: Change locking rules Peter Zijlstra
2017-03-07 13:22 ` Thomas Gleixner
2017-03-07 16:47 ` Sebastian Andrzej Siewior
2017-03-07 18:01 ` Peter Zijlstra
2017-03-04 9:27 ` [PATCH -v5 08/14] futex: Cleanup refcounting Peter Zijlstra
2017-03-04 9:27 ` [PATCH -v5 09/14] futex: Rework inconsistent rt_mutex/futex_q state Peter Zijlstra
2017-03-07 13:26 ` Thomas Gleixner
2017-03-04 9:27 ` [PATCH -v5 10/14] futex: Pull rt_mutex_futex_unlock() out from under hb->lock Peter Zijlstra
2017-03-07 14:08 ` Thomas Gleixner
2017-03-07 18:01 ` Peter Zijlstra
2017-03-04 9:27 ` [PATCH -v5 11/14] futex,rt_mutex: Introduce rt_mutex_init_waiter() Peter Zijlstra
2017-03-04 9:27 ` [PATCH -v5 12/14] futex,rt_mutex: Restructure rt_mutex_finish_proxy_lock() Peter Zijlstra
2017-03-07 14:18 ` Thomas Gleixner
2017-03-07 17:57 ` Peter Zijlstra
2017-03-07 17:59 ` Thomas Gleixner
2017-03-08 15:29 ` [PATCH] futex: move debug_rt_mutex_free_waiter() further down Sebastian Andrzej Siewior
2017-03-08 15:37 ` Sebastian Andrzej Siewior
2017-03-08 16:21 ` Steven Rostedt
2017-03-08 16:20 ` Steven Rostedt
2017-03-13 9:16 ` Peter Zijlstra
2017-03-04 9:27 ` [PATCH -v5 13/14] futex: Rework futex_lock_pi() to use rt_mutex_*_proxy_lock() Peter Zijlstra
2017-03-04 9:27 ` [PATCH -v5 14/14] futex: futex_unlock_pi() determinism Peter Zijlstra
2017-03-07 14:31 ` Thomas Gleixner
2017-03-07 17:59 ` Peter Zijlstra
2017-03-13 9:25 ` Peter Zijlstra
2017-03-13 14:25 ` Thomas Gleixner
2017-03-13 15:11 ` Peter Zijlstra
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=20170304093559.150922713@infradead.org \
--to=peterz@infradead.org \
--cc=bigeasy@linutronix.de \
--cc=bristot@redhat.com \
--cc=dvhart@infradead.org \
--cc=jdesfossez@efficios.com \
--cc=juri.lelli@arm.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mathieu.desnoyers@efficios.com \
--cc=mingo@kernel.org \
--cc=rostedt@goodmis.org \
--cc=tglx@linutronix.de \
--cc=xlpang@redhat.com \
/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;
as well as URLs for NNTP newsgroup(s).